1 files changed, 787 insertions, 199 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 94722a4d6b43..283889e4f1ce 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  mm/mprotect.c
  *
@@ -8,7 +9,7 @@
  *  (C) Copyright 2002 Red Hat Inc, All Rights Reserved
  */
 
-#include <linux/mm.h>
+#include <linux/pagewalk.h>
 #include <linux/hugetlb.h>
 #include <linux/shm.h>
 #include <linux/mman.h>
@@ -23,227 +24,687 @@
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
 #include <linux/perf_event.h>
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
+#include <linux/pkeys.h>
+#include <linux/ksm.h>
+#include <linux/uaccess.h>
+#include <linux/mm_inline.h>
+#include <linux/pgtable.h>
+#include <linux/userfaultfd_k.h>
+#include <uapi/linux/mman.h>
 #include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
 
-#ifndef pgprot_modify
-static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+#include "internal.h"
+
+static bool maybe_change_pte_writable(struct vm_area_struct *vma, pte_t pte)
 {
-	return newprot;
+	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 (pte_needs_soft_dirty_wp(vma, pte))
+		return false;
+
+	/* Do we need write faults for uffd-wp tracking? */
+	if (userfaultfd_pte_wp(vma, pte))
+		return false;
+
+	return true;
 }
-#endif
 
-static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa, bool *ret_all_same_node)
+static bool can_change_private_pte_writable(struct vm_area_struct *vma,
+					    unsigned long addr, pte_t pte)
+{
+	struct page *page;
+
+	if (!maybe_change_pte_writable(vma, pte))
+		return false;
+
+	/*
+	 * 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);
+}
+
+static bool can_change_shared_pte_writable(struct vm_area_struct *vma,
+					   pte_t pte)
+{
+	if (!maybe_change_pte_writable(vma, pte))
+		return false;
+
+	VM_WARN_ON_ONCE(is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte));
+
+	/*
+	 * 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);
+}
+
+bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t pte)
+{
+	if (!(vma->vm_flags & VM_SHARED))
+		return can_change_private_pte_writable(vma, addr, pte);
+
+	return can_change_shared_pte_writable(vma, pte);
+}
+
+static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep,
+				    pte_t pte, int max_nr_ptes, fpb_t flags)
+{
+	/* No underlying folio, so cannot batch */
+	if (!folio)
+		return 1;
+
+	if (!folio_test_large(folio))
+		return 1;
+
+	return folio_pte_batch_flags(folio, NULL, ptep, &pte, max_nr_ptes, flags);
+}
+
+/* Set nr_ptes number of ptes, starting from idx */
+static void prot_commit_flush_ptes(struct vm_area_struct *vma, unsigned long addr,
+		pte_t *ptep, pte_t oldpte, pte_t ptent, int nr_ptes,
+		int idx, bool set_write, struct mmu_gather *tlb)
+{
+	/*
+	 * Advance the position in the batch by idx; note that if idx > 0,
+	 * then the nr_ptes passed here is <= batch size - idx.
+	 */
+	addr += idx * PAGE_SIZE;
+	ptep += idx;
+	oldpte = pte_advance_pfn(oldpte, idx);
+	ptent = pte_advance_pfn(ptent, idx);
+
+	if (set_write)
+		ptent = pte_mkwrite(ptent, vma);
+
+	modify_prot_commit_ptes(vma, addr, ptep, oldpte, ptent, nr_ptes);
+	if (pte_needs_flush(oldpte, ptent))
+		tlb_flush_pte_range(tlb, addr, nr_ptes * PAGE_SIZE);
+}
+
+/*
+ * Get max length of consecutive ptes pointing to PageAnonExclusive() pages or
+ * !PageAnonExclusive() pages, starting from start_idx. Caller must enforce
+ * that the ptes point to consecutive pages of the same anon large folio.
+ */
+static int page_anon_exclusive_sub_batch(int start_idx, int max_len,
+		struct page *first_page, bool expected_anon_exclusive)
+{
+	int idx;
+
+	for (idx = start_idx + 1; idx < start_idx + max_len; ++idx) {
+		if (expected_anon_exclusive != PageAnonExclusive(first_page + idx))
+			break;
+	}
+	return idx - start_idx;
+}
+
+/*
+ * This function is a result of trying our very best to retain the
+ * "avoid the write-fault handler" optimization. In can_change_pte_writable(),
+ * if the vma is a private vma, and we cannot determine whether to change
+ * the pte to writable just from the vma and the pte, we then need to look
+ * at the actual page pointed to by the pte. Unfortunately, if we have a
+ * batch of ptes pointing to consecutive pages of the same anon large folio,
+ * the anon-exclusivity (or the negation) of the first page does not guarantee
+ * the anon-exclusivity (or the negation) of the other pages corresponding to
+ * the pte batch; hence in this case it is incorrect to decide to change or
+ * not change the ptes to writable just by using information from the first
+ * pte of the batch. Therefore, we must individually check all pages and
+ * retrieve sub-batches.
+ */
+static void commit_anon_folio_batch(struct vm_area_struct *vma,
+		struct folio *folio, struct page *first_page, unsigned long addr, pte_t *ptep,
+		pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
+{
+	bool expected_anon_exclusive;
+	int sub_batch_idx = 0;
+	int len;
+
+	while (nr_ptes) {
+		expected_anon_exclusive = PageAnonExclusive(first_page + sub_batch_idx);
+		len = page_anon_exclusive_sub_batch(sub_batch_idx, nr_ptes,
+					first_page, expected_anon_exclusive);
+		prot_commit_flush_ptes(vma, addr, ptep, oldpte, ptent, len,
+				       sub_batch_idx, expected_anon_exclusive, tlb);
+		sub_batch_idx += len;
+		nr_ptes -= len;
+	}
+}
+
+static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma,
+		struct folio *folio, struct page *page, unsigned long addr, pte_t *ptep,
+		pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
+{
+	bool set_write;
+
+	if (vma->vm_flags & VM_SHARED) {
+		set_write = can_change_shared_pte_writable(vma, ptent);
+		prot_commit_flush_ptes(vma, addr, ptep, oldpte, ptent, nr_ptes,
+				       /* idx = */ 0, set_write, tlb);
+		return;
+	}
+
+	set_write = maybe_change_pte_writable(vma, ptent) &&
+		    (folio && folio_test_anon(folio));
+	if (!set_write) {
+		prot_commit_flush_ptes(vma, addr, ptep, oldpte, ptent, nr_ptes,
+				       /* idx = */ 0, set_write, tlb);
+		return;
+	}
+	commit_anon_folio_batch(vma, folio, page, addr, ptep, oldpte, ptent, nr_ptes, tlb);
+}
+
+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)
 {
-	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
-	unsigned long pages = 0;
-	bool all_same_node = true;
-	int last_nid = -1;
-
-	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	long pages = 0;
+	bool is_private_single_threaded;
+	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;
+	int nr_ptes;
+
+	tlb_change_page_size(tlb, PAGE_SIZE);
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	if (!pte)
+		return -EAGAIN;
+
+	if (prot_numa)
+		is_private_single_threaded = vma_is_single_threaded_private(vma);
+
+	flush_tlb_batched_pending(vma->vm_mm);
 	arch_enter_lazy_mmu_mode();
 	do {
-		oldpte = *pte;
+		nr_ptes = 1;
+		oldpte = ptep_get(pte);
 		if (pte_present(oldpte)) {
+			const fpb_t flags = FPB_RESPECT_SOFT_DIRTY | FPB_RESPECT_WRITE;
+			int max_nr_ptes = (end - addr) >> PAGE_SHIFT;
+			struct folio *folio = NULL;
+			struct page *page;
 			pte_t ptent;
-			bool updated = false;
 
-			ptent = ptep_modify_prot_start(mm, addr, pte);
-			if (!prot_numa) {
-				ptent = pte_modify(ptent, newprot);
-				updated = true;
-			} else {
-				struct page *page;
-
-				page = vm_normal_page(vma, addr, oldpte);
-				if (page) {
-					int this_nid = page_to_nid(page);
-					if (last_nid == -1)
-						last_nid = this_nid;
-					if (last_nid != this_nid)
-						all_same_node = false;
-
-					/* only check non-shared pages */
-					if (!pte_numa(oldpte) &&
-					    page_mapcount(page) == 1) {
-						ptent = pte_mknuma(ptent);
-						updated = true;
-					}
-				}
-			}
+			/* Already in the desired state. */
+			if (prot_numa && pte_protnone(oldpte))
+				continue;
+
+			page = vm_normal_page(vma, addr, oldpte);
+			if (page)
+				folio = page_folio(page);
 
 			/*
-			 * Avoid taking write faults for pages we know to be
-			 * dirty.
+			 * Avoid trapping faults against the zero or KSM
+			 * pages. See similar comment in change_huge_pmd.
 			 */
-			if (dirty_accountable && pte_dirty(ptent)) {
-				ptent = pte_mkwrite(ptent);
-				updated = true;
+			if (prot_numa &&
+			    !folio_can_map_prot_numa(folio, vma,
+						is_private_single_threaded)) {
+
+				/* determine batch to skip */
+				nr_ptes = mprotect_folio_pte_batch(folio,
+					  pte, oldpte, max_nr_ptes, /* flags = */ 0);
+				continue;
 			}
 
-			if (updated)
+			nr_ptes = mprotect_folio_pte_batch(folio, pte, oldpte, max_nr_ptes, flags);
+
+			oldpte = modify_prot_start_ptes(vma, addr, pte, nr_ptes);
+			ptent = pte_modify(oldpte, newprot);
+
+			if (uffd_wp)
+				ptent = pte_mkuffd_wp(ptent);
+			else if (uffd_wp_resolve)
+				ptent = pte_clear_uffd_wp(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))
+				set_write_prot_commit_flush_ptes(vma, folio, page,
+				addr, pte, oldpte, ptent, nr_ptes, tlb);
+			else
+				prot_commit_flush_ptes(vma, addr, pte, oldpte, ptent,
+					nr_ptes, /* idx = */ 0, /* set_write = */ false, tlb);
+			pages += nr_ptes;
+		} else if (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++;
-			ptep_modify_prot_commit(mm, addr, pte, ptent);
-		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
-			swp_entry_t entry = pte_to_swp_entry(oldpte);
+			}
+		} else  {
+			softleaf_t entry = softleaf_from_pte(oldpte);
+			pte_t newpte;
+
+			if (softleaf_is_migration_write(entry)) {
+				const struct folio *folio = softleaf_to_folio(entry);
 
-			if (is_write_migration_entry(entry)) {
 				/*
 				 * A protection check is difficult so
 				 * just be safe and disable write
 				 */
-				make_migration_entry_read(&entry);
-				set_pte_at(mm, addr, pte,
-					swp_entry_to_pte(entry));
+				if (folio_test_anon(folio))
+					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);
+			} else if (softleaf_is_device_private_write(entry)) {
+				/*
+				 * We do not preserve soft-dirtiness. See
+				 * copy_nonpresent_pte() for explanation.
+				 */
+				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 (softleaf_is_marker(entry)) {
+				/*
+				 * Ignore error swap entries unconditionally,
+				 * because any access should sigbus/sigsegv
+				 * anyway.
+				 */
+				if (softleaf_is_poison_marker(entry) ||
+				    softleaf_is_guard_marker(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;
+			}
+
+			if (uffd_wp)
+				newpte = pte_swp_mkuffd_wp(newpte);
+			else if (uffd_wp_resolve)
+				newpte = pte_swp_clear_uffd_wp(newpte);
+
+			if (!pte_same(oldpte, newpte)) {
+				set_pte_at(vma->vm_mm, addr, pte, newpte);
+				pages++;
 			}
-			pages++;
 		}
-	} while (pte++, addr += PAGE_SIZE, addr != end);
+	} while (pte += nr_ptes, addr += nr_ptes * PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 
-	*ret_all_same_node = all_same_node;
 	return pages;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-				       pmd_t *pmd)
+/*
+ * Return true if we want to split THPs into PTE mappings in change
+ * protection procedure, false otherwise.
+ */
+static inline bool
+pgtable_split_needed(struct vm_area_struct *vma, unsigned long cp_flags)
 {
-	spin_lock(&mm->page_table_lock);
-	set_pmd_at(mm, addr & PMD_MASK, pmd, pmd_mknuma(*pmd));
-	spin_unlock(&mm->page_table_lock);
+	/*
+	 * pte markers only resides in pte level, if we need pte markers,
+	 * we need to split.  For example, we cannot wr-protect a file thp
+	 * (e.g. 2M shmem) 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);
 }
-#else
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-				       pmd_t *pmd)
+
+/*
+ * 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)
 {
-	BUG();
+	/* If not within ioctl(UFFDIO_WRITEPROTECT), then don't bother */
+	if (!(cp_flags & MM_CP_UFFD_WP))
+		return false;
+
+	/* Populate if the userfaultfd mode requires pte markers */
+	return userfaultfd_wp_use_markers(vma);
 }
-#endif /* CONFIG_NUMA_BALANCING */
 
-static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
-		pud_t *pud, unsigned long addr, unsigned long end,
-		pgprot_t newprot, int dirty_accountable, int prot_numa)
+/*
+ * 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;
-	bool all_same_node;
+	long pages = 0;
+	unsigned long nr_huge_updates = 0;
 
 	pmd = pmd_offset(pud, addr);
 	do {
+		long ret;
+		pmd_t _pmd;
+again:
 		next = pmd_addr_end(addr, end);
-		if (pmd_trans_huge(*pmd)) {
-			if (next - addr != HPAGE_PMD_SIZE)
-				split_huge_page_pmd(vma, addr, pmd);
-			else if (change_huge_pmd(vma, pmd, addr, newprot,
-						 prot_numa)) {
-				pages += HPAGE_PMD_NR;
-				continue;
+
+		ret = change_pmd_prepare(vma, pmd, cp_flags);
+		if (ret) {
+			pages = ret;
+			break;
+		}
+
+		if (pmd_none(*pmd))
+			goto next;
+
+		_pmd = pmdp_get_lockless(pmd);
+		if (pmd_is_huge(_pmd)) {
+			if ((next - addr != HPAGE_PMD_SIZE) ||
+			    pgtable_split_needed(vma, cp_flags)) {
+				__split_huge_pmd(vma, pmd, addr, false);
+				/*
+				 * 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 {
+				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++;
+					}
+
+					/* huge pmd was handled */
+					goto next;
+				}
 			}
-			/* fall through */
+			/* fall through, the trans huge pmd just split */
 		}
-		if (pmd_none_or_clear_bad(pmd))
-			continue;
-		pages += change_pte_range(vma, pmd, addr, next, newprot,
-				 dirty_accountable, prot_numa, &all_same_node);
 
-		/*
-		 * If we are changing protections for NUMA hinting faults then
-		 * set pmd_numa if the examined pages were all on the same
-		 * node. This allows a regular PMD to be handled as one fault
-		 * and effectively batches the taking of the PTL
-		 */
-		if (prot_numa && all_same_node)
-			change_pmd_protnuma(vma->vm_mm, addr, pmd);
+		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);
 
+	if (nr_huge_updates)
+		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
 	return pages;
 }
 
-static inline unsigned long change_pud_range(struct vm_area_struct *vma,
-		pgd_t *pgd, unsigned long addr, unsigned long end,
-		pgprot_t newprot, int dirty_accountable, int prot_numa)
+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;
+	struct mmu_notifier_range range;
+	pud_t *pudp, pud;
 	unsigned long next;
-	unsigned long pages = 0;
+	long pages = 0, ret;
+
+	range.start = 0;
 
-	pud = pud_offset(pgd, addr);
+	pudp = pud_offset(p4d, addr);
 	do {
+again:
 		next = pud_addr_end(addr, end);
-		if (pud_none_or_clear_bad(pud))
+		ret = change_prepare(vma, pudp, pmd, addr, cp_flags);
+		if (ret) {
+			pages = ret;
+			break;
+		}
+
+		pud = pudp_get(pudp);
+		if (pud_none(pud))
+			continue;
+
+		if (!range.start) {
+			mmu_notifier_range_init(&range,
+						MMU_NOTIFY_PROTECTION_VMA, 0,
+						vma->vm_mm, addr, end);
+			mmu_notifier_invalidate_range_start(&range);
+		}
+
+		if (pud_leaf(pud)) {
+			if ((next - addr != PUD_SIZE) ||
+			    pgtable_split_needed(vma, cp_flags)) {
+				__split_huge_pud(vma, pudp, addr);
+				goto again;
+			} else {
+				ret = change_huge_pud(tlb, vma, pudp,
+						      addr, newprot, cp_flags);
+				if (ret == 0)
+					goto again;
+				/* huge pud was handled */
+				if (ret == HPAGE_PUD_NR)
+					pages += HPAGE_PUD_NR;
+				continue;
+			}
+		}
+
+		pages += change_pmd_range(tlb, vma, pudp, addr, next, newprot,
+					  cp_flags);
+	} while (pudp++, addr = next, addr != end);
+
+	if (range.start)
+		mmu_notifier_invalidate_range_end(&range);
+
+	return pages;
+}
+
+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;
+	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_pmd_range(vma, pud, addr, next, newprot,
-				 dirty_accountable, prot_numa);
-	} while (pud++, addr = next, addr != end);
+		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,
-		int dirty_accountable, int prot_numa)
+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);
+	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_pud_range(vma, pgd, addr, next, newprot,
-				 dirty_accountable, prot_numa);
+		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);
+	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,
-		       int dirty_accountable, int prot_numa)
+long change_protection(struct mmu_gather *tlb,
+		       struct vm_area_struct *vma, unsigned long start,
+		       unsigned long end, unsigned long cp_flags)
 {
-	struct mm_struct *mm = vma->vm_mm;
-	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
 
-	mmu_notifier_invalidate_range_start(mm, start, end);
 	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, dirty_accountable, prot_numa);
-	mmu_notifier_invalidate_range_end(mm, start, end);
+		pages = change_protection_range(tlb, vma, start, end, newprot,
+						cp_flags);
 
 	return pages;
 }
 
+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(ptep_get(pte)),
+				  *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+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(ptep_get(pte)),
+				  *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+static int prot_none_test(unsigned long addr, unsigned long next,
+			  struct mm_walk *walk)
+{
+	return 0;
+}
+
+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, vm_flags_t newflags)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long oldflags = vma->vm_flags;
+	vm_flags_t oldflags = READ_ONCE(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 (vma_is_sealed(vma))
+		return -EPERM;
 
 	if (newflags == oldflags) {
 		*pprev = vma;
@@ -251,12 +712,35 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	}
 
 	/*
+	 * Do PROT_NONE PFN permission checks here when we can still
+	 * bail out without undoing a lot of state. This is a rather
+	 * uncommon case, so doesn't need to be very optimized.
+	 */
+	if (arch_has_pfn_modify_check() &&
+	    (oldflags & (VM_PFNMAP|VM_MIXEDMAP)) &&
+	    (newflags & VM_ACCESS_FLAGS) == 0) {
+		pgprot_t new_pgprot = vm_get_page_prot(newflags);
+
+		error = walk_page_range(current->mm, start, end,
+				&prot_none_walk_ops, &new_pgprot);
+		if (error)
+			return error;
+	}
+
+	/*
 	 * 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. */
+		if (!may_expand_vm(mm, newflags, nrpages) &&
+				may_expand_vm(mm, oldflags, nrpages))
+			return -ENOMEM;
 		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
 						VM_SHARED|VM_NORESERVE))) {
 			charged = nrpages;
@@ -264,52 +748,45 @@ 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));
-	if (*pprev) {
-		vma = *pprev;
-		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_sem
+	 * vm_flags and vm_page_prot are protected by the mmap_lock
 	 * held in write mode.
 	 */
-	vma->vm_flags = newflags;
-	vma->vm_page_prot = pgprot_modify(vma->vm_page_prot,
-					  vm_get_page_prot(newflags));
+	vma_start_write(vma);
+	vm_flags_reset_once(vma, newflags);
+	if (vma_wants_manual_pte_write_upgrade(vma))
+		mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE;
+	vma_set_page_prot(vma);
 
-	if (vma_wants_writenotify(vma)) {
-		vma->vm_page_prot = vm_get_page_prot(newflags & ~VM_SHARED);
-		dirty_accountable = 1;
-	}
+	change_protection(tlb, vma, start, end, mm_cp_flags);
 
-	change_protection(vma, start, end, vma->vm_page_prot,
-			  dirty_accountable, 0);
+	if ((oldflags & VM_ACCOUNT) && !(newflags & VM_ACCOUNT))
+		vm_unacct_memory(nrpages);
 
-	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
-	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
+	/*
+	 * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major
+	 * fault on access.
+	 */
+	if ((oldflags & (VM_WRITE | VM_SHARED | VM_LOCKED)) == VM_LOCKED &&
+			(newflags & VM_WRITE)) {
+		populate_vma_page_range(vma, start, end, NULL);
+	}
+
+	vm_stat_account(mm, oldflags, -nrpages);
+	vm_stat_account(mm, newflags, nrpages);
 	perf_event_mmap(vma);
 	return 0;
 
@@ -318,13 +795,23 @@ fail:
 	return error;
 }
 
-SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
-		unsigned long, prot)
+/*
+ * pkey==-1 when doing a legacy mprotect()
+ */
+static int do_mprotect_pkey(unsigned long start, size_t len,
+		unsigned long prot, int pkey)
 {
-	unsigned long vm_flags, nstart, end, tmp, reqprot;
+	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);
+
 	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
 	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
 		return -EINVAL;
@@ -337,25 +824,28 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 	end = start + len;
 	if (end <= start)
 		return -ENOMEM;
-	if (!arch_validate_prot(prot))
+	if (!arch_validate_prot(prot, start))
 		return -EINVAL;
 
 	reqprot = prot;
-	/*
-	 * Does the application expect PROT_READ to imply PROT_EXEC:
-	 */
-	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
-		prot |= PROT_EXEC;
 
-	vm_flags = calc_vm_prot_bits(prot);
+	if (mmap_write_lock_killable(current->mm))
+		return -EINTR;
 
-	down_write(&current->mm->mmap_sem);
+	/*
+	 * If userspace did not allocate the pkey, do not let
+	 * them use it here.
+	 */
+	error = -EINVAL;
+	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;
@@ -373,47 +863,145 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 				goto out;
 		}
 	}
+
+	prev = vma_prev(&vmi);
 	if (start > vma->vm_start)
 		prev = vma;
 
-	for (nstart = start ; ; ) {
-		unsigned long newflags;
+	tlb_gather_mmu(&tlb, current->mm);
+	nstart = start;
+	tmp = vma->vm_start;
+	for_each_vma_range(vmi, vma, end) {
+		vm_flags_t mask_off_old_flags;
+		vm_flags_t 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))
+			prot |= PROT_EXEC;
+
+		/*
+		 * Each mprotect() call explicitly passes r/w/x permissions.
+		 * If a permission is not passed to mprotect(), it must be
+		 * cleared from the VMA.
+		 */
+		mask_off_old_flags = VM_ACCESS_FLAGS | VM_FLAGS_CLEAR;
 
-		newflags = vm_flags;
-		newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
+		new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey);
+		newflags = calc_vm_prot_bits(prot, new_vma_pkey);
+		newflags |= (vma->vm_flags & ~mask_off_old_flags);
 
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */
-		if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
+		if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) {
 			error = -EACCES;
-			goto out;
+			break;
+		}
+
+		if (map_deny_write_exec(vma->vm_flags, newflags)) {
+			error = -EACCES;
+			break;
+		}
+
+		/* Allow architectures to sanity-check the new flags */
+		if (!arch_validate_flags(newflags)) {
+			error = -EINVAL;
+			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 (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)
-			goto out;
+			break;
+
+		tmp = vma_iter_end(&vmi);
 		nstart = tmp;
+		prot = reqprot;
+	}
+	tlb_finish_mmu(&tlb);
 
-		if (nstart < prev->vm_end)
-			nstart = prev->vm_end;
-		if (nstart >= end)
-			goto out;
+	if (!error && tmp < end)
+		error = -ENOMEM;
 
-		vma = prev->vm_next;
-		if (!vma || vma->vm_start != nstart) {
-			error = -ENOMEM;
-			goto out;
-		}
-	}
 out:
-	up_write(&current->mm->mmap_sem);
+	mmap_write_unlock(current->mm);
 	return error;
 }
+
+SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
+		unsigned long, prot)
+{
+	return do_mprotect_pkey(start, len, prot, -1);
+}
+
+#ifdef CONFIG_ARCH_HAS_PKEYS
+
+SYSCALL_DEFINE4(pkey_mprotect, unsigned long, start, size_t, len,
+		unsigned long, prot, int, pkey)
+{
+	return do_mprotect_pkey(start, len, prot, pkey);
+}
+
+SYSCALL_DEFINE2(pkey_alloc, unsigned long, flags, unsigned long, init_val)
+{
+	int pkey;
+	int ret;
+
+	/* No flags supported yet. */
+	if (flags)
+		return -EINVAL;
+	/* check for unsupported init values */
+	if (init_val & ~PKEY_ACCESS_MASK)
+		return -EINVAL;
+
+	mmap_write_lock(current->mm);
+	pkey = mm_pkey_alloc(current->mm);
+
+	ret = -ENOSPC;
+	if (pkey == -1)
+		goto out;
+
+	ret = arch_set_user_pkey_access(current, pkey, init_val);
+	if (ret) {
+		mm_pkey_free(current->mm, pkey);
+		goto out;
+	}
+	ret = pkey;
+out:
+	mmap_write_unlock(current->mm);
+	return ret;
+}
+
+SYSCALL_DEFINE1(pkey_free, int, pkey)
+{
+	int ret;
+
+	mmap_write_lock(current->mm);
+	ret = mm_pkey_free(current->mm, pkey);
+	mmap_write_unlock(current->mm);
+
+	/*
+	 * We could provide warnings or errors if any VMA still
+	 * has the pkey set here.
+	 */
+	return ret;
+}
+
+#endif /* CONFIG_ARCH_HAS_PKEYS */