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, 82 insertions, 0 deletions

diff --git a/drivers/edac/mce_amd.h b/drivers/edac/mce_amd.h
new file mode 100644
index 000000000..4811b18d9
--- /dev/null
+++ b/drivers/edac/mce_amd.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _EDAC_MCE_AMD_H
+#define _EDAC_MCE_AMD_H
+
+#include <linux/notifier.h>
+
+#include <asm/mce.h>
+
+#define EC(x)				((x) & 0xffff)
+
+#define LOW_SYNDROME(x)			(((x) >> 15) & 0xff)
+#define HIGH_SYNDROME(x)		(((x) >> 24) & 0xff)
+
+#define TLB_ERROR(x)			(((x) & 0xFFF0) == 0x0010)
+#define MEM_ERROR(x)			(((x) & 0xFF00) == 0x0100)
+#define BUS_ERROR(x)			(((x) & 0xF800) == 0x0800)
+#define INT_ERROR(x)			(((x) & 0xF4FF) == 0x0400)
+
+#define TT(x)				(((x) >> 2) & 0x3)
+#define TT_MSG(x)			tt_msgs[TT(x)]
+#define II(x)				(((x) >> 2) & 0x3)
+#define II_MSG(x)			ii_msgs[II(x)]
+#define LL(x)				((x) & 0x3)
+#define LL_MSG(x)			ll_msgs[LL(x)]
+#define TO(x)				(((x) >> 8) & 0x1)
+#define TO_MSG(x)			to_msgs[TO(x)]
+#define PP(x)				(((x) >> 9) & 0x3)
+#define PP_MSG(x)			pp_msgs[PP(x)]
+#define UU(x)				(((x) >> 8) & 0x3)
+#define UU_MSG(x)			uu_msgs[UU(x)]
+
+#define R4(x)				(((x) >> 4) & 0xf)
+#define R4_MSG(x)			((R4(x) < 9) ?  rrrr_msgs[R4(x)] : "Wrong R4!")
+
+extern const char * const pp_msgs[];
+
+enum tt_ids {
+	TT_INSTR = 0,
+	TT_DATA,
+	TT_GEN,
+	TT_RESV,
+};
+
+enum ll_ids {
+	LL_RESV = 0,
+	LL_L1,
+	LL_L2,
+	LL_LG,
+};
+
+enum ii_ids {
+	II_MEM = 0,
+	II_RESV,
+	II_IO,
+	II_GEN,
+};
+
+enum rrrr_ids {
+	R4_GEN	= 0,
+	R4_RD,
+	R4_WR,
+	R4_DRD,
+	R4_DWR,
+	R4_IRD,
+	R4_PREF,
+	R4_EVICT,
+	R4_SNOOP,
+};
+
+/*
+ * per-family decoder ops
+ */
+struct amd_decoder_ops {
+	bool (*mc0_mce)(u16, u8);
+	bool (*mc1_mce)(u16, u8);
+	bool (*mc2_mce)(u16, u8);
+};
+
+void amd_register_ecc_decoder(void (*f)(int, struct mce *));
+void amd_unregister_ecc_decoder(void (*f)(int, struct mce *));
+
+#endif /* _EDAC_MCE_AMD_H */