![Jerry Chu](/assets/img/avatar_default.png)
This patch built on top of Commit299603e837
("net-gro: Prepare GRO stack for the upcoming tunneling support") to add the support of the standard GRE (RFC1701/RFC2784/RFC2890) to the GRO stack. It also serves as an example for supporting other encapsulation protocols in the GRO stack in the future. The patch supports version 0 and all the flags (key, csum, seq#) but will flush any pkt with the S (seq#) flag. This is because the S flag is not support by GSO, and a GRO pkt may end up in the forwarding path, thus requiring GSO support to break it up correctly. Currently the "packet_offload" structure only contains L3 (ETH_P_IP/ ETH_P_IPV6) GRO offload support so the encapped pkts are limited to IP pkts (i.e., w/o L2 hdr). But support for other protocol type can be easily added, so is the support for GRE variations like NVGRE. The patch also support csum offload. Specifically if the csum flag is on and the h/w is capable of checksumming the payload (CHECKSUM_COMPLETE), the code will take advantage of the csum computed by the h/w when validating the GRE csum. Note that commit60769a5dcd
"ipv4: gre: add GRO capability" already introduces GRO capability to IPv4 GRE tunnels, using the gro_cells infrastructure. But GRO is done after GRE hdr has been removed (i.e., decapped). The following patch applies GRO when pkts first come in (before hitting the GRE tunnel code). There is some performance advantage for applying GRO as early as possible. Also this approach is transparent to other subsystem like Open vSwitch where GRE decap is handled outside of the IP stack hence making it harder for the gro_cells stuff to apply. On the other hand, some NICs are still not capable of hashing on the inner hdr of a GRE pkt (RSS). In that case the GRO processing of pkts from the same remote host will all happen on the same CPU and the performance may be suboptimal. I'm including some rough preliminary performance numbers below. Note that the performance will be highly dependent on traffic load, mix as usual. Moreover it also depends on NIC offload features hence the following is by no means a comprehesive study. Local testing and tuning will be needed to decide the best setting. All tests spawned 50 copies of netperf TCP_STREAM and ran for 30 secs. (super_netperf 50 -H 192.168.1.18 -l 30) An IP GRE tunnel with only the key flag on (e.g., ip tunnel add gre1 mode gre local 10.246.17.18 remote 10.246.17.17 ttl 255 key 123) is configured. The GRO support for pkts AFTER decap are controlled through the device feature of the GRE device (e.g., ethtool -K gre1 gro on/off). 1.1 ethtool -K gre1 gro off; ethtool -K eth0 gro off thruput: 9.16Gbps CPU utilization: 19% 1.2 ethtool -K gre1 gro on; ethtool -K eth0 gro off thruput: 5.9Gbps CPU utilization: 15% 1.3 ethtool -K gre1 gro off; ethtool -K eth0 gro on thruput: 9.26Gbps CPU utilization: 12-13% 1.4 ethtool -K gre1 gro on; ethtool -K eth0 gro on thruput: 9.26Gbps CPU utilization: 10% The following tests were performed on a different NIC that is capable of csum offload. I.e., the h/w is capable of computing IP payload csum (CHECKSUM_COMPLETE). 2.1 ethtool -K gre1 gro on (hence will use gro_cells) 2.1.1 ethtool -K eth0 gro off; csum offload disabled thruput: 8.53Gbps CPU utilization: 9% 2.1.2 ethtool -K eth0 gro off; csum offload enabled thruput: 8.97Gbps CPU utilization: 7-8% 2.1.3 ethtool -K eth0 gro on; csum offload disabled thruput: 8.83Gbps CPU utilization: 5-6% 2.1.4 ethtool -K eth0 gro on; csum offload enabled thruput: 8.98Gbps CPU utilization: 5% 2.2 ethtool -K gre1 gro off 2.2.1 ethtool -K eth0 gro off; csum offload disabled thruput: 5.93Gbps CPU utilization: 9% 2.2.2 ethtool -K eth0 gro off; csum offload enabled thruput: 5.62Gbps CPU utilization: 8% 2.2.3 ethtool -K eth0 gro on; csum offload disabled thruput: 7.69Gbps CPU utilization: 8% 2.2.4 ethtool -K eth0 gro on; csum offload enabled thruput: 8.96Gbps CPU utilization: 5-6% Signed-off-by: H.K. Jerry Chu <hkchu@google.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
298 lines
7.1 KiB
C
298 lines
7.1 KiB
C
/*
|
|
* IPV4 GSO/GRO offload support
|
|
* Linux INET implementation
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*
|
|
* GRE GSO support
|
|
*/
|
|
|
|
#include <linux/skbuff.h>
|
|
#include <net/protocol.h>
|
|
#include <net/gre.h>
|
|
|
|
static int gre_gso_send_check(struct sk_buff *skb)
|
|
{
|
|
if (!skb->encapsulation)
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|
|
|
|
static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
|
|
netdev_features_t features)
|
|
{
|
|
struct sk_buff *segs = ERR_PTR(-EINVAL);
|
|
netdev_features_t enc_features;
|
|
int ghl = GRE_HEADER_SECTION;
|
|
struct gre_base_hdr *greh;
|
|
u16 mac_offset = skb->mac_header;
|
|
int mac_len = skb->mac_len;
|
|
__be16 protocol = skb->protocol;
|
|
int tnl_hlen;
|
|
bool csum;
|
|
|
|
if (unlikely(skb_shinfo(skb)->gso_type &
|
|
~(SKB_GSO_TCPV4 |
|
|
SKB_GSO_TCPV6 |
|
|
SKB_GSO_UDP |
|
|
SKB_GSO_DODGY |
|
|
SKB_GSO_TCP_ECN |
|
|
SKB_GSO_GRE |
|
|
SKB_GSO_IPIP)))
|
|
goto out;
|
|
|
|
if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
|
|
goto out;
|
|
|
|
greh = (struct gre_base_hdr *)skb_transport_header(skb);
|
|
|
|
if (greh->flags & GRE_KEY)
|
|
ghl += GRE_HEADER_SECTION;
|
|
if (greh->flags & GRE_SEQ)
|
|
ghl += GRE_HEADER_SECTION;
|
|
if (greh->flags & GRE_CSUM) {
|
|
ghl += GRE_HEADER_SECTION;
|
|
csum = true;
|
|
} else
|
|
csum = false;
|
|
|
|
if (unlikely(!pskb_may_pull(skb, ghl)))
|
|
goto out;
|
|
|
|
/* setup inner skb. */
|
|
skb->protocol = greh->protocol;
|
|
skb->encapsulation = 0;
|
|
|
|
__skb_pull(skb, ghl);
|
|
skb_reset_mac_header(skb);
|
|
skb_set_network_header(skb, skb_inner_network_offset(skb));
|
|
skb->mac_len = skb_inner_network_offset(skb);
|
|
|
|
/* segment inner packet. */
|
|
enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
|
|
segs = skb_mac_gso_segment(skb, enc_features);
|
|
if (!segs || IS_ERR(segs)) {
|
|
skb_gso_error_unwind(skb, protocol, ghl, mac_offset, mac_len);
|
|
goto out;
|
|
}
|
|
|
|
skb = segs;
|
|
tnl_hlen = skb_tnl_header_len(skb);
|
|
do {
|
|
__skb_push(skb, ghl);
|
|
if (csum) {
|
|
__be32 *pcsum;
|
|
|
|
if (skb_has_shared_frag(skb)) {
|
|
int err;
|
|
|
|
err = __skb_linearize(skb);
|
|
if (err) {
|
|
kfree_skb_list(segs);
|
|
segs = ERR_PTR(err);
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
greh = (struct gre_base_hdr *)(skb->data);
|
|
pcsum = (__be32 *)(greh + 1);
|
|
*pcsum = 0;
|
|
*(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0));
|
|
}
|
|
__skb_push(skb, tnl_hlen - ghl);
|
|
|
|
skb_reset_inner_headers(skb);
|
|
skb->encapsulation = 1;
|
|
|
|
skb_reset_mac_header(skb);
|
|
skb_set_network_header(skb, mac_len);
|
|
skb->mac_len = mac_len;
|
|
skb->protocol = protocol;
|
|
} while ((skb = skb->next));
|
|
out:
|
|
return segs;
|
|
}
|
|
|
|
/* Compute the whole skb csum in s/w and store it, then verify GRO csum
|
|
* starting from gro_offset.
|
|
*/
|
|
static __sum16 gro_skb_checksum(struct sk_buff *skb)
|
|
{
|
|
__sum16 sum;
|
|
|
|
skb->csum = skb_checksum(skb, 0, skb->len, 0);
|
|
NAPI_GRO_CB(skb)->csum = csum_sub(skb->csum,
|
|
csum_partial(skb->data, skb_gro_offset(skb), 0));
|
|
sum = csum_fold(NAPI_GRO_CB(skb)->csum);
|
|
if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) {
|
|
if (unlikely(!sum))
|
|
netdev_rx_csum_fault(skb->dev);
|
|
} else
|
|
skb->ip_summed = CHECKSUM_COMPLETE;
|
|
|
|
return sum;
|
|
}
|
|
|
|
static struct sk_buff **gre_gro_receive(struct sk_buff **head,
|
|
struct sk_buff *skb)
|
|
{
|
|
struct sk_buff **pp = NULL;
|
|
struct sk_buff *p;
|
|
const struct gre_base_hdr *greh;
|
|
unsigned int hlen, grehlen;
|
|
unsigned int off;
|
|
int flush = 1;
|
|
struct packet_offload *ptype;
|
|
__be16 type;
|
|
|
|
off = skb_gro_offset(skb);
|
|
hlen = off + sizeof(*greh);
|
|
greh = skb_gro_header_fast(skb, off);
|
|
if (skb_gro_header_hard(skb, hlen)) {
|
|
greh = skb_gro_header_slow(skb, hlen, off);
|
|
if (unlikely(!greh))
|
|
goto out;
|
|
}
|
|
|
|
/* Only support version 0 and K (key), C (csum) flags. Note that
|
|
* although the support for the S (seq#) flag can be added easily
|
|
* for GRO, this is problematic for GSO hence can not be enabled
|
|
* here because a GRO pkt may end up in the forwarding path, thus
|
|
* requiring GSO support to break it up correctly.
|
|
*/
|
|
if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0)
|
|
goto out;
|
|
|
|
type = greh->protocol;
|
|
|
|
rcu_read_lock();
|
|
ptype = gro_find_receive_by_type(type);
|
|
if (ptype == NULL)
|
|
goto out_unlock;
|
|
|
|
grehlen = GRE_HEADER_SECTION;
|
|
|
|
if (greh->flags & GRE_KEY)
|
|
grehlen += GRE_HEADER_SECTION;
|
|
|
|
if (greh->flags & GRE_CSUM)
|
|
grehlen += GRE_HEADER_SECTION;
|
|
|
|
hlen = off + grehlen;
|
|
if (skb_gro_header_hard(skb, hlen)) {
|
|
greh = skb_gro_header_slow(skb, hlen, off);
|
|
if (unlikely(!greh))
|
|
goto out_unlock;
|
|
}
|
|
if (greh->flags & GRE_CSUM) { /* Need to verify GRE csum first */
|
|
__sum16 csum = 0;
|
|
|
|
if (skb->ip_summed == CHECKSUM_COMPLETE)
|
|
csum = csum_fold(NAPI_GRO_CB(skb)->csum);
|
|
/* Don't trust csum error calculated/reported by h/w */
|
|
if (skb->ip_summed == CHECKSUM_NONE || csum != 0)
|
|
csum = gro_skb_checksum(skb);
|
|
|
|
/* GRE CSUM is the 1's complement of the 1's complement sum
|
|
* of the GRE hdr plus payload so it should add up to 0xffff
|
|
* (and 0 after csum_fold()) just like the IPv4 hdr csum.
|
|
*/
|
|
if (csum)
|
|
goto out_unlock;
|
|
}
|
|
flush = 0;
|
|
|
|
for (p = *head; p; p = p->next) {
|
|
const struct gre_base_hdr *greh2;
|
|
|
|
if (!NAPI_GRO_CB(p)->same_flow)
|
|
continue;
|
|
|
|
/* The following checks are needed to ensure only pkts
|
|
* from the same tunnel are considered for aggregation.
|
|
* The criteria for "the same tunnel" includes:
|
|
* 1) same version (we only support version 0 here)
|
|
* 2) same protocol (we only support ETH_P_IP for now)
|
|
* 3) same set of flags
|
|
* 4) same key if the key field is present.
|
|
*/
|
|
greh2 = (struct gre_base_hdr *)(p->data + off);
|
|
|
|
if (greh2->flags != greh->flags ||
|
|
greh2->protocol != greh->protocol) {
|
|
NAPI_GRO_CB(p)->same_flow = 0;
|
|
continue;
|
|
}
|
|
if (greh->flags & GRE_KEY) {
|
|
/* compare keys */
|
|
if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) {
|
|
NAPI_GRO_CB(p)->same_flow = 0;
|
|
continue;
|
|
}
|
|
}
|
|
}
|
|
|
|
skb_gro_pull(skb, grehlen);
|
|
|
|
/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
|
|
skb_gro_postpull_rcsum(skb, greh, grehlen);
|
|
|
|
pp = ptype->callbacks.gro_receive(head, skb);
|
|
|
|
out_unlock:
|
|
rcu_read_unlock();
|
|
out:
|
|
NAPI_GRO_CB(skb)->flush |= flush;
|
|
|
|
return pp;
|
|
}
|
|
|
|
int gre_gro_complete(struct sk_buff *skb, int nhoff)
|
|
{
|
|
struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff);
|
|
struct packet_offload *ptype;
|
|
unsigned int grehlen = sizeof(*greh);
|
|
int err = -ENOENT;
|
|
__be16 type;
|
|
|
|
type = greh->protocol;
|
|
if (greh->flags & GRE_KEY)
|
|
grehlen += GRE_HEADER_SECTION;
|
|
|
|
if (greh->flags & GRE_CSUM)
|
|
grehlen += GRE_HEADER_SECTION;
|
|
|
|
rcu_read_lock();
|
|
ptype = gro_find_complete_by_type(type);
|
|
if (ptype != NULL)
|
|
err = ptype->callbacks.gro_complete(skb, nhoff + grehlen);
|
|
|
|
rcu_read_unlock();
|
|
return err;
|
|
}
|
|
|
|
static const struct net_offload gre_offload = {
|
|
.callbacks = {
|
|
.gso_send_check = gre_gso_send_check,
|
|
.gso_segment = gre_gso_segment,
|
|
.gro_receive = gre_gro_receive,
|
|
.gro_complete = gre_gro_complete,
|
|
},
|
|
};
|
|
|
|
static int __init gre_offload_init(void)
|
|
{
|
|
return inet_add_offload(&gre_offload, IPPROTO_GRE);
|
|
}
|
|
|
|
static void __exit gre_offload_exit(void)
|
|
{
|
|
inet_del_offload(&gre_offload, IPPROTO_GRE);
|
|
}
|
|
|
|
module_init(gre_offload_init);
|
|
module_exit(gre_offload_exit);
|