Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
   switching from a user process to a kernel thread.

 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
   Raghav.

 - zsmalloc performance improvements from Sergey Senozhatsky.

 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.

 - VFS rationalizations from Christoph Hellwig:
     - removal of most of the callers of write_one_page()
     - make __filemap_get_folio()'s return value more useful

 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing. Use `mount -o noswap'.

 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.

 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).

 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.

 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
   rather than exclusive, and has fixed a bunch of errors which were
   caused by its unintuitive meaning.

 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.

 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.

 - Cleanups to do_fault_around() by Lorenzo Stoakes.

 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.

 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.

 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.

 - Lorenzo has also contributed further cleanups of vma_merge().

 - Chaitanya Prakash provides some fixes to the mmap selftesting code.

 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.

 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.

 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.

 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.

 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.

 - Yosry Ahmed has improved the performance of memcg statistics
   flushing.

 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.

 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.

 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.

 - Pankaj Raghav has made page_endio() unneeded and has removed it.

 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.

 - Yosry Ahmed has fixed an issue around memcg's page recalim
   accounting.

 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.

 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.

 - Peter Xu fixes a few issues with uffd-wp at fork() time.

 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.

* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
  shmem: restrict noswap option to initial user namespace
  mm/khugepaged: fix conflicting mods to collapse_file()
  sparse: remove unnecessary 0 values from rc
  mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
  hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
  maple_tree: fix allocation in mas_sparse_area()
  mm: do not increment pgfault stats when page fault handler retries
  zsmalloc: allow only one active pool compaction context
  selftests/mm: add new selftests for KSM
  mm: add new KSM process and sysfs knobs
  mm: add new api to enable ksm per process
  mm: shrinkers: fix debugfs file permissions
  mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
  migrate_pages_batch: fix statistics for longterm pin retry
  userfaultfd: use helper function range_in_vma()
  lib/show_mem.c: use for_each_populated_zone() simplify code
  mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
  fs/buffer: convert create_page_buffers to folio_create_buffers
  fs/buffer: add folio_create_empty_buffers helper
  ...

11 files changed, 166 insertions, 109 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3f5bf55050e8..b1201d25a8a4 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -95,6 +95,7 @@ config ARM64
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK
+	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
 	select ARCH_WANT_DEFAULT_BPF_JIT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
@@ -1505,39 +1506,34 @@ config XEN
 
 # include/linux/mmzone.h requires the following to be true:
 #
-#   MAX_ORDER - 1 + PAGE_SHIFT <= SECTION_SIZE_BITS
+#   MAX_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
 #
-# so the maximum value of MAX_ORDER is SECTION_SIZE_BITS + 1 - PAGE_SHIFT:
+# so the maximum value of MAX_ORDER is SECTION_SIZE_BITS - PAGE_SHIFT:
 #
 #     | SECTION_SIZE_BITS |  PAGE_SHIFT  |  max MAX_ORDER  |  default MAX_ORDER |
 # ----+-------------------+--------------+-----------------+--------------------+
-# 4K  |       27          |      12      |       16        |         11         |
-# 16K |       27          |      14      |       14        |         12         |
-# 64K |       29          |      16      |       14        |         14         |
+# 4K  |       27          |      12      |       15        |         10         |
+# 16K |       27          |      14      |       13        |         11         |
+# 64K |       29          |      16      |       13        |         13         |
 config ARCH_FORCE_MAX_ORDER
-	int "Maximum zone order" if ARM64_4K_PAGES || ARM64_16K_PAGES
-	default "14" if ARM64_64K_PAGES
-	range 12 14 if ARM64_16K_PAGES
-	default "12" if ARM64_16K_PAGES
-	range 11 16 if ARM64_4K_PAGES
-	default "11"
-	help
-	  The kernel memory allocator divides physically contiguous memory
-	  blocks into "zones", where each zone is a power of two number of
-	  pages.  This option selects the largest power of two that the kernel
-	  keeps in the memory allocator.  If you need to allocate very large
-	  blocks of physically contiguous memory, then you may need to
-	  increase this value.
-
-	  This config option is actually maximum order plus one. For example,
-	  a value of 11 means that the largest free memory block is 2^10 pages.
-
-	  We make sure that we can allocate up to a HugePage size for each configuration.
-	  Hence we have :
-		MAX_ORDER = (PMD_SHIFT - PAGE_SHIFT) + 1 => PAGE_SHIFT - 2
-
-	  However for 4K, we choose a higher default value, 11 as opposed to 10, giving us
-	  4M allocations matching the default size used by generic code.
+	int "Order of maximal physically contiguous allocations" if EXPERT && (ARM64_4K_PAGES || ARM64_16K_PAGES)
+	default "13" if ARM64_64K_PAGES
+	default "11" if ARM64_16K_PAGES
+	default "10"
+	help
+	  The kernel page allocator limits the size of maximal physically
+	  contiguous allocations. The limit is called MAX_ORDER and it
+	  defines the maximal power of two of number of pages that can be
+	  allocated as a single contiguous block. This option allows
+	  overriding the default setting when ability to allocate very
+	  large blocks of physically contiguous memory is required.
+
+	  The maximal size of allocation cannot exceed the size of the
+	  section, so the value of MAX_ORDER should satisfy
+
+	    MAX_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
+
+	  Don't change if unsure.
 
 config UNMAP_KERNEL_AT_EL0
 	bool "Unmap kernel when running in userspace (aka \"KAISER\")" if EXPERT
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index efcd68154a3a..c735afdf639b 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -261,9 +261,11 @@ static inline const void *__tag_set(const void *addr, u8 tag)
 }
 
 #ifdef CONFIG_KASAN_HW_TAGS
-#define arch_enable_tagging_sync()		mte_enable_kernel_sync()
-#define arch_enable_tagging_async()		mte_enable_kernel_async()
-#define arch_enable_tagging_asymm()		mte_enable_kernel_asymm()
+#define arch_enable_tag_checks_sync()		mte_enable_kernel_sync()
+#define arch_enable_tag_checks_async()		mte_enable_kernel_async()
+#define arch_enable_tag_checks_asymm()		mte_enable_kernel_asymm()
+#define arch_suppress_tag_checks_start()	mte_enable_tco()
+#define arch_suppress_tag_checks_stop()		mte_disable_tco()
 #define arch_force_async_tag_fault()		mte_check_tfsr_exit()
 #define arch_get_random_tag()			mte_get_random_tag()
 #define arch_get_mem_tag(addr)			mte_get_mem_tag(addr)
diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h
index 9f79425fc65a..2e98028c1965 100644
--- a/arch/arm64/include/asm/mte-kasan.h
+++ b/arch/arm64/include/asm/mte-kasan.h
@@ -13,9 +13,74 @@
 
 #include <linux/types.h>
 
+#ifdef CONFIG_KASAN_HW_TAGS
+
+/* Whether the MTE asynchronous mode is enabled. */
+DECLARE_STATIC_KEY_FALSE(mte_async_or_asymm_mode);
+
+static inline bool system_uses_mte_async_or_asymm_mode(void)
+{
+	return static_branch_unlikely(&mte_async_or_asymm_mode);
+}
+
+#else /* CONFIG_KASAN_HW_TAGS */
+
+static inline bool system_uses_mte_async_or_asymm_mode(void)
+{
+	return false;
+}
+
+#endif /* CONFIG_KASAN_HW_TAGS */
+
 #ifdef CONFIG_ARM64_MTE
 
 /*
+ * The Tag Check Flag (TCF) mode for MTE is per EL, hence TCF0
+ * affects EL0 and TCF affects EL1 irrespective of which TTBR is
+ * used.
+ * The kernel accesses TTBR0 usually with LDTR/STTR instructions
+ * when UAO is available, so these would act as EL0 accesses using
+ * TCF0.
+ * However futex.h code uses exclusives which would be executed as
+ * EL1, this can potentially cause a tag check fault even if the
+ * user disables TCF0.
+ *
+ * To address the problem we set the PSTATE.TCO bit in uaccess_enable()
+ * and reset it in uaccess_disable().
+ *
+ * The Tag check override (TCO) bit disables temporarily the tag checking
+ * preventing the issue.
+ */
+static inline void mte_disable_tco(void)
+{
+	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0),
+				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+}
+
+static inline void mte_enable_tco(void)
+{
+	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1),
+				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+}
+
+/*
+ * These functions disable tag checking only if in MTE async mode
+ * since the sync mode generates exceptions synchronously and the
+ * nofault or load_unaligned_zeropad can handle them.
+ */
+static inline void __mte_disable_tco_async(void)
+{
+	if (system_uses_mte_async_or_asymm_mode())
+		mte_disable_tco();
+}
+
+static inline void __mte_enable_tco_async(void)
+{
+	if (system_uses_mte_async_or_asymm_mode())
+		mte_enable_tco();
+}
+
+/*
  * These functions are meant to be only used from KASAN runtime through
  * the arch_*() interface defined in asm/memory.h.
  * These functions don't include system_supports_mte() checks,
@@ -138,6 +203,22 @@ void mte_enable_kernel_asymm(void);
 
 #else /* CONFIG_ARM64_MTE */
 
+static inline void mte_disable_tco(void)
+{
+}
+
+static inline void mte_enable_tco(void)
+{
+}
+
+static inline void __mte_disable_tco_async(void)
+{
+}
+
+static inline void __mte_enable_tco_async(void)
+{
+}
+
 static inline u8 mte_get_ptr_tag(void *ptr)
 {
 	return 0xFF;
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index 20dd06d70af5..c028afb1cd0b 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -178,14 +178,6 @@ static inline void mte_disable_tco_entry(struct task_struct *task)
 }
 
 #ifdef CONFIG_KASAN_HW_TAGS
-/* Whether the MTE asynchronous mode is enabled. */
-DECLARE_STATIC_KEY_FALSE(mte_async_or_asymm_mode);
-
-static inline bool system_uses_mte_async_or_asymm_mode(void)
-{
-	return static_branch_unlikely(&mte_async_or_asymm_mode);
-}
-
 void mte_check_tfsr_el1(void);
 
 static inline void mte_check_tfsr_entry(void)
@@ -212,10 +204,6 @@ static inline void mte_check_tfsr_exit(void)
 	mte_check_tfsr_el1();
 }
 #else
-static inline bool system_uses_mte_async_or_asymm_mode(void)
-{
-	return false;
-}
 static inline void mte_check_tfsr_el1(void)
 {
 }
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b6ba466e2e8a..0bd18de9fd97 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -57,7 +57,7 @@ static inline bool arch_thp_swp_supported(void)
  * fault on one CPU which has been handled concurrently by another CPU
  * does not need to perform additional invalidation.
  */
-#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
+#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
 
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h
index 4b73463423c3..5f5437621029 100644
--- a/arch/arm64/include/asm/sparsemem.h
+++ b/arch/arm64/include/asm/sparsemem.h
@@ -10,7 +10,7 @@
 /*
  * Section size must be at least 512MB for 64K base
  * page size config. Otherwise it will be less than
- * (MAX_ORDER - 1) and the build process will fail.
+ * MAX_ORDER and the build process will fail.
  */
 #ifdef CONFIG_ARM64_64K_PAGES
 #define SECTION_SIZE_BITS 29
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 8209e6a86989..05f4fc265428 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -136,55 +136,9 @@ static inline void __uaccess_enable_hw_pan(void)
 			CONFIG_ARM64_PAN));
 }
 
-/*
- * The Tag Check Flag (TCF) mode for MTE is per EL, hence TCF0
- * affects EL0 and TCF affects EL1 irrespective of which TTBR is
- * used.
- * The kernel accesses TTBR0 usually with LDTR/STTR instructions
- * when UAO is available, so these would act as EL0 accesses using
- * TCF0.
- * However futex.h code uses exclusives which would be executed as
- * EL1, this can potentially cause a tag check fault even if the
- * user disables TCF0.
- *
- * To address the problem we set the PSTATE.TCO bit in uaccess_enable()
- * and reset it in uaccess_disable().
- *
- * The Tag check override (TCO) bit disables temporarily the tag checking
- * preventing the issue.
- */
-static inline void __uaccess_disable_tco(void)
-{
-	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0),
-				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
-}
-
-static inline void __uaccess_enable_tco(void)
-{
-	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1),
-				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
-}
-
-/*
- * These functions disable tag checking only if in MTE async mode
- * since the sync mode generates exceptions synchronously and the
- * nofault or load_unaligned_zeropad can handle them.
- */
-static inline void __uaccess_disable_tco_async(void)
-{
-	if (system_uses_mte_async_or_asymm_mode())
-		 __uaccess_disable_tco();
-}
-
-static inline void __uaccess_enable_tco_async(void)
-{
-	if (system_uses_mte_async_or_asymm_mode())
-		__uaccess_enable_tco();
-}
-
 static inline void uaccess_disable_privileged(void)
 {
-	__uaccess_disable_tco();
+	mte_disable_tco();
 
 	if (uaccess_ttbr0_disable())
 		return;
@@ -194,7 +148,7 @@ static inline void uaccess_disable_privileged(void)
 
 static inline void uaccess_enable_privileged(void)
 {
-	__uaccess_enable_tco();
+	mte_enable_tco();
 
 	if (uaccess_ttbr0_enable())
 		return;
@@ -302,8 +256,8 @@ do {									\
 #define get_user	__get_user
 
 /*
- * We must not call into the scheduler between __uaccess_enable_tco_async() and
- * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking
+ * We must not call into the scheduler between __mte_enable_tco_async() and
+ * __mte_disable_tco_async(). As `dst` and `src` may contain blocking
  * functions, we must evaluate these outside of the critical section.
  */
 #define __get_kernel_nofault(dst, src, type, err_label)			\
@@ -312,10 +266,10 @@ do {									\
 	__typeof__(src) __gkn_src = (src);				\
 	int __gkn_err = 0;						\
 									\
-	__uaccess_enable_tco_async();					\
+	__mte_enable_tco_async();					\
 	__raw_get_mem("ldr", *((type *)(__gkn_dst)),			\
 		      (__force type *)(__gkn_src), __gkn_err, K);	\
-	__uaccess_disable_tco_async();					\
+	__mte_disable_tco_async();					\
 									\
 	if (unlikely(__gkn_err))					\
 		goto err_label;						\
@@ -388,8 +342,8 @@ do {									\
 #define put_user	__put_user
 
 /*
- * We must not call into the scheduler between __uaccess_enable_tco_async() and
- * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking
+ * We must not call into the scheduler between __mte_enable_tco_async() and
+ * __mte_disable_tco_async(). As `dst` and `src` may contain blocking
  * functions, we must evaluate these outside of the critical section.
  */
 #define __put_kernel_nofault(dst, src, type, err_label)			\
@@ -398,10 +352,10 @@ do {									\
 	__typeof__(src) __pkn_src = (src);				\
 	int __pkn_err = 0;						\
 									\
-	__uaccess_enable_tco_async();					\
+	__mte_enable_tco_async();					\
 	__raw_put_mem("str", *((type *)(__pkn_src)),			\
 		      (__force type *)(__pkn_dst), __pkn_err, K);	\
-	__uaccess_disable_tco_async();					\
+	__mte_disable_tco_async();					\
 									\
 	if (unlikely(__pkn_err))					\
 		goto err_label;						\
diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h
index 1c8e4f2490bf..f3b151ed0d7a 100644
--- a/arch/arm64/include/asm/word-at-a-time.h
+++ b/arch/arm64/include/asm/word-at-a-time.h
@@ -55,7 +55,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
 	unsigned long ret;
 
-	__uaccess_enable_tco_async();
+	__mte_enable_tco_async();
 
 	/* Load word from unaligned pointer addr */
 	asm(
@@ -65,7 +65,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr)
 	: "=&r" (ret)
 	: "r" (addr), "Q" (*(unsigned long *)addr));
 
-	__uaccess_disable_tco_async();
+	__mte_disable_tco_async();
 
 	return ret;
 }
diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index 0a048dc06a7d..fe5472a184a3 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -16,7 +16,7 @@ struct hyp_pool {
 	 * API at EL2.
 	 */
 	hyp_spinlock_t lock;
-	struct list_head free_area[MAX_ORDER];
+	struct list_head free_area[MAX_ORDER + 1];
 	phys_addr_t range_start;
 	phys_addr_t range_end;
 	unsigned short max_order;
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index 803ba3222e75..b1e392186a0f 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -110,7 +110,7 @@ static void __hyp_attach_page(struct hyp_pool *pool,
 	 * after coalescing, so make sure to mark it HYP_NO_ORDER proactively.
 	 */
 	p->order = HYP_NO_ORDER;
-	for (; (order + 1) < pool->max_order; order++) {
+	for (; (order + 1) <= pool->max_order; order++) {
 		buddy = __find_buddy_avail(pool, p, order);
 		if (!buddy)
 			break;
@@ -203,9 +203,9 @@ void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
 	hyp_spin_lock(&pool->lock);
 
 	/* Look for a high-enough-order page */
-	while (i < pool->max_order && list_empty(&pool->free_area[i]))
+	while (i <= pool->max_order && list_empty(&pool->free_area[i]))
 		i++;
-	if (i >= pool->max_order) {
+	if (i > pool->max_order) {
 		hyp_spin_unlock(&pool->lock);
 		return NULL;
 	}
@@ -228,8 +228,8 @@ int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages,
 	int i;
 
 	hyp_spin_lock_init(&pool->lock);
-	pool->max_order = min(MAX_ORDER, get_order((nr_pages + 1) << PAGE_SHIFT));
-	for (i = 0; i < pool->max_order; i++)
+	pool->max_order = min(MAX_ORDER, get_order(nr_pages << PAGE_SHIFT));
+	for (i = 0; i <= pool->max_order; i++)
 		INIT_LIST_HEAD(&pool->free_area[i]);
 	pool->range_start = phys;
 	pool->range_end = phys + (nr_pages << PAGE_SHIFT);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index f4cb0f85ccf4..9e0db5c387e3 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -535,6 +535,9 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 	unsigned long vm_flags;
 	unsigned int mm_flags = FAULT_FLAG_DEFAULT;
 	unsigned long addr = untagged_addr(far);
+#ifdef CONFIG_PER_VMA_LOCK
+	struct vm_area_struct *vma;
+#endif
 
 	if (kprobe_page_fault(regs, esr))
 		return 0;
@@ -585,6 +588,36 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 
+#ifdef CONFIG_PER_VMA_LOCK
+	if (!(mm_flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, addr);
+	if (!vma)
+		goto lock_mmap;
+
+	if (!(vma->vm_flags & vm_flags)) {
+		vma_end_read(vma);
+		goto lock_mmap;
+	}
+	fault = handle_mm_fault(vma, addr & PAGE_MASK,
+				mm_flags | FAULT_FLAG_VMA_LOCK, regs);
+	vma_end_read(vma);
+
+	if (!(fault & VM_FAULT_RETRY)) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		goto done;
+	}
+	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+
+	/* Quick path to respond to signals */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			goto no_context;
+		return 0;
+	}
+lock_mmap:
+#endif /* CONFIG_PER_VMA_LOCK */
 	/*
 	 * As per x86, we may deadlock here. However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -628,6 +661,9 @@ retry:
 	}
 	mmap_read_unlock(mm);
 
+#ifdef CONFIG_PER_VMA_LOCK
+done:
+#endif
 	/*
 	 * Handle the "normal" (no error) case first.
 	 */