Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/memory.c b/mm/memory.c
index 4bb7c6a..4fe24cd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -65,12 +65,16 @@
 #include <linux/gfp.h>
 #include <linux/migrate.h>
 #include <linux/string.h>
-#include <linux/dma-debug.h>
 #include <linux/debugfs.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/dax.h>
 #include <linux/oom.h>
 #include <linux/numa.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+#include <linux/vmalloc.h>
+
+#include <trace/events/kmem.h>
 
 #include <asm/io.h>
 #include <asm/mmu_context.h>
@@ -78,8 +82,8 @@
 #include <linux/uaccess.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
-#include <asm/pgtable.h>
 
+#include "pgalloc-track.h"
 #include "internal.h"
 
 #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
@@ -152,6 +156,10 @@
 }
 early_initcall(init_zero_pfn);
 
+void mm_trace_rss_stat(struct mm_struct *mm, int member, long count)
+{
+	trace_rss_stat(mm, member, count);
+}
 
 #if defined(SPLIT_RSS_COUNTING)
 
@@ -432,7 +440,7 @@
 	 * of a chain of data-dependent loads, meaning most CPUs (alpha
 	 * being the notable exception) will already guarantee loads are
 	 * seen in-order. See the alpha page table accessors for the
-	 * smp_read_barrier_depends() barriers in page table walking code.
+	 * smp_rmb() barriers in page table walking code.
 	 */
 	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
 
@@ -666,7 +674,7 @@
 
 	if (pmd_devmap(pmd))
 		return NULL;
-	if (is_zero_pfn(pfn))
+	if (is_huge_zero_pmd(pmd))
 		return NULL;
 	if (unlikely(pfn > highest_memmap_pfn))
 		return NULL;
@@ -686,80 +694,186 @@
  * covered by this vma.
  */
 
-static inline unsigned long
-copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
-		unsigned long addr, int *rss)
+static unsigned long
+copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma,
+		struct vm_area_struct *src_vma, unsigned long addr, int *rss)
 {
-	unsigned long vm_flags = vma->vm_flags;
+	unsigned long vm_flags = dst_vma->vm_flags;
+	pte_t pte = *src_pte;
+	struct page *page;
+	swp_entry_t entry = pte_to_swp_entry(pte);
+
+	if (likely(!non_swap_entry(entry))) {
+		if (swap_duplicate(entry) < 0)
+			return entry.val;
+
+		/* make sure dst_mm is on swapoff's mmlist. */
+		if (unlikely(list_empty(&dst_mm->mmlist))) {
+			spin_lock(&mmlist_lock);
+			if (list_empty(&dst_mm->mmlist))
+				list_add(&dst_mm->mmlist,
+						&src_mm->mmlist);
+			spin_unlock(&mmlist_lock);
+		}
+		rss[MM_SWAPENTS]++;
+	} else if (is_migration_entry(entry)) {
+		page = migration_entry_to_page(entry);
+
+		rss[mm_counter(page)]++;
+
+		if (is_write_migration_entry(entry) &&
+				is_cow_mapping(vm_flags)) {
+			/*
+			 * COW mappings require pages in both
+			 * parent and child to be set to read.
+			 */
+			make_migration_entry_read(&entry);
+			pte = swp_entry_to_pte(entry);
+			if (pte_swp_soft_dirty(*src_pte))
+				pte = pte_swp_mksoft_dirty(pte);
+			if (pte_swp_uffd_wp(*src_pte))
+				pte = pte_swp_mkuffd_wp(pte);
+			set_pte_at(src_mm, addr, src_pte, pte);
+		}
+	} else if (is_device_private_entry(entry)) {
+		page = device_private_entry_to_page(entry);
+
+		/*
+		 * Update rss count even for unaddressable pages, as
+		 * they should treated just like normal pages in this
+		 * respect.
+		 *
+		 * We will likely want to have some new rss counters
+		 * for unaddressable pages, at some point. But for now
+		 * keep things as they are.
+		 */
+		get_page(page);
+		rss[mm_counter(page)]++;
+		page_dup_rmap(page, false);
+
+		/*
+		 * We do not preserve soft-dirty information, because so
+		 * far, checkpoint/restore is the only feature that
+		 * requires that. And checkpoint/restore does not work
+		 * when a device driver is involved (you cannot easily
+		 * save and restore device driver state).
+		 */
+		if (is_write_device_private_entry(entry) &&
+		    is_cow_mapping(vm_flags)) {
+			make_device_private_entry_read(&entry);
+			pte = swp_entry_to_pte(entry);
+			if (pte_swp_uffd_wp(*src_pte))
+				pte = pte_swp_mkuffd_wp(pte);
+			set_pte_at(src_mm, addr, src_pte, pte);
+		}
+	}
+	if (!userfaultfd_wp(dst_vma))
+		pte = pte_swp_clear_uffd_wp(pte);
+	set_pte_at(dst_mm, addr, dst_pte, pte);
+	return 0;
+}
+
+/*
+ * Copy a present and normal page if necessary.
+ *
+ * NOTE! The usual case is that this doesn't need to do
+ * anything, and can just return a positive value. That
+ * will let the caller know that it can just increase
+ * the page refcount and re-use the pte the traditional
+ * way.
+ *
+ * But _if_ we need to copy it because it needs to be
+ * pinned in the parent (and the child should get its own
+ * copy rather than just a reference to the same page),
+ * we'll do that here and return zero to let the caller
+ * know we're done.
+ *
+ * And if we need a pre-allocated page but don't yet have
+ * one, return a negative error to let the preallocation
+ * code know so that it can do so outside the page table
+ * lock.
+ */
+static inline int
+copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+		  pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
+		  struct page **prealloc, pte_t pte, struct page *page)
+{
+	struct mm_struct *src_mm = src_vma->vm_mm;
+	struct page *new_page;
+
+	if (!is_cow_mapping(src_vma->vm_flags))
+		return 1;
+
+	/*
+	 * What we want to do is to check whether this page may
+	 * have been pinned by the parent process.  If so,
+	 * instead of wrprotect the pte on both sides, we copy
+	 * the page immediately so that we'll always guarantee
+	 * the pinned page won't be randomly replaced in the
+	 * future.
+	 *
+	 * The page pinning checks are just "has this mm ever
+	 * seen pinning", along with the (inexact) check of
+	 * the page count. That might give false positives for
+	 * for pinning, but it will work correctly.
+	 */
+	if (likely(!atomic_read(&src_mm->has_pinned)))
+		return 1;
+	if (likely(!page_maybe_dma_pinned(page)))
+		return 1;
+
+	new_page = *prealloc;
+	if (!new_page)
+		return -EAGAIN;
+
+	/*
+	 * We have a prealloc page, all good!  Take it
+	 * over and copy the page & arm it.
+	 */
+	*prealloc = NULL;
+	copy_user_highpage(new_page, page, addr, src_vma);
+	__SetPageUptodate(new_page);
+	page_add_new_anon_rmap(new_page, dst_vma, addr, false);
+	lru_cache_add_inactive_or_unevictable(new_page, dst_vma);
+	rss[mm_counter(new_page)]++;
+
+	/* All done, just insert the new page copy in the child */
+	pte = mk_pte(new_page, dst_vma->vm_page_prot);
+	pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma);
+	if (userfaultfd_pte_wp(dst_vma, *src_pte))
+		/* Uffd-wp needs to be delivered to dest pte as well */
+		pte = pte_wrprotect(pte_mkuffd_wp(pte));
+	set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
+	return 0;
+}
+
+/*
+ * Copy one pte.  Returns 0 if succeeded, or -EAGAIN if one preallocated page
+ * is required to copy this pte.
+ */
+static inline int
+copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+		 pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
+		 struct page **prealloc)
+{
+	struct mm_struct *src_mm = src_vma->vm_mm;
+	unsigned long vm_flags = src_vma->vm_flags;
 	pte_t pte = *src_pte;
 	struct page *page;
 
-	/* pte contains position in swap or file, so copy. */
-	if (unlikely(!pte_present(pte))) {
-		swp_entry_t entry = pte_to_swp_entry(pte);
+	page = vm_normal_page(src_vma, addr, pte);
+	if (page) {
+		int retval;
 
-		if (likely(!non_swap_entry(entry))) {
-			if (swap_duplicate(entry) < 0)
-				return entry.val;
+		retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
+					   addr, rss, prealloc, pte, page);
+		if (retval <= 0)
+			return retval;
 
-			/* make sure dst_mm is on swapoff's mmlist. */
-			if (unlikely(list_empty(&dst_mm->mmlist))) {
-				spin_lock(&mmlist_lock);
-				if (list_empty(&dst_mm->mmlist))
-					list_add(&dst_mm->mmlist,
-							&src_mm->mmlist);
-				spin_unlock(&mmlist_lock);
-			}
-			rss[MM_SWAPENTS]++;
-		} else if (is_migration_entry(entry)) {
-			page = migration_entry_to_page(entry);
-
-			rss[mm_counter(page)]++;
-
-			if (is_write_migration_entry(entry) &&
-					is_cow_mapping(vm_flags)) {
-				/*
-				 * COW mappings require pages in both
-				 * parent and child to be set to read.
-				 */
-				make_migration_entry_read(&entry);
-				pte = swp_entry_to_pte(entry);
-				if (pte_swp_soft_dirty(*src_pte))
-					pte = pte_swp_mksoft_dirty(pte);
-				set_pte_at(src_mm, addr, src_pte, pte);
-			}
-		} else if (is_device_private_entry(entry)) {
-			page = device_private_entry_to_page(entry);
-
-			/*
-			 * Update rss count even for unaddressable pages, as
-			 * they should treated just like normal pages in this
-			 * respect.
-			 *
-			 * We will likely want to have some new rss counters
-			 * for unaddressable pages, at some point. But for now
-			 * keep things as they are.
-			 */
-			get_page(page);
-			rss[mm_counter(page)]++;
-			page_dup_rmap(page, false);
-
-			/*
-			 * We do not preserve soft-dirty information, because so
-			 * far, checkpoint/restore is the only feature that
-			 * requires that. And checkpoint/restore does not work
-			 * when a device driver is involved (you cannot easily
-			 * save and restore device driver state).
-			 */
-			if (is_write_device_private_entry(entry) &&
-			    is_cow_mapping(vm_flags)) {
-				make_device_private_entry_read(&entry);
-				pte = swp_entry_to_pte(entry);
-				set_pte_at(src_mm, addr, src_pte, pte);
-			}
-		}
-		goto out_set_pte;
+		get_page(page);
+		page_dup_rmap(page, false);
+		rss[mm_counter(page)]++;
 	}
 
 	/*
@@ -779,37 +893,56 @@
 		pte = pte_mkclean(pte);
 	pte = pte_mkold(pte);
 
-	page = vm_normal_page(vma, addr, pte);
-	if (page) {
-		get_page(page);
-		page_dup_rmap(page, false);
-		rss[mm_counter(page)]++;
-	} else if (pte_devmap(pte)) {
-		page = pte_page(pte);
-	}
+	if (!userfaultfd_wp(dst_vma))
+		pte = pte_clear_uffd_wp(pte);
 
-out_set_pte:
-	set_pte_at(dst_mm, addr, dst_pte, pte);
+	set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
 	return 0;
 }
 
-static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		   pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
-		   unsigned long addr, unsigned long end)
+static inline struct page *
+page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma,
+		   unsigned long addr)
 {
+	struct page *new_page;
+
+	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr);
+	if (!new_page)
+		return NULL;
+
+	if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) {
+		put_page(new_page);
+		return NULL;
+	}
+	cgroup_throttle_swaprate(new_page, GFP_KERNEL);
+
+	return new_page;
+}
+
+static int
+copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
+	       unsigned long end)
+{
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	pte_t *orig_src_pte, *orig_dst_pte;
 	pte_t *src_pte, *dst_pte;
 	spinlock_t *src_ptl, *dst_ptl;
-	int progress = 0;
+	int progress, ret = 0;
 	int rss[NR_MM_COUNTERS];
 	swp_entry_t entry = (swp_entry_t){0};
+	struct page *prealloc = NULL;
 
 again:
+	progress = 0;
 	init_rss_vec(rss);
 
 	dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
-	if (!dst_pte)
-		return -ENOMEM;
+	if (!dst_pte) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	src_pte = pte_offset_map(src_pmd, addr);
 	src_ptl = pte_lockptr(src_mm, src_pmd);
 	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
@@ -832,10 +965,35 @@
 			progress++;
 			continue;
 		}
-		entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
-							vma, addr, rss);
-		if (entry.val)
+		if (unlikely(!pte_present(*src_pte))) {
+			entry.val = copy_nonpresent_pte(dst_mm, src_mm,
+							dst_pte, src_pte,
+							dst_vma, src_vma,
+							addr, rss);
+			if (entry.val)
+				break;
+			progress += 8;
+			continue;
+		}
+		/* copy_present_pte() will clear `*prealloc' if consumed */
+		ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte,
+				       addr, rss, &prealloc);
+		/*
+		 * If we need a pre-allocated page for this pte, drop the
+		 * locks, allocate, and try again.
+		 */
+		if (unlikely(ret == -EAGAIN))
 			break;
+		if (unlikely(prealloc)) {
+			/*
+			 * pre-alloc page cannot be reused by next time so as
+			 * to strictly follow mempolicy (e.g., alloc_page_vma()
+			 * will allocate page according to address).  This
+			 * could only happen if one pinned pte changed.
+			 */
+			put_page(prealloc);
+			prealloc = NULL;
+		}
 		progress += 8;
 	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
 
@@ -847,19 +1005,34 @@
 	cond_resched();
 
 	if (entry.val) {
-		if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
+		if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		entry.val = 0;
+	} else if (ret) {
+		WARN_ON_ONCE(ret != -EAGAIN);
+		prealloc = page_copy_prealloc(src_mm, src_vma, addr);
+		if (!prealloc)
 			return -ENOMEM;
-		progress = 0;
+		/* We've captured and resolved the error. Reset, try again. */
+		ret = 0;
 	}
 	if (addr != end)
 		goto again;
-	return 0;
+out:
+	if (unlikely(prealloc))
+		put_page(prealloc);
+	return ret;
 }
 
-static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end)
+static inline int
+copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	pmd_t *src_pmd, *dst_pmd;
 	unsigned long next;
 
@@ -872,9 +1045,9 @@
 		if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd)
 			|| pmd_devmap(*src_pmd)) {
 			int err;
-			VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, vma);
-			err = copy_huge_pmd(dst_mm, src_mm,
-					    dst_pmd, src_pmd, addr, vma);
+			VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma);
+			err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd,
+					    addr, dst_vma, src_vma);
 			if (err == -ENOMEM)
 				return -ENOMEM;
 			if (!err)
@@ -883,17 +1056,20 @@
 		}
 		if (pmd_none_or_clear_bad(src_pmd))
 			continue;
-		if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
-						vma, addr, next))
+		if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd,
+				   addr, next))
 			return -ENOMEM;
 	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
 	return 0;
 }
 
-static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end)
+static inline int
+copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	pud_t *src_pud, *dst_pud;
 	unsigned long next;
 
@@ -906,9 +1082,9 @@
 		if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
 			int err;
 
-			VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, vma);
+			VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma);
 			err = copy_huge_pud(dst_mm, src_mm,
-					    dst_pud, src_pud, addr, vma);
+					    dst_pud, src_pud, addr, src_vma);
 			if (err == -ENOMEM)
 				return -ENOMEM;
 			if (!err)
@@ -917,17 +1093,19 @@
 		}
 		if (pud_none_or_clear_bad(src_pud))
 			continue;
-		if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
-						vma, addr, next))
+		if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud,
+				   addr, next))
 			return -ENOMEM;
 	} while (dst_pud++, src_pud++, addr = next, addr != end);
 	return 0;
 }
 
-static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end)
+static inline int
+copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
 	p4d_t *src_p4d, *dst_p4d;
 	unsigned long next;
 
@@ -939,20 +1117,22 @@
 		next = p4d_addr_end(addr, end);
 		if (p4d_none_or_clear_bad(src_p4d))
 			continue;
-		if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d,
-						vma, addr, next))
+		if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d,
+				   addr, next))
 			return -ENOMEM;
 	} while (dst_p4d++, src_p4d++, addr = next, addr != end);
 	return 0;
 }
 
-int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		struct vm_area_struct *vma)
+int
+copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 {
 	pgd_t *src_pgd, *dst_pgd;
 	unsigned long next;
-	unsigned long addr = vma->vm_start;
-	unsigned long end = vma->vm_end;
+	unsigned long addr = src_vma->vm_start;
+	unsigned long end = src_vma->vm_end;
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	struct mmu_notifier_range range;
 	bool is_cow;
 	int ret;
@@ -963,19 +1143,19 @@
 	 * readonly mappings. The tradeoff is that copy_page_range is more
 	 * efficient than faulting.
 	 */
-	if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
-			!vma->anon_vma)
+	if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
+	    !src_vma->anon_vma)
 		return 0;
 
-	if (is_vm_hugetlb_page(vma))
-		return copy_hugetlb_page_range(dst_mm, src_mm, vma);
+	if (is_vm_hugetlb_page(src_vma))
+		return copy_hugetlb_page_range(dst_mm, src_mm, src_vma);
 
-	if (unlikely(vma->vm_flags & VM_PFNMAP)) {
+	if (unlikely(src_vma->vm_flags & VM_PFNMAP)) {
 		/*
 		 * We do not free on error cases below as remove_vma
 		 * gets called on error from higher level routine
 		 */
-		ret = track_pfn_copy(vma);
+		ret = track_pfn_copy(src_vma);
 		if (ret)
 			return ret;
 	}
@@ -986,12 +1166,21 @@
 	 * parent mm. And a permission downgrade will only happen if
 	 * is_cow_mapping() returns true.
 	 */
-	is_cow = is_cow_mapping(vma->vm_flags);
+	is_cow = is_cow_mapping(src_vma->vm_flags);
 
 	if (is_cow) {
 		mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
-					0, vma, src_mm, addr, end);
+					0, src_vma, src_mm, addr, end);
 		mmu_notifier_invalidate_range_start(&range);
+		/*
+		 * Disabling preemption is not needed for the write side, as
+		 * the read side doesn't spin, but goes to the mmap_lock.
+		 *
+		 * Use the raw variant of the seqcount_t write API to avoid
+		 * lockdep complaining about preemptibility.
+		 */
+		mmap_assert_write_locked(src_mm);
+		raw_write_seqcount_begin(&src_mm->write_protect_seq);
 	}
 
 	ret = 0;
@@ -1001,15 +1190,17 @@
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(src_pgd))
 			continue;
-		if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd,
-					    vma, addr, next))) {
+		if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd,
+					    addr, next))) {
 			ret = -ENOMEM;
 			break;
 		}
 	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
 
-	if (is_cow)
+	if (is_cow) {
+		raw_write_seqcount_end(&src_mm->write_protect_seq);
 		mmu_notifier_invalidate_range_end(&range);
+	}
 	return ret;
 }
 
@@ -1083,7 +1274,7 @@
 		}
 
 		entry = pte_to_swp_entry(ptent);
-		if (non_swap_entry(entry) && is_device_private_entry(entry)) {
+		if (is_device_private_entry(entry)) {
 			struct page *page = device_private_entry_to_page(entry);
 
 			if (unlikely(details && details->check_mapping)) {
@@ -1181,7 +1372,7 @@
 		 * Here there can be other concurrent MADV_DONTNEED or
 		 * trans huge page faults running, and if the pmd is
 		 * none or trans huge it can change under us. This is
-		 * because MADV_DONTNEED holds the mmap_sem in read
+		 * because MADV_DONTNEED holds the mmap_lock in read
 		 * mode.
 		 */
 		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
@@ -1207,7 +1398,7 @@
 		next = pud_addr_end(addr, end);
 		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
 			if (next - addr != HPAGE_PUD_SIZE) {
-				VM_BUG_ON_VMA(!rwsem_is_locked(&tlb->mm->mmap_sem), vma);
+				mmap_assert_locked(tlb->mm);
 				split_huge_pud(vma, pud, addr);
 			} else if (zap_huge_pud(tlb, vma, pud, addr))
 				goto next;
@@ -1412,8 +1603,7 @@
 }
 EXPORT_SYMBOL_GPL(zap_vma_ptes);
 
-pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
-			spinlock_t **ptl)
+static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -1432,9 +1622,40 @@
 		return NULL;
 
 	VM_BUG_ON(pmd_trans_huge(*pmd));
+	return pmd;
+}
+
+pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
+			spinlock_t **ptl)
+{
+	pmd_t *pmd = walk_to_pmd(mm, addr);
+
+	if (!pmd)
+		return NULL;
 	return pte_alloc_map_lock(mm, pmd, addr, ptl);
 }
 
+static int validate_page_before_insert(struct page *page)
+{
+	if (PageAnon(page) || PageSlab(page) || page_has_type(page))
+		return -EINVAL;
+	flush_dcache_page(page);
+	return 0;
+}
+
+static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte,
+			unsigned long addr, struct page *page, pgprot_t prot)
+{
+	if (!pte_none(*pte))
+		return -EBUSY;
+	/* Ok, finally just insert the thing.. */
+	get_page(page);
+	inc_mm_counter_fast(mm, mm_counter_file(page));
+	page_add_file_rmap(page, false);
+	set_pte_at(mm, addr, pte, mk_pte(page, prot));
+	return 0;
+}
+
 /*
  * This is the old fallback for page remapping.
  *
@@ -1450,31 +1671,136 @@
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	retval = -EINVAL;
-	if (PageAnon(page) || PageSlab(page) || page_has_type(page))
+	retval = validate_page_before_insert(page);
+	if (retval)
 		goto out;
 	retval = -ENOMEM;
-	flush_dcache_page(page);
 	pte = get_locked_pte(mm, addr, &ptl);
 	if (!pte)
 		goto out;
-	retval = -EBUSY;
-	if (!pte_none(*pte))
-		goto out_unlock;
-
-	/* Ok, finally just insert the thing.. */
-	get_page(page);
-	inc_mm_counter_fast(mm, mm_counter_file(page));
-	page_add_file_rmap(page, false);
-	set_pte_at(mm, addr, pte, mk_pte(page, prot));
-
-	retval = 0;
-out_unlock:
+	retval = insert_page_into_pte_locked(mm, pte, addr, page, prot);
 	pte_unmap_unlock(pte, ptl);
 out:
 	return retval;
 }
 
+#ifdef pte_index
+static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte,
+			unsigned long addr, struct page *page, pgprot_t prot)
+{
+	int err;
+
+	if (!page_count(page))
+		return -EINVAL;
+	err = validate_page_before_insert(page);
+	if (err)
+		return err;
+	return insert_page_into_pte_locked(mm, pte, addr, page, prot);
+}
+
+/* insert_pages() amortizes the cost of spinlock operations
+ * when inserting pages in a loop. Arch *must* define pte_index.
+ */
+static int insert_pages(struct vm_area_struct *vma, unsigned long addr,
+			struct page **pages, unsigned long *num, pgprot_t prot)
+{
+	pmd_t *pmd = NULL;
+	pte_t *start_pte, *pte;
+	spinlock_t *pte_lock;
+	struct mm_struct *const mm = vma->vm_mm;
+	unsigned long curr_page_idx = 0;
+	unsigned long remaining_pages_total = *num;
+	unsigned long pages_to_write_in_pmd;
+	int ret;
+more:
+	ret = -EFAULT;
+	pmd = walk_to_pmd(mm, addr);
+	if (!pmd)
+		goto out;
+
+	pages_to_write_in_pmd = min_t(unsigned long,
+		remaining_pages_total, PTRS_PER_PTE - pte_index(addr));
+
+	/* Allocate the PTE if necessary; takes PMD lock once only. */
+	ret = -ENOMEM;
+	if (pte_alloc(mm, pmd))
+		goto out;
+
+	while (pages_to_write_in_pmd) {
+		int pte_idx = 0;
+		const int batch_size = min_t(int, pages_to_write_in_pmd, 8);
+
+		start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock);
+		for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) {
+			int err = insert_page_in_batch_locked(mm, pte,
+				addr, pages[curr_page_idx], prot);
+			if (unlikely(err)) {
+				pte_unmap_unlock(start_pte, pte_lock);
+				ret = err;
+				remaining_pages_total -= pte_idx;
+				goto out;
+			}
+			addr += PAGE_SIZE;
+			++curr_page_idx;
+		}
+		pte_unmap_unlock(start_pte, pte_lock);
+		pages_to_write_in_pmd -= batch_size;
+		remaining_pages_total -= batch_size;
+	}
+	if (remaining_pages_total)
+		goto more;
+	ret = 0;
+out:
+	*num = remaining_pages_total;
+	return ret;
+}
+#endif  /* ifdef pte_index */
+
+/**
+ * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock.
+ * @vma: user vma to map to
+ * @addr: target start user address of these pages
+ * @pages: source kernel pages
+ * @num: in: number of pages to map. out: number of pages that were *not*
+ * mapped. (0 means all pages were successfully mapped).
+ *
+ * Preferred over vm_insert_page() when inserting multiple pages.
+ *
+ * In case of error, we may have mapped a subset of the provided
+ * pages. It is the caller's responsibility to account for this case.
+ *
+ * The same restrictions apply as in vm_insert_page().
+ */
+int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
+			struct page **pages, unsigned long *num)
+{
+#ifdef pte_index
+	const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1;
+
+	if (addr < vma->vm_start || end_addr >= vma->vm_end)
+		return -EFAULT;
+	if (!(vma->vm_flags & VM_MIXEDMAP)) {
+		BUG_ON(mmap_read_trylock(vma->vm_mm));
+		BUG_ON(vma->vm_flags & VM_PFNMAP);
+		vma->vm_flags |= VM_MIXEDMAP;
+	}
+	/* Defer page refcount checking till we're about to map that page. */
+	return insert_pages(vma, addr, pages, num, vma->vm_page_prot);
+#else
+	unsigned long idx = 0, pgcount = *num;
+	int err = -EINVAL;
+
+	for (; idx < pgcount; ++idx) {
+		err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]);
+		if (err)
+			break;
+	}
+	*num = pgcount - idx;
+	return err;
+#endif  /* ifdef pte_index */
+}
+EXPORT_SYMBOL(vm_insert_pages);
+
 /**
  * vm_insert_page - insert single page into user vma
  * @vma: user vma to map to
@@ -1498,7 +1824,7 @@
  * The page does not need to be reserved.
  *
  * Usually this function is called from f_op->mmap() handler
- * under mm->mmap_sem write-lock, so it can change vma->vm_flags.
+ * under mm->mmap_lock 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.
  *
@@ -1512,7 +1838,7 @@
 	if (!page_count(page))
 		return -EINVAL;
 	if (!(vma->vm_flags & VM_MIXEDMAP)) {
-		BUG_ON(down_read_trylock(&vma->vm_mm->mmap_sem));
+		BUG_ON(mmap_read_trylock(vma->vm_mm));
 		BUG_ON(vma->vm_flags & VM_PFNMAP);
 		vma->vm_flags |= VM_MIXEDMAP;
 	}
@@ -1661,7 +1987,7 @@
  * @pfn: source kernel pfn
  * @pgprot: pgprot flags for the inserted page
  *
- * This is exactly like vmf_insert_pfn(), except that it allows drivers to
+ * This is exactly like vmf_insert_pfn(), except that it allows drivers
  * to override pgprot on a per-page basis.
  *
  * This only makes sense for IO mappings, and it makes no sense for
@@ -1669,6 +1995,9 @@
  * vmf_insert_pfn_prot should only be used if using multiple VMAs is
  * impractical.
  *
+ * See vmf_insert_mixed_prot() for a discussion of the implication of using
+ * a value of @pgprot different from that of @vma->vm_page_prot.
+ *
  * Context: Process context.  May allocate using %GFP_KERNEL.
  * Return: vm_fault_t value.
  */
@@ -1742,9 +2071,9 @@
 }
 
 static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
-		unsigned long addr, pfn_t pfn, bool mkwrite)
+		unsigned long addr, pfn_t pfn, pgprot_t pgprot,
+		bool mkwrite)
 {
-	pgprot_t pgprot = vma->vm_page_prot;
 	int err;
 
 	BUG_ON(!vm_mixed_ok(vma, pfn));
@@ -1787,10 +2116,43 @@
 	return VM_FAULT_NOPAGE;
 }
 
+/**
+ * vmf_insert_mixed_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 vmf_insert_mixed(), except that it allows drivers
+ * to override pgprot on a per-page basis.
+ *
+ * Typically this function should be used by drivers to set caching- and
+ * encryption bits different than those of @vma->vm_page_prot, because
+ * the caching- or encryption mode may not be known at mmap() time.
+ * This is ok as long as @vma->vm_page_prot is not used by the core vm
+ * to set caching and encryption bits for those vmas (except for COW pages).
+ * This is ensured by core vm only modifying these page table entries using
+ * functions that don't touch caching- or encryption bits, using pte_modify()
+ * if needed. (See for example mprotect()).
+ * Also when new page-table entries are created, this is only done using the
+ * fault() callback, and never using the value of vma->vm_page_prot,
+ * except for page-table entries that point to anonymous pages as the result
+ * of COW.
+ *
+ * Context: Process context.  May allocate using %GFP_KERNEL.
+ * Return: vm_fault_t value.
+ */
+vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr,
+				 pfn_t pfn, pgprot_t pgprot)
+{
+	return __vm_insert_mixed(vma, addr, pfn, pgprot, false);
+}
+EXPORT_SYMBOL(vmf_insert_mixed_prot);
+
 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);
+	return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false);
 }
 EXPORT_SYMBOL(vmf_insert_mixed);
 
@@ -1802,7 +2164,7 @@
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
 		unsigned long addr, pfn_t pfn)
 {
-	return __vm_insert_mixed(vma, addr, pfn, true);
+	return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true);
 }
 EXPORT_SYMBOL(vmf_insert_mixed_mkwrite);
 
@@ -1907,9 +2269,9 @@
 /**
  * remap_pfn_range - remap kernel memory to userspace
  * @vma: user vma to map to
- * @addr: target user address to start at
- * @pfn: physical address of kernel memory
- * @size: size of map area
+ * @addr: target page aligned user address to start at
+ * @pfn: page frame number of kernel physical memory address
+ * @size: size of mapping area
  * @prot: page protection flags for this mapping
  *
  * Note: this is only safe if the mm semaphore is held when called.
@@ -1926,6 +2288,9 @@
 	unsigned long remap_pfn = pfn;
 	int err;
 
+	if (WARN_ON_ONCE(!PAGE_ALIGNED(addr)))
+		return -EINVAL;
+
 	/*
 	 * Physically remapped pages are special. Tell the
 	 * rest of the world about it:
@@ -1978,7 +2343,7 @@
 /**
  * vm_iomap_memory - remap memory to userspace
  * @vma: user vma to map to
- * @start: start of area
+ * @start: start of the physical memory to be mapped
  * @len: size of area
  *
  * This is a simplified io_remap_pfn_range() for common driver use. The
@@ -2026,27 +2391,39 @@
 
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pte_t *pte;
-	int err;
-	spinlock_t *uninitialized_var(ptl);
+	int err = 0;
+	spinlock_t *ptl;
 
-	pte = (mm == &init_mm) ?
-		pte_alloc_kernel(pmd, addr) :
-		pte_alloc_map_lock(mm, pmd, addr, &ptl);
-	if (!pte)
-		return -ENOMEM;
+	if (create) {
+		pte = (mm == &init_mm) ?
+			pte_alloc_kernel_track(pmd, addr, mask) :
+			pte_alloc_map_lock(mm, pmd, addr, &ptl);
+		if (!pte)
+			return -ENOMEM;
+	} else {
+		pte = (mm == &init_mm) ?
+			pte_offset_kernel(pmd, addr) :
+			pte_offset_map_lock(mm, pmd, addr, &ptl);
+	}
 
 	BUG_ON(pmd_huge(*pmd));
 
 	arch_enter_lazy_mmu_mode();
 
-	do {
-		err = fn(pte++, addr, data);
-		if (err)
-			break;
-	} while (addr += PAGE_SIZE, addr != end);
+	if (fn) {
+		do {
+			if (create || !pte_none(*pte)) {
+				err = fn(pte++, addr, data);
+				if (err)
+					break;
+			}
+		} while (addr += PAGE_SIZE, addr != end);
+	}
+	*mask |= PGTBL_PTE_MODIFIED;
 
 	arch_leave_lazy_mmu_mode();
 
@@ -2057,63 +2434,116 @@
 
 static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pmd_t *pmd;
 	unsigned long next;
-	int err;
+	int err = 0;
 
 	BUG_ON(pud_huge(*pud));
 
-	pmd = pmd_alloc(mm, pud, addr);
-	if (!pmd)
-		return -ENOMEM;
+	if (create) {
+		pmd = pmd_alloc_track(mm, pud, addr, mask);
+		if (!pmd)
+			return -ENOMEM;
+	} else {
+		pmd = pmd_offset(pud, addr);
+	}
 	do {
 		next = pmd_addr_end(addr, end);
-		err = apply_to_pte_range(mm, pmd, addr, next, fn, data);
-		if (err)
-			break;
+		if (create || !pmd_none_or_clear_bad(pmd)) {
+			err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
+						 create, mask);
+			if (err)
+				break;
+		}
 	} while (pmd++, addr = next, addr != end);
 	return err;
 }
 
 static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pud_t *pud;
 	unsigned long next;
-	int err;
+	int err = 0;
 
-	pud = pud_alloc(mm, p4d, addr);
-	if (!pud)
-		return -ENOMEM;
+	if (create) {
+		pud = pud_alloc_track(mm, p4d, addr, mask);
+		if (!pud)
+			return -ENOMEM;
+	} else {
+		pud = pud_offset(p4d, addr);
+	}
 	do {
 		next = pud_addr_end(addr, end);
-		err = apply_to_pmd_range(mm, pud, addr, next, fn, data);
-		if (err)
-			break;
+		if (create || !pud_none_or_clear_bad(pud)) {
+			err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
+						 create, mask);
+			if (err)
+				break;
+		}
 	} while (pud++, addr = next, addr != end);
 	return err;
 }
 
 static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	p4d_t *p4d;
 	unsigned long next;
-	int err;
+	int err = 0;
 
-	p4d = p4d_alloc(mm, pgd, addr);
-	if (!p4d)
-		return -ENOMEM;
+	if (create) {
+		p4d = p4d_alloc_track(mm, pgd, addr, mask);
+		if (!p4d)
+			return -ENOMEM;
+	} else {
+		p4d = p4d_offset(pgd, addr);
+	}
 	do {
 		next = p4d_addr_end(addr, end);
-		err = apply_to_pud_range(mm, p4d, addr, next, fn, data);
+		if (create || !p4d_none_or_clear_bad(p4d)) {
+			err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
+						 create, mask);
+			if (err)
+				break;
+		}
+	} while (p4d++, addr = next, addr != end);
+	return err;
+}
+
+static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
+				 unsigned long size, pte_fn_t fn,
+				 void *data, bool create)
+{
+	pgd_t *pgd;
+	unsigned long start = addr, next;
+	unsigned long end = addr + size;
+	pgtbl_mod_mask mask = 0;
+	int err = 0;
+
+	if (WARN_ON(addr >= end))
+		return -EINVAL;
+
+	pgd = pgd_offset(mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (!create && pgd_none_or_clear_bad(pgd))
+			continue;
+		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask);
 		if (err)
 			break;
-	} while (p4d++, addr = next, addr != end);
+	} while (pgd++, addr = next, addr != end);
+
+	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
+		arch_sync_kernel_mappings(start, start + size);
+
 	return err;
 }
 
@@ -2124,27 +2554,25 @@
 int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 			unsigned long size, pte_fn_t fn, void *data)
 {
-	pgd_t *pgd;
-	unsigned long next;
-	unsigned long end = addr + size;
-	int err;
-
-	if (WARN_ON(addr >= end))
-		return -EINVAL;
-
-	pgd = pgd_offset(mm, addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data);
-		if (err)
-			break;
-	} while (pgd++, addr = next, addr != end);
-
-	return err;
+	return __apply_to_page_range(mm, addr, size, fn, data, true);
 }
 EXPORT_SYMBOL_GPL(apply_to_page_range);
 
 /*
+ * Scan a region of virtual memory, calling a provided function on
+ * each leaf page table where it exists.
+ *
+ * Unlike apply_to_page_range, this does _not_ fill in page tables
+ * where they are absent.
+ */
+int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr,
+				 unsigned long size, pte_fn_t fn, void *data)
+{
+	return __apply_to_page_range(mm, addr, size, fn, data, false);
+}
+EXPORT_SYMBOL_GPL(apply_to_existing_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
@@ -2156,7 +2584,7 @@
 				pte_t *page_table, pte_t orig_pte)
 {
 	int same = 1;
-#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION)
 	if (sizeof(pte_t) > sizeof(unsigned long)) {
 		spinlock_t *ptl = pte_lockptr(mm, pmd);
 		spin_lock(ptl);
@@ -2179,8 +2607,6 @@
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long addr = vmf->address;
 
-	debug_dma_assert_idle(src);
-
 	if (likely(src)) {
 		copy_user_highpage(dst, src, addr, vma);
 		return true;
@@ -2207,10 +2633,9 @@
 		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
 			/*
 			 * Other thread has already handled the fault
-			 * and we don't need to do anything. If it's
-			 * not the case, the fault will be triggered
-			 * again on the same address.
+			 * and update local tlb only
 			 */
+			update_mmu_tlb(vma, addr, vmf->pte);
 			ret = false;
 			goto pte_unlock;
 		}
@@ -2234,13 +2659,14 @@
 		vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
 		locked = true;
 		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
-			/* The PTE changed under us. Retry page fault. */
+			/* The PTE changed under us, update local tlb */
+			update_mmu_tlb(vma, addr, vmf->pte);
 			ret = false;
 			goto pte_unlock;
 		}
 
 		/*
-		 * The same page can be mapped back since last copy attampt.
+		 * The same page can be mapped back since last copy attempt.
 		 * Try to copy again under PTL.
 		 */
 		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
@@ -2347,7 +2773,7 @@
 	 * mapping may be NULL here because some device drivers do not
 	 * set page.mapping but still dirty their pages
 	 *
-	 * Drop the mmap_sem before waiting on IO, if we can. The file
+	 * Drop the mmap_lock before waiting on IO, if we can. The file
 	 * is pinning the mapping, as per above.
 	 */
 	if ((dirtied || page_mkwrite) && mapping) {
@@ -2392,12 +2818,13 @@
 	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);
+	count_vm_event(PGREUSE);
 }
 
 /*
  * Handle the case of a page which we actually need to copy to a new page.
  *
- * Called with mmap_sem locked and the old page referenced, but
+ * Called with mmap_lock locked and the old page referenced, but
  * without the ptl held.
  *
  * High level logic flow:
@@ -2418,7 +2845,6 @@
 	struct page *new_page = NULL;
 	pte_t entry;
 	int page_copied = 0;
-	struct mem_cgroup *memcg;
 	struct mmu_notifier_range range;
 
 	if (unlikely(anon_vma_prepare(vma)))
@@ -2449,8 +2875,9 @@
 		}
 	}
 
-	if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))
+	if (mem_cgroup_charge(new_page, mm, GFP_KERNEL))
 		goto oom_free_new;
+	cgroup_throttle_swaprate(new_page, GFP_KERNEL);
 
 	__SetPageUptodate(new_page);
 
@@ -2475,6 +2902,7 @@
 		}
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 		entry = mk_pte(new_page, vma->vm_page_prot);
+		entry = pte_sw_mkyoung(entry);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		/*
 		 * Clear the pte entry and flush it first, before updating the
@@ -2484,8 +2912,7 @@
 		 */
 		ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
 		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);
+		lru_cache_add_inactive_or_unevictable(new_page, vma);
 		/*
 		 * We call the notify macro here because, when using secondary
 		 * mmu page tables (such as kvm shadow page tables), we want the
@@ -2523,7 +2950,7 @@
 		new_page = old_page;
 		page_copied = 1;
 	} else {
-		mem_cgroup_cancel_charge(new_page, memcg, false);
+		update_mmu_tlb(vma, vmf->address, vmf->pte);
 	}
 
 	if (new_page)
@@ -2583,6 +3010,7 @@
 	 * pte_offset_map_lock.
 	 */
 	if (!pte_same(*vmf->pte, vmf->orig_pte)) {
+		update_mmu_tlb(vmf->vma, vmf->address, vmf->pte);
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		return VM_FAULT_NOPAGE;
 	}
@@ -2660,15 +3088,28 @@
  * change only once the write actually happens. This avoids a few races,
  * and potentially makes it more efficient.
  *
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), with pte both mapped and locked.
- * We return with mmap_sem still held, but pte unmapped and unlocked.
+ * We return with mmap_lock still held, but pte unmapped and unlocked.
  */
 static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	__releases(vmf->ptl)
 {
 	struct vm_area_struct *vma = vmf->vma;
 
+	if (userfaultfd_pte_wp(vma, *vmf->pte)) {
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		return handle_userfault(vmf, VM_UFFD_WP);
+	}
+
+	/*
+	 * Userfaultfd write-protect can defer flushes. Ensure the TLB
+	 * is flushed in this case before copying.
+	 */
+	if (unlikely(userfaultfd_wp(vmf->vma) &&
+		     mm_tlb_flush_pending(vmf->vma->vm_mm)))
+		flush_tlb_page(vmf->vma, vmf->address);
+
 	vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
 	if (!vmf->page) {
 		/*
@@ -2691,49 +3132,25 @@
 	 * not dirty accountable.
 	 */
 	if (PageAnon(vmf->page)) {
-		int total_map_swapcount;
-		if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) ||
-					   page_count(vmf->page) != 1))
+		struct page *page = vmf->page;
+
+		/* PageKsm() doesn't necessarily raise the page refcount */
+		if (PageKsm(page) || page_count(page) != 1)
 			goto copy;
-		if (!trylock_page(vmf->page)) {
-			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_same(*vmf->pte, vmf->orig_pte)) {
-				unlock_page(vmf->page);
-				pte_unmap_unlock(vmf->pte, vmf->ptl);
-				put_page(vmf->page);
-				return 0;
-			}
-			put_page(vmf->page);
+		if (!trylock_page(page))
+			goto copy;
+		if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) {
+			unlock_page(page);
+			goto copy;
 		}
-		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) {
-				/*
-				 * The page is all ours. Move it to
-				 * our anon_vma so the rmap code will
-				 * not search our parent or siblings.
-				 * Protected against the rmap code by
-				 * the page lock.
-				 */
-				page_move_anon_rmap(vmf->page, vma);
-			}
-			unlock_page(vmf->page);
-			wp_page_reuse(vmf);
-			return VM_FAULT_WRITE;
-		}
-		unlock_page(vmf->page);
+		/*
+		 * Ok, we've got the only map reference, and the only
+		 * page count reference, and the page is locked,
+		 * it's dark out, and we're wearing sunglasses. Hit it.
+		 */
+		unlock_page(page);
+		wp_page_reuse(vmf);
+		return VM_FAULT_WRITE;
 	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
 					(VM_WRITE|VM_SHARED))) {
 		return wp_page_shared(vmf);
@@ -2801,7 +3218,7 @@
 
 	details.check_mapping = mapping;
 	details.first_index = page->index;
-	details.last_index = page->index + hpage_nr_pages(page) - 1;
+	details.last_index = page->index + thp_nr_pages(page) - 1;
 	details.single_page = page;
 
 	i_mmap_lock_write(mapping);
@@ -2875,23 +3292,23 @@
 EXPORT_SYMBOL(unmap_mapping_range);
 
 /*
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with pte unmapped and unlocked.
  *
- * We return with the mmap_sem locked or unlocked in the same cases
+ * We return with the mmap_lock locked or unlocked in the same cases
  * as does filemap_fault().
  */
 vm_fault_t do_swap_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = NULL, *swapcache;
-	struct mem_cgroup *memcg;
 	swp_entry_t entry;
 	pte_t pte;
 	int locked;
 	int exclusive = 0;
 	vm_fault_t ret = 0;
+	void *shadow = NULL;
 
 	if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte))
 		goto out;
@@ -2921,16 +3338,33 @@
 	if (!page) {
 		struct swap_info_struct *si = swp_swap_info(entry);
 
-		if (si->flags & SWP_SYNCHRONOUS_IO &&
-				__swap_count(entry) == 1) {
+		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
+		    __swap_count(entry) == 1) {
 			/* skip swapcache */
 			page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
 							vmf->address);
 			if (page) {
+				int err;
+
 				__SetPageLocked(page);
 				__SetPageSwapBacked(page);
 				set_page_private(page, entry.val);
-				lru_cache_add_anon(page);
+
+				/* Tell memcg to use swap ownership records */
+				SetPageSwapCache(page);
+				err = mem_cgroup_charge(page, vma->vm_mm,
+							GFP_KERNEL);
+				ClearPageSwapCache(page);
+				if (err) {
+					ret = VM_FAULT_OOM;
+					goto out_page;
+				}
+
+				shadow = get_shadow_from_swap_cache(entry);
+				if (shadow)
+					workingset_refault(page, shadow);
+
+				lru_cache_add(page);
 				swap_readpage(page, true);
 			}
 		} else {
@@ -2991,11 +3425,7 @@
 		goto out_page;
 	}
 
-	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL,
-					&memcg, false)) {
-		ret = VM_FAULT_OOM;
-		goto out_page;
-	}
+	cgroup_throttle_swaprate(page, GFP_KERNEL);
 
 	/*
 	 * Back out if somebody else already faulted in this pte.
@@ -3032,6 +3462,10 @@
 	flush_icache_page(vma, page);
 	if (pte_swp_soft_dirty(vmf->orig_pte))
 		pte = pte_mksoft_dirty(pte);
+	if (pte_swp_uffd_wp(vmf->orig_pte)) {
+		pte = pte_mkuffd_wp(pte);
+		pte = pte_wrprotect(pte);
+	}
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
 	arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte);
 	vmf->orig_pte = pte;
@@ -3039,12 +3473,9 @@
 	/* ksm created a completely new copy */
 	if (unlikely(page != swapcache && swapcache)) {
 		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);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
 		do_page_add_anon_rmap(page, vma, vmf->address, exclusive);
-		mem_cgroup_commit_charge(page, memcg, true, false);
-		activate_page(page);
 	}
 
 	swap_free(entry);
@@ -3079,7 +3510,6 @@
 out:
 	return ret;
 out_nomap:
-	mem_cgroup_cancel_charge(page, memcg, false);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 out_page:
 	unlock_page(page);
@@ -3093,14 +3523,13 @@
 }
 
 /*
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
- * We return with mmap_sem still held, but pte unmapped and unlocked.
+ * We return with mmap_lock still held, but pte unmapped and unlocked.
  */
 static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct mem_cgroup *memcg;
 	struct page *page;
 	vm_fault_t ret = 0;
 	pte_t entry;
@@ -3114,10 +3543,10 @@
 	 * pte_offset_map() on pmds where a huge pmd might be created
 	 * from a different thread.
 	 *
-	 * pte_alloc_map() is safe to use under down_write(mmap_sem) or when
+	 * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when
 	 * parallel threads are excluded by other means.
 	 *
-	 * Here we only have down_read(mmap_sem).
+	 * Here we only have mmap_read_lock(mm).
 	 */
 	if (pte_alloc(vma->vm_mm, vmf->pmd))
 		return VM_FAULT_OOM;
@@ -3133,8 +3562,10 @@
 						vma->vm_page_prot));
 		vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
 				vmf->address, &vmf->ptl);
-		if (!pte_none(*vmf->pte))
+		if (!pte_none(*vmf->pte)) {
+			update_mmu_tlb(vma, vmf->address, vmf->pte);
 			goto unlock;
+		}
 		ret = check_stable_address_space(vma->vm_mm);
 		if (ret)
 			goto unlock;
@@ -3153,25 +3584,28 @@
 	if (!page)
 		goto oom;
 
-	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg,
-					false))
+	if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
 		goto oom_free_page;
+	cgroup_throttle_swaprate(page, GFP_KERNEL);
 
 	/*
 	 * The memory barrier inside __SetPageUptodate makes sure that
-	 * preceeding stores to the page contents become visible before
+	 * preceding stores to the page contents become visible before
 	 * the set_pte_at() write.
 	 */
 	__SetPageUptodate(page);
 
 	entry = mk_pte(page, vma->vm_page_prot);
+	entry = pte_sw_mkyoung(entry);
 	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_none(*vmf->pte))
+	if (!pte_none(*vmf->pte)) {
+		update_mmu_cache(vma, vmf->address, vmf->pte);
 		goto release;
+	}
 
 	ret = check_stable_address_space(vma->vm_mm);
 	if (ret)
@@ -3180,15 +3614,13 @@
 	/* Deliver the page fault to userland, check inside PT lock */
 	if (userfaultfd_missing(vma)) {
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
-		mem_cgroup_cancel_charge(page, memcg, false);
 		put_page(page);
 		return handle_userfault(vmf, VM_UFFD_MISSING);
 	}
 
 	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);
-	lru_cache_add_active_or_unevictable(page, vma);
+	lru_cache_add_inactive_or_unevictable(page, vma);
 setpte:
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
 
@@ -3198,7 +3630,6 @@
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return ret;
 release:
-	mem_cgroup_cancel_charge(page, memcg, false);
 	put_page(page);
 	goto unlock;
 oom_free_page:
@@ -3208,7 +3639,7 @@
 }
 
 /*
- * The mmap_sem must have been held on entry, and may have been
+ * The mmap_lock must have been held on entry, and may have been
  * released depending on flags and vma->vm_ops->fault() return value.
  * See filemap_fault() and __lock_page_retry().
  */
@@ -3225,7 +3656,7 @@
 	 *				unlock_page(A)
 	 * lock_page(B)
 	 *				lock_page(B)
-	 * pte_alloc_pne
+	 * pte_alloc_one
 	 *   shrink_page_list
 	 *     wait_on_page_writeback(A)
 	 *				SetPageWriteback(B)
@@ -3233,7 +3664,7 @@
 	 *				# 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);
+		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
 		smp_wmb(); /* See comment in __pte_alloc() */
@@ -3320,7 +3751,7 @@
 	return 0;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static void deposit_prealloc_pte(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -3341,13 +3772,14 @@
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	pmd_t entry;
 	int i;
-	vm_fault_t ret;
+	vm_fault_t ret = VM_FAULT_FALLBACK;
 
 	if (!transhuge_vma_suitable(vma, haddr))
-		return VM_FAULT_FALLBACK;
+		return ret;
 
-	ret = VM_FAULT_FALLBACK;
 	page = compound_head(page);
+	if (compound_order(page) != HPAGE_PMD_ORDER)
+		return ret;
 
 	/*
 	 * Archs like ppc64 need additonal space to store information
@@ -3400,10 +3832,9 @@
 
 /**
  * alloc_set_pte - setup new PTE entry for given page and add reverse page
- * mapping. If needed, the fucntion allocates page table or use pre-allocated.
+ * mapping. If needed, the function allocates page table or use pre-allocated.
  *
  * @vmf: fault environment
- * @memcg: memcg to charge page (only for private mappings)
  * @page: page to map
  *
  * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on
@@ -3414,19 +3845,14 @@
  *
  * 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)
+vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	pte_t entry;
 	vm_fault_t ret;
 
-	if (pmd_none(*vmf->pmd) && PageTransCompound(page) &&
-			IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) {
-		/* THP on COW? */
-		VM_BUG_ON_PAGE(memcg, page);
-
+	if (pmd_none(*vmf->pmd) && PageTransCompound(page)) {
 		ret = do_set_pmd(vmf, page);
 		if (ret != VM_FAULT_FALLBACK)
 			return ret;
@@ -3439,19 +3865,21 @@
 	}
 
 	/* Re-check under ptl */
-	if (unlikely(!pte_none(*vmf->pte)))
+	if (unlikely(!pte_none(*vmf->pte))) {
+		update_mmu_tlb(vma, vmf->address, vmf->pte);
 		return VM_FAULT_NOPAGE;
+	}
 
 	flush_icache_page(vma, page);
 	entry = mk_pte(page, vma->vm_page_prot);
+	entry = pte_sw_mkyoung(entry);
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 	/* copy-on-write page */
 	if (write && !(vma->vm_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);
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	} else {
 		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
 		page_add_file_rmap(page, false);
@@ -3499,7 +3927,7 @@
 	if (!(vmf->vma->vm_flags & VM_SHARED))
 		ret = check_stable_address_space(vmf->vma->vm_mm);
 	if (!ret)
-		ret = alloc_set_pte(vmf, vmf->memcg, page);
+		ret = alloc_set_pte(vmf, page);
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return ret;
@@ -3659,11 +4087,11 @@
 	if (!vmf->cow_page)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, GFP_KERNEL,
-				&vmf->memcg, false)) {
+	if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) {
 		put_page(vmf->cow_page);
 		return VM_FAULT_OOM;
 	}
+	cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL);
 
 	ret = __do_fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
@@ -3681,7 +4109,6 @@
 		goto uncharge_out;
 	return ret;
 uncharge_out:
-	mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg, false);
 	put_page(vmf->cow_page);
 	return ret;
 }
@@ -3722,11 +4149,11 @@
 }
 
 /*
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults).
- * The mmap_sem may have been released depending on flags and our
+ * The mmap_lock 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
+ * If mmap_lock is released, vma may become invalid (for example
  * by other thread calling munmap()).
  */
 static vm_fault_t do_fault(struct vm_fault *vmf)
@@ -3896,31 +4323,40 @@
 /* `inline' is required to avoid gcc 4.1.2 build error */
 static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 {
-	if (vma_is_anonymous(vmf->vma))
+	if (vma_is_anonymous(vmf->vma)) {
+		if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd))
+			return handle_userfault(vmf, VM_UFFD_WP);
 		return do_huge_pmd_wp_page(vmf, orig_pmd);
-	if (vmf->vma->vm_ops->huge_fault)
-		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
+	}
+	if (vmf->vma->vm_ops->huge_fault) {
+		vm_fault_t ret = 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);
+		if (!(ret & VM_FAULT_FALLBACK))
+			return ret;
+	}
+
+	/* COW or write-notify handled on pte level: split pmd. */
 	__split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL);
 
 	return VM_FAULT_FALLBACK;
 }
 
-static inline bool vma_is_accessible(struct vm_area_struct *vma)
-{
-	return vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE);
-}
-
 static vm_fault_t create_huge_pud(struct vm_fault *vmf)
 {
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
+	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 	/* No support for anonymous transparent PUD pages yet */
 	if (vma_is_anonymous(vmf->vma))
-		return VM_FAULT_FALLBACK;
-	if (vmf->vma->vm_ops->huge_fault)
-		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+		goto split;
+	if (vmf->vma->vm_ops->huge_fault) {
+		vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
+
+		if (!(ret & VM_FAULT_FALLBACK))
+			return ret;
+	}
+split:
+	/* COW or write-notify not handled on PUD level: split pud.*/
+	__split_huge_pud(vmf->vma, vmf->pud, vmf->address);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 	return VM_FAULT_FALLBACK;
 }
@@ -3946,10 +4382,10 @@
  * with external mmu caches can use to update those (ie the Sparc or
  * PowerPC hashed page tables that act as extended TLBs).
  *
- * We enter with non-exclusive mmap_sem (to exclude vma changes, but allow
+ * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow
  * concurrent faults).
  *
- * The mmap_sem may have been released depending on flags and our return value.
+ * The mmap_lock may have been released depending on flags and our return value.
  * See filemap_fault() and __lock_page_or_retry().
  */
 static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
@@ -3971,7 +4407,7 @@
 		/*
 		 * A regular pmd is established and it can't morph into a huge
 		 * pmd from under us anymore at this point because we hold the
-		 * mmap_sem read mode and khugepaged takes it in write mode.
+		 * mmap_lock read mode and khugepaged takes it in write mode.
 		 * So now it's safe to run pte_offset_map().
 		 */
 		vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
@@ -4008,8 +4444,10 @@
 	vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
 	spin_lock(vmf->ptl);
 	entry = vmf->orig_pte;
-	if (unlikely(!pte_same(*vmf->pte, entry)))
+	if (unlikely(!pte_same(*vmf->pte, entry))) {
+		update_mmu_tlb(vmf->vma, vmf->address, vmf->pte);
 		goto unlock;
+	}
 	if (vmf->flags & FAULT_FLAG_WRITE) {
 		if (!pte_write(entry))
 			return do_wp_page(vmf);
@@ -4020,6 +4458,9 @@
 				vmf->flags & FAULT_FLAG_WRITE)) {
 		update_mmu_cache(vmf->vma, vmf->address, vmf->pte);
 	} else {
+		/* Skip spurious TLB flush for retried page fault */
+		if (vmf->flags & FAULT_FLAG_TRIED)
+			goto unlock;
 		/*
 		 * This is needed only for protection faults but the arch code
 		 * is not yet telling us if this is a protection fault or not.
@@ -4037,7 +4478,7 @@
 /*
  * By the time we get here, we already hold the mm semaphore
  *
- * The mmap_sem may have been released depending on flags and our
+ * The mmap_lock may have been released depending on flags and our
  * return value.  See filemap_fault() and __lock_page_or_retry().
  */
 static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
@@ -4064,6 +4505,7 @@
 	vmf.pud = pud_alloc(mm, p4d, address);
 	if (!vmf.pud)
 		return VM_FAULT_OOM;
+retry_pud:
 	if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) {
 		ret = create_huge_pud(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
@@ -4090,6 +4532,11 @@
 	vmf.pmd = pmd_alloc(mm, vmf.pud, address);
 	if (!vmf.pmd)
 		return VM_FAULT_OOM;
+
+	/* Huge pud page fault raced with pmd_alloc? */
+	if (pud_trans_unstable(vmf.pud))
+		goto retry_pud;
+
 	if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) {
 		ret = create_huge_pmd(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
@@ -4123,14 +4570,75 @@
 	return handle_pte_fault(&vmf);
 }
 
+/**
+ * mm_account_fault - Do page fault accountings
+ *
+ * @regs: the pt_regs struct pointer.  When set to NULL, will skip accounting
+ *        of perf event counters, but we'll still do the per-task accounting to
+ *        the task who triggered this page fault.
+ * @address: the faulted address.
+ * @flags: the fault flags.
+ * @ret: the fault retcode.
+ *
+ * This will take care of most of the page fault accountings.  Meanwhile, it
+ * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter
+ * updates.  However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should
+ * still be in per-arch page fault handlers at the entry of page fault.
+ */
+static inline void mm_account_fault(struct pt_regs *regs,
+				    unsigned long address, unsigned int flags,
+				    vm_fault_t ret)
+{
+	bool major;
+
+	/*
+	 * We don't do accounting for some specific faults:
+	 *
+	 * - Unsuccessful faults (e.g. when the address wasn't valid).  That
+	 *   includes arch_vma_access_permitted() failing before reaching here.
+	 *   So this is not a "this many hardware page faults" counter.  We
+	 *   should use the hw profiling for that.
+	 *
+	 * - Incomplete faults (VM_FAULT_RETRY).  They will only be counted
+	 *   once they're completed.
+	 */
+	if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY))
+		return;
+
+	/*
+	 * We define the fault as a major fault when the final successful fault
+	 * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't
+	 * handle it immediately previously).
+	 */
+	major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED);
+
+	if (major)
+		current->maj_flt++;
+	else
+		current->min_flt++;
+
+	/*
+	 * If the fault is done for GUP, regs will be NULL.  We only do the
+	 * accounting for the per thread fault counters who triggered the
+	 * fault, and we skip the perf event updates.
+	 */
+	if (!regs)
+		return;
+
+	if (major)
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
+	else
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+}
+
 /*
  * By the time we get here, we already hold the mm semaphore
  *
- * The mmap_sem may have been released depending on flags and our
+ * The mmap_lock may have been released depending on flags and our
  * return value.  See filemap_fault() and __lock_page_or_retry().
  */
 vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
-		unsigned int flags)
+			   unsigned int flags, struct pt_regs *regs)
 {
 	vm_fault_t ret;
 
@@ -4171,6 +4679,8 @@
 			mem_cgroup_oom_synchronize(false);
 	}
 
+	mm_account_fault(regs, address, flags, ret);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(handle_mm_fault);
@@ -4212,19 +4722,11 @@
 	smp_wmb(); /* See comment in __pte_alloc */
 
 	spin_lock(&mm->page_table_lock);
-#ifndef __ARCH_HAS_5LEVEL_HACK
 	if (!p4d_present(*p4d)) {
 		mm_inc_nr_puds(mm);
 		p4d_populate(mm, p4d, new);
 	} else	/* Another has populated it */
 		pud_free(mm, new);
-#else
-	if (!pgd_present(*p4d)) {
-		mm_inc_nr_puds(mm);
-		pgd_populate(mm, p4d, new);
-	} else	/* Another has populated it */
-		pud_free(mm, new);
-#endif /* __ARCH_HAS_5LEVEL_HACK */
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
@@ -4245,19 +4747,11 @@
 	smp_wmb(); /* See comment in __pte_alloc */
 
 	ptl = pud_lock(mm, pud);
-#ifndef __ARCH_HAS_4LEVEL_HACK
 	if (!pud_present(*pud)) {
 		mm_inc_nr_pmds(mm);
 		pud_populate(mm, pud, new);
 	} else	/* Another has populated it */
 		pmd_free(mm, new);
-#else
-	if (!pgd_present(*pud)) {
-		mm_inc_nr_pmds(mm);
-		pgd_populate(mm, pud, new);
-	} else /* Another has populated it */
-		pmd_free(mm, new);
-#endif /* __ARCH_HAS_4LEVEL_HACK */
 	spin_unlock(ptl);
 	return 0;
 }
@@ -4456,7 +4950,7 @@
 	void *old_buf = buf;
 	int write = gup_flags & FOLL_WRITE;
 
-	if (down_read_killable(&mm->mmap_sem))
+	if (mmap_read_lock_killable(mm))
 		return 0;
 
 	/* ignore errors, just check how much was successfully transferred */
@@ -4465,7 +4959,7 @@
 		void *maddr;
 		struct page *page = NULL;
 
-		ret = get_user_pages_remote(tsk, mm, addr, 1,
+		ret = get_user_pages_remote(mm, addr, 1,
 				gup_flags, &page, &vma, NULL);
 		if (ret <= 0) {
 #ifndef CONFIG_HAVE_IOREMAP_PROT
@@ -4507,7 +5001,7 @@
 		buf += bytes;
 		addr += bytes;
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	return buf - old_buf;
 }
@@ -4564,7 +5058,7 @@
 	/*
 	 * we might be running from an atomic context so we cannot sleep
 	 */
-	if (!down_read_trylock(&mm->mmap_sem))
+	if (!mmap_read_trylock(mm))
 		return;
 
 	vma = find_vma(mm, ip);
@@ -4583,7 +5077,7 @@
 			free_page((unsigned long)buf);
 		}
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 }
 
 #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)
@@ -4591,7 +5085,7 @@
 {
 	/*
 	 * Some code (nfs/sunrpc) uses socket ops on kernel memory while
-	 * holding the mmap_sem, this is safe because kernel memory doesn't
+	 * holding the mmap_lock, this is safe because kernel memory doesn't
 	 * get paged out, therefore we'll never actually fault, and the
 	 * below annotations will generate false positives.
 	 */
@@ -4602,7 +5096,7 @@
 	__might_sleep(file, line, 0);
 #if defined(CONFIG_DEBUG_ATOMIC_SLEEP)
 	if (current->mm)
-		might_lock_read(&current->mm->mmap_sem);
+		might_lock_read(&current->mm->mmap_lock);
 #endif
 }
 EXPORT_SYMBOL(__might_fault);