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, 65 insertions, 0 deletions

diff --git a/fs/pnode.h b/fs/pnode.h
new file mode 100644
index 000000000..b029db225
--- /dev/null
+++ b/fs/pnode.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  linux/fs/pnode.h
+ *
+ * (C) Copyright IBM Corporation 2005.
+ */
+#ifndef _LINUX_PNODE_H
+#define _LINUX_PNODE_H
+
+#include <linux/list.h>
+#include "mount.h"
+
+#define IS_MNT_SHARED(m) ((m)->mnt_t_flags & T_SHARED)
+#define IS_MNT_SLAVE(m) ((m)->mnt_master)
+#define IS_MNT_NEW(m) (!(m)->mnt_ns)
+#define CLEAR_MNT_SHARED(m) ((m)->mnt_t_flags &= ~T_SHARED)
+#define IS_MNT_UNBINDABLE(m) ((m)->mnt_t_flags & T_UNBINDABLE)
+#define IS_MNT_MARKED(m) ((m)->mnt_t_flags & T_MARKED)
+#define SET_MNT_MARK(m) ((m)->mnt_t_flags |= T_MARKED)
+#define CLEAR_MNT_MARK(m) ((m)->mnt_t_flags &= ~T_MARKED)
+#define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED)
+
+#define CL_EXPIRE    		0x01
+#define CL_SLAVE     		0x02
+#define CL_COPY_UNBINDABLE	0x04
+#define CL_MAKE_SHARED 		0x08
+#define CL_PRIVATE 		0x10
+#define CL_COPY_MNT_NS_FILE	0x40
+
+/*
+ * EXCL[namespace_sem]
+ */
+static inline void set_mnt_shared(struct mount *mnt)
+{
+	mnt->mnt_t_flags &= ~T_SHARED_MASK;
+	mnt->mnt_t_flags |= T_SHARED;
+}
+
+static inline bool peers(const struct mount *m1, const struct mount *m2)
+{
+	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
+}
+
+void change_mnt_propagation(struct mount *, int);
+void bulk_make_private(struct list_head *);
+int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
+		struct hlist_head *);
+void propagate_umount(struct list_head *);
+int propagate_mount_busy(struct mount *, int);
+void propagate_mount_unlock(struct mount *);
+void mnt_release_group_id(struct mount *);
+int get_dominating_id(struct mount *mnt, const struct path *root);
+int mnt_get_count(struct mount *mnt);
+void mnt_set_mountpoint(struct mount *, struct mountpoint *,
+			struct mount *);
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
+			   struct mount *mnt);
+struct mount *copy_tree(struct mount *, struct dentry *, int);
+bool is_path_reachable(struct mount *, struct dentry *,
+			 const struct path *root);
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt);
+bool propagation_would_overmount(const struct mount *from,
+				 const struct mount *to,
+				 const struct mountpoint *mp);
+#endif /* _LINUX_PNODE_H */