From 179bc67f69b6cb53ad68cfdec5a917c2a2248355 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 20:48:04 +0000 Subject: [PATCH 1/8] net: local checksum offload for encapsulation The arithmetic properties of the ones-complement checksum mean that a correctly checksummed inner packet, including its checksum, has a ones complement sum depending only on whatever value was used to initialise the checksum field before checksumming (in the case of TCP and UDP, this is the ones complement sum of the pseudo header, complemented). Consequently, if we are going to offload the inner checksum with CHECKSUM_PARTIAL, we can compute the outer checksum based only on the packed data not covered by the inner checksum, and the initial value of the inner checksum field. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/skbuff.h | 24 ++++++++++++++++++++++++ net/ipv4/ip_tunnel_core.c | 10 +++++----- net/ipv4/udp.c | 20 ++++++++++---------- net/ipv6/ip6_checksum.c | 14 +++++++------- 4 files changed, 46 insertions(+), 22 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6ec86f1a2ed9..cf906d1ce8a7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3702,5 +3702,29 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) return hdr_len + skb_gso_transport_seglen(skb); } +/* Local Checksum Offload. + * Compute outer checksum based on the assumption that the + * inner checksum will be offloaded later. + * Fill in outer checksum adjustment (e.g. with sum of outer + * pseudo-header) before calling. + * Also ensure that inner checksum is in linear data area. + */ +static inline __wsum lco_csum(struct sk_buff *skb) +{ + char *inner_csum_field; + __wsum csum; + + /* Start with complement of inner checksum adjustment */ + inner_csum_field = skb->data + skb_checksum_start_offset(skb) + + skb->csum_offset; + csum = ~csum_unfold(*(__force __sum16 *)inner_csum_field); + /* Add in checksum of our headers (incl. outer checksum + * adjustment filled in by caller) + */ + csum = skb_checksum(skb, 0, skb_checksum_start_offset(skb), csum); + /* The result is the checksum from skb->data to end of packet */ + return csum; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 859d415c0b2d..d74ce93de1fe 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -166,20 +166,20 @@ struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, return skb; } - /* If packet is not gso and we are resolving any partial checksum, + /* If packet is not gso and we are not offloading inner checksum, * clear encapsulation flag. This allows setting CHECKSUM_PARTIAL * on the outer header without confusing devices that implement * NETIF_F_IP_CSUM with encapsulation. */ - if (csum_help) - skb->encapsulation = 0; - if (skb->ip_summed == CHECKSUM_PARTIAL && csum_help) { + skb->encapsulation = 0; err = skb_checksum_help(skb); if (unlikely(err)) goto error; - } else if (skb->ip_summed != CHECKSUM_PARTIAL) + } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_NONE; + skb->encapsulation = 0; + } return skb; error: diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ac3cedb25a9f..a59341cf483e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -848,16 +848,18 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, { struct udphdr *uh = udp_hdr(skb); - if (nocheck) + if (nocheck) { uh->check = 0; - else if (skb_is_gso(skb)) + } else if (skb_is_gso(skb)) { uh->check = ~udp_v4_check(len, saddr, daddr, 0); - else if (skb_dst(skb) && skb_dst(skb)->dev && - (skb_dst(skb)->dev->features & - (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { - - BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); - + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + uh->check = 0; + uh->check = udp_v4_check(len, saddr, daddr, lco_csum(skb)); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } else if (skb_dst(skb) && skb_dst(skb)->dev && + (skb_dst(skb)->dev->features & + (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); @@ -865,8 +867,6 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, } else { __wsum csum; - BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); - uh->check = 0; csum = skb_checksum(skb, 0, len, 0); uh->check = udp_v4_check(len, saddr, daddr, csum); diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index 9a4d7322fb22..4924bd704e89 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -98,11 +98,13 @@ void udp6_set_csum(bool nocheck, struct sk_buff *skb, uh->check = 0; else if (skb_is_gso(skb)) uh->check = ~udp_v6_check(len, saddr, daddr, 0); - else if (skb_dst(skb) && skb_dst(skb)->dev && - (skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) { - - BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); - + else if (skb->ip_summed == CHECKSUM_PARTIAL) { + uh->check = 0; + uh->check = udp_v6_check(len, saddr, daddr, lco_csum(skb)); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } else if (skb_dst(skb) && skb_dst(skb)->dev && + (skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); @@ -110,8 +112,6 @@ void udp6_set_csum(bool nocheck, struct sk_buff *skb, } else { __wsum csum; - BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); - uh->check = 0; csum = skb_checksum(skb, 0, len, 0); uh->check = udp_v6_check(len, saddr, daddr, csum); From d75f1306d9464d535007f05e5da0afcf9e3916d9 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 20:49:40 +0000 Subject: [PATCH 2/8] net: udp: always set up for CHECKSUM_PARTIAL offload If the dst device doesn't support it, it'll get fixed up later anyway by validate_xmit_skb(). Also, this allows us to take advantage of LCO to avoid summing the payload multiple times. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- net/ipv4/udp.c | 14 +------------- net/ipv6/ip6_checksum.c | 13 +------------ 2 files changed, 2 insertions(+), 25 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a59341cf483e..9fc4e9c06aae 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -857,23 +857,11 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, uh->check = udp_v4_check(len, saddr, daddr, lco_csum(skb)); if (uh->check == 0) uh->check = CSUM_MANGLED_0; - } else if (skb_dst(skb) && skb_dst(skb)->dev && - (skb_dst(skb)->dev->features & - (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { + } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); uh->check = ~udp_v4_check(len, saddr, daddr, 0); - } else { - __wsum csum; - - uh->check = 0; - csum = skb_checksum(skb, 0, len, 0); - uh->check = udp_v4_check(len, saddr, daddr, csum); - if (uh->check == 0) - uh->check = CSUM_MANGLED_0; - - skb->ip_summed = CHECKSUM_UNNECESSARY; } } EXPORT_SYMBOL(udp_set_csum); diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index 4924bd704e89..8f920580976f 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -103,22 +103,11 @@ void udp6_set_csum(bool nocheck, struct sk_buff *skb, uh->check = udp_v6_check(len, saddr, daddr, lco_csum(skb)); if (uh->check == 0) uh->check = CSUM_MANGLED_0; - } else if (skb_dst(skb) && skb_dst(skb)->dev && - (skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) { + } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); uh->check = ~udp_v6_check(len, saddr, daddr, 0); - } else { - __wsum csum; - - uh->check = 0; - csum = skb_checksum(skb, 0, len, 0); - uh->check = udp_v6_check(len, saddr, daddr, csum); - if (uh->check == 0) - uh->check = CSUM_MANGLED_0; - - skb->ip_summed = CHECKSUM_UNNECESSARY; } } EXPORT_SYMBOL(udp6_set_csum); From 21e2e7f9b5fefdbf94a107a9b24d74baa5148ef3 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 20:50:44 +0000 Subject: [PATCH 3/8] net: enable LCO for udp_tunnel_handle_offloads() users The only protocol affected at present is Geneve. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/net/udp_tunnel.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index cca2ad3082c3..734c15662ea9 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -103,7 +103,8 @@ static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb, { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; - return iptunnel_handle_offloads(skb, udp_csum, type); + /* As we're a UDP tunnel, we support LCO, so don't need csum_help */ + return iptunnel_handle_offloads(skb, false, type); } static inline void udp_tunnel_gro_complete(struct sk_buff *skb, int nhoff) From b57085019dcdd52d40ba153c6957f9e5a2f4b931 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 20:57:17 +0000 Subject: [PATCH 4/8] net: vxlan: enable local checksum offload Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ebf57d90d295..9f52203ac860 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1702,10 +1702,8 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, if (csum_start <= VXLAN_MAX_REMCSUM_START && !(csum_start & VXLAN_RCO_SHIFT_MASK) && (skb->csum_offset == offsetof(struct udphdr, check) || - skb->csum_offset == offsetof(struct tcphdr, check))) { - udp_sum = false; + skb->csum_offset == offsetof(struct tcphdr, check))) type |= SKB_GSO_TUNNEL_REMCSUM; - } } min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len @@ -1723,7 +1721,7 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, if (WARN_ON(!skb)) return -ENOMEM; - skb = iptunnel_handle_offloads(skb, udp_sum, type); + skb = iptunnel_handle_offloads(skb, false, type); if (IS_ERR(skb)) return PTR_ERR(skb); From 06f622926d0cdf923e9b33ab9f0a4d4b45983e8a Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 21:00:16 +0000 Subject: [PATCH 5/8] fou: enable LCO in FOU and GUE Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- net/ipv4/fou.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 976f0dcf6991..dac1874a5911 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -774,7 +774,6 @@ static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, uh->dest = e->dport; uh->source = sport; uh->len = htons(skb->len); - uh->check = 0; udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb, fl4->saddr, fl4->daddr, skb->len); @@ -784,11 +783,11 @@ static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4) { - bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM); - int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; + int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : + SKB_GSO_UDP_TUNNEL; __be16 sport; - skb = iptunnel_handle_offloads(skb, csum, type); + skb = iptunnel_handle_offloads(skb, false, type); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -804,8 +803,8 @@ EXPORT_SYMBOL(fou_build_header); int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4) { - bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM); - int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; + int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : + SKB_GSO_UDP_TUNNEL; struct guehdr *guehdr; size_t hdrlen, optlen = 0; __be16 sport; @@ -814,7 +813,6 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, if ((e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) && skb->ip_summed == CHECKSUM_PARTIAL) { - csum = false; optlen += GUE_PLEN_REMCSUM; type |= SKB_GSO_TUNNEL_REMCSUM; need_priv = true; @@ -822,7 +820,7 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, optlen += need_priv ? GUE_LEN_PRIV : 0; - skb = iptunnel_handle_offloads(skb, csum, type); + skb = iptunnel_handle_offloads(skb, false, type); if (IS_ERR(skb)) return PTR_ERR(skb); From 53936107ba2462f714bae19a754f3ebf69a11e40 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 21:01:07 +0000 Subject: [PATCH 6/8] net: gre: Implement LCO for GRE over IPv4 Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7c51c4e1661f..9b31532d95f4 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -440,6 +440,17 @@ drop: return 0; } +static __sum16 gre_checksum(struct sk_buff *skb) +{ + __wsum csum; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + csum = lco_csum(skb); + else + csum = skb_checksum(skb, 0, skb->len, 0); + return csum_fold(csum); +} + static void build_header(struct sk_buff *skb, int hdr_len, __be16 flags, __be16 proto, __be32 key, __be32 seq) { @@ -467,8 +478,7 @@ static void build_header(struct sk_buff *skb, int hdr_len, __be16 flags, !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; - *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0, - skb->len, 0)); + *(__sum16 *)ptr = gre_checksum(skb); } } } @@ -493,7 +503,7 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, static struct sk_buff *gre_handle_offloads(struct sk_buff *skb, bool csum) { - return iptunnel_handle_offloads(skb, csum, + return iptunnel_handle_offloads(skb, false, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } From 6fa79666e24d32be1b709f5269af41ed9e829e7e Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 21:02:31 +0000 Subject: [PATCH 7/8] net: ip_tunnel: remove 'csum_help' argument to iptunnel_handle_offloads All users now pass false, so we can remove it, and remove the code that was conditional upon it. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 2 +- include/net/ip_tunnels.h | 3 +-- include/net/udp_tunnel.h | 3 +-- net/ipv4/fou.c | 4 ++-- net/ipv4/ip_gre.c | 3 +-- net/ipv4/ip_tunnel_core.c | 18 ++++++------------ net/ipv4/ipip.c | 2 +- net/ipv6/sit.c | 4 ++-- net/netfilter/ipvs/ip_vs_xmit.c | 6 ++---- 9 files changed, 17 insertions(+), 28 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 9f52203ac860..0a23c64379d6 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1721,7 +1721,7 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, if (WARN_ON(!skb)) return -ENOMEM; - skb = iptunnel_handle_offloads(skb, false, type); + skb = iptunnel_handle_offloads(skb, type); if (IS_ERR(skb)) return PTR_ERR(skb); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 6db96ea0144f..bc439f32baa9 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -279,8 +279,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags); -struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum, - int gso_type_mask); +struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask); static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) { diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 734c15662ea9..97f5adb121a6 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -103,8 +103,7 @@ static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb, { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; - /* As we're a UDP tunnel, we support LCO, so don't need csum_help */ - return iptunnel_handle_offloads(skb, false, type); + return iptunnel_handle_offloads(skb, type); } static inline void udp_tunnel_gro_complete(struct sk_buff *skb, int nhoff) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index dac1874a5911..88dab0c1670c 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -787,7 +787,7 @@ int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, SKB_GSO_UDP_TUNNEL; __be16 sport; - skb = iptunnel_handle_offloads(skb, false, type); + skb = iptunnel_handle_offloads(skb, type); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -820,7 +820,7 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, optlen += need_priv ? GUE_LEN_PRIV : 0; - skb = iptunnel_handle_offloads(skb, false, type); + skb = iptunnel_handle_offloads(skb, type); if (IS_ERR(skb)) return PTR_ERR(skb); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 9b31532d95f4..65748db44285 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -503,8 +503,7 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, static struct sk_buff *gre_handle_offloads(struct sk_buff *skb, bool csum) { - return iptunnel_handle_offloads(skb, false, - csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); + return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } static struct rtable *gre_get_rt(struct sk_buff *skb, diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index d74ce93de1fe..a6e58b6141cd 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -148,7 +148,6 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, EXPORT_SYMBOL_GPL(iptunnel_metadata_reply); struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, - bool csum_help, int gso_type_mask) { int err; @@ -166,18 +165,13 @@ struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, return skb; } - /* If packet is not gso and we are not offloading inner checksum, - * clear encapsulation flag. This allows setting CHECKSUM_PARTIAL - * on the outer header without confusing devices that implement - * NETIF_F_IP_CSUM with encapsulation. - */ - if (skb->ip_summed == CHECKSUM_PARTIAL && csum_help) { - skb->encapsulation = 0; - err = skb_checksum_help(skb); - if (unlikely(err)) - goto error; - } else if (skb->ip_summed != CHECKSUM_PARTIAL) { + if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_NONE; + /* We clear encapsulation here to prevent badly-written + * drivers potentially deciding to offload an inner checksum + * if we set CHECKSUM_PARTIAL on the outer header. + * This should go away when the drivers are all fixed. + */ skb->encapsulation = 0; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 4044da61e747..6ec5b42fd172 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -219,7 +219,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(skb->protocol != htons(ETH_P_IP))) goto tx_error; - skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP); + skb = iptunnel_handle_offloads(skb, SKB_GSO_IPIP); if (IS_ERR(skb)) goto out; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 2066d1c25a11..9a6b407f5840 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -911,7 +911,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto tx_error; } - skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT); + skb = iptunnel_handle_offloads(skb, SKB_GSO_SIT); if (IS_ERR(skb)) { ip_rt_put(rt); goto out; @@ -1000,7 +1000,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; - skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP); + skb = iptunnel_handle_offloads(skb, SKB_GSO_IPIP); if (IS_ERR(skb)) goto out; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 3264cb49b333..a3f5cd9b3c4c 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1019,8 +1019,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (IS_ERR(skb)) goto tx_error; - skb = iptunnel_handle_offloads( - skb, false, __tun_gso_type_mask(AF_INET, cp->af)); + skb = iptunnel_handle_offloads(skb, __tun_gso_type_mask(AF_INET, cp->af)); if (IS_ERR(skb)) goto tx_error; @@ -1112,8 +1111,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (IS_ERR(skb)) goto tx_error; - skb = iptunnel_handle_offloads( - skb, false, __tun_gso_type_mask(AF_INET6, cp->af)); + skb = iptunnel_handle_offloads(skb, __tun_gso_type_mask(AF_INET6, cp->af)); if (IS_ERR(skb)) goto tx_error; From e8ae7b000e64cf76283c72cae5e3ecd246618ef4 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Thu, 11 Feb 2016 21:03:37 +0000 Subject: [PATCH 8/8] Documentation/networking: add checksum-offloads.txt to explain LCO Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- Documentation/networking/00-INDEX | 2 + .../networking/checksum-offloads.txt | 119 ++++++++++++++++++ include/linux/skbuff.h | 2 + 3 files changed, 123 insertions(+) create mode 100644 Documentation/networking/checksum-offloads.txt diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index df27a1a50776..415154a487d0 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -44,6 +44,8 @@ can.txt - documentation on CAN protocol family. cdc_mbim.txt - 3G/LTE USB modem (Mobile Broadband Interface Model) +checksum-offloads.txt + - Explanation of checksum offloads; LCO, RCO cops.txt - info on the COPS LocalTalk Linux driver cs89x0.txt diff --git a/Documentation/networking/checksum-offloads.txt b/Documentation/networking/checksum-offloads.txt new file mode 100644 index 000000000000..de2a327766a7 --- /dev/null +++ b/Documentation/networking/checksum-offloads.txt @@ -0,0 +1,119 @@ +Checksum Offloads in the Linux Networking Stack + + +Introduction +============ + +This document describes a set of techniques in the Linux networking stack + to take advantage of checksum offload capabilities of various NICs. + +The following technologies are described: + * TX Checksum Offload + * LCO: Local Checksum Offload + * RCO: Remote Checksum Offload + +Things that should be documented here but aren't yet: + * RX Checksum Offload + * CHECKSUM_UNNECESSARY conversion + + +TX Checksum Offload +=================== + +The interface for offloading a transmit checksum to a device is explained + in detail in comments near the top of include/linux/skbuff.h. +In brief, it allows to request the device fill in a single ones-complement + checksum defined by the sk_buff fields skb->csum_start and + skb->csum_offset. The device should compute the 16-bit ones-complement + checksum (i.e. the 'IP-style' checksum) from csum_start to the end of the + packet, and fill in the result at (csum_start + csum_offset). +Because csum_offset cannot be negative, this ensures that the previous + value of the checksum field is included in the checksum computation, thus + it can be used to supply any needed corrections to the checksum (such as + the sum of the pseudo-header for UDP or TCP). +This interface only allows a single checksum to be offloaded. Where + encapsulation is used, the packet may have multiple checksum fields in + different header layers, and the rest will have to be handled by another + mechanism such as LCO or RCO. +No offloading of the IP header checksum is performed; it is always done in + software. This is OK because when we build the IP header, we obviously + have it in cache, so summing it isn't expensive. It's also rather short. +The requirements for GSO are more complicated, because when segmenting an + encapsulated packet both the inner and outer checksums may need to be + edited or recomputed for each resulting segment. See the skbuff.h comment + (section 'E') for more details. + +A driver declares its offload capabilities in netdev->hw_features; see + Documentation/networking/netdev-features for more. Note that a device + which only advertises NETIF_F_IP[V6]_CSUM must still obey the csum_start + and csum_offset given in the SKB; if it tries to deduce these itself in + hardware (as some NICs do) the driver should check that the values in the + SKB match those which the hardware will deduce, and if not, fall back to + checksumming in software instead (with skb_checksum_help or one of the + skb_csum_off_chk* functions as mentioned in include/linux/skbuff.h). This + is a pain, but that's what you get when hardware tries to be clever. + +The stack should, for the most part, assume that checksum offload is + supported by the underlying device. The only place that should check is + validate_xmit_skb(), and the functions it calls directly or indirectly. + That function compares the offload features requested by the SKB (which + may include other offloads besides TX Checksum Offload) and, if they are + not supported or enabled on the device (determined by netdev->features), + performs the corresponding offload in software. In the case of TX + Checksum Offload, that means calling skb_checksum_help(skb). + + +LCO: Local Checksum Offload +=========================== + +LCO is a technique for efficiently computing the outer checksum of an + encapsulated datagram when the inner checksum is due to be offloaded. +The ones-complement sum of a correctly checksummed TCP or UDP packet is + equal to the sum of the pseudo header, because everything else gets + 'cancelled out' by the checksum field. This is because the sum was + complemented before being written to the checksum field. +More generally, this holds in any case where the 'IP-style' ones complement + checksum is used, and thus any checksum that TX Checksum Offload supports. +That is, if we have set up TX Checksum Offload with a start/offset pair, we + know that _after the device has filled in that checksum_, the ones + complement sum from csum_start to the end of the packet will be equal to + _whatever value we put in the checksum field beforehand_. This allows us + to compute the outer checksum without looking at the payload: we simply + stop summing when we get to csum_start, then add the 16-bit word at + (csum_start + csum_offset). +Then, when the true inner checksum is filled in (either by hardware or by + skb_checksum_help()), the outer checksum will become correct by virtue of + the arithmetic. + +LCO is performed by the stack when constructing an outer UDP header for an + encapsulation such as VXLAN or GENEVE, in udp_set_csum(). Similarly for + the IPv6 equivalents, in udp6_set_csum(). +It is also performed when constructing an IPv4 GRE header, in + net/ipv4/ip_gre.c:build_header(). It is *not* currently performed when + constructing an IPv6 GRE header; the GRE checksum is computed over the + whole packet in net/ipv6/ip6_gre.c:ip6gre_xmit2(), but it should be + possible to use LCO here as IPv6 GRE still uses an IP-style checksum. +All of the LCO implementations use a helper function lco_csum(), in + include/linux/skbuff.h. + +LCO can safely be used for nested encapsulations; in this case, the outer + encapsulation layer will sum over both its own header and the 'middle' + header. This does mean that the 'middle' header will get summed multiple + times, but there doesn't seem to be a way to avoid that without incurring + bigger costs (e.g. in SKB bloat). + + +RCO: Remote Checksum Offload +============================ + +RCO is a technique for eliding the inner checksum of an encapsulated + datagram, allowing the outer checksum to be offloaded. It does, however, + involve a change to the encapsulation protocols, which the receiver must + also support. For this reason, it is disabled by default. +RCO is detailed in the following Internet-Drafts: +https://tools.ietf.org/html/draft-herbert-remotecsumoffload-00 +https://tools.ietf.org/html/draft-herbert-vxlan-rco-00 +In Linux, RCO is implemented individually in each encapsulation protocol, + and most tunnel types have flags controlling its use. For instance, VXLAN + has the flag VXLAN_F_REMCSUM_TX (per struct vxlan_rdst) to indicate that + RCO should be used when transmitting to a given remote destination. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cf906d1ce8a7..39206751463e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3705,6 +3705,8 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. + * See Documentation/networking/checksum-offloads.txt for + * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. * Also ensure that inner checksum is in linear data area.