X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=kernel%2Fnet%2Fipv4%2Ftcp.c;h=036a76ba2ac293bcf6e33655cbc7508e74f7cf8f;hb=e09b41010ba33a20a87472ee821fa407a5b8da36;hp=bb2ce74f600494236638b7d40b35709f0f3736c3;hpb=f93b97fd65072de626c074dbe099a1fff05ce060;p=kvmfornfv.git diff --git a/kernel/net/ipv4/tcp.c b/kernel/net/ipv4/tcp.c index bb2ce74f6..036a76ba2 100644 --- a/kernel/net/ipv4/tcp.c +++ b/kernel/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include #include +#include #include int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; @@ -388,6 +389,7 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); + tp->rtt_min[0].rtt = ~0U; /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -450,11 +452,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) unsigned int mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); + int state; sock_rps_record_flow(sk); sock_poll_wait(file, sk_sleep(sk), wait); - if (sk->sk_state == TCP_LISTEN) + + state = sk_state_load(sk); + if (state == TCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events @@ -491,14 +496,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ - if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE) + if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= POLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLIN | POLLRDNORM | POLLRDHUP; /* Connected or passive Fast Open socket? */ - if (sk->sk_state != TCP_SYN_SENT && - (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk)) { + if (state != TCP_SYN_SENT && + (state != TCP_SYN_RECV || tp->fastopen_rsk)) { int target = sock_rcvlowat(sk, 0, INT_MAX); if (tp->urg_seq == tp->copied_seq && @@ -506,9 +511,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) tp->urg_data) target++; - /* Potential race condition. If read of tp below will - * escape above sk->sk_state, we can be illegally awaken - * in SYN_* states. */ if (tp->rcv_nxt - tp->copied_seq >= target) mask |= POLLIN | POLLRDNORM; @@ -516,8 +518,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (sk_stream_is_writeable(sk)) { mask |= POLLOUT | POLLWRNORM; } else { /* send SIGIO later */ - set_bit(SOCK_ASYNC_NOSPACE, - &sk->sk_socket->flags); + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after @@ -627,6 +628,8 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb) sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; + + tcp_slow_start_after_idle_check(sk); } static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) @@ -695,8 +698,9 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, struct tcp_splice_state *tss = rd_desc->arg.data; int ret; - ret = skb_splice_bits(skb, offset, tss->pipe, min(rd_desc->count, len), - tss->flags); + ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe, + min(rd_desc->count, len), tss->flags, + skb_socket_splice); if (ret > 0) rd_desc->count -= ret; return ret; @@ -779,7 +783,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, ret = -EAGAIN; break; } - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; @@ -809,16 +813,28 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, } EXPORT_SYMBOL(tcp_splice_read); -struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) +struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, + bool force_schedule) { struct sk_buff *skb; /* The TCP header must be at least 32-bit aligned. */ size = ALIGN(size, 4); + if (unlikely(tcp_under_memory_pressure(sk))) + sk_mem_reclaim_partial(sk); + skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp); - if (skb) { - if (sk_wmem_schedule(sk, skb->truesize)) { + if (likely(skb)) { + bool mem_scheduled; + + if (force_schedule) { + mem_scheduled = true; + sk_forced_mem_schedule(sk, skb->truesize); + } else { + mem_scheduled = sk_wmem_schedule(sk, skb->truesize); + } + if (likely(mem_scheduled)) { skb_reserve(skb, sk->sk_prot->max_header); /* * Make sure that we have exactly size bytes @@ -885,11 +901,12 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { - if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) + err = sk_stream_wait_connect(sk, &timeo); + if (err != 0) goto out_err; } - clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); mss_now = tcp_send_mss(sk, &size_goal, flags); copied = 0; @@ -908,7 +925,8 @@ new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; - skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); + skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, + skb_queue_empty(&sk->sk_write_queue)); if (!skb) goto wait_for_memory; @@ -921,7 +939,7 @@ new_segment: i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= MAX_SKB_FRAGS) { + if (!can_coalesce && i >= sysctl_max_skb_frags) { tcp_mark_push(tp, skb); goto new_segment; } @@ -951,7 +969,8 @@ new_segment: copied += copy; offset += copy; - if (!(size -= copy)) { + size -= copy; + if (!size) { tcp_tx_timestamp(sk, skb); goto out; } @@ -972,7 +991,8 @@ wait_for_memory: tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); - if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) + err = sk_stream_wait_memory(sk, &timeo); + if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); @@ -987,6 +1007,9 @@ do_error: if (copied) goto out; out_err: + /* make sure we wake any epoll edge trigger waiter */ + if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) + sk->sk_write_space(sk); return sk_stream_error(sk, flags, err); } @@ -1092,7 +1115,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { - if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) + err = sk_stream_wait_connect(sk, &timeo); + if (err != 0) goto do_error; } @@ -1110,7 +1134,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) } /* This should be in poll */ - clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); mss_now = tcp_send_mss(sk, &size_goal, flags); @@ -1144,7 +1168,8 @@ new_segment: skb = sk_stream_alloc_skb(sk, select_size(sk, sg), - sk->sk_allocation); + sk->sk_allocation, + skb_queue_empty(&sk->sk_write_queue)); if (!skb) goto wait_for_memory; @@ -1187,7 +1212,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == MAX_SKB_FRAGS || !sg) { + if (i == sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1247,7 +1272,8 @@ wait_for_memory: tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); - if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) + err = sk_stream_wait_memory(sk, &timeo); + if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); @@ -1275,6 +1301,9 @@ do_error: goto out; out_err: err = sk_stream_error(sk, flags, err); + /* make sure we wake any epoll edge trigger waiter */ + if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) + sk->sk_write_space(sk); release_sock(sk); return err; } @@ -1554,7 +1583,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int target; /* Read at least this many bytes */ long timeo; struct task_struct *user_recv = NULL; - struct sk_buff *skb; + struct sk_buff *skb, *last; u32 urg_hole = 0; if (unlikely(flags & MSG_ERRQUEUE)) @@ -1614,7 +1643,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Next get a buffer. */ + last = skb_peek_tail(&sk->sk_receive_queue); skb_queue_walk(&sk->sk_receive_queue, skb) { + last = skb; /* Now that we have two receive queues this * shouldn't happen. */ @@ -1733,15 +1764,17 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Do not sleep, just process backlog. */ release_sock(sk); lock_sock(sk); - } else - sk_wait_data(sk, &timeo); + } else { + sk_wait_data(sk, &timeo, last); + } if (user_recv) { int chunk; /* __ Restore normal policy in scheduler __ */ - if ((chunk = len - tp->ucopy.len) != 0) { + chunk = len - tp->ucopy.len; + if (chunk != 0) { NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk); len -= chunk; copied += chunk; @@ -1752,7 +1785,8 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, do_prequeue: tcp_prequeue_process(sk); - if ((chunk = len - tp->ucopy.len) != 0) { + chunk = len - tp->ucopy.len; + if (chunk != 0) { NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk); len -= chunk; copied += chunk; @@ -1900,7 +1934,7 @@ void tcp_set_state(struct sock *sk, int state) /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ - sk->sk_state = state; + sk_state_store(sk, state); #ifdef STATE_TRACE SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]); @@ -2204,7 +2238,8 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; - if ((tp->write_seq += tp->max_window + 2) == 0) + tp->write_seq += tp->max_window + 2; + if (tp->write_seq == 0) tp->write_seq = 1; icsk->icsk_backoff = 0; tp->snd_cwnd = 2; @@ -2227,13 +2262,6 @@ int tcp_disconnect(struct sock *sk, int flags) } EXPORT_SYMBOL(tcp_disconnect); -void tcp_sock_destruct(struct sock *sk) -{ - inet_sock_destruct(sk); - - kfree(inet_csk(sk)->icsk_accept_queue.fastopenq); -} - static inline bool tcp_can_repair_sock(const struct sock *sk) { return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && @@ -2483,6 +2511,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level, icsk->icsk_syn_retries = val; break; + case TCP_SAVE_SYN: + if (val < 0 || val > 1) + err = -EINVAL; + else + tp->save_syn = val; + break; + case TCP_LINGER2: if (val < 0) tp->linger2 = -1; @@ -2548,7 +2583,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, TCPF_LISTEN))) { tcp_fastopen_init_key_once(true); - err = fastopen_init_queue(sk, val); + fastopen_queue_tune(sk, val); } else { err = -EINVAL; } @@ -2599,15 +2634,19 @@ EXPORT_SYMBOL(compat_tcp_setsockopt); /* Return information about state of tcp endpoint in API format. */ void tcp_get_info(struct sock *sk, struct tcp_info *info) { - const struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; unsigned int start; + u64 rate64; u32 rate; memset(info, 0, sizeof(*info)); + if (sk->sk_type != SOCK_STREAM) + return; + + info->tcpi_state = sk_state_load(sk); - info->tcpi_state = sk->sk_state; info->tcpi_ca_state = icsk->icsk_ca_state; info->tcpi_retransmits = icsk->icsk_retransmits; info->tcpi_probes = icsk->icsk_probes_out; @@ -2635,7 +2674,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_snd_mss = tp->mss_cache; info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss; - if (sk->sk_state == TCP_LISTEN) { + if (info->tcpi_state == TCP_LISTEN) { info->tcpi_unacked = sk->sk_ack_backlog; info->tcpi_sacked = sk->sk_max_ack_backlog; } else { @@ -2665,16 +2704,20 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_total_retrans = tp->total_retrans; rate = READ_ONCE(sk->sk_pacing_rate); - info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_pacing_rate); rate = READ_ONCE(sk->sk_max_pacing_rate); - info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_max_pacing_rate); do { start = u64_stats_fetch_begin_irq(&tp->syncp); - info->tcpi_bytes_acked = tp->bytes_acked; - info->tcpi_bytes_received = tp->bytes_received; + put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked); + put_unaligned(tp->bytes_received, &info->tcpi_bytes_received); } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); + info->tcpi_segs_out = tp->segs_out; + info->tcpi_segs_in = tp->segs_in; } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -2812,10 +2855,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_FASTOPEN: - if (icsk->icsk_accept_queue.fastopenq) - val = icsk->icsk_accept_queue.fastopenq->max_qlen; - else - val = 0; + val = icsk->icsk_accept_queue.fastopenq.max_qlen; break; case TCP_TIMESTAMP: @@ -2824,6 +2864,42 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; break; + case TCP_SAVE_SYN: + val = tp->save_syn; + break; + case TCP_SAVED_SYN: { + if (get_user(len, optlen)) + return -EFAULT; + + lock_sock(sk); + if (tp->saved_syn) { + if (len < tp->saved_syn[0]) { + if (put_user(tp->saved_syn[0], optlen)) { + release_sock(sk); + return -EFAULT; + } + release_sock(sk); + return -EINVAL; + } + len = tp->saved_syn[0]; + if (put_user(len, optlen)) { + release_sock(sk); + return -EFAULT; + } + if (copy_to_user(optval, tp->saved_syn + 1, len)) { + release_sock(sk); + return -EFAULT; + } + tcp_saved_syn_free(tp); + release_sock(sk); + } else { + release_sock(sk); + len = 0; + if (put_user(len, optlen)) + return -EFAULT; + } + return 0; + } default: return -ENOPROTOOPT; } @@ -3028,11 +3104,12 @@ __setup("thash_entries=", set_thash_entries); static void __init tcp_init_mem(void) { - unsigned long limit = nr_free_buffer_pages() / 8; + unsigned long limit = nr_free_buffer_pages() / 16; + limit = max(limit, 128UL); - sysctl_tcp_mem[0] = limit / 4 * 3; - sysctl_tcp_mem[1] = limit; - sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; + sysctl_tcp_mem[0] = limit / 4 * 3; /* 4.68 % */ + sysctl_tcp_mem[1] = limit; /* 6.25 % */ + sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; /* 9.37 % */ } void __init tcp_init(void)