From 1def9238d4aa2146924994aa4b7dc861f03b9362 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 10 Jan 2013 12:36:42 +0000 Subject: [PATCH] net_sched: more precise pkt_len computation One long standing problem with TSO/GSO/GRO packets is that skb->len doesn't represent a precise amount of bytes on wire. Headers are only accounted for the first segment. For TCP, thats typically 66 bytes per 1448 bytes segment missing, an error of 4.5 % for normal MSS value. As consequences : 1) TBF/CBQ/HTB/NETEM/... can send more bytes than the assigned limits. 2) Device stats are slightly under estimated as well. Fix this by taking account of headers in qdisc_skb_cb(skb)->pkt_len computation. Packet schedulers should use qdisc pkt_len instead of skb->len for their bandwidth limitations, and TSO enabled devices drivers could use pkt_len if their statistics are not hardware assisted, and if they don't scratch skb->cb[] first word. Both egress and ingress paths work, thanks to commit fda55eca5a (net: introduce skb_transport_header_was_set()) : If GRO built a GSO packet, it also set the transport header for us. Signed-off-by: Eric Dumazet Cc: Jamal Hadi Salim Cc: Stephen Hemminger Cc: Paolo Valente Cc: Herbert Xu Cc: Patrick McHardy Signed-off-by: David S. Miller --- net/core/dev.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index 594830e83589..4794cae84939 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2532,6 +2532,26 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, return netdev_get_tx_queue(dev, queue_index); } +static void qdisc_pkt_len_init(struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + + qdisc_skb_cb(skb)->pkt_len = skb->len; + + /* To get more precise estimation of bytes sent on wire, + * we add to pkt_len the headers size of all segments + */ + if (shinfo->gso_size) { + unsigned int hdr_len = skb_transport_offset(skb); + + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len += tcp_hdrlen(skb); + else + hdr_len += sizeof(struct udphdr); + qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len; + } +} + static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) @@ -2540,7 +2560,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, bool contended; int rc; - qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_pkt_len_init(skb); qdisc_calculate_pkt_len(skb, q); /* * Heuristic to force contended enqueues to serialize on a -- 2.20.1