#include <linux/cpu.h>
#include <linux/sysctl.h>
#include <linux/module.h>
-#include <linux/kmemtrace.h>
#include <linux/rcupdate.h>
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/debugobjects.h>
#include <linux/kmemcheck.h>
#include <linux/memory.h>
+#include <linux/prefetch.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
-#include "internal.h"
+#include <trace/events/kmem.h>
/*
* DEBUG - 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
#define SLAB_LIMIT (((kmem_bufctl_t)(~0U))-3)
/*
- * struct slab
- *
- * Manages the objs in a slab. Placed either at the beginning of mem allocated
- * for a slab, or allocated from an general cache.
- * Slabs are chained into three list: fully used, partial, fully free slabs.
- */
-struct slab {
- struct list_head list;
- unsigned long colouroff;
- void *s_mem; /* including colour offset */
- unsigned int inuse; /* num of objs active in slab */
- kmem_bufctl_t free;
- unsigned short nodeid;
-};
-
-/*
* struct slab_rcu
*
* slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to
*
* rcu_read_lock before reading the address, then rcu_read_unlock after
* taking the spinlock within the structure expected at that address.
- *
- * We assume struct slab_rcu can overlay struct slab when destroying.
*/
struct slab_rcu {
struct rcu_head head;
};
/*
+ * struct slab
+ *
+ * Manages the objs in a slab. Placed either at the beginning of mem allocated
+ * for a slab, or allocated from an general cache.
+ * Slabs are chained into three list: fully used, partial, fully free slabs.
+ */
+struct slab {
+ union {
+ struct {
+ struct list_head list;
+ unsigned long colouroff;
+ void *s_mem; /* including colour offset */
+ unsigned int inuse; /* num of objs active in slab */
+ kmem_bufctl_t free;
+ unsigned short nodeid;
+ };
+ struct slab_rcu __slab_cover_slab_rcu;
+ };
+};
+
+/*
* struct array_cache
*
* Purpose:
unsigned int avail;
unsigned int limit;
unsigned int batchcount;
- unsigned int touched:1,
- reserve:1;
+ unsigned int touched;
spinlock_t lock;
void *entry[]; /*
* Must have this definition in here for the proper
struct array_cache **alien; /* on other nodes */
unsigned long next_reap; /* updated without locking */
int free_touched; /* updated without locking */
-} __attribute__((aligned(sizeof(long))));
+};
/*
* Need this for bootstrapping a per node allocator.
*/
#define NUM_INIT_LISTS (3 * MAX_NUMNODES)
-struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
+static struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
#define CACHE_CACHE 0
#define SIZE_AC MAX_NUMNODES
#define SIZE_L3 (2 * MAX_NUMNODES)
#define STATS_DEC_ACTIVE(x) do { } while (0)
#define STATS_INC_ALLOCED(x) do { } while (0)
#define STATS_INC_GROWN(x) do { } while (0)
-#define STATS_ADD_REAPED(x,y) do { } while (0)
+#define STATS_ADD_REAPED(x,y) do { (void)(y); } while (0)
#define STATS_SET_HIGH(x) do { } while (0)
#define STATS_INC_ERR(x) do { } while (0)
#define STATS_INC_NODEALLOCS(x) do { } while (0)
#endif
/*
- * Do not go above this order unless 0 objects fit into the slab.
+ * Do not go above this order unless 0 objects fit into the slab or
+ * overridden on the command line.
*/
-#define BREAK_GFP_ORDER_HI 1
-#define BREAK_GFP_ORDER_LO 0
-static int slab_break_gfp_order = BREAK_GFP_ORDER_LO;
+#define SLAB_MAX_ORDER_HI 1
+#define SLAB_MAX_ORDER_LO 0
+static int slab_max_order = SLAB_MAX_ORDER_LO;
+static bool slab_max_order_set __initdata;
/*
* Functions for storing/retrieving the cachep and or slab from the page
{ {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
/* internal cache of cache description objs */
+static struct kmem_list3 *cache_cache_nodelists[MAX_NUMNODES];
static struct kmem_cache cache_cache = {
+ .nodelists = cache_cache_nodelists,
.batchcount = 1,
.limit = BOOT_CPUCACHE_ENTRIES,
.shared = 1,
PARTIAL_AC,
PARTIAL_L3,
EARLY,
+ LATE,
FULL
} g_cpucache_up;
static struct lock_class_key on_slab_l3_key;
static struct lock_class_key on_slab_alc_key;
+static struct lock_class_key debugobj_l3_key;
+static struct lock_class_key debugobj_alc_key;
+
+static void slab_set_lock_classes(struct kmem_cache *cachep,
+ struct lock_class_key *l3_key, struct lock_class_key *alc_key,
+ int q)
+{
+ struct array_cache **alc;
+ struct kmem_list3 *l3;
+ int r;
+
+ l3 = cachep->nodelists[q];
+ if (!l3)
+ return;
+
+ lockdep_set_class(&l3->list_lock, l3_key);
+ alc = l3->alien;
+ /*
+ * FIXME: This check for BAD_ALIEN_MAGIC
+ * should go away when common slab code is taught to
+ * work even without alien caches.
+ * Currently, non NUMA code returns BAD_ALIEN_MAGIC
+ * for alloc_alien_cache,
+ */
+ if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
+ return;
+ for_each_node(r) {
+ if (alc[r])
+ lockdep_set_class(&alc[r]->lock, alc_key);
+ }
+}
+
+static void slab_set_debugobj_lock_classes_node(struct kmem_cache *cachep, int node)
+{
+ slab_set_lock_classes(cachep, &debugobj_l3_key, &debugobj_alc_key, node);
+}
+
+static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep)
+{
+ int node;
+
+ for_each_online_node(node)
+ slab_set_debugobj_lock_classes_node(cachep, node);
+}
+
static void init_node_lock_keys(int q)
{
struct cache_sizes *s = malloc_sizes;
- if (g_cpucache_up != FULL)
+ if (g_cpucache_up < LATE)
return;
for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
- struct array_cache **alc;
struct kmem_list3 *l3;
- int r;
l3 = s->cs_cachep->nodelists[q];
if (!l3 || OFF_SLAB(s->cs_cachep))
continue;
- lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
- alc = l3->alien;
- /*
- * FIXME: This check for BAD_ALIEN_MAGIC
- * should go away when common slab code is taught to
- * work even without alien caches.
- * Currently, non NUMA code returns BAD_ALIEN_MAGIC
- * for alloc_alien_cache,
- */
- if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
- continue;
- for_each_node(r) {
- if (alc[r])
- lockdep_set_class(&alc[r]->lock,
- &on_slab_alc_key);
- }
+
+ slab_set_lock_classes(s->cs_cachep, &on_slab_l3_key,
+ &on_slab_alc_key, q);
}
}
static inline void init_lock_keys(void)
{
}
+
+static void slab_set_debugobj_lock_classes_node(struct kmem_cache *cachep, int node)
+{
+}
+
+static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep)
+{
+}
#endif
/*
return cachep->array[smp_processor_id()];
}
-/*
- * If the last page came from the reserves, and the current allocation context
- * does not have access to them, force an allocation to test the watermarks.
- */
-static inline int slab_force_alloc(struct kmem_cache *cachep, gfp_t flags)
-{
- if (unlikely(cpu_cache_get(cachep)->reserve) &&
- !(gfp_to_alloc_flags(flags) & ALLOC_NO_WATERMARKS))
- return 1;
-
- return 0;
-}
-
-static inline void slab_set_reserve(struct kmem_cache *cachep, int reserve)
-{
- struct array_cache *ac = cpu_cache_get(cachep);
-
- if (unlikely(ac->reserve != reserve))
- ac->reserve = reserve;
-}
-
static inline struct kmem_cache *__find_general_cachep(size_t size,
gfp_t gfpflags)
{
}
__setup("noaliencache", noaliencache_setup);
+static int __init slab_max_order_setup(char *str)
+{
+ get_option(&str, &slab_max_order);
+ slab_max_order = slab_max_order < 0 ? 0 :
+ min(slab_max_order, MAX_ORDER - 1);
+ slab_max_order_set = true;
+
+ return 1;
+}
+__setup("slab_max_order=", slab_max_order_setup);
+
#ifdef CONFIG_NUMA
/*
* Special reaping functions for NUMA systems called from cache_reap().
static void next_reap_node(void)
{
- int node = __get_cpu_var(slab_reap_node);
+ int node = __this_cpu_read(slab_reap_node);
node = next_node(node, node_online_map);
if (unlikely(node >= MAX_NUMNODES))
node = first_node(node_online_map);
- __get_cpu_var(slab_reap_node) = node;
+ __this_cpu_write(slab_reap_node, node);
}
#else
*/
if (keventd_up() && reap_work->work.func == NULL) {
init_reap_node(cpu);
- INIT_DELAYED_WORK(reap_work, cache_reap);
+ INIT_DELAYED_WORK_DEFERRABLE(reap_work, cache_reap);
schedule_delayed_work_on(cpu, reap_work,
__round_jiffies_relative(HZ, cpu));
}
nc = kmalloc_node(memsize, gfp, node);
/*
* The array_cache structures contain pointers to free object.
- * However, when such objects are allocated or transfered to another
+ * However, when such objects are allocated or transferred to another
* cache the pointers are not cleared and they could be counted as
* valid references during a kmemleak scan. Therefore, kmemleak must
* not scan such objects.
nc->limit = entries;
nc->batchcount = batchcount;
nc->touched = 0;
- nc->reserve = 0;
spin_lock_init(&nc->lock);
}
return nc;
struct array_cache *from, unsigned int max)
{
/* Figure out how many entries to transfer */
- int nr = min(min(from->avail, max), to->limit - to->avail);
+ int nr = min3(from->avail, max, to->limit - to->avail);
if (!nr)
return 0;
#define drain_alien_cache(cachep, alien) do { } while (0)
#define reap_alien(cachep, l3) do { } while (0)
-static inline int numa_slab_nid(struct kmem_cache *cachep, gfp_t flags)
-{
- return 0;
-}
-
static inline struct array_cache **alloc_alien_cache(int node, int limit, gfp_t gfp)
{
return (struct array_cache **)BAD_ALIEN_MAGIC;
static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int);
static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
-/*
- * slow path for numa_slab_nid(), below
- */
-static noinline int __numa_slab_nid(struct kmem_cache *cachep,
- int node, gfp_t flags)
-{
- struct zonelist *zonelist;
- struct zone *zone;
- enum zone_type highest_zoneidx = gfp_zone(flags);
-
- if (likely(node_state(node, N_NORMAL_MEMORY)))
- return node;
-
- /*
- * memoryless node: consult its zonelist.
- * Cache the fallback node, if cache pointer provided.
- */
- zonelist = &NODE_DATA(node)->node_zonelists[0];
- (void)first_zones_zonelist(zonelist, highest_zoneidx,
- NULL,
- &zone);
- if (cachep)
- cachep->nodelists[node] =
- (struct kmem_list3 *)((unsigned long)zone->node << 1 | 1);
- return zone->node;
-}
-
-/*
- * "Local" node for slab is first node in zonelist with memory.
- * For nodes with memory this will be the actual local node.
- *
- * Use nodelist[numa_node_id()] to cache the fallback node for
- * memoryless nodes. We'll be loading that member soon anyway,
- * or already have, when called for cache refill, ... Use low
- * bit of "pointer" as flag for "memoryless_node", indicating
- * that the fallback nodes is stored here [<<1].
- */
-#define memoryless_node(L3L) ((L3L) & 1)
-static inline int numa_slab_nid(struct kmem_cache *cachep, gfp_t flags)
-{
- int node = numa_mem_id();
-
- if (likely(cachep)){
- unsigned long l3l = (unsigned long)cachep->nodelists[node];
-
- if (likely(l3l)) {
- if (unlikely(memoryless_node(l3l)))
- node = (int)(l3l >> 1);
- return node;
- }
- }
-
- /*
- * !cachep || !l3l - the slow path
- */
- return __numa_slab_nid(cachep, node, flags);
-}
-
static struct array_cache **alloc_alien_cache(int node, int limit, gfp_t gfp)
{
struct array_cache **ac_ptr;
*/
static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
{
- int node = __get_cpu_var(slab_reap_node);
+ int node = __this_cpu_read(slab_reap_node);
if (l3->alien) {
struct array_cache *ac = l3->alien[node];
struct array_cache *alien = NULL;
int node;
- node = numa_slab_nid(cachep, GFP_KERNEL);
+ node = numa_mem_id();
/*
* Make sure we are not freeing a object from another node to the array
spin_unlock_irq(&l3->list_lock);
kfree(shared);
free_alien_cache(alien);
+ if (cachep->flags & SLAB_DEBUG_OBJECTS)
+ slab_set_debugobj_lock_classes_node(cachep, node);
}
init_node_lock_keys(node);
* anything expensive but will only modify reap_work
* and reschedule the timer.
*/
- cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu));
+ cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
/* Now the cache_reaper is guaranteed to be not running. */
per_cpu(slab_reap_work, cpu).work.func = NULL;
break;
break;
}
out:
- return ret ? notifier_from_errno(ret) : NOTIFY_OK;
+ return notifier_from_errno(ret);
}
#endif /* CONFIG_NUMA && CONFIG_MEMORY_HOTPLUG */
/*
* Fragmentation resistance on low memory - only use bigger
- * page orders on machines with more than 32MB of memory.
+ * page orders on machines with more than 32MB of memory if
+ * not overridden on the command line.
*/
- if (totalram_pages > (32 << 20) >> PAGE_SHIFT)
- slab_break_gfp_order = BREAK_GFP_ORDER_HI;
+ if (!slab_max_order_set && totalram_pages > (32 << 20) >> PAGE_SHIFT)
+ slab_max_order = SLAB_MAX_ORDER_HI;
/* Bootstrap is tricky, because several objects are allocated
* from caches that do not exist yet:
* 6) Resize the head arrays of the kmalloc caches to their final sizes.
*/
- node = numa_slab_nid(NULL, GFP_KERNEL);
+ node = numa_mem_id();
/* 1) create the cache_cache */
INIT_LIST_HEAD(&cache_chain);
cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node];
/*
- * struct kmem_cache size depends on nr_node_ids, which
- * can be less than MAX_NUMNODES.
+ * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
*/
- cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) +
- nr_node_ids * sizeof(struct kmem_list3 *);
+ cache_cache.buffer_size = offsetof(struct kmem_cache, array[nr_cpu_ids]) +
+ nr_node_ids * sizeof(struct kmem_list3 *);
#if DEBUG
cache_cache.obj_size = cache_cache.buffer_size;
#endif
{
struct kmem_cache *cachep;
+ g_cpucache_up = LATE;
+
+ /* Annotate slab for lockdep -- annotate the malloc caches */
+ init_lock_keys();
+
/* 6) resize the head arrays to their final sizes */
mutex_lock(&cache_chain_mutex);
list_for_each_entry(cachep, &cache_chain, next)
/* Done! */
g_cpucache_up = FULL;
- /* Annotate slab for lockdep -- annotate the malloc caches */
- init_lock_keys();
-
/*
* Register a cpu startup notifier callback that initializes
* cpu_cache_get for all new cpus
}
__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.
*
* did not request dmaable memory, we might get it, but that
* would be relatively rare and ignorable.
*/
-static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid,
- int *reserve)
+static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
{
struct page *page;
int nr_pages;
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;
+ }
- *reserve = page->reserve;
nr_pages = (1 << cachep->gfporder);
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
add_zone_page_state(page_zone(page),
unsigned char error = 0;
int bad_count = 0;
- printk(KERN_ERR "%03x:", offset);
+ printk(KERN_ERR "%03x: ", offset);
for (i = 0; i < limit; i++) {
if (data[offset + i] != POISON_FREE) {
error = data[offset + i];
bad_count++;
}
- printk(" %02x", (unsigned char)data[offset + i]);
}
- printk("\n");
+ print_hex_dump(KERN_CONT, "", 0, 16, 1,
+ &data[offset], limit, 1);
if (bad_count == 1) {
error ^= POISON_FREE;
/* Print header */
if (lines == 0) {
printk(KERN_ERR
- "Slab corruption: %s start=%p, len=%d\n",
- cachep->name, realobj, size);
+ "Slab corruption (%s): %s start=%p, len=%d\n",
+ print_tainted(), cachep->name, realobj, size);
print_objinfo(cachep, objp, 0);
}
/* Hexdump the affected line */
* Large number of objects is good, but very large slabs are
* currently bad for the gfp()s.
*/
- if (gfporder >= slab_break_gfp_order)
+ if (gfporder >= slab_max_order)
break;
/*
}
}
}
- cachep->nodelists[numa_slab_nid(cachep, GFP_KERNEL)]->next_reap =
+ cachep->nodelists[numa_mem_id()]->next_reap =
jiffies + REAPTIMEOUT_LIST3 +
((unsigned long)cachep) % REAPTIMEOUT_LIST3;
cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
cpu_cache_get(cachep)->batchcount = 1;
cpu_cache_get(cachep)->touched = 0;
- cpu_cache_get(cachep)->reserve = 0;
cachep->batchcount = 1;
cachep->limit = BOOT_CPUCACHE_ENTRIES;
return 0;
*
* @name must be valid until the cache is destroyed. This implies that
* the module calling this has to destroy the cache before getting unloaded.
- * Note that kmem_cache_name() is not guaranteed to return the same pointer,
- * therefore applications must manage it themselves.
*
* The flags are
*
if (ralign < align) {
ralign = align;
}
- /* disable debug if not aligning with REDZONE_ALIGN */
- if (ralign & (__alignof__(unsigned long long) - 1))
+ /* disable debug if necessary */
+ if (ralign > __alignof__(unsigned long long))
flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
/*
* 4) Store it.
if (!cachep)
goto oops;
+ cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids];
#if DEBUG
cachep->obj_size = size;
*/
if (flags & SLAB_RED_ZONE) {
/* add space for red zone words */
- cachep->obj_offset += align;
- size += align + sizeof(unsigned long long);
+ cachep->obj_offset += sizeof(unsigned long long);
+ size += 2 * sizeof(unsigned long long);
}
if (flags & SLAB_STORE_USER) {
/* user store requires one word storage behind the end of
}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
if (size >= malloc_sizes[INDEX_L3 + 1].cs_size
- && cachep->obj_size > cache_line_size() && size < PAGE_SIZE) {
- cachep->obj_offset += PAGE_SIZE - size;
+ && cachep->obj_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) {
+ cachep->obj_offset += PAGE_SIZE - ALIGN(size, align);
size = PAGE_SIZE;
}
#endif
goto oops;
}
+ if (flags & SLAB_DEBUG_OBJECTS) {
+ /*
+ * Would deadlock through slab_destroy()->call_rcu()->
+ * debug_object_activate()->kmem_cache_alloc().
+ */
+ WARN_ON_ONCE(flags & SLAB_DESTROY_BY_RCU);
+
+ slab_set_debugobj_lock_classes(cachep);
+ }
+
/* cache setup completed, link it into the list */
list_add(&cachep->next, &cache_chain);
oops:
{
#ifdef CONFIG_SMP
check_irq_off();
- assert_spin_locked(&cachep->nodelists[numa_slab_nid(cachep, GFP_KERNEL)]->list_lock);
+ assert_spin_locked(&cachep->nodelists[numa_mem_id()]->list_lock);
#endif
}
{
struct kmem_cache *cachep = arg;
struct array_cache *ac;
- int node = numa_slab_nid(cachep, GFP_KERNEL);
+ int node = numa_mem_id();
check_irq_off();
ac = cpu_cache_get(cachep);
*
* The cache must be empty before calling this function.
*
- * The caller must guarantee that noone will allocate memory from the cache
+ * The caller must guarantee that no one will allocate memory from the cache
* during the kmem_cache_destroy().
*/
void kmem_cache_destroy(struct kmem_cache *cachep)
/*
* Map pages beginning at addr to the given cache and slab. This is required
* for the slab allocator to be able to lookup the cache and slab of a
- * virtual address for kfree, ksize, kmem_ptr_validate, and slab debugging.
+ * virtual address for kfree, ksize, and slab debugging.
*/
static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
void *addr)
size_t offset;
gfp_t local_flags;
struct kmem_list3 *l3;
- int reserve = -1;
/*
* Be lazy and only check for valid flags here, keeping it out of the
* 'nodeid'.
*/
if (!objp)
- objp = kmem_getpages(cachep, local_flags, nodeid, &reserve);
+ objp = kmem_getpages(cachep, local_flags, nodeid);
if (!objp)
goto failed;
if (local_flags & __GFP_WAIT)
local_irq_disable();
check_irq_off();
- if (reserve != -1)
- slab_set_reserve(cachep, reserve);
spin_lock(&l3->list_lock);
/* Make slab active. */
if (entries != cachep->num - slabp->inuse) {
bad:
printk(KERN_ERR "slab: Internal list corruption detected in "
- "cache '%s'(%d), slabp %p(%d). Hexdump:\n",
- cachep->name, cachep->num, slabp, slabp->inuse);
- for (i = 0;
- i < sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t);
- i++) {
- if (i % 16 == 0)
- printk("\n%03x:", i);
- printk(" %02x", ((unsigned char *)slabp)[i]);
- }
- printk("\n");
+ "cache '%s'(%d), slabp %p(%d). Tainted(%s). Hexdump:\n",
+ cachep->name, cachep->num, slabp, slabp->inuse,
+ print_tainted());
+ print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, slabp,
+ sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t),
+ 1);
BUG();
}
}
#define check_slabp(x,y) do { } while(0)
#endif
-static void *cache_alloc_refill(struct kmem_cache *cachep,
- gfp_t flags, int must_refill)
+static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
{
int batchcount;
struct kmem_list3 *l3;
retry:
check_irq_off();
- node = numa_slab_nid(cachep, flags);
- if (unlikely(must_refill))
- goto force_grow;
+ node = numa_mem_id();
ac = cpu_cache_get(cachep);
batchcount = ac->batchcount;
if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
if (unlikely(!ac->avail)) {
int x;
-force_grow:
x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL);
/* cache_grow can reenable interrupts, then ac could change. */
ac = cpu_cache_get(cachep);
-
- /* no objects in sight? abort */
- if (!x && (ac->avail == 0 || must_refill))
+ if (!x && ac->avail == 0) /* no objects in sight? abort */
return NULL;
if (!ac->avail) /* objects refilled by interrupt? */
objp += obj_offset(cachep);
if (cachep->ctor && cachep->flags & SLAB_POISON)
cachep->ctor(objp);
-#if ARCH_SLAB_MINALIGN
- if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) {
+ if (ARCH_SLAB_MINALIGN &&
+ ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) {
printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n",
- objp, ARCH_SLAB_MINALIGN);
+ objp, (int)ARCH_SLAB_MINALIGN);
}
-#endif
return objp;
}
#else
{
void *objp;
struct array_cache *ac;
- int must_refill = slab_force_alloc(cachep, flags);
check_irq_off();
ac = cpu_cache_get(cachep);
- if (likely(ac->avail && !must_refill)) {
+ if (likely(ac->avail)) {
STATS_INC_ALLOCHIT(cachep);
ac->touched = 1;
objp = ac->entry[--ac->avail];
} else {
STATS_INC_ALLOCMISS(cachep);
- objp = cache_alloc_refill(cachep, flags, must_refill);
+ objp = cache_alloc_refill(cachep, flags);
/*
* the 'ac' may be updated by cache_alloc_refill(),
* and kmemleak_erase() requires its correct value.
if (in_interrupt() || (flags & __GFP_THISNODE))
return NULL;
- nid_alloc = nid_here = numa_slab_nid(cachep, flags);
- get_mems_allowed();
+ nid_alloc = nid_here = numa_mem_id();
if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
nid_alloc = cpuset_slab_spread_node();
else if (current->mempolicy)
nid_alloc = slab_node(current->mempolicy);
- put_mems_allowed();
if (nid_alloc != nid_here)
return ____cache_alloc_node(cachep, flags, nid_alloc);
return NULL;
struct zone *zone;
enum zone_type high_zoneidx = gfp_zone(flags);
void *obj = NULL;
- int nid, reserve;
+ int nid;
+ unsigned int cpuset_mems_cookie;
if (flags & __GFP_THISNODE)
return NULL;
- get_mems_allowed();
- zonelist = node_zonelist(slab_node(current->mempolicy), flags);
local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
+retry_cpuset:
+ cpuset_mems_cookie = get_mems_allowed();
+ zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+
retry:
/*
* Look through allowed nodes for objects available
if (local_flags & __GFP_WAIT)
local_irq_enable();
kmem_flagcheck(cache, flags);
- obj = kmem_getpages(cache, local_flags, numa_mem_id(),
- &reserve);
+ obj = kmem_getpages(cache, local_flags, numa_mem_id());
if (local_flags & __GFP_WAIT)
local_irq_disable();
if (obj) {
- slab_set_reserve(cache, reserve);
/*
* Insert into the appropriate per node queues
*/
}
}
}
- put_mems_allowed();
+
+ if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj))
+ goto retry_cpuset;
return obj;
}
l3 = cachep->nodelists[nodeid];
BUG_ON(!l3);
- if (unlikely(slab_force_alloc(cachep, flags)))
- goto force_grow;
-
retry:
check_irq_off();
spin_lock(&l3->list_lock);
must_grow:
spin_unlock(&l3->list_lock);
-force_grow:
x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL);
if (x)
goto retry;
{
unsigned long save_flags;
void *ptr;
- int slab_node = numa_slab_nid(cachep, flags);
+ int slab_node = numa_mem_id();
flags &= gfp_allowed_mask;
cache_alloc_debugcheck_before(cachep, flags);
local_irq_save(save_flags);
- if (nodeid == -1)
+ if (nodeid == NUMA_NO_NODE)
nodeid = slab_node;
if (unlikely(!cachep->nodelists[nodeid])) {
* ____cache_alloc_node() knows how to locate memory on other nodes
*/
if (!objp)
- objp = ____cache_alloc_node(cache, flags,
- numa_slab_nid(cache, flags));
+ objp = ____cache_alloc_node(cache, flags, numa_mem_id());
out:
return objp;
{
int batchcount;
struct kmem_list3 *l3;
- int node = numa_slab_nid(cachep, GFP_KERNEL);
+ int node = numa_mem_id();
batchcount = ac->batchcount;
#if DEBUG
* Release an obj back to its cache. If the obj has a constructed state, it must
* be in this state _before_ it is released. Called with disabled ints.
*/
-static inline void __cache_free(struct kmem_cache *cachep, void *objp)
+static inline void __cache_free(struct kmem_cache *cachep, void *objp,
+ void *caller)
{
struct array_cache *ac = cpu_cache_get(cachep);
check_irq_off();
kmemleak_free_recursive(objp, cachep->flags);
- objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0));
+ objp = cache_free_debugcheck(cachep, objp, caller);
kmemcheck_slab_free(cachep, objp, obj_size(cachep));
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;
}
/**
EXPORT_SYMBOL(kmem_cache_alloc);
#ifdef CONFIG_TRACING
-void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags)
+void *
+kmem_cache_alloc_trace(size_t size, struct kmem_cache *cachep, gfp_t flags)
{
- return __cache_alloc(cachep, flags, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(kmem_cache_alloc_notrace);
-#endif
+ void *ret;
-/**
- * kmem_ptr_validate - check if an untrusted pointer might be a slab entry.
- * @cachep: the cache we're checking against
- * @ptr: pointer to validate
- *
- * This verifies that the untrusted pointer looks sane;
- * it is _not_ a guarantee that the pointer is actually
- * part of the slab cache in question, but it at least
- * validates that the pointer can be dereferenced and
- * looks half-way sane.
- *
- * Currently only used for dentry validation.
- */
-int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr)
-{
- unsigned long size = cachep->buffer_size;
- struct page *page;
+ ret = __cache_alloc(cachep, flags, __builtin_return_address(0));
- if (unlikely(!kern_ptr_validate(ptr, size)))
- goto out;
- page = virt_to_page(ptr);
- if (unlikely(!PageSlab(page)))
- goto out;
- if (unlikely(page_get_cache(page) != cachep))
- goto out;
- return 1;
-out:
- return 0;
+ trace_kmalloc(_RET_IP_, ret,
+ size, slab_buffer_size(cachep), flags);
+ return ret;
}
+EXPORT_SYMBOL(kmem_cache_alloc_trace);
+#endif
#ifdef CONFIG_NUMA
void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
EXPORT_SYMBOL(kmem_cache_alloc_node);
#ifdef CONFIG_TRACING
-void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep,
- gfp_t flags,
- int nodeid)
+void *kmem_cache_alloc_node_trace(size_t size,
+ struct kmem_cache *cachep,
+ gfp_t flags,
+ int nodeid)
{
- return __cache_alloc_node(cachep, flags, nodeid,
+ void *ret;
+
+ ret = __cache_alloc_node(cachep, flags, nodeid,
__builtin_return_address(0));
+ trace_kmalloc_node(_RET_IP_, ret,
+ size, slab_buffer_size(cachep),
+ flags, nodeid);
+ return ret;
}
-EXPORT_SYMBOL(kmem_cache_alloc_node_notrace);
+EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
#endif
static __always_inline void *
__do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller)
{
struct kmem_cache *cachep;
- void *ret;
cachep = kmem_find_general_cachep(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(cachep)))
return cachep;
- ret = kmem_cache_alloc_node_notrace(cachep, flags, node);
-
- trace_kmalloc_node((unsigned long) caller, ret,
- size, cachep->buffer_size, flags, node);
-
- return ret;
+ return kmem_cache_alloc_node_trace(size, cachep, flags, node);
}
#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING)
debug_check_no_locks_freed(objp, obj_size(cachep));
if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(objp, obj_size(cachep));
- __cache_free(cachep, objp);
+ __cache_free(cachep, objp, __builtin_return_address(0));
local_irq_restore(flags);
trace_kmem_cache_free(_RET_IP_, objp);
c = virt_to_cache(objp);
debug_check_no_locks_freed(objp, obj_size(c));
debug_check_no_obj_freed(objp, obj_size(c));
- __cache_free(c, (void *)objp);
+ __cache_free(c, (void *)objp, __builtin_return_address(0));
local_irq_restore(flags);
}
EXPORT_SYMBOL(kfree);
}
EXPORT_SYMBOL(kmem_cache_size);
-const char *kmem_cache_name(struct kmem_cache *cachep)
-{
- return cachep->name;
-}
-EXPORT_SYMBOL_GPL(kmem_cache_name);
-
-/*
- * Calculate the upper bound of pages required to sequentially allocate
- * @objects objects from @cachep.
- */
-unsigned kmem_alloc_estimate(struct kmem_cache *cachep,
- gfp_t flags, int objects)
-{
- /*
- * (1) memory for objects,
- */
- unsigned nr_slabs = DIV_ROUND_UP(objects, cachep->num);
- unsigned nr_pages = nr_slabs << cachep->gfporder;
-
- /*
- * (2) memory for each per-cpu queue (nr_cpu_ids),
- * (3) memory for each per-node alien queues (nr_cpu_ids), and
- * (4) some amount of memory for the slab management structures
- *
- * XXX: truely account these
- */
- nr_pages += 1 + ilog2(nr_pages);
-
- return nr_pages;
-}
-
-/*
- * Calculate the upper bound of pages required to sequentially allocate
- * @count objects of @size bytes from kmalloc given @flags.
- */
-unsigned kmalloc_estimate_objs(size_t size, gfp_t flags, int count)
-{
- struct kmem_cache *s = kmem_find_general_cachep(size, flags);
- if (!s)
- return 0;
-
- return kmem_alloc_estimate(s, flags, count);
-}
-EXPORT_SYMBOL_GPL(kmalloc_estimate_objs);
-
-/*
- * Calculate the upper bound of pages requires to sequentially allocate @bytes
- * from kmalloc in an unspecified number of allocations of nonuniform size.
- */
-unsigned kmalloc_estimate_bytes(gfp_t flags, size_t bytes)
-{
- unsigned long pages;
- struct cache_sizes *csizep = malloc_sizes;
-
- /*
- * multiply by two, in order to account the worst case slack space
- * due to the power-of-two allocation sizes.
- */
- pages = DIV_ROUND_UP(2 * bytes, PAGE_SIZE);
-
- /*
- * add the kmem_cache overhead of each possible kmalloc cache
- */
- for (csizep = malloc_sizes; csizep->cs_cachep; csizep++) {
- struct kmem_cache *s;
-
-#ifdef CONFIG_ZONE_DMA
- if (unlikely(flags & __GFP_DMA))
- s = csizep->cs_dmacachep;
- else
-#endif
- s = csizep->cs_cachep;
-
- if (s)
- pages += kmem_alloc_estimate(s, flags, 0);
- }
-
- return pages;
-}
-EXPORT_SYMBOL_GPL(kmalloc_estimate_bytes);
-
/*
* This initializes kmem_list3 or resizes various caches for all nodes.
*/
struct ccupdate_struct {
struct kmem_cache *cachep;
- struct array_cache *new[NR_CPUS];
+ struct array_cache *new[0];
};
static void do_ccupdate_local(void *info)
struct ccupdate_struct *new;
int i;
- new = kzalloc(sizeof(*new), gfp);
+ new = kzalloc(sizeof(*new) + nr_cpu_ids * sizeof(struct array_cache *),
+ gfp);
if (!new)
return -ENOMEM;
* necessary. Note that the l3 listlock also protects the array_cache
* if drain_array() is used on the shared array.
*/
-void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
+static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
struct array_cache *ac, int force, int node)
{
int tofree;
{
struct kmem_cache *searchp;
struct kmem_list3 *l3;
- int node = numa_slab_nid(NULL, GFP_KERNEL);
+ int node = numa_mem_id();
struct delayed_work *work = to_delayed_work(w);
if (!mutex_trylock(&cache_chain_mutex))
* @count: data length
* @ppos: unused
*/
-ssize_t slabinfo_write(struct file *file, const char __user * buffer,
+static ssize_t slabinfo_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
char kbuf[MAX_SLABINFO_WRITE + 1], *tmp;
static int __init slab_proc_init(void)
{
- proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations);
+ proc_create("slabinfo",S_IWUSR|S_IRUSR,NULL,&proc_slabinfo_operations);
#ifdef CONFIG_DEBUG_SLAB_LEAK
proc_create("slab_allocators", 0, NULL, &proc_slabstats_operations);
#endif