summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-12-11 23:27:06 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2014-12-11 23:27:06 +0100
commit70e71ca0af244f48a5dcf56dc435243792e3a495 (patch)
treef7d9c4c4d9a857a00043e9bf6aa2d6f533a34778 /net/ipv4/tcp.c
parentMerge tag 'sound-3.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/t... (diff)
parentFix race condition between vxlan_sock_add and vxlan_sock_release (diff)
downloadlinux-70e71ca0af244f48a5dcf56dc435243792e3a495.tar.xz
linux-70e71ca0af244f48a5dcf56dc435243792e3a495.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: 1) New offloading infrastructure and example 'rocker' driver for offloading of switching and routing to hardware. This work was done by a large group of dedicated individuals, not limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend, Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu 2) Start making the networking operate on IOV iterators instead of modifying iov objects in-situ during transfers. Thanks to Al Viro and Herbert Xu. 3) A set of new netlink interfaces for the TIPC stack, from Richard Alpe. 4) Remove unnecessary looping during ipv6 routing lookups, from Martin KaFai Lau. 5) Add PAUSE frame generation support to gianfar driver, from Matei Pavaluca. 6) Allow for larger reordering levels in TCP, which are easily achievable in the real world right now, from Eric Dumazet. 7) Add a variable of napi_schedule that doesn't need to disable cpu interrupts, from Eric Dumazet. 8) Use a doubly linked list to optimize neigh_parms_release(), from Nicolas Dichtel. 9) Various enhancements to the kernel BPF verifier, and allow eBPF programs to actually be attached to sockets. From Alexei Starovoitov. 10) Support TSO/LSO in sunvnet driver, from David L Stevens. 11) Allow controlling ECN usage via routing metrics, from Florian Westphal. 12) Remote checksum offload, from Tom Herbert. 13) Add split-header receive, BQL, and xmit_more support to amd-xgbe driver, from Thomas Lendacky. 14) Add MPLS support to openvswitch, from Simon Horman. 15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen Klassert. 16) Do gro flushes on a per-device basis using a timer, from Eric Dumazet. This tries to resolve the conflicting goals between the desired handling of bulk vs. RPC-like traffic. 17) Allow userspace to ask for the CPU upon what a packet was received/steered, via SO_INCOMING_CPU. From Eric Dumazet. 18) Limit GSO packets to half the current congestion window, from Eric Dumazet. 19) Add a generic helper so that all drivers set their RSS keys in a consistent way, from Eric Dumazet. 20) Add xmit_more support to enic driver, from Govindarajulu Varadarajan. 21) Add VLAN packet scheduler action, from Jiri Pirko. 22) Support configurable RSS hash functions via ethtool, from Eyal Perry. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits) Fix race condition between vxlan_sock_add and vxlan_sock_release net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header net/mlx4: Add support for A0 steering net/mlx4: Refactor QUERY_PORT net/mlx4_core: Add explicit error message when rule doesn't meet configuration net/mlx4: Add A0 hybrid steering net/mlx4: Add mlx4_bitmap zone allocator net/mlx4: Add a check if there are too many reserved QPs net/mlx4: Change QP allocation scheme net/mlx4_core: Use tasklet for user-space CQ completion events net/mlx4_core: Mask out host side virtualization features for guests net/mlx4_en: Set csum level for encapsulated packets be2net: Export tunnel offloads only when a VxLAN tunnel is created gianfar: Fix dma check map error when DMA_API_DEBUG is enabled cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call net: fec: only enable mdio interrupt before phy device link up net: fec: clear all interrupt events to support i.MX6SX net: fec: reset fep link status in suspend function net: sock: fix access via invalid file descriptor net: introduce helper macro for_each_cmsghdr ...
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c75
1 files changed, 28 insertions, 47 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 38c2bcb8dd5d..3075723c729b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -835,47 +835,29 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
int large_allowed)
{
struct tcp_sock *tp = tcp_sk(sk);
- u32 xmit_size_goal, old_size_goal;
-
- xmit_size_goal = mss_now;
-
- if (large_allowed && sk_can_gso(sk)) {
- 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);
-
- /* We try hard to avoid divides here */
- old_size_goal = tp->xmit_size_goal_segs * mss_now;
-
- if (likely(old_size_goal <= xmit_size_goal &&
- old_size_goal + mss_now > xmit_size_goal)) {
- xmit_size_goal = old_size_goal;
- } else {
- 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;
- }
+ u32 new_size_goal, size_goal, hlen;
+
+ if (!large_allowed || !sk_can_gso(sk))
+ return mss_now;
+
+ /* 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;
+
+ new_size_goal = sk->sk_gso_max_size - 1 - hlen;
+ new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal);
+
+ /* We try hard to avoid divides here */
+ size_goal = tp->gso_segs * mss_now;
+ if (unlikely(new_size_goal < size_goal ||
+ new_size_goal >= size_goal + mss_now)) {
+ tp->gso_segs = min_t(u16, new_size_goal / mss_now,
+ sk->sk_gso_max_segs);
+ size_goal = tp->gso_segs * mss_now;
}
- return max(xmit_size_goal, mss_now);
+ return max(size_goal, mss_now);
}
static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
@@ -1085,7 +1067,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t size)
{
- struct iovec *iov;
+ const struct iovec *iov;
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int iovlen, flags, err, copied = 0;
@@ -1136,8 +1118,8 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
mss_now = tcp_send_mss(sk, &size_goal, flags);
/* Ok commence sending. */
- iovlen = msg->msg_iovlen;
- iov = msg->msg_iov;
+ iovlen = msg->msg_iter.nr_segs;
+ iov = msg->msg_iter.iov;
copied = 0;
err = -EPIPE;
@@ -1349,7 +1331,7 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
if (len > 0) {
if (!(flags & MSG_TRUNC))
- err = memcpy_toiovec(msg->msg_iov, &c, 1);
+ err = memcpy_to_msg(msg, &c, 1);
len = 1;
} else
msg->msg_flags |= MSG_TRUNC;
@@ -1377,7 +1359,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
/* 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);
+ err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
if (err)
break;
@@ -1729,7 +1711,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
user_recv = current;
tp->ucopy.task = user_recv;
- tp->ucopy.iov = msg->msg_iov;
+ tp->ucopy.msg = msg;
}
tp->ucopy.len = len;
@@ -1833,8 +1815,7 @@ do_prequeue:
}
if (!(flags & MSG_TRUNC)) {
- err = skb_copy_datagram_iovec(skb, offset,
- msg->msg_iov, used);
+ err = skb_copy_datagram_msg(skb, offset, msg, used);
if (err) {
/* Exception. Bailout! */
if (!copied)