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, 179 insertions, 0 deletions

diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
new file mode 100644
index 000000000..ad57c4c9e
--- /dev/null
+++ b/net/ipv4/udp_bpf.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Cloudflare Ltd https://cloudflare.com */
+
+#include <linux/skmsg.h>
+#include <net/sock.h>
+#include <net/udp.h>
+#include <net/inet_common.h>
+#include <asm/ioctls.h>
+
+static struct proto *udpv6_prot_saved __read_mostly;
+
+static int sk_udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			  int flags)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6)
+		return udpv6_prot_saved->recvmsg(sk, msg, len, flags);
+#endif
+	return udp_prot.recvmsg(sk, msg, len, flags);
+}
+
+static bool udp_sk_has_data(struct sock *sk)
+{
+	return !skb_queue_empty(&udp_sk(sk)->reader_queue) ||
+	       !skb_queue_empty(&sk->sk_receive_queue);
+}
+
+static bool psock_has_data(struct sk_psock *psock)
+{
+	return !skb_queue_empty(&psock->ingress_skb) ||
+	       !sk_psock_queue_empty(psock);
+}
+
+#define udp_msg_has_data(__sk, __psock)	\
+		({ udp_sk_has_data(__sk) || psock_has_data(__psock); })
+
+static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
+			     long timeo)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	int ret = 0;
+
+	if (sk->sk_shutdown & RCV_SHUTDOWN)
+		return 1;
+
+	if (!timeo)
+		return ret;
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	ret = udp_msg_has_data(sk, psock);
+	if (!ret) {
+		release_sock(sk);
+		wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+		lock_sock(sk);
+		ret = udp_msg_has_data(sk, psock);
+	}
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	remove_wait_queue(sk_sleep(sk), &wait);
+	return ret;
+}
+
+static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			   int flags)
+{
+	struct sk_psock *psock;
+	int copied, ret;
+
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len);
+
+	if (!len)
+		return 0;
+
+	psock = sk_psock_get(sk);
+	if (unlikely(!psock))
+		return sk_udp_recvmsg(sk, msg, len, flags);
+
+	if (!psock_has_data(psock)) {
+		ret = sk_udp_recvmsg(sk, msg, len, flags);
+		goto out;
+	}
+
+	lock_sock(sk);
+msg_bytes_ready:
+	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	if (!copied) {
+		long timeo;
+		int data;
+
+		timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+		data = udp_msg_wait_data(sk, psock, timeo);
+		if (data) {
+			if (psock_has_data(psock))
+				goto msg_bytes_ready;
+
+			release_sock(sk);
+
+			ret = sk_udp_recvmsg(sk, msg, len, flags);
+			goto out;
+		}
+		copied = -EAGAIN;
+	}
+
+	release_sock(sk);
+
+	ret = copied;
+out:
+	sk_psock_put(sk, psock);
+	return ret;
+}
+
+enum {
+	UDP_BPF_IPV4,
+	UDP_BPF_IPV6,
+	UDP_BPF_NUM_PROTS,
+};
+
+static DEFINE_SPINLOCK(udpv6_prot_lock);
+static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS];
+
+static int udp_bpf_ioctl(struct sock *sk, int cmd, int *karg)
+{
+	if (cmd != SIOCINQ)
+		return udp_ioctl(sk, cmd, karg);
+
+	/* Since we don't hold a lock, sk_receive_queue may contain data.
+	 * BPF might only be processing this data at the moment. We only
+	 * care about the data in the ingress_msg here.
+	 */
+	*karg = sk_msg_first_len(sk);
+	return 0;
+}
+
+static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
+{
+	*prot			= *base;
+	prot->close		= sock_map_close;
+	prot->recvmsg		= udp_bpf_recvmsg;
+	prot->sock_is_readable	= sk_msg_is_readable;
+	prot->ioctl		= udp_bpf_ioctl;
+}
+
+static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
+{
+	if (unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
+		spin_lock_bh(&udpv6_prot_lock);
+		if (likely(ops != udpv6_prot_saved)) {
+			udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops);
+			smp_store_release(&udpv6_prot_saved, ops);
+		}
+		spin_unlock_bh(&udpv6_prot_lock);
+	}
+}
+
+static int __init udp_bpf_v4_build_proto(void)
+{
+	udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot);
+	return 0;
+}
+late_initcall(udp_bpf_v4_build_proto);
+
+int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
+{
+	int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
+
+	if (restore) {
+		WRITE_ONCE(sk->sk_write_space, psock->saved_write_space);
+		sock_replace_proto(sk, psock->sk_proto);
+		return 0;
+	}
+
+	if (sk->sk_family == AF_INET6)
+		udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
+
+	sock_replace_proto(sk, &udp_bpf_prots[family]);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(udp_bpf_update_proto);