summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-12-12 18:07:07 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2012-12-12 18:07:07 -0800
commit6be35c700f742e911ecedd07fcc43d4439922334 (patch)
treeca9f37214d204465fcc2d79c82efd291e357c53c /net/ipv4/tcp.c
parente37aa63e87bd581f9be5555ed0ba83f5295c92fc (diff)
parent520dfe3a3645257bf83660f672c47f8558f3d4c4 (diff)
downloadop-kernel-dev-6be35c700f742e911ecedd07fcc43d4439922334.zip
op-kernel-dev-6be35c700f742e911ecedd07fcc43d4439922334.tar.gz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking changes from David Miller: 1) Allow to dump, monitor, and change the bridge multicast database using netlink. From Cong Wang. 2) RFC 5961 TCP blind data injection attack mitigation, from Eric Dumazet. 3) Networking user namespace support from Eric W. Biederman. 4) tuntap/virtio-net multiqueue support by Jason Wang. 5) Support for checksum offload of encapsulated packets (basically, tunneled traffic can still be checksummed by HW). From Joseph Gasparakis. 6) Allow BPF filter access to VLAN tags, from Eric Dumazet and Daniel Borkmann. 7) Bridge port parameters over netlink and BPDU blocking support from Stephen Hemminger. 8) Improve data access patterns during inet socket demux by rearranging socket layout, from Eric Dumazet. 9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and Jon Maloy. 10) Update TCP socket hash sizing to be more in line with current day realities. The existing heurstics were choosen a decade ago. From Eric Dumazet. 11) Fix races, queue bloat, and excessive wakeups in ATM and associated drivers, from Krzysztof Mazur and David Woodhouse. 12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions in VXLAN driver, from David Stevens. 13) Add "oops_only" mode to netconsole, from Amerigo Wang. 14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also allow DCB netlink to work on namespaces other than the initial namespace. From John Fastabend. 15) Support PTP in the Tigon3 driver, from Matt Carlson. 16) tun/vhost zero copy fixes and improvements, plus turn it on by default, from Michael S. Tsirkin. 17) Support per-association statistics in SCTP, from Michele Baldessari. And many, many, driver updates, cleanups, and improvements. Too numerous to mention individually. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits) net/mlx4_en: Add support for destination MAC in steering rules net/mlx4_en: Use generic etherdevice.h functions. net: ethtool: Add destination MAC address to flow steering API bridge: add support of adding and deleting mdb entries bridge: notify mdb changes via netlink ndisc: Unexport ndisc_{build,send}_skb(). uapi: add missing netconf.h to export list pkt_sched: avoid requeues if possible solos-pci: fix double-free of TX skb in DMA mode bnx2: Fix accidental reversions. bna: Driver Version Updated to 3.1.2.1 bna: Firmware update bna: Add RX State bna: Rx Page Based Allocation bna: TX Intr Coalescing Fix bna: Tx and Rx Optimizations bna: Code Cleanup and Enhancements ath9k: check pdata variable before dereferencing it ath5k: RX timestamp is reported at end of frame ath9k_htc: RX timestamp is reported at end of frame ...
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c25
1 files changed, 14 insertions, 11 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e457c7a..1ca2536 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -536,13 +536,14 @@ 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) ||
@@ -557,7 +558,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
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;
@@ -1490,15 +1491,19 @@ 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, false);
@@ -2300,7 +2305,7 @@ void tcp_sock_destruct(struct sock *sk)
static inline bool tcp_can_repair_sock(const struct sock *sk)
{
- return capable(CAP_NET_ADMIN) &&
+ return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) &&
((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED));
}
@@ -3586,8 +3591,7 @@ void __init tcp_init(void)
alloc_large_system_hash("TCP established",
sizeof(struct inet_ehash_bucket),
thash_entries,
- (totalram_pages >= 128 * 1024) ?
- 13 : 15,
+ 17, /* one slot per 128 KB of memory */
0,
NULL,
&tcp_hashinfo.ehash_mask,
@@ -3603,8 +3607,7 @@ void __init tcp_init(void)
alloc_large_system_hash("TCP bind",
sizeof(struct inet_bind_hashbucket),
tcp_hashinfo.ehash_mask + 1,
- (totalram_pages >= 128 * 1024) ?
- 13 : 15,
+ 17, /* one slot per 128 KB of memory */
0,
&tcp_hashinfo.bhash_size,
NULL,
OpenPOWER on IntegriCloud