1 files changed, 227 insertions, 152 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 21a5e6e4758b..47fe250307c7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -69,6 +69,7 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/dax.h>
 #include <linux/oom.h>
+#include <linux/numa.h>
 
 #include <asm/io.h>
 #include <asm/mmu_context.h>
@@ -400,10 +401,10 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	}
 }
 
-int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+int __pte_alloc(struct mm_struct *mm, pmd_t *pmd)
 {
 	spinlock_t *ptl;
-	pgtable_t new = pte_alloc_one(mm, address);
+	pgtable_t new = pte_alloc_one(mm);
 	if (!new)
 		return -ENOMEM;
 
@@ -434,9 +435,9 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
 	return 0;
 }
 
-int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
+int __pte_alloc_kernel(pmd_t *pmd)
 {
-	pte_t *new = pte_alloc_one_kernel(&init_mm, address);
+	pte_t *new = pte_alloc_one_kernel(&init_mm);
 	if (!new)
 		return -ENOMEM;
 
@@ -973,8 +974,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	unsigned long next;
 	unsigned long addr = vma->vm_start;
 	unsigned long end = vma->vm_end;
-	unsigned long mmun_start;	/* For mmu_notifiers */
-	unsigned long mmun_end;		/* For mmu_notifiers */
+	struct mmu_notifier_range range;
 	bool is_cow;
 	int ret;
 
@@ -1008,11 +1008,11 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * is_cow_mapping() returns true.
 	 */
 	is_cow = is_cow_mapping(vma->vm_flags);
-	mmun_start = addr;
-	mmun_end   = end;
-	if (is_cow)
-		mmu_notifier_invalidate_range_start(src_mm, mmun_start,
-						    mmun_end);
+
+	if (is_cow) {
+		mmu_notifier_range_init(&range, src_mm, addr, end);
+		mmu_notifier_invalidate_range_start(&range);
+	}
 
 	ret = 0;
 	dst_pgd = pgd_offset(dst_mm, addr);
@@ -1029,7 +1029,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
 
 	if (is_cow)
-		mmu_notifier_invalidate_range_end(src_mm, mmun_start, mmun_end);
+		mmu_notifier_invalidate_range_end(&range);
 	return ret;
 }
 
@@ -1332,12 +1332,13 @@ void unmap_vmas(struct mmu_gather *tlb,
 		struct vm_area_struct *vma, unsigned long start_addr,
 		unsigned long end_addr)
 {
-	struct mm_struct *mm = vma->vm_mm;
+	struct mmu_notifier_range range;
 
-	mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
+	mmu_notifier_range_init(&range, vma->vm_mm, start_addr, end_addr);
+	mmu_notifier_invalidate_range_start(&range);
 	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next)
 		unmap_single_vma(tlb, vma, start_addr, end_addr, NULL);
-	mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
+	mmu_notifier_invalidate_range_end(&range);
 }
 
 /**
@@ -1351,18 +1352,18 @@ void unmap_vmas(struct mmu_gather *tlb,
 void zap_page_range(struct vm_area_struct *vma, unsigned long start,
 		unsigned long size)
 {
-	struct mm_struct *mm = vma->vm_mm;
+	struct mmu_notifier_range range;
 	struct mmu_gather tlb;
-	unsigned long end = start + size;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, start, end);
-	update_hiwater_rss(mm);
-	mmu_notifier_invalidate_range_start(mm, start, end);
-	for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
-		unmap_single_vma(&tlb, vma, start, end, NULL);
-	mmu_notifier_invalidate_range_end(mm, start, end);
-	tlb_finish_mmu(&tlb, start, end);
+	mmu_notifier_range_init(&range, vma->vm_mm, start, start + size);
+	tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end);
+	update_hiwater_rss(vma->vm_mm);
+	mmu_notifier_invalidate_range_start(&range);
+	for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next)
+		unmap_single_vma(&tlb, vma, start, range.end, NULL);
+	mmu_notifier_invalidate_range_end(&range);
+	tlb_finish_mmu(&tlb, start, range.end);
 }
 
 /**
@@ -1377,17 +1378,17 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
 static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size, struct zap_details *details)
 {
-	struct mm_struct *mm = vma->vm_mm;
+	struct mmu_notifier_range range;
 	struct mmu_gather tlb;
-	unsigned long end = address + size;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, address, end);
-	update_hiwater_rss(mm);
-	mmu_notifier_invalidate_range_start(mm, address, end);
-	unmap_single_vma(&tlb, vma, address, end, details);
-	mmu_notifier_invalidate_range_end(mm, address, end);
-	tlb_finish_mmu(&tlb, address, end);
+	mmu_notifier_range_init(&range, vma->vm_mm, address, address + size);
+	tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end);
+	update_hiwater_rss(vma->vm_mm);
+	mmu_notifier_invalidate_range_start(&range);
+	unmap_single_vma(&tlb, vma, address, range.end, details);
+	mmu_notifier_invalidate_range_end(&range);
+	tlb_finish_mmu(&tlb, address, range.end);
 }
 
 /**
@@ -1451,7 +1452,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
 	spinlock_t *ptl;
 
 	retval = -EINVAL;
-	if (PageAnon(page))
+	if (PageAnon(page) || PageSlab(page) || page_has_type(page))
 		goto out;
 	retval = -ENOMEM;
 	flush_dcache_page(page);
@@ -1503,6 +1504,8 @@ out:
  * under mm->mmap_sem write-lock, so it can change vma->vm_flags.
  * Caller must set VM_MIXEDMAP on vma if it wants to call this
  * function from other places, for example from page-fault handler.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 			struct page *page)
@@ -1520,19 +1523,16 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_insert_page);
 
-static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
+static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn, pgprot_t prot, bool mkwrite)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	int retval;
 	pte_t *pte, entry;
 	spinlock_t *ptl;
 
-	retval = -ENOMEM;
 	pte = get_locked_pte(mm, addr, &ptl);
 	if (!pte)
-		goto out;
-	retval = -EBUSY;
+		return VM_FAULT_OOM;
 	if (!pte_none(*pte)) {
 		if (mkwrite) {
 			/*
@@ -1540,10 +1540,15 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			 * in may not match the PFN we have mapped if the
 			 * mapped PFN is a writeable COW page.  In the mkwrite
 			 * case we are creating a writable PTE for a shared
-			 * mapping and we expect the PFNs to match.
+			 * mapping and we expect the PFNs to match. If they
+			 * don't match, we are likely racing with block
+			 * allocation and mapping invalidation so just skip the
+			 * update.
 			 */
-			if (WARN_ON_ONCE(pte_pfn(*pte) != pfn_t_to_pfn(pfn)))
+			if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) {
+				WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte)));
 				goto out_unlock;
+			}
 			entry = *pte;
 			goto out_mkwrite;
 		} else
@@ -1565,56 +1570,32 @@ out_mkwrite:
 	set_pte_at(mm, addr, pte, entry);
 	update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */
 
-	retval = 0;
 out_unlock:
 	pte_unmap_unlock(pte, ptl);
-out:
-	return retval;
-}
-
-/**
- * vm_insert_pfn - insert single pfn into user vma
- * @vma: user vma to map to
- * @addr: target user address of this page
- * @pfn: source kernel pfn
- *
- * Similar to vm_insert_page, this allows drivers to insert individual pages
- * they've allocated into a user vma. Same comments apply.
- *
- * This function should only be called from a vm_ops->fault handler, and
- * in that case the handler should return NULL.
- *
- * vma cannot be a COW mapping.
- *
- * As this is called only for pages that do not currently exist, we
- * do not need to flush old virtual caches or the TLB.
- */
-int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
-			unsigned long pfn)
-{
-	return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
+	return VM_FAULT_NOPAGE;
 }
-EXPORT_SYMBOL(vm_insert_pfn);
 
 /**
- * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot
+ * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot
  * @vma: user vma to map to
  * @addr: target user address of this page
  * @pfn: source kernel pfn
  * @pgprot: pgprot flags for the inserted page
  *
- * This is exactly like vm_insert_pfn, except that it allows drivers to
+ * This is exactly like vmf_insert_pfn(), except that it allows drivers to
  * to override pgprot on a per-page basis.
  *
  * This only makes sense for IO mappings, and it makes no sense for
- * cow mappings.  In general, using multiple vmas is preferable;
- * vm_insert_pfn_prot should only be used if using multiple VMAs is
+ * COW mappings.  In general, using multiple vmas is preferable;
+ * vmf_insert_pfn_prot should only be used if using multiple VMAs is
  * impractical.
+ *
+ * Context: Process context.  May allocate using %GFP_KERNEL.
+ * Return: vm_fault_t value.
  */
-int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn, pgprot_t pgprot)
 {
-	int ret;
 	/*
 	 * Technically, architectures with pte_special can avoid all these
 	 * restrictions (same for remap_pfn_range).  However we would like
@@ -1628,19 +1609,44 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 	BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
-		return -EFAULT;
+		return VM_FAULT_SIGBUS;
 
 	if (!pfn_modify_allowed(pfn, pgprot))
-		return -EACCES;
+		return VM_FAULT_SIGBUS;
 
 	track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
 
-	ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
+	return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
 			false);
+}
+EXPORT_SYMBOL(vmf_insert_pfn_prot);
 
-	return ret;
+/**
+ * vmf_insert_pfn - insert single pfn into user vma
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ *
+ * Similar to vm_insert_page, this allows drivers to insert individual pages
+ * they've allocated into a user vma. Same comments apply.
+ *
+ * This function should only be called from a vm_ops->fault handler, and
+ * in that case the handler should return the result of this function.
+ *
+ * vma cannot be a COW mapping.
+ *
+ * As this is called only for pages that do not currently exist, we
+ * do not need to flush old virtual caches or the TLB.
+ *
+ * Context: Process context.  May allocate using %GFP_KERNEL.
+ * Return: vm_fault_t value.
+ */
+vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn)
+{
+	return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
 }
-EXPORT_SYMBOL(vm_insert_pfn_prot);
+EXPORT_SYMBOL(vmf_insert_pfn);
 
 static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn)
 {
@@ -1656,20 +1662,21 @@ static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn)
 	return false;
 }
 
-static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
-			pfn_t pfn, bool mkwrite)
+static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
+		unsigned long addr, pfn_t pfn, bool mkwrite)
 {
 	pgprot_t pgprot = vma->vm_page_prot;
+	int err;
 
 	BUG_ON(!vm_mixed_ok(vma, pfn));
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
-		return -EFAULT;
+		return VM_FAULT_SIGBUS;
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
 	if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
-		return -EACCES;
+		return VM_FAULT_SIGBUS;
 
 	/*
 	 * If we don't have pte special, then we have to use the pfn_valid()
@@ -1688,36 +1695,35 @@ static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 		 * result in pfn_t_has_page() == false.
 		 */
 		page = pfn_to_page(pfn_t_to_pfn(pfn));
-		return insert_page(vma, addr, page, pgprot);
+		err = insert_page(vma, addr, page, pgprot);
+	} else {
+		return insert_pfn(vma, addr, pfn, pgprot, mkwrite);
 	}
-	return insert_pfn(vma, addr, pfn, pgprot, mkwrite);
+
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err < 0 && err != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
 }
 
-int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
-			pfn_t pfn)
+vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
+		pfn_t pfn)
 {
 	return __vm_insert_mixed(vma, addr, pfn, false);
-
 }
-EXPORT_SYMBOL(vm_insert_mixed);
+EXPORT_SYMBOL(vmf_insert_mixed);
 
 /*
  *  If the insertion of PTE failed because someone else already added a
  *  different entry in the mean time, we treat that as success as we assume
  *  the same entry was actually inserted.
  */
-
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
 		unsigned long addr, pfn_t pfn)
 {
-	int err;
-
-	err =  __vm_insert_mixed(vma, addr, pfn, true);
-	if (err == -ENOMEM)
-		return VM_FAULT_OOM;
-	if (err < 0 && err != -EBUSY)
-		return VM_FAULT_SIGBUS;
-	return VM_FAULT_NOPAGE;
+	return __vm_insert_mixed(vma, addr, pfn, true);
 }
 EXPORT_SYMBOL(vmf_insert_mixed_mkwrite);
 
@@ -1827,7 +1833,9 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
  * @size: size of map area
  * @prot: page protection flags for this mapping
  *
- *  Note: this is only safe if the mm semaphore is held when called.
+ * Note: this is only safe if the mm semaphore is held when called.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 		    unsigned long pfn, unsigned long size, pgprot_t prot)
@@ -1900,6 +1908,8 @@ EXPORT_SYMBOL(remap_pfn_range);
  *
  * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
  * whatever write-combining details or similar.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
 {
@@ -2244,9 +2254,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	struct page *new_page = NULL;
 	pte_t entry;
 	int page_copied = 0;
-	const unsigned long mmun_start = vmf->address & PAGE_MASK;
-	const unsigned long mmun_end = mmun_start + PAGE_SIZE;
 	struct mem_cgroup *memcg;
+	struct mmu_notifier_range range;
 
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;
@@ -2269,7 +2278,9 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 
 	__SetPageUptodate(new_page);
 
-	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+	mmu_notifier_range_init(&range, mm, vmf->address & PAGE_MASK,
+				(vmf->address & PAGE_MASK) + PAGE_SIZE);
+	mmu_notifier_invalidate_range_start(&range);
 
 	/*
 	 * Re-check the pte - we dropped the lock
@@ -2346,7 +2357,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	 * No need to double call mmu_notifier->invalidate_range() callback as
 	 * the above ptep_clear_flush_notify() did already call it.
 	 */
-	mmu_notifier_invalidate_range_only_end(mm, mmun_start, mmun_end);
+	mmu_notifier_invalidate_range_only_end(&range);
 	if (old_page) {
 		/*
 		 * Don't let another task, with possibly unlocked vma,
@@ -2377,12 +2388,13 @@ oom:
  *
  * This function handles all that is needed to finish a write page fault in a
  * shared mapping due to PTE being read-only once the mapped page is prepared.
- * It handles locking of PTE and modifying it. The function returns
- * VM_FAULT_WRITE on success, 0 when PTE got changed before we acquired PTE
- * lock.
+ * It handles locking of PTE and modifying it.
  *
  * The function expects the page to be locked or other protection against
  * concurrent faults / writeback (such as DAX radix tree locks).
+ *
+ * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before
+ * we acquired PTE lock.
  */
 vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf)
 {
@@ -2500,8 +2512,11 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	 * Take out anonymous pages first, anonymous shared vmas are
 	 * not dirty accountable.
 	 */
-	if (PageAnon(vmf->page) && !PageKsm(vmf->page)) {
+	if (PageAnon(vmf->page)) {
 		int total_map_swapcount;
+		if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) ||
+					   page_count(vmf->page) != 1))
+			goto copy;
 		if (!trylock_page(vmf->page)) {
 			get_page(vmf->page);
 			pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -2516,6 +2531,15 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 			}
 			put_page(vmf->page);
 		}
+		if (PageKsm(vmf->page)) {
+			bool reused = reuse_ksm_page(vmf->page, vmf->vma,
+						     vmf->address);
+			unlock_page(vmf->page);
+			if (!reused)
+				goto copy;
+			wp_page_reuse(vmf);
+			return VM_FAULT_WRITE;
+		}
 		if (reuse_swap_page(vmf->page, &total_map_swapcount)) {
 			if (total_map_swapcount == 1) {
 				/*
@@ -2536,7 +2560,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 					(VM_WRITE|VM_SHARED))) {
 		return wp_page_shared(vmf);
 	}
-
+copy:
 	/*
 	 * Ok, we need to copy. Oh, well..
 	 */
@@ -2892,7 +2916,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	 *
 	 * Here we only have down_read(mmap_sem).
 	 */
-	if (pte_alloc(vma->vm_mm, vmf->pmd, vmf->address))
+	if (pte_alloc(vma->vm_mm, vmf->pmd))
 		return VM_FAULT_OOM;
 
 	/* See the comment in pte_alloc_one_map() */
@@ -2990,6 +3014,28 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	vm_fault_t ret;
 
+	/*
+	 * Preallocate pte before we take page_lock because this might lead to
+	 * deadlocks for memcg reclaim which waits for pages under writeback:
+	 *				lock_page(A)
+	 *				SetPageWriteback(A)
+	 *				unlock_page(A)
+	 * lock_page(B)
+	 *				lock_page(B)
+	 * pte_alloc_pne
+	 *   shrink_page_list
+	 *     wait_on_page_writeback(A)
+	 *				SetPageWriteback(B)
+	 *				unlock_page(B)
+	 *				# flush A, B to clear the writeback
+	 */
+	if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) {
+		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
+		if (!vmf->prealloc_pte)
+			return VM_FAULT_OOM;
+		smp_wmb(); /* See comment in __pte_alloc() */
+	}
+
 	ret = vma->vm_ops->fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY |
 			    VM_FAULT_DONE_COW)))
@@ -3039,7 +3085,7 @@ static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf)
 		pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
 		spin_unlock(vmf->ptl);
 		vmf->prealloc_pte = NULL;
-	} else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd, vmf->address))) {
+	} else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) {
 		return VM_FAULT_OOM;
 	}
 map_pte:
@@ -3118,7 +3164,7 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	 * related to pte entry. Use the preallocated table for that.
 	 */
 	if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) {
-		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm, vmf->address);
+		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
 		smp_wmb(); /* See comment in __pte_alloc() */
@@ -3175,6 +3221,8 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
  *
  * Target users are page handler itself and implementations of
  * vm_ops->map_pages.
+ *
+ * Return: %0 on success, %VM_FAULT_ code in case of error.
  */
 vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 		struct page *page)
@@ -3235,11 +3283,12 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
  * This function handles all that is needed to finish a page fault once the
  * page to fault in is prepared. It handles locking of PTEs, inserts PTE for
  * given page, adds reverse page mapping, handles memcg charges and LRU
- * addition. The function returns 0 on success, VM_FAULT_ code in case of
- * error.
+ * addition.
  *
  * The function expects the page to be locked and on success it consumes a
  * reference of a page being mapped (for the PTE which maps it).
+ *
+ * Return: %0 on success, %VM_FAULT_ code in case of error.
  */
 vm_fault_t finish_fault(struct vm_fault *vmf)
 {
@@ -3295,12 +3344,8 @@ DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops,
 
 static int __init fault_around_debugfs(void)
 {
-	void *ret;
-
-	ret = debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL,
-			&fault_around_bytes_fops);
-	if (!ret)
-		pr_warn("Failed to create fault_around_bytes in debugfs");
+	debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL,
+				   &fault_around_bytes_fops);
 	return 0;
 }
 late_initcall(fault_around_debugfs);
@@ -3356,8 +3401,7 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 			start_pgoff + nr_pages - 1);
 
 	if (pmd_none(*vmf->pmd)) {
-		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm,
-						  vmf->address);
+		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			goto out;
 		smp_wmb(); /* See comment in __pte_alloc() */
@@ -3492,16 +3536,45 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
  * but allow concurrent faults).
  * The mmap_sem may have been released depending on flags and our
  * return value.  See filemap_fault() and __lock_page_or_retry().
+ * If mmap_sem is released, vma may become invalid (for example
+ * by other thread calling munmap()).
  */
 static vm_fault_t do_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	struct mm_struct *vm_mm = vma->vm_mm;
 	vm_fault_t ret;
 
-	/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
-	if (!vma->vm_ops->fault)
-		ret = VM_FAULT_SIGBUS;
-	else if (!(vmf->flags & FAULT_FLAG_WRITE))
+	/*
+	 * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND
+	 */
+	if (!vma->vm_ops->fault) {
+		/*
+		 * If we find a migration pmd entry or a none pmd entry, which
+		 * should never happen, return SIGBUS
+		 */
+		if (unlikely(!pmd_present(*vmf->pmd)))
+			ret = VM_FAULT_SIGBUS;
+		else {
+			vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm,
+						       vmf->pmd,
+						       vmf->address,
+						       &vmf->ptl);
+			/*
+			 * Make sure this is not a temporary clearing of pte
+			 * by holding ptl and checking again. A R/M/W update
+			 * of pte involves: take ptl, clearing the pte so that
+			 * we don't have concurrent modification by hardware
+			 * followed by an update.
+			 */
+			if (unlikely(pte_none(*vmf->pte)))
+				ret = VM_FAULT_SIGBUS;
+			else
+				ret = VM_FAULT_NOPAGE;
+
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+		}
+	} else if (!(vmf->flags & FAULT_FLAG_WRITE))
 		ret = do_read_fault(vmf);
 	else if (!(vma->vm_flags & VM_SHARED))
 		ret = do_cow_fault(vmf);
@@ -3510,7 +3583,7 @@ static vm_fault_t do_fault(struct vm_fault *vmf)
 
 	/* preallocated pagetable is unused: free it */
 	if (vmf->prealloc_pte) {
-		pte_free(vma->vm_mm, vmf->prealloc_pte);
+		pte_free(vm_mm, vmf->prealloc_pte);
 		vmf->prealloc_pte = NULL;
 	}
 	return ret;
@@ -3535,11 +3608,11 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = NULL;
-	int page_nid = -1;
+	int page_nid = NUMA_NO_NODE;
 	int last_cpupid;
 	int target_nid;
 	bool migrated = false;
-	pte_t pte;
+	pte_t pte, old_pte;
 	bool was_writable = pte_savedwrite(vmf->orig_pte);
 	int flags = 0;
 
@@ -3559,12 +3632,12 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	 * Make it present again, Depending on how arch implementes non
 	 * 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);
+	old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte);
+	pte = pte_modify(old_pte, vma->vm_page_prot);
 	pte = pte_mkyoung(pte);
 	if (was_writable)
 		pte = pte_mkwrite(pte);
-	ptep_modify_prot_commit(vma->vm_mm, vmf->address, vmf->pte, pte);
+	ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte);
 	update_mmu_cache(vma, vmf->address, vmf->pte);
 
 	page = vm_normal_page(vma, vmf->address, pte);
@@ -3602,7 +3675,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid,
 			&flags);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
-	if (target_nid == -1) {
+	if (target_nid == NUMA_NO_NODE) {
 		put_page(page);
 		goto out;
 	}
@@ -3616,7 +3689,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 		flags |= TNF_MIGRATE_FAIL;
 
 out:
-	if (page_nid != -1)
+	if (page_nid != NUMA_NO_NODE)
 		task_numa_fault(last_cpupid, page_nid, 1, flags);
 	return 0;
 }
@@ -3801,7 +3874,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 	vmf.pud = pud_alloc(mm, p4d, address);
 	if (!vmf.pud)
 		return VM_FAULT_OOM;
-	if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
+	if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) {
 		ret = create_huge_pud(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
@@ -3827,7 +3900,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 	vmf.pmd = pmd_alloc(mm, vmf.pud, address);
 	if (!vmf.pmd)
 		return VM_FAULT_OOM;
-	if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) {
+	if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) {
 		ret = create_huge_pmd(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
@@ -4001,7 +4074,7 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 #endif /* __PAGETABLE_PMD_FOLDED */
 
 static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
-			    unsigned long *start, unsigned long *end,
+			    struct mmu_notifier_range *range,
 			    pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
@@ -4029,10 +4102,10 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 		if (!pmdpp)
 			goto out;
 
-		if (start && end) {
-			*start = address & PMD_MASK;
-			*end = *start + PMD_SIZE;
-			mmu_notifier_invalidate_range_start(mm, *start, *end);
+		if (range) {
+			mmu_notifier_range_init(range, mm, address & PMD_MASK,
+					     (address & PMD_MASK) + PMD_SIZE);
+			mmu_notifier_invalidate_range_start(range);
 		}
 		*ptlp = pmd_lock(mm, pmd);
 		if (pmd_huge(*pmd)) {
@@ -4040,17 +4113,17 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 			return 0;
 		}
 		spin_unlock(*ptlp);
-		if (start && end)
-			mmu_notifier_invalidate_range_end(mm, *start, *end);
+		if (range)
+			mmu_notifier_invalidate_range_end(range);
 	}
 
 	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
 		goto out;
 
-	if (start && end) {
-		*start = address & PAGE_MASK;
-		*end = *start + PAGE_SIZE;
-		mmu_notifier_invalidate_range_start(mm, *start, *end);
+	if (range) {
+		mmu_notifier_range_init(range, mm, address & PAGE_MASK,
+				     (address & PAGE_MASK) + PAGE_SIZE);
+		mmu_notifier_invalidate_range_start(range);
 	}
 	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
 	if (!pte_present(*ptep))
@@ -4059,8 +4132,8 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 	return 0;
 unlock:
 	pte_unmap_unlock(ptep, *ptlp);
-	if (start && end)
-		mmu_notifier_invalidate_range_end(mm, *start, *end);
+	if (range)
+		mmu_notifier_invalidate_range_end(range);
 out:
 	return -EINVAL;
 }
@@ -4072,20 +4145,20 @@ static inline int follow_pte(struct mm_struct *mm, unsigned long address,
 
 	/* (void) is needed to make gcc happy */
 	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte_pmd(mm, address, NULL, NULL,
+			   !(res = __follow_pte_pmd(mm, address, NULL,
 						    ptepp, NULL, ptlp)));
 	return res;
 }
 
 int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
-			     unsigned long *start, unsigned long *end,
-			     pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
+		   struct mmu_notifier_range *range,
+		   pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	int res;
 
 	/* (void) is needed to make gcc happy */
 	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte_pmd(mm, address, start, end,
+			   !(res = __follow_pte_pmd(mm, address, range,
 						    ptepp, pmdpp, ptlp)));
 	return res;
 }
@@ -4099,7 +4172,7 @@ EXPORT_SYMBOL(follow_pte_pmd);
  *
  * Only IO mappings and raw PFN mappings are allowed.
  *
- * Returns zero and the pfn at @pfn on success, -ve otherwise.
+ * Return: zero and the pfn at @pfn on success, -ve otherwise.
  */
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
 	unsigned long *pfn)
@@ -4249,6 +4322,8 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
  * @gup_flags:	flags modifying lookup behaviour
  *
  * The caller must hold a reference on @mm.
+ *
+ * Return: number of bytes copied from source to destination.
  */
 int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags)