Commit 4c2f2454 authored Aug 18, 2016 by Marcelo Ricardo Leitner Committed by David S. Miller Aug 19, 2016

sctp: linearize early if it's not GSO

Because otherwise when crc computation is still needed it's way more
expensive than on a linear buffer to the point that it affects
performance.

It's so expensive that netperf test gives a perf output as below:

Overhead Command Shared Object Symbol
18,62% netserver [kernel.vmlinux] [k] crc32_generic_shift
2,57% netserver [kernel.vmlinux] [k] __pskb_pull_tail
1,94% netserver [kernel.vmlinux] [k] fib_table_lookup
1,90% netserver [kernel.vmlinux] [k] copy_user_enhanced_fast_string
1,66% swapper [kernel.vmlinux] [k] intel_idle
1,63% netserver [kernel.vmlinux] [k] _raw_spin_lock
1,59% netserver [sctp] [k] sctp_packet_transmit
1,55% netserver [kernel.vmlinux] [k] memcpy_erms
1,42% netserver [sctp] [k] sctp_rcv

# netperf -H 192.168.10.1 -l 10 -t SCTP_STREAM -cC -- -m 12000
SCTP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.10.1 () port 0 AF_INET
Recv Send Send Utilization Service Demand
Socket Socket Message Elapsed Send Recv Send Recv
Size Size Size Time Throughput local remote local remote
bytes bytes bytes secs. 10^6bits/s % S % S us/KB us/KB

212992 212992 12000 10.00 3016.42 2.88 3.78 1.874 2.462

After patch:
Overhead Command Shared Object Symbol
2,75% netserver [kernel.vmlinux] [k] memcpy_erms
2,63% netserver [kernel.vmlinux] [k] copy_user_enhanced_fast_string
2,39% netserver [kernel.vmlinux] [k] fib_table_lookup
2,04% netserver [kernel.vmlinux] [k] __pskb_pull_tail
1,91% netserver [kernel.vmlinux] [k] _raw_spin_lock
1,91% netserver [sctp] [k] sctp_packet_transmit
1,72% netserver [mlx4_en] [k] mlx4_en_process_rx_cq
1,68% netserver [sctp] [k] sctp_rcv

212992 212992 12000 10.00 3681.77 3.83 3.46 2.045 1.849

Fixes: 3acb50c1 ("sctp: delay as much as possible skb_linearize")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

parent 187335cd

net/sctp/input.c

+7 −4

Original line number	Original line	Diff line number	Diff line
	@@ -119,7 +119,13 @@ int sctp_rcv(struct sk_buff *skb)
	skb_transport_offset(skb))		skb_transport_offset(skb))
	goto discard_it;		goto discard_it;

	if (!pskb_may_pull(skb, sizeof(struct sctphdr)))		/* If the packet is fragmented and we need to do crc checking,
			* it's better to just linearize it otherwise crc computing
			* takes longer.
			*/
			if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) &&
			skb_linearize(skb)) \|\|
			!pskb_may_pull(skb, sizeof(struct sctphdr)))
	goto discard_it;		goto discard_it;

	/* Pull up the IP header. */		/* Pull up the IP header. */
	@@ -1177,9 +1183,6 @@ static struct sctp_association __sctp_rcv_lookup_harder(struct net net,
	if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP)		if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP)
	return NULL;		return NULL;

	if (skb_linearize(skb))
	return NULL;

	ch = (sctp_chunkhdr_t *) skb->data;		ch = (sctp_chunkhdr_t *) skb->data;

	/* The code below will attempt to walk the chunk and extract		/* The code below will attempt to walk the chunk and extract

net/sctp/inqueue.c

+0 −13

Original line number	Original line	Diff line number	Diff line
	@@ -170,19 +170,6 @@ struct sctp_chunk sctp_inq_pop(struct sctp_inq queue)

	chunk = list_entry(entry, struct sctp_chunk, list);		chunk = list_entry(entry, struct sctp_chunk, list);

	/* Linearize if it's not GSO */
	if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) != SKB_GSO_SCTP &&
	skb_is_nonlinear(chunk->skb)) {
	if (skb_linearize(chunk->skb)) {
	__SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS);
	sctp_chunk_free(chunk);
	goto next_chunk;
	}

	/* Update sctp_hdr as it probably changed */
	chunk->sctp_hdr = sctp_hdr(chunk->skb);
	}

	if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) {		if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) {
	/* GSO-marked skbs but without frags, handle		/* GSO-marked skbs but without frags, handle
	* them normally		* them normally