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, 162 insertions, 0 deletions

diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h
new file mode 100644
index 000000000..5888ed479
--- /dev/null
+++ b/fs/nilfs2/sufile.h
@@ -0,0 +1,162 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * NILFS segment usage file.
+ *
+ * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * Written by Koji Sato.
+ */
+
+#ifndef _NILFS_SUFILE_H
+#define _NILFS_SUFILE_H
+
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include "mdt.h"
+
+
+static inline unsigned long nilfs_sufile_get_nsegments(struct inode *sufile)
+{
+	return ((struct the_nilfs *)sufile->i_sb->s_fs_info)->ns_nsegments;
+}
+
+unsigned long nilfs_sufile_get_ncleansegs(struct inode *sufile);
+
+int nilfs_sufile_set_alloc_range(struct inode *sufile, __u64 start, __u64 end);
+int nilfs_sufile_alloc(struct inode *, __u64 *);
+int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum);
+int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
+				   unsigned long nblocks, time64_t modtime);
+int nilfs_sufile_get_stat(struct inode *, struct nilfs_sustat *);
+ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, void *, unsigned int,
+				size_t);
+ssize_t nilfs_sufile_set_suinfo(struct inode *, void *, unsigned int, size_t);
+
+int nilfs_sufile_updatev(struct inode *, __u64 *, size_t, int, size_t *,
+			 void (*dofunc)(struct inode *, __u64,
+					struct buffer_head *,
+					struct buffer_head *));
+int nilfs_sufile_update(struct inode *, __u64, int,
+			void (*dofunc)(struct inode *, __u64,
+				       struct buffer_head *,
+				       struct buffer_head *));
+void nilfs_sufile_do_scrap(struct inode *, __u64, struct buffer_head *,
+			   struct buffer_head *);
+void nilfs_sufile_do_free(struct inode *, __u64, struct buffer_head *,
+			  struct buffer_head *);
+void nilfs_sufile_do_cancel_free(struct inode *, __u64, struct buffer_head *,
+				 struct buffer_head *);
+void nilfs_sufile_do_set_error(struct inode *, __u64, struct buffer_head *,
+			       struct buffer_head *);
+
+int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs);
+int nilfs_sufile_read(struct super_block *sb, size_t susize,
+		      struct nilfs_inode *raw_inode, struct inode **inodep);
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range);
+
+/**
+ * nilfs_sufile_warn_on_error - warn on unexpected sufile error
+ * @sufile: inode of segment usage file
+ * @err: status code returned by a sufile function
+ *
+ * Even if buffer heads of blocks containing segment usage entries have
+ * been dirtied in advance by calling functions such as
+ * nilfs_sufile_mark_dirty() or nilfs_sufile_{alloc,free}(), those buffers
+ * can be discarded from memory after the file system detects corruption and
+ * degrades to read-only mode, which may cause sufile operations, including
+ * cancel operations, to return errors.  nilfs_sufile_warn_on_error() is used
+ * to detect unexpected errors other than during read-only degradation.
+ *
+ * Return: 0 if @err is 0, %-EROFS if in read-only degraded mode, and %-EIO
+ * otherwise.
+ */
+#define nilfs_sufile_warn_on_error(sufile, err)				\
+	({								\
+		int _err = (err);					\
+									\
+		if (unlikely(_err))					\
+			_err = WARN_ONCE(!sb_rdonly((sufile)->i_sb),	\
+				"unexpected sufile error %d\n", _err) ? \
+				-EIO : -EROFS;				\
+		_err;							\
+	})
+
+/**
+ * nilfs_sufile_scrap - make a segment garbage
+ * @sufile: inode of segment usage file
+ * @segnum: segment number to be freed
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static inline int nilfs_sufile_scrap(struct inode *sufile, __u64 segnum)
+{
+	return nilfs_sufile_update(sufile, segnum, 1, nilfs_sufile_do_scrap);
+}
+
+/**
+ * nilfs_sufile_free - free segment
+ * @sufile: inode of segment usage file
+ * @segnum: segment number to be freed
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static inline int nilfs_sufile_free(struct inode *sufile, __u64 segnum)
+{
+	return nilfs_sufile_update(sufile, segnum, 0, nilfs_sufile_do_free);
+}
+
+/**
+ * nilfs_sufile_freev - free segments
+ * @sufile: inode of segment usage file
+ * @segnumv: array of segment numbers
+ * @nsegs: size of @segnumv array
+ * @ndone: place to store the number of freed segments
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static inline int nilfs_sufile_freev(struct inode *sufile, __u64 *segnumv,
+				     size_t nsegs, size_t *ndone)
+{
+	return nilfs_sufile_updatev(sufile, segnumv, nsegs, 0, ndone,
+				    nilfs_sufile_do_free);
+}
+
+/**
+ * nilfs_sufile_cancel_freev - reallocate freeing segments
+ * @sufile: inode of segment usage file
+ * @segnumv: array of segment numbers
+ * @nsegs: size of @segnumv array
+ * @ndone: place to store the number of cancelled segments
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static inline int nilfs_sufile_cancel_freev(struct inode *sufile,
+					    __u64 *segnumv, size_t nsegs,
+					    size_t *ndone)
+{
+	return nilfs_sufile_updatev(sufile, segnumv, nsegs, 0, ndone,
+				    nilfs_sufile_do_cancel_free);
+}
+
+/**
+ * nilfs_sufile_set_error - mark a segment as erroneous
+ * @sufile: inode of segment usage file
+ * @segnum: segment number
+ *
+ * Description: nilfs_sufile_set_error() marks the segment specified by
+ * @segnum as erroneous. The error segment will never be used again.
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL	- Invalid segment usage number.
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
+ */
+static inline int nilfs_sufile_set_error(struct inode *sufile, __u64 segnum)
+{
+	return nilfs_sufile_update(sufile, segnum, 0,
+				   nilfs_sufile_do_set_error);
+}
+
+#endif	/* _NILFS_SUFILE_H */