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, 71 insertions, 0 deletions

diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
new file mode 100644
index 000000000..e3d6efdfd
--- /dev/null
+++ b/fs/gfs2/bmap.h
@@ -0,0 +1,71 @@
+/* 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 __BMAP_DOT_H__
+#define __BMAP_DOT_H__
+
+#include <linux/iomap.h>
+
+#include "inode.h"
+
+struct inode;
+struct gfs2_inode;
+struct page;
+
+
+/**
+ * gfs2_write_calc_reserv - calculate number of blocks needed to write to a file
+ * @ip: the file
+ * @len: the number of bytes to be written to the file
+ * @data_blocks: returns the number of data blocks required
+ * @ind_blocks: returns the number of indirect blocks required
+ *
+ */
+
+static inline void gfs2_write_calc_reserv(const struct gfs2_inode *ip,
+					  unsigned int len,
+					  unsigned int *data_blocks,
+					  unsigned int *ind_blocks)
+{
+	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	unsigned int tmp;
+
+	BUG_ON(gfs2_is_dir(ip));
+	*data_blocks = (len >> sdp->sd_sb.sb_bsize_shift) + 3;
+	*ind_blocks = 3 * (sdp->sd_max_height - 1);
+
+	for (tmp = *data_blocks; tmp > sdp->sd_diptrs;) {
+		tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
+		*ind_blocks += tmp;
+	}
+}
+
+extern const struct iomap_ops gfs2_iomap_ops;
+extern const struct iomap_write_ops gfs2_iomap_write_ops;
+extern const struct iomap_writeback_ops gfs2_writeback_ops;
+
+int gfs2_unstuff_dinode(struct gfs2_inode *ip);
+int gfs2_block_map(struct inode *inode, sector_t lblock,
+		   struct buffer_head *bh, int create);
+int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
+		   struct iomap *iomap);
+int gfs2_iomap_alloc(struct inode *inode, loff_t pos, loff_t length,
+		     struct iomap *iomap);
+int gfs2_get_extent(struct inode *inode, u64 lblock, u64 *dblock,
+		    unsigned int *extlen);
+int gfs2_alloc_extent(struct inode *inode, u64 lblock, u64 *dblock,
+		      unsigned *extlen, bool *new);
+int gfs2_clear_beyond_eof(struct inode *inode, loff_t end);
+int gfs2_setattr_size(struct inode *inode, u64 size);
+int gfs2_truncatei_resume(struct gfs2_inode *ip);
+int gfs2_file_dealloc(struct gfs2_inode *ip);
+int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
+			      unsigned int len);
+int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd);
+void gfs2_free_journal_extents(struct gfs2_jdesc *jd);
+int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length);
+
+#endif /* __BMAP_DOT_H__ */