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, 75 insertions, 0 deletions

diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig
new file mode 100644
index 000000000..fc989a379
--- /dev/null
+++ b/net/sctp/Kconfig
@@ -0,0 +1,75 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# SCTP configuration
+#
+
+menuconfig IP_SCTP
+	tristate "The SCTP Protocol"
+	depends on INET
+	select CRYPTO_LIB_SHA1
+	select CRYPTO_LIB_SHA256
+	select CRYPTO_LIB_UTILS
+	select NET_CRC32C
+	select NET_UDP_TUNNEL
+	help
+	  Stream Control Transmission Protocol
+
+	  From RFC 2960 <http://www.ietf.org/rfc/rfc2960.txt>.
+
+	  "SCTP is a reliable transport protocol operating on top of a
+	  connectionless packet network such as IP.  It offers the following
+	  services to its users:
+
+	  -- acknowledged error-free non-duplicated transfer of user data,
+	  -- data fragmentation to conform to discovered path MTU size,
+	  -- sequenced delivery of user messages within multiple streams,
+	  with an option for order-of-arrival delivery of individual user
+	  messages,
+	  -- optional bundling of multiple user messages into a single SCTP
+	  packet, and
+	  -- network-level fault tolerance through supporting of multi-
+	  homing at either or both ends of an association."
+
+	  To compile this protocol support as a module, choose M here: the
+	  module will be called sctp. Debug messages are handled by the
+	  kernel's dynamic debugging framework.
+
+	  If in doubt, say N.
+
+if IP_SCTP
+
+config SCTP_DBG_OBJCNT
+	bool "SCTP: Debug object counts"
+	depends on PROC_FS
+	help
+	  If you say Y, this will enable debugging support for counting the
+	  type of objects that are currently allocated.  This is useful for
+	  identifying memory leaks. This debug information can be viewed by
+	  'cat /proc/net/sctp/sctp_dbg_objcnt'
+
+	  If unsure, say N
+
+choice
+	prompt "Default SCTP cookie authentication method"
+	default SCTP_DEFAULT_COOKIE_HMAC_SHA256
+	help
+	  This option sets the default SCTP cookie authentication method, for
+	  when a method hasn't been explicitly selected via the
+	  net.sctp.cookie_hmac_alg sysctl.
+
+	  If unsure, choose the default (HMAC-SHA256).
+
+config SCTP_DEFAULT_COOKIE_HMAC_SHA256
+	bool "HMAC-SHA256"
+
+config SCTP_DEFAULT_COOKIE_HMAC_NONE
+	bool "None"
+
+endchoice
+
+config INET_SCTP_DIAG
+	depends on INET_DIAG
+	def_tristate INET_DIAG
+
+
+endif # IP_SCTP