From 5b057c6b1a25d57edf2b4d1e956e50936480a9ff Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 23 Jun 2006 02:06:41 -0700 Subject: [NET]: Avoid allocating skb in skb_pad First of all it is unnecessary to allocate a new skb in skb_pad since the existing one is not shared. More importantly, our hard_start_xmit interface does not allow a new skb to be allocated since that breaks requeueing. This patch uses pskb_expand_head to expand the existing skb and linearize it if needed. Actually, someone should sift through every instance of skb_pad on a non-linear skb as they do not fit the reasons why this was originally created. Incidentally, this fixes a minor bug when the skb is cloned (tcpdump, TCP, etc.). As it is skb_pad will simply write over a cloned skb. Because of the position of the write it is unlikely to cause problems but still it's best if we don't do it. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/skbuff.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 66f8819f9568..f8c7eb79a27f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -345,7 +345,7 @@ extern struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, extern struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); -extern struct sk_buff * skb_pad(struct sk_buff *skb, int pad); +extern int skb_pad(struct sk_buff *skb, int pad); #define dev_kfree_skb(a) kfree_skb(a) extern void skb_over_panic(struct sk_buff *skb, int len, void *here); @@ -1122,16 +1122,15 @@ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it - * is untouched. Returns the buffer, which may be a replacement - * for the original, or NULL for out of memory - in which case - * the original buffer is still freed. + * is untouched. Otherwise it is extended. Returns zero on + * success. The skb is freed on error. */ -static inline struct sk_buff *skb_padto(struct sk_buff *skb, unsigned int len) +static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) - return skb; + return 0; return skb_pad(skb, len-size); } -- cgit v1.2.3 From 7967168cefdbc63bf332d6b1548eca7cd65ebbcc Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 22 Jun 2006 02:40:14 -0700 Subject: [NET]: Merge TSO/UFO fields in sk_buff Having separate fields in sk_buff for TSO/UFO (tso_size/ufo_size) is not going to scale if we add any more segmentation methods (e.g., DCCP). So let's merge them. They were used to tell the protocol of a packet. This function has been subsumed by the new gso_type field. This is essentially a set of netdev feature bits (shifted by 16 bits) that are required to process a specific skb. As such it's easy to tell whether a given device can process a GSO skb: you just have to and the gso_type field and the netdev's features field. I've made gso_type a conjunction. The idea is that you have a base type (e.g., SKB_GSO_TCPV4) that can be modified further to support new features. For example, if we add a hardware TSO type that supports ECN, they would declare NETIF_F_TSO | NETIF_F_TSO_ECN. All TSO packets with CWR set would have a gso_type of SKB_GSO_TCPV4 | SKB_GSO_TCPV4_ECN while all other TSO packets would be SKB_GSO_TCPV4. This means that only the CWR packets need to be emulated in software. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 ++++++++++++-- include/linux/skbuff.h | 12 +++++++++--- 2 files changed, 21 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cead6be467ed..fa5671307b90 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -308,9 +308,12 @@ struct net_device #define NETIF_F_HW_VLAN_RX 256 /* Receive VLAN hw acceleration */ #define NETIF_F_HW_VLAN_FILTER 512 /* Receive filtering on VLAN */ #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_UFO 8192 /* Can offload UDP Large Send*/ + + /* Segmentation offload features */ +#define NETIF_F_GSO_SHIFT 16 +#define NETIF_F_TSO (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT) +#define NETIF_F_UFO (SKB_GSO_UDPV4 << NETIF_F_GSO_SHIFT) #define NETIF_F_GEN_CSUM (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM) #define NETIF_F_ALL_CSUM (NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM) @@ -979,6 +982,13 @@ extern void dev_seq_stop(struct seq_file *seq, void *v); extern void linkwatch_run_queue(void); +static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb) +{ + int feature = skb_shinfo(skb)->gso_type << NETIF_F_GSO_SHIFT; + return skb_shinfo(skb)->gso_size && + (dev->features & feature) != feature; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_DEV_H */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f8c7eb79a27f..97b0d2d1a6b0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -134,9 +134,10 @@ struct skb_frag_struct { struct skb_shared_info { atomic_t dataref; unsigned short nr_frags; - unsigned short tso_size; - unsigned short tso_segs; - unsigned short ufo_size; + unsigned short gso_size; + /* Warning: this field is not always filled in (UFO)! */ + unsigned short gso_segs; + unsigned short gso_type; unsigned int ip6_frag_id; struct sk_buff *frag_list; skb_frag_t frags[MAX_SKB_FRAGS]; @@ -168,6 +169,11 @@ enum { SKB_FCLONE_CLONE, }; +enum { + SKB_GSO_TCPV4 = 1 << 0, + SKB_GSO_UDPV4 = 1 << 1, +}; + /** * struct sk_buff - socket buffer * @next: Next buffer in list -- cgit v1.2.3 From f6a78bfcb141f963187464bac838d46a81c3882a Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 22 Jun 2006 02:57:17 -0700 Subject: [NET]: Add generic segmentation offload This patch adds the infrastructure for generic segmentation offload. The idea is to tap into the potential savings of TSO without hardware support by postponing the allocation of segmented skb's until just before the entry point into the NIC driver. The same structure can be used to support software IPv6 TSO, as well as UFO and segmentation offload for other relevant protocols, e.g., DCCP. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fa5671307b90..b4eae18390cc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -405,6 +405,9 @@ struct net_device struct list_head qdisc_list; unsigned long tx_queue_len; /* Max frames per queue allowed */ + /* Partially transmitted GSO packet. */ + struct sk_buff *gso_skb; + /* ingress path synchronizer */ spinlock_t ingress_lock; struct Qdisc *qdisc_ingress; @@ -539,6 +542,7 @@ struct packet_type { struct net_device *, struct packet_type *, struct net_device *); + struct sk_buff *(*gso_segment)(struct sk_buff *skb, int sg); void *af_packet_priv; struct list_head list; }; @@ -689,7 +693,8 @@ extern int dev_change_name(struct net_device *, char *); extern int dev_set_mtu(struct net_device *, int); extern int dev_set_mac_address(struct net_device *, struct sockaddr *); -extern void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); +extern int dev_hard_start_xmit(struct sk_buff *skb, + struct net_device *dev); extern void dev_init(void); @@ -963,6 +968,7 @@ extern int netdev_max_backlog; extern int weight_p; extern int netdev_set_master(struct net_device *dev, struct net_device *master); extern int skb_checksum_help(struct sk_buff *skb, int inward); +extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg); #ifdef CONFIG_BUG extern void netdev_rx_csum_fault(struct net_device *dev); #else -- cgit v1.2.3 From f4c50d990dcf11a296679dc05de3873783236711 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 22 Jun 2006 03:02:40 -0700 Subject: [NET]: Add software TSOv4 This patch adds the GSO implementation for IPv4 TCP. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 97b0d2d1a6b0..a45bba9b8cbd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1297,6 +1297,7 @@ extern void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); extern void skb_release_data(struct sk_buff *skb); +extern struct sk_buff *skb_segment(struct sk_buff *skb, int sg); static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) -- cgit v1.2.3 From 37c3185a02d4b85fbe134bf5204535405dd2c957 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 22 Jun 2006 03:07:29 -0700 Subject: [NET]: Added GSO toggle This patch adds a generic segmentation offload toggle that can be turned on/off for each net device. For now it only supports in TCPv4. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/ethtool.h | 2 ++ include/linux/netdevice.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index cf2abeca92a0..c6310aef5ab0 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -411,6 +411,8 @@ struct ethtool_ops { #define ETHTOOL_GPERMADDR 0x00000020 /* Get permanent hardware address */ #define ETHTOOL_GUFO 0x00000021 /* Get UFO enable (ethtool_value) */ #define ETHTOOL_SUFO 0x00000022 /* Set UFO enable (ethtool_value) */ +#define ETHTOOL_GGSO 0x00000023 /* Get GSO enable (ethtool_value) */ +#define ETHTOOL_SGSO 0x00000024 /* Set GSO enable (ethtool_value) */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b4eae18390cc..bc747e5d7138 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -308,6 +308,7 @@ struct net_device #define NETIF_F_HW_VLAN_RX 256 /* Receive VLAN hw acceleration */ #define NETIF_F_HW_VLAN_FILTER 512 /* Receive filtering on VLAN */ #define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */ +#define NETIF_F_GSO 2048 /* Enable software GSO. */ #define NETIF_F_LLTX 4096 /* LockLess TX */ /* Segmentation offload features */ -- cgit v1.2.3 From c8a553ad7f0bf943047943a758cf07017819cb3c Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 22 Jun 2006 14:28:09 -0700 Subject: [TCP]: Move inclusion of to correct place in The new header shouldn't be included from the !__KERNEL__ portion of tcp.h Signed-off-by: David Woodhouse Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 420a689c3fb4..8ebf497907f8 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -18,7 +18,6 @@ #define _LINUX_TCP_H #include -#include #include struct tcphdr { @@ -161,6 +160,7 @@ struct tcp_info #ifdef __KERNEL__ #include +#include #include #include #include -- cgit v1.2.3 From f4b8ea7849544114e9d3d682df4d400180854677 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 22 Jun 2006 16:00:11 -0700 Subject: [NET]: fix net-core kernel-doc Warning(/var/linsrc/linux-2617-g4//include/linux/skbuff.h:304): No description found for parameter 'dma_cookie' Warning(/var/linsrc/linux-2617-g4//include/net/sock.h:1274): No description found for parameter 'copied_early' Warning(/var/linsrc/linux-2617-g4//net/core/dev.c:3309): No description found for parameter 'chan' Warning(/var/linsrc/linux-2617-g4//net/core/dev.c:3309): No description found for parameter 'event' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a45bba9b8cbd..16eef03ce0eb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -215,6 +215,8 @@ enum { * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @tc_index: Traffic control index * @tc_verd: traffic control verdict + * @dma_cookie: a cookie to one of several possible DMA operations + * done by skb DMA functions * @secmark: security marking */ -- cgit v1.2.3