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, 79 insertions, 0 deletions

diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
new file mode 100644
index 000000000..778a38093
--- /dev/null
+++ b/net/netlink/af_netlink.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _AF_NETLINK_H
+#define _AF_NETLINK_H
+
+#include <linux/rhashtable.h>
+#include <linux/atomic.h>
+#include <net/sock.h>
+
+/* flags */
+enum {
+	NETLINK_F_KERNEL_SOCKET,
+	NETLINK_F_RECV_PKTINFO,
+	NETLINK_F_BROADCAST_SEND_ERROR,
+	NETLINK_F_RECV_NO_ENOBUFS,
+	NETLINK_F_LISTEN_ALL_NSID,
+	NETLINK_F_CAP_ACK,
+	NETLINK_F_EXT_ACK,
+	NETLINK_F_STRICT_CHK,
+};
+
+#define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
+#define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
+
+struct netlink_sock {
+	/* struct sock has to be the first member of netlink_sock */
+	struct sock		sk;
+	unsigned long		flags;
+	u32			portid;
+	u32			dst_portid;
+	u32			dst_group;
+	u32			subscriptions;
+	u32			ngroups;
+	unsigned long		*groups;
+	unsigned long		state;
+	size_t			max_recvmsg_len;
+	wait_queue_head_t	wait;
+	bool			bound;
+	bool			cb_running;
+	int			dump_done_errno;
+	struct netlink_callback	cb;
+	struct mutex		nl_cb_mutex;
+
+	void			(*netlink_rcv)(struct sk_buff *skb);
+	int			(*netlink_bind)(struct net *net, int group);
+	void			(*netlink_unbind)(struct net *net, int group);
+	void			(*netlink_release)(struct sock *sk,
+						   unsigned long *groups);
+	struct module		*module;
+
+	struct rhash_head	node;
+	struct rcu_head		rcu;
+};
+
+static inline struct netlink_sock *nlk_sk(struct sock *sk)
+{
+	return container_of(sk, struct netlink_sock, sk);
+}
+
+#define nlk_test_bit(nr, sk) test_bit(NETLINK_F_##nr, &nlk_sk(sk)->flags)
+
+struct netlink_table {
+	struct rhashtable	hash;
+	struct hlist_head	mc_list;
+	struct listeners __rcu	*listeners;
+	unsigned int		flags;
+	unsigned int		groups;
+	struct mutex		*cb_mutex;
+	struct module		*module;
+	int			(*bind)(struct net *net, int group);
+	void			(*unbind)(struct net *net, int group);
+	void                    (*release)(struct sock *sk,
+					   unsigned long *groups);
+	int			registered;
+};
+
+extern struct netlink_table *nl_table;
+extern rwlock_t nl_table_lock;
+
+#endif