From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions When using eBPF to probe CS CALL instructions within a function, a crash can be triggered. The eBPF tool probes offset 257 of the __hrtimer_run_queues() function: <__hrtimer_run_queues+249>: nopl 0x0(%rax,%rax,1) <__hrtimer_run_queues+254>: mov %r14,%rdi <__hrtimer_run_queues+257>: cs call <__x86_indirect_thunk_r12> <__hrtimer_run_queues+263>: mov %eax,%r12d <__hrtimer_run_queues+266>: xchg %ax,%ax <__hrtimer_run_queues+268>: mov %r13,%rdi Which triggers this crash: BUG: unable to handle page fault for address: 00000000000f41c9 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP NOPTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P RIP: 0010:__hrtimer_run_queues+0x106/0x230 Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is at the 6th byte of the above CS CALL instruction. Since the CS CALL instruction occupies 6 bytes, the exception occurred in the middle of that call instruction. The root cause is that when using eBPF tools to probe in the middle of a function, a kprobe with INT3 is used as the underlying implementation. During single-step emulation of the original CALL instruction, int3_emulate_call() assumes that the probed CALL instruction is 5 bytes long. However, the actual CS-prefixed CALL instruction occupies 6 bytes, so it constructs an incorrect exception return address. When the CPU returns from the kprobe handler, the next instruction to be executed is at the address of the last byte of that CS CALL instruction. Coincidentally, starting from that address, the CPU fetches and decodes a completely different instruction, which ultimately triggers a kernel crash. Fix the issue by using the actual instruction length obtained from the instruction decoder when constructing the exception return address, rather than relying on the hardcoded CALL_INSN_SIZE macro. [ mingo: Refined the changelog ] Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step") Suggested-by: Masami Hiramatsu (Google) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- lib/sg_pool.c | 180 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 180 insertions(+) create mode 100644 lib/sg_pool.c (limited to 'lib/sg_pool.c') diff --git a/lib/sg_pool.c b/lib/sg_pool.c new file mode 100644 index 000000000..9bfe60ca3 --- /dev/null +++ b/lib/sg_pool.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include + +#define SG_MEMPOOL_NR ARRAY_SIZE(sg_pools) +#define SG_MEMPOOL_SIZE 2 + +struct sg_pool { + size_t size; + char *name; + struct kmem_cache *slab; + mempool_t *pool; +}; + +#define SP(x) { .size = x, "sgpool-" __stringify(x) } +#if (SG_CHUNK_SIZE < 32) +#error SG_CHUNK_SIZE is too small (must be 32 or greater) +#endif +static struct sg_pool sg_pools[] = { + SP(8), + SP(16), +#if (SG_CHUNK_SIZE > 32) + SP(32), +#if (SG_CHUNK_SIZE > 64) + SP(64), +#if (SG_CHUNK_SIZE > 128) + SP(128), +#if (SG_CHUNK_SIZE > 256) +#error SG_CHUNK_SIZE is too large (256 MAX) +#endif +#endif +#endif +#endif + SP(SG_CHUNK_SIZE) +}; +#undef SP + +static inline unsigned int sg_pool_index(unsigned short nents) +{ + unsigned int index; + + BUG_ON(nents > SG_CHUNK_SIZE); + + if (nents <= 8) + index = 0; + else + index = get_count_order(nents) - 3; + + return index; +} + +static void sg_pool_free(struct scatterlist *sgl, unsigned int nents) +{ + struct sg_pool *sgp; + + sgp = sg_pools + sg_pool_index(nents); + mempool_free(sgl, sgp->pool); +} + +static struct scatterlist *sg_pool_alloc(unsigned int nents, gfp_t gfp_mask) +{ + struct sg_pool *sgp; + + sgp = sg_pools + sg_pool_index(nents); + return mempool_alloc(sgp->pool, gfp_mask); +} + +/** + * sg_free_table_chained - Free a previously mapped sg table + * @table: The sg table header to use + * @nents_first_chunk: size of the first_chunk SGL passed to + * sg_alloc_table_chained + * + * Description: + * Free an sg table previously allocated and setup with + * sg_alloc_table_chained(). + * + * @nents_first_chunk has to be same with that same parameter passed + * to sg_alloc_table_chained(). + * + **/ +void sg_free_table_chained(struct sg_table *table, + unsigned nents_first_chunk) +{ + if (table->orig_nents <= nents_first_chunk) + return; + + if (nents_first_chunk == 1) + nents_first_chunk = 0; + + __sg_free_table(table, SG_CHUNK_SIZE, nents_first_chunk, sg_pool_free, + table->orig_nents); +} +EXPORT_SYMBOL_GPL(sg_free_table_chained); + +/** + * sg_alloc_table_chained - Allocate and chain SGLs in an sg table + * @table: The sg table header to use + * @nents: Number of entries in sg list + * @first_chunk: first SGL + * @nents_first_chunk: number of the SGL of @first_chunk + * + * Description: + * Allocate and chain SGLs in an sg table. If @nents@ is larger than + * @nents_first_chunk a chained sg table will be setup. @first_chunk is + * ignored if nents_first_chunk <= 1 because user expects the SGL points + * non-chain SGL. + * + **/ +int sg_alloc_table_chained(struct sg_table *table, int nents, + struct scatterlist *first_chunk, unsigned nents_first_chunk) +{ + int ret; + + BUG_ON(!nents); + + if (first_chunk && nents_first_chunk) { + if (nents <= nents_first_chunk) { + table->nents = table->orig_nents = nents; + sg_init_table(table->sgl, nents); + return 0; + } + } + + /* User supposes that the 1st SGL includes real entry */ + if (nents_first_chunk <= 1) { + first_chunk = NULL; + nents_first_chunk = 0; + } + + ret = __sg_alloc_table(table, nents, SG_CHUNK_SIZE, + first_chunk, nents_first_chunk, + GFP_ATOMIC, sg_pool_alloc); + if (unlikely(ret)) + sg_free_table_chained(table, nents_first_chunk); + return ret; +} +EXPORT_SYMBOL_GPL(sg_alloc_table_chained); + +static __init int sg_pool_init(void) +{ + int i; + + for (i = 0; i < SG_MEMPOOL_NR; i++) { + struct sg_pool *sgp = sg_pools + i; + int size = sgp->size * sizeof(struct scatterlist); + + sgp->slab = kmem_cache_create(sgp->name, size, 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!sgp->slab) { + printk(KERN_ERR "SG_POOL: can't init sg slab %s\n", + sgp->name); + goto cleanup_sdb; + } + + sgp->pool = mempool_create_slab_pool(SG_MEMPOOL_SIZE, + sgp->slab); + if (!sgp->pool) { + printk(KERN_ERR "SG_POOL: can't init sg mempool %s\n", + sgp->name); + goto cleanup_sdb; + } + } + + return 0; + +cleanup_sdb: + for (i = 0; i < SG_MEMPOOL_NR; i++) { + struct sg_pool *sgp = sg_pools + i; + + mempool_destroy(sgp->pool); + kmem_cache_destroy(sgp->slab); + } + + return -ENOMEM; +} + +subsys_initcall(sg_pool_init); -- cgit v1.3.1