1 files changed, 371 insertions, 185 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 56c02beb6041..81991102f785 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -29,40 +29,73 @@
 #include <linux/uaccess.h>
 #include <linux/mm_inline.h>
 #include <linux/pgtable.h>
+#include <linux/sched/sysctl.h>
+#include <linux/userfaultfd_k.h>
+#include <linux/memory-tiers.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
 
 #include "internal.h"
 
-static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, unsigned long end, pgprot_t newprot,
-		unsigned long cp_flags)
+bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t pte)
+{
+	struct page *page;
+
+	if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE)))
+		return false;
+
+	/* Don't touch entries that are not even readable. */
+	if (pte_protnone(pte))
+		return false;
+
+	/* Do we need write faults for softdirty tracking? */
+	if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte))
+		return false;
+
+	/* Do we need write faults for uffd-wp tracking? */
+	if (userfaultfd_pte_wp(vma, pte))
+		return false;
+
+	if (!(vma->vm_flags & VM_SHARED)) {
+		/*
+		 * Writable MAP_PRIVATE mapping: We can only special-case on
+		 * exclusive anonymous pages, because we know that our
+		 * write-fault handler similarly would map them writable without
+		 * any additional checks while holding the PT lock.
+		 */
+		page = vm_normal_page(vma, addr, pte);
+		return page && PageAnon(page) && PageAnonExclusive(page);
+	}
+
+	/*
+	 * Writable MAP_SHARED mapping: "clean" might indicate that the FS still
+	 * needs a real write-fault for writenotify
+	 * (see vma_wants_writenotify()). If "dirty", the assumption is that the
+	 * FS was already notified and we can simply mark the PTE writable
+	 * just like the write-fault handler would do.
+	 */
+	return pte_dirty(pte);
+}
+
+static long change_pte_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
-	unsigned long pages = 0;
+	long pages = 0;
 	int target_node = NUMA_NO_NODE;
-	bool dirty_accountable = cp_flags & MM_CP_DIRTY_ACCT;
 	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
 	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
 	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
-	/*
-	 * Can be called with only the mmap_lock for reading by
-	 * prot_numa so we must check the pmd isn't constantly
-	 * changing from under us from pmd_none to pmd_trans_huge
-	 * and/or the other way around.
-	 */
-	if (pmd_trans_unstable(pmd))
-		return 0;
-
-	/*
-	 * The pmd points to a regular pte so the pmd can't change
-	 * from under us even if the mmap_lock is only hold for
-	 * reading.
-	 */
+	tlb_change_page_size(tlb, PAGE_SIZE);
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	if (!pte)
+		return -EAGAIN;
 
 	/* Get target node for single threaded private VMAs */
 	if (prot_numa && !(vma->vm_flags & VM_SHARED) &&
@@ -72,29 +105,31 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	flush_tlb_batched_pending(vma->vm_mm);
 	arch_enter_lazy_mmu_mode();
 	do {
-		oldpte = *pte;
+		oldpte = ptep_get(pte);
 		if (pte_present(oldpte)) {
 			pte_t ptent;
-			bool preserve_write = prot_numa && pte_write(oldpte);
 
 			/*
 			 * Avoid trapping faults against the zero or KSM
 			 * pages. See similar comment in change_huge_pmd.
 			 */
 			if (prot_numa) {
-				struct page *page;
+				struct folio *folio;
+				int nid;
+				bool toptier;
 
 				/* Avoid TLB flush if possible */
 				if (pte_protnone(oldpte))
 					continue;
 
-				page = vm_normal_page(vma, addr, oldpte);
-				if (!page || PageKsm(page))
+				folio = vm_normal_folio(vma, addr, oldpte);
+				if (!folio || folio_is_zone_device(folio) ||
+				    folio_test_ksm(folio))
 					continue;
 
 				/* Also skip shared copy-on-write pages */
 				if (is_cow_mapping(vma->vm_flags) &&
-				    page_mapcount(page) != 1)
+				    folio_ref_count(folio) != 1)
 					continue;
 
 				/*
@@ -102,67 +137,116 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				 * it cannot move them all from MIGRATE_ASYNC
 				 * context.
 				 */
-				if (page_is_file_lru(page) && PageDirty(page))
+				if (folio_is_file_lru(folio) &&
+				    folio_test_dirty(folio))
 					continue;
 
 				/*
 				 * Don't mess with PTEs if page is already on the node
 				 * a single-threaded process is running on.
 				 */
-				if (target_node == page_to_nid(page))
+				nid = folio_nid(folio);
+				if (target_node == nid)
 					continue;
+				toptier = node_is_toptier(nid);
+
+				/*
+				 * Skip scanning top tier node if normal numa
+				 * balancing is disabled
+				 */
+				if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
+				    toptier)
+					continue;
+				if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
+				    !toptier)
+					folio_xchg_access_time(folio,
+						jiffies_to_msecs(jiffies));
 			}
 
 			oldpte = ptep_modify_prot_start(vma, addr, pte);
 			ptent = pte_modify(oldpte, newprot);
-			if (preserve_write)
-				ptent = pte_mk_savedwrite(ptent);
 
-			if (uffd_wp) {
-				ptent = pte_wrprotect(ptent);
+			if (uffd_wp)
 				ptent = pte_mkuffd_wp(ptent);
-			} else if (uffd_wp_resolve) {
-				/*
-				 * Leave the write bit to be handled
-				 * by PF interrupt handler, then
-				 * things like COW could be properly
-				 * handled.
-				 */
+			else if (uffd_wp_resolve)
 				ptent = pte_clear_uffd_wp(ptent);
-			}
 
-			/* Avoid taking write faults for known dirty pages */
-			if (dirty_accountable && pte_dirty(ptent) &&
-					(pte_soft_dirty(ptent) ||
-					 !(vma->vm_flags & VM_SOFTDIRTY))) {
-				ptent = pte_mkwrite(ptent);
-			}
+			/*
+			 * In some writable, shared mappings, we might want
+			 * to catch actual write access -- see
+			 * vma_wants_writenotify().
+			 *
+			 * In all writable, private mappings, we have to
+			 * properly handle COW.
+			 *
+			 * In both cases, we can sometimes still change PTEs
+			 * writable and avoid the write-fault handler, for
+			 * example, if a PTE is already dirty and no other
+			 * COW or special handling is required.
+			 */
+			if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) &&
+			    !pte_write(ptent) &&
+			    can_change_pte_writable(vma, addr, ptent))
+				ptent = pte_mkwrite(ptent, vma);
+
 			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
+			if (pte_needs_flush(oldpte, ptent))
+				tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
 			pages++;
 		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 			pte_t newpte;
 
-			if (is_write_migration_entry(entry)) {
+			if (is_writable_migration_entry(entry)) {
+				struct page *page = pfn_swap_entry_to_page(entry);
+
 				/*
 				 * A protection check is difficult so
 				 * just be safe and disable write
 				 */
-				make_migration_entry_read(&entry);
+				if (PageAnon(page))
+					entry = make_readable_exclusive_migration_entry(
+							     swp_offset(entry));
+				else
+					entry = make_readable_migration_entry(swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				if (pte_swp_soft_dirty(oldpte))
 					newpte = pte_swp_mksoft_dirty(newpte);
-				if (pte_swp_uffd_wp(oldpte))
-					newpte = pte_swp_mkuffd_wp(newpte);
-			} else if (is_write_device_private_entry(entry)) {
+			} else if (is_writable_device_private_entry(entry)) {
 				/*
 				 * We do not preserve soft-dirtiness. See
-				 * copy_one_pte() for explanation.
+				 * copy_nonpresent_pte() for explanation.
 				 */
-				make_device_private_entry_read(&entry);
+				entry = make_readable_device_private_entry(
+							swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				if (pte_swp_uffd_wp(oldpte))
 					newpte = pte_swp_mkuffd_wp(newpte);
+			} else if (is_writable_device_exclusive_entry(entry)) {
+				entry = make_readable_device_exclusive_entry(
+							swp_offset(entry));
+				newpte = swp_entry_to_pte(entry);
+				if (pte_swp_soft_dirty(oldpte))
+					newpte = pte_swp_mksoft_dirty(newpte);
+				if (pte_swp_uffd_wp(oldpte))
+					newpte = pte_swp_mkuffd_wp(newpte);
+			} else if (is_pte_marker_entry(entry)) {
+				/*
+				 * Ignore error swap entries unconditionally,
+				 * because any access should sigbus anyway.
+				 */
+				if (is_poisoned_swp_entry(entry))
+					continue;
+				/*
+				 * If this is uffd-wp pte marker and we'd like
+				 * to unprotect it, drop it; the next page
+				 * fault will trigger without uffd trapping.
+				 */
+				if (uffd_wp_resolve) {
+					pte_clear(vma->vm_mm, addr, pte);
+					pages++;
+				}
+				continue;
 			} else {
 				newpte = oldpte;
 			}
@@ -176,6 +260,28 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				set_pte_at(vma->vm_mm, addr, pte, newpte);
 				pages++;
 			}
+		} else {
+			/* It must be an none page, or what else?.. */
+			WARN_ON_ONCE(!pte_none(oldpte));
+
+			/*
+			 * Nobody plays with any none ptes besides
+			 * userfaultfd when applying the protections.
+			 */
+			if (likely(!uffd_wp))
+				continue;
+
+			if (userfaultfd_wp_use_markers(vma)) {
+				/*
+				 * For file-backed mem, we need to be able to
+				 * wr-protect a none pte, because even if the
+				 * pte is none, the page/swap cache could
+				 * exist.  Doing that by install a marker.
+				 */
+				set_pte_at(vma->vm_mm, addr, pte,
+					   make_pte_marker(PTE_MARKER_UFFD_WP));
+				pages++;
+			}
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
@@ -185,37 +291,74 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 }
 
 /*
- * Used when setting automatic NUMA hinting protection where it is
- * critical that a numa hinting PMD is not confused with a bad PMD.
+ * Return true if we want to split THPs into PTE mappings in change
+ * protection procedure, false otherwise.
  */
-static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
+static inline bool
+pgtable_split_needed(struct vm_area_struct *vma, unsigned long cp_flags)
 {
-	pmd_t pmdval = pmd_read_atomic(pmd);
-
-	/* See pmd_none_or_trans_huge_or_clear_bad for info on barrier */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	barrier();
-#endif
+	/*
+	 * pte markers only resides in pte level, if we need pte markers,
+	 * we need to split.  We cannot wr-protect shmem thp because file
+	 * thp is handled differently when split by erasing the pmd so far.
+	 */
+	return (cp_flags & MM_CP_UFFD_WP) && !vma_is_anonymous(vma);
+}
 
-	if (pmd_none(pmdval))
-		return 1;
-	if (pmd_trans_huge(pmdval))
-		return 0;
-	if (unlikely(pmd_bad(pmdval))) {
-		pmd_clear_bad(pmd);
-		return 1;
-	}
+/*
+ * Return true if we want to populate pgtables in change protection
+ * procedure, false otherwise
+ */
+static inline bool
+pgtable_populate_needed(struct vm_area_struct *vma, unsigned long cp_flags)
+{
+	/* If not within ioctl(UFFDIO_WRITEPROTECT), then don't bother */
+	if (!(cp_flags & MM_CP_UFFD_WP))
+		return false;
 
-	return 0;
+	/* Populate if the userfaultfd mode requires pte markers */
+	return userfaultfd_wp_use_markers(vma);
 }
 
-static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
-		pud_t *pud, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+/*
+ * Populate the pgtable underneath for whatever reason if requested.
+ * When {pte|pmd|...}_alloc() failed we treat it the same way as pgtable
+ * allocation failures during page faults by kicking OOM and returning
+ * error.
+ */
+#define  change_pmd_prepare(vma, pmd, cp_flags)				\
+	({								\
+		long err = 0;						\
+		if (unlikely(pgtable_populate_needed(vma, cp_flags))) {	\
+			if (pte_alloc(vma->vm_mm, pmd))			\
+				err = -ENOMEM;				\
+		}							\
+		err;							\
+	})
+
+/*
+ * This is the general pud/p4d/pgd version of change_pmd_prepare(). We need to
+ * have separate change_pmd_prepare() because pte_alloc() returns 0 on success,
+ * while {pmd|pud|p4d}_alloc() returns the valid pointer on success.
+ */
+#define  change_prepare(vma, high, low, addr, cp_flags)			\
+	  ({								\
+		long err = 0;						\
+		if (unlikely(pgtable_populate_needed(vma, cp_flags))) {	\
+			low##_t *p = low##_alloc(vma->vm_mm, high, addr); \
+			if (p == NULL)					\
+				err = -ENOMEM;				\
+		}							\
+		err;							\
+	})
+
+static inline long change_pmd_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pud_t *pud, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pmd_t *pmd;
 	unsigned long next;
-	unsigned long pages = 0;
+	long pages = 0;
 	unsigned long nr_huge_updates = 0;
 	struct mmu_notifier_range range;
 
@@ -223,39 +366,48 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 
 	pmd = pmd_offset(pud, addr);
 	do {
-		unsigned long this_pages;
-
+		long ret;
+		pmd_t _pmd;
+again:
 		next = pmd_addr_end(addr, end);
 
-		/*
-		 * Automatic NUMA balancing walks the tables with mmap_lock
-		 * held for read. It's possible a parallel update to occur
-		 * between pmd_trans_huge() and a pmd_none_or_clear_bad()
-		 * check leading to a false positive and clearing.
-		 * Hence, it's necessary to atomically read the PMD value
-		 * for all the checks.
-		 */
-		if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) &&
-		     pmd_none_or_clear_bad_unless_trans_huge(pmd))
+		ret = change_pmd_prepare(vma, pmd, cp_flags);
+		if (ret) {
+			pages = ret;
+			break;
+		}
+
+		if (pmd_none(*pmd))
 			goto next;
 
 		/* invoke the mmu notifier if the pmd is populated */
 		if (!range.start) {
 			mmu_notifier_range_init(&range,
 				MMU_NOTIFY_PROTECTION_VMA, 0,
-				vma, vma->vm_mm, addr, end);
+				vma->vm_mm, addr, end);
 			mmu_notifier_invalidate_range_start(&range);
 		}
 
-		if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
-			if (next - addr != HPAGE_PMD_SIZE) {
+		_pmd = pmdp_get_lockless(pmd);
+		if (is_swap_pmd(_pmd) || pmd_trans_huge(_pmd) || pmd_devmap(_pmd)) {
+			if ((next - addr != HPAGE_PMD_SIZE) ||
+			    pgtable_split_needed(vma, cp_flags)) {
 				__split_huge_pmd(vma, pmd, addr, false, NULL);
+				/*
+				 * For file-backed, the pmd could have been
+				 * cleared; make sure pmd populated if
+				 * necessary, then fall-through to pte level.
+				 */
+				ret = change_pmd_prepare(vma, pmd, cp_flags);
+				if (ret) {
+					pages = ret;
+					break;
+				}
 			} else {
-				int nr_ptes = change_huge_pmd(vma, pmd, addr,
-							      newprot, cp_flags);
-
-				if (nr_ptes) {
-					if (nr_ptes == HPAGE_PMD_NR) {
+				ret = change_huge_pmd(tlb, vma, pmd,
+						addr, newprot, cp_flags);
+				if (ret) {
+					if (ret == HPAGE_PMD_NR) {
 						pages += HPAGE_PMD_NR;
 						nr_huge_updates++;
 					}
@@ -266,9 +418,12 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			}
 			/* fall through, the trans huge pmd just split */
 		}
-		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
-					      cp_flags);
-		pages += this_pages;
+
+		ret = change_pte_range(tlb, vma, pmd, addr, next, newprot,
+				       cp_flags);
+		if (ret < 0)
+			goto again;
+		pages += ret;
 next:
 		cond_resched();
 	} while (pmd++, addr = next, addr != end);
@@ -281,88 +436,108 @@ next:
 	return pages;
 }
 
-static inline unsigned long change_pud_range(struct vm_area_struct *vma,
-		p4d_t *p4d, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline long change_pud_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	pud_t *pud;
 	unsigned long next;
-	unsigned long pages = 0;
+	long pages = 0, ret;
 
 	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
+		ret = change_prepare(vma, pud, pmd, addr, cp_flags);
+		if (ret)
+			return ret;
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		pages += change_pmd_range(vma, pud, addr, next, newprot,
+		pages += change_pmd_range(tlb, vma, pud, addr, next, newprot,
 					  cp_flags);
 	} while (pud++, addr = next, addr != end);
 
 	return pages;
 }
 
-static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
-		pgd_t *pgd, unsigned long addr, unsigned long end,
-		pgprot_t newprot, unsigned long cp_flags)
+static inline long change_p4d_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	p4d_t *p4d;
 	unsigned long next;
-	unsigned long pages = 0;
+	long pages = 0, ret;
 
 	p4d = p4d_offset(pgd, addr);
 	do {
 		next = p4d_addr_end(addr, end);
+		ret = change_prepare(vma, p4d, pud, addr, cp_flags);
+		if (ret)
+			return ret;
 		if (p4d_none_or_clear_bad(p4d))
 			continue;
-		pages += change_pud_range(vma, p4d, addr, next, newprot,
+		pages += change_pud_range(tlb, vma, p4d, addr, next, newprot,
 					  cp_flags);
 	} while (p4d++, addr = next, addr != end);
 
 	return pages;
 }
 
-static unsigned long change_protection_range(struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end, pgprot_t newprot,
-		unsigned long cp_flags)
+static long change_protection_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long start = addr;
-	unsigned long pages = 0;
+	long pages = 0, ret;
 
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
-	flush_cache_range(vma, addr, end);
-	inc_tlb_flush_pending(mm);
+	tlb_start_vma(tlb, vma);
 	do {
 		next = pgd_addr_end(addr, end);
+		ret = change_prepare(vma, pgd, p4d, addr, cp_flags);
+		if (ret) {
+			pages = ret;
+			break;
+		}
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		pages += change_p4d_range(vma, pgd, addr, next, newprot,
+		pages += change_p4d_range(tlb, vma, pgd, addr, next, newprot,
 					  cp_flags);
 	} while (pgd++, addr = next, addr != end);
 
-	/* Only flush the TLB if we actually modified any entries: */
-	if (pages)
-		flush_tlb_range(vma, start, end);
-	dec_tlb_flush_pending(mm);
+	tlb_end_vma(tlb, vma);
 
 	return pages;
 }
 
-unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
-		       unsigned long end, pgprot_t newprot,
-		       unsigned long cp_flags)
+long change_protection(struct mmu_gather *tlb,
+		       struct vm_area_struct *vma, unsigned long start,
+		       unsigned long end, unsigned long cp_flags)
 {
-	unsigned long pages;
+	pgprot_t newprot = vma->vm_page_prot;
+	long pages;
 
 	BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL);
 
+#ifdef CONFIG_NUMA_BALANCING
+	/*
+	 * Ordinary protection updates (mprotect, uffd-wp, softdirty tracking)
+	 * are expected to reflect their requirements via VMA flags such that
+	 * vma_set_page_prot() will adjust vma->vm_page_prot accordingly.
+	 */
+	if (cp_flags & MM_CP_PROT_NUMA)
+		newprot = PAGE_NONE;
+#else
+	WARN_ON_ONCE(cp_flags & MM_CP_PROT_NUMA);
+#endif
+
 	if (is_vm_hugetlb_page(vma))
-		pages = hugetlb_change_protection(vma, start, end, newprot);
+		pages = hugetlb_change_protection(vma, start, end, newprot,
+						  cp_flags);
 	else
-		pages = change_protection_range(vma, start, end, newprot,
+		pages = change_protection_range(tlb, vma, start, end, newprot,
 						cp_flags);
 
 	return pages;
@@ -371,7 +546,8 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 static int prot_none_pte_entry(pte_t *pte, unsigned long addr,
 			       unsigned long next, struct mm_walk *walk)
 {
-	return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+	return pfn_modify_allowed(pte_pfn(ptep_get(pte)),
+				  *(pgprot_t *)(walk->private)) ?
 		0 : -EACCES;
 }
 
@@ -379,7 +555,8 @@ static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask,
 				   unsigned long addr, unsigned long next,
 				   struct mm_walk *walk)
 {
-	return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+	return pfn_modify_allowed(pte_pfn(ptep_get(pte)),
+				  *(pgprot_t *)(walk->private)) ?
 		0 : -EACCES;
 }
 
@@ -393,19 +570,20 @@ static const struct mm_walk_ops prot_none_walk_ops = {
 	.pte_entry		= prot_none_pte_entry,
 	.hugetlb_entry		= prot_none_hugetlb_entry,
 	.test_walk		= prot_none_test,
+	.walk_lock		= PGWALK_WRLOCK,
 };
 
 int
-mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
-	unsigned long start, unsigned long end, unsigned long newflags)
+mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb,
+	       struct vm_area_struct *vma, struct vm_area_struct **pprev,
+	       unsigned long start, unsigned long end, unsigned long newflags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long oldflags = vma->vm_flags;
 	long nrpages = (end - start) >> PAGE_SHIFT;
+	unsigned int mm_cp_flags = 0;
 	unsigned long charged = 0;
-	pgoff_t pgoff;
 	int error;
-	int dirty_accountable = 0;
 
 	if (newflags == oldflags) {
 		*pprev = vma;
@@ -431,8 +609,11 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	/*
 	 * If we make a private mapping writable we increase our commit;
 	 * but (without finer accounting) cannot reduce our commit if we
-	 * make it unwritable again. hugetlb mapping were accounted for
-	 * even if read-only so there is no need to account for them here
+	 * make it unwritable again except in the anonymous case where no
+	 * anon_vma has yet to be assigned.
+	 *
+	 * hugetlb mapping were accounted for even if read-only so there is
+	 * no need to account for them here.
 	 */
 	if (newflags & VM_WRITE) {
 		/* Check space limits when area turns into data. */
@@ -446,46 +627,33 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 				return -ENOMEM;
 			newflags |= VM_ACCOUNT;
 		}
+	} else if ((oldflags & VM_ACCOUNT) && vma_is_anonymous(vma) &&
+		   !vma->anon_vma) {
+		newflags &= ~VM_ACCOUNT;
 	}
 
-	/*
-	 * First try to merge with previous and/or next vma.
-	 */
-	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
-	*pprev = vma_merge(mm, *pprev, start, end, newflags,
-			   vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
-			   vma->vm_userfaultfd_ctx);
-	if (*pprev) {
-		vma = *pprev;
-		VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY);
-		goto success;
+	vma = vma_modify_flags(vmi, *pprev, vma, start, end, newflags);
+	if (IS_ERR(vma)) {
+		error = PTR_ERR(vma);
+		goto fail;
 	}
 
 	*pprev = vma;
 
-	if (start != vma->vm_start) {
-		error = split_vma(mm, vma, start, 1);
-		if (error)
-			goto fail;
-	}
-
-	if (end != vma->vm_end) {
-		error = split_vma(mm, vma, end, 0);
-		if (error)
-			goto fail;
-	}
-
-success:
 	/*
 	 * vm_flags and vm_page_prot are protected by the mmap_lock
 	 * held in write mode.
 	 */
-	vma->vm_flags = newflags;
-	dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot);
+	vma_start_write(vma);
+	vm_flags_reset(vma, newflags);
+	if (vma_wants_manual_pte_write_upgrade(vma))
+		mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE;
 	vma_set_page_prot(vma);
 
-	change_protection(vma, start, end, vma->vm_page_prot,
-			  dirty_accountable ? MM_CP_DIRTY_ACCT : 0);
+	change_protection(tlb, vma, start, end, mm_cp_flags);
+
+	if ((oldflags & VM_ACCOUNT) && !(newflags & VM_ACCOUNT))
+		vm_unacct_memory(nrpages);
 
 	/*
 	 * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major
@@ -514,10 +682,12 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 {
 	unsigned long nstart, end, tmp, reqprot;
 	struct vm_area_struct *vma, *prev;
-	int error = -EINVAL;
+	int error;
 	const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
 	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
 				(prot & PROT_READ);
+	struct mmu_gather tlb;
+	struct vma_iterator vmi;
 
 	start = untagged_addr(start);
 
@@ -549,11 +719,12 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	if ((pkey != -1) && !mm_pkey_is_allocated(current->mm, pkey))
 		goto out;
 
-	vma = find_vma(current->mm, start);
+	vma_iter_init(&vmi, current->mm, start);
+	vma = vma_find(&vmi, end);
 	error = -ENOMEM;
 	if (!vma)
 		goto out;
-	prev = vma->vm_prev;
+
 	if (unlikely(grows & PROT_GROWSDOWN)) {
 		if (vma->vm_start >= end)
 			goto out;
@@ -571,15 +742,23 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 				goto out;
 		}
 	}
+
+	prev = vma_prev(&vmi);
 	if (start > vma->vm_start)
 		prev = vma;
 
-	for (nstart = start ; ; ) {
+	tlb_gather_mmu(&tlb, current->mm);
+	nstart = start;
+	tmp = vma->vm_start;
+	for_each_vma_range(vmi, vma, end) {
 		unsigned long mask_off_old_flags;
 		unsigned long newflags;
 		int new_vma_pkey;
 
-		/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
+		if (vma->vm_start != tmp) {
+			error = -ENOMEM;
+			break;
+		}
 
 		/* Does the application expect PROT_READ to imply PROT_EXEC */
 		if (rier && (vma->vm_flags & VM_MAYEXEC))
@@ -590,8 +769,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		 * If a permission is not passed to mprotect(), it must be
 		 * cleared from the VMA.
 		 */
-		mask_off_old_flags = VM_READ | VM_WRITE | VM_EXEC |
-					VM_FLAGS_CLEAR;
+		mask_off_old_flags = VM_ACCESS_FLAGS | VM_FLAGS_CLEAR;
 
 		new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey);
 		newflags = calc_vm_prot_bits(prot, new_vma_pkey);
@@ -600,39 +778,47 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */
 		if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) {
 			error = -EACCES;
-			goto out;
+			break;
+		}
+
+		if (map_deny_write_exec(vma, newflags)) {
+			error = -EACCES;
+			break;
 		}
 
 		/* Allow architectures to sanity-check the new flags */
 		if (!arch_validate_flags(newflags)) {
 			error = -EINVAL;
-			goto out;
+			break;
 		}
 
 		error = security_file_mprotect(vma, reqprot, prot);
 		if (error)
-			goto out;
+			break;
 
 		tmp = vma->vm_end;
 		if (tmp > end)
 			tmp = end;
-		error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
-		if (error)
-			goto out;
-		nstart = tmp;
 
-		if (nstart < prev->vm_end)
-			nstart = prev->vm_end;
-		if (nstart >= end)
-			goto out;
-
-		vma = prev->vm_next;
-		if (!vma || vma->vm_start != nstart) {
-			error = -ENOMEM;
-			goto out;
+		if (vma->vm_ops && vma->vm_ops->mprotect) {
+			error = vma->vm_ops->mprotect(vma, nstart, tmp, newflags);
+			if (error)
+				break;
 		}
+
+		error = mprotect_fixup(&vmi, &tlb, vma, &prev, nstart, tmp, newflags);
+		if (error)
+			break;
+
+		tmp = vma_iter_end(&vmi);
+		nstart = tmp;
 		prot = reqprot;
 	}
+	tlb_finish_mmu(&tlb);
+
+	if (!error && tmp < end)
+		error = -ENOMEM;
+
 out:
 	mmap_write_unlock(current->mm);
 	return error;
@@ -691,7 +877,7 @@ SYSCALL_DEFINE1(pkey_free, int, pkey)
 	mmap_write_unlock(current->mm);
 
 	/*
-	 * We could provie warnings or errors if any VMA still
+	 * We could provide warnings or errors if any VMA still
 	 * has the pkey set here.
 	 */
 	return ret;