Randomized slab caches for kmalloc()

When exploiting memory vulnerabilities, "heap spraying" is a common
technique targeting those related to dynamic memory allocation (i.e. the
"heap"), and it plays an important role in a successful exploitation.
Basically, it is to overwrite the memory area of vulnerable object by
triggering allocation in other subsystems or modules and therefore
getting a reference to the targeted memory location. It's usable on
various types of vulnerablity including use after free (UAF), heap out-
of-bound write and etc.

There are (at least) two reasons why the heap can be sprayed: 1) generic
slab caches are shared among different subsystems and modules, and
2) dedicated slab caches could be merged with the generic ones.
Currently these two factors cannot be prevented at a low cost: the first
one is a widely used memory allocation mechanism, and shutting down slab
merging completely via `slub_nomerge` would be overkill.

To efficiently prevent heap spraying, we propose the following approach:
to create multiple copies of generic slab caches that will never be
merged, and random one of them will be used at allocation. The random
selection is based on the address of code that calls `kmalloc()`, which
means it is static at runtime (rather than dynamically determined at
each time of allocation, which could be bypassed by repeatedly spraying
in brute force). In other words, the randomness of cache selection will
be with respect to the code address rather than time, i.e. allocations
in different code paths would most likely pick different caches,
although kmalloc() at each place would use the same cache copy whenever
it is executed. In this way, the vulnerable object and memory allocated
in other subsystems and modules will (most probably) be on different
slab caches, which prevents the object from being sprayed.

Meanwhile, the static random selection is further enhanced with a
per-boot random seed, which prevents the attacker from finding a usable
kmalloc that happens to pick the same cache with the vulnerable
subsystem/module by analyzing the open source code. In other words, with
the per-boot seed, the random selection is static during each time the
system starts and runs, but not across different system startups.

The overhead of performance has been tested on a 40-core x86 server by
comparing the results of `perf bench all` between the kernels with and
without this patch based on the latest linux-next kernel, which shows
minor difference. A subset of benchmarks are listed below:

                sched/  sched/  syscall/       mem/       mem/
             messaging    pipe     basic     memcpy     memset
                 (sec)   (sec)     (sec)   (GB/sec)   (GB/sec)

control1         0.019   5.459     0.733  15.258789  51.398026
control2         0.019   5.439     0.730  16.009221  48.828125
control3         0.019   5.282     0.735  16.009221  48.828125
control_avg      0.019   5.393     0.733  15.759077  49.684759

experiment1      0.019   5.374     0.741  15.500992  46.502976
experiment2      0.019   5.440     0.746  16.276042  51.398026
experiment3      0.019   5.242     0.752  15.258789  51.398026
experiment_avg   0.019   5.352     0.746  15.678608  49.766343

The overhead of memory usage was measured by executing `free` after boot
on a QEMU VM with 1GB total memory, and as expected, it's positively
correlated with # of cache copies:

           control  4 copies  8 copies  16 copies

total       969.8M    968.2M    968.2M     968.2M
used         20.0M     21.9M     24.1M      26.7M
free        936.9M    933.6M    931.4M     928.6M
available   932.2M    928.8M    926.6M     923.9M

Co-developed-by: Xiu Jianfeng <xiujianfeng@huawei.com>
Signed-off-by: Xiu Jianfeng <xiujianfeng@huawei.com>
Signed-off-by: GONG, Ruiqi <gongruiqi@huaweicloud.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Acked-by: Dennis Zhou <dennis@kernel.org> # percpu
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

1 files changed, 44 insertions, 5 deletions

diff --git a/mm/slab_common.c b/mm/slab_common.c
index d1555ea2981a..01cdbf122463 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -678,6 +678,11 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1] __ro_after_init =
 { /* initialization for https://bugs.llvm.org/show_bug.cgi?id=42570 */ };
 EXPORT_SYMBOL(kmalloc_caches);
 
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+unsigned long random_kmalloc_seed __ro_after_init;
+EXPORT_SYMBOL(random_kmalloc_seed);
+#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
@@ -720,7 +725,7 @@ static inline unsigned int size_index_elem(unsigned int bytes)
  * Find the kmem_cache structure that serves a given size of
  * allocation
  */
-struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
+struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags, unsigned long caller)
 {
 	unsigned int index;
 
@@ -735,7 +740,7 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
 		index = fls(size - 1);
 	}
 
-	return kmalloc_caches[kmalloc_type(flags)][index];
+	return kmalloc_caches[kmalloc_type(flags, caller)][index];
 }
 
 size_t kmalloc_size_roundup(size_t size)
@@ -752,8 +757,11 @@ size_t kmalloc_size_roundup(size_t size)
 	if (size > KMALLOC_MAX_CACHE_SIZE)
 		return PAGE_SIZE << get_order(size);
 
-	/* The flags don't matter since size_index is common to all. */
-	c = kmalloc_slab(size, GFP_KERNEL);
+	/*
+	 * The flags don't matter since size_index is common to all.
+	 * Neither does the caller for just getting ->object_size.
+	 */
+	c = kmalloc_slab(size, GFP_KERNEL, 0);
 	return c ? c->object_size : 0;
 }
 EXPORT_SYMBOL(kmalloc_size_roundup);
@@ -776,12 +784,35 @@ EXPORT_SYMBOL(kmalloc_size_roundup);
 #define KMALLOC_RCL_NAME(sz)
 #endif
 
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+#define __KMALLOC_RANDOM_CONCAT(a, b) a ## b
+#define KMALLOC_RANDOM_NAME(N, sz) __KMALLOC_RANDOM_CONCAT(KMA_RAND_, N)(sz)
+#define KMA_RAND_1(sz)                  .name[KMALLOC_RANDOM_START +  1] = "kmalloc-rnd-01-" #sz,
+#define KMA_RAND_2(sz)  KMA_RAND_1(sz)  .name[KMALLOC_RANDOM_START +  2] = "kmalloc-rnd-02-" #sz,
+#define KMA_RAND_3(sz)  KMA_RAND_2(sz)  .name[KMALLOC_RANDOM_START +  3] = "kmalloc-rnd-03-" #sz,
+#define KMA_RAND_4(sz)  KMA_RAND_3(sz)  .name[KMALLOC_RANDOM_START +  4] = "kmalloc-rnd-04-" #sz,
+#define KMA_RAND_5(sz)  KMA_RAND_4(sz)  .name[KMALLOC_RANDOM_START +  5] = "kmalloc-rnd-05-" #sz,
+#define KMA_RAND_6(sz)  KMA_RAND_5(sz)  .name[KMALLOC_RANDOM_START +  6] = "kmalloc-rnd-06-" #sz,
+#define KMA_RAND_7(sz)  KMA_RAND_6(sz)  .name[KMALLOC_RANDOM_START +  7] = "kmalloc-rnd-07-" #sz,
+#define KMA_RAND_8(sz)  KMA_RAND_7(sz)  .name[KMALLOC_RANDOM_START +  8] = "kmalloc-rnd-08-" #sz,
+#define KMA_RAND_9(sz)  KMA_RAND_8(sz)  .name[KMALLOC_RANDOM_START +  9] = "kmalloc-rnd-09-" #sz,
+#define KMA_RAND_10(sz) KMA_RAND_9(sz)  .name[KMALLOC_RANDOM_START + 10] = "kmalloc-rnd-10-" #sz,
+#define KMA_RAND_11(sz) KMA_RAND_10(sz) .name[KMALLOC_RANDOM_START + 11] = "kmalloc-rnd-11-" #sz,
+#define KMA_RAND_12(sz) KMA_RAND_11(sz) .name[KMALLOC_RANDOM_START + 12] = "kmalloc-rnd-12-" #sz,
+#define KMA_RAND_13(sz) KMA_RAND_12(sz) .name[KMALLOC_RANDOM_START + 13] = "kmalloc-rnd-13-" #sz,
+#define KMA_RAND_14(sz) KMA_RAND_13(sz) .name[KMALLOC_RANDOM_START + 14] = "kmalloc-rnd-14-" #sz,
+#define KMA_RAND_15(sz) KMA_RAND_14(sz) .name[KMALLOC_RANDOM_START + 15] = "kmalloc-rnd-15-" #sz,
+#else // CONFIG_RANDOM_KMALLOC_CACHES
+#define KMALLOC_RANDOM_NAME(N, sz)
+#endif
+
 #define INIT_KMALLOC_INFO(__size, __short_size)			\
 {								\
 	.name[KMALLOC_NORMAL]  = "kmalloc-" #__short_size,	\
 	KMALLOC_RCL_NAME(__short_size)				\
 	KMALLOC_CGROUP_NAME(__short_size)			\
 	KMALLOC_DMA_NAME(__short_size)				\
+	KMALLOC_RANDOM_NAME(RANDOM_KMALLOC_CACHES_NR, __short_size)	\
 	.size = __size,						\
 }
 
@@ -890,6 +921,11 @@ new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags)
 		flags |= SLAB_CACHE_DMA;
 	}
 
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+	if (type >= KMALLOC_RANDOM_START && type <= KMALLOC_RANDOM_END)
+		flags |= SLAB_NO_MERGE;
+#endif
+
 	/*
 	 * If CONFIG_MEMCG_KMEM is enabled, disable cache merging for
 	 * KMALLOC_NORMAL caches.
@@ -941,6 +977,9 @@ void __init create_kmalloc_caches(slab_flags_t flags)
 				new_kmalloc_cache(2, type, flags);
 		}
 	}
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+	random_kmalloc_seed = get_random_u64();
+#endif
 
 	/* Kmalloc array is now usable */
 	slab_state = UP;
@@ -976,7 +1015,7 @@ void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller
 		return ret;
 	}
 
-	s = kmalloc_slab(size, flags);
+	s = kmalloc_slab(size, flags, caller);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;