From a0a9663dd2146d54339237764e1bfc60e8a39328 Mon Sep 17 00:00:00 2001 From: Sebastian Siewior Date: Thu, 12 Dec 2013 10:15:59 +0100 Subject: net: make neigh_priv_len in struct net_device 16bit instead of 8bit neigh_priv_len is defined as u8. With all debug enabled struct ipoib_neigh has 200 bytes. The largest part is sk_buff_head with 96 bytes and here the spinlock with 72 bytes. The size value still fits in this u8 leaving some room for more. On -RT struct ipoib_neigh put on weight and has 392 bytes. The main reason is sk_buff_head with 288 and the fatty here is spinlock with 192 bytes. This does no longer fit into into neigh_priv_len and gcc complains. This patch changes neigh_priv_len from being 8bit to 16bit. Since the following element (dev_id) is 16bit followed by a spinlock which is aligned, the struct remains with a total size of 3200 (allmodconfig) / 2048 (with as much debug off as possible) bytes on x86-64. On x86-32 the struct is 1856 (allmodconfig) / 1216 (with as much debug off as possible) bytes long. The numbers were gained with and without the patch to prove that this change does not increase the size of the struct. Cc: Steven Rostedt Cc: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7f0ed423a360..d9a550bf3e8e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1255,7 +1255,7 @@ struct net_device { unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ unsigned char addr_assign_type; /* hw address assignment type */ unsigned char addr_len; /* hardware address length */ - unsigned char neigh_priv_len; + unsigned short neigh_priv_len; unsigned short dev_id; /* Used to differentiate devices * that share the same link * layer address -- cgit v1.2.2 From 2205369a314e12fcec4781cc73ac9c08fc2b47de Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 31 Dec 2013 16:23:35 -0500 Subject: vlan: Fix header ops passthru when doing TX VLAN offload. When the vlan code detects that the real device can do TX VLAN offloads in hardware, it tries to arrange for the real device's header_ops to be invoked directly. But it does so illegally, by simply hooking the real device's header_ops up to the VLAN device. This doesn't work because we will end up invoking a set of header_ops routines which expect a device type which matches the real device, but will see a VLAN device instead. Fix this by providing a pass-thru set of header_ops which will arrange to pass the proper real device instead. To facilitate this add a dev_rebuild_header(). There are implementations which provide a ->cache and ->create but not a ->rebuild (f.e. PLIP). So we need a helper function just like dev_hard_header() to avoid crashes. Use this helper in the one existing place where the header_ops->rebuild was being invoked, the neighbour code. With lots of help from Florian Westphal. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d9a550bf3e8e..7514b9c37a39 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1912,6 +1912,15 @@ static inline int dev_parse_header(const struct sk_buff *skb, return dev->header_ops->parse(skb, haddr); } +static inline int dev_rebuild_header(struct sk_buff *skb) +{ + const struct net_device *dev = skb->dev; + + if (!dev->header_ops || !dev->header_ops->rebuild) + return 0; + return dev->header_ops->rebuild(skb); +} + typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); static inline int unregister_gifconf(unsigned int family) -- cgit v1.2.2 From 7a7ffbabf99445704be01bff5d7e360da908cf8e Mon Sep 17 00:00:00 2001 From: Wei-Chun Chao Date: Thu, 26 Dec 2013 13:10:22 -0800 Subject: ipv4: fix tunneled VM traffic over hw VXLAN/GRE GSO NIC VM to VM GSO traffic is broken if it goes through VXLAN or GRE tunnel and the physical NIC on the host supports hardware VXLAN/GRE GSO offload (e.g. bnx2x and next-gen mlx4). Two issues - (VXLAN) VM traffic has SKB_GSO_DODGY and SKB_GSO_UDP_TUNNEL with SKB_GSO_TCP/UDP set depending on the inner protocol. GSO header integrity check fails in udp4_ufo_fragment if inner protocol is TCP. Also gso_segs is calculated incorrectly using skb->len that includes tunnel header. Fix: robust check should only be applied to the inner packet. (VXLAN & GRE) Once GSO header integrity check passes, NULL segs is returned and the original skb is sent to hardware. However the tunnel header is already pulled. Fix: tunnel header needs to be restored so that hardware can perform GSO properly on the original packet. Signed-off-by: Wei-Chun Chao Signed-off-by: David S. Miller --- include/linux/netdevice.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7514b9c37a39..5faaadb0c74f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3017,6 +3017,19 @@ static inline void netif_set_gso_max_size(struct net_device *dev, dev->gso_max_size = size; } +static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, + int pulled_hlen, u16 mac_offset, + int mac_len) +{ + skb->protocol = protocol; + skb->encapsulation = 1; + skb_push(skb, pulled_hlen); + skb_reset_transport_header(skb); + skb->mac_header = mac_offset; + skb->network_header = skb->mac_header + mac_len; + skb->mac_len = mac_len; +} + static inline bool netif_is_macvlan(struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN; -- cgit v1.2.2 From f663dd9aaf9ed124f25f0f8452edf238f087ad50 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 10 Jan 2014 16:18:26 +0800 Subject: net: core: explicitly select a txq before doing l2 forwarding Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The will cause several issues: - NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan instead of lower device which misses the necessary txq synchronization for lower device such as txq stopping or frozen required by dev watchdog or control path. - dev_hard_start_xmit() was called with NULL txq which bypasses the net device watchdog. - dev_hard_start_xmit() does not check txq everywhere which will lead a crash when tso is disabled for lower device. Fix this by explicitly introducing a new param for .ndo_select_queue() for just selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also extended to accept this parameter and dev_queue_xmit_accel() was used to do l2 forwarding transmission. With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of dev_queue_xmit() to do the transmission. In the future, it was also required for macvtap l2 forwarding support since it provides a necessary synchronization method. Cc: John Fastabend Cc: Neil Horman Cc: e1000-devel@lists.sourceforge.net Signed-off-by: Jason Wang Acked-by: Neil Horman Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/netdevice.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5faaadb0c74f..ce2a1f5f9a1e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -769,7 +769,8 @@ struct netdev_phys_port_id { * (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX) * Required can not be NULL. * - * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb); + * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, + * void *accel_priv); * Called to decide which queue to when device supports multiple * transmit queues. * @@ -990,7 +991,8 @@ struct net_device_ops { netdev_tx_t (*ndo_start_xmit) (struct sk_buff *skb, struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, - struct sk_buff *skb); + struct sk_buff *skb, + void *accel_priv); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -1529,7 +1531,8 @@ 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); + struct sk_buff *skb, + void *accel_priv); u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); /* @@ -1819,6 +1822,7 @@ int dev_close(struct net_device *dev); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); +int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); @@ -2426,7 +2430,7 @@ int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_port_id *ppid); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq, void *accel_priv); + struct netdev_queue *txq); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); extern int netdev_budget; -- cgit v1.2.2