From d206940319c41df4299db75ed56142177bb2e5f6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Feb 2014 23:09:11 +0100 Subject: net: core: introduce netif_skb_dev_features Will be used by upcoming ipv4 forward path change that needs to determine feature mask using skb->dst->dev instead of skb->dev. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 440a02ee6f92..21d4e6be8949 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3068,7 +3068,12 @@ void netdev_change_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -netdev_features_t netif_skb_features(struct sk_buff *skb); +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev); +static inline netdev_features_t netif_skb_features(struct sk_buff *skb) +{ + return netif_skb_dev_features(skb, skb->dev); +} static inline bool net_gso_ok(netdev_features_t features, int gso_type) { -- cgit v1.2.2 From fe6cc55f3a9a053482a76f5a6b2257cee51b4663 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Feb 2014 23:09:12 +0100 Subject: net: ip, ipv6: handle gso skbs in forwarding path Marcelo Ricardo Leitner reported problems when the forwarding link path has a lower mtu than the incoming one if the inbound interface supports GRO. Given: Host R1 R2 Host sends tcp stream which is routed via R1 and R2. R1 performs GRO. In this case, the kernel will fail to send ICMP fragmentation needed messages (or pkt too big for ipv6), as GSO packets currently bypass dstmtu checks in forward path. Instead, Linux tries to send out packets exceeding the mtu. When locking route MTU on Host (i.e., no ipv4 DF bit set), R1 does not fragment the packets when forwarding, and again tries to send out packets exceeding R1-R2 link mtu. This alters the forwarding dstmtu checks to take the individual gso segment lengths into account. For ipv6, we send out pkt too big error for gso if the individual segments are too big. For ipv4, we either send icmp fragmentation needed, or, if the DF bit is not set, perform software segmentation and let the output path create fragments when the packet is leaving the machine. It is not 100% correct as the error message will contain the headers of the GRO skb instead of the original/segmented one, but it seems to work fine in my (limited) tests. Eric Dumazet suggested to simply shrink mss via ->gso_size to avoid sofware segmentation. However it turns out that skb_segment() assumes skb nr_frags is related to mss size so we would BUG there. I don't want to mess with it considering Herbert and Eric disagree on what the correct behavior should be. Hannes Frederic Sowa notes that when we would shrink gso_size skb_segment would then also need to deal with the case where SKB_MAX_FRAGS would be exceeded. This uses sofware segmentation in the forward path when we hit ipv4 non-DF packets and the outgoing link mtu is too small. Its not perfect, but given the lack of bug reports wrt. GRO fwd being broken this is a rare case anyway. Also its not like this could not be improved later once the dust settles. Acked-by: Herbert Xu Reported-by: Marcelo Ricardo Leitner Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f589c9af8cbf..3ebbbe7b6d05 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2916,5 +2916,22 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } + +/** + * skb_gso_network_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_network_seglen is used to determine the real size of the + * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). + * + * The MAC/L2 header is not accounted for. + */ +static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - + skb_network_header(skb); + return hdr_len + skb_gso_transport_seglen(skb); +} #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ -- cgit v1.2.2 From 99932d4fc03a13bb3e94938fe25458fabc8f2fc3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 16 Feb 2014 15:55:20 +0100 Subject: netdevice: add queue selection fallback handler for ndo_select_queue Add a new argument for ndo_select_queue() callback that passes a fallback handler. This gets invoked through netdev_pick_tx(); fallback handler is currently __netdev_pick_tx() as most drivers invoke this function within their customized implementation in case for skbs that don't need any special handling. This fallback handler can then be replaced on other call-sites with different queue selection methods (e.g. in packet sockets, pktgen etc). This also has the nice side-effect that __netdev_pick_tx() is then only invoked from netdev_pick_tx() and export of that function to modules can be undone. Suggested-by: David S. Miller Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 21d4e6be8949..1de9c136b066 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -752,6 +752,9 @@ struct netdev_phys_port_id { unsigned char id_len; }; +typedef u16 (*select_queue_fallback_t)(struct net_device *dev, + struct sk_buff *skb); + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -783,7 +786,7 @@ struct netdev_phys_port_id { * Required can not be NULL. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - * void *accel_priv); + * void *accel_priv, select_queue_fallback_t fallback); * Called to decide which queue to when device supports multiple * transmit queues. * @@ -1005,7 +1008,8 @@ struct net_device_ops { struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, + select_queue_fallback_t fallback); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -1551,7 +1555,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, void *accel_priv); -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); /* * Net namespace inlines -- cgit v1.2.2 From b9507bdaf40e91fea2b1c0c1ee7dc627c8ee6fd6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 16 Feb 2014 15:55:21 +0100 Subject: netdevice: move netdev_cap_txqueue for shared usage to header In order to allow users to invoke netdev_cap_txqueue, it needs to be moved into netdevice.h header file. While at it, also add kernel doc header to document the API. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1de9c136b066..e8eeebd49a98 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2278,6 +2278,26 @@ static inline void netdev_reset_queue(struct net_device *dev_queue) netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); } +/** + * netdev_cap_txqueue - check if selected tx queue exceeds device queues + * @dev: network device + * @queue_index: given tx queue index + * + * Returns 0 if given tx queue index >= number of device tx queues, + * otherwise returns the originally passed tx queue index. + */ +static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); + return 0; + } + + return queue_index; +} + /** * netif_running - test if up * @dev: network device -- cgit v1.2.2