From 48d83325b61043e3bbd24dd37b9fe433744cf330 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 19 Jun 2006 23:57:59 -0700 Subject: [NET]: Prevent multiple qdisc runs Having two or more qdisc_run's contend against each other is bad because it can induce packet reordering if the packets have to be requeued. It appears that this is an unintended consequence of relinquinshing the queue lock while transmitting. That in turn is needed for devices that spend a lot of time in their transmit routine. There are no advantages to be had as devices with queues are inherently single-threaded (the loopback device is not but then it doesn't have a queue). Even if you were to add a queue to a parallel virtual device (e.g., bolt a tbf filter in front of an ipip tunnel device), you would still want to process the queue in sequence to ensure that the packets are ordered correctly. The solution here is to steal a bit from net_device to prevent this. BTW, as qdisc_restart is no longer used by anyone as a module inside the kernel (IIRC it used to with netif_wake_queue), I have not exported the new __qdisc_run function. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e432b743dda2..39919c882a25 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -233,6 +233,7 @@ enum netdev_state_t __LINK_STATE_RX_SCHED, __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, + __LINK_STATE_QDISC_RUNNING, }; -- 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 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') 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 */ -- 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/netdevice.h') 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 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/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/netdevice.h') 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