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, 54 insertions, 0 deletions

diff --git a/fs/9p/acl.h b/fs/9p/acl.h
new file mode 100644
index 000000000..333cfcc28
--- /dev/null
+++ b/fs/9p/acl.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ */
+#ifndef FS_9P_ACL_H
+#define FS_9P_ACL_H
+
+#ifdef CONFIG_9P_FS_POSIX_ACL
+int v9fs_get_acl(struct inode *inode, struct p9_fid *fid);
+struct posix_acl *v9fs_iop_get_inode_acl(struct inode *inode, int type,
+				   bool rcu);
+struct posix_acl *v9fs_iop_get_acl(struct mnt_idmap *idmap,
+					  struct dentry *dentry, int type);
+int v9fs_iop_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+		     struct posix_acl *acl, int type);
+int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid);
+int v9fs_set_create_acl(struct inode *inode, struct p9_fid *fid,
+			struct posix_acl *dacl, struct posix_acl *acl);
+int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+		  struct posix_acl **dpacl, struct posix_acl **pacl);
+void v9fs_put_acl(struct posix_acl *dacl, struct posix_acl *acl);
+#else
+#define v9fs_iop_get_inode_acl	NULL
+#define v9fs_iop_get_acl NULL
+#define v9fs_iop_set_acl NULL
+static inline int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
+{
+	return 0;
+}
+static inline int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid)
+{
+	return 0;
+}
+static inline int v9fs_set_create_acl(struct inode *inode,
+				      struct p9_fid *fid,
+				      struct posix_acl *dacl,
+				      struct posix_acl *acl)
+{
+	return 0;
+}
+static inline void v9fs_put_acl(struct posix_acl *dacl,
+				struct posix_acl *acl)
+{
+}
+static inline int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+				struct posix_acl **dpacl,
+				struct posix_acl **pacl)
+{
+	return 0;
+}
+
+#endif
+#endif /* FS_9P_XATTR_H */