Merge tag 'mm-stable-2022-05-27' of git://git.kernel.org/pub/scm/linu…

…x/kernel/git/akpm/mm

Pull more MM updates from Andrew Morton:

 - Two follow-on fixes for the post-5.19 series "Use pageblock_order for
   cma and alloc_contig_range alignment", from Zi Yan.

 - A series of z3fold cleanups and fixes from Miaohe Lin.

 - Some memcg selftests work from Michal Koutný <[email protected]>

 - Some swap fixes and cleanups from Miaohe Lin

 - Several individual minor fixups

* tag 'mm-stable-2022-05-27' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (25 commits)
  mm/shmem.c: suppress shift warning
  mm: Kconfig: reorganize misplaced mm options
  mm: kasan: fix input of vmalloc_to_page()
  mm: fix is_pinnable_page against a cma page
  mm: filter out swapin error entry in shmem mapping
  mm/shmem: fix infinite loop when swap in shmem error at swapoff time
  mm/madvise: free hwpoison and swapin error entry in madvise_free_pte_range
  mm/swapfile: fix lost swap bits in unuse_pte()
  mm/swapfile: unuse_pte can map random data if swap read fails
  selftests: memcg: factor out common parts of memory.{low,min} tests
  selftests: memcg: remove protection from top level memcg
  selftests: memcg: adjust expected reclaim values of protected cgroups
  selftests: memcg: expect no low events in unprotected sibling
  selftests: memcg: fix compilation
  mm/z3fold: fix z3fold_page_migrate races with z3fold_map
  mm/z3fold: fix z3fold_reclaim_page races with z3fold_free
  mm/z3fold: always clear PAGE_CLAIMED under z3fold page lock
  mm/z3fold: put z3fold page back into unbuddied list when reclaim or migration fails
  revert "mm/z3fold.c: allow __GFP_HIGHMEM in z3fold_alloc"
  mm/z3fold: throw warning on failure of trylock_page in z3fold_alloc
  ...

MAINTAINERS

@@ -5062,6 +5062,7 @@ L:	[email protected]
 S:	Maintained
 F:	mm/memcontrol.c
 F:	mm/swap_cgroup.c
+F:	tools/testing/selftests/cgroup/memcg_protection.m
 F:	tools/testing/selftests/cgroup/test_kmem.c
 F:	tools/testing/selftests/cgroup/test_memcontrol.c
 

include/linux/mm.h

@@ -1594,8 +1594,13 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
 #ifdef CONFIG_MIGRATION
 static inline bool is_pinnable_page(struct page *page)
 {
-	return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) ||
-		is_zero_pfn(page_to_pfn(page));
+#ifdef CONFIG_CMA
+	int mt = get_pageblock_migratetype(page);
+
+	if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
+		return false;
+#endif
+	return !(is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page)));
 }
 #else
 static inline bool is_pinnable_page(struct page *page)

include/linux/swap.h

@@ -55,6 +55,10 @@ static inline int current_is_kswapd(void)
  * actions on faults.
  */
 
+#define SWP_SWAPIN_ERROR_NUM 1
+#define SWP_SWAPIN_ERROR     (MAX_SWAPFILES + SWP_HWPOISON_NUM + \
+			     SWP_MIGRATION_NUM + SWP_DEVICE_NUM + \
+			     SWP_PTE_MARKER_NUM)
 /*
  * PTE markers are used to persist information onto PTEs that are mapped with
  * file-backed memories.  As its name "PTE" hints, it should only be applied to
@@ -120,7 +124,8 @@ static inline int current_is_kswapd(void)
 
 #define MAX_SWAPFILES \
 	((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \
-	SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM)
+	SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \
+	SWP_PTE_MARKER_NUM - SWP_SWAPIN_ERROR_NUM)
 
 /*
  * Magic header for a swap area. The first part of the union is

include/linux/swapops.h

@@ -108,6 +108,16 @@ static inline void *swp_to_radix_entry(swp_entry_t entry)
 	return xa_mk_value(entry.val);
 }
 
+static inline swp_entry_t make_swapin_error_entry(struct page *page)
+{
+	return swp_entry(SWP_SWAPIN_ERROR, page_to_pfn(page));
+}
+
+static inline int is_swapin_error_entry(swp_entry_t entry)
+{
+	return swp_type(entry) == SWP_SWAPIN_ERROR;
+}
+
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
 static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset)
 {

init/Kconfig

@@ -1842,60 +1842,6 @@ config DEBUG_PERF_USE_VMALLOC
 
 endmenu
 
-config VM_EVENT_COUNTERS
-	default y
-	bool "Enable VM event counters for /proc/vmstat" if EXPERT
-	help
-	  VM event counters are needed for event counts to be shown.
-	  This option allows the disabling of the VM event counters
-	  on EXPERT systems.  /proc/vmstat will only show page counts
-	  if VM event counters are disabled.
-
-config SLUB_DEBUG
-	default y
-	bool "Enable SLUB debugging support" if EXPERT
-	depends on SLUB && SYSFS
-	select STACKDEPOT if STACKTRACE_SUPPORT
-	help
-	  SLUB has extensive debug support features. Disabling these can
-	  result in significant savings in code size. This also disables
-	  SLUB sysfs support. /sys/slab will not exist and there will be
-	  no support for cache validation etc.
-
-config COMPAT_BRK
-	bool "Disable heap randomization"
-	default y
-	help
-	  Randomizing heap placement makes heap exploits harder, but it
-	  also breaks ancient binaries (including anything libc5 based).
-	  This option changes the bootup default to heap randomization
-	  disabled, and can be overridden at runtime by setting
-	  /proc/sys/kernel/randomize_va_space to 2.
-
-	  On non-ancient distros (post-2000 ones) N is usually a safe choice.
-
-config MMAP_ALLOW_UNINITIALIZED
-	bool "Allow mmapped anonymous memory to be uninitialized"
-	depends on EXPERT && !MMU
-	default n
-	help
-	  Normally, and according to the Linux spec, anonymous memory obtained
-	  from mmap() has its contents cleared before it is passed to
-	  userspace.  Enabling this config option allows you to request that
-	  mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
-	  providing a huge performance boost.  If this option is not enabled,
-	  then the flag will be ignored.
-
-	  This is taken advantage of by uClibc's malloc(), and also by
-	  ELF-FDPIC binfmt's brk and stack allocator.
-
-	  Because of the obvious security issues, this option should only be
-	  enabled on embedded devices where you control what is run in
-	  userspace.  Since that isn't generally a problem on no-MMU systems,
-	  it is normally safe to say Y here.
-
-	  See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
-
 config SYSTEM_DATA_VERIFICATION
 	def_bool n
 	select SYSTEM_TRUSTED_KEYRING

lib/Kconfig.debug

@@ -699,41 +699,6 @@ config DEBUG_OBJECTS_ENABLE_DEFAULT
 	help
 	  Debug objects boot parameter default value
 
-config DEBUG_SLAB
-	bool "Debug slab memory allocations"
-	depends on DEBUG_KERNEL && SLAB
-	help
-	  Say Y here to have the kernel do limited verification on memory
-	  allocation as well as poisoning memory on free to catch use of freed
-	  memory. This can make kmalloc/kfree-intensive workloads much slower.
-
-config SLUB_DEBUG_ON
-	bool "SLUB debugging on by default"
-	depends on SLUB && SLUB_DEBUG
-	select STACKDEPOT_ALWAYS_INIT if STACKTRACE_SUPPORT
-	default n
-	help
-	  Boot with debugging on by default. SLUB boots by default with
-	  the runtime debug capabilities switched off. Enabling this is
-	  equivalent to specifying the "slub_debug" parameter on boot.
-	  There is no support for more fine grained debug control like
-	  possible with slub_debug=xxx. SLUB debugging may be switched
-	  off in a kernel built with CONFIG_SLUB_DEBUG_ON by specifying
-	  "slub_debug=-".
-
-config SLUB_STATS
-	default n
-	bool "Enable SLUB performance statistics"
-	depends on SLUB && SYSFS
-	help
-	  SLUB statistics are useful to debug SLUBs allocation behavior in
-	  order find ways to optimize the allocator. This should never be
-	  enabled for production use since keeping statistics slows down
-	  the allocator by a few percentage points. The slabinfo command
-	  supports the determination of the most active slabs to figure
-	  out which slabs are relevant to a particular load.
-	  Try running: slabinfo -DA
-
 config HAVE_DEBUG_KMEMLEAK
 	bool
 

mm/Kconfig

@@ -270,6 +270,19 @@ config SLAB_FREELIST_HARDENED
 	  sanity-checking than others. This option is most effective with
 	  CONFIG_SLUB.
 
+config SLUB_STATS
+	default n
+	bool "Enable SLUB performance statistics"
+	depends on SLUB && SYSFS
+	help
+	  SLUB statistics are useful to debug SLUBs allocation behavior in
+	  order find ways to optimize the allocator. This should never be
+	  enabled for production use since keeping statistics slows down
+	  the allocator by a few percentage points. The slabinfo command
+	  supports the determination of the most active slabs to figure
+	  out which slabs are relevant to a particular load.
+	  Try running: slabinfo -DA
+
 config SLUB_CPU_PARTIAL
 	default y
 	depends on SLUB && SMP
@@ -307,6 +320,40 @@ config SHUFFLE_PAGE_ALLOCATOR
 
 	  Say Y if unsure.
 
+config COMPAT_BRK
+	bool "Disable heap randomization"
+	default y
+	help
+	  Randomizing heap placement makes heap exploits harder, but it
+	  also breaks ancient binaries (including anything libc5 based).
+	  This option changes the bootup default to heap randomization
+	  disabled, and can be overridden at runtime by setting
+	  /proc/sys/kernel/randomize_va_space to 2.
+
+	  On non-ancient distros (post-2000 ones) N is usually a safe choice.
+
+config MMAP_ALLOW_UNINITIALIZED
+	bool "Allow mmapped anonymous memory to be uninitialized"
+	depends on EXPERT && !MMU
+	default n
+	help
+	  Normally, and according to the Linux spec, anonymous memory obtained
+	  from mmap() has its contents cleared before it is passed to
+	  userspace.  Enabling this config option allows you to request that
+	  mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
+	  providing a huge performance boost.  If this option is not enabled,
+	  then the flag will be ignored.
+
+	  This is taken advantage of by uClibc's malloc(), and also by
+	  ELF-FDPIC binfmt's brk and stack allocator.
+
+	  Because of the obvious security issues, this option should only be
+	  enabled on embedded devices where you control what is run in
+	  userspace.  Since that isn't generally a problem on no-MMU systems,
+	  it is normally safe to say Y here.
+
+	  See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
+
 config SELECT_MEMORY_MODEL
 	def_bool y
 	depends on ARCH_SELECT_MEMORY_MODEL
@@ -964,6 +1011,15 @@ config ARCH_USES_HIGH_VMA_FLAGS
 config ARCH_HAS_PKEYS
 	bool
 
+config VM_EVENT_COUNTERS
+	default y
+	bool "Enable VM event counters for /proc/vmstat" if EXPERT
+	help
+	  VM event counters are needed for event counts to be shown.
+	  This option allows the disabling of the VM event counters
+	  on EXPERT systems.  /proc/vmstat will only show page counts
+	  if VM event counters are disabled.
+
 config PERCPU_STATS
 	bool "Collect percpu memory statistics"
 	help

mm/Kconfig.debug

@@ -45,6 +45,39 @@ config DEBUG_PAGEALLOC_ENABLE_DEFAULT
 	  Enable debug page memory allocations by default? This value
 	  can be overridden by debug_pagealloc=off|on.
 
+config DEBUG_SLAB
+	bool "Debug slab memory allocations"
+	depends on DEBUG_KERNEL && SLAB
+	help
+	  Say Y here to have the kernel do limited verification on memory
+	  allocation as well as poisoning memory on free to catch use of freed
+	  memory. This can make kmalloc/kfree-intensive workloads much slower.
+
+config SLUB_DEBUG
+	default y
+	bool "Enable SLUB debugging support" if EXPERT
+	depends on SLUB && SYSFS
+	select STACKDEPOT if STACKTRACE_SUPPORT
+	help
+	  SLUB has extensive debug support features. Disabling these can
+	  result in significant savings in code size. This also disables
+	  SLUB sysfs support. /sys/slab will not exist and there will be
+	  no support for cache validation etc.
+
+config SLUB_DEBUG_ON
+	bool "SLUB debugging on by default"
+	depends on SLUB && SLUB_DEBUG
+	select STACKDEPOT_ALWAYS_INIT if STACKTRACE_SUPPORT
+	default n
+	help
+	  Boot with debugging on by default. SLUB boots by default with
+	  the runtime debug capabilities switched off. Enabling this is
+	  equivalent to specifying the "slub_debug" parameter on boot.
+	  There is no support for more fine grained debug control like
+	  possible with slub_debug=xxx. SLUB debugging may be switched
+	  off in a kernel built with CONFIG_SLUB_DEBUG_ON by specifying
+	  "slub_debug=-".
+
 config PAGE_OWNER
 	bool "Track page owner"
 	depends on DEBUG_KERNEL && STACKTRACE_SUPPORT

mm/internal.h

@@ -374,8 +374,8 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
 			  phys_addr_t min_addr,
 			  int nid, bool exact_nid);
 
-void split_free_page(struct page *free_page,
-				int order, unsigned long split_pfn_offset);
+int split_free_page(struct page *free_page,
+			unsigned int order, unsigned long split_pfn_offset);
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 

mm/kasan/report.c

@@ -347,7 +347,7 @@ static void print_address_description(void *addr, u8 tag)
 			       va->addr, va->addr + va->size, va->caller);
 			pr_err("\n");
 
-			page = vmalloc_to_page(page);
+			page = vmalloc_to_page(addr);
 		}
 	}
 

mm/madvise.c

@@ -248,10 +248,13 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 
 		if (!xa_is_value(page))
 			continue;
+		swap = radix_to_swp_entry(page);
+		/* There might be swapin error entries in shmem mapping. */
+		if (non_swap_entry(swap))
+			continue;
 		xas_pause(&xas);
 		rcu_read_unlock();
 
-		swap = radix_to_swp_entry(page);
 		page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
 					     NULL, 0, false, &splug);
 		if (page)
@@ -624,11 +627,14 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 			swp_entry_t entry;
 
 			entry = pte_to_swp_entry(ptent);
-			if (non_swap_entry(entry))
-				continue;
-			nr_swap--;
-			free_swap_and_cache(entry);
-			pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
+			if (!non_swap_entry(entry)) {
+				nr_swap--;
+				free_swap_and_cache(entry);
+				pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
+			} else if (is_hwpoison_entry(entry) ||
+				   is_swapin_error_entry(entry)) {
+				pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
+			}
 			continue;
 		}
 

mm/memory.c

@@ -1487,7 +1487,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			/* Only drop the uffd-wp marker if explicitly requested */
 			if (!zap_drop_file_uffd_wp(details))
 				continue;
-		} else if (is_hwpoison_entry(entry)) {
+		} else if (is_hwpoison_entry(entry) ||
+			   is_swapin_error_entry(entry)) {
 			if (!should_zap_cows(details))
 				continue;
 		} else {
@@ -3727,6 +3728,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;
+		} else if (is_swapin_error_entry(entry)) {
+			ret = VM_FAULT_SIGBUS;
 		} else if (is_pte_marker_entry(entry)) {
 			ret = handle_pte_marker(vmf);
 		} else {