From 0d89d2035fe063461a5ddb609b2c12e7fb006e44 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 23 May 2013 21:02:52 +0000 Subject: MPLS: Add limited GSO support 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 Cc: Pravin B Shelar Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4/af_inet.c') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index d01be2a3ae53..b05ae96aec44 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1295,6 +1295,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_GRE | SKB_GSO_TCPV6 | SKB_GSO_UDP_TUNNEL | + SKB_GSO_MPLS | 0))) goto out; -- cgit v1.2.3 From db8caf3dbc77599dc90f4ea0a803cd1d97116f30 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 31 May 2013 11:18:10 +0000 Subject: gro: should aggregate frames without DF GRO on IPv4 doesn't aggregate frames if they don't have DF bit set. Some servers use IP_MTU_DISCOVER/IP_PMTUDISC_PROBE, so linux receivers are unable to aggregate this kind of traffic. The right thing to do is to allow aggregation as long as the DF bit has same value on all segments. bnx2x LRO does this correctly. Signed-off-by: Eric Dumazet Cc: Jerry Chu Cc: Herbert Xu Cc: Ben Hutchings Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4/af_inet.c') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b05ae96aec44..9c090c7daea1 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1385,7 +1385,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, goto out_unlock; id = ntohl(*(__be32 *)&iph->id); - flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF)); + flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); id >>= 16; for (p = *head; p; p = p->next) { @@ -1407,6 +1407,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, NAPI_GRO_CB(p)->flush |= (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | + ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) | ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id); NAPI_GRO_CB(p)->flush |= flush; -- cgit v1.2.3 From 28850dc7c71da9d0c0e39246e9ff6913f41f8d0a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 7 Jun 2013 05:11:46 +0000 Subject: net: tcp: move GRO/GSO functions to tcp_offload Would be good to make things explicit and move those functions to a new file called tcp_offload.c, thus make this similar to tcpv6_offload.c. While moving all related functions into tcp_offload.c, we can also make some of them static, since they are only used there. Also, add an explicit registration function. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'net/ipv4/af_inet.c') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9c090c7daea1..7b514290efc6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1559,15 +1559,6 @@ static const struct net_protocol tcp_protocol = { .netns_ok = 1, }; -static const struct net_offload tcp_offload = { - .callbacks = { - .gso_send_check = tcp_v4_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, - }, -}; - static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, @@ -1683,8 +1674,8 @@ static int __init ipv4_offload_init(void) */ if (inet_add_offload(&udp_offload, IPPROTO_UDP) < 0) pr_crit("%s: Cannot add UDP protocol offload\n", __func__); - if (inet_add_offload(&tcp_offload, IPPROTO_TCP) < 0) - pr_crit("%s: Cannot add TCP protocol offlaod\n", __func__); + if (tcpv4_offload_init() < 0) + pr_crit("%s: Cannot add TCP protocol offload\n", __func__); dev_add_offload(&ip_packet_offload); return 0; -- cgit v1.2.3 From da5bab079f9b7d90ba234965a14914ace55e45e9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 8 Jun 2013 12:56:03 +0200 Subject: net: udp4: move GSO functions to udp_offload Similarly to TCP offloading and UDPv6 offloading, move all related UDPv4 functions to udp_offload.c to make things more explicit. Also, by this, we can make those functions static. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'net/ipv4/af_inet.c') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 7b514290efc6..5598b06d62db 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1566,13 +1566,6 @@ static const struct net_protocol udp_protocol = { .netns_ok = 1, }; -static const struct net_offload udp_offload = { - .callbacks = { - .gso_send_check = udp4_ufo_send_check, - .gso_segment = udp4_ufo_fragment, - }, -}; - static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, @@ -1672,7 +1665,7 @@ static int __init ipv4_offload_init(void) /* * Add offloads */ - if (inet_add_offload(&udp_offload, IPPROTO_UDP) < 0) + if (udpv4_offload_init() < 0) pr_crit("%s: Cannot add UDP protocol offload\n", __func__); if (tcpv4_offload_init() < 0) pr_crit("%s: Cannot add TCP protocol offload\n", __func__); -- cgit v1.2.3 From 5b9b6263775d45ccc0c8b27344bfb1a97cf6f725 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 12 Jun 2013 14:23:15 -0700 Subject: gro: remove a sparse error Fix following sparse error : net/ipv4/af_inet.c:1410:59: warning: restricted __be16 degrades to integer added in commit db8caf3dbc77599 ("gro: should aggregate frames without DF") Reported-by: kbuild test robot From: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/af_inet.c') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5598b06d62db..b4d0be2b7ce9 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1407,7 +1407,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, NAPI_GRO_CB(p)->flush |= (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | - ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) | + (__force int)((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) | ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id); NAPI_GRO_CB(p)->flush |= flush; -- cgit v1.2.3