From 4aa5dee4d9997879adff858514844efab5a15a01 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 20 Jul 2013 12:13:53 +0200 Subject: net: convert resend IGMP to notifier event Until now, bond_resend_igmp_join_requests() looks for vlans attached to bonding device, bridge where bonding act as port manually. It does not care of other scenarios, like stacked bonds or team device above. Make this more generic and use netdev notifier to propagate the event to upper devices and to actually call ip_mc_rejoin_groups(). Signed-off-by: Jiri Pirko Acked-by: Veaceslav Falico 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 0741a1e919a5..2bb2357d83bb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1633,6 +1633,7 @@ struct packet_offload { #define NETDEV_NOTIFY_PEERS 0x0013 #define NETDEV_JOIN 0x0014 #define NETDEV_CHANGEUPPER 0x0015 +#define NETDEV_RESEND_IGMP 0x0016 extern int register_netdevice_notifier(struct notifier_block *nb); extern int unregister_netdevice_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 18afa4b028b46f8b45ca64f94aefe717c297b07d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 23 Jul 2013 16:13:17 +0200 Subject: net: Make devnet_rename_seq static No users outside net/core/dev.c. Signed-off-by: Thomas Gleixner Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2bb2357d83bb..3ca60b070ef0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1666,9 +1666,6 @@ extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern rwlock_t dev_base_lock; /* Device list lock */ -extern seqcount_t devnet_rename_seq; /* Device rename seq */ - - #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_reverse(net, d) \ -- cgit v1.2.3 From 66b52b0dc82c5c88d769dc1c7d44cf45d0deb07c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 29 Jul 2013 18:16:49 +0200 Subject: net: add ndo to get id of physical port of the device This patch adds a ndo for getting physical port of the device. Driver which is aware of being virtual function of some physical port should implement this ndo. This is applicable not only for IOV, but for other solutions (NPAR, multichannel) as well. Basically if there is possible to have multiple netdevs on the single hw port. Signed-off-by: Jiri Pirko Acked-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ca60b070ef0..875f869dc38a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -728,6 +728,16 @@ struct netdev_fcoe_hbainfo { }; #endif +#define MAX_PHYS_PORT_ID_LEN 32 + +/* This structure holds a unique identifier to identify the + * physical port used by a netdevice. + */ +struct netdev_phys_port_id { + unsigned char id[MAX_PHYS_PORT_ID_LEN]; + unsigned char id_len; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -932,6 +942,12 @@ struct netdev_fcoe_hbainfo { * that determine carrier state from physical hardware properties (eg * network cables) or protocol-dependent mechanisms (eg * USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function. + * + * int (*ndo_get_phys_port_id)(struct net_device *dev, + * struct netdev_phys_port_id *ppid); + * Called to get ID of physical port of this device. If driver does + * not implement this, it is assumed that the hw is not able to have + * multiple net devices on single physical port. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1060,6 +1076,8 @@ struct net_device_ops { struct nlmsghdr *nlh); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); + int (*ndo_get_phys_port_id)(struct net_device *dev, + struct netdev_phys_port_id *ppid); }; /* @@ -2315,6 +2333,8 @@ extern int dev_set_mac_address(struct net_device *, struct sockaddr *); extern int dev_change_carrier(struct net_device *, bool new_carrier); +extern int dev_get_phys_port_id(struct net_device *dev, + struct netdev_phys_port_id *ppid); extern int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq); -- cgit v1.2.3 From 5d261913ca3daf6c2d21d38924235667b3d07c40 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Wed, 28 Aug 2013 23:25:05 +0200 Subject: net: add lower_dev_list to net_device and make a full mesh This patch adds lower_dev_list list_head to net_device, which is the same as upper_dev_list, only for lower devices, and begins to use it in the same way as the upper list. It also changes the way the whole adjacent device lists work - now they contain *all* of upper/lower devices, not only the first level. The first level devices are distinguished by the bool neighbour field in netdev_adjacent, also added by this patch. There are cases when a device can be added several times to the adjacent list, the simplest would be: /---- eth0.10 ---\ eth0- --- bond0 \---- eth0.20 ---/ where both bond0 and eth0 'see' each other in the adjacent lists two times. To avoid duplication of netdev_adjacent structures ref_nr is being kept as the number of times the device was added to the list. The 'full view' is achieved by adding, on link creation, all of the upper_dev's upper_dev_list devices as upper devices to all of the lower_dev's lower_dev_list devices (and to the lower_dev itself), and vice versa. On unlink they are removed using the same logic. I've tested it with thousands vlans/bonds/bridges, everything works ok and no observable lags even on a huge number of interfaces. Memory footprint for 128 devices interconnected with each other via both upper and lower (which is impossible, but for the comparison) lists would be: 128*128*2*sizeof(netdev_adjacent) = 1.5MB but in the real world we usualy have at most several devices with slaves and a lot of vlans, so the footprint will be much lower. CC: "David S. Miller" CC: Eric Dumazet CC: Jiri Pirko CC: Alexander Duyck CC: Cong Wang Signed-off-by: Veaceslav Falico 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 077363dcd860..5ccf5b73c378 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1125,6 +1125,7 @@ struct net_device { struct list_head napi_list; struct list_head unreg_list; struct list_head upper_dev_list; /* List of upper devices */ + struct list_head lower_dev_list; /* currently active device features */ -- cgit v1.2.3 From 8b5be8561b804edf6b58fc27edbccf1d45863e08 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Wed, 28 Aug 2013 23:25:08 +0200 Subject: net: add netdev_for_each_upper_dev_rcu() The new macro netdev_for_each_upper_dev_rcu(dev, upper, iter) iterates through the dev->upper_dev_list starting from the first element, using the netdev_upper_get_next_dev_rcu(dev, &iter). Must be called under RCU read lock. CC: "David S. Miller" CC: Eric Dumazet CC: Jiri Pirko CC: Alexander Duyck CC: Cong Wang Signed-off-by: Veaceslav Falico Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5ccf5b73c378..3ad49b833eab 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2768,6 +2768,16 @@ extern int bpf_jit_enable; extern bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); extern bool netdev_has_any_upper_dev(struct net_device *dev); +extern struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter); + +/* iterate through upper list, must be called under RCU read lock */ +#define netdev_for_each_upper_dev_rcu(dev, upper, iter) \ + for (iter = &(dev)->upper_dev_list, \ + upper = netdev_upper_get_next_dev_rcu(dev, &(iter)); \ + upper; \ + upper = netdev_upper_get_next_dev_rcu(dev, &(iter))) + extern struct net_device *netdev_master_upper_dev_get(struct net_device *dev); extern struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); extern int netdev_upper_dev_link(struct net_device *dev, -- cgit v1.2.3 From 53cf527513eed6e7170e9dceacd198f9267171b0 Mon Sep 17 00:00:00 2001 From: Joseph Gasparakis Date: Wed, 4 Sep 2013 02:13:38 -0700 Subject: vxlan: Notify drivers for listening UDP port changes This patch adds two more ndo ops: ndo_add_rx_vxlan_port() and ndo_del_rx_vxlan_port(). Drivers can get notifications through the above functions about changes of the UDP listening port of VXLAN. Also, when physical ports come up, now they can call vxlan_get_rx_port() in order to obtain the port number(s) of the existing VXLAN interface in case they already up before them. This information about the listening UDP port would be used for VXLAN related offloads. A big thank you to John Fastabend (john.r.fastabend@intel.com) for his input and his suggestions on this patch set. CC: John Fastabend CC: Stephen Hemminger Signed-off-by: Joseph Gasparakis Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/netdevice.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ad49b833eab..8ed4ae943053 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -948,6 +948,19 @@ struct netdev_phys_port_id { * Called to get ID of physical port of this device. If driver does * not implement this, it is assumed that the hw is not able to have * multiple net devices on single physical port. + * + * void (*ndo_add_vxlan_port)(struct net_device *dev, + * sa_family_t sa_family, __u16 port); + * Called by vxlan to notiy a driver about the UDP port and socket + * address family that vxlan is listnening to. It is called only when + * a new port starts listening. The operation is protected by the + * vxlan_net->sock_lock. + * + * void (*ndo_del_vxlan_port)(struct net_device *dev, + * sa_family_t sa_family, __u16 port); + * Called by vxlan to notify the driver about a UDP port and socket + * address family that vxlan is not listening to anymore. The operation + * is protected by the vxlan_net->sock_lock. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1078,6 +1091,12 @@ struct net_device_ops { bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_port_id *ppid); + void (*ndo_add_vxlan_port)(struct net_device *dev, + sa_family_t sa_family, + __u16 port); + void (*ndo_del_vxlan_port)(struct net_device *dev, + sa_family_t sa_family, + __u16 port); }; /* -- cgit v1.2.3 From 0042d0c840c616186a5b09207a0e77fab7581db3 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 6 Sep 2013 16:58:00 +0100 Subject: net: add documentation for BQL helpers Provide a kernel-doc comment documentation for the BQL helpers: - netdev_sent_queue - netdev_completed_queue - netdev_reset_queue Similarly to how it is done for the other functions, the documentation only covers the function operating on struct net_device and not struct netdev_queue. Signed-off-by: Florian Fainelli Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8ed4ae943053..041b42a305f6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2101,6 +2101,15 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, #endif } +/** + * netdev_sent_queue - report the number of bytes queued to hardware + * @dev: network device + * @bytes: number of bytes queued to the hardware device queue + * + * Report the number of bytes queued for sending/completion to the network + * device hardware queue. @bytes should be a good approximation and should + * exactly match netdev_completed_queue() @bytes + */ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) { netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes); @@ -2130,6 +2139,16 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, #endif } +/** + * netdev_completed_queue - report bytes and packets completed by device + * @dev: network device + * @pkts: actual number of packets sent over the medium + * @bytes: actual number of bytes sent over the medium + * + * Report the number of bytes and packets transmitted by the network device + * hardware queue over the physical medium, @bytes must exactly match the + * @bytes amount passed to netdev_sent_queue() + */ static inline void netdev_completed_queue(struct net_device *dev, unsigned int pkts, unsigned int bytes) { @@ -2144,6 +2163,13 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q) #endif } +/** + * netdev_reset_queue - reset the packets and bytes count of a network device + * @dev_queue: network device + * + * Reset the bytes and packet count of a network device and clear the + * software flow control OFF bit for this network device + */ static inline void netdev_reset_queue(struct net_device *dev_queue) { netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); -- cgit v1.2.3 From 35e4237973665c8a1ad4e3f7a7cb87573deaa24a Mon Sep 17 00:00:00 2001 From: Joseph Gasparakis Date: Fri, 13 Sep 2013 07:34:13 -0700 Subject: vxlan: Fix sparse warnings This patch fixes sparse warnings when incorrectly handling the port number and using int instead of unsigned int iterating through &vn->sock_list[]. Keeping the port as __be16 also makes things clearer wrt endianess. Also, it was pointed out that vxlan_get_rx_port() had unnecessary checks which got removed. Signed-off-by: Joseph Gasparakis Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 041b42a305f6..3de49aca4519 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -950,14 +950,14 @@ struct netdev_phys_port_id { * multiple net devices on single physical port. * * void (*ndo_add_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __u16 port); + * sa_family_t sa_family, __be16 port); * Called by vxlan to notiy a driver about the UDP port and socket * address family that vxlan is listnening to. It is called only when * a new port starts listening. The operation is protected by the * vxlan_net->sock_lock. * * void (*ndo_del_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __u16 port); + * sa_family_t sa_family, __be16 port); * Called by vxlan to notify the driver about a UDP port and socket * address family that vxlan is not listening to anymore. The operation * is protected by the vxlan_net->sock_lock. @@ -1093,10 +1093,10 @@ struct net_device_ops { struct netdev_phys_port_id *ppid); void (*ndo_add_vxlan_port)(struct net_device *dev, sa_family_t sa_family, - __u16 port); + __be16 port); void (*ndo_del_vxlan_port)(struct net_device *dev, sa_family_t sa_family, - __u16 port); + __be16 port); }; /* -- cgit v1.2.3