Merge branch 'next' into for-linus

Prepare input updates for 5.11 merge window.

126 files changed, 5942 insertions, 1352 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 5d53f9609c25..b4b98a03ff98 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -19,6 +19,9 @@ config RAID6_PQ_BENCHMARK
 	  Benchmark all available RAID6 PQ functions on init and choose the
 	  fastest one.
 
+config LINEAR_RANGES
+	tristate
+
 config PACKING
 	bool "Generic bitfield packing and unpacking"
 	default n
@@ -80,6 +83,9 @@ config ARCH_USE_CMPXCHG_LOCKREF
 config ARCH_HAS_FAST_MULTIPLIER
 	bool
 
+config ARCH_USE_SYM_ANNOTATIONS
+	bool
+
 config INDIRECT_PIO
 	bool "Access I/O in non-MMIO mode"
 	depends on ARM64
@@ -336,6 +342,10 @@ config DECOMPRESS_LZ4
 	select LZ4_DECOMPRESS
 	tristate
 
+config DECOMPRESS_ZSTD
+	select ZSTD_DECOMPRESS
+	tristate
+
 #
 # Generic allocator support is selected if needed
 #
@@ -427,7 +437,7 @@ config INTERVAL_TREE
 
 	  See:
 
-		Documentation/rbtree.txt
+		Documentation/core-api/rbtree.rst
 
 	  for more information.
 
@@ -670,3 +680,7 @@ config GENERIC_LIB_CMPDI2
 
 config GENERIC_LIB_UCMPDI2
 	bool
+
+config PLDMFW
+	bool
+	default n
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 21d9c5f6e7ec..0c781f912f9f 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -99,6 +99,7 @@ config DYNAMIC_DEBUG
 	default n
 	depends on PRINTK
 	depends on (DEBUG_FS || PROC_FS)
+	select DYNAMIC_DEBUG_CORE
 	help
 
 	  Compiles debug level messages into the kernel, which would not
@@ -165,6 +166,17 @@ config DYNAMIC_DEBUG
 	  See Documentation/admin-guide/dynamic-debug-howto.rst for additional
 	  information.
 
+config DYNAMIC_DEBUG_CORE
+	bool "Enable core function of dynamic debug support"
+	depends on PRINTK
+	depends on (DEBUG_FS || PROC_FS)
+	help
+	  Enable core functional support of dynamic debug. It is useful
+	  when you want to tie dynamic debug to your kernel modules with
+	  DYNAMIC_DEBUG_MODULE defined for each of them, especially for
+	  the case of embedded system where the kernel image size is
+	  sensitive for people.
+
 config SYMBOLIC_ERRNAME
 	bool "Support symbolic error names in printf"
 	default y if PRINTK
@@ -213,6 +225,22 @@ config DEBUG_INFO_REDUCED
 	  DEBUG_INFO build and compile times are reduced too.
 	  Only works with newer gcc versions.
 
+config DEBUG_INFO_COMPRESSED
+	bool "Compressed debugging information"
+	depends on DEBUG_INFO
+	depends on $(cc-option,-gz=zlib)
+	depends on $(ld-option,--compress-debug-sections=zlib)
+	help
+	  Compress the debug information using zlib.  Requires GCC 5.0+ or Clang
+	  5.0+, binutils 2.26+, and zlib.
+
+	  Users of dpkg-deb via scripts/package/builddeb may find an increase in
+	  size of their debug .deb packages with this config set, due to the
+	  debug info being compressed with zlib, then the object files being
+	  recompressed with a different compression scheme. But this is still
+	  preferable to setting $KDEB_COMPRESS to "none" which would be even
+	  larger.
+
 config DEBUG_INFO_SPLIT
 	bool "Produce split debuginfo in .dwo files"
 	depends on DEBUG_INFO
@@ -337,6 +365,17 @@ config SECTION_MISMATCH_WARN_ONLY
 
 	  If unsure, say Y.
 
+config DEBUG_FORCE_FUNCTION_ALIGN_32B
+	bool "Force all function address 32B aligned" if EXPERT
+	help
+	  There are cases that a commit from one domain changes the function
+	  address alignment of other domains, and cause magic performance
+	  bump (regression or improvement). Enable this option will help to
+	  verify if the bump is caused by function alignment changes, while
+	  it will slightly increase the kernel size and affect icache usage.
+
+	  It is mainly for debug and performance tuning use.
+
 #
 # Select this config option from the architecture Kconfig, if it
 # is preferred to always offer frame pointers as a config
@@ -369,6 +408,11 @@ config STACK_VALIDATION
 	  For more information, see
 	  tools/objtool/Documentation/stack-validation.txt.
 
+config VMLINUX_VALIDATION
+	bool
+	depends on STACK_VALIDATION && DEBUG_ENTRY && !PARAVIRT
+	default y
+
 config DEBUG_FORCE_WEAK_PER_CPU
 	bool "Force weak per-cpu definitions"
 	depends on DEBUG_KERNEL
@@ -443,9 +487,41 @@ config DEBUG_FS
 
 	  If unsure, say N.
 
-source "lib/Kconfig.kgdb"
+choice
+	prompt "Debugfs default access"
+	depends on DEBUG_FS
+	default DEBUG_FS_ALLOW_ALL
+	help
+	  This selects the default access restrictions for debugfs.
+	  It can be overridden with kernel command line option
+	  debugfs=[on,no-mount,off]. The restrictions apply for API access
+	  and filesystem registration.
 
+config DEBUG_FS_ALLOW_ALL
+	bool "Access normal"
+	help
+	  No restrictions apply. Both API and filesystem registration
+	  is on. This is the normal default operation.
+
+config DEBUG_FS_DISALLOW_MOUNT
+	bool "Do not register debugfs as filesystem"
+	help
+	  The API is open but filesystem is not loaded. Clients can still do
+	  their work and read with debug tools that do not need
+	  debugfs filesystem.
+
+config DEBUG_FS_ALLOW_NONE
+	bool "No access"
+	help
+	  Access is off. Clients get -PERM when trying to create nodes in
+	  debugfs tree and debugfs is not registered as a filesystem.
+	  Client can then back-off or continue without debugfs access.
+
+endchoice
+
+source "lib/Kconfig.kgdb"
 source "lib/Kconfig.ubsan"
+source "lib/Kconfig.kcsan"
 
 endmenu
 
@@ -653,6 +729,12 @@ config SCHED_STACK_END_CHECK
 	  data corruption or a sporadic crash at a later stage once the region
 	  is examined. The runtime overhead introduced is minimal.
 
+config ARCH_HAS_DEBUG_VM_PGTABLE
+	bool
+	help
+	  An architecture should select this when it can successfully
+	  build and run DEBUG_VM_PGTABLE.
+
 config DEBUG_VM
 	bool "Debug VM"
 	depends on DEBUG_KERNEL
@@ -688,6 +770,22 @@ config DEBUG_VM_PGFLAGS
 
 	  If unsure, say N.
 
+config DEBUG_VM_PGTABLE
+	bool "Debug arch page table for semantics compliance"
+	depends on MMU
+	depends on ARCH_HAS_DEBUG_VM_PGTABLE
+	default y if DEBUG_VM
+	help
+	  This option provides a debug method which can be used to test
+	  architecture page table helper functions on various platforms in
+	  verifying if they comply with expected generic MM semantics. This
+	  will help architecture code in making sure that any changes or
+	  new additions of these helpers still conform to expected
+	  semantics of the generic MM. Platforms will have to opt in for
+	  this through ARCH_HAS_DEBUG_VM_PGTABLE.
+
+	  If unsure, say N.
+
 config ARCH_HAS_DEBUG_VIRTUAL
 	bool
 
@@ -766,7 +864,7 @@ config HAVE_DEBUG_STACKOVERFLOW
 config DEBUG_STACKOVERFLOW
 	bool "Check for stack overflows"
 	depends on DEBUG_KERNEL && HAVE_DEBUG_STACKOVERFLOW
-	---help---
+	help
 	  Say Y here if you want to check for overflows of kernel, IRQ
 	  and exception stacks (if your architecture uses them). This
 	  option will show detailed messages if free stack space drops
@@ -789,10 +887,10 @@ config DEBUG_SHIRQ
 	bool "Debug shared IRQ handlers"
 	depends on DEBUG_KERNEL
 	help
-	  Enable this to generate a spurious interrupt as soon as a shared
-	  interrupt handler is registered, and just before one is deregistered.
-	  Drivers ought to be able to handle interrupts coming in at those
-	  points; some don't and need to be caught.
+	  Enable this to generate a spurious interrupt just before a shared
+	  interrupt handler is deregistered (generating one when registering
+	  is currently disabled). Drivers need to handle this correctly. Some
+	  don't and need to be caught.
 
 menu "Debug Oops, Lockups and Hangs"
 
@@ -819,7 +917,7 @@ config PANIC_TIMEOUT
 	int "panic timeout"
 	default 0
 	help
-	  Set the timeout value (in seconds) until a reboot occurs when the
+	  Set the timeout value (in seconds) until a reboot occurs when
 	  the kernel panics. If n = 0, then we wait forever. A timeout
 	  value n > 0 will wait n seconds before rebooting, while a timeout
 	  value n < 0 will reboot immediately.
@@ -980,6 +1078,7 @@ config WQ_WATCHDOG
 
 config TEST_LOCKUP
 	tristate "Test module to generate lockups"
+	depends on m
 	help
 	  This builds the "test_lockup" module that helps to make sure
 	  that watchdogs and lockup detectors are working properly.
@@ -1062,6 +1161,7 @@ config PROVE_LOCKING
 	select DEBUG_RWSEMS
 	select DEBUG_WW_MUTEX_SLOWPATH
 	select DEBUG_LOCK_ALLOC
+	select PREEMPT_COUNT if !ARCH_NO_PREEMPT
 	select TRACE_IRQFLAGS
 	default n
 	help
@@ -1270,11 +1370,17 @@ config WW_MUTEX_SELFTEST
 endmenu # lock debugging
 
 config TRACE_IRQFLAGS
+	depends on TRACE_IRQFLAGS_SUPPORT
 	bool
 	help
 	  Enables hooks to interrupt enabling and disabling for
 	  either tracing or lock debugging.
 
+config TRACE_IRQFLAGS_NMI
+	def_bool y
+	depends on TRACE_IRQFLAGS
+	depends on TRACE_IRQFLAGS_NMI_SUPPORT
+
 config STACKTRACE
 	bool "Stack backtrace support"
 	depends on STACKTRACE_SUPPORT
@@ -1510,7 +1616,7 @@ config PROVIDE_OHCI1394_DMA_INIT
 	  This code (~1k) is freed after boot. By then, the firewire stack
 	  in charge of the OHCI-1394 controllers should be used instead.
 
-	  See Documentation/debugging-via-ohci1394.txt for more information.
+	  See Documentation/core-api/debugging-via-ohci1394.rst for more information.
 
 source "samples/Kconfig"
 
@@ -1769,6 +1875,15 @@ config KCOV_INSTRUMENT_ALL
 	  filesystem fuzzing with AFL) then you will want to enable coverage
 	  for more specific subsets of files, and should say n here.
 
+config KCOV_IRQ_AREA_SIZE
+	hex "Size of interrupt coverage collection area in words"
+	depends on KCOV
+	default 0x40000
+	help
+	  KCOV uses preallocated per-cpu areas to collect coverage from
+	  soft interrupts. This specifies the size of those areas in the
+	  number of unsigned long words.
+
 menuconfig RUNTIME_TESTING_MENU
 	bool "Runtime Testing"
 	def_bool y
@@ -1889,7 +2004,7 @@ config ASYNC_RAID6_TEST
 	tristate "Self test for hardware accelerated raid6 recovery"
 	depends on ASYNC_RAID6_RECOV
 	select ASYNC_MEMCPY
-	---help---
+	help
 	  This is a one-shot self test that permutes through the
 	  recovery of all the possible two disk failure scenarios for a
 	  N-disk array.  Recovery is performed with the asynchronous
@@ -1986,6 +2101,19 @@ config TEST_LKM
 
 	  If unsure, say N.
 
+config TEST_BITOPS
+	tristate "Test module for compilation of bitops operations"
+	depends on m
+	help
+	  This builds the "test_bitops" module that is much like the
+	  TEST_LKM module except that it does a basic exercise of the
+	  set/clear_bit macros and get_count_order/long to make sure there are
+	  no compiler warnings from C=1 sparse checker or -Wextra
+	  compilations. It has no dependencies and doesn't run or load unless
+	  explicitly requested by name.  for example: modprobe test_bitops.
+
+	  If unsure, say N.
+
 config TEST_VMALLOC
 	tristate "Test module for stress/performance analysis of vmalloc allocator"
 	default n
@@ -2064,8 +2192,9 @@ config TEST_SYSCTL
 	  If unsure, say N.
 
 config SYSCTL_KUNIT_TEST
-	tristate "KUnit test for sysctl"
+	tristate "KUnit test for sysctl" if !KUNIT_ALL_TESTS
 	depends on KUNIT
+	default KUNIT_ALL_TESTS
 	help
 	  This builds the proc sysctl unit test, which runs on boot.
 	  Tests the API contract and implementation correctness of sysctl.
@@ -2075,15 +2204,16 @@ config SYSCTL_KUNIT_TEST
 	  If unsure, say N.
 
 config LIST_KUNIT_TEST
-	tristate "KUnit Test for Kernel Linked-list structures"
+	tristate "KUnit Test for Kernel Linked-list structures" if !KUNIT_ALL_TESTS
 	depends on KUNIT
+	default KUNIT_ALL_TESTS
 	help
 	  This builds the linked list KUnit test suite.
 	  It tests that the API and basic functionality of the list_head type
 	  and associated macros.
 
 	  KUnit tests run during boot and output the results to the debug log
-	  in TAP format (http://testanything.org/). Only useful for kernel devs
+	  in TAP format (https://testanything.org/). Only useful for kernel devs
 	  running the KUnit test harness, and not intended for inclusion into a
 	  production build.
 
@@ -2092,6 +2222,29 @@ config LIST_KUNIT_TEST
 
 	  If unsure, say N.
 
+config LINEAR_RANGES_TEST
+	tristate "KUnit test for linear_ranges"
+	depends on KUNIT
+	select LINEAR_RANGES
+	help
+	  This builds the linear_ranges unit test, which runs on boot.
+	  Tests the linear_ranges logic correctness.
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
+config BITS_TEST
+	tristate "KUnit test for bits.h"
+	depends on KUNIT
+	help
+	  This builds the bits unit test.
+	  Tests the logic of macros defined in bits.h.
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 config TEST_UDELAY
 	tristate "udelay test driver"
 	help
@@ -2201,11 +2354,35 @@ config TEST_MEMINIT
 
 	  If unsure, say N.
 
+config TEST_HMM
+	tristate "Test HMM (Heterogeneous Memory Management)"
+	depends on TRANSPARENT_HUGEPAGE
+	depends on DEVICE_PRIVATE
+	select HMM_MIRROR
+	select MMU_NOTIFIER
+	help
+	  This is a pseudo device driver solely for testing HMM.
+	  Say M here if you want to build the HMM test module.
+	  Doing so will allow you to run tools/testing/selftest/vm/hmm-tests.
+
+	  If unsure, say N.
+
+config TEST_FPU
+	tristate "Test floating point operations in kernel space"
+	depends on X86 && !KCOV_INSTRUMENT_ALL
+	help
+	  Enable this option to add /sys/kernel/debug/selftest_helpers/test_fpu
+	  which will trigger a sequence of floating point operations. This is used
+	  for self-testing floating point control register setting in
+	  kernel_fpu_begin().
+
+	  If unsure, say N.
+
 endif # RUNTIME_TESTING_MENU
 
 config MEMTEST
 	bool "Memtest"
-	---help---
+	help
 	  This option adds a kernel parameter 'memtest', which allows memtest
 	  to be set.
 	        memtest=0, mean disabled; -- default
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 81f5464ea9e1..047b53dbfd58 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -15,19 +15,24 @@ config CC_HAS_KASAN_GENERIC
 config CC_HAS_KASAN_SW_TAGS
 	def_bool $(cc-option, -fsanitize=kernel-hwaddress)
 
-config KASAN
+config CC_HAS_WORKING_NOSANITIZE_ADDRESS
+	def_bool !CC_IS_GCC || GCC_VERSION >= 80300
+
+menuconfig KASAN
 	bool "KASAN: runtime memory debugger"
 	depends on (HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC) || \
 		   (HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS)
 	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
+	depends on CC_HAS_WORKING_NOSANITIZE_ADDRESS
 	help
 	  Enables KASAN (KernelAddressSANitizer) - runtime memory debugger,
 	  designed to find out-of-bounds accesses and use-after-free bugs.
 	  See Documentation/dev-tools/kasan.rst for details.
 
+if KASAN
+
 choice
 	prompt "KASAN mode"
-	depends on KASAN
 	default KASAN_GENERIC
 	help
 	  KASAN has two modes: generic KASAN (similar to userspace ASan,
@@ -35,6 +40,7 @@ choice
 	  software tag-based KASAN (a version based on software memory
 	  tagging, arm64 only, similar to userspace HWASan, enabled with
 	  CONFIG_KASAN_SW_TAGS).
+
 	  Both generic and tag-based KASAN are strictly debugging features.
 
 config KASAN_GENERIC
@@ -46,16 +52,18 @@ config KASAN_GENERIC
 	select STACKDEPOT
 	help
 	  Enables generic KASAN mode.
-	  Supported in both GCC and Clang. With GCC it requires version 4.9.2
-	  or later for basic support and version 5.0 or later for detection of
-	  out-of-bounds accesses for stack and global variables and for inline
-	  instrumentation mode (CONFIG_KASAN_INLINE). With Clang it requires
-	  version 3.7.0 or later and it doesn't support detection of
-	  out-of-bounds accesses for global variables yet.
+
+	  This mode is supported in both GCC and Clang. With GCC it requires
+	  version 8.3.0 or later. With Clang it requires version 7.0.0 or
+	  later, but detection of out-of-bounds accesses for global variables
+	  is supported only since Clang 11.
+
 	  This mode consumes about 1/8th of available memory at kernel start
 	  and introduces an overhead of ~x1.5 for the rest of the allocations.
 	  The performance slowdown is ~x3.
+
 	  For better error detection enable CONFIG_STACKTRACE.
+
 	  Currently CONFIG_KASAN_GENERIC doesn't work with CONFIG_DEBUG_SLAB
 	  (the resulting kernel does not boot).
 
@@ -68,15 +76,19 @@ config KASAN_SW_TAGS
 	select STACKDEPOT
 	help
 	  Enables software tag-based KASAN mode.
+
 	  This mode requires Top Byte Ignore support by the CPU and therefore
-	  is only supported for arm64.
-	  This mode requires Clang version 7.0.0 or later.
+	  is only supported for arm64. This mode requires Clang version 7.0.0
+	  or later.
+
 	  This mode consumes about 1/16th of available memory at kernel start
 	  and introduces an overhead of ~20% for the rest of the allocations.
 	  This mode may potentially introduce problems relating to pointer
 	  casting and comparison, as it embeds tags into the top byte of each
 	  pointer.
+
 	  For better error detection enable CONFIG_STACKTRACE.
+
 	  Currently CONFIG_KASAN_SW_TAGS doesn't work with CONFIG_DEBUG_SLAB
 	  (the resulting kernel does not boot).
 
@@ -84,7 +96,6 @@ endchoice
 
 choice
 	prompt "Instrumentation type"
-	depends on KASAN
 	default KASAN_OUTLINE
 
 config KASAN_OUTLINE
@@ -103,13 +114,11 @@ config KASAN_INLINE
 	  memory accesses. This is faster than outline (in some workloads
 	  it gives about x2 boost over outline instrumentation), but
 	  make kernel's .text size much bigger.
-	  For CONFIG_KASAN_GENERIC this requires GCC 5.0 or later.
 
 endchoice
 
 config KASAN_STACK_ENABLE
 	bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST
-	depends on KASAN
 	help
 	  The LLVM stack address sanitizer has a know problem that
 	  causes excessive stack usage in a lot of functions, see
@@ -130,7 +139,7 @@ config KASAN_STACK
 
 config KASAN_S390_4_LEVEL_PAGING
 	bool "KASan: use 4-level paging"
-	depends on KASAN && S390
+	depends on S390
 	help
 	  Compiling the kernel with KASan disables automatic 3-level vs
 	  4-level paging selection. 3-level paging is used by default (up
@@ -147,7 +156,7 @@ config KASAN_SW_TAGS_IDENTIFY
 
 config KASAN_VMALLOC
 	bool "Back mappings in vmalloc space with real shadow memory"
-	depends on KASAN && HAVE_ARCH_KASAN_VMALLOC
+	depends on HAVE_ARCH_KASAN_VMALLOC
 	help
 	  By default, the shadow region for vmalloc space is the read-only
 	  zero page. This means that KASAN cannot detect errors involving
@@ -160,8 +169,10 @@ config KASAN_VMALLOC
 
 config TEST_KASAN
 	tristate "Module for testing KASAN for bug detection"
-	depends on m && KASAN
+	depends on m
 	help
 	  This is a test module doing various nasty things like
 	  out of bounds accesses, use after free. It is useful for testing
 	  kernel debugging features like KASAN.
+
+endif # KASAN
diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan
new file mode 100644
index 000000000000..3d282d51849b
--- /dev/null
+++ b/lib/Kconfig.kcsan
@@ -0,0 +1,221 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config HAVE_ARCH_KCSAN
+	bool
+
+config HAVE_KCSAN_COMPILER
+	def_bool (CC_IS_CLANG && $(cc-option,-fsanitize=thread -mllvm -tsan-distinguish-volatile=1)) || \
+		 (CC_IS_GCC && $(cc-option,-fsanitize=thread --param tsan-distinguish-volatile=1))
+	help
+	  For the list of compilers that support KCSAN, please see
+	  <file:Documentation/dev-tools/kcsan.rst>.
+
+config KCSAN_KCOV_BROKEN
+	def_bool KCOV && CC_HAS_SANCOV_TRACE_PC
+	depends on CC_IS_CLANG
+	depends on !$(cc-option,-Werror=unused-command-line-argument -fsanitize=thread -fsanitize-coverage=trace-pc)
+	help
+	  Some versions of clang support either KCSAN and KCOV but not the
+	  combination of the two.
+	  See https://bugs.llvm.org/show_bug.cgi?id=45831 for the status
+	  in newer releases.
+
+menuconfig KCSAN
+	bool "KCSAN: dynamic data race detector"
+	depends on HAVE_ARCH_KCSAN && HAVE_KCSAN_COMPILER
+	depends on DEBUG_KERNEL && !KASAN
+	depends on !KCSAN_KCOV_BROKEN
+	select STACKTRACE
+	help
+	  The Kernel Concurrency Sanitizer (KCSAN) is a dynamic
+	  data-race detector that relies on compile-time instrumentation.
+	  KCSAN uses a watchpoint-based sampling approach to detect races.
+
+	  While KCSAN's primary purpose is to detect data races, it
+	  also provides assertions to check data access constraints.
+	  These assertions can expose bugs that do not manifest as
+	  data races.
+
+	  See <file:Documentation/dev-tools/kcsan.rst> for more details.
+
+if KCSAN
+
+config KCSAN_VERBOSE
+	bool "Show verbose reports with more information about system state"
+	depends on PROVE_LOCKING
+	help
+	  If enabled, reports show more information about the system state that
+	  may help better analyze and debug races. This includes held locks and
+	  IRQ trace events.
+
+	  While this option should generally be benign, we call into more
+	  external functions on report generation; if a race report is
+	  generated from any one of them, system stability may suffer due to
+	  deadlocks or recursion.  If in doubt, say N.
+
+config KCSAN_DEBUG
+	bool "Debugging of KCSAN internals"
+
+config KCSAN_SELFTEST
+	bool "Perform short selftests on boot"
+	default y
+	help
+	  Run KCSAN selftests on boot. On test failure, causes the kernel to
+	  panic. Recommended to be enabled, ensuring critical functionality
+	  works as intended.
+
+config KCSAN_TEST
+	tristate "KCSAN test for integrated runtime behaviour"
+	depends on TRACEPOINTS && KUNIT
+	select TORTURE_TEST
+	help
+	  KCSAN test focusing on behaviour of the integrated runtime. Tests
+	  various race scenarios, and verifies the reports generated to
+	  console. Makes use of KUnit for test organization, and the Torture
+	  framework for test thread control.
+
+	  Each test case may run at least up to KCSAN_REPORT_ONCE_IN_MS
+	  milliseconds. Test run duration may be optimized by building the
+	  kernel and KCSAN test with KCSAN_REPORT_ONCE_IN_MS set to a lower
+	  than default value.
+
+	  Say Y here if you want the test to be built into the kernel and run
+	  during boot; say M if you want the test to build as a module; say N
+	  if you are unsure.
+
+config KCSAN_EARLY_ENABLE
+	bool "Early enable during boot"
+	default y
+	help
+	  If KCSAN should be enabled globally as soon as possible. KCSAN can
+	  later be enabled/disabled via debugfs.
+
+config KCSAN_NUM_WATCHPOINTS
+	int "Number of available watchpoints"
+	default 64
+	help
+	  Total number of available watchpoints. An address range maps into a
+	  specific watchpoint slot as specified in kernel/kcsan/encoding.h.
+	  Although larger number of watchpoints may not be usable due to
+	  limited number of CPUs, a larger value helps to improve performance
+	  due to reducing cache-line contention. The chosen default is a
+	  conservative value; we should almost never observe "no_capacity"
+	  events (see /sys/kernel/debug/kcsan).
+
+config KCSAN_UDELAY_TASK
+	int "Delay in microseconds (for tasks)"
+	default 80
+	help
+	  For tasks, the microsecond delay after setting up a watchpoint.
+
+config KCSAN_UDELAY_INTERRUPT
+	int "Delay in microseconds (for interrupts)"
+	default 20
+	help
+	  For interrupts, the microsecond delay after setting up a watchpoint.
+	  Interrupts have tighter latency requirements, and their delay should
+	  be lower than for tasks.
+
+config KCSAN_DELAY_RANDOMIZE
+	bool "Randomize above delays"
+	default y
+	help
+	  If delays should be randomized, where the maximum is KCSAN_UDELAY_*.
+	  If false, the chosen delays are always the KCSAN_UDELAY_* values
+	  as defined above.
+
+config KCSAN_SKIP_WATCH
+	int "Skip instructions before setting up watchpoint"
+	default 4000
+	help
+	  The number of per-CPU memory operations to skip, before another
+	  watchpoint is set up, i.e. one in KCSAN_WATCH_SKIP per-CPU
+	  memory operations are used to set up a watchpoint. A smaller value
+	  results in more aggressive race detection, whereas a larger value
+	  improves system performance at the cost of missing some races.
+
+config KCSAN_SKIP_WATCH_RANDOMIZE
+	bool "Randomize watchpoint instruction skip count"
+	default y
+	help
+	  If instruction skip count should be randomized, where the maximum is
+	  KCSAN_WATCH_SKIP. If false, the chosen value is always
+	  KCSAN_WATCH_SKIP.
+
+config KCSAN_INTERRUPT_WATCHER
+	bool "Interruptible watchers"
+	help
+	  If enabled, a task that set up a watchpoint may be interrupted while
+	  delayed. This option will allow KCSAN to detect races between
+	  interrupted tasks and other threads of execution on the same CPU.
+
+	  Currently disabled by default, because not all safe per-CPU access
+	  primitives and patterns may be accounted for, and therefore could
+	  result in false positives.
+
+config KCSAN_REPORT_ONCE_IN_MS
+	int "Duration in milliseconds, in which any given race is only reported once"
+	default 3000
+	help
+	  Any given race is only reported once in the defined time window.
+	  Different races may still generate reports within a duration that is
+	  smaller than the duration defined here. This allows rate limiting
+	  reporting to avoid flooding the console with reports.  Setting this
+	  to 0 disables rate limiting.
+
+# The main purpose of the below options is to control reported data races (e.g.
+# in fuzzer configs), and are not expected to be switched frequently by other
+# users. We could turn some of them into boot parameters, but given they should
+# not be switched normally, let's keep them here to simplify configuration.
+#
+# The defaults below are chosen to be very conservative, and may miss certain
+# bugs.
+
+config KCSAN_REPORT_RACE_UNKNOWN_ORIGIN
+	bool "Report races of unknown origin"
+	default y
+	help
+	  If KCSAN should report races where only one access is known, and the
+	  conflicting access is of unknown origin. This type of race is
+	  reported if it was only possible to infer a race due to a data value
+	  change while an access is being delayed on a watchpoint.
+
+config KCSAN_REPORT_VALUE_CHANGE_ONLY
+	bool "Only report races where watcher observed a data value change"
+	default y
+	help
+	  If enabled and a conflicting write is observed via a watchpoint, but
+	  the data value of the memory location was observed to remain
+	  unchanged, do not report the data race.
+
+config KCSAN_ASSUME_PLAIN_WRITES_ATOMIC
+	bool "Assume that plain aligned writes up to word size are atomic"
+	default y
+	help
+	  Assume that plain aligned writes up to word size are atomic by
+	  default, and also not subject to other unsafe compiler optimizations
+	  resulting in data races. This will cause KCSAN to not report data
+	  races due to conflicts where the only plain accesses are aligned
+	  writes up to word size: conflicts between marked reads and plain
+	  aligned writes up to word size will not be reported as data races;
+	  notice that data races between two conflicting plain aligned writes
+	  will also not be reported.
+
+config KCSAN_IGNORE_ATOMICS
+	bool "Do not instrument marked atomic accesses"
+	help
+	  Never instrument marked atomic accesses. This option can be used for
+	  additional filtering. Conflicting marked atomic reads and plain
+	  writes will never be reported as a data race, however, will cause
+	  plain reads and marked writes to result in "unknown origin" reports.
+	  If combined with CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN=n, data
+	  races where at least one access is marked atomic will never be
+	  reported.
+
+	  Similar to KCSAN_ASSUME_PLAIN_WRITES_ATOMIC, but including unaligned
+	  accesses, conflicting marked atomic reads and plain writes will not
+	  be reported as data races; however, unlike that option, data races
+	  due to two conflicting plain writes will be reported (aligned and
+	  unaligned, if CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n).
+
+endif # KCSAN
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index 933680b59e2d..256f2486f9bd 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -3,6 +3,11 @@
 config HAVE_ARCH_KGDB
 	bool
 
+# set if architecture has the its kgdb_arch_handle_qxfer_pkt
+# function to enable gdb stub to address XML packet sent from GDB.
+config HAVE_ARCH_KGDB_QXFER_PKT
+	bool
+
 menuconfig KGDB
 	bool "KGDB: kernel debugger"
 	depends on HAVE_ARCH_KGDB
@@ -124,4 +129,22 @@ config KDB_CONTINUE_CATASTROPHIC
 	  CONFIG_KDB_CONTINUE_CATASTROPHIC == 2. KDB forces a reboot.
 	  If you are not sure, say 0.
 
+config ARCH_HAS_EARLY_DEBUG
+	bool
+	default n
+	help
+	  If an architecture can definitely handle entering the debugger
+	  when early_param's are parsed then it select this config.
+	  Otherwise, if "kgdbwait" is passed on the kernel command line it
+	  won't actually be processed until dbg_late_init() just after the
+	  call to kgdb_arch_late() is made.
+
+	  NOTE: Even if this isn't selected by an architecture we will
+	  still try to register kgdb to handle breakpoints and crashes
+	  when early_param's are parsed, we just won't act on the
+	  "kgdbwait" parameter until dbg_late_init().  If you get a
+	  crash and try to drop into kgdb somewhere between these two
+	  places you might or might not end up being able to use kgdb
+	  depending on exactly how far along the architecture has initted.
+
 endif # KGDB
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index 929211039bac..774315de555a 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -26,9 +26,20 @@ config UBSAN_TRAP
 	  the system. For some system builders this is an acceptable
 	  trade-off.
 
+config UBSAN_KCOV_BROKEN
+	def_bool KCOV && CC_HAS_SANCOV_TRACE_PC
+	depends on CC_IS_CLANG
+	depends on !$(cc-option,-Werror=unused-command-line-argument -fsanitize=bounds -fsanitize-coverage=trace-pc)
+	help
+	  Some versions of clang support either UBSAN or KCOV but not the
+	  combination of the two.
+	  See https://bugs.llvm.org/show_bug.cgi?id=45831 for the status
+	  in newer releases.
+
 config UBSAN_BOUNDS
 	bool "Perform array index bounds checking"
 	default UBSAN
+	depends on !UBSAN_KCOV_BROKEN
 	help
 	  This option enables detection of directly indexed out of bounds
 	  array accesses, where the array size is known at compile time.
@@ -63,7 +74,7 @@ config UBSAN_SANITIZE_ALL
 config UBSAN_ALIGNMENT
 	bool "Enable checks for pointers alignment"
 	default !HAVE_EFFICIENT_UNALIGNED_ACCESS
-	depends on !X86 || !COMPILE_TEST
+	depends on !UBSAN_TRAP
 	help
 	  This option enables the check of unaligned memory accesses.
 	  Enabling this option on architectures that support unaligned
diff --git a/lib/Makefile b/lib/Makefile
index 685aee60de1d..a4a4c6864f51 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -3,10 +3,7 @@
 # Makefile for some libs needed in the kernel.
 #
 
-ifdef CONFIG_FUNCTION_TRACER
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))
-endif
+ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
 
 # These files are disabled because they produce lots of non-interesting and/or
 # flaky coverage that is not a function of syscall inputs. For example,
@@ -18,13 +15,21 @@ KCOV_INSTRUMENT_debugobjects.o := n
 KCOV_INSTRUMENT_dynamic_debug.o := n
 KCOV_INSTRUMENT_fault-inject.o := n
 
+# string.o implements standard library functions like memset/memcpy etc.
+# Use -ffreestanding to ensure that the compiler does not try to "optimize"
+# them into calls to themselves.
+CFLAGS_string.o := -ffreestanding
+
 # Early boot use of cmdline, don't instrument it
 ifdef CONFIG_AMD_MEM_ENCRYPT
 KASAN_SANITIZE_string.o := n
 
-CFLAGS_string.o := $(call cc-option, -fno-stack-protector)
+CFLAGS_string.o += -fno-stack-protector
 endif
 
+# Used by KCSAN while enabled, avoid recursion.
+KCSAN_SANITIZE_random32.o := n
+
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
 	 idr.o extable.o sha1.o irq_regs.o argv_split.o \
@@ -34,7 +39,6 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o
 
 lib-$(CONFIG_PRINTK) += dump_stack.o
-lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
 
 lib-y	+= kobject.o klist.o
@@ -56,6 +60,8 @@ obj-y += kstrtox.o
 obj-$(CONFIG_FIND_BIT_BENCHMARK) += find_bit_benchmark.o
 obj-$(CONFIG_TEST_BPF) += test_bpf.o
 obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
+obj-$(CONFIG_TEST_BITOPS) += test_bitops.o
+CFLAGS_test_bitops.o += -Werror
 obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o
 obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o
 obj-$(CONFIG_TEST_IDA) += test_ida.o
@@ -92,6 +98,31 @@ obj-$(CONFIG_TEST_STACKINIT) += test_stackinit.o
 obj-$(CONFIG_TEST_BLACKHOLE_DEV) += test_blackhole_dev.o
 obj-$(CONFIG_TEST_MEMINIT) += test_meminit.o
 obj-$(CONFIG_TEST_LOCKUP) += test_lockup.o
+obj-$(CONFIG_TEST_HMM) += test_hmm.o
+
+#
+# CFLAGS for compiling floating point code inside the kernel. x86/Makefile turns
+# off the generation of FPU/SSE* instructions for kernel proper but FPU_FLAGS
+# get appended last to CFLAGS and thus override those previous compiler options.
+#
+FPU_CFLAGS := -mhard-float -msse -msse2
+ifdef CONFIG_CC_IS_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
+#
+# The "-msse" in the first argument is there so that the
+# -mpreferred-stack-boundary=3 build error:
+#
+#  -mpreferred-stack-boundary=3 is not between 4 and 12
+#
+# can be triggered. Otherwise gcc doesn't complain.
+FPU_CFLAGS += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4)
+endif
+
+obj-$(CONFIG_TEST_FPU) += test_fpu.o
+CFLAGS_test_fpu.o += $(FPU_CFLAGS)
 
 obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/
 
@@ -125,6 +156,7 @@ obj-$(CONFIG_DEBUG_LIST) += list_debug.o
 obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
 
 obj-$(CONFIG_BITREVERSE) += bitrev.o
+obj-$(CONFIG_LINEAR_RANGES) += linear_ranges.o
 obj-$(CONFIG_PACKING)	+= packing.o
 obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
 obj-$(CONFIG_CRC16)	+= crc16.o
@@ -163,6 +195,7 @@ lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o
 lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o
 lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o
 lib-$(CONFIG_DECOMPRESS_LZ4) += decompress_unlz4.o
+lib-$(CONFIG_DECOMPRESS_ZSTD) += decompress_unzstd.o
 
 obj-$(CONFIG_TEXTSEARCH) += textsearch.o
 obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
@@ -186,7 +219,7 @@ lib-$(CONFIG_GENERIC_BUG) += bug.o
 
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
 
-obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
+obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o
 obj-$(CONFIG_SYMBOLIC_ERRNAME) += errname.o
 
 obj-$(CONFIG_NLATTR) += nlattr.o
@@ -292,7 +325,8 @@ endif
 
 UBSAN_SANITIZE_ubsan.o := n
 KASAN_SANITIZE_ubsan.o := n
-CFLAGS_ubsan.o := $(call cc-option, -fno-stack-protector) $(DISABLE_STACKLEAK_PLUGIN)
+KCSAN_SANITIZE_ubsan.o := n
+CFLAGS_ubsan.o := -fno-stack-protector $(DISABLE_STACKLEAK_PLUGIN)
 
 obj-$(CONFIG_SBITMAP) += sbitmap.o
 
@@ -307,5 +341,10 @@ obj-$(CONFIG_GENERIC_LIB_CMPDI2) += cmpdi2.o
 obj-$(CONFIG_GENERIC_LIB_UCMPDI2) += ucmpdi2.o
 obj-$(CONFIG_OBJAGG) += objagg.o
 
+# pldmfw library
+obj-$(CONFIG_PLDMFW) += pldmfw/
+
 # KUnit tests
 obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o
+obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o
+obj-$(CONFIG_BITS_TEST) += test_bits.o
diff --git a/lib/bch.c b/lib/bch.c
index 052d3fb753a0..7c031ee8b93b 100644
--- a/lib/bch.c
+++ b/lib/bch.c
@@ -23,15 +23,15 @@
  * This library provides runtime configurable encoding/decoding of binary
  * Bose-Chaudhuri-Hocquenghem (BCH) codes.
  *
- * Call init_bch to get a pointer to a newly allocated bch_control structure for
+ * Call bch_init to get a pointer to a newly allocated bch_control structure for
  * the given m (Galois field order), t (error correction capability) and
  * (optional) primitive polynomial parameters.
  *
- * Call encode_bch to compute and store ecc parity bytes to a given buffer.
- * Call decode_bch to detect and locate errors in received data.
+ * Call bch_encode to compute and store ecc parity bytes to a given buffer.
+ * Call bch_decode to detect and locate errors in received data.
  *
  * On systems supporting hw BCH features, intermediate results may be provided
- * to decode_bch in order to skip certain steps. See decode_bch() documentation
+ * to bch_decode in order to skip certain steps. See bch_decode() documentation
  * for details.
  *
  * Option CONFIG_BCH_CONST_PARAMS can be used to force fixed values of
@@ -114,10 +114,53 @@ struct gf_poly_deg1 {
 	unsigned int   c[2];
 };
 
+static u8 swap_bits_table[] = {
+	0x00, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0,
+	0x10, 0x90, 0x50, 0xd0, 0x30, 0xb0, 0x70, 0xf0,
+	0x08, 0x88, 0x48, 0xc8, 0x28, 0xa8, 0x68, 0xe8,
+	0x18, 0x98, 0x58, 0xd8, 0x38, 0xb8, 0x78, 0xf8,
+	0x04, 0x84, 0x44, 0xc4, 0x24, 0xa4, 0x64, 0xe4,
+	0x14, 0x94, 0x54, 0xd4, 0x34, 0xb4, 0x74, 0xf4,
+	0x0c, 0x8c, 0x4c, 0xcc, 0x2c, 0xac, 0x6c, 0xec,
+	0x1c, 0x9c, 0x5c, 0xdc, 0x3c, 0xbc, 0x7c, 0xfc,
+	0x02, 0x82, 0x42, 0xc2, 0x22, 0xa2, 0x62, 0xe2,
+	0x12, 0x92, 0x52, 0xd2, 0x32, 0xb2, 0x72, 0xf2,
+	0x0a, 0x8a, 0x4a, 0xca, 0x2a, 0xaa, 0x6a, 0xea,
+	0x1a, 0x9a, 0x5a, 0xda, 0x3a, 0xba, 0x7a, 0xfa,
+	0x06, 0x86, 0x46, 0xc6, 0x26, 0xa6, 0x66, 0xe6,
+	0x16, 0x96, 0x56, 0xd6, 0x36, 0xb6, 0x76, 0xf6,
+	0x0e, 0x8e, 0x4e, 0xce, 0x2e, 0xae, 0x6e, 0xee,
+	0x1e, 0x9e, 0x5e, 0xde, 0x3e, 0xbe, 0x7e, 0xfe,
+	0x01, 0x81, 0x41, 0xc1, 0x21, 0xa1, 0x61, 0xe1,
+	0x11, 0x91, 0x51, 0xd1, 0x31, 0xb1, 0x71, 0xf1,
+	0x09, 0x89, 0x49, 0xc9, 0x29, 0xa9, 0x69, 0xe9,
+	0x19, 0x99, 0x59, 0xd9, 0x39, 0xb9, 0x79, 0xf9,
+	0x05, 0x85, 0x45, 0xc5, 0x25, 0xa5, 0x65, 0xe5,
+	0x15, 0x95, 0x55, 0xd5, 0x35, 0xb5, 0x75, 0xf5,
+	0x0d, 0x8d, 0x4d, 0xcd, 0x2d, 0xad, 0x6d, 0xed,
+	0x1d, 0x9d, 0x5d, 0xdd, 0x3d, 0xbd, 0x7d, 0xfd,
+	0x03, 0x83, 0x43, 0xc3, 0x23, 0xa3, 0x63, 0xe3,
+	0x13, 0x93, 0x53, 0xd3, 0x33, 0xb3, 0x73, 0xf3,
+	0x0b, 0x8b, 0x4b, 0xcb, 0x2b, 0xab, 0x6b, 0xeb,
+	0x1b, 0x9b, 0x5b, 0xdb, 0x3b, 0xbb, 0x7b, 0xfb,
+	0x07, 0x87, 0x47, 0xc7, 0x27, 0xa7, 0x67, 0xe7,
+	0x17, 0x97, 0x57, 0xd7, 0x37, 0xb7, 0x77, 0xf7,
+	0x0f, 0x8f, 0x4f, 0xcf, 0x2f, 0xaf, 0x6f, 0xef,
+	0x1f, 0x9f, 0x5f, 0xdf, 0x3f, 0xbf, 0x7f, 0xff,
+};
+
+static u8 swap_bits(struct bch_control *bch, u8 in)
+{
+	if (!bch->swap_bits)
+		return in;
+
+	return swap_bits_table[in];
+}
+
 /*
- * same as encode_bch(), but process input data one byte at a time
+ * same as bch_encode(), but process input data one byte at a time
  */
-static void encode_bch_unaligned(struct bch_control *bch,
+static void bch_encode_unaligned(struct bch_control *bch,
 				 const unsigned char *data, unsigned int len,
 				 uint32_t *ecc)
 {
@@ -126,7 +169,9 @@ static void encode_bch_unaligned(struct bch_control *bch,
 	const int l = BCH_ECC_WORDS(bch)-1;
 
 	while (len--) {
-		p = bch->mod8_tab + (l+1)*(((ecc[0] >> 24)^(*data++)) & 0xff);
+		u8 tmp = swap_bits(bch, *data++);
+
+		p = bch->mod8_tab + (l+1)*(((ecc[0] >> 24)^(tmp)) & 0xff);
 
 		for (i = 0; i < l; i++)
 			ecc[i] = ((ecc[i] << 8)|(ecc[i+1] >> 24))^(*p++);
@@ -145,10 +190,16 @@ static void load_ecc8(struct bch_control *bch, uint32_t *dst,
 	unsigned int i, nwords = BCH_ECC_WORDS(bch)-1;
 
 	for (i = 0; i < nwords; i++, src += 4)
-		dst[i] = (src[0] << 24)|(src[1] << 16)|(src[2] << 8)|src[3];
+		dst[i] = ((u32)swap_bits(bch, src[0]) << 24) |
+			((u32)swap_bits(bch, src[1]) << 16) |
+			((u32)swap_bits(bch, src[2]) << 8) |
+			swap_bits(bch, src[3]);
 
 	memcpy(pad, src, BCH_ECC_BYTES(bch)-4*nwords);
-	dst[nwords] = (pad[0] << 24)|(pad[1] << 16)|(pad[2] << 8)|pad[3];
+	dst[nwords] = ((u32)swap_bits(bch, pad[0]) << 24) |
+		((u32)swap_bits(bch, pad[1]) << 16) |
+		((u32)swap_bits(bch, pad[2]) << 8) |
+		swap_bits(bch, pad[3]);
 }
 
 /*
@@ -161,20 +212,20 @@ static void store_ecc8(struct bch_control *bch, uint8_t *dst,
 	unsigned int i, nwords = BCH_ECC_WORDS(bch)-1;
 
 	for (i = 0; i < nwords; i++) {
-		*dst++ = (src[i] >> 24);
-		*dst++ = (src[i] >> 16) & 0xff;
-		*dst++ = (src[i] >>  8) & 0xff;
-		*dst++ = (src[i] >>  0) & 0xff;
+		*dst++ = swap_bits(bch, src[i] >> 24);
+		*dst++ = swap_bits(bch, src[i] >> 16);
+		*dst++ = swap_bits(bch, src[i] >> 8);
+		*dst++ = swap_bits(bch, src[i]);
 	}
-	pad[0] = (src[nwords] >> 24);
-	pad[1] = (src[nwords] >> 16) & 0xff;
-	pad[2] = (src[nwords] >>  8) & 0xff;
-	pad[3] = (src[nwords] >>  0) & 0xff;
+	pad[0] = swap_bits(bch, src[nwords] >> 24);
+	pad[1] = swap_bits(bch, src[nwords] >> 16);
+	pad[2] = swap_bits(bch, src[nwords] >> 8);
+	pad[3] = swap_bits(bch, src[nwords]);
 	memcpy(dst, pad, BCH_ECC_BYTES(bch)-4*nwords);
 }
 
 /**
- * encode_bch - calculate BCH ecc parity of data
+ * bch_encode - calculate BCH ecc parity of data
  * @bch:   BCH control structure
  * @data:  data to encode
  * @len:   data length in bytes
@@ -187,7 +238,7 @@ static void store_ecc8(struct bch_control *bch, uint8_t *dst,
  * The exact number of computed ecc parity bits is given by member @ecc_bits of
  * @bch; it may be less than m*t for large values of t.
  */
-void encode_bch(struct bch_control *bch, const uint8_t *data,
+void bch_encode(struct bch_control *bch, const uint8_t *data,
 		unsigned int len, uint8_t *ecc)
 {
 	const unsigned int l = BCH_ECC_WORDS(bch)-1;
@@ -215,7 +266,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 	m = ((unsigned long)data) & 3;
 	if (m) {
 		mlen = (len < (4-m)) ? len : 4-m;
-		encode_bch_unaligned(bch, data, mlen, bch->ecc_buf);
+		bch_encode_unaligned(bch, data, mlen, bch->ecc_buf);
 		data += mlen;
 		len  -= mlen;
 	}
@@ -240,7 +291,13 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 	 */
 	while (mlen--) {
 		/* input data is read in big-endian format */
-		w = r[0]^cpu_to_be32(*pdata++);
+		w = cpu_to_be32(*pdata++);
+		if (bch->swap_bits)
+			w = (u32)swap_bits(bch, w) |
+			    ((u32)swap_bits(bch, w >> 8) << 8) |
+			    ((u32)swap_bits(bch, w >> 16) << 16) |
+			    ((u32)swap_bits(bch, w >> 24) << 24);
+		w ^= r[0];
 		p0 = tab0 + (l+1)*((w >>  0) & 0xff);
 		p1 = tab1 + (l+1)*((w >>  8) & 0xff);
 		p2 = tab2 + (l+1)*((w >> 16) & 0xff);
@@ -255,13 +312,13 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 
 	/* process last unaligned bytes */
 	if (len)
-		encode_bch_unaligned(bch, data, len, bch->ecc_buf);
+		bch_encode_unaligned(bch, data, len, bch->ecc_buf);
 
 	/* store ecc parity bytes into original parity buffer */
 	if (ecc)
 		store_ecc8(bch, ecc, bch->ecc_buf);
 }
-EXPORT_SYMBOL_GPL(encode_bch);
+EXPORT_SYMBOL_GPL(bch_encode);
 
 static inline int modulo(struct bch_control *bch, unsigned int v)
 {
@@ -952,7 +1009,7 @@ static int chien_search(struct bch_control *bch, unsigned int len,
 #endif /* USE_CHIEN_SEARCH */
 
 /**
- * decode_bch - decode received codeword and find bit error locations
+ * bch_decode - decode received codeword and find bit error locations
  * @bch:      BCH control structure
  * @data:     received data, ignored if @calc_ecc is provided
  * @len:      data length in bytes, must always be provided
@@ -966,22 +1023,22 @@ static int chien_search(struct bch_control *bch, unsigned int len,
  *  invalid parameters were provided
  *
  * Depending on the available hw BCH support and the need to compute @calc_ecc
- * separately (using encode_bch()), this function should be called with one of
+ * separately (using bch_encode()), this function should be called with one of
  * the following parameter configurations -
  *
  * by providing @data and @recv_ecc only:
- *   decode_bch(@bch, @data, @len, @recv_ecc, NULL, NULL, @errloc)
+ *   bch_decode(@bch, @data, @len, @recv_ecc, NULL, NULL, @errloc)
  *
  * by providing @recv_ecc and @calc_ecc:
- *   decode_bch(@bch, NULL, @len, @recv_ecc, @calc_ecc, NULL, @errloc)
+ *   bch_decode(@bch, NULL, @len, @recv_ecc, @calc_ecc, NULL, @errloc)
  *
  * by providing ecc = recv_ecc XOR calc_ecc:
- *   decode_bch(@bch, NULL, @len, NULL, ecc, NULL, @errloc)
+ *   bch_decode(@bch, NULL, @len, NULL, ecc, NULL, @errloc)
  *
  * by providing syndrome results @syn:
- *   decode_bch(@bch, NULL, @len, NULL, NULL, @syn, @errloc)
+ *   bch_decode(@bch, NULL, @len, NULL, NULL, @syn, @errloc)
  *
- * Once decode_bch() has successfully returned with a positive value, error
+ * Once bch_decode() has successfully returned with a positive value, error
  * locations returned in array @errloc should be interpreted as follows -
  *
  * if (errloc[n] >= 8*len), then n-th error is located in ecc (no need for
@@ -993,7 +1050,7 @@ static int chien_search(struct bch_control *bch, unsigned int len,
  * Note that this function does not perform any data correction by itself, it
  * merely indicates error locations.
  */
-int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len,
+int bch_decode(struct bch_control *bch, const uint8_t *data, unsigned int len,
 	       const uint8_t *recv_ecc, const uint8_t *calc_ecc,
 	       const unsigned int *syn, unsigned int *errloc)
 {
@@ -1012,7 +1069,7 @@ int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len,
 			/* compute received data ecc into an internal buffer */
 			if (!data || !recv_ecc)
 				return -EINVAL;
-			encode_bch(bch, data, len, NULL);
+			bch_encode(bch, data, len, NULL);
 		} else {
 			/* load provided calculated ecc */
 			load_ecc8(bch, bch->ecc_buf, calc_ecc);
@@ -1048,12 +1105,14 @@ int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len,
 				break;
 			}
 			errloc[i] = nbits-1-errloc[i];
-			errloc[i] = (errloc[i] & ~7)|(7-(errloc[i] & 7));
+			if (!bch->swap_bits)
+				errloc[i] = (errloc[i] & ~7) |
+					    (7-(errloc[i] & 7));
 		}
 	}
 	return (err >= 0) ? err : -EBADMSG;
 }
-EXPORT_SYMBOL_GPL(decode_bch);
+EXPORT_SYMBOL_GPL(bch_decode);
 
 /*
  * generate Galois field lookup tables
@@ -1236,27 +1295,29 @@ finish:
 }
 
 /**
- * init_bch - initialize a BCH encoder/decoder
+ * bch_init - initialize a BCH encoder/decoder
  * @m:          Galois field order, should be in the range 5-15
  * @t:          maximum error correction capability, in bits
  * @prim_poly:  user-provided primitive polynomial (or 0 to use default)
+ * @swap_bits:  swap bits within data and syndrome bytes
  *
  * Returns:
  *  a newly allocated BCH control structure if successful, NULL otherwise
  *
  * This initialization can take some time, as lookup tables are built for fast
  * encoding/decoding; make sure not to call this function from a time critical
- * path. Usually, init_bch() should be called on module/driver init and
- * free_bch() should be called to release memory on exit.
+ * path. Usually, bch_init() should be called on module/driver init and
+ * bch_free() should be called to release memory on exit.
  *
  * You may provide your own primitive polynomial of degree @m in argument
- * @prim_poly, or let init_bch() use its default polynomial.
+ * @prim_poly, or let bch_init() use its default polynomial.
  *
- * Once init_bch() has successfully returned a pointer to a newly allocated
+ * Once bch_init() has successfully returned a pointer to a newly allocated
  * BCH control structure, ecc length in bytes is given by member @ecc_bytes of
  * the structure.
  */
-struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
+struct bch_control *bch_init(int m, int t, unsigned int prim_poly,
+			     bool swap_bits)
 {
 	int err = 0;
 	unsigned int i, words;
@@ -1321,6 +1382,7 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
 	bch->syn       = bch_alloc(2*t*sizeof(*bch->syn), &err);
 	bch->cache     = bch_alloc(2*t*sizeof(*bch->cache), &err);
 	bch->elp       = bch_alloc((t+1)*sizeof(struct gf_poly_deg1), &err);
+	bch->swap_bits = swap_bits;
 
 	for (i = 0; i < ARRAY_SIZE(bch->poly_2t); i++)
 		bch->poly_2t[i] = bch_alloc(GF_POLY_SZ(2*t), &err);
@@ -1347,16 +1409,16 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
 	return bch;
 
 fail:
-	free_bch(bch);
+	bch_free(bch);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(init_bch);
+EXPORT_SYMBOL_GPL(bch_init);
 
 /**
- *  free_bch - free the BCH control structure
+ *  bch_free - free the BCH control structure
  *  @bch:    BCH control structure to release
  */
-void free_bch(struct bch_control *bch)
+void bch_free(struct bch_control *bch)
 {
 	unsigned int i;
 
@@ -1377,7 +1439,7 @@ void free_bch(struct bch_control *bch)
 		kfree(bch);
 	}
 }
-EXPORT_SYMBOL_GPL(free_bch);
+EXPORT_SYMBOL_GPL(bch_free);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Ivan Djelic <ivan.djelic@parrot.com>");
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 89260aa342d6..c13d859bc7ab 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -182,21 +182,22 @@ EXPORT_SYMBOL(__bitmap_shift_left);
  *
  * In pictures, example for a big-endian 32-bit architecture:
  *
- * @src:
- * 31                                   63
- * |                                    |
- * 10000000 11000001 11110010 00010101  10000000 11000001 01110010 00010101
- *                 |  |              |                                    |
- *                16  14             0                                   32
- *
- * if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is:
- *
- * 31                                   63
- * |                                    |
- * 10110000 00011000 00110010 00010101  00010000 00011000 00101110 01000010
- *                    |              |                                    |
- *                    14 (bit 17     0                                   32
- *                        from @src)
+ * The @src bitmap is::
+ *
+ *   31                                   63
+ *   |                                    |
+ *   10000000 11000001 11110010 00010101  10000000 11000001 01110010 00010101
+ *                   |  |              |                                    |
+ *                  16  14             0                                   32
+ *
+ * if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is::
+ *
+ *   31                                   63
+ *   |                                    |
+ *   10110000 00011000 00110010 00010101  00010000 00011000 00101110 01000010
+ *                      |              |                                    |
+ *                      14 (bit 17     0                                   32
+ *                          from @src)
  *
  * Note that @dst and @src might overlap partially or entirely.
  *
@@ -211,13 +212,13 @@ void bitmap_cut(unsigned long *dst, const unsigned long *src,
 	unsigned long keep = 0, carry;
 	int i;
 
-	memmove(dst, src, len * sizeof(*dst));
-
 	if (first % BITS_PER_LONG) {
 		keep = src[first / BITS_PER_LONG] &
 		       (~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG));
 	}
 
+	memmove(dst, src, len * sizeof(*dst));
+
 	while (cut--) {
 		for (i = first / BITS_PER_LONG; i < len; i++) {
 			if (i < len - 1)
@@ -740,8 +741,9 @@ int bitmap_parse(const char *start, unsigned int buflen,
 	int chunks = BITS_TO_U32(nmaskbits);
 	u32 *bitmap = (u32 *)maskp;
 	int unset_bit;
+	int chunk;
 
-	while (1) {
+	for (chunk = 0; ; chunk++) {
 		end = bitmap_find_region_reverse(start, end);
 		if (start > end)
 			break;
@@ -749,7 +751,11 @@ int bitmap_parse(const char *start, unsigned int buflen,
 		if (!chunks--)
 			return -EOVERFLOW;
 
-		end = bitmap_get_x32_reverse(start, end, bitmap++);
+#if defined(CONFIG_64BIT) && defined(__BIG_ENDIAN)
+		end = bitmap_get_x32_reverse(start, end, &bitmap[chunk ^ 1]);
+#else
+		end = bitmap_get_x32_reverse(start, end, &bitmap[chunk]);
+#endif
 		if (IS_ERR(end))
 			return PTR_ERR(end);
 	}
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 912ef4921398..649ed44f199c 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -31,6 +31,8 @@ static size_t xbc_data_size __initdata;
 static struct xbc_node *last_parent __initdata;
 static const char *xbc_err_msg __initdata;
 static int xbc_err_pos __initdata;
+static int open_brace[XBC_DEPTH_MAX] __initdata;
+static int brace_index __initdata;
 
 static int __init xbc_parse_error(const char *msg, const char *p)
 {
@@ -329,22 +331,30 @@ const char * __init xbc_node_find_next_key_value(struct xbc_node *root,
 
 /* XBC parse and tree build */
 
+static int __init xbc_init_node(struct xbc_node *node, char *data, u32 flag)
+{
+	unsigned long offset = data - xbc_data;
+
+	if (WARN_ON(offset >= XBC_DATA_MAX))
+		return -EINVAL;
+
+	node->data = (u16)offset | flag;
+	node->child = 0;
+	node->next = 0;
+
+	return 0;
+}
+
 static struct xbc_node * __init xbc_add_node(char *data, u32 flag)
 {
 	struct xbc_node *node;
-	unsigned long offset;
 
 	if (xbc_node_num == XBC_NODE_MAX)
 		return NULL;
 
 	node = &xbc_nodes[xbc_node_num++];
-	offset = data - xbc_data;
-	node->data = (u16)offset;
-	if (WARN_ON(offset >= XBC_DATA_MAX))
+	if (xbc_init_node(node, data, flag) < 0)
 		return NULL;
-	node->data |= flag;
-	node->child = 0;
-	node->next = 0;
 
 	return node;
 }
@@ -423,27 +433,27 @@ static char *skip_spaces_until_newline(char *p)
 	return p;
 }
 
-static int __init __xbc_open_brace(void)
+static int __init __xbc_open_brace(char *p)
 {
-	/* Mark the last key as open brace */
-	last_parent->next = XBC_NODE_MAX;
+	/* Push the last key as open brace */
+	open_brace[brace_index++] = xbc_node_index(last_parent);
+	if (brace_index >= XBC_DEPTH_MAX)
+		return xbc_parse_error("Exceed max depth of braces", p);
 
 	return 0;
 }
 
 static int __init __xbc_close_brace(char *p)
 {
-	struct xbc_node *node;
-
-	if (!last_parent || last_parent->next != XBC_NODE_MAX)
+	brace_index--;
+	if (!last_parent || brace_index < 0 ||
+	    (open_brace[brace_index] != xbc_node_index(last_parent)))
 		return xbc_parse_error("Unexpected closing brace", p);
 
-	node = last_parent;
-	node->next = 0;
-	do {
-		node = xbc_node_get_parent(node);
-	} while (node && node->next != XBC_NODE_MAX);
-	last_parent = node;
+	if (brace_index == 0)
+		last_parent = NULL;
+	else
+		last_parent = &xbc_nodes[open_brace[brace_index - 1]];
 
 	return 0;
 }
@@ -484,8 +494,8 @@ static int __init __xbc_parse_value(char **__v, char **__n)
 			break;
 		}
 		if (strchr(",;\n#}", c)) {
-			v = strim(v);
 			*p++ = '\0';
+			v = strim(v);
 			break;
 		}
 	}
@@ -603,7 +613,9 @@ static int __init xbc_parse_kv(char **k, char *v, int op)
 	if (c < 0)
 		return c;
 
-	if (!xbc_add_sibling(v, XBC_VALUE))
+	if (op == ':' && child) {
+		xbc_init_node(child, v, XBC_VALUE);
+	} else if (!xbc_add_sibling(v, XBC_VALUE))
 		return -ENOMEM;
 
 	if (c == ',') {	/* Array */
@@ -651,7 +663,7 @@ static int __init xbc_open_brace(char **k, char *n)
 		return ret;
 	*k = n;
 
-	return __xbc_open_brace();
+	return __xbc_open_brace(n - 1);
 }
 
 static int __init xbc_close_brace(char **k, char *n)
@@ -671,6 +683,13 @@ static int __init xbc_verify_tree(void)
 	int i, depth, len, wlen;
 	struct xbc_node *n, *m;
 
+	/* Brace closing */
+	if (brace_index) {
+		n = &xbc_nodes[open_brace[brace_index]];
+		return xbc_parse_error("Brace is not closed",
+					xbc_node_get_data(n));
+	}
+
 	/* Empty tree */
 	if (xbc_node_num == 0) {
 		xbc_parse_error("Empty config", xbc_data);
@@ -735,6 +754,7 @@ void __init xbc_destroy_all(void)
 	xbc_node_num = 0;
 	memblock_free(__pa(xbc_nodes), sizeof(struct xbc_node) * XBC_NODE_MAX);
 	xbc_nodes = NULL;
+	brace_index = 0;
 }
 
 /**
@@ -787,7 +807,7 @@ int __init xbc_init(char *buf, const char **emsg, int *epos)
 
 	p = buf;
 	do {
-		q = strpbrk(p, "{}=+;\n#");
+		q = strpbrk(p, "{}=+;:\n#");
 		if (!q) {
 			p = skip_spaces(p);
 			if (*p != '\0')
@@ -798,13 +818,16 @@ int __init xbc_init(char *buf, const char **emsg, int *epos)
 		c = *q;
 		*q++ = '\0';
 		switch (c) {
+		case ':':
 		case '+':
 			if (*q++ != '=') {
-				ret = xbc_parse_error("Wrong '+' operator",
+				ret = xbc_parse_error(c == '+' ?
+						"Wrong '+' operator" :
+						"Wrong ':' operator",
 							q - 2);
 				break;
 			}
-			/* Fall through */
+			/* fall through */
 		case '=':
 			ret = xbc_parse_kv(&p, q, c);
 			break;
diff --git a/lib/bsearch.c b/lib/bsearch.c
index 8b3aae5ae77a..bf86aa66f2b2 100644
--- a/lib/bsearch.c
+++ b/lib/bsearch.c
@@ -28,27 +28,9 @@
  * the key and elements in the array are of the same type, you can use
  * the same comparison function for both sort() and bsearch().
  */
-void *bsearch(const void *key, const void *base, size_t num, size_t size,
-	      cmp_func_t cmp)
+void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp)
 {
-	const char *pivot;
-	int result;
-
-	while (num > 0) {
-		pivot = base + (num >> 1) * size;
-		result = cmp(key, pivot);
-
-		if (result == 0)
-			return (void *)pivot;
-
-		if (result > 0) {
-			base = pivot + size;
-			num--;
-		}
-		num >>= 1;
-	}
-
-	return NULL;
+	return __inline_bsearch(key, base, num, size, cmp);
 }
 EXPORT_SYMBOL(bsearch);
 NOKPROBE_SYMBOL(bsearch);
diff --git a/lib/bug.c b/lib/bug.c
index 8c98af0bf585..7103440c0ee1 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -47,6 +47,7 @@
 #include <linux/bug.h>
 #include <linux/sched.h>
 #include <linux/rculist.h>
+#include <linux/ftrace.h>
 
 extern struct bug_entry __start___bug_table[], __stop___bug_table[];
 
@@ -153,6 +154,8 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 	if (!bug)
 		return BUG_TRAP_TYPE_NONE;
 
+	disable_trace_on_warning();
+
 	file = NULL;
 	line = 0;
 	warning = 0;
diff --git a/lib/checksum.c b/lib/checksum.c
index de032ad96f4a..c7861e84c526 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -146,35 +146,15 @@ __sum16 ip_compute_csum(const void *buff, int len)
 EXPORT_SYMBOL(ip_compute_csum);
 
 /*
- * copy from fs while checksumming, otherwise like csum_partial
- */
-__wsum
-csum_partial_copy_from_user(const void __user *src, void *dst, int len,
-						__wsum sum, int *csum_err)
-{
-	int missing;
-
-	missing = __copy_from_user(dst, src, len);
-	if (missing) {
-		memset(dst + len - missing, 0, missing);
-		*csum_err = -EFAULT;
-	} else
-		*csum_err = 0;
-
-	return csum_partial(dst, len, sum);
-}
-EXPORT_SYMBOL(csum_partial_copy_from_user);
-
-/*
  * copy from ds while checksumming, otherwise like csum_partial
  */
 __wsum
-csum_partial_copy(const void *src, void *dst, int len, __wsum sum)
+csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
 {
 	memcpy(dst, src, len);
 	return csum_partial(dst, len, sum);
 }
-EXPORT_SYMBOL(csum_partial_copy);
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
 
 #ifndef csum_tcpudp_nofold
 static inline u32 from64to32(u64 x)
diff --git a/lib/cpumask.c b/lib/cpumask.c
index fb22fb266f93..85da6ab4fbb5 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -6,6 +6,7 @@
 #include <linux/export.h>
 #include <linux/memblock.h>
 #include <linux/numa.h>
+#include <linux/sched/isolation.h>
 
 /**
  * cpumask_next - get the next cpu in a cpumask
@@ -205,22 +206,27 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
  */
 unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-	int cpu;
+	int cpu, hk_flags;
+	const struct cpumask *mask;
 
+	hk_flags = HK_FLAG_DOMAIN | HK_FLAG_MANAGED_IRQ;
+	mask = housekeeping_cpumask(hk_flags);
 	/* Wrap: we always want a cpu. */
-	i %= num_online_cpus();
+	i %= cpumask_weight(mask);
 
 	if (node == NUMA_NO_NODE) {
-		for_each_cpu(cpu, cpu_online_mask)
+		for_each_cpu(cpu, mask) {
 			if (i-- == 0)
 				return cpu;
+		}
 	} else {
 		/* NUMA first. */
-		for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask)
+		for_each_cpu_and(cpu, cpumask_of_node(node), mask) {
 			if (i-- == 0)
 				return cpu;
+		}
 
-		for_each_cpu(cpu, cpu_online_mask) {
+		for_each_cpu(cpu, mask) {
 			/* Skip NUMA nodes, done above. */
 			if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
 				continue;
diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c
index 8cc01a603416..1ed2ed487097 100644
--- a/lib/crc-t10dif.c
+++ b/lib/crc-t10dif.c
@@ -17,64 +17,69 @@
 #include <linux/notifier.h>
 
 static struct crypto_shash __rcu *crct10dif_tfm;
-static struct static_key crct10dif_fallback __read_mostly;
+static DEFINE_STATIC_KEY_TRUE(crct10dif_fallback);
 static DEFINE_MUTEX(crc_t10dif_mutex);
+static struct work_struct crct10dif_rehash_work;
 
-static int crc_t10dif_rehash(struct notifier_block *self, unsigned long val, void *data)
+static int crc_t10dif_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	struct crypto_alg *alg = data;
-	struct crypto_shash *new, *old;
 
 	if (val != CRYPTO_MSG_ALG_LOADED ||
-	    static_key_false(&crct10dif_fallback) ||
-	    strncmp(alg->cra_name, CRC_T10DIF_STRING, strlen(CRC_T10DIF_STRING)))
-		return 0;
+	    strcmp(alg->cra_name, CRC_T10DIF_STRING))
+		return NOTIFY_DONE;
+
+	schedule_work(&crct10dif_rehash_work);
+	return NOTIFY_OK;
+}
+
+static void crc_t10dif_rehash(struct work_struct *work)
+{
+	struct crypto_shash *new, *old;
 
 	mutex_lock(&crc_t10dif_mutex);
 	old = rcu_dereference_protected(crct10dif_tfm,
 					lockdep_is_held(&crc_t10dif_mutex));
-	if (!old) {
-		mutex_unlock(&crc_t10dif_mutex);
-		return 0;
-	}
-	new = crypto_alloc_shash("crct10dif", 0, 0);
+	new = crypto_alloc_shash(CRC_T10DIF_STRING, 0, 0);
 	if (IS_ERR(new)) {
 		mutex_unlock(&crc_t10dif_mutex);
-		return 0;
+		return;
 	}
 	rcu_assign_pointer(crct10dif_tfm, new);
 	mutex_unlock(&crc_t10dif_mutex);
 
-	synchronize_rcu();
-	crypto_free_shash(old);
-	return 0;
+	if (old) {
+		synchronize_rcu();
+		crypto_free_shash(old);
+	} else {
+		static_branch_disable(&crct10dif_fallback);
+	}
 }
 
 static struct notifier_block crc_t10dif_nb = {
-	.notifier_call = crc_t10dif_rehash,
+	.notifier_call = crc_t10dif_notify,
 };
 
 __u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len)
 {
 	struct {
 		struct shash_desc shash;
-		char ctx[2];
+		__u16 crc;
 	} desc;
 	int err;
 
-	if (static_key_false(&crct10dif_fallback))
+	if (static_branch_unlikely(&crct10dif_fallback))
 		return crc_t10dif_generic(crc, buffer, len);
 
 	rcu_read_lock();
 	desc.shash.tfm = rcu_dereference(crct10dif_tfm);
-	*(__u16 *)desc.ctx = crc;
-
+	desc.crc = crc;
 	err = crypto_shash_update(&desc.shash, buffer, len);
 	rcu_read_unlock();
 
 	BUG_ON(err);
 
-	return *(__u16 *)desc.ctx;
+	return desc.crc;
 }
 EXPORT_SYMBOL(crc_t10dif_update);
 
@@ -86,19 +91,17 @@ EXPORT_SYMBOL(crc_t10dif);
 
 static int __init crc_t10dif_mod_init(void)
 {
+	INIT_WORK(&crct10dif_rehash_work, crc_t10dif_rehash);
 	crypto_register_notifier(&crc_t10dif_nb);
-	crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
-	if (IS_ERR(crct10dif_tfm)) {
-		static_key_slow_inc(&crct10dif_fallback);
-		crct10dif_tfm = NULL;
-	}
+	crc_t10dif_rehash(&crct10dif_rehash_work);
 	return 0;
 }
 
 static void __exit crc_t10dif_mod_fini(void)
 {
 	crypto_unregister_notifier(&crc_t10dif_nb);
-	crypto_free_shash(crct10dif_tfm);
+	cancel_work_sync(&crct10dif_rehash_work);
+	crypto_free_shash(rcu_dereference_protected(crct10dif_tfm, 1));
 }
 
 module_init(crc_t10dif_mod_init);
@@ -106,15 +109,23 @@ module_exit(crc_t10dif_mod_fini);
 
 static int crc_t10dif_transform_show(char *buffer, const struct kernel_param *kp)
 {
-	if (static_key_false(&crct10dif_fallback))
+	struct crypto_shash *tfm;
+	int len;
+
+	if (static_branch_unlikely(&crct10dif_fallback))
 		return sprintf(buffer, "fallback\n");
 
-	return sprintf(buffer, "%s\n",
-		crypto_tfm_alg_driver_name(crypto_shash_tfm(crct10dif_tfm)));
+	rcu_read_lock();
+	tfm = rcu_dereference(crct10dif_tfm);
+	len = snprintf(buffer, PAGE_SIZE, "%s\n",
+		       crypto_shash_driver_name(tfm));
+	rcu_read_unlock();
+
+	return len;
 }
 
-module_param_call(transform, NULL, crc_t10dif_transform_show, NULL, 0644);
+module_param_call(transform, NULL, crc_t10dif_transform_show, NULL, 0444);
 
-MODULE_DESCRIPTION("T10 DIF CRC calculation");
+MODULE_DESCRIPTION("T10 DIF CRC calculation (library API)");
 MODULE_LICENSE("GPL");
 MODULE_SOFTDEP("pre: crct10dif");
diff --git a/lib/crc32.c b/lib/crc32.c
index 4a20455d1f61..35a03d03f973 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -24,7 +24,7 @@
  * Version 2.  See the file COPYING for more details.
  */
 
-/* see: Documentation/crc32.txt for a description of algorithms */
+/* see: Documentation/staging/crc32.rst for a description of algorithms */
 
 #include <linux/crc32.h>
 #include <linux/crc32poly.h>
diff --git a/lib/crc64.c b/lib/crc64.c
index f8928ce28280..47cfa054827f 100644
--- a/lib/crc64.c
+++ b/lib/crc64.c
@@ -4,7 +4,7 @@
  *
  * This is a basic crc64 implementation following ECMA-182 specification,
  * which can be found from,
- * http://www.ecma-international.org/publications/standards/Ecma-182.htm
+ * https://www.ecma-international.org/publications/standards/Ecma-182.htm
  *
  * Dr. Ross N. Williams has a great document to introduce the idea of CRC
  * algorithm, here the CRC64 code is also inspired by the table-driven
diff --git a/lib/crypto/chacha.c b/lib/crypto/chacha.c
index 65ead6b0c7e0..4ccbec442469 100644
--- a/lib/crypto/chacha.c
+++ b/lib/crypto/chacha.c
@@ -10,7 +10,6 @@
 #include <linux/export.h>
 #include <linux/bitops.h>
 #include <linux/string.h>
-#include <linux/cryptohash.h>
 #include <asm/unaligned.h>
 #include <crypto/chacha.h>
 
diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c
index ad0699ce702f..431e04280332 100644
--- a/lib/crypto/chacha20poly1305.c
+++ b/lib/crypto/chacha20poly1305.c
@@ -21,8 +21,6 @@
 
 #define CHACHA_KEY_WORDS	(CHACHA_KEY_SIZE / sizeof(u32))
 
-bool __init chacha20poly1305_selftest(void);
-
 static void chacha_load_key(u32 *k, const u8 *in)
 {
 	k[0] = get_unaligned_le32(in);
diff --git a/lib/crypto/sha256.c b/lib/crypto/sha256.c
index 66cb04b0cf4e..2321f6cb322f 100644
--- a/lib/crypto/sha256.c
+++ b/lib/crypto/sha256.c
@@ -206,7 +206,7 @@ static void sha256_transform(u32 *state, const u8 *input)
 	memzero_explicit(W, 64 * sizeof(u32));
 }
 
-int sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
+void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
 {
 	unsigned int partial, done;
 	const u8 *src;
@@ -232,18 +232,16 @@ int sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
 		partial = 0;
 	}
 	memcpy(sctx->buf + partial, src, len - done);
-
-	return 0;
 }
 EXPORT_SYMBOL(sha256_update);
 
-int sha224_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
+void sha224_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
 {
-	return sha256_update(sctx, data, len);
+	sha256_update(sctx, data, len);
 }
 EXPORT_SYMBOL(sha224_update);
 
-static int __sha256_final(struct sha256_state *sctx, u8 *out, int digest_words)
+static void __sha256_final(struct sha256_state *sctx, u8 *out, int digest_words)
 {
 	__be32 *dst = (__be32 *)out;
 	__be64 bits;
@@ -268,20 +266,28 @@ static int __sha256_final(struct sha256_state *sctx, u8 *out, int digest_words)
 
 	/* Zeroize sensitive information. */
 	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
 }
 
-int sha256_final(struct sha256_state *sctx, u8 *out)
+void sha256_final(struct sha256_state *sctx, u8 *out)
 {
-	return __sha256_final(sctx, out, 8);
+	__sha256_final(sctx, out, 8);
 }
 EXPORT_SYMBOL(sha256_final);
 
-int sha224_final(struct sha256_state *sctx, u8 *out)
+void sha224_final(struct sha256_state *sctx, u8 *out)
 {
-	return __sha256_final(sctx, out, 7);
+	__sha256_final(sctx, out, 7);
 }
 EXPORT_SYMBOL(sha224_final);
 
+void sha256(const u8 *data, unsigned int len, u8 *out)
+{
+	struct sha256_state sctx;
+
+	sha256_init(&sctx);
+	sha256_update(&sctx, data, len);
+	sha256_final(&sctx, out);
+}
+EXPORT_SYMBOL(sha256);
+
 MODULE_LICENSE("GPL");
diff --git a/lib/debug_locks.c b/lib/debug_locks.c
index a75ee30b77cb..06d3135bd184 100644
--- a/lib/debug_locks.c
+++ b/lib/debug_locks.c
@@ -36,7 +36,7 @@ EXPORT_SYMBOL_GPL(debug_locks_silent);
 /*
  * Generic 'turn off all lock debugging' function:
  */
-int debug_locks_off(void)
+noinstr int debug_locks_off(void)
 {
 	if (debug_locks && __debug_locks_off()) {
 		if (!debug_locks_silent) {
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 48054dbf1b51..fe4557955d97 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -1022,18 +1022,7 @@ static int debug_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, "objs_freed    :%d\n", debug_objects_freed);
 	return 0;
 }
-
-static int debug_stats_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, debug_stats_show, NULL);
-}
-
-static const struct file_operations debug_stats_fops = {
-	.open		= debug_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(debug_stats);
 
 static int __init debug_objects_init_debugfs(void)
 {
diff --git a/lib/decompress.c b/lib/decompress.c
index 857ab1af1ef3..ab3fc90ffc64 100644
--- a/lib/decompress.c
+++ b/lib/decompress.c
@@ -13,6 +13,7 @@
 #include <linux/decompress/inflate.h>
 #include <linux/decompress/unlzo.h>
 #include <linux/decompress/unlz4.h>
+#include <linux/decompress/unzstd.h>
 
 #include <linux/types.h>
 #include <linux/string.h>
@@ -37,6 +38,9 @@
 #ifndef CONFIG_DECOMPRESS_LZ4
 # define unlz4 NULL
 #endif
+#ifndef CONFIG_DECOMPRESS_ZSTD
+# define unzstd NULL
+#endif
 
 struct compress_format {
 	unsigned char magic[2];
@@ -52,6 +56,7 @@ static const struct compress_format compressed_formats[] __initconst = {
 	{ {0xfd, 0x37}, "xz", unxz },
 	{ {0x89, 0x4c}, "lzo", unlzo },
 	{ {0x02, 0x21}, "lz4", unlz4 },
+	{ {0x28, 0xb5}, "zstd", unzstd },
 	{ {0, 0}, NULL, NULL }
 };
 
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 7c4932eed748..f9628f3924ce 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -34,7 +34,7 @@
 		Phone (337) 232-1234 or 1-800-738-2226
 		Fax   (337) 232-1297
 
-		http://www.hospiceacadiana.com/
+		https://www.hospiceacadiana.com/
 
 	Manuel
  */
diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c
index ed7a1fd819f2..1cf409ef8d04 100644
--- a/lib/decompress_unlzma.c
+++ b/lib/decompress_unlzma.c
@@ -8,7 +8,7 @@
  *implementation for lzma.
  *Copyright (C) 2006  Aurelien Jacobs < aurel@gnuage.org >
  *
- *Based on LzmaDecode.c from the LZMA SDK 4.22 (http://www.7-zip.org/)
+ *Based on LzmaDecode.c from the LZMA SDK 4.22 (https://www.7-zip.org/)
  *Copyright (C) 1999-2005  Igor Pavlov
  *
  *Copyrights of the parts, see headers below.
@@ -56,7 +56,7 @@ static long long INIT read_int(unsigned char *ptr, int size)
 /* Small range coder implementation for lzma.
  *Copyright (C) 2006  Aurelien Jacobs < aurel@gnuage.org >
  *
- *Based on LzmaDecode.c from the LZMA SDK 4.22 (http://www.7-zip.org/)
+ *Based on LzmaDecode.c from the LZMA SDK 4.22 (https://www.7-zip.org/)
  *Copyright (c) 1999-2005  Igor Pavlov
  */
 
@@ -213,7 +213,7 @@ rc_bit_tree_decode(struct rc *rc, uint16_t *p, int num_levels, int *symbol)
  * Small lzma deflate implementation.
  * Copyright (C) 2006  Aurelien Jacobs < aurel@gnuage.org >
  *
- * Based on LzmaDecode.c from the LZMA SDK 4.22 (http://www.7-zip.org/)
+ * Based on LzmaDecode.c from the LZMA SDK 4.22 (https://www.7-zip.org/)
  * Copyright (C) 1999-2005  Igor Pavlov
  */
 
diff --git a/lib/decompress_unzstd.c b/lib/decompress_unzstd.c
new file mode 100644
index 000000000000..0ad2c15479ed
--- /dev/null
+++ b/lib/decompress_unzstd.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Important notes about in-place decompression
+ *
+ * At least on x86, the kernel is decompressed in place: the compressed data
+ * is placed to the end of the output buffer, and the decompressor overwrites
+ * most of the compressed data. There must be enough safety margin to
+ * guarantee that the write position is always behind the read position.
+ *
+ * The safety margin for ZSTD with a 128 KB block size is calculated below.
+ * Note that the margin with ZSTD is bigger than with GZIP or XZ!
+ *
+ * The worst case for in-place decompression is that the beginning of
+ * the file is compressed extremely well, and the rest of the file is
+ * uncompressible. Thus, we must look for worst-case expansion when the
+ * compressor is encoding uncompressible data.
+ *
+ * The structure of the .zst file in case of a compresed kernel is as follows.
+ * Maximum sizes (as bytes) of the fields are in parenthesis.
+ *
+ *    Frame Header: (18)
+ *    Blocks: (N)
+ *    Checksum: (4)
+ *
+ * The frame header and checksum overhead is at most 22 bytes.
+ *
+ * ZSTD stores the data in blocks. Each block has a header whose size is
+ * a 3 bytes. After the block header, there is up to 128 KB of payload.
+ * The maximum uncompressed size of the payload is 128 KB. The minimum
+ * uncompressed size of the payload is never less than the payload size
+ * (excluding the block header).
+ *
+ * The assumption, that the uncompressed size of the payload is never
+ * smaller than the payload itself, is valid only when talking about
+ * the payload as a whole. It is possible that the payload has parts where
+ * the decompressor consumes more input than it produces output. Calculating
+ * the worst case for this would be tricky. Instead of trying to do that,
+ * let's simply make sure that the decompressor never overwrites any bytes
+ * of the payload which it is currently reading.
+ *
+ * Now we have enough information to calculate the safety margin. We need
+ *   - 22 bytes for the .zst file format headers;
+ *   - 3 bytes per every 128 KiB of uncompressed size (one block header per
+ *     block); and
+ *   - 128 KiB (biggest possible zstd block size) to make sure that the
+ *     decompressor never overwrites anything from the block it is currently
+ *     reading.
+ *
+ * We get the following formula:
+ *
+ *    safety_margin = 22 + uncompressed_size * 3 / 131072 + 131072
+ *                 <= 22 + (uncompressed_size >> 15) + 131072
+ */
+
+/*
+ * Preboot environments #include "path/to/decompress_unzstd.c".
+ * All of the source files we depend on must be #included.
+ * zstd's only source dependeny is xxhash, which has no source
+ * dependencies.
+ *
+ * When UNZSTD_PREBOOT is defined we declare __decompress(), which is
+ * used for kernel decompression, instead of unzstd().
+ *
+ * Define __DISABLE_EXPORTS in preboot environments to prevent symbols
+ * from xxhash and zstd from being exported by the EXPORT_SYMBOL macro.
+ */
+#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"
+#endif
+
+#include <linux/decompress/mm.h>
+#include <linux/kernel.h>
+#include <linux/zstd.h>
+
+/* 128MB is the maximum window size supported by zstd. */
+#define ZSTD_WINDOWSIZE_MAX	(1 << ZSTD_WINDOWLOG_MAX)
+/*
+ * Size of the input and output buffers in multi-call mode.
+ * Pick a larger size because it isn't used during kernel decompression,
+ * since that is single pass, and we have to allocate a large buffer for
+ * zstd's window anyway. The larger size speeds up initramfs decompression.
+ */
+#define ZSTD_IOBUF_SIZE		(1 << 17)
+
+static int INIT handle_zstd_error(size_t ret, void (*error)(char *x))
+{
+	const int err = ZSTD_getErrorCode(ret);
+
+	if (!ZSTD_isError(ret))
+		return 0;
+
+	switch (err) {
+	case ZSTD_error_memory_allocation:
+		error("ZSTD decompressor ran out of memory");
+		break;
+	case ZSTD_error_prefix_unknown:
+		error("Input is not in the ZSTD format (wrong magic bytes)");
+		break;
+	case ZSTD_error_dstSize_tooSmall:
+	case ZSTD_error_corruption_detected:
+	case ZSTD_error_checksum_wrong:
+		error("ZSTD-compressed data is corrupt");
+		break;
+	default:
+		error("ZSTD-compressed data is probably corrupt");
+		break;
+	}
+	return -1;
+}
+
+/*
+ * Handle the case where we have the entire input and output in one segment.
+ * We can allocate less memory (no circular buffer for the sliding window),
+ * and avoid some memcpy() calls.
+ */
+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();
+	void *wksp = large_malloc(wksp_size);
+	ZSTD_DCtx *dctx = ZSTD_initDCtx(wksp, wksp_size);
+	int err;
+	size_t ret;
+
+	if (dctx == NULL) {
+		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.
+	 */
+	ret = ZSTD_findFrameCompressedSize(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);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+
+	if (in_pos != NULL)
+		*in_pos = in_len;
+
+	err = 0;
+out:
+	if (wksp != NULL)
+		large_free(wksp);
+	return err;
+}
+
+static int INIT __unzstd(unsigned char *in_buf, long in_len,
+			 long (*fill)(void*, unsigned long),
+			 long (*flush)(void*, unsigned long),
+			 unsigned char *out_buf, long out_len,
+			 long *in_pos,
+			 void (*error)(char *x))
+{
+	ZSTD_inBuffer in;
+	ZSTD_outBuffer out;
+	ZSTD_frameParams params;
+	void *in_allocated = NULL;
+	void *out_allocated = NULL;
+	void *wksp = NULL;
+	size_t wksp_size;
+	ZSTD_DStream *dstream;
+	int err;
+	size_t ret;
+
+	if (out_len == 0)
+		out_len = LONG_MAX; /* no limit */
+
+	if (fill == NULL && flush == NULL)
+		/*
+		 * We can decompress faster and with less memory when we have a
+		 * single chunk.
+		 */
+		return decompress_single(in_buf, in_len, out_buf, out_len,
+					 in_pos, error);
+
+	/*
+	 * If in_buf is not provided, we must be using fill(), so allocate
+	 * a large enough buffer. If it is provided, it must be at least
+	 * ZSTD_IOBUF_SIZE large.
+	 */
+	if (in_buf == NULL) {
+		in_allocated = large_malloc(ZSTD_IOBUF_SIZE);
+		if (in_allocated == NULL) {
+			error("Out of memory while allocating input buffer");
+			err = -1;
+			goto out;
+		}
+		in_buf = in_allocated;
+		in_len = 0;
+	}
+	/* Read the first chunk, since we need to decode the frame header. */
+	if (fill != NULL)
+		in_len = fill(in_buf, ZSTD_IOBUF_SIZE);
+	if (in_len < 0) {
+		error("ZSTD-compressed data is truncated");
+		err = -1;
+		goto out;
+	}
+	/* Set the first non-empty input buffer. */
+	in.src = in_buf;
+	in.pos = 0;
+	in.size = in_len;
+	/* Allocate the output buffer if we are using flush(). */
+	if (flush != NULL) {
+		out_allocated = large_malloc(ZSTD_IOBUF_SIZE);
+		if (out_allocated == NULL) {
+			error("Out of memory while allocating output buffer");
+			err = -1;
+			goto out;
+		}
+		out_buf = out_allocated;
+		out_len = ZSTD_IOBUF_SIZE;
+	}
+	/* Set the output buffer. */
+	out.dst = out_buf;
+	out.pos = 0;
+	out.size = out_len;
+
+	/*
+	 * 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);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+	if (ret != 0) {
+		error("ZSTD-compressed data has an incomplete frame header");
+		err = -1;
+		goto out;
+	}
+	if (params.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
+	 * required.
+	 */
+	wksp_size = ZSTD_DStreamWorkspaceBound(params.windowSize);
+	wksp = large_malloc(wksp_size);
+	dstream = ZSTD_initDStream(params.windowSize, wksp, wksp_size);
+	if (dstream == NULL) {
+		error("Out of memory while allocating ZSTD_DStream");
+		err = -1;
+		goto out;
+	}
+
+	/*
+	 * Decompression loop:
+	 * Read more data if necessary (error if no more data can be read).
+	 * Call the decompression function, which returns 0 when finished.
+	 * Flush any data produced if using flush().
+	 */
+	if (in_pos != NULL)
+		*in_pos = 0;
+	do {
+		/*
+		 * If we need to reload data, either we have fill() and can
+		 * try to get more data, or we don't and the input is truncated.
+		 */
+		if (in.pos == in.size) {
+			if (in_pos != NULL)
+				*in_pos += in.pos;
+			in_len = fill ? fill(in_buf, ZSTD_IOBUF_SIZE) : -1;
+			if (in_len < 0) {
+				error("ZSTD-compressed data is truncated");
+				err = -1;
+				goto out;
+			}
+			in.pos = 0;
+			in.size = in_len;
+		}
+		/* Returns zero when the frame is complete. */
+		ret = ZSTD_decompressStream(dstream, &out, &in);
+		err = handle_zstd_error(ret, error);
+		if (err)
+			goto out;
+		/* Flush all of the data produced if using flush(). */
+		if (flush != NULL && out.pos > 0) {
+			if (out.pos != flush(out.dst, out.pos)) {
+				error("Failed to flush()");
+				err = -1;
+				goto out;
+			}
+			out.pos = 0;
+		}
+	} while (ret != 0);
+
+	if (in_pos != NULL)
+		*in_pos += in.pos;
+
+	err = 0;
+out:
+	if (in_allocated != NULL)
+		large_free(in_allocated);
+	if (out_allocated != NULL)
+		large_free(out_allocated);
+	if (wksp != NULL)
+		large_free(wksp);
+	return err;
+}
+
+#ifndef UNZSTD_PREBOOT
+STATIC int INIT unzstd(unsigned char *buf, long len,
+		       long (*fill)(void*, unsigned long),
+		       long (*flush)(void*, unsigned long),
+		       unsigned char *out_buf,
+		       long *pos,
+		       void (*error)(char *x))
+{
+	return __unzstd(buf, len, fill, flush, out_buf, 0, pos, error);
+}
+#else
+STATIC int INIT __decompress(unsigned char *buf, long len,
+			     long (*fill)(void*, unsigned long),
+			     long (*flush)(void*, unsigned long),
+			     unsigned char *out_buf, long out_len,
+			     long *pos,
+			     void (*error)(char *x))
+{
+	return __unzstd(buf, len, fill, flush, out_buf, out_len, pos, error);
+}
+#endif
diff --git a/lib/devres.c b/lib/devres.c
index 6ef51f159c54..ebb1573d9ae3 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -119,6 +119,7 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res,
 {
 	resource_size_t size;
 	void __iomem *dest_ptr;
+	char *pretty_name;
 
 	BUG_ON(!dev);
 
@@ -129,7 +130,15 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res,
 
 	size = resource_size(res);
 
-	if (!devm_request_mem_region(dev, res->start, size, dev_name(dev))) {
+	if (res->name)
+		pretty_name = devm_kasprintf(dev, GFP_KERNEL, "%s %s",
+					     dev_name(dev), res->name);
+	else
+		pretty_name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL);
+	if (!pretty_name)
+		return IOMEM_ERR_PTR(-ENOMEM);
+
+	if (!devm_request_mem_region(dev, res->start, size, pretty_name)) {
 		dev_err(dev, "can't request region for resource %pR\n", res);
 		return IOMEM_ERR_PTR(-EBUSY);
 	}
@@ -204,6 +213,12 @@ void __iomem *devm_ioremap_resource_wc(struct device *dev,
  *	base = devm_of_iomap(&pdev->dev, node, 0, NULL);
  *	if (IS_ERR(base))
  *		return PTR_ERR(base);
+ *
+ * Please Note: This is not a one-to-one replacement for of_iomap() because the
+ * of_iomap() function does not track whether the region is already mapped.  If
+ * two drivers try to map the same memory, the of_iomap() function will succeed
+ * but the the devm_of_iomap() function will return -EBUSY.
+ *
  */
 void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index,
 			    resource_size_t *size)
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 33ffbf308853..a00ee6eedc7c 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -74,7 +74,7 @@ void show_regs_print_info(const char *log_lvl)
 static void __dump_stack(void)
 {
 	dump_stack_print_info(KERN_DEFAULT);
-	show_stack(NULL, NULL);
+	show_stack(NULL, NULL, KERN_DEFAULT);
 }
 
 /**
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 8f199f403ab5..2d4dfd44b0fa 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -11,7 +11,7 @@
  * Copyright (C) 2013 Du, Changbin <changbin.du@gmail.com>
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__
+#define pr_fmt(fmt) "dyndbg: " fmt
 
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -39,8 +39,8 @@
 
 #include <rdma/ib_verbs.h>
 
-extern struct _ddebug __start___verbose[];
-extern struct _ddebug __stop___verbose[];
+extern struct _ddebug __start___dyndbg[];
+extern struct _ddebug __stop___dyndbg[];
 
 struct ddebug_table {
 	struct list_head link;
@@ -62,6 +62,11 @@ struct ddebug_iter {
 	unsigned int idx;
 };
 
+struct flag_settings {
+	unsigned int flags;
+	unsigned int mask;
+};
+
 static DEFINE_MUTEX(ddebug_lock);
 static LIST_HEAD(ddebug_tables);
 static int verbose;
@@ -87,30 +92,33 @@ static struct { unsigned flag:8; char opt_char; } opt_array[] = {
 	{ _DPRINTK_FLAGS_NONE, '_' },
 };
 
+struct flagsbuf { char buf[ARRAY_SIZE(opt_array)+1]; };
+
 /* format a string into buf[] which describes the _ddebug's flags */
-static char *ddebug_describe_flags(struct _ddebug *dp, char *buf,
-				    size_t maxlen)
+static char *ddebug_describe_flags(unsigned int flags, struct flagsbuf *fb)
 {
-	char *p = buf;
+	char *p = fb->buf;
 	int i;
 
-	BUG_ON(maxlen < 6);
 	for (i = 0; i < ARRAY_SIZE(opt_array); ++i)
-		if (dp->flags & opt_array[i].flag)
+		if (flags & opt_array[i].flag)
 			*p++ = opt_array[i].opt_char;
-	if (p == buf)
+	if (p == fb->buf)
 		*p++ = '_';
 	*p = '\0';
 
-	return buf;
+	return fb->buf;
 }
 
-#define vpr_info(fmt, ...)					\
+#define vnpr_info(lvl, fmt, ...)				\
 do {								\
-	if (verbose)						\
+	if (verbose >= lvl)					\
 		pr_info(fmt, ##__VA_ARGS__);			\
 } while (0)
 
+#define vpr_info(fmt, ...)	vnpr_info(1, fmt, ##__VA_ARGS__)
+#define v2pr_info(fmt, ...)	vnpr_info(2, fmt, ##__VA_ARGS__)
+
 static void vpr_info_dq(const struct ddebug_query *query, const char *msg)
 {
 	/* trim any trailing newlines */
@@ -124,10 +132,10 @@ static void vpr_info_dq(const struct ddebug_query *query, const char *msg)
 
 	vpr_info("%s: func=\"%s\" file=\"%s\" module=\"%s\" format=\"%.*s\" lineno=%u-%u\n",
 		 msg,
-		 query->function ? query->function : "",
-		 query->filename ? query->filename : "",
-		 query->module ? query->module : "",
-		 fmtlen, query->format ? query->format : "",
+		 query->function ?: "",
+		 query->filename ?: "",
+		 query->module ?: "",
+		 fmtlen, query->format ?: "",
 		 query->first_lineno, query->last_lineno);
 }
 
@@ -138,13 +146,13 @@ static void vpr_info_dq(const struct ddebug_query *query, const char *msg)
  * logs the changes.  Takes ddebug_lock.
  */
 static int ddebug_change(const struct ddebug_query *query,
-			unsigned int flags, unsigned int mask)
+			 struct flag_settings *modifiers)
 {
 	int i;
 	struct ddebug_table *dt;
 	unsigned int newflags;
 	unsigned int nfound = 0;
-	char flagbuf[10];
+	struct flagsbuf fbuf;
 
 	/* search for matching ddebugs */
 	mutex_lock(&ddebug_lock);
@@ -173,9 +181,16 @@ static int ddebug_change(const struct ddebug_query *query,
 				continue;
 
 			/* match against the format */
-			if (query->format &&
-			    !strstr(dp->format, query->format))
-				continue;
+			if (query->format) {
+				if (*query->format == '^') {
+					char *p;
+					/* anchored search. match must be at beginning */
+					p = strstr(dp->format, query->format+1);
+					if (p != dp->format)
+						continue;
+				} else if (!strstr(dp->format, query->format))
+					continue;
+			}
 
 			/* match against the line number range */
 			if (query->first_lineno &&
@@ -187,22 +202,21 @@ static int ddebug_change(const struct ddebug_query *query,
 
 			nfound++;
 
-			newflags = (dp->flags & mask) | flags;
+			newflags = (dp->flags & modifiers->mask) | modifiers->flags;
 			if (newflags == dp->flags)
 				continue;
 #ifdef CONFIG_JUMP_LABEL
 			if (dp->flags & _DPRINTK_FLAGS_PRINT) {
-				if (!(flags & _DPRINTK_FLAGS_PRINT))
+				if (!(modifiers->flags & _DPRINTK_FLAGS_PRINT))
 					static_branch_disable(&dp->key.dd_key_true);
-			} else if (flags & _DPRINTK_FLAGS_PRINT)
+			} else if (modifiers->flags & _DPRINTK_FLAGS_PRINT)
 				static_branch_enable(&dp->key.dd_key_true);
 #endif
 			dp->flags = newflags;
-			vpr_info("changed %s:%d [%s]%s =%s\n",
+			v2pr_info("changed %s:%d [%s]%s =%s\n",
 				 trim_prefix(dp->filename), dp->lineno,
 				 dt->mod_name, dp->function,
-				 ddebug_describe_flags(dp, flagbuf,
-						       sizeof(flagbuf)));
+				 ddebug_describe_flags(dp->flags, &fbuf));
 		}
 	}
 	mutex_unlock(&ddebug_lock);
@@ -289,6 +303,41 @@ static inline int parse_lineno(const char *str, unsigned int *val)
 	return 0;
 }
 
+static int parse_linerange(struct ddebug_query *query, const char *first)
+{
+	char *last = strchr(first, '-');
+
+	if (query->first_lineno || query->last_lineno) {
+		pr_err("match-spec: line used 2x\n");
+		return -EINVAL;
+	}
+	if (last)
+		*last++ = '\0';
+	if (parse_lineno(first, &query->first_lineno) < 0)
+		return -EINVAL;
+	if (last) {
+		/* range <first>-<last> */
+		if (parse_lineno(last, &query->last_lineno) < 0)
+			return -EINVAL;
+
+		/* special case for last lineno not specified */
+		if (query->last_lineno == 0)
+			query->last_lineno = UINT_MAX;
+
+		if (query->last_lineno < query->first_lineno) {
+			pr_err("last-line:%d < 1st-line:%d\n",
+			       query->last_lineno,
+			       query->first_lineno);
+			return -EINVAL;
+		}
+	} else {
+		query->last_lineno = query->first_lineno;
+	}
+	vpr_info("parsed line %d-%d\n", query->first_lineno,
+		 query->last_lineno);
+	return 0;
+}
+
 static int check_set(const char **dest, char *src, char *name)
 {
 	int rc = 0;
@@ -322,13 +371,13 @@ static int ddebug_parse_query(char *words[], int nwords,
 {
 	unsigned int i;
 	int rc = 0;
+	char *fline;
 
 	/* check we have an even number of words */
 	if (nwords % 2 != 0) {
 		pr_err("expecting pairs of match-spec <value>\n");
 		return -EINVAL;
 	}
-	memset(query, 0, sizeof(*query));
 
 	if (modname)
 		/* support $modname.dyndbg=<multiple queries> */
@@ -338,7 +387,22 @@ static int ddebug_parse_query(char *words[], int nwords,
 		if (!strcmp(words[i], "func")) {
 			rc = check_set(&query->function, words[i+1], "func");
 		} else if (!strcmp(words[i], "file")) {
-			rc = check_set(&query->filename, words[i+1], "file");
+			if (check_set(&query->filename, words[i+1], "file"))
+				return -EINVAL;
+
+			/* tail :$info is function or line-range */
+			fline = strchr(query->filename, ':');
+			if (!fline)
+				break;
+			*fline++ = '\0';
+			if (isalpha(*fline) || *fline == '*' || *fline == '?') {
+				/* take as function name */
+				if (check_set(&query->function, fline, "func"))
+					return -EINVAL;
+			} else {
+				if (parse_linerange(query, fline))
+					return -EINVAL;
+			}
 		} else if (!strcmp(words[i], "module")) {
 			rc = check_set(&query->module, words[i+1], "module");
 		} else if (!strcmp(words[i], "format")) {
@@ -347,34 +411,8 @@ static int ddebug_parse_query(char *words[], int nwords,
 							    UNESCAPE_SPECIAL);
 			rc = check_set(&query->format, words[i+1], "format");
 		} else if (!strcmp(words[i], "line")) {
-			char *first = words[i+1];
-			char *last = strchr(first, '-');
-			if (query->first_lineno || query->last_lineno) {
-				pr_err("match-spec: line used 2x\n");
-				return -EINVAL;
-			}
-			if (last)
-				*last++ = '\0';
-			if (parse_lineno(first, &query->first_lineno) < 0)
+			if (parse_linerange(query, words[i+1]))
 				return -EINVAL;
-			if (last) {
-				/* range <first>-<last> */
-				if (parse_lineno(last, &query->last_lineno) < 0)
-					return -EINVAL;
-
-				/* special case for last lineno not specified */
-				if (query->last_lineno == 0)
-					query->last_lineno = UINT_MAX;
-
-				if (query->last_lineno < query->first_lineno) {
-					pr_err("last-line:%d < 1st-line:%d\n",
-						query->last_lineno,
-						query->first_lineno);
-					return -EINVAL;
-				}
-			} else {
-				query->last_lineno = query->first_lineno;
-			}
 		} else {
 			pr_err("unknown keyword \"%s\"\n", words[i]);
 			return -EINVAL;
@@ -392,11 +430,9 @@ static int ddebug_parse_query(char *words[], int nwords,
  * flags fields of matched _ddebug's.  Returns 0 on success
  * or <0 on error.
  */
-static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
-			       unsigned int *maskp)
+static int ddebug_parse_flags(const char *str, struct flag_settings *modifiers)
 {
-	unsigned flags = 0;
-	int op = '=', i;
+	int op, i;
 
 	switch (*str) {
 	case '+':
@@ -413,40 +449,40 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
 	for (; *str ; ++str) {
 		for (i = ARRAY_SIZE(opt_array) - 1; i >= 0; i--) {
 			if (*str == opt_array[i].opt_char) {
-				flags |= opt_array[i].flag;
+				modifiers->flags |= opt_array[i].flag;
 				break;
 			}
 		}
 		if (i < 0) {
-			pr_err("unknown flag '%c' in \"%s\"\n", *str, str);
+			pr_err("unknown flag '%c'\n", *str);
 			return -EINVAL;
 		}
 	}
-	vpr_info("flags=0x%x\n", flags);
+	vpr_info("flags=0x%x\n", modifiers->flags);
 
-	/* calculate final *flagsp, *maskp according to mask and op */
+	/* calculate final flags, mask based upon op */
 	switch (op) {
 	case '=':
-		*maskp = 0;
-		*flagsp = flags;
+		/* modifiers->flags already set */
+		modifiers->mask = 0;
 		break;
 	case '+':
-		*maskp = ~0U;
-		*flagsp = flags;
+		modifiers->mask = ~0U;
 		break;
 	case '-':
-		*maskp = ~flags;
-		*flagsp = 0;
+		modifiers->mask = ~modifiers->flags;
+		modifiers->flags = 0;
 		break;
 	}
-	vpr_info("*flagsp=0x%x *maskp=0x%x\n", *flagsp, *maskp);
+	vpr_info("*flagsp=0x%x *maskp=0x%x\n", modifiers->flags, modifiers->mask);
+
 	return 0;
 }
 
 static int ddebug_exec_query(char *query_string, const char *modname)
 {
-	unsigned int flags = 0, mask = 0;
-	struct ddebug_query query;
+	struct flag_settings modifiers = {};
+	struct ddebug_query query = {};
 #define MAXWORDS 9
 	int nwords, nfound;
 	char *words[MAXWORDS];
@@ -457,7 +493,7 @@ static int ddebug_exec_query(char *query_string, const char *modname)
 		return -EINVAL;
 	}
 	/* check flags 1st (last arg) so query is pairs of spec,val */
-	if (ddebug_parse_flags(words[nwords-1], &flags, &mask)) {
+	if (ddebug_parse_flags(words[nwords-1], &modifiers)) {
 		pr_err("flags parse failed\n");
 		return -EINVAL;
 	}
@@ -466,7 +502,7 @@ static int ddebug_exec_query(char *query_string, const char *modname)
 		return -EINVAL;
 	}
 	/* actually go and implement the change */
-	nfound = ddebug_change(&query, flags, mask);
+	nfound = ddebug_change(&query, &modifiers);
 	vpr_info_dq(&query, nfound ? "applied" : "no-match");
 
 	return nfound;
@@ -509,6 +545,30 @@ static int ddebug_exec_queries(char *query, const char *modname)
 	return nfound;
 }
 
+/**
+ * dynamic_debug_exec_queries - select and change dynamic-debug prints
+ * @query: query-string described in admin-guide/dynamic-debug-howto
+ * @modname: string containing module name, usually &module.mod_name
+ *
+ * This uses the >/proc/dynamic_debug/control reader, allowing module
+ * authors to modify their dynamic-debug callsites. The modname is
+ * canonically struct module.mod_name, but can also be null or a
+ * module-wildcard, for example: "drm*".
+ */
+int dynamic_debug_exec_queries(const char *query, const char *modname)
+{
+	int rc;
+	char *qry = kstrndup(query, PAGE_SIZE, GFP_KERNEL);
+
+	if (!query)
+		return -ENOMEM;
+
+	rc = ddebug_exec_queries(qry, modname);
+	kfree(qry);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(dynamic_debug_exec_queries);
+
 #define PREFIX_SIZE 64
 
 static int remaining(int wrote)
@@ -771,8 +831,6 @@ static void *ddebug_proc_start(struct seq_file *m, loff_t *pos)
 	struct _ddebug *dp;
 	int n = *pos;
 
-	vpr_info("called m=%p *pos=%lld\n", m, (unsigned long long)*pos);
-
 	mutex_lock(&ddebug_lock);
 
 	if (!n)
@@ -795,9 +853,6 @@ static void *ddebug_proc_next(struct seq_file *m, void *p, loff_t *pos)
 	struct ddebug_iter *iter = m->private;
 	struct _ddebug *dp;
 
-	vpr_info("called m=%p p=%p *pos=%lld\n",
-		 m, p, (unsigned long long)*pos);
-
 	if (p == SEQ_START_TOKEN)
 		dp = ddebug_iter_first(iter);
 	else
@@ -816,9 +871,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 {
 	struct ddebug_iter *iter = m->private;
 	struct _ddebug *dp = p;
-	char flagsbuf[10];
-
-	vpr_info("called m=%p p=%p\n", m, p);
+	struct flagsbuf flags;
 
 	if (p == SEQ_START_TOKEN) {
 		seq_puts(m,
@@ -829,7 +882,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 	seq_printf(m, "%s:%u [%s]%s =%s \"",
 		   trim_prefix(dp->filename), dp->lineno,
 		   iter->table->mod_name, dp->function,
-		   ddebug_describe_flags(dp, flagsbuf, sizeof(flagsbuf)));
+		   ddebug_describe_flags(dp->flags, &flags));
 	seq_escape(m, dp->format, "\t\r\n\"");
 	seq_puts(m, "\"\n");
 
@@ -842,7 +895,6 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
  */
 static void ddebug_proc_stop(struct seq_file *m, void *p)
 {
-	vpr_info("called m=%p p=%p\n", m, p);
 	mutex_unlock(&ddebug_lock);
 }
 
@@ -853,13 +905,6 @@ static const struct seq_operations ddebug_proc_seqops = {
 	.stop = ddebug_proc_stop
 };
 
-/*
- * File_ops->open method for <debugfs>/dynamic_debug/control.  Does
- * the seq_file setup dance, and also creates an iterator to walk the
- * _ddebugs.  Note that we create a seq_file always, even for O_WRONLY
- * files where it's not needed, as doing so simplifies the ->release
- * method.
- */
 static int ddebug_proc_open(struct inode *inode, struct file *file)
 {
 	vpr_info("called\n");
@@ -909,10 +954,10 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 	dt->ddebugs = tab;
 
 	mutex_lock(&ddebug_lock);
-	list_add_tail(&dt->link, &ddebug_tables);
+	list_add(&dt->link, &ddebug_tables);
 	mutex_unlock(&ddebug_lock);
 
-	vpr_info("%u debug prints in module %s\n", n, dt->mod_name);
+	v2pr_info("%3u debug prints in module %s\n", n, dt->mod_name);
 	return 0;
 }
 
@@ -971,7 +1016,7 @@ int ddebug_remove_module(const char *mod_name)
 	struct ddebug_table *dt, *nextdt;
 	int ret = -ENOENT;
 
-	vpr_info("removing module \"%s\"\n", mod_name);
+	v2pr_info("removing module \"%s\"\n", mod_name);
 
 	mutex_lock(&ddebug_lock);
 	list_for_each_entry_safe(dt, nextdt, &ddebug_tables, link) {
@@ -1029,20 +1074,21 @@ static int __init dynamic_debug_init(void)
 	char *cmdline;
 	int ret = 0;
 	int n = 0, entries = 0, modct = 0;
-	int verbose_bytes = 0;
 
-	if (&__start___verbose == &__stop___verbose) {
-		pr_warn("_ddebug table is empty in a CONFIG_DYNAMIC_DEBUG build\n");
-		return 1;
+	if (&__start___dyndbg == &__stop___dyndbg) {
+		if (IS_ENABLED(CONFIG_DYNAMIC_DEBUG)) {
+			pr_warn("_ddebug table is empty in a CONFIG_DYNAMIC_DEBUG build\n");
+			return 1;
+		}
+		pr_info("Ignore empty _ddebug table in a CONFIG_DYNAMIC_DEBUG_CORE build\n");
+		ddebug_init_success = 1;
+		return 0;
 	}
-	iter = __start___verbose;
+	iter = __start___dyndbg;
 	modname = iter->modname;
 	iter_start = iter;
-	for (; iter < __stop___verbose; iter++) {
+	for (; iter < __stop___dyndbg; iter++) {
 		entries++;
-		verbose_bytes += strlen(iter->modname) + strlen(iter->function)
-			+ strlen(iter->filename) + strlen(iter->format);
-
 		if (strcmp(modname, iter->modname)) {
 			modct++;
 			ret = ddebug_add_module(iter_start, n, modname);
@@ -1059,9 +1105,9 @@ static int __init dynamic_debug_init(void)
 		goto out_err;
 
 	ddebug_init_success = 1;
-	vpr_info("%d modules, %d entries and %d bytes in ddebug tables, %d bytes in (readonly) verbose section\n",
+	vpr_info("%d modules, %d entries and %d bytes in ddebug tables, %d bytes in __dyndbg section\n",
 		 modct, entries, (int)(modct * sizeof(struct ddebug_table)),
-		 verbose_bytes + (int)(__stop___verbose - __start___verbose));
+		 (int)(entries * sizeof(struct _ddebug)));
 
 	/* apply ddebug_query boot param, dont unload tables on err */
 	if (ddebug_setup_string[0] != '\0') {
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index 8186ca84910b..ce12621b4275 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -106,7 +106,9 @@ bool should_fail(struct fault_attr *attr, ssize_t size)
 		unsigned int fail_nth = READ_ONCE(current->fail_nth);
 
 		if (fail_nth) {
-			if (!WRITE_ONCE(current->fail_nth, fail_nth - 1))
+			fail_nth--;
+			WRITE_ONCE(current->fail_nth, fail_nth);
+			if (!fail_nth)
 				goto fail;
 
 			return false;
diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c
index 7852bfff50b1..451543937524 100644
--- a/lib/flex_proportions.c
+++ b/lib/flex_proportions.c
@@ -266,8 +266,7 @@ void __fprop_inc_percpu_max(struct fprop_global *p,
 		if (numerator >
 		    (((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT)
 			return;
-	} else
-		fprop_reflect_period_percpu(p, pl);
-	percpu_counter_add_batch(&pl->events, 1, PROP_BATCH);
-	percpu_counter_add(&p->events, 1);
+	}
+
+	__fprop_inc_percpu(p, pl);
 }
diff --git a/lib/fonts/font_10x18.c b/lib/fonts/font_10x18.c
index 532f0ff89a96..0e2deac97da0 100644
--- a/lib/fonts/font_10x18.c
+++ b/lib/fonts/font_10x18.c
@@ -8,8 +8,8 @@
 
 #define FONTDATAMAX 9216
 
-static const unsigned char fontdata_10x18[FONTDATAMAX] = {
-
+static struct font_data fontdata_10x18 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, 0x00, /* 0000000000 */
 	0x00, 0x00, /* 0000000000 */
@@ -5129,8 +5129,7 @@ static const unsigned char fontdata_10x18[FONTDATAMAX] = {
 	0x00, 0x00, /* 0000000000 */
 	0x00, 0x00, /* 0000000000 */
 	0x00, 0x00, /* 0000000000 */
-
-};
+} };
 
 
 const struct font_desc font_10x18 = {
@@ -5138,7 +5137,7 @@ const struct font_desc font_10x18 = {
 	.name	= "10x18",
 	.width	= 10,
 	.height	= 18,
-	.data	= fontdata_10x18,
+	.data	= fontdata_10x18.data,
 #ifdef __sparc__
 	.pref	= 5,
 #else
diff --git a/lib/fonts/font_6x10.c b/lib/fonts/font_6x10.c
index 09b2cc03435b..87da8acd07db 100644
--- a/lib/fonts/font_6x10.c
+++ b/lib/fonts/font_6x10.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/font.h>
 
-static const unsigned char fontdata_6x10[] = {
+#define FONTDATAMAX 2560
 
+static struct font_data fontdata_6x10 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
@@ -3074,14 +3076,13 @@ static const unsigned char fontdata_6x10[] = {
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
-
-};
+} };
 
 const struct font_desc font_6x10 = {
 	.idx	= FONT6x10_IDX,
 	.name	= "6x10",
 	.width	= 6,
 	.height	= 10,
-	.data	= fontdata_6x10,
+	.data	= fontdata_6x10.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_6x11.c b/lib/fonts/font_6x11.c
index d7136c33f1f0..5e975dfa10a5 100644
--- a/lib/fonts/font_6x11.c
+++ b/lib/fonts/font_6x11.c
@@ -9,8 +9,8 @@
 
 #define FONTDATAMAX (11*256)
 
-static const unsigned char fontdata_6x11[FONTDATAMAX] = {
-
+static struct font_data fontdata_6x11 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
@@ -3338,8 +3338,7 @@ static const unsigned char fontdata_6x11[FONTDATAMAX] = {
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
-
-};
+} };
 
 
 const struct font_desc font_vga_6x11 = {
@@ -3347,7 +3346,7 @@ const struct font_desc font_vga_6x11 = {
 	.name	= "ProFont6x11",
 	.width	= 6,
 	.height	= 11,
-	.data	= fontdata_6x11,
+	.data	= fontdata_6x11.data,
 	/* Try avoiding this font if possible unless on MAC */
 	.pref	= -2000,
 };
diff --git a/lib/fonts/font_7x14.c b/lib/fonts/font_7x14.c
index 89752d0b23e8..86d298f38505 100644
--- a/lib/fonts/font_7x14.c
+++ b/lib/fonts/font_7x14.c
@@ -8,8 +8,8 @@
 
 #define FONTDATAMAX 3584
 
-static const unsigned char fontdata_7x14[FONTDATAMAX] = {
-
+static struct font_data fontdata_7x14 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 0000000 */
 	0x00, /* 0000000 */
@@ -4105,8 +4105,7 @@ static const unsigned char fontdata_7x14[FONTDATAMAX] = {
 	0x00, /* 0000000 */
 	0x00, /* 0000000 */
 	0x00, /* 0000000 */
-
-};
+} };
 
 
 const struct font_desc font_7x14 = {
@@ -4114,6 +4113,6 @@ const struct font_desc font_7x14 = {
 	.name	= "7x14",
 	.width	= 7,
 	.height	= 14,
-	.data	= fontdata_7x14,
+	.data	= fontdata_7x14.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_8x16.c b/lib/fonts/font_8x16.c
index b7ab1f5fbdb8..37cedd36ca5e 100644
--- a/lib/fonts/font_8x16.c
+++ b/lib/fonts/font_8x16.c
@@ -10,8 +10,8 @@
 
 #define FONTDATAMAX 4096
 
-static const unsigned char fontdata_8x16[FONTDATAMAX] = {
-
+static struct font_data fontdata_8x16 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
@@ -4619,8 +4619,7 @@ static const unsigned char fontdata_8x16[FONTDATAMAX] = {
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
-
-};
+} };
 
 
 const struct font_desc font_vga_8x16 = {
@@ -4628,7 +4627,7 @@ const struct font_desc font_vga_8x16 = {
 	.name	= "VGA8x16",
 	.width	= 8,
 	.height	= 16,
-	.data	= fontdata_8x16,
+	.data	= fontdata_8x16.data,
 	.pref	= 0,
 };
 EXPORT_SYMBOL(font_vga_8x16);
diff --git a/lib/fonts/font_8x8.c b/lib/fonts/font_8x8.c
index 2328ebc8bab5..8ab695538395 100644
--- a/lib/fonts/font_8x8.c
+++ b/lib/fonts/font_8x8.c
@@ -9,8 +9,8 @@
 
 #define FONTDATAMAX 2048
 
-static const unsigned char fontdata_8x8[FONTDATAMAX] = {
-
+static struct font_data fontdata_8x8 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
@@ -2570,8 +2570,7 @@ static const unsigned char fontdata_8x8[FONTDATAMAX] = {
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
 	0x00, /* 00000000 */
-
-};
+} };
 
 
 const struct font_desc font_vga_8x8 = {
@@ -2579,6 +2578,6 @@ const struct font_desc font_vga_8x8 = {
 	.name	= "VGA8x8",
 	.width	= 8,
 	.height	= 8,
-	.data	= fontdata_8x8,
+	.data	= fontdata_8x8.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_acorn_8x8.c b/lib/fonts/font_acorn_8x8.c
index 0ff0e85d4481..069b3e80c434 100644
--- a/lib/fonts/font_acorn_8x8.c
+++ b/lib/fonts/font_acorn_8x8.c
@@ -3,7 +3,10 @@
 
 #include <linux/font.h>
 
-static const unsigned char acorndata_8x8[] = {
+#define FONTDATAMAX 2048
+
+static struct font_data acorndata_8x8 = {
+{ 0, 0, FONTDATAMAX, 0 }, {
 /* 00 */  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* ^@ */
 /* 01 */  0x7e, 0x81, 0xa5, 0x81, 0xbd, 0x99, 0x81, 0x7e, /* ^A */
 /* 02 */  0x7e, 0xff, 0xbd, 0xff, 0xc3, 0xe7, 0xff, 0x7e, /* ^B */
@@ -260,14 +263,14 @@ static const unsigned char acorndata_8x8[] = {
 /* FD */  0x38, 0x04, 0x18, 0x20, 0x3c, 0x00, 0x00, 0x00,
 /* FE */  0x00, 0x00, 0x3c, 0x3c, 0x3c, 0x3c, 0x00, 0x00,
 /* FF */  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
-};
+} };
 
 const struct font_desc font_acorn_8x8 = {
 	.idx	= ACORN8x8_IDX,
 	.name	= "Acorn8x8",
 	.width	= 8,
 	.height	= 8,
-	.data	= acorndata_8x8,
+	.data	= acorndata_8x8.data,
 #ifdef CONFIG_ARCH_ACORN
 	.pref	= 20,
 #else
diff --git a/lib/fonts/font_mini_4x6.c b/lib/fonts/font_mini_4x6.c
index 838caa1cfef7..1449876c6a27 100644
--- a/lib/fonts/font_mini_4x6.c
+++ b/lib/fonts/font_mini_4x6.c
@@ -43,8 +43,8 @@ __END__;
 
 #define FONTDATAMAX 1536
 
-static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = {
-
+static struct font_data fontdata_mini_4x6 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/*{*/
 	  	/*   Char 0: ' '  */
 	0xee,	/*=  [*** ]       */
@@ -2145,14 +2145,14 @@ static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = {
 	0xee,	/*=   [*** ]        */
 	0x00,	/*=   [    ]        */
 	/*}*/
-};
+} };
 
 const struct font_desc font_mini_4x6 = {
 	.idx	= MINI4x6_IDX,
 	.name	= "MINI4x6",
 	.width	= 4,
 	.height	= 6,
-	.data	= fontdata_mini_4x6,
+	.data	= fontdata_mini_4x6.data,
 	.pref	= 3,
 };
 
diff --git a/lib/fonts/font_pearl_8x8.c b/lib/fonts/font_pearl_8x8.c
index b15d3c342c5b..32d65551e7ed 100644
--- a/lib/fonts/font_pearl_8x8.c
+++ b/lib/fonts/font_pearl_8x8.c
@@ -14,8 +14,8 @@
 
 #define FONTDATAMAX 2048
 
-static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = {
-
+static struct font_data fontdata_pearl8x8 = {
+   { 0, 0, FONTDATAMAX, 0 }, {
    /* 0 0x00 '^@' */
    0x00, /* 00000000 */
    0x00, /* 00000000 */
@@ -2575,14 +2575,13 @@ static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = {
    0x00, /* 00000000 */
    0x00, /* 00000000 */
    0x00, /* 00000000 */
-
-};
+} };
 
 const struct font_desc font_pearl_8x8 = {
 	.idx	= PEARL8x8_IDX,
 	.name	= "PEARL8x8",
 	.width	= 8,
 	.height	= 8,
-	.data	= fontdata_pearl8x8,
+	.data	= fontdata_pearl8x8.data,
 	.pref	= 2,
 };
diff --git a/lib/fonts/font_sun12x22.c b/lib/fonts/font_sun12x22.c
index 955d6eee3959..641a6b4dca42 100644
--- a/lib/fonts/font_sun12x22.c
+++ b/lib/fonts/font_sun12x22.c
@@ -3,8 +3,8 @@
 
 #define FONTDATAMAX 11264
 
-static const unsigned char fontdata_sun12x22[FONTDATAMAX] = {
-
+static struct font_data fontdata_sun12x22 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, 0x00, /* 000000000000 */
 	0x00, 0x00, /* 000000000000 */
@@ -6148,8 +6148,7 @@ static const unsigned char fontdata_sun12x22[FONTDATAMAX] = {
 	0x00, 0x00, /* 000000000000 */
 	0x00, 0x00, /* 000000000000 */
 	0x00, 0x00, /* 000000000000 */
-
-};
+} };
 
 
 const struct font_desc font_sun_12x22 = {
@@ -6157,7 +6156,7 @@ const struct font_desc font_sun_12x22 = {
 	.name	= "SUN12x22",
 	.width	= 12,
 	.height	= 22,
-	.data	= fontdata_sun12x22,
+	.data	= fontdata_sun12x22.data,
 #ifdef __sparc__
 	.pref	= 5,
 #else
diff --git a/lib/fonts/font_sun8x16.c b/lib/fonts/font_sun8x16.c
index 03d71e53954a..193fe6d988e0 100644
--- a/lib/fonts/font_sun8x16.c
+++ b/lib/fonts/font_sun8x16.c
@@ -3,7 +3,8 @@
 
 #define FONTDATAMAX 4096
 
-static const unsigned char fontdata_sun8x16[FONTDATAMAX] = {
+static struct font_data fontdata_sun8x16 = {
+{ 0, 0, FONTDATAMAX, 0 }, {
 /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 /* */ 0x00,0x00,0x7e,0x81,0xa5,0x81,0x81,0xbd,0x99,0x81,0x81,0x7e,0x00,0x00,0x00,0x00,
 /* */ 0x00,0x00,0x7e,0xff,0xdb,0xff,0xff,0xc3,0xe7,0xff,0xff,0x7e,0x00,0x00,0x00,0x00,
@@ -260,14 +261,14 @@ static const unsigned char fontdata_sun8x16[FONTDATAMAX] = {
 /* */ 0x00,0x70,0xd8,0x30,0x60,0xc8,0xf8,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 /* */ 0x00,0x00,0x00,0x00,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x00,0x00,0x00,0x00,0x00,
 /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
-};
+} };
 
 const struct font_desc font_sun_8x16 = {
 	.idx	= SUN8x16_IDX,
 	.name	= "SUN8x16",
 	.width	= 8,
 	.height	= 16,
-	.data	= fontdata_sun8x16,
+	.data	= fontdata_sun8x16.data,
 #ifdef __sparc__
 	.pref	= 10,
 #else
diff --git a/lib/fonts/font_ter16x32.c b/lib/fonts/font_ter16x32.c
index 3f0cf1ccdf3a..91b9c283bd9c 100644
--- a/lib/fonts/font_ter16x32.c
+++ b/lib/fonts/font_ter16x32.c
@@ -4,8 +4,8 @@
 
 #define FONTDATAMAX 16384
 
-static const unsigned char fontdata_ter16x32[FONTDATAMAX] = {
-
+static struct font_data fontdata_ter16x32 = {
+	{ 0, 0, FONTDATAMAX, 0 }, {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x7f, 0xfc, 0x7f, 0xfc,
 	0x70, 0x1c, 0x70, 0x1c, 0x70, 0x1c, 0x70, 0x1c,
@@ -2054,8 +2054,7 @@ static const unsigned char fontdata_ter16x32[FONTDATAMAX] = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 255 */
-
-};
+} };
 
 
 const struct font_desc font_ter_16x32 = {
@@ -2063,7 +2062,7 @@ const struct font_desc font_ter_16x32 = {
 	.name	= "TER16x32",
 	.width	= 16,
 	.height = 32,
-	.data	= fontdata_ter16x32,
+	.data	= fontdata_ter16x32.data,
 #ifdef __sparc__
 	.pref	= 5,
 #else
diff --git a/lib/glob.c b/lib/glob.c
index 0ba3ea86b546..52e3ed7e4a9b 100644
--- a/lib/glob.c
+++ b/lib/glob.c
@@ -102,7 +102,7 @@ bool __pure glob_match(char const *pat, char const *str)
 			break;
 		case '\\':
 			d = *pat++;
-			/*FALLTHROUGH*/
+			/* fall through */
 		default:	/* Literal character */
 literal:
 			if (c == d) {
diff --git a/lib/iomap.c b/lib/iomap.c
index e909ab71e995..fbaa3e8f19d6 100644
--- a/lib/iomap.c
+++ b/lib/iomap.c
@@ -70,27 +70,27 @@ static void bad_io_access(unsigned long port, const char *access)
 #define mmio_read64be(addr) swab64(readq(addr))
 #endif
 
-unsigned int ioread8(void __iomem *addr)
+unsigned int ioread8(const void __iomem *addr)
 {
 	IO_COND(addr, return inb(port), return readb(addr));
 	return 0xff;
 }
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	IO_COND(addr, return inw(port), return readw(addr));
 	return 0xffff;
 }
-unsigned int ioread16be(void __iomem *addr)
+unsigned int ioread16be(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read16be(port), return mmio_read16be(addr));
 	return 0xffff;
 }
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	IO_COND(addr, return inl(port), return readl(addr));
 	return 0xffffffff;
 }
-unsigned int ioread32be(void __iomem *addr)
+unsigned int ioread32be(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read32be(port), return mmio_read32be(addr));
 	return 0xffffffff;
@@ -142,26 +142,26 @@ static u64 pio_read64be_hi_lo(unsigned long port)
 	return lo | (hi << 32);
 }
 
-u64 ioread64_lo_hi(void __iomem *addr)
+u64 ioread64_lo_hi(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64_lo_hi(port), return readq(addr));
 	return 0xffffffffffffffffULL;
 }
 
-u64 ioread64_hi_lo(void __iomem *addr)
+u64 ioread64_hi_lo(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64_hi_lo(port), return readq(addr));
 	return 0xffffffffffffffffULL;
 }
 
-u64 ioread64be_lo_hi(void __iomem *addr)
+u64 ioread64be_lo_hi(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64be_lo_hi(port),
 		return mmio_read64be(addr));
 	return 0xffffffffffffffffULL;
 }
 
-u64 ioread64be_hi_lo(void __iomem *addr)
+u64 ioread64be_hi_lo(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64be_hi_lo(port),
 		return mmio_read64be(addr));
@@ -275,7 +275,7 @@ EXPORT_SYMBOL(iowrite64be_hi_lo);
  * order" (we also don't have IO barriers).
  */
 #ifndef mmio_insb
-static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
+static inline void mmio_insb(const void __iomem *addr, u8 *dst, int count)
 {
 	while (--count >= 0) {
 		u8 data = __raw_readb(addr);
@@ -283,7 +283,7 @@ static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
 		dst++;
 	}
 }
-static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
+static inline void mmio_insw(const void __iomem *addr, u16 *dst, int count)
 {
 	while (--count >= 0) {
 		u16 data = __raw_readw(addr);
@@ -291,7 +291,7 @@ static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
 		dst++;
 	}
 }
-static inline void mmio_insl(void __iomem *addr, u32 *dst, int count)
+static inline void mmio_insl(const void __iomem *addr, u32 *dst, int count)
 {
 	while (--count >= 0) {
 		u32 data = __raw_readl(addr);
@@ -325,15 +325,15 @@ static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count)
 }
 #endif
 
-void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	IO_COND(addr, insb(port,dst,count), mmio_insb(addr, dst, count));
 }
-void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	IO_COND(addr, insw(port,dst,count), mmio_insw(addr, dst, count));
 }
-void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	IO_COND(addr, insl(port,dst,count), mmio_insl(addr, dst, count));
 }
diff --git a/lib/ioremap.c b/lib/ioremap.c
deleted file mode 100644
index 3f0e18543de8..000000000000
--- a/lib/ioremap.c
+++ /dev/null
@@ -1,272 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Re-map IO memory to kernel address space so that we can access it.
- * This is needed for high PCI addresses that aren't mapped in the
- * 640k-1MB IO memory area on PC's
- *
- * (C) Copyright 1995 1996 Linus Torvalds
- */
-#include <linux/vmalloc.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/io.h>
-#include <linux/export.h>
-#include <asm/cacheflush.h>
-#include <asm/pgtable.h>
-
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static int __read_mostly ioremap_p4d_capable;
-static int __read_mostly ioremap_pud_capable;
-static int __read_mostly ioremap_pmd_capable;
-static int __read_mostly ioremap_huge_disabled;
-
-static int __init set_nohugeiomap(char *str)
-{
-	ioremap_huge_disabled = 1;
-	return 0;
-}
-early_param("nohugeiomap", set_nohugeiomap);
-
-void __init ioremap_huge_init(void)
-{
-	if (!ioremap_huge_disabled) {
-		if (arch_ioremap_p4d_supported())
-			ioremap_p4d_capable = 1;
-		if (arch_ioremap_pud_supported())
-			ioremap_pud_capable = 1;
-		if (arch_ioremap_pmd_supported())
-			ioremap_pmd_capable = 1;
-	}
-}
-
-static inline int ioremap_p4d_enabled(void)
-{
-	return ioremap_p4d_capable;
-}
-
-static inline int ioremap_pud_enabled(void)
-{
-	return ioremap_pud_capable;
-}
-
-static inline int ioremap_pmd_enabled(void)
-{
-	return ioremap_pmd_capable;
-}
-
-#else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
-static inline int ioremap_p4d_enabled(void) { return 0; }
-static inline int ioremap_pud_enabled(void) { return 0; }
-static inline int ioremap_pmd_enabled(void) { return 0; }
-#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
-
-static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
-		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
-{
-	pte_t *pte;
-	u64 pfn;
-
-	pfn = phys_addr >> PAGE_SHIFT;
-	pte = pte_alloc_kernel(pmd, addr);
-	if (!pte)
-		return -ENOMEM;
-	do {
-		BUG_ON(!pte_none(*pte));
-		set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
-		pfn++;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-	return 0;
-}
-
-static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr,
-				unsigned long end, phys_addr_t phys_addr,
-				pgprot_t prot)
-{
-	if (!ioremap_pmd_enabled())
-		return 0;
-
-	if ((end - addr) != PMD_SIZE)
-		return 0;
-
-	if (!IS_ALIGNED(addr, PMD_SIZE))
-		return 0;
-
-	if (!IS_ALIGNED(phys_addr, PMD_SIZE))
-		return 0;
-
-	if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
-		return 0;
-
-	return pmd_set_huge(pmd, phys_addr, prot);
-}
-
-static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
-		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
-{
-	pmd_t *pmd;
-	unsigned long next;
-
-	pmd = pmd_alloc(&init_mm, pud, addr);
-	if (!pmd)
-		return -ENOMEM;
-	do {
-		next = pmd_addr_end(addr, end);
-
-		if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr, prot))
-			continue;
-
-		if (ioremap_pte_range(pmd, addr, next, phys_addr, prot))
-			return -ENOMEM;
-	} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
-	return 0;
-}
-
-static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr,
-				unsigned long end, phys_addr_t phys_addr,
-				pgprot_t prot)
-{
-	if (!ioremap_pud_enabled())
-		return 0;
-
-	if ((end - addr) != PUD_SIZE)
-		return 0;
-
-	if (!IS_ALIGNED(addr, PUD_SIZE))
-		return 0;
-
-	if (!IS_ALIGNED(phys_addr, PUD_SIZE))
-		return 0;
-
-	if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
-		return 0;
-
-	return pud_set_huge(pud, phys_addr, prot);
-}
-
-static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
-		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
-{
-	pud_t *pud;
-	unsigned long next;
-
-	pud = pud_alloc(&init_mm, p4d, addr);
-	if (!pud)
-		return -ENOMEM;
-	do {
-		next = pud_addr_end(addr, end);
-
-		if (ioremap_try_huge_pud(pud, addr, next, phys_addr, prot))
-			continue;
-
-		if (ioremap_pmd_range(pud, addr, next, phys_addr, prot))
-			return -ENOMEM;
-	} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
-	return 0;
-}
-
-static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr,
-				unsigned long end, phys_addr_t phys_addr,
-				pgprot_t prot)
-{
-	if (!ioremap_p4d_enabled())
-		return 0;
-
-	if ((end - addr) != P4D_SIZE)
-		return 0;
-
-	if (!IS_ALIGNED(addr, P4D_SIZE))
-		return 0;
-
-	if (!IS_ALIGNED(phys_addr, P4D_SIZE))
-		return 0;
-
-	if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
-		return 0;
-
-	return p4d_set_huge(p4d, phys_addr, prot);
-}
-
-static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
-		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
-{
-	p4d_t *p4d;
-	unsigned long next;
-
-	p4d = p4d_alloc(&init_mm, pgd, addr);
-	if (!p4d)
-		return -ENOMEM;
-	do {
-		next = p4d_addr_end(addr, end);
-
-		if (ioremap_try_huge_p4d(p4d, addr, next, phys_addr, prot))
-			continue;
-
-		if (ioremap_pud_range(p4d, addr, next, phys_addr, prot))
-			return -ENOMEM;
-	} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
-	return 0;
-}
-
-int ioremap_page_range(unsigned long addr,
-		       unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
-{
-	pgd_t *pgd;
-	unsigned long start;
-	unsigned long next;
-	int err;
-
-	might_sleep();
-	BUG_ON(addr >= end);
-
-	start = addr;
-	pgd = pgd_offset_k(addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		err = ioremap_p4d_range(pgd, addr, next, phys_addr, prot);
-		if (err)
-			break;
-	} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
-
-	flush_cache_vmap(start, end);
-
-	return err;
-}
-
-#ifdef CONFIG_GENERIC_IOREMAP
-void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot)
-{
-	unsigned long offset, vaddr;
-	phys_addr_t last_addr;
-	struct vm_struct *area;
-
-	/* Disallow wrap-around or zero size */
-	last_addr = addr + size - 1;
-	if (!size || last_addr < addr)
-		return NULL;
-
-	/* Page-align mappings */
-	offset = addr & (~PAGE_MASK);
-	addr -= offset;
-	size = PAGE_ALIGN(size + offset);
-
-	area = get_vm_area_caller(size, VM_IOREMAP,
-			__builtin_return_address(0));
-	if (!area)
-		return NULL;
-	vaddr = (unsigned long)area->addr;
-
-	if (ioremap_page_range(vaddr, vaddr + size, addr, __pgprot(prot))) {
-		free_vm_area(area);
-		return NULL;
-	}
-
-	return (void __iomem *)(vaddr + offset);
-}
-EXPORT_SYMBOL(ioremap_prot);
-
-void iounmap(volatile void __iomem *addr)
-{
-	vunmap((void *)((unsigned long)addr & PAGE_MASK));
-}
-EXPORT_SYMBOL(iounmap);
-#endif /* CONFIG_GENERIC_IOREMAP */
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 51595bf3af85..5e40786c8f12 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <crypto/hash.h>
 #include <linux/export.h>
 #include <linux/bvec.h>
 #include <linux/uio.h>
@@ -8,6 +9,7 @@
 #include <linux/splice.h>
 #include <net/checksum.h>
 #include <linux/scatterlist.h>
+#include <linux/instrumented.h>
 
 #define PIPE_PARANOIA /* for now */
 
@@ -138,7 +140,7 @@
 static int copyout(void __user *to, const void *from, size_t n)
 {
 	if (access_ok(to, n)) {
-		kasan_check_read(from, n);
+		instrument_copy_to_user(to, from, n);
 		n = raw_copy_to_user(to, from, n);
 	}
 	return n;
@@ -147,7 +149,7 @@ static int copyout(void __user *to, const void *from, size_t n)
 static int copyin(void *to, const void __user *from, size_t n)
 {
 	if (access_ok(from, n)) {
-		kasan_check_write(to, n);
+		instrument_copy_from_user(to, from, n);
 		n = raw_copy_from_user(to, from, n);
 	}
 	return n;
@@ -639,7 +641,7 @@ EXPORT_SYMBOL(_copy_to_iter);
 static int copyout_mcsafe(void __user *to, const void *from, size_t n)
 {
 	if (access_ok(to, n)) {
-		kasan_check_read(from, n);
+		instrument_copy_to_user(to, from, n);
 		n = copy_to_user_mcsafe((__force void *) to, from, n);
 	}
 	return n;
@@ -1566,7 +1568,7 @@ EXPORT_SYMBOL(csum_and_copy_to_iter);
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i)
 {
-#ifdef CONFIG_CRYPTO
+#ifdef CONFIG_CRYPTO_HASH
 	struct ahash_request *hash = hashp;
 	struct scatterlist sg;
 	size_t copied;
diff --git a/lib/kobject.c b/lib/kobject.c
index 83198cb37d8d..ea53b30cf483 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -6,7 +6,7 @@
  * Copyright (c) 2006-2007 Greg Kroah-Hartman <greg@kroah.com>
  * Copyright (c) 2006-2007 Novell Inc.
  *
- * Please see the file Documentation/kobject.txt for critical information
+ * Please see the file Documentation/core-api/kobject.rst for critical information
  * about using the kobject interface.
  */
 
@@ -599,35 +599,50 @@ out:
 }
 EXPORT_SYMBOL_GPL(kobject_move);
 
-/**
- * kobject_del() - Unlink kobject from hierarchy.
- * @kobj: object.
- *
- * This is the function that should be called to delete an object
- * successfully added via kobject_add().
- */
-void kobject_del(struct kobject *kobj)
+static void __kobject_del(struct kobject *kobj)
 {
 	struct kernfs_node *sd;
 	const struct kobj_type *ktype;
 
-	if (!kobj)
-		return;
-
 	sd = kobj->sd;
 	ktype = get_ktype(kobj);
 
 	if (ktype)
 		sysfs_remove_groups(kobj, ktype->default_groups);
 
+	/* send "remove" if the caller did not do it but sent "add" */
+	if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) {
+		pr_debug("kobject: '%s' (%p): auto cleanup 'remove' event\n",
+			 kobject_name(kobj), kobj);
+		kobject_uevent(kobj, KOBJ_REMOVE);
+	}
+
 	sysfs_remove_dir(kobj);
 	sysfs_put(sd);
 
 	kobj->state_in_sysfs = 0;
 	kobj_kset_leave(kobj);
-	kobject_put(kobj->parent);
 	kobj->parent = NULL;
 }
+
+/**
+ * kobject_del() - Unlink kobject from hierarchy.
+ * @kobj: object.
+ *
+ * This is the function that should be called to delete an object
+ * successfully added via kobject_add().
+ */
+void kobject_del(struct kobject *kobj)
+{
+	struct kobject *parent;
+
+	if (!kobj)
+		return;
+
+	parent = kobj->parent;
+	__kobject_del(kobj);
+	kobject_put(parent);
+}
 EXPORT_SYMBOL(kobject_del);
 
 /**
@@ -663,6 +678,7 @@ EXPORT_SYMBOL(kobject_get_unless_zero);
  */
 static void kobject_cleanup(struct kobject *kobj)
 {
+	struct kobject *parent = kobj->parent;
 	struct kobj_type *t = get_ktype(kobj);
 	const char *name = kobj->name;
 
@@ -670,21 +686,17 @@ static void kobject_cleanup(struct kobject *kobj)
 		 kobject_name(kobj), kobj, __func__, kobj->parent);
 
 	if (t && !t->release)
-		pr_debug("kobject: '%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/kobject.txt.\n",
-			 kobject_name(kobj), kobj);
-
-	/* send "remove" if the caller did not do it but sent "add" */
-	if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) {
-		pr_debug("kobject: '%s' (%p): auto cleanup 'remove' event\n",
+		pr_debug("kobject: '%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n",
 			 kobject_name(kobj), kobj);
-		kobject_uevent(kobj, KOBJ_REMOVE);
-	}
 
 	/* remove from sysfs if the caller did not do it */
 	if (kobj->state_in_sysfs) {
 		pr_debug("kobject: '%s' (%p): auto cleanup kobject_del\n",
 			 kobject_name(kobj), kobj);
-		kobject_del(kobj);
+		__kobject_del(kobj);
+	} else {
+		/* avoid dropping the parent reference unnecessarily */
+		parent = NULL;
 	}
 
 	if (t && t->release) {
@@ -698,6 +710,8 @@ static void kobject_cleanup(struct kobject *kobj)
 		pr_debug("kobject: '%s': free name\n", name);
 		kfree_const(name);
 	}
+
+	kobject_put(parent);
 }
 
 #ifdef CONFIG_DEBUG_KOBJECT_RELEASE
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index 1006bf70bf74..a14ccf905055 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -115,8 +115,7 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
- * be checked.
+ * Preferred over simple_strtoull(). Return code must be checked.
  */
 int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
 {
@@ -139,8 +138,7 @@ EXPORT_SYMBOL(kstrtoull);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
- * be checked.
+ * Preferred over simple_strtoll(). Return code must be checked.
  */
 int kstrtoll(const char *s, unsigned int base, long long *res)
 {
@@ -211,8 +209,7 @@ EXPORT_SYMBOL(_kstrtol);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
- * be checked.
+ * Preferred over simple_strtoul(). Return code must be checked.
  */
 int kstrtouint(const char *s, unsigned int base, unsigned int *res)
 {
@@ -242,8 +239,7 @@ EXPORT_SYMBOL(kstrtouint);
  * @res: Where to write the result of the conversion on success.
  *
  * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
- * be checked.
+ * Preferred over simple_strtol(). Return code must be checked.
  */
 int kstrtoint(const char *s, unsigned int base, int *res)
 {
diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig
index 95d12e3d6d95..00909e6a2443 100644
--- a/lib/kunit/Kconfig
+++ b/lib/kunit/Kconfig
@@ -15,7 +15,8 @@ menuconfig KUNIT
 if KUNIT
 
 config KUNIT_DEBUGFS
-	bool "KUnit - Enable /sys/kernel/debug/kunit debugfs representation"
+	bool "KUnit - Enable /sys/kernel/debug/kunit debugfs representation" if !KUNIT_ALL_TESTS
+	default KUNIT_ALL_TESTS
 	help
 	  Enable debugfs representation for kunit.  Currently this consists
 	  of /sys/kernel/debug/kunit/<test_suite>/results files for each
@@ -23,7 +24,8 @@ config KUNIT_DEBUGFS
 	  run that occurred.
 
 config KUNIT_TEST
-	tristate "KUnit test for KUnit"
+	tristate "KUnit test for KUnit" if !KUNIT_ALL_TESTS
+	default KUNIT_ALL_TESTS
 	help
 	  Enables the unit tests for the KUnit test framework. These tests test
 	  the KUnit test framework itself; the tests are both written using
@@ -32,7 +34,8 @@ config KUNIT_TEST
 	  expected.
 
 config KUNIT_EXAMPLE_TEST
-	tristate "Example test for KUnit"
+	tristate "Example test for KUnit" if !KUNIT_ALL_TESTS
+	default KUNIT_ALL_TESTS
 	help
 	  Enables an example unit test that illustrates some of the basic
 	  features of KUnit. This test only exists to help new users understand
@@ -41,4 +44,18 @@ config KUNIT_EXAMPLE_TEST
 	  is intended for curious hackers who would like to understand how to
 	  use KUnit for kernel development.
 
+config KUNIT_ALL_TESTS
+	tristate "All KUnit tests with satisfied dependencies"
+	help
+	  Enables all KUnit tests, if they can be enabled.
+	  KUnit tests run during boot and output the results to the debug log
+	  in TAP format (http://testanything.org/). Only useful for kernel devs
+	  running the KUnit test harness, and not intended for inclusion into a
+	  production build.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 endif # KUNIT
diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c
index 4f3d36a72f8f..69f902440a0e 100644
--- a/lib/kunit/kunit-test.c
+++ b/lib/kunit/kunit-test.c
@@ -118,14 +118,14 @@ static int fake_resource_init(struct kunit_resource *res, void *context)
 {
 	struct kunit_test_resource_context *ctx = context;
 
-	res->allocation = &ctx->is_resource_initialized;
+	res->data = &ctx->is_resource_initialized;
 	ctx->is_resource_initialized = true;
 	return 0;
 }
 
 static void fake_resource_free(struct kunit_resource *res)
 {
-	bool *is_resource_initialized = res->allocation;
+	bool *is_resource_initialized = res->data;
 
 	*is_resource_initialized = false;
 }
@@ -154,11 +154,21 @@ static void kunit_resource_test_alloc_resource(struct kunit *test)
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, res);
 	KUNIT_EXPECT_PTR_EQ(test,
 			    &ctx->is_resource_initialized,
-			    (bool *) res->allocation);
+			    (bool *)res->data);
 	KUNIT_EXPECT_TRUE(test, list_is_last(&res->node, &ctx->test.resources));
 	KUNIT_EXPECT_PTR_EQ(test, free, res->free);
+
+	kunit_put_resource(res);
 }
 
+/*
+ * Note: tests below use kunit_alloc_and_get_resource(), so as a consequence
+ * they have a reference to the associated resource that they must release
+ * via kunit_put_resource().  In normal operation, users will only
+ * have to do this for cases where they use kunit_find_resource(), and the
+ * kunit_alloc_resource() function will be used (which does not take a
+ * resource reference).
+ */
 static void kunit_resource_test_destroy_resource(struct kunit *test)
 {
 	struct kunit_test_resource_context *ctx = test->priv;
@@ -169,11 +179,12 @@ static void kunit_resource_test_destroy_resource(struct kunit *test)
 			GFP_KERNEL,
 			ctx);
 
+	kunit_put_resource(res);
+
 	KUNIT_ASSERT_FALSE(test,
-			   kunit_resource_destroy(&ctx->test,
+			   kunit_destroy_resource(&ctx->test,
 						  kunit_resource_instance_match,
-						  res->free,
-						  res->allocation));
+						  res->data));
 
 	KUNIT_EXPECT_FALSE(test, ctx->is_resource_initialized);
 	KUNIT_EXPECT_TRUE(test, list_empty(&ctx->test.resources));
@@ -191,6 +202,7 @@ static void kunit_resource_test_cleanup_resources(struct kunit *test)
 							    fake_resource_free,
 							    GFP_KERNEL,
 							    ctx);
+		kunit_put_resource(resources[i]);
 	}
 
 	kunit_cleanup(&ctx->test);
@@ -221,14 +233,14 @@ static int fake_resource_2_init(struct kunit_resource *res, void *context)
 
 	KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, allocate_order, 2);
 
-	res->allocation = ctx;
+	res->data = ctx;
 
 	return 0;
 }
 
 static void fake_resource_2_free(struct kunit_resource *res)
 {
-	struct kunit_test_resource_context *ctx = res->allocation;
+	struct kunit_test_resource_context *ctx = res->data;
 
 	KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, free_order, 2);
 }
@@ -236,23 +248,26 @@ static void fake_resource_2_free(struct kunit_resource *res)
 static int fake_resource_1_init(struct kunit_resource *res, void *context)
 {
 	struct kunit_test_resource_context *ctx = context;
+	struct kunit_resource *res2;
 
-	kunit_alloc_and_get_resource(&ctx->test,
-				     fake_resource_2_init,
-				     fake_resource_2_free,
-				     GFP_KERNEL,
-				     ctx);
+	res2 = kunit_alloc_and_get_resource(&ctx->test,
+					    fake_resource_2_init,
+					    fake_resource_2_free,
+					    GFP_KERNEL,
+					    ctx);
 
 	KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, allocate_order, 1);
 
-	res->allocation = ctx;
+	res->data = ctx;
+
+	kunit_put_resource(res2);
 
 	return 0;
 }
 
 static void fake_resource_1_free(struct kunit_resource *res)
 {
-	struct kunit_test_resource_context *ctx = res->allocation;
+	struct kunit_test_resource_context *ctx = res->data;
 
 	KUNIT_RESOURCE_TEST_MARK_ORDER(ctx, free_order, 1);
 }
@@ -265,13 +280,14 @@ static void fake_resource_1_free(struct kunit_resource *res)
 static void kunit_resource_test_proper_free_ordering(struct kunit *test)
 {
 	struct kunit_test_resource_context *ctx = test->priv;
+	struct kunit_resource *res;
 
 	/* fake_resource_1 allocates a fake_resource_2 in its init. */
-	kunit_alloc_and_get_resource(&ctx->test,
-				     fake_resource_1_init,
-				     fake_resource_1_free,
-				     GFP_KERNEL,
-				     ctx);
+	res = kunit_alloc_and_get_resource(&ctx->test,
+					   fake_resource_1_init,
+					   fake_resource_1_free,
+					   GFP_KERNEL,
+					   ctx);
 
 	/*
 	 * Since fake_resource_2_init calls KUNIT_RESOURCE_TEST_MARK_ORDER
@@ -281,6 +297,8 @@ static void kunit_resource_test_proper_free_ordering(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, ctx->allocate_order[0], 2);
 	KUNIT_EXPECT_EQ(test, ctx->allocate_order[1], 1);
 
+	kunit_put_resource(res);
+
 	kunit_cleanup(&ctx->test);
 
 	/*
@@ -292,6 +310,57 @@ static void kunit_resource_test_proper_free_ordering(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, ctx->free_order[1], 2);
 }
 
+static void kunit_resource_test_static(struct kunit *test)
+{
+	struct kunit_test_resource_context ctx;
+	struct kunit_resource res;
+
+	KUNIT_EXPECT_EQ(test, kunit_add_resource(test, NULL, NULL, &res, &ctx),
+			0);
+
+	KUNIT_EXPECT_PTR_EQ(test, res.data, (void *)&ctx);
+
+	kunit_cleanup(test);
+
+	KUNIT_EXPECT_TRUE(test, list_empty(&test->resources));
+}
+
+static void kunit_resource_test_named(struct kunit *test)
+{
+	struct kunit_resource res1, res2, *found = NULL;
+	struct kunit_test_resource_context ctx;
+
+	KUNIT_EXPECT_EQ(test,
+			kunit_add_named_resource(test, NULL, NULL, &res1,
+						 "resource_1", &ctx),
+			0);
+	KUNIT_EXPECT_PTR_EQ(test, res1.data, (void *)&ctx);
+
+	KUNIT_EXPECT_EQ(test,
+			kunit_add_named_resource(test, NULL, NULL, &res1,
+						 "resource_1", &ctx),
+			-EEXIST);
+
+	KUNIT_EXPECT_EQ(test,
+			kunit_add_named_resource(test, NULL, NULL, &res2,
+						 "resource_2", &ctx),
+			0);
+
+	found = kunit_find_named_resource(test, "resource_1");
+
+	KUNIT_EXPECT_PTR_EQ(test, found, &res1);
+
+	if (found)
+		kunit_put_resource(&res1);
+
+	KUNIT_EXPECT_EQ(test, kunit_destroy_named_resource(test, "resource_2"),
+			0);
+
+	kunit_cleanup(test);
+
+	KUNIT_EXPECT_TRUE(test, list_empty(&test->resources));
+}
+
 static int kunit_resource_test_init(struct kunit *test)
 {
 	struct kunit_test_resource_context *ctx =
@@ -320,6 +389,8 @@ static struct kunit_case kunit_resource_test_cases[] = {
 	KUNIT_CASE(kunit_resource_test_destroy_resource),
 	KUNIT_CASE(kunit_resource_test_cleanup_resources),
 	KUNIT_CASE(kunit_resource_test_proper_free_ordering),
+	KUNIT_CASE(kunit_resource_test_static),
+	KUNIT_CASE(kunit_resource_test_named),
 	{}
 };
 
diff --git a/lib/kunit/string-stream.c b/lib/kunit/string-stream.c
index 350392013c14..141789ca8949 100644
--- a/lib/kunit/string-stream.c
+++ b/lib/kunit/string-stream.c
@@ -33,14 +33,14 @@ static int string_stream_fragment_init(struct kunit_resource *res,
 	if (!frag->fragment)
 		return -ENOMEM;
 
-	res->allocation = frag;
+	res->data = frag;
 
 	return 0;
 }
 
 static void string_stream_fragment_free(struct kunit_resource *res)
 {
-	struct string_stream_fragment *frag = res->allocation;
+	struct string_stream_fragment *frag = res->data;
 
 	list_del(&frag->node);
 	kunit_kfree(frag->test, frag->fragment);
@@ -65,9 +65,8 @@ static struct string_stream_fragment *alloc_string_stream_fragment(
 
 static int string_stream_fragment_destroy(struct string_stream_fragment *frag)
 {
-	return kunit_resource_destroy(frag->test,
+	return kunit_destroy_resource(frag->test,
 				      kunit_resource_instance_match,
-				      string_stream_fragment_free,
 				      frag);
 }
 
@@ -179,7 +178,7 @@ static int string_stream_init(struct kunit_resource *res, void *context)
 	if (!stream)
 		return -ENOMEM;
 
-	res->allocation = stream;
+	res->data = stream;
 	stream->gfp = ctx->gfp;
 	stream->test = ctx->test;
 	INIT_LIST_HEAD(&stream->fragments);
@@ -190,7 +189,7 @@ static int string_stream_init(struct kunit_resource *res, void *context)
 
 static void string_stream_free(struct kunit_resource *res)
 {
-	struct string_stream *stream = res->allocation;
+	struct string_stream *stream = res->data;
 
 	string_stream_clear(stream);
 }
@@ -211,8 +210,7 @@ struct string_stream *alloc_string_stream(struct kunit *test, gfp_t gfp)
 
 int string_stream_destroy(struct string_stream *stream)
 {
-	return kunit_resource_destroy(stream->test,
+	return kunit_destroy_resource(stream->test,
 				      kunit_resource_instance_match,
-				      string_stream_free,
 				      stream);
 }
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index ccb2ffad8dcf..c36037200310 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -8,6 +8,7 @@
 
 #include <kunit/test.h>
 #include <linux/kernel.h>
+#include <linux/kref.h>
 #include <linux/sched/debug.h>
 
 #include "debugfs.h"
@@ -406,90 +407,116 @@ void __kunit_test_suites_exit(struct kunit_suite **suites)
 }
 EXPORT_SYMBOL_GPL(__kunit_test_suites_exit);
 
-struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test,
-						    kunit_resource_init_t init,
-						    kunit_resource_free_t free,
-						    gfp_t internal_gfp,
-						    void *context)
+/*
+ * Used for static resources and when a kunit_resource * has been created by
+ * kunit_alloc_resource().  When an init function is supplied, @data is passed
+ * into the init function; otherwise, we simply set the resource data field to
+ * the data value passed in.
+ */
+int kunit_add_resource(struct kunit *test,
+		       kunit_resource_init_t init,
+		       kunit_resource_free_t free,
+		       struct kunit_resource *res,
+		       void *data)
 {
-	struct kunit_resource *res;
-	int ret;
+	int ret = 0;
 
-	res = kzalloc(sizeof(*res), internal_gfp);
-	if (!res)
-		return NULL;
+	res->free = free;
+	kref_init(&res->refcount);
 
-	ret = init(res, context);
-	if (ret)
-		return NULL;
+	if (init) {
+		ret = init(res, data);
+		if (ret)
+			return ret;
+	} else {
+		res->data = data;
+	}
 
-	res->free = free;
 	spin_lock(&test->lock);
 	list_add_tail(&res->node, &test->resources);
+	/* refcount for list is established by kref_init() */
 	spin_unlock(&test->lock);
 
-	return res;
+	return ret;
 }
-EXPORT_SYMBOL_GPL(kunit_alloc_and_get_resource);
+EXPORT_SYMBOL_GPL(kunit_add_resource);
 
-static void kunit_resource_free(struct kunit *test, struct kunit_resource *res)
+int kunit_add_named_resource(struct kunit *test,
+			     kunit_resource_init_t init,
+			     kunit_resource_free_t free,
+			     struct kunit_resource *res,
+			     const char *name,
+			     void *data)
 {
-	res->free(res);
-	kfree(res);
+	struct kunit_resource *existing;
+
+	if (!name)
+		return -EINVAL;
+
+	existing = kunit_find_named_resource(test, name);
+	if (existing) {
+		kunit_put_resource(existing);
+		return -EEXIST;
+	}
+
+	res->name = name;
+
+	return kunit_add_resource(test, init, free, res, data);
 }
+EXPORT_SYMBOL_GPL(kunit_add_named_resource);
 
-static struct kunit_resource *kunit_resource_find(struct kunit *test,
-						  kunit_resource_match_t match,
-						  kunit_resource_free_t free,
-						  void *match_data)
+struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test,
+						    kunit_resource_init_t init,
+						    kunit_resource_free_t free,
+						    gfp_t internal_gfp,
+						    void *data)
 {
-	struct kunit_resource *resource;
+	struct kunit_resource *res;
+	int ret;
 
-	lockdep_assert_held(&test->lock);
+	res = kzalloc(sizeof(*res), internal_gfp);
+	if (!res)
+		return NULL;
 
-	list_for_each_entry_reverse(resource, &test->resources, node) {
-		if (resource->free != free)
-			continue;
-		if (match(test, resource->allocation, match_data))
-			return resource;
+	ret = kunit_add_resource(test, init, free, res, data);
+	if (!ret) {
+		/*
+		 * bump refcount for get; kunit_resource_put() should be called
+		 * when done.
+		 */
+		kunit_get_resource(res);
+		return res;
 	}
-
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(kunit_alloc_and_get_resource);
 
-static struct kunit_resource *kunit_resource_remove(
-		struct kunit *test,
-		kunit_resource_match_t match,
-		kunit_resource_free_t free,
-		void *match_data)
+void kunit_remove_resource(struct kunit *test, struct kunit_resource *res)
 {
-	struct kunit_resource *resource;
-
 	spin_lock(&test->lock);
-	resource = kunit_resource_find(test, match, free, match_data);
-	if (resource)
-		list_del(&resource->node);
+	list_del(&res->node);
 	spin_unlock(&test->lock);
-
-	return resource;
+	kunit_put_resource(res);
 }
+EXPORT_SYMBOL_GPL(kunit_remove_resource);
 
-int kunit_resource_destroy(struct kunit *test,
-			   kunit_resource_match_t match,
-			   kunit_resource_free_t free,
+int kunit_destroy_resource(struct kunit *test, kunit_resource_match_t match,
 			   void *match_data)
 {
-	struct kunit_resource *resource;
-
-	resource = kunit_resource_remove(test, match, free, match_data);
+	struct kunit_resource *res = kunit_find_resource(test, match,
+							 match_data);
 
-	if (!resource)
+	if (!res)
 		return -ENOENT;
 
-	kunit_resource_free(test, resource);
+	kunit_remove_resource(test, res);
+
+	/* We have a reference also via _find(); drop it. */
+	kunit_put_resource(res);
+
 	return 0;
 }
-EXPORT_SYMBOL_GPL(kunit_resource_destroy);
+EXPORT_SYMBOL_GPL(kunit_destroy_resource);
 
 struct kunit_kmalloc_params {
 	size_t size;
@@ -500,8 +527,8 @@ static int kunit_kmalloc_init(struct kunit_resource *res, void *context)
 {
 	struct kunit_kmalloc_params *params = context;
 
-	res->allocation = kmalloc(params->size, params->gfp);
-	if (!res->allocation)
+	res->data = kmalloc(params->size, params->gfp);
+	if (!res->data)
 		return -ENOMEM;
 
 	return 0;
@@ -509,7 +536,7 @@ static int kunit_kmalloc_init(struct kunit_resource *res, void *context)
 
 static void kunit_kmalloc_free(struct kunit_resource *res)
 {
-	kfree(res->allocation);
+	kfree(res->data);
 }
 
 void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp)
@@ -529,20 +556,25 @@ EXPORT_SYMBOL_GPL(kunit_kmalloc);
 
 void kunit_kfree(struct kunit *test, const void *ptr)
 {
-	int rc;
+	struct kunit_resource *res;
 
-	rc = kunit_resource_destroy(test,
-				    kunit_resource_instance_match,
-				    kunit_kmalloc_free,
-				    (void *)ptr);
+	res = kunit_find_resource(test, kunit_resource_instance_match,
+				  (void *)ptr);
+
+	/*
+	 * Removing the resource from the list of resources drops the
+	 * reference count to 1; the final put will trigger the free.
+	 */
+	kunit_remove_resource(test, res);
+
+	kunit_put_resource(res);
 
-	WARN_ON(rc);
 }
 EXPORT_SYMBOL_GPL(kunit_kfree);
 
 void kunit_cleanup(struct kunit *test)
 {
-	struct kunit_resource *resource;
+	struct kunit_resource *res;
 
 	/*
 	 * test->resources is a stack - each allocation must be freed in the
@@ -559,13 +591,16 @@ void kunit_cleanup(struct kunit *test)
 			spin_unlock(&test->lock);
 			break;
 		}
-		resource = list_last_entry(&test->resources,
-					   struct kunit_resource,
-					   node);
-		list_del(&resource->node);
+		res = list_last_entry(&test->resources,
+				      struct kunit_resource,
+				      node);
+		/*
+		 * Need to unlock here as a resource may remove another
+		 * resource, and this can't happen if the test->lock
+		 * is held.
+		 */
 		spin_unlock(&test->lock);
-
-		kunit_resource_free(test, resource);
+		kunit_remove_resource(test, res);
 	}
 }
 EXPORT_SYMBOL_GPL(kunit_cleanup);
diff --git a/lib/linear_ranges.c b/lib/linear_ranges.c
new file mode 100644
index 000000000000..9495ef3572b7
--- /dev/null
+++ b/lib/linear_ranges.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * helpers to map values in a linear range to range index
+ *
+ * Original idea borrowed from regulator framework
+ *
+ * It might be useful if we could support also inversely proportional ranges?
+ * Copyright 2020 ROHM Semiconductors
+ */
+
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/linear_range.h>
+#include <linux/module.h>
+
+/**
+ * linear_range_values_in_range - return the amount of values in a range
+ * @r:		pointer to linear range where values are counted
+ *
+ * Compute the amount of values in range pointed by @r. Note, values can
+ * be all equal - range with selectors 0,...,2 with step 0 still contains
+ * 3 values even though they are all equal.
+ *
+ * Return: the amount of values in range pointed by @r
+ */
+unsigned int linear_range_values_in_range(const struct linear_range *r)
+{
+	if (!r)
+		return 0;
+	return r->max_sel - r->min_sel + 1;
+}
+EXPORT_SYMBOL_GPL(linear_range_values_in_range);
+
+/**
+ * linear_range_values_in_range_array - return the amount of values in ranges
+ * @r:		pointer to array of linear ranges where values are counted
+ * @ranges:	amount of ranges we include in computation.
+ *
+ * Compute the amount of values in ranges pointed by @r. Note, values can
+ * be all equal - range with selectors 0,...,2 with step 0 still contains
+ * 3 values even though they are all equal.
+ *
+ * Return: the amount of values in first @ranges ranges pointed by @r
+ */
+unsigned int linear_range_values_in_range_array(const struct linear_range *r,
+						int ranges)
+{
+	int i, values_in_range = 0;
+
+	for (i = 0; i < ranges; i++) {
+		int values;
+
+		values = linear_range_values_in_range(&r[i]);
+		if (!values)
+			return values;
+
+		values_in_range += values;
+	}
+	return values_in_range;
+}
+EXPORT_SYMBOL_GPL(linear_range_values_in_range_array);
+
+/**
+ * linear_range_get_max_value - return the largest value in a range
+ * @r:		pointer to linear range where value is looked from
+ *
+ * Return: the largest value in the given range
+ */
+unsigned int linear_range_get_max_value(const struct linear_range *r)
+{
+	return r->min + (r->max_sel - r->min_sel) * r->step;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_max_value);
+
+/**
+ * linear_range_get_value - fetch a value from given range
+ * @r:		pointer to linear range where value is looked from
+ * @selector:	selector for which the value is searched
+ * @val:	address where found value is updated
+ *
+ * Search given ranges for value which matches given selector.
+ *
+ * Return: 0 on success, -EINVAL given selector is not found from any of the
+ * ranges.
+ */
+int linear_range_get_value(const struct linear_range *r, unsigned int selector,
+			   unsigned int *val)
+{
+	if (r->min_sel > selector || r->max_sel < selector)
+		return -EINVAL;
+
+	*val = r->min + (selector - r->min_sel) * r->step;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_value);
+
+/**
+ * linear_range_get_value_array - fetch a value from array of ranges
+ * @r:		pointer to array of linear ranges where value is looked from
+ * @ranges:	amount of ranges in an array
+ * @selector:	selector for which the value is searched
+ * @val:	address where found value is updated
+ *
+ * Search through an array of ranges for value which matches given selector.
+ *
+ * Return: 0 on success, -EINVAL given selector is not found from any of the
+ * ranges.
+ */
+int linear_range_get_value_array(const struct linear_range *r, int ranges,
+				 unsigned int selector, unsigned int *val)
+{
+	int i;
+
+	for (i = 0; i < ranges; i++)
+		if (r[i].min_sel <= selector && r[i].max_sel >= selector)
+			return linear_range_get_value(&r[i], selector, val);
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_value_array);
+
+/**
+ * linear_range_get_selector_low - return linear range selector for value
+ * @r:		pointer to linear range where selector is looked from
+ * @val:	value for which the selector is searched
+ * @selector:	address where found selector value is updated
+ * @found:	flag to indicate that given value was in the range
+ *
+ * Return selector which which range value is closest match for given
+ * input value. Value is matching if it is equal or smaller than given
+ * value. If given value is in the range, then @found is set true.
+ *
+ * Return: 0 on success, -EINVAL if range is invalid or does not contain
+ * value smaller or equal to given value
+ */
+int linear_range_get_selector_low(const struct linear_range *r,
+				  unsigned int val, unsigned int *selector,
+				  bool *found)
+{
+	*found = false;
+
+	if (r->min > val)
+		return -EINVAL;
+
+	if (linear_range_get_max_value(r) < val) {
+		*selector = r->max_sel;
+		return 0;
+	}
+
+	*found = true;
+
+	if (r->step == 0)
+		*selector = r->min_sel;
+	else
+		*selector = (val - r->min) / r->step + r->min_sel;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_selector_low);
+
+/**
+ * linear_range_get_selector_low_array - return linear range selector for value
+ * @r:		pointer to array of linear ranges where selector is looked from
+ * @ranges:	amount of ranges to scan from array
+ * @val:	value for which the selector is searched
+ * @selector:	address where found selector value is updated
+ * @found:	flag to indicate that given value was in the range
+ *
+ * Scan array of ranges for selector which which range value matches given
+ * input value. Value is matching if it is equal or smaller than given
+ * value. If given value is found to be in a range scanning is stopped and
+ * @found is set true. If a range with values smaller than given value is found
+ * but the range max is being smaller than given value, then the ranges
+ * biggest selector is updated to @selector but scanning ranges is continued
+ * and @found is set to false.
+ *
+ * Return: 0 on success, -EINVAL if range array is invalid or does not contain
+ * range with a value smaller or equal to given value
+ */
+int linear_range_get_selector_low_array(const struct linear_range *r,
+					int ranges, unsigned int val,
+					unsigned int *selector, bool *found)
+{
+	int i;
+	int ret = -EINVAL;
+
+	for (i = 0; i < ranges; i++) {
+		int tmpret;
+
+		tmpret = linear_range_get_selector_low(&r[i], val, selector,
+						       found);
+		if (!tmpret)
+			ret = 0;
+
+		if (*found)
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_selector_low_array);
+
+/**
+ * linear_range_get_selector_high - return linear range selector for value
+ * @r:		pointer to linear range where selector is looked from
+ * @val:	value for which the selector is searched
+ * @selector:	address where found selector value is updated
+ * @found:	flag to indicate that given value was in the range
+ *
+ * Return selector which which range value is closest match for given
+ * input value. Value is matching if it is equal or higher than given
+ * value. If given value is in the range, then @found is set true.
+ *
+ * Return: 0 on success, -EINVAL if range is invalid or does not contain
+ * value greater or equal to given value
+ */
+int linear_range_get_selector_high(const struct linear_range *r,
+				   unsigned int val, unsigned int *selector,
+				   bool *found)
+{
+	*found = false;
+
+	if (linear_range_get_max_value(r) < val)
+		return -EINVAL;
+
+	if (r->min > val) {
+		*selector = r->min_sel;
+		return 0;
+	}
+
+	*found = true;
+
+	if (r->step == 0)
+		*selector = r->max_sel;
+	else
+		*selector = DIV_ROUND_UP(val - r->min, r->step) + r->min_sel;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_selector_high);
+
+MODULE_DESCRIPTION("linear-ranges helper");
+MODULE_LICENSE("GPL");
diff --git a/lib/livepatch/Makefile b/lib/livepatch/Makefile
index 295b94bff370..dcc912b3478f 100644
--- a/lib/livepatch/Makefile
+++ b/lib/livepatch/Makefile
@@ -12,7 +12,3 @@ obj-$(CONFIG_TEST_LIVEPATCH) += test_klp_atomic_replace.o \
 				test_klp_state.o \
 				test_klp_state2.o \
 				test_klp_state3.o
-
-# Target modules to be livepatched require CC_FLAGS_FTRACE
-CFLAGS_test_klp_callbacks_busy.o	+= $(CC_FLAGS_FTRACE)
-CFLAGS_test_klp_callbacks_mod.o		+= $(CC_FLAGS_FTRACE)
diff --git a/lib/livepatch/test_klp_callbacks_busy.c b/lib/livepatch/test_klp_callbacks_busy.c
index 40beddf8a0e2..7ac845f65be5 100644
--- a/lib/livepatch/test_klp_callbacks_busy.c
+++ b/lib/livepatch/test_klp_callbacks_busy.c
@@ -5,34 +5,53 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/sched.h>
 #include <linux/workqueue.h>
 #include <linux/delay.h>
 
-static int sleep_secs;
-module_param(sleep_secs, int, 0644);
-MODULE_PARM_DESC(sleep_secs, "sleep_secs (default=0)");
+/* load/run-time control from sysfs writer  */
+static bool block_transition;
+module_param(block_transition, bool, 0644);
+MODULE_PARM_DESC(block_transition, "block_transition (default=false)");
 
 static void busymod_work_func(struct work_struct *work);
-static DECLARE_DELAYED_WORK(work, busymod_work_func);
+static DECLARE_WORK(work, busymod_work_func);
 
 static void busymod_work_func(struct work_struct *work)
 {
-	pr_info("%s, sleeping %d seconds ...\n", __func__, sleep_secs);
-	msleep(sleep_secs * 1000);
+	pr_info("%s enter\n", __func__);
+
+	while (READ_ONCE(block_transition)) {
+		/*
+		 * Busy-wait until the sysfs writer has acknowledged a
+		 * blocked transition and clears the flag.
+		 */
+		msleep(20);
+	}
+
 	pr_info("%s exit\n", __func__);
 }
 
 static int test_klp_callbacks_busy_init(void)
 {
 	pr_info("%s\n", __func__);
-	schedule_delayed_work(&work,
-		msecs_to_jiffies(1000 * 0));
+	schedule_work(&work);
+
+	if (!block_transition) {
+		/*
+		 * Serialize output: print all messages from the work
+		 * function before returning from init().
+		 */
+		flush_work(&work);
+	}
+
 	return 0;
 }
 
 static void test_klp_callbacks_busy_exit(void)
 {
-	cancel_delayed_work_sync(&work);
+	WRITE_ONCE(block_transition, false);
+	flush_work(&work);
 	pr_info("%s\n", __func__);
 }
 
diff --git a/lib/livepatch/test_klp_shadow_vars.c b/lib/livepatch/test_klp_shadow_vars.c
index f0b5a1d24e55..b99116490858 100644
--- a/lib/livepatch/test_klp_shadow_vars.c
+++ b/lib/livepatch/test_klp_shadow_vars.c
@@ -109,8 +109,7 @@ static void shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor)
 static void shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor)
 {
 	klp_shadow_free_all(id, dtor);
-	pr_info("klp_%s(id=0x%lx, dtor=PTR%d)\n",
-		__func__, id, ptr_id(dtor));
+	pr_info("klp_%s(id=0x%lx, dtor=PTR%d)\n", __func__, id, ptr_id(dtor));
 }
 
 
@@ -124,12 +123,16 @@ static int shadow_ctor(void *obj, void *shadow_data, void *ctor_data)
 		return -EINVAL;
 
 	*sv = *var;
-	pr_info("%s: PTR%d -> PTR%d\n",
-		__func__, ptr_id(sv), ptr_id(*var));
+	pr_info("%s: PTR%d -> PTR%d\n", __func__, ptr_id(sv), ptr_id(*var));
 
 	return 0;
 }
 
+/*
+ * With more than one item to free in the list, order is not determined and
+ * shadow_dtor will not be passed to shadow_free_all() which would make the
+ * test fail. (see pass 6)
+ */
 static void shadow_dtor(void *obj, void *shadow_data)
 {
 	int **sv = shadow_data;
@@ -138,132 +141,153 @@ static void shadow_dtor(void *obj, void *shadow_data)
 		__func__, ptr_id(obj), ptr_id(sv));
 }
 
-static int test_klp_shadow_vars_init(void)
-{
-	void *obj			= THIS_MODULE;
-	int id			= 0x1234;
-	gfp_t gfp_flags		= GFP_KERNEL;
+/* number of objects we simulate that need shadow vars */
+#define NUM_OBJS 3
 
-	int var1, var2, var3, var4;
-	int *pv1, *pv2, *pv3, *pv4;
-	int **sv1, **sv2, **sv3, **sv4;
+/* dynamically created obj fields have the following shadow var id values */
+#define SV_ID1 0x1234
+#define SV_ID2 0x1235
 
-	int **sv;
+/*
+ * The main test case adds/removes new fields (shadow var) to each of these
+ * test structure instances. The last group of fields in the struct represent
+ * the idea that shadow variables may be added and removed to and from the
+ * struct during execution.
+ */
+struct test_object {
+	 /* add anything here below and avoid to define an empty struct */
+	struct shadow_ptr sp;
 
-	pv1 = &var1;
-	pv2 = &var2;
-	pv3 = &var3;
-	pv4 = &var4;
+	/* these represent shadow vars added and removed with SV_ID{1,2} */
+	/* char nfield1; */
+	/* int  nfield2; */
+};
+
+static int test_klp_shadow_vars_init(void)
+{
+	struct test_object objs[NUM_OBJS];
+	char nfields1[NUM_OBJS], *pnfields1[NUM_OBJS], **sv1[NUM_OBJS];
+	char *pndup[NUM_OBJS];
+	int nfields2[NUM_OBJS], *pnfields2[NUM_OBJS], **sv2[NUM_OBJS];
+	void **sv;
+	int ret;
+	int i;
 
 	ptr_id(NULL);
-	ptr_id(pv1);
-	ptr_id(pv2);
-	ptr_id(pv3);
-	ptr_id(pv4);
 
 	/*
 	 * With an empty shadow variable hash table, expect not to find
 	 * any matches.
 	 */
-	sv = shadow_get(obj, id);
+	sv = shadow_get(&objs[0], SV_ID1);
 	if (!sv)
 		pr_info("  got expected NULL result\n");
 
-	/*
-	 * Allocate a few shadow variables with different <obj> and <id>.
-	 */
-	sv1 = shadow_alloc(obj, id, sizeof(pv1), gfp_flags, shadow_ctor, &pv1);
-	if (!sv1)
-		return -ENOMEM;
-
-	sv2 = shadow_alloc(obj + 1, id, sizeof(pv2), gfp_flags, shadow_ctor, &pv2);
-	if (!sv2)
-		return -ENOMEM;
-
-	sv3 = shadow_alloc(obj, id + 1, sizeof(pv3), gfp_flags, shadow_ctor, &pv3);
-	if (!sv3)
-		return -ENOMEM;
-
-	/*
-	 * Verify we can find our new shadow variables and that they point
-	 * to expected data.
-	 */
-	sv = shadow_get(obj, id);
-	if (!sv)
-		return -EINVAL;
-	if (sv == sv1 && *sv1 == pv1)
-		pr_info("  got expected PTR%d -> PTR%d result\n",
-			ptr_id(sv1), ptr_id(*sv1));
-
-	sv = shadow_get(obj + 1, id);
-	if (!sv)
-		return -EINVAL;
-	if (sv == sv2 && *sv2 == pv2)
-		pr_info("  got expected PTR%d -> PTR%d result\n",
-			ptr_id(sv2), ptr_id(*sv2));
-	sv = shadow_get(obj, id + 1);
-	if (!sv)
-		return -EINVAL;
-	if (sv == sv3 && *sv3 == pv3)
-		pr_info("  got expected PTR%d -> PTR%d result\n",
-			ptr_id(sv3), ptr_id(*sv3));
-
-	/*
-	 * Allocate or get a few more, this time with the same <obj>, <id>.
-	 * The second invocation should return the same shadow var.
-	 */
-	sv4 = shadow_get_or_alloc(obj + 2, id, sizeof(pv4), gfp_flags, shadow_ctor, &pv4);
-	if (!sv4)
-		return -ENOMEM;
-
-	sv = shadow_get_or_alloc(obj + 2, id, sizeof(pv4), gfp_flags, shadow_ctor, &pv4);
-	if (!sv)
-		return -EINVAL;
-	if (sv == sv4 && *sv4 == pv4)
-		pr_info("  got expected PTR%d -> PTR%d result\n",
-			ptr_id(sv4), ptr_id(*sv4));
-
-	/*
-	 * Free the <obj=*, id> shadow variables and check that we can no
-	 * longer find them.
-	 */
-	shadow_free(obj, id, shadow_dtor);			/* sv1 */
-	sv = shadow_get(obj, id);
-	if (!sv)
-		pr_info("  got expected NULL result\n");
+	/* pass 1: init & alloc a char+int pair of svars for each objs */
+	for (i = 0; i < NUM_OBJS; i++) {
+		pnfields1[i] = &nfields1[i];
+		ptr_id(pnfields1[i]);
+
+		if (i % 2) {
+			sv1[i] = shadow_alloc(&objs[i], SV_ID1,
+					sizeof(pnfields1[i]), GFP_KERNEL,
+					shadow_ctor, &pnfields1[i]);
+		} else {
+			sv1[i] = shadow_get_or_alloc(&objs[i], SV_ID1,
+					sizeof(pnfields1[i]), GFP_KERNEL,
+					shadow_ctor, &pnfields1[i]);
+		}
+		if (!sv1[i]) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		pnfields2[i] = &nfields2[i];
+		ptr_id(pnfields2[i]);
+		sv2[i] = shadow_alloc(&objs[i], SV_ID2, sizeof(pnfields2[i]),
+					GFP_KERNEL, shadow_ctor, &pnfields2[i]);
+		if (!sv2[i]) {
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
 
-	shadow_free(obj + 1, id, shadow_dtor);			/* sv2 */
-	sv = shadow_get(obj + 1, id);
-	if (!sv)
-		pr_info("  got expected NULL result\n");
+	/* pass 2: verify we find allocated svars and where they point to */
+	for (i = 0; i < NUM_OBJS; i++) {
+		/* check the "char" svar for all objects */
+		sv = shadow_get(&objs[i], SV_ID1);
+		if (!sv) {
+			ret = -EINVAL;
+			goto out;
+		}
+		if ((char **)sv == sv1[i] && *sv1[i] == pnfields1[i])
+			pr_info("  got expected PTR%d -> PTR%d result\n",
+				ptr_id(sv1[i]), ptr_id(*sv1[i]));
+
+		/* check the "int" svar for all objects */
+		sv = shadow_get(&objs[i], SV_ID2);
+		if (!sv) {
+			ret = -EINVAL;
+			goto out;
+		}
+		if ((int **)sv == sv2[i] && *sv2[i] == pnfields2[i])
+			pr_info("  got expected PTR%d -> PTR%d result\n",
+				ptr_id(sv2[i]), ptr_id(*sv2[i]));
+	}
 
-	shadow_free(obj + 2, id, shadow_dtor);			/* sv4 */
-	sv = shadow_get(obj + 2, id);
-	if (!sv)
-		pr_info("  got expected NULL result\n");
+	/* pass 3: verify that 'get_or_alloc' returns already allocated svars */
+	for (i = 0; i < NUM_OBJS; i++) {
+		pndup[i] = &nfields1[i];
+		ptr_id(pndup[i]);
+
+		sv = shadow_get_or_alloc(&objs[i], SV_ID1, sizeof(pndup[i]),
+					GFP_KERNEL, shadow_ctor, &pndup[i]);
+		if (!sv) {
+			ret = -EINVAL;
+			goto out;
+		}
+		if ((char **)sv == sv1[i] && *sv1[i] == pnfields1[i])
+			pr_info("  got expected PTR%d -> PTR%d result\n",
+					ptr_id(sv1[i]), ptr_id(*sv1[i]));
+	}
 
-	/*
-	 * We should still find an <id+1> variable.
-	 */
-	sv = shadow_get(obj, id + 1);
-	if (!sv)
-		return -EINVAL;
-	if (sv == sv3 && *sv3 == pv3)
-		pr_info("  got expected PTR%d -> PTR%d result\n",
-			ptr_id(sv3), ptr_id(*sv3));
+	/* pass 4: free <objs[*], SV_ID1> pairs of svars, verify removal */
+	for (i = 0; i < NUM_OBJS; i++) {
+		shadow_free(&objs[i], SV_ID1, shadow_dtor); /* 'char' pairs */
+		sv = shadow_get(&objs[i], SV_ID1);
+		if (!sv)
+			pr_info("  got expected NULL result\n");
+	}
 
-	/*
-	 * Free all the <id+1> variables, too.
-	 */
-	shadow_free_all(id + 1, shadow_dtor);			/* sv3 */
-	sv = shadow_get(obj, id);
-	if (!sv)
-		pr_info("  shadow_get() got expected NULL result\n");
+	/* pass 5: check we still find <objs[*], SV_ID2> svar pairs */
+	for (i = 0; i < NUM_OBJS; i++) {
+		sv = shadow_get(&objs[i], SV_ID2);	/* 'int' pairs */
+		if (!sv) {
+			ret = -EINVAL;
+			goto out;
+		}
+		if ((int **)sv == sv2[i] && *sv2[i] == pnfields2[i])
+			pr_info("  got expected PTR%d -> PTR%d result\n",
+					ptr_id(sv2[i]), ptr_id(*sv2[i]));
+	}
 
+	/* pass 6: free all the <objs[*], SV_ID2> svar pairs too. */
+	shadow_free_all(SV_ID2, NULL);		/* 'int' pairs */
+	for (i = 0; i < NUM_OBJS; i++) {
+		sv = shadow_get(&objs[i], SV_ID2);
+		if (!sv)
+			pr_info("  got expected NULL result\n");
+	}
 
 	free_ptr_list();
 
 	return 0;
+out:
+	shadow_free_all(SV_ID1, NULL);		/* 'char' pairs */
+	shadow_free_all(SV_ID2, NULL);		/* 'int' pairs */
+	free_ptr_list();
+
+	return ret;
 }
 
 static void test_klp_shadow_vars_exit(void)
diff --git a/lib/logic_pio.c b/lib/logic_pio.c
index f511a99bb389..f32fe481b492 100644
--- a/lib/logic_pio.c
+++ b/lib/logic_pio.c
@@ -229,13 +229,13 @@ unsigned long logic_pio_trans_cpuaddr(resource_size_t addr)
 }
 
 #if defined(CONFIG_INDIRECT_PIO) && defined(PCI_IOBASE)
-#define BUILD_LOGIC_IO(bw, type)					\
-type logic_in##bw(unsigned long addr)					\
+#define BUILD_LOGIC_IO(bwl, type)					\
+type logic_in##bwl(unsigned long addr)					\
 {									\
 	type ret = (type)~0;						\
 									\
 	if (addr < MMIO_UPPER_LIMIT) {					\
-		ret = read##bw(PCI_IOBASE + addr);			\
+		ret = _in##bwl(addr);					\
 	} else if (addr >= MMIO_UPPER_LIMIT && addr < IO_SPACE_LIMIT) { \
 		struct logic_pio_hwaddr *entry = find_io_range(addr);	\
 									\
@@ -248,10 +248,10 @@ type logic_in##bw(unsigned long addr)					\
 	return ret;							\
 }									\
 									\
-void logic_out##bw(type value, unsigned long addr)			\
+void logic_out##bwl(type value, unsigned long addr)			\
 {									\
 	if (addr < MMIO_UPPER_LIMIT) {					\
-		write##bw(value, PCI_IOBASE + addr);			\
+		_out##bwl(value, addr);				\
 	} else if (addr >= MMIO_UPPER_LIMIT && addr < IO_SPACE_LIMIT) {	\
 		struct logic_pio_hwaddr *entry = find_io_range(addr);	\
 									\
@@ -263,11 +263,11 @@ void logic_out##bw(type value, unsigned long addr)			\
 	}								\
 }									\
 									\
-void logic_ins##bw(unsigned long addr, void *buffer,			\
-		   unsigned int count)					\
+void logic_ins##bwl(unsigned long addr, void *buffer,			\
+		    unsigned int count)					\
 {									\
 	if (addr < MMIO_UPPER_LIMIT) {					\
-		reads##bw(PCI_IOBASE + addr, buffer, count);		\
+		reads##bwl(PCI_IOBASE + addr, buffer, count);		\
 	} else if (addr >= MMIO_UPPER_LIMIT && addr < IO_SPACE_LIMIT) {	\
 		struct logic_pio_hwaddr *entry = find_io_range(addr);	\
 									\
@@ -280,11 +280,11 @@ void logic_ins##bw(unsigned long addr, void *buffer,			\
 									\
 }									\
 									\
-void logic_outs##bw(unsigned long addr, const void *buffer,		\
-		    unsigned int count)					\
+void logic_outs##bwl(unsigned long addr, const void *buffer,		\
+		     unsigned int count)				\
 {									\
 	if (addr < MMIO_UPPER_LIMIT) {					\
-		writes##bw(PCI_IOBASE + addr, buffer, count);		\
+		writes##bwl(PCI_IOBASE + addr, buffer, count);		\
 	} else if (addr >= MMIO_UPPER_LIMIT && addr < IO_SPACE_LIMIT) {	\
 		struct logic_pio_hwaddr *entry = find_io_range(addr);	\
 									\
diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c
index cc7b6d4cc7c7..90bb67994688 100644
--- a/lib/lz4/lz4_compress.c
+++ b/lib/lz4/lz4_compress.c
@@ -446,7 +446,7 @@ _last_literals:
 			*op++ = (BYTE)(lastRun << ML_BITS);
 		}
 
-		memcpy(op, anchor, lastRun);
+		LZ4_memcpy(op, anchor, lastRun);
 
 		op += lastRun;
 	}
@@ -708,7 +708,7 @@ _last_literals:
 		} else {
 			*op++ = (BYTE)(lastRunSize<<ML_BITS);
 		}
-		memcpy(op, anchor, lastRunSize);
+		LZ4_memcpy(op, anchor, lastRunSize);
 		op += lastRunSize;
 	}
 
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 0c9d3ad17e0f..00cb0d0b73e1 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -141,6 +141,9 @@ static FORCE_INLINE int LZ4_decompress_generic(
 		 * space in the output for those 18 bytes earlier, upon
 		 * entering the shortcut (in other words, there is a
 		 * combined check for both stages).
+		 *
+		 * The & in the likely() below is intentionally not && so that
+		 * some compilers can produce better parallelized runtime code
 		 */
 		if ((endOnInput ? length != RUN_MASK : length <= 8)
 		   /*
@@ -150,7 +153,7 @@ static FORCE_INLINE int LZ4_decompress_generic(
 		   && likely((endOnInput ? ip < shortiend : 1) &
 			     (op <= shortoend))) {
 			/* Copy the literals */
-			memcpy(op, ip, endOnInput ? 16 : 8);
+			LZ4_memcpy(op, ip, endOnInput ? 16 : 8);
 			op += length; ip += length;
 
 			/*
@@ -169,9 +172,9 @@ static FORCE_INLINE int LZ4_decompress_generic(
 			    (offset >= 8) &&
 			    (dict == withPrefix64k || match >= lowPrefix)) {
 				/* Copy the match. */
-				memcpy(op + 0, match + 0, 8);
-				memcpy(op + 8, match + 8, 8);
-				memcpy(op + 16, match + 16, 2);
+				LZ4_memcpy(op + 0, match + 0, 8);
+				LZ4_memcpy(op + 8, match + 8, 8);
+				LZ4_memcpy(op + 16, match + 16, 2);
 				op += length + MINMATCH;
 				/* Both stages worked, load the next token. */
 				continue;
@@ -260,7 +263,7 @@ static FORCE_INLINE int LZ4_decompress_generic(
 				}
 			}
 
-			memcpy(op, ip, length);
+			LZ4_memcpy(op, ip, length);
 			ip += length;
 			op += length;
 
@@ -347,7 +350,7 @@ _copy_match:
 				size_t const copySize = (size_t)(lowPrefix - match);
 				size_t const restSize = length - copySize;
 
-				memcpy(op, dictEnd - copySize, copySize);
+				LZ4_memcpy(op, dictEnd - copySize, copySize);
 				op += copySize;
 				if (restSize > (size_t)(op - lowPrefix)) {
 					/* overlap copy */
@@ -357,7 +360,7 @@ _copy_match:
 					while (op < endOfMatch)
 						*op++ = *copyFrom++;
 				} else {
-					memcpy(op, lowPrefix, restSize);
+					LZ4_memcpy(op, lowPrefix, restSize);
 					op += restSize;
 				}
 			}
@@ -383,7 +386,7 @@ _copy_match:
 				while (op < copyEnd)
 					*op++ = *match++;
 			} else {
-				memcpy(op, match, mlen);
+				LZ4_memcpy(op, match, mlen);
 			}
 			op = copyEnd;
 			if (op == oend)
@@ -397,7 +400,7 @@ _copy_match:
 			op[2] = match[2];
 			op[3] = match[3];
 			match += inc32table[offset];
-			memcpy(op + 4, match, 4);
+			LZ4_memcpy(op + 4, match, 4);
 			match -= dec64table[offset];
 		} else {
 			LZ4_copy8(op, match);
diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
index 1a7fa9d9170f..c91dd96ef629 100644
--- a/lib/lz4/lz4defs.h
+++ b/lib/lz4/lz4defs.h
@@ -137,6 +137,16 @@ static FORCE_INLINE void LZ4_writeLE16(void *memPtr, U16 value)
 	return put_unaligned_le16(value, memPtr);
 }
 
+/*
+ * LZ4 relies on memcpy with a constant size being inlined. In freestanding
+ * environments, the compiler can't assume the implementation of memcpy() is
+ * standard compliant, so apply its specialized memcpy() inlining logic. When
+ * possible, use __builtin_memcpy() to tell the compiler to analyze memcpy()
+ * as-if it were standard compliant, so it can inline it in freestanding
+ * environments. This is needed when decompressing the Linux Kernel, for example.
+ */
+#define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size)
+
 static FORCE_INLINE void LZ4_copy8(void *dst, const void *src)
 {
 #if LZ4_ARCH64
diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c
index 1b61d874e337..e7ac8694b797 100644
--- a/lib/lz4/lz4hc_compress.c
+++ b/lib/lz4/lz4hc_compress.c
@@ -570,7 +570,7 @@ _Search3:
 			*op++ = (BYTE) lastRun;
 		} else
 			*op++ = (BYTE)(lastRun<<ML_BITS);
-		memcpy(op, anchor, iend - anchor);
+		LZ4_memcpy(op, anchor, iend - anchor);
 		op += iend - anchor;
 	}
 
diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c
index 717c940112f9..8ad5ba2b86e2 100644
--- a/lib/lzo/lzo1x_compress.c
+++ b/lib/lzo/lzo1x_compress.c
@@ -268,6 +268,19 @@ m_len_done:
 				*op++ = (M4_MARKER | ((m_off >> 11) & 8)
 						| (m_len - 2));
 			else {
+				if (unlikely(((m_off & 0x403f) == 0x403f)
+						&& (m_len >= 261)
+						&& (m_len <= 264))
+						&& likely(bitstream_version)) {
+					// Under lzo-rle, block copies
+					// for 261 <= length <= 264 and
+					// (distance & 0x80f3) == 0x80f3
+					// can result in ambiguous
+					// output. Adjust length
+					// to 260 to prevent ambiguity.
+					ip -= m_len - 260;
+					m_len = 260;
+				}
 				m_len -= M4_MAX_LEN;
 				*op++ = (M4_MARKER | ((m_off >> 11) & 8));
 				while (unlikely(m_len > 255)) {
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 2717c7963acd..7892a40cf765 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -32,7 +32,7 @@
  * depending on the base count. Since the base count is taken from a u8
  * and a few bits, it is safe to assume that it will always be lower than
  * or equal to 2*255, thus we can always prevent any overflow by accepting
- * two less 255 steps. See Documentation/lzo.txt for more information.
+ * two less 255 steps. See Documentation/staging/lzo.rst for more information.
  */
 #define MAX_255_COUNT      ((((size_t)~0) / 255) - 2)
 
diff --git a/lib/math/Kconfig b/lib/math/Kconfig
index 15bd50d92308..f19bc9734fa7 100644
--- a/lib/math/Kconfig
+++ b/lib/math/Kconfig
@@ -6,7 +6,12 @@ config CORDIC
 	  calculations are in fixed point. Module will be called cordic.
 
 config PRIME_NUMBERS
-	tristate
+	tristate "Simple prime number generator for testing"
+	help
+	  This option provides a simple prime number generator for test
+	  modules.
+
+	  If unsure, say N.
 
 config RATIONAL
 	bool
diff --git a/lib/math/div64.c b/lib/math/div64.c
index 368ca7fd0d82..3952a07130d8 100644
--- a/lib/math/div64.c
+++ b/lib/math/div64.c
@@ -190,3 +190,44 @@ u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
 	return __iter_div_u64_rem(dividend, divisor, remainder);
 }
 EXPORT_SYMBOL(iter_div_u64_rem);
+
+#ifndef mul_u64_u64_div_u64
+u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 c)
+{
+	u64 res = 0, div, rem;
+	int shift;
+
+	/* can a * b overflow ? */
+	if (ilog2(a) + ilog2(b) > 62) {
+		/*
+		 * (b * a) / c is equal to
+		 *
+		 *      (b / c) * a +
+		 *      (b % c) * a / c
+		 *
+		 * if nothing overflows. Can the 1st multiplication
+		 * overflow? Yes, but we do not care: this can only
+		 * happen if the end result can't fit in u64 anyway.
+		 *
+		 * So the code below does
+		 *
+		 *      res = (b / c) * a;
+		 *      b = b % c;
+		 */
+		div = div64_u64_rem(b, c, &rem);
+		res = div * a;
+		b = rem;
+
+		shift = ilog2(a) + ilog2(b) - 62;
+		if (shift > 0) {
+			/* drop precision */
+			b >>= shift;
+			c >>= shift;
+			if (!c)
+				return res;
+		}
+	}
+
+	return res + div64_u64(a * b, c);
+}
+#endif
diff --git a/lib/math/prime_numbers.c b/lib/math/prime_numbers.c
index 052f5b727be7..d42cebf7407f 100644
--- a/lib/math/prime_numbers.c
+++ b/lib/math/prime_numbers.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#define pr_fmt(fmt) "prime numbers: " fmt "\n"
+#define pr_fmt(fmt) "prime numbers: " fmt
 
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -253,7 +253,7 @@ static void dump_primes(void)
 
 	if (buf)
 		bitmap_print_to_pagebuf(true, buf, p->primes, p->sz);
-	pr_info("primes.{last=%lu, .sz=%lu, .primes[]=...x%lx} = %s",
+	pr_info("primes.{last=%lu, .sz=%lu, .primes[]=...x%lx} = %s\n",
 		p->last, p->sz, p->primes[BITS_TO_LONGS(p->sz) - 1], buf);
 
 	rcu_read_unlock();
@@ -273,7 +273,7 @@ static int selftest(unsigned long max)
 		bool fast = is_prime_number(x);
 
 		if (slow != fast) {
-			pr_err("inconsistent result for is-prime(%lu): slow=%s, fast=%s!",
+			pr_err("inconsistent result for is-prime(%lu): slow=%s, fast=%s!\n",
 			       x, slow ? "yes" : "no", fast ? "yes" : "no");
 			goto err;
 		}
@@ -282,14 +282,14 @@ static int selftest(unsigned long max)
 			continue;
 
 		if (next_prime_number(last) != x) {
-			pr_err("incorrect result for next-prime(%lu): expected %lu, got %lu",
+			pr_err("incorrect result for next-prime(%lu): expected %lu, got %lu\n",
 			       last, x, next_prime_number(last));
 			goto err;
 		}
 		last = x;
 	}
 
-	pr_info("selftest(%lu) passed, last prime was %lu", x, last);
+	pr_info("%s(%lu) passed, last prime was %lu\n", __func__, x, last);
 	return 0;
 
 err:
diff --git a/lib/math/rational.c b/lib/math/rational.c
index 31fb27db2deb..df75c8809693 100644
--- a/lib/math/rational.c
+++ b/lib/math/rational.c
@@ -27,7 +27,7 @@
  * with the fractional part size described in given_denominator.
  *
  * for theoretical background, see:
- * http://en.wikipedia.org/wiki/Continued_fraction
+ * https://en.wikipedia.org/wiki/Continued_fraction
  */
 
 void rational_best_approximation(
diff --git a/lib/memregion.c b/lib/memregion.c
index 77c85b5251da..be5cfa5a3b57 100644
--- a/lib/memregion.c
+++ b/lib/memregion.c
@@ -2,6 +2,7 @@
 /* identifiers for device / performance-differentiated memory regions */
 #include <linux/idr.h>
 #include <linux/types.h>
+#include <linux/memregion.h>
 
 static DEFINE_IDA(memregion_ids);
 
diff --git a/lib/mpi/Makefile b/lib/mpi/Makefile
index d5874a7f5ff9..43b8fce14079 100644
--- a/lib/mpi/Makefile
+++ b/lib/mpi/Makefile
@@ -16,6 +16,7 @@ mpi-y = \
 	mpicoder.o			\
 	mpi-bit.o			\
 	mpi-cmp.o			\
+	mpi-sub-ui.o			\
 	mpih-cmp.o			\
 	mpih-div.o			\
 	mpih-mul.o			\
diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h
index 891e1c3549c4..afbd99987cf8 100644
--- a/lib/mpi/longlong.h
+++ b/lib/mpi/longlong.h
@@ -653,7 +653,7 @@ do {						\
 	**************  MIPS/64  **************
 	***************************************/
 #if (defined(__mips) && __mips >= 3) && W_TYPE_SIZE == 64
-#if defined(__mips_isa_rev) && __mips_isa_rev >= 6
+#if defined(__mips_isa_rev) && __mips_isa_rev >= 6 && defined(CONFIG_CC_IS_GCC)
 /*
  * GCC ends up emitting a __multi3 intrinsic call for MIPS64r6 with the plain C
  * code below, so we special case MIPS64r6 until the compiler can do better.
diff --git a/lib/mpi/mpi-sub-ui.c b/lib/mpi/mpi-sub-ui.c
new file mode 100644
index 000000000000..b41b082b5f3e
--- /dev/null
+++ b/lib/mpi/mpi-sub-ui.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* mpi-sub-ui.c - Subtract an unsigned integer from an MPI.
+ *
+ * Copyright 1991, 1993, 1994, 1996, 1999-2002, 2004, 2012, 2013, 2015
+ * Free Software Foundation, Inc.
+ *
+ * This file was based on the GNU MP Library source file:
+ * https://gmplib.org/repo/gmp-6.2/file/510b83519d1c/mpz/aors_ui.h
+ *
+ * The GNU MP Library is free software; you can redistribute it and/or modify
+ * it under the terms of either:
+ *
+ *   * the GNU Lesser General Public License as published by the Free
+ *     Software Foundation; either version 3 of the License, or (at your
+ *     option) any later version.
+ *
+ * or
+ *
+ *   * the GNU General Public License as published by the Free Software
+ *     Foundation; either version 2 of the License, or (at your option) any
+ *     later version.
+ *
+ * or both in parallel, as here.
+ *
+ * The GNU MP Library is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ *
+ * You should have received copies of the GNU General Public License and the
+ * GNU Lesser General Public License along with the GNU MP Library.  If not,
+ * see https://www.gnu.org/licenses/.
+ */
+
+#include "mpi-internal.h"
+
+int mpi_sub_ui(MPI w, MPI u, unsigned long vval)
+{
+	if (u->nlimbs == 0) {
+		if (mpi_resize(w, 1) < 0)
+			return -ENOMEM;
+		w->d[0] = vval;
+		w->nlimbs = (vval != 0);
+		w->sign = (vval != 0);
+		return 0;
+	}
+
+	/* If not space for W (and possible carry), increase space. */
+	if (mpi_resize(w, u->nlimbs + 1))
+		return -ENOMEM;
+
+	if (u->sign) {
+		mpi_limb_t cy;
+
+		cy = mpihelp_add_1(w->d, u->d, u->nlimbs, (mpi_limb_t) vval);
+		w->d[u->nlimbs] = cy;
+		w->nlimbs = u->nlimbs + cy;
+		w->sign = 1;
+	} else {
+		/* The signs are different.  Need exact comparison to determine
+		 * which operand to subtract from which.
+		 */
+		if (u->nlimbs == 1 && u->d[0] < vval) {
+			w->d[0] = vval - u->d[0];
+			w->nlimbs = 1;
+			w->sign = 1;
+		} else {
+			mpihelp_sub_1(w->d, u->d, u->nlimbs, (mpi_limb_t) vval);
+			/* Size can decrease with at most one limb. */
+			w->nlimbs = (u->nlimbs - (w->d[u->nlimbs - 1] == 0));
+			w->sign = 0;
+		}
+	}
+
+	mpi_normalize(w);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mpi_sub_ui);
diff --git a/lib/mpi/mpiutil.c b/lib/mpi/mpiutil.c
index 20ed0f766787..4cd2b335cb7f 100644
--- a/lib/mpi/mpiutil.c
+++ b/lib/mpi/mpiutil.c
@@ -69,7 +69,7 @@ void mpi_free_limb_space(mpi_ptr_t a)
 	if (!a)
 		return;
 
-	kzfree(a);
+	kfree_sensitive(a);
 }
 
 void mpi_assign_limb_space(MPI a, mpi_ptr_t ap, unsigned nlimbs)
@@ -95,7 +95,7 @@ int mpi_resize(MPI a, unsigned nlimbs)
 		if (!p)
 			return -ENOMEM;
 		memcpy(p, a->d, a->alloced * sizeof(mpi_limb_t));
-		kzfree(a->d);
+		kfree_sensitive(a->d);
 		a->d = p;
 	} else {
 		a->d = kcalloc(nlimbs, sizeof(mpi_limb_t), GFP_KERNEL);
@@ -112,7 +112,7 @@ void mpi_free(MPI a)
 		return;
 
 	if (a->flags & 4)
-		kzfree(a->d);
+		kfree_sensitive(a->d);
 	else
 		mpi_free_limb_space(a->d);
 
diff --git a/lib/nlattr.c b/lib/nlattr.c
index cace9b307781..bc5b5cf608c4 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -44,8 +44,22 @@ static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
 	[NLA_S64]	= sizeof(s64),
 };
 
+/*
+ * Nested policies might refer back to the original
+ * policy in some cases, and userspace could try to
+ * abuse that and recurse by nesting in the right
+ * ways. Limit recursion to avoid this problem.
+ */
+#define MAX_POLICY_RECURSION_DEPTH	10
+
+static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype,
+				const struct nla_policy *policy,
+				unsigned int validate,
+				struct netlink_ext_ack *extack,
+				struct nlattr **tb, unsigned int depth);
+
 static int validate_nla_bitfield32(const struct nlattr *nla,
-				   const u32 *valid_flags_mask)
+				   const u32 valid_flags_mask)
 {
 	const struct nla_bitfield32 *bf = nla_data(nla);
 
@@ -53,11 +67,11 @@ static int validate_nla_bitfield32(const struct nlattr *nla,
 		return -EINVAL;
 
 	/*disallow invalid bit selector */
-	if (bf->selector & ~*valid_flags_mask)
+	if (bf->selector & ~valid_flags_mask)
 		return -EINVAL;
 
 	/*disallow invalid bit values */
-	if (bf->value & ~*valid_flags_mask)
+	if (bf->value & ~valid_flags_mask)
 		return -EINVAL;
 
 	/*disallow valid bit values that are not selected*/
@@ -70,7 +84,7 @@ static int validate_nla_bitfield32(const struct nlattr *nla,
 static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
 			      const struct nla_policy *policy,
 			      struct netlink_ext_ack *extack,
-			      unsigned int validate)
+			      unsigned int validate, unsigned int depth)
 {
 	const struct nlattr *entry;
 	int rem;
@@ -87,8 +101,9 @@ static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
 			return -ERANGE;
 		}
 
-		ret = __nla_validate(nla_data(entry), nla_len(entry),
-				     maxtype, policy, validate, extack);
+		ret = __nla_validate_parse(nla_data(entry), nla_len(entry),
+					   maxtype, policy, validate, extack,
+					   NULL, depth + 1);
 		if (ret < 0)
 			return ret;
 	}
@@ -96,17 +111,58 @@ static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
 	return 0;
 }
 
-static int nla_validate_int_range(const struct nla_policy *pt,
-				  const struct nlattr *nla,
-				  struct netlink_ext_ack *extack)
+void nla_get_range_unsigned(const struct nla_policy *pt,
+			    struct netlink_range_validation *range)
 {
-	bool validate_min, validate_max;
-	s64 value;
+	WARN_ON_ONCE(pt->validation_type != NLA_VALIDATE_RANGE_PTR &&
+		     (pt->min < 0 || pt->max < 0));
 
-	validate_min = pt->validation_type == NLA_VALIDATE_RANGE ||
-		       pt->validation_type == NLA_VALIDATE_MIN;
-	validate_max = pt->validation_type == NLA_VALIDATE_RANGE ||
-		       pt->validation_type == NLA_VALIDATE_MAX;
+	range->min = 0;
+
+	switch (pt->type) {
+	case NLA_U8:
+		range->max = U8_MAX;
+		break;
+	case NLA_U16:
+		range->max = U16_MAX;
+		break;
+	case NLA_U32:
+		range->max = U32_MAX;
+		break;
+	case NLA_U64:
+	case NLA_MSECS:
+		range->max = U64_MAX;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	switch (pt->validation_type) {
+	case NLA_VALIDATE_RANGE:
+		range->min = pt->min;
+		range->max = pt->max;
+		break;
+	case NLA_VALIDATE_RANGE_PTR:
+		*range = *pt->range;
+		break;
+	case NLA_VALIDATE_MIN:
+		range->min = pt->min;
+		break;
+	case NLA_VALIDATE_MAX:
+		range->max = pt->max;
+		break;
+	default:
+		break;
+	}
+}
+
+static int nla_validate_int_range_unsigned(const struct nla_policy *pt,
+					   const struct nlattr *nla,
+					   struct netlink_ext_ack *extack)
+{
+	struct netlink_range_validation range;
+	u64 value;
 
 	switch (pt->type) {
 	case NLA_U8:
@@ -118,6 +174,77 @@ static int nla_validate_int_range(const struct nla_policy *pt,
 	case NLA_U32:
 		value = nla_get_u32(nla);
 		break;
+	case NLA_U64:
+	case NLA_MSECS:
+		value = nla_get_u64(nla);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	nla_get_range_unsigned(pt, &range);
+
+	if (value < range.min || value > range.max) {
+		NL_SET_ERR_MSG_ATTR(extack, nla,
+				    "integer out of range");
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+void nla_get_range_signed(const struct nla_policy *pt,
+			  struct netlink_range_validation_signed *range)
+{
+	switch (pt->type) {
+	case NLA_S8:
+		range->min = S8_MIN;
+		range->max = S8_MAX;
+		break;
+	case NLA_S16:
+		range->min = S16_MIN;
+		range->max = S16_MAX;
+		break;
+	case NLA_S32:
+		range->min = S32_MIN;
+		range->max = S32_MAX;
+		break;
+	case NLA_S64:
+		range->min = S64_MIN;
+		range->max = S64_MAX;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	switch (pt->validation_type) {
+	case NLA_VALIDATE_RANGE:
+		range->min = pt->min;
+		range->max = pt->max;
+		break;
+	case NLA_VALIDATE_RANGE_PTR:
+		*range = *pt->range_signed;
+		break;
+	case NLA_VALIDATE_MIN:
+		range->min = pt->min;
+		break;
+	case NLA_VALIDATE_MAX:
+		range->max = pt->max;
+		break;
+	default:
+		break;
+	}
+}
+
+static int nla_validate_int_range_signed(const struct nla_policy *pt,
+					 const struct nlattr *nla,
+					 struct netlink_ext_ack *extack)
+{
+	struct netlink_range_validation_signed range;
+	s64 value;
+
+	switch (pt->type) {
 	case NLA_S8:
 		value = nla_get_s8(nla);
 		break;
@@ -130,22 +257,13 @@ static int nla_validate_int_range(const struct nla_policy *pt,
 	case NLA_S64:
 		value = nla_get_s64(nla);
 		break;
-	case NLA_U64:
-		/* treat this one specially, since it may not fit into s64 */
-		if ((validate_min && nla_get_u64(nla) < pt->min) ||
-		    (validate_max && nla_get_u64(nla) > pt->max)) {
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "integer out of range");
-			return -ERANGE;
-		}
-		return 0;
 	default:
-		WARN_ON(1);
 		return -EINVAL;
 	}
 
-	if ((validate_min && value < pt->min) ||
-	    (validate_max && value > pt->max)) {
+	nla_get_range_signed(pt, &range);
+
+	if (value < range.min || value > range.max) {
 		NL_SET_ERR_MSG_ATTR(extack, nla,
 				    "integer out of range");
 		return -ERANGE;
@@ -154,9 +272,31 @@ static int nla_validate_int_range(const struct nla_policy *pt,
 	return 0;
 }
 
+static int nla_validate_int_range(const struct nla_policy *pt,
+				  const struct nlattr *nla,
+				  struct netlink_ext_ack *extack)
+{
+	switch (pt->type) {
+	case NLA_U8:
+	case NLA_U16:
+	case NLA_U32:
+	case NLA_U64:
+	case NLA_MSECS:
+		return nla_validate_int_range_unsigned(pt, nla, extack);
+	case NLA_S8:
+	case NLA_S16:
+	case NLA_S32:
+	case NLA_S64:
+		return nla_validate_int_range_signed(pt, nla, extack);
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+}
+
 static int validate_nla(const struct nlattr *nla, int maxtype,
 			const struct nla_policy *policy, unsigned int validate,
-			struct netlink_ext_ack *extack)
+			struct netlink_ext_ack *extack, unsigned int depth)
 {
 	u16 strict_start_type = policy[0].strict_start_type;
 	const struct nla_policy *pt;
@@ -174,7 +314,9 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 	BUG_ON(pt->type > NLA_TYPE_MAX);
 
 	if ((nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) ||
-	    (pt->type == NLA_EXACT_LEN_WARN && attrlen != pt->len)) {
+	    (pt->type == NLA_EXACT_LEN &&
+	     pt->validation_type == NLA_VALIDATE_WARN_TOO_LONG &&
+	     attrlen != pt->len)) {
 		pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
 				    current->comm, type);
 		if (validate & NL_VALIDATE_STRICT_ATTRS) {
@@ -200,15 +342,10 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 	}
 
 	switch (pt->type) {
-	case NLA_EXACT_LEN:
-		if (attrlen != pt->len)
-			goto out_err;
-		break;
-
 	case NLA_REJECT:
-		if (extack && pt->validation_data) {
+		if (extack && pt->reject_message) {
 			NL_SET_BAD_ATTR(extack, nla);
-			extack->_msg = pt->validation_data;
+			extack->_msg = pt->reject_message;
 			return -EINVAL;
 		}
 		err = -EINVAL;
@@ -223,7 +360,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 		if (attrlen != sizeof(struct nla_bitfield32))
 			goto out_err;
 
-		err = validate_nla_bitfield32(nla, pt->validation_data);
+		err = validate_nla_bitfield32(nla, pt->bitfield32_valid);
 		if (err)
 			goto out_err;
 		break;
@@ -268,10 +405,11 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 			break;
 		if (attrlen < NLA_HDRLEN)
 			goto out_err;
-		if (pt->validation_data) {
-			err = __nla_validate(nla_data(nla), nla_len(nla), pt->len,
-					     pt->validation_data, validate,
-					     extack);
+		if (pt->nested_policy) {
+			err = __nla_validate_parse(nla_data(nla), nla_len(nla),
+						   pt->len, pt->nested_policy,
+						   validate, extack, NULL,
+						   depth + 1);
 			if (err < 0) {
 				/*
 				 * return directly to preserve the inner
@@ -289,12 +427,12 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 			break;
 		if (attrlen < NLA_HDRLEN)
 			goto out_err;
-		if (pt->validation_data) {
+		if (pt->nested_policy) {
 			int err;
 
 			err = nla_validate_array(nla_data(nla), nla_len(nla),
-						 pt->len, pt->validation_data,
-						 extack, validate);
+						 pt->len, pt->nested_policy,
+						 extack, validate, depth);
 			if (err < 0) {
 				/*
 				 * return directly to preserve the inner
@@ -317,6 +455,13 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 			goto out_err;
 		break;
 
+	case NLA_EXACT_LEN:
+		if (pt->validation_type != NLA_VALIDATE_WARN_TOO_LONG) {
+			if (attrlen != pt->len)
+				goto out_err;
+			break;
+		}
+		/* fall through */
 	default:
 		if (pt->len)
 			minlen = pt->len;
@@ -332,6 +477,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 	case NLA_VALIDATE_NONE:
 		/* nothing to do */
 		break;
+	case NLA_VALIDATE_RANGE_PTR:
 	case NLA_VALIDATE_RANGE:
 	case NLA_VALIDATE_MIN:
 	case NLA_VALIDATE_MAX:
@@ -358,11 +504,17 @@ static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype,
 				const struct nla_policy *policy,
 				unsigned int validate,
 				struct netlink_ext_ack *extack,
-				struct nlattr **tb)
+				struct nlattr **tb, unsigned int depth)
 {
 	const struct nlattr *nla;
 	int rem;
 
+	if (depth >= MAX_POLICY_RECURSION_DEPTH) {
+		NL_SET_ERR_MSG(extack,
+			       "allowed policy recursion depth exceeded");
+		return -EINVAL;
+	}
+
 	if (tb)
 		memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
 
@@ -379,7 +531,7 @@ static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype,
 		}
 		if (policy) {
 			int err = validate_nla(nla, maxtype, policy,
-					       validate, extack);
+					       validate, extack, depth);
 
 			if (err < 0)
 				return err;
@@ -421,7 +573,7 @@ int __nla_validate(const struct nlattr *head, int len, int maxtype,
 		   struct netlink_ext_ack *extack)
 {
 	return __nla_validate_parse(head, len, maxtype, policy, validate,
-				    extack, NULL);
+				    extack, NULL, 0);
 }
 EXPORT_SYMBOL(__nla_validate);
 
@@ -476,7 +628,7 @@ int __nla_parse(struct nlattr **tb, int maxtype,
 		struct netlink_ext_ack *extack)
 {
 	return __nla_validate_parse(head, len, maxtype, policy, validate,
-				    extack, tb);
+				    extack, tb, 0);
 }
 EXPORT_SYMBOL(__nla_parse);
 
diff --git a/lib/packing.c b/lib/packing.c
index 50d1e9f2f5a7..6ed72dccfdb5 100644
--- a/lib/packing.c
+++ b/lib/packing.c
@@ -73,6 +73,7 @@ static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit,
  * @endbit: The index (in logical notation, compensated for quirks) where
  *	    the packed value ends within pbuf. Must be smaller than, or equal
  *	    to, startbit.
+ * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf.
  * @op: If PACK, then uval will be treated as const pointer and copied (packed)
  *	into pbuf, between startbit and endbit.
  *	If UNPACK, then pbuf will be treated as const pointer and the logical
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 8d092609928e..0ba686b8fe57 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#define pr_fmt(fmt) "%s: " fmt "\n", __func__
+#define pr_fmt(fmt) "%s: " fmt, __func__
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -141,8 +141,8 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
 	for_each_possible_cpu(cpu)
 		count += *per_cpu_ptr(percpu_count, cpu);
 
-	pr_debug("global %ld percpu %ld",
-		 atomic_long_read(&ref->count), (long)count);
+	pr_debug("global %lu percpu %lu\n",
+		 atomic_long_read(&ref->count), count);
 
 	/*
 	 * It's crucial that we sum the percpu counters _before_ adding the sum
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index a66595ba5543..a2345de90e93 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -99,6 +99,25 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 EXPORT_SYMBOL(percpu_counter_add_batch);
 
 /*
+ * For percpu_counter with a big batch, the devication of its count could
+ * be big, and there is requirement to reduce the deviation, like when the
+ * counter's batch could be runtime decreased to get a better accuracy,
+ * which can be achieved by running this sync function on each CPU.
+ */
+void percpu_counter_sync(struct percpu_counter *fbc)
+{
+	unsigned long flags;
+	s64 count;
+
+	raw_spin_lock_irqsave(&fbc->lock, flags);
+	count = __this_cpu_read(*fbc->counters);
+	fbc->count += count;
+	__this_cpu_sub(*fbc->counters, count);
+	raw_spin_unlock_irqrestore(&fbc->lock, flags);
+}
+EXPORT_SYMBOL(percpu_counter_sync);
+
+/*
  * Add up all the per-cpu counts, return the result.  This is a more accurate
  * but much slower version of percpu_counter_read_positive()
  */
diff --git a/lib/pldmfw/Makefile b/lib/pldmfw/Makefile
new file mode 100644
index 000000000000..99ad10711abe
--- /dev/null
+++ b/lib/pldmfw/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_PLDMFW)	+= pldmfw.o
diff --git a/lib/pldmfw/pldmfw.c b/lib/pldmfw/pldmfw.c
new file mode 100644
index 000000000000..e5d4b3b2af81
--- /dev/null
+++ b/lib/pldmfw/pldmfw.c
@@ -0,0 +1,879 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2018-2019, Intel Corporation. */
+
+#include <asm/unaligned.h>
+#include <linux/crc32.h>
+#include <linux/device.h>
+#include <linux/firmware.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pldmfw.h>
+#include <linux/slab.h>
+#include <linux/uuid.h>
+
+#include "pldmfw_private.h"
+
+/* Internal structure used to store details about the PLDM image file as it is
+ * being validated and processed.
+ */
+struct pldmfw_priv {
+	struct pldmfw *context;
+	const struct firmware *fw;
+
+	/* current offset of firmware image */
+	size_t offset;
+
+	struct list_head records;
+	struct list_head components;
+
+	/* PLDM Firmware Package Header */
+	const struct __pldm_header *header;
+	u16 total_header_size;
+
+	/* length of the component bitmap */
+	u16 component_bitmap_len;
+	u16 bitmap_size;
+
+	/* Start of the component image information */
+	u16 component_count;
+	const u8 *component_start;
+
+	/* Start pf the firmware device id records */
+	const u8 *record_start;
+	u8 record_count;
+
+	/* The CRC at the end of the package header */
+	u32 header_crc;
+
+	struct pldmfw_record *matching_record;
+};
+
+/**
+ * pldm_check_fw_space - Verify that the firmware image has space left
+ * @data: pointer to private data
+ * @offset: offset to start from
+ * @length: length to check for
+ *
+ * Verify that the firmware data can hold a chunk of bytes with the specified
+ * offset and length.
+ *
+ * Returns: zero on success, or -EFAULT if the image does not have enough
+ * space left to fit the expected length.
+ */
+static int
+pldm_check_fw_space(struct pldmfw_priv *data, size_t offset, size_t length)
+{
+	size_t expected_size = offset + length;
+	struct device *dev = data->context->dev;
+
+	if (data->fw->size < expected_size) {
+		dev_dbg(dev, "Firmware file size smaller than expected. Got %zu bytes, needed %zu bytes\n",
+			data->fw->size, expected_size);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_move_fw_offset - Move the current firmware offset forward
+ * @data: pointer to private data
+ * @bytes_to_move: number of bytes to move the offset forward by
+ *
+ * Check that there is enough space past the current offset, and then move the
+ * offset forward by this ammount.
+ *
+ * Returns: zero on success, or -EFAULT if the image is too small to fit the
+ * expected length.
+ */
+static int
+pldm_move_fw_offset(struct pldmfw_priv *data, size_t bytes_to_move)
+{
+	int err;
+
+	err = pldm_check_fw_space(data, data->offset, bytes_to_move);
+	if (err)
+		return err;
+
+	data->offset += bytes_to_move;
+
+	return 0;
+}
+
+/**
+ * pldm_parse_header - Validate and extract details about the PLDM header
+ * @data: pointer to private data
+ *
+ * Performs initial basic verification of the PLDM image, up to the first
+ * firmware record.
+ *
+ * This includes the following checks and extractions
+ *
+ *   * Verify that the UUID at the start of the header matches the expected
+ *     value as defined in the DSP0267 PLDM specification
+ *   * Check that the revision is 0x01
+ *   * Extract the total header_size and verify that the image is large enough
+ *     to contain at least the length of this header
+ *   * Extract the size of the component bitmap length
+ *   * Extract a pointer to the start of the record area
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int pldm_parse_header(struct pldmfw_priv *data)
+{
+	const struct __pldmfw_record_area *record_area;
+	struct device *dev = data->context->dev;
+	const struct __pldm_header *header;
+	size_t header_size;
+	int err;
+
+	err = pldm_move_fw_offset(data, sizeof(*header));
+	if (err)
+		return err;
+
+	header = (const struct __pldm_header *)data->fw->data;
+	data->header = header;
+
+	if (!uuid_equal(&header->id, &pldm_firmware_header_id)) {
+		dev_dbg(dev, "Invalid package header identifier. Expected UUID %pUB, but got %pUB\n",
+			&pldm_firmware_header_id, &header->id);
+		return -EINVAL;
+	}
+
+	if (header->revision != PACKAGE_HEADER_FORMAT_REVISION) {
+		dev_dbg(dev, "Invalid package header revision. Expected revision %u but got %u\n",
+			PACKAGE_HEADER_FORMAT_REVISION, header->revision);
+		return -EOPNOTSUPP;
+	}
+
+	data->total_header_size = get_unaligned_le16(&header->size);
+	header_size = data->total_header_size - sizeof(*header);
+
+	err = pldm_check_fw_space(data, data->offset, header_size);
+	if (err)
+		return err;
+
+	data->component_bitmap_len =
+		get_unaligned_le16(&header->component_bitmap_len);
+
+	if (data->component_bitmap_len % 8 != 0) {
+		dev_dbg(dev, "Invalid component bitmap length. The length is %u, which is not a multiple of 8\n",
+			data->component_bitmap_len);
+		return -EINVAL;
+	}
+
+	data->bitmap_size = data->component_bitmap_len / 8;
+
+	err = pldm_move_fw_offset(data, header->version_len);
+	if (err)
+		return err;
+
+	/* extract a pointer to the record area, which just follows the main
+	 * PLDM header data.
+	 */
+	record_area = (const struct __pldmfw_record_area *)(data->fw->data +
+							 data->offset);
+
+	err = pldm_move_fw_offset(data, sizeof(*record_area));
+	if (err)
+		return err;
+
+	data->record_count = record_area->record_count;
+	data->record_start = record_area->records;
+
+	return 0;
+}
+
+/**
+ * pldm_check_desc_tlv_len - Check that the length matches expectation
+ * @data: pointer to image details
+ * @type: the descriptor type
+ * @size: the length from the descriptor header
+ *
+ * If the descriptor type is one of the documented descriptor types according
+ * to the standard, verify that the provided length matches.
+ *
+ * If the type is not recognized or is VENDOR_DEFINED, return zero.
+ *
+ * Returns: zero on success, or -EINVAL if the specified size of a standard
+ * TLV does not match the expected value defined for that TLV.
+ */
+static int
+pldm_check_desc_tlv_len(struct pldmfw_priv *data, u16 type, u16 size)
+{
+	struct device *dev = data->context->dev;
+	u16 expected_size;
+
+	switch (type) {
+	case PLDM_DESC_ID_PCI_VENDOR_ID:
+	case PLDM_DESC_ID_PCI_DEVICE_ID:
+	case PLDM_DESC_ID_PCI_SUBVENDOR_ID:
+	case PLDM_DESC_ID_PCI_SUBDEV_ID:
+		expected_size = 2;
+		break;
+	case PLDM_DESC_ID_PCI_REVISION_ID:
+		expected_size = 1;
+		break;
+	case PLDM_DESC_ID_PNP_VENDOR_ID:
+		expected_size = 3;
+		break;
+	case PLDM_DESC_ID_IANA_ENTERPRISE_ID:
+	case PLDM_DESC_ID_ACPI_VENDOR_ID:
+	case PLDM_DESC_ID_PNP_PRODUCT_ID:
+	case PLDM_DESC_ID_ACPI_PRODUCT_ID:
+		expected_size = 4;
+		break;
+	case PLDM_DESC_ID_UUID:
+		expected_size = 16;
+		break;
+	case PLDM_DESC_ID_VENDOR_DEFINED:
+		return 0;
+	default:
+		/* Do not report an error on an unexpected TLV */
+		dev_dbg(dev, "Found unrecognized TLV type 0x%04x\n", type);
+		return 0;
+	}
+
+	if (size != expected_size) {
+		dev_dbg(dev, "Found TLV type 0x%04x with unexpected length. Got %u bytes, but expected %u bytes\n",
+			type, size, expected_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_parse_desc_tlvs - Check and skip past a number of TLVs
+ * @data: pointer to private data
+ * @record: pointer to the record this TLV belongs too
+ * @desc_count: descriptor count
+ *
+ * From the current offset, read and extract the descriptor TLVs, updating the
+ * current offset each time.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int
+pldm_parse_desc_tlvs(struct pldmfw_priv *data, struct pldmfw_record *record, u8 desc_count)
+{
+	const struct __pldmfw_desc_tlv *__desc;
+	const u8 *desc_start;
+	u8 i;
+
+	desc_start = data->fw->data + data->offset;
+
+	pldm_for_each_desc_tlv(i, __desc, desc_start, desc_count) {
+		struct pldmfw_desc_tlv *desc;
+		int err;
+		u16 type, size;
+
+		err = pldm_move_fw_offset(data, sizeof(*__desc));
+		if (err)
+			return err;
+
+		type = get_unaligned_le16(&__desc->type);
+
+		/* According to DSP0267, this only includes the data field */
+		size = get_unaligned_le16(&__desc->size);
+
+		err = pldm_check_desc_tlv_len(data, type, size);
+		if (err)
+			return err;
+
+		/* check that we have space and move the offset forward */
+		err = pldm_move_fw_offset(data, size);
+		if (err)
+			return err;
+
+		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+		if (!desc)
+			return -ENOMEM;
+
+		desc->type = type;
+		desc->size = size;
+		desc->data = __desc->data;
+
+		list_add_tail(&desc->entry, &record->descs);
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_parse_one_record - Verify size of one PLDM record
+ * @data: pointer to image details
+ * @__record: pointer to the record to check
+ *
+ * This function checks that the record size does not exceed either the size
+ * of the firmware file or the total length specified in the header section.
+ *
+ * It also verifies that the recorded length of the start of the record
+ * matches the size calculated by adding the static structure length, the
+ * component bitmap length, the version string length, the length of all
+ * descriptor TLVs, and the length of the package data.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int
+pldm_parse_one_record(struct pldmfw_priv *data,
+		      const struct __pldmfw_record_info *__record)
+{
+	struct pldmfw_record *record;
+	size_t measured_length;
+	int err;
+	const u8 *bitmap_ptr;
+	u16 record_len;
+	int i;
+
+	/* Make a copy and insert it into the record list */
+	record = kzalloc(sizeof(*record), GFP_KERNEL);
+	if (!record)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&record->descs);
+	list_add_tail(&record->entry, &data->records);
+
+	/* Then check that we have space and move the offset */
+	err = pldm_move_fw_offset(data, sizeof(*__record));
+	if (err)
+		return err;
+
+	record_len = get_unaligned_le16(&__record->record_len);
+	record->package_data_len = get_unaligned_le16(&__record->package_data_len);
+	record->version_len = __record->version_len;
+	record->version_type = __record->version_type;
+
+	bitmap_ptr = data->fw->data + data->offset;
+
+	/* check that we have space for the component bitmap length */
+	err = pldm_move_fw_offset(data, data->bitmap_size);
+	if (err)
+		return err;
+
+	record->component_bitmap_len = data->component_bitmap_len;
+	record->component_bitmap = bitmap_zalloc(record->component_bitmap_len,
+						 GFP_KERNEL);
+	if (!record->component_bitmap)
+		return -ENOMEM;
+
+	for (i = 0; i < data->bitmap_size; i++)
+		bitmap_set_value8(record->component_bitmap, bitmap_ptr[i], i * 8);
+
+	record->version_string = data->fw->data + data->offset;
+
+	err = pldm_move_fw_offset(data, record->version_len);
+	if (err)
+		return err;
+
+	/* Scan through the descriptor TLVs and find the end */
+	err = pldm_parse_desc_tlvs(data, record, __record->descriptor_count);
+	if (err)
+		return err;
+
+	record->package_data = data->fw->data + data->offset;
+
+	err = pldm_move_fw_offset(data, record->package_data_len);
+	if (err)
+		return err;
+
+	measured_length = data->offset - ((const u8 *)__record - data->fw->data);
+	if (measured_length != record_len) {
+		dev_dbg(data->context->dev, "Unexpected record length. Measured record length is %zu bytes, expected length is %u bytes\n",
+			measured_length, record_len);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_parse_records - Locate the start of the component area
+ * @data: pointer to private data
+ *
+ * Extract the record count, and loop through each record, searching for the
+ * component area.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int pldm_parse_records(struct pldmfw_priv *data)
+{
+	const struct __pldmfw_component_area *component_area;
+	const struct __pldmfw_record_info *record;
+	int err;
+	u8 i;
+
+	pldm_for_each_record(i, record, data->record_start, data->record_count) {
+		err = pldm_parse_one_record(data, record);
+		if (err)
+			return err;
+	}
+
+	/* Extract a pointer to the component area, which just follows the
+	 * PLDM device record data.
+	 */
+	component_area = (const struct __pldmfw_component_area *)(data->fw->data + data->offset);
+
+	err = pldm_move_fw_offset(data, sizeof(*component_area));
+	if (err)
+		return err;
+
+	data->component_count =
+		get_unaligned_le16(&component_area->component_image_count);
+	data->component_start = component_area->components;
+
+	return 0;
+}
+
+/**
+ * pldm_parse_components - Locate the CRC header checksum
+ * @data: pointer to private data
+ *
+ * Extract the component count, and find the pointer to the component area.
+ * Scan through each component searching for the end, which should point to
+ * the package header checksum.
+ *
+ * Extract the package header CRC and save it for verification.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int pldm_parse_components(struct pldmfw_priv *data)
+{
+	const struct __pldmfw_component_info *__component;
+	struct device *dev = data->context->dev;
+	const u8 *header_crc_ptr;
+	int err;
+	u8 i;
+
+	pldm_for_each_component(i, __component, data->component_start, data->component_count) {
+		struct pldmfw_component *component;
+		u32 offset, size;
+
+		err = pldm_move_fw_offset(data, sizeof(*__component));
+		if (err)
+			return err;
+
+		err = pldm_move_fw_offset(data, __component->version_len);
+		if (err)
+			return err;
+
+		offset = get_unaligned_le32(&__component->location_offset);
+		size = get_unaligned_le32(&__component->size);
+
+		err = pldm_check_fw_space(data, offset, size);
+		if (err)
+			return err;
+
+		component = kzalloc(sizeof(*component), GFP_KERNEL);
+		if (!component)
+			return -ENOMEM;
+
+		component->index = i;
+		component->classification = get_unaligned_le16(&__component->classification);
+		component->identifier = get_unaligned_le16(&__component->identifier);
+		component->comparison_stamp = get_unaligned_le32(&__component->comparison_stamp);
+		component->options = get_unaligned_le16(&__component->options);
+		component->activation_method = get_unaligned_le16(&__component->activation_method);
+		component->version_type = __component->version_type;
+		component->version_len = __component->version_len;
+		component->version_string = __component->version_string;
+		component->component_data = data->fw->data + offset;
+		component->component_size = size;
+
+		list_add_tail(&component->entry, &data->components);
+	}
+
+	header_crc_ptr = data->fw->data + data->offset;
+
+	err = pldm_move_fw_offset(data, sizeof(data->header_crc));
+	if (err)
+		return err;
+
+	/* Make sure that we reached the expected offset */
+	if (data->offset != data->total_header_size) {
+		dev_dbg(dev, "Invalid firmware header size. Expected %u but got %zu\n",
+			data->total_header_size, data->offset);
+		return -EFAULT;
+	}
+
+	data->header_crc = get_unaligned_le32(header_crc_ptr);
+
+	return 0;
+}
+
+/**
+ * pldm_verify_header_crc - Verify that the CRC in the header matches
+ * @data: pointer to private data
+ *
+ * Calculates the 32-bit CRC using the standard IEEE 802.3 CRC polynomial and
+ * compares it to the value stored in the header.
+ *
+ * Returns: zero on success if the CRC matches, or -EBADMSG on an invalid CRC.
+ */
+static int pldm_verify_header_crc(struct pldmfw_priv *data)
+{
+	struct device *dev = data->context->dev;
+	u32 calculated_crc;
+	size_t length;
+
+	/* Calculate the 32-bit CRC of the header header contents up to but
+	 * not including the checksum. Note that the Linux crc32_le function
+	 * does not perform an expected final XOR.
+	 */
+	length = data->offset - sizeof(data->header_crc);
+	calculated_crc = crc32_le(~0, data->fw->data, length) ^ ~0;
+
+	if (calculated_crc != data->header_crc) {
+		dev_dbg(dev, "Invalid CRC in firmware header. Got 0x%08x but expected 0x%08x\n",
+			calculated_crc, data->header_crc);
+		return -EBADMSG;
+	}
+
+	return 0;
+}
+
+/**
+ * pldmfw_free_priv - Free memory allocated while parsing the PLDM image
+ * @data: pointer to the PLDM data structure
+ *
+ * Loops through and clears all allocated memory associated with each
+ * allocated descriptor, record, and component.
+ */
+static void pldmfw_free_priv(struct pldmfw_priv *data)
+{
+	struct pldmfw_component *component, *c_safe;
+	struct pldmfw_record *record, *r_safe;
+	struct pldmfw_desc_tlv *desc, *d_safe;
+
+	list_for_each_entry_safe(component, c_safe, &data->components, entry) {
+		list_del(&component->entry);
+		kfree(component);
+	}
+
+	list_for_each_entry_safe(record, r_safe, &data->records, entry) {
+		list_for_each_entry_safe(desc, d_safe, &record->descs, entry) {
+			list_del(&desc->entry);
+			kfree(desc);
+		}
+
+		if (record->component_bitmap) {
+			bitmap_free(record->component_bitmap);
+			record->component_bitmap = NULL;
+		}
+
+		list_del(&record->entry);
+		kfree(record);
+	}
+}
+
+/**
+ * pldm_parse_image - parse and extract details from PLDM image
+ * @data: pointer to private data
+ *
+ * Verify that the firmware file contains valid data for a PLDM firmware
+ * file. Extract useful pointers and data from the firmware file and store
+ * them in the data structure.
+ *
+ * The PLDM firmware file format is defined in DMTF DSP0267 1.0.0. Care
+ * should be taken to use get_unaligned_le* when accessing data from the
+ * pointers in data.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int pldm_parse_image(struct pldmfw_priv *data)
+{
+	int err;
+
+	if (WARN_ON(!(data->context->dev && data->fw->data && data->fw->size)))
+		return -EINVAL;
+
+	err = pldm_parse_header(data);
+	if (err)
+		return err;
+
+	err = pldm_parse_records(data);
+	if (err)
+		return err;
+
+	err = pldm_parse_components(data);
+	if (err)
+		return err;
+
+	return pldm_verify_header_crc(data);
+}
+
+/* these are u32 so that we can store PCI_ANY_ID */
+struct pldm_pci_record_id {
+	int vendor;
+	int device;
+	int subsystem_vendor;
+	int subsystem_device;
+};
+
+/**
+ * pldmfw_op_pci_match_record - Check if a PCI device matches the record
+ * @context: PLDM fw update structure
+ * @record: list of records extracted from the PLDM image
+ *
+ * Determine of the PCI device associated with this device matches the record
+ * data provided.
+ *
+ * Searches the descriptor TLVs and extracts the relevant descriptor data into
+ * a pldm_pci_record_id. This is then compared against the PCI device ID
+ * information.
+ *
+ * Returns: true if the device matches the record, false otherwise.
+ */
+bool pldmfw_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record)
+{
+	struct pci_dev *pdev = to_pci_dev(context->dev);
+	struct pldm_pci_record_id id = {
+		.vendor = PCI_ANY_ID,
+		.device = PCI_ANY_ID,
+		.subsystem_vendor = PCI_ANY_ID,
+		.subsystem_device = PCI_ANY_ID,
+	};
+	struct pldmfw_desc_tlv *desc;
+
+	list_for_each_entry(desc, &record->descs, entry) {
+		u16 value;
+		int *ptr;
+
+		switch (desc->type) {
+		case PLDM_DESC_ID_PCI_VENDOR_ID:
+			ptr = &id.vendor;
+			break;
+		case PLDM_DESC_ID_PCI_DEVICE_ID:
+			ptr = &id.device;
+			break;
+		case PLDM_DESC_ID_PCI_SUBVENDOR_ID:
+			ptr = &id.subsystem_vendor;
+			break;
+		case PLDM_DESC_ID_PCI_SUBDEV_ID:
+			ptr = &id.subsystem_device;
+			break;
+		default:
+			/* Skip unrelated TLVs */
+			continue;
+		}
+
+		value = get_unaligned_le16(desc->data);
+		/* A value of zero for one of the descriptors is sometimes
+		 * used when the record should ignore this field when matching
+		 * device. For example if the record applies to any subsystem
+		 * device or vendor.
+		 */
+		if (value)
+			*ptr = (int)value;
+		else
+			*ptr = PCI_ANY_ID;
+	}
+
+	if ((id.vendor == PCI_ANY_ID || id.vendor == pdev->vendor) &&
+	    (id.device == PCI_ANY_ID || id.device == pdev->device) &&
+	    (id.subsystem_vendor == PCI_ANY_ID || id.subsystem_vendor == pdev->subsystem_vendor) &&
+	    (id.subsystem_device == PCI_ANY_ID || id.subsystem_device == pdev->subsystem_device))
+		return true;
+	else
+		return false;
+}
+EXPORT_SYMBOL(pldmfw_op_pci_match_record);
+
+/**
+ * pldm_find_matching_record - Find the first matching PLDM record
+ * @data: pointer to private data
+ *
+ * Search through PLDM records and find the first matching entry. It is
+ * expected that only one entry matches.
+ *
+ * Store a pointer to the matching record, if found.
+ *
+ * Returns: zero on success, or -ENOENT if no matching record is found.
+ */
+static int pldm_find_matching_record(struct pldmfw_priv *data)
+{
+	struct pldmfw_record *record;
+
+	list_for_each_entry(record, &data->records, entry) {
+		if (data->context->ops->match_record(data->context, record)) {
+			data->matching_record = record;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+/**
+ * pldm_send_package_data - Send firmware the package data for the record
+ * @data: pointer to private data
+ *
+ * Send the package data associated with the matching record to the firmware,
+ * using the send_pkg_data operation.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int
+pldm_send_package_data(struct pldmfw_priv *data)
+{
+	struct pldmfw_record *record = data->matching_record;
+	const struct pldmfw_ops *ops = data->context->ops;
+
+	return ops->send_package_data(data->context, record->package_data,
+				      record->package_data_len);
+}
+
+/**
+ * pldm_send_component_tables - Send component table information to firmware
+ * @data: pointer to private data
+ *
+ * Loop over each component, sending the applicable components to the firmware
+ * via the send_component_table operation.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int
+pldm_send_component_tables(struct pldmfw_priv *data)
+{
+	unsigned long *bitmap = data->matching_record->component_bitmap;
+	struct pldmfw_component *component;
+	int err;
+
+	list_for_each_entry(component, &data->components, entry) {
+		u8 index = component->index, transfer_flag = 0;
+
+		/* Skip components which are not intended for this device */
+		if (!test_bit(index, bitmap))
+			continue;
+
+		/* determine whether this is the start, middle, end, or both
+		 * the start and end of the component tables
+		 */
+		if (index == find_first_bit(bitmap, data->component_bitmap_len))
+			transfer_flag |= PLDM_TRANSFER_FLAG_START;
+		if (index == find_last_bit(bitmap, data->component_bitmap_len))
+			transfer_flag |= PLDM_TRANSFER_FLAG_END;
+		if (!transfer_flag)
+			transfer_flag = PLDM_TRANSFER_FLAG_MIDDLE;
+
+		err = data->context->ops->send_component_table(data->context,
+							       component,
+							       transfer_flag);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_flash_components - Program each component to device flash
+ * @data: pointer to private data
+ *
+ * Loop through each component that is active for the matching device record,
+ * and send it to the device driver for flashing.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+static int pldm_flash_components(struct pldmfw_priv *data)
+{
+	unsigned long *bitmap = data->matching_record->component_bitmap;
+	struct pldmfw_component *component;
+	int err;
+
+	list_for_each_entry(component, &data->components, entry) {
+		u8 index = component->index;
+
+		/* Skip components which are not intended for this device */
+		if (!test_bit(index, bitmap))
+			continue;
+
+		err = data->context->ops->flash_component(data->context, component);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * pldm_finalize_update - Finalize the device flash update
+ * @data: pointer to private data
+ *
+ * Tell the device driver to perform any remaining logic to complete the
+ * device update.
+ *
+ * Returns: zero on success, or a PLFM_FWU error indicating the reason for
+ * failure.
+ */
+static int pldm_finalize_update(struct pldmfw_priv *data)
+{
+	if (data->context->ops->finalize_update)
+		return data->context->ops->finalize_update(data->context);
+
+	return 0;
+}
+
+/**
+ * pldmfw_flash_image - Write a PLDM-formatted firmware image to the device
+ * @context: ops and data for firmware update
+ * @fw: firmware object pointing to the relevant firmware file to program
+ *
+ * Parse the data for a given firmware file, verifying that it is a valid PLDM
+ * formatted image that matches this device.
+ *
+ * Extract the device record Package Data and Component Tables and send them
+ * to the device firmware. Extract and write the flash data for each of the
+ * components indicated in the firmware file.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+int pldmfw_flash_image(struct pldmfw *context, const struct firmware *fw)
+{
+	struct pldmfw_priv *data;
+	int err;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&data->records);
+	INIT_LIST_HEAD(&data->components);
+
+	data->fw = fw;
+	data->context = context;
+
+	err = pldm_parse_image(data);
+	if (err)
+		goto out_release_data;
+
+	err = pldm_find_matching_record(data);
+	if (err)
+		goto out_release_data;
+
+	err = pldm_send_package_data(data);
+	if (err)
+		goto out_release_data;
+
+	err = pldm_send_component_tables(data);
+	if (err)
+		goto out_release_data;
+
+	err = pldm_flash_components(data);
+	if (err)
+		goto out_release_data;
+
+	err = pldm_finalize_update(data);
+
+out_release_data:
+	pldmfw_free_priv(data);
+	kfree(data);
+
+	return err;
+}
+EXPORT_SYMBOL(pldmfw_flash_image);
+
+MODULE_AUTHOR("Jacob Keller <jacob.e.keller@intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("PLDM firmware flash update library");
diff --git a/lib/pldmfw/pldmfw_private.h b/lib/pldmfw/pldmfw_private.h
new file mode 100644
index 000000000000..687ef2200692
--- /dev/null
+++ b/lib/pldmfw/pldmfw_private.h
@@ -0,0 +1,238 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018-2019, Intel Corporation. */
+
+#ifndef _PLDMFW_PRIVATE_H_
+#define _PLDMFW_PRIVATE_H_
+
+/* The following data structures define the layout of a firmware binary
+ * following the "PLDM For Firmware Update Specification", DMTF standard
+ * #DSP0267.
+ *
+ * pldmfw.c uses these structures to implement a simple engine that will parse
+ * a fw binary file in this format and perform a firmware update for a given
+ * device.
+ *
+ * Due to the variable sized data layout, alignment of fields within these
+ * structures is not guaranteed when reading. For this reason, all multi-byte
+ * field accesses should be done using the unaligned access macros.
+ * Additionally, the standard specifies that multi-byte fields are in
+ * LittleEndian format.
+ *
+ * The structure definitions are not made public, in order to keep direct
+ * accesses within code that is prepared to deal with the limitation of
+ * unaligned access.
+ */
+
+/* UUID for PLDM firmware packages: f018878c-cb7d-4943-9800-a02f059aca02 */
+static const uuid_t pldm_firmware_header_id =
+	UUID_INIT(0xf018878c, 0xcb7d, 0x4943,
+		  0x98, 0x00, 0xa0, 0x2f, 0x05, 0x9a, 0xca, 0x02);
+
+/* Revision number of the PLDM header format this code supports */
+#define PACKAGE_HEADER_FORMAT_REVISION 0x01
+
+/* timestamp104 structure defined in PLDM Base specification */
+#define PLDM_TIMESTAMP_SIZE 13
+struct __pldm_timestamp {
+	u8 b[PLDM_TIMESTAMP_SIZE];
+} __packed __aligned(1);
+
+/* Package Header Information */
+struct __pldm_header {
+	uuid_t id;			    /* PackageHeaderIdentifier */
+	u8 revision;			    /* PackageHeaderFormatRevision */
+	__le16 size;			    /* PackageHeaderSize */
+	struct __pldm_timestamp release_date; /* PackageReleaseDateTime */
+	__le16 component_bitmap_len;	    /* ComponentBitmapBitLength */
+	u8 version_type;		    /* PackageVersionStringType */
+	u8 version_len;			    /* PackageVersionStringLength */
+
+	/*
+	 * DSP0267 also includes the following variable length fields at the
+	 * end of this structure:
+	 *
+	 * PackageVersionString, length is version_len.
+	 *
+	 * The total size of this section is
+	 *   sizeof(pldm_header) + version_len;
+	 */
+	u8 version_string[];		/* PackageVersionString */
+} __packed __aligned(1);
+
+/* Firmware Device ID Record */
+struct __pldmfw_record_info {
+	__le16 record_len;		/* RecordLength */
+	u8 descriptor_count;		/* DescriptorCount */
+	__le32 device_update_flags;	/* DeviceUpdateOptionFlags */
+	u8 version_type;		/* ComponentImageSetVersionType */
+	u8 version_len;			/* ComponentImageSetVersionLength */
+	__le16 package_data_len;	/* FirmwareDevicePackageDataLength */
+
+	/*
+	 * DSP0267 also includes the following variable length fields at the
+	 * end of this structure:
+	 *
+	 * ApplicableComponents, length is component_bitmap_len from header
+	 * ComponentImageSetVersionString, length is version_len
+	 * RecordDescriptors, a series of TLVs with 16bit type and length
+	 * FirmwareDevicePackageData, length is package_data_len
+	 *
+	 * The total size of each record is
+	 *   sizeof(pldmfw_record_info) +
+	 *   component_bitmap_len (converted to bytes!) +
+	 *   version_len +
+	 *   <length of RecordDescriptors> +
+	 *   package_data_len
+	 */
+	u8 variable_record_data[];
+} __packed __aligned(1);
+
+/* Firmware Descriptor Definition */
+struct __pldmfw_desc_tlv {
+	__le16 type;			/* DescriptorType */
+	__le16 size;			/* DescriptorSize */
+	u8 data[];			/* DescriptorData */
+} __aligned(1);
+
+/* Firmware Device Identification Area */
+struct __pldmfw_record_area {
+	u8 record_count;		/* DeviceIDRecordCount */
+	/* This is not a struct type because the size of each record varies */
+	u8 records[];
+} __aligned(1);
+
+/* Individual Component Image Information */
+struct __pldmfw_component_info {
+	__le16 classification;		/* ComponentClassfication */
+	__le16 identifier;		/* ComponentIdentifier */
+	__le32 comparison_stamp;	/* ComponentComparisonStamp */
+	__le16 options;			/* componentOptions */
+	__le16 activation_method;	/* RequestedComponentActivationMethod */
+	__le32 location_offset;		/* ComponentLocationOffset */
+	__le32 size;			/* ComponentSize */
+	u8 version_type;		/* ComponentVersionStringType */
+	u8 version_len;		/* ComponentVersionStringLength */
+
+	/*
+	 * DSP0267 also includes the following variable length fields at the
+	 * end of this structure:
+	 *
+	 * ComponentVersionString, length is version_len
+	 *
+	 * The total size of this section is
+	 *   sizeof(pldmfw_component_info) + version_len;
+	 */
+	u8 version_string[];		/* ComponentVersionString */
+} __packed __aligned(1);
+
+/* Component Image Information Area */
+struct __pldmfw_component_area {
+	__le16 component_image_count;
+	/* This is not a struct type because the component size varies */
+	u8 components[];
+} __aligned(1);
+
+/**
+ * pldm_first_desc_tlv
+ * @start: byte offset of the start of the descriptor TLVs
+ *
+ * Converts the starting offset of the descriptor TLVs into a pointer to the
+ * first descriptor.
+ */
+#define pldm_first_desc_tlv(start)					\
+	((const struct __pldmfw_desc_tlv *)(start))
+
+/**
+ * pldm_next_desc_tlv
+ * @desc: pointer to a descriptor TLV
+ *
+ * Finds the pointer to the next descriptor following a given descriptor
+ */
+#define pldm_next_desc_tlv(desc)						\
+	((const struct __pldmfw_desc_tlv *)((desc)->data +			\
+					     get_unaligned_le16(&(desc)->size)))
+
+/**
+ * pldm_for_each_desc_tlv
+ * @i: variable to store descriptor index
+ * @desc: variable to store descriptor pointer
+ * @start: byte offset of the start of the descriptors
+ * @count: the number of descriptors
+ *
+ * for loop macro to iterate over all of the descriptors of a given PLDM
+ * record.
+ */
+#define pldm_for_each_desc_tlv(i, desc, start, count)			\
+	for ((i) = 0, (desc) = pldm_first_desc_tlv(start);		\
+	     (i) < (count);						\
+	     (i)++, (desc) = pldm_next_desc_tlv(desc))
+
+/**
+ * pldm_first_record
+ * @start: byte offset of the start of the PLDM records
+ *
+ * Converts a starting offset of the PLDM records into a pointer to the first
+ * record.
+ */
+#define pldm_first_record(start)					\
+	((const struct __pldmfw_record_info *)(start))
+
+/**
+ * pldm_next_record
+ * @record: pointer to a PLDM record
+ *
+ * Finds a pointer to the next record following a given record
+ */
+#define pldm_next_record(record)					\
+	((const struct __pldmfw_record_info *)				\
+	 ((const u8 *)(record) + get_unaligned_le16(&(record)->record_len)))
+
+/**
+ * pldm_for_each_record
+ * @i: variable to store record index
+ * @record: variable to store record pointer
+ * @start: byte offset of the start of the records
+ * @count: the number of records
+ *
+ * for loop macro to iterate over all of the records of a PLDM file.
+ */
+#define pldm_for_each_record(i, record, start, count)			\
+	for ((i) = 0, (record) = pldm_first_record(start);		\
+	     (i) < (count);						\
+	     (i)++, (record) = pldm_next_record(record))
+
+/**
+ * pldm_first_component
+ * @start: byte offset of the start of the PLDM components
+ *
+ * Convert a starting offset of the PLDM components into a pointer to the
+ * first component
+ */
+#define pldm_first_component(start)					\
+	((const struct __pldmfw_component_info *)(start))
+
+/**
+ * pldm_next_component
+ * @component: pointer to a PLDM component
+ *
+ * Finds a pointer to the next component following a given component
+ */
+#define pldm_next_component(component)						\
+	((const struct __pldmfw_component_info *)((component)->version_string +	\
+						  (component)->version_len))
+
+/**
+ * pldm_for_each_component
+ * @i: variable to store component index
+ * @component: variable to store component pointer
+ * @start: byte offset to the start of the first component
+ * @count: the number of components
+ *
+ * for loop macro to iterate over all of the components of a PLDM file.
+ */
+#define pldm_for_each_component(i, component, start, count)		\
+	for ((i) = 0, (component) = pldm_first_component(start);	\
+	     (i) < (count);						\
+	     (i)++, (component) = pldm_next_component(component))
+
+#endif
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 2ee6ae3b0ade..8e4a3a4397f2 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -20,6 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/kmemleak.h>
 #include <linux/percpu.h>
+#include <linux/local_lock.h>
 #include <linux/preempt.h>		/* in_interrupt() */
 #include <linux/radix-tree.h>
 #include <linux/rcupdate.h>
@@ -27,7 +28,6 @@
 #include <linux/string.h>
 #include <linux/xarray.h>
 
-
 /*
  * Radix tree node cache.
  */
@@ -58,12 +58,10 @@ struct kmem_cache *radix_tree_node_cachep;
 /*
  * Per-cpu pool of preloaded nodes
  */
-struct radix_tree_preload {
-	unsigned nr;
-	/* nodes->parent points to next preallocated node */
-	struct radix_tree_node *nodes;
+DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = {
+	.lock = INIT_LOCAL_LOCK(lock),
 };
-static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
+EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads);
 
 static inline struct radix_tree_node *entry_to_node(void *ptr)
 {
@@ -332,14 +330,14 @@ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr)
 	 */
 	gfp_mask &= ~__GFP_ACCOUNT;
 
-	preempt_disable();
+	local_lock(&radix_tree_preloads.lock);
 	rtp = this_cpu_ptr(&radix_tree_preloads);
 	while (rtp->nr < nr) {
-		preempt_enable();
+		local_unlock(&radix_tree_preloads.lock);
 		node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
 		if (node == NULL)
 			goto out;
-		preempt_disable();
+		local_lock(&radix_tree_preloads.lock);
 		rtp = this_cpu_ptr(&radix_tree_preloads);
 		if (rtp->nr < nr) {
 			node->parent = rtp->nodes;
@@ -381,7 +379,7 @@ int radix_tree_maybe_preload(gfp_t gfp_mask)
 	if (gfpflags_allow_blocking(gfp_mask))
 		return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE);
 	/* Preloading doesn't help anything with this gfp mask, skip it */
-	preempt_disable();
+	local_lock(&radix_tree_preloads.lock);
 	return 0;
 }
 EXPORT_SYMBOL(radix_tree_maybe_preload);
@@ -1031,7 +1029,7 @@ void *radix_tree_tag_clear(struct radix_tree_root *root,
 {
 	struct radix_tree_node *node, *parent;
 	unsigned long maxindex;
-	int uninitialized_var(offset);
+	int offset;
 
 	radix_tree_load_root(root, &node, &maxindex);
 	if (index > maxindex)
@@ -1470,7 +1468,7 @@ EXPORT_SYMBOL(radix_tree_tagged);
 void idr_preload(gfp_t gfp_mask)
 {
 	if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE))
-		preempt_disable();
+		local_lock(&radix_tree_preloads.lock);
 }
 EXPORT_SYMBOL(idr_preload);
 
diff --git a/lib/random32.c b/lib/random32.c
index 763b920a6206..dfb9981ab798 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -39,6 +39,7 @@
 #include <linux/random.h>
 #include <linux/sched.h>
 #include <asm/unaligned.h>
+#include <trace/events/random.h>
 
 #ifdef CONFIG_RANDOM32_SELFTEST
 static void __init prandom_state_selftest(void);
@@ -48,7 +49,7 @@ static inline void prandom_state_selftest(void)
 }
 #endif
 
-static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
+DEFINE_PER_CPU(struct rnd_state, net_rand_state)  __latent_entropy;
 
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
@@ -82,6 +83,7 @@ u32 prandom_u32(void)
 	u32 res;
 
 	res = prandom_u32_state(state);
+	trace_prandom_u32(res);
 	put_cpu_var(net_rand_state);
 
 	return res;
diff --git a/lib/rbtree.c b/lib/rbtree.c
index 8545872e61db..c4ac5c2421f2 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -13,7 +13,7 @@
 #include <linux/export.h>
 
 /*
- * red-black trees properties:  http://en.wikipedia.org/wiki/Rbtree
+ * red-black trees properties:  https://en.wikipedia.org/wiki/Rbtree
  *
  *  1) A node is either red or black
  *  2) The root is black
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index bdb7e4cadf05..c949c1e3b87c 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -31,7 +31,7 @@
 
 union nested_table {
 	union nested_table __rcu *table;
-	struct rhash_lock_head *bucket;
+	struct rhash_lock_head __rcu *bucket;
 };
 
 static u32 head_hashfn(struct rhashtable *ht,
@@ -63,13 +63,22 @@ EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
 #define ASSERT_RHT_MUTEX(HT)
 #endif
 
+static inline union nested_table *nested_table_top(
+	const struct bucket_table *tbl)
+{
+	/* The top-level bucket entry does not need RCU protection
+	 * because it's set at the same time as tbl->nest.
+	 */
+	return (void *)rcu_dereference_protected(tbl->buckets[0], 1);
+}
+
 static void nested_table_free(union nested_table *ntbl, unsigned int size)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
 	const unsigned int len = 1 << shift;
 	unsigned int i;
 
-	ntbl = rcu_dereference_raw(ntbl->table);
+	ntbl = rcu_dereference_protected(ntbl->table, 1);
 	if (!ntbl)
 		return;
 
@@ -89,7 +98,7 @@ static void nested_bucket_table_free(const struct bucket_table *tbl)
 	union nested_table *ntbl;
 	unsigned int i;
 
-	ntbl = (union nested_table *)rcu_dereference_raw(tbl->buckets[0]);
+	ntbl = nested_table_top(tbl);
 
 	for (i = 0; i < len; i++)
 		nested_table_free(ntbl + i, size);
@@ -213,7 +222,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht,
 }
 
 static int rhashtable_rehash_one(struct rhashtable *ht,
-				 struct rhash_lock_head **bkt,
+				 struct rhash_lock_head __rcu **bkt,
 				 unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
@@ -266,7 +275,7 @@ static int rhashtable_rehash_chain(struct rhashtable *ht,
 				    unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
-	struct rhash_lock_head **bkt = rht_bucket_var(old_tbl, old_hash);
+	struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash);
 	int err;
 
 	if (!bkt)
@@ -476,7 +485,7 @@ fail:
 }
 
 static void *rhashtable_lookup_one(struct rhashtable *ht,
-				   struct rhash_lock_head **bkt,
+				   struct rhash_lock_head __rcu **bkt,
 				   struct bucket_table *tbl, unsigned int hash,
 				   const void *key, struct rhash_head *obj)
 {
@@ -526,12 +535,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 	return ERR_PTR(-ENOENT);
 }
 
-static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
-						  struct rhash_lock_head **bkt,
-						  struct bucket_table *tbl,
-						  unsigned int hash,
-						  struct rhash_head *obj,
-						  void *data)
+static struct bucket_table *rhashtable_insert_one(
+	struct rhashtable *ht, struct rhash_lock_head __rcu **bkt,
+	struct bucket_table *tbl, unsigned int hash, struct rhash_head *obj,
+	void *data)
 {
 	struct bucket_table *new_tbl;
 	struct rhash_head *head;
@@ -582,7 +589,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 {
 	struct bucket_table *new_tbl;
 	struct bucket_table *tbl;
-	struct rhash_lock_head **bkt;
+	struct rhash_lock_head __rcu **bkt;
 	unsigned int hash;
 	void *data;
 
@@ -1164,8 +1171,8 @@ void rhashtable_destroy(struct rhashtable *ht)
 }
 EXPORT_SYMBOL_GPL(rhashtable_destroy);
 
-struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl,
-					     unsigned int hash)
+struct rhash_lock_head __rcu **__rht_bucket_nested(
+	const struct bucket_table *tbl, unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
@@ -1173,7 +1180,7 @@ struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl,
 	unsigned int subhash = hash;
 	union nested_table *ntbl;
 
-	ntbl = (union nested_table *)rcu_dereference_raw(tbl->buckets[0]);
+	ntbl = nested_table_top(tbl);
 	ntbl = rht_dereference_bucket_rcu(ntbl[index].table, tbl, hash);
 	subhash >>= tbl->nest;
 
@@ -1193,10 +1200,10 @@ struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl,
 }
 EXPORT_SYMBOL_GPL(__rht_bucket_nested);
 
-struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl,
-					   unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested(
+	const struct bucket_table *tbl, unsigned int hash)
 {
-	static struct rhash_lock_head *rhnull;
+	static struct rhash_lock_head __rcu *rhnull;
 
 	if (!rhnull)
 		INIT_RHT_NULLS_HEAD(rhnull);
@@ -1204,16 +1211,15 @@ struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl,
 }
 EXPORT_SYMBOL_GPL(rht_bucket_nested);
 
-struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht,
-						  struct bucket_table *tbl,
-						  unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(
+	struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
 	unsigned int size = tbl->size >> tbl->nest;
 	union nested_table *ntbl;
 
-	ntbl = (union nested_table *)rcu_dereference_raw(tbl->buckets[0]);
+	ntbl = nested_table_top(tbl);
 	hash >>= tbl->nest;
 	ntbl = nested_table_alloc(ht, &ntbl[index].table,
 				  size <= (1 << shift));
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index af88d1346dd7..267aa7709416 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -292,8 +292,11 @@ void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m)
 
 	for (i = 0; i < sb->map_nr; i++) {
 		unsigned long word = READ_ONCE(sb->map[i].word);
+		unsigned long cleared = READ_ONCE(sb->map[i].cleared);
 		unsigned int word_bits = READ_ONCE(sb->map[i].depth);
 
+		word &= ~cleared;
+
 		while (word_bits > 0) {
 			unsigned int bits = min(8 - byte_bits, word_bits);
 
diff --git a/lib/seq_buf.c b/lib/seq_buf.c
index 4e865d42ab03..707453f5d58e 100644
--- a/lib/seq_buf.c
+++ b/lib/seq_buf.c
@@ -91,6 +91,7 @@ int seq_buf_printf(struct seq_buf *s, const char *fmt, ...)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(seq_buf_printf);
 
 #ifdef CONFIG_BINARY_PRINTF
 /**
diff --git a/lib/sha1.c b/lib/sha1.c
index 1d96d2c02b82..49257a915bb6 100644
--- a/lib/sha1.c
+++ b/lib/sha1.c
@@ -9,7 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/bitops.h>
-#include <linux/cryptohash.h>
+#include <crypto/sha.h>
 #include <asm/unaligned.h>
 
 /*
@@ -64,22 +64,24 @@
 #define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) ,  0xca62c1d6, A, B, C, D, E )
 
 /**
- * sha_transform - single block SHA1 transform
+ * sha1_transform - single block SHA1 transform (deprecated)
  *
  * @digest: 160 bit digest to update
  * @data:   512 bits of data to hash
  * @array:  16 words of workspace (see note)
  *
- * This function generates a SHA1 digest for a single 512-bit block.
- * Be warned, it does not handle padding and message digest, do not
- * confuse it with the full FIPS 180-1 digest algorithm for variable
- * length messages.
+ * This function executes SHA-1's internal compression function.  It updates the
+ * 160-bit internal state (@digest) with a single 512-bit data block (@data).
+ *
+ * Don't use this function.  SHA-1 is no longer considered secure.  And even if
+ * you do have to use SHA-1, this isn't the correct way to hash something with
+ * SHA-1 as this doesn't handle padding and finalization.
  *
  * Note: If the hash is security sensitive, the caller should be sure
  * to clear the workspace. This is left to the caller to avoid
  * unnecessary clears between chained hashing operations.
  */
-void sha_transform(__u32 *digest, const char *data, __u32 *array)
+void sha1_transform(__u32 *digest, const char *data, __u32 *array)
 {
 	__u32 A, B, C, D, E;
 
@@ -185,13 +187,13 @@ void sha_transform(__u32 *digest, const char *data, __u32 *array)
 	digest[3] += D;
 	digest[4] += E;
 }
-EXPORT_SYMBOL(sha_transform);
+EXPORT_SYMBOL(sha1_transform);
 
 /**
- * sha_init - initialize the vectors for a SHA1 digest
+ * sha1_init - initialize the vectors for a SHA1 digest
  * @buf: vector to initialize
  */
-void sha_init(__u32 *buf)
+void sha1_init(__u32 *buf)
 {
 	buf[0] = 0x67452301;
 	buf[1] = 0xefcdab89;
@@ -199,4 +201,4 @@ void sha_init(__u32 *buf)
 	buf[3] = 0x10325476;
 	buf[4] = 0xc3d2e1f0;
 }
-EXPORT_SYMBOL(sha_init);
+EXPORT_SYMBOL(sha1_init);
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index bd9571653288..525222e4f409 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -8,7 +8,7 @@
 #include <linux/kprobes.h>
 #include <linux/sched.h>
 
-notrace static nokprobe_inline
+noinstr static
 unsigned int check_preemption_disabled(const char *what1, const char *what2)
 {
 	int this_cpu = raw_smp_processor_id();
@@ -37,6 +37,7 @@ unsigned int check_preemption_disabled(const char *what1, const char *what2)
 	 */
 	preempt_disable_notrace();
 
+	instrumentation_begin();
 	if (!printk_ratelimit())
 		goto out_enable;
 
@@ -45,6 +46,7 @@ unsigned int check_preemption_disabled(const char *what1, const char *what2)
 
 	printk("caller is %pS\n", __builtin_return_address(0));
 	dump_stack();
+	instrumentation_end();
 
 out_enable:
 	preempt_enable_no_resched_notrace();
@@ -52,16 +54,14 @@ out:
 	return this_cpu;
 }
 
-notrace unsigned int debug_smp_processor_id(void)
+noinstr unsigned int debug_smp_processor_id(void)
 {
 	return check_preemption_disabled("smp_processor_id", "");
 }
 EXPORT_SYMBOL(debug_smp_processor_id);
-NOKPROBE_SYMBOL(debug_smp_processor_id);
 
-notrace void __this_cpu_preempt_check(const char *op)
+noinstr void __this_cpu_preempt_check(const char *op)
 {
 	check_preemption_disabled("__this_cpu_", op);
 }
 EXPORT_SYMBOL(__this_cpu_preempt_check);
-NOKPROBE_SYMBOL(__this_cpu_preempt_check);
diff --git a/lib/string.c b/lib/string.c
index 6012c385fb31..4288e0158d47 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -272,6 +272,30 @@ ssize_t strscpy_pad(char *dest, const char *src, size_t count)
 }
 EXPORT_SYMBOL(strscpy_pad);
 
+/**
+ * stpcpy - copy a string from src to dest returning a pointer to the new end
+ *          of dest, including src's %NUL-terminator. May overrun dest.
+ * @dest: pointer to end of string being copied into. Must be large enough
+ *        to receive copy.
+ * @src: pointer to the beginning of string being copied from. Must not overlap
+ *       dest.
+ *
+ * stpcpy differs from strcpy in a key way: the return value is a pointer
+ * to the new %NUL-terminating character in @dest. (For strcpy, the return
+ * value is a pointer to the start of @dest). This interface is considered
+ * unsafe as it doesn't perform bounds checking of the inputs. As such it's
+ * not recommended for usage. Instead, its definition is provided in case
+ * the compiler lowers other libcalls to stpcpy.
+ */
+char *stpcpy(char *__restrict__ dest, const char *__restrict__ src);
+char *stpcpy(char *__restrict__ dest, const char *__restrict__ src)
+{
+	while ((*dest++ = *src++) != '\0')
+		/* nothing */;
+	return --dest;
+}
+EXPORT_SYMBOL(stpcpy);
+
 #ifndef __HAVE_ARCH_STRCAT
 /**
  * strcat - Append one %NUL-terminated string to another
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index 706020b06617..34696a348864 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -98,6 +98,7 @@ long strncpy_from_user(char *dst, const char __user *src, long count)
 {
 	unsigned long max_addr, src_addr;
 
+	might_fault();
 	if (unlikely(count <= 0))
 		return 0;
 
@@ -116,9 +117,9 @@ long strncpy_from_user(char *dst, const char __user *src, long count)
 
 		kasan_check_write(dst, count);
 		check_object_size(dst, count, false);
-		if (user_access_begin(src, max)) {
+		if (user_read_access_begin(src, max)) {
 			retval = do_strncpy_from_user(dst, src, count, max);
-			user_access_end();
+			user_read_access_end();
 			return retval;
 		}
 	}
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index 41670d4a5816..1616710b8a82 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -109,9 +109,9 @@ long strnlen_user(const char __user *str, long count)
 		if (max > count)
 			max = count;
 
-		if (user_access_begin(str, max)) {
+		if (user_read_access_begin(str, max)) {
 			retval = do_strnlen_user(str, count, max);
-			user_access_end();
+			user_read_access_end();
 			return retval;
 		}
 	}
diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c
index 25b5cbfb7615..10360d4ea273 100644
--- a/lib/test-string_helpers.c
+++ b/lib/test-string_helpers.c
@@ -238,6 +238,28 @@ static const struct test_string_2 escape1[] __initconst = {{
 	/* terminator */
 }};
 
+static const struct test_string strings_upper[] __initconst = {
+	{
+		.in = "abcdefgh1234567890test",
+		.out = "ABCDEFGH1234567890TEST",
+	},
+	{
+		.in = "abCdeFgH1234567890TesT",
+		.out = "ABCDEFGH1234567890TEST",
+	},
+};
+
+static const struct test_string strings_lower[] __initconst = {
+	{
+		.in = "ABCDEFGH1234567890TEST",
+		.out = "abcdefgh1234567890test",
+	},
+	{
+		.in = "abCdeFgH1234567890TesT",
+		.out = "abcdefgh1234567890test",
+	},
+};
+
 static __init const char *test_string_find_match(const struct test_string_2 *s2,
 						 unsigned int flags)
 {
@@ -390,6 +412,48 @@ static __init void test_string_get_size(void)
 	test_string_get_size_one(4096, U64_MAX, "75.6 ZB", "64.0 ZiB");
 }
 
+static void __init test_string_upper_lower(void)
+{
+	char *dst;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(strings_upper); i++) {
+		const char *s = strings_upper[i].in;
+		int len = strlen(strings_upper[i].in) + 1;
+
+		dst = kmalloc(len, GFP_KERNEL);
+		if (!dst)
+			return;
+
+		string_upper(dst, s);
+		if (memcmp(dst, strings_upper[i].out, len)) {
+			pr_warn("Test 'string_upper' failed : expected %s, got %s!\n",
+				strings_upper[i].out, dst);
+			kfree(dst);
+			return;
+		}
+		kfree(dst);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(strings_lower); i++) {
+		const char *s = strings_lower[i].in;
+		int len = strlen(strings_lower[i].in) + 1;
+
+		dst = kmalloc(len, GFP_KERNEL);
+		if (!dst)
+			return;
+
+		string_lower(dst, s);
+		if (memcmp(dst, strings_lower[i].out, len)) {
+			pr_warn("Test 'string_lower failed : : expected %s, got %s!\n",
+				strings_lower[i].out, dst);
+			kfree(dst);
+			return;
+		}
+		kfree(dst);
+	}
+}
+
 static int __init test_string_helpers_init(void)
 {
 	unsigned int i;
@@ -411,6 +475,9 @@ static int __init test_string_helpers_init(void)
 	/* Test string_get_size() */
 	test_string_get_size();
 
+	/* Test string upper(), string_lower() */
+	test_string_upper_lower();
+
 	return -EINVAL;
 }
 module_init(test_string_helpers_init);
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index 6b13150667f5..df903c53952b 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -610,6 +610,63 @@ static void __init test_for_each_set_clump8(void)
 		expect_eq_clump8(start, CLUMP_EXP_NUMBITS, clump_exp, &clump);
 }
 
+struct test_bitmap_cut {
+	unsigned int first;
+	unsigned int cut;
+	unsigned int nbits;
+	unsigned long in[4];
+	unsigned long expected[4];
+};
+
+static struct test_bitmap_cut test_cut[] = {
+	{  0,  0,  8, { 0x0000000aUL, }, { 0x0000000aUL, }, },
+	{  0,  0, 32, { 0xdadadeadUL, }, { 0xdadadeadUL, }, },
+	{  0,  3,  8, { 0x000000aaUL, }, { 0x00000015UL, }, },
+	{  3,  3,  8, { 0x000000aaUL, }, { 0x00000012UL, }, },
+	{  0,  1, 32, { 0xa5a5a5a5UL, }, { 0x52d2d2d2UL, }, },
+	{  0,  8, 32, { 0xdeadc0deUL, }, { 0x00deadc0UL, }, },
+	{  1,  1, 32, { 0x5a5a5a5aUL, }, { 0x2d2d2d2cUL, }, },
+	{  0, 15, 32, { 0xa5a5a5a5UL, }, { 0x00014b4bUL, }, },
+	{  0, 16, 32, { 0xa5a5a5a5UL, }, { 0x0000a5a5UL, }, },
+	{ 15, 15, 32, { 0xa5a5a5a5UL, }, { 0x000125a5UL, }, },
+	{ 15, 16, 32, { 0xa5a5a5a5UL, }, { 0x0000a5a5UL, }, },
+	{ 16, 15, 32, { 0xa5a5a5a5UL, }, { 0x0001a5a5UL, }, },
+
+	{ BITS_PER_LONG, BITS_PER_LONG, BITS_PER_LONG,
+		{ 0xa5a5a5a5UL, 0xa5a5a5a5UL, },
+		{ 0xa5a5a5a5UL, 0xa5a5a5a5UL, },
+	},
+	{ 1, BITS_PER_LONG - 1, BITS_PER_LONG,
+		{ 0xa5a5a5a5UL, 0xa5a5a5a5UL, },
+		{ 0x00000001UL, 0x00000001UL, },
+	},
+
+	{ 0, BITS_PER_LONG * 2, BITS_PER_LONG * 2 + 1,
+		{ 0xa5a5a5a5UL, 0x00000001UL, 0x00000001UL, 0x00000001UL },
+		{ 0x00000001UL, },
+	},
+	{ 16, BITS_PER_LONG * 2 + 1, BITS_PER_LONG * 2 + 1 + 16,
+		{ 0x0000ffffUL, 0x5a5a5a5aUL, 0x5a5a5a5aUL, 0x5a5a5a5aUL },
+		{ 0x2d2dffffUL, },
+	},
+};
+
+static void __init test_bitmap_cut(void)
+{
+	unsigned long b[5], *in = &b[1], *out = &b[0];	/* Partial overlap */
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_cut); i++) {
+		struct test_bitmap_cut *t = &test_cut[i];
+
+		memcpy(in, t->in, sizeof(t->in));
+
+		bitmap_cut(out, in, t->first, t->cut, t->nbits);
+
+		expect_eq_bitmap(t->expected, out, t->nbits);
+	}
+}
+
 static void __init selftest(void)
 {
 	test_zero_clear();
@@ -623,6 +680,7 @@ static void __init selftest(void)
 	test_bitmap_parselist_user();
 	test_mem_optimisations();
 	test_for_each_set_clump8();
+	test_bitmap_cut();
 }
 
 KSTM_MODULE_LOADERS(test_bitmap);
diff --git a/lib/test_bitops.c b/lib/test_bitops.c
new file mode 100644
index 000000000000..471141ddd691
--- /dev/null
+++ b/lib/test_bitops.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Intel Corporation
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+
+/* a tiny module only meant to test
+ *
+ *   set/clear_bit
+ *   get_count_order/long
+ */
+
+/* use an enum because thats the most common BITMAP usage */
+enum bitops_fun {
+	BITOPS_4 = 4,
+	BITOPS_7 = 7,
+	BITOPS_11 = 11,
+	BITOPS_31 = 31,
+	BITOPS_88 = 88,
+	BITOPS_LAST = 255,
+	BITOPS_LENGTH = 256
+};
+
+static DECLARE_BITMAP(g_bitmap, BITOPS_LENGTH);
+
+static unsigned int order_comb[][2] = {
+	{0x00000003,  2},
+	{0x00000004,  2},
+	{0x00001fff, 13},
+	{0x00002000, 13},
+	{0x50000000, 31},
+	{0x80000000, 31},
+	{0x80003000, 32},
+};
+
+#ifdef CONFIG_64BIT
+static unsigned long order_comb_long[][2] = {
+	{0x0000000300000000, 34},
+	{0x0000000400000000, 34},
+	{0x00001fff00000000, 45},
+	{0x0000200000000000, 45},
+	{0x5000000000000000, 63},
+	{0x8000000000000000, 63},
+	{0x8000300000000000, 64},
+};
+#endif
+
+static int __init test_bitops_startup(void)
+{
+	int i, bit_set;
+
+	pr_info("Starting bitops test\n");
+	set_bit(BITOPS_4, g_bitmap);
+	set_bit(BITOPS_7, g_bitmap);
+	set_bit(BITOPS_11, g_bitmap);
+	set_bit(BITOPS_31, g_bitmap);
+	set_bit(BITOPS_88, g_bitmap);
+
+	for (i = 0; i < ARRAY_SIZE(order_comb); i++) {
+		if (order_comb[i][1] != get_count_order(order_comb[i][0]))
+			pr_warn("get_count_order wrong for %x\n",
+				       order_comb[i][0]);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(order_comb); i++) {
+		if (order_comb[i][1] != get_count_order_long(order_comb[i][0]))
+			pr_warn("get_count_order_long wrong for %x\n",
+				       order_comb[i][0]);
+	}
+
+#ifdef CONFIG_64BIT
+	for (i = 0; i < ARRAY_SIZE(order_comb_long); i++) {
+		if (order_comb_long[i][1] !=
+			       get_count_order_long(order_comb_long[i][0]))
+			pr_warn("get_count_order_long wrong for %lx\n",
+				       order_comb_long[i][0]);
+	}
+#endif
+
+	barrier();
+
+	clear_bit(BITOPS_4, g_bitmap);
+	clear_bit(BITOPS_7, g_bitmap);
+	clear_bit(BITOPS_11, g_bitmap);
+	clear_bit(BITOPS_31, g_bitmap);
+	clear_bit(BITOPS_88, g_bitmap);
+
+	bit_set = find_first_bit(g_bitmap, BITOPS_LAST);
+	if (bit_set != BITOPS_LAST)
+		pr_err("ERROR: FOUND SET BIT %d\n", bit_set);
+
+	pr_info("Completed bitops test\n");
+
+	return 0;
+}
+
+static void __exit test_bitops_unstartup(void)
+{
+}
+
+module_init(test_bitops_startup);
+module_exit(test_bitops_unstartup);
+
+MODULE_AUTHOR("Jesse Brandeburg <jesse.brandeburg@intel.com>, Wei Yang <richard.weiyang@gmail.com>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Bit testing module");
diff --git a/lib/test_bits.c b/lib/test_bits.c
new file mode 100644
index 000000000000..c9368a2314e7
--- /dev/null
+++ b/lib/test_bits.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Test cases for functions and macros in bits.h
+ */
+
+#include <kunit/test.h>
+#include <linux/bits.h>
+
+
+static void genmask_test(struct kunit *test)
+{
+	KUNIT_EXPECT_EQ(test, 1ul, GENMASK(0, 0));
+	KUNIT_EXPECT_EQ(test, 3ul, GENMASK(1, 0));
+	KUNIT_EXPECT_EQ(test, 6ul, GENMASK(2, 1));
+	KUNIT_EXPECT_EQ(test, 0xFFFFFFFFul, GENMASK(31, 0));
+
+#ifdef TEST_GENMASK_FAILURES
+	/* these should fail compilation */
+	GENMASK(0, 1);
+	GENMASK(0, 10);
+	GENMASK(9, 10);
+#endif
+
+
+}
+
+static void genmask_ull_test(struct kunit *test)
+{
+	KUNIT_EXPECT_EQ(test, 1ull, GENMASK_ULL(0, 0));
+	KUNIT_EXPECT_EQ(test, 3ull, GENMASK_ULL(1, 0));
+	KUNIT_EXPECT_EQ(test, 0x000000ffffe00000ull, GENMASK_ULL(39, 21));
+	KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_ULL(63, 0));
+
+#ifdef TEST_GENMASK_FAILURES
+	/* these should fail compilation */
+	GENMASK_ULL(0, 1);
+	GENMASK_ULL(0, 10);
+	GENMASK_ULL(9, 10);
+#endif
+}
+
+static void genmask_input_check_test(struct kunit *test)
+{
+	unsigned int x, y;
+	int z, w;
+
+	/* Unknown input */
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(x, 0));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(0, x));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(x, y));
+
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(z, 0));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(0, z));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(z, w));
+
+	/* Valid input */
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(1, 1));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(39, 21));
+}
+
+
+static struct kunit_case bits_test_cases[] = {
+	KUNIT_CASE(genmask_test),
+	KUNIT_CASE(genmask_ull_test),
+	KUNIT_CASE(genmask_input_check_test),
+	{}
+};
+
+static struct kunit_suite bits_test_suite = {
+	.name = "bits-test",
+	.test_cases = bits_test_cases,
+};
+kunit_test_suite(bits_test_suite);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index a5fddf9ebcb7..ca7d635bccd9 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -5275,31 +5275,21 @@ static struct bpf_test tests[] = {
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Ctx heavy transformations",
 		{ },
-#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
-		CLASSIC | FLAG_EXPECTED_FAIL,
-#else
 		CLASSIC,
-#endif
 		{ },
 		{
 			{  1, SKB_VLAN_PRESENT },
 			{ 10, SKB_VLAN_PRESENT }
 		},
 		.fill_helper = bpf_fill_maxinsns6,
-		.expected_errcode = -ENOTSUPP,
 	},
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Call heavy transformations",
 		{ },
-#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
-		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
-#else
 		CLASSIC | FLAG_NO_DATA,
-#endif
 		{ },
 		{ { 1, 0 }, { 10, 0 } },
 		.fill_helper = bpf_fill_maxinsns7,
-		.expected_errcode = -ENOTSUPP,
 	},
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Jump heavy test",
@@ -5350,28 +5340,18 @@ static struct bpf_test tests[] = {
 	{
 		"BPF_MAXINSNS: exec all MSH",
 		{ },
-#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
-		CLASSIC | FLAG_EXPECTED_FAIL,
-#else
 		CLASSIC,
-#endif
 		{ 0xfa, 0xfb, 0xfc, 0xfd, },
 		{ { 4, 0xababab83 } },
 		.fill_helper = bpf_fill_maxinsns13,
-		.expected_errcode = -ENOTSUPP,
 	},
 	{
 		"BPF_MAXINSNS: ld_abs+get_processor_id",
 		{ },
-#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
-		CLASSIC | FLAG_EXPECTED_FAIL,
-#else
 		CLASSIC,
-#endif
 		{ },
 		{ { 1, 0xbee } },
 		.fill_helper = bpf_fill_ld_abs_get_processor_id,
-		.expected_errcode = -ENOTSUPP,
 	},
 	/*
 	 * LD_IND / LD_ABS on fragmented SKBs
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 0c7fbcf07ac5..06c955057756 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -26,6 +26,8 @@
 #include <linux/vmalloc.h>
 #include <linux/efi_embedded_fw.h>
 
+MODULE_IMPORT_NS(TEST_FIRMWARE);
+
 #define TEST_FIRMWARE_NAME	"test-firmware.bin"
 #define TEST_FIRMWARE_NUM_REQS	4
 #define TEST_FIRMWARE_BUF_SIZE	SZ_1K
@@ -310,27 +312,13 @@ static int test_dev_config_update_bool(const char *buf, size_t size,
 	return ret;
 }
 
-static ssize_t
-test_dev_config_show_bool(char *buf,
-			  bool config)
+static ssize_t test_dev_config_show_bool(char *buf, bool val)
 {
-	bool val;
-
-	mutex_lock(&test_fw_mutex);
-	val = config;
-	mutex_unlock(&test_fw_mutex);
-
 	return snprintf(buf, PAGE_SIZE, "%d\n", val);
 }
 
-static ssize_t test_dev_config_show_int(char *buf, int cfg)
+static ssize_t test_dev_config_show_int(char *buf, int val)
 {
-	int val;
-
-	mutex_lock(&test_fw_mutex);
-	val = cfg;
-	mutex_unlock(&test_fw_mutex);
-
 	return snprintf(buf, PAGE_SIZE, "%d\n", val);
 }
 
@@ -354,14 +342,8 @@ static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg)
 	return size;
 }
 
-static ssize_t test_dev_config_show_u8(char *buf, u8 cfg)
+static ssize_t test_dev_config_show_u8(char *buf, u8 val)
 {
-	u8 val;
-
-	mutex_lock(&test_fw_mutex);
-	val = cfg;
-	mutex_unlock(&test_fw_mutex);
-
 	return snprintf(buf, PAGE_SIZE, "%u\n", val);
 }
 
@@ -509,6 +491,9 @@ out:
 static DEVICE_ATTR_WO(trigger_request);
 
 #ifdef CONFIG_EFI_EMBEDDED_FIRMWARE
+extern struct list_head efi_embedded_fw_list;
+extern bool efi_embedded_fw_checked;
+
 static ssize_t trigger_request_platform_store(struct device *dev,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
@@ -521,6 +506,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	};
 	struct efi_embedded_fw efi_embedded_fw;
 	const struct firmware *firmware = NULL;
+	bool saved_efi_embedded_fw_checked;
 	char *name;
 	int rc;
 
@@ -533,6 +519,8 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	efi_embedded_fw.data = (void *)test_data;
 	efi_embedded_fw.length = sizeof(test_data);
 	list_add(&efi_embedded_fw.list, &efi_embedded_fw_list);
+	saved_efi_embedded_fw_checked = efi_embedded_fw_checked;
+	efi_embedded_fw_checked = true;
 
 	pr_info("loading '%s'\n", name);
 	rc = firmware_request_platform(&firmware, name, dev);
@@ -550,6 +538,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	rc = count;
 
 out:
+	efi_embedded_fw_checked = saved_efi_embedded_fw_checked;
 	release_firmware(firmware);
 	list_del(&efi_embedded_fw.list);
 	kfree(name);
diff --git a/lib/test_fpu.c b/lib/test_fpu.c
new file mode 100644
index 000000000000..c33764aa3eb8
--- /dev/null
+++ b/lib/test_fpu.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Test cases for using floating point operations inside a kernel module.
+ *
+ * This tests kernel_fpu_begin() and kernel_fpu_end() functions, especially
+ * when userland has modified the floating point control registers. The kernel
+ * state might depend on the state set by the userland thread that was active
+ * before a syscall.
+ *
+ * To facilitate the test, this module registers file
+ * /sys/kernel/debug/selftest_helpers/test_fpu, which when read causes a
+ * sequence of floating point operations. If the operations fail, either the
+ * read returns error status or the kernel crashes.
+ * If the operations succeed, the read returns "1\n".
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/debugfs.h>
+#include <asm/fpu/api.h>
+
+static int test_fpu(void)
+{
+	/*
+	 * This sequence of operations tests that rounding mode is
+	 * to nearest and that denormal numbers are supported.
+	 * Volatile variables are used to avoid compiler optimizing
+	 * the calculations away.
+	 */
+	volatile double a, b, c, d, e, f, g;
+
+	a = 4.0;
+	b = 1e-15;
+	c = 1e-310;
+
+	/* Sets precision flag */
+	d = a + b;
+
+	/* Result depends on rounding mode */
+	e = a + b / 2;
+
+	/* Denormal and very large values */
+	f = b / c;
+
+	/* Depends on denormal support */
+	g = a + c * f;
+
+	if (d > a && e > a && g > a)
+		return 0;
+	else
+		return -EINVAL;
+}
+
+static int test_fpu_get(void *data, u64 *val)
+{
+	int status = -EINVAL;
+
+	kernel_fpu_begin();
+	status = test_fpu();
+	kernel_fpu_end();
+
+	*val = 1;
+	return status;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(test_fpu_fops, test_fpu_get, NULL, "%lld\n");
+static struct dentry *selftest_dir;
+
+static int __init test_fpu_init(void)
+{
+	selftest_dir = debugfs_create_dir("selftest_helpers", NULL);
+	if (!selftest_dir)
+		return -ENOMEM;
+
+	debugfs_create_file("test_fpu", 0444, selftest_dir, NULL,
+			    &test_fpu_fops);
+
+	return 0;
+}
+
+static void __exit test_fpu_exit(void)
+{
+	debugfs_remove(selftest_dir);
+}
+
+module_init(test_fpu_init);
+module_exit(test_fpu_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
new file mode 100644
index 000000000000..e7dc3de355b7
--- /dev/null
+++ b/lib/test_hmm.c
@@ -0,0 +1,1164 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This is a module to test the HMM (Heterogeneous Memory Management)
+ * mirror and zone device private memory migration APIs of the kernel.
+ * Userspace programs can register with the driver to mirror their own address
+ * space and can use the device to read/write any valid virtual address.
+ */
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+#include <linux/delay.h>
+#include <linux/pagemap.h>
+#include <linux/hmm.h>
+#include <linux/vmalloc.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/sched/mm.h>
+#include <linux/platform_device.h>
+
+#include "test_hmm_uapi.h"
+
+#define DMIRROR_NDEVICES		2
+#define DMIRROR_RANGE_FAULT_TIMEOUT	1000
+#define DEVMEM_CHUNK_SIZE		(256 * 1024 * 1024U)
+#define DEVMEM_CHUNKS_RESERVE		16
+
+static const struct dev_pagemap_ops dmirror_devmem_ops;
+static const struct mmu_interval_notifier_ops dmirror_min_ops;
+static dev_t dmirror_dev;
+static struct page *dmirror_zero_page;
+
+struct dmirror_device;
+
+struct dmirror_bounce {
+	void			*ptr;
+	unsigned long		size;
+	unsigned long		addr;
+	unsigned long		cpages;
+};
+
+#define DPT_XA_TAG_WRITE 3UL
+
+/*
+ * Data structure to track address ranges and register for mmu interval
+ * notifier updates.
+ */
+struct dmirror_interval {
+	struct mmu_interval_notifier	notifier;
+	struct dmirror			*dmirror;
+};
+
+/*
+ * Data attached to the open device file.
+ * Note that it might be shared after a fork().
+ */
+struct dmirror {
+	struct dmirror_device		*mdevice;
+	struct xarray			pt;
+	struct mmu_interval_notifier	notifier;
+	struct mutex			mutex;
+};
+
+/*
+ * ZONE_DEVICE pages for migration and simulating device memory.
+ */
+struct dmirror_chunk {
+	struct dev_pagemap	pagemap;
+	struct dmirror_device	*mdevice;
+};
+
+/*
+ * Per device data.
+ */
+struct dmirror_device {
+	struct cdev		cdevice;
+	struct hmm_devmem	*devmem;
+
+	unsigned int		devmem_capacity;
+	unsigned int		devmem_count;
+	struct dmirror_chunk	**devmem_chunks;
+	struct mutex		devmem_lock;	/* protects the above */
+
+	unsigned long		calloc;
+	unsigned long		cfree;
+	struct page		*free_pages;
+	spinlock_t		lock;		/* protects the above */
+};
+
+static struct dmirror_device dmirror_devices[DMIRROR_NDEVICES];
+
+static int dmirror_bounce_init(struct dmirror_bounce *bounce,
+			       unsigned long addr,
+			       unsigned long size)
+{
+	bounce->addr = addr;
+	bounce->size = size;
+	bounce->cpages = 0;
+	bounce->ptr = vmalloc(size);
+	if (!bounce->ptr)
+		return -ENOMEM;
+	return 0;
+}
+
+static void dmirror_bounce_fini(struct dmirror_bounce *bounce)
+{
+	vfree(bounce->ptr);
+}
+
+static int dmirror_fops_open(struct inode *inode, struct file *filp)
+{
+	struct cdev *cdev = inode->i_cdev;
+	struct dmirror *dmirror;
+	int ret;
+
+	/* Mirror this process address space */
+	dmirror = kzalloc(sizeof(*dmirror), GFP_KERNEL);
+	if (dmirror == NULL)
+		return -ENOMEM;
+
+	dmirror->mdevice = container_of(cdev, struct dmirror_device, cdevice);
+	mutex_init(&dmirror->mutex);
+	xa_init(&dmirror->pt);
+
+	ret = mmu_interval_notifier_insert(&dmirror->notifier, current->mm,
+				0, ULONG_MAX & PAGE_MASK, &dmirror_min_ops);
+	if (ret) {
+		kfree(dmirror);
+		return ret;
+	}
+
+	filp->private_data = dmirror;
+	return 0;
+}
+
+static int dmirror_fops_release(struct inode *inode, struct file *filp)
+{
+	struct dmirror *dmirror = filp->private_data;
+
+	mmu_interval_notifier_remove(&dmirror->notifier);
+	xa_destroy(&dmirror->pt);
+	kfree(dmirror);
+	return 0;
+}
+
+static struct dmirror_device *dmirror_page_to_device(struct page *page)
+
+{
+	return container_of(page->pgmap, struct dmirror_chunk,
+			    pagemap)->mdevice;
+}
+
+static int dmirror_do_fault(struct dmirror *dmirror, struct hmm_range *range)
+{
+	unsigned long *pfns = range->hmm_pfns;
+	unsigned long pfn;
+
+	for (pfn = (range->start >> PAGE_SHIFT);
+	     pfn < (range->end >> PAGE_SHIFT);
+	     pfn++, pfns++) {
+		struct page *page;
+		void *entry;
+
+		/*
+		 * Since we asked for hmm_range_fault() to populate pages,
+		 * it shouldn't return an error entry on success.
+		 */
+		WARN_ON(*pfns & HMM_PFN_ERROR);
+		WARN_ON(!(*pfns & HMM_PFN_VALID));
+
+		page = hmm_pfn_to_page(*pfns);
+		WARN_ON(!page);
+
+		entry = page;
+		if (*pfns & HMM_PFN_WRITE)
+			entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
+		else if (WARN_ON(range->default_flags & HMM_PFN_WRITE))
+			return -EFAULT;
+		entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
+		if (xa_is_err(entry))
+			return xa_err(entry);
+	}
+
+	return 0;
+}
+
+static void dmirror_do_update(struct dmirror *dmirror, unsigned long start,
+			      unsigned long end)
+{
+	unsigned long pfn;
+	void *entry;
+
+	/*
+	 * The XArray doesn't hold references to pages since it relies on
+	 * the mmu notifier to clear page pointers when they become stale.
+	 * Therefore, it is OK to just clear the entry.
+	 */
+	xa_for_each_range(&dmirror->pt, pfn, entry, start >> PAGE_SHIFT,
+			  end >> PAGE_SHIFT)
+		xa_erase(&dmirror->pt, pfn);
+}
+
+static bool dmirror_interval_invalidate(struct mmu_interval_notifier *mni,
+				const struct mmu_notifier_range *range,
+				unsigned long cur_seq)
+{
+	struct dmirror *dmirror = container_of(mni, struct dmirror, notifier);
+
+	/*
+	 * Ignore invalidation callbacks for device private pages since
+	 * the invalidation is handled as part of the migration process.
+	 */
+	if (range->event == MMU_NOTIFY_MIGRATE &&
+	    range->migrate_pgmap_owner == dmirror->mdevice)
+		return true;
+
+	if (mmu_notifier_range_blockable(range))
+		mutex_lock(&dmirror->mutex);
+	else if (!mutex_trylock(&dmirror->mutex))
+		return false;
+
+	mmu_interval_set_seq(mni, cur_seq);
+	dmirror_do_update(dmirror, range->start, range->end);
+
+	mutex_unlock(&dmirror->mutex);
+	return true;
+}
+
+static const struct mmu_interval_notifier_ops dmirror_min_ops = {
+	.invalidate = dmirror_interval_invalidate,
+};
+
+static int dmirror_range_fault(struct dmirror *dmirror,
+				struct hmm_range *range)
+{
+	struct mm_struct *mm = dmirror->notifier.mm;
+	unsigned long timeout =
+		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+	int ret;
+
+	while (true) {
+		if (time_after(jiffies, timeout)) {
+			ret = -EBUSY;
+			goto out;
+		}
+
+		range->notifier_seq = mmu_interval_read_begin(range->notifier);
+		mmap_read_lock(mm);
+		ret = hmm_range_fault(range);
+		mmap_read_unlock(mm);
+		if (ret) {
+			if (ret == -EBUSY)
+				continue;
+			goto out;
+		}
+
+		mutex_lock(&dmirror->mutex);
+		if (mmu_interval_read_retry(range->notifier,
+					    range->notifier_seq)) {
+			mutex_unlock(&dmirror->mutex);
+			continue;
+		}
+		break;
+	}
+
+	ret = dmirror_do_fault(dmirror, range);
+
+	mutex_unlock(&dmirror->mutex);
+out:
+	return ret;
+}
+
+static int dmirror_fault(struct dmirror *dmirror, unsigned long start,
+			 unsigned long end, bool write)
+{
+	struct mm_struct *mm = dmirror->notifier.mm;
+	unsigned long addr;
+	unsigned long pfns[64];
+	struct hmm_range range = {
+		.notifier = &dmirror->notifier,
+		.hmm_pfns = pfns,
+		.pfn_flags_mask = 0,
+		.default_flags =
+			HMM_PFN_REQ_FAULT | (write ? HMM_PFN_REQ_WRITE : 0),
+		.dev_private_owner = dmirror->mdevice,
+	};
+	int ret = 0;
+
+	/* Since the mm is for the mirrored process, get a reference first. */
+	if (!mmget_not_zero(mm))
+		return 0;
+
+	for (addr = start; addr < end; addr = range.end) {
+		range.start = addr;
+		range.end = min(addr + (ARRAY_SIZE(pfns) << PAGE_SHIFT), end);
+
+		ret = dmirror_range_fault(dmirror, &range);
+		if (ret)
+			break;
+	}
+
+	mmput(mm);
+	return ret;
+}
+
+static int dmirror_do_read(struct dmirror *dmirror, unsigned long start,
+			   unsigned long end, struct dmirror_bounce *bounce)
+{
+	unsigned long pfn;
+	void *ptr;
+
+	ptr = bounce->ptr + ((start - bounce->addr) & PAGE_MASK);
+
+	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
+		void *entry;
+		struct page *page;
+		void *tmp;
+
+		entry = xa_load(&dmirror->pt, pfn);
+		page = xa_untag_pointer(entry);
+		if (!page)
+			return -ENOENT;
+
+		tmp = kmap(page);
+		memcpy(ptr, tmp, PAGE_SIZE);
+		kunmap(page);
+
+		ptr += PAGE_SIZE;
+		bounce->cpages++;
+	}
+
+	return 0;
+}
+
+static int dmirror_read(struct dmirror *dmirror, struct hmm_dmirror_cmd *cmd)
+{
+	struct dmirror_bounce bounce;
+	unsigned long start, end;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	int ret;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	ret = dmirror_bounce_init(&bounce, start, size);
+	if (ret)
+		return ret;
+
+	while (1) {
+		mutex_lock(&dmirror->mutex);
+		ret = dmirror_do_read(dmirror, start, end, &bounce);
+		mutex_unlock(&dmirror->mutex);
+		if (ret != -ENOENT)
+			break;
+
+		start = cmd->addr + (bounce.cpages << PAGE_SHIFT);
+		ret = dmirror_fault(dmirror, start, end, false);
+		if (ret)
+			break;
+		cmd->faults++;
+	}
+
+	if (ret == 0) {
+		if (copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr,
+				 bounce.size))
+			ret = -EFAULT;
+	}
+	cmd->cpages = bounce.cpages;
+	dmirror_bounce_fini(&bounce);
+	return ret;
+}
+
+static int dmirror_do_write(struct dmirror *dmirror, unsigned long start,
+			    unsigned long end, struct dmirror_bounce *bounce)
+{
+	unsigned long pfn;
+	void *ptr;
+
+	ptr = bounce->ptr + ((start - bounce->addr) & PAGE_MASK);
+
+	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
+		void *entry;
+		struct page *page;
+		void *tmp;
+
+		entry = xa_load(&dmirror->pt, pfn);
+		page = xa_untag_pointer(entry);
+		if (!page || xa_pointer_tag(entry) != DPT_XA_TAG_WRITE)
+			return -ENOENT;
+
+		tmp = kmap(page);
+		memcpy(tmp, ptr, PAGE_SIZE);
+		kunmap(page);
+
+		ptr += PAGE_SIZE;
+		bounce->cpages++;
+	}
+
+	return 0;
+}
+
+static int dmirror_write(struct dmirror *dmirror, struct hmm_dmirror_cmd *cmd)
+{
+	struct dmirror_bounce bounce;
+	unsigned long start, end;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	int ret;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	ret = dmirror_bounce_init(&bounce, start, size);
+	if (ret)
+		return ret;
+	if (copy_from_user(bounce.ptr, u64_to_user_ptr(cmd->ptr),
+			   bounce.size)) {
+		ret = -EFAULT;
+		goto fini;
+	}
+
+	while (1) {
+		mutex_lock(&dmirror->mutex);
+		ret = dmirror_do_write(dmirror, start, end, &bounce);
+		mutex_unlock(&dmirror->mutex);
+		if (ret != -ENOENT)
+			break;
+
+		start = cmd->addr + (bounce.cpages << PAGE_SHIFT);
+		ret = dmirror_fault(dmirror, start, end, true);
+		if (ret)
+			break;
+		cmd->faults++;
+	}
+
+fini:
+	cmd->cpages = bounce.cpages;
+	dmirror_bounce_fini(&bounce);
+	return ret;
+}
+
+static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
+				   struct page **ppage)
+{
+	struct dmirror_chunk *devmem;
+	struct resource *res;
+	unsigned long pfn;
+	unsigned long pfn_first;
+	unsigned long pfn_last;
+	void *ptr;
+
+	mutex_lock(&mdevice->devmem_lock);
+
+	if (mdevice->devmem_count == mdevice->devmem_capacity) {
+		struct dmirror_chunk **new_chunks;
+		unsigned int new_capacity;
+
+		new_capacity = mdevice->devmem_capacity +
+				DEVMEM_CHUNKS_RESERVE;
+		new_chunks = krealloc(mdevice->devmem_chunks,
+				sizeof(new_chunks[0]) * new_capacity,
+				GFP_KERNEL);
+		if (!new_chunks)
+			goto err;
+		mdevice->devmem_capacity = new_capacity;
+		mdevice->devmem_chunks = new_chunks;
+	}
+
+	res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
+					"hmm_dmirror");
+	if (IS_ERR(res))
+		goto err;
+
+	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
+	if (!devmem)
+		goto err_release;
+
+	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
+	devmem->pagemap.res = *res;
+	devmem->pagemap.ops = &dmirror_devmem_ops;
+	devmem->pagemap.owner = mdevice;
+
+	ptr = memremap_pages(&devmem->pagemap, numa_node_id());
+	if (IS_ERR(ptr))
+		goto err_free;
+
+	devmem->mdevice = mdevice;
+	pfn_first = devmem->pagemap.res.start >> PAGE_SHIFT;
+	pfn_last = pfn_first +
+		(resource_size(&devmem->pagemap.res) >> PAGE_SHIFT);
+	mdevice->devmem_chunks[mdevice->devmem_count++] = devmem;
+
+	mutex_unlock(&mdevice->devmem_lock);
+
+	pr_info("added new %u MB chunk (total %u chunks, %u MB) PFNs [0x%lx 0x%lx)\n",
+		DEVMEM_CHUNK_SIZE / (1024 * 1024),
+		mdevice->devmem_count,
+		mdevice->devmem_count * (DEVMEM_CHUNK_SIZE / (1024 * 1024)),
+		pfn_first, pfn_last);
+
+	spin_lock(&mdevice->lock);
+	for (pfn = pfn_first; pfn < pfn_last; pfn++) {
+		struct page *page = pfn_to_page(pfn);
+
+		page->zone_device_data = mdevice->free_pages;
+		mdevice->free_pages = page;
+	}
+	if (ppage) {
+		*ppage = mdevice->free_pages;
+		mdevice->free_pages = (*ppage)->zone_device_data;
+		mdevice->calloc++;
+	}
+	spin_unlock(&mdevice->lock);
+
+	return true;
+
+err_free:
+	kfree(devmem);
+err_release:
+	release_mem_region(res->start, resource_size(res));
+err:
+	mutex_unlock(&mdevice->devmem_lock);
+	return false;
+}
+
+static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
+{
+	struct page *dpage = NULL;
+	struct page *rpage;
+
+	/*
+	 * This is a fake device so we alloc real system memory to store
+	 * our device memory.
+	 */
+	rpage = alloc_page(GFP_HIGHUSER);
+	if (!rpage)
+		return NULL;
+
+	spin_lock(&mdevice->lock);
+
+	if (mdevice->free_pages) {
+		dpage = mdevice->free_pages;
+		mdevice->free_pages = dpage->zone_device_data;
+		mdevice->calloc++;
+		spin_unlock(&mdevice->lock);
+	} else {
+		spin_unlock(&mdevice->lock);
+		if (!dmirror_allocate_chunk(mdevice, &dpage))
+			goto error;
+	}
+
+	dpage->zone_device_data = rpage;
+	get_page(dpage);
+	lock_page(dpage);
+	return dpage;
+
+error:
+	__free_page(rpage);
+	return NULL;
+}
+
+static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
+					   struct dmirror *dmirror)
+{
+	struct dmirror_device *mdevice = dmirror->mdevice;
+	const unsigned long *src = args->src;
+	unsigned long *dst = args->dst;
+	unsigned long addr;
+
+	for (addr = args->start; addr < args->end; addr += PAGE_SIZE,
+						   src++, dst++) {
+		struct page *spage;
+		struct page *dpage;
+		struct page *rpage;
+
+		if (!(*src & MIGRATE_PFN_MIGRATE))
+			continue;
+
+		/*
+		 * Note that spage might be NULL which is OK since it is an
+		 * unallocated pte_none() or read-only zero page.
+		 */
+		spage = migrate_pfn_to_page(*src);
+
+		dpage = dmirror_devmem_alloc_page(mdevice);
+		if (!dpage)
+			continue;
+
+		rpage = dpage->zone_device_data;
+		if (spage)
+			copy_highpage(rpage, spage);
+		else
+			clear_highpage(rpage);
+
+		/*
+		 * Normally, a device would use the page->zone_device_data to
+		 * point to the mirror but here we use it to hold the page for
+		 * the simulated device memory and that page holds the pointer
+		 * to the mirror.
+		 */
+		rpage->zone_device_data = dmirror;
+
+		*dst = migrate_pfn(page_to_pfn(dpage)) |
+			    MIGRATE_PFN_LOCKED;
+		if ((*src & MIGRATE_PFN_WRITE) ||
+		    (!spage && args->vma->vm_flags & VM_WRITE))
+			*dst |= MIGRATE_PFN_WRITE;
+	}
+}
+
+static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
+					    struct dmirror *dmirror)
+{
+	unsigned long start = args->start;
+	unsigned long end = args->end;
+	const unsigned long *src = args->src;
+	const unsigned long *dst = args->dst;
+	unsigned long pfn;
+
+	/* Map the migrated pages into the device's page tables. */
+	mutex_lock(&dmirror->mutex);
+
+	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++,
+								src++, dst++) {
+		struct page *dpage;
+		void *entry;
+
+		if (!(*src & MIGRATE_PFN_MIGRATE))
+			continue;
+
+		dpage = migrate_pfn_to_page(*dst);
+		if (!dpage)
+			continue;
+
+		/*
+		 * Store the page that holds the data so the page table
+		 * doesn't have to deal with ZONE_DEVICE private pages.
+		 */
+		entry = dpage->zone_device_data;
+		if (*dst & MIGRATE_PFN_WRITE)
+			entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
+		entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
+		if (xa_is_err(entry)) {
+			mutex_unlock(&dmirror->mutex);
+			return xa_err(entry);
+		}
+	}
+
+	mutex_unlock(&dmirror->mutex);
+	return 0;
+}
+
+static int dmirror_migrate(struct dmirror *dmirror,
+			   struct hmm_dmirror_cmd *cmd)
+{
+	unsigned long start, end, addr;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	struct mm_struct *mm = dmirror->notifier.mm;
+	struct vm_area_struct *vma;
+	unsigned long src_pfns[64];
+	unsigned long dst_pfns[64];
+	struct dmirror_bounce bounce;
+	struct migrate_vma args;
+	unsigned long next;
+	int ret;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	/* Since the mm is for the mirrored process, get a reference first. */
+	if (!mmget_not_zero(mm))
+		return -EINVAL;
+
+	mmap_read_lock(mm);
+	for (addr = start; addr < end; addr = next) {
+		vma = find_vma(mm, addr);
+		if (!vma || addr < vma->vm_start ||
+		    !(vma->vm_flags & VM_READ)) {
+			ret = -EINVAL;
+			goto out;
+		}
+		next = min(end, addr + (ARRAY_SIZE(src_pfns) << PAGE_SHIFT));
+		if (next > vma->vm_end)
+			next = vma->vm_end;
+
+		args.vma = vma;
+		args.src = src_pfns;
+		args.dst = dst_pfns;
+		args.start = addr;
+		args.end = next;
+		args.pgmap_owner = dmirror->mdevice;
+		args.flags = MIGRATE_VMA_SELECT_SYSTEM;
+		ret = migrate_vma_setup(&args);
+		if (ret)
+			goto out;
+
+		dmirror_migrate_alloc_and_copy(&args, dmirror);
+		migrate_vma_pages(&args);
+		dmirror_migrate_finalize_and_map(&args, dmirror);
+		migrate_vma_finalize(&args);
+	}
+	mmap_read_unlock(mm);
+	mmput(mm);
+
+	/* Return the migrated data for verification. */
+	ret = dmirror_bounce_init(&bounce, start, size);
+	if (ret)
+		return ret;
+	mutex_lock(&dmirror->mutex);
+	ret = dmirror_do_read(dmirror, start, end, &bounce);
+	mutex_unlock(&dmirror->mutex);
+	if (ret == 0) {
+		if (copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr,
+				 bounce.size))
+			ret = -EFAULT;
+	}
+	cmd->cpages = bounce.cpages;
+	dmirror_bounce_fini(&bounce);
+	return ret;
+
+out:
+	mmap_read_unlock(mm);
+	mmput(mm);
+	return ret;
+}
+
+static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range,
+			    unsigned char *perm, unsigned long entry)
+{
+	struct page *page;
+
+	if (entry & HMM_PFN_ERROR) {
+		*perm = HMM_DMIRROR_PROT_ERROR;
+		return;
+	}
+	if (!(entry & HMM_PFN_VALID)) {
+		*perm = HMM_DMIRROR_PROT_NONE;
+		return;
+	}
+
+	page = hmm_pfn_to_page(entry);
+	if (is_device_private_page(page)) {
+		/* Is the page migrated to this device or some other? */
+		if (dmirror->mdevice == dmirror_page_to_device(page))
+			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL;
+		else
+			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE;
+	} else if (is_zero_pfn(page_to_pfn(page)))
+		*perm = HMM_DMIRROR_PROT_ZERO;
+	else
+		*perm = HMM_DMIRROR_PROT_NONE;
+	if (entry & HMM_PFN_WRITE)
+		*perm |= HMM_DMIRROR_PROT_WRITE;
+	else
+		*perm |= HMM_DMIRROR_PROT_READ;
+	if (hmm_pfn_to_map_order(entry) + PAGE_SHIFT == PMD_SHIFT)
+		*perm |= HMM_DMIRROR_PROT_PMD;
+	else if (hmm_pfn_to_map_order(entry) + PAGE_SHIFT == PUD_SHIFT)
+		*perm |= HMM_DMIRROR_PROT_PUD;
+}
+
+static bool dmirror_snapshot_invalidate(struct mmu_interval_notifier *mni,
+				const struct mmu_notifier_range *range,
+				unsigned long cur_seq)
+{
+	struct dmirror_interval *dmi =
+		container_of(mni, struct dmirror_interval, notifier);
+	struct dmirror *dmirror = dmi->dmirror;
+
+	if (mmu_notifier_range_blockable(range))
+		mutex_lock(&dmirror->mutex);
+	else if (!mutex_trylock(&dmirror->mutex))
+		return false;
+
+	/*
+	 * Snapshots only need to set the sequence number since any
+	 * invalidation in the interval invalidates the whole snapshot.
+	 */
+	mmu_interval_set_seq(mni, cur_seq);
+
+	mutex_unlock(&dmirror->mutex);
+	return true;
+}
+
+static const struct mmu_interval_notifier_ops dmirror_mrn_ops = {
+	.invalidate = dmirror_snapshot_invalidate,
+};
+
+static int dmirror_range_snapshot(struct dmirror *dmirror,
+				  struct hmm_range *range,
+				  unsigned char *perm)
+{
+	struct mm_struct *mm = dmirror->notifier.mm;
+	struct dmirror_interval notifier;
+	unsigned long timeout =
+		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+	unsigned long i;
+	unsigned long n;
+	int ret = 0;
+
+	notifier.dmirror = dmirror;
+	range->notifier = &notifier.notifier;
+
+	ret = mmu_interval_notifier_insert(range->notifier, mm,
+			range->start, range->end - range->start,
+			&dmirror_mrn_ops);
+	if (ret)
+		return ret;
+
+	while (true) {
+		if (time_after(jiffies, timeout)) {
+			ret = -EBUSY;
+			goto out;
+		}
+
+		range->notifier_seq = mmu_interval_read_begin(range->notifier);
+
+		mmap_read_lock(mm);
+		ret = hmm_range_fault(range);
+		mmap_read_unlock(mm);
+		if (ret) {
+			if (ret == -EBUSY)
+				continue;
+			goto out;
+		}
+
+		mutex_lock(&dmirror->mutex);
+		if (mmu_interval_read_retry(range->notifier,
+					    range->notifier_seq)) {
+			mutex_unlock(&dmirror->mutex);
+			continue;
+		}
+		break;
+	}
+
+	n = (range->end - range->start) >> PAGE_SHIFT;
+	for (i = 0; i < n; i++)
+		dmirror_mkentry(dmirror, range, perm + i, range->hmm_pfns[i]);
+
+	mutex_unlock(&dmirror->mutex);
+out:
+	mmu_interval_notifier_remove(range->notifier);
+	return ret;
+}
+
+static int dmirror_snapshot(struct dmirror *dmirror,
+			    struct hmm_dmirror_cmd *cmd)
+{
+	struct mm_struct *mm = dmirror->notifier.mm;
+	unsigned long start, end;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	unsigned long addr;
+	unsigned long next;
+	unsigned long pfns[64];
+	unsigned char perm[64];
+	char __user *uptr;
+	struct hmm_range range = {
+		.hmm_pfns = pfns,
+		.dev_private_owner = dmirror->mdevice,
+	};
+	int ret = 0;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	/* Since the mm is for the mirrored process, get a reference first. */
+	if (!mmget_not_zero(mm))
+		return -EINVAL;
+
+	/*
+	 * Register a temporary notifier to detect invalidations even if it
+	 * overlaps with other mmu_interval_notifiers.
+	 */
+	uptr = u64_to_user_ptr(cmd->ptr);
+	for (addr = start; addr < end; addr = next) {
+		unsigned long n;
+
+		next = min(addr + (ARRAY_SIZE(pfns) << PAGE_SHIFT), end);
+		range.start = addr;
+		range.end = next;
+
+		ret = dmirror_range_snapshot(dmirror, &range, perm);
+		if (ret)
+			break;
+
+		n = (range.end - range.start) >> PAGE_SHIFT;
+		if (copy_to_user(uptr, perm, n)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		cmd->cpages += n;
+		uptr += n;
+	}
+	mmput(mm);
+
+	return ret;
+}
+
+static long dmirror_fops_unlocked_ioctl(struct file *filp,
+					unsigned int command,
+					unsigned long arg)
+{
+	void __user *uarg = (void __user *)arg;
+	struct hmm_dmirror_cmd cmd;
+	struct dmirror *dmirror;
+	int ret;
+
+	dmirror = filp->private_data;
+	if (!dmirror)
+		return -EINVAL;
+
+	if (copy_from_user(&cmd, uarg, sizeof(cmd)))
+		return -EFAULT;
+
+	if (cmd.addr & ~PAGE_MASK)
+		return -EINVAL;
+	if (cmd.addr >= (cmd.addr + (cmd.npages << PAGE_SHIFT)))
+		return -EINVAL;
+
+	cmd.cpages = 0;
+	cmd.faults = 0;
+
+	switch (command) {
+	case HMM_DMIRROR_READ:
+		ret = dmirror_read(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_WRITE:
+		ret = dmirror_write(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_MIGRATE:
+		ret = dmirror_migrate(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_SNAPSHOT:
+		ret = dmirror_snapshot(dmirror, &cmd);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+	if (ret)
+		return ret;
+
+	if (copy_to_user(uarg, &cmd, sizeof(cmd)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static const struct file_operations dmirror_fops = {
+	.open		= dmirror_fops_open,
+	.release	= dmirror_fops_release,
+	.unlocked_ioctl = dmirror_fops_unlocked_ioctl,
+	.llseek		= default_llseek,
+	.owner		= THIS_MODULE,
+};
+
+static void dmirror_devmem_free(struct page *page)
+{
+	struct page *rpage = page->zone_device_data;
+	struct dmirror_device *mdevice;
+
+	if (rpage)
+		__free_page(rpage);
+
+	mdevice = dmirror_page_to_device(page);
+
+	spin_lock(&mdevice->lock);
+	mdevice->cfree++;
+	page->zone_device_data = mdevice->free_pages;
+	mdevice->free_pages = page;
+	spin_unlock(&mdevice->lock);
+}
+
+static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
+						      struct dmirror *dmirror)
+{
+	const unsigned long *src = args->src;
+	unsigned long *dst = args->dst;
+	unsigned long start = args->start;
+	unsigned long end = args->end;
+	unsigned long addr;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE,
+				       src++, dst++) {
+		struct page *dpage, *spage;
+
+		spage = migrate_pfn_to_page(*src);
+		if (!spage || !(*src & MIGRATE_PFN_MIGRATE))
+			continue;
+		spage = spage->zone_device_data;
+
+		dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
+		if (!dpage)
+			continue;
+
+		lock_page(dpage);
+		xa_erase(&dmirror->pt, addr >> PAGE_SHIFT);
+		copy_highpage(dpage, spage);
+		*dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
+		if (*src & MIGRATE_PFN_WRITE)
+			*dst |= MIGRATE_PFN_WRITE;
+	}
+	return 0;
+}
+
+static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
+{
+	struct migrate_vma args;
+	unsigned long src_pfns;
+	unsigned long dst_pfns;
+	struct page *rpage;
+	struct dmirror *dmirror;
+	vm_fault_t ret;
+
+	/*
+	 * Normally, a device would use the page->zone_device_data to point to
+	 * the mirror but here we use it to hold the page for the simulated
+	 * device memory and that page holds the pointer to the mirror.
+	 */
+	rpage = vmf->page->zone_device_data;
+	dmirror = rpage->zone_device_data;
+
+	/* FIXME demonstrate how we can adjust migrate range */
+	args.vma = vmf->vma;
+	args.start = vmf->address;
+	args.end = args.start + PAGE_SIZE;
+	args.src = &src_pfns;
+	args.dst = &dst_pfns;
+	args.pgmap_owner = dmirror->mdevice;
+	args.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
+
+	if (migrate_vma_setup(&args))
+		return VM_FAULT_SIGBUS;
+
+	ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror);
+	if (ret)
+		return ret;
+	migrate_vma_pages(&args);
+	/*
+	 * No device finalize step is needed since
+	 * dmirror_devmem_fault_alloc_and_copy() will have already
+	 * invalidated the device page table.
+	 */
+	migrate_vma_finalize(&args);
+	return 0;
+}
+
+static const struct dev_pagemap_ops dmirror_devmem_ops = {
+	.page_free	= dmirror_devmem_free,
+	.migrate_to_ram	= dmirror_devmem_fault,
+};
+
+static int dmirror_device_init(struct dmirror_device *mdevice, int id)
+{
+	dev_t dev;
+	int ret;
+
+	dev = MKDEV(MAJOR(dmirror_dev), id);
+	mutex_init(&mdevice->devmem_lock);
+	spin_lock_init(&mdevice->lock);
+
+	cdev_init(&mdevice->cdevice, &dmirror_fops);
+	mdevice->cdevice.owner = THIS_MODULE;
+	ret = cdev_add(&mdevice->cdevice, dev, 1);
+	if (ret)
+		return ret;
+
+	/* Build a list of free ZONE_DEVICE private struct pages */
+	dmirror_allocate_chunk(mdevice, NULL);
+
+	return 0;
+}
+
+static void dmirror_device_remove(struct dmirror_device *mdevice)
+{
+	unsigned int i;
+
+	if (mdevice->devmem_chunks) {
+		for (i = 0; i < mdevice->devmem_count; i++) {
+			struct dmirror_chunk *devmem =
+				mdevice->devmem_chunks[i];
+
+			memunmap_pages(&devmem->pagemap);
+			release_mem_region(devmem->pagemap.res.start,
+					   resource_size(&devmem->pagemap.res));
+			kfree(devmem);
+		}
+		kfree(mdevice->devmem_chunks);
+	}
+
+	cdev_del(&mdevice->cdevice);
+}
+
+static int __init hmm_dmirror_init(void)
+{
+	int ret;
+	int id;
+
+	ret = alloc_chrdev_region(&dmirror_dev, 0, DMIRROR_NDEVICES,
+				  "HMM_DMIRROR");
+	if (ret)
+		goto err_unreg;
+
+	for (id = 0; id < DMIRROR_NDEVICES; id++) {
+		ret = dmirror_device_init(dmirror_devices + id, id);
+		if (ret)
+			goto err_chrdev;
+	}
+
+	/*
+	 * Allocate a zero page to simulate a reserved page of device private
+	 * memory which is always zero. The zero_pfn page isn't used just to
+	 * make the code here simpler (i.e., we need a struct page for it).
+	 */
+	dmirror_zero_page = alloc_page(GFP_HIGHUSER | __GFP_ZERO);
+	if (!dmirror_zero_page) {
+		ret = -ENOMEM;
+		goto err_chrdev;
+	}
+
+	pr_info("HMM test module loaded. This is only for testing HMM.\n");
+	return 0;
+
+err_chrdev:
+	while (--id >= 0)
+		dmirror_device_remove(dmirror_devices + id);
+	unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES);
+err_unreg:
+	return ret;
+}
+
+static void __exit hmm_dmirror_exit(void)
+{
+	int id;
+
+	if (dmirror_zero_page)
+		__free_page(dmirror_zero_page);
+	for (id = 0; id < DMIRROR_NDEVICES; id++)
+		dmirror_device_remove(dmirror_devices + id);
+	unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES);
+}
+
+module_init(hmm_dmirror_init);
+module_exit(hmm_dmirror_exit);
+MODULE_LICENSE("GPL");
diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h
new file mode 100644
index 000000000000..670b4ef2a5b6
--- /dev/null
+++ b/lib/test_hmm_uapi.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * This is a module to test the HMM (Heterogeneous Memory Management) API
+ * of the kernel. It allows a userspace program to expose its entire address
+ * space through the HMM test module device file.
+ */
+#ifndef _LIB_TEST_HMM_UAPI_H
+#define _LIB_TEST_HMM_UAPI_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * Structure to pass to the HMM test driver to mimic a device accessing
+ * system memory and ZONE_DEVICE private memory through device page tables.
+ *
+ * @addr: (in) user address the device will read/write
+ * @ptr: (in) user address where device data is copied to/from
+ * @npages: (in) number of pages to read/write
+ * @cpages: (out) number of pages copied
+ * @faults: (out) number of device page faults seen
+ */
+struct hmm_dmirror_cmd {
+	__u64		addr;
+	__u64		ptr;
+	__u64		npages;
+	__u64		cpages;
+	__u64		faults;
+};
+
+/* Expose the address space of the calling process through hmm device file */
+#define HMM_DMIRROR_READ		_IOWR('H', 0x00, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_WRITE		_IOWR('H', 0x01, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_MIGRATE		_IOWR('H', 0x02, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_SNAPSHOT		_IOWR('H', 0x03, struct hmm_dmirror_cmd)
+
+/*
+ * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT.
+ * HMM_DMIRROR_PROT_ERROR: no valid mirror PTE for this page
+ * HMM_DMIRROR_PROT_NONE: unpopulated PTE or PTE with no access
+ * HMM_DMIRROR_PROT_READ: read-only PTE
+ * HMM_DMIRROR_PROT_WRITE: read/write PTE
+ * HMM_DMIRROR_PROT_PMD: PMD sized page is fully mapped by same permissions
+ * HMM_DMIRROR_PROT_PUD: PUD sized page is fully mapped by same permissions
+ * HMM_DMIRROR_PROT_ZERO: special read-only zero page
+ * HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL: Migrated device private page on the
+ *					device the ioctl() is made
+ * HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE: Migrated device private page on some
+ *					other device
+ */
+enum {
+	HMM_DMIRROR_PROT_ERROR			= 0xFF,
+	HMM_DMIRROR_PROT_NONE			= 0x00,
+	HMM_DMIRROR_PROT_READ			= 0x01,
+	HMM_DMIRROR_PROT_WRITE			= 0x02,
+	HMM_DMIRROR_PROT_PMD			= 0x04,
+	HMM_DMIRROR_PROT_PUD			= 0x08,
+	HMM_DMIRROR_PROT_ZERO			= 0x10,
+	HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL	= 0x20,
+	HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE	= 0x30,
+};
+
+#endif /* _LIB_TEST_HMM_UAPI_H */
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index e3087d90e00d..53e953bb1d1d 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -23,6 +23,18 @@
 
 #include <asm/page.h>
 
+#include "../mm/kasan/kasan.h"
+
+#define OOB_TAG_OFF (IS_ENABLED(CONFIG_KASAN_GENERIC) ? 0 : KASAN_SHADOW_SCALE_SIZE)
+
+/*
+ * We assign some test results to these globals to make sure the tests
+ * are not eliminated as dead code.
+ */
+
+int kasan_int_result;
+void *kasan_ptr_result;
+
 /*
  * Note: test functions are marked noinline so that their names appear in
  * reports.
@@ -40,7 +52,8 @@ static noinline void __init kmalloc_oob_right(void)
 		return;
 	}
 
-	ptr[size] = 'x';
+	ptr[size + OOB_TAG_OFF] = 'x';
+
 	kfree(ptr);
 }
 
@@ -92,7 +105,8 @@ static noinline void __init kmalloc_pagealloc_oob_right(void)
 		return;
 	}
 
-	ptr[size] = 0;
+	ptr[size + OOB_TAG_OFF] = 0;
+
 	kfree(ptr);
 }
 
@@ -162,7 +176,8 @@ static noinline void __init kmalloc_oob_krealloc_more(void)
 		return;
 	}
 
-	ptr2[size2] = 'x';
+	ptr2[size2 + OOB_TAG_OFF] = 'x';
+
 	kfree(ptr2);
 }
 
@@ -180,7 +195,9 @@ static noinline void __init kmalloc_oob_krealloc_less(void)
 		kfree(ptr1);
 		return;
 	}
-	ptr2[size2] = 'x';
+
+	ptr2[size2 + OOB_TAG_OFF] = 'x';
+
 	kfree(ptr2);
 }
 
@@ -216,7 +233,8 @@ static noinline void __init kmalloc_oob_memset_2(void)
 		return;
 	}
 
-	memset(ptr+7, 0, 2);
+	memset(ptr + 7 + OOB_TAG_OFF, 0, 2);
+
 	kfree(ptr);
 }
 
@@ -232,7 +250,8 @@ static noinline void __init kmalloc_oob_memset_4(void)
 		return;
 	}
 
-	memset(ptr+5, 0, 4);
+	memset(ptr + 5 + OOB_TAG_OFF, 0, 4);
+
 	kfree(ptr);
 }
 
@@ -249,7 +268,8 @@ static noinline void __init kmalloc_oob_memset_8(void)
 		return;
 	}
 
-	memset(ptr+1, 0, 8);
+	memset(ptr + 1 + OOB_TAG_OFF, 0, 8);
+
 	kfree(ptr);
 }
 
@@ -265,7 +285,8 @@ static noinline void __init kmalloc_oob_memset_16(void)
 		return;
 	}
 
-	memset(ptr+1, 0, 16);
+	memset(ptr + 1 + OOB_TAG_OFF, 0, 16);
+
 	kfree(ptr);
 }
 
@@ -281,7 +302,8 @@ static noinline void __init kmalloc_oob_in_memset(void)
 		return;
 	}
 
-	memset(ptr, 0, size+5);
+	memset(ptr, 0, size + 5 + OOB_TAG_OFF);
+
 	kfree(ptr);
 }
 
@@ -415,7 +437,8 @@ static noinline void __init kmem_cache_oob(void)
 		return;
 	}
 
-	*p = p[size];
+	*p = p[size + OOB_TAG_OFF];
+
 	kmem_cache_free(cache, p);
 	kmem_cache_destroy(cache);
 }
@@ -465,7 +488,7 @@ static noinline void __init kasan_global_oob(void)
 static noinline void __init kasan_stack_oob(void)
 {
 	char stack_array[10];
-	volatile int i = 0;
+	volatile int i = OOB_TAG_OFF;
 	char *p = &stack_array[ARRAY_SIZE(stack_array) + i];
 
 	pr_info("out-of-bounds on stack\n");
@@ -512,25 +535,25 @@ static noinline void __init copy_user_test(void)
 	}
 
 	pr_info("out-of-bounds in copy_from_user()\n");
-	unused = copy_from_user(kmem, usermem, size + 1);
+	unused = copy_from_user(kmem, usermem, size + 1 + OOB_TAG_OFF);
 
 	pr_info("out-of-bounds in copy_to_user()\n");
-	unused = copy_to_user(usermem, kmem, size + 1);
+	unused = copy_to_user(usermem, kmem, size + 1 + OOB_TAG_OFF);
 
 	pr_info("out-of-bounds in __copy_from_user()\n");
-	unused = __copy_from_user(kmem, usermem, size + 1);
+	unused = __copy_from_user(kmem, usermem, size + 1 + OOB_TAG_OFF);
 
 	pr_info("out-of-bounds in __copy_to_user()\n");
-	unused = __copy_to_user(usermem, kmem, size + 1);
+	unused = __copy_to_user(usermem, kmem, size + 1 + OOB_TAG_OFF);
 
 	pr_info("out-of-bounds in __copy_from_user_inatomic()\n");
-	unused = __copy_from_user_inatomic(kmem, usermem, size + 1);
+	unused = __copy_from_user_inatomic(kmem, usermem, size + 1 + OOB_TAG_OFF);
 
 	pr_info("out-of-bounds in __copy_to_user_inatomic()\n");
-	unused = __copy_to_user_inatomic(usermem, kmem, size + 1);
+	unused = __copy_to_user_inatomic(usermem, kmem, size + 1 + OOB_TAG_OFF);
 
 	pr_info("out-of-bounds in strncpy_from_user()\n");
-	unused = strncpy_from_user(kmem, usermem, size + 1);
+	unused = strncpy_from_user(kmem, usermem, size + 1 + OOB_TAG_OFF);
 
 	vm_munmap((unsigned long)usermem, PAGE_SIZE);
 	kfree(kmem);
@@ -622,7 +645,7 @@ static noinline void __init kasan_memchr(void)
 	if (!ptr)
 		return;
 
-	memchr(ptr, '1', size + 1);
+	kasan_ptr_result = memchr(ptr, '1', size + 1);
 	kfree(ptr);
 }
 
@@ -638,7 +661,7 @@ static noinline void __init kasan_memcmp(void)
 		return;
 
 	memset(arr, 0, sizeof(arr));
-	memcmp(ptr, arr, size+1);
+	kasan_int_result = memcmp(ptr, arr, size + 1);
 	kfree(ptr);
 }
 
@@ -661,22 +684,22 @@ static noinline void __init kasan_strings(void)
 	 * will likely point to zeroed byte.
 	 */
 	ptr += 16;
-	strchr(ptr, '1');
+	kasan_ptr_result = strchr(ptr, '1');
 
 	pr_info("use-after-free in strrchr\n");
-	strrchr(ptr, '1');
+	kasan_ptr_result = strrchr(ptr, '1');
 
 	pr_info("use-after-free in strcmp\n");
-	strcmp(ptr, "2");
+	kasan_int_result = strcmp(ptr, "2");
 
 	pr_info("use-after-free in strncmp\n");
-	strncmp(ptr, "2", 1);
+	kasan_int_result = strncmp(ptr, "2", 1);
 
 	pr_info("use-after-free in strlen\n");
-	strlen(ptr);
+	kasan_int_result = strlen(ptr);
 
 	pr_info("use-after-free in strnlen\n");
-	strnlen(ptr, 1);
+	kasan_int_result = strnlen(ptr, 1);
 }
 
 static noinline void __init kasan_bitops(void)
@@ -743,11 +766,12 @@ static noinline void __init kasan_bitops(void)
 	__test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits);
 
 	pr_info("out-of-bounds in test_bit\n");
-	(void)test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits);
+	kasan_int_result = test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits);
 
 #if defined(clear_bit_unlock_is_negative_byte)
 	pr_info("out-of-bounds in clear_bit_unlock_is_negative_byte\n");
-	clear_bit_unlock_is_negative_byte(BITS_PER_LONG + BITS_PER_BYTE, bits);
+	kasan_int_result = clear_bit_unlock_is_negative_byte(BITS_PER_LONG +
+		BITS_PER_BYTE, bits);
 #endif
 	kfree(bits);
 }
@@ -757,15 +781,15 @@ static noinline void __init kmalloc_double_kzfree(void)
 	char *ptr;
 	size_t size = 16;
 
-	pr_info("double-free (kzfree)\n");
+	pr_info("double-free (kfree_sensitive)\n");
 	ptr = kmalloc(size, GFP_KERNEL);
 	if (!ptr) {
 		pr_err("Allocation failed\n");
 		return;
 	}
 
-	kzfree(ptr);
-	kzfree(ptr);
+	kfree_sensitive(ptr);
+	kfree_sensitive(ptr);
 }
 
 #ifdef CONFIG_KASAN_VMALLOC
@@ -792,6 +816,35 @@ static noinline void __init vmalloc_oob(void)
 static void __init vmalloc_oob(void) {}
 #endif
 
+static struct kasan_rcu_info {
+	int i;
+	struct rcu_head rcu;
+} *global_rcu_ptr;
+
+static noinline void __init kasan_rcu_reclaim(struct rcu_head *rp)
+{
+	struct kasan_rcu_info *fp = container_of(rp,
+						struct kasan_rcu_info, rcu);
+
+	kfree(fp);
+	fp->i = 1;
+}
+
+static noinline void __init kasan_rcu_uaf(void)
+{
+	struct kasan_rcu_info *ptr;
+
+	pr_info("use-after-free in kasan_rcu_reclaim\n");
+	ptr = kmalloc(sizeof(struct kasan_rcu_info), GFP_KERNEL);
+	if (!ptr) {
+		pr_err("Allocation failed\n");
+		return;
+	}
+
+	global_rcu_ptr = rcu_dereference_protected(ptr, NULL);
+	call_rcu(&global_rcu_ptr->rcu, kasan_rcu_reclaim);
+}
+
 static int __init kmalloc_tests_init(void)
 {
 	/*
@@ -839,6 +892,7 @@ static int __init kmalloc_tests_init(void)
 	kasan_bitops();
 	kmalloc_double_kzfree();
 	vmalloc_oob();
+	kasan_rcu_uaf();
 
 	kasan_restore_multi_shot(multishot);
 
diff --git a/lib/test_kmod.c b/lib/test_kmod.c
index e651c37d56db..eab52770070d 100644
--- a/lib/test_kmod.c
+++ b/lib/test_kmod.c
@@ -745,7 +745,7 @@ static int trigger_config_run_type(struct kmod_test_device *test_dev,
 		break;
 	case TEST_KMOD_FS_TYPE:
 		kfree_const(config->test_fs);
-		config->test_driver = NULL;
+		config->test_fs = NULL;
 		copied = config_copy_test_fs(config, test_str,
 					     strlen(test_str));
 		break;
diff --git a/lib/test_linear_ranges.c b/lib/test_linear_ranges.c
new file mode 100644
index 000000000000..676e0b8abcdd
--- /dev/null
+++ b/lib/test_linear_ranges.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test for the linear_ranges helper.
+ *
+ * Copyright (C) 2020, ROHM Semiconductors.
+ * Author: Matti Vaittinen <matti.vaittien@fi.rohmeurope.com>
+ */
+#include <kunit/test.h>
+
+#include <linux/linear_range.h>
+
+/* First things first. I deeply dislike unit-tests. I have seen all the hell
+ * breaking loose when people who think the unit tests are "the silver bullet"
+ * to kill bugs get to decide how a company should implement testing strategy...
+ *
+ * Believe me, it may get _really_ ridiculous. It is tempting to think that
+ * walking through all the possible execution branches will nail down 100% of
+ * bugs. This may lead to ideas about demands to get certain % of "test
+ * coverage" - measured as line coverage. And that is one of the worst things
+ * you can do.
+ *
+ * Ask people to provide line coverage and they do. I've seen clever tools
+ * which generate test cases to test the existing functions - and by default
+ * these tools expect code to be correct and just generate checks which are
+ * passing when ran against current code-base. Run this generator and you'll get
+ * tests that do not test code is correct but just verify nothing changes.
+ * Problem is that testing working code is pointless. And if it is not
+ * working, your test must not assume it is working. You won't catch any bugs
+ * by such tests. What you can do is to generate a huge amount of tests.
+ * Especially if you were are asked to proivde 100% line-coverage x_x. So what
+ * does these tests - which are not finding any bugs now - do?
+ *
+ * They add inertia to every future development. I think it was Terry Pratchet
+ * who wrote someone having same impact as thick syrup has to chronometre.
+ * Excessive amount of unit-tests have this effect to development. If you do
+ * actually find _any_ bug from code in such environment and try fixing it...
+ * ...chances are you also need to fix the test cases. In sunny day you fix one
+ * test. But I've done refactoring which resulted 500+ broken tests (which had
+ * really zero value other than proving to managers that we do do "quality")...
+ *
+ * After this being said - there are situations where UTs can be handy. If you
+ * have algorithms which take some input and should produce output - then you
+ * can implement few, carefully selected simple UT-cases which test this. I've
+ * previously used this for example for netlink and device-tree data parsing
+ * functions. Feed some data examples to functions and verify the output is as
+ * expected. I am not covering all the cases but I will see the logic should be
+ * working.
+ *
+ * Here we also do some minor testing. I don't want to go through all branches
+ * or test more or less obvious things - but I want to see the main logic is
+ * working. And I definitely don't want to add 500+ test cases that break when
+ * some simple fix is done x_x. So - let's only add few, well selected tests
+ * which ensure as much logic is good as possible.
+ */
+
+/*
+ * Test Range 1:
+ * selectors:	2	3	4	5	6
+ * values (5):	10	20	30	40	50
+ *
+ * Test Range 2:
+ * selectors:	7	8	9	10
+ * values (4):	100	150	200	250
+ */
+
+#define RANGE1_MIN 10
+#define RANGE1_MIN_SEL 2
+#define RANGE1_STEP 10
+
+/* 2, 3, 4, 5, 6 */
+static const unsigned int range1_sels[] = { RANGE1_MIN_SEL, RANGE1_MIN_SEL + 1,
+					    RANGE1_MIN_SEL + 2,
+					    RANGE1_MIN_SEL + 3,
+					    RANGE1_MIN_SEL + 4 };
+/* 10, 20, 30, 40, 50 */
+static const unsigned int range1_vals[] = { RANGE1_MIN, RANGE1_MIN +
+					    RANGE1_STEP,
+					    RANGE1_MIN + RANGE1_STEP * 2,
+					    RANGE1_MIN + RANGE1_STEP * 3,
+					    RANGE1_MIN + RANGE1_STEP * 4 };
+
+#define RANGE2_MIN 100
+#define RANGE2_MIN_SEL 7
+#define RANGE2_STEP 50
+
+/*  7, 8, 9, 10 */
+static const unsigned int range2_sels[] = { RANGE2_MIN_SEL, RANGE2_MIN_SEL + 1,
+					    RANGE2_MIN_SEL + 2,
+					    RANGE2_MIN_SEL + 3 };
+/* 100, 150, 200, 250 */
+static const unsigned int range2_vals[] = { RANGE2_MIN, RANGE2_MIN +
+					    RANGE2_STEP,
+					    RANGE2_MIN + RANGE2_STEP * 2,
+					    RANGE2_MIN + RANGE2_STEP * 3 };
+
+#define RANGE1_NUM_VALS (ARRAY_SIZE(range1_vals))
+#define RANGE2_NUM_VALS (ARRAY_SIZE(range2_vals))
+#define RANGE_NUM_VALS (RANGE1_NUM_VALS + RANGE2_NUM_VALS)
+
+#define RANGE1_MAX_SEL (RANGE1_MIN_SEL + RANGE1_NUM_VALS - 1)
+#define RANGE1_MAX_VAL (range1_vals[RANGE1_NUM_VALS - 1])
+
+#define RANGE2_MAX_SEL (RANGE2_MIN_SEL + RANGE2_NUM_VALS - 1)
+#define RANGE2_MAX_VAL (range2_vals[RANGE2_NUM_VALS - 1])
+
+#define SMALLEST_SEL RANGE1_MIN_SEL
+#define SMALLEST_VAL RANGE1_MIN
+
+static struct linear_range testr[] = {
+	{
+		.min = RANGE1_MIN,
+		.min_sel = RANGE1_MIN_SEL,
+		.max_sel = RANGE1_MAX_SEL,
+		.step = RANGE1_STEP,
+	}, {
+		.min = RANGE2_MIN,
+		.min_sel = RANGE2_MIN_SEL,
+		.max_sel = RANGE2_MAX_SEL,
+		.step = RANGE2_STEP
+	},
+};
+
+static void range_test_get_value(struct kunit *test)
+{
+	int ret, i;
+	unsigned int sel, val;
+
+	for (i = 0; i < RANGE1_NUM_VALS; i++) {
+		sel = range1_sels[i];
+		ret = linear_range_get_value_array(&testr[0], 2, sel, &val);
+		KUNIT_EXPECT_EQ(test, 0, ret);
+		KUNIT_EXPECT_EQ(test, val, range1_vals[i]);
+	}
+	for (i = 0; i < RANGE2_NUM_VALS; i++) {
+		sel = range2_sels[i];
+		ret = linear_range_get_value_array(&testr[0], 2, sel, &val);
+		KUNIT_EXPECT_EQ(test, 0, ret);
+		KUNIT_EXPECT_EQ(test, val, range2_vals[i]);
+	}
+	ret = linear_range_get_value_array(&testr[0], 2, sel + 1, &val);
+	KUNIT_EXPECT_NE(test, 0, ret);
+}
+
+static void range_test_get_selector_high(struct kunit *test)
+{
+	int ret, i;
+	unsigned int sel;
+	bool found;
+
+	for (i = 0; i < RANGE1_NUM_VALS; i++) {
+		ret = linear_range_get_selector_high(&testr[0], range1_vals[i],
+						     &sel, &found);
+		KUNIT_EXPECT_EQ(test, 0, ret);
+		KUNIT_EXPECT_EQ(test, sel, range1_sels[i]);
+		KUNIT_EXPECT_TRUE(test, found);
+	}
+
+	ret = linear_range_get_selector_high(&testr[0], RANGE1_MAX_VAL + 1,
+					     &sel, &found);
+	KUNIT_EXPECT_LE(test, ret, 0);
+
+	ret = linear_range_get_selector_high(&testr[0], RANGE1_MIN - 1,
+					     &sel, &found);
+	KUNIT_EXPECT_EQ(test, 0, ret);
+	KUNIT_EXPECT_FALSE(test, found);
+	KUNIT_EXPECT_EQ(test, sel, range1_sels[0]);
+}
+
+static void range_test_get_value_amount(struct kunit *test)
+{
+	int ret;
+
+	ret = linear_range_values_in_range_array(&testr[0], 2);
+	KUNIT_EXPECT_EQ(test, (int)RANGE_NUM_VALS, ret);
+}
+
+static void range_test_get_selector_low(struct kunit *test)
+{
+	int i, ret;
+	unsigned int sel;
+	bool found;
+
+	for (i = 0; i < RANGE1_NUM_VALS; i++) {
+		ret = linear_range_get_selector_low_array(&testr[0], 2,
+							  range1_vals[i], &sel,
+							  &found);
+		KUNIT_EXPECT_EQ(test, 0, ret);
+		KUNIT_EXPECT_EQ(test, sel, range1_sels[i]);
+		KUNIT_EXPECT_TRUE(test, found);
+	}
+	for (i = 0; i < RANGE2_NUM_VALS; i++) {
+		ret = linear_range_get_selector_low_array(&testr[0], 2,
+							  range2_vals[i], &sel,
+							  &found);
+		KUNIT_EXPECT_EQ(test, 0, ret);
+		KUNIT_EXPECT_EQ(test, sel, range2_sels[i]);
+		KUNIT_EXPECT_TRUE(test, found);
+	}
+
+	/*
+	 * Seek value greater than range max => get_selector_*_low should
+	 * return Ok - but set found to false as value is not in range
+	 */
+	ret = linear_range_get_selector_low_array(&testr[0], 2,
+					range2_vals[RANGE2_NUM_VALS - 1] + 1,
+					&sel, &found);
+
+	KUNIT_EXPECT_EQ(test, 0, ret);
+	KUNIT_EXPECT_EQ(test, sel, range2_sels[RANGE2_NUM_VALS - 1]);
+	KUNIT_EXPECT_FALSE(test, found);
+}
+
+static struct kunit_case range_test_cases[] = {
+	KUNIT_CASE(range_test_get_value_amount),
+	KUNIT_CASE(range_test_get_selector_high),
+	KUNIT_CASE(range_test_get_selector_low),
+	KUNIT_CASE(range_test_get_value),
+	{},
+};
+
+static struct kunit_suite range_test_module = {
+	.name = "linear-ranges-test",
+	.test_cases = range_test_cases,
+};
+
+kunit_test_suites(&range_test_module);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/test_lockup.c b/lib/test_lockup.c
index ea09ca335b21..f1a020bcc763 100644
--- a/lib/test_lockup.c
+++ b/lib/test_lockup.c
@@ -103,7 +103,7 @@ MODULE_PARM_DESC(lock_rcu, "grab rcu_read_lock: generate rcu stalls");
 
 static bool lock_mmap_sem;
 module_param(lock_mmap_sem, bool, 0400);
-MODULE_PARM_DESC(lock_mmap_sem, "lock mm->mmap_sem: block procfs interfaces");
+MODULE_PARM_DESC(lock_mmap_sem, "lock mm->mmap_lock: block procfs interfaces");
 
 static unsigned long lock_rwsem_ptr;
 module_param_unsafe(lock_rwsem_ptr, ulong, 0400);
@@ -142,7 +142,7 @@ module_param(reallocate_pages, bool, 0400);
 MODULE_PARM_DESC(reallocate_pages, "free and allocate pages between iterations");
 
 struct file *test_file;
-struct inode *test_inode;
+static struct inode *test_inode;
 static char test_file_path[256];
 module_param_string(file_path, test_file_path, sizeof(test_file_path), 0400);
 MODULE_PARM_DESC(file_path, "file path to test");
@@ -168,7 +168,7 @@ static int master_cpu;
 
 static void test_lock(bool master, bool verbose)
 {
-	u64 uninitialized_var(wait_start);
+	u64 wait_start;
 
 	if (measure_lock_wait)
 		wait_start = local_clock();
@@ -191,11 +191,11 @@ static void test_lock(bool master, bool verbose)
 
 	if (lock_mmap_sem && master) {
 		if (verbose)
-			pr_notice("lock mmap_sem pid=%d\n", main_task->pid);
+			pr_notice("lock mmap_lock pid=%d\n", main_task->pid);
 		if (lock_read)
-			down_read(&main_task->mm->mmap_sem);
+			mmap_read_lock(main_task->mm);
 		else
-			down_write(&main_task->mm->mmap_sem);
+			mmap_write_lock(main_task->mm);
 	}
 
 	if (test_disable_irq)
@@ -276,11 +276,11 @@ static void test_unlock(bool master, bool verbose)
 
 	if (lock_mmap_sem && master) {
 		if (lock_read)
-			up_read(&main_task->mm->mmap_sem);
+			mmap_read_unlock(main_task->mm);
 		else
-			up_write(&main_task->mm->mmap_sem);
+			mmap_write_unlock(main_task->mm);
 		if (verbose)
-			pr_notice("unlock mmap_sem pid=%d\n", main_task->pid);
+			pr_notice("unlock mmap_lock pid=%d\n", main_task->pid);
 	}
 
 	if (lock_rwsem_ptr && master) {
@@ -400,7 +400,7 @@ static void test_lockup(bool master)
 	test_unlock(master, true);
 }
 
-DEFINE_PER_CPU(struct work_struct, test_works);
+static DEFINE_PER_CPU(struct work_struct, test_works);
 
 static void test_work_fn(struct work_struct *work)
 {
@@ -419,8 +419,8 @@ static bool test_kernel_ptr(unsigned long addr, int size)
 	/* should be at least readable kernel address */
 	if (access_ok(ptr, 1) ||
 	    access_ok(ptr + size - 1, 1) ||
-	    probe_kernel_address(ptr, buf) ||
-	    probe_kernel_address(ptr + size - 1, buf)) {
+	    get_kernel_nofault(buf, ptr) ||
+	    get_kernel_nofault(buf, ptr + size - 1)) {
 		pr_err("invalid kernel ptr: %#lx\n", addr);
 		return true;
 	}
@@ -437,7 +437,7 @@ static bool __maybe_unused test_magic(unsigned long addr, int offset,
 	if (!addr)
 		return false;
 
-	if (probe_kernel_address(ptr, magic) || magic != expected) {
+	if (get_kernel_nofault(magic, ptr) || magic != expected) {
 		pr_err("invalid magic at %#lx + %#x = %#x, expected %#x\n",
 		       addr, offset, magic, expected);
 		return true;
@@ -505,15 +505,15 @@ static int __init test_lockup_init(void)
 	}
 
 	if (lock_mmap_sem && !main_task->mm) {
-		pr_err("no mm to lock mmap_sem\n");
+		pr_err("no mm to lock mmap_lock\n");
 		return -EINVAL;
 	}
 
 	if (test_file_path[0]) {
 		test_file = filp_open(test_file_path, O_RDONLY, 0);
 		if (IS_ERR(test_file)) {
-			pr_err("cannot find file_path\n");
-			return -EINVAL;
+			pr_err("failed to open %s: %ld\n", test_file_path, PTR_ERR(test_file));
+			return PTR_ERR(test_file);
 		}
 		test_inode = file_inode(test_file);
 	} else if (test_lock_inode ||
diff --git a/lib/test_objagg.c b/lib/test_objagg.c
index 72c1abfa154d..da137939a410 100644
--- a/lib/test_objagg.c
+++ b/lib/test_objagg.c
@@ -979,10 +979,10 @@ err_check_expect_stats2:
 err_world2_obj_get:
 	for (i--; i >= 0; i--)
 		world_obj_put(&world2, objagg, hints_case->key_ids[i]);
-	objagg_hints_put(hints);
-	objagg_destroy(objagg2);
 	i = hints_case->key_ids_count;
+	objagg_destroy(objagg2);
 err_check_expect_hints_stats:
+	objagg_hints_put(hints);
 err_hints_get:
 err_check_expect_stats:
 err_world_obj_get:
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 6b1622f4d7c2..7ac87f18a10f 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -494,7 +494,7 @@ struct_va_format(void)
 }
 
 static void __init
-struct_rtc_time(void)
+time_and_date(void)
 {
 	/* 1543210543 */
 	const struct rtc_time tm = {
@@ -505,14 +505,21 @@ struct_rtc_time(void)
 		.tm_mon = 10,
 		.tm_year = 118,
 	};
+	/* 2019-01-04T15:32:23 */
+	time64_t t = 1546615943;
 
-	test("(%ptR?)", "%pt", &tm);
+	test("(%pt?)", "%pt", &tm);
 	test("2018-11-26T05:35:43", "%ptR", &tm);
 	test("0118-10-26T05:35:43", "%ptRr", &tm);
 	test("05:35:43|2018-11-26", "%ptRt|%ptRd", &tm, &tm);
 	test("05:35:43|0118-10-26", "%ptRtr|%ptRdr", &tm, &tm);
 	test("05:35:43|2018-11-26", "%ptRttr|%ptRdtr", &tm, &tm);
 	test("05:35:43 tr|2018-11-26 tr", "%ptRt tr|%ptRd tr", &tm, &tm);
+
+	test("2019-01-04T15:32:23", "%ptT", &t);
+	test("0119-00-04T15:32:23", "%ptTr", &t);
+	test("15:32:23|2019-01-04", "%ptTt|%ptTd", &t, &t);
+	test("15:32:23|0119-00-04", "%ptTtr|%ptTdr", &t, &t);
 }
 
 static void __init
@@ -637,7 +644,9 @@ static void __init fwnode_pointer(void)
 	test(second_name, "%pfwP", software_node_fwnode(&softnodes[1]));
 	test(third_name, "%pfwP", software_node_fwnode(&softnodes[2]));
 
-	software_node_unregister_nodes(softnodes);
+	software_node_unregister(&softnodes[2]);
+	software_node_unregister(&softnodes[1]);
+	software_node_unregister(&softnodes[0]);
 }
 
 static void __init
@@ -678,7 +687,7 @@ test_pointer(void)
 	uuid();
 	dentry();
 	struct_va_format();
-	struct_rtc_time();
+	time_and_date();
 	struct_clk();
 	bitmap();
 	netdev_features();
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index c5a6fef7b45d..76c607ee6db5 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -434,7 +434,7 @@ static int __init test_rhltable(unsigned int entries)
 		} else {
 			if (WARN(err != -ENOENT, "removed non-existent element, error %d not %d",
 				 err, -ENOENT))
-			continue;
+				continue;
 		}
 	}
 
diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c
index 566dad3f4196..98bc92a91662 100644
--- a/lib/test_sysctl.c
+++ b/lib/test_sysctl.c
@@ -44,6 +44,8 @@ struct test_sysctl_data {
 	int int_0002;
 	int int_0003[4];
 
+	int boot_int;
+
 	unsigned int uint_0001;
 
 	char string_0001[65];
@@ -61,6 +63,8 @@ static struct test_sysctl_data test_data = {
 	.int_0003[2] = 2,
 	.int_0003[3] = 3,
 
+	.boot_int = 0,
+
 	.uint_0001 = 314,
 
 	.string_0001 = "(none)",
@@ -92,6 +96,15 @@ static struct ctl_table test_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
+		.procname	= "boot_int",
+		.data		= &test_data.boot_int,
+		.maxlen		= sizeof(test_data.boot_int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+	{
 		.procname	= "uint_0001",
 		.data		= &test_data.uint_0001,
 		.maxlen		= sizeof(unsigned int),
@@ -149,7 +162,7 @@ static int __init test_sysctl_init(void)
 	}
 	return 0;
 }
-late_initcall(test_sysctl_init);
+module_init(test_sysctl_init);
 
 static void __exit test_sysctl_exit(void)
 {
diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
index 8bbefcaddfe8..5cf2fe9aab9e 100644
--- a/lib/test_vmalloc.c
+++ b/lib/test_vmalloc.c
@@ -15,6 +15,8 @@
 #include <linux/delay.h>
 #include <linux/rwsem.h>
 #include <linux/mm.h>
+#include <linux/rcupdate.h>
+#include <linux/slab.h>
 
 #define __param(type, name, init, msg)		\
 	static type name = init;				\
@@ -35,14 +37,18 @@ __param(int, test_loop_count, 1000000,
 
 __param(int, run_test_mask, INT_MAX,
 	"Set tests specified in the mask.\n\n"
-		"\t\tid: 1,   name: fix_size_alloc_test\n"
-		"\t\tid: 2,   name: full_fit_alloc_test\n"
-		"\t\tid: 4,   name: long_busy_list_alloc_test\n"
-		"\t\tid: 8,   name: random_size_alloc_test\n"
-		"\t\tid: 16,  name: fix_align_alloc_test\n"
-		"\t\tid: 32,  name: random_size_align_alloc_test\n"
-		"\t\tid: 64,  name: align_shift_alloc_test\n"
-		"\t\tid: 128, name: pcpu_alloc_test\n"
+		"\t\tid: 1,    name: fix_size_alloc_test\n"
+		"\t\tid: 2,    name: full_fit_alloc_test\n"
+		"\t\tid: 4,    name: long_busy_list_alloc_test\n"
+		"\t\tid: 8,    name: random_size_alloc_test\n"
+		"\t\tid: 16,   name: fix_align_alloc_test\n"
+		"\t\tid: 32,   name: random_size_align_alloc_test\n"
+		"\t\tid: 64,   name: align_shift_alloc_test\n"
+		"\t\tid: 128,  name: pcpu_alloc_test\n"
+		"\t\tid: 256,  name: kvfree_rcu_1_arg_vmalloc_test\n"
+		"\t\tid: 512,  name: kvfree_rcu_2_arg_vmalloc_test\n"
+		"\t\tid: 1024, name: kvfree_rcu_1_arg_slab_test\n"
+		"\t\tid: 2048, name: kvfree_rcu_2_arg_slab_test\n"
 		/* Add a new test case description here. */
 );
 
@@ -91,12 +97,8 @@ static int random_size_align_alloc_test(void)
 		 */
 		size = ((rnd % 10) + 1) * PAGE_SIZE;
 
-		ptr = __vmalloc_node_range(size, align,
-		   VMALLOC_START, VMALLOC_END,
-		   GFP_KERNEL | __GFP_ZERO,
-		   PAGE_KERNEL,
-		   0, 0, __builtin_return_address(0));
-
+		ptr = __vmalloc_node(size, align, GFP_KERNEL | __GFP_ZERO, 0,
+				__builtin_return_address(0));
 		if (!ptr)
 			return -1;
 
@@ -118,12 +120,8 @@ static int align_shift_alloc_test(void)
 	for (i = 0; i < BITS_PER_LONG; i++) {
 		align = ((unsigned long) 1) << i;
 
-		ptr = __vmalloc_node_range(PAGE_SIZE, align,
-			VMALLOC_START, VMALLOC_END,
-			GFP_KERNEL | __GFP_ZERO,
-			PAGE_KERNEL,
-			0, 0, __builtin_return_address(0));
-
+		ptr = __vmalloc_node(PAGE_SIZE, align, GFP_KERNEL|__GFP_ZERO, 0,
+				__builtin_return_address(0));
 		if (!ptr)
 			return -1;
 
@@ -139,13 +137,9 @@ static int fix_align_alloc_test(void)
 	int i;
 
 	for (i = 0; i < test_loop_count; i++) {
-		ptr = __vmalloc_node_range(5 * PAGE_SIZE,
-			THREAD_ALIGN << 1,
-			VMALLOC_START, VMALLOC_END,
-			GFP_KERNEL | __GFP_ZERO,
-			PAGE_KERNEL,
-			0, 0, __builtin_return_address(0));
-
+		ptr = __vmalloc_node(5 * PAGE_SIZE, THREAD_ALIGN << 1,
+				GFP_KERNEL | __GFP_ZERO, 0,
+				__builtin_return_address(0));
 		if (!ptr)
 			return -1;
 
@@ -328,6 +322,83 @@ pcpu_alloc_test(void)
 	return rv;
 }
 
+struct test_kvfree_rcu {
+	struct rcu_head rcu;
+	unsigned char array[20];
+};
+
+static int
+kvfree_rcu_1_arg_vmalloc_test(void)
+{
+	struct test_kvfree_rcu *p;
+	int i;
+
+	for (i = 0; i < test_loop_count; i++) {
+		p = vmalloc(1 * PAGE_SIZE);
+		if (!p)
+			return -1;
+
+		p->array[0] = 'a';
+		kvfree_rcu(p);
+	}
+
+	return 0;
+}
+
+static int
+kvfree_rcu_2_arg_vmalloc_test(void)
+{
+	struct test_kvfree_rcu *p;
+	int i;
+
+	for (i = 0; i < test_loop_count; i++) {
+		p = vmalloc(1 * PAGE_SIZE);
+		if (!p)
+			return -1;
+
+		p->array[0] = 'a';
+		kvfree_rcu(p, rcu);
+	}
+
+	return 0;
+}
+
+static int
+kvfree_rcu_1_arg_slab_test(void)
+{
+	struct test_kvfree_rcu *p;
+	int i;
+
+	for (i = 0; i < test_loop_count; i++) {
+		p = kmalloc(sizeof(*p), GFP_KERNEL);
+		if (!p)
+			return -1;
+
+		p->array[0] = 'a';
+		kvfree_rcu(p);
+	}
+
+	return 0;
+}
+
+static int
+kvfree_rcu_2_arg_slab_test(void)
+{
+	struct test_kvfree_rcu *p;
+	int i;
+
+	for (i = 0; i < test_loop_count; i++) {
+		p = kmalloc(sizeof(*p), GFP_KERNEL);
+		if (!p)
+			return -1;
+
+		p->array[0] = 'a';
+		kvfree_rcu(p, rcu);
+	}
+
+	return 0;
+}
+
 struct test_case_desc {
 	const char *test_name;
 	int (*test_func)(void);
@@ -342,6 +413,10 @@ static struct test_case_desc test_case_array[] = {
 	{ "random_size_align_alloc_test", random_size_align_alloc_test },
 	{ "align_shift_alloc_test", align_shift_alloc_test },
 	{ "pcpu_alloc_test", pcpu_alloc_test },
+	{ "kvfree_rcu_1_arg_vmalloc_test", kvfree_rcu_1_arg_vmalloc_test },
+	{ "kvfree_rcu_2_arg_vmalloc_test", kvfree_rcu_2_arg_vmalloc_test },
+	{ "kvfree_rcu_1_arg_slab_test", kvfree_rcu_1_arg_slab_test },
+	{ "kvfree_rcu_2_arg_slab_test", kvfree_rcu_2_arg_slab_test },
 	/* Add a new test case here. */
 };
 
diff --git a/lib/ts_bm.c b/lib/ts_bm.c
index 277cb4417ac2..4cf250031f0f 100644
--- a/lib/ts_bm.c
+++ b/lib/ts_bm.c
@@ -11,7 +11,7 @@
  *   [1] A Fast String Searching Algorithm, R.S. Boyer and Moore.
  *       Communications of the Association for Computing Machinery, 
  *       20(10), 1977, pp. 762-772.
- *       http://www.cs.utexas.edu/users/moore/publications/fstrpos.pdf
+ *       https://www.cs.utexas.edu/users/moore/publications/fstrpos.pdf
  *
  *   [2] Handbook of Exact String Matching Algorithms, Thierry Lecroq, 2004
  *       http://www-igm.univ-mlv.fr/~lecroq/string/string.pdf
diff --git a/lib/ubsan.c b/lib/ubsan.c
index f8c0ccf35f29..cb9af3f6b77e 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -189,7 +189,7 @@ static void handle_overflow(struct overflow_data *data, void *lhs,
 	ubsan_epilogue();
 }
 
-void __ubsan_handle_add_overflow(struct overflow_data *data,
+void __ubsan_handle_add_overflow(void *data,
 				void *lhs, void *rhs)
 {
 
@@ -197,23 +197,23 @@ void __ubsan_handle_add_overflow(struct overflow_data *data,
 }
 EXPORT_SYMBOL(__ubsan_handle_add_overflow);
 
-void __ubsan_handle_sub_overflow(struct overflow_data *data,
+void __ubsan_handle_sub_overflow(void *data,
 				void *lhs, void *rhs)
 {
 	handle_overflow(data, lhs, rhs, '-');
 }
 EXPORT_SYMBOL(__ubsan_handle_sub_overflow);
 
-void __ubsan_handle_mul_overflow(struct overflow_data *data,
+void __ubsan_handle_mul_overflow(void *data,
 				void *lhs, void *rhs)
 {
 	handle_overflow(data, lhs, rhs, '*');
 }
 EXPORT_SYMBOL(__ubsan_handle_mul_overflow);
 
-void __ubsan_handle_negate_overflow(struct overflow_data *data,
-				void *old_val)
+void __ubsan_handle_negate_overflow(void *_data, void *old_val)
 {
+	struct overflow_data *data = _data;
 	char old_val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
@@ -231,9 +231,9 @@ void __ubsan_handle_negate_overflow(struct overflow_data *data,
 EXPORT_SYMBOL(__ubsan_handle_negate_overflow);
 
 
-void __ubsan_handle_divrem_overflow(struct overflow_data *data,
-				void *lhs, void *rhs)
+void __ubsan_handle_divrem_overflow(void *_data, void *lhs, void *rhs)
 {
+	struct overflow_data *data = _data;
 	char rhs_val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
@@ -326,10 +326,9 @@ void __ubsan_handle_type_mismatch(struct type_mismatch_data *data,
 }
 EXPORT_SYMBOL(__ubsan_handle_type_mismatch);
 
-void __ubsan_handle_type_mismatch_v1(struct type_mismatch_data_v1 *data,
-				void *ptr)
+void __ubsan_handle_type_mismatch_v1(void *_data, void *ptr)
 {
-
+	struct type_mismatch_data_v1 *data = _data;
 	struct type_mismatch_data_common common_data = {
 		.location = &data->location,
 		.type = data->type,
@@ -341,8 +340,9 @@ void __ubsan_handle_type_mismatch_v1(struct type_mismatch_data_v1 *data,
 }
 EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1);
 
-void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data, void *index)
+void __ubsan_handle_out_of_bounds(void *_data, void *index)
 {
+	struct out_of_bounds_data *data = _data;
 	char index_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
@@ -357,9 +357,9 @@ void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data, void *index)
 }
 EXPORT_SYMBOL(__ubsan_handle_out_of_bounds);
 
-void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
-					void *lhs, void *rhs)
+void __ubsan_handle_shift_out_of_bounds(void *_data, void *lhs, void *rhs)
 {
+	struct shift_out_of_bounds_data *data = _data;
 	struct type_descriptor *rhs_type = data->rhs_type;
 	struct type_descriptor *lhs_type = data->lhs_type;
 	char rhs_str[VALUE_LENGTH];
@@ -399,8 +399,9 @@ out:
 EXPORT_SYMBOL(__ubsan_handle_shift_out_of_bounds);
 
 
-void __ubsan_handle_builtin_unreachable(struct unreachable_data *data)
+void __ubsan_handle_builtin_unreachable(void *_data)
 {
+	struct unreachable_data *data = _data;
 	ubsan_prologue(&data->location, "unreachable");
 	pr_err("calling __builtin_unreachable()\n");
 	ubsan_epilogue();
@@ -408,9 +409,9 @@ void __ubsan_handle_builtin_unreachable(struct unreachable_data *data)
 }
 EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable);
 
-void __ubsan_handle_load_invalid_value(struct invalid_value_data *data,
-				void *val)
+void __ubsan_handle_load_invalid_value(void *_data, void *val)
 {
+	struct invalid_value_data *data = _data;
 	char val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
diff --git a/lib/usercopy.c b/lib/usercopy.c
index cbb4d9ec00f2..b26509f112f9 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/uaccess.h>
 #include <linux/bitops.h>
+#include <linux/instrumented.h>
+#include <linux/uaccess.h>
 
 /* out-of-line parts */
 
@@ -10,7 +11,7 @@ unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n
 	unsigned long res = n;
 	might_fault();
 	if (likely(access_ok(from, n))) {
-		kasan_check_write(to, n);
+		instrument_copy_from_user(to, from, n);
 		res = raw_copy_from_user(to, from, n);
 	}
 	if (unlikely(res))
@@ -25,7 +26,7 @@ unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
 	if (likely(access_ok(to, n))) {
-		kasan_check_read(from, n);
+		instrument_copy_to_user(to, from, n);
 		n = raw_copy_to_user(to, from, n);
 	}
 	return n;
@@ -58,7 +59,7 @@ int check_zeroed_user(const void __user *from, size_t size)
 	from -= align;
 	size += align;
 
-	if (!user_access_begin(from, size))
+	if (!user_read_access_begin(from, size))
 		return -EFAULT;
 
 	unsafe_get_user(val, (unsigned long __user *) from, err_fault);
@@ -79,10 +80,10 @@ int check_zeroed_user(const void __user *from, size_t size)
 		val &= aligned_byte_mask(size);
 
 done:
-	user_access_end();
+	user_read_access_end();
 	return (val == 0);
 err_fault:
-	user_access_end();
+	user_read_access_end();
 	return -EFAULT;
 }
 EXPORT_SYMBOL(check_zeroed_user);
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index a2909af4b924..2919f1698140 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -38,6 +38,13 @@ static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
 }
 #endif
 
+#ifndef vdso_cycles_ok
+static inline bool vdso_cycles_ok(u64 cycles)
+{
+	return true;
+}
+#endif
+
 #ifdef CONFIG_TIME_NS
 static int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
 			  struct __kernel_timespec *ts)
@@ -61,7 +68,9 @@ static int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
 		if (unlikely(!vdso_clocksource_ok(vd)))
 			return -1;
 
-		cycles = __arch_get_hw_counter(vd->clock_mode);
+		cycles = __arch_get_hw_counter(vd->clock_mode, vd);
+		if (unlikely(!vdso_cycles_ok(cycles)))
+			return -1;
 		ns = vdso_ts->nsec;
 		last = vd->cycle_last;
 		ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult);
@@ -129,7 +138,9 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk,
 		if (unlikely(!vdso_clocksource_ok(vd)))
 			return -1;
 
-		cycles = __arch_get_hw_counter(vd->clock_mode);
+		cycles = __arch_get_hw_counter(vd->clock_mode, vd);
+		if (unlikely(!vdso_cycles_ok(cycles)))
+			return -1;
 		ns = vdso_ts->nsec;
 		last = vd->cycle_last;
 		ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult);
@@ -210,7 +221,7 @@ static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk,
 	return 0;
 }
 
-static __maybe_unused int
+static __always_inline int
 __cvdso_clock_gettime_common(const struct vdso_data *vd, clockid_t clock,
 			     struct __kernel_timespec *ts)
 {
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 7c47ad52ce2f..afb9521ddf91 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -34,6 +34,7 @@
 #include <linux/dcache.h>
 #include <linux/cred.h>
 #include <linux/rtc.h>
+#include <linux/time.h>
 #include <linux/uuid.h>
 #include <linux/of.h>
 #include <net/addrconf.h>
@@ -58,7 +59,7 @@
  * @endp: A pointer to the end of the parsed string will be placed here
  * @base: The number base to use
  *
- * This function is obsolete. Please use kstrtoull instead.
+ * This function has caveats. Please use kstrtoull instead.
  */
 unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base)
 {
@@ -83,7 +84,7 @@ EXPORT_SYMBOL(simple_strtoull);
  * @endp: A pointer to the end of the parsed string will be placed here
  * @base: The number base to use
  *
- * This function is obsolete. Please use kstrtoul instead.
+ * This function has caveats. Please use kstrtoul instead.
  */
 unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base)
 {
@@ -97,7 +98,7 @@ EXPORT_SYMBOL(simple_strtoul);
  * @endp: A pointer to the end of the parsed string will be placed here
  * @base: The number base to use
  *
- * This function is obsolete. Please use kstrtol instead.
+ * This function has caveats. Please use kstrtol instead.
  */
 long simple_strtol(const char *cp, char **endp, unsigned int base)
 {
@@ -114,7 +115,7 @@ EXPORT_SYMBOL(simple_strtol);
  * @endp: A pointer to the end of the parsed string will be placed here
  * @base: The number base to use
  *
- * This function is obsolete. Please use kstrtoll instead.
+ * This function has caveats. Please use kstrtoll instead.
  */
 long long simple_strtoll(const char *cp, char **endp, unsigned int base)
 {
@@ -380,6 +381,9 @@ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width)
 #define SMALL	32		/* use lowercase in hex (must be 32 == 0x20) */
 #define SPECIAL	64		/* prefix hex with "0x", octal with "0" */
 
+static_assert(ZEROPAD == ('0' - ' '));
+static_assert(SMALL == ' ');
+
 enum format_type {
 	FORMAT_TYPE_NONE, /* Just a string part */
 	FORMAT_TYPE_WIDTH,
@@ -506,7 +510,7 @@ char *number(char *buf, char *end, unsigned long long num,
 	/* zero or space padding */
 	if (!(spec.flags & LEFT)) {
 		char c = ' ' + (spec.flags & ZEROPAD);
-		BUILD_BUG_ON(' ' + ZEROPAD != '0');
+
 		while (--field_width >= 0) {
 			if (buf < end)
 				*buf = c;
@@ -1677,7 +1681,8 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
 
 	switch (*(++fmt)) {
 	case 'L':
-		uc = true;		/* fall-through */
+		uc = true;
+		/* fall through */
 	case 'l':
 		index = guid_index;
 		break;
@@ -1827,14 +1832,39 @@ char *rtc_str(char *buf, char *end, const struct rtc_time *tm,
 }
 
 static noinline_for_stack
+char *time64_str(char *buf, char *end, const time64_t time,
+		 struct printf_spec spec, const char *fmt)
+{
+	struct rtc_time rtc_time;
+	struct tm tm;
+
+	time64_to_tm(time, 0, &tm);
+
+	rtc_time.tm_sec = tm.tm_sec;
+	rtc_time.tm_min = tm.tm_min;
+	rtc_time.tm_hour = tm.tm_hour;
+	rtc_time.tm_mday = tm.tm_mday;
+	rtc_time.tm_mon = tm.tm_mon;
+	rtc_time.tm_year = tm.tm_year;
+	rtc_time.tm_wday = tm.tm_wday;
+	rtc_time.tm_yday = tm.tm_yday;
+
+	rtc_time.tm_isdst = 0;
+
+	return rtc_str(buf, end, &rtc_time, spec, fmt);
+}
+
+static noinline_for_stack
 char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec,
 		    const char *fmt)
 {
 	switch (fmt[1]) {
 	case 'R':
 		return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt);
+	case 'T':
+		return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt);
 	default:
-		return error_string(buf, end, "(%ptR?)", spec);
+		return error_string(buf, end, "(%pt?)", spec);
 	}
 }
 
@@ -1908,7 +1938,7 @@ char *flags_string(char *buf, char *end, void *flags_ptr,
 		names = vmaflag_names;
 		break;
 	case 'g':
-		flags = *(gfp_t *)flags_ptr;
+		flags = (__force unsigned long)(*(gfp_t *)flags_ptr);
 		names = gfpflag_names;
 		break;
 	default:
@@ -1950,12 +1980,6 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 	char *buf_start = buf;
 	struct property *prop;
 	bool has_mult, pass;
-	static const struct printf_spec num_spec = {
-		.flags = SMALL,
-		.field_width = -1,
-		.precision = -1,
-		.base = 10,
-	};
 
 	struct printf_spec str_spec = spec;
 	str_spec.field_width = -1;
@@ -1995,7 +2019,7 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 			str_spec.precision = precision;
 			break;
 		case 'p':	/* phandle */
-			buf = number(buf, end, (unsigned int)dn->phandle, num_spec);
+			buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec);
 			break;
 		case 'P':	/* path-spec */
 			p = fwnode_get_name(of_fwnode_handle(dn));
@@ -2108,7 +2132,7 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode,
  *       [4] or [6] and is able to print port [p], flowinfo [f], scope [s]
  * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order
  * - 'I[6S]c' for IPv6 addresses printed as specified by
- *       http://tools.ietf.org/html/rfc5952
+ *       https://tools.ietf.org/html/rfc5952
  * - 'E[achnops]' For an escaped buffer, where rules are defined by combination
  *                of the following flags (see string_escape_mem() for the
  *                details):
@@ -2150,8 +2174,9 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode,
  * - 'd[234]' For a dentry name (optionally 2-4 last components)
  * - 'D[234]' Same as 'd' but for a struct file
  * - 'g' For block_device name (gendisk + partition number)
- * - 't[R][dt][r]' For time and date as represented:
+ * - 't[RT][dt][r]' For time and date as represented by:
  *      R    struct rtc_time
+ *      T    time64_t
  * - 'C' For a clock, it prints the name (Common Clock Framework) or address
  *       (legacy clock framework) of the clock
  * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address
@@ -2194,7 +2219,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 	case 'S':
 	case 's':
 		ptr = dereference_symbol_descriptor(ptr);
-		/* Fallthrough */
+		/* fall through */
 	case 'B':
 		return symbol_string(buf, end, ptr, spec, fmt);
 	case 'R':
@@ -2443,7 +2468,7 @@ qualifier:
 		 * utility, treat it as any other invalid or
 		 * unsupported format specifier.
 		 */
-		/* Fall-through */
+		/* fall through */
 
 	default:
 		WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt);
diff --git a/lib/xxhash.c b/lib/xxhash.c
index aa61e2a3802f..d5bb9ff10607 100644
--- a/lib/xxhash.c
+++ b/lib/xxhash.c
@@ -34,7 +34,7 @@
  * ("BSD").
  *
  * You can contact the author at:
- * - xxHash homepage: http://cyan4973.github.io/xxHash/
+ * - xxHash homepage: https://cyan4973.github.io/xxHash/
  * - xxHash source repository: https://github.com/Cyan4973/xxHash
  */
 
diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig
index 22528743d4ce..5cb50245a878 100644
--- a/lib/xz/Kconfig
+++ b/lib/xz/Kconfig
@@ -5,7 +5,7 @@ config XZ_DEC
 	help
 	  LZMA2 compression algorithm and BCJ filters are supported using
 	  the .xz file format as the container. For integrity checking,
-	  CRC32 is supported. See Documentation/xz.txt for more information.
+	  CRC32 is supported. See Documentation/staging/xz.rst for more information.
 
 if XZ_DEC
 
diff --git a/lib/xz/xz_crc32.c b/lib/xz/xz_crc32.c
index 912aae5fa09e..88a2c35e1b59 100644
--- a/lib/xz/xz_crc32.c
+++ b/lib/xz/xz_crc32.c
@@ -2,7 +2,7 @@
  * CRC32 using the polynomial from IEEE-802.3
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
- *          Igor Pavlov <http://7-zip.org/>
+ *          Igor Pavlov <https://7-zip.org/>
  *
  * This file has been put into the public domain.
  * You can do whatever you want with this file.
diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c
index a768e6d28bbb..72ddac6ef2ec 100644
--- a/lib/xz/xz_dec_bcj.c
+++ b/lib/xz/xz_dec_bcj.c
@@ -2,7 +2,7 @@
  * Branch/Call/Jump (BCJ) filter decoders
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
- *          Igor Pavlov <http://7-zip.org/>
+ *          Igor Pavlov <https://7-zip.org/>
  *
  * This file has been put into the public domain.
  * You can do whatever you want with this file.
diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c
index 156f26fdc4c9..65a1aad8c223 100644
--- a/lib/xz/xz_dec_lzma2.c
+++ b/lib/xz/xz_dec_lzma2.c
@@ -2,7 +2,7 @@
  * LZMA2 decoder
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
- *          Igor Pavlov <http://7-zip.org/>
+ *          Igor Pavlov <https://7-zip.org/>
  *
  * This file has been put into the public domain.
  * You can do whatever you want with this file.
@@ -1043,7 +1043,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s,
 
 			s->lzma2.sequence = SEQ_LZMA_PREPARE;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_LZMA_PREPARE:
 			if (s->lzma2.compressed < RC_INIT_BYTES)
@@ -1055,7 +1055,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s,
 			s->lzma2.compressed -= RC_INIT_BYTES;
 			s->lzma2.sequence = SEQ_LZMA_RUN;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_LZMA_RUN:
 			/*
diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c
index bd1d182419d7..32ab2a08b7cb 100644
--- a/lib/xz/xz_dec_stream.c
+++ b/lib/xz/xz_dec_stream.c
@@ -583,7 +583,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 			if (ret != XZ_OK)
 				return ret;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_BLOCK_START:
 			/* We need one byte of input to continue. */
@@ -608,7 +608,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 			s->temp.pos = 0;
 			s->sequence = SEQ_BLOCK_HEADER;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_BLOCK_HEADER:
 			if (!fill_temp(s, b))
@@ -620,7 +620,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 
 			s->sequence = SEQ_BLOCK_UNCOMPRESS;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_BLOCK_UNCOMPRESS:
 			ret = dec_block(s, b);
@@ -629,7 +629,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 
 			s->sequence = SEQ_BLOCK_PADDING;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_BLOCK_PADDING:
 			/*
@@ -651,7 +651,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 
 			s->sequence = SEQ_BLOCK_CHECK;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_BLOCK_CHECK:
 			if (s->check_type == XZ_CHECK_CRC32) {
@@ -675,7 +675,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 
 			s->sequence = SEQ_INDEX_PADDING;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_INDEX_PADDING:
 			while ((s->index.size + (b->in_pos - s->in_start))
@@ -699,7 +699,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 
 			s->sequence = SEQ_INDEX_CRC32;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_INDEX_CRC32:
 			ret = crc32_validate(s, b);
@@ -709,7 +709,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
 			s->temp.size = STREAM_HEADER_SIZE;
 			s->sequence = SEQ_STREAM_FOOTER;
 
-		/* Fall through */
+			/* fall through */
 
 		case SEQ_STREAM_FOOTER:
 			if (!fill_temp(s, b))
diff --git a/lib/xz/xz_lzma2.h b/lib/xz/xz_lzma2.h
index 071d67bee9f5..92d852d4f87a 100644
--- a/lib/xz/xz_lzma2.h
+++ b/lib/xz/xz_lzma2.h
@@ -2,7 +2,7 @@
  * LZMA2 definitions
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
- *          Igor Pavlov <http://7-zip.org/>
+ *          Igor Pavlov <https://7-zip.org/>
  *
  * This file has been put into the public domain.
  * You can do whatever you want with this file.
diff --git a/lib/xz/xz_stream.h b/lib/xz/xz_stream.h
index 66cb5a7055ec..430bb3a0d195 100644
--- a/lib/xz/xz_stream.h
+++ b/lib/xz/xz_stream.h
@@ -19,7 +19,7 @@
 
 /*
  * See the .xz file format specification at
- * http://tukaani.org/xz/xz-file-format.txt
+ * https://tukaani.org/xz/xz-file-format.txt
  * to understand the container format.
  */
 
diff --git a/lib/zlib_inflate/inffast.c b/lib/zlib_inflate/inffast.c
index 2c13ecc5bb2c..ed1f3df27260 100644
--- a/lib/zlib_inflate/inffast.c
+++ b/lib/zlib_inflate/inffast.c
@@ -10,17 +10,6 @@
 
 #ifndef ASMINF
 
-/* Allow machine dependent optimization for post-increment or pre-increment.
-   Based on testing to date,
-   Pre-increment preferred for:
-   - PowerPC G3 (Adler)
-   - MIPS R5000 (Randers-Pehrson)
-   Post-increment preferred for:
-   - none
-   No measurable difference:
-   - Pentium III (Anderson)
-   - M68060 (Nikl)
- */
 union uu {
 	unsigned short us;
 	unsigned char b[2];
@@ -38,16 +27,6 @@ get_unaligned16(const unsigned short *p)
 	return mm.us;
 }
 
-#ifdef POSTINC
-#  define OFF 0
-#  define PUP(a) *(a)++
-#  define UP_UNALIGNED(a) get_unaligned16((a)++)
-#else
-#  define OFF 1
-#  define PUP(a) *++(a)
-#  define UP_UNALIGNED(a) get_unaligned16(++(a))
-#endif
-
 /*
    Decode literal, length, and distance codes and write out the resulting
    literal and match bytes until either not enough input or output is
@@ -115,9 +94,9 @@ void inflate_fast(z_streamp strm, unsigned start)
 
     /* copy state to local variables */
     state = (struct inflate_state *)strm->state;
-    in = strm->next_in - OFF;
+    in = strm->next_in;
     last = in + (strm->avail_in - 5);
-    out = strm->next_out - OFF;
+    out = strm->next_out;
     beg = out - (start - strm->avail_out);
     end = out + (strm->avail_out - 257);
 #ifdef INFLATE_STRICT
@@ -138,9 +117,9 @@ void inflate_fast(z_streamp strm, unsigned start)
        input data or output space */
     do {
         if (bits < 15) {
-            hold += (unsigned long)(PUP(in)) << bits;
+            hold += (unsigned long)(*in++) << bits;
             bits += 8;
-            hold += (unsigned long)(PUP(in)) << bits;
+            hold += (unsigned long)(*in++) << bits;
             bits += 8;
         }
         this = lcode[hold & lmask];
@@ -150,14 +129,14 @@ void inflate_fast(z_streamp strm, unsigned start)
         bits -= op;
         op = (unsigned)(this.op);
         if (op == 0) {                          /* literal */
-            PUP(out) = (unsigned char)(this.val);
+            *out++ = (unsigned char)(this.val);
         }
         else if (op & 16) {                     /* length base */
             len = (unsigned)(this.val);
             op &= 15;                           /* number of extra bits */
             if (op) {
                 if (bits < op) {
-                    hold += (unsigned long)(PUP(in)) << bits;
+                    hold += (unsigned long)(*in++) << bits;
                     bits += 8;
                 }
                 len += (unsigned)hold & ((1U << op) - 1);
@@ -165,9 +144,9 @@ void inflate_fast(z_streamp strm, unsigned start)
                 bits -= op;
             }
             if (bits < 15) {
-                hold += (unsigned long)(PUP(in)) << bits;
+                hold += (unsigned long)(*in++) << bits;
                 bits += 8;
-                hold += (unsigned long)(PUP(in)) << bits;
+                hold += (unsigned long)(*in++) << bits;
                 bits += 8;
             }
             this = dcode[hold & dmask];
@@ -180,10 +159,10 @@ void inflate_fast(z_streamp strm, unsigned start)
                 dist = (unsigned)(this.val);
                 op &= 15;                       /* number of extra bits */
                 if (bits < op) {
-                    hold += (unsigned long)(PUP(in)) << bits;
+                    hold += (unsigned long)(*in++) << bits;
                     bits += 8;
                     if (bits < op) {
-                        hold += (unsigned long)(PUP(in)) << bits;
+                        hold += (unsigned long)(*in++) << bits;
                         bits += 8;
                     }
                 }
@@ -205,13 +184,13 @@ void inflate_fast(z_streamp strm, unsigned start)
                         state->mode = BAD;
                         break;
                     }
-                    from = window - OFF;
+                    from = window;
                     if (write == 0) {           /* very common case */
                         from += wsize - op;
                         if (op < len) {         /* some from window */
                             len -= op;
                             do {
-                                PUP(out) = PUP(from);
+                                *out++ = *from++;
                             } while (--op);
                             from = out - dist;  /* rest from output */
                         }
@@ -222,14 +201,14 @@ void inflate_fast(z_streamp strm, unsigned start)
                         if (op < len) {         /* some from end of window */
                             len -= op;
                             do {
-                                PUP(out) = PUP(from);
+                                *out++ = *from++;
                             } while (--op);
-                            from = window - OFF;
+                            from = window;
                             if (write < len) {  /* some from start of window */
                                 op = write;
                                 len -= op;
                                 do {
-                                    PUP(out) = PUP(from);
+                                    *out++ = *from++;
                                 } while (--op);
                                 from = out - dist;      /* rest from output */
                             }
@@ -240,21 +219,21 @@ void inflate_fast(z_streamp strm, unsigned start)
                         if (op < len) {         /* some from window */
                             len -= op;
                             do {
-                                PUP(out) = PUP(from);
+                                *out++ = *from++;
                             } while (--op);
                             from = out - dist;  /* rest from output */
                         }
                     }
                     while (len > 2) {
-                        PUP(out) = PUP(from);
-                        PUP(out) = PUP(from);
-                        PUP(out) = PUP(from);
+                        *out++ = *from++;
+                        *out++ = *from++;
+                        *out++ = *from++;
                         len -= 3;
                     }
                     if (len) {
-                        PUP(out) = PUP(from);
+                        *out++ = *from++;
                         if (len > 1)
-                            PUP(out) = PUP(from);
+                            *out++ = *from++;
                     }
                 }
                 else {
@@ -264,29 +243,29 @@ void inflate_fast(z_streamp strm, unsigned start)
                     from = out - dist;          /* copy direct from output */
 		    /* minimum length is three */
 		    /* Align out addr */
-		    if (!((long)(out - 1 + OFF) & 1)) {
-			PUP(out) = PUP(from);
+		    if (!((long)(out - 1) & 1)) {
+			*out++ = *from++;
 			len--;
 		    }
-		    sout = (unsigned short *)(out - OFF);
+		    sout = (unsigned short *)(out);
 		    if (dist > 2) {
 			unsigned short *sfrom;
 
-			sfrom = (unsigned short *)(from - OFF);
+			sfrom = (unsigned short *)(from);
 			loops = len >> 1;
 			do
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-			    PUP(sout) = PUP(sfrom);
+			    *sout++ = *sfrom++;
 #else
-			    PUP(sout) = UP_UNALIGNED(sfrom);
+			    *sout++ = get_unaligned16(sfrom++);
 #endif
 			while (--loops);
-			out = (unsigned char *)sout + OFF;
-			from = (unsigned char *)sfrom + OFF;
+			out = (unsigned char *)sout;
+			from = (unsigned char *)sfrom;
 		    } else { /* dist == 1 or dist == 2 */
 			unsigned short pat16;
 
-			pat16 = *(sout-1+OFF);
+			pat16 = *(sout-1);
 			if (dist == 1) {
 				union uu mm;
 				/* copy one char pattern to both bytes */
@@ -296,12 +275,12 @@ void inflate_fast(z_streamp strm, unsigned start)
 			}
 			loops = len >> 1;
 			do
-			    PUP(sout) = pat16;
+			    *sout++ = pat16;
 			while (--loops);
-			out = (unsigned char *)sout + OFF;
+			out = (unsigned char *)sout;
 		    }
 		    if (len & 1)
-			PUP(out) = PUP(from);
+			*out++ = *from++;
                 }
             }
             else if ((op & 64) == 0) {          /* 2nd level distance code */
@@ -336,8 +315,8 @@ void inflate_fast(z_streamp strm, unsigned start)
     hold &= (1U << bits) - 1;
 
     /* update state and return */
-    strm->next_in = in + OFF;
-    strm->next_out = out + OFF;
+    strm->next_in = in;
+    strm->next_out = out;
     strm->avail_in = (unsigned)(in < last ? 5 + (last - in) : 5 - (in - last));
     strm->avail_out = (unsigned)(out < end ?
                                  257 + (end - out) : 257 - (out - end));
diff --git a/lib/zstd/decompress.c b/lib/zstd/decompress.c
index 269ee9a796c1..db6761ea4deb 100644
--- a/lib/zstd/decompress.c
+++ b/lib/zstd/decompress.c
@@ -442,7 +442,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx *dctx, const void *src, size_t srcSize
 		case set_repeat:
 			if (dctx->litEntropy == 0)
 				return ERROR(dictionary_corrupted);
-		/* fall-through */
+			/* fall through */
 		case set_compressed:
 			if (srcSize < 5)
 				return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3 */
@@ -2309,7 +2309,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 		switch (zds->stage) {
 		case zdss_init:
 			ZSTD_resetDStream(zds); /* transparent reset on starting decoding a new frame */
-						/* fall-through */
+			/* fall through */
 
 		case zdss_loadHeader: {
 			size_t const hSize = ZSTD_getFrameParams(&zds->fParams, zds->headerBuffer, zds->lhSize);
@@ -2376,7 +2376,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 			}
 			zds->stage = zdss_read;
 		}
-		/* fall through */
+			/* fall through */
 
 		case zdss_read: {
 			size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
@@ -2405,7 +2405,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 			zds->stage = zdss_load;
 			/* pass-through */
 		}
-		/* fall through */
+			/* fall through */
 
 		case zdss_load: {
 			size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
@@ -2438,7 +2438,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 				/* pass-through */
 			}
 		}
-		/* fall through */
+			/* fall through */
 
 		case zdss_flush: {
 			size_t const toFlushSize = zds->outEnd - zds->outStart;
diff --git a/lib/zstd/fse_decompress.c b/lib/zstd/fse_decompress.c
index a84300e5a013..0b353530fb3f 100644
--- a/lib/zstd/fse_decompress.c
+++ b/lib/zstd/fse_decompress.c
@@ -47,6 +47,7 @@
 ****************************************************************/
 #include "bitstream.h"
 #include "fse.h"
+#include "zstd_internal.h"
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/string.h> /* memcpy, memset */
@@ -60,14 +61,6 @@
 		enum { FSE_static_assert = 1 / (int)(!!(c)) }; \
 	} /* use only *after* variable declarations */
 
-/* check and forward error code */
-#define CHECK_F(f)                  \
-	{                           \
-		size_t const e = f; \
-		if (FSE_isError(e)) \
-			return e;   \
-	}
-
 /* **************************************************************
 *  Templates
 ****************************************************************/
diff --git a/lib/zstd/zstd_internal.h b/lib/zstd/zstd_internal.h
index 1a79fab9e13a..dac753397f86 100644
--- a/lib/zstd/zstd_internal.h
+++ b/lib/zstd/zstd_internal.h
@@ -127,7 +127,14 @@ static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG;
 *  Shared functions to include for inlining
 *********************************************/
 ZSTD_STATIC void ZSTD_copy8(void *dst, const void *src) {
-	memcpy(dst, src, 8);
+	/*
+	 * 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) */
@@ -137,13 +144,16 @@ 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;
-	/* Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388.
+#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;