diff options
Diffstat (limited to 'net/ipv4/tcp.c')
| -rw-r--r-- | net/ipv4/tcp.c | 1569 |
1 files changed, 933 insertions, 636 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 17b89c523f9..9d2118e5fbc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -245,6 +245,8 @@ * TCP_CLOSE socket is finished */ +#define pr_fmt(fmt) "TCP: " fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> @@ -264,8 +266,11 @@ #include <linux/cache.h> #include <linux/err.h> #include <linux/crypto.h> +#include <linux/time.h> +#include <linux/slab.h> #include <net/icmp.h> +#include <net/inet_common.h> #include <net/tcp.h> #include <net/xfrm.h> #include <net/ip.h> @@ -274,13 +279,18 @@ #include <asm/uaccess.h> #include <asm/ioctls.h> +#include <net/busy_poll.h> int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; +int sysctl_tcp_min_tso_segs __read_mostly = 2; + +int sysctl_tcp_autocorking __read_mostly = 1; + struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); -int sysctl_tcp_mem[3] __read_mostly; +long sysctl_tcp_mem[3] __read_mostly; int sysctl_tcp_wmem[3] __read_mostly; int sysctl_tcp_rmem[3] __read_mostly; @@ -288,7 +298,7 @@ EXPORT_SYMBOL(sysctl_tcp_mem); EXPORT_SYMBOL(sysctl_tcp_rmem); EXPORT_SYMBOL(sysctl_tcp_wmem); -atomic_t tcp_memory_allocated; /* Current allocated memory. */ +atomic_long_t tcp_memory_allocated; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); /* @@ -313,7 +323,6 @@ struct tcp_splice_state { * is strict, actions are advisory and have some latency. */ int tcp_memory_pressure __read_mostly; - EXPORT_SYMBOL(tcp_memory_pressure); void tcp_enter_memory_pressure(struct sock *sk) @@ -323,9 +332,100 @@ void tcp_enter_memory_pressure(struct sock *sk) tcp_memory_pressure = 1; } } - EXPORT_SYMBOL(tcp_enter_memory_pressure); +/* Convert seconds to retransmits based on initial and max timeout */ +static u8 secs_to_retrans(int seconds, int timeout, int rto_max) +{ + u8 res = 0; + + if (seconds > 0) { + int period = timeout; + + res = 1; + while (seconds > period && res < 255) { + res++; + timeout <<= 1; + if (timeout > rto_max) + timeout = rto_max; + period += timeout; + } + } + return res; +} + +/* Convert retransmits to seconds based on initial and max timeout */ +static int retrans_to_secs(u8 retrans, int timeout, int rto_max) +{ + int period = 0; + + if (retrans > 0) { + period = timeout; + while (--retrans) { + timeout <<= 1; + if (timeout > rto_max) + timeout = rto_max; + period += timeout; + } + } + return period; +} + +/* Address-family independent initialization for a tcp_sock. + * + * NOTE: A lot of things set to zero explicitly by call to + * sk_alloc() so need not be done here. + */ +void tcp_init_sock(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + + __skb_queue_head_init(&tp->out_of_order_queue); + tcp_init_xmit_timers(sk); + tcp_prequeue_init(tp); + INIT_LIST_HEAD(&tp->tsq_node); + + icsk->icsk_rto = TCP_TIMEOUT_INIT; + tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); + + /* So many TCP implementations out there (incorrectly) count the + * initial SYN frame in their delayed-ACK and congestion control + * algorithms that we must have the following bandaid to talk + * efficiently to them. -DaveM + */ + tp->snd_cwnd = TCP_INIT_CWND; + + /* See draft-stevens-tcpca-spec-01 for discussion of the + * initialization of these values. + */ + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + tp->snd_cwnd_clamp = ~0; + tp->mss_cache = TCP_MSS_DEFAULT; + + tp->reordering = sysctl_tcp_reordering; + tcp_enable_early_retrans(tp); + icsk->icsk_ca_ops = &tcp_init_congestion_ops; + + tp->tsoffset = 0; + + sk->sk_state = TCP_CLOSE; + + sk->sk_write_space = sk_stream_write_space; + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + icsk->icsk_sync_mss = tcp_sync_mss; + + sk->sk_sndbuf = sysctl_tcp_wmem[1]; + sk->sk_rcvbuf = sysctl_tcp_rmem[1]; + + local_bh_disable(); + sock_update_memcg(sk); + sk_sockets_allocated_inc(sk); + local_bh_enable(); +} +EXPORT_SYMBOL(tcp_init_sock); + /* * Wait for a TCP event. * @@ -337,9 +437,11 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) { unsigned int mask; struct sock *sk = sock->sk; - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); + + sock_rps_record_flow(sk); - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == TCP_LISTEN) return inet_csk_listen_poll(sk); @@ -349,8 +451,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) */ mask = 0; - if (sk->sk_err) - mask = POLLERR; /* * POLLHUP is certainly not done right. But poll() doesn't @@ -384,14 +484,15 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLIN | POLLRDNORM | POLLRDHUP; - /* Connected? */ - if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) { + /* Connected or passive Fast Open socket? */ + if (sk->sk_state != TCP_SYN_SENT && + (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk != NULL)) { int target = sock_rcvlowat(sk, 0, INT_MAX); if (tp->urg_seq == tp->copied_seq && !sock_flag(sk, SOCK_URGINLINE) && tp->urg_data) - target--; + target++; /* Potential race condition. If read of tp below will * escape above sk->sk_state, we can be illegally awaken @@ -400,7 +501,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) mask |= POLLIN | POLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { + if (sk_stream_is_writeable(sk)) { mask |= POLLOUT | POLLWRNORM; } else { /* send SIGIO later */ set_bit(SOCK_ASYNC_NOSPACE, @@ -411,45 +512,51 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * wspace test but before the flags are set, * IO signal will be lost. */ - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) + if (sk_stream_is_writeable(sk)) mask |= POLLOUT | POLLWRNORM; } - } + } else + mask |= POLLOUT | POLLWRNORM; if (tp->urg_data & TCP_URG_VALID) mask |= POLLPRI; } + /* This barrier is coupled with smp_wmb() in tcp_reset() */ + smp_rmb(); + if (sk->sk_err) + mask |= POLLERR; + return mask; } +EXPORT_SYMBOL(tcp_poll); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct tcp_sock *tp = tcp_sk(sk); int answ; + bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; - lock_sock(sk); + slow = lock_sock_fast(sk); if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || before(tp->urg_seq, tp->copied_seq) || !before(tp->urg_seq, tp->rcv_nxt)) { - struct sk_buff *skb; answ = tp->rcv_nxt - tp->copied_seq; - /* Subtract 1, if FIN is in queue. */ - skb = skb_peek_tail(&sk->sk_receive_queue); - if (answ && skb) - answ -= tcp_hdr(skb)->fin; + /* Subtract 1, if FIN was received */ + if (answ && sock_flag(sk, SOCK_DONE)) + answ--; } else answ = tp->urg_seq - tp->copied_seq; - release_sock(sk); + unlock_sock_fast(sk, slow); break; case SIOCATMARK: answ = tp->urg_data && tp->urg_seq == tp->copied_seq; @@ -463,20 +570,30 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) else answ = tp->write_seq - tp->snd_una; break; + case SIOCOUTQNSD: + if (sk->sk_state == TCP_LISTEN) + return -EINVAL; + + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) + answ = 0; + else + answ = tp->write_seq - tp->snd_nxt; + break; default: return -ENOIOCTLCMD; } return put_user(answ, (int __user *)arg); } +EXPORT_SYMBOL(tcp_ioctl); static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { - TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH; + TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; tp->pushed_seq = tp->write_seq; } -static inline int forced_push(struct tcp_sock *tp) +static inline bool forced_push(const struct tcp_sock *tp) { return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1)); } @@ -488,7 +605,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb) skb->csum = 0; tcb->seq = tcb->end_seq = tp->write_seq; - tcb->flags = TCPCB_FLAG_ACK; + tcb->tcp_flags = TCPHDR_ACK; tcb->sacked = 0; skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); @@ -498,26 +615,64 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb) tp->nonagle &= ~TCP_NAGLE_PUSH; } -static inline void tcp_mark_urg(struct tcp_sock *tp, int flags, - struct sk_buff *skb) +static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) { if (flags & MSG_OOB) tp->snd_up = tp->write_seq; } -static inline void tcp_push(struct sock *sk, int flags, int mss_now, - int nonagle) +/* If a not yet filled skb is pushed, do not send it if + * we have data packets in Qdisc or NIC queues : + * Because TX completion will happen shortly, it gives a chance + * to coalesce future sendmsg() payload into this skb, without + * need for a timer, and with no latency trade off. + * As packets containing data payload have a bigger truesize + * than pure acks (dataless) packets, the last checks prevent + * autocorking if we only have an ACK in Qdisc/NIC queues, + * or if TX completion was delayed after we processed ACK packet. + */ +static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, + int size_goal) +{ + return skb->len < size_goal && + sysctl_tcp_autocorking && + skb != tcp_write_queue_head(sk) && + atomic_read(&sk->sk_wmem_alloc) > skb->truesize; +} + +static void tcp_push(struct sock *sk, int flags, int mss_now, + int nonagle, int size_goal) { struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; - if (tcp_send_head(sk)) { - struct sk_buff *skb = tcp_write_queue_tail(sk); - if (!(flags & MSG_MORE) || forced_push(tp)) - tcp_mark_push(tp, skb); - tcp_mark_urg(tp, flags, skb); - __tcp_push_pending_frames(sk, mss_now, - (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle); + if (!tcp_send_head(sk)) + return; + + skb = tcp_write_queue_tail(sk); + if (!(flags & MSG_MORE) || forced_push(tp)) + tcp_mark_push(tp, skb); + + tcp_mark_urg(tp, flags); + + if (tcp_should_autocork(sk, skb, size_goal)) { + + /* avoid atomic op if TSQ_THROTTLED bit is already set */ + if (!test_bit(TSQ_THROTTLED, &tp->tsq_flags)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); + set_bit(TSQ_THROTTLED, &tp->tsq_flags); + } + /* It is possible TX completion already happened + * before we set TSQ_THROTTLED. + */ + if (atomic_read(&sk->sk_wmem_alloc) > skb->truesize) + return; } + + if (flags & MSG_MORE) + nonagle = TCP_NAGLE_CORK; + + __tcp_push_pending_frames(sk, mss_now, nonagle); } static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, @@ -570,6 +725,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, ssize_t spliced; int ret; + sock_rps_record_flow(sk); /* * We can't seek on a socket input */ @@ -580,7 +736,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, lock_sock(sk); - timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK); + timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK); while (tss.len) { ret = __tcp_splice_read(sk, &tss); if (ret < 0) @@ -637,6 +793,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, return ret; } +EXPORT_SYMBOL(tcp_splice_read); struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) { @@ -648,11 +805,12 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp); if (skb) { if (sk_wmem_schedule(sk, skb->truesize)) { + skb_reserve(skb, sk->sk_prot->max_header); /* * Make sure that we have exactly size bytes * available to the caller, no more, no less. */ - skb_reserve(skb, skb_tailroom(skb) - size); + skb->reserved_tailroom = skb->end - skb->tail - size; return skb; } __kfree_skb(skb); @@ -672,10 +830,24 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, xmit_size_goal = mss_now; if (large_allowed && sk_can_gso(sk)) { - xmit_size_goal = ((sk->sk_gso_max_size - 1) - - inet_csk(sk)->icsk_af_ops->net_header_len - - inet_csk(sk)->icsk_ext_hdr_len - - tp->tcp_header_len); + u32 gso_size, hlen; + + /* Maybe we should/could use sk->sk_prot->max_header here ? */ + hlen = inet_csk(sk)->icsk_af_ops->net_header_len + + inet_csk(sk)->icsk_ext_hdr_len + + tp->tcp_header_len; + + /* Goal is to send at least one packet per ms, + * not one big TSO packet every 100 ms. + * This preserves ACK clocking and is consistent + * with tcp_tso_should_defer() heuristic. + */ + gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC); + gso_size = max_t(u32, gso_size, + sysctl_tcp_min_tso_segs * mss_now); + + xmit_size_goal = min_t(u32, gso_size, + sk->sk_gso_max_size - 1 - hlen); xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal); @@ -686,7 +858,9 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, old_size_goal + mss_now > xmit_size_goal)) { xmit_size_goal = old_size_goal; } else { - tp->xmit_size_goal_segs = xmit_size_goal / mss_now; + tp->xmit_size_goal_segs = + min_t(u16, xmit_size_goal / mss_now, + sk->sk_gso_max_segs); xmit_size_goal = tp->xmit_size_goal_segs * mss_now; } } @@ -704,8 +878,8 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } -static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffset, - size_t psize, int flags) +static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, + size_t size, int flags) { struct tcp_sock *tp = tcp_sk(sk); int mss_now, size_goal; @@ -713,10 +887,15 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse ssize_t copied; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - /* Wait for a connection to finish. */ - if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) + /* Wait for a connection to finish. One exception is TCP Fast Open + * (passive side) where data is allowed to be sent before a connection + * is fully established. + */ + if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && + !tcp_passive_fastopen(sk)) { if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) goto out_err; + } clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); @@ -727,12 +906,10 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto out_err; - while (psize > 0) { + while (size > 0) { struct sk_buff *skb = tcp_write_queue_tail(sk); - struct page *page = pages[poffset / PAGE_SIZE]; - int copy, i, can_coalesce; - int offset = poffset % PAGE_SIZE; - int size = min_t(size_t, psize, PAGE_SIZE - offset); + int copy, i; + bool can_coalesce; if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) { new_segment: @@ -760,11 +937,12 @@ new_segment: goto wait_for_memory; if (can_coalesce) { - skb_shinfo(skb)->frags[i - 1].size += copy; + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { get_page(page); skb_fill_page_desc(skb, i, page, offset, copy); } + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; skb->len += copy; skb->data_len += copy; @@ -777,11 +955,11 @@ new_segment: skb_shinfo(skb)->gso_segs = 0; if (!copied) - TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH; + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; copied += copy; - poffset += copy; - if (!(psize -= copy)) + offset += copy; + if (!(size -= copy)) goto out; if (skb->len < size_goal || (flags & MSG_OOB)) @@ -797,8 +975,8 @@ new_segment: wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: - if (copied) - tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); + tcp_push(sk, flags & ~MSG_MORE, mss_now, + TCP_NAGLE_PUSH, size_goal); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) goto do_error; @@ -807,8 +985,8 @@ wait_for_memory: } out: - if (copied) - tcp_push(sk, flags, mss_now, tp->nonagle); + if (copied && !(flags & MSG_SENDPAGE_NOTLAST)) + tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); return copied; do_error: @@ -818,36 +996,35 @@ out_err: return sk_stream_error(sk, flags, err); } -ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset, - size_t size, int flags) +int tcp_sendpage(struct sock *sk, struct page *page, int offset, + size_t size, int flags) { ssize_t res; - struct sock *sk = sock->sk; if (!(sk->sk_route_caps & NETIF_F_SG) || !(sk->sk_route_caps & NETIF_F_ALL_CSUM)) - return sock_no_sendpage(sock, page, offset, size, flags); + return sock_no_sendpage(sk->sk_socket, page, offset, size, + flags); lock_sock(sk); - TCP_CHECK_TIMER(sk); - res = do_tcp_sendpages(sk, &page, offset, size, flags); - TCP_CHECK_TIMER(sk); + res = do_tcp_sendpages(sk, page, offset, size, flags); release_sock(sk); return res; } +EXPORT_SYMBOL(tcp_sendpage); -#define TCP_PAGE(sk) (sk->sk_sndmsg_page) -#define TCP_OFF(sk) (sk->sk_sndmsg_off) - -static inline int select_size(struct sock *sk) +static inline int select_size(const struct sock *sk, bool sg) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); int tmp = tp->mss_cache; - if (sk->sk_route_caps & NETIF_F_SG) { - if (sk_can_gso(sk)) - tmp = 0; - else { + if (sg) { + if (sk_can_gso(sk)) { + /* Small frames wont use a full page: + * Payload will immediately follow tcp header. + */ + tmp = SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER); + } else { int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER); if (tmp >= pgbreak && @@ -859,29 +1036,88 @@ static inline int select_size(struct sock *sk) return tmp; } -int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, +void tcp_free_fastopen_req(struct tcp_sock *tp) +{ + if (tp->fastopen_req != NULL) { + kfree(tp->fastopen_req); + tp->fastopen_req = NULL; + } +} + +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, + int *copied, size_t size) +{ + struct tcp_sock *tp = tcp_sk(sk); + int err, flags; + + if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE)) + return -EOPNOTSUPP; + if (tp->fastopen_req != NULL) + return -EALREADY; /* Another Fast Open is in progress */ + + tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request), + sk->sk_allocation); + if (unlikely(tp->fastopen_req == NULL)) + return -ENOBUFS; + tp->fastopen_req->data = msg; + tp->fastopen_req->size = size; + + flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; + err = __inet_stream_connect(sk->sk_socket, msg->msg_name, + msg->msg_namelen, flags); + *copied = tp->fastopen_req->copied; + tcp_free_fastopen_req(tp); + return err; +} + +int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size) { - struct sock *sk = sock->sk; struct iovec *iov; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int iovlen, flags; - int mss_now, size_goal; - int err, copied; + int iovlen, flags, err, copied = 0; + int mss_now = 0, size_goal, copied_syn = 0, offset = 0; + bool sg; long timeo; lock_sock(sk); - TCP_CHECK_TIMER(sk); flags = msg->msg_flags; + if (flags & MSG_FASTOPEN) { + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); + if (err == -EINPROGRESS && copied_syn > 0) + goto out; + else if (err) + goto out_err; + offset = copied_syn; + } + timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - /* Wait for a connection to finish. */ - if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) + /* Wait for a connection to finish. One exception is TCP Fast Open + * (passive side) where data is allowed to be sent before a connection + * is fully established. + */ + if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && + !tcp_passive_fastopen(sk)) { if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) + goto do_error; + } + + if (unlikely(tp->repair)) { + if (tp->repair_queue == TCP_RECV_QUEUE) { + copied = tcp_send_rcvq(sk, msg, size); + goto out_nopush; + } + + err = -EINVAL; + if (tp->repair_queue == TCP_NO_QUEUE) goto out_err; + /* 'common' sending to sendq */ + } + /* This should be in poll */ clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); @@ -896,20 +1132,35 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto out_err; + sg = !!(sk->sk_route_caps & NETIF_F_SG); + while (--iovlen >= 0) { - int seglen = iov->iov_len; + size_t seglen = iov->iov_len; unsigned char __user *from = iov->iov_base; iov++; + if (unlikely(offset > 0)) { /* Skip bytes copied in SYN */ + if (offset >= seglen) { + offset -= seglen; + continue; + } + seglen -= offset; + from += offset; + offset = 0; + } while (seglen > 0) { - int copy; + int copy = 0; + int max = size_goal; skb = tcp_write_queue_tail(sk); + if (tcp_send_head(sk)) { + if (skb->ip_summed == CHECKSUM_NONE) + max = mss_now; + copy = max - skb->len; + } - if (!tcp_send_head(sk) || - (copy = size_goal - skb->len) <= 0) { - + if (copy <= 0) { new_segment: /* Allocate new segment. If the interface is SG, * allocate skb fitting to single page. @@ -917,12 +1168,20 @@ new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; - skb = sk_stream_alloc_skb(sk, select_size(sk), - sk->sk_allocation); + skb = sk_stream_alloc_skb(sk, + select_size(sk, sg), + sk->sk_allocation); if (!skb) goto wait_for_memory; /* + * All packets are restored as if they have + * already been sent. + */ + if (tp->repair) + TCP_SKB_CB(skb)->when = tcp_time_stamp; + + /* * Check whether we can use HW checksum. */ if (sk->sk_route_caps & NETIF_F_ALL_CSUM) @@ -930,6 +1189,7 @@ new_segment: skb_entail(sk, skb); copy = size_goal; + max = size_goal; } /* Try to append data to the end of skb. */ @@ -937,87 +1197,54 @@ new_segment: copy = seglen; /* Where to copy to? */ - if (skb_tailroom(skb) > 0) { + if (skb_availroom(skb) > 0) { /* We have some space in skb head. Superb! */ - if (copy > skb_tailroom(skb)) - copy = skb_tailroom(skb); - if ((err = skb_add_data(skb, from, copy)) != 0) + copy = min_t(int, copy, skb_availroom(skb)); + err = skb_add_data_nocache(sk, skb, from, copy); + if (err) goto do_fault; } else { - int merge = 0; + bool merge = true; int i = skb_shinfo(skb)->nr_frags; - struct page *page = TCP_PAGE(sk); - int off = TCP_OFF(sk); - - if (skb_can_coalesce(skb, i, page, off) && - off != PAGE_SIZE) { - /* We can extend the last page - * fragment. */ - merge = 1; - } else if (i == MAX_SKB_FRAGS || - (!i && - !(sk->sk_route_caps & NETIF_F_SG))) { - /* Need to add new fragment and cannot - * do this because interface is non-SG, - * or because all the page slots are - * busy. */ - tcp_mark_push(tp, skb); - goto new_segment; - } else if (page) { - if (off == PAGE_SIZE) { - put_page(page); - TCP_PAGE(sk) = page = NULL; - off = 0; + struct page_frag *pfrag = sk_page_frag(sk); + + if (!sk_page_frag_refill(sk, pfrag)) + goto wait_for_memory; + + if (!skb_can_coalesce(skb, i, pfrag->page, + pfrag->offset)) { + if (i == MAX_SKB_FRAGS || !sg) { + tcp_mark_push(tp, skb); + goto new_segment; } - } else - off = 0; + merge = false; + } - if (copy > PAGE_SIZE - off) - copy = PAGE_SIZE - off; + copy = min_t(int, copy, pfrag->size - pfrag->offset); if (!sk_wmem_schedule(sk, copy)) goto wait_for_memory; - if (!page) { - /* Allocate new cache page. */ - if (!(page = sk_stream_alloc_page(sk))) - goto wait_for_memory; - } - - /* Time to copy data. We are close to - * the end! */ - err = skb_copy_to_page(sk, from, skb, page, - off, copy); - if (err) { - /* If this page was new, give it to the - * socket so it does not get leaked. - */ - if (!TCP_PAGE(sk)) { - TCP_PAGE(sk) = page; - TCP_OFF(sk) = 0; - } + err = skb_copy_to_page_nocache(sk, from, skb, + pfrag->page, + pfrag->offset, + copy); + if (err) goto do_error; - } /* Update the skb. */ if (merge) { - skb_shinfo(skb)->frags[i - 1].size += - copy; + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { - skb_fill_page_desc(skb, i, page, off, copy); - if (TCP_PAGE(sk)) { - get_page(page); - } else if (off + copy < PAGE_SIZE) { - get_page(page); - TCP_PAGE(sk) = page; - } + skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, copy); + get_page(pfrag->page); } - - TCP_OFF(sk) = off + copy; + pfrag->offset += copy; } if (!copied) - TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH; + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; tp->write_seq += copy; TCP_SKB_CB(skb)->end_seq += copy; @@ -1028,7 +1255,7 @@ new_segment: if ((seglen -= copy) == 0 && iovlen == 0) goto out; - if (skb->len < size_goal || (flags & MSG_OOB)) + if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { @@ -1042,7 +1269,8 @@ wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: if (copied) - tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); + tcp_push(sk, flags & ~MSG_MORE, mss_now, + TCP_NAGLE_PUSH, size_goal); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) goto do_error; @@ -1053,10 +1281,10 @@ wait_for_memory: out: if (copied) - tcp_push(sk, flags, mss_now, tp->nonagle); - TCP_CHECK_TIMER(sk); + tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); +out_nopush: release_sock(sk); - return copied; + return copied + copied_syn; do_fault: if (!skb->len) { @@ -1069,14 +1297,14 @@ do_fault: } do_error: - if (copied) + if (copied + copied_syn) goto out; out_err: err = sk_stream_error(sk, flags, err); - TCP_CHECK_TIMER(sk); release_sock(sk); return err; } +EXPORT_SYMBOL(tcp_sendmsg); /* * Handle reading urgent data. BSD has very simple semantics for @@ -1127,6 +1355,24 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) return -EAGAIN; } +static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) +{ + struct sk_buff *skb; + int copied = 0, err = 0; + + /* XXX -- need to support SO_PEEK_OFF */ + + skb_queue_walk(&sk->sk_write_queue, skb) { + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len); + if (err) + break; + + copied += skb->len; + } + + return err ?: copied; +} + /* Clean up the receive buffer for full frames taken by the user, * then send an ACK if necessary. COPIED is the number of bytes * tcp_recvmsg has given to the user so far, it speeds up the @@ -1136,13 +1382,13 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) void tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); - int time_to_ack = 0; + bool time_to_ack = false; -#if TCP_DEBUG struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); - WARN_ON(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq)); -#endif + WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), + "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", + tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); if (inet_csk_ack_scheduled(sk)) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1162,7 +1408,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && !icsk->icsk_ack.pingpong)) && !atomic_read(&sk->sk_rmem_alloc))) - time_to_ack = 1; + time_to_ack = true; } /* We send an ACK if we can now advertise a non-zero window @@ -1184,7 +1430,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) * "Lots" means "at least twice" here. */ if (new_window && new_window >= 2 * rcv_window_now) - time_to_ack = 1; + time_to_ack = true; } } if (time_to_ack) @@ -1209,12 +1455,45 @@ static void tcp_prequeue_process(struct sock *sk) tp->ucopy.memory = 0; } -static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) +#ifdef CONFIG_NET_DMA +static void tcp_service_net_dma(struct sock *sk, bool wait) +{ + dma_cookie_t done, used; + dma_cookie_t last_issued; + struct tcp_sock *tp = tcp_sk(sk); + + if (!tp->ucopy.dma_chan) + return; + + last_issued = tp->ucopy.dma_cookie; + dma_async_issue_pending(tp->ucopy.dma_chan); + + do { + if (dma_async_is_tx_complete(tp->ucopy.dma_chan, + last_issued, &done, + &used) == DMA_COMPLETE) { + /* Safe to free early-copied skbs now */ + __skb_queue_purge(&sk->sk_async_wait_queue); + break; + } else { + struct sk_buff *skb; + while ((skb = skb_peek(&sk->sk_async_wait_queue)) && + (dma_async_is_complete(skb->dma_cookie, done, + used) == DMA_COMPLETE)) { + __skb_dequeue(&sk->sk_async_wait_queue); + kfree_skb(skb); + } + } + } while (wait); +} +#endif + +static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; u32 offset; - skb_queue_walk(&sk->sk_receive_queue, skb) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { offset = seq - TCP_SKB_CB(skb)->seq; if (tcp_hdr(skb)->syn) offset--; @@ -1222,6 +1501,11 @@ static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) *off = offset; return skb; } + /* This looks weird, but this can happen if TCP collapsing + * splitted a fat GRO packet, while we released socket lock + * in skb_splice_bits() + */ + sk_eat_skb(sk, skb, false); } return NULL; } @@ -1263,7 +1547,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, break; } used = recv_actor(desc, skb, offset, len); - if (used < 0) { + if (used <= 0) { if (!copied) copied = used; break; @@ -1272,34 +1556,42 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, copied += used; offset += used; } - /* - * If recv_actor drops the lock (e.g. TCP splice + /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it * while aggregating skbs from the socket queue. */ - skb = tcp_recv_skb(sk, seq-1, &offset); - if (!skb || (offset+1 != skb->len)) + skb = tcp_recv_skb(sk, seq - 1, &offset); + if (!skb) break; + /* TCP coalescing might have appended data to the skb. + * Try to splice more frags + */ + if (offset + 1 != skb->len) + continue; } if (tcp_hdr(skb)->fin) { - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); ++seq; break; } - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); if (!desc->count) break; + tp->copied_seq = seq; } tp->copied_seq = seq; tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ - if (copied > 0) + if (copied > 0) { + tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); + } return copied; } +EXPORT_SYMBOL(tcp_read_sock); /* * This routine copies from a sock struct into the user buffer. @@ -1321,13 +1613,15 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int target; /* Read at least this many bytes */ long timeo; struct task_struct *user_recv = NULL; - int copied_early = 0; + bool copied_early = false; struct sk_buff *skb; u32 urg_hole = 0; - lock_sock(sk); + if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) && + (sk->sk_state == TCP_ESTABLISHED)) + sk_busy_loop(sk, nonblock); - TCP_CHECK_TIMER(sk); + lock_sock(sk); err = -ENOTCONN; if (sk->sk_state == TCP_LISTEN) @@ -1339,6 +1633,21 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto recv_urg; + if (unlikely(tp->repair)) { + err = -EPERM; + if (!(flags & MSG_PEEK)) + goto out; + + if (tp->repair_queue == TCP_SEND_QUEUE) + goto recv_sndq; + + err = -EINVAL; + if (tp->repair_queue == TCP_NO_QUEUE) + goto out; + + /* 'common' recv queue MSG_PEEK-ing */ + } + seq = &tp->copied_seq; if (flags & MSG_PEEK) { peek_seq = tp->copied_seq; @@ -1359,12 +1668,12 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if ((available < target) && (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) && !sysctl_tcp_low_latency && - dma_find_channel(DMA_MEMCPY)) { - preempt_enable_no_resched(); + net_dma_find_channel()) { + preempt_enable(); tp->ucopy.pinned_list = dma_pin_iovec_pages(msg->msg_iov, len); } else { - preempt_enable_no_resched(); + preempt_enable(); } } #endif @@ -1388,11 +1697,12 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, /* Now that we have two receive queues this * shouldn't happen. */ - if (before(*seq, TCP_SKB_CB(skb)->seq)) { - printk(KERN_INFO "recvmsg bug: copied %X " - "seq %X\n", *seq, TCP_SKB_CB(skb)->seq); + if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), + "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n", + *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, + flags)) break; - } + offset = *seq - TCP_SKB_CB(skb)->seq; if (tcp_hdr(skb)->syn) offset--; @@ -1400,7 +1710,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto found_ok_skb; if (tcp_hdr(skb)->fin) goto found_fin_ok; - WARN_ON(!(flags & MSG_PEEK)); + WARN(!(flags & MSG_PEEK), + "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n", + *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } /* Well, if we have backlog, try to process it now yet. */ @@ -1496,6 +1808,16 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, /* __ Set realtime policy in scheduler __ */ } +#ifdef CONFIG_NET_DMA + if (tp->ucopy.dma_chan) { + if (tp->rcv_wnd == 0 && + !skb_queue_empty(&sk->sk_async_wait_queue)) { + tcp_service_net_dma(sk, true); + tcp_cleanup_rbuf(sk, copied); + } else + dma_async_issue_pending(tp->ucopy.dma_chan); + } +#endif if (copied >= target) { /* Do not sleep, just process backlog. */ release_sock(sk); @@ -1504,6 +1826,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sk_wait_data(sk, &timeo); #ifdef CONFIG_NET_DMA + tcp_service_net_dma(sk, false); /* Don't block */ tp->ucopy.wakeup = 0; #endif @@ -1532,9 +1855,9 @@ do_prequeue: } if ((flags & MSG_PEEK) && (peek_seq - copied - urg_hole != tp->copied_seq)) { - if (net_ratelimit()) - printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n", - current->comm, task_pid_nr(current)); + net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", + current->comm, + task_pid_nr(current)); peek_seq = tp->copied_seq; } continue; @@ -1566,7 +1889,7 @@ do_prequeue: if (!(flags & MSG_TRUNC)) { #ifdef CONFIG_NET_DMA if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) - tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY); + tp->ucopy.dma_chan = net_dma_find_channel(); if (tp->ucopy.dma_chan) { tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec( @@ -1576,15 +1899,19 @@ do_prequeue: if (tp->ucopy.dma_cookie < 0) { - printk(KERN_ALERT "dma_cookie < 0\n"); + pr_alert("%s: dma_cookie < 0\n", + __func__); /* Exception. Bailout! */ if (!copied) copied = -EFAULT; break; } + + dma_async_issue_pending(tp->ucopy.dma_chan); + if ((offset + used) == skb->len) - copied_early = 1; + copied_early = true; } else #endif @@ -1618,7 +1945,7 @@ skip_copy: goto found_fin_ok; if (!(flags & MSG_PEEK)) { sk_eat_skb(sk, skb, copied_early); - copied_early = 0; + copied_early = false; } continue; @@ -1627,7 +1954,7 @@ skip_copy: ++*seq; if (!(flags & MSG_PEEK)) { sk_eat_skb(sk, skb, copied_early); - copied_early = 0; + copied_early = false; } break; } while (len > 0); @@ -1652,27 +1979,9 @@ skip_copy: } #ifdef CONFIG_NET_DMA - if (tp->ucopy.dma_chan) { - dma_cookie_t done, used; - - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); - - while (dma_async_memcpy_complete(tp->ucopy.dma_chan, - tp->ucopy.dma_cookie, &done, - &used) == DMA_IN_PROGRESS) { - /* do partial cleanup of sk_async_wait_queue */ - while ((skb = skb_peek(&sk->sk_async_wait_queue)) && - (dma_async_is_complete(skb->dma_cookie, done, - used) == DMA_SUCCESS)) { - __skb_dequeue(&sk->sk_async_wait_queue); - kfree_skb(skb); - } - } + tcp_service_net_dma(sk, true); /* Wait for queue to drain */ + tp->ucopy.dma_chan = NULL; - /* Safe to free early-copied skbs now */ - __skb_queue_purge(&sk->sk_async_wait_queue); - tp->ucopy.dma_chan = NULL; - } if (tp->ucopy.pinned_list) { dma_unpin_iovec_pages(tp->ucopy.pinned_list); tp->ucopy.pinned_list = NULL; @@ -1686,19 +1995,22 @@ skip_copy: /* Clean up data we have read: This will do ACK frames. */ tcp_cleanup_rbuf(sk, copied); - TCP_CHECK_TIMER(sk); release_sock(sk); return copied; out: - TCP_CHECK_TIMER(sk); release_sock(sk); return err; recv_urg: err = tcp_recv_urg(sk, msg, len, flags); goto out; + +recv_sndq: + err = tcp_peek_sndq(sk, msg, len); + goto out; } +EXPORT_SYMBOL(tcp_recvmsg); void tcp_set_state(struct sock *sk, int state) { @@ -1791,6 +2103,21 @@ void tcp_shutdown(struct sock *sk, int how) tcp_send_fin(sk); } } +EXPORT_SYMBOL(tcp_shutdown); + +bool tcp_check_oom(struct sock *sk, int shift) +{ + bool too_many_orphans, out_of_socket_memory; + + too_many_orphans = tcp_too_many_orphans(sk, shift); + out_of_socket_memory = tcp_out_of_memory(sk); + + if (too_many_orphans) + net_info_ratelimited("too many orphaned sockets\n"); + if (out_of_socket_memory) + net_info_ratelimited("out of memory -- consider tuning tcp_mem\n"); + return too_many_orphans || out_of_socket_memory; +} void tcp_close(struct sock *sk, long timeout) { @@ -1823,6 +2150,10 @@ void tcp_close(struct sock *sk, long timeout) sk_mem_reclaim(sk); + /* If socket has been already reset (e.g. in tcp_reset()) - kill it. */ + if (sk->sk_state == TCP_CLOSE) + goto adjudge_to_death; + /* As outlined in RFC 2525, section 2.17, we send a RST here because * data was lost. To witness the awful effects of the old behavior of * always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk @@ -1830,11 +2161,13 @@ void tcp_close(struct sock *sk, long timeout) * advertise a zero window, then kill -9 the FTP client, wheee... * Note: timeout is always zero in such a case. */ - if (data_was_unread) { + if (unlikely(tcp_sk(sk)->repair)) { + sk->sk_prot->disconnect(sk, 0); + } else if (data_was_unread) { /* Unread data was tossed, zap the connection. */ NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_KERNEL); + tcp_send_active_reset(sk, sk->sk_allocation); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -1864,6 +2197,10 @@ void tcp_close(struct sock *sk, long timeout) * they look as CLOSING or LAST_ACK for Linux) * Probably, I missed some more holelets. * --ANK + * XXX (TFO) - To start off we don't support SYN+ACK+FIN + * in a single packet! (May consider it later but will + * probably need API support or TCP_CORK SYN-ACK until + * data is written and socket is closed.) */ tcp_send_fin(sk); } @@ -1895,7 +2232,7 @@ adjudge_to_death: /* This is a (useful) BSD violating of the RFC. There is a * problem with TCP as specified in that the other end could * keep a socket open forever with no application left this end. - * We use a 3 minute timeout (about the same as BSD) then kill + * We use a 1 minute timeout (about the same as BSD) then kill * our end. If they send after that then tough - BUT: long enough * that we won't make the old 4*rto = almost no time - whoops * reset mistake. @@ -1926,14 +2263,8 @@ adjudge_to_death: } } if (sk->sk_state != TCP_CLOSE) { - int orphan_count = percpu_counter_read_positive( - sk->sk_prot->orphan_count); - sk_mem_reclaim(sk); - if (tcp_too_many_orphans(sk, orphan_count)) { - if (net_ratelimit()) - printk(KERN_INFO "TCP: too many of orphaned " - "sockets\n"); + if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC); NET_INC_STATS_BH(sock_net(sk), @@ -1941,8 +2272,16 @@ adjudge_to_death: } } - if (sk->sk_state == TCP_CLOSE) + if (sk->sk_state == TCP_CLOSE) { + struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + /* We could get here with a non-NULL req if the socket is + * aborted (e.g., closed with unread data) before 3WHS + * finishes. + */ + if (req != NULL) + reqsk_fastopen_remove(sk, req, false); inet_csk_destroy_sock(sk); + } /* Otherwise, socket is reprieved until protocol close. */ out: @@ -1950,10 +2289,11 @@ out: local_bh_enable(); sock_put(sk); } +EXPORT_SYMBOL(tcp_close); /* These states need RST on ABORT according to RFC793 */ -static inline int tcp_need_reset(int state) +static inline bool tcp_need_reset(int state) { return (1 << state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 | @@ -1974,6 +2314,8 @@ int tcp_disconnect(struct sock *sk, int flags) /* ABORT function of RFC793 */ if (old_state == TCP_LISTEN) { inet_csk_listen_stop(sk); + } else if (unlikely(tp->repair)) { + sk->sk_err = ECONNABORTED; } else if (tcp_need_reset(old_state) || (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) { @@ -1993,23 +2335,23 @@ int tcp_disconnect(struct sock *sk, int flags) __skb_queue_purge(&sk->sk_async_wait_queue); #endif - inet->dport = 0; + inet->inet_dport = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); - tp->srtt = 0; + tp->srtt_us = 0; if ((tp->write_seq += tp->max_window + 2) == 0) tp->write_seq = 1; icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; tp->packets_out = 0; - tp->snd_ssthresh = 0x7fffffff; + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; - tp->bytes_acked = 0; + tp->window_clamp = 0; tcp_set_ca_state(sk, TCP_CA_Open); tcp_clear_retrans(tp); inet_csk_delack_init(sk); @@ -2017,32 +2359,96 @@ int tcp_disconnect(struct sock *sk, int flags) memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); - WARN_ON(inet->num && !icsk->icsk_bind_hash); + WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); sk->sk_error_report(sk); return err; } +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) && + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED)); +} + +static int tcp_repair_options_est(struct tcp_sock *tp, + struct tcp_repair_opt __user *optbuf, unsigned int len) +{ + struct tcp_repair_opt opt; + + while (len >= sizeof(opt)) { + if (copy_from_user(&opt, optbuf, sizeof(opt))) + return -EFAULT; + + optbuf++; + len -= sizeof(opt); + + switch (opt.opt_code) { + case TCPOPT_MSS: + tp->rx_opt.mss_clamp = opt.opt_val; + break; + case TCPOPT_WINDOW: + { + u16 snd_wscale = opt.opt_val & 0xFFFF; + u16 rcv_wscale = opt.opt_val >> 16; + + if (snd_wscale > 14 || rcv_wscale > 14) + return -EFBIG; + + tp->rx_opt.snd_wscale = snd_wscale; + tp->rx_opt.rcv_wscale = rcv_wscale; + tp->rx_opt.wscale_ok = 1; + } + break; + case TCPOPT_SACK_PERM: + if (opt.opt_val != 0) + return -EINVAL; + + tp->rx_opt.sack_ok |= TCP_SACK_SEEN; + if (sysctl_tcp_fack) + tcp_enable_fack(tp); + break; + case TCPOPT_TIMESTAMP: + if (opt.opt_val != 0) + return -EINVAL; + + tp->rx_opt.tstamp_ok = 1; + break; + } + } + + return 0; +} /* * Socket option code for TCP. */ static int do_tcp_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int val; int err = 0; - /* This is a string value all the others are int's */ - if (optname == TCP_CONGESTION) { + /* These are data/string values, all the others are ints */ + switch (optname) { + case TCP_CONGESTION: { char name[TCP_CA_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_user(name, optval, - min(TCP_CA_NAME_MAX-1, optlen)); + min_t(long, TCP_CA_NAME_MAX-1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; @@ -2052,6 +2458,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, release_sock(sk); return err; } + default: + /* fallthru */ + break; + } if (optlen < sizeof(int)) return -EINVAL; @@ -2066,7 +2476,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ - if (val < 8 || val > MAX_TCP_WINDOW) { + if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) { err = -EINVAL; break; } @@ -2090,6 +2500,70 @@ static int do_tcp_setsockopt(struct sock *sk, int level, } break; + case TCP_THIN_LINEAR_TIMEOUTS: + if (val < 0 || val > 1) + err = -EINVAL; + else + tp->thin_lto = val; + break; + + case TCP_THIN_DUPACK: + if (val < 0 || val > 1) + err = -EINVAL; + else { + tp->thin_dupack = val; + if (tp->thin_dupack) + tcp_disable_early_retrans(tp); + } + break; + + case TCP_REPAIR: + if (!tcp_can_repair_sock(sk)) + err = -EPERM; + else if (val == 1) { + tp->repair = 1; + sk->sk_reuse = SK_FORCE_REUSE; + tp->repair_queue = TCP_NO_QUEUE; + } else if (val == 0) { + tp->repair = 0; + sk->sk_reuse = SK_NO_REUSE; + tcp_send_window_probe(sk); + } else + err = -EINVAL; + + break; + + case TCP_REPAIR_QUEUE: + if (!tp->repair) + err = -EPERM; + else if (val < TCP_QUEUES_NR) + tp->repair_queue = val; + else + err = -EINVAL; + break; + + case TCP_QUEUE_SEQ: + if (sk->sk_state != TCP_CLOSE) + err = -EPERM; + else if (tp->repair_queue == TCP_SEND_QUEUE) + tp->write_seq = val; + else if (tp->repair_queue == TCP_RECV_QUEUE) + tp->rcv_nxt = val; + else + err = -EINVAL; + break; + + case TCP_REPAIR_OPTIONS: + if (!tp->repair) + err = -EINVAL; + else if (sk->sk_state == TCP_ESTABLISHED) + err = tcp_repair_options_est(tp, + (struct tcp_repair_opt __user *)optval, + optlen); + else + err = -EPERM; + break; + case TCP_CORK: /* When set indicates to always queue non-full frames. * Later the user clears this option and we transmit @@ -2120,7 +2594,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { - __u32 elapsed = tcp_time_stamp - tp->rcv_tstamp; + u32 elapsed = keepalive_time_elapsed(tp); if (tp->keepalive_time > elapsed) elapsed = tp->keepalive_time - elapsed; else @@ -2158,16 +2632,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; case TCP_DEFER_ACCEPT: - icsk->icsk_accept_queue.rskq_defer_accept = 0; - if (val > 0) { - /* Translate value in seconds to number of - * retransmits */ - while (icsk->icsk_accept_queue.rskq_defer_accept < 32 && - val > ((TCP_TIMEOUT_INIT / HZ) << - icsk->icsk_accept_queue.rskq_defer_accept)) - icsk->icsk_accept_queue.rskq_defer_accept++; - icsk->icsk_accept_queue.rskq_defer_accept++; - } + /* Translate value in seconds to number of retransmits */ + icsk->icsk_accept_queue.rskq_defer_accept = + secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: @@ -2204,7 +2672,33 @@ static int do_tcp_setsockopt(struct sock *sk, int level, err = tp->af_specific->md5_parse(sk, optval, optlen); break; #endif + case TCP_USER_TIMEOUT: + /* Cap the max timeout in ms TCP will retry/retrans + * before giving up and aborting (ETIMEDOUT) a connection. + */ + if (val < 0) + err = -EINVAL; + else + icsk->icsk_user_timeout = msecs_to_jiffies(val); + break; + case TCP_FASTOPEN: + if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | + TCPF_LISTEN))) + err = fastopen_init_queue(sk, val); + else + err = -EINVAL; + break; + case TCP_TIMESTAMP: + if (!tp->repair) + err = -EPERM; + else + tp->tsoffset = val - tcp_time_stamp; + break; + case TCP_NOTSENT_LOWAT: + tp->notsent_lowat = val; + sk->sk_write_space(sk); + break; default: err = -ENOPROTOOPT; break; @@ -2215,33 +2709,33 @@ static int do_tcp_setsockopt(struct sock *sk, int level, } int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen) + unsigned int optlen) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) return icsk->icsk_af_ops->setsockopt(sk, level, optname, optval, optlen); return do_tcp_setsockopt(sk, level, optname, optval, optlen); } +EXPORT_SYMBOL(tcp_setsockopt); #ifdef CONFIG_COMPAT int compat_tcp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_TCP) return inet_csk_compat_setsockopt(sk, level, optname, optval, optlen); return do_tcp_setsockopt(sk, level, optname, optval, optlen); } - EXPORT_SYMBOL(compat_tcp_setsockopt); #endif /* Return information about state of tcp endpoint in API format. */ -void tcp_get_info(struct sock *sk, struct tcp_info *info) +void tcp_get_info(const struct sock *sk, struct tcp_info *info) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; @@ -2263,8 +2757,12 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale; } - if (tp->ecn_flags&TCP_ECN_OK) + if (tp->ecn_flags & TCP_ECN_OK) info->tcpi_options |= TCPI_OPT_ECN; + if (tp->ecn_flags & TCP_ECN_SEEN) + info->tcpi_options |= TCPI_OPT_ECN_SEEN; + if (tp->syn_data_acked) + info->tcpi_options |= TCPI_OPT_SYN_DATA; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato); @@ -2288,8 +2786,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_pmtu = icsk->icsk_pmtu_cookie; info->tcpi_rcv_ssthresh = tp->rcv_ssthresh; - info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3; - info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2; + info->tcpi_rtt = tp->srtt_us >> 3; + info->tcpi_rttvar = tp->mdev_us >> 2; info->tcpi_snd_ssthresh = tp->snd_ssthresh; info->tcpi_snd_cwnd = tp->snd_cwnd; info->tcpi_advmss = tp->advmss; @@ -2299,8 +2797,12 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_rcv_space = tp->rcvq_space.space; info->tcpi_total_retrans = tp->total_retrans; -} + info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ? + sk->sk_pacing_rate : ~0ULL; + info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ? + sk->sk_max_pacing_rate : ~0ULL; +} EXPORT_SYMBOL_GPL(tcp_get_info); static int do_tcp_getsockopt(struct sock *sk, int level, @@ -2323,6 +2825,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = tp->mss_cache; if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; + if (tp->repair) + val = tp->rx_opt.mss_clamp; break; case TCP_NODELAY: val = !!(tp->nonagle&TCP_NAGLE_OFF); @@ -2331,13 +2835,13 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = !!(tp->nonagle&TCP_NAGLE_CORK); break; case TCP_KEEPIDLE: - val = (tp->keepalive_time ? : sysctl_tcp_keepalive_time) / HZ; + val = keepalive_time_when(tp) / HZ; break; case TCP_KEEPINTVL: - val = (tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl) / HZ; + val = keepalive_intvl_when(tp) / HZ; break; case TCP_KEEPCNT: - val = tp->keepalive_probes ? : sysctl_tcp_keepalive_probes; + val = keepalive_probes(tp); break; case TCP_SYNCNT: val = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; @@ -2348,8 +2852,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = (val ? : sysctl_tcp_fin_timeout) / HZ; break; case TCP_DEFER_ACCEPT: - val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 : - ((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1)); + val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, + TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; @@ -2382,6 +2886,51 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (copy_to_user(optval, icsk->icsk_ca_ops->name, len)) return -EFAULT; return 0; + + case TCP_THIN_LINEAR_TIMEOUTS: + val = tp->thin_lto; + break; + case TCP_THIN_DUPACK: + val = tp->thin_dupack; + break; + + case TCP_REPAIR: + val = tp->repair; + break; + + case TCP_REPAIR_QUEUE: + if (tp->repair) + val = tp->repair_queue; + else + return -EINVAL; + break; + + case TCP_QUEUE_SEQ: + if (tp->repair_queue == TCP_SEND_QUEUE) + val = tp->write_seq; + else if (tp->repair_queue == TCP_RECV_QUEUE) + val = tp->rcv_nxt; + else + return -EINVAL; + break; + + case TCP_USER_TIMEOUT: + val = jiffies_to_msecs(icsk->icsk_user_timeout); + break; + + case TCP_FASTOPEN: + if (icsk->icsk_accept_queue.fastopenq != NULL) + val = icsk->icsk_accept_queue.fastopenq->max_qlen; + else + val = 0; + break; + + case TCP_TIMESTAMP: + val = tcp_time_stamp + tp->tsoffset; + break; + case TCP_NOTSENT_LOWAT: + val = tp->notsent_lowat; + break; default: return -ENOPROTOOPT; } @@ -2403,6 +2952,7 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, optval, optlen); return do_tcp_getsockopt(sk, level, optname, optval, optlen); } +EXPORT_SYMBOL(tcp_getsockopt); #ifdef CONFIG_COMPAT int compat_tcp_getsockopt(struct sock *sk, int level, int optname, @@ -2413,366 +2963,119 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, optval, optlen); return do_tcp_getsockopt(sk, level, optname, optval, optlen); } - EXPORT_SYMBOL(compat_tcp_getsockopt); #endif -struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features) -{ - struct sk_buff *segs = ERR_PTR(-EINVAL); - struct tcphdr *th; - unsigned thlen; - unsigned int seq; - __be32 delta; - unsigned int oldlen; - unsigned int mss; - - if (!pskb_may_pull(skb, sizeof(*th))) - goto out; - - th = tcp_hdr(skb); - thlen = th->doff * 4; - if (thlen < sizeof(*th)) - goto out; - - if (!pskb_may_pull(skb, thlen)) - goto out; - - oldlen = (u16)~skb->len; - __skb_pull(skb, thlen); - - mss = skb_shinfo(skb)->gso_size; - if (unlikely(skb->len <= mss)) - goto out; - - if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { - /* Packet is from an untrusted source, reset gso_segs. */ - int type = skb_shinfo(skb)->gso_type; - - if (unlikely(type & - ~(SKB_GSO_TCPV4 | - SKB_GSO_DODGY | - SKB_GSO_TCP_ECN | - SKB_GSO_TCPV6 | - 0) || - !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) - goto out; - - skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); - - segs = NULL; - goto out; - } - - segs = skb_segment(skb, features); - if (IS_ERR(segs)) - goto out; - - delta = htonl(oldlen + (thlen + mss)); - - skb = segs; - th = tcp_hdr(skb); - seq = ntohl(th->seq); - - do { - th->fin = th->psh = 0; - - th->check = ~csum_fold((__force __wsum)((__force u32)th->check + - (__force u32)delta)); - if (skb->ip_summed != CHECKSUM_PARTIAL) - th->check = - csum_fold(csum_partial(skb_transport_header(skb), - thlen, skb->csum)); - - seq += mss; - skb = skb->next; - th = tcp_hdr(skb); - - th->seq = htonl(seq); - th->cwr = 0; - } while (skb->next); - - delta = htonl(oldlen + (skb->tail - skb->transport_header) + - skb->data_len); - th->check = ~csum_fold((__force __wsum)((__force u32)th->check + - (__force u32)delta)); - if (skb->ip_summed != CHECKSUM_PARTIAL) - th->check = csum_fold(csum_partial(skb_transport_header(skb), - thlen, skb->csum)); - -out: - return segs; -} -EXPORT_SYMBOL(tcp_tso_segment); - -struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) -{ - struct sk_buff **pp = NULL; - struct sk_buff *p; - struct tcphdr *th; - struct tcphdr *th2; - unsigned int len; - unsigned int thlen; - unsigned int flags; - unsigned int mss = 1; - unsigned int hlen; - unsigned int off; - int flush = 1; - int i; - - off = skb_gro_offset(skb); - hlen = off + sizeof(*th); - th = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) { - th = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!th)) - goto out; - } - - thlen = th->doff * 4; - if (thlen < sizeof(*th)) - goto out; - - hlen = off + thlen; - if (skb_gro_header_hard(skb, hlen)) { - th = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!th)) - goto out; - } - - skb_gro_pull(skb, thlen); - - len = skb_gro_len(skb); - flags = tcp_flag_word(th); - - for (; (p = *head); head = &p->next) { - if (!NAPI_GRO_CB(p)->same_flow) - continue; - - th2 = tcp_hdr(p); - - if (*(u32 *)&th->source ^ *(u32 *)&th2->source) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - - goto found; - } - - goto out_check_final; - -found: - flush = NAPI_GRO_CB(p)->flush; - flush |= flags & TCP_FLAG_CWR; - flush |= (flags ^ tcp_flag_word(th2)) & - ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH); - flush |= th->ack_seq ^ th2->ack_seq; - for (i = sizeof(*th); i < thlen; i += 4) - flush |= *(u32 *)((u8 *)th + i) ^ - *(u32 *)((u8 *)th2 + i); - - mss = skb_shinfo(p)->gso_size; - - flush |= (len - 1) >= mss; - flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); - - if (flush || skb_gro_receive(head, skb)) { - mss = 1; - goto out_check_final; - } - - p = *head; - th2 = tcp_hdr(p); - tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH); - -out_check_final: - flush = len < mss; - flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST | - TCP_FLAG_SYN | TCP_FLAG_FIN); - - if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) - pp = head; - -out: - NAPI_GRO_CB(skb)->flush |= flush; - - return pp; -} -EXPORT_SYMBOL(tcp_gro_receive); - -int tcp_gro_complete(struct sk_buff *skb) -{ - struct tcphdr *th = tcp_hdr(skb); - - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - skb->ip_summed = CHECKSUM_PARTIAL; - - skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - - if (th->cwr) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; - - return 0; -} -EXPORT_SYMBOL(tcp_gro_complete); - #ifdef CONFIG_TCP_MD5SIG -static unsigned long tcp_md5sig_users; -static struct tcp_md5sig_pool **tcp_md5sig_pool; -static DEFINE_SPINLOCK(tcp_md5sig_pool_lock); +static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly; +static DEFINE_MUTEX(tcp_md5sig_mutex); -static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool **pool) +static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool) { int cpu; - for_each_possible_cpu(cpu) { - struct tcp_md5sig_pool *p = *per_cpu_ptr(pool, cpu); - if (p) { - if (p->md5_desc.tfm) - crypto_free_hash(p->md5_desc.tfm); - kfree(p); - p = NULL; - } - } - free_percpu(pool); -} -void tcp_free_md5sig_pool(void) -{ - struct tcp_md5sig_pool **pool = NULL; + for_each_possible_cpu(cpu) { + struct tcp_md5sig_pool *p = per_cpu_ptr(pool, cpu); - spin_lock_bh(&tcp_md5sig_pool_lock); - if (--tcp_md5sig_users == 0) { - pool = tcp_md5sig_pool; - tcp_md5sig_pool = NULL; + if (p->md5_desc.tfm) + crypto_free_hash(p->md5_desc.tfm); } - spin_unlock_bh(&tcp_md5sig_pool_lock); - if (pool) - __tcp_free_md5sig_pool(pool); + free_percpu(pool); } -EXPORT_SYMBOL(tcp_free_md5sig_pool); - -static struct tcp_md5sig_pool **__tcp_alloc_md5sig_pool(void) +static void __tcp_alloc_md5sig_pool(void) { int cpu; - struct tcp_md5sig_pool **pool; + struct tcp_md5sig_pool __percpu *pool; - pool = alloc_percpu(struct tcp_md5sig_pool *); + pool = alloc_percpu(struct tcp_md5sig_pool); if (!pool) - return NULL; + return; for_each_possible_cpu(cpu) { - struct tcp_md5sig_pool *p; struct crypto_hash *hash; - p = kzalloc(sizeof(*p), GFP_KERNEL); - if (!p) - goto out_free; - *per_cpu_ptr(pool, cpu) = p; - hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (!hash || IS_ERR(hash)) + if (IS_ERR_OR_NULL(hash)) goto out_free; - p->md5_desc.tfm = hash; + per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash; } - return pool; + /* before setting tcp_md5sig_pool, we must commit all writes + * to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool() + */ + smp_wmb(); + tcp_md5sig_pool = pool; + return; out_free: __tcp_free_md5sig_pool(pool); - return NULL; } -struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(void) +bool tcp_alloc_md5sig_pool(void) { - struct tcp_md5sig_pool **pool; - int alloc = 0; - -retry: - spin_lock_bh(&tcp_md5sig_pool_lock); - pool = tcp_md5sig_pool; - if (tcp_md5sig_users++ == 0) { - alloc = 1; - spin_unlock_bh(&tcp_md5sig_pool_lock); - } else if (!pool) { - tcp_md5sig_users--; - spin_unlock_bh(&tcp_md5sig_pool_lock); - cpu_relax(); - goto retry; - } else - spin_unlock_bh(&tcp_md5sig_pool_lock); - - if (alloc) { - /* we cannot hold spinlock here because this may sleep. */ - struct tcp_md5sig_pool **p = __tcp_alloc_md5sig_pool(); - spin_lock_bh(&tcp_md5sig_pool_lock); - if (!p) { - tcp_md5sig_users--; - spin_unlock_bh(&tcp_md5sig_pool_lock); - return NULL; - } - pool = tcp_md5sig_pool; - if (pool) { - /* oops, it has already been assigned. */ - spin_unlock_bh(&tcp_md5sig_pool_lock); - __tcp_free_md5sig_pool(p); - } else { - tcp_md5sig_pool = pool = p; - spin_unlock_bh(&tcp_md5sig_pool_lock); - } + if (unlikely(!tcp_md5sig_pool)) { + mutex_lock(&tcp_md5sig_mutex); + + if (!tcp_md5sig_pool) + __tcp_alloc_md5sig_pool(); + + mutex_unlock(&tcp_md5sig_mutex); } - return pool; + return tcp_md5sig_pool != NULL; } - EXPORT_SYMBOL(tcp_alloc_md5sig_pool); -struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu) + +/** + * tcp_get_md5sig_pool - get md5sig_pool for this user + * + * We use percpu structure, so if we succeed, we exit with preemption + * and BH disabled, to make sure another thread or softirq handling + * wont try to get same context. + */ +struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) { - struct tcp_md5sig_pool **p; - spin_lock_bh(&tcp_md5sig_pool_lock); - p = tcp_md5sig_pool; - if (p) - tcp_md5sig_users++; - spin_unlock_bh(&tcp_md5sig_pool_lock); - return (p ? *per_cpu_ptr(p, cpu) : NULL); -} + struct tcp_md5sig_pool __percpu *p; -EXPORT_SYMBOL(__tcp_get_md5sig_pool); + local_bh_disable(); + p = ACCESS_ONCE(tcp_md5sig_pool); + if (p) + return __this_cpu_ptr(p); -void __tcp_put_md5sig_pool(void) -{ - tcp_free_md5sig_pool(); + local_bh_enable(); + return NULL; } - -EXPORT_SYMBOL(__tcp_put_md5sig_pool); +EXPORT_SYMBOL(tcp_get_md5sig_pool); int tcp_md5_hash_header(struct tcp_md5sig_pool *hp, - struct tcphdr *th) + const struct tcphdr *th) { struct scatterlist sg; + struct tcphdr hdr; int err; - __sum16 old_checksum = th->check; - th->check = 0; + /* We are not allowed to change tcphdr, make a local copy */ + memcpy(&hdr, th, sizeof(hdr)); + hdr.check = 0; + /* options aren't included in the hash */ - sg_init_one(&sg, th, sizeof(struct tcphdr)); - err = crypto_hash_update(&hp->md5_desc, &sg, sizeof(struct tcphdr)); - th->check = old_checksum; + sg_init_one(&sg, &hdr, sizeof(hdr)); + err = crypto_hash_update(&hp->md5_desc, &sg, sizeof(hdr)); return err; } - EXPORT_SYMBOL(tcp_md5_hash_header); int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, - struct sk_buff *skb, unsigned header_len) + const struct sk_buff *skb, unsigned int header_len) { struct scatterlist sg; const struct tcphdr *tp = tcp_hdr(skb); struct hash_desc *desc = &hp->md5_desc; - unsigned i; - const unsigned head_data_len = skb_headlen(skb) > header_len ? - skb_headlen(skb) - header_len : 0; + unsigned int i; + const unsigned int head_data_len = skb_headlen(skb) > header_len ? + skb_headlen(skb) - header_len : 0; const struct skb_shared_info *shi = skb_shinfo(skb); + struct sk_buff *frag_iter; sg_init_table(&sg, 1); @@ -2782,35 +3085,45 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, for (i = 0; i < shi->nr_frags; ++i) { const struct skb_frag_struct *f = &shi->frags[i]; - sg_set_page(&sg, f->page, f->size, f->page_offset); - if (crypto_hash_update(desc, &sg, f->size)) + unsigned int offset = f->page_offset; + struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT); + + sg_set_page(&sg, page, skb_frag_size(f), + offset_in_page(offset)); + if (crypto_hash_update(desc, &sg, skb_frag_size(f))) return 1; } + skb_walk_frags(skb, frag_iter) + if (tcp_md5_hash_skb_data(hp, frag_iter, 0)) + return 1; + return 0; } - EXPORT_SYMBOL(tcp_md5_hash_skb_data); -int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, struct tcp_md5sig_key *key) +int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key) { struct scatterlist sg; sg_init_one(&sg, key->key, key->keylen); return crypto_hash_update(&hp->md5_desc, &sg, key->keylen); } - EXPORT_SYMBOL(tcp_md5_hash_key); #endif void tcp_done(struct sock *sk) { + struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS); tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); + if (req != NULL) + reqsk_fastopen_remove(sk, req, false); sk->sk_shutdown = SHUTDOWN_MASK; @@ -2826,18 +3139,34 @@ extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; static int __init set_thash_entries(char *str) { + ssize_t ret; + if (!str) return 0; - thash_entries = simple_strtoul(str, &str, 0); + + ret = kstrtoul(str, 0, &thash_entries); + if (ret) + return 0; + return 1; } __setup("thash_entries=", set_thash_entries); +static void tcp_init_mem(void) +{ + unsigned long limit = nr_free_buffer_pages() / 8; + 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; +} + void __init tcp_init(void) { struct sk_buff *skb = NULL; - unsigned long nr_pages, limit; - int order, i, max_share; + unsigned long limit; + int max_rshare, max_wshare, cnt; + unsigned int i; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -2857,92 +3186,60 @@ void __init tcp_init(void) alloc_large_system_hash("TCP established", sizeof(struct inet_ehash_bucket), thash_entries, - (num_physpages >= 128 * 1024) ? - 13 : 15, + 17, /* one slot per 128 KB of memory */ 0, - &tcp_hashinfo.ehash_size, NULL, + &tcp_hashinfo.ehash_mask, + 0, thash_entries ? 0 : 512 * 1024); - tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size; - for (i = 0; i < tcp_hashinfo.ehash_size; i++) { + for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); - INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].twchain, i); - } + if (inet_ehash_locks_alloc(&tcp_hashinfo)) panic("TCP: failed to alloc ehash_locks"); tcp_hashinfo.bhash = alloc_large_system_hash("TCP bind", sizeof(struct inet_bind_hashbucket), - tcp_hashinfo.ehash_size, - (num_physpages >= 128 * 1024) ? - 13 : 15, + tcp_hashinfo.ehash_mask + 1, + 17, /* one slot per 128 KB of memory */ 0, &tcp_hashinfo.bhash_size, NULL, + 0, 64 * 1024); - tcp_hashinfo.bhash_size = 1 << tcp_hashinfo.bhash_size; + tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); } - /* Try to be a bit smarter and adjust defaults depending - * on available memory. - */ - for (order = 0; ((1 << order) << PAGE_SHIFT) < - (tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket)); - order++) - ; - if (order >= 4) { - tcp_death_row.sysctl_max_tw_buckets = 180000; - sysctl_tcp_max_orphans = 4096 << (order - 4); - sysctl_max_syn_backlog = 1024; - } else if (order < 3) { - tcp_death_row.sysctl_max_tw_buckets >>= (3 - order); - sysctl_tcp_max_orphans >>= (3 - order); - sysctl_max_syn_backlog = 128; - } - /* Set the pressure threshold to be a fraction of global memory that - * is up to 1/2 at 256 MB, decreasing toward zero with the amount of - * memory, with a floor of 128 pages. - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); - 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; + cnt = tcp_hashinfo.ehash_mask + 1; + + tcp_death_row.sysctl_max_tw_buckets = cnt / 2; + sysctl_tcp_max_orphans = cnt / 2; + sysctl_max_syn_backlog = max(128, cnt / 256); + tcp_init_mem(); /* Set per-socket limits to no more than 1/128 the pressure threshold */ - limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7); - max_share = min(4UL*1024*1024, limit); + limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); + max_wshare = min(4UL*1024*1024, limit); + max_rshare = min(6UL*1024*1024, limit); sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; sysctl_tcp_wmem[1] = 16*1024; - sysctl_tcp_wmem[2] = max(64*1024, max_share); + sysctl_tcp_wmem[2] = max(64*1024, max_wshare); sysctl_tcp_rmem[0] = SK_MEM_QUANTUM; sysctl_tcp_rmem[1] = 87380; - sysctl_tcp_rmem[2] = max(87380, max_share); + sysctl_tcp_rmem[2] = max(87380, max_rshare); + + pr_info("Hash tables configured (established %u bind %u)\n", + tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); - printk(KERN_INFO "TCP: Hash tables configured " - "(established %d bind %d)\n", - tcp_hashinfo.ehash_size, tcp_hashinfo.bhash_size); + tcp_metrics_init(); tcp_register_congestion_control(&tcp_reno); -} -EXPORT_SYMBOL(tcp_close); -EXPORT_SYMBOL(tcp_disconnect); -EXPORT_SYMBOL(tcp_getsockopt); -EXPORT_SYMBOL(tcp_ioctl); -EXPORT_SYMBOL(tcp_poll); -EXPORT_SYMBOL(tcp_read_sock); -EXPORT_SYMBOL(tcp_recvmsg); -EXPORT_SYMBOL(tcp_sendmsg); -EXPORT_SYMBOL(tcp_splice_read); -EXPORT_SYMBOL(tcp_sendpage); -EXPORT_SYMBOL(tcp_setsockopt); -EXPORT_SYMBOL(tcp_shutdown); + tcp_tasklet_init(); +} |