1 files changed, 684 insertions, 346 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 0e18b4d649ec..9b8a01d941cb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -182,7 +182,7 @@ void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
 {
         __sync_task_rss_stat(task, mm);
 }
-#else
+#else /* SPLIT_RSS_COUNTING */
 
 #define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member)
 #define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member)
@@ -191,8 +191,206 @@ static void check_sync_rss_stat(struct task_struct *task)
 {
 }
 
+#endif /* SPLIT_RSS_COUNTING */
+
+#ifdef HAVE_GENERIC_MMU_GATHER
+
+static int tlb_next_batch(struct mmu_gather *tlb)
+{
+        struct mmu_gather_batch *batch;
+
+        batch = tlb->active;
+        if (batch->next) {
+                tlb->active = batch->next;
+                return 1;
+        }
+
+        batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
+        if (!batch)
+                return 0;
+
+        batch->next = NULL;
+        batch->nr   = 0;
+        batch->max  = MAX_GATHER_BATCH;
+
+        tlb->active->next = batch;
+        tlb->active = batch;
+
+        return 1;
+}
+
+/* tlb_gather_mmu
+ *      Called to initialize an (on-stack) mmu_gather structure for page-table
+ *      tear-down from @mm. The @fullmm argument is used when @mm is without
+ *      users and we're going to destroy the full address space (exit/execve).
+ */
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
+{
+        tlb->mm = mm;
+
+        tlb->fullmm     = fullmm;
+        tlb->need_flush = 0;
+        tlb->fast_mode  = (num_possible_cpus() == 1);
+        tlb->local.next = NULL;
+        tlb->local.nr   = 0;
+        tlb->local.max  = ARRAY_SIZE(tlb->__pages);
+        tlb->active     = &tlb->local;
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        tlb->batch = NULL;
+#endif
+}
+
+void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+        struct mmu_gather_batch *batch;
+
+        if (!tlb->need_flush)
+                return;
+        tlb->need_flush = 0;
+        tlb_flush(tlb);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        tlb_table_flush(tlb);
 #endif
 
+        if (tlb_fast_mode(tlb))
+                return;
+
+        for (batch = &tlb->local; batch; batch = batch->next) {
+                free_pages_and_swap_cache(batch->pages, batch->nr);
+                batch->nr = 0;
+        }
+        tlb->active = &tlb->local;
+}
+
+/* tlb_finish_mmu
+ *      Called at the end of the shootdown operation to free up any resources
+ *      that were required.
+ */
+void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+{
+        struct mmu_gather_batch *batch, *next;
+
+        tlb_flush_mmu(tlb);
+
+        /* keep the page table cache within bounds */
+        check_pgt_cache();
+
+        for (batch = tlb->local.next; batch; batch = next) {
+                next = batch->next;
+                free_pages((unsigned long)batch, 0);
+        }
+        tlb->local.next = NULL;
+}
+
+/* __tlb_remove_page
+ *      Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
+ *      handling the additional races in SMP caused by other CPUs caching valid
+ *      mappings in their TLBs. Returns the number of free page slots left.
+ *      When out of page slots we must call tlb_flush_mmu().
+ */
+int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+        struct mmu_gather_batch *batch;
+
+        tlb->need_flush = 1;
+
+        if (tlb_fast_mode(tlb)) {
+                free_page_and_swap_cache(page);
+                return 1; /* avoid calling tlb_flush_mmu() */
+        }
+
+        batch = tlb->active;
+        batch->pages[batch->nr++] = page;
+        if (batch->nr == batch->max) {
+                if (!tlb_next_batch(tlb))
+                        return 0;
+                batch = tlb->active;
+        }
+        VM_BUG_ON(batch->nr > batch->max);
+
+        return batch->max - batch->nr;
+}
+
+#endif /* HAVE_GENERIC_MMU_GATHER */
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+
+/*
+ * See the comment near struct mmu_table_batch.
+ */
+
+static void tlb_remove_table_smp_sync(void *arg)
+{
+        /* Simply deliver the interrupt */
+}
+
+static void tlb_remove_table_one(void *table)
+{
+        /*
+         * This isn't an RCU grace period and hence the page-tables cannot be
+         * assumed to be actually RCU-freed.
+         *
+         * It is however sufficient for software page-table walkers that rely on
+         * IRQ disabling. See the comment near struct mmu_table_batch.
+         */
+        smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+        __tlb_remove_table(table);
+}
+
+static void tlb_remove_table_rcu(struct rcu_head *head)
+{
+        struct mmu_table_batch *batch;
+        int i;
+
+        batch = container_of(head, struct mmu_table_batch, rcu);
+
+        for (i = 0; i < batch->nr; i++)
+                __tlb_remove_table(batch->tables[i]);
+
+        free_page((unsigned long)batch);
+}
+
+void tlb_table_flush(struct mmu_gather *tlb)
+{
+        struct mmu_table_batch **batch = &tlb->batch;
+
+        if (*batch) {
+                call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
+                *batch = NULL;
+        }
+}
+
+void tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+        struct mmu_table_batch **batch = &tlb->batch;
+
+        tlb->need_flush = 1;
+
+        /*
+         * When there's less then two users of this mm there cannot be a
+         * concurrent page-table walk.
+         */
+        if (atomic_read(&tlb->mm->mm_users) < 2) {
+                __tlb_remove_table(table);
+                return;
+        }
+
+        if (*batch == NULL) {
+                *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+                if (*batch == NULL) {
+                        tlb_remove_table_one(table);
+                        return;
+                }
+                (*batch)->nr = 0;
+        }
+        (*batch)->tables[(*batch)->nr++] = table;
+        if ((*batch)->nr == MAX_TABLE_BATCH)
+                tlb_table_flush(tlb);
+}
+
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
 /*
  * If a p?d_bad entry is found while walking page tables, report
  * the error, before resetting entry to p?d_none.  Usually (but
@@ -394,9 +592,11 @@ 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, struct vm_area_struct *vma,
+                pmd_t *pmd, unsigned long address)
 {
         pgtable_t new = pte_alloc_one(mm, address);
+        int wait_split_huge_page;
         if (!new)
                 return -ENOMEM;
 
@@ -416,14 +616,18 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
         smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
 
         spin_lock(&mm->page_table_lock);
-        if (!pmd_present(*pmd)) {       /* Has another populated it ? */
+        wait_split_huge_page = 0;
+        if (likely(pmd_none(*pmd))) {   /* Has another populated it ? */
                 mm->nr_ptes++;
                 pmd_populate(mm, pmd, new);
                 new = NULL;
-        }
+        } else if (unlikely(pmd_trans_splitting(*pmd)))
+                wait_split_huge_page = 1;
         spin_unlock(&mm->page_table_lock);
         if (new)
                 pte_free(mm, new);
+        if (wait_split_huge_page)
+                wait_split_huge_page(vma->anon_vma, pmd);
         return 0;
 }
 
@@ -436,10 +640,11 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
         smp_wmb(); /* See comment in __pte_alloc */
 
         spin_lock(&init_mm.page_table_lock);
-        if (!pmd_present(*pmd)) {       /* Has another populated it ? */
+        if (likely(pmd_none(*pmd))) {   /* Has another populated it ? */
                 pmd_populate_kernel(&init_mm, pmd, new);
                 new = NULL;
-        }
+        } else
+                VM_BUG_ON(pmd_trans_splitting(*pmd));
         spin_unlock(&init_mm.page_table_lock);
         if (new)
                 pte_free_kernel(&init_mm, new);
@@ -526,7 +731,7 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
         add_taint(TAINT_BAD_PAGE);
 }
 
-static inline int is_cow_mapping(unsigned int flags)
+static inline int is_cow_mapping(vm_flags_t flags)
 {
         return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 }
@@ -719,9 +924,9 @@ out_set_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)
+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)
 {
         pte_t *orig_src_pte, *orig_dst_pte;
         pte_t *src_pte, *dst_pte;
@@ -736,7 +941,7 @@ again:
         dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
         if (!dst_pte)
                 return -ENOMEM;
-        src_pte = pte_offset_map_nested(src_pmd, addr);
+        src_pte = pte_offset_map(src_pmd, addr);
         src_ptl = pte_lockptr(src_mm, src_pmd);
         spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
         orig_src_pte = src_pte;
@@ -767,7 +972,7 @@ again:
 
         arch_leave_lazy_mmu_mode();
         spin_unlock(src_ptl);
-        pte_unmap_nested(orig_src_pte);
+        pte_unmap(orig_src_pte);
         add_mm_rss_vec(dst_mm, rss);
         pte_unmap_unlock(orig_dst_pte, dst_ptl);
         cond_resched();
@@ -795,6 +1000,17 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
         src_pmd = pmd_offset(src_pud, addr);
         do {
                 next = pmd_addr_end(addr, end);
+                if (pmd_trans_huge(*src_pmd)) {
+                        int err;
+                        VM_BUG_ON(next-addr != HPAGE_PMD_SIZE);
+                        err = copy_huge_pmd(dst_mm, src_mm,
+                                            dst_pmd, src_pmd, addr, vma);
+                        if (err == -ENOMEM)
+                                return -ENOMEM;
+                        if (!err)
+                                continue;
+                        /* fall through */
+                }
                 if (pmd_none_or_clear_bad(src_pmd))
                         continue;
                 if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
@@ -891,26 +1107,26 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
                                 struct vm_area_struct *vma, pmd_t *pmd,
                                 unsigned long addr, unsigned long end,
-                                long *zap_work, struct zap_details *details)
+                                struct zap_details *details)
 {
         struct mm_struct *mm = tlb->mm;
-        pte_t *pte;
-        spinlock_t *ptl;
+        int force_flush = 0;
         int rss[NR_MM_COUNTERS];
+        spinlock_t *ptl;
+        pte_t *start_pte;
+        pte_t *pte;
 
+again:
         init_rss_vec(rss);
-
-        pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+        start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+        pte = start_pte;
         arch_enter_lazy_mmu_mode();
         do {
                 pte_t ptent = *pte;
                 if (pte_none(ptent)) {
-                        (*zap_work)--;
                         continue;
                 }
 
-                (*zap_work) -= PAGE_SIZE;
-
                 if (pte_present(ptent)) {
                         struct page *page;
 
@@ -956,7 +1172,9 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
                         page_remove_rmap(page);
                         if (unlikely(page_mapcount(page) < 0))
                                 print_bad_pte(vma, addr, ptent, page);
-                        tlb_remove_page(tlb, page);
+                        force_flush = !__tlb_remove_page(tlb, page);
+                        if (force_flush)
+                                break;
                         continue;
                 }
                 /*
@@ -977,11 +1195,23 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
                                 print_bad_pte(vma, addr, ptent, NULL);
                 }
                 pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
-        } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
+        } while (pte++, addr += PAGE_SIZE, addr != end);
 
         add_mm_rss_vec(mm, rss);
         arch_leave_lazy_mmu_mode();
-        pte_unmap_unlock(pte - 1, ptl);
+        pte_unmap_unlock(start_pte, ptl);
+
+        /*
+         * mmu_gather ran out of room to batch pages, we break out of
+         * the PTE lock to avoid doing the potential expensive TLB invalidate
+         * and page-free while holding it.
+         */
+        if (force_flush) {
+                force_flush = 0;
+                tlb_flush_mmu(tlb);
+                if (addr != end)
+                        goto again;
+        }
 
         return addr;
 }
@@ -989,7 +1219,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
                                 struct vm_area_struct *vma, pud_t *pud,
                                 unsigned long addr, unsigned long end,
-                                long *zap_work, struct zap_details *details)
+                                struct zap_details *details)
 {
         pmd_t *pmd;
         unsigned long next;
@@ -997,13 +1227,19 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
         pmd = pmd_offset(pud, addr);
         do {
                 next = pmd_addr_end(addr, end);
-                if (pmd_none_or_clear_bad(pmd)) {
-                        (*zap_work)--;
-                        continue;
+                if (pmd_trans_huge(*pmd)) {
+                        if (next-addr != HPAGE_PMD_SIZE) {
+                                VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
+                                split_huge_page_pmd(vma->vm_mm, pmd);
+                        } else if (zap_huge_pmd(tlb, vma, pmd))
+                                continue;
+                        /* fall through */
                 }
-                next = zap_pte_range(tlb, vma, pmd, addr, next,
-                                                zap_work, details);
-        } while (pmd++, addr = next, (addr != end && *zap_work > 0));
+                if (pmd_none_or_clear_bad(pmd))
+                        continue;
+                next = zap_pte_range(tlb, vma, pmd, addr, next, details);
+                cond_resched();
+        } while (pmd++, addr = next, addr != end);
 
         return addr;
 }
@@ -1011,7 +1247,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
                                 struct vm_area_struct *vma, pgd_t *pgd,
                                 unsigned long addr, unsigned long end,
-                                long *zap_work, struct zap_details *details)
+                                struct zap_details *details)
 {
         pud_t *pud;
         unsigned long next;
@@ -1019,13 +1255,10 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
         pud = pud_offset(pgd, addr);
         do {
                 next = pud_addr_end(addr, end);
-                if (pud_none_or_clear_bad(pud)) {
-                        (*zap_work)--;
+                if (pud_none_or_clear_bad(pud))
                         continue;
-                }
-                next = zap_pmd_range(tlb, vma, pud, addr, next,
-                                                zap_work, details);
-        } while (pud++, addr = next, (addr != end && *zap_work > 0));
+                next = zap_pmd_range(tlb, vma, pud, addr, next, details);
+        } while (pud++, addr = next, addr != end);
 
         return addr;
 }
@@ -1033,7 +1266,7 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 static unsigned long unmap_page_range(struct mmu_gather *tlb,
                                 struct vm_area_struct *vma,
                                 unsigned long addr, unsigned long end,
-                                long *zap_work, struct zap_details *details)
+                                struct zap_details *details)
 {
         pgd_t *pgd;
         unsigned long next;
@@ -1047,13 +1280,10 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb,
         pgd = pgd_offset(vma->vm_mm, addr);
         do {
                 next = pgd_addr_end(addr, end);
-                if (pgd_none_or_clear_bad(pgd)) {
-                        (*zap_work)--;
+                if (pgd_none_or_clear_bad(pgd))
                         continue;
-                }
-                next = zap_pud_range(tlb, vma, pgd, addr, next,
-                                                zap_work, details);
-        } while (pgd++, addr = next, (addr != end && *zap_work > 0));
+                next = zap_pud_range(tlb, vma, pgd, addr, next, details);
+        } while (pgd++, addr = next, addr != end);
         tlb_end_vma(tlb, vma);
         mem_cgroup_uncharge_end();
 
@@ -1069,7 +1299,7 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb,
 
 /**
  * unmap_vmas - unmap a range of memory covered by a list of vma's
- * @tlbp: address of the caller's struct mmu_gather
+ * @tlb: address of the caller's struct mmu_gather
  * @vma: the starting vma
  * @start_addr: virtual address at which to start unmapping
  * @end_addr: virtual address at which to end unmapping
@@ -1093,17 +1323,12 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb,
  * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
  * drops the lock and schedules.
  */
-unsigned long unmap_vmas(struct mmu_gather **tlbp,
+unsigned long unmap_vmas(struct mmu_gather *tlb,
                 struct vm_area_struct *vma, unsigned long start_addr,
                 unsigned long end_addr, unsigned long *nr_accounted,
                 struct zap_details *details)
 {
-        long zap_work = ZAP_BLOCK_SIZE;
-        unsigned long tlb_start = 0;    /* For tlb_finish_mmu */
-        int tlb_start_valid = 0;
         unsigned long start = start_addr;
-        spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
-        int fullmm = (*tlbp)->fullmm;
         struct mm_struct *mm = vma->vm_mm;
 
         mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
@@ -1124,11 +1349,6 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
                         untrack_pfn_vma(vma, 0, 0);
 
                 while (start != end) {
-                        if (!tlb_start_valid) {
-                                tlb_start = start;
-                                tlb_start_valid = 1;
-                        }
-
                         if (unlikely(is_vm_hugetlb_page(vma))) {
                                 /*
                                  * It is undesirable to test vma->vm_file as it
@@ -1141,39 +1361,15 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
                                  * Since no pte has actually been setup, it is
                                  * safe to do nothing in this case.
                                  */
-                                if (vma->vm_file) {
+                                if (vma->vm_file)
                                         unmap_hugepage_range(vma, start, end, NULL);
-                                        zap_work -= (end - start) /
-                                        pages_per_huge_page(hstate_vma(vma));
-                                }
 
                                 start = end;
                         } else
-                                start = unmap_page_range(*tlbp, vma,
-                                                start, end, &zap_work, details);
-
-                        if (zap_work > 0) {
-                                BUG_ON(start != end);
-                                break;
-                        }
-
-                        tlb_finish_mmu(*tlbp, tlb_start, start);
-
-                        if (need_resched() ||
-                                (i_mmap_lock && spin_needbreak(i_mmap_lock))) {
-                                if (i_mmap_lock) {
-                                        *tlbp = NULL;
-                                        goto out;
-                                }
-                                cond_resched();
-                        }
-
-                        *tlbp = tlb_gather_mmu(vma->vm_mm, fullmm);
-                        tlb_start_valid = 0;
-                        zap_work = ZAP_BLOCK_SIZE;
+                                start = unmap_page_range(tlb, vma, start, end, details);
                 }
         }
-out:
+
         mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
         return start;   /* which is now the end (or restart) address */
 }
@@ -1189,16 +1385,15 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
                 unsigned long size, struct zap_details *details)
 {
         struct mm_struct *mm = vma->vm_mm;
-        struct mmu_gather *tlb;
+        struct mmu_gather tlb;
         unsigned long end = address + size;
         unsigned long nr_accounted = 0;
 
         lru_add_drain();
-        tlb = tlb_gather_mmu(mm, 0);
+        tlb_gather_mmu(&tlb, mm, 0);
         update_hiwater_rss(mm);
         end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details);
-        if (tlb)
-                tlb_finish_mmu(tlb, address, end);
+        tlb_finish_mmu(&tlb, address, end);
         return end;
 }
 
@@ -1262,7 +1457,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
         pud = pud_offset(pgd, address);
         if (pud_none(*pud))
                 goto no_page_table;
-        if (pud_huge(*pud)) {
+        if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
                 BUG_ON(flags & FOLL_GET);
                 page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
                 goto out;
@@ -1273,11 +1468,32 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
         pmd = pmd_offset(pud, address);
         if (pmd_none(*pmd))
                 goto no_page_table;
-        if (pmd_huge(*pmd)) {
+        if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
                 BUG_ON(flags & FOLL_GET);
                 page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
                 goto out;
         }
+        if (pmd_trans_huge(*pmd)) {
+                if (flags & FOLL_SPLIT) {
+                        split_huge_page_pmd(mm, pmd);
+                        goto split_fallthrough;
+                }
+                spin_lock(&mm->page_table_lock);
+                if (likely(pmd_trans_huge(*pmd))) {
+                        if (unlikely(pmd_trans_splitting(*pmd))) {
+                                spin_unlock(&mm->page_table_lock);
+                                wait_split_huge_page(vma->anon_vma, pmd);
+                        } else {
+                                page = follow_trans_huge_pmd(mm, address,
+                                                             pmd, flags);
+                                spin_unlock(&mm->page_table_lock);
+                                goto out;
+                        }
+                } else
+                        spin_unlock(&mm->page_table_lock);
+                /* fall through */
+        }
+split_fallthrough:
         if (unlikely(pmd_bad(*pmd)))
                 goto no_page_table;
 
@@ -1310,6 +1526,28 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
                  */
                 mark_page_accessed(page);
         }
+        if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
+                /*
+                 * The preliminary mapping check is mainly to avoid the
+                 * pointless overhead of lock_page on the ZERO_PAGE
+                 * which might bounce very badly if there is contention.
+                 *
+                 * If the page is already locked, we don't need to
+                 * handle it now - vmscan will handle it later if and
+                 * when it attempts to reclaim the page.
+                 */
+                if (page->mapping && trylock_page(page)) {
+                        lru_add_drain();  /* push cached pages to LRU */
+                        /*
+                         * Because we lock page here and migration is
+                         * blocked by the pte's page reference, we need
+                         * only check for file-cache page truncation.
+                         */
+                        if (page->mapping)
+                                mlock_vma_page(page);
+                        unlock_page(page);
+                }
+        }
 unlock:
         pte_unmap_unlock(ptep, ptl);
 out:
@@ -1339,9 +1577,65 @@ no_page_table:
         return page;
 }
 
+static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr)
+{
+        return stack_guard_page_start(vma, addr) ||
+               stack_guard_page_end(vma, addr+PAGE_SIZE);
+}
+
+/**
+ * __get_user_pages() - pin user pages in memory
+ * @tsk:        task_struct of target task
+ * @mm:         mm_struct of target mm
+ * @start:      starting user address
+ * @nr_pages:   number of pages from start to pin
+ * @gup_flags:  flags modifying pin behaviour
+ * @pages:      array that receives pointers to the pages pinned.
+ *              Should be at least nr_pages long. Or NULL, if caller
+ *              only intends to ensure the pages are faulted in.
+ * @vmas:       array of pointers to vmas corresponding to each page.
+ *              Or NULL if the caller does not require them.
+ * @nonblocking: whether waiting for disk IO or mmap_sem contention
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno. Each page returned must be released
+ * with a put_page() call when it is finished with. vmas will only
+ * remain valid while mmap_sem is held.
+ *
+ * Must be called with mmap_sem held for read or write.
+ *
+ * __get_user_pages walks a process's page tables and takes a reference to
+ * each struct page that each user address corresponds to at a given
+ * instant. That is, it takes the page that would be accessed if a user
+ * thread accesses the given user virtual address at that instant.
+ *
+ * This does not guarantee that the page exists in the user mappings when
+ * __get_user_pages returns, and there may even be a completely different
+ * page there in some cases (eg. if mmapped pagecache has been invalidated
+ * and subsequently re faulted). However it does guarantee that the page
+ * won't be freed completely. And mostly callers simply care that the page
+ * contains data that was valid *at some point in time*. Typically, an IO
+ * or similar operation cannot guarantee anything stronger anyway because
+ * locks can't be held over the syscall boundary.
+ *
+ * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If
+ * the page is written to, set_page_dirty (or set_page_dirty_lock, as
+ * appropriate) must be called after the page is finished with, and
+ * before put_page is called.
+ *
+ * If @nonblocking != NULL, __get_user_pages will not wait for disk IO
+ * or mmap_sem contention, and if waiting is needed to pin all pages,
+ * *@nonblocking will be set to 0.
+ *
+ * In most cases, get_user_pages or get_user_pages_fast should be used
+ * instead of __get_user_pages. __get_user_pages should be used only if
+ * you need some special @gup_flags.
+ */
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                      unsigned long start, int nr_pages, unsigned int gup_flags,
-                     struct page **pages, struct vm_area_struct **vmas)
+                     struct page **pages, struct vm_area_struct **vmas,
+                     int *nonblocking)
 {
         int i;
         unsigned long vm_flags;
@@ -1365,9 +1659,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                 struct vm_area_struct *vma;
 
                 vma = find_extend_vma(mm, start);
-                if (!vma && in_gate_area(tsk, start)) {
+                if (!vma && in_gate_area(mm, start)) {
                         unsigned long pg = start & PAGE_MASK;
-                        struct vm_area_struct *gate_vma = get_gate_vma(tsk);
                         pgd_t *pgd;
                         pud_t *pud;
                         pmd_t *pmd;
@@ -1386,15 +1679,17 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                         pmd = pmd_offset(pud, pg);
                         if (pmd_none(*pmd))
                                 return i ? : -EFAULT;
+                        VM_BUG_ON(pmd_trans_huge(*pmd));
                         pte = pte_offset_map(pmd, pg);
                         if (pte_none(*pte)) {
                                 pte_unmap(pte);
                                 return i ? : -EFAULT;
                         }
+                        vma = get_gate_vma(mm);
                         if (pages) {
                                 struct page *page;
 
-                                page = vm_normal_page(gate_vma, start, *pte);
+                                page = vm_normal_page(vma, start, *pte);
                                 if (!page) {
                                         if (!(gup_flags & FOLL_DUMP) &&
                                              is_zero_pfn(pte_pfn(*pte)))
@@ -1408,12 +1703,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                                 get_page(page);
                         }
                         pte_unmap(pte);
-                        if (vmas)
-                                vmas[i] = gate_vma;
-                        i++;
-                        start += PAGE_SIZE;
-                        nr_pages--;
-                        continue;
+                        goto next_page;
                 }
 
                 if (!vma ||
@@ -1441,23 +1731,52 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                         cond_resched();
                         while (!(page = follow_page(vma, start, foll_flags))) {
                                 int ret;
+                                unsigned int fault_flags = 0;
+
+                                /* For mlock, just skip the stack guard page. */
+                                if (foll_flags & FOLL_MLOCK) {
+                                        if (stack_guard_page(vma, start))
+                                                goto next_page;
+                                }
+                                if (foll_flags & FOLL_WRITE)
+                                        fault_flags |= FAULT_FLAG_WRITE;
+                                if (nonblocking)
+                                        fault_flags |= FAULT_FLAG_ALLOW_RETRY;
+                                if (foll_flags & FOLL_NOWAIT)
+                                        fault_flags |= (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT);
 
                                 ret = handle_mm_fault(mm, vma, start,
-                                        (foll_flags & FOLL_WRITE) ?
-                                        FAULT_FLAG_WRITE : 0);
+                                                        fault_flags);
 
                                 if (ret & VM_FAULT_ERROR) {
                                         if (ret & VM_FAULT_OOM)
                                                 return i ? i : -ENOMEM;
-                                        if (ret &
-                                            (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS))
+                                        if (ret & (VM_FAULT_HWPOISON |
+                                                   VM_FAULT_HWPOISON_LARGE)) {
+                                                if (i)
+                                                        return i;
+                                                else if (gup_flags & FOLL_HWPOISON)
+                                                        return -EHWPOISON;
+                                                else
+                                                        return -EFAULT;
+                                        }
+                                        if (ret & VM_FAULT_SIGBUS)
                                                 return i ? i : -EFAULT;
                                         BUG();
                                 }
-                                if (ret & VM_FAULT_MAJOR)
-                                        tsk->maj_flt++;
-                                else
-                                        tsk->min_flt++;
+
+                                if (tsk) {
+                                        if (ret & VM_FAULT_MAJOR)
+                                                tsk->maj_flt++;
+                                        else
+                                                tsk->min_flt++;
+                                }
+
+                                if (ret & VM_FAULT_RETRY) {
+                                        if (nonblocking)
+                                                *nonblocking = 0;
+                                        return i;
+                                }
 
                                 /*
                                  * The VM_FAULT_WRITE bit tells us that
@@ -1485,6 +1804,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                                 flush_anon_page(vma, page, start);
                                 flush_dcache_page(page);
                         }
+next_page:
                         if (vmas)
                                 vmas[i] = vma;
                         i++;
@@ -1494,10 +1814,12 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
         } while (nr_pages);
         return i;
 }
+EXPORT_SYMBOL(__get_user_pages);
 
 /**
  * get_user_pages() - pin user pages in memory
- * @tsk:        task_struct of target task
+ * @tsk:        the task_struct to use for page fault accounting, or
+ *              NULL if faults are not to be recorded.
  * @mm:         mm_struct of target mm
  * @start:      starting user address
  * @nr_pages:   number of pages from start to pin
@@ -1558,7 +1880,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
         if (force)
                 flags |= FOLL_FORCE;
 
-        return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
+        return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
+                                NULL);
 }
 EXPORT_SYMBOL(get_user_pages);
 
@@ -1583,22 +1906,25 @@ struct page *get_dump_page(unsigned long addr)
         struct page *page;
 
         if (__get_user_pages(current, current->mm, addr, 1,
-                        FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma) < 1)
+                             FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
+                             NULL) < 1)
                 return NULL;
         flush_cache_page(vma, addr, page_to_pfn(page));
         return page;
 }
 #endif /* CONFIG_ELF_CORE */
 
-pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
+pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
                         spinlock_t **ptl)
 {
         pgd_t * pgd = pgd_offset(mm, addr);
         pud_t * pud = pud_alloc(mm, pgd, addr);
         if (pud) {
                 pmd_t * pmd = pmd_alloc(mm, pud, addr);
-                if (pmd)
+                if (pmd) {
+                        VM_BUG_ON(pmd_trans_huge(*pmd));
                         return pte_alloc_map_lock(mm, pmd, addr, ptl);
+                }
         }
         return NULL;
 }
@@ -1817,6 +2143,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
         pmd = pmd_alloc(mm, pud, addr);
         if (!pmd)
                 return -ENOMEM;
+        VM_BUG_ON(pmd_trans_huge(*pmd));
         do {
                 next = pmd_addr_end(addr, end);
                 if (remap_pte_range(mm, pmd, addr, next,
@@ -2026,10 +2353,10 @@ EXPORT_SYMBOL_GPL(apply_to_page_range);
  * handle_pte_fault chooses page fault handler according to an entry
  * which was read non-atomically.  Before making any commitment, on
  * those architectures or configurations (e.g. i386 with PAE) which
- * might give a mix of unmatched parts, do_swap_page and do_file_page
+ * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault
  * must check under lock before unmapping the pte and proceeding
  * (but do_wp_page is only called after already making such a check;
- * and do_anonymous_page and do_no_page can safely check later on).
+ * and do_anonymous_page can safely check later on).
  */
 static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
                                 pte_t *page_table, pte_t orig_pte)
@@ -2047,19 +2374,6 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
         return same;
 }
 
-/*
- * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
- * servicing faults for write access.  In the normal case, do always want
- * pte_mkwrite.  But get_user_pages can cause write faults for mappings
- * that do not have writing enabled, when used by access_process_vm.
- */
-static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
-{
-        if (likely(vma->vm_flags & VM_WRITE))
-                pte = pte_mkwrite(pte);
-        return pte;
-}
-
 static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
 {
         /*
@@ -2079,7 +2393,7 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
                  * zeroes.
                  */
                 if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
-                        memset(kaddr, 0, PAGE_SIZE);
+                        clear_page(kaddr);
                 kunmap_atomic(kaddr, KM_USER0);
                 flush_dcache_page(dst);
         } else
@@ -2107,10 +2421,11 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
 static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 unsigned long address, pte_t *page_table, pmd_t *pmd,
                 spinlock_t *ptl, pte_t orig_pte)
+        __releases(ptl)
 {
         struct page *old_page, *new_page;
         pte_t entry;
-        int reuse = 0, ret = 0;
+        int ret = 0;
         int page_mkwrite = 0;
         struct page *dirty_page = NULL;
 
@@ -2142,19 +2457,20 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
                                                          &ptl);
                         if (!pte_same(*page_table, orig_pte)) {
                                 unlock_page(old_page);
-                                page_cache_release(old_page);
                                 goto unlock;
                         }
                         page_cache_release(old_page);
                 }
-                reuse = reuse_swap_page(old_page);
-                if (reuse)
+                if (reuse_swap_page(old_page)) {
                         /*
                          * 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(old_page, vma, address);
+                        unlock_page(old_page);
+                        goto reuse;
+                }
                 unlock_page(old_page);
         } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
                                         (VM_WRITE|VM_SHARED))) {
@@ -2210,7 +2526,6 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
                                                          &ptl);
                         if (!pte_same(*page_table, orig_pte)) {
                                 unlock_page(old_page);
-                                page_cache_release(old_page);
                                 goto unlock;
                         }
 
@@ -2218,18 +2533,52 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 }
                 dirty_page = old_page;
                 get_page(dirty_page);
-                reuse = 1;
-        }
 
-        if (reuse) {
 reuse:
                 flush_cache_page(vma, address, pte_pfn(orig_pte));
                 entry = pte_mkyoung(orig_pte);
                 entry = maybe_mkwrite(pte_mkdirty(entry), vma);
                 if (ptep_set_access_flags(vma, address, page_table, entry,1))
                         update_mmu_cache(vma, address, page_table);
+                pte_unmap_unlock(page_table, ptl);
                 ret |= VM_FAULT_WRITE;
-                goto unlock;
+
+                if (!dirty_page)
+                        return ret;
+
+                /*
+                 * Yes, Virginia, this is actually required to prevent a race
+                 * with clear_page_dirty_for_io() from clearing the page dirty
+                 * bit after it clear all dirty ptes, but before a racing
+                 * do_wp_page installs a dirty pte.
+                 *
+                 * __do_fault is protected similarly.
+                 */
+                if (!page_mkwrite) {
+                        wait_on_page_locked(dirty_page);
+                        set_page_dirty_balance(dirty_page, page_mkwrite);
+                }
+                put_page(dirty_page);
+                if (page_mkwrite) {
+                        struct address_space *mapping = dirty_page->mapping;
+
+                        set_page_dirty(dirty_page);
+                        unlock_page(dirty_page);
+                        page_cache_release(dirty_page);
+                        if (mapping)    {
+                                /*
+                                 * Some device drivers do not set page.mapping
+                                 * but still dirty their pages
+                                 */
+                                balance_dirty_pages_ratelimited(mapping);
+                        }
+                }
+
+                /* file_update_time outside page_lock */
+                if (vma->vm_file)
+                        file_update_time(vma->vm_file);
+
+                return ret;
         }
 
         /*
@@ -2254,16 +2603,6 @@ gotten:
         }
         __SetPageUptodate(new_page);
 
-        /*
-         * Don't let another task, with possibly unlocked vma,
-         * keep the mlocked page.
-         */
-        if ((vma->vm_flags & VM_LOCKED) && old_page) {
-                lock_page(old_page);    /* for LRU manipulation */
-                clear_page_mlock(old_page);
-                unlock_page(old_page);
-        }
-
         if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
                 goto oom_free_new;
 
@@ -2331,42 +2670,19 @@ gotten:
 
         if (new_page)
                 page_cache_release(new_page);
-        if (old_page)
-                page_cache_release(old_page);
 unlock:
         pte_unmap_unlock(page_table, ptl);
-        if (dirty_page) {
+        if (old_page) {
                 /*
-                 * Yes, Virginia, this is actually required to prevent a race
-                 * with clear_page_dirty_for_io() from clearing the page dirty
-                 * bit after it clear all dirty ptes, but before a racing
-                 * do_wp_page installs a dirty pte.
-                 *
-                 * do_no_page is protected similarly.
+                 * Don't let another task, with possibly unlocked vma,
+                 * keep the mlocked page.
                  */
-                if (!page_mkwrite) {
-                        wait_on_page_locked(dirty_page);
-                        set_page_dirty_balance(dirty_page, page_mkwrite);
-                }
-                put_page(dirty_page);
-                if (page_mkwrite) {
-                        struct address_space *mapping = dirty_page->mapping;
-
-                        set_page_dirty(dirty_page);
-                        unlock_page(dirty_page);
-                        page_cache_release(dirty_page);
-                        if (mapping)    {
-                                /*
-                                 * Some device drivers do not set page.mapping
-                                 * but still dirty their pages
-                                 */
-                                balance_dirty_pages_ratelimited(mapping);
-                        }
+                if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) {
+                        lock_page(old_page);    /* LRU manipulation */
+                        munlock_vma_page(old_page);
+                        unlock_page(old_page);
                 }
-
-                /* file_update_time outside page_lock */
-                if (vma->vm_file)
-                        file_update_time(vma->vm_file);
+                page_cache_release(old_page);
         }
         return ret;
 oom_free_new:
@@ -2386,96 +2702,11 @@ unwritable_page:
         return ret;
 }
 
-/*
- * Helper functions for unmap_mapping_range().
- *
- * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
- *
- * We have to restart searching the prio_tree whenever we drop the lock,
- * since the iterator is only valid while the lock is held, and anyway
- * a later vma might be split and reinserted earlier while lock dropped.
- *
- * The list of nonlinear vmas could be handled more efficiently, using
- * a placeholder, but handle it in the same way until a need is shown.
- * It is important to search the prio_tree before nonlinear list: a vma
- * may become nonlinear and be shifted from prio_tree to nonlinear list
- * while the lock is dropped; but never shifted from list to prio_tree.
- *
- * In order to make forward progress despite restarting the search,
- * vm_truncate_count is used to mark a vma as now dealt with, so we can
- * quickly skip it next time around.  Since the prio_tree search only
- * shows us those vmas affected by unmapping the range in question, we
- * can't efficiently keep all vmas in step with mapping->truncate_count:
- * so instead reset them all whenever it wraps back to 0 (then go to 1).
- * mapping->truncate_count and vma->vm_truncate_count are protected by
- * i_mmap_lock.
- *
- * In order to make forward progress despite repeatedly restarting some
- * large vma, note the restart_addr from unmap_vmas when it breaks out:
- * and restart from that address when we reach that vma again.  It might
- * have been split or merged, shrunk or extended, but never shifted: so
- * restart_addr remains valid so long as it remains in the vma's range.
- * unmap_mapping_range forces truncate_count to leap over page-aligned
- * values so we can save vma's restart_addr in its truncate_count field.
- */
-#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))
-
-static void reset_vma_truncate_counts(struct address_space *mapping)
-{
-        struct vm_area_struct *vma;
-        struct prio_tree_iter iter;
-
-        vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
-                vma->vm_truncate_count = 0;
-        list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
-                vma->vm_truncate_count = 0;
-}
-
-static int unmap_mapping_range_vma(struct vm_area_struct *vma,
+static void unmap_mapping_range_vma(struct vm_area_struct *vma,
                 unsigned long start_addr, unsigned long end_addr,
                 struct zap_details *details)
 {
-        unsigned long restart_addr;
-        int need_break;
-
-        /*
-         * files that support invalidating or truncating portions of the
-         * file from under mmaped areas must have their ->fault function
-         * return a locked page (and set VM_FAULT_LOCKED in the return).
-         * This provides synchronisation against concurrent unmapping here.
-         */
-
-again:
-        restart_addr = vma->vm_truncate_count;
-        if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
-                start_addr = restart_addr;
-                if (start_addr >= end_addr) {
-                        /* Top of vma has been split off since last time */
-                        vma->vm_truncate_count = details->truncate_count;
-                        return 0;
-                }
-        }
-
-        restart_addr = zap_page_range(vma, start_addr,
-                                        end_addr - start_addr, details);
-        need_break = need_resched() || spin_needbreak(details->i_mmap_lock);
-
-        if (restart_addr >= end_addr) {
-                /* We have now completed this vma: mark it so */
-                vma->vm_truncate_count = details->truncate_count;
-                if (!need_break)
-                        return 0;
-        } else {
-                /* Note restart_addr in vma's truncate_count field */
-                vma->vm_truncate_count = restart_addr;
-                if (!need_break)
-                        goto again;
-        }
-
-        spin_unlock(details->i_mmap_lock);
-        cond_resched();
-        spin_lock(details->i_mmap_lock);
-        return -EINTR;
+        zap_page_range(vma, start_addr, end_addr - start_addr, details);
 }
 
 static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
@@ -2485,12 +2716,8 @@ static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
         struct prio_tree_iter iter;
         pgoff_t vba, vea, zba, zea;
 
-restart:
         vma_prio_tree_foreach(vma, &iter, root,
                         details->first_index, details->last_index) {
-                /* Skip quickly over those we have already dealt with */
-                if (vma->vm_truncate_count == details->truncate_count)
-                        continue;
 
                 vba = vma->vm_pgoff;
                 vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
@@ -2502,11 +2729,10 @@ restart:
                 if (zea > vea)
                         zea = vea;
 
-                if (unmap_mapping_range_vma(vma,
+                unmap_mapping_range_vma(vma,
                         ((zba - vba) << PAGE_SHIFT) + vma->vm_start,
                         ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
-                                details) < 0)
-                        goto restart;
+                                details);
         }
 }
 
@@ -2521,15 +2747,9 @@ static inline void unmap_mapping_range_list(struct list_head *head,
          * across *all* the pages in each nonlinear VMA, not just the pages
          * whose virtual address lies outside the file truncation point.
          */
-restart:
         list_for_each_entry(vma, head, shared.vm_set.list) {
-                /* Skip quickly over those we have already dealt with */
-                if (vma->vm_truncate_count == details->truncate_count)
-                        continue;
                 details->nonlinear_vma = vma;
-                if (unmap_mapping_range_vma(vma, vma->vm_start,
-                                        vma->vm_end, details) < 0)
-                        goto restart;
+                unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details);
         }
 }
 
@@ -2568,51 +2788,17 @@ void unmap_mapping_range(struct address_space *mapping,
         details.last_index = hba + hlen - 1;
         if (details.last_index < details.first_index)
                 details.last_index = ULONG_MAX;
-        details.i_mmap_lock = &mapping->i_mmap_lock;
-
-        spin_lock(&mapping->i_mmap_lock);
 
-        /* Protect against endless unmapping loops */
-        mapping->truncate_count++;
-        if (unlikely(is_restart_addr(mapping->truncate_count))) {
-                if (mapping->truncate_count == 0)
-                        reset_vma_truncate_counts(mapping);
-                mapping->truncate_count++;
-        }
-        details.truncate_count = mapping->truncate_count;
 
+        mutex_lock(&mapping->i_mmap_mutex);
         if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
                 unmap_mapping_range_tree(&mapping->i_mmap, &details);
         if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
                 unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
-        spin_unlock(&mapping->i_mmap_lock);
+        mutex_unlock(&mapping->i_mmap_mutex);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
-int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
-{
-        struct address_space *mapping = inode->i_mapping;
-
-        /*
-         * If the underlying filesystem is not going to provide
-         * a way to truncate a range of blocks (punch a hole) -
-         * we should return failure right now.
-         */
-        if (!inode->i_op->truncate_range)
-                return -ENOSYS;
-
-        mutex_lock(&inode->i_mutex);
-        down_write(&inode->i_alloc_sem);
-        unmap_mapping_range(mapping, offset, (end - offset), 1);
-        truncate_inode_pages_range(mapping, offset, end);
-        unmap_mapping_range(mapping, offset, (end - offset), 1);
-        inode->i_op->truncate_range(inode, offset, end);
-        up_write(&inode->i_alloc_sem);
-        mutex_unlock(&inode->i_mutex);
-
-        return 0;
-}
-
 /*
  * We enter with non-exclusive mmap_sem (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
@@ -2626,7 +2812,8 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
         struct page *page, *swapcache = NULL;
         swp_entry_t entry;
         pte_t pte;
-        struct mem_cgroup *ptr = NULL;
+        int locked;
+        struct mem_cgroup *ptr;
         int exclusive = 0;
         int ret = 0;
 
@@ -2666,6 +2853,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 /* Had to read the page from swap area: Major fault */
                 ret = VM_FAULT_MAJOR;
                 count_vm_event(PGMAJFAULT);
+                mem_cgroup_count_vm_event(mm, PGMAJFAULT);
         } else if (PageHWPoison(page)) {
                 /*
                  * hwpoisoned dirty swapcache pages are kept for killing
@@ -2676,8 +2864,12 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 goto out_release;
         }
 
-        lock_page(page);
+        locked = lock_page_or_retry(page, mm, flags);
         delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+        if (!locked) {
+                ret |= VM_FAULT_RETRY;
+                goto out_release;
+        }
 
         /*
          * Make sure try_to_free_swap or reuse_swap_page or swapoff did not
@@ -2810,7 +3002,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
                 if (prev && prev->vm_end == address)
                         return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
 
-                expand_stack(vma, address - PAGE_SIZE);
+                expand_downwards(vma, address - PAGE_SIZE);
         }
         if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
                 struct vm_area_struct *next = vma->vm_next;
@@ -2926,7 +3118,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         vmf.page = NULL;
 
         ret = vma->vm_ops->fault(vma, &vmf);
-        if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
+        if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE |
+                            VM_FAULT_RETRY)))
                 return ret;
 
         if (unlikely(PageHWPoison(vmf.page))) {
@@ -2967,12 +3160,6 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                                 goto out;
                         }
                         charged = 1;
-                        /*
-                         * Don't let another task, with possibly unlocked vma,
-                         * keep the mlocked page.
-                         */
-                        if (vma->vm_flags & VM_LOCKED)
-                                clear_page_mlock(vmf.page);
                         copy_user_highpage(page, vmf.page, address, vma);
                         __SetPageUptodate(page);
                 } else {
@@ -3139,9 +3326,9 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
  */
-static inline int handle_pte_fault(struct mm_struct *mm,
-                struct vm_area_struct *vma, unsigned long address,
-                pte_t *pte, pmd_t *pmd, unsigned int flags)
+int handle_pte_fault(struct mm_struct *mm,
+                     struct vm_area_struct *vma, unsigned long address,
+                     pte_t *pte, pmd_t *pmd, unsigned int flags)
 {
         pte_t entry;
         spinlock_t *ptl;
@@ -3185,7 +3372,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
                  * with threads.
                  */
                 if (flags & FAULT_FLAG_WRITE)
-                        flush_tlb_page(vma, address);
+                        flush_tlb_fix_spurious_fault(vma, address);
         }
 unlock:
         pte_unmap_unlock(pte, ptl);
@@ -3206,6 +3393,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         __set_current_state(TASK_RUNNING);
 
         count_vm_event(PGFAULT);
+        mem_cgroup_count_vm_event(mm, PGFAULT);
 
         /* do counter updates before entering really critical section. */
         check_sync_rss_stat(current);
@@ -3220,9 +3408,40 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         pmd = pmd_alloc(mm, pud, address);
         if (!pmd)
                 return VM_FAULT_OOM;
-        pte = pte_alloc_map(mm, pmd, address);
-        if (!pte)
+        if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
+                if (!vma->vm_ops)
+                        return do_huge_pmd_anonymous_page(mm, vma, address,
+                                                          pmd, flags);
+        } else {
+                pmd_t orig_pmd = *pmd;
+                barrier();
+                if (pmd_trans_huge(orig_pmd)) {
+                        if (flags & FAULT_FLAG_WRITE &&
+                            !pmd_write(orig_pmd) &&
+                            !pmd_trans_splitting(orig_pmd))
+                                return do_huge_pmd_wp_page(mm, vma, address,
+                                                           pmd, orig_pmd);
+                        return 0;
+                }
+        }
+
+        /*
+         * Use __pte_alloc instead of pte_alloc_map, because we can't
+         * run pte_offset_map on the pmd, if an huge pmd could
+         * materialize from under us from a different thread.
+         */
+        if (unlikely(pmd_none(*pmd)) && __pte_alloc(mm, vma, pmd, address))
                 return VM_FAULT_OOM;
+        /* if an huge pmd materialized from under us just retry later */
+        if (unlikely(pmd_trans_huge(*pmd)))
+                return 0;
+        /*
+         * 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. So now it's
+         * safe to run pte_offset_map().
+         */
+        pte = pte_offset_map(pmd, address);
 
         return handle_pte_fault(mm, vma, address, pte, pmd, flags);
 }
@@ -3288,7 +3507,12 @@ int make_pages_present(unsigned long addr, unsigned long end)
         vma = find_vma(current->mm, addr);
         if (!vma)
                 return -ENOMEM;
-        write = (vma->vm_flags & VM_WRITE) != 0;
+        /*
+         * We want to touch writable mappings with a write fault in order
+         * to break COW, except for shared mappings because these don't COW
+         * and we would not want to dirty them for nothing.
+         */
+        write = (vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE;
         BUG_ON(addr >= end);
         BUG_ON(end > vma->vm_end);
         len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
@@ -3323,7 +3547,7 @@ static int __init gate_vma_init(void)
 __initcall(gate_vma_init);
 #endif
 
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 #ifdef AT_SYSINFO_EHDR
         return &gate_vma;
@@ -3332,7 +3556,7 @@ struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
 #endif
 }
 
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
 {
 #ifdef AT_SYSINFO_EHDR
         if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END))
@@ -3343,7 +3567,7 @@ int in_gate_area_no_task(unsigned long addr)
 
 #endif  /* __HAVE_ARCH_GATE_AREA */
 
-static int follow_pte(struct mm_struct *mm, unsigned long address,
+static int __follow_pte(struct mm_struct *mm, unsigned long address,
                 pte_t **ptepp, spinlock_t **ptlp)
 {
         pgd_t *pgd;
@@ -3360,6 +3584,7 @@ static int follow_pte(struct mm_struct *mm, unsigned long address,
                 goto out;
 
         pmd = pmd_offset(pud, address);
+        VM_BUG_ON(pmd_trans_huge(*pmd));
         if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
                 goto out;
 
@@ -3380,6 +3605,17 @@ out:
         return -EINVAL;
 }
 
+static inline int follow_pte(struct mm_struct *mm, unsigned long address,
+                             pte_t **ptepp, spinlock_t **ptlp)
+{
+        int res;
+
+        /* (void) is needed to make gcc happy */
+        (void) __cond_lock(*ptlp,
+                           !(res = __follow_pte(mm, address, ptepp, ptlp)));
+        return res;
+}
+
 /**
  * follow_pfn - look up PFN at a user virtual address
  * @vma: memory mapping
@@ -3461,20 +3697,15 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 #endif
 
 /*
- * Access another process' address space.
- * Source/target buffer must be kernel space,
- * Do not walk the page table directly, use get_user_pages
+ * Access another process' address space as given in mm.  If non-NULL, use the
+ * given task for page fault accounting.
  */
-int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
+static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
+                unsigned long addr, void *buf, int len, int write)
 {
-        struct mm_struct *mm;
         struct vm_area_struct *vma;
         void *old_buf = buf;
 
-        mm = get_task_mm(tsk);
-        if (!mm)
-                return 0;
-
         down_read(&mm->mmap_sem);
         /* ignore errors, just check how much was successfully transferred */
         while (len) {
@@ -3491,7 +3722,7 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
                          */
 #ifdef CONFIG_HAVE_IOREMAP_PROT
                         vma = find_vma(mm, addr);
-                        if (!vma)
+                        if (!vma || vma->vm_start > addr)
                                 break;
                         if (vma->vm_ops && vma->vm_ops->access)
                                 ret = vma->vm_ops->access(vma, addr, buf,
@@ -3523,11 +3754,47 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
                 addr += bytes;
         }
         up_read(&mm->mmap_sem);
-        mmput(mm);
 
         return buf - old_buf;
 }
 
+/**
+ * access_remote_vm - access another process' address space
+ * @mm:         the mm_struct of the target address space
+ * @addr:       start address to access
+ * @buf:        source or destination buffer
+ * @len:        number of bytes to transfer
+ * @write:      whether the access is a write
+ *
+ * The caller must hold a reference on @mm.
+ */
+int access_remote_vm(struct mm_struct *mm, unsigned long addr,
+                void *buf, int len, int write)
+{
+        return __access_remote_vm(NULL, mm, addr, buf, len, write);
+}
+
+/*
+ * Access another process' address space.
+ * Source/target buffer must be kernel space,
+ * Do not walk the page table directly, use get_user_pages
+ */
+int access_process_vm(struct task_struct *tsk, unsigned long addr,
+                void *buf, int len, int write)
+{
+        struct mm_struct *mm;
+        int ret;
+
+        mm = get_task_mm(tsk);
+        if (!mm)
+                return 0;
+
+        ret = __access_remote_vm(tsk, mm, addr, buf, len, write);
+        mmput(mm);
+
+        return ret;
+}
+
 /*
  * Print the name of a VMA.
  */
@@ -3589,3 +3856,74 @@ void might_fault(void)
 }
 EXPORT_SYMBOL(might_fault);
 #endif
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
+static void clear_gigantic_page(struct page *page,
+                                unsigned long addr,
+                                unsigned int pages_per_huge_page)
+{
+        int i;
+        struct page *p = page;
+
+        might_sleep();
+        for (i = 0; i < pages_per_huge_page;
+             i++, p = mem_map_next(p, page, i)) {
+                cond_resched();
+                clear_user_highpage(p, addr + i * PAGE_SIZE);
+        }
+}
+void clear_huge_page(struct page *page,
+                     unsigned long addr, unsigned int pages_per_huge_page)
+{
+        int i;
+
+        if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
+                clear_gigantic_page(page, addr, pages_per_huge_page);
+                return;
+        }
+
+        might_sleep();
+        for (i = 0; i < pages_per_huge_page; i++) {
+                cond_resched();
+                clear_user_highpage(page + i, addr + i * PAGE_SIZE);
+        }
+}
+
+static void copy_user_gigantic_page(struct page *dst, struct page *src,
+                                    unsigned long addr,
+                                    struct vm_area_struct *vma,
+                                    unsigned int pages_per_huge_page)
+{
+        int i;
+        struct page *dst_base = dst;
+        struct page *src_base = src;
+
+        for (i = 0; i < pages_per_huge_page; ) {
+                cond_resched();
+                copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
+
+                i++;
+                dst = mem_map_next(dst, dst_base, i);
+                src = mem_map_next(src, src_base, i);
+        }
+}
+
+void copy_user_huge_page(struct page *dst, struct page *src,
+                         unsigned long addr, struct vm_area_struct *vma,
+                         unsigned int pages_per_huge_page)
+{
+        int i;
+
+        if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
+                copy_user_gigantic_page(dst, src, addr, vma,
+                                        pages_per_huge_page);
+                return;
+        }
+
+        might_sleep();
+        for (i = 0; i < pages_per_huge_page; i++) {
+                cond_resched();
+                copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
+        }
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */