Merge tag 'v3.4-rc2' into perf/core

Merge Linux 3.4-rc2: we were on v3.3, update the base.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

8 files changed, 211 insertions, 60 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index c3811bc6b9e3..79c4b2b0b14e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -813,20 +813,19 @@ EXPORT_SYMBOL(find_or_create_page);
 unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
 			    unsigned int nr_pages, struct page **pages)
 {
-	unsigned int i;
-	unsigned int ret;
-	unsigned int nr_found, nr_skip;
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned ret = 0;
+
+	if (unlikely(!nr_pages))
+		return 0;
 
 	rcu_read_lock();
 restart:
-	nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
-				(void ***)pages, NULL, start, nr_pages);
-	ret = 0;
-	nr_skip = 0;
-	for (i = 0; i < nr_found; i++) {
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
 		struct page *page;
 repeat:
-		page = radix_tree_deref_slot((void **)pages[i]);
+		page = radix_tree_deref_slot(slot);
 		if (unlikely(!page))
 			continue;
 
@@ -837,7 +836,7 @@ repeat:
 				 * when entry at index 0 moves out of or back
 				 * to root: none yet gotten, safe to restart.
 				 */
-				WARN_ON(start | i);
+				WARN_ON(iter.index);
 				goto restart;
 			}
 			/*
@@ -845,7 +844,6 @@ repeat:
 			 * here as an exceptional entry: so skip over it -
 			 * we only reach this from invalidate_mapping_pages().
 			 */
-			nr_skip++;
 			continue;
 		}
 
@@ -853,21 +851,16 @@ repeat:
 			goto repeat;
 
 		/* Has the page moved? */
-		if (unlikely(page != *((void **)pages[i]))) {
+		if (unlikely(page != *slot)) {
 			page_cache_release(page);
 			goto repeat;
 		}
 
 		pages[ret] = page;
-		ret++;
+		if (++ret == nr_pages)
+			break;
 	}
 
-	/*
-	 * If all entries were removed before we could secure them,
-	 * try again, because callers stop trying once 0 is returned.
-	 */
-	if (unlikely(!ret && nr_found > nr_skip))
-		goto restart;
 	rcu_read_unlock();
 	return ret;
 }
@@ -887,21 +880,22 @@ repeat:
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
 			       unsigned int nr_pages, struct page **pages)
 {
-	unsigned int i;
-	unsigned int ret;
-	unsigned int nr_found;
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
+
+	if (unlikely(!nr_pages))
+		return 0;
 
 	rcu_read_lock();
 restart:
-	nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
-				(void ***)pages, NULL, index, nr_pages);
-	ret = 0;
-	for (i = 0; i < nr_found; i++) {
+	radix_tree_for_each_contig(slot, &mapping->page_tree, &iter, index) {
 		struct page *page;
 repeat:
-		page = radix_tree_deref_slot((void **)pages[i]);
+		page = radix_tree_deref_slot(slot);
+		/* The hole, there no reason to continue */
 		if (unlikely(!page))
-			continue;
+			break;
 
 		if (radix_tree_exception(page)) {
 			if (radix_tree_deref_retry(page)) {
@@ -924,7 +918,7 @@ repeat:
 			goto repeat;
 
 		/* Has the page moved? */
-		if (unlikely(page != *((void **)pages[i]))) {
+		if (unlikely(page != *slot)) {
 			page_cache_release(page);
 			goto repeat;
 		}
@@ -934,14 +928,14 @@ repeat:
 		 * otherwise we can get both false positives and false
 		 * negatives, which is just confusing to the caller.
 		 */
-		if (page->mapping == NULL || page->index != index) {
+		if (page->mapping == NULL || page->index != iter.index) {
 			page_cache_release(page);
 			break;
 		}
 
 		pages[ret] = page;
-		ret++;
-		index++;
+		if (++ret == nr_pages)
+			break;
 	}
 	rcu_read_unlock();
 	return ret;
@@ -962,19 +956,20 @@ EXPORT_SYMBOL(find_get_pages_contig);
 unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
 			int tag, unsigned int nr_pages, struct page **pages)
 {
-	unsigned int i;
-	unsigned int ret;
-	unsigned int nr_found;
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned ret = 0;
+
+	if (unlikely(!nr_pages))
+		return 0;
 
 	rcu_read_lock();
 restart:
-	nr_found = radix_tree_gang_lookup_tag_slot(&mapping->page_tree,
-				(void ***)pages, *index, nr_pages, tag);
-	ret = 0;
-	for (i = 0; i < nr_found; i++) {
+	radix_tree_for_each_tagged(slot, &mapping->page_tree,
+				   &iter, *index, tag) {
 		struct page *page;
 repeat:
-		page = radix_tree_deref_slot((void **)pages[i]);
+		page = radix_tree_deref_slot(slot);
 		if (unlikely(!page))
 			continue;
 
@@ -998,21 +993,16 @@ repeat:
 			goto repeat;
 
 		/* Has the page moved? */
-		if (unlikely(page != *((void **)pages[i]))) {
+		if (unlikely(page != *slot)) {
 			page_cache_release(page);
 			goto repeat;
 		}
 
 		pages[ret] = page;
-		ret++;
+		if (++ret == nr_pages)
+			break;
 	}
 
-	/*
-	 * If all entries were removed before we could secure them,
-	 * try again, because callers stop trying once 0 is returned.
-	 */
-	if (unlikely(!ret && nr_found))
-		goto restart;
 	rcu_read_unlock();
 
 	if (ret)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b2ee6df0e9bb..7d698df4a067 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5306,6 +5306,8 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 		return 0;
 	}
 
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE)
 		if (get_mctgt_type(vma, addr, *pte, NULL))
@@ -5502,6 +5504,8 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 		return 0;
 	}
 
+	if (pmd_trans_unstable(pmd))
+		return 0;
 retry:
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; addr += PAGE_SIZE) {
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3fc261705b1e..26adea8ca2e7 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -95,6 +95,8 @@ unsigned long vm_dirty_bytes;
  */
 unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */
 
+EXPORT_SYMBOL_GPL(dirty_writeback_interval);
+
 /*
  * The longest time for which data is allowed to remain dirty
  */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index caea788628e4..a712fb9e04ce 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1161,11 +1161,47 @@ void drain_local_pages(void *arg)
 }
 
 /*
- * Spill all the per-cpu pages from all CPUs back into the buddy allocator
+ * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
+ *
+ * Note that this code is protected against sending an IPI to an offline
+ * CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
+ * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
+ * nothing keeps CPUs from showing up after we populated the cpumask and
+ * before the call to on_each_cpu_mask().
  */
 void drain_all_pages(void)
 {
-	on_each_cpu(drain_local_pages, NULL, 1);
+	int cpu;
+	struct per_cpu_pageset *pcp;
+	struct zone *zone;
+
+	/*
+	 * Allocate in the BSS so we wont require allocation in
+	 * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
+	 */
+	static cpumask_t cpus_with_pcps;
+
+	/*
+	 * We don't care about racing with CPU hotplug event
+	 * as offline notification will cause the notified
+	 * cpu to drain that CPU pcps and on_each_cpu_mask
+	 * disables preemption as part of its processing
+	 */
+	for_each_online_cpu(cpu) {
+		bool has_pcps = false;
+		for_each_populated_zone(zone) {
+			pcp = per_cpu_ptr(zone->pageset, cpu);
+			if (pcp->pcp.count) {
+				has_pcps = true;
+				break;
+			}
+		}
+		if (has_pcps)
+			cpumask_set_cpu(cpu, &cpus_with_pcps);
+		else
+			cpumask_clear_cpu(cpu, &cpus_with_pcps);
+	}
+	on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1);
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -2308,6 +2344,10 @@ rebalance:
 		if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
 			if (oom_killer_disabled)
 				goto nopage;
+			/* Coredumps can quickly deplete all memory reserves */
+			if ((current->flags & PF_DUMPCORE) &&
+			    !(gfp_mask & __GFP_NOFAIL))
+				goto nopage;
 			page = __alloc_pages_may_oom(gfp_mask, order,
 					zonelist, high_zoneidx,
 					nodemask, preferred_zone,
diff --git a/mm/slab.c b/mm/slab.c
index 29c8716eb7a9..e901a36e2520 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1731,6 +1731,52 @@ static int __init cpucache_init(void)
 }
 __initcall(cpucache_init);
 
+static noinline void
+slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
+{
+	struct kmem_list3 *l3;
+	struct slab *slabp;
+	unsigned long flags;
+	int node;
+
+	printk(KERN_WARNING
+		"SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n",
+		nodeid, gfpflags);
+	printk(KERN_WARNING "  cache: %s, object size: %d, order: %d\n",
+		cachep->name, cachep->buffer_size, cachep->gfporder);
+
+	for_each_online_node(node) {
+		unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
+		unsigned long active_slabs = 0, num_slabs = 0;
+
+		l3 = cachep->nodelists[node];
+		if (!l3)
+			continue;
+
+		spin_lock_irqsave(&l3->list_lock, flags);
+		list_for_each_entry(slabp, &l3->slabs_full, list) {
+			active_objs += cachep->num;
+			active_slabs++;
+		}
+		list_for_each_entry(slabp, &l3->slabs_partial, list) {
+			active_objs += slabp->inuse;
+			active_slabs++;
+		}
+		list_for_each_entry(slabp, &l3->slabs_free, list)
+			num_slabs++;
+
+		free_objects += l3->free_objects;
+		spin_unlock_irqrestore(&l3->list_lock, flags);
+
+		num_slabs += active_slabs;
+		num_objs = num_slabs * cachep->num;
+		printk(KERN_WARNING
+			"  node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
+			node, active_slabs, num_slabs, active_objs, num_objs,
+			free_objects);
+	}
+}
+
 /*
  * Interface to system's page allocator. No need to hold the cache-lock.
  *
@@ -1757,8 +1803,11 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 		flags |= __GFP_RECLAIMABLE;
 
 	page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
-	if (!page)
+	if (!page) {
+		if (!(flags & __GFP_NOWARN) && printk_ratelimit())
+			slab_out_of_memory(cachep, flags, nodeid);
 		return NULL;
+	}
 
 	nr_pages = (1 << cachep->gfporder);
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
@@ -3696,13 +3745,12 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp,
 
 	if (likely(ac->avail < ac->limit)) {
 		STATS_INC_FREEHIT(cachep);
-		ac->entry[ac->avail++] = objp;
-		return;
 	} else {
 		STATS_INC_FREEMISS(cachep);
 		cache_flusharray(cachep, ac);
-		ac->entry[ac->avail++] = objp;
 	}
+
+	ac->entry[ac->avail++] = objp;
 }
 
 /**
diff --git a/mm/slub.c b/mm/slub.c
index f4a6229848fd..ffe13fdf8144 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -29,6 +29,7 @@
 #include <linux/math64.h>
 #include <linux/fault-inject.h>
 #include <linux/stacktrace.h>
+#include <linux/prefetch.h>
 
 #include <trace/events/kmem.h>
 
@@ -269,6 +270,11 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object)
 	return *(void **)(object + s->offset);
 }
 
+static void prefetch_freepointer(const struct kmem_cache *s, void *object)
+{
+	prefetch(object + s->offset);
+}
+
 static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
 {
 	void *p;
@@ -1560,6 +1566,7 @@ static void *get_partial_node(struct kmem_cache *s,
 		} else {
 			page->freelist = t;
 			available = put_cpu_partial(s, page, 0);
+			stat(s, CPU_PARTIAL_NODE);
 		}
 		if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
 			break;
@@ -1983,6 +1990,7 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 				local_irq_restore(flags);
 				pobjects = 0;
 				pages = 0;
+				stat(s, CPU_PARTIAL_DRAIN);
 			}
 		}
 
@@ -1994,7 +2002,6 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 		page->next = oldpage;
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
-	stat(s, CPU_PARTIAL_FREE);
 	return pobjects;
 }
 
@@ -2028,9 +2035,17 @@ static void flush_cpu_slab(void *d)
 	__flush_cpu_slab(s, smp_processor_id());
 }
 
+static bool has_cpu_slab(int cpu, void *info)
+{
+	struct kmem_cache *s = info;
+	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
+
+	return !!(c->page);
+}
+
 static void flush_all(struct kmem_cache *s)
 {
-	on_each_cpu(flush_cpu_slab, s, 1);
+	on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC);
 }
 
 /*
@@ -2319,6 +2334,8 @@ redo:
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 
 	else {
+		void *next_object = get_freepointer_safe(s, object);
+
 		/*
 		 * The cmpxchg will only match if there was no additional
 		 * operation and if we are on the right processor.
@@ -2334,11 +2351,12 @@ redo:
 		if (unlikely(!this_cpu_cmpxchg_double(
 				s->cpu_slab->freelist, s->cpu_slab->tid,
 				object, tid,
-				get_freepointer_safe(s, object), next_tid(tid)))) {
+				next_object, next_tid(tid)))) {
 
 			note_cmpxchg_failure("slab_alloc", s, tid);
 			goto redo;
 		}
+		prefetch_freepointer(s, next_object);
 		stat(s, ALLOC_FASTPATH);
 	}
 
@@ -2475,9 +2493,10 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 		 * If we just froze the page then put it onto the
 		 * per cpu partial list.
 		 */
-		if (new.frozen && !was_frozen)
+		if (new.frozen && !was_frozen) {
 			put_cpu_partial(s, page, 1);
-
+			stat(s, CPU_PARTIAL_FREE);
+		}
 		/*
 		 * The list lock was not taken therefore no list
 		 * activity can be necessary.
@@ -3939,13 +3958,14 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		if (kmem_cache_open(s, n,
 				size, align, flags, ctor)) {
 			list_add(&s->list, &slab_caches);
+			up_write(&slub_lock);
 			if (sysfs_slab_add(s)) {
+				down_write(&slub_lock);
 				list_del(&s->list);
 				kfree(n);
 				kfree(s);
 				goto err;
 			}
-			up_write(&slub_lock);
 			return s;
 		}
 		kfree(n);
@@ -5069,6 +5089,8 @@ STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail);
 STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail);
 STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc);
 STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free);
+STAT_ATTR(CPU_PARTIAL_NODE, cpu_partial_node);
+STAT_ATTR(CPU_PARTIAL_DRAIN, cpu_partial_drain);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -5134,6 +5156,8 @@ static struct attribute *slab_attrs[] = {
 	&cmpxchg_double_cpu_fail_attr.attr,
 	&cpu_partial_alloc_attr.attr,
 	&cpu_partial_free_attr.attr,
+	&cpu_partial_node_attr.attr,
+	&cpu_partial_drain_attr.attr,
 #endif
 #ifdef CONFIG_FAILSLAB
 	&failslab_attr.attr,
diff --git a/mm/swapfile.c b/mm/swapfile.c
index dae42f380d6e..fafc26d1b1dc 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2022,6 +2022,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	struct page *page = NULL;
 	struct inode *inode = NULL;
 
+	if (swap_flags & ~SWAP_FLAGS_VALID)
+		return -EINVAL;
+
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
diff --git a/mm/truncate.c b/mm/truncate.c
index 18aded3a89fc..61a183b89df6 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -626,3 +626,43 @@ int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 
 	return 0;
 }
+
+/**
+ * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
+ * @inode: inode
+ * @lstart: offset of beginning of hole
+ * @lend: offset of last byte of hole
+ *
+ * This function should typically be called before the filesystem
+ * releases resources associated with the freed range (eg. deallocates
+ * blocks). This way, pagecache will always stay logically coherent
+ * with on-disk format, and the filesystem would not have to deal with
+ * situations such as writepage being called for a page that has already
+ * had its underlying blocks deallocated.
+ */
+void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend)
+{
+	struct address_space *mapping = inode->i_mapping;
+	loff_t unmap_start = round_up(lstart, PAGE_SIZE);
+	loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1;
+	/*
+	 * This rounding is currently just for example: unmap_mapping_range
+	 * expands its hole outwards, whereas we want it to contract the hole
+	 * inwards.  However, existing callers of truncate_pagecache_range are
+	 * doing their own page rounding first; and truncate_inode_pages_range
+	 * currently BUGs if lend is not pagealigned-1 (it handles partial
+	 * page at start of hole, but not partial page at end of hole).  Note
+	 * unmap_mapping_range allows holelen 0 for all, and we allow lend -1.
+	 */
+
+	/*
+	 * Unlike in truncate_pagecache, unmap_mapping_range is called only
+	 * once (before truncating pagecache), and without "even_cows" flag:
+	 * hole-punching should not remove private COWed pages from the hole.
+	 */
+	if ((u64)unmap_end > (u64)unmap_start)
+		unmap_mapping_range(mapping, unmap_start,
+				    1 + unmap_end - unmap_start, 0);
+	truncate_inode_pages_range(mapping, lstart, lend);
+}
+EXPORT_SYMBOL(truncate_pagecache_range);