![Simon Horman](/assets/img/avatar_default.png)
In the case where a non-MPLS packet is received and an MPLS stack is added it may well be the case that the original skb is GSO but the NIC used for transmit does not support GSO of MPLS packets. The aim of this code is to provide GSO in software for MPLS packets whose skbs are GSO. SKB Usage: When an implementation adds an MPLS stack to a non-MPLS packet it should do the following to skb metadata: * Set skb->inner_protocol to the old non-MPLS ethertype of the packet. skb->inner_protocol is added by this patch. * Set skb->protocol to the new MPLS ethertype of the packet. * Set skb->network_header to correspond to the end of the L3 header, including the MPLS label stack. I have posted a patch, "[PATCH v3.29] datapath: Add basic MPLS support to kernel" which adds MPLS support to the kernel datapath of Open vSwtich. That patch sets the above requirements in datapath/actions.c:push_mpls() and was used to exercise this code. The datapath patch is against the Open vSwtich tree but it is intended that it be added to the Open vSwtich code present in the mainline Linux kernel at some point. Features: I believe that the approach that I have taken is at least partially consistent with the handling of other protocols. Jesse, I understand that you have some ideas here. I am more than happy to change my implementation. This patch adds dev->mpls_features which may be used by devices to advertise features supported for MPLS packets. A new NETIF_F_MPLS_GSO feature is added for devices which support hardware MPLS GSO offload. Currently no devices support this and MPLS GSO always falls back to software. Alternate Implementation: One possible alternate implementation is to teach netif_skb_features() and skb_network_protocol() about MPLS, in a similar way to their understanding of VLANs. I believe this would avoid the need for net/mpls/mpls_gso.c and in particular the calls to __skb_push() and __skb_push() in mpls_gso_segment(). I have decided on the implementation in this patch as it should not introduce any overhead in the case where mpls_gso is not compiled into the kernel or inserted as a module. MPLS GSO suggested by Jesse Gross. Based in part on "v4 GRE: Add TCP segmentation offload for GRE" by Pravin B Shelar. Cc: Jesse Gross <jesse@nicira.com> Cc: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
129 lines
3.5 KiB
C
129 lines
3.5 KiB
C
/*
|
|
* IPV6 GSO/GRO offload support
|
|
* Linux INET6 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.
|
|
*
|
|
* UDPv6 GSO support
|
|
*/
|
|
#include <linux/skbuff.h>
|
|
#include <net/protocol.h>
|
|
#include <net/ipv6.h>
|
|
#include <net/udp.h>
|
|
#include <net/ip6_checksum.h>
|
|
#include "ip6_offload.h"
|
|
|
|
static int udp6_ufo_send_check(struct sk_buff *skb)
|
|
{
|
|
const struct ipv6hdr *ipv6h;
|
|
struct udphdr *uh;
|
|
|
|
/* UDP Tunnel offload on ipv6 is not yet supported. */
|
|
if (skb->encapsulation)
|
|
return -EINVAL;
|
|
|
|
if (!pskb_may_pull(skb, sizeof(*uh)))
|
|
return -EINVAL;
|
|
|
|
ipv6h = ipv6_hdr(skb);
|
|
uh = udp_hdr(skb);
|
|
|
|
uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len,
|
|
IPPROTO_UDP, 0);
|
|
skb->csum_start = skb_transport_header(skb) - skb->head;
|
|
skb->csum_offset = offsetof(struct udphdr, check);
|
|
skb->ip_summed = CHECKSUM_PARTIAL;
|
|
return 0;
|
|
}
|
|
|
|
static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
|
|
netdev_features_t features)
|
|
{
|
|
struct sk_buff *segs = ERR_PTR(-EINVAL);
|
|
unsigned int mss;
|
|
unsigned int unfrag_ip6hlen, unfrag_len;
|
|
struct frag_hdr *fptr;
|
|
u8 *mac_start, *prevhdr;
|
|
u8 nexthdr;
|
|
u8 frag_hdr_sz = sizeof(struct frag_hdr);
|
|
int offset;
|
|
__wsum csum;
|
|
|
|
mss = skb_shinfo(skb)->gso_size;
|
|
if (unlikely(skb->len <= mss))
|
|
goto out;
|
|
|
|
if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
|
|
/* Packet is from an untrusted source, reset gso_segs. */
|
|
int type = skb_shinfo(skb)->gso_type;
|
|
|
|
if (unlikely(type & ~(SKB_GSO_UDP |
|
|
SKB_GSO_DODGY |
|
|
SKB_GSO_UDP_TUNNEL |
|
|
SKB_GSO_GRE |
|
|
SKB_GSO_MPLS) ||
|
|
!(type & (SKB_GSO_UDP))))
|
|
goto out;
|
|
|
|
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
|
|
|
|
segs = NULL;
|
|
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.
|
|
*/
|
|
offset = skb_checksum_start_offset(skb);
|
|
csum = skb_checksum(skb, offset, skb->len - offset, 0);
|
|
offset += skb->csum_offset;
|
|
*(__sum16 *)(skb->data + offset) = csum_fold(csum);
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
|
|
/* Check if there is enough headroom to insert fragment header. */
|
|
if ((skb_mac_header(skb) < skb->head + frag_hdr_sz) &&
|
|
pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC))
|
|
goto out;
|
|
|
|
/* Find the unfragmentable header and shift it left by frag_hdr_sz
|
|
* bytes to insert fragment header.
|
|
*/
|
|
unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
|
|
nexthdr = *prevhdr;
|
|
*prevhdr = NEXTHDR_FRAGMENT;
|
|
unfrag_len = skb_network_header(skb) - skb_mac_header(skb) +
|
|
unfrag_ip6hlen;
|
|
mac_start = skb_mac_header(skb);
|
|
memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len);
|
|
|
|
skb->mac_header -= frag_hdr_sz;
|
|
skb->network_header -= frag_hdr_sz;
|
|
|
|
fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
|
|
fptr->nexthdr = nexthdr;
|
|
fptr->reserved = 0;
|
|
ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb));
|
|
|
|
/* Fragment the skb. ipv6 header and the remaining fields of the
|
|
* fragment header are updated in ipv6_gso_segment()
|
|
*/
|
|
segs = skb_segment(skb, features);
|
|
|
|
out:
|
|
return segs;
|
|
}
|
|
static const struct net_offload udpv6_offload = {
|
|
.callbacks = {
|
|
.gso_send_check = udp6_ufo_send_check,
|
|
.gso_segment = udp6_ufo_fragment,
|
|
},
|
|
};
|
|
|
|
int __init udp_offload_init(void)
|
|
{
|
|
return inet6_add_offload(&udpv6_offload, IPPROTO_UDP);
|
|
}
|