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, 95 insertions, 0 deletions

diff --git a/net/handshake/handshake.h b/net/handshake/handshake.h
new file mode 100644
index 000000000..da61cadd1
--- /dev/null
+++ b/net/handshake/handshake.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Generic netlink handshake service
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+
+#ifndef _INTERNAL_HANDSHAKE_H
+#define _INTERNAL_HANDSHAKE_H
+
+/* Per-net namespace context */
+struct handshake_net {
+	spinlock_t		hn_lock;	/* protects next 3 fields */
+	int			hn_pending;
+	int			hn_pending_max;
+	struct list_head	hn_requests;
+
+	unsigned long		hn_flags;
+};
+
+enum hn_flags_bits {
+	HANDSHAKE_F_NET_DRAINING,
+};
+
+struct file;
+struct handshake_proto;
+
+/* One handshake request */
+struct handshake_req {
+	struct list_head		hr_list;
+	struct rhash_head		hr_rhash;
+	unsigned long			hr_flags;
+	const struct handshake_proto	*hr_proto;
+	struct file			*hr_file;
+	struct sock			*hr_sk;
+	void				(*hr_odestruct)(struct sock *sk);
+
+	/* Always the last field */
+	char				hr_priv[];
+};
+
+enum hr_flags_bits {
+	HANDSHAKE_F_REQ_COMPLETED,
+	HANDSHAKE_F_REQ_SESSION,
+};
+
+struct genl_info;
+
+/* Invariants for all handshake requests for one transport layer
+ * security protocol
+ */
+struct handshake_proto {
+	int			hp_handler_class;
+	size_t			hp_privsize;
+	unsigned long		hp_flags;
+
+	int			(*hp_accept)(struct handshake_req *req,
+					     struct genl_info *info, int fd);
+	void			(*hp_done)(struct handshake_req *req,
+					   int status,
+					   struct genl_info *info);
+	void			(*hp_destroy)(struct handshake_req *req);
+};
+
+enum hp_flags_bits {
+	HANDSHAKE_F_PROTO_NOTIFY,
+};
+
+/* alert.c */
+int tls_alert_send(struct socket *sock, u8 level, u8 description);
+
+/* netlink.c */
+int handshake_genl_notify(struct net *net, const struct handshake_proto *proto,
+			  gfp_t flags);
+struct nlmsghdr *handshake_genl_put(struct sk_buff *msg,
+				    struct genl_info *info);
+struct handshake_net *handshake_pernet(struct net *net);
+
+/* request.c */
+struct handshake_req *handshake_req_alloc(const struct handshake_proto *proto,
+					  gfp_t flags);
+int handshake_req_hash_init(void);
+void handshake_req_hash_destroy(void);
+void *handshake_req_private(struct handshake_req *req);
+struct handshake_req *handshake_req_hash_lookup(struct sock *sk);
+struct handshake_req *handshake_req_next(struct handshake_net *hn, int class);
+int handshake_req_submit(struct socket *sock, struct handshake_req *req,
+			 gfp_t flags);
+void handshake_complete(struct handshake_req *req, int status,
+			struct genl_info *info);
+bool handshake_req_cancel(struct sock *sk);
+
+#endif /* _INTERNAL_HANDSHAKE_H */