8 files changed, 106 insertions, 47 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d0351e31f474..cafdcee154e8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2370,7 +2370,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
         long chg = region_truncate(&inode->i_mapping->private_list, offset);
 
         spin_lock(&inode->i_lock);
-        inode->i_blocks -= blocks_per_huge_page(h);
+        inode->i_blocks -= (blocks_per_huge_page(h) * freed);
         spin_unlock(&inode->i_lock);
 
         hugetlb_put_quota(inode->i_mapping, (chg - freed));
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 5aabd41ffb8f..487267310a84 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1217,7 +1217,6 @@ static void *kmemleak_seq_start(struct seq_file *seq, loff_t *pos)
         }
         object = NULL;
 out:
-        rcu_read_unlock();
         return object;
 }
 
@@ -1233,13 +1232,11 @@ static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
         ++(*pos);
 
-        rcu_read_lock();
         list_for_each_continue_rcu(n, &object_list) {
                 next_obj = list_entry(n, struct kmemleak_object, object_list);
                 if (get_object(next_obj))
                         break;
         }
-        rcu_read_unlock();
 
         put_object(prev_obj);
         return next_obj;
@@ -1255,6 +1252,7 @@ static void kmemleak_seq_stop(struct seq_file *seq, void *v)
                  * kmemleak_seq_start may return ERR_PTR if the scan_mutex
                  * waiting was interrupted, so only release it if !IS_ERR.
                  */
+                rcu_read_unlock();
                 mutex_unlock(&scan_mutex);
                 if (v)
                         put_object(v);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e717964cb5a0..fd4529d86de5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1207,6 +1207,12 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
         ret = 0;
 out:
         unlock_page_cgroup(pc);
+        /*
+         * We charges against "to" which may not have any tasks. Then, "to"
+         * can be under rmdir(). But in current implementation, caller of
+         * this function is just force_empty() and it's garanteed that
+         * "to" is never removed. So, we don't check rmdir status here.
+         */
         return ret;
 }
 
@@ -1428,6 +1434,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
                 return;
         if (!ptr)
                 return;
+        cgroup_exclude_rmdir(&ptr->css);
         pc = lookup_page_cgroup(page);
         mem_cgroup_lru_del_before_commit_swapcache(page);
         __mem_cgroup_commit_charge(ptr, pc, ctype);
@@ -1457,8 +1464,12 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
                 }
                 rcu_read_unlock();
         }
-        /* add this page(page_cgroup) to the LRU we want. */
-
+        /*
+         * At swapin, we may charge account against cgroup which has no tasks.
+         * So, rmdir()->pre_destroy() can be called while we do this charge.
+         * In that case, we need to call pre_destroy() again. check it here.
+         */
+        cgroup_release_and_wakeup_rmdir(&ptr->css);
 }
 
 void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
@@ -1664,7 +1675,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
 
         if (!mem)
                 return;
-
+        cgroup_exclude_rmdir(&mem->css);
         /* at migration success, oldpage->mapping is NULL. */
         if (oldpage->mapping) {
                 target = oldpage;
@@ -1704,6 +1715,12 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
          */
         if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
                 mem_cgroup_uncharge_page(target);
+        /*
+         * At migration, we may charge account against cgroup which has no tasks
+         * So, rmdir()->pre_destroy() can be called while we do this charge.
+         * In that case, we need to call pre_destroy() again. check it here.
+         */
+        cgroup_release_and_wakeup_rmdir(&mem->css);
 }
 
 /*
diff --git a/mm/memory.c b/mm/memory.c
index 65216194eb8d..aede2ce3aba4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -135,11 +135,12 @@ void pmd_clear_bad(pmd_t *pmd)
  * Note: this doesn't free the actual pages themselves. That
  * has been handled earlier when unmapping all the memory regions.
  */
-static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
+static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+                           unsigned long addr)
 {
         pgtable_t token = pmd_pgtable(*pmd);
         pmd_clear(pmd);
-        pte_free_tlb(tlb, token);
+        pte_free_tlb(tlb, token, addr);
         tlb->mm->nr_ptes--;
 }
 
@@ -157,7 +158,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
                 next = pmd_addr_end(addr, end);
                 if (pmd_none_or_clear_bad(pmd))
                         continue;
-                free_pte_range(tlb, pmd);
+                free_pte_range(tlb, pmd, addr);
         } while (pmd++, addr = next, addr != end);
 
         start &= PUD_MASK;
@@ -173,7 +174,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 
         pmd = pmd_offset(pud, start);
         pud_clear(pud);
-        pmd_free_tlb(tlb, pmd);
+        pmd_free_tlb(tlb, pmd, start);
 }
 
 static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
@@ -206,7 +207,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 
         pud = pud_offset(pgd, start);
         pgd_clear(pgd);
-        pud_free_tlb(tlb, pud);
+        pud_free_tlb(tlb, pud, start);
 }
 
 /*
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e08e2c4da63a..7dd9d9f80694 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -191,25 +191,27 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
  * Must be called holding task's alloc_lock to protect task's mems_allowed
  * and mempolicy.  May also be called holding the mmap_semaphore for write.
  */
-static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
+static int mpol_set_nodemask(struct mempolicy *pol,
+                     const nodemask_t *nodes, struct nodemask_scratch *nsc)
 {
-        nodemask_t cpuset_context_nmask;
         int ret;
 
         /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */
         if (pol == NULL)
                 return 0;
+        /* Check N_HIGH_MEMORY */
+        nodes_and(nsc->mask1,
+                  cpuset_current_mems_allowed, node_states[N_HIGH_MEMORY]);
 
         VM_BUG_ON(!nodes);
         if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes))
                 nodes = NULL;   /* explicit local allocation */
         else {
                 if (pol->flags & MPOL_F_RELATIVE_NODES)
-                        mpol_relative_nodemask(&cpuset_context_nmask, nodes,
-                                               &cpuset_current_mems_allowed);
+                        mpol_relative_nodemask(&nsc->mask2, nodes,&nsc->mask1);
                 else
-                        nodes_and(cpuset_context_nmask, *nodes,
-                                  cpuset_current_mems_allowed);
+                        nodes_and(nsc->mask2, *nodes, nsc->mask1);
+
                 if (mpol_store_user_nodemask(pol))
                         pol->w.user_nodemask = *nodes;
                 else
@@ -217,8 +219,10 @@ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
                                                 cpuset_current_mems_allowed;
         }
 
-        ret = mpol_ops[pol->mode].create(pol,
-                                nodes ? &cpuset_context_nmask : NULL);
+        if (nodes)
+                ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
+        else
+                ret = mpol_ops[pol->mode].create(pol, NULL);
         return ret;
 }
 
@@ -620,12 +624,17 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 {
         struct mempolicy *new, *old;
         struct mm_struct *mm = current->mm;
+        NODEMASK_SCRATCH(scratch);
         int ret;
 
-        new = mpol_new(mode, flags, nodes);
-        if (IS_ERR(new))
-                return PTR_ERR(new);
+        if (!scratch)
+                return -ENOMEM;
 
+        new = mpol_new(mode, flags, nodes);
+        if (IS_ERR(new)) {
+                ret = PTR_ERR(new);
+                goto out;
+        }
         /*
          * prevent changing our mempolicy while show_numa_maps()
          * is using it.
@@ -635,13 +644,13 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
         if (mm)
                 down_write(&mm->mmap_sem);
         task_lock(current);
-        ret = mpol_set_nodemask(new, nodes);
+        ret = mpol_set_nodemask(new, nodes, scratch);
         if (ret) {
                 task_unlock(current);
                 if (mm)
                         up_write(&mm->mmap_sem);
                 mpol_put(new);
-                return ret;
+                goto out;
         }
         old = current->mempolicy;
         current->mempolicy = new;
@@ -654,7 +663,10 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
                 up_write(&mm->mmap_sem);
 
         mpol_put(old);
-        return 0;
+        ret = 0;
+out:
+        NODEMASK_SCRATCH_FREE(scratch);
+        return ret;
 }
 
 /*
@@ -1014,12 +1026,20 @@ static long do_mbind(unsigned long start, unsigned long len,
                 if (err)
                         return err;
         }
-        down_write(&mm->mmap_sem);
-        task_lock(current);
-        err = mpol_set_nodemask(new, nmask);
-        task_unlock(current);
+        {
+                NODEMASK_SCRATCH(scratch);
+                if (scratch) {
+                        down_write(&mm->mmap_sem);
+                        task_lock(current);
+                        err = mpol_set_nodemask(new, nmask, scratch);
+                        task_unlock(current);
+                        if (err)
+                                up_write(&mm->mmap_sem);
+                } else
+                        err = -ENOMEM;
+                NODEMASK_SCRATCH_FREE(scratch);
+        }
         if (err) {
-                up_write(&mm->mmap_sem);
                 mpol_put(new);
                 return err;
         }
@@ -1891,6 +1911,7 @@ restart:
  * Install non-NULL @mpol in inode's shared policy rb-tree.
  * On entry, the current task has a reference on a non-NULL @mpol.
  * This must be released on exit.
+ * This is called at get_inode() calls and we can use GFP_KERNEL.
  */
 void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 {
@@ -1902,19 +1923,24 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
         if (mpol) {
                 struct vm_area_struct pvma;
                 struct mempolicy *new;
+                NODEMASK_SCRATCH(scratch);
 
+                if (!scratch)
+                        return;
                 /* contextualize the tmpfs mount point mempolicy */
                 new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
                 if (IS_ERR(new)) {
                         mpol_put(mpol); /* drop our ref on sb mpol */
+                        NODEMASK_SCRATCH_FREE(scratch);
                         return;         /* no valid nodemask intersection */
                 }
 
                 task_lock(current);
-                ret = mpol_set_nodemask(new, &mpol->w.user_nodemask);
+                ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch);
                 task_unlock(current);
                 mpol_put(mpol); /* drop our ref on sb mpol */
                 if (ret) {
+                        NODEMASK_SCRATCH_FREE(scratch);
                         mpol_put(new);
                         return;
                 }
@@ -1924,6 +1950,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
                 pvma.vm_end = TASK_SIZE;        /* policy covers entire file */
                 mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
                 mpol_put(new);                  /* drop initial ref */
+                NODEMASK_SCRATCH_FREE(scratch);
         }
 }
 
@@ -2140,13 +2167,18 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
                 err = 1;
         else {
                 int ret;
-
-                task_lock(current);
-                ret = mpol_set_nodemask(new, &nodes);
-                task_unlock(current);
-                if (ret)
+                NODEMASK_SCRATCH(scratch);
+                if (scratch) {
+                        task_lock(current);
+                        ret = mpol_set_nodemask(new, &nodes, scratch);
+                        task_unlock(current);
+                } else
+                        ret = -ENOMEM;
+                NODEMASK_SCRATCH_FREE(scratch);
+                if (ret) {
                         err = 1;
-                else if (no_context) {
+                        mpol_put(new);
+                } else if (no_context) {
                         /* save for contextualization */
                         new->w.user_nodemask = nodes;
                 }
diff --git a/mm/mempool.c b/mm/mempool.c
index a46eb1b4bb66..32e75d400503 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -303,14 +303,14 @@ EXPORT_SYMBOL(mempool_free_slab);
  */
 void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data)
 {
-        size_t size = (size_t)(long)pool_data;
+        size_t size = (size_t)pool_data;
         return kmalloc(size, gfp_mask);
 }
 EXPORT_SYMBOL(mempool_kmalloc);
 
 void *mempool_kzalloc(gfp_t gfp_mask, void *pool_data)
 {
-        size_t size = (size_t) pool_data;
+        size_t size = (size_t)pool_data;
         return kzalloc(size, gfp_mask);
 }
 EXPORT_SYMBOL(mempool_kzalloc);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index caa92689aac9..d052abbe3063 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -882,7 +882,7 @@ retry_reserve:
  */
 static int rmqueue_bulk(struct zone *zone, unsigned int order, 
                         unsigned long count, struct list_head *list,
-                        int migratetype)
+                        int migratetype, int cold)
 {
         int i;
         
@@ -901,7 +901,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
                  * merge IO requests if the physical pages are ordered
                  * properly.
                  */
-                list_add(&page->lru, list);
+                if (likely(cold == 0))
+                        list_add(&page->lru, list);
+                else
+                        list_add_tail(&page->lru, list);
                 set_page_private(page, migratetype);
                 list = &page->lru;
         }
@@ -1119,7 +1122,8 @@ again:
                 local_irq_save(flags);
                 if (!pcp->count) {
                         pcp->count = rmqueue_bulk(zone, 0,
-                                        pcp->batch, &pcp->list, migratetype);
+                                        pcp->batch, &pcp->list,
+                                        migratetype, cold);
                         if (unlikely(!pcp->count))
                                 goto failed;
                 }
@@ -1138,7 +1142,8 @@ again:
                 /* Allocate more to the pcp list if necessary */
                 if (unlikely(&page->lru == &pcp->list)) {
                         pcp->count += rmqueue_bulk(zone, 0,
-                                        pcp->batch, &pcp->list, migratetype);
+                                        pcp->batch, &pcp->list,
+                                        migratetype, cold);
                         page = list_entry(pcp->list.next, struct page, lru);
                 }
 
@@ -1740,8 +1745,10 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
          * be using allocators in order of preference for an area that is
          * too large.
          */
-        if (WARN_ON_ONCE(order >= MAX_ORDER))
+        if (order >= MAX_ORDER) {
+                WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN));
                 return NULL;
+        }
 
         /*
          * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
@@ -1789,6 +1796,10 @@ rebalance:
         if (p->flags & PF_MEMALLOC)
                 goto nopage;
 
+        /* Avoid allocations with no watermarks from looping endlessly */
+        if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
+                goto nopage;
+
         /* Try direct reclaim and then allocating */
         page = __alloc_pages_direct_reclaim(gfp_mask, order,
                                         zonelist, high_zoneidx,
diff --git a/mm/swapfile.c b/mm/swapfile.c
index d1ade1a48ee7..8ffdc0d23c53 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -753,7 +753,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
 
                 if (!bdev) {
                         if (bdev_p)
-                                *bdev_p = bdget(sis->bdev->bd_dev);
+                                *bdev_p = bdgrab(sis->bdev);
 
                         spin_unlock(&swap_lock);
                         return i;
@@ -765,7 +765,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
                                         struct swap_extent, list);
                         if (se->start_block == offset) {
                                 if (bdev_p)
-                                        *bdev_p = bdget(sis->bdev->bd_dev);
+                                        *bdev_p = bdgrab(sis->bdev);
 
                                 spin_unlock(&swap_lock);
                                 bdput(bdev);