[PATCH v2 00/20] Speculative page faults

@@ -2131,30 +2131,6 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(apply_to_page_range);
 
-/*
- * handle_pte_fault chooses page fault handler according to an entry which was
- * read non-atomically.  Before making any commitment, on those architectures
- * or configurations (e.g. i386 with PAE) which might give a mix of unmatched
- * parts, do_swap_page must check under lock before unmapping the pte and
- * proceeding (but do_wp_page is only called after already making such a check;
- * and do_anonymous_page can safely check later on).
- */
-static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
-				pte_t *page_table, pte_t orig_pte)
-{
-	int same = 1;
-#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
-	if (sizeof(pte_t) > sizeof(unsigned long)) {
-		spinlock_t *ptl = pte_lockptr(mm, pmd);
-		spin_lock(ptl);
-		same = pte_same(*page_table, orig_pte);
-		spin_unlock(ptl);
-	}
-#endif
-	pte_unmap(page_table);
-	return same;
-}
-
 static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
 {
 	debug_dma_assert_idle(src);

@@ -2711,9 +2687,6 @@ int do_swap_page(struct vm_fault *vmf)
 	int exclusive = 0;
 	int ret = 0;
 
-	if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte))
-		goto out;
-
 	entry = pte_to_swp_entry(vmf->orig_pte);
 	if (unlikely(non_swap_entry(entry))) {
 		if (is_migration_entry(entry)) {

@@ -2269,6 +2269,13 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 }
 
+static bool pte_spinlock(struct vm_fault *vmf)
+{
+	vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
+	spin_lock(vmf->ptl);
+	return true;
+}
+
 static bool pte_map_lock(struct vm_fault *vmf)
 {
 	vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl);

@@ -3543,8 +3550,8 @@ static int do_numa_page(struct vm_fault *vmf)
 	 * validation through pte_unmap_same(). It's of NUMA type but
 	 * the pfn may be screwed if the read is non atomic.
 	 */
-	vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd);
-	spin_lock(vmf->ptl);
+	if (!pte_spinlock(vmf))
+		return VM_FAULT_RETRY;
 	if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		goto out;

@@ -3736,8 +3743,8 @@ static int handle_pte_fault(struct vm_fault *vmf)
 	if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma))
 		return do_numa_page(vmf);
 
-	vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
-	spin_lock(vmf->ptl);
+	if (!pte_spinlock(vmf))
+		return VM_FAULT_RETRY;
 	entry = vmf->orig_pte;
 	if (unlikely(!pte_same(*vmf->pte, entry)))
 		goto unlock;

@@ -342,6 +342,7 @@ struct vm_area_struct {
 	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
 #endif
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
+	seqcount_t vm_sequence;
 } __randomize_layout;
 
 struct core_thread {

@@ -1408,6 +1408,7 @@ void unmap_page_range(struct mmu_gather *tlb,
 	unsigned long next;
 
 	BUG_ON(addr >= end);
+	write_seqcount_begin(&vma->vm_sequence);
 	tlb_start_vma(tlb, vma);
 	pgd = pgd_offset(vma->vm_mm, addr);
 	do {

@@ -1417,6 +1418,7 @@ void unmap_page_range(struct mmu_gather *tlb,
 		next = zap_p4d_range(tlb, vma, pgd, addr, next, details);
 	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
+	write_seqcount_end(&vma->vm_sequence);
 }
 
 

@@ -557,6 +557,8 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
 	else
 		mm->highest_vm_end = vm_end_gap(vma);
 
+	seqcount_init(&vma->vm_sequence);
+
 	/*
 	 * vma->vm_prev wasn't known when we followed the rbtree to find the
 	 * correct insertion point for that vma. As a result, we could not

@@ -798,6 +800,11 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 		}
 	}
 
+	write_seqcount_begin(&vma->vm_sequence);
+	if (next && next != vma)
+		write_seqcount_begin_nested(&next->vm_sequence,
+					    SINGLE_DEPTH_NESTING);
+
 	anon_vma = vma->anon_vma;
 	if (!anon_vma && adjust_next)
 		anon_vma = next->anon_vma;

@@ -902,6 +909,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 		mm->map_count--;
 		mpol_put(vma_policy(next));
 		kmem_cache_free(vm_area_cachep, next);
+		write_seqcount_end(&next->vm_sequence);
 		/*
 		 * In mprotect's case 6 (see comments on vma_merge),
 		 * we must remove another next too. It would clutter

@@ -931,11 +939,14 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 		if (remove_next == 2) {
 			remove_next = 1;
 			end = next->vm_end;
+			write_seqcount_end(&vma->vm_sequence);
 			goto again;
-		}
-		else if (next)
+		} else if (next) {
+			if (next != vma)
+				write_seqcount_begin_nested(&next->vm_sequence,
+							    SINGLE_DEPTH_NESTING);
 			vma_gap_update(next);
-		else {
+		} else {
 			/*
 			 * If remove_next == 2 we obviously can't
 			 * reach this path.

@@ -961,6 +972,10 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	if (insert && file)
 		uprobe_mmap(insert);
 
+	if (next && next != vma)
+		write_seqcount_end(&next->vm_sequence);
+	write_seqcount_end(&vma->vm_sequence);
+
 	validate_mm(mm);
 
 	return 0;

@@ -1067,8 +1067,11 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 					goto out_mm;
 				}
 				for (vma = mm->mmap; vma; vma = vma->vm_next) {
-					vma->vm_flags &= ~VM_SOFTDIRTY;
+					write_seqcount_begin(&vma->vm_sequence);
+					WRITE_ONCE(vma->vm_flags,
+						   vma->vm_flags & ~VM_SOFTDIRTY);
 					vma_set_page_prot(vma);
+					write_seqcount_end(&vma->vm_sequence);
 				}
 				downgrade_write(&mm->mmap_sem);
 				break;

@@ -612,8 +612,11 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 
 	octx = vma->vm_userfaultfd_ctx.ctx;
 	if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
+		write_seqcount_begin(&vma->vm_sequence);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-		vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+		WRITE_ONCE(vma->vm_flags,
+			   vma->vm_flags & ~(VM_UFFD_WP | VM_UFFD_MISSING));
+		write_seqcount_end(&vma->vm_sequence);
 		return 0;
 	}
 

@@ -838,8 +841,10 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 			vma = prev;
 		else
 			prev = vma;
-		vma->vm_flags = new_flags;
+		write_seqcount_begin(&vma->vm_sequence);
+		WRITE_ONCE(vma->vm_flags, new_flags);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+		write_seqcount_end(&vma->vm_sequence);
 	}
 	up_write(&mm->mmap_sem);
 	mmput(mm);

@@ -1357,8 +1362,10 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		 * the next vma was merged into the current one and
 		 * the current one has not been updated yet.
 		 */
-		vma->vm_flags = new_flags;
+		write_seqcount_begin(&vma->vm_sequence);
+		WRITE_ONCE(vma->vm_flags, new_flags);
 		vma->vm_userfaultfd_ctx.ctx = ctx;
+		write_seqcount_end(&vma->vm_sequence);
 
 	skip:
 		prev = vma;

@@ -1515,8 +1522,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		 * the next vma was merged into the current one and
 		 * the current one has not been updated yet.
 		 */
-		vma->vm_flags = new_flags;
+		write_seqcount_begin(&vma->vm_sequence);
+		WRITE_ONCE(vma->vm_flags, new_flags);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+		write_seqcount_end(&vma->vm_sequence);
 
 	skip:
 		prev = vma;

@@ -1005,6 +1005,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	if (mm_find_pmd(mm, address) != pmd)
 		goto out;
 
+	write_seqcount_begin(&vma->vm_sequence);
 	anon_vma_lock_write(vma->anon_vma);
 
 	pte = pte_offset_map(pmd, address);

@@ -1040,6 +1041,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 		pmd_populate(mm, pmd, pmd_pgtable(_pmd));
 		spin_unlock(pmd_ptl);
 		anon_vma_unlock_write(vma->anon_vma);
+		write_seqcount_end(&vma->vm_sequence);
 		result = SCAN_FAIL;
 		goto out;
 	}

@@ -1074,6 +1076,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
 	spin_unlock(pmd_ptl);
+	write_seqcount_end(&vma->vm_sequence);
 
 	*hpage = NULL;
 

@@ -172,7 +172,9 @@ static long madvise_behavior(struct vm_area_struct *vma,
 	/*
 	 * vm_flags is protected by the mmap_sem held in write mode.
 	 */
-	vma->vm_flags = new_flags;
+	write_seqcount_begin(&vma->vm_sequence);
+	WRITE_ONCE(vma->vm_flags, new_flags);
+	write_seqcount_end(&vma->vm_sequence);
 out:
 	return error;
 }

@@ -440,9 +442,11 @@ static void madvise_free_page_range(struct mmu_gather *tlb,
 		.private = tlb,
 	};
 
+	write_seqcount_begin(&vma->vm_sequence);
 	tlb_start_vma(tlb, vma);
 	walk_page_range(addr, end, &free_walk);
 	tlb_end_vma(tlb, vma);
+	write_seqcount_end(&vma->vm_sequence);
 }
 
 static int madvise_free_single_vma(struct vm_area_struct *vma,

@@ -378,8 +378,11 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
 	struct vm_area_struct *vma;
 
 	down_write(&mm->mmap_sem);
-	for (vma = mm->mmap; vma; vma = vma->vm_next)
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		write_seqcount_begin(&vma->vm_sequence);
 		mpol_rebind_policy(vma->vm_policy, new);
+		write_seqcount_end(&vma->vm_sequence);
+	}
 	up_write(&mm->mmap_sem);
 }
 

@@ -537,9 +540,11 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
 {
 	int nr_updated;
 
+	write_seqcount_begin(&vma->vm_sequence);
 	nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1);
 	if (nr_updated)
 		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
+	write_seqcount_end(&vma->vm_sequence);
 
 	return nr_updated;
 }

@@ -640,6 +645,7 @@ static int vma_replace_policy(struct vm_area_struct *vma,
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 
+	write_seqcount_begin(&vma->vm_sequence);
 	if (vma->vm_ops && vma->vm_ops->set_policy) {
 		err = vma->vm_ops->set_policy(vma, new);
 		if (err)

@@ -647,11 +653,17 @@ static int vma_replace_policy(struct vm_area_struct *vma,
 	}
 
 	old = vma->vm_policy;
-	vma->vm_policy = new; /* protected by mmap_sem */
+	/*
+	 * The speculative page fault handler access this field without
+	 * hodling the mmap_sem.
+	 */
+	WRITE_ONCE(vma->vm_policy,  new);
+	write_seqcount_end(&vma->vm_sequence);
 	mpol_put(old);
 
 	return 0;
  err_out:
+	write_seqcount_end(&vma->vm_sequence);
 	mpol_put(new);
 	return err;
 }

@@ -1505,23 +1517,28 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
 struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
 						unsigned long addr)
 {
-	struct mempolicy *pol = NULL;
+	struct mempolicy *pol;
 
-	if (vma) {
-		if (vma->vm_ops && vma->vm_ops->get_policy) {
-			pol = vma->vm_ops->get_policy(vma, addr);
-		} else if (vma->vm_policy) {
-			pol = vma->vm_policy;
+	if (!vma)
+		return NULL;
 
-			/*
-			 * shmem_alloc_page() passes MPOL_F_SHARED policy with
-			 * a pseudo vma whose vma->vm_ops=NULL. Take a reference
-			 * count on these policies which will be dropped by
-			 * mpol_cond_put() later
-			 */
-			if (mpol_needs_cond_ref(pol))
-				mpol_get(pol);
-		}
+	if (vma->vm_ops && vma->vm_ops->get_policy)
+		return vma->vm_ops->get_policy(vma, addr);
+
+	/*
+	 * This could be called without holding the mmap_sem in the
+	 * speculative page fault handler's path.
+	 */
+	pol = READ_ONCE(vma->vm_policy);
+	if (pol) {
+		/*
+		 * shmem_alloc_page() passes MPOL_F_SHARED policy with
+		 * a pseudo vma whose vma->vm_ops=NULL. Take a reference
+		 * count on these policies which will be dropped by
+		 * mpol_cond_put() later
+		 */
+		if (mpol_needs_cond_ref(pol))
+			mpol_get(pol);
 	}
 
 	return pol;

@@ -438,7 +438,9 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
 void munlock_vma_pages_range(struct vm_area_struct *vma,
 			     unsigned long start, unsigned long end)
 {
-	vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
+	write_seqcount_begin(&vma->vm_sequence);
+	WRITE_ONCE(vma->vm_flags, vma->vm_flags & VM_LOCKED_CLEAR_MASK);
+	write_seqcount_end(&vma->vm_sequence);
 
 	while (start < end) {
 		struct page *page;

@@ -563,10 +565,11 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	 * It's okay if try_to_unmap_one unmaps a page just after we
 	 * set VM_LOCKED, populate_vma_page_range will bring it back.
 	 */
-
-	if (lock)
-		vma->vm_flags = newflags;
-	else
+	if (lock) {
+		write_seqcount_begin(&vma->vm_sequence);
+		WRITE_ONCE(vma->vm_flags, newflags);
+		write_seqcount_end(&vma->vm_sequence);
+	} else
 		munlock_vma_pages_range(vma, start, end);
 
 out:

@@ -825,17 +825,18 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	}
 
 	if (start != vma->vm_start) {
-		vma->vm_start = start;
+		WRITE_ONCE(vma->vm_start, start);
 		start_changed = true;
 	}
 	if (end != vma->vm_end) {
-		vma->vm_end = end;
+		WRITE_ONCE(vma->vm_end, end);
 		end_changed = true;
 	}
-	vma->vm_pgoff = pgoff;
+	WRITE_ONCE(vma->vm_pgoff, pgoff);
 	if (adjust_next) {
-		next->vm_start += adjust_next << PAGE_SHIFT;
-		next->vm_pgoff += adjust_next;
+		WRITE_ONCE(next->vm_start,
+			   next->vm_start + (adjust_next << PAGE_SHIFT));
+		WRITE_ONCE(next->vm_pgoff, next->vm_pgoff + adjust_next);
 	}
 
 	if (root) {

@@ -1734,6 +1735,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 out:
 	perf_event_mmap(vma);
 
+	write_seqcount_begin(&vma->vm_sequence);
 	vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT);
 	if (vm_flags & VM_LOCKED) {
 		if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) ||

@@ -1756,6 +1758,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	vma->vm_flags |= VM_SOFTDIRTY;
 
 	vma_set_page_prot(vma);
+	write_seqcount_end(&vma->vm_sequence);
 
 	return addr;
 

@@ -2384,8 +2387,8 @@ int expand_downwards(struct vm_area_struct *vma,
 					mm->locked_vm += grow;
 				vm_stat_account(mm, vma->vm_flags, grow);
 				anon_vma_interval_tree_pre_update_vma(vma);
-				vma->vm_start = address;
-				vma->vm_pgoff -= grow;
+				WRITE_ONCE(vma->vm_start, address);
+				WRITE_ONCE(vma->vm_pgoff, vma->vm_pgoff - grow);
 				anon_vma_interval_tree_post_update_vma(vma);
 				vma_gap_update(vma);
 				spin_unlock(&mm->page_table_lock);

@@ -344,7 +344,8 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	 * vm_flags and vm_page_prot are protected by the mmap_sem
 	 * held in write mode.
 	 */
-	vma->vm_flags = newflags;
+	write_seqcount_begin(&vma->vm_sequence);
+	WRITE_ONCE(vma->vm_flags, newflags);
 	dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot);
 	vma_set_page_prot(vma);
 

@@ -359,6 +360,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 			(newflags & VM_WRITE)) {
 		populate_vma_page_range(vma, start, end, NULL);
 	}
+	write_seqcount_end(&vma->vm_sequence);
 
 	vm_stat_account(mm, oldflags, -nrpages);
 	vm_stat_account(mm, newflags, nrpages);

@@ -301,6 +301,10 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	if (!new_vma)
 		return -ENOMEM;
 
+	write_seqcount_begin(&vma->vm_sequence);
+	write_seqcount_begin_nested(&new_vma->vm_sequence,
+				    SINGLE_DEPTH_NESTING);
+
 	moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len,
 				     need_rmap_locks);
 	if (moved_len < old_len) {

@@ -317,6 +321,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 		 */
 		move_page_tables(new_vma, new_addr, vma, old_addr, moved_len,
 				 true);
+		write_seqcount_end(&vma->vm_sequence);
 		vma = new_vma;
 		old_len = new_len;
 		old_addr = new_addr;

@@ -325,7 +330,9 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 		mremap_userfaultfd_prep(new_vma, uf);
 		arch_remap(mm, old_addr, old_addr + old_len,
 			   new_addr, new_addr + new_len);
+		write_seqcount_end(&vma->vm_sequence);
 	}
+	write_seqcount_end(&new_vma->vm_sequence);
 
 	/* Conceal VM_ACCOUNT so old reservation is not undone */
 	if (vm_flags & VM_ACCOUNT) {

@@ -345,6 +345,12 @@ struct vm_fault {
 					 * page table to avoid allocation from
 					 * atomic context.
 					 */
+	/*
+	 * These entries are required when handling speculative page fault.
+	 * This way the page handling is done using consistent field values.
+	 */
+	unsigned long vma_flags;
+	pgprot_t vma_page_prot;
 };
 
 /* page entry size for vm->huge_fault() */

@@ -3676,6 +3676,8 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				.vma = vma,
 				.address = address,
 				.flags = flags,
+				.vma_flags = vma->vm_flags,
+				.vma_page_prot = vma->vm_page_prot,
 				/*
 				 * Hard to debug if it ends up being
 				 * used by a callee that assumes

@@ -881,6 +881,8 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 		.flags = FAULT_FLAG_ALLOW_RETRY,
 		.pmd = pmd,
 		.pgoff = linear_page_index(vma, address),
+		.vma_flags = vma->vm_flags,
+		.vma_page_prot = vma->vm_page_prot,
 	};
 
 	/* we only decide to swapin, if there is enough young ptes */

@@ -2417,7 +2417,7 @@ static int wp_page_copy(struct vm_fault *vmf)
 		 * Don't let another task, with possibly unlocked vma,
 		 * keep the mlocked page.
 		 */
-		if (page_copied && (vma->vm_flags & VM_LOCKED)) {
+		if (page_copied && (vmf->vma_flags & VM_LOCKED)) {
 			lock_page(old_page);	/* LRU manipulation */
 			if (PageMlocked(old_page))
 				munlock_vma_page(old_page);

@@ -2451,7 +2451,7 @@ static int wp_page_copy(struct vm_fault *vmf)
  */
 int finish_mkwrite_fault(struct vm_fault *vmf)
 {
-	WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED));
+	WARN_ON_ONCE(!(vmf->vma_flags & VM_SHARED));
 	if (!pte_map_lock(vmf))
 		return VM_FAULT_RETRY;
 	/*

@@ -2553,7 +2553,7 @@ static int do_wp_page(struct vm_fault *vmf)
 		 * We should not cow pages in a shared writeable mapping.
 		 * Just mark the pages writable and/or call ops->pfn_mkwrite.
 		 */
-		if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
+		if ((vmf->vma_flags & (VM_WRITE|VM_SHARED)) ==
 				     (VM_WRITE|VM_SHARED))
 			return wp_pfn_shared(vmf);
 

@@ -2600,7 +2600,7 @@ static int do_wp_page(struct vm_fault *vmf)
 			return VM_FAULT_WRITE;
 		}
 		unlock_page(vmf->page);
-	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
+	} else if (unlikely((vmf->vma_flags & (VM_WRITE|VM_SHARED)) ==
 					(VM_WRITE|VM_SHARED))) {
 		return wp_page_shared(vmf);
 	}

@@ -2817,7 +2817,7 @@ int do_swap_page(struct vm_fault *vmf)
 
 	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 	dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS);
-	pte = mk_pte(page, vma->vm_page_prot);
+	pte = mk_pte(page, vmf->vma_page_prot);
 	if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) {
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 		vmf->flags &= ~FAULT_FLAG_WRITE;

@@ -2841,7 +2841,7 @@ int do_swap_page(struct vm_fault *vmf)
 
 	swap_free(entry);
 	if (mem_cgroup_swap_full(page) ||
-	    (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
+	    (vmf->vma_flags & VM_LOCKED) || PageMlocked(page))
 		try_to_free_swap(page);
 	unlock_page(page);
 	if (page != swapcache) {

@@ -2897,7 +2897,7 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	pte_t entry;
 
 	/* File mapping without ->vm_ops ? */
-	if (vma->vm_flags & VM_SHARED)
+	if (vmf->vma_flags & VM_SHARED)
 		return VM_FAULT_SIGBUS;
 
 	/*

@@ -2921,7 +2921,7 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	if (!(vmf->flags & FAULT_FLAG_WRITE) &&
 			!mm_forbids_zeropage(vma->vm_mm)) {
 		entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address),
-						vma->vm_page_prot));
+						vmf->vma_page_prot));
 		if (!pte_map_lock(vmf))
 			return VM_FAULT_RETRY;
 		if (!pte_none(*vmf->pte))

@@ -2951,8 +2951,8 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	 */
 	__SetPageUptodate(page);
 
-	entry = mk_pte(page, vma->vm_page_prot);
-	if (vma->vm_flags & VM_WRITE)
+	entry = mk_pte(page, vmf->vma_page_prot);
+	if (vmf->vma_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry));
 
 	if (!pte_map_lock(vmf)) {

@@ -3144,7 +3144,7 @@ static int do_set_pmd(struct vm_fault *vmf, struct page *page)
 	for (i = 0; i < HPAGE_PMD_NR; i++)
 		flush_icache_page(vma, page + i);
 
-	entry = mk_huge_pmd(page, vma->vm_page_prot);
+	entry = mk_huge_pmd(page, vmf->vma_page_prot);
 	if (write)
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 

@@ -3218,11 +3218,11 @@ int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 		return VM_FAULT_NOPAGE;
 
 	flush_icache_page(vma, page);
-	entry = mk_pte(page, vma->vm_page_prot);
+	entry = mk_pte(page, vmf->vma_page_prot);
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 	/* copy-on-write page */
-	if (write && !(vma->vm_flags & VM_SHARED)) {
+	if (write && !(vmf->vma_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);

@@ -3261,7 +3261,7 @@ int finish_fault(struct vm_fault *vmf)
 
 	/* Did we COW the page? */
 	if ((vmf->flags & FAULT_FLAG_WRITE) &&
-	    !(vmf->vma->vm_flags & VM_SHARED))
+	    !(vmf->vma_flags & VM_SHARED))
 		page = vmf->cow_page;
 	else
 		page = vmf->page;

@@ -3507,7 +3507,7 @@ static int do_fault(struct vm_fault *vmf)
 		ret = VM_FAULT_SIGBUS;
 	else if (!(vmf->flags & FAULT_FLAG_WRITE))
 		ret = do_read_fault(vmf);
-	else if (!(vma->vm_flags & VM_SHARED))
+	else if (!(vmf->vma_flags & VM_SHARED))
 		ret = do_cow_fault(vmf);
 	else
 		ret = do_shared_fault(vmf);

@@ -3564,7 +3564,7 @@ static int do_numa_page(struct vm_fault *vmf)
 	 * accessible ptes, some can allow access by kernel mode.
 	 */
 	pte = ptep_modify_prot_start(vma->vm_mm, vmf->address, vmf->pte);
-	pte = pte_modify(pte, vma->vm_page_prot);
+	pte = pte_modify(pte, vmf->vma_page_prot);
 	pte = pte_mkyoung(pte);
 	if (was_writable)
 		pte = pte_mkwrite(pte);

@@ -3598,7 +3598,7 @@ static int do_numa_page(struct vm_fault *vmf)
 	 * Flag if the page is shared between multiple address spaces. This
 	 * is later used when determining whether to group tasks together
 	 */
-	if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
+	if (page_mapcount(page) > 1 && (vmf->vma_flags & VM_SHARED))
 		flags |= TNF_SHARED;
 
 	last_cpupid = page_cpupid_last(page);

@@ -3642,7 +3642,7 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
 
 	/* COW handled on pte level: split pmd */
-	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
+	VM_BUG_ON_VMA(vmf->vma_flags & VM_SHARED, vmf->vma);
 	__split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL);
 
 	return VM_FAULT_FALLBACK;

@@ -3789,6 +3789,8 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 		.flags = flags,
 		.pgoff = linear_page_index(vma, address),
 		.gfp_mask = __get_fault_gfp_mask(vma),
+		.vma_flags = vma->vm_flags,
+		.vma_page_prot = vma->vm_page_prot,
 	};
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;

@@ -668,13 +668,18 @@ void free_compound_page(struct page *page);
  * pte_mkwrite.  But get_user_pages can cause write faults for mappings
  * that do not have writing enabled, when used by access_process_vm.
  */
-static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+static inline pte_t __maybe_mkwrite(pte_t pte, unsigned long vma_flags)
 {
-	if (likely(vma->vm_flags & VM_WRITE))
+	if (likely(vma_flags & VM_WRITE))
 		pte = pte_mkwrite(pte);
 	return pte;
 }
 
+static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+	return __maybe_mkwrite(pte, vma->vm_flags);
+}
+
 int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 		struct page *page);
 int finish_fault(struct vm_fault *vmf);

@@ -2269,7 +2269,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 
 	flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 	entry = pte_mkyoung(vmf->orig_pte);
-	entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+	entry = __maybe_mkwrite(pte_mkdirty(entry), vmf->vma_flags);
 	if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
 		update_mmu_cache(vma, vmf->address, vmf->pte);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);

@@ -2359,8 +2359,8 @@ static int wp_page_copy(struct vm_fault *vmf)
 			inc_mm_counter_fast(mm, MM_ANONPAGES);
 		}
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
-		entry = mk_pte(new_page, vma->vm_page_prot);
-		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		entry = mk_pte(new_page, vmf->vma_page_prot);
+		entry = __maybe_mkwrite(pte_mkdirty(entry), vmf->vma_flags);
 		/*
 		 * Clear the pte entry and flush it first, before updating the
 		 * pte with the new entry. This will avoid a race condition

@@ -170,8 +170,16 @@ void page_add_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long, bool);
 void do_page_add_anon_rmap(struct page *, struct vm_area_struct *,
 			   unsigned long, int);
-void page_add_new_anon_rmap(struct page *, struct vm_area_struct *,
-		unsigned long, bool);
+void __page_add_new_anon_rmap(struct page *, struct vm_area_struct *,
+			      unsigned long, bool);
+static inline void page_add_new_anon_rmap(struct page *page,
+					  struct vm_area_struct *vma,
+					  unsigned long address, bool compound)
+{
+	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
+	__page_add_new_anon_rmap(page, vma, address, compound);
+}
+
 void page_add_file_rmap(struct page *, bool);
 void page_remove_rmap(struct page *, bool);
 

@@ -2376,7 +2376,7 @@ static int wp_page_copy(struct vm_fault *vmf)
 		 * thread doing COW.
 		 */
 		ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
-		page_add_new_anon_rmap(new_page, vma, vmf->address, false);
+		__page_add_new_anon_rmap(new_page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(new_page, memcg, false, false);
 		__lru_cache_add_active_or_unevictable(new_page, vmf->vma_flags);
 		/*

@@ -2847,7 +2847,7 @@ int do_swap_page(struct vm_fault *vmf)
 		mem_cgroup_commit_charge(page, memcg, true, false);
 		activate_page(page);
 	} else { /* ksm created a completely new copy */
-		page_add_new_anon_rmap(page, vma, vmf->address, false);
+		__page_add_new_anon_rmap(page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
 		__lru_cache_add_active_or_unevictable(page, vmf->vma_flags);
 	}

@@ -2985,7 +2985,7 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	}
 
 	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-	page_add_new_anon_rmap(page, vma, vmf->address, false);
+	__page_add_new_anon_rmap(page, vma, vmf->address, false);
 	mem_cgroup_commit_charge(page, memcg, false, false);
 	__lru_cache_add_active_or_unevictable(page, vmf->vma_flags);
 setpte:

@@ -3237,7 +3237,7 @@ int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 	/* copy-on-write page */
 	if (write && !(vmf->vma_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-		page_add_new_anon_rmap(page, vma, vmf->address, false);
+		__page_add_new_anon_rmap(page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
 		__lru_cache_add_active_or_unevictable(page, vmf->vma_flags);
 	} else {

@@ -1122,7 +1122,7 @@ void do_page_add_anon_rmap(struct page *page,
 }
 
 /**
- * page_add_new_anon_rmap - add pte mapping to a new anonymous page
+ * __page_add_new_anon_rmap - add pte mapping to a new anonymous page
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped

@@ -1132,12 +1132,11 @@ void do_page_add_anon_rmap(struct page *page,
  * This means the inc-and-test can be bypassed.
  * Page does not have to be locked.
  */
-void page_add_new_anon_rmap(struct page *page,
+void __page_add_new_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address, bool compound)
 {
 	int nr = compound ? hpage_nr_pages(page) : 1;
 
-	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
 	__SetPageSwapBacked(page);
 	if (compound) {
 		VM_BUG_ON_PAGE(!PageTransHuge(page), page);

@@ -2300,7 +2300,8 @@ static bool pte_spinlock(struct vm_fault *vmf)
 		goto out;
 
 	vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
-	spin_lock(vmf->ptl);
+	if (unlikely(!spin_trylock(vmf->ptl)))
+		goto out;
 
 	if (vma_has_changed(vmf)) {
 		spin_unlock(vmf->ptl);

@@ -2336,8 +2337,20 @@ static bool pte_map_lock(struct vm_fault *vmf)
 	if (vma_has_changed(vmf))
 		goto out;
 
-	pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd,
-				  vmf->address, &ptl);
+	/*
+	 * Same as pte_offset_map_lock() except that we call
+	 * spin_trylock() in place of spin_lock() to avoid race with
+	 * unmap path which may have the lock and wait for this CPU
+	 * to invalidate TLB but this CPU has irq disabled.
+	 * Since we are in a speculative patch, accept it could fail
+	 */
+	ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
+	pte = pte_offset_map(vmf->pmd, vmf->address);
+	if (unlikely(!spin_trylock(ptl))) {
+		pte_unmap(pte);
+		goto out;
+	}
+
 	if (vma_has_changed(vmf)) {
 		pte_unmap_unlock(pte, ptl);
 		goto out;