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, 110 insertions, 0 deletions

diff --git a/fs/fuse/dev.h b/fs/fuse/dev.h
new file mode 100644
index 000000000..8d25378c0
--- /dev/null
+++ b/fs/fuse/dev.h
@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _FS_FUSE_DEV_H
+#define _FS_FUSE_DEV_H
+
+#include <linux/cleanup.h>
+
+/** Maximum number of outstanding background requests */
+#define FUSE_DEFAULT_MAX_BACKGROUND 12
+
+struct fuse_conn;
+struct fuse_chan;
+struct fuse_dev;
+struct fuse_args;
+struct fuse_copy_state;
+struct fuse_backing_map;
+struct file;
+struct folio;
+enum fuse_notify_code;
+
+struct fuse_chan_param {
+	unsigned int minor;
+	unsigned int max_write;
+	unsigned int max_pages;
+	bool io_uring_enabled;
+};
+
+struct fuse_chan *fuse_chan_new(void);
+struct fuse_chan *fuse_dev_chan_new(void);
+void fuse_chan_release(struct fuse_chan *fch);
+void fuse_chan_free(struct fuse_chan *fch);
+unsigned int fuse_chan_num_background(struct fuse_chan *fch);
+unsigned int fuse_chan_max_background(struct fuse_chan *fch);
+void fuse_chan_max_background_set(struct fuse_chan *fch, unsigned int val);
+unsigned int fuse_chan_num_waiting(struct fuse_chan *fch);
+void fuse_chan_set_fc(struct fuse_chan *fch, struct fuse_conn *fc);
+void fuse_chan_set_initialized(struct fuse_chan *fch, struct fuse_chan_param *param);
+ssize_t fuse_chan_send(struct fuse_chan *fch, struct fuse_args *args);
+int fuse_chan_send_bg(struct fuse_chan *fch, struct fuse_args *args, gfp_t gfp_flags);
+int fuse_chan_send_notify_reply(struct fuse_chan *fch, struct fuse_args *args, u64 unique);
+void fuse_chan_resend(struct fuse_chan *fch);
+
+struct fuse_forget_link *fuse_alloc_forget(void);
+void fuse_chan_queue_forget(struct fuse_chan *fch, struct fuse_forget_link *forget,
+			    u64 nodeid, u64 nlookup);
+
+DEFINE_FREE(fuse_chan_free, struct fuse_chan *, if (_T) fuse_chan_free(_T))
+
+/**
+ * Initialize the client device
+ */
+int fuse_dev_init(void);
+
+/**
+ * Cleanup the client device
+ */
+void fuse_dev_cleanup(void);
+
+void fuse_dev_install(struct fuse_dev *fud, struct fuse_chan *fch);
+bool fuse_dev_verify(struct fuse_dev *fud, struct fuse_chan *fch);
+void fuse_dev_put(struct fuse_dev *fud);
+bool fuse_dev_is_installed(struct fuse_dev *fud);
+bool fuse_dev_is_sync_init(struct fuse_dev *fud);
+struct fuse_dev *fuse_dev_grab(struct file *file);
+
+void fuse_init_server_timeout(struct fuse_chan *fch, unsigned int timeout);
+
+/* Abort all requests */
+void fuse_chan_abort(struct fuse_chan *fch, bool abort_with_err);
+void fuse_chan_wait_aborted(struct fuse_chan *fch);
+
+/**
+ * Acquire reference to fuse_conn
+ */
+struct fuse_conn *fuse_conn_get(struct fuse_conn *fc);
+
+/**
+ * Release reference to fuse_conn
+ */
+void fuse_conn_put(struct fuse_conn *fc);
+
+dev_t fuse_conn_get_id(struct fuse_conn *fc);
+
+void fuse_end_polls(struct fuse_conn *fc);
+int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
+		unsigned int size, struct fuse_copy_state *cs);
+
+int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map);
+int fuse_backing_close(struct fuse_conn *fc, int backing_id);
+
+int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size);
+int fuse_copy_folio(struct fuse_copy_state *cs, struct folio **foliop,
+		    unsigned offset, unsigned count, int zeroing);
+void fuse_copy_finish(struct fuse_copy_state *cs);
+
+#ifdef CONFIG_FUSE_IO_URING
+bool fuse_uring_enabled(void);
+void fuse_uring_destruct(struct fuse_chan *fch);
+#else /* CONFIG_FUSE_IO_URING */
+static inline bool fuse_uring_enabled(void)
+{
+	return false;
+}
+
+static inline void fuse_uring_destruct(struct fuse_chan *fch)
+{
+}
+#endif /* CONFIG_FUSE_IO_URING */
+
+#endif /* _FS_FUSE_DEV_H */