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 --- Documentation/ABI/testing/devlink-resource-mlxsw | 33 ++++++++++++++++++++++++ 1 file changed, 33 insertions(+) create mode 100644 Documentation/ABI/testing/devlink-resource-mlxsw (limited to 'Documentation/ABI/testing/devlink-resource-mlxsw') diff --git a/Documentation/ABI/testing/devlink-resource-mlxsw b/Documentation/ABI/testing/devlink-resource-mlxsw new file mode 100644 index 000000000..259ed2948 --- /dev/null +++ b/Documentation/ABI/testing/devlink-resource-mlxsw @@ -0,0 +1,33 @@ +What: /kvd/ +Date: 08-Jan-2018 +KernelVersion: v4.16 +Contact: mlxsw@mellanox.com +Description: The main database in the Spectrum device is a centralized + KVD database used for many of the tables used to configure + the chip including L2 FDB, L3 LPM, ECMP and more. The KVD + is divided into two sections, the first is hash-based table + and the second is a linear access table. The division + between the linear and hash-based sections is static and + require reload before the changes take effect. + +What: /kvd/linear +Date: 08-Jan-2018 +KernelVersion: v4.16 +Contact: mlxsw@mellanox.com +Description: The linear section of the KVD is managed by software as a + flat memory accessed using an index. + +What: /kvd/hash_single +Date: 08-Jan-2018 +KernelVersion: v4.16 +Contact: mlxsw@mellanox.com +Description: The hash based section of the KVD is managed by the switch + device. Used in case the key size is smaller or equal to + 64bit. + +What: /kvd/hash_double +Date: 08-Jan-2018 +KernelVersion: v4.16 +Contact: mlxsw@mellanox.com +Description: The hash based section of the KVD is managed by the switch + device. Used in case the key is larger than 64 bit. -- cgit v1.3.1