Merge branch 'slub/cleanups' into slab/next

* Fix a merge conflict in mm/slub.c::acquire_slab() due to commit 02d7633
  ("slub: fix a memory leak in get_partial_node()").

Conflicts:
	mm/slub.c

Signed-off-by: Pekka Enberg <penberg@kernel.org>

2 files changed, 92 insertions, 82 deletions

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index c2f8c8b..ebdcf4b 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -48,7 +48,6 @@ struct kmem_cache_cpu {
 	unsigned long tid;	/* Globally unique transaction id */
 	struct page *page;	/* The slab from which we are allocating */
 	struct page *partial;	/* Partially allocated frozen slabs */
-	int node;		/* The node of the page (or -1 for debug) */
 #ifdef CONFIG_SLUB_STATS
 	unsigned stat[NR_SLUB_STAT_ITEMS];
 #endif
diff --git a/mm/slub.c b/mm/slub.c
index 8c691fa..2de3c99 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1490,12 +1490,12 @@ static inline void remove_partial(struct kmem_cache_node *n,
 }
 
 /*
- * Lock slab, remove from the partial list and put the object into the
- * per cpu freelist.
+ * Remove slab from the partial list, freeze it and
+ * return the pointer to the freelist.
  *
  * Returns a list of objects or NULL if it fails.
  *
- * Must hold list_lock.
+ * Must hold list_lock since we modify the partial list.
  */
 static inline void *acquire_slab(struct kmem_cache *s,
 		struct kmem_cache_node *n, struct page *page,
@@ -1510,26 +1510,27 @@ static inline void *acquire_slab(struct kmem_cache *s,
 	 * The old freelist is the list of objects for the
 	 * per cpu allocation list.
 	 */
-	do {
-		freelist = page->freelist;
-		counters = page->counters;
-		new.counters = counters;
-		if (mode) {
-			new.inuse = page->objects;
-			new.freelist = NULL;
-		} else {
-			new.freelist = freelist;
-		}
+	freelist = page->freelist;
+	counters = page->counters;
+	new.counters = counters;
+	if (mode) {
+		new.inuse = page->objects;
+		new.freelist = NULL;
+	} else {
+		new.freelist = freelist;
+	}
 
-		VM_BUG_ON(new.frozen);
-		new.frozen = 1;
+	VM_BUG_ON(new.frozen);
+	new.frozen = 1;
 
-	} while (!__cmpxchg_double_slab(s, page,
+	if (!__cmpxchg_double_slab(s, page,
 			freelist, counters,
 			new.freelist, new.counters,
-			"lock and freeze"));
+			"acquire_slab"))
+		return NULL;
 
 	remove_partial(n, page);
+	WARN_ON(!freelist);
 	return freelist;
 }
 
@@ -1563,7 +1564,6 @@ static void *get_partial_node(struct kmem_cache *s,
 
 		if (!object) {
 			c->page = page;
-			c->node = page_to_nid(page);
 			stat(s, ALLOC_FROM_PARTIAL);
 			object = t;
 			available =  page->objects - page->inuse;
@@ -1731,14 +1731,12 @@ void init_kmem_cache_cpus(struct kmem_cache *s)
 /*
  * Remove the cpu slab
  */
-static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
+static void deactivate_slab(struct kmem_cache *s, struct page *page, void *freelist)
 {
 	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
-	struct page *page = c->page;
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
 	int lock = 0;
 	enum slab_modes l = M_NONE, m = M_NONE;
-	void *freelist;
 	void *nextfree;
 	int tail = DEACTIVATE_TO_HEAD;
 	struct page new;
@@ -1749,11 +1747,6 @@ static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 		tail = DEACTIVATE_TO_TAIL;
 	}
 
-	c->tid = next_tid(c->tid);
-	c->page = NULL;
-	freelist = c->freelist;
-	c->freelist = NULL;
-
 	/*
 	 * Stage one: Free all available per cpu objects back
 	 * to the page freelist while it is still frozen. Leave the
@@ -2011,7 +2004,11 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
 	stat(s, CPUSLAB_FLUSH);
-	deactivate_slab(s, c);
+	deactivate_slab(s, c->page, c->freelist);
+
+	c->tid = next_tid(c->tid);
+	c->page = NULL;
+	c->freelist = NULL;
 }
 
 /*
@@ -2055,10 +2052,10 @@ static void flush_all(struct kmem_cache *s)
  * Check if the objects in a per cpu structure fit numa
  * locality expectations.
  */
-static inline int node_match(struct kmem_cache_cpu *c, int node)
+static inline int node_match(struct page *page, int node)
 {
 #ifdef CONFIG_NUMA
-	if (node != NUMA_NO_NODE && c->node != node)
+	if (node != NUMA_NO_NODE && page_to_nid(page) != node)
 		return 0;
 #endif
 	return 1;
@@ -2130,10 +2127,16 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
 			int node, struct kmem_cache_cpu **pc)
 {
-	void *object;
-	struct kmem_cache_cpu *c;
-	struct page *page = new_slab(s, flags, node);
+	void *freelist;
+	struct kmem_cache_cpu *c = *pc;
+	struct page *page;
+
+	freelist = get_partial(s, flags, node, c);
 
+	if (freelist)
+		return freelist;
+
+	page = new_slab(s, flags, node);
 	if (page) {
 		c = __this_cpu_ptr(s->cpu_slab);
 		if (c->page)
@@ -2143,17 +2146,16 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
 		 * No other reference to the page yet so we can
 		 * muck around with it freely without cmpxchg
 		 */
-		object = page->freelist;
+		freelist = page->freelist;
 		page->freelist = NULL;
 
 		stat(s, ALLOC_SLAB);
-		c->node = page_to_nid(page);
 		c->page = page;
 		*pc = c;
 	} else
-		object = NULL;
+		freelist = NULL;
 
-	return object;
+	return freelist;
 }
 
 /*
@@ -2173,6 +2175,7 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page)
 	do {
 		freelist = page->freelist;
 		counters = page->counters;
+
 		new.counters = counters;
 		VM_BUG_ON(!new.frozen);
 
@@ -2206,7 +2209,8 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page)
 static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			  unsigned long addr, struct kmem_cache_cpu *c)
 {
-	void **object;
+	void *freelist;
+	struct page *page;
 	unsigned long flags;
 
 	local_irq_save(flags);
@@ -2219,25 +2223,29 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	c = this_cpu_ptr(s->cpu_slab);
 #endif
 
-	if (!c->page)
+	page = c->page;
+	if (!page)
 		goto new_slab;
 redo:
-	if (unlikely(!node_match(c, node))) {
+
+	if (unlikely(!node_match(page, node))) {
 		stat(s, ALLOC_NODE_MISMATCH);
-		deactivate_slab(s, c);
+		deactivate_slab(s, page, c->freelist);
+		c->page = NULL;
+		c->freelist = NULL;
 		goto new_slab;
 	}
 
 	/* must check again c->freelist in case of cpu migration or IRQ */
-	object = c->freelist;
-	if (object)
+	freelist = c->freelist;
+	if (freelist)
 		goto load_freelist;
 
 	stat(s, ALLOC_SLOWPATH);
 
-	object = get_freelist(s, c->page);
+	freelist = get_freelist(s, page);
 
-	if (!object) {
+	if (!freelist) {
 		c->page = NULL;
 		stat(s, DEACTIVATE_BYPASS);
 		goto new_slab;
@@ -2246,50 +2254,50 @@ redo:
 	stat(s, ALLOC_REFILL);
 
 load_freelist:
-	c->freelist = get_freepointer(s, object);
+	/*
+	 * freelist is pointing to the list of objects to be used.
+	 * page is pointing to the page from which the objects are obtained.
+	 * That page must be frozen for per cpu allocations to work.
+	 */
+	VM_BUG_ON(!c->page->frozen);
+	c->freelist = get_freepointer(s, freelist);
 	c->tid = next_tid(c->tid);
 	local_irq_restore(flags);
-	return object;
+	return freelist;
 
 new_slab:
 
 	if (c->partial) {
-		c->page = c->partial;
-		c->partial = c->page->next;
-		c->node = page_to_nid(c->page);
+		page = c->page = c->partial;
+		c->partial = page->next;
 		stat(s, CPU_PARTIAL_ALLOC);
 		c->freelist = NULL;
 		goto redo;
 	}
 
-	/* Then do expensive stuff like retrieving pages from the partial lists */
-	object = get_partial(s, gfpflags, node, c);
-
-	if (unlikely(!object)) {
+	freelist = new_slab_objects(s, gfpflags, node, &c);
 
-		object = new_slab_objects(s, gfpflags, node, &c);
+	if (unlikely(!freelist)) {
+		if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
+			slab_out_of_memory(s, gfpflags, node);
 
-		if (unlikely(!object)) {
-			if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
-				slab_out_of_memory(s, gfpflags, node);
-
-			local_irq_restore(flags);
-			return NULL;
-		}
+		local_irq_restore(flags);
+		return NULL;
 	}
 
+	page = c->page;
 	if (likely(!kmem_cache_debug(s)))
 		goto load_freelist;
 
 	/* Only entered in the debug case */
-	if (!alloc_debug_processing(s, c->page, object, addr))
+	if (!alloc_debug_processing(s, page, freelist, addr))
 		goto new_slab;	/* Slab failed checks. Next slab needed */
 
-	c->freelist = get_freepointer(s, object);
-	deactivate_slab(s, c);
-	c->node = NUMA_NO_NODE;
+	deactivate_slab(s, page, get_freepointer(s, freelist));
+	c->page = NULL;
+	c->freelist = NULL;
 	local_irq_restore(flags);
-	return object;
+	return freelist;
 }
 
 /*
@@ -2307,6 +2315,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 {
 	void **object;
 	struct kmem_cache_cpu *c;
+	struct page *page;
 	unsigned long tid;
 
 	if (slab_pre_alloc_hook(s, gfpflags))
@@ -2332,7 +2341,8 @@ redo:
 	barrier();
 
 	object = c->freelist;
-	if (unlikely(!object || !node_match(c, node)))
+	page = c->page;
+	if (unlikely(!object || !node_match(page, node)))
 
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 
@@ -4500,30 +4510,31 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 
 		for_each_possible_cpu(cpu) {
 			struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
-			int node = ACCESS_ONCE(c->node);
+			int node;
 			struct page *page;
 
-			if (node < 0)
-				continue;
 			page = ACCESS_ONCE(c->page);
-			if (page) {
-				if (flags & SO_TOTAL)
-					x = page->objects;
-				else if (flags & SO_OBJECTS)
-					x = page->inuse;
-				else
-					x = 1;
+			if (!page)
+				continue;
 
-				total += x;
-				nodes[node] += x;
-			}
-			page = c->partial;
+			node = page_to_nid(page);
+			if (flags & SO_TOTAL)
+				x = page->objects;
+			else if (flags & SO_OBJECTS)
+				x = page->inuse;
+			else
+				x = 1;
 
+			total += x;
+			nodes[node] += x;
+
+			page = ACCESS_ONCE(c->partial);
 			if (page) {
 				x = page->pobjects;
 				total += x;
 				nodes[node] += x;
 			}
+
 			per_cpu[node]++;
 		}
 	}