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, 91 insertions, 0 deletions

diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
new file mode 100644
index 000000000..772557b63
--- /dev/null
+++ b/fs/gfs2/lops.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
+ */
+
+#ifndef __LOPS_DOT_H__
+#define __LOPS_DOT_H__
+
+#include <linux/list.h>
+#include "incore.h"
+
+extern const struct gfs2_log_operations *gfs2_log_ops[];
+
+void gfs2_log_incr_head(struct gfs2_sbd *sdp);
+u64 gfs2_log_bmap(struct gfs2_jdesc *jd, unsigned int lbn);
+void gfs2_log_write(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
+		    struct page *page, unsigned size, unsigned offset,
+		    u64 blkno, blk_opf_t opf);
+void gfs2_log_submit_write(struct bio **biop);
+void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
+int gfs2_find_jhead(struct gfs2_jdesc *jd,
+		    struct gfs2_log_header_host *head);
+void gfs2_drain_revokes(struct gfs2_sbd *sdp);
+
+static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
+{
+	return sdp->sd_ldptrs;
+}
+
+static inline unsigned int databuf_limit(struct gfs2_sbd *sdp)
+{
+	return sdp->sd_ldptrs / 2;
+}
+
+static inline void lops_before_commit(struct gfs2_sbd *sdp,
+				      struct gfs2_trans *tr)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_commit)
+			gfs2_log_ops[x]->lo_before_commit(sdp, tr);
+}
+
+static inline void lops_after_commit(struct gfs2_sbd *sdp,
+				     struct gfs2_trans *tr)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_after_commit)
+			gfs2_log_ops[x]->lo_after_commit(sdp, tr);
+}
+
+static inline void lops_before_scan(struct gfs2_jdesc *jd,
+				    struct gfs2_log_header_host *head,
+				    unsigned int pass)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_scan)
+			gfs2_log_ops[x]->lo_before_scan(jd, head, pass);
+}
+
+static inline int lops_scan_elements(struct gfs2_jdesc *jd, u32 start,
+				     struct gfs2_log_descriptor *ld,
+				     __be64 *ptr,
+				     unsigned int pass)
+{
+	int x, error;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_scan_elements) {
+			error = gfs2_log_ops[x]->lo_scan_elements(jd, start,
+								  ld, ptr, pass);
+			if (error)
+				return error;
+		}
+
+	return 0;
+}
+
+static inline void lops_after_scan(struct gfs2_jdesc *jd, int error,
+				   unsigned int pass)
+{
+	int x;
+	for (x = 0; gfs2_log_ops[x]; x++)
+		if (gfs2_log_ops[x]->lo_before_scan)
+			gfs2_log_ops[x]->lo_after_scan(jd, error, pass);
+}
+
+#endif /* __LOPS_DOT_H__ */
+