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, 56 insertions, 0 deletions

diff --git a/fs/ext4/fsmap.h b/fs/ext4/fsmap.h
new file mode 100644
index 000000000..ac642be23
--- /dev/null
+++ b/fs/ext4/fsmap.h
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2017 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#ifndef __EXT4_FSMAP_H__
+#define	__EXT4_FSMAP_H__
+
+struct fsmap;
+
+/* internal fsmap representation */
+struct ext4_fsmap {
+	struct list_head	fmr_list;
+	dev_t		fmr_device;	/* device id */
+	uint32_t	fmr_flags;	/* mapping flags */
+	uint64_t	fmr_physical;	/* device offset of segment */
+	uint64_t	fmr_owner;	/* owner id */
+	uint64_t	fmr_length;	/* length of segment, blocks */
+};
+
+struct ext4_fsmap_head {
+	uint32_t	fmh_iflags;	/* control flags */
+	uint32_t	fmh_oflags;	/* output flags */
+	unsigned int	fmh_count;	/* # of entries in array incl. input */
+	unsigned int	fmh_entries;	/* # of entries filled in (output). */
+
+	struct ext4_fsmap fmh_keys[2];	/* low and high keys */
+};
+
+void ext4_fsmap_from_internal(struct super_block *sb, struct fsmap *dest,
+		struct ext4_fsmap *src);
+void ext4_fsmap_to_internal(struct super_block *sb, struct ext4_fsmap *dest,
+		struct fsmap *src);
+
+/* fsmap to userspace formatter - copy to user & advance pointer */
+typedef int (*ext4_fsmap_format_t)(struct ext4_fsmap *, void *);
+
+int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head,
+		ext4_fsmap_format_t formatter, void *arg);
+
+#define EXT4_QUERY_RANGE_ABORT		1
+#define EXT4_QUERY_RANGE_CONTINUE	0
+
+/*	fmr_owner special values for FS_IOC_GETFSMAP; some share w/ XFS */
+#define EXT4_FMR_OWN_FREE	FMR_OWN_FREE      /* free space */
+#define EXT4_FMR_OWN_UNKNOWN	FMR_OWN_UNKNOWN   /* unknown owner */
+#define EXT4_FMR_OWN_FS		FMR_OWNER('X', 1) /* static fs metadata */
+#define EXT4_FMR_OWN_LOG	FMR_OWNER('X', 2) /* journalling log */
+#define EXT4_FMR_OWN_INODES	FMR_OWNER('X', 5) /* inodes */
+#define EXT4_FMR_OWN_GDT	FMR_OWNER('f', 1) /* group descriptors */
+#define EXT4_FMR_OWN_RESV_GDT	FMR_OWNER('f', 2) /* reserved gdt blocks */
+#define EXT4_FMR_OWN_BLKBM	FMR_OWNER('f', 3) /* block bitmap */
+#define EXT4_FMR_OWN_INOBM	FMR_OWNER('f', 4) /* inode bitmap */
+
+#endif /* __EXT4_FSMAP_H__ */