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, 195 insertions, 0 deletions

diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
new file mode 100644
index 000000000..c666be69f
--- /dev/null
+++ b/fs/xfs/scrub/alloc.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2017-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs_platform.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_btree.h"
+#include "xfs_alloc.h"
+#include "xfs_rmap.h"
+#include "xfs_ag.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/repair.h"
+
+/*
+ * Set us up to scrub free space btrees.
+ */
+int
+xchk_setup_ag_allocbt(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	if (xchk_need_intent_drain(sc))
+		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
+	error = xchk_setup_ag_btree(sc, false);
+	if (error)
+		return error;
+
+	if (xchk_could_repair(sc))
+		return xrep_setup_ag_allocbt(sc);
+
+	return 0;
+}
+
+/* Free space btree scrubber. */
+
+struct xchk_alloc {
+	/* Previous free space extent. */
+	struct xfs_alloc_rec_incore	prev;
+};
+
+/*
+ * Ensure there's a corresponding cntbt/bnobt record matching this
+ * bnobt/cntbt record, respectively.
+ */
+STATIC void
+xchk_allocbt_xref_other(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
+{
+	struct xfs_btree_cur	**pcur;
+	xfs_agblock_t		fbno;
+	xfs_extlen_t		flen;
+	int			has_otherrec;
+	int			error;
+
+	if (sc->sm->sm_type == XFS_SCRUB_TYPE_BNOBT)
+		pcur = &sc->sa.cnt_cur;
+	else
+		pcur = &sc->sa.bno_cur;
+	if (!*pcur || xchk_skip_xref(sc->sm))
+		return;
+
+	error = xfs_alloc_lookup_le(*pcur, agbno, len, &has_otherrec);
+	if (!xchk_should_check_xref(sc, &error, pcur))
+		return;
+	if (!has_otherrec) {
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
+		return;
+	}
+
+	error = xfs_alloc_get_rec(*pcur, &fbno, &flen, &has_otherrec);
+	if (!xchk_should_check_xref(sc, &error, pcur))
+		return;
+	if (!has_otherrec) {
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
+		return;
+	}
+
+	if (fbno != agbno || flen != len)
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
+}
+
+/* Cross-reference with the other btrees. */
+STATIC void
+xchk_allocbt_xref(
+	struct xfs_scrub	*sc,
+	const struct xfs_alloc_rec_incore *irec)
+{
+	xfs_agblock_t		agbno = irec->ar_startblock;
+	xfs_extlen_t		len = irec->ar_blockcount;
+
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return;
+
+	xchk_allocbt_xref_other(sc, agbno, len);
+	xchk_xref_is_not_inode_chunk(sc, agbno, len);
+	xchk_xref_has_no_owner(sc, agbno, len);
+	xchk_xref_is_not_shared(sc, agbno, len);
+	xchk_xref_is_not_cow_staging(sc, agbno, len);
+}
+
+/* Flag failures for records that could be merged. */
+STATIC void
+xchk_allocbt_mergeable(
+	struct xchk_btree	*bs,
+	struct xchk_alloc	*ca,
+	const struct xfs_alloc_rec_incore *irec)
+{
+	if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return;
+
+	if (ca->prev.ar_blockcount > 0 &&
+	    ca->prev.ar_startblock + ca->prev.ar_blockcount == irec->ar_startblock &&
+	    ca->prev.ar_blockcount + irec->ar_blockcount < (uint32_t)~0U)
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+
+	memcpy(&ca->prev, irec, sizeof(*irec));
+}
+
+/* Scrub a bnobt/cntbt record. */
+STATIC int
+xchk_allocbt_rec(
+	struct xchk_btree		*bs,
+	const union xfs_btree_rec	*rec)
+{
+	struct xfs_alloc_rec_incore	irec;
+	struct xchk_alloc		*ca = bs->private;
+
+	xfs_alloc_btrec_to_irec(rec, &irec);
+	if (xfs_alloc_check_irec(to_perag(bs->cur->bc_group), &irec) != NULL) {
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
+		return 0;
+	}
+
+	if (bs->sc->sm->sm_type == XFS_SCRUB_TYPE_BNOBT)
+		xchk_allocbt_mergeable(bs, ca, &irec);
+	xchk_allocbt_xref(bs->sc, &irec);
+
+	return 0;
+}
+
+/* Scrub one of the freespace btrees for some AG. */
+int
+xchk_allocbt(
+	struct xfs_scrub	*sc)
+{
+	struct xchk_alloc	ca = { };
+	struct xfs_btree_cur	*cur;
+
+	switch (sc->sm->sm_type) {
+	case XFS_SCRUB_TYPE_BNOBT:
+		cur = sc->sa.bno_cur;
+		break;
+	case XFS_SCRUB_TYPE_CNTBT:
+		cur = sc->sa.cnt_cur;
+		break;
+	default:
+		ASSERT(0);
+		return -EIO;
+	}
+
+	return xchk_btree(sc, cur, xchk_allocbt_rec, &XFS_RMAP_OINFO_AG, &ca);
+}
+
+/* xref check that the extent is not free */
+void
+xchk_xref_is_used_space(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
+{
+	enum xbtree_recpacking	outcome;
+	int			error;
+
+	if (!sc->sa.bno_cur || xchk_skip_xref(sc->sm))
+		return;
+
+	error = xfs_alloc_has_records(sc->sa.bno_cur, agbno, len, &outcome);
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
+		return;
+	if (outcome != XBTREE_RECPACKING_EMPTY)
+		xchk_btree_xref_set_corrupt(sc, sc->sa.bno_cur, 0);
+}