| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20210615021342.7416-2-xiyou.wangcong@gmail.com>
Date: Mon, 14 Jun 2021 19:13:35 -0700
From: Cong Wang <xiyou.wangcong@...il.com>
To: netdev@...r.kernel.org
Cc: bpf@...r.kernel.org, Cong Wang <cong.wang@...edance.com>,
John Fastabend <john.fastabend@...il.com>,
Daniel Borkmann <daniel@...earbox.net>,
Jakub Sitnicki <jakub@...udflare.com>,
Lorenz Bauer <lmb@...udflare.com>
Subject: [PATCH RESEND bpf v3 1/8] skmsg: improve udp_bpf_recvmsg() accuracy
From: Cong Wang <cong.wang@...edance.com>
I tried to reuse sk_msg_wait_data() for different protocols,
but it turns out it can not be simply reused. For example,
UDP actually uses two queues to receive skb:
udp_sk(sk)->reader_queue and sk->sk_receive_queue. So we have
to check both of them to know whether we have received any
packet.
Also, UDP does not lock the sock during BH Rx path, it makes
no sense for its ->recvmsg() to lock the sock. It is always
possible for ->recvmsg() to be called before packets actually
arrive in the receive queue, we just use best effort to make
it accurate here.
Fixes: 1f5be6b3b063 ("udp: Implement udp_bpf_recvmsg() for sockmap")
Cc: John Fastabend <john.fastabend@...il.com>
Cc: Daniel Borkmann <daniel@...earbox.net>
Cc: Jakub Sitnicki <jakub@...udflare.com>
Cc: Lorenz Bauer <lmb@...udflare.com>
Signed-off-by: Cong Wang <cong.wang@...edance.com>
---
include/linux/skmsg.h | 2 --
net/core/skmsg.c | 23 ---------------------
net/ipv4/tcp_bpf.c | 24 +++++++++++++++++++++-
net/ipv4/udp_bpf.c | 47 ++++++++++++++++++++++++++++++++++++++-----
4 files changed, 65 insertions(+), 31 deletions(-)
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index aba0f0f429be..e3d080c299f6 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -126,8 +126,6 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
struct sk_msg *msg, u32 bytes);
int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
struct sk_msg *msg, u32 bytes);
-int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
- long timeo, int *err);
int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
int len, int flags);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 43ce17a6a585..f9a81b314e4c 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -399,29 +399,6 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
}
EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
-int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
- long timeo, int *err)
-{
- 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 = sk_wait_event(sk, &timeo,
- !list_empty(&psock->ingress_msg) ||
- !skb_queue_empty(&sk->sk_receive_queue), &wait);
- sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- remove_wait_queue(sk_sleep(sk), &wait);
- return ret;
-}
-EXPORT_SYMBOL_GPL(sk_msg_wait_data);
-
/* Receive sk_msg from psock->ingress_msg to @msg. */
int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
int len, int flags)
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ad9d17923fc5..bb49b52d7be8 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -163,6 +163,28 @@ static bool tcp_bpf_stream_read(const struct sock *sk)
return !empty;
}
+static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
+ long timeo, int *err)
+{
+ 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 = sk_wait_event(sk, &timeo,
+ !list_empty(&psock->ingress_msg) ||
+ !skb_queue_empty(&sk->sk_receive_queue), &wait);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
+ return ret;
+}
+
static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len)
{
@@ -188,7 +210,7 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
long timeo;
timeo = sock_rcvtimeo(sk, nonblock);
- data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
+ data = tcp_msg_wait_data(sk, psock, flags, timeo, &err);
if (data) {
if (!sk_psock_queue_empty(psock))
goto msg_bytes_ready;
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 954c4591a6fd..565a70040c57 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -21,6 +21,45 @@ static int sk_udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
return udp_prot.recvmsg(sk, msg, len, noblock, flags, addr_len);
}
+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, int flags,
+ long timeo, int *err)
+{
+ 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) {
+ wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+ 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 nonblock, int flags, int *addr_len)
{
@@ -34,8 +73,7 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
if (unlikely(!psock))
return sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
- lock_sock(sk);
- if (sk_psock_queue_empty(psock)) {
+ if (!psock_has_data(psock)) {
ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
goto out;
}
@@ -47,9 +85,9 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
long timeo;
timeo = sock_rcvtimeo(sk, nonblock);
- data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
+ data = udp_msg_wait_data(sk, psock, flags, timeo, &err);
if (data) {
- if (!sk_psock_queue_empty(psock))
+ if (psock_has_data(psock))
goto msg_bytes_ready;
ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
goto out;
@@ -62,7 +100,6 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
}
ret = copied;
out:
- release_sock(sk);
sk_psock_put(sk, psock);
return ret;
}
--
2.25.1
Powered by blists - more mailing lists