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, 105 insertions, 0 deletions

diff --git a/fs/fs_dirent.c b/fs/fs_dirent.c
new file mode 100644
index 000000000..e5e08f213
--- /dev/null
+++ b/fs/fs_dirent.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs_dirent.h>
+#include <linux/export.h>
+
+/*
+ * fs on-disk file type to dirent file type conversion
+ */
+static const unsigned char fs_dtype_by_ftype[FT_MAX] = {
+	[FT_UNKNOWN]	= DT_UNKNOWN,
+	[FT_REG_FILE]	= DT_REG,
+	[FT_DIR]	= DT_DIR,
+	[FT_CHRDEV]	= DT_CHR,
+	[FT_BLKDEV]	= DT_BLK,
+	[FT_FIFO]	= DT_FIFO,
+	[FT_SOCK]	= DT_SOCK,
+	[FT_SYMLINK]	= DT_LNK
+};
+
+/**
+ * fs_ftype_to_dtype() - fs on-disk file type to dirent type.
+ * @filetype: The on-disk file type to convert.
+ *
+ * This function converts the on-disk file type value (FT_*) to the directory
+ * entry type (DT_*).
+ *
+ * Context: Any context.
+ * Return:
+ * * DT_UNKNOWN		- Unknown type
+ * * DT_FIFO		- FIFO
+ * * DT_CHR		- Character device
+ * * DT_DIR		- Directory
+ * * DT_BLK		- Block device
+ * * DT_REG		- Regular file
+ * * DT_LNK		- Symbolic link
+ * * DT_SOCK		- Local-domain socket
+ */
+unsigned char fs_ftype_to_dtype(unsigned int filetype)
+{
+	if (filetype >= FT_MAX)
+		return DT_UNKNOWN;
+
+	return fs_dtype_by_ftype[filetype];
+}
+EXPORT_SYMBOL_GPL(fs_ftype_to_dtype);
+
+/*
+ * dirent file type to fs on-disk file type conversion
+ * Values not initialized explicitly are FT_UNKNOWN (0).
+ */
+static const unsigned char fs_ftype_by_dtype[DT_MAX] = {
+	[DT_REG]	= FT_REG_FILE,
+	[DT_DIR]	= FT_DIR,
+	[DT_LNK]	= FT_SYMLINK,
+	[DT_CHR]	= FT_CHRDEV,
+	[DT_BLK]	= FT_BLKDEV,
+	[DT_FIFO]	= FT_FIFO,
+	[DT_SOCK]	= FT_SOCK,
+};
+
+/**
+ * fs_umode_to_ftype() - file mode to on-disk file type.
+ * @mode: The file mode to convert.
+ *
+ * This function converts the file mode value to the on-disk file type (FT_*).
+ *
+ * Context: Any context.
+ * Return:
+ * * FT_UNKNOWN		- Unknown type
+ * * FT_REG_FILE	- Regular file
+ * * FT_DIR		- Directory
+ * * FT_CHRDEV		- Character device
+ * * FT_BLKDEV		- Block device
+ * * FT_FIFO		- FIFO
+ * * FT_SOCK		- Local-domain socket
+ * * FT_SYMLINK		- Symbolic link
+ */
+unsigned char fs_umode_to_ftype(umode_t mode)
+{
+	return fs_ftype_by_dtype[S_DT(mode)];
+}
+EXPORT_SYMBOL_GPL(fs_umode_to_ftype);
+
+/**
+ * fs_umode_to_dtype() - file mode to dirent file type.
+ * @mode: The file mode to convert.
+ *
+ * This function converts the file mode value to the directory
+ * entry type (DT_*).
+ *
+ * Context: Any context.
+ * Return:
+ * * DT_UNKNOWN		- Unknown type
+ * * DT_FIFO		- FIFO
+ * * DT_CHR		- Character device
+ * * DT_DIR		- Directory
+ * * DT_BLK		- Block device
+ * * DT_REG		- Regular file
+ * * DT_LNK		- Symbolic link
+ * * DT_SOCK		- Local-domain socket
+ */
+unsigned char fs_umode_to_dtype(umode_t mode)
+{
+	return fs_ftype_to_dtype(fs_umode_to_ftype(mode));
+}
+EXPORT_SYMBOL_GPL(fs_umode_to_dtype);