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, 119 insertions, 0 deletions

diff --git a/include/net/protocol.h b/include/net/protocol.h
new file mode 100644
index 000000000..b2499f88f
--- /dev/null
+++ b/include/net/protocol.h
@@ -0,0 +1,119 @@
+/* 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 protocol dispatcher.
+ *
+ * Version:	@(#)protocol.h	1.0.2	05/07/93
+ *
+ * Author:	Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ *	Changes:
+ *		Alan Cox	:	Added a name field and a frag handler
+ *					field for later.
+ *		Alan Cox	:	Cleaned up, and sorted types.
+ *		Pedro Roque	:	inet6 protocols
+ */
+ 
+#ifndef _PROTOCOL_H
+#define _PROTOCOL_H
+
+#include <linux/in6.h>
+#include <linux/skbuff.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <linux/ipv6.h>
+#endif
+#include <linux/netdevice.h>
+
+/* This is one larger than the largest protocol value that can be
+ * found in an ipv4 or ipv6 header.  Since in both cases the protocol
+ * value is presented in a __u8, this is defined to be 256.
+ */
+#define MAX_INET_PROTOS		256
+
+/* This is used to register protocols. */
+struct net_protocol {
+	int			(*handler)(struct sk_buff *skb);
+
+	/* This returns an error if we weren't able to handle the error. */
+	int			(*err_handler)(struct sk_buff *skb, u32 info);
+
+	unsigned int		no_policy:1,
+				/* does the protocol do more stringent
+				 * icmp tag validation than simple
+				 * socket lookup?
+				 */
+				icmp_strict_tag_validation:1;
+	u32			secret;
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+struct inet6_protocol {
+	int	(*handler)(struct sk_buff *skb);
+
+	/* This returns an error if we weren't able to handle the error. */
+	int	(*err_handler)(struct sk_buff *skb,
+			       struct inet6_skb_parm *opt,
+			       u8 type, u8 code, int offset,
+			       __be32 info);
+
+	unsigned int	flags;	/* INET6_PROTO_xxx */
+	u32		secret;
+};
+
+#define INET6_PROTO_NOPOLICY	0x1
+#define INET6_PROTO_FINAL	0x2
+#endif
+
+struct net_offload {
+	struct offload_callbacks callbacks;
+	unsigned int		 flags;	/* Flags used by IPv6 for now */
+	u32			 secret;
+};
+/* This should be set for any extension header which is compatible with GSO. */
+#define INET6_PROTO_GSO_EXTHDR	0x1
+
+/* This is used to register socket interfaces for IP protocols.  */
+struct inet_protosw {
+	struct list_head list;
+
+        /* These two fields form the lookup key.  */
+	unsigned short	 type;	   /* This is the 2nd argument to socket(2). */
+	unsigned short	 protocol; /* This is the L4 protocol number.  */
+
+	struct proto	 *prot;
+	const struct proto_ops *ops;
+  
+	unsigned char	 flags;      /* See INET_PROTOSW_* below.  */
+};
+#define INET_PROTOSW_REUSE 0x01	     /* Are ports automatically reusable? */
+#define INET_PROTOSW_PERMANENT 0x02  /* Permanent protocols are unremovable. */
+#define INET_PROTOSW_ICSK      0x04  /* Is this an inet_connection_sock? */
+
+extern struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
+extern const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS];
+extern const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS];
+
+#if IS_ENABLED(CONFIG_IPV6)
+extern struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
+#endif
+
+int inet_add_protocol(const struct net_protocol *prot, unsigned char num);
+int inet_del_protocol(const struct net_protocol *prot, unsigned char num);
+int inet_add_offload(const struct net_offload *prot, unsigned char num);
+int inet_del_offload(const struct net_offload *prot, unsigned char num);
+void inet_register_protosw(struct inet_protosw *p);
+void inet_unregister_protosw(struct inet_protosw *p);
+
+#if IS_ENABLED(CONFIG_IPV6)
+int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num);
+int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num);
+int inet6_register_protosw(struct inet_protosw *p);
+void inet6_unregister_protosw(struct inet_protosw *p);
+#endif
+int inet6_add_offload(const struct net_offload *prot, unsigned char num);
+int inet6_del_offload(const struct net_offload *prot, unsigned char num);
+
+#endif	/* _PROTOCOL_H */