[PATCH 00/16] Speculative page faults

@@ -2103,30 +2103,6 @@ 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);

@@ -2683,9 +2659,6 @@ 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)) {

@@ -2241,6 +2241,13 @@ 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);

@@ -3515,8 +3522,8 @@ 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;

@@ -3708,8 +3715,8 @@ 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;

@@ -286,6 +286,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_USER		0x40	/* The fault originated in userspace */
 #define FAULT_FLAG_REMOTE	0x80	/* faulting for non current tsk/mm */
 #define FAULT_FLAG_INSTRUCTION  0x100	/* The fault was during an instruction fetch */
+#define FAULT_FLAG_SPECULATIVE	0x200	/* Speculative fault, not holding mmap_sem */
 
 #define FAULT_FLAG_TRACE \
 	{ FAULT_FLAG_WRITE,		"WRITE" }, \

@@ -2241,6 +2241,12 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 }
 
+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);
+	return true;
+}
+
 /*
  * Handle the case of a page which we actually need to copy to a new page.
  *

@@ -2268,6 +2274,7 @@ static int wp_page_copy(struct vm_fault *vmf)
 	const unsigned long mmun_start = vmf->address & PAGE_MASK;
 	const unsigned long mmun_end = mmun_start + PAGE_SIZE;
 	struct mem_cgroup *memcg;
+	int ret = VM_FAULT_OOM;
 
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;

@@ -2295,7 +2302,11 @@ static int wp_page_copy(struct vm_fault *vmf)
 	/*
 	 * Re-check the pte - we dropped the lock
 	 */
-	vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl);
+	if (!pte_map_lock(vmf)) {
+		mem_cgroup_cancel_charge(new_page, memcg, false);
+		ret = VM_FAULT_RETRY;
+		goto oom_free_new;
+	}
 	if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
 		if (old_page) {
 			if (!PageAnon(old_page)) {

@@ -2383,7 +2394,7 @@ static int wp_page_copy(struct vm_fault *vmf)
 oom:
 	if (old_page)
 		put_page(old_page);
-	return VM_FAULT_OOM;
+	return ret;
 }
 
 /**

@@ -2404,8 +2415,8 @@ 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));
-	vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address,
-				       &vmf->ptl);
+	if (!pte_map_lock(vmf))
+		return VM_FAULT_RETRY;
 	/*
 	 * We might have raced with another page fault while we released the
 	 * pte_offset_map_lock.

@@ -2523,8 +2534,11 @@ static int do_wp_page(struct vm_fault *vmf)
 			get_page(vmf->page);
 			pte_unmap_unlock(vmf->pte, vmf->ptl);
 			lock_page(vmf->page);
-			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
-					vmf->address, &vmf->ptl);
+			if (!pte_map_lock(vmf)) {
+				unlock_page(vmf->page);
+				put_page(vmf->page);
+				return VM_FAULT_RETRY;
+			}
 			if (!pte_same(*vmf->pte, vmf->orig_pte)) {
 				unlock_page(vmf->page);
 				pte_unmap_unlock(vmf->pte, vmf->ptl);

@@ -2682,8 +2696,10 @@ int do_swap_page(struct vm_fault *vmf)
 			 * Back out if somebody else faulted in this pte
 			 * while we released the pte lock.
 			 */
-			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
-					vmf->address, &vmf->ptl);
+			if (!pte_map_lock(vmf)) {
+				delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+				return VM_FAULT_RETRY;
+			}
 			if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
 				ret = VM_FAULT_OOM;
 			delayacct_clear_flag(DELAYACCT_PF_SWAPIN);

@@ -2739,8 +2755,11 @@ int do_swap_page(struct vm_fault *vmf)
 	/*
 	 * Back out if somebody else already faulted in this pte.
 	 */
-	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
-			&vmf->ptl);
+	if (!pte_map_lock(vmf)) {
+		ret = VM_FAULT_RETRY;
+		mem_cgroup_cancel_charge(page, memcg, false);
+		goto out_page;
+	}
 	if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte)))
 		goto out_nomap;
 

@@ -2866,8 +2885,8 @@ static int do_anonymous_page(struct vm_fault *vmf)
 			!mm_forbids_zeropage(vma->vm_mm)) {
 		entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address),
 						vma->vm_page_prot));
-		vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
-				vmf->address, &vmf->ptl);
+		if (!pte_map_lock(vmf))
+			return VM_FAULT_RETRY;
 		if (!pte_none(*vmf->pte))
 			goto unlock;
 		/* Deliver the page fault to userland, check inside PT lock */

@@ -2899,8 +2918,11 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	if (vma->vm_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry));
 
-	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
-			&vmf->ptl);
+	if (!pte_map_lock(vmf)) {
+		mem_cgroup_cancel_charge(page, memcg, false);
+		put_page(page);
+		return VM_FAULT_RETRY;
+	}
 	if (!pte_none(*vmf->pte))
 		goto release;
 

@@ -3020,8 +3042,9 @@ static int pte_alloc_one_map(struct vm_fault *vmf)
 	 * pte_none() under vmf->ptl protection when we return to
 	 * alloc_set_pte().
 	 */
-	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
-			&vmf->ptl);
+	if (!pte_map_lock(vmf))
+		return VM_FAULT_RETRY;
+
 	return 0;
 }
 

@@ -343,6 +343,7 @@ struct vm_area_struct {
 #endif
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 	seqcount_t vm_sequence;
+	struct rcu_head vm_rcu_head;
 } __randomize_layout;
 
 struct core_thread {

@@ -360,6 +361,7 @@ struct kioctx_table;
 struct mm_struct {
 	struct vm_area_struct *mmap;		/* list of VMAs */
 	struct rb_root mm_rb;
+	seqlock_t mm_seq;
 	u32 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
 	unsigned long (*get_unmapped_area) (struct file *filp,

@@ -791,6 +791,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm->mmap = NULL;
 	mm->mm_rb = RB_ROOT;
 	mm->vmacache_seqnum = 0;
+	seqlock_init(&mm->mm_seq);
 	atomic_set(&mm->mm_users, 1);
 	atomic_set(&mm->mm_count, 1);
 	init_rwsem(&mm->mmap_sem);

@@ -16,6 +16,7 @@
 
 struct mm_struct init_mm = {
 	.mm_rb		= RB_ROOT,
+	.mm_seq		= __SEQLOCK_UNLOCKED(init_mm.mm_seq),
 	.pgd		= swapper_pg_dir,
 	.mm_users	= ATOMIC_INIT(2),
 	.mm_count	= ATOMIC_INIT(1),

@@ -40,6 +40,25 @@ void page_writeback_init(void);
 
 int do_swap_page(struct vm_fault *vmf);
 
+extern struct srcu_struct vma_srcu;
+
+extern struct vm_area_struct *find_vma_srcu(struct mm_struct *mm,
+					    unsigned long addr);
+
+static inline bool vma_has_changed(struct vm_fault *vmf)
+{
+	int ret = RB_EMPTY_NODE(&vmf->vma->vm_rb);
+	unsigned seq = ACCESS_ONCE(vmf->vma->vm_sequence.sequence);
+
+	/*
+	 * Matches both the wmb in write_seqlock_{begin,end}() and
+	 * the wmb in vma_rb_erase().
+	 */
+	smp_rmb();
+
+	return ret || seq != vmf->sequence;
+}
+
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
 

@@ -159,6 +159,23 @@ void unlink_file_vma(struct vm_area_struct *vma)
 	}
 }
 
+DEFINE_SRCU(vma_srcu);
+
+static void __free_vma(struct rcu_head *head)
+{
+	struct vm_area_struct *vma =
+		container_of(head, struct vm_area_struct, vm_rcu_head);
+
+	if (vma->vm_file)
+		fput(vma->vm_file);
+	kmem_cache_free(vm_area_cachep, vma);
+}
+
+static void free_vma(struct vm_area_struct *vma)
+{
+	call_srcu(&vma_srcu, &vma->vm_rcu_head, __free_vma);
+}
+
 /*
  * Close a vm structure and free it, returning the next.
  */

@@ -169,10 +186,8 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	might_sleep();
 	if (vma->vm_ops && vma->vm_ops->close)
 		vma->vm_ops->close(vma);
-	if (vma->vm_file)
-		fput(vma->vm_file);
 	mpol_put(vma_policy(vma));
-	kmem_cache_free(vm_area_cachep, vma);
+	free_vma(vma);
 	return next;
 }
 

@@ -410,26 +425,37 @@ static void vma_gap_update(struct vm_area_struct *vma)
 }
 
 static inline void vma_rb_insert(struct vm_area_struct *vma,
-				 struct rb_root *root)
+				 struct mm_struct *mm)
 {
+	struct rb_root *root = &mm->mm_rb;
+
 	/* All rb_subtree_gap values must be consistent prior to insertion */
 	validate_mm_rb(root, NULL);
 
 	rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
 }
 
-static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root)
+static void __vma_rb_erase(struct vm_area_struct *vma, struct mm_struct *mm)
 {
+	struct rb_root *root = &mm->mm_rb;
 	/*
 	 * Note rb_erase_augmented is a fairly large inline function,
 	 * so make sure we instantiate it only once with our desired
 	 * augmented rbtree callbacks.
 	 */
+	write_seqlock(&mm->mm_seq);
 	rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
+	write_sequnlock(&mm->mm_seq); /* wmb */
+
+	/*
+	 * Ensure the removal is complete before clearing the node.
+	 * Matched by vma_has_changed()/handle_speculative_fault().
+	 */
+	RB_CLEAR_NODE(&vma->vm_rb);
 }
 
 static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma,
-						struct rb_root *root,
+						struct mm_struct *mm,
 						struct vm_area_struct *ignore)
 {
 	/*

@@ -437,21 +463,21 @@ static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma,
 	 * with the possible exception of the "next" vma being erased if
 	 * next->vm_start was reduced.
 	 */
-	validate_mm_rb(root, ignore);
+	validate_mm_rb(&mm->mm_rb, ignore);
 
-	__vma_rb_erase(vma, root);
+	__vma_rb_erase(vma, mm);
 }
 
 static __always_inline void vma_rb_erase(struct vm_area_struct *vma,
-					 struct rb_root *root)
+					 struct mm_struct *mm)
 {
 	/*
 	 * All rb_subtree_gap values must be consistent prior to erase,
 	 * with the possible exception of the vma being erased.
 	 */
-	validate_mm_rb(root, vma);
+	validate_mm_rb(&mm->mm_rb, vma);
 
-	__vma_rb_erase(vma, root);
+	__vma_rb_erase(vma, mm);
 }
 
 /*

@@ -568,10 +594,12 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * immediately update the gap to the correct value. Finally we
 	 * rebalance the rbtree after all augmented values have been set.
 	 */
+	write_seqlock(&mm->mm_seq);
 	rb_link_node(&vma->vm_rb, rb_parent, rb_link);
 	vma->rb_subtree_gap = 0;
 	vma_gap_update(vma);
-	vma_rb_insert(vma, &mm->mm_rb);
+	vma_rb_insert(vma, mm);
+	write_sequnlock(&mm->mm_seq);
 }
 
 static void __vma_link_file(struct vm_area_struct *vma)

@@ -647,7 +675,7 @@ static __always_inline void __vma_unlink_common(struct mm_struct *mm,
 {
 	struct vm_area_struct *next;
 
-	vma_rb_erase_ignore(vma, &mm->mm_rb, ignore);
+	vma_rb_erase_ignore(vma, mm, ignore);
 	next = vma->vm_next;
 	if (has_prev)
 		prev->vm_next = next;

@@ -900,15 +928,13 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	}
 
 	if (remove_next) {
-		if (file) {
+		if (file)
 			uprobe_munmap(next, next->vm_start, next->vm_end);
-			fput(file);
-		}
 		if (next->anon_vma)
 			anon_vma_merge(vma, next);
 		mm->map_count--;
 		mpol_put(vma_policy(next));
-		kmem_cache_free(vm_area_cachep, next);
+		free_vma(next);
 		write_seqcount_end(&next->vm_sequence);
 		/*
 		 * In mprotect's case 6 (see comments on vma_merge),

@@ -2129,15 +2155,10 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 EXPORT_SYMBOL(get_unmapped_area);
 
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
-struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+static struct vm_area_struct *__find_vma(struct mm_struct *mm, unsigned long addr)
 {
 	struct rb_node *rb_node;
-	struct vm_area_struct *vma;
-
-	/* Check the cache first. */
-	vma = vmacache_find(mm, addr);
-	if (likely(vma))
-		return vma;
+	struct vm_area_struct *vma = NULL;
 
 	rb_node = mm->mm_rb.rb_node;
 

@@ -2155,13 +2176,40 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 			rb_node = rb_node->rb_right;
 	}
 
+	return vma;
+}
+
+struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma;
+
+	/* Check the cache first. */
+	vma = vmacache_find(mm, addr);
+	if (likely(vma))
+		return vma;
+
+	vma = __find_vma(mm, addr);
 	if (vma)
 		vmacache_update(addr, vma);
 	return vma;
 }
-
 EXPORT_SYMBOL(find_vma);
 
+struct vm_area_struct *find_vma_srcu(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma;
+	unsigned int seq;
+
+	WARN_ON_ONCE(!srcu_read_lock_held(&vma_srcu));
+
+	do {
+		seq = read_seqbegin(&mm->mm_seq);
+		vma = __find_vma(mm, addr);
+	} while (read_seqretry(&mm->mm_seq, seq));
+
+	return vma;
+}
+
 /*
  * Same as find_vma, but also return a pointer to the previous VMA in *pprev.
  */

@@ -2529,7 +2577,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	insertion_point = (prev ? &prev->vm_next : &mm->mmap);
 	vma->vm_prev = NULL;
 	do {
-		vma_rb_erase(vma, &mm->mm_rb);
+		vma_rb_erase(vma, mm);
 		mm->map_count--;
 		tail_vma = vma;
 		vma = vma->vm_next;

@@ -315,6 +315,7 @@ struct vm_fault {
 	gfp_t gfp_mask;			/* gfp mask to be used for allocations */
 	pgoff_t pgoff;			/* Logical page offset based on vma */
 	unsigned long address;		/* Faulting virtual address */
+	unsigned int sequence;
 	pmd_t *pmd;			/* Pointer to pmd entry matching
 					 * the 'address' */
 	pud_t *pud;			/* Pointer to pud entry matching

@@ -1286,6 +1287,8 @@ int invalidate_inode_page(struct page *page);
 #ifdef CONFIG_MMU
 extern int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 		unsigned int flags);
+extern int handle_speculative_fault(struct mm_struct *mm,
+				    unsigned long address, unsigned int flags);
 extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 			    unsigned long address, unsigned int fault_flags,
 			    bool *unlocked);

@@ -2245,15 +2245,69 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 
 static bool pte_spinlock(struct vm_fault *vmf)
 {
+	bool ret = false;
+
+	/* Check if vma is still valid */
+	if (!(vmf->flags & FAULT_FLAG_SPECULATIVE)) {
+		vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
+		spin_lock(vmf->ptl);
+		return true;
+	}
+
+	local_irq_disable();
+	if (vma_has_changed(vmf))
+		goto out;
+
 	vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
 	spin_lock(vmf->ptl);
-	return true;
+
+	if (vma_has_changed(vmf)) {
+		spin_unlock(vmf->ptl);
+		goto out;
+	}
+
+	ret = true;
+out:
+	local_irq_enable();
+	return ret;
 }
 
 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);
-	return true;
+	bool ret = false;
+	pte_t *pte;
+	spinlock_t *ptl;
+
+	if (!(vmf->flags & FAULT_FLAG_SPECULATIVE)) {
+		vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd,
+					       vmf->address, &vmf->ptl);
+		return true;
+	}
+
+	/*
+	 * The first vma_has_changed() guarantees the page-tables are still
+	 * valid, having IRQs disabled ensures they stay around, hence the
+	 * second vma_has_changed() to make sure they are still valid once
+	 * we've got the lock. After that a concurrent zap_pte_range() will
+	 * block on the PTL and thus we're safe.
+	 */
+	local_irq_disable();
+	if (vma_has_changed(vmf))
+		goto out;
+
+	pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd,
+				  vmf->address, &ptl);
+	if (vma_has_changed(vmf)) {
+		pte_unmap_unlock(pte, ptl);
+		goto out;
+	}
+
+	vmf->pte = pte;
+	vmf->ptl = ptl;
+	ret = true;
+out:
+	local_irq_enable();
+	return ret;
 }
 
 /*

@@ -2872,6 +2926,10 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	if (vma->vm_flags & VM_SHARED)
 		return VM_FAULT_SIGBUS;
 
+	/* Can't call userland page fault handler in the speculative path */
+	if (vmf->flags & FAULT_FLAG_SPECULATIVE && userfaultfd_missing(vma))
+		return VM_FAULT_RETRY;
+
 	/*
 	 * Use pte_alloc() instead of pte_alloc_map().  We can't run
 	 * pte_offset_map() on pmds where a huge pmd might be created

@@ -3707,6 +3765,8 @@ static int handle_pte_fault(struct vm_fault *vmf)
 	if (!vmf->pte) {
 		if (vma_is_anonymous(vmf->vma))
 			return do_anonymous_page(vmf);
+		else if (vmf->flags & FAULT_FLAG_SPECULATIVE)
+			return VM_FAULT_RETRY;
 		else
 			return do_fault(vmf);
 	}

@@ -3802,6 +3862,7 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	vmf.pmd = pmd_alloc(mm, vmf.pud, address);
 	if (!vmf.pmd)
 		return VM_FAULT_OOM;
+	vmf.sequence = raw_read_seqcount(&vma->vm_sequence);
 	if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) {
 		ret = create_huge_pmd(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))

@@ -3829,6 +3890,122 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	return handle_pte_fault(&vmf);
 }
 
+int handle_speculative_fault(struct mm_struct *mm, unsigned long address,
+			     unsigned int flags)
+{
+	struct vm_fault vmf = {
+		.address = address,
+	};
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	int dead, seq, idx, ret = VM_FAULT_RETRY;
+	struct vm_area_struct *vma;
+
+	/* Clear flags that may lead to release the mmap_sem to retry */
+	flags &= ~(FAULT_FLAG_ALLOW_RETRY|FAULT_FLAG_KILLABLE);
+	flags |= FAULT_FLAG_SPECULATIVE;
+
+	idx = srcu_read_lock(&vma_srcu);
+	vma = find_vma_srcu(mm, address);
+	if (!vma)
+		goto unlock;
+
+	/*
+	 * Validate the VMA found by the lockless lookup.
+	 */
+	dead = RB_EMPTY_NODE(&vma->vm_rb);
+	seq = raw_read_seqcount(&vma->vm_sequence); /* rmb <-> seqlock,vma_rb_erase() */
+	if ((seq & 1) || dead)
+		goto unlock;
+
+	/*
+	 * We need to re-validate the VMA after checking the bounds, otherwise
+	 * we might have a false positive on the bounds.
+	 */
+	if (address < vma->vm_start || vma->vm_end <= address)
+		goto unlock;
+
+	/*
+	 * Huge pages are not yet supported.
+	 */
+	if (unlikely(is_vm_hugetlb_page(vma)))
+		goto unlock;
+
+	/*
+	 * The three following checks are copied from access_error from
+	 * arch/x86/mm/fault.c
+	 */
+	if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE,
+				       flags & FAULT_FLAG_INSTRUCTION,
+				       flags & FAULT_FLAG_REMOTE))
+		goto unlock;
+
+	/* This is one is required to check that the VMA has write access set */
+	if (flags & FAULT_FLAG_WRITE) {
+		if (unlikely(!(vma->vm_flags & VM_WRITE)))
+			goto unlock;
+	} else {
+		if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
+			goto unlock;
+	}
+
+	if (read_seqcount_retry(&vma->vm_sequence, seq))
+		goto unlock;
+
+	/*
+	 * Do a speculative lookup of the PTE entry.
+	 */
+	local_irq_disable();
+	pgd = pgd_offset(mm, address);
+	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
+		goto out_walk;
+
+	p4d = p4d_alloc(mm, pgd, address);
+	if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d)))
+		goto out_walk;
+
+	pud = pud_alloc(mm, p4d, address);
+	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
+		goto out_walk;
+
+	pmd = pmd_offset(pud, address);
+	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+		goto out_walk;
+
+	/*
+	 * The above does not allocate/instantiate page-tables because doing so
+	 * would lead to the possibility of instantiating page-tables after
+	 * free_pgtables() -- and consequently leaking them.
+	 *
+	 * The result is that we take at least one !speculative fault per PMD
+	 * in order to instantiate it.
+	 */
+
+	if (unlikely(pmd_huge(*pmd)))
+		goto out_walk;
+
+	vmf.vma = vma;
+	vmf.pmd = pmd;
+	vmf.pgoff = linear_page_index(vma, address);
+	vmf.gfp_mask = __get_fault_gfp_mask(vma);
+	vmf.sequence = seq;
+	vmf.flags = flags;
+
+	local_irq_enable();
+
+	ret = handle_pte_fault(&vmf);
+
+unlock:
+	srcu_read_unlock(&vma_srcu, idx);
+	return ret;
+
+out_walk:
+	local_irq_enable();
+	goto unlock;
+}
+
 /*
  * By the time we get here, we already hold the mm semaphore
  *

@@ -1365,6 +1365,19 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	if (error_code & PF_INSTR)
 		flags |= FAULT_FLAG_INSTRUCTION;
 
+	if (error_code & PF_USER) {
+		fault = handle_speculative_fault(mm, address, flags);
+
+		/*
+		 * We also check against VM_FAULT_ERROR because we have to
+		 * raise a signal by calling later mm_fault_error() which
+		 * requires the vma pointer to be set. So in that case,
+		 * we fall through the normal path.
+		 */
+		if (!(fault & VM_FAULT_RETRY || fault & VM_FAULT_ERROR))
+			goto done;
+	}
+
 	/*
 	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in

@@ -1474,6 +1487,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		return;
 	}
 
+done:
 	/*
 	 * Major/minor page fault accounting. If any of the events
 	 * returned VM_FAULT_MAJOR, we account it as a major fault.

@@ -291,9 +291,31 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (is_write && is_user)
 		store_update_sp = store_updates_sp(regs);
 
-	if (is_user)
+	if (is_user) {
 		flags |= FAULT_FLAG_USER;
 
+		/* let's try a speculative page fault without grabbing the
+		 * mmap_sem.
+		 */
+
+		/*
+		 * flags is set later based on the VMA's flags, for the common
+		 * speculative service, we need some flags to be set.
+		 */
+		if (is_write)
+			flags |= FAULT_FLAG_WRITE;
+
+		fault = handle_speculative_fault(mm, address, flags);
+		if (!(fault & VM_FAULT_RETRY || fault & VM_FAULT_ERROR))
+			goto done;
+
+		/*
+		 * Resetting flags since the following code assumes
+		 * FAULT_FLAG_WRITE is not set.
+		 */
+		flags &= ~FAULT_FLAG_WRITE;
+	}
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an

@@ -479,6 +501,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 			rc = 0;
 	}
 
+done:
 	/*
 	 * Major/minor page fault accounting.
 	 */

@@ -587,7 +587,9 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 * Hide vma from rmap and truncate_pagecache before freeing
 		 * pgtables
 		 */
+		write_seqcount_begin(&vma->vm_sequence);
 		unlink_anon_vmas(vma);
+		write_seqcount_end(&vma->vm_sequence);
 		unlink_file_vma(vma);
 
 		if (is_vm_hugetlb_page(vma)) {

@@ -601,7 +603,9 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			       && !is_vm_hugetlb_page(next)) {
 				vma = next;
 				next = vma->vm_next;
+				write_seqcount_begin(&vma->vm_sequence);
 				unlink_anon_vmas(vma);
+				write_seqcount_end(&vma->vm_sequence);
 				unlink_file_vma(vma);
 			}
 			free_pgd_range(tlb, addr, vma->vm_end,

@@ -2403,7 +2407,7 @@ 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, vma);
 		/*

@@ -2873,7 +2877,7 @@ 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, vma);
 	}

@@ -3015,7 +3019,7 @@ 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, vma);
 setpte:

@@ -3940,6 +3944,9 @@ int handle_speculative_fault(struct mm_struct *mm, unsigned long address,
 	if (address < vma->vm_start || vma->vm_end <= address)
 		goto unlock;
 
+	if (unlikely(!vma->anon_vma))
+		goto unlock;
+
 	/*
 	 * Huge pages are not yet supported.
 	 */