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/cache_maint.c | 138 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 138 insertions(+) create mode 100644 lib/cache_maint.c (limited to 'lib/cache_maint.c') diff --git a/lib/cache_maint.c b/lib/cache_maint.c new file mode 100644 index 000000000..9256a9ffc --- /dev/null +++ b/lib/cache_maint.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generic support for Memory System Cache Maintenance operations. + * + * Coherency maintenance drivers register with this simple framework that will + * iterate over each registered instance to first kick off invalidation and + * then to wait until it is complete. + * + * If no implementations are registered yet cpu_cache_has_invalidate_memregion() + * will return false. If this runs concurrently with unregistration then a + * race exists but this is no worse than the case where the operations instance + * responsible for a given memory region has not yet registered. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static LIST_HEAD(cache_ops_instance_list); +static DECLARE_RWSEM(cache_ops_instance_list_lock); + +static void __cache_coherency_ops_instance_free(struct kref *kref) +{ + struct cache_coherency_ops_inst *cci = + container_of(kref, struct cache_coherency_ops_inst, kref); + kfree(cci); +} + +void cache_coherency_ops_instance_put(struct cache_coherency_ops_inst *cci) +{ + kref_put(&cci->kref, __cache_coherency_ops_instance_free); +} +EXPORT_SYMBOL_GPL(cache_coherency_ops_instance_put); + +static int cache_inval_one(struct cache_coherency_ops_inst *cci, void *data) +{ + if (!cci->ops) + return -EINVAL; + + return cci->ops->wbinv(cci, data); +} + +static int cache_inval_done_one(struct cache_coherency_ops_inst *cci) +{ + if (!cci->ops) + return -EINVAL; + + if (!cci->ops->done) + return 0; + + return cci->ops->done(cci); +} + +static int cache_invalidate_memregion(phys_addr_t addr, size_t size) +{ + int ret; + struct cache_coherency_ops_inst *cci; + struct cc_inval_params params = { + .addr = addr, + .size = size, + }; + + guard(rwsem_read)(&cache_ops_instance_list_lock); + list_for_each_entry(cci, &cache_ops_instance_list, node) { + ret = cache_inval_one(cci, ¶ms); + if (ret) + return ret; + } + list_for_each_entry(cci, &cache_ops_instance_list, node) { + ret = cache_inval_done_one(cci); + if (ret) + return ret; + } + + return 0; +} + +struct cache_coherency_ops_inst * +_cache_coherency_ops_instance_alloc(const struct cache_coherency_ops *ops, + size_t size) +{ + struct cache_coherency_ops_inst *cci; + + if (!ops || !ops->wbinv) + return NULL; + + cci = kzalloc(size, GFP_KERNEL); + if (!cci) + return NULL; + + cci->ops = ops; + INIT_LIST_HEAD(&cci->node); + kref_init(&cci->kref); + + return cci; +} +EXPORT_SYMBOL_NS_GPL(_cache_coherency_ops_instance_alloc, "CACHE_COHERENCY"); + +int cache_coherency_ops_instance_register(struct cache_coherency_ops_inst *cci) +{ + guard(rwsem_write)(&cache_ops_instance_list_lock); + list_add(&cci->node, &cache_ops_instance_list); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cache_coherency_ops_instance_register, "CACHE_COHERENCY"); + +void cache_coherency_ops_instance_unregister(struct cache_coherency_ops_inst *cci) +{ + guard(rwsem_write)(&cache_ops_instance_list_lock); + list_del(&cci->node); +} +EXPORT_SYMBOL_NS_GPL(cache_coherency_ops_instance_unregister, "CACHE_COHERENCY"); + +int cpu_cache_invalidate_memregion(phys_addr_t start, size_t len) +{ + return cache_invalidate_memregion(start, len); +} +EXPORT_SYMBOL_NS_GPL(cpu_cache_invalidate_memregion, "DEVMEM"); + +/* + * Used for optimization / debug purposes only as removal can race + * + * Machines that do not support invalidation, e.g. VMs, will not have any + * operations instance to register and so this will always return false. + */ +bool cpu_cache_has_invalidate_memregion(void) +{ + guard(rwsem_read)(&cache_ops_instance_list_lock); + return !list_empty(&cache_ops_instance_list); +} +EXPORT_SYMBOL_NS_GPL(cpu_cache_has_invalidate_memregion, "DEVMEM"); -- cgit v1.3.1