From fc6415bcb0f58f03adb910e56d7e1df6368794e0 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 5 Jul 2005 15:17:45 -0700 Subject: [TCP]: Fix quick-ack decrementing with TSO. On each packet output, we call tcp_dec_quickack_mode() if the ACK flag is set. It drops tp->ack.quick until it hits zero, at which time we deflate the ATO value. When doing TSO, we are emitting multiple packets with ACK set, so we should decrement tp->ack.quick that many segments. Note that, unlike this case, tcp_enter_cwr() should not take the tcp_skb_pcount(skb) into consideration. That function, one time, readjusts tp->snd_cwnd and moves into TCP_CA_CWR state. Signed-off-by: David S. Miller --- include/net/tcp.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index ec9e20c27179..afe41c5de2f2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -721,11 +721,16 @@ static inline int tcp_ack_scheduled(struct tcp_sock *tp) return tp->ack.pending&TCP_ACK_SCHED; } -static __inline__ void tcp_dec_quickack_mode(struct tcp_sock *tp) +static __inline__ void tcp_dec_quickack_mode(struct tcp_sock *tp, unsigned int pkts) { - if (tp->ack.quick && --tp->ack.quick == 0) { - /* Leaving quickack mode we deflate ATO. */ - tp->ack.ato = TCP_ATO_MIN; + if (tp->ack.quick) { + if (pkts >= tp->ack.quick) { + tp->ack.quick = 0; + + /* Leaving quickack mode we deflate ATO. */ + tp->ack.ato = TCP_ATO_MIN; + } else + tp->ack.quick -= pkts; } } -- cgit v1.2.2 From f6302d1d78f77c2d4c8bd32b0afc2df7fdf5f281 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 5 Jul 2005 15:18:03 -0700 Subject: [TCP]: Move send test logic out of net/tcp.h This just moves the code into tcp_output.c, no code logic changes are made by this patch. Using this as a baseline, we can begin to untangle the mess of comparisons for the Nagle test et al. We will also be able to reduce all of the redundant computation that occurs when outputting data packets. Signed-off-by: David S. Miller --- include/net/tcp.h | 113 ++---------------------------------------------------- 1 file changed, 3 insertions(+), 110 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index afe41c5de2f2..f2b104532de1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -849,6 +849,9 @@ extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, /* tcp_output.c */ extern int tcp_write_xmit(struct sock *, int nonagle); +extern void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp, + unsigned cur_mss, int nonagle); +extern int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp); extern int tcp_retransmit_skb(struct sock *, struct sk_buff *); extern void tcp_xmit_retransmit_queue(struct sock *); extern void tcp_simple_retransmit(struct sock *); @@ -1284,12 +1287,6 @@ static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp) return 3; } -static __inline__ int tcp_minshall_check(const struct tcp_sock *tp) -{ - return after(tp->snd_sml,tp->snd_una) && - !after(tp->snd_sml, tp->snd_nxt); -} - static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss, const struct sk_buff *skb) { @@ -1297,122 +1294,18 @@ static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss, tp->snd_sml = TCP_SKB_CB(skb)->end_seq; } -/* Return 0, if packet can be sent now without violation Nagle's rules: - 1. It is full sized. - 2. Or it contains FIN. - 3. Or TCP_NODELAY was set. - 4. Or TCP_CORK is not set, and all sent packets are ACKed. - With Minshall's modification: all sent small packets are ACKed. - */ - -static __inline__ int -tcp_nagle_check(const struct tcp_sock *tp, const struct sk_buff *skb, - unsigned mss_now, int nonagle) -{ - return (skb->len < mss_now && - !(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) && - ((nonagle&TCP_NAGLE_CORK) || - (!nonagle && - tp->packets_out && - tcp_minshall_check(tp)))); -} - -extern void tcp_set_skb_tso_segs(struct sock *, struct sk_buff *); - -/* This checks if the data bearing packet SKB (usually sk->sk_send_head) - * should be put on the wire right now. - */ -static __inline__ int tcp_snd_test(struct sock *sk, - struct sk_buff *skb, - unsigned cur_mss, int nonagle) -{ - struct tcp_sock *tp = tcp_sk(sk); - int pkts = tcp_skb_pcount(skb); - - if (!pkts) { - tcp_set_skb_tso_segs(sk, skb); - pkts = tcp_skb_pcount(skb); - } - - /* RFC 1122 - section 4.2.3.4 - * - * We must queue if - * - * a) The right edge of this frame exceeds the window - * b) There are packets in flight and we have a small segment - * [SWS avoidance and Nagle algorithm] - * (part of SWS is done on packetization) - * Minshall version sounds: there are no _small_ - * segments in flight. (tcp_nagle_check) - * c) We have too many packets 'in flight' - * - * Don't use the nagle rule for urgent data (or - * for the final FIN -DaveM). - * - * Also, Nagle rule does not apply to frames, which - * sit in the middle of queue (they have no chances - * to get new data) and if room at tail of skb is - * not enough to save something seriously (<32 for now). - */ - - /* Don't be strict about the congestion window for the - * final FIN frame. -DaveM - */ - return (((nonagle&TCP_NAGLE_PUSH) || tp->urg_mode - || !tcp_nagle_check(tp, skb, cur_mss, nonagle)) && - (((tcp_packets_in_flight(tp) + (pkts-1)) < tp->snd_cwnd) || - (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)) && - !after(TCP_SKB_CB(skb)->end_seq, tp->snd_una + tp->snd_wnd)); -} - static __inline__ void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *tp) { if (!tp->packets_out && !tp->pending) tcp_reset_xmit_timer(sk, TCP_TIME_PROBE0, tp->rto); } -static __inline__ int tcp_skb_is_last(const struct sock *sk, - const struct sk_buff *skb) -{ - return skb->next == (struct sk_buff *)&sk->sk_write_queue; -} - -/* Push out any pending frames which were held back due to - * TCP_CORK or attempt at coalescing tiny packets. - * The socket must be locked by the caller. - */ -static __inline__ void __tcp_push_pending_frames(struct sock *sk, - struct tcp_sock *tp, - unsigned cur_mss, - int nonagle) -{ - struct sk_buff *skb = sk->sk_send_head; - - if (skb) { - if (!tcp_skb_is_last(sk, skb)) - nonagle = TCP_NAGLE_PUSH; - if (!tcp_snd_test(sk, skb, cur_mss, nonagle) || - tcp_write_xmit(sk, nonagle)) - tcp_check_probe_timer(sk, tp); - } - tcp_cwnd_validate(sk, tp); -} - static __inline__ void tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp) { __tcp_push_pending_frames(sk, tp, tcp_current_mss(sk, 1), tp->nonagle); } -static __inline__ int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp) -{ - struct sk_buff *skb = sk->sk_send_head; - - return (skb && - tcp_snd_test(sk, skb, tcp_current_mss(sk, 1), - tcp_skb_is_last(sk, skb) ? TCP_NAGLE_PUSH : tp->nonagle)); -} - static __inline__ void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq) { tp->snd_wl1 = seq; -- cgit v1.2.2 From 84d3e7b9573291a1ea845bdd51b74bb484597661 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 5 Jul 2005 15:18:18 -0700 Subject: [TCP]: Move __tcp_data_snd_check into tcp_output.c It reimplements portions of tcp_snd_check(), so it we move it to tcp_output.c we can consolidate it's logic much easier in a later change. Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index f2b104532de1..4888f9d3f56b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -849,6 +849,7 @@ extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, /* tcp_output.c */ extern int tcp_write_xmit(struct sock *, int nonagle); +extern void __tcp_data_snd_check(struct sock *sk, struct sk_buff *skb); extern void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp, unsigned cur_mss, int nonagle); extern int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp); -- cgit v1.2.2 From a762a9800752f05fa8768bb0ac35d0e7f1bcfe7f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 5 Jul 2005 15:18:51 -0700 Subject: [TCP]: Kill extra cwnd validate in __tcp_push_pending_frames(). The tcp_cwnd_validate() function should only be invoked if we actually send some frames, yet __tcp_push_pending_frames() will always invoke it. tcp_write_xmit() does the call for us, so the call here can simply be removed. Also, tcp_write_xmit() can be marked static. Signed-off-by: David S. Miller --- include/net/tcp.h | 26 +++----------------------- 1 file changed, 3 insertions(+), 23 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 4888f9d3f56b..f32e7aed2c75 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -848,7 +848,6 @@ extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, /* tcp_output.c */ -extern int tcp_write_xmit(struct sock *, int nonagle); extern void __tcp_data_snd_check(struct sock *sk, struct sk_buff *skb); extern void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp, unsigned cur_mss, int nonagle); @@ -868,6 +867,9 @@ extern void tcp_push_one(struct sock *, unsigned mss_now); extern void tcp_send_ack(struct sock *sk); extern void tcp_send_delayed_ack(struct sock *sk); +/* tcp_input.c */ +extern void tcp_cwnd_application_limited(struct sock *sk); + /* tcp_timer.c */ extern void tcp_init_xmit_timers(struct sock *); extern void tcp_clear_xmit_timers(struct sock *); @@ -1234,28 +1236,6 @@ static inline void tcp_sync_left_out(struct tcp_sock *tp) tp->left_out = tp->sacked_out + tp->lost_out; } -extern void tcp_cwnd_application_limited(struct sock *sk); - -/* Congestion window validation. (RFC2861) */ - -static inline void tcp_cwnd_validate(struct sock *sk, struct tcp_sock *tp) -{ - __u32 packets_out = tp->packets_out; - - if (packets_out >= tp->snd_cwnd) { - /* Network is feed fully. */ - tp->snd_cwnd_used = 0; - tp->snd_cwnd_stamp = tcp_time_stamp; - } else { - /* Network starves. */ - if (tp->packets_out > tp->snd_cwnd_used) - tp->snd_cwnd_used = tp->packets_out; - - if ((s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= tp->rto) - tcp_cwnd_application_limited(sk); - } -} - /* Set slow start threshould and cwnd not falling to slow start */ static inline void __tcp_enter_cwr(struct tcp_sock *tp) { -- cgit v1.2.2 From a2e2a59c93cc8ba39caa9011c2573f429e40ccd9 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 5 Jul 2005 15:19:23 -0700 Subject: [TCP]: Fix redundant calculations of tcp_current_mss() tcp_write_xmit() uses tcp_current_mss(), but some of it's callers, namely __tcp_push_pending_frames(), already has this value available already. While we're here, fix the "cur_mss" argument to be "unsigned int" instead of plain "unsigned". Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index f32e7aed2c75..9416236cc395 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -850,7 +850,7 @@ extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, extern void __tcp_data_snd_check(struct sock *sk, struct sk_buff *skb); extern void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp, - unsigned cur_mss, int nonagle); + unsigned int cur_mss, int nonagle); extern int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp); extern int tcp_retransmit_skb(struct sock *, struct sk_buff *); extern void tcp_xmit_retransmit_queue(struct sock *); -- cgit v1.2.2 From 55c97f3e990c1ff63957c64f6cb10711a09fd70e Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 5 Jul 2005 15:19:38 -0700 Subject: [TCP]: Fix __tcp_push_pending_frames() 'nonagle' handling. 'nonagle' should be passed to the tcp_snd_test() function as 'TCP_NAGLE_PUSH' if we are checking an SKB not at the tail of the write_queue. This is because Nagle does not apply to such frames since we cannot possibly tack more data onto them. However, while doing this __tcp_push_pending_frames() makes all of the packets in the write_queue use this modified 'nonagle' value. Fix the bug and simplify this function by just calling tcp_write_xmit() directly if sk_send_head is non-NULL. As a result, we can now make tcp_data_snd_check() just call tcp_push_pending_frames() instead of the specialized __tcp_data_snd_check(). Signed-off-by: David S. Miller --- include/net/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 9416236cc395..b19238027da8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -848,7 +848,6 @@ extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, /* tcp_output.c */ -extern void __tcp_data_snd_check(struct sock *sk, struct sk_buff *skb); extern void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp, unsigned int cur_mss, int nonagle); extern int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp); -- cgit v1.2.2 From c1b4a7e69576d65efc31a8cea0714173c2841244 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 5 Jul 2005 15:24:38 -0700 Subject: [TCP]: Move to new TSO segmenting scheme. Make TSO segment transmit size decisions at send time not earlier. The basic scheme is that we try to build as large a TSO frame as possible when pulling in the user data, but the size of the TSO frame output to the card is determined at transmit time. This is guided by tp->xmit_size_goal. It is always set to a multiple of MSS and tells sendmsg/sendpage how large an SKB to try and build. Later, tcp_write_xmit() and tcp_push_one() chop up the packet if necessary and conditions warrant. These routines can also decide to "defer" in order to wait for more ACKs to arrive and thus allow larger TSO frames to be emitted. A general observation is that TSO elongates the pipe, thus requiring a larger congestion window and larger buffering especially at the sender side. Therefore, it is important that applications 1) get a large enough socket send buffer (this is accomplished by our dynamic send buffer expansion code) 2) do large enough writes. Signed-off-by: David S. Miller --- include/net/tcp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index b19238027da8..a166918ca56d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -862,7 +862,7 @@ extern int tcp_write_wakeup(struct sock *); extern void tcp_send_fin(struct sock *sk); extern void tcp_send_active_reset(struct sock *sk, int priority); extern int tcp_send_synack(struct sock *); -extern void tcp_push_one(struct sock *, unsigned mss_now); +extern void tcp_push_one(struct sock *, unsigned int mss_now); extern void tcp_send_ack(struct sock *sk); extern void tcp_send_delayed_ack(struct sock *sk); @@ -968,7 +968,7 @@ static inline void tcp_reset_xmit_timer(struct sock *sk, int what, unsigned long static inline void tcp_initialize_rcv_mss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - unsigned int hint = min(tp->advmss, tp->mss_cache_std); + unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache); hint = min(hint, tp->rcv_wnd/2); hint = min(hint, TCP_MIN_RCVMSS); -- cgit v1.2.2 From b03efcfb2180289718991bb984044ce6c5b7d1b0 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 8 Jul 2005 14:57:23 -0700 Subject: [NET]: Transform skb_queue_len() binary tests into skb_queue_empty() This is part of the grand scheme to eliminate the qlen member of skb_queue_head, and subsequently remove the 'list' member of sk_buff. Most users of skb_queue_len() want to know if the queue is empty or not, and that's trivially done with skb_queue_empty() which doesn't use the skb_queue_head->qlen member and instead uses the queue list emptyness as the test. Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index a166918ca56d..4d5b12e4dc11 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -991,7 +991,7 @@ static __inline__ void tcp_fast_path_on(struct tcp_sock *tp) static inline void tcp_fast_path_check(struct sock *sk, struct tcp_sock *tp) { - if (skb_queue_len(&tp->out_of_order_queue) == 0 && + if (skb_queue_empty(&tp->out_of_order_queue) && tp->rcv_wnd && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && !tp->urg_data) -- cgit v1.2.2 From 86a76caf8705e3524e15f343f3c4806939a06dc8 Mon Sep 17 00:00:00 2001 From: Victor Fusco Date: Fri, 8 Jul 2005 14:57:47 -0700 Subject: [NET]: Fix sparse warnings From: Victor Fusco Fix the sparse warning "implicit cast to nocast type" Signed-off-by: Victor Fusco Signed-off-by: Domen Puncer Signed-off-by: David S. Miller --- include/net/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 4d5b12e4dc11..f4f9aba07ac2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -860,7 +860,8 @@ extern void tcp_send_probe0(struct sock *); extern void tcp_send_partial(struct sock *); extern int tcp_write_wakeup(struct sock *); extern void tcp_send_fin(struct sock *sk); -extern void tcp_send_active_reset(struct sock *sk, int priority); +extern void tcp_send_active_reset(struct sock *sk, + unsigned int __nocast priority); extern int tcp_send_synack(struct sock *); extern void tcp_push_one(struct sock *, unsigned int mss_now); extern void tcp_send_ack(struct sock *sk); -- cgit v1.2.2