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, 65 insertions, 0 deletions

diff --git a/fs/nilfs2/btree.h b/fs/nilfs2/btree.h
new file mode 100644
index 000000000..2a220f716
--- /dev/null
+++ b/fs/nilfs2/btree.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * NILFS B-tree.
+ *
+ * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * Written by Koji Sato.
+ */
+
+#ifndef _NILFS_BTREE_H
+#define _NILFS_BTREE_H
+
+#include <linux/types.h>
+#include <linux/buffer_head.h>
+#include <linux/list.h>
+#include <linux/nilfs2_ondisk.h>	/* nilfs_btree_node */
+#include "btnode.h"
+#include "bmap.h"
+
+/**
+ * struct nilfs_btree_path - A path on which B-tree operations are executed
+ * @bp_bh: buffer head of node block
+ * @bp_sib_bh: buffer head of sibling node block
+ * @bp_index: index of child node
+ * @bp_oldreq: ptr end request for old ptr
+ * @bp_newreq: ptr alloc request for new ptr
+ * @bp_ctxt: context information for changing the key of a b-tree node block
+ * @bp_op: rebalance operation
+ */
+struct nilfs_btree_path {
+	struct buffer_head *bp_bh;
+	struct buffer_head *bp_sib_bh;
+	int bp_index;
+	union nilfs_bmap_ptr_req bp_oldreq;
+	union nilfs_bmap_ptr_req bp_newreq;
+	struct nilfs_btnode_chkey_ctxt bp_ctxt;
+	void (*bp_op)(struct nilfs_bmap *, struct nilfs_btree_path *,
+		      int, __u64 *, __u64 *);
+};
+
+#define NILFS_BTREE_ROOT_SIZE		NILFS_BMAP_SIZE
+#define NILFS_BTREE_ROOT_NCHILDREN_MAX					\
+	((NILFS_BTREE_ROOT_SIZE - sizeof(struct nilfs_btree_node)) /	\
+	 (sizeof(__le64 /* dkey */) + sizeof(__le64 /* dptr */)))
+#define NILFS_BTREE_ROOT_NCHILDREN_MIN	0
+#define NILFS_BTREE_NODE_EXTRA_PAD_SIZE	(sizeof(__le64))
+#define NILFS_BTREE_NODE_NCHILDREN_MAX(nodesize)			\
+	(((nodesize) - sizeof(struct nilfs_btree_node) -		\
+		NILFS_BTREE_NODE_EXTRA_PAD_SIZE) /			\
+	 (sizeof(__le64 /* dkey */) + sizeof(__le64 /* dptr */)))
+#define NILFS_BTREE_NODE_NCHILDREN_MIN(nodesize)			\
+	((NILFS_BTREE_NODE_NCHILDREN_MAX(nodesize) - 1) / 2 + 1)
+#define NILFS_BTREE_KEY_MIN	((__u64)0)
+#define NILFS_BTREE_KEY_MAX	(~(__u64)0)
+
+extern struct kmem_cache *nilfs_btree_path_cache;
+
+int nilfs_btree_init(struct nilfs_bmap *);
+int nilfs_btree_convert_and_insert(struct nilfs_bmap *, __u64, __u64,
+				   const __u64 *, const __u64 *, int);
+void nilfs_btree_init_gc(struct nilfs_bmap *);
+
+int nilfs_btree_broken_node_block(struct buffer_head *bh);
+
+#endif	/* _NILFS_BTREE_H */