mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Alexander Duyck](/assets/img/avatar_default.png)
This patch allows us to take care of unrolling the first segment and the last segment of the loop for processing the segmented skb. Part of the motivation for this is that it makes it easier to process the fact that the first fame and all of the frames in between should be mostly identical in terms of header data, and the last frame has differences in the length and partial checksum. In addition I am dropping the header length calculation since we don't really need it for anything but the last frame and it can be easily obtained by just pulling the data_len and offset of tail from the transport header. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
462 lines
12 KiB
C
462 lines
12 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.
|
|
*
|
|
* UDPv4 GSO support
|
|
*/
|
|
|
|
#include <linux/skbuff.h>
|
|
#include <net/udp.h>
|
|
#include <net/protocol.h>
|
|
|
|
static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
|
|
netdev_features_t features,
|
|
struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
|
|
netdev_features_t features),
|
|
__be16 new_protocol, bool is_ipv6)
|
|
{
|
|
int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
|
|
bool remcsum, need_csum, offload_csum, gso_partial;
|
|
struct sk_buff *segs = ERR_PTR(-EINVAL);
|
|
struct udphdr *uh = udp_hdr(skb);
|
|
u16 mac_offset = skb->mac_header;
|
|
__be16 protocol = skb->protocol;
|
|
u16 mac_len = skb->mac_len;
|
|
int udp_offset, outer_hlen;
|
|
__wsum partial;
|
|
bool need_ipsec;
|
|
|
|
if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
|
|
goto out;
|
|
|
|
/* Adjust partial header checksum to negate old length.
|
|
* We cannot rely on the value contained in uh->len as it is
|
|
* possible that the actual value exceeds the boundaries of the
|
|
* 16 bit length field due to the header being added outside of an
|
|
* IP or IPv6 frame that was already limited to 64K - 1.
|
|
*/
|
|
if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)
|
|
partial = (__force __wsum)uh->len;
|
|
else
|
|
partial = (__force __wsum)htonl(skb->len);
|
|
partial = csum_sub(csum_unfold(uh->check), partial);
|
|
|
|
/* setup inner skb. */
|
|
skb->encapsulation = 0;
|
|
SKB_GSO_CB(skb)->encap_level = 0;
|
|
__skb_pull(skb, tnl_hlen);
|
|
skb_reset_mac_header(skb);
|
|
skb_set_network_header(skb, skb_inner_network_offset(skb));
|
|
skb->mac_len = skb_inner_network_offset(skb);
|
|
skb->protocol = new_protocol;
|
|
|
|
need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
|
|
skb->encap_hdr_csum = need_csum;
|
|
|
|
remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM);
|
|
skb->remcsum_offload = remcsum;
|
|
|
|
need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
|
|
/* Try to offload checksum if possible */
|
|
offload_csum = !!(need_csum &&
|
|
!need_ipsec &&
|
|
(skb->dev->features &
|
|
(is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) :
|
|
(NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
|
|
|
|
features &= skb->dev->hw_enc_features;
|
|
|
|
/* The only checksum offload we care about from here on out is the
|
|
* outer one so strip the existing checksum feature flags and
|
|
* instead set the flag based on our outer checksum offload value.
|
|
*/
|
|
if (remcsum) {
|
|
features &= ~NETIF_F_CSUM_MASK;
|
|
if (!need_csum || offload_csum)
|
|
features |= NETIF_F_HW_CSUM;
|
|
}
|
|
|
|
/* segment inner packet. */
|
|
segs = gso_inner_segment(skb, features);
|
|
if (IS_ERR_OR_NULL(segs)) {
|
|
skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
|
|
mac_len);
|
|
goto out;
|
|
}
|
|
|
|
gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
|
|
|
|
outer_hlen = skb_tnl_header_len(skb);
|
|
udp_offset = outer_hlen - tnl_hlen;
|
|
skb = segs;
|
|
do {
|
|
unsigned int len;
|
|
|
|
if (remcsum)
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
|
|
/* Set up inner headers if we are offloading inner checksum */
|
|
if (skb->ip_summed == CHECKSUM_PARTIAL) {
|
|
skb_reset_inner_headers(skb);
|
|
skb->encapsulation = 1;
|
|
}
|
|
|
|
skb->mac_len = mac_len;
|
|
skb->protocol = protocol;
|
|
|
|
__skb_push(skb, outer_hlen);
|
|
skb_reset_mac_header(skb);
|
|
skb_set_network_header(skb, mac_len);
|
|
skb_set_transport_header(skb, udp_offset);
|
|
len = skb->len - udp_offset;
|
|
uh = udp_hdr(skb);
|
|
|
|
/* If we are only performing partial GSO the inner header
|
|
* will be using a length value equal to only one MSS sized
|
|
* segment instead of the entire frame.
|
|
*/
|
|
if (gso_partial && skb_is_gso(skb)) {
|
|
uh->len = htons(skb_shinfo(skb)->gso_size +
|
|
SKB_GSO_CB(skb)->data_offset +
|
|
skb->head - (unsigned char *)uh);
|
|
} else {
|
|
uh->len = htons(len);
|
|
}
|
|
|
|
if (!need_csum)
|
|
continue;
|
|
|
|
uh->check = ~csum_fold(csum_add(partial,
|
|
(__force __wsum)htonl(len)));
|
|
|
|
if (skb->encapsulation || !offload_csum) {
|
|
uh->check = gso_make_checksum(skb, ~uh->check);
|
|
if (uh->check == 0)
|
|
uh->check = CSUM_MANGLED_0;
|
|
} else {
|
|
skb->ip_summed = CHECKSUM_PARTIAL;
|
|
skb->csum_start = skb_transport_header(skb) - skb->head;
|
|
skb->csum_offset = offsetof(struct udphdr, check);
|
|
}
|
|
} while ((skb = skb->next));
|
|
out:
|
|
return segs;
|
|
}
|
|
|
|
struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
|
|
netdev_features_t features,
|
|
bool is_ipv6)
|
|
{
|
|
__be16 protocol = skb->protocol;
|
|
const struct net_offload **offloads;
|
|
const struct net_offload *ops;
|
|
struct sk_buff *segs = ERR_PTR(-EINVAL);
|
|
struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
|
|
netdev_features_t features);
|
|
|
|
rcu_read_lock();
|
|
|
|
switch (skb->inner_protocol_type) {
|
|
case ENCAP_TYPE_ETHER:
|
|
protocol = skb->inner_protocol;
|
|
gso_inner_segment = skb_mac_gso_segment;
|
|
break;
|
|
case ENCAP_TYPE_IPPROTO:
|
|
offloads = is_ipv6 ? inet6_offloads : inet_offloads;
|
|
ops = rcu_dereference(offloads[skb->inner_ipproto]);
|
|
if (!ops || !ops->callbacks.gso_segment)
|
|
goto out_unlock;
|
|
gso_inner_segment = ops->callbacks.gso_segment;
|
|
break;
|
|
default:
|
|
goto out_unlock;
|
|
}
|
|
|
|
segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment,
|
|
protocol, is_ipv6);
|
|
|
|
out_unlock:
|
|
rcu_read_unlock();
|
|
|
|
return segs;
|
|
}
|
|
EXPORT_SYMBOL(skb_udp_tunnel_segment);
|
|
|
|
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
|
|
netdev_features_t features)
|
|
{
|
|
struct sock *sk = gso_skb->sk;
|
|
unsigned int sum_truesize = 0;
|
|
struct sk_buff *segs, *seg;
|
|
struct udphdr *uh;
|
|
unsigned int mss;
|
|
__sum16 check;
|
|
__be16 newlen;
|
|
|
|
mss = skb_shinfo(gso_skb)->gso_size;
|
|
if (gso_skb->len <= sizeof(*uh) + mss)
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
skb_pull(gso_skb, sizeof(*uh));
|
|
|
|
/* clear destructor to avoid skb_segment assigning it to tail */
|
|
WARN_ON_ONCE(gso_skb->destructor != sock_wfree);
|
|
gso_skb->destructor = NULL;
|
|
|
|
segs = skb_segment(gso_skb, features);
|
|
if (unlikely(IS_ERR_OR_NULL(segs))) {
|
|
gso_skb->destructor = sock_wfree;
|
|
return segs;
|
|
}
|
|
|
|
seg = segs;
|
|
uh = udp_hdr(seg);
|
|
|
|
/* compute checksum adjustment based on old length versus new */
|
|
newlen = htons(sizeof(*uh) + mss);
|
|
check = csum16_add(csum16_sub(uh->check, uh->len), newlen);
|
|
|
|
for (;;) {
|
|
seg->destructor = sock_wfree;
|
|
seg->sk = sk;
|
|
sum_truesize += seg->truesize;
|
|
|
|
if (!seg->next)
|
|
break;
|
|
|
|
uh->len = newlen;
|
|
uh->check = check;
|
|
|
|
seg = seg->next;
|
|
uh = udp_hdr(seg);
|
|
}
|
|
|
|
/* last packet can be partial gso_size, account for that in checksum */
|
|
newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) +
|
|
seg->data_len);
|
|
check = csum16_add(csum16_sub(uh->check, uh->len), newlen);
|
|
|
|
uh->len = newlen;
|
|
uh->check = check;
|
|
|
|
/* update refcount for the packet */
|
|
refcount_add(sum_truesize - gso_skb->truesize, &sk->sk_wmem_alloc);
|
|
|
|
return segs;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__udp_gso_segment);
|
|
|
|
static struct sk_buff *__udp4_gso_segment(struct sk_buff *gso_skb,
|
|
netdev_features_t features)
|
|
{
|
|
if (!can_checksum_protocol(features, htons(ETH_P_IP)))
|
|
return ERR_PTR(-EIO);
|
|
|
|
return __udp_gso_segment(gso_skb, features);
|
|
}
|
|
|
|
static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
|
|
netdev_features_t features)
|
|
{
|
|
struct sk_buff *segs = ERR_PTR(-EINVAL);
|
|
unsigned int mss;
|
|
__wsum csum;
|
|
struct udphdr *uh;
|
|
struct iphdr *iph;
|
|
|
|
if (skb->encapsulation &&
|
|
(skb_shinfo(skb)->gso_type &
|
|
(SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
|
|
segs = skb_udp_tunnel_segment(skb, features, false);
|
|
goto out;
|
|
}
|
|
|
|
if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4)))
|
|
goto out;
|
|
|
|
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
|
|
goto out;
|
|
|
|
if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
|
|
return __udp4_gso_segment(skb, features);
|
|
|
|
mss = skb_shinfo(skb)->gso_size;
|
|
if (unlikely(skb->len <= mss))
|
|
goto out;
|
|
|
|
/* Do software UFO. Complete and fill in the UDP checksum as
|
|
* HW cannot do checksum of UDP packets sent as multiple
|
|
* IP fragments.
|
|
*/
|
|
|
|
uh = udp_hdr(skb);
|
|
iph = ip_hdr(skb);
|
|
|
|
uh->check = 0;
|
|
csum = skb_checksum(skb, 0, skb->len, 0);
|
|
uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
|
|
if (uh->check == 0)
|
|
uh->check = CSUM_MANGLED_0;
|
|
|
|
skb->ip_summed = CHECKSUM_UNNECESSARY;
|
|
|
|
/* If there is no outer header we can fake a checksum offload
|
|
* due to the fact that we have already done the checksum in
|
|
* software prior to segmenting the frame.
|
|
*/
|
|
if (!skb->encap_hdr_csum)
|
|
features |= NETIF_F_HW_CSUM;
|
|
|
|
/* Fragment the skb. IP headers of the fragments are updated in
|
|
* inet_gso_segment()
|
|
*/
|
|
segs = skb_segment(skb, features);
|
|
out:
|
|
return segs;
|
|
}
|
|
|
|
struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
|
|
struct udphdr *uh, udp_lookup_t lookup)
|
|
{
|
|
struct sk_buff *p, **pp = NULL;
|
|
struct udphdr *uh2;
|
|
unsigned int off = skb_gro_offset(skb);
|
|
int flush = 1;
|
|
struct sock *sk;
|
|
|
|
if (NAPI_GRO_CB(skb)->encap_mark ||
|
|
(skb->ip_summed != CHECKSUM_PARTIAL &&
|
|
NAPI_GRO_CB(skb)->csum_cnt == 0 &&
|
|
!NAPI_GRO_CB(skb)->csum_valid))
|
|
goto out;
|
|
|
|
/* mark that this skb passed once through the tunnel gro layer */
|
|
NAPI_GRO_CB(skb)->encap_mark = 1;
|
|
|
|
rcu_read_lock();
|
|
sk = (*lookup)(skb, uh->source, uh->dest);
|
|
|
|
if (sk && udp_sk(sk)->gro_receive)
|
|
goto unflush;
|
|
goto out_unlock;
|
|
|
|
unflush:
|
|
flush = 0;
|
|
|
|
for (p = *head; p; p = p->next) {
|
|
if (!NAPI_GRO_CB(p)->same_flow)
|
|
continue;
|
|
|
|
uh2 = (struct udphdr *)(p->data + off);
|
|
|
|
/* Match ports and either checksums are either both zero
|
|
* or nonzero.
|
|
*/
|
|
if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) ||
|
|
(!uh->check ^ !uh2->check)) {
|
|
NAPI_GRO_CB(p)->same_flow = 0;
|
|
continue;
|
|
}
|
|
}
|
|
|
|
skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
|
|
skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
|
|
pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
|
|
|
|
out_unlock:
|
|
rcu_read_unlock();
|
|
out:
|
|
NAPI_GRO_CB(skb)->flush |= flush;
|
|
return pp;
|
|
}
|
|
EXPORT_SYMBOL(udp_gro_receive);
|
|
|
|
static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
|
|
struct sk_buff *skb)
|
|
{
|
|
struct udphdr *uh = udp_gro_udphdr(skb);
|
|
|
|
if (unlikely(!uh))
|
|
goto flush;
|
|
|
|
/* Don't bother verifying checksum if we're going to flush anyway. */
|
|
if (NAPI_GRO_CB(skb)->flush)
|
|
goto skip;
|
|
|
|
if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
|
|
inet_gro_compute_pseudo))
|
|
goto flush;
|
|
else if (uh->check)
|
|
skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
|
|
inet_gro_compute_pseudo);
|
|
skip:
|
|
NAPI_GRO_CB(skb)->is_ipv6 = 0;
|
|
return udp_gro_receive(head, skb, uh, udp4_lib_lookup_skb);
|
|
|
|
flush:
|
|
NAPI_GRO_CB(skb)->flush = 1;
|
|
return NULL;
|
|
}
|
|
|
|
int udp_gro_complete(struct sk_buff *skb, int nhoff,
|
|
udp_lookup_t lookup)
|
|
{
|
|
__be16 newlen = htons(skb->len - nhoff);
|
|
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
|
|
int err = -ENOSYS;
|
|
struct sock *sk;
|
|
|
|
uh->len = newlen;
|
|
|
|
/* Set encapsulation before calling into inner gro_complete() functions
|
|
* to make them set up the inner offsets.
|
|
*/
|
|
skb->encapsulation = 1;
|
|
|
|
rcu_read_lock();
|
|
sk = (*lookup)(skb, uh->source, uh->dest);
|
|
if (sk && udp_sk(sk)->gro_complete)
|
|
err = udp_sk(sk)->gro_complete(sk, skb,
|
|
nhoff + sizeof(struct udphdr));
|
|
rcu_read_unlock();
|
|
|
|
if (skb->remcsum_offload)
|
|
skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM;
|
|
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL(udp_gro_complete);
|
|
|
|
static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
|
|
{
|
|
const struct iphdr *iph = ip_hdr(skb);
|
|
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
|
|
|
|
if (uh->check) {
|
|
skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
|
|
uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
|
|
iph->daddr, 0);
|
|
} else {
|
|
skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
|
|
}
|
|
|
|
return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
|
|
}
|
|
|
|
static const struct net_offload udpv4_offload = {
|
|
.callbacks = {
|
|
.gso_segment = udp4_ufo_fragment,
|
|
.gro_receive = udp4_gro_receive,
|
|
.gro_complete = udp4_gro_complete,
|
|
},
|
|
};
|
|
|
|
int __init udpv4_offload_init(void)
|
|
{
|
|
return inet_add_offload(&udpv4_offload, IPPROTO_UDP);
|
|
}
|