mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-05 02:19:51 +00:00
c7ce4f60ac
Provides an optional config (CONFIG_SLAB_FREELIST_RANDOM) to randomize the SLAB freelist. 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. Before pre-computed lists are available freelists are generated dynamically. This security feature reduces the predictability of the kernel SLAB allocator against heap overflows rendering attacks much less stable. For example this attack against SLUB (also applicable against SLAB) would be affected: https://jon.oberheide.org/blog/2010/09/10/linux-kernel-can-slub-overflow/ Also, since v4.6 the freelist was moved at the end of the SLAB. It means a controllable heap is opened to new attacks not yet publicly discussed. A kernel heap overflow can be transformed to multiple use-after-free. This feature makes this type of attack harder too. To generate entropy, we use get_random_bytes_arch because 0 bits of entropy is available in the boot stage. In the worse case this function will fallback to the get_random_bytes sub API. We also generate a shift random number to shift pre-computed freelist for each new set of pages. The config option name is not specific to the SLAB as this approach will be extended to other allocators like SLUB. Performance results highlighted no major changes: Hackbench (running 90 10 times): Before average: 0.0698 After average: 0.0663 (-5.01%) slab_test 1 run on boot. Difference only seen on the 2048 size test being the worse case scenario covered by freelist randomization. New slab pages are constantly being created on the 10000 allocations. Variance should be mainly due to getting new pages every few allocations. Before: Single thread testing ===================== 1. Kmalloc: Repeatedly allocate then free test 10000 times kmalloc(8) -> 99 cycles kfree -> 112 cycles 10000 times kmalloc(16) -> 109 cycles kfree -> 140 cycles 10000 times kmalloc(32) -> 129 cycles kfree -> 137 cycles 10000 times kmalloc(64) -> 141 cycles kfree -> 141 cycles 10000 times kmalloc(128) -> 152 cycles kfree -> 148 cycles 10000 times kmalloc(256) -> 195 cycles kfree -> 167 cycles 10000 times kmalloc(512) -> 257 cycles kfree -> 199 cycles 10000 times kmalloc(1024) -> 393 cycles kfree -> 251 cycles 10000 times kmalloc(2048) -> 649 cycles kfree -> 228 cycles 10000 times kmalloc(4096) -> 806 cycles kfree -> 370 cycles 10000 times kmalloc(8192) -> 814 cycles kfree -> 411 cycles 10000 times kmalloc(16384) -> 892 cycles kfree -> 455 cycles 2. Kmalloc: alloc/free test 10000 times kmalloc(8)/kfree -> 121 cycles 10000 times kmalloc(16)/kfree -> 121 cycles 10000 times kmalloc(32)/kfree -> 121 cycles 10000 times kmalloc(64)/kfree -> 121 cycles 10000 times kmalloc(128)/kfree -> 121 cycles 10000 times kmalloc(256)/kfree -> 119 cycles 10000 times kmalloc(512)/kfree -> 119 cycles 10000 times kmalloc(1024)/kfree -> 119 cycles 10000 times kmalloc(2048)/kfree -> 119 cycles 10000 times kmalloc(4096)/kfree -> 121 cycles 10000 times kmalloc(8192)/kfree -> 119 cycles 10000 times kmalloc(16384)/kfree -> 119 cycles After: Single thread testing ===================== 1. Kmalloc: Repeatedly allocate then free test 10000 times kmalloc(8) -> 130 cycles kfree -> 86 cycles 10000 times kmalloc(16) -> 118 cycles kfree -> 86 cycles 10000 times kmalloc(32) -> 121 cycles kfree -> 85 cycles 10000 times kmalloc(64) -> 176 cycles kfree -> 102 cycles 10000 times kmalloc(128) -> 178 cycles kfree -> 100 cycles 10000 times kmalloc(256) -> 205 cycles kfree -> 109 cycles 10000 times kmalloc(512) -> 262 cycles kfree -> 136 cycles 10000 times kmalloc(1024) -> 342 cycles kfree -> 157 cycles 10000 times kmalloc(2048) -> 701 cycles kfree -> 238 cycles 10000 times kmalloc(4096) -> 803 cycles kfree -> 364 cycles 10000 times kmalloc(8192) -> 835 cycles kfree -> 404 cycles 10000 times kmalloc(16384) -> 896 cycles kfree -> 441 cycles 2. Kmalloc: alloc/free test 10000 times kmalloc(8)/kfree -> 121 cycles 10000 times kmalloc(16)/kfree -> 121 cycles 10000 times kmalloc(32)/kfree -> 123 cycles 10000 times kmalloc(64)/kfree -> 142 cycles 10000 times kmalloc(128)/kfree -> 121 cycles 10000 times kmalloc(256)/kfree -> 119 cycles 10000 times kmalloc(512)/kfree -> 119 cycles 10000 times kmalloc(1024)/kfree -> 119 cycles 10000 times kmalloc(2048)/kfree -> 119 cycles 10000 times kmalloc(4096)/kfree -> 119 cycles 10000 times kmalloc(8192)/kfree -> 119 cycles 10000 times kmalloc(16384)/kfree -> 119 cycles [akpm@linux-foundation.org: propagate gfp_t into cache_random_seq_create()] Signed-off-by: Thomas Garnier <thgarnie@google.com> Acked-by: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Kees Cook <keescook@chromium.org> Cc: Greg Thelen <gthelen@google.com> Cc: Laura Abbott <labbott@fedoraproject.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
101 lines
2.3 KiB
C
101 lines
2.3 KiB
C
#ifndef _LINUX_SLAB_DEF_H
|
|
#define _LINUX_SLAB_DEF_H
|
|
|
|
#include <linux/reciprocal_div.h>
|
|
|
|
/*
|
|
* Definitions unique to the original Linux SLAB allocator.
|
|
*/
|
|
|
|
struct kmem_cache {
|
|
struct array_cache __percpu *cpu_cache;
|
|
|
|
/* 1) Cache tunables. Protected by slab_mutex */
|
|
unsigned int batchcount;
|
|
unsigned int limit;
|
|
unsigned int shared;
|
|
|
|
unsigned int size;
|
|
struct reciprocal_value reciprocal_buffer_size;
|
|
/* 2) touched by every alloc & free from the backend */
|
|
|
|
unsigned int flags; /* constant flags */
|
|
unsigned int num; /* # of objs per slab */
|
|
|
|
/* 3) cache_grow/shrink */
|
|
/* order of pgs per slab (2^n) */
|
|
unsigned int gfporder;
|
|
|
|
/* force GFP flags, e.g. GFP_DMA */
|
|
gfp_t allocflags;
|
|
|
|
size_t colour; /* cache colouring range */
|
|
unsigned int colour_off; /* colour offset */
|
|
struct kmem_cache *freelist_cache;
|
|
unsigned int freelist_size;
|
|
|
|
/* constructor func */
|
|
void (*ctor)(void *obj);
|
|
|
|
/* 4) cache creation/removal */
|
|
const char *name;
|
|
struct list_head list;
|
|
int refcount;
|
|
int object_size;
|
|
int align;
|
|
|
|
/* 5) statistics */
|
|
#ifdef CONFIG_DEBUG_SLAB
|
|
unsigned long num_active;
|
|
unsigned long num_allocations;
|
|
unsigned long high_mark;
|
|
unsigned long grown;
|
|
unsigned long reaped;
|
|
unsigned long errors;
|
|
unsigned long max_freeable;
|
|
unsigned long node_allocs;
|
|
unsigned long node_frees;
|
|
unsigned long node_overflow;
|
|
atomic_t allochit;
|
|
atomic_t allocmiss;
|
|
atomic_t freehit;
|
|
atomic_t freemiss;
|
|
#ifdef CONFIG_DEBUG_SLAB_LEAK
|
|
atomic_t store_user_clean;
|
|
#endif
|
|
|
|
/*
|
|
* If debugging is enabled, then the allocator can add additional
|
|
* fields and/or padding to every object. size contains the total
|
|
* object size including these internal fields, the following two
|
|
* variables contain the offset to the user object and its size.
|
|
*/
|
|
int obj_offset;
|
|
#endif /* CONFIG_DEBUG_SLAB */
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
struct memcg_cache_params memcg_params;
|
|
#endif
|
|
#ifdef CONFIG_KASAN
|
|
struct kasan_cache kasan_info;
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLAB_FREELIST_RANDOM
|
|
void *random_seq;
|
|
#endif
|
|
|
|
struct kmem_cache_node *node[MAX_NUMNODES];
|
|
};
|
|
|
|
static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
|
|
void *x) {
|
|
void *object = x - (x - page->s_mem) % cache->size;
|
|
void *last_object = page->s_mem + (cache->num - 1) * cache->size;
|
|
|
|
if (unlikely(object > last_object))
|
|
return last_object;
|
|
else
|
|
return object;
|
|
}
|
|
|
|
#endif /* _LINUX_SLAB_DEF_H */
|