struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- __skb_queue_head_init(&tp->out_of_order_queue);
+ tp->out_of_order_queue = RB_ROOT;
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);
- tp->rtt_min[0].rtt = ~0U;
+ minmax_reset(&tp->rtt_min, tcp_time_stamp, ~0U);
/* So many TCP implementations out there (incorrectly) count the
* initial SYN frame in their delayed-ACK and congestion control
*/
tp->snd_cwnd = TCP_INIT_CWND;
+ /* There's a bubble in the pipe until at least the first ACK. */
+ tp->app_limited = ~0U;
+
/* See draft-stevens-tcpca-spec-01 for discussion of the
* initialization of these values.
*/
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
local_bh_disable();
- if (mem_cgroup_sockets_enabled)
- sock_update_memcg(sk);
sk_sockets_allocated_inc(sk);
local_bh_enable();
}
int ret;
ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe,
- min(rd_desc->count, len), tss->flags,
- skb_socket_splice);
+ min(rd_desc->count, len), tss->flags);
if (ret > 0)
rd_desc->count -= ret;
return ret;
flags);
lock_sock(sk);
+
+ tcp_rate_check_app_limited(sk); /* is sending application-limited? */
+
res = do_tcp_sendpages(sk, page, offset, size, flags);
release_sock(sk);
return res;
}
EXPORT_SYMBOL(tcp_sendpage);
-static inline int select_size(const struct sock *sk, bool sg)
+/* Do not bother using a page frag for very small frames.
+ * But use this heuristic only for the first skb in write queue.
+ *
+ * Having no payload in skb->head allows better SACK shifting
+ * in tcp_shift_skb_data(), reducing sack/rack overhead, because
+ * write queue has less skbs.
+ * Each skb can hold up to MAX_SKB_FRAGS * 32Kbytes, or ~0.5 MB.
+ * This also speeds up tso_fragment(), since it wont fallback
+ * to tcp_fragment().
+ */
+static int linear_payload_sz(bool first_skb)
+{
+ if (first_skb)
+ return SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER);
+ return 0;
+}
+
+static int select_size(const struct sock *sk, bool sg, bool first_skb)
{
const struct tcp_sock *tp = tcp_sk(sk);
int tmp = tp->mss_cache;
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);
+ tmp = linear_payload_sz(first_skb);
} else {
int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
+ tcp_rate_check_app_limited(sk); /* is sending application-limited? */
+
/* 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 (copy <= 0 || !tcp_skb_can_collapse_to(skb)) {
+ bool first_skb;
+
new_segment:
/* Allocate new segment. If the interface is SG,
* allocate skb fitting to single page.
process_backlog = false;
goto restart;
}
+ first_skb = skb_queue_empty(&sk->sk_write_queue);
skb = sk_stream_alloc_skb(sk,
- select_size(sk, sg),
+ select_size(sk, sg, first_skb),
sk->sk_allocation,
- skb_queue_empty(&sk->sk_write_queue));
+ first_skb);
if (!skb)
goto wait_for_memory;
}
EXPORT_SYMBOL(tcp_read_sock);
+int tcp_peek_len(struct socket *sock)
+{
+ return tcp_inq(sock->sk);
+}
+EXPORT_SYMBOL(tcp_peek_len);
+
/*
* This routine copies from a sock struct into the user buffer.
*
tcp_clear_xmit_timers(sk);
__skb_queue_purge(&sk->sk_receive_queue);
tcp_write_queue_purge(sk);
- __skb_queue_purge(&tp->out_of_order_queue);
+ skb_rbtree_purge(&tp->out_of_order_queue);
inet->inet_dport = 0;
{
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;
+ u32 now = tcp_time_stamp, intv;
unsigned int start;
int notsent_bytes;
u64 rate64;
info->tcpi_min_rtt = tcp_min_rtt(tp);
info->tcpi_data_segs_in = tp->data_segs_in;
info->tcpi_data_segs_out = tp->data_segs_out;
+
+ info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0;
+ rate = READ_ONCE(tp->rate_delivered);
+ intv = READ_ONCE(tp->rate_interval_us);
+ if (rate && intv) {
+ rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC;
+ do_div(rate64, intv);
+ put_unaligned(rate64, &info->tcpi_delivery_rate);
+ }
}
EXPORT_SYMBOL_GPL(tcp_get_info);
}
EXPORT_SYMBOL(tcp_get_md5sig_pool);
-int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
- const struct tcphdr *th)
-{
- struct scatterlist sg;
- struct tcphdr hdr;
-
- /* 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, &hdr, sizeof(hdr));
- ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(hdr));
- return crypto_ahash_update(hp->md5_req);
-}
-EXPORT_SYMBOL(tcp_md5_hash_header);
-
int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
const struct sk_buff *skb, unsigned int header_len)
{
void __init tcp_init(void)
{
- unsigned long limit;
int max_rshare, max_wshare, cnt;
+ unsigned long limit;
unsigned int i;
- sock_skb_cb_check_size(sizeof(struct tcp_skb_cb));
+ BUILD_BUG_ON(sizeof(struct tcp_skb_cb) >
+ FIELD_SIZEOF(struct sk_buff, cb));
percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);
projects / cascardo / linux.git / blobdiff