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, 43 insertions, 0 deletions

diff --git a/include/sound/sof/debug.h b/include/sound/sof/debug.h
new file mode 100644
index 000000000..8b308d7e5
--- /dev/null
+++ b/include/sound/sof/debug.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * Copyright(c) 2020 Intel Corporation
+ *
+ * Author: Karol Trzcinski <karolx.trzcinski@linux.intel.com>
+ */
+
+#ifndef __INCLUDE_SOUND_SOF_DEBUG_H__
+#define __INCLUDE_SOUND_SOF_DEBUG_H__
+
+#include <sound/sof/header.h>
+
+/** ABI3.18 */
+enum sof_ipc_dbg_mem_zone {
+	SOF_IPC_MEM_ZONE_SYS		= 0,	/**< System zone */
+	SOF_IPC_MEM_ZONE_SYS_RUNTIME	= 1,	/**< System-runtime zone */
+	SOF_IPC_MEM_ZONE_RUNTIME	= 2,	/**< Runtime zone */
+	SOF_IPC_MEM_ZONE_BUFFER		= 3,	/**< Buffer zone */
+	SOF_IPC_MEM_ZONE_RUNTIME_SHARED	= 4,	/**< System runtime zone */
+	SOF_IPC_MEM_ZONE_SYS_SHARED	= 5,	/**< System shared zone */
+};
+
+/** ABI3.18 */
+struct sof_ipc_dbg_mem_usage_elem {
+	uint32_t zone;		/**< see sof_ipc_dbg_mem_zone */
+	uint32_t id;		/**< heap index within zone */
+	uint32_t used;		/**< number of bytes used in zone */
+	uint32_t free;		/**< number of bytes free to use within zone */
+	uint32_t reserved;	/**< for future use */
+} __packed;
+
+/** ABI3.18 */
+struct sof_ipc_dbg_mem_usage {
+	struct sof_ipc_reply rhdr;			/**< generic IPC reply header */
+	uint32_t reserved[4];				/**< reserved for future use */
+	uint32_t num_elems;				/**< elems[] counter */
+	struct sof_ipc_dbg_mem_usage_elem elems[];	/**< memory usage information */
+} __packed;
+
+#endif