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, 61 insertions, 0 deletions

diff --git a/fs/9p/fid.h b/fs/9p/fid.h
new file mode 100644
index 000000000..0d6138bee
--- /dev/null
+++ b/fs/9p/fid.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * V9FS FID Management
+ *
+ *  Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
+ */
+#ifndef FS_9P_FID_H
+#define FS_9P_FID_H
+#include <linux/list.h>
+#include "v9fs.h"
+
+struct p9_fid *v9fs_fid_find_inode(struct inode *inode, bool want_writeable,
+	kuid_t uid, bool any);
+struct p9_fid *v9fs_fid_lookup(struct dentry *dentry);
+static inline struct p9_fid *v9fs_parent_fid(struct dentry *dentry)
+{
+	return v9fs_fid_lookup(dentry->d_parent);
+}
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid **fid);
+void v9fs_open_fid_add(struct inode *inode, struct p9_fid **fid);
+static inline struct p9_fid *clone_fid(struct p9_fid *fid)
+{
+	return IS_ERR(fid) ? fid :  p9_client_walk(fid, 0, NULL, 1);
+}
+static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry)
+{
+	struct p9_fid *fid, *nfid;
+
+	fid = v9fs_fid_lookup(dentry);
+	if (!fid || IS_ERR(fid))
+		return fid;
+
+	nfid = clone_fid(fid);
+	p9_fid_put(fid);
+	return nfid;
+}
+/**
+ * v9fs_fid_addmodes - add cache flags to fid mode (for client use only)
+ * @fid: fid to augment
+ * @s_flags: session info mount flags
+ * @s_cache: session info cache flags
+ * @f_flags: unix open flags
+ *
+ * make sure mode reflects flags of underlying mounts
+ * also qid.version == 0 reflects a synthetic or legacy file system
+ * NOTE: these are set after open so only reflect 9p client not
+ * underlying file system on server.
+ */
+static inline void v9fs_fid_add_modes(struct p9_fid *fid, unsigned int s_flags,
+	unsigned int s_cache, unsigned int f_flags)
+{
+	if ((!s_cache) ||
+	   ((fid->qid.version == 0) && !(s_flags & V9FS_IGNORE_QV)) ||
+	   (s_flags & V9FS_DIRECT_IO) || (f_flags & O_DIRECT)) {
+		fid->mode |= P9L_DIRECT; /* no read or write cache */
+	} else if ((!(s_cache & CACHE_WRITEBACK)) ||
+				(f_flags & O_DSYNC) || (s_flags & V9FS_SYNC)) {
+		fid->mode |= P9L_NOWRITECACHE;
+	}
+}
+#endif