diff options
Diffstat (limited to 'net/ipv4/tcp_output.c')
| -rw-r--r-- | net/ipv4/tcp_output.c | 2332 |
1 files changed, 1530 insertions, 802 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 72b9350006f..179b51e6bda 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -5,8 +5,6 @@ * * Implementation of the Transmission Control Protocol(TCP). * - * Version: $Id: tcp_output.c,v 1.146 2002/02/01 22:01:04 davem Exp $ - * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> @@ -36,19 +34,25 @@ * */ +#define pr_fmt(fmt) "TCP: " fmt + #include <net/tcp.h> #include <linux/compiler.h> +#include <linux/gfp.h> #include <linux/module.h> /* People can turn this off for buggy TCP's found in printers etc. */ int sysctl_tcp_retrans_collapse __read_mostly = 1; -/* People can turn this on to work with those rare, broken TCPs that +/* People can turn this on to work with those rare, broken TCPs that * interpret the window field as a signed quantity. */ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; +/* Default TSQ limit of two TSO segments */ +int sysctl_tcp_limit_output_bytes __read_mostly = 131072; + /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. @@ -56,27 +60,35 @@ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; int sysctl_tcp_tso_win_divisor __read_mostly = 3; int sysctl_tcp_mtu_probing __read_mostly = 0; -int sysctl_tcp_base_mss __read_mostly = 512; +int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; -static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) +unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX; +EXPORT_SYMBOL(sysctl_tcp_notsent_lowat); + +static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, + int push_one, gfp_t gfp); + +/* Account for new data that has been sent to the network. */ +static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) { + struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; tcp_advance_send_head(sk, skb); tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; - /* Don't override Nagle indefinately with F-RTO */ - if (tp->frto_counter == 2) - tp->frto_counter = 3; - tp->packets_out += tcp_skb_pcount(skb); - if (!prior_packets) - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, TCP_RTO_MAX); + if (!prior_packets || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { + tcp_rearm_rto(sk); + } + + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, + tcp_skb_pcount(skb)); } /* SND.NXT, if window was not shrunk. @@ -85,9 +97,9 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) * Anything in between SND.UNA...SND.UNA+SND.WND also can be already * invalid. OK, let's make this for now: */ -static inline __u32 tcp_acceptable_seq(struct sock *sk) +static inline __u32 tcp_acceptable_seq(const struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); if (!before(tcp_wnd_end(tp), tp->snd_nxt)) return tp->snd_nxt; @@ -112,12 +124,16 @@ static inline __u32 tcp_acceptable_seq(struct sock *sk) static __u16 tcp_advertise_mss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); + const struct dst_entry *dst = __sk_dst_get(sk); int mss = tp->advmss; - if (dst && dst_metric(dst, RTAX_ADVMSS) < mss) { - mss = dst_metric(dst, RTAX_ADVMSS); - tp->advmss = mss; + if (dst) { + unsigned int metric = dst_metric_advmss(dst); + + if (metric < mss) { + mss = metric; + tp->advmss = mss; + } } return (__u16)mss; @@ -125,7 +141,7 @@ static __u16 tcp_advertise_mss(struct sock *sk) /* RFC2861. Reset CWND after idle period longer RTO to "restart window". * This is the first part of cwnd validation mechanism. */ -static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst) +static void tcp_cwnd_restart(struct sock *sk, const struct dst_entry *dst) { struct tcp_sock *tp = tcp_sk(sk); s32 delta = tcp_time_stamp - tp->lsndtime; @@ -144,11 +160,13 @@ static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst) tp->snd_cwnd_used = 0; } +/* Congestion state accounting after a packet has been sent. */ static void tcp_event_data_sent(struct tcp_sock *tp, - struct sk_buff *skb, struct sock *sk) + struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_time_stamp; + const struct dst_entry *dst = __sk_dst_get(sk); if (sysctl_tcp_slow_start_after_idle && (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto)) @@ -159,16 +177,33 @@ static void tcp_event_data_sent(struct tcp_sock *tp, /* If it is a reply for ato after last received * packet, enter pingpong mode. */ - if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) - icsk->icsk_ack.pingpong = 1; + if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato && + (!dst || !dst_metric(dst, RTAX_QUICKACK))) + icsk->icsk_ack.pingpong = 1; } +/* Account for an ACK we sent. */ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) { tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } + +u32 tcp_default_init_rwnd(u32 mss) +{ + /* Initial receive window should be twice of TCP_INIT_CWND to + * enable proper sending of new unsent data during fast recovery + * (RFC 3517, Section 4, NextSeg() rule (2)). Further place a + * limit when mss is larger than 1460. + */ + u32 init_rwnd = TCP_INIT_CWND * 2; + + if (mss > 1460) + init_rwnd = max((1460 * init_rwnd) / mss, 2U); + return init_rwnd; +} + /* Determine a window scaling and initial window to offer. * Based on the assumption that the given amount of space * will be offered. Store the results in the tp structure. @@ -178,7 +213,8 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) */ void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, - int wscale_ok, __u8 *rcv_wscale) + int wscale_ok, __u8 *rcv_wscale, + __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); @@ -217,23 +253,16 @@ void tcp_select_initial_window(int __space, __u32 mss, } } - /* Set initial window to value enough for senders, - * following RFC2414. Senders, not following this RFC, - * will be satisfied with 2. - */ if (mss > (1 << *rcv_wscale)) { - int init_cwnd = 4; - if (mss > 1460 * 3) - init_cwnd = 2; - else if (mss > 1460) - init_cwnd = 3; - if (*rcv_wnd > init_cwnd * mss) - *rcv_wnd = init_cwnd * mss; + if (!init_rcv_wnd) /* Use default unless specified otherwise */ + init_rcv_wnd = tcp_default_init_rwnd(mss); + *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); } /* Set the clamp no higher than max representable value */ (*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp); } +EXPORT_SYMBOL(tcp_select_initial_window); /* Chose a new window to advertise, update state in tcp_sock for the * socket, and return result with RFC1323 scaling applied. The return @@ -243,6 +272,7 @@ void tcp_select_initial_window(int __space, __u32 mss, static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 old_win = tp->rcv_wnd; u32 cur_win = tcp_receive_window(tp); u32 new_win = __tcp_select_window(sk); @@ -255,6 +285,9 @@ static u16 tcp_select_window(struct sock *sk) * * Relax Will Robinson. */ + if (new_win == 0) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPWANTZEROWINDOWADV); new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; @@ -272,37 +305,48 @@ static u16 tcp_select_window(struct sock *sk) new_win >>= tp->rx_opt.rcv_wscale; /* If we advertise zero window, disable fast path. */ - if (new_win == 0) + if (new_win == 0) { tp->pred_flags = 0; + if (old_win) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPTOZEROWINDOWADV); + } else if (old_win == 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV); + } return new_win; } -static inline void TCP_ECN_send_synack(struct tcp_sock *tp, struct sk_buff *skb) +/* Packet ECN state for a SYN-ACK */ +static inline void TCP_ECN_send_synack(const struct tcp_sock *tp, struct sk_buff *skb) { - TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_CWR; + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; if (!(tp->ecn_flags & TCP_ECN_OK)) - TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_ECE; + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; } +/* Packet ECN state for a SYN. */ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); tp->ecn_flags = 0; - if (sysctl_tcp_ecn) { - TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ECE | TCPCB_FLAG_CWR; + if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) { + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; } } static __inline__ void -TCP_ECN_make_synack(struct request_sock *req, struct tcphdr *th) +TCP_ECN_make_synack(const struct request_sock *req, struct tcphdr *th) { if (inet_rsk(req)->ecn_ok) th->ece = 1; } +/* Set up ECN state for a packet on a ESTABLISHED socket that is about to + * be sent. + */ static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb, int tcp_header_len) { @@ -332,127 +376,479 @@ static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb, */ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + + skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - TCP_SKB_CB(skb)->flags = flags; + TCP_SKB_CB(skb)->tcp_flags = flags; TCP_SKB_CB(skb)->sacked = 0; - skb_shinfo(skb)->gso_segs = 1; - skb_shinfo(skb)->gso_size = 0; - skb_shinfo(skb)->gso_type = 0; + shinfo->gso_segs = 1; + shinfo->gso_size = 0; + shinfo->gso_type = 0; TCP_SKB_CB(skb)->seq = seq; - if (flags & (TCPCB_FLAG_SYN | TCPCB_FLAG_FIN)) + if (flags & (TCPHDR_SYN | TCPHDR_FIN)) seq++; TCP_SKB_CB(skb)->end_seq = seq; } -static void tcp_build_and_update_options(__be32 *ptr, struct tcp_sock *tp, - __u32 tstamp, __u8 **md5_hash) +static inline bool tcp_urg_mode(const struct tcp_sock *tp) +{ + return tp->snd_una != tp->snd_up; +} + +#define OPTION_SACK_ADVERTISE (1 << 0) +#define OPTION_TS (1 << 1) +#define OPTION_MD5 (1 << 2) +#define OPTION_WSCALE (1 << 3) +#define OPTION_FAST_OPEN_COOKIE (1 << 8) + +struct tcp_out_options { + u16 options; /* bit field of OPTION_* */ + u16 mss; /* 0 to disable */ + u8 ws; /* window scale, 0 to disable */ + u8 num_sack_blocks; /* number of SACK blocks to include */ + u8 hash_size; /* bytes in hash_location */ + __u8 *hash_location; /* temporary pointer, overloaded */ + __u32 tsval, tsecr; /* need to include OPTION_TS */ + struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ +}; + +/* Write previously computed TCP options to the packet. + * + * Beware: Something in the Internet is very sensitive to the ordering of + * TCP options, we learned this through the hard way, so be careful here. + * Luckily we can at least blame others for their non-compliance but from + * inter-operability perspective it seems that we're somewhat stuck with + * the ordering which we have been using if we want to keep working with + * those broken things (not that it currently hurts anybody as there isn't + * particular reason why the ordering would need to be changed). + * + * At least SACK_PERM as the first option is known to lead to a disaster + * (but it may well be that other scenarios fail similarly). + */ +static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, + struct tcp_out_options *opts) { - if (tp->rx_opt.tstamp_ok) { + u16 options = opts->options; /* mungable copy */ + + if (unlikely(OPTION_MD5 & options)) { + *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); + /* overload cookie hash location */ + opts->hash_location = (__u8 *)ptr; + ptr += 4; + } + + if (unlikely(opts->mss)) { + *ptr++ = htonl((TCPOPT_MSS << 24) | + (TCPOLEN_MSS << 16) | + opts->mss); + } + + if (likely(OPTION_TS & options)) { + if (unlikely(OPTION_SACK_ADVERTISE & options)) { + *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | + (TCPOLEN_SACK_PERM << 16) | + (TCPOPT_TIMESTAMP << 8) | + TCPOLEN_TIMESTAMP); + options &= ~OPTION_SACK_ADVERTISE; + } else { + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | + TCPOLEN_TIMESTAMP); + } + *ptr++ = htonl(opts->tsval); + *ptr++ = htonl(opts->tsecr); + } + + if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | - (TCPOPT_TIMESTAMP << 8) | - TCPOLEN_TIMESTAMP); - *ptr++ = htonl(tstamp); - *ptr++ = htonl(tp->rx_opt.ts_recent); + (TCPOPT_SACK_PERM << 8) | + TCPOLEN_SACK_PERM); + } + + if (unlikely(OPTION_WSCALE & options)) { + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_WINDOW << 16) | + (TCPOLEN_WINDOW << 8) | + opts->ws); } - if (tp->rx_opt.eff_sacks) { - struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks; + + if (unlikely(opts->num_sack_blocks)) { + struct tcp_sack_block *sp = tp->rx_opt.dsack ? + tp->duplicate_sack : tp->selective_acks; int this_sack; *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK << 8) | - (TCPOLEN_SACK_BASE + (tp->rx_opt.eff_sacks * + (TCPOLEN_SACK_BASE + (opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK))); - for (this_sack = 0; this_sack < tp->rx_opt.eff_sacks; this_sack++) { + for (this_sack = 0; this_sack < opts->num_sack_blocks; + ++this_sack) { *ptr++ = htonl(sp[this_sack].start_seq); *ptr++ = htonl(sp[this_sack].end_seq); } - if (tp->rx_opt.dsack) { - tp->rx_opt.dsack = 0; - tp->rx_opt.eff_sacks--; + tp->rx_opt.dsack = 0; + } + + if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { + struct tcp_fastopen_cookie *foc = opts->fastopen_cookie; + + *ptr++ = htonl((TCPOPT_EXP << 24) | + ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) | + TCPOPT_FASTOPEN_MAGIC); + + memcpy(ptr, foc->val, foc->len); + if ((foc->len & 3) == 2) { + u8 *align = ((u8 *)ptr) + foc->len; + align[0] = align[1] = TCPOPT_NOP; } + ptr += (foc->len + 3) >> 2; } +} + +/* Compute TCP options for SYN packets. This is not the final + * network wire format yet. + */ +static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, + struct tcp_out_options *opts, + struct tcp_md5sig_key **md5) +{ + struct tcp_sock *tp = tcp_sk(sk); + unsigned int remaining = MAX_TCP_OPTION_SPACE; + struct tcp_fastopen_request *fastopen = tp->fastopen_req; + #ifdef CONFIG_TCP_MD5SIG - if (md5_hash) { - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | - (TCPOPT_MD5SIG << 8) | - TCPOLEN_MD5SIG); - *md5_hash = (__u8 *)ptr; + *md5 = tp->af_specific->md5_lookup(sk, sk); + if (*md5) { + opts->options |= OPTION_MD5; + remaining -= TCPOLEN_MD5SIG_ALIGNED; } +#else + *md5 = NULL; #endif + + /* We always get an MSS option. The option bytes which will be seen in + * normal data packets should timestamps be used, must be in the MSS + * advertised. But we subtract them from tp->mss_cache so that + * calculations in tcp_sendmsg are simpler etc. So account for this + * fact here if necessary. If we don't do this correctly, as a + * receiver we won't recognize data packets as being full sized when we + * should, and thus we won't abide by the delayed ACK rules correctly. + * SACKs don't matter, we never delay an ACK when we have any of those + * going out. */ + opts->mss = tcp_advertise_mss(sk); + remaining -= TCPOLEN_MSS_ALIGNED; + + if (likely(sysctl_tcp_timestamps && *md5 == NULL)) { + opts->options |= OPTION_TS; + opts->tsval = TCP_SKB_CB(skb)->when + tp->tsoffset; + opts->tsecr = tp->rx_opt.ts_recent; + remaining -= TCPOLEN_TSTAMP_ALIGNED; + } + if (likely(sysctl_tcp_window_scaling)) { + opts->ws = tp->rx_opt.rcv_wscale; + opts->options |= OPTION_WSCALE; + remaining -= TCPOLEN_WSCALE_ALIGNED; + } + if (likely(sysctl_tcp_sack)) { + opts->options |= OPTION_SACK_ADVERTISE; + if (unlikely(!(OPTION_TS & opts->options))) + remaining -= TCPOLEN_SACKPERM_ALIGNED; + } + + if (fastopen && fastopen->cookie.len >= 0) { + u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len; + need = (need + 3) & ~3U; /* Align to 32 bits */ + if (remaining >= need) { + opts->options |= OPTION_FAST_OPEN_COOKIE; + opts->fastopen_cookie = &fastopen->cookie; + remaining -= need; + tp->syn_fastopen = 1; + } + } + + return MAX_TCP_OPTION_SPACE - remaining; } -/* Construct a tcp options header for a SYN or SYN_ACK packet. - * If this is every changed make sure to change the definition of - * MAX_SYN_SIZE to match the new maximum number of options that you - * can generate. - * - * Note - that with the RFC2385 TCP option, we make room for the - * 16 byte MD5 hash. This will be filled in later, so the pointer for the - * location to be filled is passed back up. +/* Set up TCP options for SYN-ACKs. */ +static unsigned int tcp_synack_options(struct sock *sk, + struct request_sock *req, + unsigned int mss, struct sk_buff *skb, + struct tcp_out_options *opts, + struct tcp_md5sig_key **md5, + struct tcp_fastopen_cookie *foc) +{ + struct inet_request_sock *ireq = inet_rsk(req); + unsigned int remaining = MAX_TCP_OPTION_SPACE; + +#ifdef CONFIG_TCP_MD5SIG + *md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req); + if (*md5) { + opts->options |= OPTION_MD5; + remaining -= TCPOLEN_MD5SIG_ALIGNED; + + /* We can't fit any SACK blocks in a packet with MD5 + TS + * options. There was discussion about disabling SACK + * rather than TS in order to fit in better with old, + * buggy kernels, but that was deemed to be unnecessary. + */ + ireq->tstamp_ok &= !ireq->sack_ok; + } +#else + *md5 = NULL; +#endif + + /* We always send an MSS option. */ + opts->mss = mss; + remaining -= TCPOLEN_MSS_ALIGNED; + + if (likely(ireq->wscale_ok)) { + opts->ws = ireq->rcv_wscale; + opts->options |= OPTION_WSCALE; + remaining -= TCPOLEN_WSCALE_ALIGNED; + } + if (likely(ireq->tstamp_ok)) { + opts->options |= OPTION_TS; + opts->tsval = TCP_SKB_CB(skb)->when; + opts->tsecr = req->ts_recent; + remaining -= TCPOLEN_TSTAMP_ALIGNED; + } + if (likely(ireq->sack_ok)) { + opts->options |= OPTION_SACK_ADVERTISE; + if (unlikely(!ireq->tstamp_ok)) + remaining -= TCPOLEN_SACKPERM_ALIGNED; + } + if (foc != NULL && foc->len >= 0) { + u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; + need = (need + 3) & ~3U; /* Align to 32 bits */ + if (remaining >= need) { + opts->options |= OPTION_FAST_OPEN_COOKIE; + opts->fastopen_cookie = foc; + remaining -= need; + } + } + + return MAX_TCP_OPTION_SPACE - remaining; +} + +/* Compute TCP options for ESTABLISHED sockets. This is not the + * final wire format yet. */ -static void tcp_syn_build_options(__be32 *ptr, int mss, int ts, int sack, - int offer_wscale, int wscale, __u32 tstamp, - __u32 ts_recent, __u8 **md5_hash) -{ - /* We always get an MSS option. - * The option bytes which will be seen in normal data - * packets should timestamps be used, must be in the MSS - * advertised. But we subtract them from tp->mss_cache so - * that calculations in tcp_sendmsg are simpler etc. - * So account for this fact here if necessary. If we - * don't do this correctly, as a receiver we won't - * recognize data packets as being full sized when we - * should, and thus we won't abide by the delayed ACK - * rules correctly. - * SACKs don't matter, we never delay an ACK when we - * have any of those going out. - */ - *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss); - if (ts) { - if (sack) - *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | - (TCPOLEN_SACK_PERM << 16) | - (TCPOPT_TIMESTAMP << 8) | - TCPOLEN_TIMESTAMP); - else - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | - (TCPOPT_TIMESTAMP << 8) | - TCPOLEN_TIMESTAMP); - *ptr++ = htonl(tstamp); /* TSVAL */ - *ptr++ = htonl(ts_recent); /* TSECR */ - } else if (sack) - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | - (TCPOPT_SACK_PERM << 8) | - TCPOLEN_SACK_PERM); - if (offer_wscale) - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_WINDOW << 16) | - (TCPOLEN_WINDOW << 8) | - (wscale)); +static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb, + struct tcp_out_options *opts, + struct tcp_md5sig_key **md5) +{ + struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL; + struct tcp_sock *tp = tcp_sk(sk); + unsigned int size = 0; + unsigned int eff_sacks; + + opts->options = 0; + #ifdef CONFIG_TCP_MD5SIG - /* - * If MD5 is enabled, then we set the option, and include the size - * (always 18). The actual MD5 hash is added just before the - * packet is sent. - */ - if (md5_hash) { - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | - (TCPOPT_MD5SIG << 8) | - TCPOLEN_MD5SIG); - *md5_hash = (__u8 *)ptr; + *md5 = tp->af_specific->md5_lookup(sk, sk); + if (unlikely(*md5)) { + opts->options |= OPTION_MD5; + size += TCPOLEN_MD5SIG_ALIGNED; } +#else + *md5 = NULL; #endif + + if (likely(tp->rx_opt.tstamp_ok)) { + opts->options |= OPTION_TS; + opts->tsval = tcb ? tcb->when + tp->tsoffset : 0; + opts->tsecr = tp->rx_opt.ts_recent; + size += TCPOLEN_TSTAMP_ALIGNED; + } + + eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; + if (unlikely(eff_sacks)) { + const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + opts->num_sack_blocks = + min_t(unsigned int, eff_sacks, + (remaining - TCPOLEN_SACK_BASE_ALIGNED) / + TCPOLEN_SACK_PERBLOCK); + size += TCPOLEN_SACK_BASE_ALIGNED + + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + } + + return size; +} + + +/* TCP SMALL QUEUES (TSQ) + * + * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev) + * to reduce RTT and bufferbloat. + * We do this using a special skb destructor (tcp_wfree). + * + * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb + * needs to be reallocated in a driver. + * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc + * + * Since transmit from skb destructor is forbidden, we use a tasklet + * to process all sockets that eventually need to send more skbs. + * We use one tasklet per cpu, with its own queue of sockets. + */ +struct tsq_tasklet { + struct tasklet_struct tasklet; + struct list_head head; /* queue of tcp sockets */ +}; +static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); + +static void tcp_tsq_handler(struct sock *sk) +{ + if ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | + TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) + tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle, + 0, GFP_ATOMIC); +} +/* + * One tasklet per cpu tries to send more skbs. + * We run in tasklet context but need to disable irqs when + * transferring tsq->head because tcp_wfree() might + * interrupt us (non NAPI drivers) + */ +static void tcp_tasklet_func(unsigned long data) +{ + struct tsq_tasklet *tsq = (struct tsq_tasklet *)data; + LIST_HEAD(list); + unsigned long flags; + struct list_head *q, *n; + struct tcp_sock *tp; + struct sock *sk; + + local_irq_save(flags); + list_splice_init(&tsq->head, &list); + local_irq_restore(flags); + + list_for_each_safe(q, n, &list) { + tp = list_entry(q, struct tcp_sock, tsq_node); + list_del(&tp->tsq_node); + + sk = (struct sock *)tp; + bh_lock_sock(sk); + + if (!sock_owned_by_user(sk)) { + tcp_tsq_handler(sk); + } else { + /* defer the work to tcp_release_cb() */ + set_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags); + } + bh_unlock_sock(sk); + + clear_bit(TSQ_QUEUED, &tp->tsq_flags); + sk_free(sk); + } +} + +#define TCP_DEFERRED_ALL ((1UL << TCP_TSQ_DEFERRED) | \ + (1UL << TCP_WRITE_TIMER_DEFERRED) | \ + (1UL << TCP_DELACK_TIMER_DEFERRED) | \ + (1UL << TCP_MTU_REDUCED_DEFERRED)) +/** + * tcp_release_cb - tcp release_sock() callback + * @sk: socket + * + * called from release_sock() to perform protocol dependent + * actions before socket release. + */ +void tcp_release_cb(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + unsigned long flags, nflags; + + /* perform an atomic operation only if at least one flag is set */ + do { + flags = tp->tsq_flags; + if (!(flags & TCP_DEFERRED_ALL)) + return; + nflags = flags & ~TCP_DEFERRED_ALL; + } while (cmpxchg(&tp->tsq_flags, flags, nflags) != flags); + + if (flags & (1UL << TCP_TSQ_DEFERRED)) + tcp_tsq_handler(sk); + + /* Here begins the tricky part : + * We are called from release_sock() with : + * 1) BH disabled + * 2) sk_lock.slock spinlock held + * 3) socket owned by us (sk->sk_lock.owned == 1) + * + * But following code is meant to be called from BH handlers, + * so we should keep BH disabled, but early release socket ownership + */ + sock_release_ownership(sk); + + if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) { + tcp_write_timer_handler(sk); + __sock_put(sk); + } + if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED)) { + tcp_delack_timer_handler(sk); + __sock_put(sk); + } + if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) { + sk->sk_prot->mtu_reduced(sk); + __sock_put(sk); + } +} +EXPORT_SYMBOL(tcp_release_cb); + +void __init tcp_tasklet_init(void) +{ + int i; + + for_each_possible_cpu(i) { + struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); + + INIT_LIST_HEAD(&tsq->head); + tasklet_init(&tsq->tasklet, + tcp_tasklet_func, + (unsigned long)tsq); + } +} + +/* + * Write buffer destructor automatically called from kfree_skb. + * We can't xmit new skbs from this context, as we might already + * hold qdisc lock. + */ +void tcp_wfree(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + struct tcp_sock *tp = tcp_sk(sk); + + if (test_and_clear_bit(TSQ_THROTTLED, &tp->tsq_flags) && + !test_and_set_bit(TSQ_QUEUED, &tp->tsq_flags)) { + unsigned long flags; + struct tsq_tasklet *tsq; + + /* Keep a ref on socket. + * This last ref will be released in tcp_tasklet_func() + */ + atomic_sub(skb->truesize - 1, &sk->sk_wmem_alloc); + + /* queue this socket to tasklet queue */ + local_irq_save(flags); + tsq = &__get_cpu_var(tsq_tasklet); + list_add(&tp->tsq_node, &tsq->head); + tasklet_schedule(&tsq->tasklet); + local_irq_restore(flags); + } else { + sock_wfree(skb); + } } /* This routine actually transmits TCP packets queued in by @@ -473,93 +869,65 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, struct inet_sock *inet; struct tcp_sock *tp; struct tcp_skb_cb *tcb; - int tcp_header_size; -#ifdef CONFIG_TCP_MD5SIG + struct tcp_out_options opts; + unsigned int tcp_options_size, tcp_header_size; struct tcp_md5sig_key *md5; - __u8 *md5_hash_location; -#endif struct tcphdr *th; - int sysctl_flags; int err; BUG_ON(!skb || !tcp_skb_pcount(skb)); - /* If congestion control is doing timestamping, we must - * take such a timestamp before we potentially clone/copy. - */ - if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP) - __net_timestamp(skb); + if (clone_it) { + skb_mstamp_get(&skb->skb_mstamp); - if (likely(clone_it)) { if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); else skb = skb_clone(skb, gfp_mask); if (unlikely(!skb)) return -ENOBUFS; + /* Our usage of tstamp should remain private */ + skb->tstamp.tv64 = 0; } inet = inet_sk(sk); tp = tcp_sk(sk); tcb = TCP_SKB_CB(skb); - tcp_header_size = tp->tcp_header_len; - -#define SYSCTL_FLAG_TSTAMPS 0x1 -#define SYSCTL_FLAG_WSCALE 0x2 -#define SYSCTL_FLAG_SACK 0x4 - - sysctl_flags = 0; - if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) { - tcp_header_size = sizeof(struct tcphdr) + TCPOLEN_MSS; - if (sysctl_tcp_timestamps) { - tcp_header_size += TCPOLEN_TSTAMP_ALIGNED; - sysctl_flags |= SYSCTL_FLAG_TSTAMPS; - } - if (sysctl_tcp_window_scaling) { - tcp_header_size += TCPOLEN_WSCALE_ALIGNED; - sysctl_flags |= SYSCTL_FLAG_WSCALE; - } - if (sysctl_tcp_sack) { - sysctl_flags |= SYSCTL_FLAG_SACK; - if (!(sysctl_flags & SYSCTL_FLAG_TSTAMPS)) - tcp_header_size += TCPOLEN_SACKPERM_ALIGNED; - } - } else if (unlikely(tp->rx_opt.eff_sacks)) { - /* A SACK is 2 pad bytes, a 2 byte header, plus - * 2 32-bit sequence numbers for each SACK block. - */ - tcp_header_size += (TCPOLEN_SACK_BASE_ALIGNED + - (tp->rx_opt.eff_sacks * - TCPOLEN_SACK_PERBLOCK)); - } + memset(&opts, 0, sizeof(opts)); + + if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) + tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5); + else + tcp_options_size = tcp_established_options(sk, skb, &opts, + &md5); + tcp_header_size = tcp_options_size + sizeof(struct tcphdr); if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); -#ifdef CONFIG_TCP_MD5SIG - /* - * Are we doing MD5 on this segment? If so - make - * room for it. + /* if no packet is in qdisc/device queue, then allow XPS to select + * another queue. */ - md5 = tp->af_specific->md5_lookup(sk, sk); - if (md5) - tcp_header_size += TCPOLEN_MD5SIG_ALIGNED; -#endif + skb->ooo_okay = sk_wmem_alloc_get(sk) == 0; skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); - skb_set_owner_w(skb, sk); + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = tcp_wfree; + atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ th = tcp_hdr(skb); - th->source = inet->sport; - th->dest = inet->dport; + th->source = inet->inet_sport; + th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); th->ack_seq = htonl(tp->rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | - tcb->flags); + tcb->tcp_flags); - if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) { + if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) { /* RFC1323: The window in SYN & SYN/ACK segments * is never scaled. */ @@ -570,73 +938,52 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->check = 0; th->urg_ptr = 0; - if (unlikely(tp->urg_mode && - between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF))) { - th->urg_ptr = htons(tp->snd_up - tcb->seq); - th->urg = 1; + /* The urg_mode check is necessary during a below snd_una win probe */ + if (unlikely(tcp_urg_mode(tp) && before(tcb->seq, tp->snd_up))) { + if (before(tp->snd_up, tcb->seq + 0x10000)) { + th->urg_ptr = htons(tp->snd_up - tcb->seq); + th->urg = 1; + } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) { + th->urg_ptr = htons(0xFFFF); + th->urg = 1; + } } - if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) { - tcp_syn_build_options((__be32 *)(th + 1), - tcp_advertise_mss(sk), - (sysctl_flags & SYSCTL_FLAG_TSTAMPS), - (sysctl_flags & SYSCTL_FLAG_SACK), - (sysctl_flags & SYSCTL_FLAG_WSCALE), - tp->rx_opt.rcv_wscale, - tcb->when, - tp->rx_opt.ts_recent, - -#ifdef CONFIG_TCP_MD5SIG - md5 ? &md5_hash_location : -#endif - NULL); - } else { - tcp_build_and_update_options((__be32 *)(th + 1), - tp, tcb->when, -#ifdef CONFIG_TCP_MD5SIG - md5 ? &md5_hash_location : -#endif - NULL); + tcp_options_write((__be32 *)(th + 1), tp, &opts); + if (likely((tcb->tcp_flags & TCPHDR_SYN) == 0)) TCP_ECN_send(sk, skb, tcp_header_size); - } #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ if (md5) { - tp->af_specific->calc_md5_hash(md5_hash_location, - md5, - sk, NULL, NULL, - tcp_hdr(skb), - sk->sk_protocol, - skb->len); + sk_nocaps_add(sk, NETIF_F_GSO_MASK); + tp->af_specific->calc_md5_hash(opts.hash_location, + md5, sk, NULL, skb); } #endif - icsk->icsk_af_ops->send_check(sk, skb->len, skb); + icsk->icsk_af_ops->send_check(sk, skb); - if (likely(tcb->flags & TCPCB_FLAG_ACK)) + if (likely(tcb->tcp_flags & TCPHDR_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); if (skb->len != tcp_header_size) - tcp_event_data_sent(tp, skb, sk); + tcp_event_data_sent(tp, sk); if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) - TCP_INC_STATS(TCP_MIB_OUTSEGS); + TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, + tcp_skb_pcount(skb)); - err = icsk->icsk_af_ops->queue_xmit(skb, 0); + err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl); if (likely(err <= 0)) return err; tcp_enter_cwr(sk, 1); return net_xmit_eval(err); - -#undef SYSCTL_FLAG_TSTAMPS -#undef SYSCTL_FLAG_WSCALE -#undef SYSCTL_FLAG_SACK } -/* This routine just queue's the buffer +/* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, * otherwise socket can stall. @@ -653,27 +1000,33 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) sk_mem_charge(sk, skb->truesize); } -static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, +/* Initialize TSO segments for a packet. */ +static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || !sk_can_gso(sk)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + + /* Make sure we own this skb before messing gso_size/gso_segs */ + WARN_ON_ONCE(skb_cloned(skb)); + + if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal * non-TSO case. */ - skb_shinfo(skb)->gso_segs = 1; - skb_shinfo(skb)->gso_size = 0; - skb_shinfo(skb)->gso_type = 0; + shinfo->gso_segs = 1; + shinfo->gso_size = 0; + shinfo->gso_type = 0; } else { - skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss_now); - skb_shinfo(skb)->gso_size = mss_now; - skb_shinfo(skb)->gso_type = sk->sk_gso_type; + shinfo->gso_segs = DIV_ROUND_UP(skb->len, mss_now); + shinfo->gso_size = mss_now; + shinfo->gso_type = sk->sk_gso_type; } } /* When a modification to fackets out becomes necessary, we need to check * skb is counted to fackets_out or not. */ -static void tcp_adjust_fackets_out(struct sock *sk, struct sk_buff *skb, +static void tcp_adjust_fackets_out(struct sock *sk, const struct sk_buff *skb, int decr) { struct tcp_sock *tp = tcp_sk(sk); @@ -685,34 +1038,62 @@ static void tcp_adjust_fackets_out(struct sock *sk, struct sk_buff *skb, tp->fackets_out -= decr; } +/* Pcount in the middle of the write queue got changed, we need to do various + * tweaks to fix counters + */ +static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int decr) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tp->packets_out -= decr; + + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) + tp->sacked_out -= decr; + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) + tp->retrans_out -= decr; + if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) + tp->lost_out -= decr; + + /* Reno case is special. Sigh... */ + if (tcp_is_reno(tp) && decr > 0) + tp->sacked_out -= min_t(u32, tp->sacked_out, decr); + + tcp_adjust_fackets_out(sk, skb, decr); + + if (tp->lost_skb_hint && + before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && + (tcp_is_fack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))) + tp->lost_cnt_hint -= decr; + + tcp_verify_left_out(tp); +} + /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, - unsigned int mss_now) + unsigned int mss_now, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int nsize, old_factor; int nlen; - u16 flags; + u8 flags; - BUG_ON(len > skb->len); + if (WARN_ON(len > skb->len)) + return -EINVAL; - tcp_clear_retrans_hints_partial(tp); nsize = skb_headlen(skb) - len; if (nsize < 0) nsize = 0; - if (skb_cloned(skb) && - skb_is_nonlinear(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, gfp)) return -ENOMEM; /* Get a new skb... force flag on. */ - buff = sk_stream_alloc_skb(sk, nsize, GFP_ATOMIC); + buff = sk_stream_alloc_skb(sk, nsize, gfp); if (buff == NULL) return -ENOMEM; /* We'll just try again later. */ @@ -728,9 +1109,9 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ - flags = TCP_SKB_CB(skb)->flags; - TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN | TCPCB_FLAG_PSH); - TCP_SKB_CB(buff)->flags = flags; + flags = TCP_SKB_CB(skb)->tcp_flags; + TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); + TCP_SKB_CB(buff)->tcp_flags = flags; TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) { @@ -768,22 +1149,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, int diff = old_factor - tcp_skb_pcount(skb) - tcp_skb_pcount(buff); - tp->packets_out -= diff; - - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) - tp->sacked_out -= diff; - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) - tp->retrans_out -= diff; - - if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) - tp->lost_out -= diff; - - /* Adjust Reno SACK estimate. */ - if (tcp_is_reno(tp) && diff > 0) { - tcp_dec_pcount_approx_int(&tp->sacked_out, diff); - tcp_verify_left_out(tp); - } - tcp_adjust_fackets_out(sk, skb, diff); + if (diff) + tcp_adjust_pcount(sk, skb, diff); } /* Link BUFF into the send queue. */ @@ -799,41 +1166,49 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, */ static void __pskb_trim_head(struct sk_buff *skb, int len) { + struct skb_shared_info *shinfo; int i, k, eat; + eat = min_t(int, len, skb_headlen(skb)); + if (eat) { + __skb_pull(skb, eat); + len -= eat; + if (!len) + return; + } eat = len; k = 0; - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - if (skb_shinfo(skb)->frags[i].size <= eat) { - put_page(skb_shinfo(skb)->frags[i].page); - eat -= skb_shinfo(skb)->frags[i].size; + shinfo = skb_shinfo(skb); + for (i = 0; i < shinfo->nr_frags; i++) { + int size = skb_frag_size(&shinfo->frags[i]); + + if (size <= eat) { + skb_frag_unref(skb, i); + eat -= size; } else { - skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; + shinfo->frags[k] = shinfo->frags[i]; if (eat) { - skb_shinfo(skb)->frags[k].page_offset += eat; - skb_shinfo(skb)->frags[k].size -= eat; + shinfo->frags[k].page_offset += eat; + skb_frag_size_sub(&shinfo->frags[k], eat); eat = 0; } k++; } } - skb_shinfo(skb)->nr_frags = k; + shinfo->nr_frags = k; skb_reset_tail_pointer(skb); skb->data_len -= len; skb->len = skb->data_len; } +/* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { - if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; - /* If len == headlen, we avoid __skb_pull to preserve alignment. */ - if (unlikely(len < skb_headlen(skb))) - __skb_pull(skb, len); - else - __pskb_trim_head(skb, len - skb_headlen(skb)); + __pskb_trim_head(skb, len); TCP_SKB_CB(skb)->seq += len; skb->ip_summed = CHECKSUM_PARTIAL; @@ -843,20 +1218,18 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) sk_mem_uncharge(sk, len); sock_set_flag(sk, SOCK_QUEUE_SHRUNK); - /* Any change of skb->len requires recalculation of tso - * factor and mss. - */ + /* Any change of skb->len requires recalculation of tso factor. */ if (tcp_skb_pcount(skb) > 1) - tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk, 1)); + tcp_set_skb_tso_segs(sk, skb, tcp_skb_mss(skb)); return 0; } -/* Not accounting for SACKs here. */ -int tcp_mtu_to_mss(struct sock *sk, int pmtu) +/* Calculate MSS not accounting any TCP options. */ +static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) { - struct tcp_sock *tp = tcp_sk(sk); - struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_sock *tp = tcp_sk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; /* Calculate base mss without TCP options: @@ -864,6 +1237,14 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); + /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ + if (icsk->icsk_af_ops->net_frag_header_len) { + const struct dst_entry *dst = __sk_dst_get(sk); + + if (dst && dst_allfrag(dst)) + mss_now -= icsk->icsk_af_ops->net_frag_header_len; + } + /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; @@ -874,18 +1255,22 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) /* Then reserve room for full set of TCP options and 8 bytes of data */ if (mss_now < 48) mss_now = 48; - - /* Now subtract TCP options size, not including SACKs */ - mss_now -= tp->tcp_header_len - sizeof(struct tcphdr); - return mss_now; } +/* Calculate MSS. Not accounting for SACKs here. */ +int tcp_mtu_to_mss(struct sock *sk, int pmtu) +{ + /* Subtract TCP options size, not including SACKs */ + return __tcp_mtu_to_mss(sk, pmtu) - + (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); +} + /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { - struct tcp_sock *tp = tcp_sk(sk); - struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_sock *tp = tcp_sk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); int mtu; mtu = mss + @@ -893,9 +1278,17 @@ int tcp_mss_to_mtu(struct sock *sk, int mss) icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; + /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ + if (icsk->icsk_af_ops->net_frag_header_len) { + const struct dst_entry *dst = __sk_dst_get(sk); + + if (dst && dst_allfrag(dst)) + mtu += icsk->icsk_af_ops->net_frag_header_len; + } return mtu; } +/* MTU probing init per socket */ void tcp_mtup_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -907,15 +1300,7 @@ void tcp_mtup_init(struct sock *sk) icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, sysctl_tcp_base_mss); icsk->icsk_mtup.probe_size = 0; } - -/* Bound MSS / TSO packet size with the half of the window */ -static int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) -{ - if (tp->max_window && pktsize > (tp->max_window >> 1)) - return max(tp->max_window >> 1, 68U - tp->tcp_header_len); - else - return pktsize; -} +EXPORT_SYMBOL(tcp_mtup_init); /* This function synchronize snd mss to current pmtu/exthdr set. @@ -959,64 +1344,79 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) return mss_now; } +EXPORT_SYMBOL(tcp_sync_mss); /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. - * - * LARGESEND note: !urg_mode is overkill, only frames up to snd_up - * cannot be large. However, taking into account rare use of URG, this - * is not a big flaw. */ -unsigned int tcp_current_mss(struct sock *sk, int large_allowed) +unsigned int tcp_current_mss(struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); + const struct tcp_sock *tp = tcp_sk(sk); + const struct dst_entry *dst = __sk_dst_get(sk); u32 mss_now; - u16 xmit_size_goal; - int doing_tso = 0; + unsigned int header_len; + struct tcp_out_options opts; + struct tcp_md5sig_key *md5; mss_now = tp->mss_cache; - if (large_allowed && sk_can_gso(sk) && !tp->urg_mode) - doing_tso = 1; - if (dst) { u32 mtu = dst_mtu(dst); if (mtu != inet_csk(sk)->icsk_pmtu_cookie) mss_now = tcp_sync_mss(sk, mtu); } - if (tp->rx_opt.eff_sacks) - mss_now -= (TCPOLEN_SACK_BASE_ALIGNED + - (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK)); - -#ifdef CONFIG_TCP_MD5SIG - if (tp->af_specific->md5_lookup(sk, sk)) - mss_now -= TCPOLEN_MD5SIG_ALIGNED; -#endif + header_len = tcp_established_options(sk, NULL, &opts, &md5) + + sizeof(struct tcphdr); + /* The mss_cache is sized based on tp->tcp_header_len, which assumes + * some common options. If this is an odd packet (because we have SACK + * blocks etc) then our calculated header_len will be different, and + * we have to adjust mss_now correspondingly */ + if (header_len != tp->tcp_header_len) { + int delta = (int) header_len - tp->tcp_header_len; + mss_now -= delta; + } - xmit_size_goal = mss_now; + return mss_now; +} - if (doing_tso) { - xmit_size_goal = (65535 - - inet_csk(sk)->icsk_af_ops->net_header_len - - inet_csk(sk)->icsk_ext_hdr_len - - tp->tcp_header_len); +/* RFC2861, slow part. Adjust cwnd, after it was not full during one rto. + * As additional protections, we do not touch cwnd in retransmission phases, + * and if application hit its sndbuf limit recently. + */ +static void tcp_cwnd_application_limited(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); - xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal); - xmit_size_goal -= (xmit_size_goal % mss_now); + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open && + sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + /* Limited by application or receiver window. */ + u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk)); + u32 win_used = max(tp->snd_cwnd_used, init_win); + if (win_used < tp->snd_cwnd) { + tp->snd_ssthresh = tcp_current_ssthresh(sk); + tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1; + } + tp->snd_cwnd_used = 0; } - tp->xmit_size_goal = xmit_size_goal; - - return mss_now; + tp->snd_cwnd_stamp = tcp_time_stamp; } -/* Congestion window validation. (RFC2861) */ -static void tcp_cwnd_validate(struct sock *sk) +static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) { struct tcp_sock *tp = tcp_sk(sk); - if (tp->packets_out >= tp->snd_cwnd) { + /* Track the maximum number of outstanding packets in each + * window, and remember whether we were cwnd-limited then. + */ + if (!before(tp->snd_una, tp->max_packets_seq) || + tp->packets_out > tp->max_packets_out) { + tp->max_packets_out = tp->packets_out; + tp->max_packets_seq = tp->snd_nxt; + tp->is_cwnd_limited = is_cwnd_limited; + } + + if (tcp_is_cwnd_limited(sk)) { /* Network is feed fully. */ tp->snd_cwnd_used = 0; tp->snd_cwnd_stamp = tcp_time_stamp; @@ -1031,48 +1431,84 @@ static void tcp_cwnd_validate(struct sock *sk) } } -/* Returns the portion of skb which can be sent right away without - * introducing MSS oddities to segment boundaries. In rare cases where - * mss_now != mss_cache, we will request caller to create a small skb - * per input skb which could be mostly avoided here (if desired). - * - * We explicitly want to create a request for splitting write queue tail - * to a small skb for Nagle purposes while avoiding unnecessary modulos, - * thus all the complexity (cwnd_len is always MSS multiple which we - * return whenever allowed by the other factors). Basically we need the - * modulo only when the receiver window alone is the limiting factor or - * when we would be allowed to send the split-due-to-Nagle skb fully. +/* Minshall's variant of the Nagle send check. */ +static bool tcp_minshall_check(const struct tcp_sock *tp) +{ + return after(tp->snd_sml, tp->snd_una) && + !after(tp->snd_sml, tp->snd_nxt); +} + +/* Update snd_sml if this skb is under mss + * Note that a TSO packet might end with a sub-mss segment + * The test is really : + * if ((skb->len % mss) != 0) + * tp->snd_sml = TCP_SKB_CB(skb)->end_seq; + * But we can avoid doing the divide again given we already have + * skb_pcount = skb->len / mss_now */ -static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb, - unsigned int mss_now, unsigned int cwnd) +static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now, + const struct sk_buff *skb) { - struct tcp_sock *tp = tcp_sk(sk); - u32 needed, window, cwnd_len; + if (skb->len < tcp_skb_pcount(skb) * mss_now) + tp->snd_sml = TCP_SKB_CB(skb)->end_seq; +} + +/* Return false, if packet can be sent now without violation Nagle's rules: + * 1. It is full sized. (provided by caller in %partial bool) + * 2. Or it contains FIN. (already checked by caller) + * 3. Or TCP_CORK is not set, and TCP_NODELAY is 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 bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, + int nonagle) +{ + return partial && + ((nonagle & TCP_NAGLE_CORK) || + (!nonagle && tp->packets_out && tcp_minshall_check(tp))); +} +/* Returns the portion of skb which can be sent right away */ +static unsigned int tcp_mss_split_point(const struct sock *sk, + const struct sk_buff *skb, + unsigned int mss_now, + unsigned int max_segs, + int nonagle) +{ + const struct tcp_sock *tp = tcp_sk(sk); + u32 partial, needed, window, max_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; - cwnd_len = mss_now * cwnd; + max_len = mss_now * max_segs; - if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk))) - return cwnd_len; + if (likely(max_len <= window && skb != tcp_write_queue_tail(sk))) + return max_len; needed = min(skb->len, window); - if (skb == tcp_write_queue_tail(sk) && cwnd_len <= needed) - return cwnd_len; + if (max_len <= needed) + return max_len; - return needed - needed % mss_now; + partial = needed % mss_now; + /* If last segment is not a full MSS, check if Nagle rules allow us + * to include this last segment in this skb. + * Otherwise, we'll split the skb at last MSS boundary + */ + if (tcp_nagle_check(partial != 0, tp, nonagle)) + return needed - partial; + + return needed; } /* Can at least one segment of SKB be sent right now, according to the * congestion window rules? If so, return how many segments are allowed. */ -static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, - struct sk_buff *skb) +static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp, + const struct sk_buff *skb) { u32 in_flight, cwnd; /* Don't be strict about the congestion window for the final FIN. */ - if ((TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) && + if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) && tcp_skb_pcount(skb) == 1) return 1; @@ -1084,10 +1520,11 @@ static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, return 0; } -/* This must be invoked the first time we consider transmitting +/* Initialize TSO state of a skb. + * This must be invoked the first time we consider transmitting * SKB onto the wire. */ -static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, +static int tcp_init_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); @@ -1099,33 +1536,12 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, return tso_segs; } -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); -} - -/* Return 0, if packet can be sent now without violation Nagle's rules: - * 1. It is full sized. - * 2. Or it contains FIN. (already checked by caller) - * 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 && - ((nonagle & TCP_NAGLE_CORK) || - (!nonagle && tp->packets_out && tcp_minshall_check(tp)))); -} -/* Return non-zero if the Nagle test allows this packet to be +/* Return true if the Nagle test allows this packet to be * sent now. */ -static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb, - unsigned int cur_mss, int nonagle) +static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, + unsigned int cur_mss, int nonagle) { /* Nagle rule does not apply to frames, which sit in the middle of the * write_queue (they have no chances to get new data). @@ -1134,24 +1550,22 @@ static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb, * argument based upon the location of SKB in the send queue. */ if (nonagle & TCP_NAGLE_PUSH) - return 1; + return true; - /* Don't use the nagle rule for urgent data (or for the final FIN). - * Nagle can be ignored during F-RTO too (see RFC4138). - */ - if (tp->urg_mode || (tp->frto_counter == 2) || - (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)) - return 1; + /* Don't use the nagle rule for urgent data (or for the final FIN). */ + if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) + return true; - if (!tcp_nagle_check(tp, skb, cur_mss, nonagle)) - return 1; + if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle)) + return true; - return 0; + return false; } /* Does at least the first segment of SKB fit into the send window? */ -static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb, - unsigned int cur_mss) +static bool tcp_snd_wnd_test(const struct tcp_sock *tp, + const struct sk_buff *skb, + unsigned int cur_mss) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; @@ -1165,10 +1579,10 @@ static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb, * should be put on the wire right now. If so, it returns the number of * packets allowed by the congestion window. */ -static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb, +static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb, unsigned int cur_mss, int nonagle) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); unsigned int cwnd_quota; tcp_init_tso_segs(sk, skb, cur_mss); @@ -1183,15 +1597,16 @@ static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb, return cwnd_quota; } -int tcp_may_send_now(struct sock *sk) +/* Test if sending is allowed right now. */ +bool tcp_may_send_now(struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = tcp_send_head(sk); - return (skb && - tcp_snd_test(sk, skb, tcp_current_mss(sk, 1), + return skb && + tcp_snd_test(sk, skb, tcp_current_mss(sk), (tcp_skb_is_last(sk, skb) ? - tp->nonagle : TCP_NAGLE_PUSH))); + tp->nonagle : TCP_NAGLE_PUSH)); } /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet @@ -1202,17 +1617,17 @@ int tcp_may_send_now(struct sock *sk) * packet has never been sent out before (and thus is not cloned). */ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, - unsigned int mss_now) + unsigned int mss_now, gfp_t gfp) { struct sk_buff *buff; int nlen = skb->len - len; - u16 flags; + u8 flags; /* All of a TSO frame must be composed of paged data. */ if (skb->len != skb->data_len) - return tcp_fragment(sk, skb, len, mss_now); + return tcp_fragment(sk, skb, len, mss_now, gfp); - buff = sk_stream_alloc_skb(sk, 0, GFP_ATOMIC); + buff = sk_stream_alloc_skb(sk, 0, gfp); if (unlikely(buff == NULL)) return -ENOMEM; @@ -1227,9 +1642,9 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ - flags = TCP_SKB_CB(skb)->flags; - TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN | TCPCB_FLAG_PSH); - TCP_SKB_CB(buff)->flags = flags; + flags = TCP_SKB_CB(skb)->tcp_flags; + TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); + TCP_SKB_CB(buff)->tcp_flags = flags; /* This packet was never sent out yet, so no SACK bits. */ TCP_SKB_CB(buff)->sacked = 0; @@ -1253,13 +1668,15 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, * * This algorithm is from John Heffner. */ -static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) +static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, + bool *is_cwnd_limited) { struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 send_win, cong_win, limit, in_flight; + int win_divisor; - if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto send_now; if (icsk->icsk_ca_state != TCP_CA_Open) @@ -1267,7 +1684,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) /* Defer for less than two clock ticks. */ if (tp->tso_deferred && - ((jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1) + (((u32)jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1) goto send_now; in_flight = tcp_packets_in_flight(tp); @@ -1282,16 +1699,22 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) limit = min(send_win, cong_win); /* If a full-sized TSO skb can be sent, do it. */ - if (limit >= 65536) + if (limit >= min_t(unsigned int, sk->sk_gso_max_size, + tp->xmit_size_goal_segs * tp->mss_cache)) goto send_now; - if (sysctl_tcp_tso_win_divisor) { + /* Middle in queue won't get any more data, full sendable already? */ + if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) + goto send_now; + + win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor); + if (win_divisor) { u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); /* If at least some fraction of a window is available, * just use it. */ - chunk /= sysctl_tcp_tso_win_divisor; + chunk /= win_divisor; if (limit >= chunk) goto send_now; } else { @@ -1300,21 +1723,31 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) * frame, so if we have space for more than 3 frames * then send now. */ - if (limit > tcp_max_burst(tp) * tp->mss_cache) + if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache) goto send_now; } - /* Ok, it looks like it is advisable to defer. */ - tp->tso_deferred = 1 | (jiffies << 1); + /* Ok, it looks like it is advisable to defer. + * Do not rearm the timer if already set to not break TCP ACK clocking. + */ + if (!tp->tso_deferred) + tp->tso_deferred = 1 | (jiffies << 1); + + if (cong_win < send_win && cong_win < skb->len) + *is_cwnd_limited = true; - return 1; + return true; send_now: tp->tso_deferred = 0; - return 0; + return false; } /* Create a new MTU probe if we are ready. + * MTU probe is regularly attempting to increase the path MTU by + * deliberately sending larger packets. This discovers routing + * changes resulting in larger path MTUs. + * * Returns 0 if we should wait to probe (no cwnd available), * 1 if a probe was sent, * -1 otherwise @@ -1338,11 +1771,11 @@ static int tcp_mtu_probe(struct sock *sk) icsk->icsk_mtup.probe_size || inet_csk(sk)->icsk_ca_state != TCP_CA_Open || tp->snd_cwnd < 11 || - tp->rx_opt.eff_sacks) + tp->rx_opt.num_sacks || tp->rx_opt.dsack) return -1; /* Very simple search strategy: just double the MSS. */ - mss_now = tcp_current_mss(sk, 0); + mss_now = tcp_current_mss(sk); probe_size = 2 * tp->mss_cache; size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache; if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) { @@ -1377,7 +1810,7 @@ static int tcp_mtu_probe(struct sock *sk) TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; - TCP_SKB_CB(nskb)->flags = TCPCB_FLAG_ACK; + TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK; TCP_SKB_CB(nskb)->sacked = 0; nskb->csum = 0; nskb->ip_summed = skb->ip_summed; @@ -1397,12 +1830,12 @@ static int tcp_mtu_probe(struct sock *sk) if (skb->len <= copy) { /* We've eaten all the data from this skb. * Throw it away. */ - TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags; + TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { - TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags & - ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH); + TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags & + ~(TCPHDR_FIN|TCPHDR_PSH); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); if (skb->ip_summed != CHECKSUM_PARTIAL) @@ -1445,31 +1878,36 @@ static int tcp_mtu_probe(struct sock *sk) * send_head. This happens as incoming acks open up the remote * window for us. * - * Returns 1, if no segments are in flight and we have queued segments, but - * cannot send anything now because of SWS or another problem. + * LARGESEND note: !tcp_urg_mode is overkill, only frames between + * snd_up-64k-mss .. snd_up cannot be large. However, taking into + * account rare use of URG, this is not a big flaw. + * + * Send at most one packet when push_one > 0. Temporarily ignore + * cwnd limit to force at most one packet out when push_one == 2. + + * Returns true, if no segments are in flight and we have queued segments, + * but cannot send anything now because of SWS or another problem. */ -static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) +static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, + int push_one, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; unsigned int tso_segs, sent_pkts; int cwnd_quota; int result; - - /* If we are closed, the bytes will have to remain here. - * In time closedown will finish, we empty the write queue and all - * will be happy. - */ - if (unlikely(sk->sk_state == TCP_CLOSE)) - return 0; + bool is_cwnd_limited = false; sent_pkts = 0; - /* Do MTU probing. */ - if ((result = tcp_mtu_probe(sk)) == 0) { - return 0; - } else if (result > 0) { - sent_pkts = 1; + if (!push_one) { + /* Do MTU probing. */ + result = tcp_mtu_probe(sk); + if (!result) { + return false; + } else if (result > 0) { + sent_pkts = 1; + } } while ((skb = tcp_send_head(sk))) { @@ -1478,9 +1916,18 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); + if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) + goto repair; /* Skip network transmission */ + cwnd_quota = tcp_cwnd_test(tp, skb); - if (!cwnd_quota) - break; + if (!cwnd_quota) { + is_cwnd_limited = true; + if (push_one == 2) + /* Force out a loss probe pkt. */ + cwnd_quota = 1; + else + break; + } if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) break; @@ -1491,38 +1938,211 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) nonagle : TCP_NAGLE_PUSH)))) break; } else { - if (tcp_tso_should_defer(sk, skb)) + if (!push_one && + tcp_tso_should_defer(sk, skb, &is_cwnd_limited)) + break; + } + + /* TCP Small Queues : + * Control number of packets in qdisc/devices to two packets / or ~1 ms. + * This allows for : + * - better RTT estimation and ACK scheduling + * - faster recovery + * - high rates + * Alas, some drivers / subsystems require a fair amount + * of queued bytes to ensure line rate. + * One example is wifi aggregation (802.11 AMPDU) + */ + limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes, + sk->sk_pacing_rate >> 10); + + if (atomic_read(&sk->sk_wmem_alloc) > limit) { + set_bit(TSQ_THROTTLED, &tp->tsq_flags); + /* It is possible TX completion already happened + * before we set TSQ_THROTTLED, so we must + * test again the condition. + */ + smp_mb__after_atomic(); + if (atomic_read(&sk->sk_wmem_alloc) > limit) break; } limit = mss_now; - if (tso_segs > 1) + if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, - cwnd_quota); + min_t(unsigned int, + cwnd_quota, + sk->sk_gso_max_segs), + nonagle); if (skb->len > limit && - unlikely(tso_fragment(sk, skb, limit, mss_now))) + unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) break; TCP_SKB_CB(skb)->when = tcp_time_stamp; - if (unlikely(tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC))) + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; +repair: /* Advance the send_head. This one is sent out. * This call will increment packets_out. */ tcp_event_new_data_sent(sk, skb); tcp_minshall_update(tp, mss_now, skb); - sent_pkts++; + sent_pkts += tcp_skb_pcount(skb); + + if (push_one) + break; } if (likely(sent_pkts)) { - tcp_cwnd_validate(sk); - return 0; + if (tcp_in_cwnd_reduction(sk)) + tp->prr_out += sent_pkts; + + /* Send one loss probe per tail loss episode. */ + if (push_one != 2) + tcp_schedule_loss_probe(sk); + tcp_cwnd_validate(sk, is_cwnd_limited); + return false; + } + return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk)); +} + +bool tcp_schedule_loss_probe(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + u32 timeout, tlp_time_stamp, rto_time_stamp; + u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3); + + if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS)) + return false; + /* No consecutive loss probes. */ + if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) { + tcp_rearm_rto(sk); + return false; + } + /* Don't do any loss probe on a Fast Open connection before 3WHS + * finishes. + */ + if (sk->sk_state == TCP_SYN_RECV) + return false; + + /* TLP is only scheduled when next timer event is RTO. */ + if (icsk->icsk_pending != ICSK_TIME_RETRANS) + return false; + + /* Schedule a loss probe in 2*RTT for SACK capable connections + * in Open state, that are either limited by cwnd or application. + */ + if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out || + !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open) + return false; + + if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) && + tcp_send_head(sk)) + return false; + + /* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account + * for delayed ack when there's one outstanding packet. + */ + timeout = rtt << 1; + if (tp->packets_out == 1) + timeout = max_t(u32, timeout, + (rtt + (rtt >> 1) + TCP_DELACK_MAX)); + timeout = max_t(u32, timeout, msecs_to_jiffies(10)); + + /* If RTO is shorter, just schedule TLP in its place. */ + tlp_time_stamp = tcp_time_stamp + timeout; + rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout; + if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) { + s32 delta = rto_time_stamp - tcp_time_stamp; + if (delta > 0) + timeout = delta; + } + + inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, + TCP_RTO_MAX); + return true; +} + +/* Thanks to skb fast clones, we can detect if a prior transmit of + * a packet is still in a qdisc or driver queue. + * In this case, there is very little point doing a retransmit ! + * Note: This is called from BH context only. + */ +static bool skb_still_in_host_queue(const struct sock *sk, + const struct sk_buff *skb) +{ + const struct sk_buff *fclone = skb + 1; + + if (unlikely(skb->fclone == SKB_FCLONE_ORIG && + fclone->fclone == SKB_FCLONE_CLONE)) { + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + return true; } - return !tp->packets_out && tcp_send_head(sk); + return false; +} + +/* When probe timeout (PTO) fires, send a new segment if one exists, else + * retransmit the last segment. + */ +void tcp_send_loss_probe(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + int pcount; + int mss = tcp_current_mss(sk); + int err = -1; + + if (tcp_send_head(sk) != NULL) { + err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); + goto rearm_timer; + } + + /* At most one outstanding TLP retransmission. */ + if (tp->tlp_high_seq) + goto rearm_timer; + + /* Retransmit last segment. */ + skb = tcp_write_queue_tail(sk); + if (WARN_ON(!skb)) + goto rearm_timer; + + if (skb_still_in_host_queue(sk, skb)) + goto rearm_timer; + + pcount = tcp_skb_pcount(skb); + if (WARN_ON(!pcount)) + goto rearm_timer; + + if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { + if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss, + GFP_ATOMIC))) + goto rearm_timer; + skb = tcp_write_queue_tail(sk); + } + + if (WARN_ON(!skb || !tcp_skb_pcount(skb))) + goto rearm_timer; + + err = __tcp_retransmit_skb(sk, skb); + + /* Record snd_nxt for loss detection. */ + if (likely(!err)) + tp->tlp_high_seq = tp->snd_nxt; + +rearm_timer: + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + inet_csk(sk)->icsk_rto, + TCP_RTO_MAX); + + if (likely(!err)) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPLOSSPROBES); } /* Push out any pending frames which were held back due to @@ -1532,12 +2152,16 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle) { - struct sk_buff *skb = tcp_send_head(sk); + /* If we are closed, the bytes will have to remain here. + * In time closedown will finish, we empty the write queue and + * all will be happy. + */ + if (unlikely(sk->sk_state == TCP_CLOSE)) + return; - if (skb) { - if (tcp_write_xmit(sk, cur_mss, nonagle)) - tcp_check_probe_timer(sk); - } + if (tcp_write_xmit(sk, cur_mss, nonagle, 0, + sk_gfp_atomic(sk, GFP_ATOMIC))) + tcp_check_probe_timer(sk); } /* Send _single_ skb sitting at the send head. This function requires @@ -1546,36 +2170,10 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, void tcp_push_one(struct sock *sk, unsigned int mss_now) { struct sk_buff *skb = tcp_send_head(sk); - unsigned int tso_segs, cwnd_quota; BUG_ON(!skb || skb->len < mss_now); - tso_segs = tcp_init_tso_segs(sk, skb, mss_now); - cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH); - - if (likely(cwnd_quota)) { - unsigned int limit; - - BUG_ON(!tso_segs); - - limit = mss_now; - if (tso_segs > 1) - limit = tcp_mss_split_point(sk, skb, mss_now, - cwnd_quota); - - if (skb->len > limit && - unlikely(tso_fragment(sk, skb, limit, mss_now))) - return; - - /* Send it out now. */ - TCP_SKB_CB(skb)->when = tcp_time_stamp; - - if (likely(!tcp_transmit_skb(sk, skb, 1, sk->sk_allocation))) { - tcp_event_new_data_sent(sk, skb); - tcp_cwnd_validate(sk); - return; - } - } + tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation); } /* This function returns the amount that we can raise the @@ -1642,7 +2240,8 @@ u32 __tcp_select_window(struct sock *sk) */ int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); - int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk)); + int allowed_space = tcp_full_space(sk); + int full_space = min_t(int, tp->window_clamp, allowed_space); int window; if (mss > full_space) @@ -1651,11 +2250,23 @@ u32 __tcp_select_window(struct sock *sk) if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; - if (tcp_memory_pressure) + if (sk_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); - if (free_space < mss) + /* free_space might become our new window, make sure we don't + * increase it due to wscale. + */ + free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); + + /* if free space is less than mss estimate, or is below 1/16th + * of the maximum allowed, try to move to zero-window, else + * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and + * new incoming data is dropped due to memory limits. + * With large window, mss test triggers way too late in order + * to announce zero window in time before rmem limit kicks in. + */ + if (free_space < (allowed_space >> 4) || free_space < mss) return 0; } @@ -1695,46 +2306,20 @@ u32 __tcp_select_window(struct sock *sk) return window; } -/* Attempt to collapse two adjacent SKB's during retransmission. */ -static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, - int mss_now) +/* Collapses two adjacent SKB's during retransmission. */ +static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *next_skb = tcp_write_queue_next(sk, skb); int skb_size, next_skb_size; - u16 flags; - - /* The first test we must make is that neither of these two - * SKB's are still referenced by someone else. - */ - if (skb_cloned(skb) || skb_cloned(next_skb)) - return; skb_size = skb->len; next_skb_size = next_skb->len; - flags = TCP_SKB_CB(skb)->flags; - - /* Also punt if next skb has been SACK'd. */ - if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_ACKED) - return; - - /* Next skb is out of window. */ - if (after(TCP_SKB_CB(next_skb)->end_seq, tcp_wnd_end(tp))) - return; - - /* Punt if not enough space exists in the first SKB for - * the data in the second, or the total combined payload - * would exceed the MSS. - */ - if ((next_skb_size > skb_tailroom(skb)) || - ((skb_size + next_skb_size) > mss_now)) - return; BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1); tcp_highest_sack_combine(sk, next_skb, skb); - /* Ok. We will be able to collapse the packet. */ tcp_unlink_write_queue(next_skb, sk); skb_copy_from_linear_data(next_skb, skb_put(skb, next_skb_size), @@ -1749,91 +2334,93 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, /* Update sequence range on original skb. */ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; - /* Merge over control information. */ - flags |= TCP_SKB_CB(next_skb)->flags; /* This moves PSH/FIN etc. over */ - TCP_SKB_CB(skb)->flags = flags; + /* Merge over control information. This moves PSH/FIN etc. over */ + TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(next_skb)->tcp_flags; /* All done, get rid of second SKB and account for it so * packet counting does not break. */ TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS; - if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_RETRANS) - tp->retrans_out -= tcp_skb_pcount(next_skb); - if (TCP_SKB_CB(next_skb)->sacked & TCPCB_LOST) - tp->lost_out -= tcp_skb_pcount(next_skb); - /* Reno case is special. Sigh... */ - if (tcp_is_reno(tp) && tp->sacked_out) - tcp_dec_pcount_approx(&tp->sacked_out, next_skb); - - tcp_adjust_fackets_out(sk, next_skb, tcp_skb_pcount(next_skb)); - tp->packets_out -= tcp_skb_pcount(next_skb); /* changed transmit queue under us so clear hints */ tcp_clear_retrans_hints_partial(tp); + if (next_skb == tp->retransmit_skb_hint) + tp->retransmit_skb_hint = skb; + + tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb)); sk_wmem_free_skb(sk, next_skb); } -/* Do a simple retransmit without using the backoff mechanisms in - * tcp_timer. This is used for path mtu discovery. - * The socket is already locked here. +/* Check if coalescing SKBs is legal. */ +static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) +{ + if (tcp_skb_pcount(skb) > 1) + return false; + /* TODO: SACK collapsing could be used to remove this condition */ + if (skb_shinfo(skb)->nr_frags != 0) + return false; + if (skb_cloned(skb)) + return false; + if (skb == tcp_send_head(sk)) + return false; + /* Some heurestics for collapsing over SACK'd could be invented */ + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) + return false; + + return true; +} + +/* Collapse packets in the retransmit queue to make to create + * less packets on the wire. This is only done on retransmission. */ -void tcp_simple_retransmit(struct sock *sk) +static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, + int space) { - const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - unsigned int mss = tcp_current_mss(sk, 0); - int lost = 0; + struct sk_buff *skb = to, *tmp; + bool first = true; - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) + if (!sysctl_tcp_retrans_collapse) + return; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) + return; + + tcp_for_write_queue_from_safe(skb, tmp, sk) { + if (!tcp_can_collapse(sk, skb)) break; - if (skb->len > mss && - !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; - tp->retrans_out -= tcp_skb_pcount(skb); - } - if (!(TCP_SKB_CB(skb)->sacked & TCPCB_LOST)) { - TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; - tp->lost_out += tcp_skb_pcount(skb); - lost = 1; - } - } - } - tcp_clear_all_retrans_hints(tp); + space -= skb->len; - if (!lost) - return; + if (first) { + first = false; + continue; + } - tcp_verify_left_out(tp); + if (space < 0) + break; + /* Punt if not enough space exists in the first SKB for + * the data in the second + */ + if (skb->len > skb_availroom(to)) + break; - /* Don't muck with the congestion window here. - * Reason is that we do not increase amount of _data_ - * in network, but units changed and effective - * cwnd/ssthresh really reduced now. - */ - if (icsk->icsk_ca_state != TCP_CA_Loss) { - tp->high_seq = tp->snd_nxt; - tp->snd_ssthresh = tcp_current_ssthresh(sk); - tp->prior_ssthresh = 0; - tp->undo_marker = 0; - tcp_set_ca_state(sk, TCP_CA_Loss); + if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) + break; + + tcp_collapse_retrans(sk, to); } - tcp_xmit_retransmit_queue(sk); } /* This retransmits one SKB. Policy decisions and retransmit queue * state updates are done by the caller. Returns non-zero if an * error occurred which prevented the send. */ -int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) +int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); - unsigned int cur_mss = tcp_current_mss(sk, 0); + unsigned int cur_mss; int err; /* Inconslusive MTU probe */ @@ -1848,6 +2435,9 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) return -EAGAIN; + if (skb_still_in_host_queue(sk, skb)) + return -EBUSY; + if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) BUG(); @@ -1855,67 +2445,75 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) return -ENOMEM; } + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) + return -EHOSTUNREACH; /* Routing failure or similar. */ + + cur_mss = tcp_current_mss(sk); + /* If receiver has shrunk his window, and skb is out of * new window, do not retransmit it. The exception is the * case, when window is shrunk to zero. In this case * our retransmit serves as a zero window probe. */ - if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) - && TCP_SKB_CB(skb)->seq != tp->snd_una) + if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) && + TCP_SKB_CB(skb)->seq != tp->snd_una) return -EAGAIN; if (skb->len > cur_mss) { - if (tcp_fragment(sk, skb, cur_mss, cur_mss)) + if (tcp_fragment(sk, skb, cur_mss, cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ - } - - /* Collapse two adjacent packets if worthwhile and we can. */ - if (!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN) && - (skb->len < (cur_mss >> 1)) && - (tcp_write_queue_next(sk, skb) != tcp_send_head(sk)) && - (!tcp_skb_is_last(sk, skb)) && - (skb_shinfo(skb)->nr_frags == 0 && - skb_shinfo(tcp_write_queue_next(sk, skb))->nr_frags == 0) && - (tcp_skb_pcount(skb) == 1 && - tcp_skb_pcount(tcp_write_queue_next(sk, skb)) == 1) && - (sysctl_tcp_retrans_collapse != 0)) - tcp_retrans_try_collapse(sk, skb, cur_mss); - - if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) - return -EHOSTUNREACH; /* Routing failure or similar. */ + } else { + int oldpcount = tcp_skb_pcount(skb); - /* Some Solaris stacks overoptimize and ignore the FIN on a - * retransmit when old data is attached. So strip it off - * since it is cheap to do so and saves bytes on the network. - */ - if (skb->len > 0 && - (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) && - tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) { - if (!pskb_trim(skb, 0)) { - /* Reuse, even though it does some unnecessary work */ - tcp_init_nondata_skb(skb, TCP_SKB_CB(skb)->end_seq - 1, - TCP_SKB_CB(skb)->flags); - skb->ip_summed = CHECKSUM_NONE; + if (unlikely(oldpcount > 1)) { + if (skb_unclone(skb, GFP_ATOMIC)) + return -ENOMEM; + tcp_init_tso_segs(sk, skb, cur_mss); + tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb)); } } + tcp_retrans_try_collapse(sk, skb, cur_mss); + /* Make a copy, if the first transmission SKB clone we made * is still in somebody's hands, else make a clone. */ TCP_SKB_CB(skb)->when = tcp_time_stamp; - err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + /* make sure skb->data is aligned on arches that require it + * and check if ack-trimming & collapsing extended the headroom + * beyond what csum_start can cover. + */ + if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || + skb_headroom(skb) >= 0xFFFF)) { + struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, + GFP_ATOMIC); + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; + } else { + err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + } - if (err == 0) { + if (likely(!err)) { + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; /* Update global TCP statistics. */ - TCP_INC_STATS(TCP_MIB_RETRANSSEGS); - + TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); tp->total_retrans++; + } + return err; +} +int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + int err = __tcp_retransmit_skb(sk, skb); + + if (err == 0) { #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { - if (net_ratelimit()) - printk(KERN_DEBUG "retrans_out leaked.\n"); + net_dbg_ratelimited("retrans_out leaked\n"); } #endif if (!tp->retrans_out) @@ -1927,93 +2525,35 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (!tp->retrans_stamp) tp->retrans_stamp = TCP_SKB_CB(skb)->when; - tp->undo_retrans++; - /* snd_nxt is stored to detect loss of retransmitted segment, * see tcp_input.c tcp_sacktag_write_queue(). */ TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt; + } else if (err != -EBUSY) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); } + + if (tp->undo_retrans < 0) + tp->undo_retrans = 0; + tp->undo_retrans += tcp_skb_pcount(skb); return err; } -/* This gets called after a retransmit timeout, and the initially - * retransmitted data is acknowledged. It tries to continue - * resending the rest of the retransmit queue, until either - * we've sent it all or the congestion window limit is reached. - * If doing SACK, the first ACK which comes back for a timeout - * based retransmit packet might feed us FACK information again. - * If so, we use it to avoid unnecessarily retransmissions. +/* Check if we forward retransmits are possible in the current + * window/congestion state. */ -void tcp_xmit_retransmit_queue(struct sock *sk) +static bool tcp_can_forward_retransmit(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - int packet_cnt; - - if (tp->retransmit_skb_hint) { - skb = tp->retransmit_skb_hint; - packet_cnt = tp->retransmit_cnt_hint; - } else { - skb = tcp_write_queue_head(sk); - packet_cnt = 0; - } - - /* First pass: retransmit lost packets. */ - if (tp->lost_out) { - tcp_for_write_queue_from(skb, sk) { - __u8 sacked = TCP_SKB_CB(skb)->sacked; - - if (skb == tcp_send_head(sk)) - break; - /* we could do better than to assign each time */ - tp->retransmit_skb_hint = skb; - tp->retransmit_cnt_hint = packet_cnt; - - /* Assume this retransmit will generate - * only one packet for congestion window - * calculation purposes. This works because - * tcp_retransmit_skb() will chop up the - * packet to be MSS sized and all the - * packet counting works out. - */ - if (tcp_packets_in_flight(tp) >= tp->snd_cwnd) - return; - - if (sacked & TCPCB_LOST) { - if (!(sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))) { - if (tcp_retransmit_skb(sk, skb)) { - tp->retransmit_skb_hint = NULL; - return; - } - if (icsk->icsk_ca_state != TCP_CA_Loss) - NET_INC_STATS_BH(LINUX_MIB_TCPFASTRETRANS); - else - NET_INC_STATS_BH(LINUX_MIB_TCPSLOWSTARTRETRANS); - - if (skb == tcp_write_queue_head(sk)) - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, - TCP_RTO_MAX); - } - - packet_cnt += tcp_skb_pcount(skb); - if (packet_cnt >= tp->lost_out) - break; - } - } - } - - /* OK, demanded retransmission is finished. */ + const struct tcp_sock *tp = tcp_sk(sk); /* Forward retransmissions are possible only during Recovery. */ if (icsk->icsk_ca_state != TCP_CA_Recovery) - return; + return false; /* No forward retransmissions in Reno are possible. */ if (tcp_is_reno(tp)) - return; + return false; /* Yeah, we have to make difficult choice between forward transmission * and retransmission... Both ways have their merits... @@ -2024,43 +2564,110 @@ void tcp_xmit_retransmit_queue(struct sock *sk) */ if (tcp_may_send_now(sk)) - return; + return false; + + return true; +} + +/* This gets called after a retransmit timeout, and the initially + * retransmitted data is acknowledged. It tries to continue + * resending the rest of the retransmit queue, until either + * we've sent it all or the congestion window limit is reached. + * If doing SACK, the first ACK which comes back for a timeout + * based retransmit packet might feed us FACK information again. + * If so, we use it to avoid unnecessarily retransmissions. + */ +void tcp_xmit_retransmit_queue(struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + struct sk_buff *hole = NULL; + u32 last_lost; + int mib_idx; + int fwd_rexmitting = 0; - /* If nothing is SACKed, highest_sack in the loop won't be valid */ - if (!tp->sacked_out) + if (!tp->packets_out) return; - if (tp->forward_skb_hint) - skb = tp->forward_skb_hint; - else + if (!tp->lost_out) + tp->retransmit_high = tp->snd_una; + + if (tp->retransmit_skb_hint) { + skb = tp->retransmit_skb_hint; + last_lost = TCP_SKB_CB(skb)->end_seq; + if (after(last_lost, tp->retransmit_high)) + last_lost = tp->retransmit_high; + } else { skb = tcp_write_queue_head(sk); + last_lost = tp->snd_una; + } tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - tp->forward_skb_hint = skb; + __u8 sacked = TCP_SKB_CB(skb)->sacked; - if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) + if (skb == tcp_send_head(sk)) break; + /* we could do better than to assign each time */ + if (hole == NULL) + tp->retransmit_skb_hint = skb; + /* Assume this retransmit will generate + * only one packet for congestion window + * calculation purposes. This works because + * tcp_retransmit_skb() will chop up the + * packet to be MSS sized and all the + * packet counting works out. + */ if (tcp_packets_in_flight(tp) >= tp->snd_cwnd) - break; + return; - if (TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) + if (fwd_rexmitting) { +begin_fwd: + if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) + break; + mib_idx = LINUX_MIB_TCPFORWARDRETRANS; + + } else if (!before(TCP_SKB_CB(skb)->seq, tp->retransmit_high)) { + tp->retransmit_high = last_lost; + if (!tcp_can_forward_retransmit(sk)) + break; + /* Backtrack if necessary to non-L'ed skb */ + if (hole != NULL) { + skb = hole; + hole = NULL; + } + fwd_rexmitting = 1; + goto begin_fwd; + + } else if (!(sacked & TCPCB_LOST)) { + if (hole == NULL && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED))) + hole = skb; continue; - /* Ok, retransmit it. */ - if (tcp_retransmit_skb(sk, skb)) { - tp->forward_skb_hint = NULL; - break; + } else { + last_lost = TCP_SKB_CB(skb)->end_seq; + if (icsk->icsk_ca_state != TCP_CA_Loss) + mib_idx = LINUX_MIB_TCPFASTRETRANS; + else + mib_idx = LINUX_MIB_TCPSLOWSTARTRETRANS; } + if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS)) + continue; + + if (tcp_retransmit_skb(sk, skb)) + return; + + NET_INC_STATS_BH(sock_net(sk), mib_idx); + + if (tcp_in_cwnd_reduction(sk)) + tp->prr_out += tcp_skb_pcount(skb); + if (skb == tcp_write_queue_head(sk)) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); - - NET_INC_STATS_BH(LINUX_MIB_TCPFORWARDRETRANS); } } @@ -2077,16 +2684,17 @@ void tcp_send_fin(struct sock *sk) * unsent frames. But be careful about outgoing SACKS * and IP options. */ - mss_now = tcp_current_mss(sk, 1); + mss_now = tcp_current_mss(sk); if (tcp_send_head(sk) != NULL) { - TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_FIN; + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(skb)->end_seq++; tp->write_seq++; } else { /* Socket is locked, keep trying until memory is available. */ for (;;) { - skb = alloc_skb_fclone(MAX_TCP_HEADER, GFP_KERNEL); + skb = alloc_skb_fclone(MAX_TCP_HEADER, + sk->sk_allocation); if (skb) break; yield(); @@ -2096,7 +2704,7 @@ void tcp_send_fin(struct sock *sk) skb_reserve(skb, MAX_TCP_HEADER); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, - TCPCB_FLAG_ACK | TCPCB_FLAG_FIN); + TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF); @@ -2114,21 +2722,24 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) /* NOTE: No TCP options attached and we never retransmit this. */ skb = alloc_skb(MAX_TCP_HEADER, priority); if (!skb) { - NET_INC_STATS(LINUX_MIB_TCPABORTFAILED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), - TCPCB_FLAG_ACK | TCPCB_FLAG_RST); + TCPHDR_ACK | TCPHDR_RST); /* Send it off. */ TCP_SKB_CB(skb)->when = tcp_time_stamp; if (tcp_transmit_skb(sk, skb, 0, priority)) - NET_INC_STATS(LINUX_MIB_TCPABORTFAILED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); + + TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); } -/* WARNING: This routine must only be called when we have already sent +/* Send a crossed SYN-ACK during socket establishment. + * WARNING: This routine must only be called when we have already sent * a SYN packet that crossed the incoming SYN that caused this routine * to get called. If this assumption fails then the initial rcv_wnd * and rcv_wscale values will not be correct. @@ -2138,11 +2749,11 @@ int tcp_send_synack(struct sock *sk) struct sk_buff *skb; skb = tcp_write_queue_head(sk); - if (skb == NULL || !(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN)) { - printk(KERN_DEBUG "tcp_send_synack: wrong queue state\n"); + if (skb == NULL || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { + pr_debug("%s: wrong queue state\n", __func__); return -EFAULT; } - if (!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_ACK)) { + if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); if (nskb == NULL) @@ -2156,50 +2767,60 @@ int tcp_send_synack(struct sock *sk) skb = nskb; } - TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ACK; + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK; TCP_ECN_send_synack(tcp_sk(sk), skb); } TCP_SKB_CB(skb)->when = tcp_time_stamp; return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } -/* - * Prepare a SYN-ACK. +/** + * tcp_make_synack - Prepare a SYN-ACK. + * sk: listener socket + * dst: dst entry attached to the SYNACK + * req: request_sock pointer + * + * Allocate one skb and build a SYNACK packet. + * @dst is consumed : Caller should not use it again. */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, - struct request_sock *req) + struct request_sock *req, + struct tcp_fastopen_cookie *foc) { + struct tcp_out_options opts; struct inet_request_sock *ireq = inet_rsk(req); struct tcp_sock *tp = tcp_sk(sk); struct tcphdr *th; - int tcp_header_size; struct sk_buff *skb; -#ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *md5; - __u8 *md5_hash_location; -#endif + int tcp_header_size; + int mss; - skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC); - if (skb == NULL) + skb = sock_wmalloc(sk, MAX_TCP_HEADER, 1, GFP_ATOMIC); + if (unlikely(!skb)) { + dst_release(dst); return NULL; - + } /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst); + security_skb_owned_by(skb, sk); - tcp_header_size = (sizeof(struct tcphdr) + TCPOLEN_MSS + - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) + - (ireq->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) + - /* SACK_PERM is in the place of NOP NOP of TS */ - ((ireq->sack_ok && !ireq->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0)); + mss = dst_metric_advmss(dst); + if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) + mss = tp->rx_opt.user_mss; -#ifdef CONFIG_TCP_MD5SIG - /* Are we doing MD5 on this segment? If so - make room for it */ - md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req); - if (md5) - tcp_header_size += TCPOLEN_MD5SIG_ALIGNED; + memset(&opts, 0, sizeof(opts)); +#ifdef CONFIG_SYN_COOKIES + if (unlikely(req->cookie_ts)) + TCP_SKB_CB(skb)->when = cookie_init_timestamp(req); + else #endif + TCP_SKB_CB(skb)->when = tcp_time_stamp; + tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5, + foc) + sizeof(*th); + skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -2208,67 +2829,40 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, th->syn = 1; th->ack = 1; TCP_ECN_make_synack(req, th); - th->source = inet_sk(sk)->sport; - th->dest = ireq->rmt_port; + th->source = htons(ireq->ir_num); + th->dest = ireq->ir_rmt_port; /* Setting of flags are superfluous here for callers (and ECE is * not even correctly set) */ tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn, - TCPCB_FLAG_SYN | TCPCB_FLAG_ACK); + TCPHDR_SYN | TCPHDR_ACK); + th->seq = htonl(TCP_SKB_CB(skb)->seq); - th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1); - if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */ - __u8 rcv_wscale; - /* Set this up on the first call only */ - req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW); - /* tcp_full_space because it is guaranteed to be the first packet */ - tcp_select_initial_window(tcp_full_space(sk), - dst_metric(dst, RTAX_ADVMSS) - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), - &req->rcv_wnd, - &req->window_clamp, - ireq->wscale_ok, - &rcv_wscale); - ireq->rcv_wscale = rcv_wscale; - } + /* XXX data is queued and acked as is. No buffer/window check */ + th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rcv_wnd, 65535U)); - - TCP_SKB_CB(skb)->when = tcp_time_stamp; - tcp_syn_build_options((__be32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok, - ireq->sack_ok, ireq->wscale_ok, ireq->rcv_wscale, - TCP_SKB_CB(skb)->when, - req->ts_recent, - ( -#ifdef CONFIG_TCP_MD5SIG - md5 ? &md5_hash_location : -#endif - NULL) - ); - + tcp_options_write((__be32 *)(th + 1), tp, &opts); th->doff = (tcp_header_size >> 2); - TCP_INC_STATS(TCP_MIB_OUTSEGS); + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ if (md5) { - tp->af_specific->calc_md5_hash(md5_hash_location, - md5, - NULL, dst, req, - tcp_hdr(skb), sk->sk_protocol, - skb->len); + tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, + md5, NULL, req, skb); } #endif return skb; } +EXPORT_SYMBOL(tcp_make_synack); -/* - * Do all connect socket setups that can be done AF independent. - */ +/* Do all connect socket setups that can be done AF independent. */ static void tcp_connect_init(struct sock *sk) { - struct dst_entry *dst = __sk_dst_get(sk); + const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; @@ -2292,15 +2886,24 @@ static void tcp_connect_init(struct sock *sk) if (!tp->window_clamp) tp->window_clamp = dst_metric(dst, RTAX_WINDOW); - tp->advmss = dst_metric(dst, RTAX_ADVMSS); + tp->advmss = dst_metric_advmss(dst); + if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->advmss) + tp->advmss = tp->rx_opt.user_mss; + tcp_initialize_rcv_mss(sk); + /* limit the window selection if the user enforce a smaller rx buffer */ + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) + tp->window_clamp = tcp_full_space(sk); + tcp_select_initial_window(tcp_full_space(sk), tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, sysctl_tcp_window_scaling, - &rcv_wscale); + &rcv_wscale, + dst_metric(dst, RTAX_INITRWND)); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; @@ -2308,28 +2911,152 @@ static void tcp_connect_init(struct sock *sk) sk->sk_err = 0; sock_reset_flag(sk, SOCK_DONE); tp->snd_wnd = 0; - tcp_init_wl(tp, tp->write_seq, 0); + tcp_init_wl(tp, 0); tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; - tp->rcv_nxt = 0; - tp->rcv_wup = 0; - tp->copied_seq = 0; + tp->snd_up = tp->write_seq; + tp->snd_nxt = tp->write_seq; + + if (likely(!tp->repair)) + tp->rcv_nxt = 0; + else + tp->rcv_tstamp = tcp_time_stamp; + tp->rcv_wup = tp->rcv_nxt; + tp->copied_seq = tp->rcv_nxt; inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; inet_csk(sk)->icsk_retransmits = 0; tcp_clear_retrans(tp); } -/* - * Build a SYN and send it off. +static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + + tcb->end_seq += skb->len; + skb_header_release(skb); + __tcp_add_write_queue_tail(sk, skb); + sk->sk_wmem_queued += skb->truesize; + sk_mem_charge(sk, skb->truesize); + tp->write_seq = tcb->end_seq; + tp->packets_out += tcp_skb_pcount(skb); +} + +/* Build and send a SYN with data and (cached) Fast Open cookie. However, + * queue a data-only packet after the regular SYN, such that regular SYNs + * are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges + * only the SYN sequence, the data are retransmitted in the first ACK. + * If cookie is not cached or other error occurs, falls back to send a + * regular SYN with Fast Open cookie request option. */ +static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_fastopen_request *fo = tp->fastopen_req; + int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen; + struct sk_buff *syn_data = NULL, *data; + unsigned long last_syn_loss = 0; + + tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ + tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie, + &syn_loss, &last_syn_loss); + /* Recurring FO SYN losses: revert to regular handshake temporarily */ + if (syn_loss > 1 && + time_before(jiffies, last_syn_loss + (60*HZ << syn_loss))) { + fo->cookie.len = -1; + goto fallback; + } + + if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) + fo->cookie.len = -1; + else if (fo->cookie.len <= 0) + goto fallback; + + /* MSS for SYN-data is based on cached MSS and bounded by PMTU and + * user-MSS. Reserve maximum option space for middleboxes that add + * private TCP options. The cost is reduced data space in SYN :( + */ + if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp) + tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; + space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - + MAX_TCP_OPTION_SPACE; + + space = min_t(size_t, space, fo->size); + + /* limit to order-0 allocations */ + space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); + + syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space, + sk->sk_allocation); + if (syn_data == NULL) + goto fallback; + + for (i = 0; i < iovlen && syn_data->len < space; ++i) { + struct iovec *iov = &fo->data->msg_iov[i]; + unsigned char __user *from = iov->iov_base; + int len = iov->iov_len; + + if (syn_data->len + len > space) + len = space - syn_data->len; + else if (i + 1 == iovlen) + /* No more data pending in inet_wait_for_connect() */ + fo->data = NULL; + + if (skb_add_data(syn_data, from, len)) + goto fallback; + } + + /* Queue a data-only packet after the regular SYN for retransmission */ + data = pskb_copy(syn_data, sk->sk_allocation); + if (data == NULL) + goto fallback; + TCP_SKB_CB(data)->seq++; + TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN; + TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH); + tcp_connect_queue_skb(sk, data); + fo->copied = data->len; + + /* syn_data is about to be sent, we need to take current time stamps + * for the packets that are in write queue : SYN packet and DATA + */ + skb_mstamp_get(&syn->skb_mstamp); + data->skb_mstamp = syn->skb_mstamp; + + if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { + tp->syn_data = (fo->copied > 0); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); + goto done; + } + syn_data = NULL; + +fallback: + /* Send a regular SYN with Fast Open cookie request option */ + if (fo->cookie.len > 0) + fo->cookie.len = 0; + err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); + if (err) + tp->syn_fastopen = 0; + kfree_skb(syn_data); +done: + fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ + return err; +} + +/* Build a SYN and send it off. */ int tcp_connect(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; + int err; tcp_connect_init(sk); + if (unlikely(tp->repair)) { + tcp_finish_connect(sk, NULL); + return 0; + } + buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation); if (unlikely(buff == NULL)) return -ENOBUFS; @@ -2337,32 +3064,30 @@ int tcp_connect(struct sock *sk) /* Reserve space for headers. */ skb_reserve(buff, MAX_TCP_HEADER); - tp->snd_nxt = tp->write_seq; - tcp_init_nondata_skb(buff, tp->write_seq++, TCPCB_FLAG_SYN); + tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); + tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp; + tcp_connect_queue_skb(sk, buff); TCP_ECN_send_syn(sk, buff); - /* Send it off. */ - TCP_SKB_CB(buff)->when = tcp_time_stamp; - tp->retrans_stamp = TCP_SKB_CB(buff)->when; - skb_header_release(buff); - __tcp_add_write_queue_tail(sk, buff); - sk->sk_wmem_queued += buff->truesize; - sk_mem_charge(sk, buff->truesize); - tp->packets_out += tcp_skb_pcount(buff); - tcp_transmit_skb(sk, buff, 1, GFP_KERNEL); + /* Send off SYN; include data in Fast Open. */ + err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : + tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); + if (err == -ECONNREFUSED) + return err; /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. */ tp->snd_nxt = tp->write_seq; tp->pushed_seq = tp->write_seq; - TCP_INC_STATS(TCP_MIB_ACTIVEOPENS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); /* Timer for repeating the SYN until an answer. */ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); return 0; } +EXPORT_SYMBOL(tcp_connect); /* Send out a delayed ack, the caller does the policy checking * to see if we should even be here. See tcp_input.c:tcp_ack_snd_check() @@ -2388,8 +3113,9 @@ void tcp_send_delayed_ack(struct sock *sk) * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements * directly. */ - if (tp->srtt) { - int rtt = max(tp->srtt >> 3, TCP_DELACK_MIN); + if (tp->srtt_us) { + int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3), + TCP_DELACK_MIN); if (rtt < max_ato) max_ato = rtt; @@ -2433,7 +3159,7 @@ void tcp_send_ack(struct sock *sk) * tcp_transmit_skb() will set the ownership to this * sock. */ - buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); + buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); if (buff == NULL) { inet_csk_schedule_ack(sk); inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; @@ -2444,11 +3170,11 @@ void tcp_send_ack(struct sock *sk) /* Reserve space for headers and prepare control bits. */ skb_reserve(buff, MAX_TCP_HEADER); - tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPCB_FLAG_ACK); + tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK); /* Send it off, this clears delayed acks for us. */ TCP_SKB_CB(buff)->when = tcp_time_stamp; - tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC); + tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC)); } /* This routine sends a packet with an out of date sequence @@ -2468,7 +3194,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ - skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); + skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); if (skb == NULL) return -1; @@ -2478,11 +3204,20 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) * end to send an ack. Don't queue or clone SKB, just * send it. */ - tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPCB_FLAG_ACK); + tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); TCP_SKB_CB(skb)->when = tcp_time_stamp; return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); } +void tcp_send_window_probe(struct sock *sk) +{ + if (sk->sk_state == TCP_ESTABLISHED) { + tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; + tcp_xmit_probe_skb(sk, 0); + } +} + +/* Initiate keepalive or window probe from timer. */ int tcp_write_wakeup(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -2494,7 +3229,7 @@ int tcp_write_wakeup(struct sock *sk) if ((skb = tcp_send_head(sk)) != NULL && before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) { int err; - unsigned int mss = tcp_current_mss(sk, 0); + unsigned int mss = tcp_current_mss(sk); unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq)) @@ -2507,21 +3242,20 @@ int tcp_write_wakeup(struct sock *sk) if (seg_size < TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq || skb->len > mss) { seg_size = min(seg_size, mss); - TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH; - if (tcp_fragment(sk, skb, seg_size, mss)) + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; + if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(sk, skb, mss); - TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH; + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; TCP_SKB_CB(skb)->when = tcp_time_stamp; err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); if (!err) tcp_event_new_data_sent(sk, skb); return err; } else { - if (tp->urg_mode && - between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF)) + if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF)) tcp_xmit_probe_skb(sk, 1); return tcp_xmit_probe_skb(sk, 0); } @@ -2567,9 +3301,3 @@ void tcp_send_probe0(struct sock *sk) TCP_RTO_MAX); } } - -EXPORT_SYMBOL(tcp_connect); -EXPORT_SYMBOL(tcp_make_synack); -EXPORT_SYMBOL(tcp_simple_retransmit); -EXPORT_SYMBOL(tcp_sync_mss); -EXPORT_SYMBOL(tcp_mtup_init); |