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, 44 insertions, 0 deletions

diff --git a/fs/overlayfs/params.h b/fs/overlayfs/params.h
new file mode 100644
index 000000000..ffd53cdd8
--- /dev/null
+++ b/fs/overlayfs/params.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
+
+struct ovl_fs;
+struct ovl_config;
+
+extern const struct fs_parameter_spec ovl_parameter_spec[];
+extern const struct constant_table ovl_parameter_redirect_dir[];
+
+/* The set of options that user requested explicitly via mount options */
+struct ovl_opt_set {
+	bool metacopy;
+	bool redirect;
+	bool nfs_export;
+	bool index;
+};
+
+#define OVL_MAX_STACK 500
+
+struct ovl_fs_context_layer {
+	char *name;
+	struct path path;
+};
+
+struct ovl_fs_context {
+	struct path upper;
+	struct path work;
+	size_t capacity;
+	size_t nr; /* includes nr_data */
+	size_t nr_data;
+	struct ovl_opt_set set;
+	struct ovl_fs_context_layer *lower;
+	char *lowerdir_all; /* user provided lowerdir string */
+	bool casefold_set;
+};
+
+int ovl_init_fs_context(struct fs_context *fc);
+void ovl_free_fs(struct ovl_fs *ofs);
+int ovl_fs_params_verify(const struct ovl_fs_context *ctx,
+			 struct ovl_config *config);
+int ovl_show_options(struct seq_file *m, struct dentry *dentry);
+const char *ovl_xino_mode(struct ovl_config *config);