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, 107 insertions, 0 deletions

diff --git a/include/sound/sof/trace.h b/include/sound/sof/trace.h
new file mode 100644
index 000000000..ac2ebb6fb
--- /dev/null
+++ b/include/sound/sof/trace.h
@@ -0,0 +1,107 @@
+/* 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) 2018 Intel Corporation
+ */
+
+#ifndef __INCLUDE_SOUND_SOF_TRACE_H__
+#define __INCLUDE_SOUND_SOF_TRACE_H__
+
+#include <sound/sof/header.h>
+#include <sound/sof/stream.h>
+
+/*
+ * DMA for Trace
+ */
+
+#define SOF_TRACE_FILENAME_SIZE		32
+
+/* DMA for Trace params info - SOF_IPC_DEBUG_DMA_PARAMS */
+/* Deprecated - use sof_ipc_dma_trace_params_ext */
+struct sof_ipc_dma_trace_params {
+	struct sof_ipc_cmd_hdr hdr;
+	struct sof_ipc_host_buffer buffer;
+	uint32_t stream_tag;
+}  __packed;
+
+/* DMA for Trace params info - SOF_IPC_DEBUG_DMA_PARAMS_EXT */
+struct sof_ipc_dma_trace_params_ext {
+	struct sof_ipc_cmd_hdr hdr;
+	struct sof_ipc_host_buffer buffer;
+	uint32_t stream_tag;
+	uint64_t timestamp_ns; /* in nanosecond */
+	uint32_t reserved[8];
+}  __packed;
+
+/* DMA for Trace params info - SOF_IPC_DEBUG_DMA_PARAMS */
+struct sof_ipc_dma_trace_posn {
+	struct sof_ipc_reply rhdr;
+	uint32_t host_offset;	/* Offset of DMA host buffer */
+	uint32_t overflow;	/* overflow bytes if any */
+	uint32_t messages;	/* total trace messages */
+}  __packed;
+
+/* Values used in sof_ipc_trace_filter_elem: */
+
+/* bits 6..0 */
+#define SOF_IPC_TRACE_FILTER_ELEM_SET_LEVEL	0x01	/**< trace level for selected components */
+#define SOF_IPC_TRACE_FILTER_ELEM_BY_UUID	0x02	/**< filter by uuid key */
+#define SOF_IPC_TRACE_FILTER_ELEM_BY_PIPE	0x03	/**< filter by pipeline */
+#define SOF_IPC_TRACE_FILTER_ELEM_BY_COMP	0x04	/**< filter by component id */
+
+/* bit 7 */
+#define SOF_IPC_TRACE_FILTER_ELEM_FIN		0x80	/**< mark last filter in set */
+
+/* bits 31..8: Unused */
+
+/** part of sof_ipc_trace_filter, ABI3.17 */
+struct sof_ipc_trace_filter_elem {
+	uint32_t key;		/**< SOF_IPC_TRACE_FILTER_ELEM_ {LEVEL, UUID, COMP, PIPE} */
+	uint32_t value;		/**< element value */
+} __packed;
+
+/** Runtime tracing filtration data - SOF_IPC_TRACE_FILTER_UPDATE, ABI3.17 */
+struct sof_ipc_trace_filter {
+	struct sof_ipc_cmd_hdr hdr;	/**< IPC command header */
+	uint32_t elem_cnt;		/**< number of entries in elems[] array */
+	uint32_t reserved[8];		/**< reserved for future usage */
+	/** variable size array with new filtering settings */
+	struct sof_ipc_trace_filter_elem elems[];
+} __packed;
+
+/*
+ * Commom debug
+ */
+
+/*
+ * SOF panic codes
+ */
+#define SOF_IPC_PANIC_MAGIC			0x0dead000
+#define SOF_IPC_PANIC_MAGIC_MASK		0x0ffff000
+#define SOF_IPC_PANIC_CODE_MASK			0x00000fff
+#define SOF_IPC_PANIC_MEM			(SOF_IPC_PANIC_MAGIC | 0x0)
+#define SOF_IPC_PANIC_WORK			(SOF_IPC_PANIC_MAGIC | 0x1)
+#define SOF_IPC_PANIC_IPC			(SOF_IPC_PANIC_MAGIC | 0x2)
+#define SOF_IPC_PANIC_ARCH			(SOF_IPC_PANIC_MAGIC | 0x3)
+#define SOF_IPC_PANIC_PLATFORM			(SOF_IPC_PANIC_MAGIC | 0x4)
+#define SOF_IPC_PANIC_TASK			(SOF_IPC_PANIC_MAGIC | 0x5)
+#define SOF_IPC_PANIC_EXCEPTION			(SOF_IPC_PANIC_MAGIC | 0x6)
+#define SOF_IPC_PANIC_DEADLOCK			(SOF_IPC_PANIC_MAGIC | 0x7)
+#define SOF_IPC_PANIC_STACK			(SOF_IPC_PANIC_MAGIC | 0x8)
+#define SOF_IPC_PANIC_IDLE			(SOF_IPC_PANIC_MAGIC | 0x9)
+#define SOF_IPC_PANIC_WFI			(SOF_IPC_PANIC_MAGIC | 0xa)
+#define SOF_IPC_PANIC_ASSERT			(SOF_IPC_PANIC_MAGIC | 0xb)
+
+/* panic info include filename and line number
+ * filename array will not include null terminator if fully filled
+ */
+struct sof_ipc_panic_info {
+	struct sof_ipc_hdr hdr;
+	uint32_t code;			/* SOF_IPC_PANIC_ */
+	uint8_t filename[SOF_TRACE_FILENAME_SIZE];
+	uint32_t linenum;
+}  __packed;
+
+#endif