Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "181 patches.

  Subsystems affected by this patch series: kbuild, scripts, ntfs,
  ocfs2, vfs, mm (slab, slub, kmemleak, dax, debug, pagecache, fadvise,
  gup, swap, memremap, memcg, selftests, pagemap, mincore, hmm, dma,
  memory-failure, vmallo and migration)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (181 commits)
  mm/migrate: remove obsolete comment about device public
  mm/migrate: remove cpages-- in migrate_vma_finalize()
  mm, oom_adj: don't loop through tasks in __set_oom_adj when not necessary
  memblock: use separate iterators for memory and reserved regions
  memblock: implement for_each_reserved_mem_region() using __next_mem_region()
  memblock: remove unused memblock_mem_size()
  x86/setup: simplify reserve_crashkernel()
  x86/setup: simplify initrd relocation and reservation
  arch, drivers: replace for_each_membock() with for_each_mem_range()
  arch, mm: replace for_each_memblock() with for_each_mem_pfn_range()
  memblock: reduce number of parameters in for_each_mem_range()
  memblock: make memblock_debug and related functionality private
  memblock: make for_each_memblock_type() iterator private
  mircoblaze: drop unneeded NUMA and sparsemem initializations
  riscv: drop unneeded node initialization
  h8300, nds32, openrisc: simplify detection of memory extents
  arm64: numa: simplify dummy_numa_init()
  arm, xtensa: simplify initialization of high memory pages
  dma-contiguous: simplify cma_early_percent_memory()
  KVM: PPC: Book3S HV: simplify kvm_cma_reserve()
  ...

.clang-format

@@ -203,11 +203,13 @@ ForEachMacros:
   - 'for_each_matching_node'
   - 'for_each_matching_node_and_match'
   - 'for_each_member'
-  - 'for_each_memblock'
+  - 'for_each_mem_region'
   - 'for_each_memblock_type'
   - 'for_each_memcg_cache_index'
   - 'for_each_mem_pfn_range'
+  - '__for_each_mem_range'
   - 'for_each_mem_range'
+  - '__for_each_mem_range_rev'
   - 'for_each_mem_range_rev'
   - 'for_each_migratetype_order'
   - 'for_each_msi_entry'
@@ -271,6 +273,7 @@ ForEachMacros:
   - 'for_each_registered_fb'
   - 'for_each_requested_gpio'
   - 'for_each_requested_gpio_in_range'
+  - 'for_each_reserved_mem_range'
   - 'for_each_reserved_mem_region'
   - 'for_each_rtd_codec_dais'
   - 'for_each_rtd_codec_dais_rollback'

Documentation/admin-guide/cgroup-v2.rst

@@ -1259,6 +1259,10 @@ PAGE_SIZE multiple when read back.
 	can show up in the middle. Don't rely on items remaining in a
 	fixed position; use the keys to look up specific values!
 
+	If the entry has no per-node counter(or not show in the
+	mempry.numa_stat). We use 'npn'(non-per-node) as the tag
+	to indicate that it will not show in the mempry.numa_stat.
+
 	  anon
 		Amount of memory used in anonymous mappings such as
 		brk(), sbrk(), and mmap(MAP_ANONYMOUS)
@@ -1270,15 +1274,11 @@ PAGE_SIZE multiple when read back.
 	  kernel_stack
 		Amount of memory allocated to kernel stacks.
 
-	  slab
-		Amount of memory used for storing in-kernel data
-		structures.
-
-	  percpu
+	  percpu(npn)
 		Amount of memory used for storing per-cpu kernel
 		data structures.
 
-	  sock
+	  sock(npn)
 		Amount of memory used in network transmission buffers
 
 	  shmem
@@ -1318,11 +1318,9 @@ PAGE_SIZE multiple when read back.
 		Part of "slab" that cannot be reclaimed on memory
 		pressure.
 
-	  pgfault
-		Total number of page faults incurred
-
-	  pgmajfault
-		Number of major page faults incurred
+	  slab(npn)
+		Amount of memory used for storing in-kernel data
+		structures.
 
 	  workingset_refault_anon
 		Number of refaults of previously evicted anonymous pages.
@@ -1348,37 +1346,68 @@ PAGE_SIZE multiple when read back.
 	  workingset_nodereclaim
 		Number of times a shadow node has been reclaimed
 
-	  pgrefill
+	  pgfault(npn)
+		Total number of page faults incurred
+
+	  pgmajfault(npn)
+		Number of major page faults incurred
+
+	  pgrefill(npn)
 		Amount of scanned pages (in an active LRU list)
 
-	  pgscan
+	  pgscan(npn)
 		Amount of scanned pages (in an inactive LRU list)
 
-	  pgsteal
+	  pgsteal(npn)
 		Amount of reclaimed pages
 
-	  pgactivate
+	  pgactivate(npn)
 		Amount of pages moved to the active LRU list
 
-	  pgdeactivate
+	  pgdeactivate(npn)
 		Amount of pages moved to the inactive LRU list
 
-	  pglazyfree
+	  pglazyfree(npn)
 		Amount of pages postponed to be freed under memory pressure
 
-	  pglazyfreed
+	  pglazyfreed(npn)
 		Amount of reclaimed lazyfree pages
 
-	  thp_fault_alloc
+	  thp_fault_alloc(npn)
 		Number of transparent hugepages which were allocated to satisfy
 		a page fault. This counter is not present when CONFIG_TRANSPARENT_HUGEPAGE
                 is not set.
 
-	  thp_collapse_alloc
+	  thp_collapse_alloc(npn)
 		Number of transparent hugepages which were allocated to allow
 		collapsing an existing range of pages. This counter is not
 		present when CONFIG_TRANSPARENT_HUGEPAGE is not set.
 
+  memory.numa_stat
+	A read-only nested-keyed file which exists on non-root cgroups.
+
+	This breaks down the cgroup's memory footprint into different
+	types of memory, type-specific details, and other information
+	per node on the state of the memory management system.
+
+	This is useful for providing visibility into the NUMA locality
+	information within an memcg since the pages are allowed to be
+	allocated from any physical node. One of the use case is evaluating
+	application performance by combining this information with the
+	application's CPU allocation.
+
+	All memory amounts are in bytes.
+
+	The output format of memory.numa_stat is::
+
+	  type N0=<bytes in node 0> N1=<bytes in node 1> ...
+
+	The entries are ordered to be human readable, and new entries
+	can show up in the middle. Don't rely on items remaining in a
+	fixed position; use the keys to look up specific values!
+
+	The entries can refer to the memory.stat.
+
   memory.swap.current
 	A read-only single value file which exists on non-root
 	cgroups.

Documentation/admin-guide/mm/hugetlbpage.rst

@@ -131,7 +131,7 @@ hugepages
 	parameter is preceded by an invalid hugepagesz parameter, it will
 	be ignored.
 default_hugepagesz
-	pecify the default huge page size.  This parameter can
+	Specify the default huge page size.  This parameter can
 	only be specified once on the command line.  default_hugepagesz can
 	optionally be followed by the hugepages parameter to preallocate a
 	specific number of huge pages of default size.  The number of default

Documentation/dev-tools/kasan.rst

@@ -13,10 +13,10 @@ KASAN uses compile-time instrumentation to insert validity checks before every
 memory access, and therefore requires a compiler version that supports that.
 
 Generic KASAN 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
+8.3.0 or later. Any supported Clang version is compatible, but detection of
 out-of-bounds accesses for global variables is only supported since Clang 11.
 
-Tag-based KASAN is only supported in Clang and requires version 7.0.0 or later.
+Tag-based KASAN is only supported in Clang.
 
 Currently generic KASAN is supported for the x86_64, arm64, xtensa, s390 and
 riscv architectures, and tag-based KASAN is supported only for arm64.
@@ -281,3 +281,73 @@ unmapped. This will require changes in arch-specific code.
 
 This allows ``VMAP_STACK`` support on x86, and can simplify support of
 architectures that do not have a fixed module region.
+
+CONFIG_KASAN_KUNIT_TEST & CONFIG_TEST_KASAN_MODULE
+--------------------------------------------------
+
+``CONFIG_KASAN_KUNIT_TEST`` utilizes the KUnit Test Framework for testing.
+This means each test focuses on a small unit of functionality and
+there are a few ways these tests can be run.
+
+Each test will print the KASAN report if an error is detected and then
+print the number of the test and the status of the test:
+
+pass::
+
+        ok 28 - kmalloc_double_kzfree
+or, if kmalloc failed::
+
+        # kmalloc_large_oob_right: ASSERTION FAILED at lib/test_kasan.c:163
+        Expected ptr is not null, but is
+        not ok 4 - kmalloc_large_oob_right
+or, if a KASAN report was expected, but not found::
+
+        # kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629
+        Expected kasan_data->report_expected == kasan_data->report_found, but
+        kasan_data->report_expected == 1
+        kasan_data->report_found == 0
+        not ok 28 - kmalloc_double_kzfree
+
+All test statuses are tracked as they run and an overall status will
+be printed at the end::
+
+        ok 1 - kasan
+
+or::
+
+        not ok 1 - kasan
+
+(1) Loadable Module
+~~~~~~~~~~~~~~~~~~~~
+
+With ``CONFIG_KUNIT`` enabled, ``CONFIG_KASAN_KUNIT_TEST`` can be built as
+a loadable module and run on any architecture that supports KASAN
+using something like insmod or modprobe. The module is called ``test_kasan``.
+
+(2) Built-In
+~~~~~~~~~~~~~
+
+With ``CONFIG_KUNIT`` built-in, ``CONFIG_KASAN_KUNIT_TEST`` can be built-in
+on any architecure that supports KASAN. These and any other KUnit
+tests enabled will run and print the results at boot as a late-init
+call.
+
+(3) Using kunit_tool
+~~~~~~~~~~~~~~~~~~~~~
+
+With ``CONFIG_KUNIT`` and ``CONFIG_KASAN_KUNIT_TEST`` built-in, we can also
+use kunit_tool to see the results of these along with other KUnit
+tests in a more readable way. This will not print the KASAN reports
+of tests that passed. Use `KUnit documentation <https://www.kernel.org/doc/html/latest/dev-tools/kunit/index.html>`_ for more up-to-date
+information on kunit_tool.
+
+.. _KUnit: https://www.kernel.org/doc/html/latest/dev-tools/kunit/index.html
+
+``CONFIG_TEST_KASAN_MODULE`` is a set of KASAN tests that could not be
+converted to KUnit. These tests can be run only as a module with
+``CONFIG_TEST_KASAN_MODULE`` built as a loadable module and
+``CONFIG_KASAN`` built-in. The type of error expected and the
+function being run is printed before the expression expected to give
+an error. Then the error is printed, if found, and that test
+should be interpretted to pass only if the error was the one expected
+by the test.

Documentation/dev-tools/kmemleak.rst

@@ -229,7 +229,7 @@ Testing with kmemleak-test
 
 To check if you have all set up to use kmemleak, you can use the kmemleak-test
 module, a module that deliberately leaks memory. Set CONFIG_DEBUG_KMEMLEAK_TEST
-as module (it can't be used as bult-in) and boot the kernel with kmemleak
+as module (it can't be used as built-in) and boot the kernel with kmemleak
 enabled. Load the module and perform a scan with::
 
         # modprobe kmemleak-test

Documentation/kbuild/makefiles.rst

@@ -21,6 +21,7 @@ This document describes the Linux kernel Makefiles.
 	   --- 3.10 Special Rules
 	   --- 3.11 $(CC) support functions
 	   --- 3.12 $(LD) support functions
+	   --- 3.13 Script Invocation
 
 	=== 4 Host Program support
 	   --- 4.1 Simple Host Program
@@ -605,6 +606,25 @@ more details, with real examples.
 		#Makefile
 		LDFLAGS_vmlinux += $(call ld-option, -X)
 
+3.13 Script invocation
+----------------------
+
+	Make rules may invoke scripts to build the kernel. The rules shall
+	always provide the appropriate interpreter to execute the script. They
+	shall not rely on the execute bits being set, and shall not invoke the
+	script directly. For the convenience of manual script invocation, such
+	as invoking ./scripts/checkpatch.pl, it is recommended to set execute
+	bits on the scripts nonetheless.
+
+	Kbuild provides variables $(CONFIG_SHELL), $(AWK), $(PERL),
+	$(PYTHON) and $(PYTHON3) to refer to interpreters for the respective
+	scripts.
+
+	Example::
+
+		#Makefile
+		cmd_depmod = $(CONFIG_SHELL) $(srctree)/scripts/depmod.sh $(DEPMOD) \
+			     $(KERNELRELEASE)
 
 4 Host Program support
 ======================

Documentation/vm/active_mm.rst

@@ -64,7 +64,7 @@ Active MM
  actually get cases where you have a address space that is _only_ used by
  lazy users. That is often a short-lived state, because once that thread
  gets scheduled away in favour of a real thread, the "zombie" mm gets
- released because "mm_users" becomes zero.
+ released because "mm_count" becomes zero.
 
  Also, a new rule is that _nobody_ ever has "init_mm" as a real MM any
  more. "init_mm" should be considered just a "lazy context when no other

Documentation/x86/x86_64/boot-options.rst

@@ -173,6 +173,10 @@ NUMA
   numa=noacpi
     Don't parse the SRAT table for NUMA setup
 
+  numa=nohmat
+    Don't parse the HMAT table for NUMA setup, or soft-reserved memory
+    partitioning.
+
   numa=fake=<size>[MG]
     If given as a memory unit, fills all system RAM with nodes of
     size interleaved over physical nodes.

MAINTAINERS

@@ -9727,8 +9727,8 @@ M:	Catalin Marinas <catalin.marinas@arm.com>
 S:	Maintained
 F:	Documentation/dev-tools/kmemleak.rst
 F:	include/linux/kmemleak.h
-F:	mm/kmemleak-test.c
 F:	mm/kmemleak.c
+F:	samples/kmemleak/kmemleak-test.c
 
 KMOD KERNEL MODULE LOADER - USERMODE HELPER
 M:	Luis Chamberlain <mcgrof@kernel.org>

Makefile

@@ -921,15 +921,6 @@ KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized)
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
-# clang sets -fmerge-all-constants by default as optimization, but this
-# is non-conforming behavior for C and in fact breaks the kernel, so we
-# need to disable it here generally.
-KBUILD_CFLAGS	+= $(call cc-option,-fno-merge-all-constants)
-
-# for gcc -fno-merge-all-constants disables everything, but it is fine
-# to have actual conforming behavior enabled.
-KBUILD_CFLAGS	+= $(call cc-option,-fmerge-constants)
-
 # Make sure -fstack-check isn't enabled (like gentoo apparently did)
 KBUILD_CFLAGS  += $(call cc-option,-fno-stack-check,)
 

arch/arm/Kconfig

@@ -85,7 +85,7 @@ config ARM
 	select HAVE_FAST_GUP if ARM_LPAE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
-	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && (CC_IS_GCC || CLANG_VERSION >= 100000)
+	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
 	select HAVE_IDE if PCI || ISA || PCMCIA

arch/arm/include/asm/tlb.h

@@ -59,6 +59,7 @@ __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
 #ifdef CONFIG_ARM_LPAE
 	struct page *page = virt_to_page(pmdp);
 
+	pgtable_pmd_page_dtor(page);
 	tlb_remove_table(tlb, page);
 #endif
 }

arch/arm/kernel/setup.c

@@ -843,19 +843,25 @@ early_param("mem", early_mem);
 
 static void __init request_standard_resources(const struct machine_desc *mdesc)
 {
-	struct memblock_region *region;
+	phys_addr_t start, end, res_end;
 	struct resource *res;
+	u64 i;
 
 	kernel_code.start   = virt_to_phys(_text);
 	kernel_code.end     = virt_to_phys(__init_begin - 1);
 	kernel_data.start   = virt_to_phys(_sdata);
 	kernel_data.end     = virt_to_phys(_end - 1);
 
-	for_each_memblock(memory, region) {
-		phys_addr_t start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
-		phys_addr_t end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
+	for_each_mem_range(i, &start, &end) {
 		unsigned long boot_alias_start;
 
+		/*
+		 * In memblock, end points to the first byte after the
+		 * range while in resourses, end points to the last byte in
+		 * the range.
+		 */
+		res_end = end - 1;
+
 		/*
 		 * Some systems have a special memory alias which is only
 		 * used for booting.  We need to advertise this region to
@@ -869,7 +875,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 				      __func__, sizeof(*res));
 			res->name = "System RAM (boot alias)";
 			res->start = boot_alias_start;
-			res->end = phys_to_idmap(end);
+			res->end = phys_to_idmap(res_end);
 			res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 			request_resource(&iomem_resource, res);
 		}
@@ -880,7 +886,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 			      sizeof(*res));
 		res->name  = "System RAM";
 		res->start = start;
-		res->end = end;
+		res->end = res_end;
 		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 		request_resource(&iomem_resource, res);