x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

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) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 180 insertions, 0 deletions

diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
new file mode 100644
index 000000000..84ea7b929
--- /dev/null
+++ b/include/uapi/asm-generic/socket.h
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_SOCKET_H
+#define __ASM_GENERIC_SOCKET_H
+
+#include <linux/posix_types.h>
+#include <asm/sockios.h>
+
+/* For setsockopt(2) */
+#define SOL_SOCKET	1
+
+#define SO_DEBUG	1
+#define SO_REUSEADDR	2
+#define SO_TYPE		3
+#define SO_ERROR	4
+#define SO_DONTROUTE	5
+#define SO_BROADCAST	6
+#define SO_SNDBUF	7
+#define SO_RCVBUF	8
+#define SO_SNDBUFFORCE	32
+#define SO_RCVBUFFORCE	33
+#define SO_KEEPALIVE	9
+#define SO_OOBINLINE	10
+#define SO_NO_CHECK	11
+#define SO_PRIORITY	12
+#define SO_LINGER	13
+#define SO_BSDCOMPAT	14
+#define SO_REUSEPORT	15
+#ifndef SO_PASSCRED /* powerpc only differs in these */
+#define SO_PASSCRED	16
+#define SO_PEERCRED	17
+#define SO_RCVLOWAT	18
+#define SO_SNDLOWAT	19
+#define SO_RCVTIMEO_OLD	20
+#define SO_SNDTIMEO_OLD	21
+#endif
+
+/* Security levels - as per NRL IPv6 - don't actually do anything */
+#define SO_SECURITY_AUTHENTICATION		22
+#define SO_SECURITY_ENCRYPTION_TRANSPORT	23
+#define SO_SECURITY_ENCRYPTION_NETWORK		24
+
+#define SO_BINDTODEVICE	25
+
+/* Socket filtering */
+#define SO_ATTACH_FILTER	26
+#define SO_DETACH_FILTER	27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
+
+#define SO_PEERNAME		28
+
+#define SO_ACCEPTCONN		30
+
+#define SO_PEERSEC		31
+#define SO_PASSSEC		34
+
+#define SO_MARK			36
+
+#define SO_PROTOCOL		38
+#define SO_DOMAIN		39
+
+#define SO_RXQ_OVFL             40
+
+#define SO_WIFI_STATUS		41
+#define SCM_WIFI_STATUS	SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
+
+/* Instruct lower device to use last 4-bytes of skb data as FCS */
+#define SO_NOFCS		43
+
+#define SO_LOCK_FILTER		44
+
+#define SO_SELECT_ERR_QUEUE	45
+
+#define SO_BUSY_POLL		46
+
+#define SO_MAX_PACING_RATE	47
+
+#define SO_BPF_EXTENSIONS	48
+
+#define SO_INCOMING_CPU		49
+
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
+#define SO_ATTACH_REUSEPORT_CBPF	51
+#define SO_ATTACH_REUSEPORT_EBPF	52
+
+#define SO_CNX_ADVICE		53
+
+#define SCM_TIMESTAMPING_OPT_STATS	54
+
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
+#define SCM_TIMESTAMPING_PKTINFO	58
+
+#define SO_PEERGROUPS		59
+
+#define SO_ZEROCOPY		60
+
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
+#define SO_BINDTOIFINDEX	62
+
+#define SO_TIMESTAMP_OLD        29
+#define SO_TIMESTAMPNS_OLD      35
+#define SO_TIMESTAMPING_OLD     37
+
+#define SO_TIMESTAMP_NEW        63
+#define SO_TIMESTAMPNS_NEW      64
+#define SO_TIMESTAMPING_NEW     65
+
+#define SO_RCVTIMEO_NEW         66
+#define SO_SNDTIMEO_NEW         67
+
+#define SO_DETACH_REUSEPORT_BPF 68
+
+#define SO_PREFER_BUSY_POLL	69
+#define SO_BUSY_POLL_BUDGET	70
+
+#define SO_NETNS_COOKIE		71
+
+#define SO_BUF_LOCK		72
+
+#define SO_RESERVE_MEM		73
+
+#define SO_TXREHASH		74
+
+#define SO_RCVMARK		75
+
+#define SO_PASSPIDFD		76
+#define SO_PEERPIDFD		77
+
+#define SO_DEVMEM_LINEAR	78
+#define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
+#define SO_DEVMEM_DMABUF	79
+#define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
+
+#define SCM_TS_OPT_ID		81
+
+#define SO_RCVPRIORITY		82
+
+#define SO_PASSRIGHTS		83
+
+#define SO_INQ			84
+#define SCM_INQ			SO_INQ
+
+#define SO_RIGHTS_NOTRUNC	85
+
+#if !defined(__KERNEL__)
+
+#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
+/* on 64-bit and x32, avoid the ?: operator */
+#define SO_TIMESTAMP		SO_TIMESTAMP_OLD
+#define SO_TIMESTAMPNS		SO_TIMESTAMPNS_OLD
+#define SO_TIMESTAMPING		SO_TIMESTAMPING_OLD
+
+#define SO_RCVTIMEO		SO_RCVTIMEO_OLD
+#define SO_SNDTIMEO		SO_SNDTIMEO_OLD
+#else
+#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW)
+#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW)
+#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW)
+
+#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW)
+#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW)
+#endif
+
+#define SCM_TIMESTAMP           SO_TIMESTAMP
+#define SCM_TIMESTAMPNS         SO_TIMESTAMPNS
+#define SCM_TIMESTAMPING        SO_TIMESTAMPING
+
+#endif
+
+#endif /* __ASM_GENERIC_SOCKET_H */