diff options
| -rw-r--r-- | Documentation/networking/segmentation-offloads.txt | 130 | ||||
| -rw-r--r-- | include/linux/netdev_features.h | 8 | ||||
| -rw-r--r-- | include/linux/netdevice.h | 8 | ||||
| -rw-r--r-- | include/linux/skbuff.h | 27 | ||||
| -rw-r--r-- | net/core/dev.c | 67 | ||||
| -rw-r--r-- | net/core/ethtool.c | 4 | ||||
| -rw-r--r-- | net/core/skbuff.c | 29 | ||||
| -rw-r--r-- | net/ipv4/af_inet.c | 70 | ||||
| -rw-r--r-- | net/ipv4/gre_offload.c | 27 | ||||
| -rw-r--r-- | net/ipv4/tcp_offload.c | 30 | ||||
| -rw-r--r-- | net/ipv4/udp_offload.c | 27 | ||||
| -rw-r--r-- | net/ipv6/ip6_offload.c | 21 | ||||
| -rw-r--r-- | net/mpls/mpls_gso.c | 1 |
13 files changed, 395 insertions, 54 deletions
diff --git a/Documentation/networking/segmentation-offloads.txt b/Documentation/networking/segmentation-offloads.txt new file mode 100644 index 000000000000..f200467ade38 --- /dev/null +++ b/Documentation/networking/segmentation-offloads.txt @@ -0,0 +1,130 @@ +Segmentation Offloads in the Linux Networking Stack + +Introduction +============ + +This document describes a set of techniques in the Linux networking stack +to take advantage of segmentation offload capabilities of various NICs. + +The following technologies are described: + * TCP Segmentation Offload - TSO + * UDP Fragmentation Offload - UFO + * IPIP, SIT, GRE, and UDP Tunnel Offloads + * Generic Segmentation Offload - GSO + * Generic Receive Offload - GRO + * Partial Generic Segmentation Offload - GSO_PARTIAL + +TCP Segmentation Offload +======================== + +TCP segmentation allows a device to segment a single frame into multiple +frames with a data payload size specified in skb_shinfo()->gso_size. +When TCP segmentation requested the bit for either SKB_GSO_TCP or +SKB_GSO_TCP6 should be set in skb_shinfo()->gso_type and +skb_shinfo()->gso_size should be set to a non-zero value. + +TCP segmentation is dependent on support for the use of partial checksum +offload. For this reason TSO is normally disabled if the Tx checksum +offload for a given device is disabled. + +In order to support TCP segmentation offload it is necessary to populate +the network and transport header offsets of the skbuff so that the device +drivers will be able determine the offsets of the IP or IPv6 header and the +TCP header. In addition as CHECKSUM_PARTIAL is required csum_start should +also point to the TCP header of the packet. + +For IPv4 segmentation we support one of two types in terms of the IP ID. +The default behavior is to increment the IP ID with every segment. If the +GSO type SKB_GSO_TCP_FIXEDID is specified then we will not increment the IP +ID and all segments will use the same IP ID. If a device has +NETIF_F_TSO_MANGLEID set then the IP ID can be ignored when performing TSO +and we will either increment the IP ID for all frames, or leave it at a +static value based on driver preference. + +UDP Fragmentation Offload +========================= + +UDP fragmentation offload allows a device to fragment an oversized UDP +datagram into multiple IPv4 fragments. Many of the requirements for UDP +fragmentation offload are the same as TSO. However the IPv4 ID for +fragments should not increment as a single IPv4 datagram is fragmented. + +IPIP, SIT, GRE, UDP Tunnel, and Remote Checksum Offloads +======================================================== + +In addition to the offloads described above it is possible for a frame to +contain additional headers such as an outer tunnel. In order to account +for such instances an additional set of segmentation offload types were +introduced including SKB_GSO_IPIP, SKB_GSO_SIT, SKB_GSO_GRE, and +SKB_GSO_UDP_TUNNEL. These extra segmentation types are used to identify +cases where there are more than just 1 set of headers. For example in the +case of IPIP and SIT we should have the network and transport headers moved +from the standard list of headers to "inner" header offsets. + +Currently only two levels of headers are supported. The convention is to +refer to the tunnel headers as the outer headers, while the encapsulated +data is normally referred to as the inner headers. Below is the list of +calls to access the given headers: + +IPIP/SIT Tunnel: + Outer Inner +MAC skb_mac_header +Network skb_network_header skb_inner_network_header +Transport skb_transport_header + +UDP/GRE Tunnel: + Outer Inner +MAC skb_mac_header skb_inner_mac_header +Network skb_network_header skb_inner_network_header +Transport skb_transport_header skb_inner_transport_header + +In addition to the above tunnel types there are also SKB_GSO_GRE_CSUM and +SKB_GSO_UDP_TUNNEL_CSUM. These two additional tunnel types reflect the +fact that the outer header also requests to have a non-zero checksum +included in the outer header. + +Finally there is SKB_GSO_REMCSUM which indicates that a given tunnel header +has requested a remote checksum offload. In this case the inner headers +will be left with a partial checksum and only the outer header checksum +will be computed. + +Generic Segmentation Offload +============================ + +Generic segmentation offload is a pure software offload that is meant to +deal with cases where device drivers cannot perform the offloads described +above. What occurs in GSO is that a given skbuff will have its data broken +out over multiple skbuffs that have been resized to match the MSS provided +via skb_shinfo()->gso_size. + +Before enabling any hardware segmentation offload a corresponding software +offload is required in GSO. Otherwise it becomes possible for a frame to +be re-routed between devices and end up being unable to be transmitted. + +Generic Receive Offload +======================= + +Generic receive offload is the complement to GSO. Ideally any frame +assembled by GRO should be segmented to create an identical sequence of +frames using GSO, and any sequence of frames segmented by GSO should be +able to be reassembled back to the original by GRO. The only exception to +this is IPv4 ID in the case that the DF bit is set for a given IP header. +If the value of the IPv4 ID is not sequentially incrementing it will be +altered so that it is when a frame assembled via GRO is segmented via GSO. + +Partial Generic Segmentation Offload +==================================== + +Partial generic segmentation offload is a hybrid between TSO and GSO. What +it effectively does is take advantage of certain traits of TCP and tunnels +so that instead of having to rewrite the packet headers for each segment +only the inner-most transport header and possibly the outer-most network +header need to be updated. This allows devices that do not support tunnel +offloads or tunnel offloads with checksum to still make use of segmentation. + +With the partial offload what occurs is that all headers excluding the +inner transport header are updated such that they will contain the correct +values for if the header was simply duplicated. The one exception to this +is the outer IPv4 ID field. It is up to the device drivers to guarantee +that the IPv4 ID field is incremented in the case that a given header does +not have the DF bit set. diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index a734bf43d190..9fc79df0e561 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -39,6 +39,7 @@ enum { NETIF_F_UFO_BIT, /* ... UDPv4 fragmentation */ NETIF_F_GSO_ROBUST_BIT, /* ... ->SKB_GSO_DODGY */ NETIF_F_TSO_ECN_BIT, /* ... TCP ECN support */ + NETIF_F_TSO_MANGLEID_BIT, /* ... IPV4 ID mangling allowed */ NETIF_F_TSO6_BIT, /* ... TCPv6 segmentation */ NETIF_F_FSO_BIT, /* ... FCoE segmentation */ NETIF_F_GSO_GRE_BIT, /* ... GRE with TSO */ @@ -47,6 +48,10 @@ enum { NETIF_F_GSO_SIT_BIT, /* ... SIT tunnel with TSO */ NETIF_F_GSO_UDP_TUNNEL_BIT, /* ... UDP TUNNEL with TSO */ NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */ + NETIF_F_GSO_PARTIAL_BIT, /* ... Only segment inner-most L4 + * in hardware and all other + * headers in software. + */ NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ NETIF_F_GSO_TUNNEL_REMCSUM_BIT, @@ -120,6 +125,8 @@ enum { #define NETIF_F_GSO_SIT __NETIF_F(GSO_SIT) #define NETIF_F_GSO_UDP_TUNNEL __NETIF_F(GSO_UDP_TUNNEL) #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM) +#define NETIF_F_TSO_MANGLEID __NETIF_F(TSO_MANGLEID) +#define NETIF_F_GSO_PARTIAL __NETIF_F(GSO_PARTIAL) #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM) #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) #define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) @@ -147,6 +154,7 @@ enum { /* List of features with software fallbacks. */ #define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \ + NETIF_F_TSO_MANGLEID | \ NETIF_F_TSO6 | NETIF_F_UFO) /* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9884fe9a6552..a3bb534576a3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1654,6 +1654,7 @@ struct net_device { netdev_features_t vlan_features; netdev_features_t hw_enc_features; netdev_features_t mpls_features; + netdev_features_t gso_partial_features; int ifindex; int group; @@ -2121,7 +2122,10 @@ struct napi_gro_cb { /* Used in GRE, set in fou/gue_gro_receive */ u8 is_fou:1; - /* 6 bit hole */ + /* Used to determine if flush_id can be ignored */ + u8 is_atomic:1; + + /* 5 bit hole */ /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; @@ -3992,6 +3996,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT)); @@ -4000,6 +4005,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_SIT != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 007381270ff8..da0ace389fec 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -465,23 +465,27 @@ enum { /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 3, - SKB_GSO_TCPV6 = 1 << 4, + SKB_GSO_TCP_FIXEDID = 1 << 4, - SKB_GSO_FCOE = 1 << 5, + SKB_GSO_TCPV6 = 1 << 5, - SKB_GSO_GRE = 1 << 6, + SKB_GSO_FCOE = 1 << 6, - SKB_GSO_GRE_CSUM = 1 << 7, + SKB_GSO_GRE = 1 << 7, - SKB_GSO_IPIP = 1 << 8, + SKB_GSO_GRE_CSUM = 1 << 8, - SKB_GSO_SIT = 1 << 9, + SKB_GSO_IPIP = 1 << 9, - SKB_GSO_UDP_TUNNEL = 1 << 10, + SKB_GSO_SIT = 1 << 10, - SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, + SKB_GSO_UDP_TUNNEL = 1 << 11, - SKB_GSO_TUNNEL_REMCSUM = 1 << 12, + SKB_GSO_UDP_TUNNEL_CSUM = 1 << 12, + + SKB_GSO_PARTIAL = 1 << 13, + + SKB_GSO_TUNNEL_REMCSUM = 1 << 14, }; #if BITS_PER_LONG > 32 @@ -3589,7 +3593,10 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb) * Keeps track of level of encapsulation of network headers. */ struct skb_gso_cb { - int mac_offset; + union { + int mac_offset; + int data_offset; + }; int encap_level; __wsum csum; __u16 csum_start; diff --git a/net/core/dev.c b/net/core/dev.c index 09fb1ace9dc8..556dd09af3b8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2711,6 +2711,19 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, return ERR_PTR(err); } + /* Only report GSO partial support if it will enable us to + * support segmentation on this frame without needing additional + * work. + */ + if (features & NETIF_F_GSO_PARTIAL) { + netdev_features_t partial_features = NETIF_F_GSO_ROBUST; + struct net_device *dev = skb->dev; + + partial_features |= dev->features & dev->gso_partial_features; + if (!skb_gso_ok(skb, features | partial_features)) + features &= ~NETIF_F_GSO_PARTIAL; + } + BUILD_BUG_ON(SKB_SGO_CB_OFFSET + sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb)); @@ -2825,14 +2838,45 @@ static netdev_features_t dflt_features_check(const struct sk_buff *skb, return vlan_features_check(skb, features); } +static netdev_features_t gso_features_check(const struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + u16 gso_segs = skb_shinfo(skb)->gso_segs; + + if (gso_segs > dev->gso_max_segs) + return features & ~NETIF_F_GSO_MASK; + + /* Support for GSO partial features requires software + * intervention before we can actually process the packets + * so we need to strip support for any partial features now + * and we can pull them back in after we have partially + * segmented the frame. + */ + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)) + features &= ~dev->gso_partial_features; + + /* Make sure to clear the IPv4 ID mangling feature if the + * IPv4 header has the potential to be fragmented. + */ + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { + struct iphdr *iph = skb->encapsulation ? + inner_ip_hdr(skb) : ip_hdr(skb); + + if (!(iph->frag_off & htons(IP_DF))) + features &= ~NETIF_F_TSO_MANGLEID; + } + + return features; +} + netdev_features_t netif_skb_features(struct sk_buff *skb) { struct net_device *dev = skb->dev; netdev_features_t features = dev->features; - u16 gso_segs = skb_shinfo(skb)->gso_segs; - if (gso_segs > dev->gso_max_segs) - features &= ~NETIF_F_GSO_MASK; + if (skb_is_gso(skb)) + features = gso_features_check(skb, dev, features); /* If encapsulation offload request, verify we are testing * hardware encapsulation features instead of standard @@ -4440,6 +4484,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->free = 0; NAPI_GRO_CB(skb)->encap_mark = 0; NAPI_GRO_CB(skb)->is_fou = 0; + NAPI_GRO_CB(skb)->is_atomic = 1; NAPI_GRO_CB(skb)->gro_remcsum_start = 0; /* Setup for GRO checksum validation */ @@ -6706,6 +6751,14 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, } } + /* GSO partial features require GSO partial be set */ + if ((features & dev->gso_partial_features) && + !(features & NETIF_F_GSO_PARTIAL)) { + netdev_dbg(dev, + "Dropping partially supported GSO features since no GSO partial.\n"); + features &= ~dev->gso_partial_features; + } + #ifdef CONFIG_NET_RX_BUSY_POLL if (dev->netdev_ops->ndo_busy_poll) features |= NETIF_F_BUSY_POLL; @@ -6976,9 +7029,11 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_SOFT_FEATURES; dev->wanted_features = dev->features & dev->hw_features; - if (!(dev->flags & IFF_LOOPBACK)) { + if (!(dev->flags & IFF_LOOPBACK)) dev->hw_features |= NETIF_F_NOCACHE_COPY; - } + + if (dev->hw_features & NETIF_F_TSO) + dev->hw_features |= NETIF_F_TSO_MANGLEID; /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. */ @@ -6986,7 +7041,7 @@ int register_netdevice(struct net_device *dev) /* Make NETIF_F_SG inheritable to tunnel devices. */ - dev->hw_enc_features |= NETIF_F_SG; + dev->hw_enc_features |= NETIF_F_SG | NETIF_F_GSO_PARTIAL; /* Make NETIF_F_SG inheritable to MPLS. */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index f426c5ad6149..e0cf20a3b3dd 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -79,12 +79,16 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_UFO_BIT] = "tx-udp-fragmentation", [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust", [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", + [NETIF_F_TSO_MANGLEID_BIT] = "tx-tcp-mangleid-segmentation", [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", + [NETIF_F_GSO_GRE_CSUM_BIT] = "tx-gre-csum-segmentation", [NETIF_F_GSO_IPIP_BIT] = "tx-ipip-segmentation", [NETIF_F_GSO_SIT_BIT] = "tx-sit-segmentation", [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", + [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", + [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d04c2d1c8c87..4cc594cdaada 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3076,8 +3076,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, struct sk_buff *frag_skb = head_skb; unsigned int offset = doffset; unsigned int tnl_hlen = skb_tnl_header_len(head_skb); + unsigned int partial_segs = 0; unsigned int headroom; - unsigned int len; + unsigned int len = head_skb->len; __be16 proto; bool csum; int sg = !!(features & NETIF_F_SG); @@ -3094,6 +3095,15 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, csum = !!can_checksum_protocol(features, proto); + /* GSO partial only requires that we trim off any excess that + * doesn't fit into an MSS sized block, so take care of that + * now. + */ + if (features & NETIF_F_GSO_PARTIAL) { + partial_segs = len / mss; + mss *= partial_segs; + } + headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); @@ -3281,6 +3291,23 @@ perform_csum_check: */ segs->prev = tail; + /* Update GSO info on first skb in partial sequence. */ + if (partial_segs) { + int type = skb_shinfo(head_skb)->gso_type; + + /* Update type to add partial and then remove dodgy if set */ + type |= SKB_GSO_PARTIAL; + type &= ~SKB_GSO_DODGY; + + /* Update GSO info and prepare to start updating headers on + * our way back down the stack of protocols. + */ + skb_shinfo(segs)->gso_size = skb_shinfo(head_skb)->gso_size; + skb_shinfo(segs)->gso_segs = partial_segs; + skb_shinfo(segs)->gso_type = type; + SKB_GSO_CB(segs)->data_offset = skb_headroom(segs) + doffset; + } + /* Following permits correct backpressure, for protocols * using skb_set_owner_w(). * Idea is to tranfert ownership from head_skb to last segment. diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8217cd22f921..2e6e65fc4d20 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1195,12 +1195,12 @@ EXPORT_SYMBOL(inet_sk_rebuild_header); static struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { + bool udpfrag = false, fixedid = false, encap; struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; unsigned int offset = 0; - bool udpfrag, encap; struct iphdr *iph; - int proto; + int proto, tot_len; int nhoff; int ihl; int id; @@ -1217,7 +1217,9 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_TCPV6 | SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM | + SKB_GSO_TCP_FIXEDID | SKB_GSO_TUNNEL_REMCSUM | + SKB_GSO_PARTIAL | 0))) goto out; @@ -1248,11 +1250,14 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); - if (skb->encapsulation && - skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) - udpfrag = proto == IPPROTO_UDP && encap; - else - udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; + if (!skb->encapsulation || encap) { + udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); + fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); + + /* fixed ID is invalid if DF bit is not set */ + if (fixedid && !(iph->frag_off & htons(IP_DF))) + goto out; + } ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) @@ -1265,15 +1270,25 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, do { iph = (struct iphdr *)(skb_mac_header(skb) + nhoff); if (udpfrag) { - iph->id = htons(id); iph->frag_off = htons(offset >> 3); if (skb->next) iph->frag_off |= htons(IP_MF); offset += skb->len - nhoff - ihl; + tot_len = skb->len - nhoff; + } else if (skb_is_gso(skb)) { + if (!fixedid) { + iph->id = htons(id); + id += skb_shinfo(skb)->gso_segs; + } + tot_len = skb_shinfo(skb)->gso_size + + SKB_GSO_CB(skb)->data_offset + + skb->head - (unsigned char *)iph; } else { - iph->id = htons(id++); + if (!fixedid) + iph->id = htons(id++); + tot_len = skb->len - nhoff; } - iph->tot_len = htons(skb->len - nhoff); + iph->tot_len = htons(tot_len); ip_send_check(iph); if (encap) skb_reset_inner_headers(skb); @@ -1325,6 +1340,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, for (p = *head; p; p = p->next) { struct iphdr *iph2; + u16 flush_id; if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -1348,16 +1364,36 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, (iph->tos ^ iph2->tos) | ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)); - /* Save the IP ID check to be included later when we get to - * the transport layer so only the inner most IP ID is checked. - * This is because some GSO/TSO implementations do not - * correctly increment the IP ID for the outer hdrs. - */ - NAPI_GRO_CB(p)->flush_id = - ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id); NAPI_GRO_CB(p)->flush |= flush; + + /* We need to store of the IP ID check to be included later + * when we can verify that this packet does in fact belong + * to a given flow. + */ + flush_id = (u16)(id - ntohs(iph2->id)); + + /* This bit of code makes it much easier for us to identify + * the cases where we are doing atomic vs non-atomic IP ID + * checks. Specifically an atomic check can return IP ID + * values 0 - 0xFFFF, while a non-atomic check can only + * return 0 or 0xFFFF. + */ + if (!NAPI_GRO_CB(p)->is_atomic || + !(iph->frag_off & htons(IP_DF))) { + flush_id ^= NAPI_GRO_CB(p)->count; + flush_id = flush_id ? 0xFFFF : 0; + } + + /* If the previous IP ID value was based on an atomic + * datagram we can overwrite the value and ignore it. + */ + if (NAPI_GRO_CB(skb)->is_atomic) + NAPI_GRO_CB(p)->flush_id = flush_id; + else + NAPI_GRO_CB(p)->flush_id |= flush_id; } + NAPI_GRO_CB(skb)->is_atomic = !!(iph->frag_off & htons(IP_DF)); NAPI_GRO_CB(skb)->flush |= flush; skb_set_network_header(skb, off); /* The above will be needed by the transport layer if there is one diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 6a5bd4317866..20557f211408 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -32,10 +32,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_TCP_FIXEDID | SKB_GSO_GRE | SKB_GSO_GRE_CSUM | SKB_GSO_IPIP | - SKB_GSO_SIT))) + SKB_GSO_SIT | + SKB_GSO_PARTIAL))) goto out; if (!skb->encapsulation) @@ -86,7 +88,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, skb = segs; do { struct gre_base_hdr *greh; - __be32 *pcsum; + __sum16 *pcsum; /* Set up inner headers if we are offloading inner checksum */ if (skb->ip_summed == CHECKSUM_PARTIAL) { @@ -106,10 +108,25 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, continue; greh = (struct gre_base_hdr *)skb_transport_header(skb); - pcsum = (__be32 *)(greh + 1); + pcsum = (__sum16 *)(greh + 1); + + if (skb_is_gso(skb)) { + unsigned int partial_adj; + + /* Adjust checksum to account for the fact that + * the partial checksum is based on actual size + * whereas headers should be based on MSS size. + */ + partial_adj = skb->len + skb_headroom(skb) - + SKB_GSO_CB(skb)->data_offset - + skb_shinfo(skb)->gso_size; + *pcsum = ~csum_fold((__force __wsum)htonl(partial_adj)); + } else { + *pcsum = 0; + } - *pcsum = 0; - *(__sum16 *)pcsum = gso_make_checksum(skb, 0); + *(pcsum + 1) = 0; + *pcsum = gso_make_checksum(skb, 0); } while ((skb = skb->next)); out: return segs; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 773083b7f1e9..02737b607aa7 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -89,6 +89,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, ~(SKB_GSO_TCPV4 | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_TCP_FIXEDID | SKB_GSO_TCPV6 | SKB_GSO_GRE | SKB_GSO_GRE_CSUM | @@ -98,7 +99,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, SKB_GSO_UDP_TUNNEL_CSUM | SKB_GSO_TUNNEL_REMCSUM | 0) || - !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) + !(type & (SKB_GSO_TCPV4 | + SKB_GSO_TCPV6)))) goto out; skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); @@ -107,6 +109,12 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, goto out; } + /* GSO partial only requires splitting the frame into an MSS + * multiple and possibly a remainder. So update the mss now. + */ + if (features & NETIF_F_GSO_PARTIAL) + mss = skb->len - (skb->len % mss); + copy_destructor = gso_skb->destructor == tcp_wfree; ooo_okay = gso_skb->ooo_okay; /* All segments but the first should have ooo_okay cleared */ @@ -131,7 +139,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, newcheck = ~csum_fold((__force __wsum)((__force u32)th->check + (__force u32)delta)); - do { + while (skb->next) { th->fin = th->psh = 0; th->check = newcheck; @@ -151,7 +159,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, th->seq = htonl(seq); th->cwr = 0; - } while (skb->next); + } /* Following permits TCP Small Queues to work well with GSO : * The callback to TCP stack will be called at the time last frag @@ -237,7 +245,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) found: /* Include the IP ID check below from the inner most IP hdr */ - flush = NAPI_GRO_CB(p)->flush | NAPI_GRO_CB(p)->flush_id; + flush = NAPI_GRO_CB(p)->flush; flush |= (__force int)(flags & TCP_FLAG_CWR); flush |= (__force int)((flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH)); @@ -246,6 +254,17 @@ found: flush |= *(u32 *)((u8 *)th + i) ^ *(u32 *)((u8 *)th2 + i); + /* When we receive our second frame we can made a decision on if we + * continue this flow as an atomic flow with a fixed ID or if we use + * an incrementing ID. + */ + if (NAPI_GRO_CB(p)->flush_id != 1 || + NAPI_GRO_CB(p)->count != 1 || + !NAPI_GRO_CB(p)->is_atomic) + flush |= NAPI_GRO_CB(p)->flush_id; + else + NAPI_GRO_CB(p)->is_atomic = false; + mss = skb_shinfo(p)->gso_size; flush |= (len - 1) >= mss; @@ -314,6 +333,9 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff) iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; + if (NAPI_GRO_CB(skb)->is_atomic) + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID; + return tcp_gro_complete(skb); } diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6230cf4b0d2d..097060def7f0 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -39,8 +39,11 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, * 16 bit length field due to the header being added outside of an * IP or IPv6 frame that was already limited to 64K - 1. */ - partial = csum_sub(csum_unfold(uh->check), - (__force __wsum)htonl(skb->len)); + 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; @@ -89,7 +92,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, udp_offset = outer_hlen - tnl_hlen; skb = segs; do { - __be16 len; + unsigned int len; if (remcsum) skb->ip_summed = CHECKSUM_NONE; @@ -107,14 +110,26 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_set_transport_header(skb, udp_offset); - len = htons(skb->len - udp_offset); + len = skb->len - udp_offset; uh = udp_hdr(skb); - uh->len = len; + + /* 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 (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)len)); + uh->check = ~csum_fold(csum_add(partial, + (__force __wsum)htonl(len))); if (skb->encapsulation || !offload_csum) { uh->check = gso_make_checksum(skb, ~uh->check); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 204af2219471..f5eb184e1093 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -63,6 +63,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int proto; struct frag_hdr *fptr; unsigned int unfrag_ip6hlen; + unsigned int payload_len; u8 *prevhdr; int offset = 0; bool encap, udpfrag; @@ -73,6 +74,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_TCP_FIXEDID | + SKB_GSO_TCPV6 | SKB_GSO_GRE | SKB_GSO_GRE_CSUM | SKB_GSO_IPIP | @@ -80,7 +83,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM | SKB_GSO_TUNNEL_REMCSUM | - SKB_GSO_TCPV6 | + SKB_GSO_PARTIAL | 0))) goto out; @@ -117,7 +120,13 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, for (skb = segs; skb; skb = skb->next) { ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); - ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h)); + if (skb_is_gso(skb)) + payload_len = skb_shinfo(skb)->gso_size + + SKB_GSO_CB(skb)->data_offset + + skb->head - (unsigned char *)(ipv6h + 1); + else + payload_len = skb->len - nhoff - sizeof(*ipv6h); + ipv6h->payload_len = htons(payload_len); skb->network_header = (u8 *)ipv6h - skb->head; if (udpfrag) { @@ -239,10 +248,14 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); NAPI_GRO_CB(p)->flush |= flush; - /* Clear flush_id, there's really no concept of ID in IPv6. */ - NAPI_GRO_CB(p)->flush_id = 0; + /* If the previous IP ID value was based on an atomic + * datagram we can overwrite the value and ignore it. + */ + if (NAPI_GRO_CB(skb)->is_atomic) + NAPI_GRO_CB(p)->flush_id = 0; } + NAPI_GRO_CB(skb)->is_atomic = true; NAPI_GRO_CB(skb)->flush |= flush; skb_gro_postpull_rcsum(skb, iph, nlen); diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index 0183b32da942..bbcf60465e5c 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -31,6 +31,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, SKB_GSO_TCPV6 | SKB_GSO_UDP | SKB_GSO_DODGY | + SKB_GSO_TCP_FIXEDID | SKB_GSO_TCP_ECN))) goto out; |