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, 95 insertions, 0 deletions

diff --git a/sound/soc/sof/ipc4-telemetry.c b/sound/soc/sof/ipc4-telemetry.c
new file mode 100644
index 000000000..ddc3bc494
--- /dev/null
+++ b/sound/soc/sof/ipc4-telemetry.c
@@ -0,0 +1,95 @@
+// 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) 2018-2023 Intel Corporation
+//
+
+#include <linux/debugfs.h>
+#include <linux/io.h>
+#include <linux/pm_runtime.h>
+#include <sound/sof/debug.h>
+#include <sound/sof/ipc4/header.h>
+#include "sof-priv.h"
+#include "ops.h"
+#include "ipc4-telemetry.h"
+#include "ipc4-priv.h"
+
+static void __iomem *sof_ipc4_query_exception_address(struct snd_sof_dev *sdev)
+{
+	u32 type = SOF_IPC4_DEBUG_SLOT_TELEMETRY;
+	size_t telemetry_slot_offset;
+	u32 offset;
+
+	telemetry_slot_offset = sof_ipc4_find_debug_slot_offset_by_type(sdev, type);
+	if (!telemetry_slot_offset)
+		return NULL;
+
+	/* skip the first separator magic number */
+	offset = telemetry_slot_offset + sizeof(u32);
+
+	return sdev->bar[sdev->mailbox_bar] + offset;
+}
+
+static ssize_t sof_telemetry_entry_read(struct file *file, char __user *buffer,
+					size_t count, loff_t *ppos)
+{
+	struct snd_sof_dfsentry *dfse = file->private_data;
+	struct snd_sof_dev *sdev = dfse->sdev;
+	void __iomem *io_addr;
+	loff_t pos = *ppos;
+	size_t size_ret;
+	u8 *buf;
+
+	if (pos < 0)
+		return -EINVAL;
+	/* skip the first separator magic number */
+	if (pos >= SOF_IPC4_DEBUG_SLOT_SIZE - 4 || !count)
+		return 0;
+	if (count > SOF_IPC4_DEBUG_SLOT_SIZE - 4 - pos)
+		count = SOF_IPC4_DEBUG_SLOT_SIZE - 4 - pos;
+
+	io_addr = sof_ipc4_query_exception_address(sdev);
+	if (!io_addr)
+		return -EFAULT;
+
+	buf = kzalloc(SOF_IPC4_DEBUG_SLOT_SIZE - 4, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy_fromio(buf, io_addr, SOF_IPC4_DEBUG_SLOT_SIZE - 4);
+	size_ret = copy_to_user(buffer, buf + pos, count);
+	if (size_ret) {
+		kfree(buf);
+		return -EFAULT;
+	}
+
+	*ppos = pos + count;
+	kfree(buf);
+
+	return count;
+}
+
+static const struct file_operations sof_telemetry_fops = {
+	.open = simple_open,
+	.read = sof_telemetry_entry_read,
+};
+
+void sof_ipc4_create_exception_debugfs_node(struct snd_sof_dev *sdev)
+{
+	struct snd_sof_dfsentry *dfse;
+
+	dfse = devm_kzalloc(sdev->dev, sizeof(*dfse), GFP_KERNEL);
+	if (!dfse)
+		return;
+
+	dfse->type = SOF_DFSENTRY_TYPE_IOMEM;
+	dfse->size = SOF_IPC4_DEBUG_SLOT_SIZE - 4;
+	dfse->access_type = SOF_DEBUGFS_ACCESS_ALWAYS;
+	dfse->sdev = sdev;
+
+	list_add(&dfse->list, &sdev->dfsentry_list);
+
+	debugfs_create_file("exception", 0444, sdev->debugfs_root, dfse, &sof_telemetry_fops);
+}