diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-20 21:04:47 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-20 21:04:47 -0700 |
commit | 3b59bf081622b6446db77ad06c93fe23677bc533 (patch) | |
tree | 3f4bb5a27c90cc86994a1f6d3c53fbf9208003cb /net/ipv4/tcp_input.c | |
parent | e45836fafe157df137a837093037f741ad8f4c90 (diff) | |
parent | bbdb32cb5b73597386913d052165423b9d736145 (diff) | |
download | linux-3b59bf081622b6446db77ad06c93fe23677bc533.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking merge from David Miller:
"1) Move ixgbe driver over to purely page based buffering on receive.
From Alexander Duyck.
2) Add receive packet steering support to e1000e, from Bruce Allan.
3) Convert TCP MD5 support over to RCU, from Eric Dumazet.
4) Reduce cpu usage in handling out-of-order TCP packets on modern
systems, also from Eric Dumazet.
5) Support the IP{,V6}_UNICAST_IF socket options, making the wine
folks happy, from Erich Hoover.
6) Support VLAN trunking from guests in hyperv driver, from Haiyang
Zhang.
7) Support byte-queue-limtis in r8169, from Igor Maravic.
8) Outline code intended for IP_RECVTOS in IP_PKTOPTIONS existed but
was never properly implemented, Jiri Benc fixed that.
9) 64-bit statistics support in r8169 and 8139too, from Junchang Wang.
10) Support kernel side dump filtering by ctmark in netfilter
ctnetlink, from Pablo Neira Ayuso.
11) Support byte-queue-limits in gianfar driver, from Paul Gortmaker.
12) Add new peek socket options to assist with socket migration, from
Pavel Emelyanov.
13) Add sch_plug packet scheduler whose queue is controlled by
userland daemons using explicit freeze and release commands. From
Shriram Rajagopalan.
14) Fix FCOE checksum offload handling on transmit, from Yi Zou."
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1846 commits)
Fix pppol2tp getsockname()
Remove printk from rds_sendmsg
ipv6: fix incorrent ipv6 ipsec packet fragment
cpsw: Hook up default ndo_change_mtu.
net: qmi_wwan: fix build error due to cdc-wdm dependecy
netdev: driver: ethernet: Add TI CPSW driver
netdev: driver: ethernet: add cpsw address lookup engine support
phy: add am79c874 PHY support
mlx4_core: fix race on comm channel
bonding: send igmp report for its master
fs_enet: Add MPC5125 FEC support and PHY interface selection
net: bpf_jit: fix BPF_S_LDX_B_MSH compilation
net: update the usage of CHECKSUM_UNNECESSARY
fcoe: use CHECKSUM_UNNECESSARY instead of CHECKSUM_PARTIAL on tx
net: do not do gso for CHECKSUM_UNNECESSARY in netif_needs_gso
ixgbe: Fix issues with SR-IOV loopback when flow control is disabled
net/hyperv: Fix the code handling tx busy
ixgbe: fix namespace issues when FCoE/DCB is not enabled
rtlwifi: Remove unused ETH_ADDR_LEN defines
igbvf: Use ETH_ALEN
...
Fix up fairly trivial conflicts in drivers/isdn/gigaset/interface.c and
drivers/net/usb/{Kconfig,qmi_wwan.c} as per David.
Diffstat (limited to 'net/ipv4/tcp_input.c')
-rw-r--r-- | net/ipv4/tcp_input.c | 241 |
1 files changed, 138 insertions, 103 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b5e315f13641..e886e2f7fa8d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -61,6 +61,8 @@ * Pasi Sarolahti: F-RTO for dealing with spurious RTOs */ +#define pr_fmt(fmt) "TCP: " fmt + #include <linux/mm.h> #include <linux/slab.h> #include <linux/module.h> @@ -3867,9 +3869,9 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o opt_rx->wscale_ok = 1; if (snd_wscale > 14) { if (net_ratelimit()) - printk(KERN_INFO "tcp_parse_options: Illegal window " - "scaling value %d >14 received.\n", - snd_wscale); + pr_info("%s: Illegal window scaling value %d >14 received\n", + __func__, + snd_wscale); snd_wscale = 14; } opt_rx->snd_wscale = snd_wscale; @@ -4191,7 +4193,7 @@ static void tcp_fin(struct sock *sk) /* Only TCP_LISTEN and TCP_CLOSE are left, in these * cases we should never reach this piece of code. */ - printk(KERN_ERR "%s: Impossible, sk->sk_state=%d\n", + pr_err("%s: Impossible, sk->sk_state=%d\n", __func__, sk->sk_state); break; } @@ -4444,6 +4446,137 @@ static inline int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) return 0; } +static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb1; + u32 seq, end_seq; + + TCP_ECN_check_ce(tp, skb); + + if (tcp_try_rmem_schedule(sk, skb->truesize)) { + /* TODO: should increment a counter */ + __kfree_skb(skb); + return; + } + + /* Disable header prediction. */ + tp->pred_flags = 0; + inet_csk_schedule_ack(sk); + + SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", + tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); + + skb1 = skb_peek_tail(&tp->out_of_order_queue); + if (!skb1) { + /* Initial out of order segment, build 1 SACK. */ + if (tcp_is_sack(tp)) { + tp->rx_opt.num_sacks = 1; + tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq; + tp->selective_acks[0].end_seq = + TCP_SKB_CB(skb)->end_seq; + } + __skb_queue_head(&tp->out_of_order_queue, skb); + goto end; + } + + seq = TCP_SKB_CB(skb)->seq; + end_seq = TCP_SKB_CB(skb)->end_seq; + + if (seq == TCP_SKB_CB(skb1)->end_seq) { + /* Packets in ofo can stay in queue a long time. + * Better try to coalesce them right now + * to avoid future tcp_collapse_ofo_queue(), + * probably the most expensive function in tcp stack. + */ + if (skb->len <= skb_tailroom(skb1) && !tcp_hdr(skb)->fin) { + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPRCVCOALESCE); + BUG_ON(skb_copy_bits(skb, 0, + skb_put(skb1, skb->len), + skb->len)); + TCP_SKB_CB(skb1)->end_seq = end_seq; + TCP_SKB_CB(skb1)->ack_seq = TCP_SKB_CB(skb)->ack_seq; + __kfree_skb(skb); + skb = NULL; + } else { + __skb_queue_after(&tp->out_of_order_queue, skb1, skb); + } + + if (!tp->rx_opt.num_sacks || + tp->selective_acks[0].end_seq != seq) + goto add_sack; + + /* Common case: data arrive in order after hole. */ + tp->selective_acks[0].end_seq = end_seq; + goto end; + } + + /* Find place to insert this segment. */ + while (1) { + if (!after(TCP_SKB_CB(skb1)->seq, seq)) + break; + if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) { + skb1 = NULL; + break; + } + skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1); + } + + /* Do skb overlap to previous one? */ + if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { + if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { + /* All the bits are present. Drop. */ + __kfree_skb(skb); + skb = NULL; + tcp_dsack_set(sk, seq, end_seq); + goto add_sack; + } + if (after(seq, TCP_SKB_CB(skb1)->seq)) { + /* Partial overlap. */ + tcp_dsack_set(sk, seq, + TCP_SKB_CB(skb1)->end_seq); + } else { + if (skb_queue_is_first(&tp->out_of_order_queue, + skb1)) + skb1 = NULL; + else + skb1 = skb_queue_prev( + &tp->out_of_order_queue, + skb1); + } + } + if (!skb1) + __skb_queue_head(&tp->out_of_order_queue, skb); + else + __skb_queue_after(&tp->out_of_order_queue, skb1, skb); + + /* And clean segments covered by new one as whole. */ + while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) { + skb1 = skb_queue_next(&tp->out_of_order_queue, skb); + + if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) + break; + if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { + tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, + end_seq); + break; + } + __skb_unlink(skb1, &tp->out_of_order_queue); + tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, + TCP_SKB_CB(skb1)->end_seq); + __kfree_skb(skb1); + } + +add_sack: + if (tcp_is_sack(tp)) + tcp_sack_new_ofo_skb(sk, seq, end_seq); +end: + if (skb) + skb_set_owner_r(skb, sk); +} + + static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); @@ -4559,105 +4692,7 @@ drop: goto queue_and_out; } - TCP_ECN_check_ce(tp, skb); - - if (tcp_try_rmem_schedule(sk, skb->truesize)) - goto drop; - - /* Disable header prediction. */ - tp->pred_flags = 0; - inet_csk_schedule_ack(sk); - - SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", - tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); - - skb_set_owner_r(skb, sk); - - if (!skb_peek(&tp->out_of_order_queue)) { - /* Initial out of order segment, build 1 SACK. */ - if (tcp_is_sack(tp)) { - tp->rx_opt.num_sacks = 1; - tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq; - tp->selective_acks[0].end_seq = - TCP_SKB_CB(skb)->end_seq; - } - __skb_queue_head(&tp->out_of_order_queue, skb); - } else { - struct sk_buff *skb1 = skb_peek_tail(&tp->out_of_order_queue); - u32 seq = TCP_SKB_CB(skb)->seq; - u32 end_seq = TCP_SKB_CB(skb)->end_seq; - - if (seq == TCP_SKB_CB(skb1)->end_seq) { - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); - - if (!tp->rx_opt.num_sacks || - tp->selective_acks[0].end_seq != seq) - goto add_sack; - - /* Common case: data arrive in order after hole. */ - tp->selective_acks[0].end_seq = end_seq; - return; - } - - /* Find place to insert this segment. */ - while (1) { - if (!after(TCP_SKB_CB(skb1)->seq, seq)) - break; - if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) { - skb1 = NULL; - break; - } - skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1); - } - - /* Do skb overlap to previous one? */ - if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { - if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { - /* All the bits are present. Drop. */ - __kfree_skb(skb); - tcp_dsack_set(sk, seq, end_seq); - goto add_sack; - } - if (after(seq, TCP_SKB_CB(skb1)->seq)) { - /* Partial overlap. */ - tcp_dsack_set(sk, seq, - TCP_SKB_CB(skb1)->end_seq); - } else { - if (skb_queue_is_first(&tp->out_of_order_queue, - skb1)) - skb1 = NULL; - else - skb1 = skb_queue_prev( - &tp->out_of_order_queue, - skb1); - } - } - if (!skb1) - __skb_queue_head(&tp->out_of_order_queue, skb); - else - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); - - /* And clean segments covered by new one as whole. */ - while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) { - skb1 = skb_queue_next(&tp->out_of_order_queue, skb); - - if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) - break; - if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { - tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, - end_seq); - break; - } - __skb_unlink(skb1, &tp->out_of_order_queue); - tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, - TCP_SKB_CB(skb1)->end_seq); - __kfree_skb(skb1); - } - -add_sack: - if (tcp_is_sack(tp)) - tcp_sack_new_ofo_skb(sk, seq, end_seq); - } + tcp_data_queue_ofo(sk, skb); } static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, |