linux/mm/slab_common.c
Jiri Kosina 210ed9deff mm, slab: release slab_mutex earlier in kmem_cache_destroy()
Commit 1331e7a1bb ("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>
2012-10-10 09:25:08 +03:00

195 lines
4.3 KiB
C

/*
* 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 <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.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(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;
}
if (!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(const char *name, size_t size)
{
return 0;
}
#endif
/*
* 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(const char *name, size_t size, size_t align,
unsigned long flags, void (*ctor)(void *))
{
struct kmem_cache *s = NULL;
int err = 0;
get_online_cpus();
mutex_lock(&slab_mutex);
if (!kmem_cache_sanity_check(name, size) == 0)
goto out_locked;
s = __kmem_cache_alias(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 = align;
s->ctor = ctor;
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);
} 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;
}
EXPORT_SYMBOL(kmem_cache_create);
void kmem_cache_destroy(struct kmem_cache *s)
{
get_online_cpus();
mutex_lock(&slab_mutex);
s->refcount--;
if (!s->refcount) {
list_del(&s->list);
if (!__kmem_cache_shutdown(s)) {
mutex_unlock(&slab_mutex);
if (s->flags & SLAB_DESTROY_BY_RCU)
rcu_barrier();
kfree(s->name);
kmem_cache_free(kmem_cache, s);
} else {
list_add(&s->list, &slab_caches);
mutex_unlock(&slab_mutex);
printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
s->name);
dump_stack();
}
} else {
mutex_unlock(&slab_mutex);
}
put_online_cpus();
}
EXPORT_SYMBOL(kmem_cache_destroy);
int slab_is_available(void)
{
return slab_state >= UP;
}