From mboxrd@z Thu Jan 1 00:00:00 1970 From: ravinandan.arakali@neterion.com Subject: [PATCH 2.6.12-rc4] IPv4/IPv6: USO v2, fragment list approach Date: Thu, 2 Jun 2005 17:43:51 -0700 (PDT) Message-ID: <20050603004351.41BFB7B990@linux.site> Cc: raghavendra.koushik@neterion.com, ravinandan.arakali@neterion.com, leonid.grossman@neterion.com, ananda.raju@neterion.com, rapuru.sriram@neterion.com Return-path: To: davem@davemloft.net, jgarzik@pobox.com, netdev@oss.sgi.com Sender: netdev-bounce@oss.sgi.com Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org Hi, Attached below is version 2 of kernel patch for UDP Large send offload feature. This patch uses the "fragment list" approach. It also incorporates David Miller's comments on the first version. Also, below is a "how-to" on changes required in network drivers to use the USO interface. UDP Large Send Offload (USO) Interface: --------------------------------------- USO is a feature wherein the Linux kernel network stack will offload the IP fragmentation functionality of large UDP datagram to hardware. This will reduce the overhead of stack in fragmenting the large UDP datagram to MTU sized packets. 1) Drivers indicate their capability of USO using dev->features |= NETIF_F_USO | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST NETIF_F_HW_CSUM is required for USO over IPv6. 2) USO packet will be submitted for transmission using driver xmit routine. USO packet will have a non zero value for "skb_shinfo(skb)->uso_size" skb_shinfo(skb)->uso_size indicates the length of data part in each IP fragment going out of the adapter after IP fragmentation by hardware. skb->data and skb_shinfo(skb)->frag_list will contain complete large UDP datagram. The driver is required to traverse each skb in skb_shinfo(skb)->frag_list to get complete UDP packet. The skb->ip_summed will be set to CHECKSUM_HW indicating that hardware has to perform checksum calculation. Hardware should compute the UDP checksum of complete UDP datagram and also ip header checksum of each fragmented IP packet. For IPV6 the USO provides the fragment identification id in skb_shinfo(skb)->ip6_frag_id. The adapter should use this ID for generating IPv6 fragments. Signed-off-by: Ananda Raju Signed-off-by: Ravinandan Arakali --- diff -uNr linux-2.6.12-rc4.org/include/linux/ethtool.h linux-2.6.12-rc4/include/linux/ethtool.h --- linux-2.6.12-rc4.org/include/linux/ethtool.h 2005-06-02 16:55:51.000000000 +0545 +++ linux-2.6.12-rc4/include/linux/ethtool.h 2005-06-02 16:56:46.000000000 +0545 @@ -260,6 +260,8 @@ int ethtool_op_set_sg(struct net_device *dev, u32 data); u32 ethtool_op_get_tso(struct net_device *dev); int ethtool_op_set_tso(struct net_device *dev, u32 data); +u32 ethtool_op_get_uso(struct net_device *dev); +int ethtool_op_set_uso(struct net_device *dev, u32 data); /** * ðtool_ops - Alter and report network device settings @@ -289,6 +291,8 @@ * set_sg: Turn scatter-gather on or off * get_tso: Report whether TCP segmentation offload is enabled * set_tso: Turn TCP segmentation offload on or off + * get_uso: Report whether UDP large send offload is enabled + * set_uso: Turn UDP large send offload on or off * self_test: Run specified self-tests * get_strings: Return a set of strings that describe the requested objects * phys_id: Identify the device @@ -353,6 +357,8 @@ void (*get_ethtool_stats)(struct net_device *, struct ethtool_stats *, u64 *); int (*begin)(struct net_device *); void (*complete)(struct net_device *); + u32 (*get_uso)(struct net_device *); + int (*set_uso)(struct net_device *, u32); }; /* CMDs currently supported */ @@ -388,6 +394,8 @@ #define ETHTOOL_GSTATS 0x0000001d /* get NIC-specific statistics */ #define ETHTOOL_GTSO 0x0000001e /* Get TSO enable (ethtool_value) */ #define ETHTOOL_STSO 0x0000001f /* Set TSO enable (ethtool_value) */ +#define ETHTOOL_GUSO 0x00000020 /* Get USO enable (ethtool_value) */ +#define ETHTOOL_SUSO 0x00000021 /* Set USO enable (ethtool_value) */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET diff -uNr linux-2.6.12-rc4.org/include/linux/netdevice.h linux-2.6.12-rc4/include/linux/netdevice.h --- linux-2.6.12-rc4.org/include/linux/netdevice.h 2005-05-27 23:22:46.000000000 +0545 +++ linux-2.6.12-rc4/include/linux/netdevice.h 2005-05-31 10:02:02.000000000 +0545 @@ -414,6 +414,7 @@ #define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */ #define NETIF_F_TSO 2048 /* Can offload TCP/IP segmentation */ #define NETIF_F_LLTX 4096 /* LockLess TX */ +#define NETIF_F_USO 8192 /* Can offload UDP Large Send*/ /* Called after device is detached from network. */ void (*uninit)(struct net_device *dev); diff -uNr linux-2.6.12-rc4.org/include/linux/skbuff.h linux-2.6.12-rc4/include/linux/skbuff.h --- linux-2.6.12-rc4.org/include/linux/skbuff.h 2005-05-27 23:22:46.000000000 +0545 +++ linux-2.6.12-rc4/include/linux/skbuff.h 2005-06-02 20:27:43.000000000 +0545 @@ -136,6 +136,8 @@ unsigned int nr_frags; unsigned short tso_size; unsigned short tso_segs; + unsigned short uso_size; + unsigned int ip6_frag_id; struct sk_buff *frag_list; skb_frag_t frags[MAX_SKB_FRAGS]; }; diff -uNr linux-2.6.12-rc4.org/net/core/dev.c linux-2.6.12-rc4/net/core/dev.c --- linux-2.6.12-rc4.org/net/core/dev.c 2005-05-28 01:49:18.000000000 +0545 +++ linux-2.6.12-rc4/net/core/dev.c 2005-05-31 22:57:22.000000000 +0545 @@ -2793,6 +2793,18 @@ dev->name); dev->features &= ~NETIF_F_TSO; } + if (dev->features & NETIF_F_USO) { + if(!(dev->features & NETIF_F_FRAGLIST)) { + printk("%s: Dropping NETIF_F_USO since no ", dev->name); + printk("NETIF_F_FRAGLIST feature.\n"); + dev->features &= ~NETIF_F_USO; + } + if(!(dev->features & NETIF_F_HW_CSUM)) { + printk("%s: Dropping NETIF_F_USO since no ", dev->name); + printk("NETIF_F_HW_CSUM feature.\n"); + dev->features &= ~NETIF_F_USO; + } + } /* * nil rebuild_header routine, diff -uNr linux-2.6.12-rc4.org/net/core/ethtool.c linux-2.6.12-rc4/net/core/ethtool.c --- linux-2.6.12-rc4.org/net/core/ethtool.c 2005-06-02 16:55:32.000000000 +0545 +++ linux-2.6.12-rc4/net/core/ethtool.c 2005-06-02 21:53:16.000000000 +0545 @@ -72,6 +72,21 @@ return 0; } +u32 ethtool_op_get_uso(struct net_device *dev) +{ + return (dev->features & NETIF_F_USO) != 0; +} + +int ethtool_op_set_uso(struct net_device *dev, u32 data) +{ + if (data) + dev->features |= NETIF_F_USO; + else + dev->features &= ~NETIF_F_USO; + + return 0; +} + /* Handlers for each ethtool command */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) @@ -548,6 +563,39 @@ return dev->ethtool_ops->set_tso(dev, edata.data); } +static int ethtool_get_uso(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value edata = { ETHTOOL_GTSO }; + + if (!dev->ethtool_ops->get_uso) + return -EOPNOTSUPP; + + edata.data = dev->ethtool_ops->get_uso(dev); + + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + return 0; +} + +static int ethtool_set_uso(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value edata; + + if (!dev->ethtool_ops->set_uso) + return -EOPNOTSUPP; + + if (copy_from_user(&edata, useraddr, sizeof(edata))) + return -EFAULT; + + if (edata.data && !(dev->features & NETIF_F_FRAGLIST)) + return -EINVAL; + + if (edata.data && !(dev->features & NETIF_F_HW_CSUM)) + return -EINVAL; + + return dev->ethtool_ops->set_uso(dev, edata.data); +} + static int ethtool_self_test(struct net_device *dev, char __user *useraddr) { struct ethtool_test test; @@ -795,6 +843,12 @@ case ETHTOOL_GSTATS: rc = ethtool_get_stats(dev, useraddr); break; + case ETHTOOL_GUSO: + rc = ethtool_get_uso(dev, useraddr); + break; + case ETHTOOL_SUSO: + rc = ethtool_set_uso(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } @@ -817,3 +871,6 @@ EXPORT_SYMBOL(ethtool_op_set_sg); EXPORT_SYMBOL(ethtool_op_set_tso); EXPORT_SYMBOL(ethtool_op_set_tx_csum); +EXPORT_SYMBOL(ethtool_op_set_uso); +EXPORT_SYMBOL(ethtool_op_get_uso); + diff -uNr linux-2.6.12-rc4.org/net/core/skbuff.c linux-2.6.12-rc4/net/core/skbuff.c --- linux-2.6.12-rc4.org/net/core/skbuff.c 2005-05-27 23:22:46.000000000 +0545 +++ linux-2.6.12-rc4/net/core/skbuff.c 2005-06-02 20:27:27.000000000 +0545 @@ -159,6 +159,8 @@ skb_shinfo(skb)->tso_size = 0; skb_shinfo(skb)->tso_segs = 0; skb_shinfo(skb)->frag_list = NULL; + skb_shinfo(skb)->ip6_frag_id = 0; + skb_shinfo(skb)->uso_size = 0; out: return skb; nodata: diff -uNr linux-2.6.12-rc4.org/net/ipv4/ip_output.c linux-2.6.12-rc4/net/ipv4/ip_output.c --- linux-2.6.12-rc4.org/net/ipv4/ip_output.c 2005-05-27 23:22:46.000000000 +0545 +++ linux-2.6.12-rc4/net/ipv4/ip_output.c 2005-05-31 15:55:39.000000000 +0545 @@ -291,7 +291,8 @@ { IP_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - if (skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->tso_size) + if (skb->len > dst_mtu(skb->dst) && + !(skb_shinfo(skb)->tso_size || skb_shinfo(skb)->uso_size)) return ip_fragment(skb, ip_finish_output); else return ip_finish_output(skb); @@ -768,7 +769,6 @@ mtu = inet->cork.fragsize; } hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); - fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; @@ -864,6 +864,12 @@ skb->ip_summed = csummode; skb->csum = 0; skb_reserve(skb, hh_len); + if ((!offset) && (length > mtu) && + (sk->sk_protocol == IPPROTO_UDP) && + (rt->u.dst.dev->features & NETIF_F_USO)) { + skb_shinfo(skb)->uso_size = mtu - fragheaderlen; + skb->ip_summed = CHECKSUM_HW; + } /* * Find where to start putting bytes. diff -uNr linux-2.6.12-rc4.org/net/ipv4/udp.c linux-2.6.12-rc4/net/ipv4/udp.c --- linux-2.6.12-rc4.org/net/ipv4/udp.c 2005-05-27 23:23:55.000000000 +0545 +++ linux-2.6.12-rc4/net/ipv4/udp.c 2005-05-31 21:14:44.000000000 +0545 @@ -424,9 +424,10 @@ goto send; } - if (skb_queue_len(&sk->sk_write_queue) == 1) { + if ((skb_queue_len(&sk->sk_write_queue) == 1) || + (skb_shinfo(skb)->uso_size)) { /* - * Only one fragment on the socket. + * Only one fragment on the socket or it is udp lso skb. */ if (skb->ip_summed == CHECKSUM_HW) { skb->csum = offsetof(struct udphdr, check); diff -uNr linux-2.6.12-rc4.org/net/ipv6/ip6_output.c linux-2.6.12-rc4/net/ipv6/ip6_output.c --- linux-2.6.12-rc4.org/net/ipv6/ip6_output.c 2005-05-27 23:22:46.000000000 +0545 +++ linux-2.6.12-rc4/net/ipv6/ip6_output.c 2005-06-02 20:27:55.000000000 +0545 @@ -147,7 +147,8 @@ int ip6_output(struct sk_buff *skb) { - if (skb->len > dst_mtu(skb->dst) || dst_allfrag(skb->dst)) + if ((skb->len > dst_mtu(skb->dst) || dst_allfrag(skb->dst)) && + !skb_shinfo(skb)->uso_size) return ip6_fragment(skb, ip6_output2); else return ip6_output2(skb); @@ -977,6 +978,19 @@ skb->csum = 0; /* reserve for fragmentation */ skb_reserve(skb, hh_len+sizeof(struct frag_hdr)); + if ((!offset) && (length > mtu) && + (sk->sk_protocol == IPPROTO_UDP) && + (rt->u.dst.dev->features & NETIF_F_USO)) { + struct frag_hdr fhdr; + + skb_shinfo(skb)->uso_size = + (mtu - fragheaderlen - + sizeof(struct frag_hdr)); + skb->ip_summed = CHECKSUM_HW; + ipv6_select_ident(skb, &fhdr); + skb_shinfo(skb)->ip6_frag_id = + fhdr.identification; + } /* * Find where to start putting bytes diff -uNr linux-2.6.12-rc4.org/net/ipv6/udp.c linux-2.6.12-rc4/net/ipv6/udp.c --- linux-2.6.12-rc4.org/net/ipv6/udp.c 2005-05-27 23:24:12.000000000 +0545 +++ linux-2.6.12-rc4/net/ipv6/udp.c 2005-05-31 17:32:31.000000000 +0545 @@ -590,7 +590,8 @@ goto send; } - if (skb_queue_len(&sk->sk_write_queue) == 1) { + if ((skb_queue_len(&sk->sk_write_queue) == 1) || + (skb_shinfo(skb)->uso_size)) { skb->csum = csum_partial((char *)uh, sizeof(struct udphdr), skb->csum); uh->check = csum_ipv6_magic(&fl->fl6_src,