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, 20 insertions, 3 deletions

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 848c7c82ad5a..8228d1276a2f 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -19,6 +19,7 @@
 #include <linux/workqueue.h>
 #include <linux/percpu-refcount.h>
 #include <linux/cleanup.h>
+#include <linux/hash.h>
 
 
 /*
@@ -345,6 +346,12 @@ static inline unsigned int arch_slab_minalign(void)
 #define SLAB_OBJ_MIN_SIZE      (KMALLOC_MIN_SIZE < 16 ? \
                                (KMALLOC_MIN_SIZE) : 16)
 
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+#define RANDOM_KMALLOC_CACHES_NR	15 // # of cache copies
+#else
+#define RANDOM_KMALLOC_CACHES_NR	0
+#endif
+
 /*
  * Whenever changing this, take care of that kmalloc_type() and
  * create_kmalloc_caches() still work as intended.
@@ -361,6 +368,8 @@ enum kmalloc_cache_type {
 #ifndef CONFIG_MEMCG_KMEM
 	KMALLOC_CGROUP = KMALLOC_NORMAL,
 #endif
+	KMALLOC_RANDOM_START = KMALLOC_NORMAL,
+	KMALLOC_RANDOM_END = KMALLOC_RANDOM_START + RANDOM_KMALLOC_CACHES_NR,
 #ifdef CONFIG_SLUB_TINY
 	KMALLOC_RECLAIM = KMALLOC_NORMAL,
 #else
@@ -386,14 +395,22 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1];
 	(IS_ENABLED(CONFIG_ZONE_DMA)   ? __GFP_DMA : 0) |	\
 	(IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0))
 
-static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags)
+extern unsigned long random_kmalloc_seed;
+
+static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigned long caller)
 {
 	/*
 	 * The most common case is KMALLOC_NORMAL, so test for it
 	 * with a single branch for all the relevant flags.
 	 */
 	if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0))
+#ifdef CONFIG_RANDOM_KMALLOC_CACHES
+		/* RANDOM_KMALLOC_CACHES_NR (=15) copies + the KMALLOC_NORMAL */
+		return KMALLOC_RANDOM_START + hash_64(caller ^ random_kmalloc_seed,
+						      ilog2(RANDOM_KMALLOC_CACHES_NR + 1));
+#else
 		return KMALLOC_NORMAL;
+#endif
 
 	/*
 	 * At least one of the flags has to be set. Their priorities in
@@ -580,7 +597,7 @@ static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags)
 
 		index = kmalloc_index(size);
 		return kmalloc_trace(
-				kmalloc_caches[kmalloc_type(flags)][index],
+				kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index],
 				flags, size);
 	}
 	return __kmalloc(size, flags);
@@ -596,7 +613,7 @@ static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t fla
 
 		index = kmalloc_index(size);
 		return kmalloc_node_trace(
-				kmalloc_caches[kmalloc_type(flags)][index],
+				kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index],
 				flags, node, size);
 	}
 	return __kmalloc_node(size, flags, node);