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, 85 insertions, 0 deletions

diff --git a/include/net/ping.h b/include/net/ping.h
new file mode 100644
index 000000000..bcbdb5a13
--- /dev/null
+++ b/include/net/ping.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Definitions for the "ping" module.
+ */
+#ifndef _PING_H
+#define _PING_H
+
+#include <net/icmp.h>
+#include <net/netns/hash.h>
+
+/* PING_HTABLE_SIZE must be power of 2 */
+#define PING_HTABLE_SIZE 	64
+#define PING_HTABLE_MASK 	(PING_HTABLE_SIZE-1)
+
+#define GID_T_MAX (((gid_t)~0U) - 1)
+
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+struct pingv6_ops {
+	int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len);
+	void (*ip6_datagram_recv_common_ctl)(struct sock *sk,
+					     struct msghdr *msg,
+					     struct sk_buff *skb);
+	void (*ip6_datagram_recv_specific_ctl)(struct sock *sk,
+					       struct msghdr *msg,
+					       struct sk_buff *skb);
+	int (*icmpv6_err_convert)(u8 type, u8 code, int *err);
+	void (*ipv6_icmp_error)(struct sock *sk, struct sk_buff *skb, int err,
+				__be16 port, u32 info, u8 *payload);
+	int (*ipv6_chk_addr)(struct net *net, const struct in6_addr *addr,
+			     const struct net_device *dev, int strict);
+};
+
+struct ping_iter_state {
+	struct seq_net_private  p;
+	int			bucket;
+	sa_family_t		family;
+};
+
+extern struct proto ping_prot;
+#if IS_ENABLED(CONFIG_IPV6)
+extern struct pingv6_ops pingv6_ops;
+#endif
+
+struct pingfakehdr {
+	struct icmphdr icmph;
+	struct msghdr *msg;
+	sa_family_t family;
+	__wsum wcheck;
+};
+
+int  ping_get_port(struct sock *sk, unsigned short ident);
+void ping_unhash(struct sock *sk);
+
+int  ping_init_sock(struct sock *sk);
+void ping_close(struct sock *sk, long timeout);
+int  ping_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
+void ping_err(struct sk_buff *skb, int offset, u32 info);
+int  ping_getfrag(void *from, char *to, int offset, int fraglen, int odd,
+		  struct sk_buff *);
+
+int  ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		  int flags);
+int  ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+			 void *user_icmph, size_t icmph_len);
+int  ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+enum skb_drop_reason ping_rcv(struct sk_buff *skb);
+
+#ifdef CONFIG_PROC_FS
+void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family);
+void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+void ping_seq_stop(struct seq_file *seq, void *v);
+
+int __init ping_proc_init(void);
+void ping_proc_exit(void);
+#endif
+
+void __init ping_init(void);
+int  __init pingv6_init(void);
+void pingv6_exit(void);
+
+#endif /* _PING_H */