linux_dsm_epyc7002/include/linux/slub_def.h
Tejun Heo 3b7b314053 slub: make sysfs file removal asynchronous
Commit bf5eb3de38 ("slub: separate out sysfs_slab_release() from
sysfs_slab_remove()") made slub sysfs file removals synchronous to
kmem_cache shutdown.

Unfortunately, this created a possible ABBA deadlock between slab_mutex
and sysfs draining mechanism triggering the following lockdep warning.

  ======================================================
  [ INFO: possible circular locking dependency detected ]
  4.10.0-test+ #48 Not tainted
  -------------------------------------------------------
  rmmod/1211 is trying to acquire lock:
   (s_active#120){++++.+}, at: [<ffffffff81308073>] kernfs_remove+0x23/0x40

  but task is already holding lock:
   (slab_mutex){+.+.+.}, at: [<ffffffff8120f691>] kmem_cache_destroy+0x41/0x2d0

  which lock already depends on the new lock.

  the existing dependency chain (in reverse order) is:

  -> #1 (slab_mutex){+.+.+.}:
	 lock_acquire+0xf6/0x1f0
	 __mutex_lock+0x75/0x950
	 mutex_lock_nested+0x1b/0x20
	 slab_attr_store+0x75/0xd0
	 sysfs_kf_write+0x45/0x60
	 kernfs_fop_write+0x13c/0x1c0
	 __vfs_write+0x28/0x120
	 vfs_write+0xc8/0x1e0
	 SyS_write+0x49/0xa0
	 entry_SYSCALL_64_fastpath+0x1f/0xc2

  -> #0 (s_active#120){++++.+}:
	 __lock_acquire+0x10ed/0x1260
	 lock_acquire+0xf6/0x1f0
	 __kernfs_remove+0x254/0x320
	 kernfs_remove+0x23/0x40
	 sysfs_remove_dir+0x51/0x80
	 kobject_del+0x18/0x50
	 __kmem_cache_shutdown+0x3e6/0x460
	 kmem_cache_destroy+0x1fb/0x2d0
	 kvm_exit+0x2d/0x80 [kvm]
	 vmx_exit+0x19/0xa1b [kvm_intel]
	 SyS_delete_module+0x198/0x1f0
	 entry_SYSCALL_64_fastpath+0x1f/0xc2

  other info that might help us debug this:

   Possible unsafe locking scenario:

	 CPU0                    CPU1
	 ----                    ----
    lock(slab_mutex);
				 lock(s_active#120);
				 lock(slab_mutex);
    lock(s_active#120);

   *** DEADLOCK ***

  2 locks held by rmmod/1211:
   #0:  (cpu_hotplug.dep_map){++++++}, at: [<ffffffff810a7877>] get_online_cpus+0x37/0x80
   #1:  (slab_mutex){+.+.+.}, at: [<ffffffff8120f691>] kmem_cache_destroy+0x41/0x2d0

  stack backtrace:
  CPU: 3 PID: 1211 Comm: rmmod Not tainted 4.10.0-test+ #48
  Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v02.05 05/07/2012
  Call Trace:
   print_circular_bug+0x1be/0x210
   __lock_acquire+0x10ed/0x1260
   lock_acquire+0xf6/0x1f0
   __kernfs_remove+0x254/0x320
   kernfs_remove+0x23/0x40
   sysfs_remove_dir+0x51/0x80
   kobject_del+0x18/0x50
   __kmem_cache_shutdown+0x3e6/0x460
   kmem_cache_destroy+0x1fb/0x2d0
   kvm_exit+0x2d/0x80 [kvm]
   vmx_exit+0x19/0xa1b [kvm_intel]
   SyS_delete_module+0x198/0x1f0
   ? SyS_delete_module+0x5/0x1f0
   entry_SYSCALL_64_fastpath+0x1f/0xc2

It'd be the cleanest to deal with the issue by removing sysfs files
without holding slab_mutex before the rest of shutdown; however, given
the current code structure, it is pretty difficult to do so.

This patch punts sysfs file removal to a work item.  Before commit
bf5eb3de38, the removal was punted to a RCU delayed work item which is
executed after release.  Now, we're punting to a different work item on
shutdown which still maintains the goal removing the sysfs files earlier
when destroying kmem_caches.

Link: http://lkml.kernel.org/r/20170620204512.GI21326@htj.duckdns.org
Fixes: bf5eb3de38 ("slub: separate out sysfs_slab_release() from sysfs_slab_remove()")
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-23 16:15:55 -07:00

141 lines
4.5 KiB
C

#ifndef _LINUX_SLUB_DEF_H
#define _LINUX_SLUB_DEF_H
/*
* SLUB : A Slab allocator without object queues.
*
* (C) 2007 SGI, Christoph Lameter
*/
#include <linux/kobject.h>
enum stat_item {
ALLOC_FASTPATH, /* Allocation from cpu slab */
ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */
FREE_FASTPATH, /* Free to cpu slab */
FREE_SLOWPATH, /* Freeing not to cpu slab */
FREE_FROZEN, /* Freeing to frozen slab */
FREE_ADD_PARTIAL, /* Freeing moves slab to partial list */
FREE_REMOVE_PARTIAL, /* Freeing removes last object */
ALLOC_FROM_PARTIAL, /* Cpu slab acquired from node partial list */
ALLOC_SLAB, /* Cpu slab acquired from page allocator */
ALLOC_REFILL, /* Refill cpu slab from slab freelist */
ALLOC_NODE_MISMATCH, /* Switching cpu slab */
FREE_SLAB, /* Slab freed to the page allocator */
CPUSLAB_FLUSH, /* Abandoning of the cpu slab */
DEACTIVATE_FULL, /* Cpu slab was full when deactivated */
DEACTIVATE_EMPTY, /* Cpu slab was empty when deactivated */
DEACTIVATE_TO_HEAD, /* Cpu slab was moved to the head of partials */
DEACTIVATE_TO_TAIL, /* Cpu slab was moved to the tail of partials */
DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
DEACTIVATE_BYPASS, /* Implicit deactivation */
ORDER_FALLBACK, /* Number of times fallback was necessary */
CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
CMPXCHG_DOUBLE_FAIL, /* Number of times that cmpxchg double did not match */
CPU_PARTIAL_ALLOC, /* Used cpu partial on alloc */
CPU_PARTIAL_FREE, /* Refill cpu partial on free */
CPU_PARTIAL_NODE, /* Refill cpu partial from node partial */
CPU_PARTIAL_DRAIN, /* Drain cpu partial to node partial */
NR_SLUB_STAT_ITEMS };
struct kmem_cache_cpu {
void **freelist; /* Pointer to next available object */
unsigned long tid; /* Globally unique transaction id */
struct page *page; /* The slab from which we are allocating */
struct page *partial; /* Partially allocated frozen slabs */
#ifdef CONFIG_SLUB_STATS
unsigned stat[NR_SLUB_STAT_ITEMS];
#endif
};
/*
* Word size structure that can be atomically updated or read and that
* contains both the order and the number of objects that a slab of the
* given order would contain.
*/
struct kmem_cache_order_objects {
unsigned long x;
};
/*
* Slab cache management.
*/
struct kmem_cache {
struct kmem_cache_cpu __percpu *cpu_slab;
/* Used for retriving partial slabs etc */
unsigned long flags;
unsigned long min_partial;
int size; /* The size of an object including meta data */
int object_size; /* The size of an object without meta data */
int offset; /* Free pointer offset. */
int cpu_partial; /* Number of per cpu partial objects to keep around */
struct kmem_cache_order_objects oo;
/* Allocation and freeing of slabs */
struct kmem_cache_order_objects max;
struct kmem_cache_order_objects min;
gfp_t allocflags; /* gfp flags to use on each alloc */
int refcount; /* Refcount for slab cache destroy */
void (*ctor)(void *);
int inuse; /* Offset to metadata */
int align; /* Alignment */
int reserved; /* Reserved bytes at the end of slabs */
const char *name; /* Name (only for display!) */
struct list_head list; /* List of slab caches */
int red_left_pad; /* Left redzone padding size */
#ifdef CONFIG_SYSFS
struct kobject kobj; /* For sysfs */
struct work_struct kobj_remove_work;
#endif
#ifdef CONFIG_MEMCG
struct memcg_cache_params memcg_params;
int max_attr_size; /* for propagation, maximum size of a stored attr */
#ifdef CONFIG_SYSFS
struct kset *memcg_kset;
#endif
#endif
#ifdef CONFIG_NUMA
/*
* Defragmentation by allocating from a remote node.
*/
int remote_node_defrag_ratio;
#endif
#ifdef CONFIG_SLAB_FREELIST_RANDOM
unsigned int *random_seq;
#endif
#ifdef CONFIG_KASAN
struct kasan_cache kasan_info;
#endif
struct kmem_cache_node *node[MAX_NUMNODES];
};
#ifdef CONFIG_SYSFS
#define SLAB_SUPPORTS_SYSFS
void sysfs_slab_release(struct kmem_cache *);
#else
static inline void sysfs_slab_release(struct kmem_cache *s)
{
}
#endif
void object_err(struct kmem_cache *s, struct page *page,
u8 *object, char *reason);
void *fixup_red_left(struct kmem_cache *s, void *p);
static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
void *x) {
void *object = x - (x - page_address(page)) % cache->size;
void *last_object = page_address(page) +
(page->objects - 1) * cache->size;
void *result = (unlikely(object > last_object)) ? last_object : object;
result = fixup_red_left(cache, result);
return result;
}
#endif /* _LINUX_SLUB_DEF_H */