mm, sl[aou]b: Use a common mutex definition
Use the mutex definition from SLAB and make it the common way to take a sleeping lock.
This has the effect of using a mutex instead of a rw semaphore for SLUB.
SLOB gains the use of a mutex for kmem_cache_create serialization.
Not needed now but SLOB may acquire some more features later (like slabinfo
/ sysfs support) through the expansion of the common code that will
need this.
Reviewed-by: Glauber Costa <glommer@parallels.com>
Reviewed-by: Joonsoo Kim <js1304@gmail.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
diff --git a/mm/slab.c b/mm/slab.c
index 59a466b..fd7dac6 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -68,7 +68,7 @@
* Further notes from the original documentation:
*
* 11 April '97. Started multi-threading - markhe
- * The global cache-chain is protected by the mutex 'cache_chain_mutex'.
+ * The global cache-chain is protected by the mutex 'slab_mutex'.
* The sem is only needed when accessing/extending the cache-chain, which
* can never happen inside an interrupt (kmem_cache_create(),
* kmem_cache_shrink() and kmem_cache_reap()).
@@ -671,12 +671,6 @@
}
#endif
-/*
- * Guard access to the cache-chain.
- */
-static DEFINE_MUTEX(cache_chain_mutex);
-static struct list_head cache_chain;
-
static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
@@ -1100,7 +1094,7 @@
* When hotplugging memory or a cpu, existing nodelists are not replaced if
* already in use.
*
- * Must hold cache_chain_mutex.
+ * Must hold slab_mutex.
*/
static int init_cache_nodelists_node(int node)
{
@@ -1108,7 +1102,7 @@
struct kmem_list3 *l3;
const int memsize = sizeof(struct kmem_list3);
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
/*
* Set up the size64 kmemlist for cpu before we can
* begin anything. Make sure some other cpu on this
@@ -1124,7 +1118,7 @@
/*
* The l3s don't come and go as CPUs come and
- * go. cache_chain_mutex is sufficient
+ * go. slab_mutex is sufficient
* protection here.
*/
cachep->nodelists[node] = l3;
@@ -1146,7 +1140,7 @@
int node = cpu_to_mem(cpu);
const struct cpumask *mask = cpumask_of_node(node);
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
struct array_cache *nc;
struct array_cache *shared;
struct array_cache **alien;
@@ -1196,7 +1190,7 @@
* the respective cache's slabs, now we can go ahead and
* shrink each nodelist to its limit.
*/
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
l3 = cachep->nodelists[node];
if (!l3)
continue;
@@ -1225,7 +1219,7 @@
* Now we can go ahead with allocating the shared arrays and
* array caches
*/
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
struct array_cache *nc;
struct array_cache *shared = NULL;
struct array_cache **alien = NULL;
@@ -1293,9 +1287,9 @@
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
err = cpuup_prepare(cpu);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
@@ -1305,7 +1299,7 @@
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
/*
- * Shutdown cache reaper. Note that the cache_chain_mutex is
+ * Shutdown cache reaper. Note that the slab_mutex is
* held so that if cache_reap() is invoked it cannot do
* anything expensive but will only modify reap_work
* and reschedule the timer.
@@ -1332,9 +1326,9 @@
#endif
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
cpuup_canceled(cpu);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
}
return notifier_from_errno(err);
@@ -1350,14 +1344,14 @@
* Returns -EBUSY if all objects cannot be drained so that the node is not
* removed.
*
- * Must hold cache_chain_mutex.
+ * Must hold slab_mutex.
*/
static int __meminit drain_cache_nodelists_node(int node)
{
struct kmem_cache *cachep;
int ret = 0;
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
struct kmem_list3 *l3;
l3 = cachep->nodelists[node];
@@ -1388,14 +1382,14 @@
switch (action) {
case MEM_GOING_ONLINE:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
ret = init_cache_nodelists_node(nid);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
case MEM_GOING_OFFLINE:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
ret = drain_cache_nodelists_node(nid);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
case MEM_ONLINE:
case MEM_OFFLINE:
@@ -1499,8 +1493,8 @@
node = numa_mem_id();
/* 1) create the cache_cache */
- INIT_LIST_HEAD(&cache_chain);
- list_add(&cache_cache.list, &cache_chain);
+ INIT_LIST_HEAD(&slab_caches);
+ list_add(&cache_cache.list, &slab_caches);
cache_cache.colour_off = cache_line_size();
cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node];
@@ -1642,11 +1636,11 @@
init_lock_keys();
/* 6) resize the head arrays to their final sizes */
- mutex_lock(&cache_chain_mutex);
- list_for_each_entry(cachep, &cache_chain, list)
+ mutex_lock(&slab_mutex);
+ list_for_each_entry(cachep, &slab_caches, list)
if (enable_cpucache(cachep, GFP_NOWAIT))
BUG();
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
/* Done! */
slab_state = FULL;
@@ -2253,10 +2247,10 @@
*/
if (slab_is_available()) {
get_online_cpus();
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
}
- list_for_each_entry(pc, &cache_chain, list) {
+ list_for_each_entry(pc, &slab_caches, list) {
char tmp;
int res;
@@ -2500,10 +2494,10 @@
}
/* cache setup completed, link it into the list */
- list_add(&cachep->list, &cache_chain);
+ list_add(&cachep->list, &slab_caches);
oops:
if (slab_is_available()) {
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
put_online_cpus();
}
return cachep;
@@ -2622,7 +2616,7 @@
return nr_freed;
}
-/* Called with cache_chain_mutex held to protect against cpu hotplug */
+/* Called with slab_mutex held to protect against cpu hotplug */
static int __cache_shrink(struct kmem_cache *cachep)
{
int ret = 0, i = 0;
@@ -2657,9 +2651,9 @@
BUG_ON(!cachep || in_interrupt());
get_online_cpus();
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
ret = __cache_shrink(cachep);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
put_online_cpus();
return ret;
}
@@ -2687,15 +2681,15 @@
/* Find the cache in the chain of caches. */
get_online_cpus();
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
/*
* the chain is never empty, cache_cache is never destroyed
*/
list_del(&cachep->list);
if (__cache_shrink(cachep)) {
slab_error(cachep, "Can't free all objects");
- list_add(&cachep->list, &cache_chain);
- mutex_unlock(&cache_chain_mutex);
+ list_add(&cachep->list, &slab_caches);
+ mutex_unlock(&slab_mutex);
put_online_cpus();
return;
}
@@ -2704,7 +2698,7 @@
rcu_barrier();
__kmem_cache_destroy(cachep);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
put_online_cpus();
}
EXPORT_SYMBOL(kmem_cache_destroy);
@@ -4017,7 +4011,7 @@
new->new[smp_processor_id()] = old;
}
-/* Always called with the cache_chain_mutex held */
+/* Always called with the slab_mutex held */
static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
int batchcount, int shared, gfp_t gfp)
{
@@ -4061,7 +4055,7 @@
return alloc_kmemlist(cachep, gfp);
}
-/* Called with cache_chain_mutex held always */
+/* Called with slab_mutex held always */
static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
{
int err;
@@ -4163,11 +4157,11 @@
int node = numa_mem_id();
struct delayed_work *work = to_delayed_work(w);
- if (!mutex_trylock(&cache_chain_mutex))
+ if (!mutex_trylock(&slab_mutex))
/* Give up. Setup the next iteration. */
goto out;
- list_for_each_entry(searchp, &cache_chain, list) {
+ list_for_each_entry(searchp, &slab_caches, list) {
check_irq_on();
/*
@@ -4205,7 +4199,7 @@
cond_resched();
}
check_irq_on();
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
next_reap_node();
out:
/* Set up the next iteration */
@@ -4241,21 +4235,21 @@
{
loff_t n = *pos;
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
if (!n)
print_slabinfo_header(m);
- return seq_list_start(&cache_chain, *pos);
+ return seq_list_start(&slab_caches, *pos);
}
static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
- return seq_list_next(p, &cache_chain, pos);
+ return seq_list_next(p, &slab_caches, pos);
}
static void s_stop(struct seq_file *m, void *p)
{
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
}
static int s_show(struct seq_file *m, void *p)
@@ -4406,9 +4400,9 @@
return -EINVAL;
/* Find the cache in the chain of caches. */
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
res = -EINVAL;
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
if (!strcmp(cachep->name, kbuf)) {
if (limit < 1 || batchcount < 1 ||
batchcount > limit || shared < 0) {
@@ -4421,7 +4415,7 @@
break;
}
}
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
if (res >= 0)
res = count;
return res;
@@ -4444,8 +4438,8 @@
static void *leaks_start(struct seq_file *m, loff_t *pos)
{
- mutex_lock(&cache_chain_mutex);
- return seq_list_start(&cache_chain, *pos);
+ mutex_lock(&slab_mutex);
+ return seq_list_start(&slab_caches, *pos);
}
static inline int add_caller(unsigned long *n, unsigned long v)
@@ -4544,17 +4538,17 @@
name = cachep->name;
if (n[0] == n[1]) {
/* Increase the buffer size */
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
m->private = kzalloc(n[0] * 4 * sizeof(unsigned long), GFP_KERNEL);
if (!m->private) {
/* Too bad, we are really out */
m->private = n;
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
return -ENOMEM;
}
*(unsigned long *)m->private = n[0] * 2;
kfree(n);
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
/* Now make sure this entry will be retried */
m->count = m->size;
return 0;
diff --git a/mm/slab.h b/mm/slab.h
index f9a9815..db7848c 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -23,6 +23,10 @@
extern enum slab_state slab_state;
+/* The slab cache mutex protects the management structures during changes */
+extern struct mutex slab_mutex;
+extern struct list_head slab_caches;
+
struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
size_t align, unsigned long flags, void (*ctor)(void *));
diff --git a/mm/slab_common.c b/mm/slab_common.c
index ca1aaf6..50e1ff1 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -19,6 +19,8 @@
#include "slab.h"
enum slab_state slab_state;
+LIST_HEAD(slab_caches);
+DEFINE_MUTEX(slab_mutex);
/*
* kmem_cache_create - Create a cache.
diff --git a/mm/slub.c b/mm/slub.c
index 4c385164..8c4fd37 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -36,13 +36,13 @@
/*
* Lock order:
- * 1. slub_lock (Global Semaphore)
+ * 1. slab_mutex (Global Mutex)
* 2. node->list_lock
* 3. slab_lock(page) (Only on some arches and for debugging)
*
- * slub_lock
+ * slab_mutex
*
- * The role of the slub_lock is to protect the list of all the slabs
+ * The role of the slab_mutex is to protect the list of all the slabs
* and to synchronize major metadata changes to slab cache structures.
*
* The slab_lock is only used for debugging and on arches that do not
@@ -183,10 +183,6 @@
static struct notifier_block slab_notifier;
#endif
-/* A list of all slab caches on the system */
-static DECLARE_RWSEM(slub_lock);
-static LIST_HEAD(slab_caches);
-
/*
* Tracking user of a slab.
*/
@@ -3177,11 +3173,11 @@
*/
void kmem_cache_destroy(struct kmem_cache *s)
{
- down_write(&slub_lock);
+ mutex_lock(&slab_mutex);
s->refcount--;
if (!s->refcount) {
list_del(&s->list);
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
if (kmem_cache_close(s)) {
printk(KERN_ERR "SLUB %s: %s called for cache that "
"still has objects.\n", s->name, __func__);
@@ -3191,7 +3187,7 @@
rcu_barrier();
sysfs_slab_remove(s);
} else
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
}
EXPORT_SYMBOL(kmem_cache_destroy);
@@ -3253,7 +3249,7 @@
/*
* This function is called with IRQs disabled during early-boot on
- * single CPU so there's no need to take slub_lock here.
+ * single CPU so there's no need to take slab_mutex here.
*/
if (!kmem_cache_open(s, name, size, ARCH_KMALLOC_MINALIGN,
flags, NULL))
@@ -3538,10 +3534,10 @@
{
struct kmem_cache *s;
- down_read(&slub_lock);
+ mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list)
kmem_cache_shrink(s);
- up_read(&slub_lock);
+ mutex_unlock(&slab_mutex);
return 0;
}
@@ -3562,7 +3558,7 @@
if (offline_node < 0)
return;
- down_read(&slub_lock);
+ mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
n = get_node(s, offline_node);
if (n) {
@@ -3578,7 +3574,7 @@
kmem_cache_free(kmem_cache_node, n);
}
}
- up_read(&slub_lock);
+ mutex_unlock(&slab_mutex);
}
static int slab_mem_going_online_callback(void *arg)
@@ -3601,7 +3597,7 @@
* allocate a kmem_cache_node structure in order to bring the node
* online.
*/
- down_read(&slub_lock);
+ mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
/*
* XXX: kmem_cache_alloc_node will fallback to other nodes
@@ -3617,7 +3613,7 @@
s->node[nid] = n;
}
out:
- up_read(&slub_lock);
+ mutex_unlock(&slab_mutex);
return ret;
}
@@ -3915,7 +3911,7 @@
struct kmem_cache *s;
char *n;
- down_write(&slub_lock);
+ mutex_lock(&slab_mutex);
s = find_mergeable(size, align, flags, name, ctor);
if (s) {
s->refcount++;
@@ -3930,7 +3926,7 @@
s->refcount--;
goto err;
}
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
return s;
}
@@ -3943,9 +3939,9 @@
if (kmem_cache_open(s, n,
size, align, flags, ctor)) {
list_add(&s->list, &slab_caches);
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
if (sysfs_slab_add(s)) {
- down_write(&slub_lock);
+ mutex_lock(&slab_mutex);
list_del(&s->list);
kfree(n);
kfree(s);
@@ -3957,7 +3953,7 @@
}
kfree(n);
err:
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
return s;
}
@@ -3978,13 +3974,13 @@
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- down_read(&slub_lock);
+ mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
local_irq_save(flags);
__flush_cpu_slab(s, cpu);
local_irq_restore(flags);
}
- up_read(&slub_lock);
+ mutex_unlock(&slab_mutex);
break;
default:
break;
@@ -5360,11 +5356,11 @@
struct kmem_cache *s;
int err;
- down_write(&slub_lock);
+ mutex_lock(&slab_mutex);
slab_kset = kset_create_and_add("slab", &slab_uevent_ops, kernel_kobj);
if (!slab_kset) {
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
printk(KERN_ERR "Cannot register slab subsystem.\n");
return -ENOSYS;
}
@@ -5389,7 +5385,7 @@
kfree(al);
}
- up_write(&slub_lock);
+ mutex_unlock(&slab_mutex);
resiliency_test();
return 0;
}
@@ -5415,7 +5411,7 @@
{
loff_t n = *pos;
- down_read(&slub_lock);
+ mutex_lock(&slab_mutex);
if (!n)
print_slabinfo_header(m);
@@ -5429,7 +5425,7 @@
static void s_stop(struct seq_file *m, void *p)
{
- up_read(&slub_lock);
+ mutex_unlock(&slab_mutex);
}
static int s_show(struct seq_file *m, void *p)