X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=mm%2Fslab.c;h=3ce9bc024d676c9db1f58a298d5aacc5f1d9c6fa;hb=5615d9f1b9f5221d5b69dfa3722c16918c896cdd;hp=6d65cf4e4b2e03fb1cbd860a1932ce0cd5cb2621;hpb=08f3dfe8c4b91189890019d307aad236c3633515;p=linux-2.6-omap-h63xx.git

diff --git a/mm/slab.c b/mm/slab.c
index 6d65cf4e4b2..3ce9bc024d6 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -137,6 +137,7 @@
 
 /* Shouldn't this be in a header file somewhere? */
 #define	BYTES_PER_WORD		sizeof(void *)
+#define	REDZONE_ALIGN		max(BYTES_PER_WORD, __alignof__(unsigned long long))
 
 #ifndef cache_line_size
 #define cache_line_size()	L1_CACHE_BYTES
@@ -266,11 +267,10 @@ struct array_cache {
 	unsigned int batchcount;
 	unsigned int touched;
 	spinlock_t lock;
-	void *entry[0];	/*
+	void *entry[];	/*
 			 * Must have this definition in here for the proper
 			 * alignment of array_cache. Also simplifies accessing
 			 * the entries.
-			 * [0] is for gcc 2.95. It should really be [].
 			 */
 };
 
@@ -407,7 +407,7 @@ struct kmem_cache {
 	unsigned int dflags;		/* dynamic flags */
 
 	/* constructor func */
-	void (*ctor) (void *, struct kmem_cache *, unsigned long);
+	void (*ctor)(struct kmem_cache *, void *);
 
 /* 5) cache creation/removal */
 	const char *name;
@@ -547,7 +547,7 @@ static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
 	if (cachep->flags & SLAB_STORE_USER)
 		return (unsigned long long *)(objp + cachep->buffer_size -
 					      sizeof(unsigned long long) -
-					      BYTES_PER_WORD);
+					      REDZONE_ALIGN);
 	return (unsigned long long *) (objp + cachep->buffer_size -
 				       sizeof(unsigned long long));
 }
@@ -774,7 +774,9 @@ static inline struct kmem_cache *__find_general_cachep(size_t size,
 	 */
 	BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL);
 #endif
-	WARN_ON_ONCE(size == 0);
+	if (!size)
+		return ZERO_SIZE_PTR;
+
 	while (size > csizep->cs_size)
 		csizep++;
 
@@ -880,6 +882,7 @@ static void __slab_error(const char *function, struct kmem_cache *cachep,
   */
 
 static int use_alien_caches __read_mostly = 1;
+static int numa_platform __read_mostly = 1;
 static int __init noaliencache_setup(char *s)
 {
 	use_alien_caches = 0;
@@ -929,7 +932,7 @@ static void next_reap_node(void)
  * the CPUs getting into lockstep and contending for the global cache chain
  * lock.
  */
-static void __devinit start_cpu_timer(int cpu)
+static void __cpuinit start_cpu_timer(int cpu)
 {
 	struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
 
@@ -1160,7 +1163,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 	struct kmem_cache *cachep;
 	struct kmem_list3 *l3 = NULL;
 	int node = cpu_to_node(cpu);
-	int memsize = sizeof(struct kmem_list3);
+	const int memsize = sizeof(struct kmem_list3);
 
 	switch (action) {
 	case CPU_LOCK_ACQUIRE:
@@ -1396,8 +1399,10 @@ void __init kmem_cache_init(void)
 	int order;
 	int node;
 
-	if (num_possible_nodes() == 1)
+	if (num_possible_nodes() == 1) {
 		use_alien_caches = 0;
+		numa_platform = 0;
+	}
 
 	for (i = 0; i < NUM_INIT_LISTS; i++) {
 		kmem_list3_init(&initkmem_list3[i]);
@@ -1481,7 +1486,7 @@ void __init kmem_cache_init(void)
 					sizes[INDEX_AC].cs_size,
 					ARCH_KMALLOC_MINALIGN,
 					ARCH_KMALLOC_FLAGS|SLAB_PANIC,
-					NULL, NULL);
+					NULL);
 
 	if (INDEX_AC != INDEX_L3) {
 		sizes[INDEX_L3].cs_cachep =
@@ -1489,7 +1494,7 @@ void __init kmem_cache_init(void)
 				sizes[INDEX_L3].cs_size,
 				ARCH_KMALLOC_MINALIGN,
 				ARCH_KMALLOC_FLAGS|SLAB_PANIC,
-				NULL, NULL);
+				NULL);
 	}
 
 	slab_early_init = 0;
@@ -1507,7 +1512,7 @@ void __init kmem_cache_init(void)
 					sizes->cs_size,
 					ARCH_KMALLOC_MINALIGN,
 					ARCH_KMALLOC_FLAGS|SLAB_PANIC,
-					NULL, NULL);
+					NULL);
 		}
 #ifdef CONFIG_ZONE_DMA
 		sizes->cs_dmacachep = kmem_cache_create(
@@ -1516,7 +1521,7 @@ void __init kmem_cache_init(void)
 					ARCH_KMALLOC_MINALIGN,
 					ARCH_KMALLOC_FLAGS|SLAB_CACHE_DMA|
 						SLAB_PANIC,
-					NULL, NULL);
+					NULL);
 #endif
 		sizes++;
 		names++;
@@ -1562,7 +1567,7 @@ void __init kmem_cache_init(void)
 		/* Replace the static kmem_list3 structures for the boot cpu */
 		init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], node);
 
-		for_each_online_node(nid) {
+		for_each_node_state(nid, N_NORMAL_MEMORY) {
 			init_list(malloc_sizes[INDEX_AC].cs_cachep,
 				  &initkmem_list3[SIZE_AC + nid], nid);
 
@@ -1637,6 +1642,8 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 #endif
 
 	flags |= cachep->gfpflags;
+	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
+		flags |= __GFP_RECLAIMABLE;
 
 	page = alloc_pages_node(nodeid, flags, cachep->gfporder);
 	if (!page)
@@ -1938,7 +1945,7 @@ static void __init set_up_list3s(struct kmem_cache *cachep, int index)
 {
 	int node;
 
-	for_each_online_node(node) {
+	for_each_node_state(node, N_NORMAL_MEMORY) {
 		cachep->nodelists[node] = &initkmem_list3[index + node];
 		cachep->nodelists[node]->next_reap = jiffies +
 		    REAPTIMEOUT_LIST3 +
@@ -2069,7 +2076,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep)
 			g_cpucache_up = PARTIAL_L3;
 		} else {
 			int node;
-			for_each_online_node(node) {
+			for_each_node_state(node, N_NORMAL_MEMORY) {
 				cachep->nodelists[node] =
 				    kmalloc_node(sizeof(struct kmem_list3),
 						GFP_KERNEL, node);
@@ -2098,12 +2105,10 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep)
  * @align: The required alignment for the objects.
  * @flags: SLAB flags
  * @ctor: A constructor for the objects.
- * @dtor: A destructor for the objects (not implemented anymore).
  *
  * Returns a ptr to the cache on success, NULL on failure.
  * Cannot be called within a int, but can be interrupted.
- * The @ctor is run when new pages are allocated by the cache
- * and the @dtor is run before the pages are handed back.
+ * The @ctor is run when new pages are allocated by the cache.
  *
  * @name must be valid until the cache is destroyed. This implies that
  * the module calling this has to destroy the cache before getting unloaded.
@@ -2123,8 +2128,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep)
 struct kmem_cache *
 kmem_cache_create (const char *name, size_t size, size_t align,
 	unsigned long flags,
-	void (*ctor)(void*, struct kmem_cache *, unsigned long),
-	void (*dtor)(void*, struct kmem_cache *, unsigned long))
+	void (*ctor)(struct kmem_cache *, void *))
 {
 	size_t left_over, slab_size, ralign;
 	struct kmem_cache *cachep = NULL, *pc;
@@ -2133,7 +2137,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	 * Sanity checks... these are all serious usage bugs.
 	 */
 	if (!name || in_interrupt() || (size < BYTES_PER_WORD) ||
-	    size > KMALLOC_MAX_SIZE || dtor) {
+	    size > KMALLOC_MAX_SIZE) {
 		printk(KERN_ERR "%s: Early error in slab %s\n", __FUNCTION__,
 				name);
 		BUG();
@@ -2179,7 +2183,8 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	 * above the next power of two: caches with object sizes just above a
 	 * power of two have a significant amount of internal fragmentation.
 	 */
-	if (size < 4096 || fls(size - 1) == fls(size-1 + 3 * BYTES_PER_WORD))
+	if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN +
+						2 * sizeof(unsigned long long)))
 		flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
 	if (!(flags & SLAB_DESTROY_BY_RCU))
 		flags |= SLAB_POISON;
@@ -2220,12 +2225,20 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	}
 
 	/*
-	 * Redzoning and user store require word alignment. Note this will be
-	 * overridden by architecture or caller mandated alignment if either
-	 * is greater than BYTES_PER_WORD.
+	 * Redzoning and user store require word alignment or possibly larger.
+	 * Note this will be overridden by architecture or caller mandated
+	 * alignment if either is greater than BYTES_PER_WORD.
 	 */
-	if (flags & SLAB_RED_ZONE || flags & SLAB_STORE_USER)
-		ralign = __alignof__(unsigned long long);
+	if (flags & SLAB_STORE_USER)
+		ralign = BYTES_PER_WORD;
+
+	if (flags & SLAB_RED_ZONE) {
+		ralign = REDZONE_ALIGN;
+		/* If redzoning, ensure that the second redzone is suitably
+		 * aligned, by adjusting the object size accordingly. */
+		size += REDZONE_ALIGN - 1;
+		size &= ~(REDZONE_ALIGN - 1);
+	}
 
 	/* 2) arch mandated alignment */
 	if (ralign < ARCH_SLAB_MINALIGN) {
@@ -2262,9 +2275,13 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	}
 	if (flags & SLAB_STORE_USER) {
 		/* user store requires one word storage behind the end of
-		 * the real object.
+		 * the real object. But if the second red zone needs to be
+		 * aligned to 64 bits, we must allow that much space.
 		 */
-		size += BYTES_PER_WORD;
+		if (flags & SLAB_RED_ZONE)
+			size += REDZONE_ALIGN;
+		else
+			size += BYTES_PER_WORD;
 	}
 #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
 	if (size >= malloc_sizes[INDEX_L3 + 1].cs_size
@@ -2338,7 +2355,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		 * this should not happen at all.
 		 * But leave a BUG_ON for some lucky dude.
 		 */
-		BUG_ON(!cachep->slabp_cache);
+		BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache));
 	}
 	cachep->ctor = ctor;
 	cachep->name = name;
@@ -2618,8 +2635,7 @@ static void cache_init_objs(struct kmem_cache *cachep,
 		 * They must also be threaded.
 		 */
 		if (cachep->ctor && !(cachep->flags & SLAB_POISON))
-			cachep->ctor(objp + obj_offset(cachep), cachep,
-				     0);
+			cachep->ctor(cachep, objp + obj_offset(cachep));
 
 		if (cachep->flags & SLAB_RED_ZONE) {
 			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
@@ -2635,7 +2651,7 @@ static void cache_init_objs(struct kmem_cache *cachep,
 					 cachep->buffer_size / PAGE_SIZE, 0);
 #else
 		if (cachep->ctor)
-			cachep->ctor(objp, cachep, 0);
+			cachep->ctor(cachep, objp);
 #endif
 		slab_bufctl(slabp)[i] = i + 1;
 	}
@@ -2730,9 +2746,9 @@ static int cache_grow(struct kmem_cache *cachep,
 	 * Be lazy and only check for valid flags here,  keeping it out of the
 	 * critical path in kmem_cache_alloc().
 	 */
-	BUG_ON(flags & ~(GFP_DMA | GFP_LEVEL_MASK));
+	BUG_ON(flags & GFP_SLAB_BUG_MASK);
+	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
-	local_flags = (flags & GFP_LEVEL_MASK);
 	/* Take the l3 list lock to change the colour_next on this node */
 	check_irq_off();
 	l3 = cachep->nodelists[nodeid];
@@ -2763,13 +2779,13 @@ static int cache_grow(struct kmem_cache *cachep,
 	 * 'nodeid'.
 	 */
 	if (!objp)
-		objp = kmem_getpages(cachep, flags, nodeid);
+		objp = kmem_getpages(cachep, local_flags, nodeid);
 	if (!objp)
 		goto failed;
 
 	/* Get slab management. */
 	slabp = alloc_slabmgmt(cachep, objp, offset,
-			local_flags & ~GFP_THISNODE, nodeid);
+			local_flags & ~GFP_CONSTRAINT_MASK, nodeid);
 	if (!slabp)
 		goto opps1;
 
@@ -3060,7 +3076,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 #endif
 	objp += obj_offset(cachep);
 	if (cachep->ctor && cachep->flags & SLAB_POISON)
-		cachep->ctor(objp, cachep, 0);
+		cachep->ctor(cachep, objp);
 #if ARCH_SLAB_MINALIGN
 	if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) {
 		printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n",
@@ -3209,7 +3225,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 
 	zonelist = &NODE_DATA(slab_node(current->mempolicy))
 			->node_zonelists[gfp_zone(flags)];
-	local_flags = (flags & GFP_LEVEL_MASK);
+	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
 retry:
 	/*
@@ -3376,6 +3392,9 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	local_irq_restore(save_flags);
 	ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
 
+	if (unlikely((flags & __GFP_ZERO) && ptr))
+		memset(ptr, 0, obj_size(cachep));
+
 	return ptr;
 }
 
@@ -3427,6 +3446,9 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 	objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
 	prefetchw(objp);
 
+	if (unlikely((flags & __GFP_ZERO) && objp))
+		memset(objp, 0, obj_size(cachep));
+
 	return objp;
 }
 
@@ -3539,7 +3561,14 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp)
 	check_irq_off();
 	objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0));
 
-	if (cache_free_alien(cachep, objp))
+	/*
+	 * Skip calling cache_free_alien() when the platform is not numa.
+	 * This will avoid cache misses that happen while accessing slabp (which
+	 * is per page memory  reference) to get nodeid. Instead use a global
+	 * variable to skip the call, which is mostly likely to be present in
+	 * the cache.
+	 */
+	if (numa_platform && cache_free_alien(cachep, objp))
 		return;
 
 	if (likely(ac->avail < ac->limit)) {
@@ -3567,23 +3596,6 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 }
 EXPORT_SYMBOL(kmem_cache_alloc);
 
-/**
- * kmem_cache_zalloc - Allocate an object. The memory is set to zero.
- * @cache: The cache to allocate from.
- * @flags: See kmalloc().
- *
- * Allocate an object from this cache and set the allocated memory to zero.
- * The flags are only relevant if the cache has no available objects.
- */
-void *kmem_cache_zalloc(struct kmem_cache *cache, gfp_t flags)
-{
-	void *ret = __cache_alloc(cache, flags, __builtin_return_address(0));
-	if (ret)
-		memset(ret, 0, obj_size(cache));
-	return ret;
-}
-EXPORT_SYMBOL(kmem_cache_zalloc);
-
 /**
  * kmem_ptr_validate - check if an untrusted pointer might
  *	be a slab entry.
@@ -3640,8 +3652,8 @@ __do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller)
 	struct kmem_cache *cachep;
 
 	cachep = kmem_find_general_cachep(size, flags);
-	if (unlikely(cachep == NULL))
-		return NULL;
+	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
+		return cachep;
 	return kmem_cache_alloc_node(cachep, flags, node);
 }
 
@@ -3685,8 +3697,8 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 	 * functions.
 	 */
 	cachep = __find_general_cachep(size, flags);
-	if (unlikely(cachep == NULL))
-		return NULL;
+	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
+		return cachep;
 	return __cache_alloc(cachep, flags, caller);
 }
 
@@ -3712,52 +3724,6 @@ void *__kmalloc(size_t size, gfp_t flags)
 EXPORT_SYMBOL(__kmalloc);
 #endif
 
-/**
- * krealloc - reallocate memory. The contents will remain unchanged.
- * @p: object to reallocate memory for.
- * @new_size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
- *
- * The contents of the object pointed to are preserved up to the
- * lesser of the new and old sizes.  If @p is %NULL, krealloc()
- * behaves exactly like kmalloc().  If @size is 0 and @p is not a
- * %NULL pointer, the object pointed to is freed.
- */
-void *krealloc(const void *p, size_t new_size, gfp_t flags)
-{
-	struct kmem_cache *cache, *new_cache;
-	void *ret;
-
-	if (unlikely(!p))
-		return kmalloc_track_caller(new_size, flags);
-
-	if (unlikely(!new_size)) {
-		kfree(p);
-		return NULL;
-	}
-
-	cache = virt_to_cache(p);
-	new_cache = __find_general_cachep(new_size, flags);
-
-	/*
- 	 * If new size fits in the current cache, bail out.
- 	 */
-	if (likely(cache == new_cache))
-		return (void *)p;
-
-	/*
- 	 * We are on the slow-path here so do not use __cache_alloc
- 	 * because it bloats kernel text.
- 	 */
-	ret = kmalloc_track_caller(new_size, flags);
-	if (ret) {
-		memcpy(ret, p, min(new_size, ksize(p)));
-		kfree(p);
-	}
-	return ret;
-}
-EXPORT_SYMBOL(krealloc);
-
 /**
  * kmem_cache_free - Deallocate an object
  * @cachep: The cache the allocation was from.
@@ -3793,7 +3759,7 @@ void kfree(const void *objp)
 	struct kmem_cache *c;
 	unsigned long flags;
 
-	if (unlikely(!objp))
+	if (unlikely(ZERO_OR_NULL_PTR(objp)))
 		return;
 	local_irq_save(flags);
 	kfree_debugcheck(objp);
@@ -3826,7 +3792,7 @@ static int alloc_kmemlist(struct kmem_cache *cachep)
 	struct array_cache *new_shared;
 	struct array_cache **new_alien = NULL;
 
-	for_each_online_node(node) {
+	for_each_node_state(node, N_NORMAL_MEMORY) {
 
                 if (use_alien_caches) {
                         new_alien = alloc_alien_cache(node, cachep->limit);
@@ -4144,26 +4110,17 @@ static void print_slabinfo_header(struct seq_file *m)
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
 	loff_t n = *pos;
-	struct list_head *p;
 
 	mutex_lock(&cache_chain_mutex);
 	if (!n)
 		print_slabinfo_header(m);
-	p = cache_chain.next;
-	while (n--) {
-		p = p->next;
-		if (p == &cache_chain)
-			return NULL;
-	}
-	return list_entry(p, struct kmem_cache, next);
+
+	return seq_list_start(&cache_chain, *pos);
 }
 
 static void *s_next(struct seq_file *m, void *p, loff_t *pos)
 {
-	struct kmem_cache *cachep = p;
-	++*pos;
-	return cachep->next.next == &cache_chain ?
-		NULL : list_entry(cachep->next.next, struct kmem_cache, next);
+	return seq_list_next(p, &cache_chain, pos);
 }
 
 static void s_stop(struct seq_file *m, void *p)
@@ -4173,7 +4130,7 @@ static void s_stop(struct seq_file *m, void *p)
 
 static int s_show(struct seq_file *m, void *p)
 {
-	struct kmem_cache *cachep = p;
+	struct kmem_cache *cachep = list_entry(p, struct kmem_cache, next);
 	struct slab *slabp;
 	unsigned long active_objs;
 	unsigned long num_objs;
@@ -4342,17 +4299,8 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer,
 
 static void *leaks_start(struct seq_file *m, loff_t *pos)
 {
-	loff_t n = *pos;
-	struct list_head *p;
-
 	mutex_lock(&cache_chain_mutex);
-	p = cache_chain.next;
-	while (n--) {
-		p = p->next;
-		if (p == &cache_chain)
-			return NULL;
-	}
-	return list_entry(p, struct kmem_cache, next);
+	return seq_list_start(&cache_chain, *pos);
 }
 
 static inline int add_caller(unsigned long *n, unsigned long v)
@@ -4403,7 +4351,7 @@ static void show_symbol(struct seq_file *m, unsigned long address)
 {
 #ifdef CONFIG_KALLSYMS
 	unsigned long offset, size;
-	char modname[MODULE_NAME_LEN + 1], name[KSYM_NAME_LEN + 1];
+	char modname[MODULE_NAME_LEN], name[KSYM_NAME_LEN];
 
 	if (lookup_symbol_attrs(address, &size, &offset, modname, name) == 0) {
 		seq_printf(m, "%s+%#lx/%#lx", name, offset, size);
@@ -4417,7 +4365,7 @@ static void show_symbol(struct seq_file *m, unsigned long address)
 
 static int leaks_show(struct seq_file *m, void *p)
 {
-	struct kmem_cache *cachep = p;
+	struct kmem_cache *cachep = list_entry(p, struct kmem_cache, next);
 	struct slab *slabp;
 	struct kmem_list3 *l3;
 	const char *name;
@@ -4498,7 +4446,8 @@ const struct seq_operations slabstats_op = {
  */
 size_t ksize(const void *objp)
 {
-	if (unlikely(objp == NULL))
+	BUG_ON(!objp);
+	if (unlikely(objp == ZERO_SIZE_PTR))
 		return 0;
 
 	return obj_size(virt_to_cache(objp));