GitHub-Mirror/Star64_linux
2
0
Fork 0
mirror of https://github.com/Fishwaldo/Star64_linux.git synced 2025-06-21 06:01:23 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

tcp: add coalescing attempt in tcp_ofo_queue()

Browse source 
In order to make TCP more resilient in presence of reorders, we need
to allow coalescing to happen when skbs from out of order queue are
transferred into receive queue. LRO/GRO can be completely canceled
in some pathological cases, like per packet load balancing on aggregated
links.

I had to move tcp_try_coalesce() up in the file above tcp_ofo_queue()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Eric Dumazet 2014-09-19 08:26:20 -07:00 • committed by David S. Miller
parent 4cdf507d54
commit bd1e75abf4
1 changed files with 66 additions and 61 deletions
Download patch file Download diff file Expand all files Collapse all files

127
net/ipv4/tcp_input.c
View file

@ -4061,67 +4061,6 @@ static void tcp_sack_remove(struct tcp_sock *tp)
tp->rx_opt.num_sacks = num_sacks; tp->rx_opt.num_sacks = num_sacks;
} }
/* This one checks to see if we can put data from the
* out_of_order queue into the receive_queue.
*/
static void tcp_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
__u32 dsack_high = tp->rcv_nxt;
struct sk_buff *skb;
while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) {
if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
break;
if (before(TCP_SKB_CB(skb)->seq, dsack_high)) {
__u32 dsack = dsack_high;
if (before(TCP_SKB_CB(skb)->end_seq, dsack_high))
dsack_high = TCP_SKB_CB(skb)->end_seq;
tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack);
}
if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
SOCK_DEBUG(sk, "ofo packet was already received\n");
__skb_unlink(skb, &tp->out_of_order_queue);
__kfree_skb(skb);
continue;
}
SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n",
tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(skb)->end_seq);
__skb_unlink(skb, &tp->out_of_order_queue);
__skb_queue_tail(&sk->sk_receive_queue, skb);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
tcp_fin(sk);
}
}
static bool tcp_prune_ofo_queue(struct sock *sk);
static int tcp_prune_queue(struct sock *sk);
static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
unsigned int size)
{
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
!sk_rmem_schedule(sk, skb, size)) {
if (tcp_prune_queue(sk) < 0)
return -1;
if (!sk_rmem_schedule(sk, skb, size)) {
if (!tcp_prune_ofo_queue(sk))
return -1;
if (!sk_rmem_schedule(sk, skb, size))
return -1;
}
}
return 0;
}
/** /**
* tcp_try_coalesce - try to merge skb to prior one * tcp_try_coalesce - try to merge skb to prior one
* @sk: socket * @sk: socket
@ -4160,6 +4099,72 @@ static bool tcp_try_coalesce(struct sock *sk,
return true; return true;
} }
/* This one checks to see if we can put data from the
* out_of_order queue into the receive_queue.
*/
static void tcp_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
__u32 dsack_high = tp->rcv_nxt;
struct sk_buff *skb, *tail;
bool fragstolen, eaten;
while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) {
if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
break;
if (before(TCP_SKB_CB(skb)->seq, dsack_high)) {
__u32 dsack = dsack_high;
if (before(TCP_SKB_CB(skb)->end_seq, dsack_high))
dsack_high = TCP_SKB_CB(skb)->end_seq;
tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack);
}
__skb_unlink(skb, &tp->out_of_order_queue);
if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
SOCK_DEBUG(sk, "ofo packet was already received\n");
__kfree_skb(skb);
continue;
}
SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n",
tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(skb)->end_seq);
tail = skb_peek_tail(&sk->sk_receive_queue);
eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
if (!eaten)
__skb_queue_tail(&sk->sk_receive_queue, skb);
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
tcp_fin(sk);
if (eaten)
kfree_skb_partial(skb, fragstolen);
}
}
static bool tcp_prune_ofo_queue(struct sock *sk);
static int tcp_prune_queue(struct sock *sk);
static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
unsigned int size)
{
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
!sk_rmem_schedule(sk, skb, size)) {
if (tcp_prune_queue(sk) < 0)
return -1;
if (!sk_rmem_schedule(sk, skb, size)) {
if (!tcp_prune_ofo_queue(sk))
return -1;
if (!sk_rmem_schedule(sk, skb, size))
return -1;
}
}
return 0;
}
static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
{ {
struct tcp_sock *tp = tcp_sk(sk); struct tcp_sock *tp = tcp_sk(sk);