Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "A few small subsystems and some of MM.

  172 patches.

  Subsystems affected by this patch series: hexagon, scripts, ntfs,
  ocfs2, vfs, and mm (slab-generic, slab, slub, debug, pagecache, swap,
  memcg, pagemap, mprotect, mremap, page-reporting, vmalloc, kasan,
  pagealloc, memory-failure, hugetlb, vmscan, z3fold, compaction,
  mempolicy, oom-kill, hugetlbfs, and migration)"

* emailed patches from Andrew Morton <[email protected]>: (172 commits)
  mm/migrate: remove unneeded semicolons
  hugetlbfs: remove unneeded return value of hugetlb_vmtruncate()
  hugetlbfs: fix some comment typos
  hugetlbfs: correct some obsolete comments about inode i_mutex
  hugetlbfs: make hugepage size conversion more readable
  hugetlbfs: remove meaningless variable avoid_reserve
  hugetlbfs: correct obsolete function name in hugetlbfs_read_iter()
  hugetlbfs: use helper macro default_hstate in init_hugetlbfs_fs
  hugetlbfs: remove useless BUG_ON(!inode) in hugetlbfs_setattr()
  hugetlbfs: remove special hugetlbfs_set_page_dirty()
  mm/hugetlb: change hugetlb_reserve_pages() to type bool
  mm, oom: fix a comment in dump_task()
  mm/mempolicy: use helper range_in_vma() in queue_pages_test_walk()
  numa balancing: migrate on fault among multiple bound nodes
  mm, compaction: make fast_isolate_freepages() stay within zone
  mm/compaction: fix misbehaviors of fast_find_migrateblock()
  mm/compaction: correct deferral logic for proactive compaction
  mm/compaction: remove duplicated VM_BUG_ON_PAGE !PageLocked
  mm/compaction: remove rcu_read_lock during page compaction
  z3fold: simplify the zhdr initialization code in init_z3fold_page()
  ...

Author: torvalds

Documentation/admin-guide/cgroup-v2.rst

@@ -1299,6 +1299,10 @@ PAGE_SIZE multiple when read back.
 		Amount of cached filesystem data that was modified and
 		is currently being written back to disk
 
+	  swapcached
+		Amount of swap cached in memory. The swapcache is accounted
+		against both memory and swap usage.
+
 	  anon_thp
 		Amount of memory used in anonymous mappings backed by
 		transparent hugepages

Documentation/admin-guide/kernel-parameters.txt

@@ -4904,14 +4904,6 @@
 			last alloc / free. For more information see
 			Documentation/vm/slub.rst.
 
-	slub_memcg_sysfs=	[MM, SLUB]
-			Determines whether to enable sysfs directories for
-			memory cgroup sub-caches. 1 to enable, 0 to disable.
-			The default is determined by CONFIG_SLUB_MEMCG_SYSFS_ON.
-			Enabling this can lead to a very high number of	debug
-			directories and files being created under
-			/sys/kernel/slub.
-
 	slub_max_order= [MM, SLUB]
 			Determines the maximum allowed order for slabs.
 			A high setting may cause OOMs due to memory

Documentation/admin-guide/sysctl/vm.rst

@@ -983,11 +983,11 @@ that benefit from having their data cached, zone_reclaim_mode should be
 left disabled as the caching effect is likely to be more important than
 data locality.
 
-zone_reclaim may be enabled if it's known that the workload is partitioned
-such that each partition fits within a NUMA node and that accessing remote
-memory would cause a measurable performance reduction.  The page allocator
-will then reclaim easily reusable pages (those page cache pages that are
-currently not used) before allocating off node pages.
+Consider enabling one or more zone_reclaim mode bits if it's known that the
+workload is partitioned such that each partition fits within a NUMA node
+and that accessing remote memory would cause a measurable performance
+reduction.  The page allocator will take additional actions before
+allocating off node pages.
 
 Allowing zone reclaim to write out pages stops processes that are
 writing large amounts of data from dirtying pages on other nodes. Zone

Documentation/core-api/mm-api.rst

@@ -19,11 +19,8 @@ User Space Memory Access
 Memory Allocation Controls
 ==========================
 
-Functions which need to allocate memory often use GFP flags to express
-how that memory should be allocated. The GFP acronym stands for "get
-free pages", the underlying memory allocation function. Not every GFP
-flag is allowed to every function which may allocate memory. Most
-users will want to use a plain ``GFP_KERNEL``.
+.. kernel-doc:: include/linux/gfp.h
+   :internal:
 
 .. kernel-doc:: include/linux/gfp.h
    :doc: Page mobility and placement hints

Documentation/dev-tools/kasan.rst

@@ -147,15 +147,14 @@ negative values to distinguish between different kinds of inaccessible memory
 like redzones or freed memory (see mm/kasan/kasan.h).
 
 In the report above the arrows point to the shadow byte 03, which means that
-the accessed address is partially accessible.
-
-For tag-based KASAN this last report section shows the memory tags around the
-accessed address (see `Implementation details`_ section).
+the accessed address is partially accessible. For tag-based KASAN modes this
+last report section shows the memory tags around the accessed address
+(see the `Implementation details`_ section).
 
 Boot parameters
 ~~~~~~~~~~~~~~~
 
-Hardware tag-based KASAN mode (see the section about different mode below) is
+Hardware tag-based KASAN mode (see the section about various modes below) is
 intended for use in production as a security mitigation. Therefore it supports
 boot parameters that allow to disable KASAN competely or otherwise control
 particular KASAN features.
@@ -289,6 +288,13 @@ reserved to tag freed memory regions.
 Hardware tag-based KASAN currently only supports tagging of
 kmem_cache_alloc/kmalloc and page_alloc memory.
 
+If the hardware doesn't support MTE (pre ARMv8.5), hardware tag-based KASAN
+won't be enabled. In this case all boot parameters are ignored.
+
+Note, that enabling CONFIG_KASAN_HW_TAGS always results in in-kernel TBI being
+enabled. Even when kasan.mode=off is provided, or when the hardware doesn't
+support MTE (but supports TBI).
+
 What memory accesses are sanitised by KASAN?
 --------------------------------------------
 
@@ -352,17 +358,17 @@ 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 and CONFIG_KASAN_MODULE_TEST
+----------------------------------------------------
 
-KASAN tests consist on two parts:
+KASAN tests consist of two parts:
 
 1. Tests that are integrated with the KUnit Test Framework. Enabled with
 ``CONFIG_KASAN_KUNIT_TEST``. These tests can be run and partially verified
 automatically in a few different ways, see the instructions below.
 
 2. Tests that are currently incompatible with KUnit. Enabled with
-``CONFIG_TEST_KASAN_MODULE`` and can only be run as a module. These tests can
+``CONFIG_KASAN_MODULE_TEST`` and can only be run as a module. These tests can
 only be verified manually, by loading the kernel module and inspecting the
 kernel log for KASAN reports.
 

Documentation/vm/arch_pgtable_helpers.rst

@@ -50,7 +50,7 @@ PTE Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pte_mkwrite               | Creates a writable PTE                           |
 +---------------------------+--------------------------------------------------+
-| pte_mkwrprotect           | Creates a write protected PTE                    |
+| pte_wrprotect             | Creates a write protected PTE                    |
 +---------------------------+--------------------------------------------------+
 | pte_mkspecial             | Creates a special PTE                            |
 +---------------------------+--------------------------------------------------+
@@ -120,7 +120,7 @@ PMD Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pmd_mkwrite               | Creates a writable PMD                           |
 +---------------------------+--------------------------------------------------+
-| pmd_mkwrprotect           | Creates a write protected PMD                    |
+| pmd_wrprotect             | Creates a write protected PMD                    |
 +---------------------------+--------------------------------------------------+
 | pmd_mkspecial             | Creates a special PMD                            |
 +---------------------------+--------------------------------------------------+
@@ -186,7 +186,7 @@ PUD Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pud_mkwrite               | Creates a writable PUD                           |
 +---------------------------+--------------------------------------------------+
-| pud_mkwrprotect           | Creates a write protected PUD                    |
+| pud_wrprotect             | Creates a write protected PUD                    |
 +---------------------------+--------------------------------------------------+
 | pud_mkdevmap              | Creates a ZONE_DEVICE mapped PUD                 |
 +---------------------------+--------------------------------------------------+
@@ -224,7 +224,7 @@ HugeTLB Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | huge_pte_mkwrite          | Creates a writable HugeTLB                       |
 +---------------------------+--------------------------------------------------+
-| huge_pte_mkwrprotect      | Creates a write protected HugeTLB                |
+| huge_pte_wrprotect        | Creates a write protected HugeTLB                |
 +---------------------------+--------------------------------------------------+
 | huge_ptep_get_and_clear   | Clears a HugeTLB                                 |
 +---------------------------+--------------------------------------------------+

arch/arm64/include/asm/memory.h

@@ -244,6 +244,7 @@ static inline const void *__tag_set(const void *addr, u8 tag)
 
 #ifdef CONFIG_KASAN_HW_TAGS
 #define arch_enable_tagging()			mte_enable_kernel()
+#define arch_set_tagging_report_once(state)	mte_set_report_once(state)
 #define arch_init_tags(max_tag)			mte_init_tags(max_tag)
 #define arch_get_random_tag()			mte_get_random_tag()
 #define arch_get_mem_tag(addr)			mte_get_mem_tag(addr)

arch/arm64/include/asm/mte-kasan.h

@@ -32,6 +32,9 @@ void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag);
 void mte_enable_kernel(void);
 void mte_init_tags(u64 max_tag);
 
+void mte_set_report_once(bool state);
+bool mte_report_once(void);
+
 #else /* CONFIG_ARM64_MTE */
 
 static inline u8 mte_get_ptr_tag(void *ptr)
@@ -60,6 +63,15 @@ static inline void mte_init_tags(u64 max_tag)
 {
 }
 
+static inline void mte_set_report_once(bool state)
+{
+}
+
+static inline bool mte_report_once(void)
+{
+	return false;
+}
+
 #endif /* CONFIG_ARM64_MTE */
 
 #endif /* __ASSEMBLY__ */

arch/arm64/kernel/mte.c

@@ -25,6 +25,8 @@
 
 u64 gcr_kernel_excl __ro_after_init;
 
+static bool report_fault_once = true;
+
 static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
 {
 	pte_t old_pte = READ_ONCE(*ptep);
@@ -158,6 +160,16 @@ void mte_enable_kernel(void)
 	isb();
 }
 
+void mte_set_report_once(bool state)
+{
+	WRITE_ONCE(report_fault_once, state);
+}
+
+bool mte_report_once(void)
+{
+	return READ_ONCE(report_fault_once);
+}
+
 static void update_sctlr_el1_tcf0(u64 tcf0)
 {
 	/* ISB required for the kernel uaccess routines */

arch/arm64/mm/fault.c

@@ -302,12 +302,24 @@ static void die_kernel_fault(const char *msg, unsigned long addr,
 static void report_tag_fault(unsigned long addr, unsigned int esr,
 			     struct pt_regs *regs)
 {
-	bool is_write  = ((esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT) != 0;
+	static bool reported;
+	bool is_write;
+
+	if (READ_ONCE(reported))
+		return;
+
+	/*
+	 * This is used for KASAN tests and assumes that no MTE faults
+	 * happened before running the tests.
+	 */
+	if (mte_report_once())
+		WRITE_ONCE(reported, true);
 
 	/*
 	 * SAS bits aren't set for all faults reported in EL1, so we can't
 	 * find out access size.
 	 */
+	is_write = !!(esr & ESR_ELx_WNR);
 	kasan_report(addr, 0, is_write, regs->pc);
 }
 #else
@@ -319,12 +331,8 @@ static inline void report_tag_fault(unsigned long addr, unsigned int esr,
 static void do_tag_recovery(unsigned long addr, unsigned int esr,
 			   struct pt_regs *regs)
 {
-	static bool reported;
 
-	if (!READ_ONCE(reported)) {
-		report_tag_fault(addr, esr, regs);
-		WRITE_ONCE(reported, true);
-	}
+	report_tag_fault(addr, esr, regs);
 
 	/*
 	 * Disable MTE Tag Checking on the local CPU for the current EL.