[NET] Generalise TCP's struct open_request minisock infrastructure
Kept this first changeset minimal, without changing existing names to
ease peer review.
Basicaly tcp_openreq_alloc now receives the or_calltable, that in turn
has two new members:
->slab, that replaces tcp_openreq_cachep
->obj_size, to inform the size of the openreq descendant for
a specific protocol
The protocol specific fields in struct open_request were moved to a
class hierarchy, with the things that are common to all connection
oriented PF_INET protocols in struct inet_request_sock, the TCP ones
in tcp_request_sock, that is an inet_request_sock, that is an
open_request.
I.e. this uses the same approach used for the struct sock class
hierarchy, with sk_prot indicating if the protocol wants to use the
open_request infrastructure by filling in sk_prot->rsk_prot with an
or_calltable.
Results? Performance is improved and TCP v4 now uses only 64 bytes per
open request minisock, down from 96 without this patch :-)
Next changeset will rename some of the structs, fields and functions
mentioned above, struct or_calltable is way unclear, better name it
struct request_sock_ops, s/struct open_request/struct request_sock/g,
etc.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fa24e7a..f3c8747 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1358,6 +1358,7 @@
struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct open_request *req)
{
+ struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_sock *tp = tcp_sk(sk);
struct tcphdr *th;
int tcp_header_size;
@@ -1373,47 +1374,47 @@
skb->dst = dst_clone(dst);
tcp_header_size = (sizeof(struct tcphdr) + TCPOLEN_MSS +
- (req->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) +
- (req->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) +
+ (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) +
+ (ireq->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) +
/* SACK_PERM is in the place of NOP NOP of TS */
- ((req->sack_ok && !req->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0));
+ ((ireq->sack_ok && !ireq->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0));
skb->h.th = th = (struct tcphdr *) skb_push(skb, tcp_header_size);
memset(th, 0, sizeof(struct tcphdr));
th->syn = 1;
th->ack = 1;
if (dst->dev->features&NETIF_F_TSO)
- req->ecn_ok = 0;
+ ireq->ecn_ok = 0;
TCP_ECN_make_synack(req, th);
th->source = inet_sk(sk)->sport;
- th->dest = req->rmt_port;
- TCP_SKB_CB(skb)->seq = req->snt_isn;
+ th->dest = ireq->rmt_port;
+ TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn;
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
TCP_SKB_CB(skb)->sacked = 0;
skb_shinfo(skb)->tso_segs = 1;
skb_shinfo(skb)->tso_size = 0;
th->seq = htonl(TCP_SKB_CB(skb)->seq);
- th->ack_seq = htonl(req->rcv_isn + 1);
+ th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
__u8 rcv_wscale;
/* Set this up on the first call only */
req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
/* tcp_full_space because it is guaranteed to be the first packet */
tcp_select_initial_window(tcp_full_space(sk),
- dst_metric(dst, RTAX_ADVMSS) - (req->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
+ dst_metric(dst, RTAX_ADVMSS) - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
&req->rcv_wnd,
&req->window_clamp,
- req->wscale_ok,
+ ireq->wscale_ok,
&rcv_wscale);
- req->rcv_wscale = rcv_wscale;
+ ireq->rcv_wscale = rcv_wscale;
}
/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
th->window = htons(req->rcv_wnd);
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), req->tstamp_ok,
- req->sack_ok, req->wscale_ok, req->rcv_wscale,
+ tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok,
+ ireq->sack_ok, ireq->wscale_ok, ireq->rcv_wscale,
TCP_SKB_CB(skb)->when,
req->ts_recent);