tcp: remove prequeue support

prequeue is a tcp receive optimization that moves part of rx processing
from bh to process context.

This only works if the socket being processed belongs to a process that
is blocked in recv on that socket.

In practice, this doesn't happen anymore that often because nowadays
servers tend to use an event driven (epoll) model.

Even normal client applications (web browsers) commonly use many tcp
connections in parallel.

This has measureable impact only in netperf (which uses plain recv and
thus allows prequeue use) from host to locally running vm (~4%), however,
there were no changes when using netperf between two physical hosts with
ixgbe interfaces.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/tcp.h

@@ -192,15 +192,6 @@ struct tcp_sock {
 
 	struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
 
-	/* Data for direct copy to user */
-	struct {
-		struct sk_buff_head	prequeue;
-		struct task_struct	*task;
-		struct msghdr		*msg;
-		int			memory;
-		int			len;
-	} ucopy;
-
 	u32	snd_wl1;	/* Sequence for window update		*/
 	u32	snd_wnd;	/* The window we expect to receive	*/
 	u32	max_window;	/* Maximal window ever seen from peer	*/

include/net/tcp.h

@@ -1244,17 +1244,6 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb)
 		__tcp_checksum_complete(skb);
 }
 
-/* Prequeue for VJ style copy to user, combined with checksumming. */
-
-static inline void tcp_prequeue_init(struct tcp_sock *tp)
-{
-	tp->ucopy.task = NULL;
-	tp->ucopy.len = 0;
-	tp->ucopy.memory = 0;
-	skb_queue_head_init(&tp->ucopy.prequeue);
-}
-
-bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb);
 int tcp_filter(struct sock *sk, struct sk_buff *skb);
 

net/ipv4/tcp.c

@@ -400,7 +400,6 @@ void tcp_init_sock(struct sock *sk)
 
 	tp->out_of_order_queue = RB_ROOT;
 	tcp_init_xmit_timers(sk);
-	tcp_prequeue_init(tp);
 	INIT_LIST_HEAD(&tp->tsq_node);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
@@ -1525,20 +1524,6 @@ static void tcp_cleanup_rbuf(struct sock *sk, int copied)
 		tcp_send_ack(sk);
 }
 
-static void tcp_prequeue_process(struct sock *sk)
-{
-	struct sk_buff *skb;
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPREQUEUED);
-
-	while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
-		sk_backlog_rcv(sk, skb);
-
-	/* Clear memory counter. */
-	tp->ucopy.memory = 0;
-}
-
 static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 {
 	struct sk_buff *skb;
@@ -1671,7 +1656,6 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	int err;
 	int target;		/* Read at least this many bytes */
 	long timeo;
-	struct task_struct *user_recv = NULL;
 	struct sk_buff *skb, *last;
 	u32 urg_hole = 0;
 
@@ -1806,51 +1790,6 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 
 		tcp_cleanup_rbuf(sk, copied);
 
-		if (!sysctl_tcp_low_latency && tp->ucopy.task == user_recv) {
-			/* Install new reader */
-			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
-				user_recv = current;
-				tp->ucopy.task = user_recv;
-				tp->ucopy.msg = msg;
-			}
-
-			tp->ucopy.len = len;
-
-			WARN_ON(tp->copied_seq != tp->rcv_nxt &&
-				!(flags & (MSG_PEEK | MSG_TRUNC)));
-
-			/* Ugly... If prequeue is not empty, we have to
-			 * process it before releasing socket, otherwise
-			 * order will be broken at second iteration.
-			 * More elegant solution is required!!!
-			 *
-			 * Look: we have the following (pseudo)queues:
-			 *
-			 * 1. packets in flight
-			 * 2. backlog
-			 * 3. prequeue
-			 * 4. receive_queue
-			 *
-			 * Each queue can be processed only if the next ones
-			 * are empty. At this point we have empty receive_queue.
-			 * But prequeue _can_ be not empty after 2nd iteration,
-			 * when we jumped to start of loop because backlog
-			 * processing added something to receive_queue.
-			 * We cannot release_sock(), because backlog contains
-			 * packets arrived _after_ prequeued ones.
-			 *
-			 * Shortly, algorithm is clear --- to process all
-			 * the queues in order. We could make it more directly,
-			 * requeueing packets from backlog to prequeue, if
-			 * is not empty. It is more elegant, but eats cycles,
-			 * unfortunately.
-			 */
-			if (!skb_queue_empty(&tp->ucopy.prequeue))
-				goto do_prequeue;
-
-			/* __ Set realtime policy in scheduler __ */
-		}
-
 		if (copied >= target) {
 			/* Do not sleep, just process backlog. */
 			release_sock(sk);
@@ -1859,31 +1798,6 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 			sk_wait_data(sk, &timeo, last);
 		}
 
-		if (user_recv) {
-			int chunk;
-
-			/* __ Restore normal policy in scheduler __ */
-
-			chunk = len - tp->ucopy.len;
-			if (chunk != 0) {
-				NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);
-				len -= chunk;
-				copied += chunk;
-			}
-
-			if (tp->rcv_nxt == tp->copied_seq &&
-			    !skb_queue_empty(&tp->ucopy.prequeue)) {
-do_prequeue:
-				tcp_prequeue_process(sk);
-
-				chunk = len - tp->ucopy.len;
-				if (chunk != 0) {
-					NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
-					len -= chunk;
-					copied += chunk;
-				}
-			}
-		}
 		if ((flags & MSG_PEEK) &&
 		    (peek_seq - copied - urg_hole != tp->copied_seq)) {
 			net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n",
@@ -1955,25 +1869,6 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		break;
 	} while (len > 0);
 
-	if (user_recv) {
-		if (!skb_queue_empty(&tp->ucopy.prequeue)) {
-			int chunk;
-
-			tp->ucopy.len = copied > 0 ? len : 0;
-
-			tcp_prequeue_process(sk);
-
-			if (copied > 0 && (chunk = len - tp->ucopy.len) != 0) {
-				NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
-				len -= chunk;
-				copied += chunk;
-			}
-		}
-
-		tp->ucopy.task = NULL;
-		tp->ucopy.len = 0;
-	}
-
 	/* According to UNIX98, msg_name/msg_namelen are ignored
 	 * on connected socket. I was just happy when found this 8) --ANK
 	 */

net/ipv4/tcp_input.c

@@ -4611,22 +4611,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 			goto out_of_window;
 
 		/* Ok. In sequence. In window. */
-		if (tp->ucopy.task == current &&
-		    tp->copied_seq == tp->rcv_nxt && tp->ucopy.len &&
-		    sock_owned_by_user(sk) && !tp->urg_data) {
-			int chunk = min_t(unsigned int, skb->len,
-					  tp->ucopy.len);
-
-			__set_current_state(TASK_RUNNING);
-
-			if (!skb_copy_datagram_msg(skb, 0, tp->ucopy.msg, chunk)) {
-				tp->ucopy.len -= chunk;
-				tp->copied_seq += chunk;
-				eaten = (chunk == skb->len);
-				tcp_rcv_space_adjust(sk);
-			}
-		}
-
 		if (eaten <= 0) {
 queue_and_out:
 			if (eaten < 0) {
@@ -5186,26 +5170,6 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
 	}
 }
 
-static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	int chunk = skb->len - hlen;
-	int err;
-
-	if (skb_csum_unnecessary(skb))
-		err = skb_copy_datagram_msg(skb, hlen, tp->ucopy.msg, chunk);
-	else
-		err = skb_copy_and_csum_datagram_msg(skb, hlen, tp->ucopy.msg);
-
-	if (!err) {
-		tp->ucopy.len -= chunk;
-		tp->copied_seq += chunk;
-		tcp_rcv_space_adjust(sk);
-	}
-
-	return err;
-}
-
 /* Accept RST for rcv_nxt - 1 after a FIN.
  * When tcp connections are abruptly terminated from Mac OSX (via ^C), a
  * FIN is sent followed by a RST packet. The RST is sent with the same
@@ -5446,32 +5410,6 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			int eaten = 0;
 			bool fragstolen = false;
 
-			if (tp->ucopy.task == current &&
-			    tp->copied_seq == tp->rcv_nxt &&
-			    len - tcp_header_len <= tp->ucopy.len &&
-			    sock_owned_by_user(sk)) {
-				__set_current_state(TASK_RUNNING);
-
-				if (!tcp_copy_to_iovec(sk, skb, tcp_header_len)) {
-					/* Predicted packet is in window by definition.
-					 * seq == rcv_nxt and rcv_wup <= rcv_nxt.
-					 * Hence, check seq<=rcv_wup reduces to:
-					 */
-					if (tcp_header_len ==
-					    (sizeof(struct tcphdr) +
-					     TCPOLEN_TSTAMP_ALIGNED) &&
-					    tp->rcv_nxt == tp->rcv_wup)
-						tcp_store_ts_recent(tp);
-
-					tcp_rcv_rtt_measure_ts(sk, skb);
-
-					__skb_pull(skb, tcp_header_len);
-					tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
-					NET_INC_STATS(sock_net(sk),
-							LINUX_MIB_TCPHPHITSTOUSER);
-					eaten = 1;
-				}
-			}
 			if (!eaten) {
 				if (tcp_checksum_complete(skb))
 					goto csum_error;

net/ipv4/tcp_ipv4.c

@@ -1541,61 +1541,6 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 	}
 }
 
-/* Packet is added to VJ-style prequeue for processing in process
- * context, if a reader task is waiting. Apparently, this exciting
- * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
- * failed somewhere. Latency? Burstiness? Well, at least now we will
- * see, why it failed. 8)8)				  --ANK
- *
- */
-bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (sysctl_tcp_low_latency || !tp->ucopy.task)
-		return false;
-
-	if (skb->len <= tcp_hdrlen(skb) &&
-	    skb_queue_len(&tp->ucopy.prequeue) == 0)
-		return false;
-
-	/* Before escaping RCU protected region, we need to take care of skb
-	 * dst. Prequeue is only enabled for established sockets.
-	 * For such sockets, we might need the skb dst only to set sk->sk_rx_dst
-	 * Instead of doing full sk_rx_dst validity here, let's perform
-	 * an optimistic check.
-	 */
-	if (likely(sk->sk_rx_dst))
-		skb_dst_drop(skb);
-	else
-		skb_dst_force_safe(skb);
-
-	__skb_queue_tail(&tp->ucopy.prequeue, skb);
-	tp->ucopy.memory += skb->truesize;
-	if (skb_queue_len(&tp->ucopy.prequeue) >= 32 ||
-	    tp->ucopy.memory + atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) {
-		struct sk_buff *skb1;
-
-		BUG_ON(sock_owned_by_user(sk));
-		__NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPPREQUEUEDROPPED,
-				skb_queue_len(&tp->ucopy.prequeue));
-
-		while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
-			sk_backlog_rcv(sk, skb1);
-
-		tp->ucopy.memory = 0;
-	} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
-		wake_up_interruptible_sync_poll(sk_sleep(sk),
-					   POLLIN | POLLRDNORM | POLLRDBAND);
-		if (!inet_csk_ack_scheduled(sk))
-			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-						  (3 * tcp_rto_min(sk)) / 4,
-						  TCP_RTO_MAX);
-	}
-	return true;
-}
-EXPORT_SYMBOL(tcp_prequeue);
-
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;
@@ -1770,7 +1715,6 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
-		if (!tcp_prequeue(sk, skb))
 		ret = tcp_v4_do_rcv(sk, skb);
 	} else if (tcp_add_backlog(sk, skb)) {
 		goto discard_and_relse;
@@ -1936,9 +1880,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	}
 #endif
 
-	/* Clean prequeue, it must be empty really */
-	__skb_queue_purge(&tp->ucopy.prequeue);
-
 	/* Clean up a referenced TCP bind bucket. */
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);

net/ipv4/tcp_minisocks.c

@@ -445,7 +445,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->snd_sml = newtp->snd_una =
 		newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
 
-		tcp_prequeue_init(newtp);
 		INIT_LIST_HEAD(&newtp->tsq_node);
 
 		tcp_init_wl(newtp, treq->rcv_isn);

net/ipv4/tcp_timer.c

@@ -239,7 +239,6 @@ static int tcp_write_timeout(struct sock *sk)
 /* Called with BH disabled */
 void tcp_delack_timer_handler(struct sock *sk)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	sk_mem_reclaim_partial(sk);
@@ -254,17 +253,6 @@ void tcp_delack_timer_handler(struct sock *sk)
 	}
 	icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER;
 
-	if (!skb_queue_empty(&tp->ucopy.prequeue)) {
-		struct sk_buff *skb;
-
-		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSCHEDULERFAILED);
-
-		while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
-			sk_backlog_rcv(sk, skb);
-
-		tp->ucopy.memory = 0;
-	}
-
 	if (inet_csk_ack_scheduled(sk)) {
 		if (!icsk->icsk_ack.pingpong) {
 			/* Delayed ACK missed: inflate ATO. */

net/ipv6/tcp_ipv6.c

@@ -1505,7 +1505,6 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
-		if (!tcp_prequeue(sk, skb))
 		ret = tcp_v6_do_rcv(sk, skb);
 	} else if (tcp_add_backlog(sk, skb)) {
 		goto discard_and_relse;