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, 80 insertions, 0 deletions

diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
new file mode 100644
index 000000000..78a690b48
--- /dev/null
+++ b/fs/xfs/xfs_rtalloc.h
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ */
+#ifndef __XFS_RTALLOC_H__
+#define	__XFS_RTALLOC_H__
+
+/* kernel only definitions and functions */
+
+struct xfs_mount;
+struct xfs_trans;
+
+#ifdef CONFIG_XFS_RT
+/* rtgroup superblock initialization */
+int xfs_rtmount_readsb(struct xfs_mount *mp);
+void xfs_rtmount_freesb(struct xfs_mount *mp);
+
+/*
+ * Initialize realtime fields in the mount structure.
+ */
+int					/* error */
+xfs_rtmount_init(
+	struct xfs_mount	*mp);	/* file system mount structure */
+void
+xfs_rtunmount_inodes(
+	struct xfs_mount	*mp);
+
+/*
+ * Get the bitmap and summary inodes into the mount structure
+ * at mount time.
+ */
+int					/* error */
+xfs_rtmount_inodes(
+	struct xfs_mount	*mp);	/* file system mount structure */
+
+/*
+ * Grow the realtime area of the filesystem.
+ */
+int
+xfs_growfs_rt(
+	struct xfs_mount	*mp,	/* file system mount structure */
+	xfs_growfs_rt_t		*in);	/* user supplied growfs struct */
+
+int xfs_rtalloc_reinit_frextents(struct xfs_mount *mp);
+int xfs_growfs_check_rtgeom(const struct xfs_mount *mp, xfs_rfsblock_t dblocks,
+		xfs_rfsblock_t rblocks, xfs_agblock_t rextsize);
+#else
+# define xfs_growfs_rt(mp,in)				(-ENOSYS)
+# define xfs_rtalloc_reinit_frextents(m)		(0)
+# define xfs_rtmount_readsb(mp)				(0)
+# define xfs_rtmount_freesb(mp)				((void)0)
+static inline int		/* error */
+xfs_rtmount_init(
+	xfs_mount_t	*mp)	/* file system mount structure */
+{
+	if (mp->m_sb.sb_rblocks == 0)
+		return 0;
+
+	xfs_warn(mp, "Not built with CONFIG_XFS_RT");
+	return -ENOSYS;
+}
+# define xfs_rtmount_inodes(m)  (((mp)->m_sb.sb_rblocks == 0)? 0 : (-ENOSYS))
+# define xfs_rtunmount_inodes(m)
+
+static inline int
+xfs_growfs_check_rtgeom(const struct xfs_mount *mp,
+		xfs_rfsblock_t dblocks, xfs_rfsblock_t rblocks,
+		xfs_extlen_t rextsize)
+{
+	return 0;
+}
+#endif	/* CONFIG_XFS_RT */
+
+int xfs_rtallocate_rtgs(struct xfs_trans *tp, xfs_fsblock_t bno_hint,
+		xfs_rtxlen_t minlen, xfs_rtxlen_t maxlen, xfs_rtxlen_t prod,
+		bool wasdel, bool initial_user_data, xfs_rtblock_t *bno,
+		xfs_extlen_t *blen);
+
+#endif	/* __XFS_RTALLOC_H__ */