linux-stable/include/linux/slub_def.h
Thomas Garnier 210e7a43fa mm: SLUB freelist randomization
Implements freelist randomization for the SLUB allocator.  It was
previous implemented for the SLAB allocator.  Both use the same
configuration option (CONFIG_SLAB_FREELIST_RANDOM).

The list is randomized during initialization of a new set of pages.  The
order on different freelist sizes is pre-computed at boot for
performance.  Each kmem_cache has its own randomized freelist.

This security feature reduces the predictability of the kernel SLUB
allocator against heap overflows rendering attacks much less stable.

For example these attacks exploit the predictability of the heap:
 - Linux Kernel CAN SLUB overflow (https://goo.gl/oMNWkU)
 - Exploiting Linux Kernel Heap corruptions (http://goo.gl/EXLn95)

Performance results:

slab_test impact is between 3% to 4% on average for 100000 attempts
without smp.  It is a very focused testing, kernbench show the overall
impact on the system is way lower.

Before:

  Single thread testing
  =====================
  1. Kmalloc: Repeatedly allocate then free test
  100000 times kmalloc(8) -> 49 cycles kfree -> 77 cycles
  100000 times kmalloc(16) -> 51 cycles kfree -> 79 cycles
  100000 times kmalloc(32) -> 53 cycles kfree -> 83 cycles
  100000 times kmalloc(64) -> 62 cycles kfree -> 90 cycles
  100000 times kmalloc(128) -> 81 cycles kfree -> 97 cycles
  100000 times kmalloc(256) -> 98 cycles kfree -> 121 cycles
  100000 times kmalloc(512) -> 95 cycles kfree -> 122 cycles
  100000 times kmalloc(1024) -> 96 cycles kfree -> 126 cycles
  100000 times kmalloc(2048) -> 115 cycles kfree -> 140 cycles
  100000 times kmalloc(4096) -> 149 cycles kfree -> 171 cycles
  2. Kmalloc: alloc/free test
  100000 times kmalloc(8)/kfree -> 70 cycles
  100000 times kmalloc(16)/kfree -> 70 cycles
  100000 times kmalloc(32)/kfree -> 70 cycles
  100000 times kmalloc(64)/kfree -> 70 cycles
  100000 times kmalloc(128)/kfree -> 70 cycles
  100000 times kmalloc(256)/kfree -> 69 cycles
  100000 times kmalloc(512)/kfree -> 70 cycles
  100000 times kmalloc(1024)/kfree -> 73 cycles
  100000 times kmalloc(2048)/kfree -> 72 cycles
  100000 times kmalloc(4096)/kfree -> 71 cycles

After:

  Single thread testing
  =====================
  1. Kmalloc: Repeatedly allocate then free test
  100000 times kmalloc(8) -> 57 cycles kfree -> 78 cycles
  100000 times kmalloc(16) -> 61 cycles kfree -> 81 cycles
  100000 times kmalloc(32) -> 76 cycles kfree -> 93 cycles
  100000 times kmalloc(64) -> 83 cycles kfree -> 94 cycles
  100000 times kmalloc(128) -> 106 cycles kfree -> 107 cycles
  100000 times kmalloc(256) -> 118 cycles kfree -> 117 cycles
  100000 times kmalloc(512) -> 114 cycles kfree -> 116 cycles
  100000 times kmalloc(1024) -> 115 cycles kfree -> 118 cycles
  100000 times kmalloc(2048) -> 147 cycles kfree -> 131 cycles
  100000 times kmalloc(4096) -> 214 cycles kfree -> 161 cycles
  2. Kmalloc: alloc/free test
  100000 times kmalloc(8)/kfree -> 66 cycles
  100000 times kmalloc(16)/kfree -> 66 cycles
  100000 times kmalloc(32)/kfree -> 66 cycles
  100000 times kmalloc(64)/kfree -> 66 cycles
  100000 times kmalloc(128)/kfree -> 65 cycles
  100000 times kmalloc(256)/kfree -> 67 cycles
  100000 times kmalloc(512)/kfree -> 67 cycles
  100000 times kmalloc(1024)/kfree -> 64 cycles
  100000 times kmalloc(2048)/kfree -> 67 cycles
  100000 times kmalloc(4096)/kfree -> 67 cycles

Kernbench, before:

  Average Optimal load -j 12 Run (std deviation):
  Elapsed Time 101.873 (1.16069)
  User Time 1045.22 (1.60447)
  System Time 88.969 (0.559195)
  Percent CPU 1112.9 (13.8279)
  Context Switches 189140 (2282.15)
  Sleeps 99008.6 (768.091)

After:

  Average Optimal load -j 12 Run (std deviation):
  Elapsed Time 102.47 (0.562732)
  User Time 1045.3 (1.34263)
  System Time 88.311 (0.342554)
  Percent CPU 1105.8 (6.49444)
  Context Switches 189081 (2355.78)
  Sleeps 99231.5 (800.358)

Link: http://lkml.kernel.org/r/1464295031-26375-3-git-send-email-thgarnie@google.com
Signed-off-by: Thomas Garnier <thgarnie@google.com>
Reviewed-by: Kees Cook <keescook@chromium.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>
2016-07-26 16:19:19 -07:00

133 lines
4.3 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 */
#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
struct kmem_cache_node *node[MAX_NUMNODES];
};
#ifdef CONFIG_SYSFS
#define SLAB_SUPPORTS_SYSFS
void sysfs_slab_remove(struct kmem_cache *);
#else
static inline void sysfs_slab_remove(struct kmem_cache *s)
{
}
#endif
void object_err(struct kmem_cache *s, struct page *page,
u8 *object, char *reason);
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;
if (unlikely(object > last_object))
return last_object;
else
return object;
}
#endif /* _LINUX_SLUB_DEF_H */