Merge commit 'v3.3' into fbdev-next

13 files changed, 130 insertions, 97 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 91d3efb25d15..8f7fc394f636 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -671,6 +671,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		set_pmd_at(mm, haddr, pmd, entry);
 		prepare_pmd_huge_pte(pgtable, mm);
 		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
+		mm->nr_ptes++;
 		spin_unlock(&mm->page_table_lock);
 	}
 
@@ -789,6 +790,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	pmd = pmd_mkold(pmd_wrprotect(pmd));
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
 	prepare_pmd_huge_pte(pgtable, dst_mm);
+	dst_mm->nr_ptes++;
 
 	ret = 0;
 out_unlock:
@@ -887,7 +889,6 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 	}
 	kfree(pages);
 
-	mm->nr_ptes++;
 	smp_wmb(); /* make pte visible before pmd */
 	pmd_populate(mm, pmd, pgtable);
 	page_remove_rmap(page);
@@ -1047,6 +1048,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			VM_BUG_ON(page_mapcount(page) < 0);
 			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
 			VM_BUG_ON(!PageHead(page));
+			tlb->mm->nr_ptes--;
 			spin_unlock(&tlb->mm->page_table_lock);
 			tlb_remove_page(tlb, page);
 			pte_free(tlb->mm, pgtable);
@@ -1375,7 +1377,6 @@ static int __split_huge_page_map(struct page *page,
 			pte_unmap(pte);
 		}
 
-		mm->nr_ptes++;
 		smp_wmb(); /* make pte visible before pmd */
 		/*
 		 * Up to this point the pmd is present and huge and
@@ -1988,7 +1989,6 @@ static void collapse_huge_page(struct mm_struct *mm,
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache(vma, address, _pmd);
 	prepare_pmd_huge_pte(pgtable, mm);
-	mm->nr_ptes--;
 	spin_unlock(&mm->page_table_lock);
 
 #ifndef CONFIG_NUMA
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5f34bd8dda34..a876871f6be5 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2277,8 +2277,8 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			set_page_dirty(page);
 		list_add(&page->lru, &page_list);
 	}
-	spin_unlock(&mm->page_table_lock);
 	flush_tlb_range(vma, start, end);
+	spin_unlock(&mm->page_table_lock);
 	mmu_notifier_invalidate_range_end(mm, start, end);
 	list_for_each_entry_safe(page, tmp, &page_list, lru) {
 		page_remove_rmap(page);
diff --git a/mm/ksm.c b/mm/ksm.c
index 1925ffbfb27f..310544a379ae 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -28,7 +28,6 @@
 #include <linux/kthread.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
-#include <linux/memcontrol.h>
 #include <linux/rbtree.h>
 #include <linux/memory.h>
 #include <linux/mmu_notifier.h>
@@ -1572,16 +1571,6 @@ struct page *ksm_does_need_to_copy(struct page *page,
 
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
 	if (new_page) {
-		/*
-		 * The memcg-specific accounting when moving
-		 * pages around the LRU lists relies on the
-		 * page's owner (memcg) to be valid.  Usually,
-		 * pages are assigned to a new owner before
-		 * being put on the LRU list, but since this
-		 * is not the case here, the stale owner from
-		 * a previous allocation cycle must be reset.
-		 */
-		mem_cgroup_reset_owner(new_page);
 		copy_user_highpage(new_page, page, address, vma);
 
 		SetPageDirty(new_page);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 228d6461c12a..58a08fc7414a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -230,10 +230,30 @@ struct mem_cgroup {
 	 * the counter to account for memory usage
 	 */
 	struct res_counter res;
-	/*
-	 * the counter to account for mem+swap usage.
-	 */
-	struct res_counter memsw;
+
+	union {
+		/*
+		 * the counter to account for mem+swap usage.
+		 */
+		struct res_counter memsw;
+
+		/*
+		 * rcu_freeing is used only when freeing struct mem_cgroup,
+		 * so put it into a union to avoid wasting more memory.
+		 * It must be disjoint from the css field.  It could be
+		 * in a union with the res field, but res plays a much
+		 * larger part in mem_cgroup life than memsw, and might
+		 * be of interest, even at time of free, when debugging.
+		 * So share rcu_head with the less interesting memsw.
+		 */
+		struct rcu_head rcu_freeing;
+		/*
+		 * But when using vfree(), that cannot be done at
+		 * interrupt time, so we must then queue the work.
+		 */
+		struct work_struct work_freeing;
+	};
+
 	/*
 	 * Per cgroup active and inactive list, similar to the
 	 * per zone LRU lists.
@@ -1042,6 +1062,19 @@ struct lruvec *mem_cgroup_lru_add_list(struct zone *zone, struct page *page,
 
 	pc = lookup_page_cgroup(page);
 	memcg = pc->mem_cgroup;
+
+	/*
+	 * Surreptitiously switch any uncharged page to root:
+	 * an uncharged page off lru does nothing to secure
+	 * its former mem_cgroup from sudden removal.
+	 *
+	 * Our caller holds lru_lock, and PageCgroupUsed is updated
+	 * under page_cgroup lock: between them, they make all uses
+	 * of pc->mem_cgroup safe.
+	 */
+	if (!PageCgroupUsed(pc) && memcg != root_mem_cgroup)
+		pc->mem_cgroup = memcg = root_mem_cgroup;
+
 	mz = page_cgroup_zoneinfo(memcg, page);
 	/* compound_order() is stabilized through lru_lock */
 	MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page);
@@ -2408,8 +2441,12 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 				       struct page *page,
 				       unsigned int nr_pages,
 				       struct page_cgroup *pc,
-				       enum charge_type ctype)
+				       enum charge_type ctype,
+				       bool lrucare)
 {
+	struct zone *uninitialized_var(zone);
+	bool was_on_lru = false;
+
 	lock_page_cgroup(pc);
 	if (unlikely(PageCgroupUsed(pc))) {
 		unlock_page_cgroup(pc);
@@ -2420,6 +2457,21 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	 * we don't need page_cgroup_lock about tail pages, becase they are not
 	 * accessed by any other context at this point.
 	 */
+
+	/*
+	 * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page
+	 * may already be on some other mem_cgroup's LRU.  Take care of it.
+	 */
+	if (lrucare) {
+		zone = page_zone(page);
+		spin_lock_irq(&zone->lru_lock);
+		if (PageLRU(page)) {
+			ClearPageLRU(page);
+			del_page_from_lru_list(zone, page, page_lru(page));
+			was_on_lru = true;
+		}
+	}
+
 	pc->mem_cgroup = memcg;
 	/*
 	 * We access a page_cgroup asynchronously without lock_page_cgroup().
@@ -2443,9 +2495,18 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 		break;
 	}
 
+	if (lrucare) {
+		if (was_on_lru) {
+			VM_BUG_ON(PageLRU(page));
+			SetPageLRU(page);
+			add_page_to_lru_list(zone, page, page_lru(page));
+		}
+		spin_unlock_irq(&zone->lru_lock);
+	}
+
 	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), nr_pages);
 	unlock_page_cgroup(pc);
-	WARN_ON_ONCE(PageLRU(page));
+
 	/*
 	 * "charge_statistics" updated event counter. Then, check it.
 	 * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
@@ -2643,7 +2704,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 	ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &memcg, oom);
 	if (ret == -ENOMEM)
 		return ret;
-	__mem_cgroup_commit_charge(memcg, page, nr_pages, pc, ctype);
+	__mem_cgroup_commit_charge(memcg, page, nr_pages, pc, ctype, false);
 	return 0;
 }
 
@@ -2663,35 +2724,6 @@ static void
 __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
 					enum charge_type ctype);
 
-static void
-__mem_cgroup_commit_charge_lrucare(struct page *page, struct mem_cgroup *memcg,
-					enum charge_type ctype)
-{
-	struct page_cgroup *pc = lookup_page_cgroup(page);
-	struct zone *zone = page_zone(page);
-	unsigned long flags;
-	bool removed = false;
-
-	/*
-	 * In some case, SwapCache, FUSE(splice_buf->radixtree), the page
-	 * is already on LRU. It means the page may on some other page_cgroup's
-	 * LRU. Take care of it.
-	 */
-	spin_lock_irqsave(&zone->lru_lock, flags);
-	if (PageLRU(page)) {
-		del_page_from_lru_list(zone, page, page_lru(page));
-		ClearPageLRU(page);
-		removed = true;
-	}
-	__mem_cgroup_commit_charge(memcg, page, 1, pc, ctype);
-	if (removed) {
-		add_page_to_lru_list(zone, page, page_lru(page));
-		SetPageLRU(page);
-	}
-	spin_unlock_irqrestore(&zone->lru_lock, flags);
-	return;
-}
-
 int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask)
 {
@@ -2769,13 +2801,16 @@ static void
 __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 					enum charge_type ctype)
 {
+	struct page_cgroup *pc;
+
 	if (mem_cgroup_disabled())
 		return;
 	if (!memcg)
 		return;
 	cgroup_exclude_rmdir(&memcg->css);
 
-	__mem_cgroup_commit_charge_lrucare(page, memcg, ctype);
+	pc = lookup_page_cgroup(page);
+	__mem_cgroup_commit_charge(memcg, page, 1, pc, ctype, true);
 	/*
 	 * Now swap is on-memory. This means this page may be
 	 * counted both as mem and swap....double count.
@@ -3027,23 +3062,6 @@ void mem_cgroup_uncharge_end(void)
 	batch->memcg = NULL;
 }
 
-/*
- * A function for resetting pc->mem_cgroup for newly allocated pages.
- * This function should be called if the newpage will be added to LRU
- * before start accounting.
- */
-void mem_cgroup_reset_owner(struct page *newpage)
-{
-	struct page_cgroup *pc;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	pc = lookup_page_cgroup(newpage);
-	VM_BUG_ON(PageCgroupUsed(pc));
-	pc->mem_cgroup = root_mem_cgroup;
-}
-
 #ifdef CONFIG_SWAP
 /*
  * called after __delete_from_swap_cache() and drop "page" account.
@@ -3248,7 +3266,7 @@ 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, newpage, 1, pc, ctype);
+	__mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype, false);
 	return ret;
 }
 
@@ -3332,7 +3350,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	 * the newpage may be on LRU(or pagevec for LRU) already. We lock
 	 * LRU while we overwrite pc->mem_cgroup.
 	 */
-	__mem_cgroup_commit_charge_lrucare(newpage, memcg, type);
+	__mem_cgroup_commit_charge(memcg, newpage, 1, pc, type, true);
 }
 
 #ifdef CONFIG_DEBUG_VM
@@ -4782,6 +4800,27 @@ out_free:
 }
 
 /*
+ * Helpers for freeing a vzalloc()ed mem_cgroup by RCU,
+ * but in process context.  The work_freeing structure is overlaid
+ * on the rcu_freeing structure, which itself is overlaid on memsw.
+ */
+static void vfree_work(struct work_struct *work)
+{
+	struct mem_cgroup *memcg;
+
+	memcg = container_of(work, struct mem_cgroup, work_freeing);
+	vfree(memcg);
+}
+static void vfree_rcu(struct rcu_head *rcu_head)
+{
+	struct mem_cgroup *memcg;
+
+	memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
+	INIT_WORK(&memcg->work_freeing, vfree_work);
+	schedule_work(&memcg->work_freeing);
+}
+
+/*
  * At destroying mem_cgroup, references from swap_cgroup can remain.
  * (scanning all at force_empty is too costly...)
  *
@@ -4804,9 +4843,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 
 	free_percpu(memcg->stat);
 	if (sizeof(struct mem_cgroup) < PAGE_SIZE)
-		kfree(memcg);
+		kfree_rcu(memcg, rcu_freeing);
 	else
-		vfree(memcg);
+		call_rcu(&memcg->rcu_freeing, vfree_rcu);
 }
 
 static void mem_cgroup_get(struct mem_cgroup *memcg)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 06b145fb64ab..47296fee23db 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -640,10 +640,11 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 	unsigned long vmstart;
 	unsigned long vmend;
 
-	vma = find_vma_prev(mm, start, &prev);
+	vma = find_vma(mm, start);
 	if (!vma || vma->vm_start > start)
 		return -EFAULT;
 
+	prev = vma->vm_prev;
 	if (start > vma->vm_start)
 		prev = vma;
 
diff --git a/mm/migrate.c b/mm/migrate.c
index df141f60289e..1503b6b54ecb 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -839,8 +839,6 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	if (!newpage)
 		return -ENOMEM;
 
-	mem_cgroup_reset_owner(newpage);
-
 	if (page_count(page) == 1) {
 		/* page was freed from under us. So we are done. */
 		goto out;
diff --git a/mm/mlock.c b/mm/mlock.c
index 4f4f53bdc65d..ef726e8aa8e9 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -385,10 +385,11 @@ static int do_mlock(unsigned long start, size_t len, int on)
 		return -EINVAL;
 	if (end == start)
 		return 0;
-	vma = find_vma_prev(current->mm, start, &prev);
+	vma = find_vma(current->mm, start);
 	if (!vma || vma->vm_start > start)
 		return -ENOMEM;
 
+	prev = vma->vm_prev;
 	if (start > vma->vm_start)
 		prev = vma;
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 3f758c7f4c81..da15a79b1441 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1266,8 +1266,9 @@ munmap_back:
 	vma->vm_pgoff = pgoff;
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
+	error = -EINVAL;	/* when rejecting VM_GROWSDOWN|VM_GROWSUP */
+
 	if (file) {
-		error = -EINVAL;
 		if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
 			goto free_vma;
 		if (vm_flags & VM_DENYWRITE) {
@@ -1293,6 +1294,8 @@ munmap_back:
 		pgoff = vma->vm_pgoff;
 		vm_flags = vma->vm_flags;
 	} else if (vm_flags & VM_SHARED) {
+		if (unlikely(vm_flags & (VM_GROWSDOWN|VM_GROWSUP)))
+			goto free_vma;
 		error = shmem_zero_setup(vma);
 		if (error)
 			goto free_vma;
@@ -1605,7 +1608,6 @@ EXPORT_SYMBOL(find_vma);
 
 /*
  * Same as find_vma, but also return a pointer to the previous VMA in *pprev.
- * Note: pprev is set to NULL when return value is NULL.
  */
 struct vm_area_struct *
 find_vma_prev(struct mm_struct *mm, unsigned long addr,
@@ -1614,7 +1616,16 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr,
 	struct vm_area_struct *vma;
 
 	vma = find_vma(mm, addr);
-	*pprev = vma ? vma->vm_prev : NULL;
+	if (vma) {
+		*pprev = vma->vm_prev;
+	} else {
+		struct rb_node *rb_node = mm->mm_rb.rb_node;
+		*pprev = NULL;
+		while (rb_node) {
+			*pprev = rb_entry(rb_node, struct vm_area_struct, vm_rb);
+			rb_node = rb_node->rb_right;
+		}
+	}
 	return vma;
 }
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 5a688a2756be..f437d054c3bf 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -262,10 +262,11 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 
 	down_write(&current->mm->mmap_sem);
 
-	vma = find_vma_prev(current->mm, start, &prev);
+	vma = find_vma(current->mm, start);
 	error = -ENOMEM;
 	if (!vma)
 		goto out;
+	prev = vma->vm_prev;
 	if (unlikely(grows & PROT_GROWSDOWN)) {
 		if (vma->vm_start >= end)
 			goto out;
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index de1616aa9b1e..1ccbd714059c 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -379,13 +379,15 @@ static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
 	pgoff_t offset = swp_offset(ent);
 	struct swap_cgroup_ctrl *ctrl;
 	struct page *mappage;
+	struct swap_cgroup *sc;
 
 	ctrl = &swap_cgroup_ctrl[swp_type(ent)];
 	if (ctrlp)
 		*ctrlp = ctrl;
 
 	mappage = ctrl->map[offset / SC_PER_PAGE];
-	return page_address(mappage) + offset % SC_PER_PAGE;
+	sc = page_address(mappage);
+	return sc + offset % SC_PER_PAGE;
 }
 
 /**
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 12a48a88c0d8..405d331804c3 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -184,8 +184,7 @@ static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
 				   page_end - page_start);
 	}
 
-	for (i = page_start; i < page_end; i++)
-		__clear_bit(i, populated);
+	bitmap_clear(populated, page_start, page_end - page_start);
 }
 
 /**
diff --git a/mm/swap.c b/mm/swap.c
index fff1ff7fb9ad..14380e9fbe33 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -652,7 +652,7 @@ EXPORT_SYMBOL(__pagevec_release);
 void lru_add_page_tail(struct zone* zone,
 		       struct page *page, struct page *page_tail)
 {
-	int active;
+	int uninitialized_var(active);
 	enum lru_list lru;
 	const int file = 0;
 
@@ -672,7 +672,6 @@ void lru_add_page_tail(struct zone* zone,
 			active = 0;
 			lru = LRU_INACTIVE_ANON;
 		}
-		update_page_reclaim_stat(zone, page_tail, file, active);
 	} else {
 		SetPageUnevictable(page_tail);
 		lru = LRU_UNEVICTABLE;
@@ -693,6 +692,9 @@ void lru_add_page_tail(struct zone* zone,
 		list_head = page_tail->lru.prev;
 		list_move_tail(&page_tail->lru, list_head);
 	}
+
+	if (!PageUnevictable(page))
+		update_page_reclaim_stat(zone, page_tail, file, active);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -710,8 +712,8 @@ static void __pagevec_lru_add_fn(struct page *page, void *arg)
 	SetPageLRU(page);
 	if (active)
 		SetPageActive(page);
-	update_page_reclaim_stat(zone, page, file, active);
 	add_page_to_lru_list(zone, page, lru);
+	update_page_reclaim_stat(zone, page, file, active);
 }
 
 /*
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 470038a91873..ea6b32d61873 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -300,16 +300,6 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			new_page = alloc_page_vma(gfp_mask, vma, addr);
 			if (!new_page)
 				break;		/* Out of memory */
-			/*
-			 * The memcg-specific accounting when moving
-			 * pages around the LRU lists relies on the
-			 * page's owner (memcg) to be valid.  Usually,
-			 * pages are assigned to a new owner before
-			 * being put on the LRU list, but since this
-			 * is not the case here, the stale owner from
-			 * a previous allocation cycle must be reset.
-			 */
-			mem_cgroup_reset_owner(new_page);
 		}
 
 		/*