summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-10-08 21:40:54 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2014-10-08 21:40:54 -0400
commit35a9ad8af0bb0fa3525e6d0d20e32551d226f38e (patch)
tree15b4b33206818886d9cff371fd2163e073b70568 /net/ipv4/tcp.c
parentd5935b07da53f74726e2a65dd4281d0f2c70e5d4 (diff)
parent64b1f00a0830e1c53874067273a096b228d83d36 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Most notable changes in here: 1) By far the biggest accomplishment, thanks to a large range of contributors, is the addition of multi-send for transmit. This is the result of discussions back in Chicago, and the hard work of several individuals. Now, when the ->ndo_start_xmit() method of a driver sees skb->xmit_more as true, it can choose to defer the doorbell telling the driver to start processing the new TX queue entires. skb->xmit_more means that the generic networking is guaranteed to call the driver immediately with another SKB to send. There is logic added to the qdisc layer to dequeue multiple packets at a time, and the handling mis-predicted offloads in software is now done with no locks held. Finally, pktgen is extended to have a "burst" parameter that can be used to test a multi-send implementation. Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4, virtio_net Adding support is almost trivial, so export more drivers to support this optimization soon. I want to thank, in no particular or implied order, Jesper Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann, David Tat, Hannes Frederic Sowa, and Rusty Russell. 2) PTP and timestamping support in bnx2x, from Michal Kalderon. 3) Allow adjusting the rx_copybreak threshold for a driver via ethtool, and add rx_copybreak support to enic driver. From Govindarajulu Varadarajan. 4) Significant enhancements to the generic PHY layer and the bcm7xxx driver in particular (EEE support, auto power down, etc.) from Florian Fainelli. 5) Allow raw buffers to be used for flow dissection, allowing drivers to determine the optimal "linear pull" size for devices that DMA into pools of pages. The objective is to get exactly the necessary amount of headers into the linear SKB area pre-pulled, but no more. The new interface drivers use is eth_get_headlen(). From WANG Cong, with driver conversions (several had their own by-hand duplicated implementations) by Alexander Duyck and Eric Dumazet. 6) Support checksumming more smoothly and efficiently for encapsulations, and add "foo over UDP" facility. From Tom Herbert. 7) Add Broadcom SF2 switch driver to DSA layer, from Florian Fainelli. 8) eBPF now can load programs via a system call and has an extensive testsuite. Alexei Starovoitov and Daniel Borkmann. 9) Major overhaul of the packet scheduler to use RCU in several major areas such as the classifiers and rate estimators. From John Fastabend. 10) Add driver for Intel FM10000 Ethernet Switch, from Alexander Duyck. 11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric Dumazet. 12) Add Datacenter TCP congestion control algorithm support, From Florian Westphal. 13) Reorganize sk_buff so that __copy_skb_header() is significantly faster. From Eric Dumazet" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits) netlabel: directly return netlbl_unlabel_genl_init() net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers net: description of dma_cookie cause make xmldocs warning cxgb4: clean up a type issue cxgb4: potential shift wrapping bug i40e: skb->xmit_more support net: fs_enet: Add NAPI TX net: fs_enet: Remove non NAPI RX r8169:add support for RTL8168EP net_sched: copy exts->type in tcf_exts_change() wimax: convert printk to pr_foo() af_unix: remove 0 assignment on static ipv6: Do not warn for informational ICMP messages, regardless of type. Update Intel Ethernet Driver maintainers list bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING tipc: fix bug in multicast congestion handling net: better IFF_XMIT_DST_RELEASE support net/mlx4_en: remove NETDEV_TX_BUSY 3c59x: fix bad split of cpu_to_le32(pci_map_single()) net: bcmgenet: fix Tx ring priority programming ...
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c36
1 files changed, 18 insertions, 18 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8ee43ae90396..461003d258ba 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -404,7 +404,7 @@ void tcp_init_sock(struct sock *sk)
tp->reordering = sysctl_tcp_reordering;
tcp_enable_early_retrans(tp);
- icsk->icsk_ca_ops = &tcp_init_congestion_ops;
+ tcp_assign_congestion_control(sk);
tp->tsoffset = 0;
@@ -608,7 +608,7 @@ static inline bool forced_push(const struct tcp_sock *tp)
return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
}
-static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
+static void skb_entail(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
@@ -617,7 +617,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
tcb->seq = tcb->end_seq = tp->write_seq;
tcb->tcp_flags = TCPHDR_ACK;
tcb->sacked = 0;
- skb_header_release(skb);
+ __skb_header_release(skb);
tcp_add_write_queue_tail(sk, skb);
sk->sk_wmem_queued += skb->truesize;
sk_mem_charge(sk, skb->truesize);
@@ -962,7 +962,7 @@ new_segment:
skb->ip_summed = CHECKSUM_PARTIAL;
tp->write_seq += copy;
TCP_SKB_CB(skb)->end_seq += copy;
- skb_shinfo(skb)->gso_segs = 0;
+ tcp_skb_pcount_set(skb, 0);
if (!copied)
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
@@ -1260,7 +1260,7 @@ new_segment:
tp->write_seq += copy;
TCP_SKB_CB(skb)->end_seq += copy;
- skb_shinfo(skb)->gso_segs = 0;
+ tcp_skb_pcount_set(skb, 0);
from += copy;
copied += copy;
@@ -1476,9 +1476,9 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
offset = seq - TCP_SKB_CB(skb)->seq;
- if (tcp_hdr(skb)->syn)
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
offset--;
- if (offset < skb->len || tcp_hdr(skb)->fin) {
+ if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) {
*off = offset;
return skb;
}
@@ -1551,7 +1551,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
if (offset + 1 != skb->len)
continue;
}
- if (tcp_hdr(skb)->fin) {
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
sk_eat_skb(sk, skb);
++seq;
break;
@@ -1665,11 +1665,11 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
break;
offset = *seq - TCP_SKB_CB(skb)->seq;
- if (tcp_hdr(skb)->syn)
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
offset--;
if (offset < skb->len)
goto found_ok_skb;
- if (tcp_hdr(skb)->fin)
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
WARN(!(flags & MSG_PEEK),
"recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
@@ -1857,7 +1857,7 @@ skip_copy:
if (used + offset < skb->len)
continue;
- if (tcp_hdr(skb)->fin)
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
if (!(flags & MSG_PEEK))
sk_eat_skb(sk, skb);
@@ -2044,8 +2044,10 @@ void tcp_close(struct sock *sk, long timeout)
* reader process may not have drained the data yet!
*/
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
- u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq -
- tcp_hdr(skb)->fin;
+ u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq;
+
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+ len--;
data_was_unread += len;
__kfree_skb(skb);
}
@@ -2572,7 +2574,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
break;
#endif
case TCP_USER_TIMEOUT:
- /* Cap the max timeout in ms TCP will retry/retrans
+ /* Cap the max time in ms TCP will retry or probe the window
* before giving up and aborting (ETIMEDOUT) a connection.
*/
if (val < 0)
@@ -3051,7 +3053,7 @@ static int __init set_thash_entries(char *str)
}
__setup("thash_entries=", set_thash_entries);
-static void tcp_init_mem(void)
+static void __init tcp_init_mem(void)
{
unsigned long limit = nr_free_buffer_pages() / 8;
limit = max(limit, 128UL);
@@ -3137,8 +3139,6 @@ void __init tcp_init(void)
tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
tcp_metrics_init();
-
- tcp_register_congestion_control(&tcp_reno);
-
+ BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
tcp_tasklet_init();
}