linux/mm/slab_common.c

649 lines
15 KiB
C
Raw Normal View History

/*
* Slab allocator functions that are independent of the allocator strategy
*
* (C) 2012 Christoph Lameter <cl@linux.com>
*/
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/poison.h>
#include <linux/interrupt.h>
#include <linux/memory.h>
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/cpu.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <linux/memcontrol.h>
#include "slab.h"
enum slab_state slab_state;
LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
struct kmem_cache *kmem_cache;
#ifdef CONFIG_DEBUG_VM
static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
size_t size)
{
struct kmem_cache *s = NULL;
if (!name || in_interrupt() || size < sizeof(void *) ||
size > KMALLOC_MAX_SIZE) {
pr_err("kmem_cache_create(%s) integrity check failed\n", name);
return -EINVAL;
}
list_for_each_entry(s, &slab_caches, list) {
char tmp;
int res;
/*
* This happens when the module gets unloaded and doesn't
* destroy its slab cache and no-one else reuses the vmalloc
* area of the module. Print a warning.
*/
res = probe_kernel_address(s->name, tmp);
if (res) {
pr_err("Slab cache with size %d has lost its name\n",
s->object_size);
continue;
}
/*
* For simplicity, we won't check this in the list of memcg
* caches. We have control over memcg naming, and if there
* aren't duplicates in the global list, there won't be any
* duplicates in the memcg lists as well.
*/
if (!memcg && !strcmp(s->name, name)) {
pr_err("%s (%s): Cache name already exists.\n",
__func__, name);
dump_stack();
s = NULL;
return -EINVAL;
}
}
WARN_ON(strchr(name, ' ')); /* It confuses parsers */
return 0;
}
#else
static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
const char *name, size_t size)
{
return 0;
}
#endif
memcg: allocate memory for memcg caches whenever a new memcg appears Every cache that is considered a root cache (basically the "original" caches, tied to the root memcg/no-memcg) will have an array that should be large enough to store a cache pointer per each memcg in the system. Theoreticaly, this is as high as 1 << sizeof(css_id), which is currently in the 64k pointers range. Most of the time, we won't be using that much. What goes in this patch, is a simple scheme to dynamically allocate such an array, in order to minimize memory usage for memcg caches. Because we would also like to avoid allocations all the time, at least for now, the array will only grow. It will tend to be big enough to hold the maximum number of kmem-limited memcgs ever achieved. We'll allocate it to be a minimum of 64 kmem-limited memcgs. When we have more than that, we'll start doubling the size of this array every time the limit is reached. Because we are only considering kmem limited memcgs, a natural point for this to happen is when we write to the limit. At that point, we already have set_limit_mutex held, so that will become our natural synchronization mechanism. Signed-off-by: Glauber Costa <glommer@parallels.com> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Frederic Weisbecker <fweisbec@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: JoonSoo Kim <js1304@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michal Hocko <mhocko@suse.cz> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Rik van Riel <riel@redhat.com> Cc: Suleiman Souhlal <suleiman@google.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-18 22:22:38 +00:00
#ifdef CONFIG_MEMCG_KMEM
int memcg_update_all_caches(int num_memcgs)
{
struct kmem_cache *s;
int ret = 0;
mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
if (!is_root_cache(s))
continue;
ret = memcg_update_cache_size(s, num_memcgs);
/*
* See comment in memcontrol.c, memcg_update_cache_size:
* Instead of freeing the memory, we'll just leave the caches
* up to this point in an updated state.
*/
if (ret)
goto out;
}
memcg_update_array_size(num_memcgs);
out:
mutex_unlock(&slab_mutex);
return ret;
}
#endif
/*
* Figure out what the alignment of the objects will be given a set of
* flags, a user specified alignment and the size of the objects.
*/
unsigned long calculate_alignment(unsigned long flags,
unsigned long align, unsigned long size)
{
/*
* If the user wants hardware cache aligned objects then follow that
* suggestion if the object is sufficiently large.
*
* The hardware cache alignment cannot override the specified
* alignment though. If that is greater then use it.
*/
if (flags & SLAB_HWCACHE_ALIGN) {
unsigned long ralign = cache_line_size();
while (size <= ralign / 2)
ralign /= 2;
align = max(align, ralign);
}
if (align < ARCH_SLAB_MINALIGN)
align = ARCH_SLAB_MINALIGN;
return ALIGN(align, sizeof(void *));
}
/*
* kmem_cache_create - Create a cache.
* @name: A string which is used in /proc/slabinfo to identify this cache.
* @size: The size of objects to be created in this cache.
* @align: The required alignment for the objects.
* @flags: SLAB flags
* @ctor: A constructor for the objects.
*
* Returns a ptr to the cache on success, NULL on failure.
* Cannot be called within a interrupt, but can be interrupted.
* The @ctor is run when new pages are allocated by the cache.
*
* The flags are
*
* %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
* to catch references to uninitialised memory.
*
* %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
* for buffer overruns.
*
* %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
* cacheline. This can be beneficial if you're counting cycles as closely
* as davem.
*/
struct kmem_cache *
kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
slab: propagate tunable values SLAB allows us to tune a particular cache behavior with tunables. When creating a new memcg cache copy, we'd like to preserve any tunables the parent cache already had. This could be done by an explicit call to do_tune_cpucache() after the cache is created. But this is not very convenient now that the caches are created from common code, since this function is SLAB-specific. Another method of doing that is taking advantage of the fact that do_tune_cpucache() is always called from enable_cpucache(), which is called at cache initialization. We can just preset the values, and then things work as expected. It can also happen that a root cache has its tunables updated during normal system operation. In this case, we will propagate the change to all caches that are already active. This change will require us to move the assignment of root_cache in memcg_params a bit earlier. We need this to be already set - which memcg_kmem_register_cache will do - when we reach __kmem_cache_create() Signed-off-by: Glauber Costa <glommer@parallels.com> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Frederic Weisbecker <fweisbec@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: JoonSoo Kim <js1304@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michal Hocko <mhocko@suse.cz> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Rik van Riel <riel@redhat.com> Cc: Suleiman Souhlal <suleiman@google.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-18 22:23:03 +00:00
size_t align, unsigned long flags, void (*ctor)(void *),
struct kmem_cache *parent_cache)
{
struct kmem_cache *s = NULL;
int err = 0;
get_online_cpus();
mutex_lock(&slab_mutex);
if (!kmem_cache_sanity_check(memcg, name, size) == 0)
goto out_locked;
/*
* Some allocators will constraint the set of valid flags to a subset
* of all flags. We expect them to define CACHE_CREATE_MASK in this
* case, and we'll just provide them with a sanitized version of the
* passed flags.
*/
flags &= CACHE_CREATE_MASK;
s = __kmem_cache_alias(memcg, name, size, align, flags, ctor);
if (s)
goto out_locked;
s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
if (s) {
s->object_size = s->size = size;
s->align = calculate_alignment(flags, align, size);
s->ctor = ctor;
slab: propagate tunable values SLAB allows us to tune a particular cache behavior with tunables. When creating a new memcg cache copy, we'd like to preserve any tunables the parent cache already had. This could be done by an explicit call to do_tune_cpucache() after the cache is created. But this is not very convenient now that the caches are created from common code, since this function is SLAB-specific. Another method of doing that is taking advantage of the fact that do_tune_cpucache() is always called from enable_cpucache(), which is called at cache initialization. We can just preset the values, and then things work as expected. It can also happen that a root cache has its tunables updated during normal system operation. In this case, we will propagate the change to all caches that are already active. This change will require us to move the assignment of root_cache in memcg_params a bit earlier. We need this to be already set - which memcg_kmem_register_cache will do - when we reach __kmem_cache_create() Signed-off-by: Glauber Costa <glommer@parallels.com> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Frederic Weisbecker <fweisbec@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: JoonSoo Kim <js1304@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michal Hocko <mhocko@suse.cz> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Rik van Riel <riel@redhat.com> Cc: Suleiman Souhlal <suleiman@google.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-18 22:23:03 +00:00
if (memcg_register_cache(memcg, s, parent_cache)) {
kmem_cache_free(kmem_cache, s);
err = -ENOMEM;
goto out_locked;
}
s->name = kstrdup(name, GFP_KERNEL);
if (!s->name) {
kmem_cache_free(kmem_cache, s);
err = -ENOMEM;
goto out_locked;
}
err = __kmem_cache_create(s, flags);
if (!err) {
s->refcount = 1;
list_add(&s->list, &slab_caches);
memcg_cache_list_add(memcg, s);
} else {
kfree(s->name);
kmem_cache_free(kmem_cache, s);
}
} else
err = -ENOMEM;
out_locked:
mutex_unlock(&slab_mutex);
put_online_cpus();
if (err) {
if (flags & SLAB_PANIC)
panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
name, err);
else {
printk(KERN_WARNING "kmem_cache_create(%s) failed with error %d",
name, err);
dump_stack();
}
return NULL;
}
return s;
}
struct kmem_cache *
kmem_cache_create(const char *name, size_t size, size_t align,
unsigned long flags, void (*ctor)(void *))
{
slab: propagate tunable values SLAB allows us to tune a particular cache behavior with tunables. When creating a new memcg cache copy, we'd like to preserve any tunables the parent cache already had. This could be done by an explicit call to do_tune_cpucache() after the cache is created. But this is not very convenient now that the caches are created from common code, since this function is SLAB-specific. Another method of doing that is taking advantage of the fact that do_tune_cpucache() is always called from enable_cpucache(), which is called at cache initialization. We can just preset the values, and then things work as expected. It can also happen that a root cache has its tunables updated during normal system operation. In this case, we will propagate the change to all caches that are already active. This change will require us to move the assignment of root_cache in memcg_params a bit earlier. We need this to be already set - which memcg_kmem_register_cache will do - when we reach __kmem_cache_create() Signed-off-by: Glauber Costa <glommer@parallels.com> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Frederic Weisbecker <fweisbec@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: JoonSoo Kim <js1304@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michal Hocko <mhocko@suse.cz> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Rik van Riel <riel@redhat.com> Cc: Suleiman Souhlal <suleiman@google.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-18 22:23:03 +00:00
return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL);
}
EXPORT_SYMBOL(kmem_cache_create);
void kmem_cache_destroy(struct kmem_cache *s)
{
/* Destroy all the children caches if we aren't a memcg cache */
kmem_cache_destroy_memcg_children(s);
get_online_cpus();
mutex_lock(&slab_mutex);
s->refcount--;
if (!s->refcount) {
list_del(&s->list);
if (!__kmem_cache_shutdown(s)) {
mm, slab: release slab_mutex earlier in kmem_cache_destroy() Commit 1331e7a1bbe1 ("rcu: Remove _rcu_barrier() dependency on __stop_machine()") introduced slab_mutex -> cpu_hotplug.lock dependency through kmem_cache_destroy() -> rcu_barrier() -> _rcu_barrier() -> get_online_cpus(). Lockdep thinks that this might actually result in ABBA deadlock, and reports it as below: === [ cut here ] === ====================================================== [ INFO: possible circular locking dependency detected ] 3.6.0-rc5-00004-g0d8ee37 #143 Not tainted ------------------------------------------------------- kworker/u:2/40 is trying to acquire lock: (rcu_sched_state.barrier_mutex){+.+...}, at: [<ffffffff810f2126>] _rcu_barrier+0x26/0x1e0 but task is already holding lock: (slab_mutex){+.+.+.}, at: [<ffffffff81176e15>] kmem_cache_destroy+0x45/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (slab_mutex){+.+.+.}: [<ffffffff810ae1e2>] validate_chain+0x632/0x720 [<ffffffff810ae5d9>] __lock_acquire+0x309/0x530 [<ffffffff810ae921>] lock_acquire+0x121/0x190 [<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450 [<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50 [<ffffffff81558cb5>] cpuup_callback+0x2f/0xbe [<ffffffff81564b83>] notifier_call_chain+0x93/0x140 [<ffffffff81076f89>] __raw_notifier_call_chain+0x9/0x10 [<ffffffff8155719d>] _cpu_up+0xba/0x14e [<ffffffff815572ed>] cpu_up+0xbc/0x117 [<ffffffff81ae05e3>] smp_init+0x6b/0x9f [<ffffffff81ac47d6>] kernel_init+0x147/0x1dc [<ffffffff8156ab44>] kernel_thread_helper+0x4/0x10 -> #1 (cpu_hotplug.lock){+.+.+.}: [<ffffffff810ae1e2>] validate_chain+0x632/0x720 [<ffffffff810ae5d9>] __lock_acquire+0x309/0x530 [<ffffffff810ae921>] lock_acquire+0x121/0x190 [<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450 [<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50 [<ffffffff81049197>] get_online_cpus+0x37/0x50 [<ffffffff810f21bb>] _rcu_barrier+0xbb/0x1e0 [<ffffffff810f22f0>] rcu_barrier_sched+0x10/0x20 [<ffffffff810f2309>] rcu_barrier+0x9/0x10 [<ffffffff8118c129>] deactivate_locked_super+0x49/0x90 [<ffffffff8118cc01>] deactivate_super+0x61/0x70 [<ffffffff811aaaa7>] mntput_no_expire+0x127/0x180 [<ffffffff811ab49e>] sys_umount+0x6e/0xd0 [<ffffffff81569979>] system_call_fastpath+0x16/0x1b -> #0 (rcu_sched_state.barrier_mutex){+.+...}: [<ffffffff810adb4e>] check_prev_add+0x3de/0x440 [<ffffffff810ae1e2>] validate_chain+0x632/0x720 [<ffffffff810ae5d9>] __lock_acquire+0x309/0x530 [<ffffffff810ae921>] lock_acquire+0x121/0x190 [<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450 [<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50 [<ffffffff810f2126>] _rcu_barrier+0x26/0x1e0 [<ffffffff810f22f0>] rcu_barrier_sched+0x10/0x20 [<ffffffff810f2309>] rcu_barrier+0x9/0x10 [<ffffffff81176ea1>] kmem_cache_destroy+0xd1/0xe0 [<ffffffffa04c3154>] nf_conntrack_cleanup_net+0xe4/0x110 [nf_conntrack] [<ffffffffa04c31aa>] nf_conntrack_cleanup+0x2a/0x70 [nf_conntrack] [<ffffffffa04c42ce>] nf_conntrack_net_exit+0x5e/0x80 [nf_conntrack] [<ffffffff81454b79>] ops_exit_list+0x39/0x60 [<ffffffff814551ab>] cleanup_net+0xfb/0x1b0 [<ffffffff8106917b>] process_one_work+0x26b/0x4c0 [<ffffffff81069f3e>] worker_thread+0x12e/0x320 [<ffffffff8106f73e>] kthread+0x9e/0xb0 [<ffffffff8156ab44>] kernel_thread_helper+0x4/0x10 other info that might help us debug this: Chain exists of: rcu_sched_state.barrier_mutex --> cpu_hotplug.lock --> slab_mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(slab_mutex); lock(cpu_hotplug.lock); lock(slab_mutex); lock(rcu_sched_state.barrier_mutex); *** DEADLOCK *** === [ cut here ] === This is actually a false positive. Lockdep has no way of knowing the fact that the ABBA can actually never happen, because of special semantics of cpu_hotplug.refcount and its handling in cpu_hotplug_begin(); the mutual exclusion there is not achieved through mutex, but through cpu_hotplug.refcount. The "neither cpu_up() nor cpu_down() will proceed past cpu_hotplug_begin() until everyone who called get_online_cpus() will call put_online_cpus()" semantics is totally invisible to lockdep. This patch therefore moves the unlock of slab_mutex so that rcu_barrier() is being called with it unlocked. It has two advantages: - it slightly reduces hold time of slab_mutex; as it's used to protect the cachep list, it's not necessary to hold it over kmem_cache_free() call any more - it silences the lockdep false positive warning, as it avoids lockdep ever learning about slab_mutex -> cpu_hotplug.lock dependency Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-10-08 07:26:01 +00:00
mutex_unlock(&slab_mutex);
if (s->flags & SLAB_DESTROY_BY_RCU)
rcu_barrier();
memcg_release_cache(s);
kfree(s->name);
kmem_cache_free(kmem_cache, s);
} else {
list_add(&s->list, &slab_caches);
mm, slab: release slab_mutex earlier in kmem_cache_destroy() Commit 1331e7a1bbe1 ("rcu: Remove _rcu_barrier() dependency on __stop_machine()") introduced slab_mutex -> cpu_hotplug.lock dependency through kmem_cache_destroy() -> rcu_barrier() -> _rcu_barrier() -> get_online_cpus(). Lockdep thinks that this might actually result in ABBA deadlock, and reports it as below: === [ cut here ] === ====================================================== [ INFO: possible circular locking dependency detected ] 3.6.0-rc5-00004-g0d8ee37 #143 Not tainted ------------------------------------------------------- kworker/u:2/40 is trying to acquire lock: (rcu_sched_state.barrier_mutex){+.+...}, at: [<ffffffff810f2126>] _rcu_barrier+0x26/0x1e0 but task is already holding lock: (slab_mutex){+.+.+.}, at: [<ffffffff81176e15>] kmem_cache_destroy+0x45/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (slab_mutex){+.+.+.}: [<ffffffff810ae1e2>] validate_chain+0x632/0x720 [<ffffffff810ae5d9>] __lock_acquire+0x309/0x530 [<ffffffff810ae921>] lock_acquire+0x121/0x190 [<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450 [<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50 [<ffffffff81558cb5>] cpuup_callback+0x2f/0xbe [<ffffffff81564b83>] notifier_call_chain+0x93/0x140 [<ffffffff81076f89>] __raw_notifier_call_chain+0x9/0x10 [<ffffffff8155719d>] _cpu_up+0xba/0x14e [<ffffffff815572ed>] cpu_up+0xbc/0x117 [<ffffffff81ae05e3>] smp_init+0x6b/0x9f [<ffffffff81ac47d6>] kernel_init+0x147/0x1dc [<ffffffff8156ab44>] kernel_thread_helper+0x4/0x10 -> #1 (cpu_hotplug.lock){+.+.+.}: [<ffffffff810ae1e2>] validate_chain+0x632/0x720 [<ffffffff810ae5d9>] __lock_acquire+0x309/0x530 [<ffffffff810ae921>] lock_acquire+0x121/0x190 [<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450 [<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50 [<ffffffff81049197>] get_online_cpus+0x37/0x50 [<ffffffff810f21bb>] _rcu_barrier+0xbb/0x1e0 [<ffffffff810f22f0>] rcu_barrier_sched+0x10/0x20 [<ffffffff810f2309>] rcu_barrier+0x9/0x10 [<ffffffff8118c129>] deactivate_locked_super+0x49/0x90 [<ffffffff8118cc01>] deactivate_super+0x61/0x70 [<ffffffff811aaaa7>] mntput_no_expire+0x127/0x180 [<ffffffff811ab49e>] sys_umount+0x6e/0xd0 [<ffffffff81569979>] system_call_fastpath+0x16/0x1b -> #0 (rcu_sched_state.barrier_mutex){+.+...}: [<ffffffff810adb4e>] check_prev_add+0x3de/0x440 [<ffffffff810ae1e2>] validate_chain+0x632/0x720 [<ffffffff810ae5d9>] __lock_acquire+0x309/0x530 [<ffffffff810ae921>] lock_acquire+0x121/0x190 [<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450 [<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50 [<ffffffff810f2126>] _rcu_barrier+0x26/0x1e0 [<ffffffff810f22f0>] rcu_barrier_sched+0x10/0x20 [<ffffffff810f2309>] rcu_barrier+0x9/0x10 [<ffffffff81176ea1>] kmem_cache_destroy+0xd1/0xe0 [<ffffffffa04c3154>] nf_conntrack_cleanup_net+0xe4/0x110 [nf_conntrack] [<ffffffffa04c31aa>] nf_conntrack_cleanup+0x2a/0x70 [nf_conntrack] [<ffffffffa04c42ce>] nf_conntrack_net_exit+0x5e/0x80 [nf_conntrack] [<ffffffff81454b79>] ops_exit_list+0x39/0x60 [<ffffffff814551ab>] cleanup_net+0xfb/0x1b0 [<ffffffff8106917b>] process_one_work+0x26b/0x4c0 [<ffffffff81069f3e>] worker_thread+0x12e/0x320 [<ffffffff8106f73e>] kthread+0x9e/0xb0 [<ffffffff8156ab44>] kernel_thread_helper+0x4/0x10 other info that might help us debug this: Chain exists of: rcu_sched_state.barrier_mutex --> cpu_hotplug.lock --> slab_mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(slab_mutex); lock(cpu_hotplug.lock); lock(slab_mutex); lock(rcu_sched_state.barrier_mutex); *** DEADLOCK *** === [ cut here ] === This is actually a false positive. Lockdep has no way of knowing the fact that the ABBA can actually never happen, because of special semantics of cpu_hotplug.refcount and its handling in cpu_hotplug_begin(); the mutual exclusion there is not achieved through mutex, but through cpu_hotplug.refcount. The "neither cpu_up() nor cpu_down() will proceed past cpu_hotplug_begin() until everyone who called get_online_cpus() will call put_online_cpus()" semantics is totally invisible to lockdep. This patch therefore moves the unlock of slab_mutex so that rcu_barrier() is being called with it unlocked. It has two advantages: - it slightly reduces hold time of slab_mutex; as it's used to protect the cachep list, it's not necessary to hold it over kmem_cache_free() call any more - it silences the lockdep false positive warning, as it avoids lockdep ever learning about slab_mutex -> cpu_hotplug.lock dependency Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-10-08 07:26:01 +00:00
mutex_unlock(&slab_mutex);
printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
s->name);
dump_stack();
}
mm, slab: release slab_mutex earlier in kmem_cache_destroy() Commit 1331e7a1bbe1 ("rcu: Remove _rcu_barrier() dependency on __stop_machine()") introduced slab_mutex -> cpu_hotplug.lock dependency through kmem_cache_destroy() -> rcu_barrier() -> _rcu_barrier() -> get_online_cpus(). Lockdep thinks that this might actually result in ABBA deadlock, and reports it as below: === [ cut here ] === ====================================================== [ INFO: possible circular locking dependency detected ] 3.6.0-rc5-00004-g0d8ee37 #143 Not tainted ------------------------------------------------------- kworker/u:2/40 is trying to acquire lock: (rcu_sched_state.barrier_mutex){+.+...}, at: [<ffffffff810f2126>] _rcu_barrier+0x26/0x1e0 but task is already holding lock: (slab_mutex){+.+.+.}, at: [<ffffffff81176e15>] kmem_cache_destroy+0x45/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (slab_mutex){+.+.+.}: [<ffffffff810ae1e2>] validate_chain+0x632/0x720 [<ffffffff810ae5d9>] __lock_acquire+0x309/0x530 [<ffffffff810ae921>] lock_acquire+0x121/0x190 [<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450 [<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50 [<ffffffff81558cb5>] cpuup_callback+0x2f/0xbe [<ffffffff81564b83>] notifier_call_chain+0x93/0x140 [<ffffffff81076f89>] __raw_notifier_call_chain+0x9/0x10 [<ffffffff8155719d>] _cpu_up+0xba/0x14e [<ffffffff815572ed>] cpu_up+0xbc/0x117 [<ffffffff81ae05e3>] smp_init+0x6b/0x9f [<ffffffff81ac47d6>] kernel_init+0x147/0x1dc [<ffffffff8156ab44>] kernel_thread_helper+0x4/0x10 -> #1 (cpu_hotplug.lock){+.+.+.}: [<ffffffff810ae1e2>] validate_chain+0x632/0x720 [<ffffffff810ae5d9>] __lock_acquire+0x309/0x530 [<ffffffff810ae921>] lock_acquire+0x121/0x190 [<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450 [<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50 [<ffffffff81049197>] get_online_cpus+0x37/0x50 [<ffffffff810f21bb>] _rcu_barrier+0xbb/0x1e0 [<ffffffff810f22f0>] rcu_barrier_sched+0x10/0x20 [<ffffffff810f2309>] rcu_barrier+0x9/0x10 [<ffffffff8118c129>] deactivate_locked_super+0x49/0x90 [<ffffffff8118cc01>] deactivate_super+0x61/0x70 [<ffffffff811aaaa7>] mntput_no_expire+0x127/0x180 [<ffffffff811ab49e>] sys_umount+0x6e/0xd0 [<ffffffff81569979>] system_call_fastpath+0x16/0x1b -> #0 (rcu_sched_state.barrier_mutex){+.+...}: [<ffffffff810adb4e>] check_prev_add+0x3de/0x440 [<ffffffff810ae1e2>] validate_chain+0x632/0x720 [<ffffffff810ae5d9>] __lock_acquire+0x309/0x530 [<ffffffff810ae921>] lock_acquire+0x121/0x190 [<ffffffff8155d4cc>] __mutex_lock_common+0x5c/0x450 [<ffffffff8155d9ee>] mutex_lock_nested+0x3e/0x50 [<ffffffff810f2126>] _rcu_barrier+0x26/0x1e0 [<ffffffff810f22f0>] rcu_barrier_sched+0x10/0x20 [<ffffffff810f2309>] rcu_barrier+0x9/0x10 [<ffffffff81176ea1>] kmem_cache_destroy+0xd1/0xe0 [<ffffffffa04c3154>] nf_conntrack_cleanup_net+0xe4/0x110 [nf_conntrack] [<ffffffffa04c31aa>] nf_conntrack_cleanup+0x2a/0x70 [nf_conntrack] [<ffffffffa04c42ce>] nf_conntrack_net_exit+0x5e/0x80 [nf_conntrack] [<ffffffff81454b79>] ops_exit_list+0x39/0x60 [<ffffffff814551ab>] cleanup_net+0xfb/0x1b0 [<ffffffff8106917b>] process_one_work+0x26b/0x4c0 [<ffffffff81069f3e>] worker_thread+0x12e/0x320 [<ffffffff8106f73e>] kthread+0x9e/0xb0 [<ffffffff8156ab44>] kernel_thread_helper+0x4/0x10 other info that might help us debug this: Chain exists of: rcu_sched_state.barrier_mutex --> cpu_hotplug.lock --> slab_mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(slab_mutex); lock(cpu_hotplug.lock); lock(slab_mutex); lock(rcu_sched_state.barrier_mutex); *** DEADLOCK *** === [ cut here ] === This is actually a false positive. Lockdep has no way of knowing the fact that the ABBA can actually never happen, because of special semantics of cpu_hotplug.refcount and its handling in cpu_hotplug_begin(); the mutual exclusion there is not achieved through mutex, but through cpu_hotplug.refcount. The "neither cpu_up() nor cpu_down() will proceed past cpu_hotplug_begin() until everyone who called get_online_cpus() will call put_online_cpus()" semantics is totally invisible to lockdep. This patch therefore moves the unlock of slab_mutex so that rcu_barrier() is being called with it unlocked. It has two advantages: - it slightly reduces hold time of slab_mutex; as it's used to protect the cachep list, it's not necessary to hold it over kmem_cache_free() call any more - it silences the lockdep false positive warning, as it avoids lockdep ever learning about slab_mutex -> cpu_hotplug.lock dependency Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Pekka Enberg <penberg@kernel.org>
2012-10-08 07:26:01 +00:00
} else {
mutex_unlock(&slab_mutex);
}
put_online_cpus();
}
EXPORT_SYMBOL(kmem_cache_destroy);
int slab_is_available(void)
{
return slab_state >= UP;
}
#ifndef CONFIG_SLOB
/* Create a cache during boot when no slab services are available yet */
void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t size,
unsigned long flags)
{
int err;
s->name = name;
s->size = s->object_size = size;
s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
err = __kmem_cache_create(s, flags);
if (err)
panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
name, size, err);
s->refcount = -1; /* Exempt from merging for now */
}
struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
unsigned long flags)
{
struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
if (!s)
panic("Out of memory when creating slab %s\n", name);
create_boot_cache(s, name, size, flags);
list_add(&s->list, &slab_caches);
s->refcount = 1;
return s;
}
struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
EXPORT_SYMBOL(kmalloc_caches);
#ifdef CONFIG_ZONE_DMA
struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
EXPORT_SYMBOL(kmalloc_dma_caches);
#endif
/*
* Conversion table for small slabs sizes / 8 to the index in the
* kmalloc array. This is necessary for slabs < 192 since we have non power
* of two cache sizes there. The size of larger slabs can be determined using
* fls.
*/
static s8 size_index[24] = {
3, /* 8 */
4, /* 16 */
5, /* 24 */
5, /* 32 */
6, /* 40 */
6, /* 48 */
6, /* 56 */
6, /* 64 */
1, /* 72 */
1, /* 80 */
1, /* 88 */
1, /* 96 */
7, /* 104 */
7, /* 112 */
7, /* 120 */
7, /* 128 */
2, /* 136 */
2, /* 144 */
2, /* 152 */
2, /* 160 */
2, /* 168 */
2, /* 176 */
2, /* 184 */
2 /* 192 */
};
static inline int size_index_elem(size_t bytes)
{
return (bytes - 1) / 8;
}
/*
* Find the kmem_cache structure that serves a given size of
* allocation
*/
struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
{
int index;
slab: prevent warnings when allocating with __GFP_NOWARN Sasha Levin noticed that the warning introduced by commit 6286ae9 ("slab: Return NULL for oversized allocations) is being triggered: WARNING: CPU: 15 PID: 21519 at mm/slab_common.c:376 kmalloc_slab+0x2f/0xb0() can: request_module (can-proto-4) failed. mpoa: proc_mpc_write: could not parse '' Modules linked in: CPU: 15 PID: 21519 Comm: trinity-child15 Tainted: G W 3.10.0-rc4-next-20130607-sasha-00011-gcd78395-dirty #2 0000000000000009 ffff880020a95e30 ffffffff83ff4041 0000000000000000 ffff880020a95e68 ffffffff8111fe12 fffffffffffffff0 00000000000082d0 0000000000080000 0000000000080000 0000000001400000 ffff880020a95e78 Call Trace: [<ffffffff83ff4041>] dump_stack+0x4e/0x82 [<ffffffff8111fe12>] warn_slowpath_common+0x82/0xb0 [<ffffffff8111fe55>] warn_slowpath_null+0x15/0x20 [<ffffffff81243dcf>] kmalloc_slab+0x2f/0xb0 [<ffffffff81278d54>] __kmalloc+0x24/0x4b0 [<ffffffff8196ffe3>] ? security_capable+0x13/0x20 [<ffffffff812a26b7>] ? pipe_fcntl+0x107/0x210 [<ffffffff812a26b7>] pipe_fcntl+0x107/0x210 [<ffffffff812b7ea0>] ? fget_raw_light+0x130/0x3f0 [<ffffffff812aa5fb>] SyS_fcntl+0x60b/0x6a0 [<ffffffff8403ca98>] tracesys+0xe1/0xe6 Andrew Morton writes: __GFP_NOWARN is frequently used by kernel code to probe for "how big an allocation can I get". That's a bit lame, but it's used on slow paths and is pretty simple. However, SLAB would still spew a warning when a big allocation happens if the __GFP_NOWARN flag is _not_ set to expose kernel bugs. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> [ penberg@kernel.org: improve changelog ] Signed-off-by: Pekka Enberg <penberg@kernel.org>
2013-06-10 19:18:00 +00:00
if (size > KMALLOC_MAX_SIZE) {
WARN_ON_ONCE(!(flags & __GFP_NOWARN));
return NULL;
slab: prevent warnings when allocating with __GFP_NOWARN Sasha Levin noticed that the warning introduced by commit 6286ae9 ("slab: Return NULL for oversized allocations) is being triggered: WARNING: CPU: 15 PID: 21519 at mm/slab_common.c:376 kmalloc_slab+0x2f/0xb0() can: request_module (can-proto-4) failed. mpoa: proc_mpc_write: could not parse '' Modules linked in: CPU: 15 PID: 21519 Comm: trinity-child15 Tainted: G W 3.10.0-rc4-next-20130607-sasha-00011-gcd78395-dirty #2 0000000000000009 ffff880020a95e30 ffffffff83ff4041 0000000000000000 ffff880020a95e68 ffffffff8111fe12 fffffffffffffff0 00000000000082d0 0000000000080000 0000000000080000 0000000001400000 ffff880020a95e78 Call Trace: [<ffffffff83ff4041>] dump_stack+0x4e/0x82 [<ffffffff8111fe12>] warn_slowpath_common+0x82/0xb0 [<ffffffff8111fe55>] warn_slowpath_null+0x15/0x20 [<ffffffff81243dcf>] kmalloc_slab+0x2f/0xb0 [<ffffffff81278d54>] __kmalloc+0x24/0x4b0 [<ffffffff8196ffe3>] ? security_capable+0x13/0x20 [<ffffffff812a26b7>] ? pipe_fcntl+0x107/0x210 [<ffffffff812a26b7>] pipe_fcntl+0x107/0x210 [<ffffffff812b7ea0>] ? fget_raw_light+0x130/0x3f0 [<ffffffff812aa5fb>] SyS_fcntl+0x60b/0x6a0 [<ffffffff8403ca98>] tracesys+0xe1/0xe6 Andrew Morton writes: __GFP_NOWARN is frequently used by kernel code to probe for "how big an allocation can I get". That's a bit lame, but it's used on slow paths and is pretty simple. However, SLAB would still spew a warning when a big allocation happens if the __GFP_NOWARN flag is _not_ set to expose kernel bugs. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> [ penberg@kernel.org: improve changelog ] Signed-off-by: Pekka Enberg <penberg@kernel.org>
2013-06-10 19:18:00 +00:00
}
if (size <= 192) {
if (!size)
return ZERO_SIZE_PTR;
index = size_index[size_index_elem(size)];
} else
index = fls(size - 1);
#ifdef CONFIG_ZONE_DMA
if (unlikely((flags & GFP_DMA)))
return kmalloc_dma_caches[index];
#endif
return kmalloc_caches[index];
}
/*
* Create the kmalloc array. Some of the regular kmalloc arrays
* may already have been created because they were needed to
* enable allocations for slab creation.
*/
void __init create_kmalloc_caches(unsigned long flags)
{
int i;
/*
* Patch up the size_index table if we have strange large alignment
* requirements for the kmalloc array. This is only the case for
* MIPS it seems. The standard arches will not generate any code here.
*
* Largest permitted alignment is 256 bytes due to the way we
* handle the index determination for the smaller caches.
*
* Make sure that nothing crazy happens if someone starts tinkering
* around with ARCH_KMALLOC_MINALIGN
*/
BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
(KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
int elem = size_index_elem(i);
if (elem >= ARRAY_SIZE(size_index))
break;
size_index[elem] = KMALLOC_SHIFT_LOW;
}
if (KMALLOC_MIN_SIZE >= 64) {
/*
* The 96 byte size cache is not used if the alignment
* is 64 byte.
*/
for (i = 64 + 8; i <= 96; i += 8)
size_index[size_index_elem(i)] = 7;
}
if (KMALLOC_MIN_SIZE >= 128) {
/*
* The 192 byte sized cache is not used if the alignment
* is 128 byte. Redirect kmalloc to use the 256 byte cache
* instead.
*/
for (i = 128 + 8; i <= 192; i += 8)
size_index[size_index_elem(i)] = 8;
}
for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
if (!kmalloc_caches[i]) {
kmalloc_caches[i] = create_kmalloc_cache(NULL,
1 << i, flags);
}
/*
* Caches that are not of the two-to-the-power-of size.
* These have to be created immediately after the
* earlier power of two caches
*/
if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6)
kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags);
if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7)
kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags);
}
/* Kmalloc array is now usable */
slab_state = UP;
for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
struct kmem_cache *s = kmalloc_caches[i];
char *n;
if (s) {
n = kasprintf(GFP_NOWAIT, "kmalloc-%d", kmalloc_size(i));
BUG_ON(!n);
s->name = n;
}
}
#ifdef CONFIG_ZONE_DMA
for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
struct kmem_cache *s = kmalloc_caches[i];
if (s) {
int size = kmalloc_size(i);
char *n = kasprintf(GFP_NOWAIT,
"dma-kmalloc-%d", size);
BUG_ON(!n);
kmalloc_dma_caches[i] = create_kmalloc_cache(n,
size, SLAB_CACHE_DMA | flags);
}
}
#endif
}
#endif /* !CONFIG_SLOB */
#ifdef CONFIG_SLABINFO
#ifdef CONFIG_SLAB
#define SLABINFO_RIGHTS (S_IWUSR | S_IRUSR)
#else
#define SLABINFO_RIGHTS S_IRUSR
#endif
void print_slabinfo_header(struct seq_file *m)
{
/*
* Output format version, so at least we can change it
* without _too_ many complaints.
*/
#ifdef CONFIG_DEBUG_SLAB
seq_puts(m, "slabinfo - version: 2.1 (statistics)\n");
#else
seq_puts(m, "slabinfo - version: 2.1\n");
#endif
seq_puts(m, "# name <active_objs> <num_objs> <objsize> "
"<objperslab> <pagesperslab>");
seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
#ifdef CONFIG_DEBUG_SLAB
seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> "
"<error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
#endif
seq_putc(m, '\n');
}
static void *s_start(struct seq_file *m, loff_t *pos)
{
loff_t n = *pos;
mutex_lock(&slab_mutex);
if (!n)
print_slabinfo_header(m);
return seq_list_start(&slab_caches, *pos);
}
void *slab_next(struct seq_file *m, void *p, loff_t *pos)
{
return seq_list_next(p, &slab_caches, pos);
}
void slab_stop(struct seq_file *m, void *p)
{
mutex_unlock(&slab_mutex);
}
static void
memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
{
struct kmem_cache *c;
struct slabinfo sinfo;
int i;
if (!is_root_cache(s))
return;
for_each_memcg_cache_index(i) {
c = cache_from_memcg(s, i);
if (!c)
continue;
memset(&sinfo, 0, sizeof(sinfo));
get_slabinfo(c, &sinfo);
info->active_slabs += sinfo.active_slabs;
info->num_slabs += sinfo.num_slabs;
info->shared_avail += sinfo.shared_avail;
info->active_objs += sinfo.active_objs;
info->num_objs += sinfo.num_objs;
}
}
int cache_show(struct kmem_cache *s, struct seq_file *m)
{
struct slabinfo sinfo;
memset(&sinfo, 0, sizeof(sinfo));
get_slabinfo(s, &sinfo);
memcg_accumulate_slabinfo(s, &sinfo);
seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
cache_name(s), sinfo.active_objs, sinfo.num_objs, s->size,
sinfo.objects_per_slab, (1 << sinfo.cache_order));
seq_printf(m, " : tunables %4u %4u %4u",
sinfo.limit, sinfo.batchcount, sinfo.shared);
seq_printf(m, " : slabdata %6lu %6lu %6lu",
sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail);
slabinfo_show_stats(m, s);
seq_putc(m, '\n');
return 0;
}
static int s_show(struct seq_file *m, void *p)
{
struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
if (!is_root_cache(s))
return 0;
return cache_show(s, m);
}
/*
* slabinfo_op - iterator that generates /proc/slabinfo
*
* Output layout:
* cache-name
* num-active-objs
* total-objs
* object size
* num-active-slabs
* total-slabs
* num-pages-per-slab
* + further values on SMP and with statistics enabled
*/
static const struct seq_operations slabinfo_op = {
.start = s_start,
.next = slab_next,
.stop = slab_stop,
.show = s_show,
};
static int slabinfo_open(struct inode *inode, struct file *file)
{
return seq_open(file, &slabinfo_op);
}
static const struct file_operations proc_slabinfo_operations = {
.open = slabinfo_open,
.read = seq_read,
.write = slabinfo_write,
.llseek = seq_lseek,
.release = seq_release,
};
static int __init slab_proc_init(void)
{
proc_create("slabinfo", SLABINFO_RIGHTS, NULL,
&proc_slabinfo_operations);
return 0;
}
module_init(slab_proc_init);
#endif /* CONFIG_SLABINFO */