17 files changed, 224 insertions, 146 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 7ba8feae11b8..dd8e2aafb07e 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -318,7 +318,7 @@ static void wakeup_timer_fn(unsigned long data)
         if (bdi->wb.task) {
                 trace_writeback_wake_thread(bdi);
                 wake_up_process(bdi->wb.task);
-        } else {
+        } else if (bdi->dev) {
                 /*
                  * When bdi tasks are inactive for long time, they are killed.
                  * In this case we have to wake-up the forker thread which
@@ -584,6 +584,8 @@ EXPORT_SYMBOL(bdi_register_dev);
  */
 static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
+        struct task_struct *task;
+
         if (!bdi_cap_writeback_dirty(bdi))
                 return;
 
@@ -602,8 +604,13 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
          * Finally, kill the kernel thread. We don't need to be RCU
          * safe anymore, since the bdi is gone from visibility.
          */
-        if (bdi->wb.task)
-                kthread_stop(bdi->wb.task);
+        spin_lock_bh(&bdi->wb_lock);
+        task = bdi->wb.task;
+        bdi->wb.task = NULL;
+        spin_unlock_bh(&bdi->wb_lock);
+
+        if (task)
+                kthread_stop(task);
 }
 
 /*
@@ -623,7 +630,9 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 
 void bdi_unregister(struct backing_dev_info *bdi)
 {
-        if (bdi->dev) {
+        struct device *dev = bdi->dev;
+
+        if (dev) {
                 bdi_set_min_ratio(bdi, 0);
                 trace_writeback_bdi_unregister(bdi);
                 bdi_prune_sb(bdi);
@@ -632,8 +641,12 @@ void bdi_unregister(struct backing_dev_info *bdi)
                 if (!bdi_cap_flush_forker(bdi))
                         bdi_wb_shutdown(bdi);
                 bdi_debug_unregister(bdi);
-                device_unregister(bdi->dev);
+
+                spin_lock_bh(&bdi->wb_lock);
                 bdi->dev = NULL;
+                spin_unlock_bh(&bdi->wb_lock);
+
+                device_unregister(dev);
         }
 }
 EXPORT_SYMBOL(bdi_unregister);
diff --git a/mm/compaction.c b/mm/compaction.c
index 71a58f67f481..d9ebebe1a2aa 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -313,12 +313,34 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
                 } else if (!locked)
                         spin_lock_irq(&zone->lru_lock);
 
+                /*
+                 * migrate_pfn does not necessarily start aligned to a
+                 * pageblock. Ensure that pfn_valid is called when moving
+                 * into a new MAX_ORDER_NR_PAGES range in case of large
+                 * memory holes within the zone
+                 */
+                if ((low_pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
+                        if (!pfn_valid(low_pfn)) {
+                                low_pfn += MAX_ORDER_NR_PAGES - 1;
+                                continue;
+                        }
+                }
+
                 if (!pfn_valid_within(low_pfn))
                         continue;
                 nr_scanned++;
 
-                /* Get the page and skip if free */
+                /*
+                 * Get the page and ensure the page is within the same zone.
+                 * See the comment in isolate_freepages about overlapping
+                 * nodes. It is deliberate that the new zone lock is not taken
+                 * as memory compaction should not move pages between nodes.
+                 */
                 page = pfn_to_page(low_pfn);
+                if (page_zone(page) != zone)
+                        continue;
+
+                /* Skip if free */
                 if (PageBuddy(page))
                         continue;
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 97f49ed35bd2..b66275757c28 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1400,15 +1400,12 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
         unsigned long seg = 0;
         size_t count;
         loff_t *ppos = &iocb->ki_pos;
-        struct blk_plug plug;
 
         count = 0;
         retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
         if (retval)
                 return retval;
 
-        blk_start_plug(&plug);
-
         /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
         if (filp->f_flags & O_DIRECT) {
                 loff_t size;
@@ -1424,8 +1421,12 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
                         retval = filemap_write_and_wait_range(mapping, pos,
                                         pos + iov_length(iov, nr_segs) - 1);
                         if (!retval) {
+                                struct blk_plug plug;
+
+                                blk_start_plug(&plug);
                                 retval = mapping->a_ops->direct_IO(READ, iocb,
                                                         iov, pos, nr_segs);
+                                blk_finish_plug(&plug);
                         }
                         if (retval > 0) {
                                 *ppos = pos + retval;
@@ -1481,7 +1482,6 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
                         break;
         }
 out:
-        blk_finish_plug(&plug);
         return retval;
 }
 EXPORT_SYMBOL(generic_file_aio_read);
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index f91b2f687343..a4eb31132229 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -263,7 +263,12 @@ found:
                                                         xip_pfn);
                 if (err == -ENOMEM)
                         return VM_FAULT_OOM;
-                BUG_ON(err);
+                /*
+                 * err == -EBUSY is fine, we've raced against another thread
+                 * that faulted-in the same page
+                 */
+                if (err != -EBUSY)
+                        BUG_ON(err);
                 return VM_FAULT_NOPAGE;
         } else {
                 int err, ret = VM_FAULT_OOM;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b3ffc21ce801..91d3efb25d15 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2083,7 +2083,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot)
 {
         struct mm_struct *mm = mm_slot->mm;
 
-        VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock));
+        VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock));
 
         if (khugepaged_test_exit(mm)) {
                 /* free mm_slot */
@@ -2113,7 +2113,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
         int progress = 0;
 
         VM_BUG_ON(!pages);
-        VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock));
+        VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock));
 
         if (khugepaged_scan.mm_slot)
                 mm_slot = khugepaged_scan.mm_slot;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ea8c3a4cd2ae..5f34bd8dda34 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2508,6 +2508,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
         struct hstate *h = hstate_vma(vma);
         int ret = VM_FAULT_SIGBUS;
+        int anon_rmap = 0;
         pgoff_t idx;
         unsigned long size;
         struct page *page;
@@ -2562,14 +2563,13 @@ retry:
                         spin_lock(&inode->i_lock);
                         inode->i_blocks += blocks_per_huge_page(h);
                         spin_unlock(&inode->i_lock);
-                        page_dup_rmap(page);
                 } else {
                         lock_page(page);
                         if (unlikely(anon_vma_prepare(vma))) {
                                 ret = VM_FAULT_OOM;
                                 goto backout_unlocked;
                         }
-                        hugepage_add_new_anon_rmap(page, vma, address);
+                        anon_rmap = 1;
                 }
         } else {
                 /*
@@ -2582,7 +2582,6 @@ retry:
                               VM_FAULT_SET_HINDEX(h - hstates);
                         goto backout_unlocked;
                 }
-                page_dup_rmap(page);
         }
 
         /*
@@ -2606,6 +2605,10 @@ retry:
         if (!huge_pte_none(huge_ptep_get(ptep)))
                 goto backout;
 
+        if (anon_rmap)
+                hugepage_add_new_anon_rmap(page, vma, address);
+        else
+                page_dup_rmap(page);
         new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
                                 && (vma->vm_flags & VM_SHARED)));
         set_huge_pte_at(mm, address, ptep, new_pte);
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index c833addd94d7..45eb6217bf38 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1036,7 +1036,7 @@ void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp)
 {
         pr_debug("%s(0x%p)\n", __func__, ptr);
 
-        if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+        if (atomic_read(&kmemleak_enabled) && ptr && size && !IS_ERR(ptr))
                 add_scan_area((unsigned long)ptr, size, gfp);
         else if (atomic_read(&kmemleak_early_log))
                 log_early(KMEMLEAK_SCAN_AREA, ptr, size, 0);
@@ -1757,6 +1757,7 @@ void __init kmemleak_init(void)
 
 #ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF
         if (!kmemleak_skip_disable) {
+                atomic_set(&kmemleak_early_log, 0);
                 kmemleak_disable();
                 return;
         }
diff --git a/mm/memblock.c b/mm/memblock.c
index 2f55f19b7c86..77b5f227e1d8 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -106,14 +106,17 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
         if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
                 end = memblock.current_limit;
 
-        /* adjust @start to avoid underflow and allocating the first page */
-        start = max3(start, size, (phys_addr_t)PAGE_SIZE);
+        /* avoid allocating the first page */
+        start = max_t(phys_addr_t, start, PAGE_SIZE);
         end = max(start, end);
 
         for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) {
                 this_start = clamp(this_start, start, end);
                 this_end = clamp(this_end, start, end);
 
+                if (this_end < size)
+                        continue;
+
                 cand = round_down(this_end - size, align);
                 if (cand >= this_start)
                         return cand;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3dbff4dcde35..228d6461c12a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -379,7 +379,7 @@ static void mem_cgroup_put(struct mem_cgroup *memcg);
 static bool mem_cgroup_is_root(struct mem_cgroup *memcg);
 void sock_update_memcg(struct sock *sk)
 {
-        if (static_branch(&memcg_socket_limit_enabled)) {
+        if (mem_cgroup_sockets_enabled) {
                 struct mem_cgroup *memcg;
 
                 BUG_ON(!sk->sk_prot->proto_cgroup);
@@ -411,7 +411,7 @@ EXPORT_SYMBOL(sock_update_memcg);
 
 void sock_release_memcg(struct sock *sk)
 {
-        if (static_branch(&memcg_socket_limit_enabled) && sk->sk_cgrp) {
+        if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
                 struct mem_cgroup *memcg;
                 WARN_ON(!sk->sk_cgrp->memcg);
                 memcg = sk->sk_cgrp->memcg;
@@ -776,7 +776,8 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
         /* threshold event is triggered in finer grain than soft limit */
         if (unlikely(mem_cgroup_event_ratelimit(memcg,
                                                 MEM_CGROUP_TARGET_THRESH))) {
-                bool do_softlimit, do_numainfo;
+                bool do_softlimit;
+                bool do_numainfo __maybe_unused;
 
                 do_softlimit = mem_cgroup_event_ratelimit(memcg,
                                                 MEM_CGROUP_TARGET_SOFTLIMIT);
@@ -3247,7 +3248,7 @@ int mem_cgroup_prepare_migration(struct page *page,
                 ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
         else
                 ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-        __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype);
+        __mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype);
         return ret;
 }
 
@@ -4413,6 +4414,9 @@ static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
          */
         BUG_ON(!thresholds);
 
+        if (!thresholds->primary)
+                goto unlock;
+
         usage = mem_cgroup_usage(memcg, type == _MEMSWAP);
 
         /* Check if a threshold crossed before removing */
@@ -4461,7 +4465,7 @@ swap_buffers:
 
         /* To be sure that nobody uses thresholds */
         synchronize_rcu();
-
+unlock:
         mutex_unlock(&memcg->thresholds_lock);
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 5e30583c2605..fa2f04e0337c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -878,15 +878,24 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                         }
                         if (likely(!non_swap_entry(entry)))
                                 rss[MM_SWAPENTS]++;
-                        else 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);
-                                set_pte_at(src_mm, addr, src_pte, pte);
+                        else if (is_migration_entry(entry)) {
+                                page = migration_entry_to_page(entry);
+
+                                if (PageAnon(page))
+                                        rss[MM_ANONPAGES]++;
+                                else
+                                        rss[MM_FILEPAGES]++;
+
+                                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);
+                                        set_pte_at(src_mm, addr, src_pte, pte);
+                                }
                         }
                 }
                 goto out_set_pte;
@@ -1191,6 +1200,16 @@ again:
 
                         if (!non_swap_entry(entry))
                                 rss[MM_SWAPENTS]--;
+                        else if (is_migration_entry(entry)) {
+                                struct page *page;
+
+                                page = migration_entry_to_page(entry);
+
+                                if (PageAnon(page))
+                                        rss[MM_ANONPAGES]--;
+                                else
+                                        rss[MM_FILEPAGES]--;
+                        }
                         if (unlikely(!free_swap_and_cache(entry)))
                                 print_bad_pte(vma, addr, ptent, NULL);
                 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 9871a56d82c3..df141f60289e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -445,7 +445,6 @@ void migrate_page_copy(struct page *newpage, struct page *page)
         ClearPageSwapCache(page);
         ClearPagePrivate(page);
         set_page_private(page, 0);
-        page->mapping = NULL;
 
         /*
          * If any waiters have accumulated on the new page then
@@ -667,6 +666,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
         } else {
                 if (remap_swapcache)
                         remove_migration_ptes(page, newpage);
+                page->mapping = NULL;
         }
 
         unlock_page(newpage);
diff --git a/mm/nommu.c b/mm/nommu.c
index b982290fd962..f59e170fceb4 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -696,9 +696,11 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
         if (vma->vm_file) {
                 mapping = vma->vm_file->f_mapping;
 
+                mutex_lock(&mapping->i_mmap_mutex);
                 flush_dcache_mmap_lock(mapping);
                 vma_prio_tree_insert(vma, &mapping->i_mmap);
                 flush_dcache_mmap_unlock(mapping);
+                mutex_unlock(&mapping->i_mmap_mutex);
         }
 
         /* add the VMA to the tree */
@@ -760,9 +762,11 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
         if (vma->vm_file) {
                 mapping = vma->vm_file->f_mapping;
 
+                mutex_lock(&mapping->i_mmap_mutex);
                 flush_dcache_mmap_lock(mapping);
                 vma_prio_tree_remove(vma, &mapping->i_mmap);
                 flush_dcache_mmap_unlock(mapping);
+                mutex_unlock(&mapping->i_mmap_mutex);
         }
 
         /* remove from the MM's tree and list */
@@ -775,8 +779,6 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 
         if (vma->vm_next)
                 vma->vm_next->vm_prev = vma->vm_prev;
-
-        vma->vm_mm = NULL;
 }
 
 /*
@@ -2052,6 +2054,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
         high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
         down_write(&nommu_region_sem);
+        mutex_lock(&inode->i_mapping->i_mmap_mutex);
 
         /* search for VMAs that fall within the dead zone */
         vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
@@ -2059,6 +2062,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
                 /* found one - only interested if it's shared out of the page
                  * cache */
                 if (vma->vm_flags & VM_SHARED) {
+                        mutex_unlock(&inode->i_mapping->i_mmap_mutex);
                         up_write(&nommu_region_sem);
                         return -ETXTBSY; /* not quite true, but near enough */
                 }
@@ -2086,6 +2090,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
                 }
         }
 
+        mutex_unlock(&inode->i_mapping->i_mmap_mutex);
         up_write(&nommu_region_sem);
         return 0;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0027d8f4a1bb..a13ded1938f0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5236,6 +5236,7 @@ void *__init alloc_large_system_hash(const char *tablename,
                 max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
                 do_div(max, bucketsize);
         }
+        max = min(max, 0x80000000ULL);
 
         if (numentries > max)
                 numentries = max;
@@ -5413,7 +5414,25 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count)
 
 bool is_pageblock_removable_nolock(struct page *page)
 {
-        struct zone *zone = page_zone(page);
+        struct zone *zone;
+        unsigned long pfn;
+
+        /*
+         * We have to be careful here because we are iterating over memory
+         * sections which are not zone aware so we might end up outside of
+         * the zone but still within the section.
+         * We have to take care about the node as well. If the node is offline
+         * its NODE_DATA will be NULL - see page_zone.
+         */
+        if (!node_online(page_to_nid(page)))
+                return false;
+
+        zone = page_zone(page);
+        pfn = page_to_pfn(page);
+        if (zone->zone_start_pfn > pfn ||
+                        zone->zone_start_pfn + zone->spanned_pages <= pfn)
+                return false;
+
         return __count_immobile_pages(zone, page, 0);
 }
 
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index e920aa3ce104..c20ff48994c2 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -298,23 +298,18 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
                 goto free_proc_pages;
         }
 
-        task_lock(task);
-        if (__ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
-                task_unlock(task);
-                rc = -EPERM;
-                goto put_task_struct;
-        }
-        mm = task->mm;
-
-        if (!mm || (task->flags & PF_KTHREAD)) {
-                task_unlock(task);
-                rc = -EINVAL;
+        mm = mm_access(task, PTRACE_MODE_ATTACH);
+        if (!mm || IS_ERR(mm)) {
+                rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
+                /*
+                 * Explicitly map EACCES to EPERM as EPERM is a more a
+                 * appropriate error code for process_vw_readv/writev
+                 */
+                if (rc == -EACCES)
+                        rc = -EPERM;
                 goto put_task_struct;
         }
 
-        atomic_inc(&mm->mm_users);
-        task_unlock(task);
-
         for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) {
                 rc = process_vm_rw_single_vec(
                         (unsigned long)rvec[i].iov_base, rvec[i].iov_len,
diff --git a/mm/shmem.c b/mm/shmem.c
index feead1943d92..269d049294ab 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -379,7 +379,7 @@ static int shmem_free_swap(struct address_space *mapping,
 /*
  * Pagevec may contain swap entries, so shuffle up pages before releasing.
  */
-static void shmem_pagevec_release(struct pagevec *pvec)
+static void shmem_deswap_pagevec(struct pagevec *pvec)
 {
         int i, j;
 
@@ -389,7 +389,36 @@ static void shmem_pagevec_release(struct pagevec *pvec)
                         pvec->pages[j++] = page;
         }
         pvec->nr = j;
-        pagevec_release(pvec);
+}
+
+/*
+ * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
+ */
+void shmem_unlock_mapping(struct address_space *mapping)
+{
+        struct pagevec pvec;
+        pgoff_t indices[PAGEVEC_SIZE];
+        pgoff_t index = 0;
+
+        pagevec_init(&pvec, 0);
+        /*
+         * Minor point, but we might as well stop if someone else SHM_LOCKs it.
+         */
+        while (!mapping_unevictable(mapping)) {
+                /*
+                 * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
+                 * has finished, if it hits a row of PAGEVEC_SIZE swap entries.
+                 */
+                pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+                                        PAGEVEC_SIZE, pvec.pages, indices);
+                if (!pvec.nr)
+                        break;
+                index = indices[pvec.nr - 1] + 1;
+                shmem_deswap_pagevec(&pvec);
+                check_move_unevictable_pages(pvec.pages, pvec.nr);
+                pagevec_release(&pvec);
+                cond_resched();
+        }
 }
 
 /*
@@ -440,7 +469,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
                         }
                         unlock_page(page);
                 }
-                shmem_pagevec_release(&pvec);
+                shmem_deswap_pagevec(&pvec);
+                pagevec_release(&pvec);
                 mem_cgroup_uncharge_end();
                 cond_resched();
                 index++;
@@ -470,7 +500,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
                         continue;
                 }
                 if (index == start && indices[0] > end) {
-                        shmem_pagevec_release(&pvec);
+                        shmem_deswap_pagevec(&pvec);
+                        pagevec_release(&pvec);
                         break;
                 }
                 mem_cgroup_uncharge_start();
@@ -494,7 +525,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
                         }
                         unlock_page(page);
                 }
-                shmem_pagevec_release(&pvec);
+                shmem_deswap_pagevec(&pvec);
+                pagevec_release(&pvec);
                 mem_cgroup_uncharge_end();
                 index++;
         }
@@ -1068,13 +1100,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
                 user_shm_unlock(inode->i_size, user);
                 info->flags &= ~VM_LOCKED;
                 mapping_clear_unevictable(file->f_mapping);
-                /*
-                 * Ensure that a racing putback_lru_page() can see
-                 * the pages of this mapping are evictable when we
-                 * skip them due to !PageLRU during the scan.
-                 */
-                smp_mb__after_clear_bit();
-                scan_mapping_unevictable_pages(file->f_mapping);
         }
         retval = 0;
 
@@ -2445,6 +2470,10 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
         return 0;
 }
 
+void shmem_unlock_mapping(struct address_space *mapping)
+{
+}
+
 void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 {
         truncate_inode_pages_range(inode->i_mapping, lstart, lend);
diff --git a/mm/swap.c b/mm/swap.c
index b0f529b38979..fff1ff7fb9ad 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -659,7 +659,7 @@ void lru_add_page_tail(struct zone* zone,
         VM_BUG_ON(!PageHead(page));
         VM_BUG_ON(PageCompound(page_tail));
         VM_BUG_ON(PageLRU(page_tail));
-        VM_BUG_ON(!spin_is_locked(&zone->lru_lock));
+        VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&zone->lru_lock));
 
         SetPageLRU(page_tail);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2880396f7953..c52b23552659 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -26,7 +26,6 @@
 #include <linux/buffer_head.h>  /* for try_to_release_page(),
                                         buffer_heads_over_limit */
 #include <linux/mm_inline.h>
-#include <linux/pagevec.h>
 #include <linux/backing-dev.h>
 #include <linux/rmap.h>
 #include <linux/topology.h>
@@ -661,7 +660,7 @@ redo:
                  * When racing with an mlock or AS_UNEVICTABLE clearing
                  * (page is unlocked) make sure that if the other thread
                  * does not observe our setting of PG_lru and fails
-                 * isolation/check_move_unevictable_page,
+                 * isolation/check_move_unevictable_pages,
                  * we see PG_mlocked/AS_UNEVICTABLE cleared below and move
                  * the page back to the evictable list.
                  *
@@ -3499,100 +3498,61 @@ int page_evictable(struct page *page, struct vm_area_struct *vma)
         return 1;
 }
 
+#ifdef CONFIG_SHMEM
 /**
- * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list
- * @page: page to check evictability and move to appropriate lru list
- * @zone: zone page is in
+ * check_move_unevictable_pages - check pages for evictability and move to appropriate zone lru list
+ * @pages:      array of pages to check
+ * @nr_pages:   number of pages to check
  *
- * Checks a page for evictability and moves the page to the appropriate
- * zone lru list.
+ * Checks pages for evictability and moves them to the appropriate lru list.
  *
- * Restrictions: zone->lru_lock must be held, page must be on LRU and must
- * have PageUnevictable set.
+ * This function is only used for SysV IPC SHM_UNLOCK.
  */
-static void check_move_unevictable_page(struct page *page, struct zone *zone)
+void check_move_unevictable_pages(struct page **pages, int nr_pages)
 {
         struct lruvec *lruvec;
+        struct zone *zone = NULL;
+        int pgscanned = 0;
+        int pgrescued = 0;
+        int i;
 
-        VM_BUG_ON(PageActive(page));
-retry:
-        ClearPageUnevictable(page);
-        if (page_evictable(page, NULL)) {
-                enum lru_list l = page_lru_base_type(page);
-
-                __dec_zone_state(zone, NR_UNEVICTABLE);
-                lruvec = mem_cgroup_lru_move_lists(zone, page,
-                                                   LRU_UNEVICTABLE, l);
-                list_move(&page->lru, &lruvec->lists[l]);
-                __inc_zone_state(zone, NR_INACTIVE_ANON + l);
-                __count_vm_event(UNEVICTABLE_PGRESCUED);
-        } else {
-                /*
-                 * rotate unevictable list
-                 */
-                SetPageUnevictable(page);
-                lruvec = mem_cgroup_lru_move_lists(zone, page, LRU_UNEVICTABLE,
-                                                   LRU_UNEVICTABLE);
-                list_move(&page->lru, &lruvec->lists[LRU_UNEVICTABLE]);
-                if (page_evictable(page, NULL))
-                        goto retry;
-        }
-}
-
-/**
- * scan_mapping_unevictable_pages - scan an address space for evictable pages
- * @mapping: struct address_space to scan for evictable pages
- *
- * Scan all pages in mapping.  Check unevictable pages for
- * evictability and move them to the appropriate zone lru list.
- */
-void scan_mapping_unevictable_pages(struct address_space *mapping)
-{
-        pgoff_t next = 0;
-        pgoff_t end   = (i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1) >>
-                         PAGE_CACHE_SHIFT;
-        struct zone *zone;
-        struct pagevec pvec;
-
-        if (mapping->nrpages == 0)
-                return;
-
-        pagevec_init(&pvec, 0);
-        while (next < end &&
-                pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
-                int i;
-                int pg_scanned = 0;
-
-                zone = NULL;
-
-                for (i = 0; i < pagevec_count(&pvec); i++) {
-                        struct page *page = pvec.pages[i];
-                        pgoff_t page_index = page->index;
-                        struct zone *pagezone = page_zone(page);
+        for (i = 0; i < nr_pages; i++) {
+                struct page *page = pages[i];
+                struct zone *pagezone;
 
-                        pg_scanned++;
-                        if (page_index > next)
-                                next = page_index;
-                        next++;
+                pgscanned++;
+                pagezone = page_zone(page);
+                if (pagezone != zone) {
+                        if (zone)
+                                spin_unlock_irq(&zone->lru_lock);
+                        zone = pagezone;
+                        spin_lock_irq(&zone->lru_lock);
+                }
 
-                        if (pagezone != zone) {
-                                if (zone)
-                                        spin_unlock_irq(&zone->lru_lock);
-                                zone = pagezone;
-                                spin_lock_irq(&zone->lru_lock);
-                        }
+                if (!PageLRU(page) || !PageUnevictable(page))
+                        continue;
 
-                        if (PageLRU(page) && PageUnevictable(page))
-                                check_move_unevictable_page(page, zone);
+                if (page_evictable(page, NULL)) {
+                        enum lru_list lru = page_lru_base_type(page);
+
+                        VM_BUG_ON(PageActive(page));
+                        ClearPageUnevictable(page);
+                        __dec_zone_state(zone, NR_UNEVICTABLE);
+                        lruvec = mem_cgroup_lru_move_lists(zone, page,
+                                                LRU_UNEVICTABLE, lru);
+                        list_move(&page->lru, &lruvec->lists[lru]);
+                        __inc_zone_state(zone, NR_INACTIVE_ANON + lru);
+                        pgrescued++;
                 }
-                if (zone)
-                        spin_unlock_irq(&zone->lru_lock);
-                pagevec_release(&pvec);
-
-                count_vm_events(UNEVICTABLE_PGSCANNED, pg_scanned);
         }
 
+        if (zone) {
+                __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
+                __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
+                spin_unlock_irq(&zone->lru_lock);
+        }
 }
+#endif /* CONFIG_SHMEM */
 
 static void warn_scan_unevictable_pages(void)
 {