/* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, * Mark Evans, * Corey Minyard * Florian La Roche, * Charles Hedrick, * Linus Torvalds, * Alan Cox, * Matthew Dillon, * Arnt Gulbrandsen, * Jorge Cwik, */ /* * Changes: Pedro Roque : Retransmit queue handled by TCP. * : Fragmentation on mtu decrease * : Segment collapse on retransmit * : AF independence * * Linus Torvalds : send_delayed_ack * David S. Miller : Charge memory using the right skb * during syn/ack processing. * David S. Miller : Output engine completely rewritten. * Andrea Arcangeli: SYNACK carry ts_recent in tsecr. * Cacophonix Gaul : draft-minshall-nagle-01 * J Hadi Salim : ECN support * */ #include #include #include /* 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 * interpret the window field as a signed quantity. */ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; /* 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. */ 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; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { 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); } /* SND.NXT, if window was not shrunk. * If window has been shrunk, what should we make? It is not clear at all. * Using SND.UNA we will fail to open window, SND.NXT is out of window. :-( * 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) { struct tcp_sock *tp = tcp_sk(sk); if (!before(tcp_wnd_end(tp), tp->snd_nxt)) return tp->snd_nxt; else return tcp_wnd_end(tp); } /* Calculate mss to advertise in SYN segment. * RFC1122, RFC1063, draft-ietf-tcpimpl-pmtud-01 state that: * * 1. It is independent of path mtu. * 2. Ideally, it is maximal possible segment size i.e. 65535-40. * 3. For IPv4 it is reasonable to calculate it from maximal MTU of * attached devices, because some buggy hosts are confused by * large MSS. * 4. We do not make 3, we advertise MSS, calculated from first * hop device mtu, but allow to raise it to ip_rt_min_advmss. * This may be overridden via information stored in routing table. * 5. Value 65535 for MSS is valid in IPv6 and means "as large as possible, * probably even Jumbo". */ static __u16 tcp_advertise_mss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); 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; } return (__u16)mss; } /* 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) { struct tcp_sock *tp = tcp_sk(sk); s32 delta = tcp_time_stamp - tp->lsndtime; u32 restart_cwnd = tcp_init_cwnd(tp, dst); u32 cwnd = tp->snd_cwnd; tcp_ca_event(sk, CA_EVENT_CWND_RESTART); tp->snd_ssthresh = tcp_current_ssthresh(sk); restart_cwnd = min(restart_cwnd, cwnd); while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd) cwnd >>= 1; tp->snd_cwnd = max(cwnd, restart_cwnd); tp->snd_cwnd_stamp = tcp_time_stamp; 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 inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_time_stamp; if (sysctl_tcp_slow_start_after_idle && (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto)) tcp_cwnd_restart(sk, __sk_dst_get(sk)); tp->lsndtime = now; /* 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; } /* 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); } /* 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. * NOTE: for smooth operation initial space offering should * be a multiple of mss if possible. We assume here that mss >= 1. * This MUST be enforced by all callers. */ void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale) { unsigned int space = (__space < 0 ? 0 : __space); /* If no clamp set the clamp to the max possible scaled window */ if (*window_clamp == 0) (*window_clamp) = (65535 << 14); space = min(*window_clamp, space); /* Quantize space offering to a multiple of mss if possible. */ if (space > mss) space = (space / mss) * mss; /* NOTE: offering an initial window larger than 32767 * will break some buggy TCP stacks. If the admin tells us * it is likely we could be speaking with such a buggy stack * we will truncate our initial window offering to 32K-1 * unless the remote has sent us a window scaling option, * which we interpret as a sign the remote TCP is not * misinterpreting the window field as a signed quantity. */ if (sysctl_tcp_workaround_signed_windows) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else (*rcv_wnd) = space; (*rcv_wscale) = 0; if (wscale_ok) { /* Set window scaling on max possible window * See RFC1323 for an explanation of the limit to 14 */ space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max); space = min_t(u32, space, *window_clamp); while (space > 65535 && (*rcv_wscale) < 14) { space >>= 1; (*rcv_wscale)++; } } /* 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; } /* Set the clamp no higher than max representable value */ (*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp); } /* Chose a new window to advertise, update state in tcp_sock for the * socket, and return result with RFC1323 scaling applied. The return * value can be stuffed directly into th->window for an outgoing * frame. */ static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 cur_win = tcp_receive_window(tp); u32 new_win = __tcp_select_window(sk); /* Never shrink the offered window */ if (new_win < cur_win) { /* Danger Will Robinson! * Don't update rcv_wup/rcv_wnd here or else * we will not be able to advertise a zero * window in time. --DaveM * * Relax Will Robinson. */ new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; tp->rcv_wup = tp->rcv_nxt; /* Make sure we do not exceed the maximum possible * scaled window. */ if (!tp->rx_opt.rcv_wscale && sysctl_tcp_workaround_signed_windows) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); /* RFC1323 scaling applied */ new_win >>= tp->rx_opt.rcv_wscale; /* If we advertise zero window, disable fast path. */ if (new_win == 0) tp->pred_flags = 0; return new_win; } /* Packet ECN state for a SYN-ACK */ static inline void TCP_ECN_send_synack(struct tcp_sock *tp, struct sk_buff *skb) { TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_CWR; if (!(tp->ecn_flags & TCP_ECN_OK)) TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_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 == 1) { TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ECE | TCPCB_FLAG_CWR; tp->ecn_flags = TCP_ECN_OK; } } static __inline__ void TCP_ECN_make_synack(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) { struct tcp_sock *tp = tcp_sk(sk); if (tp->ecn_flags & TCP_ECN_OK) { /* Not-retransmitted data segment: set ECT and inject CWR. */ if (skb->len != tcp_header_len && !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) { INET_ECN_xmit(sk); if (tp->ecn_flags & TCP_ECN_QUEUE_CWR) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; tcp_hdr(skb)->cwr = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; } } else { /* ACK or retransmitted segment: clear ECT|CE */ INET_ECN_dontxmit(sk); } if (tp->ecn_flags & TCP_ECN_DEMAND_CWR) tcp_hdr(skb)->ece = 1; } } /* Constructs common control bits of non-data skb. If SYN/FIN is present, * auto increment end seqno. */ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) { skb->csum = 0; TCP_SKB_CB(skb)->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; TCP_SKB_CB(skb)->seq = seq; if (flags & (TCPCB_FLAG_SYN | TCPCB_FLAG_FIN)) seq++; TCP_SKB_CB(skb)->end_seq = seq; } static inline int 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) struct tcp_out_options { u8 options; /* bit field of OPTION_* */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ u16 mss; /* 0 to disable */ __u32 tsval, tsecr; /* need to include OPTION_TS */ }; /* 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-operatibility 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, const struct tcp_out_options *opts, __u8 **md5_hash) { if (unlikely(OPTION_MD5 & opts->options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); *md5_hash = (__u8 *)ptr; ptr += 4; } else { *md5_hash = NULL; } if (unlikely(opts->mss)) { *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | opts->mss); } if (likely(OPTION_TS & opts->options)) { if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) { *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(opts->tsval); *ptr++ = htonl(opts->tsecr); } if (unlikely(OPTION_SACK_ADVERTISE & opts->options && !(OPTION_TS & opts->options))) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); } if (unlikely(opts->ws)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | opts->ws); } 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 + (opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK))); 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); } tp->rx_opt.dsack = 0; } } /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ static unsigned 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 size = 0; #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; size += 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); size += TCPOLEN_MSS_ALIGNED; if (likely(sysctl_tcp_timestamps && *md5 == NULL)) { opts->options |= OPTION_TS; opts->tsval = TCP_SKB_CB(skb)->when; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } if (likely(sysctl_tcp_window_scaling)) { opts->ws = tp->rx_opt.rcv_wscale; if (likely(opts->ws)) size += TCPOLEN_WSCALE_ALIGNED; } if (likely(sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) size += TCPOLEN_SACKPERM_ALIGNED; } return size; } /* Set up TCP options for SYN-ACKs. */ static unsigned tcp_synack_options(struct sock *sk, struct request_sock *req, unsigned mss, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { unsigned size = 0; struct inet_request_sock *ireq = inet_rsk(req); char doing_ts; #ifdef CONFIG_TCP_MD5SIG *md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req); if (*md5) { opts->options |= OPTION_MD5; size += TCPOLEN_MD5SIG_ALIGNED; } #else *md5 = NULL; #endif /* 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. */ doing_ts = ireq->tstamp_ok && !(*md5 && ireq->sack_ok); opts->mss = mss; size += TCPOLEN_MSS_ALIGNED; if (likely(ireq->wscale_ok)) { opts->ws = ireq->rcv_wscale; if (likely(opts->ws)) size += TCPOLEN_WSCALE_ALIGNED; } if (likely(doing_ts)) { opts->options |= OPTION_TS; opts->tsval = TCP_SKB_CB(skb)->when; opts->tsecr = req->ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!doing_ts)) size += TCPOLEN_SACKPERM_ALIGNED; } return size; } /* Compute TCP options for ESTABLISHED sockets. This is not the * final wire format yet. */ static unsigned 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 size = 0; unsigned int eff_sacks; #ifdef CONFIG_TCP_MD5SIG *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 : 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 remaining = MAX_TCP_OPTION_SPACE - size; opts->num_sack_blocks = min_t(unsigned, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); size += TCPOLEN_SACK_BASE_ALIGNED + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } return size; } /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. * All SKB's seen here are completely headerless. It is our * job to build the TCP header, and pass the packet down to * IP so it can do the same plus pass the packet off to the * device. * * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; struct tcp_sock *tp; struct tcp_skb_cb *tcb; struct tcp_out_options opts; unsigned tcp_options_size, tcp_header_size; struct tcp_md5sig_key *md5; __u8 *md5_hash_location; struct tcphdr *th; 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 (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; } inet = inet_sk(sk); tp = tcp_sk(sk); tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts)); if (unlikely(tcb->flags & TCPCB_FLAG_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); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); skb_set_owner_w(skb, sk); /* Build TCP header and checksum it. */ th = tcp_hdr(skb); th->source = inet->sport; th->dest = 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); if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) { /* RFC1323: The window in SYN & SYN/ACK segments * is never scaled. */ th->window = htons(min(tp->rcv_wnd, 65535U)); } else { th->window = htons(tcp_select_window(sk)); } th->check = 0; th->urg_ptr = 0; /* 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 = 0xFFFF; th->urg = 1; } } tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location); if (likely((tcb->flags & TCPCB_FLAG_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) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; tp->af_specific->calc_md5_hash(md5_hash_location, md5, sk, NULL, skb); } #endif icsk->icsk_af_ops->send_check(sk, skb->len, skb); if (likely(tcb->flags & TCPCB_FLAG_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); if (skb->len != tcp_header_size) tcp_event_data_sent(tp, skb, sk); if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); err = icsk->icsk_af_ops->queue_xmit(skb, 0); if (likely(err <= 0)) return err; tcp_enter_cwr(sk, 1); return net_xmit_eval(err); } /* 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. */ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ tp->write_seq = TCP_SKB_CB(skb)->end_seq; skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); sk->sk_wmem_queued += skb->truesize; sk_mem_charge(sk, skb->truesize); } /* Initialize TSO segments for a packet. */ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { if (skb->len <= mss_now || !sk_can_gso(sk) || 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; } 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; } } /* 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, int decr) { struct tcp_sock *tp = tcp_sk(sk); if (!tp->sacked_out || tcp_is_reno(tp)) return; if (after(tcp_highest_sack_seq(tp), TCP_SKB_CB(skb)->seq)) 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, 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) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int nsize, old_factor; int nlen; u8 flags; BUG_ON(len > skb->len); 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)) return -ENOMEM; /* Get a new skb... force flag on. */ buff = sk_stream_alloc_skb(sk, nsize, GFP_ATOMIC); if (buff == NULL) return -ENOMEM; /* We'll just try again later. */ sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); nlen = skb->len - len - nsize; buff->truesize += nlen; skb->truesize -= nlen; /* Correct the sequence numbers. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; 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; TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) { /* Copy and checksum data tail into the new buffer. */ buff->csum = csum_partial_copy_nocheck(skb->data + len, skb_put(buff, nsize), nsize, 0); skb_trim(skb, len); skb->csum = csum_block_sub(skb->csum, buff->csum, len); } else { skb->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); } buff->ip_summed = skb->ip_summed; /* Looks stupid, but our code really uses when of * skbs, which it never sent before. --ANK */ TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when; buff->tstamp = skb->tstamp; old_factor = tcp_skb_pcount(skb); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(sk, skb, mss_now); tcp_set_skb_tso_segs(sk, buff, mss_now); /* If this packet has been sent out already, we must * adjust the various packet counters. */ if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) { int diff = old_factor - tcp_skb_pcount(skb) - tcp_skb_pcount(buff); if (diff) tcp_adjust_pcount(sk, skb, diff); } /* Link BUFF into the send queue. */ skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk); return 0; } /* This is similar to __pskb_pull_head() (it will go to core/skbuff.c * eventually). The difference is that pulled data not copied, but * immediately discarded. */ static void __pskb_trim_head(struct sk_buff *skb, int len) { int i, k, eat; 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; } else { skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; if (eat) { skb_shinfo(skb)->frags[k].page_offset += eat; skb_shinfo(skb)->frags[k].size -= eat; eat = 0; } k++; } } skb_shinfo(skb)->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)) 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)); TCP_SKB_CB(skb)->seq += len; skb->ip_summed = CHECKSUM_PARTIAL; skb->truesize -= len; sk->sk_wmem_queued -= 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. */ if (tcp_skb_pcount(skb) > 1) tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk)); return 0; } /* Calculate MSS. Not accounting for SACKs here. */ 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); int mss_now; /* Calculate base mss without TCP options: It is MMS_S - sizeof(tcphdr) of rfc1122 */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; /* Now subtract optional transport overhead */ mss_now -= icsk->icsk_ext_hdr_len; /* 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; } /* 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); int mtu; mtu = mss + tp->tcp_header_len + icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; return mtu; } /* MTU probing init per socket */ void tcp_mtup_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_mtup.enabled = sysctl_tcp_mtu_probing > 1; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, sysctl_tcp_base_mss); icsk->icsk_mtup.probe_size = 0; } /* This function synchronize snd mss to current pmtu/exthdr set. tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts for TCP options, but includes only bare TCP header. tp->rx_opt.mss_clamp is mss negotiated at connection setup. It is minimum of user_mss and mss received with SYN. It also does not include TCP options. inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function. tp->mss_cache is current effective sending mss, including all tcp options except for SACKs. It is evaluated, taking into account current pmtu, but never exceeds tp->rx_opt.mss_clamp. NOTE1. rfc1122 clearly states that advertised MSS DOES NOT include either tcp or ip options. NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache are READ ONLY outside this function. --ANK (980731) */ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; if (icsk->icsk_mtup.search_high > pmtu) icsk->icsk_mtup.search_high = pmtu; mss_now = tcp_mtu_to_mss(sk, pmtu); mss_now = tcp_bound_to_half_wnd(tp, mss_now); /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; if (icsk->icsk_mtup.enabled) mss_now = min(mss_now, tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low)); tp->mss_cache = mss_now; return mss_now; } /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. */ unsigned int tcp_current_mss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct dst_entry *dst = __sk_dst_get(sk); u32 mss_now; unsigned header_len; struct tcp_out_options opts; struct tcp_md5sig_key *md5; mss_now = tp->mss_cache; if (dst) { u32 mtu = dst_mtu(dst); if (mtu != inet_csk(sk)->icsk_pmtu_cookie) mss_now = tcp_sync_mss(sk, mtu); } 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; } return mss_now; } /* Congestion window validation. (RFC2861) */ static void tcp_cwnd_validate(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (tp->packets_out >= tp->snd_cwnd) { /* Network is feed fully. */ tp->snd_cwnd_used = 0; tp->snd_cwnd_stamp = tcp_time_stamp; } else { /* Network starves. */ if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; if (sysctl_tcp_slow_start_after_idle && (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto) tcp_cwnd_application_limited(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. */ static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd) { struct tcp_sock *tp = tcp_sk(sk); u32 needed, window, cwnd_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; cwnd_len = mss_now * cwnd; if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk))) return cwnd_len; needed = min(skb->len, window); if (cwnd_len <= needed) return cwnd_len; return needed - needed % mss_now; } /* 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) { 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) && tcp_skb_pcount(skb) == 1) return 1; in_flight = tcp_packets_in_flight(tp); cwnd = tp->snd_cwnd; if (in_flight < cwnd) return (cwnd - in_flight); return 0; } /* Intialize 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, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) { tcp_set_skb_tso_segs(sk, skb, mss_now); tso_segs = tcp_skb_pcount(skb); } return tso_segs; } /* Minshall's variant of the Nagle send check. */ 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 * sent now. */ static inline int tcp_nagle_test(struct tcp_sock *tp, 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). * * This is implemented in the callers, where they modify the 'nonagle' * argument based upon the location of SKB in the send queue. */ if (nonagle & TCP_NAGLE_PUSH) return 1; /* 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 (tcp_urg_mode(tp) || (tp->frto_counter == 2) || (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)) return 1; if (!tcp_nagle_check(tp, skb, cur_mss, nonagle)) return 1; return 0; } /* 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) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (skb->len > cur_mss) end_seq = TCP_SKB_CB(skb)->seq + cur_mss; return !after(end_seq, tcp_wnd_end(tp)); } /* This checks if the data bearing packet SKB (usually tcp_send_head(sk)) * 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, unsigned int cur_mss, int nonagle) { struct tcp_sock *tp = tcp_sk(sk); unsigned int cwnd_quota; tcp_init_tso_segs(sk, skb, cur_mss); if (!tcp_nagle_test(tp, skb, cur_mss, nonagle)) return 0; cwnd_quota = tcp_cwnd_test(tp, skb); if (cwnd_quota && !tcp_snd_wnd_test(tp, skb, cur_mss)) cwnd_quota = 0; return cwnd_quota; } /* Test if sending is allowed right now. */ int tcp_may_send_now(struct sock *sk) { 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), (tcp_skb_is_last(sk, skb) ? tp->nonagle : TCP_NAGLE_PUSH))); } /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet * which is put after SKB on the list. It is very much like * tcp_fragment() except that it may make several kinds of assumptions * in order to speed up the splitting operation. In particular, we * know that all the data is in scatter-gather pages, and that the * 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) { struct sk_buff *buff; int nlen = skb->len - len; 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); buff = sk_stream_alloc_skb(sk, 0, GFP_ATOMIC); if (unlikely(buff == NULL)) return -ENOMEM; sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); buff->truesize += nlen; skb->truesize -= nlen; /* Correct the sequence numbers. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; 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; /* This packet was never sent out yet, so no SACK bits. */ TCP_SKB_CB(buff)->sacked = 0; buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(sk, skb, mss_now); tcp_set_skb_tso_segs(sk, buff, mss_now); /* Link BUFF into the send queue. */ skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk); return 0; } /* Try to defer sending, if possible, in order to minimize the amount * of TSO splitting we do. View it as a kind of TSO Nagle test. * * This algorithm is from John Heffner. */ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 send_win, cong_win, limit, in_flight; if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) goto send_now; if (icsk->icsk_ca_state != TCP_CA_Open) goto send_now; /* Defer for less than two clock ticks. */ if (tp->tso_deferred && (((u32)jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1) goto send_now; in_flight = tcp_packets_in_flight(tp); BUG_ON(tcp_skb_pcount(skb) <= 1 || (tp->snd_cwnd <= in_flight)); send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; /* From in_flight test above, we know that cwnd > in_flight. */ cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache; limit = min(send_win, cong_win); /* If a full-sized TSO skb can be sent, do it. */ if (limit >= sk->sk_gso_max_size) goto send_now; /* 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; if (sysctl_tcp_tso_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; if (limit >= chunk) goto send_now; } else { /* Different approach, try not to defer past a single * ACK. Receiver should ACK every other full sized * frame, so if we have space for more than 3 frames * then send now. */ if (limit > tcp_max_burst(tp) * tp->mss_cache) goto send_now; } /* Ok, it looks like it is advisable to defer. */ tp->tso_deferred = 1 | (jiffies << 1); return 1; send_now: tp->tso_deferred = 0; return 0; } /* 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 */ static int tcp_mtu_probe(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb, *nskb, *next; int len; int probe_size; int size_needed; int copy; int mss_now; /* Not currently probing/verifying, * not in recovery, * have enough cwnd, and * not SACKing (the variable headers throw things off) */ if (!icsk->icsk_mtup.enabled || icsk->icsk_mtup.probe_size || inet_csk(sk)->icsk_ca_state != TCP_CA_Open || tp->snd_cwnd < 11 || 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); 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)) { /* TODO: set timer for probe_converge_event */ return -1; } /* Have enough data in the send queue to probe? */ if (tp->write_seq - tp->snd_nxt < size_needed) return -1; if (tp->snd_wnd < size_needed) return -1; if (after(tp->snd_nxt + size_needed, tcp_wnd_end(tp))) return 0; /* Do we need to wait to drain cwnd? With none in flight, don't stall */ if (tcp_packets_in_flight(tp) + 2 > tp->snd_cwnd) { if (!tcp_packets_in_flight(tp)) return -1; else return 0; } /* We're allowed to probe. Build it now. */ if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL) return -1; sk->sk_wmem_queued += nskb->truesize; sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(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)->sacked = 0; nskb->csum = 0; nskb->ip_summed = skb->ip_summed; tcp_insert_write_queue_before(nskb, skb, sk); len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); if (nskb->ip_summed) skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); else nskb->csum = skb_copy_and_csum_bits(skb, 0, skb_put(nskb, copy), copy, nskb->csum); 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_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); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); if (skb->ip_summed != CHECKSUM_PARTIAL) skb->csum = csum_partial(skb->data, skb->len, 0); } else { __pskb_trim_head(skb, copy); tcp_set_skb_tso_segs(sk, skb, mss_now); } TCP_SKB_CB(skb)->seq += copy; } len += copy; if (len >= probe_size) break; } tcp_init_tso_segs(sk, nskb, nskb->len); /* We're ready to send. If this fails, the probe will * be resegmented into mss-sized pieces by tcp_write_xmit(). */ TCP_SKB_CB(nskb)->when = tcp_time_stamp; if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) { /* Decrement cwnd here because we are sending * effectively two packets. */ tp->snd_cwnd--; tcp_event_new_data_sent(sk, nskb); icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len); tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq; tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq; return 1; } return -1; } /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. * * 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. * * Returns 1, 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, 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; sent_pkts = 0; if (!push_one) { /* Do MTU probing. */ result = tcp_mtu_probe(sk); if (!result) { return 0; } else if (result > 0) { sent_pkts = 1; } } while ((skb = tcp_send_head(sk))) { unsigned int limit; tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) break; if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) break; if (tso_segs == 1) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) break; } else { if (!push_one && tcp_tso_should_defer(sk, skb)) break; } limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, cwnd_quota); if (skb->len > limit && unlikely(tso_fragment(sk, skb, limit, mss_now))) break; TCP_SKB_CB(skb)->when = tcp_time_stamp; if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; /* 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++; if (push_one) break; } if (likely(sent_pkts)) { tcp_cwnd_validate(sk); return 0; } return !tp->packets_out && tcp_send_head(sk); } /* Push out any pending frames which were held back due to * TCP_CORK or attempt at coalescing tiny packets. * The socket must be locked by the caller. */ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle) { struct sk_buff *skb = tcp_send_head(sk); if (!skb) return; /* 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 (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC)) tcp_check_probe_timer(sk); } /* Send _single_ skb sitting at the send head. This function requires * true push pending frames to setup probe timer etc. */ void tcp_push_one(struct sock *sk, unsigned int mss_now) { struct sk_buff *skb = tcp_send_head(sk); BUG_ON(!skb || skb->len < mss_now); tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation); } /* This function returns the amount that we can raise the * usable window based on the following constraints * * 1. The window can never be shrunk once it is offered (RFC 793) * 2. We limit memory per socket * * RFC 1122: * "the suggested [SWS] avoidance algorithm for the receiver is to keep * RECV.NEXT + RCV.WIN fixed until: * RCV.BUFF - RCV.USER - RCV.WINDOW >= min(1/2 RCV.BUFF, MSS)" * * i.e. don't raise the right edge of the window until you can raise * it at least MSS bytes. * * Unfortunately, the recommended algorithm breaks header prediction, * since header prediction assumes th->window stays fixed. * * Strictly speaking, keeping th->window fixed violates the receiver * side SWS prevention criteria. The problem is that under this rule * a stream of single byte packets will cause the right side of the * window to always advance by a single byte. * * Of course, if the sender implements sender side SWS prevention * then this will not be a problem. * * BSD seems to make the following compromise: * * If the free space is less than the 1/4 of the maximum * space available and the free space is less than 1/2 mss, * then set the window to 0. * [ Actually, bsd uses MSS and 1/4 of maximal _window_ ] * Otherwise, just prevent the window from shrinking * and from being larger than the largest representable value. * * This prevents incremental opening of the window in the regime * where TCP is limited by the speed of the reader side taking * data out of the TCP receive queue. It does nothing about * those cases where the window is constrained on the sender side * because the pipeline is full. * * BSD also seems to "accidentally" limit itself to windows that are a * multiple of MSS, at least until the free space gets quite small. * This would appear to be a side effect of the mbuf implementation. * Combining these two algorithms results in the observed behavior * of having a fixed window size at almost all times. * * Below we obtain similar behavior by forcing the offered window to * a multiple of the mss when it is feasible to do so. * * Note, we don't "adjust" for TIMESTAMP or SACK option bytes. * Regular options like TIMESTAMP are taken into account. */ u32 __tcp_select_window(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); /* MSS for the peer's data. Previous versions used mss_clamp * here. I don't know if the value based on our guesses * of peer's MSS is better for the performance. It's more correct * but may be worse for the performance because of rcv_mss * fluctuations. --SAW 1998/11/1 */ 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 window; if (mss > full_space) mss = full_space; if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; if (tcp_memory_pressure) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); if (free_space < mss) return 0; } if (free_space > tp->rcv_ssthresh) free_space = tp->rcv_ssthresh; /* Don't do rounding if we are using window scaling, since the * scaled window will not line up with the MSS boundary anyway. */ window = tp->rcv_wnd; if (tp->rx_opt.rcv_wscale) { window = free_space; /* Advertise enough space so that it won't get scaled away. * Import case: prevent zero window announcement if * 1< mss. */ if (((window >> tp->rx_opt.rcv_wscale) << tp->rx_opt.rcv_wscale) != window) window = (((window >> tp->rx_opt.rcv_wscale) + 1) << tp->rx_opt.rcv_wscale); } else { /* Get the largest window that is a nice multiple of mss. * Window clamp already applied above. * If our current window offering is within 1 mss of the * free space we just keep it. This prevents the divide * and multiply from happening most of the time. * We also don't do any window rounding when the free space * is too small. */ if (window <= free_space - mss || window > free_space) window = (free_space / mss) * mss; else if (mss == full_space && free_space > window + (full_space >> 1)) window = free_space; } return window; } /* 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; skb_size = skb->len; next_skb_size = next_skb->len; BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1); tcp_highest_sack_combine(sk, next_skb, skb); tcp_unlink_write_queue(next_skb, sk); skb_copy_from_linear_data(next_skb, skb_put(skb, next_skb_size), next_skb_size); if (next_skb->ip_summed == CHECKSUM_PARTIAL) skb->ip_summed = CHECKSUM_PARTIAL; if (skb->ip_summed != CHECKSUM_PARTIAL) skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size); /* Update sequence range on original skb. */ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; /* Merge over control information. This moves PSH/FIN etc. over */ TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(next_skb)->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; /* 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); } /* Check if coalescing SKBs is legal. */ static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb) { if (tcp_skb_pcount(skb) > 1) return 0; /* TODO: SACK collapsing could be used to remove this condition */ if (skb_shinfo(skb)->nr_frags != 0) return 0; if (skb_cloned(skb)) return 0; if (skb == tcp_send_head(sk)) return 0; /* Some heurestics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return 0; return 1; } /* Collapse packets in the retransmit queue to make to create * less packets on the wire. This is only done on retransmission. */ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, int space) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = to, *tmp; int first = 1; if (!sysctl_tcp_retrans_collapse) return; if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN) return; tcp_for_write_queue_from_safe(skb, tmp, sk) { if (!tcp_can_collapse(sk, skb)) break; space -= skb->len; if (first) { first = 0; continue; } if (space < 0) break; /* Punt if not enough space exists in the first SKB for * the data in the second */ if (skb->len > skb_tailroom(to)) break; if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) break; tcp_collapse_retrans(sk, to); } } /* 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) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); unsigned int cur_mss; int err; /* Inconslusive MTU probe */ if (icsk->icsk_mtup.probe_size) { icsk->icsk_mtup.probe_size = 0; } /* Do not sent more than we queued. 1/4 is reserved for possible * copying overhead: fragmentation, tunneling, mangling etc. */ if (atomic_read(&sk->sk_wmem_alloc) > min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) return -EAGAIN; if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) BUG(); if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) 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) return -EAGAIN; if (skb->len > cur_mss) { if (tcp_fragment(sk, skb, cur_mss, cur_mss)) return -ENOMEM; /* We'll try again later. */ } else { int oldpcount = tcp_skb_pcount(skb); if (unlikely(oldpcount > 1)) { 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); /* 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; } } /* 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); if (err == 0) { /* Update global TCP statistics. */ TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); tp->total_retrans++; #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { if (net_ratelimit()) printk(KERN_DEBUG "retrans_out leaked.\n"); } #endif if (!tp->retrans_out) tp->lost_retrans_low = tp->snd_nxt; TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS; tp->retrans_out += tcp_skb_pcount(skb); /* Save stamp of the first retransmit. */ 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; } return err; } /* Check if we forward retransmits are possible in the current * window/congestion state. */ static int tcp_can_forward_retransmit(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); /* Forward retransmissions are possible only during Recovery. */ if (icsk->icsk_ca_state != TCP_CA_Recovery) return 0; /* No forward retransmissions in Reno are possible. */ if (tcp_is_reno(tp)) return 0; /* Yeah, we have to make difficult choice between forward transmission * and retransmission... Both ways have their merits... * * For now we do not retransmit anything, while we have some new * segments to send. In the other cases, follow rule 3 for * NextSeg() specified in RFC3517. */ if (tcp_may_send_now(sk)) return 0; return 1; } /* 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 (!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) { __u8 sacked = TCP_SKB_CB(skb)->sacked; 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) return; 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; } 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 (skb == tcp_write_queue_head(sk)) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); } } /* Send a fin. The caller locks the socket for us. This cannot be * allowed to fail queueing a FIN frame under any circumstances. */ void tcp_send_fin(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = tcp_write_queue_tail(sk); int mss_now; /* Optimization, tack on the FIN if we have a queue of * unsent frames. But be careful about outgoing SACKS * and IP options. */ mss_now = tcp_current_mss(sk); if (tcp_send_head(sk) != NULL) { TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_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, sk->sk_allocation); if (skb) break; yield(); } /* Reserve space for headers and prepare control bits. */ 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); tcp_queue_skb(sk, skb); } __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to * an explicit close() or as a byproduct of exit()'ing) and there * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ void tcp_send_active_reset(struct sock *sk, gfp_t priority) { struct sk_buff *skb; /* NOTE: No TCP options attached and we never retransmit this. */ skb = alloc_skb(MAX_TCP_HEADER, priority); if (!skb) { 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); /* Send it off. */ TCP_SKB_CB(skb)->when = tcp_time_stamp; if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); } /* 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. */ 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"); return -EFAULT; } if (!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_ACK)) { if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); if (nskb == NULL) return -ENOMEM; tcp_unlink_write_queue(skb, sk); skb_header_release(nskb); __tcp_add_write_queue_head(sk, nskb); sk_wmem_free_skb(sk, skb); sk->sk_wmem_queued += nskb->truesize; sk_mem_charge(sk, nskb->truesize); skb = nskb; } TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_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. */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req) { struct inet_request_sock *ireq = inet_rsk(req); struct tcp_sock *tp = tcp_sk(sk); struct tcphdr *th; int tcp_header_size; struct tcp_out_options opts; struct sk_buff *skb; struct tcp_md5sig_key *md5; __u8 *md5_hash_location; int mss; skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC); if (skb == NULL) return NULL; /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); skb_dst_set(skb, dst_clone(dst)); mss = dst_metric(dst, RTAX_ADVMSS); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) mss = tp->rx_opt.user_mss; 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), mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), &req->rcv_wnd, &req->window_clamp, ireq->wscale_ok, &rcv_wscale); ireq->rcv_wscale = rcv_wscale; } 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) + sizeof(struct tcphdr); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); th = tcp_hdr(skb); memset(th, 0, sizeof(struct tcphdr)); th->syn = 1; th->ack = 1; TCP_ECN_make_synack(req, th); th->source = ireq->loc_port; th->dest = ireq->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); th->seq = htonl(TCP_SKB_CB(skb)->seq); th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location); th->doff = (tcp_header_size >> 2); TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ if (md5) { tcp_rsk(req)->af_specific->calc_md5_hash(md5_hash_location, md5, NULL, req, skb); } #endif return skb; } /* 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); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; /* We'll fix this up when we get a response from the other end. * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr) + (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0); #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk) != NULL) tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif /* If user gave his TCP_MAXSEG, record it to clamp */ if (tp->rx_opt.user_mss) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; tp->max_window = 0; tcp_mtup_init(sk); tcp_sync_mss(sk, dst_mtu(dst)); if (!tp->window_clamp) tp->window_clamp = dst_metric(dst, RTAX_WINDOW); tp->advmss = dst_metric(dst, RTAX_ADVMSS); 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); 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); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; sk->sk_err = 0; sock_reset_flag(sk, SOCK_DONE); tp->snd_wnd = 0; tcp_init_wl(tp, 0); tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; tp->rcv_nxt = 0; tp->rcv_wup = 0; tp->copied_seq = 0; 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. */ int tcp_connect(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; tcp_connect_init(sk); buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation); if (unlikely(buff == NULL)) return -ENOBUFS; /* 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_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, sk->sk_allocation); /* 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(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; } /* 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() * for details. */ void tcp_send_delayed_ack(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int ato = icsk->icsk_ack.ato; unsigned long timeout; if (ato > TCP_DELACK_MIN) { const struct tcp_sock *tp = tcp_sk(sk); int max_ato = HZ / 2; if (icsk->icsk_ack.pingpong || (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)) max_ato = TCP_DELACK_MAX; /* Slow path, intersegment interval is "high". */ /* If some rtt estimate is known, use it to bound delayed ack. * 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 (rtt < max_ato) max_ato = rtt; } ato = min(ato, max_ato); } /* Stay within the limit we were given */ timeout = jiffies + ato; /* Use new timeout only if there wasn't a older one earlier. */ if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) { /* If delack timer was blocked or is about to expire, * send ACK now. */ if (icsk->icsk_ack.blocked || time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) { tcp_send_ack(sk); return; } if (!time_before(timeout, icsk->icsk_ack.timeout)) timeout = icsk->icsk_ack.timeout; } icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; icsk->icsk_ack.timeout = timeout; sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } /* This routine sends an ack and also updates the window. */ void tcp_send_ack(struct sock *sk) { struct sk_buff *buff; /* If we have been reset, we may not send again. */ if (sk->sk_state == TCP_CLOSE) return; /* We are not putting this on the write queue, so * tcp_transmit_skb() will set the ownership to this * sock. */ buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (buff == NULL) { inet_csk_schedule_ack(sk); inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, TCP_DELACK_MAX, TCP_RTO_MAX); return; } /* 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); /* 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); } /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. * * Question: what should we make while urgent mode? * 4.4BSD forces sending single byte of data. We cannot send * out of window data, because we have SND.NXT==SND.MAX... * * Current solution: to send TWO zero-length segments in urgent mode: * one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is * out-of-date with SND.UNA-1 to probe window. */ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (skb == NULL) return -1; /* Reserve space for headers and set control bits. */ skb_reserve(skb, MAX_TCP_HEADER); /* Use a previous sequence. This should cause the other * 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_SKB_CB(skb)->when = tcp_time_stamp; return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); } /* Initiate keepalive or window probe from timer. */ int tcp_write_wakeup(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; if (sk->sk_state == TCP_CLOSE) return -1; 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); unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq)) tp->pushed_seq = TCP_SKB_CB(skb)->end_seq; /* We are probing the opening of a window * but the window size is != 0 * must have been a result SWS avoidance ( sender ) */ 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)) 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)->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 (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); } } /* A window probe timeout has occurred. If window is not closed send * a partial packet else a zero probe. */ void tcp_send_probe0(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int err; err = tcp_write_wakeup(sk); if (tp->packets_out || !tcp_send_head(sk)) { /* Cancel probe timer, if it is not required. */ icsk->icsk_probes_out = 0; icsk->icsk_backoff = 0; return; } if (err <= 0) { if (icsk->icsk_backoff < sysctl_tcp_retries2) icsk->icsk_backoff++; icsk->icsk_probes_out++; inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX), TCP_RTO_MAX); } else { /* If packet was not sent due to local congestion, * do not backoff and do not remember icsk_probes_out. * Let local senders to fight for local resources. * * Use accumulated backoff yet. */ if (!icsk->icsk_probes_out) icsk->icsk_probes_out = 1; inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RESOURCE_PROBE_INTERVAL), TCP_RTO_MAX); } } EXPORT_SYMBOL(tcp_select_initial_window); EXPORT_SYMBOL(tcp_connect); EXPORT_SYMBOL(tcp_make_synack); EXPORT_SYMBOL(tcp_simple_retransmit); EXPORT_SYMBOL(tcp_sync_mss); EXPORT_SYMBOL(tcp_mtup_init); 2062'>2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222
/******************************************************************************/
/*                                                                            */
/* Broadcom BCM5700 Linux Network Driver, Copyright (c) 2000 Broadcom         */
/* Corporation.                                                               */
/* All rights reserved.                                                       */
/*                                                                            */
/* This program is free software; you can redistribute it and/or modify       */
/* it under the terms of the GNU General Public License as published by       */
/* the Free Software Foundation, located in the file LICENSE.                 */
/*                                                                            */
/* History:                                                                   */
/******************************************************************************/
#include <common.h>
#include "bcm570x_mm.h"
#include <asm/types.h>
#if (CONFIG_COMMANDS & CFG_CMD_NET) && !defined(CONFIG_NET_MULTI) && \
	defined(CONFIG_TIGON3)
#ifdef CONFIG_BMW
#include <mpc824x.h>
#endif
#include <malloc.h>
#include <linux/byteorder/big_endian.h>

#define EMBEDDED 1
/******************************************************************************/
/* Local functions. */
/******************************************************************************/

LM_STATUS LM_Abort(PLM_DEVICE_BLOCK pDevice);
LM_STATUS LM_QueueRxPackets(PLM_DEVICE_BLOCK pDevice);

static LM_STATUS LM_TranslateRequestedMediaType(
    LM_REQUESTED_MEDIA_TYPE RequestedMediaType,
    PLM_MEDIA_TYPE pMediaType, PLM_LINE_SPEED pLineSpeed,
    PLM_DUPLEX_MODE pDuplexMode);

static LM_STATUS LM_InitBcm540xPhy(PLM_DEVICE_BLOCK pDevice);

__inline static LM_VOID LM_ServiceRxInterrupt(PLM_DEVICE_BLOCK pDevice);
__inline static LM_VOID LM_ServiceTxInterrupt(PLM_DEVICE_BLOCK pDevice);

static LM_STATUS LM_ForceAutoNegBcm540xPhy(PLM_DEVICE_BLOCK pDevice,
    LM_REQUESTED_MEDIA_TYPE RequestedMediaType);
static LM_STATUS LM_ForceAutoNeg(PLM_DEVICE_BLOCK pDevice,
    LM_REQUESTED_MEDIA_TYPE RequestedMediaType);
static LM_UINT32 GetPhyAdFlowCntrlSettings(PLM_DEVICE_BLOCK pDevice);
STATIC LM_STATUS LM_SetFlowControl(PLM_DEVICE_BLOCK pDevice,
    LM_UINT32 LocalPhyAd, LM_UINT32 RemotePhyAd);
#if INCLUDE_TBI_SUPPORT
STATIC LM_STATUS LM_SetupFiberPhy(PLM_DEVICE_BLOCK pDevice);
STATIC LM_STATUS LM_InitBcm800xPhy(PLM_DEVICE_BLOCK pDevice);
#endif
STATIC LM_STATUS LM_SetupCopperPhy(PLM_DEVICE_BLOCK pDevice);
STATIC PLM_ADAPTER_INFO LM_GetAdapterInfoBySsid(LM_UINT16 Svid, LM_UINT16 Ssid);
STATIC LM_STATUS LM_DmaTest(PLM_DEVICE_BLOCK pDevice, PLM_UINT8 pBufferVirt,
           LM_PHYSICAL_ADDRESS BufferPhy, LM_UINT32 BufferSize);
STATIC LM_STATUS LM_HaltCpu(PLM_DEVICE_BLOCK pDevice,LM_UINT32 cpu_number);
STATIC LM_STATUS LM_ResetChip(PLM_DEVICE_BLOCK pDevice);
STATIC LM_STATUS LM_Test4GBoundary(PLM_DEVICE_BLOCK pDevice, PLM_PACKET pPacket,
    PT3_SND_BD pSendBd);

/******************************************************************************/
/* External functions. */
/******************************************************************************/

LM_STATUS LM_LoadRlsFirmware(PLM_DEVICE_BLOCK pDevice);


/******************************************************************************/
/* Description:                                                               */
/*                                                                            */
/* Return:                                                                    */
/******************************************************************************/
LM_UINT32
LM_RegRdInd(
PLM_DEVICE_BLOCK pDevice,
LM_UINT32 Register) {
    LM_UINT32 Value32;

#if PCIX_TARGET_WORKAROUND
    MM_ACQUIRE_UNDI_LOCK(pDevice);
#endif
    MM_WriteConfig32(pDevice, T3_PCI_REG_ADDR_REG, Register);
    MM_ReadConfig32(pDevice, T3_PCI_REG_DATA_REG, &Value32);
#if PCIX_TARGET_WORKAROUND
    MM_RELEASE_UNDI_LOCK(pDevice);
#endif

    return Value32;
} /* LM_RegRdInd */



/******************************************************************************/
/* Description:                                                               */
/*                                                                            */
/* Return:                                                                    */
/******************************************************************************/
LM_VOID
LM_RegWrInd(
PLM_DEVICE_BLOCK pDevice,
LM_UINT32 Register,
LM_UINT32 Value32) {

#if PCIX_TARGET_WORKAROUND
    MM_ACQUIRE_UNDI_LOCK(pDevice);
#endif
    MM_WriteConfig32(pDevice, T3_PCI_REG_ADDR_REG, Register);
    MM_WriteConfig32(pDevice, T3_PCI_REG_DATA_REG, Value32);
#if PCIX_TARGET_WORKAROUND
    MM_RELEASE_UNDI_LOCK(pDevice);
#endif
} /* LM_RegWrInd */



/******************************************************************************/
/* Description:                                                               */
/*                                                                            */
/* Return:                                                                    */
/******************************************************************************/
LM_UINT32
LM_MemRdInd(
PLM_DEVICE_BLOCK pDevice,
LM_UINT32 MemAddr) {
    LM_UINT32 Value32;

    MM_ACQUIRE_UNDI_LOCK(pDevice);
#ifdef BIG_ENDIAN_HOST
    MM_WriteConfig32(pDevice, T3_PCI_MEM_WIN_ADDR_REG, MemAddr);
    Value32 = REG_RD(pDevice, PciCfg.MemWindowData);
    /*    Value32 = REG_RD(pDevice,uIntMem.Mbuf[(MemAddr & 0x7fff)/4]); */
#else
    MM_WriteConfig32(pDevice, T3_PCI_MEM_WIN_ADDR_REG, MemAddr);
    MM_ReadConfig32(pDevice, T3_PCI_MEM_WIN_DATA_REG, &Value32);
#endif
    MM_RELEASE_UNDI_LOCK(pDevice);

    return Value32;
} /* LM_MemRdInd */



/******************************************************************************/
/* Description:                                                               */
/*                                                                            */
/* Return:                                                                    */
/******************************************************************************/
LM_VOID
LM_MemWrInd(
PLM_DEVICE_BLOCK pDevice,
LM_UINT32 MemAddr,
LM_UINT32 Value32) {
    MM_ACQUIRE_UNDI_LOCK(pDevice);
#ifdef BIG_ENDIAN_HOST
    REG_WR(pDevice,PciCfg.MemWindowBaseAddr,MemAddr);
    REG_WR(pDevice,uIntMem.Mbuf[(MemAddr & 0x7fff)/4],Value32);
#else
    MM_WriteConfig32(pDevice, T3_PCI_MEM_WIN_ADDR_REG, MemAddr);
    MM_WriteConfig32(pDevice, T3_PCI_MEM_WIN_DATA_REG, Value32);
#endif
    MM_RELEASE_UNDI_LOCK(pDevice);
} /* LM_MemWrInd */



/******************************************************************************/
/* Description:                                                               */
/*                                                                            */
/* Return:                                                                    */
/******************************************************************************/
LM_STATUS
LM_QueueRxPackets(
PLM_DEVICE_BLOCK pDevice) {
    LM_STATUS Lmstatus;
    PLM_PACKET pPacket;
    PT3_RCV_BD pRcvBd;
    LM_UINT32 StdBdAdded = 0;
#if T3_JUMBO_RCV_RCB_ENTRY_COUNT
    LM_UINT32 JumboBdAdded = 0;
#endif /* T3_JUMBO_RCV_RCB_ENTRY_COUNT */

    Lmstatus = LM_STATUS_SUCCESS;

    pPacket = (PLM_PACKET) QQ_PopHead(&pDevice->RxPacketFreeQ.Container);
    while(pPacket) {
        switch(pPacket->u.Rx.RcvProdRing) {
#if T3_JUMBO_RCV_RCB_ENTRY_COUNT
            case T3_JUMBO_RCV_PROD_RING:        /* Jumbo Receive Ring. */
                /* Initialize the buffer descriptor. */
                pRcvBd =
                    &pDevice->pRxJumboBdVirt[pDevice->RxJumboProdIdx];
                pRcvBd->Flags = RCV_BD_FLAG_END | RCV_BD_FLAG_JUMBO_RING;
                pRcvBd->Len = (LM_UINT16) pDevice->RxJumboBufferSize;

                /* Initialize the receive buffer pointer */
#if 0 /* Jimmy, deleted in new */
                pRcvBd->HostAddr.Low = pPacket->u.Rx.RxBufferPhy.Low;
                pRcvBd->HostAddr.High = pPacket->u.Rx.RxBufferPhy.High;
#endif
                MM_MapRxDma(pDevice, pPacket, &pRcvBd->HostAddr);

                /* The opaque field may point to an offset from a fix addr. */
                pRcvBd->Opaque = (LM_UINT32) (MM_UINT_PTR(pPacket) -
                    MM_UINT_PTR(pDevice->pPacketDescBase));

                /* Update the producer index. */
                pDevice->RxJumboProdIdx = (pDevice->RxJumboProdIdx + 1) &
                    T3_JUMBO_RCV_RCB_ENTRY_COUNT_MASK;

                JumboBdAdded++;
                break;
#endif /* T3_JUMBO_RCV_RCB_ENTRY_COUNT */

            case T3_STD_RCV_PROD_RING:      /* Standard Receive Ring. */
                /* Initialize the buffer descriptor. */
                pRcvBd = &pDevice->pRxStdBdVirt[pDevice->RxStdProdIdx];
                pRcvBd->Flags = RCV_BD_FLAG_END;
                pRcvBd->Len = MAX_STD_RCV_BUFFER_SIZE;

                /* Initialize the receive buffer pointer */
#if 0  /* Jimmy, deleted in new replaced with MM_MapRxDma */
                pRcvBd->HostAddr.Low = pPacket->u.Rx.RxBufferPhy.Low;
                pRcvBd->HostAddr.High = pPacket->u.Rx.RxBufferPhy.High;
#endif
                MM_MapRxDma(pDevice, pPacket, &pRcvBd->HostAddr);

                /* The opaque field may point to an offset from a fix addr. */
                pRcvBd->Opaque = (LM_UINT32) (MM_UINT_PTR(pPacket) -
                    MM_UINT_PTR(pDevice->pPacketDescBase));

                /* Update the producer index. */
                pDevice->RxStdProdIdx = (pDevice->RxStdProdIdx + 1) &
                    T3_STD_RCV_RCB_ENTRY_COUNT_MASK;

                StdBdAdded++;
                break;

            case T3_UNKNOWN_RCV_PROD_RING:
            default:
                Lmstatus = LM_STATUS_FAILURE;
                break;
        } /* switch */

        /* Bail out if there is any error. */
        if(Lmstatus != LM_STATUS_SUCCESS)
        {
            break;
        }

        pPacket = (PLM_PACKET) QQ_PopHead(&pDevice->RxPacketFreeQ.Container);
    } /* while */

    wmb();
    /* Update the procedure index. */
    if(StdBdAdded)
    {
        MB_REG_WR(pDevice, Mailbox.RcvStdProdIdx.Low, pDevice->RxStdProdIdx);
    }
#if T3_JUMBO_RCV_RCB_ENTRY_COUNT
    if(JumboBdAdded)
    {
        MB_REG_WR(pDevice, Mailbox.RcvJumboProdIdx.Low,
            pDevice->RxJumboProdIdx);
    }
#endif /* T3_JUMBO_RCV_RCB_ENTRY_COUNT */

    return Lmstatus;
} /* LM_QueueRxPackets */


/******************************************************************************/
/* Description:                                                               */
/*                                                                            */
/* Return:                                                                    */
/******************************************************************************/
STATIC LM_VOID
LM_NvramInit(
    PLM_DEVICE_BLOCK pDevice)
{
    LM_UINT32 Value32;
    LM_UINT32 j;

    /* Intialize clock period and state machine. */
    Value32 = SEEPROM_ADDR_CLK_PERD(SEEPROM_CLOCK_PERIOD) |
        SEEPROM_ADDR_FSM_RESET;
    REG_WR(pDevice, Grc.EepromAddr, Value32);

    for(j = 0; j < 100; j++)
    {
        MM_Wait(10);
    }

    /* Serial eeprom access using the Grc.EepromAddr/EepromData registers. */
    Value32 = REG_RD(pDevice, Grc.LocalCtrl);
    REG_WR(pDevice, Grc.LocalCtrl, Value32 | GRC_MISC_LOCAL_CTRL_AUTO_SEEPROM);

    /* Set the 5701 compatibility mode if we are using EEPROM. */
    if(T3_ASIC_REV(pDevice->ChipRevId) != T3_ASIC_REV_5700 &&
        T3_ASIC_REV(pDevice->ChipRevId) != T3_ASIC_REV_5701)
    {
        Value32 = REG_RD(pDevice, Nvram.Config1);
        if((Value32 & FLASH_INTERFACE_ENABLE) == 0)
        {
            /* Use the new interface to read EEPROM. */
            Value32 &= ~FLASH_COMPAT_BYPASS;

            REG_WR(pDevice, Nvram.Config1, Value32);
        }
    }
} /* LM_NvRamInit */


/******************************************************************************/
/* Description:                                                               */
/*                                                                            */
/* Return:                                                                    */
/******************************************************************************/
STATIC LM_STATUS
LM_EepromRead(
    PLM_DEVICE_BLOCK pDevice,
    LM_UINT32 Offset,
    LM_UINT32 *pData)
{
    LM_UINT32 Value32;
    LM_UINT32 Addr;
    LM_UINT32 Dev;
    LM_UINT32 j;

    if(Offset > SEEPROM_CHIP_SIZE)
    {
        return LM_STATUS_FAILURE;
    }

    Dev = Offset / SEEPROM_CHIP_SIZE;
    Addr = Offset % SEEPROM_CHIP_SIZE;

    Value32 = REG_RD(pDevice, Grc.EepromAddr);
    Value32 &= ~(SEEPROM_ADDR_ADDRESS_MASK | SEEPROM_ADDR_DEV_ID_MASK |
        SEEPROM_ADDR_RW_MASK);
    REG_WR(pDevice, Grc.EepromAddr, Value32 | SEEPROM_ADDR_DEV_ID(Dev) |
        SEEPROM_ADDR_ADDRESS(Addr) | SEEPROM_ADDR_START | SEEPROM_ADDR_READ);

    for(j = 0; j < 1000; j++)
    {
        Value32 = REG_RD(pDevice, Grc.EepromAddr);
        if(Value32 & SEEPROM_ADDR_COMPLETE)
        {
            break;
        }
        MM_Wait(10);
    }

    if(Value32 & SEEPROM_ADDR_COMPLETE)
    {
        Value32 = REG_RD(pDevice, Grc.EepromData);
        *pData = Value32;

        return LM_STATUS_SUCCESS;
    }

    return LM_STATUS_FAILURE;
} /* LM_EepromRead */



/******************************************************************************/
/* Description:                                                               */
/*                                                                            */
/* Return:                                                                    */
/******************************************************************************/
STATIC LM_STATUS
LM_NvramRead(
    PLM_DEVICE_BLOCK pDevice,
    LM_UINT32 Offset,
    LM_UINT32 *pData)
{
    LM_UINT32 Value32;
    LM_STATUS Status;
    LM_UINT32 j;

    if(T3_ASIC_REV(pDevice->ChipRevId) == T3_ASIC_REV_5700 ||
        T3_ASIC_REV(pDevice->ChipRevId) == T3_ASIC_REV_5701)
    {
        Status = LM_EepromRead(pDevice, Offset, pData);
    }
    else
    {
        /* Determine if we have flash or EEPROM. */
        Value32 = REG_RD(pDevice, Nvram.Config1);
        if(Value32 & FLASH_INTERFACE_ENABLE)
        {
            if(Value32 & FLASH_SSRAM_BUFFERRED_MODE)
            {
                Offset = ((Offset/BUFFERED_FLASH_PAGE_SIZE) <<
                    BUFFERED_FLASH_PAGE_POS) +
                    (Offset % BUFFERED_FLASH_PAGE_SIZE);
            }
        }

        REG_WR(pDevice, Nvram.SwArb, SW_ARB_REQ_SET1);
        for (j = 0; j < 1000; j++)
        {
            if (REG_RD(pDevice, Nvram.SwArb) & SW_ARB_GNT1)
            {
                break;
            }
            MM_Wait(20);
        }
        if (j == 1000)
        {
            return LM_STATUS_FAILURE;
        }

        /* Read from flash or EEPROM with the new 5703/02 interface. */
        REG_WR(pDevice, Nvram.Addr, Offset & NVRAM_ADDRESS_MASK);

        REG_WR(pDevice, Nvram.Cmd, NVRAM_CMD_RD | NVRAM_CMD_DO_IT |
            NVRAM_CMD_FIRST | NVRAM_CMD_LAST | NVRAM_CMD_DONE);

        /* Wait for the done bit to clear. */
        for(j = 0; j < 500; j++)
        {
            MM_Wait(10);

            Value32 = REG_RD(pDevice, Nvram.Cmd);
            if(!(Value32 & NVRAM_CMD_DONE))
            {
                break;
            }
        }

        /* Wait for the done bit. */
        if(!(Value32 & NVRAM_CMD_DONE))
        {
            for(j = 0; j < 500; j++)
            {
                MM_Wait(10);

                Value32 = REG_RD(pDevice, Nvram.Cmd);
                if(Value32 & NVRAM_CMD_DONE)
                {
                    MM_Wait(10);

                    *pData = REG_RD(pDevice, Nvram.ReadData);

                    /* Change the endianess. */
                    *pData = ((*pData & 0xff) << 24)| ((*pData & 0xff00) << 8)|
                        ((*pData & 0xff0000) >> 8) | ((*pData >> 24) & 0xff);

                    break;
                }
            }
        }

        REG_WR(pDevice, Nvram.SwArb, SW_ARB_REQ_CLR1);
        if(Value32 & NVRAM_CMD_DONE)
        {
            Status = LM_STATUS_SUCCESS;
        }
        else
        {
            Status = LM_STATUS_FAILURE;
        }
    }

    return Status;
} /* LM_NvramRead */


STATIC void
LM_ReadVPD(PLM_DEVICE_BLOCK pDevice)
{
    LM_UINT32 Vpd_arr[256/4];
    LM_UINT8 *Vpd = (LM_UINT8 *) &Vpd_arr[0];
    LM_UINT32 *Vpd_dptr = &Vpd_arr[0];
    LM_UINT32 Value32;
    unsigned int j;

    /* Read PN from VPD */
    for (j = 0; j < 256; j += 4, Vpd_dptr++ )
    {
        if (LM_NvramRead(pDevice, 0x100 + j, &Value32) != LM_STATUS_SUCCESS) {
            printf("BCM570x: LM_ReadVPD: VPD read failed"
		   " (no EEPROM onboard)\n");
            return;
        }
        *Vpd_dptr = cpu_to_le32(Value32);
    }
    for (j = 0; j < 256; )
    {
        unsigned int Vpd_r_len;
        unsigned int Vpd_r_end;

        if ((Vpd[j] == 0x82) || (Vpd[j] == 0x91))
        {
            j = j + 3 + Vpd[j + 1] + (Vpd[j + 2] << 8);
        }
        else if (Vpd[j] == 0x90)
        {
            Vpd_r_len =  Vpd[j + 1] + (Vpd[j + 2] << 8);
            j += 3;
            Vpd_r_end = Vpd_r_len + j;
            while (j < Vpd_r_end)
            {
                if ((Vpd[j] == 'P') && (Vpd[j + 1] == 'N'))
                {
                    unsigned int len = Vpd[j + 2];

                    if (len <= 24)
                    {
                        memcpy(pDevice->PartNo, &Vpd[j + 3], len);
                    }
                    break;
                }
                else
                {
                    if (Vpd[j + 2] == 0)
                    {
                        break;
                    }
                    j = j + Vpd[j + 2];
                }
            }
            break;
        }
        else {
            break;
        }
    }
}

STATIC void
LM_ReadBootCodeVersion(PLM_DEVICE_BLOCK pDevice)
{
    LM_UINT32 Value32, offset, ver_offset;
    int i;

    if (LM_NvramRead(pDevice, 0x0, &Value32) != LM_STATUS_SUCCESS)
        return;
    if (Value32 != 0xaa559966)
        return;
    if (LM_NvramRead(pDevice, 0xc, &offset) != LM_STATUS_SUCCESS)
        return;

    offset = ((offset & 0xff) << 24)| ((offset & 0xff00) << 8)|
        ((offset & 0xff0000) >> 8) | ((offset >> 24) & 0xff);
    if (LM_NvramRead(pDevice, offset, &Value32) != LM_STATUS_SUCCESS)
        return;
    if ((Value32 == 0x0300000e) &&
        (LM_NvramRead(pDevice, offset + 4, &Value32) == LM_STATUS_SUCCESS) &&
        (Value32 == 0)) {

        if (LM_NvramRead(pDevice, offset + 8, &ver_offset) != LM_STATUS_SUCCESS)
            return;
        ver_offset = ((ver_offset & 0xff0000) >> 8) |
            ((ver_offset >> 24) & 0xff);
        for (i = 0; i < 16; i += 4) {
            if (LM_NvramRead(pDevice, offset + ver_offset + i, &Value32) !=
                LM_STATUS_SUCCESS)
            {
                return;
            }
            *((LM_UINT32 *) &pDevice->BootCodeVer[i]) = cpu_to_le32(Value32);
        }
    }
    else {
        char c;

        if (LM_NvramRead(pDevice, 0x94, &Value32) != LM_STATUS_SUCCESS)
            return;

        i = 0;
        c = ((Value32 & 0xff0000) >> 16);

        if (c < 10) {
            pDevice->BootCodeVer[i++] = c + '0';
        }
        else {
            pDevice->BootCodeVer[i++] = (c / 10) + '0';
            pDevice->BootCodeVer[i++] = (c % 10) + '0';
        }
        pDevice->BootCodeVer[i++] = '.';
        c = (Value32 & 0xff000000) >> 24;
        if (c < 10) {
            pDevice->BootCodeVer[i++] = c + '0';
        }
        else {
            pDevice->BootCodeVer[i++] = (c / 10) + '0';
            pDevice->BootCodeVer[i++] = (c % 10) + '0';
        }
        pDevice->BootCodeVer[i] = 0;
    }
}

STATIC void
LM_GetBusSpeed(PLM_DEVICE_BLOCK pDevice)
{
    LM_UINT32 PciState = pDevice->PciState;
    LM_UINT32 ClockCtrl;
    char *SpeedStr = "";

    if (PciState & T3_PCI_STATE_32BIT_PCI_BUS)
    {
        strcpy(pDevice->BusSpeedStr, "32-bit ");
    }
    else
    {
        strcpy(pDevice->BusSpeedStr, "64-bit ");
    }
    if (PciState & T3_PCI_STATE_CONVENTIONAL_PCI_MODE)
    {
        strcat(pDevice->BusSpeedStr, "PCI ");
        if (PciState & T3_PCI_STATE_HIGH_BUS_SPEED)
        {
            SpeedStr = "66MHz";
        }
        else
        {
            SpeedStr = "33MHz";
        }
    }
    else
    {
        strcat(pDevice->BusSpeedStr, "PCIX ");
        if (pDevice->BondId == GRC_MISC_BD_ID_5704CIOBE)
        {
            SpeedStr = "133MHz";
        }
        else
        {
            ClockCtrl = REG_RD(pDevice, PciCfg.ClockCtrl) & 0x1f;
            switch (ClockCtrl)
            {
            case 0:
                SpeedStr = "33MHz";
                break;

            case 2:
                SpeedStr = "50MHz";
                break;

            case 4:
                SpeedStr = "66MHz";
                break;

            case 6:
                SpeedStr = "100MHz";
                break;

            case 7:
                SpeedStr = "133MHz";
                break;
            }
        }
    }
    strcat(pDevice->BusSpeedStr, SpeedStr);
}

/******************************************************************************/
/* Description:                                                               */
/*    This routine initializes default parameters and reads the PCI           */
/*    configurations.                                                         */
/*                                                                            */
/* Return:                                                                    */
/*    LM_STATUS_SUCCESS                                                       */
/******************************************************************************/
LM_STATUS
LM_GetAdapterInfo(
PLM_DEVICE_BLOCK pDevice)
{
    PLM_ADAPTER_INFO pAdapterInfo;
    LM_UINT32 Value32;
    LM_STATUS Status;
    LM_UINT32 j;
    LM_UINT32 EeSigFound;
    LM_UINT32 EePhyTypeSerdes = 0;
    LM_UINT32 EePhyLedMode = 0;
    LM_UINT32 EePhyId = 0;

    /* Get Device Id and Vendor Id */
    Status = MM_ReadConfig32(pDevice, PCI_VENDOR_ID_REG, &Value32);
    if(Status != LM_STATUS_SUCCESS)
    {
        return Status;