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, 77 insertions, 0 deletions

diff --git a/fs/xfs/scrub/rtbitmap.h b/fs/xfs/scrub/rtbitmap.h
new file mode 100644
index 000000000..fe52b8772
--- /dev/null
+++ b/fs/xfs/scrub/rtbitmap.h
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_RTBITMAP_H__
+#define __XFS_SCRUB_RTBITMAP_H__
+
+/*
+ * We use an xfile to construct new bitmap blocks for the portion of the
+ * rtbitmap file that we're replacing.  Whereas the ondisk bitmap must be
+ * accessed through the buffer cache, the xfile bitmap supports direct
+ * word-level accesses.  Therefore, we create a small abstraction for linear
+ * access.
+ */
+typedef unsigned long long xrep_wordoff_t;
+typedef unsigned int xrep_wordcnt_t;
+
+/* Mask to round an rtx down to the nearest bitmap word. */
+#define XREP_RTBMP_WORDMASK	((1ULL << XFS_NBWORDLOG) - 1)
+
+
+struct xchk_rtbitmap {
+	struct xfs_scrub	*sc;
+
+	uint64_t		rextents;
+	uint64_t		rbmblocks;
+	unsigned int		rextslog;
+	unsigned int		resblks;
+
+	/* The next free rt group block number that we expect to see. */
+	xfs_rgblock_t		next_free_rgbno;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+	/* stuff for staging a new bitmap */
+	struct xfs_rtalloc_args	args;
+	struct xrep_tempexch	tempexch;
+#endif
+
+	/* The next rtgroup block we expect to see during our rtrmapbt walk. */
+	xfs_rgblock_t		next_rgbno;
+
+	/* rtgroup lock flags */
+	unsigned int		rtglock_flags;
+
+	/* rtword position of xfile as we write buffers to disk. */
+	xrep_wordoff_t		prep_wordoff;
+
+	/* In-Memory rtbitmap for repair. */
+	union xfs_rtword_raw	words[];
+};
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+int xrep_setup_rtbitmap(struct xfs_scrub *sc, struct xchk_rtbitmap *rtb);
+
+/*
+ * How big should the words[] buffer be?
+ *
+ * For repairs, we want a full fsblock worth of space so that we can memcpy a
+ * buffer full of 1s into the xfile bitmap.  The xfile bitmap doesn't have
+ * rtbitmap block headers, so we don't use blockwsize.  Scrub doesn't use the
+ * words buffer at all.
+ */
+static inline unsigned int
+xchk_rtbitmap_wordcnt(
+	struct xfs_scrub	*sc)
+{
+	if (xchk_could_repair(sc))
+		return sc->mp->m_sb.sb_blocksize >> XFS_WORDLOG;
+	return 0;
+}
+#else
+# define xrep_setup_rtbitmap(sc, rtb)	(0)
+# define xchk_rtbitmap_wordcnt(sc)	(0)
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_RTBITMAP_H__ */