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, 82 insertions, 0 deletions

diff --git a/fs/gfs2/dir.h b/fs/gfs2/dir.h
new file mode 100644
index 000000000..25a857c78
--- /dev/null
+++ b/fs/gfs2/dir.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ */
+
+#ifndef __DIR_DOT_H__
+#define __DIR_DOT_H__
+
+#include <linux/dcache.h>
+#include <linux/crc32.h>
+
+struct inode;
+struct gfs2_inode;
+struct gfs2_inum;
+struct buffer_head;
+struct gfs2_dirent;
+
+struct gfs2_diradd {
+	unsigned nr_blocks;
+	struct gfs2_dirent *dent;
+	struct buffer_head *bh;
+	int save_loc;
+};
+
+struct inode *gfs2_dir_search(struct inode *dir,
+			      const struct qstr *filename,
+			      bool fail_on_exist);
+int gfs2_dir_check(struct inode *dir, const struct qstr *filename,
+		   const struct gfs2_inode *ip);
+int gfs2_dir_add(struct inode *inode, const struct qstr *filename,
+		 const struct gfs2_inode *ip, struct gfs2_diradd *da);
+static inline void gfs2_dir_no_add(struct gfs2_diradd *da)
+{
+	brelse(da->bh);
+	da->bh = NULL;
+}
+int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry);
+int gfs2_dir_read(struct inode *inode, struct dir_context *ctx,
+		  struct file_ra_state *f_ra);
+int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
+		   const struct gfs2_inode *nip, unsigned int new_type);
+
+int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip);
+
+int gfs2_diradd_alloc_required(struct inode *dir,
+			       const struct qstr *filename,
+			       struct gfs2_diradd *da);
+int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
+			    struct buffer_head **bhp);
+void gfs2_dir_hash_inval(struct gfs2_inode *ip);
+
+static inline u32 gfs2_disk_hash(const char *data, int len)
+{
+        return crc32_le((u32)~0, data, len) ^ (u32)~0;
+}
+
+
+static inline void gfs2_str2qstr(struct qstr *name, const char *fname)
+{
+	name->name = fname;
+	name->len = strlen(fname);
+	name->hash = gfs2_disk_hash(name->name, name->len);
+}
+
+/* N.B. This probably ought to take inum & type as args as well */
+static inline void gfs2_qstr2dirent(const struct qstr *name, u16 reclen, struct gfs2_dirent *dent)
+{
+	dent->de_inum.no_addr = cpu_to_be64(0);
+	dent->de_inum.no_formal_ino = cpu_to_be64(0);
+	dent->de_hash = cpu_to_be32(name->hash);
+	dent->de_rec_len = cpu_to_be16(reclen);
+	dent->de_name_len = cpu_to_be16(name->len);
+	dent->de_type = cpu_to_be16(0);
+	memset(dent->__pad, 0, sizeof(dent->__pad));
+	memcpy(dent + 1, name->name, name->len);
+}
+
+extern struct qstr gfs2_qdot;
+extern struct qstr gfs2_qdotdot;
+
+#endif /* __DIR_DOT_H__ */