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, 298 insertions, 0 deletions

diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
new file mode 100644
index 000000000..4c1f836aa
--- /dev/null
+++ b/net/ipv4/tunnel4.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* tunnel4.c: Generic IP tunnel transformer.
+ *
+ * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/mpls.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/protocol.h>
+#include <net/xfrm.h>
+
+static struct xfrm_tunnel __rcu *tunnel4_handlers __read_mostly;
+static struct xfrm_tunnel __rcu *tunnel64_handlers __read_mostly;
+static struct xfrm_tunnel __rcu *tunnelmpls4_handlers __read_mostly;
+static DEFINE_MUTEX(tunnel4_mutex);
+
+static inline struct xfrm_tunnel __rcu **fam_handlers(unsigned short family)
+{
+	return (family == AF_INET) ? &tunnel4_handlers :
+		(family == AF_INET6) ? &tunnel64_handlers :
+		&tunnelmpls4_handlers;
+}
+
+int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family)
+{
+	struct xfrm_tunnel __rcu **pprev;
+	struct xfrm_tunnel *t;
+
+	int ret = -EEXIST;
+	int priority = handler->priority;
+
+	mutex_lock(&tunnel4_mutex);
+
+	for (pprev = fam_handlers(family);
+	     (t = rcu_dereference_protected(*pprev,
+			lockdep_is_held(&tunnel4_mutex))) != NULL;
+	     pprev = &t->next) {
+		if (t->priority > priority)
+			break;
+		if (t->priority == priority)
+			goto err;
+	}
+
+	handler->next = *pprev;
+	rcu_assign_pointer(*pprev, handler);
+
+	ret = 0;
+
+err:
+	mutex_unlock(&tunnel4_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL(xfrm4_tunnel_register);
+
+int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family)
+{
+	struct xfrm_tunnel __rcu **pprev;
+	struct xfrm_tunnel *t;
+	int ret = -ENOENT;
+
+	mutex_lock(&tunnel4_mutex);
+
+	for (pprev = fam_handlers(family);
+	     (t = rcu_dereference_protected(*pprev,
+			lockdep_is_held(&tunnel4_mutex))) != NULL;
+	     pprev = &t->next) {
+		if (t == handler) {
+			*pprev = handler->next;
+			ret = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&tunnel4_mutex);
+
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL(xfrm4_tunnel_deregister);
+
+#define for_each_tunnel_rcu(head, handler)		\
+	for (handler = rcu_dereference(head);		\
+	     handler != NULL;				\
+	     handler = rcu_dereference(handler->next))	\
+
+static int tunnel4_rcv(struct sk_buff *skb)
+{
+	struct xfrm_tunnel *handler;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		goto drop;
+
+	for_each_tunnel_rcu(tunnel4_handlers, handler)
+		if (!handler->handler(skb))
+			return 0;
+
+	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+drop:
+	kfree_skb(skb);
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL)
+static int tunnel4_rcv_cb(struct sk_buff *skb, u8 proto, int err)
+{
+	struct xfrm_tunnel __rcu *head;
+	struct xfrm_tunnel *handler;
+	int ret;
+
+	head = (proto == IPPROTO_IPIP) ? tunnel4_handlers : tunnel64_handlers;
+
+	for_each_tunnel_rcu(head, handler) {
+		if (handler->cb_handler) {
+			ret = handler->cb_handler(skb, err);
+			if (ret <= 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static const struct xfrm_input_afinfo tunnel4_input_afinfo = {
+	.family		=	AF_INET,
+	.is_ipip	=	true,
+	.callback	=	tunnel4_rcv_cb,
+};
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int tunnel64_rcv(struct sk_buff *skb)
+{
+	struct xfrm_tunnel *handler;
+
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+		goto drop;
+
+	for_each_tunnel_rcu(tunnel64_handlers, handler)
+		if (!handler->handler(skb))
+			return 0;
+
+	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+drop:
+	kfree_skb(skb);
+	return 0;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_MPLS)
+static int tunnelmpls4_rcv(struct sk_buff *skb)
+{
+	struct xfrm_tunnel *handler;
+
+	if (!pskb_may_pull(skb, sizeof(struct mpls_label)))
+		goto drop;
+
+	for_each_tunnel_rcu(tunnelmpls4_handlers, handler)
+		if (!handler->handler(skb))
+			return 0;
+
+	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+drop:
+	kfree_skb(skb);
+	return 0;
+}
+#endif
+
+static int tunnel4_err(struct sk_buff *skb, u32 info)
+{
+	struct xfrm_tunnel *handler;
+
+	for_each_tunnel_rcu(tunnel4_handlers, handler)
+		if (!handler->err_handler(skb, info))
+			return 0;
+
+	return -ENOENT;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int tunnel64_err(struct sk_buff *skb, u32 info)
+{
+	struct xfrm_tunnel *handler;
+
+	for_each_tunnel_rcu(tunnel64_handlers, handler)
+		if (!handler->err_handler(skb, info))
+			return 0;
+
+	return -ENOENT;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_MPLS)
+static int tunnelmpls4_err(struct sk_buff *skb, u32 info)
+{
+	struct xfrm_tunnel *handler;
+
+	for_each_tunnel_rcu(tunnelmpls4_handlers, handler)
+		if (!handler->err_handler(skb, info))
+			return 0;
+
+	return -ENOENT;
+}
+#endif
+
+static const struct net_protocol tunnel4_protocol = {
+	.handler	=	tunnel4_rcv,
+	.err_handler	=	tunnel4_err,
+	.no_policy	=	1,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static const struct net_protocol tunnel64_protocol = {
+	.handler	=	tunnel64_rcv,
+	.err_handler	=	tunnel64_err,
+	.no_policy	=	1,
+};
+#endif
+
+#if IS_ENABLED(CONFIG_MPLS)
+static const struct net_protocol tunnelmpls4_protocol = {
+	.handler	=	tunnelmpls4_rcv,
+	.err_handler	=	tunnelmpls4_err,
+	.no_policy	=	1,
+};
+#endif
+
+static int __init tunnel4_init(void)
+{
+	if (inet_add_protocol(&tunnel4_protocol, IPPROTO_IPIP))
+		goto err;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (inet_add_protocol(&tunnel64_protocol, IPPROTO_IPV6)) {
+		inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP);
+		goto err;
+	}
+#endif
+#if IS_ENABLED(CONFIG_MPLS)
+	if (inet_add_protocol(&tunnelmpls4_protocol, IPPROTO_MPLS)) {
+		inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP);
+#if IS_ENABLED(CONFIG_IPV6)
+		inet_del_protocol(&tunnel64_protocol, IPPROTO_IPV6);
+#endif
+		goto err;
+	}
+#endif
+#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL)
+	if (xfrm_input_register_afinfo(&tunnel4_input_afinfo)) {
+		inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP);
+#if IS_ENABLED(CONFIG_IPV6)
+		inet_del_protocol(&tunnel64_protocol, IPPROTO_IPV6);
+#endif
+#if IS_ENABLED(CONFIG_MPLS)
+		inet_del_protocol(&tunnelmpls4_protocol, IPPROTO_MPLS);
+#endif
+		goto err;
+	}
+#endif
+	return 0;
+
+err:
+	pr_err("%s: can't add protocol\n", __func__);
+	return -EAGAIN;
+}
+
+static void __exit tunnel4_fini(void)
+{
+#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL)
+	if (xfrm_input_unregister_afinfo(&tunnel4_input_afinfo))
+		pr_err("tunnel4 close: can't remove input afinfo\n");
+#endif
+#if IS_ENABLED(CONFIG_MPLS)
+	if (inet_del_protocol(&tunnelmpls4_protocol, IPPROTO_MPLS))
+		pr_err("tunnelmpls4 close: can't remove protocol\n");
+#endif
+#if IS_ENABLED(CONFIG_IPV6)
+	if (inet_del_protocol(&tunnel64_protocol, IPPROTO_IPV6))
+		pr_err("tunnel64 close: can't remove protocol\n");
+#endif
+	if (inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP))
+		pr_err("tunnel4 close: can't remove protocol\n");
+}
+
+module_init(tunnel4_init);
+module_exit(tunnel4_fini);
+MODULE_DESCRIPTION("IPv4 XFRM tunnel library");
+MODULE_LICENSE("GPL");