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, 63 insertions, 0 deletions

diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
new file mode 100644
index 000000000..10beda624
--- /dev/null
+++ b/fs/gfs2/log.h
@@ -0,0 +1,63 @@
+/* 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 __LOG_DOT_H__
+#define __LOG_DOT_H__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/writeback.h>
+#include "incore.h"
+#include "inode.h"
+
+/*
+ * The minimum amount of log space required for a log flush is one block for
+ * revokes and one block for the log header.  Log flushes other than
+ * GFS2_LOG_HEAD_FLUSH_NORMAL may write one or two more log headers.
+ */
+#define GFS2_LOG_FLUSH_MIN_BLOCKS 4
+
+static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+	if (gfs2_is_jdata(ip) || !gfs2_is_ordered(sdp))
+		return;
+
+	if (list_empty(&ip->i_ordered)) {
+		spin_lock(&sdp->sd_ordered_lock);
+		if (list_empty(&ip->i_ordered))
+			list_add(&ip->i_ordered, &sdp->sd_log_ordered);
+		spin_unlock(&sdp->sd_ordered_lock);
+	}
+}
+
+void gfs2_ordered_del_inode(struct gfs2_inode *ip);
+unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct);
+bool gfs2_log_is_empty(struct gfs2_sbd *sdp);
+void gfs2_log_release_revokes(struct gfs2_sbd *sdp, unsigned int revokes);
+void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
+bool gfs2_log_try_reserve(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+			  unsigned int *extra_revokes);
+void gfs2_log_reserve(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+		      unsigned int *extra_revokes);
+void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
+			   u64 seq, u32 tail, u32 lblock, u32 flags,
+			   blk_opf_t op_flags);
+void gfs2_remove_from_journal(struct buffer_head *bh, int meta);
+void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
+		    u32 type);
+void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
+void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc);
+void log_flush_wait(struct gfs2_sbd *sdp);
+
+int gfs2_logd(void *data);
+void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
+void gfs2_glock_remove_revoke(struct gfs2_glock *gl);
+void gfs2_flush_revokes(struct gfs2_sbd *sdp);
+void gfs2_ail_drain(struct gfs2_sbd *sdp);
+
+#endif /* __LOG_DOT_H__ */