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 --- include/uapi/asm-generic/poll.h | 42 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) create mode 100644 include/uapi/asm-generic/poll.h (limited to 'include/uapi/asm-generic/poll.h') diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h new file mode 100644 index 000000000..f9c520ce4 --- /dev/null +++ b/include/uapi/asm-generic/poll.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_POLL_H +#define __ASM_GENERIC_POLL_H + +/* These are specified by iBCS2 */ +#define POLLIN 0x0001 +#define POLLPRI 0x0002 +#define POLLOUT 0x0004 +#define POLLERR 0x0008 +#define POLLHUP 0x0010 +#define POLLNVAL 0x0020 + +/* The rest seem to be more-or-less nonstandard. Check them! */ +#define POLLRDNORM 0x0040 +#define POLLRDBAND 0x0080 +#ifndef POLLWRNORM +#define POLLWRNORM 0x0100 +#endif +#ifndef POLLWRBAND +#define POLLWRBAND 0x0200 +#endif +#ifndef POLLMSG +#define POLLMSG 0x0400 +#endif +#ifndef POLLREMOVE +#define POLLREMOVE 0x1000 +#endif +#ifndef POLLRDHUP +#define POLLRDHUP 0x2000 +#endif + +#define POLLFREE (__force __poll_t)0x4000 + +#define POLL_BUSY_LOOP (__force __poll_t)0x8000 + +struct pollfd { + int fd; + short events; + short revents; +}; + +#endif /* __ASM_GENERIC_POLL_H */ -- cgit v1.3.1