net: Generalize socket rx gap / receive queue overflow cmsg
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/atm/common.c b/net/atm/common.c
index 950bd16..d61e051 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -496,7 +496,7 @@
error = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
if (error)
return error;
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
pr_debug("RcvM %d -= %d\n", atomic_read(&sk->sk_rmem_alloc), skb->truesize);
atm_return(vcc, skb->truesize);
skb_free_datagram(sk, skb);
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 1f6e49c..399e59c 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -257,7 +257,7 @@
skb_reset_transport_header(skb);
err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
if (err == 0)
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
skb_free_datagram(sk, skb);
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index c707865..d3bfc1b 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -703,7 +703,7 @@
copied += chunk;
size -= chunk;
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
if (!(flags & MSG_PEEK)) {
atomic_sub(chunk, &sk->sk_rmem_alloc);
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 597da4f..2f47039 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1534,7 +1534,7 @@
return err;
}
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
if (msg->msg_name) {
msg->msg_namelen = sizeof(struct sockaddr_can);
diff --git a/net/can/raw.c b/net/can/raw.c
index b5e8979..962fc9f 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -702,7 +702,7 @@
return err;
}
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
if (msg->msg_name) {
msg->msg_namelen = sizeof(struct sockaddr_can);
diff --git a/net/core/sock.c b/net/core/sock.c
index 7626b6a..43ca2c9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -276,6 +276,8 @@
{
int err = 0;
int skb_len;
+ unsigned long flags;
+ struct sk_buff_head *list = &sk->sk_receive_queue;
/* Cast sk->rcvbuf to unsigned... It's pointless, but reduces
number of warnings when compiling with -W --ANK
@@ -305,7 +307,10 @@
*/
skb_len = skb->len;
- skb_queue_tail(&sk->sk_receive_queue, skb);
+ spin_lock_irqsave(&list->lock, flags);
+ skb->dropcount = atomic_read(&sk->sk_drops);
+ __skb_queue_tail(list, skb);
+ spin_unlock_irqrestore(&list->lock, flags);
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_data_ready(sk, skb_len);
@@ -702,6 +707,12 @@
/* We implement the SO_SNDLOWAT etc to
not be settable (1003.1g 5.3) */
+ case SO_RXQ_OVFL:
+ if (valbool)
+ sock_set_flag(sk, SOCK_RXQ_OVFL);
+ else
+ sock_reset_flag(sk, SOCK_RXQ_OVFL);
+ break;
default:
ret = -ENOPROTOOPT;
break;
@@ -901,6 +912,10 @@
v.val = sk->sk_mark;
break;
+ case SO_RXQ_OVFL:
+ v.val = !!sock_flag(sk, SOCK_RXQ_OVFL);
+ break;
+
default:
return -ENOPROTOOPT;
}
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index a413b1b..25ad956 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -303,7 +303,7 @@
if (err)
goto done;
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
if (flags & MSG_TRUNC)
copied = skb->len;
diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c
index 30e74ee..769c8d1 100644
--- a/net/ieee802154/raw.c
+++ b/net/ieee802154/raw.c
@@ -191,7 +191,7 @@
if (err)
goto done;
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
if (flags & MSG_TRUNC)
copied = skb->len;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 757c917..f18172b 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -682,7 +682,7 @@
if (err)
goto done;
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
/* Copy the address. */
if (sin) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 194bcdc..71e5353 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -955,7 +955,7 @@
UDP_INC_STATS_USER(sock_net(sk),
UDP_MIB_INDATAGRAMS, is_udplite);
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
/* Copy the address. */
if (sin) {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 4f24570..d8375bc 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -497,7 +497,7 @@
sin6->sin6_scope_id = IP6CB(skb)->iif;
}
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
if (np->rxopt.all)
datagram_recv_ctl(sk, msg, skb);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index ff778c1..1f8e2af 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -252,7 +252,7 @@
UDP_MIB_INDATAGRAMS, is_udplite);
}
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
/* Copy the address. */
if (msg->msg_name) {
diff --git a/net/key/af_key.c b/net/key/af_key.c
index c078ae6..472f659 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3606,7 +3606,7 @@
if (err)
goto out_free;
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
err = (flags & MSG_TRUNC) ? skb->len : copied;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f87ed48..bf3a295 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -627,15 +627,14 @@
spin_lock(&sk->sk_receive_queue.lock);
po->stats.tp_packets++;
+ skb->dropcount = atomic_read(&sk->sk_drops);
__skb_queue_tail(&sk->sk_receive_queue, skb);
spin_unlock(&sk->sk_receive_queue.lock);
sk->sk_data_ready(sk, skb->len);
return 0;
drop_n_acct:
- spin_lock(&sk->sk_receive_queue.lock);
- po->stats.tp_drops++;
- spin_unlock(&sk->sk_receive_queue.lock);
+ po->stats.tp_drops = atomic_inc_return(&sk->sk_drops);
drop_n_restore:
if (skb_head != skb->data && skb_shared(skb)) {
@@ -1478,7 +1477,7 @@
if (err)
goto out_free;
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
if (msg->msg_name)
memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index a39bf97..60c2b94e 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -146,7 +146,7 @@
memcpy(msg->msg_name,
&call->conn->trans->peer->srx,
sizeof(call->conn->trans->peer->srx));
- sock_recv_timestamp(msg, &rx->sk, skb);
+ sock_recv_ts_and_drops(msg, &rx->sk, skb);
}
/* receive the message */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index c8d0575..0970e92 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1958,7 +1958,7 @@
if (err)
goto out_free;
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
if (sctp_ulpevent_is_notification(event)) {
msg->msg_flags |= MSG_NOTIFICATION;
sp->pf->event_msgname(event, msg->msg_name, addr_len);
diff --git a/net/socket.c b/net/socket.c
index 954f338..8079356 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -668,6 +668,21 @@
EXPORT_SYMBOL_GPL(__sock_recv_timestamp);
+inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
+{
+ if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount)
+ put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL,
+ sizeof(__u32), &skb->dropcount);
+}
+
+void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
+ struct sk_buff *skb)
+{
+ sock_recv_timestamp(msg, sk, skb);
+ sock_recv_drops(msg, sk, skb);
+}
+EXPORT_SYMBOL_GPL(sock_recv_ts_and_drops);
+
static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size, int flags)
{