diff options
Diffstat (limited to 'net/ipv4/tcp.c')
| -rw-r--r-- | net/ipv4/tcp.c | 146 |
1 files changed, 145 insertions, 1 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9ce1c726185e..dfd090ea54ad 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1701,6 +1701,144 @@ int tcp_peek_len(struct socket *sock) } EXPORT_SYMBOL(tcp_peek_len); +/* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ +int tcp_set_rcvlowat(struct sock *sk, int val) +{ + sk->sk_rcvlowat = val ? : 1; + + /* Check if we need to signal EPOLLIN right now */ + tcp_data_ready(sk); + + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + return 0; + + /* val comes from user space and might be close to INT_MAX */ + val <<= 1; + if (val < 0) + val = INT_MAX; + + val = min(val, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); + if (val > sk->sk_rcvbuf) { + sk->sk_rcvbuf = val; + tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); + } + return 0; +} +EXPORT_SYMBOL(tcp_set_rcvlowat); + +/* When user wants to mmap X pages, we first need to perform the mapping + * before freeing any skbs in receive queue, otherwise user would be unable + * to fallback to standard recvmsg(). This happens if some data in the + * requested block is not exactly fitting in a page. + * + * We only support order-0 pages for the moment. + * mmap() on TCP is very strict, there is no point + * trying to accommodate with pathological layouts. + */ +int tcp_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma) +{ + unsigned long size = vma->vm_end - vma->vm_start; + unsigned int nr_pages = size >> PAGE_SHIFT; + struct page **pages_array = NULL; + u32 seq, len, offset, nr = 0; + struct sock *sk = sock->sk; + const skb_frag_t *frags; + struct tcp_sock *tp; + struct sk_buff *skb; + int ret; + + if (vma->vm_pgoff || !nr_pages) + return -EINVAL; + + if (vma->vm_flags & VM_WRITE) + return -EPERM; + /* TODO: Maybe the following is not needed if pages are COW */ + vma->vm_flags &= ~VM_MAYWRITE; + + lock_sock(sk); + + ret = -ENOTCONN; + if (sk->sk_state == TCP_LISTEN) + goto out; + + sock_rps_record_flow(sk); + + if (tcp_inq(sk) < size) { + ret = sock_flag(sk, SOCK_DONE) ? -EIO : -EAGAIN; + goto out; + } + tp = tcp_sk(sk); + seq = tp->copied_seq; + /* Abort if urgent data is in the area */ + if (unlikely(tp->urg_data)) { + u32 urg_offset = tp->urg_seq - seq; + + ret = -EINVAL; + if (urg_offset < size) + goto out; + } + ret = -ENOMEM; + pages_array = kvmalloc_array(nr_pages, sizeof(struct page *), + GFP_KERNEL); + if (!pages_array) + goto out; + skb = tcp_recv_skb(sk, seq, &offset); + ret = -EINVAL; +skb_start: + /* We do not support anything not in page frags */ + offset -= skb_headlen(skb); + if ((int)offset < 0) + goto out; + if (skb_has_frag_list(skb)) + goto out; + len = skb->data_len - offset; + frags = skb_shinfo(skb)->frags; + while (offset) { + if (frags->size > offset) + goto out; + offset -= frags->size; + frags++; + } + while (nr < nr_pages) { + if (len) { + if (len < PAGE_SIZE) + goto out; + if (frags->size != PAGE_SIZE || frags->page_offset) + goto out; + pages_array[nr++] = skb_frag_page(frags); + frags++; + len -= PAGE_SIZE; + seq += PAGE_SIZE; + continue; + } + skb = skb->next; + offset = seq - TCP_SKB_CB(skb)->seq; + goto skb_start; + } + /* OK, we have a full set of pages ready to be inserted into vma */ + for (nr = 0; nr < nr_pages; nr++) { + ret = vm_insert_page(vma, vma->vm_start + (nr << PAGE_SHIFT), + pages_array[nr]); + if (ret) + goto out; + } + /* operation is complete, we can 'consume' all skbs */ + tp->copied_seq = seq; + tcp_rcv_space_adjust(sk); + + /* Clean up data we have read: This will do ACK frames. */ + tcp_recv_skb(sk, seq, &offset); + tcp_cleanup_rbuf(sk, size); + + ret = 0; +out: + release_sock(sk); + kvfree(pages_array); + return ret; +} +EXPORT_SYMBOL(tcp_mmap); + static void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping *tss) { @@ -2421,6 +2559,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; + tp->delivered_ce = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); @@ -3030,6 +3169,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) rate64 = tcp_compute_delivery_rate(tp); if (rate64) info->tcpi_delivery_rate = rate64; + info->tcpi_delivered = tp->delivered; + info->tcpi_delivered_ce = tp->delivered_ce; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -3043,7 +3184,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) u32 rate; stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) + - 5 * nla_total_size(sizeof(u32)) + + 7 * nla_total_size(sizeof(u32)) + 3 * nla_total_size(sizeof(u8)), GFP_ATOMIC); if (!stats) return NULL; @@ -3074,9 +3215,12 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); + nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); + nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce); nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); + return stats; } |