From d476059e77d1af48453a58f9de1e36f2eaff6450 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Mar 2015 00:11:09 -0600 Subject: net: Kill dev_rebuild_header Now that there are no more users kill dev_rebuild_header and all of it's implementations. This is long overdue. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netdevice.h | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5897b4ea5a3f..2007f3b44d05 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -261,7 +261,6 @@ struct header_ops { unsigned short type, const void *daddr, const void *saddr, unsigned int len); int (*parse)(const struct sk_buff *skb, unsigned char *haddr); - int (*rebuild)(struct sk_buff *skb); int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, @@ -1346,7 +1345,7 @@ enum netdev_priv_flags { * if one wants to override the ndo_*() functions * @ethtool_ops: Management operations * @fwd_ops: Management operations - * @header_ops: Includes callbacks for creating,parsing,rebuilding,etc + * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * * @flags: Interface flags (a la BSD) @@ -2399,15 +2398,6 @@ 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 v1.2.3 From 4586f1bb911ce219a4bc1c2a9d6eee2e058b2b51 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:14 -0800 Subject: netdevice: add IPv4 fib add/del ops Add two new ndo ops for IPv4 fib offload support, add and del. Add uses modifiy semantics if fib entry already offloaded. Drivers implementing the new ndo ops will return err<0 if programming device fails, for example if device's tables are full. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 625c8d71511b..45413784a3b1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -768,6 +768,8 @@ struct netdev_phys_item_id { typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); +struct fib_info; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1031,6 +1033,14 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state); * Called to notify switch device port of bridge port STP * state change. + * int (*ndo_sw_parent_fib_ipv4_add)(struct net_device *dev, __be32 dst, + * int dst_len, struct fib_info *fi, + * u8 tos, u8 type, u32 tb_id); + * Called to add/modify IPv4 route to switch device. + * int (*ndo_sw_parent_fib_ipv4_del)(struct net_device *dev, __be32 dst, + * int dst_len, struct fib_info *fi, + * u8 tos, u8 type, u32 tb_id); + * Called to delete IPv4 route from switch device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1192,6 +1202,18 @@ struct net_device_ops { struct netdev_phys_item_id *psid); int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state); + int (*ndo_switch_fib_ipv4_add)(struct net_device *dev, + __be32 dst, + int dst_len, + struct fib_info *fi, + u8 tos, u8 type, + u32 tb_id); + int (*ndo_switch_fib_ipv4_del)(struct net_device *dev, + __be32 dst, + int dst_len, + struct fib_info *fi, + u8 tos, u8 type, + u32 tb_id); #endif }; -- cgit v1.2.3 From f8f2147150de303e814c0452075d467734d3544b Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Mon, 9 Mar 2015 13:59:09 -0700 Subject: switchdev: add netlink flags to IPv4 FIB add op Pass in the netlink flags (NLM_F_*) into switchdev driver for IPv4 FIB add op to allow driver to 1) optimize hardware updates, 2) handle ip route prepend and append commands correctly. Suggested-by: Jamal Hadi Salim Suggested-by: Roopa Prabhu Signed-off-by: Scott Feldman Reviewed-by: Simon Horman Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 45413784a3b1..1354ae83efc8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1035,7 +1035,7 @@ struct fib_info; * state change. * int (*ndo_sw_parent_fib_ipv4_add)(struct net_device *dev, __be32 dst, * int dst_len, struct fib_info *fi, - * u8 tos, u8 type, u32 tb_id); + * u8 tos, u8 type, u32 nlflags, u32 tb_id); * Called to add/modify IPv4 route to switch device. * int (*ndo_sw_parent_fib_ipv4_del)(struct net_device *dev, __be32 dst, * int dst_len, struct fib_info *fi, @@ -1207,6 +1207,7 @@ struct net_device_ops { int dst_len, struct fib_info *fi, u8 tos, u8 type, + u32 nlflags, u32 tb_id); int (*ndo_switch_fib_ipv4_del)(struct net_device *dev, __be32 dst, -- cgit v1.2.3 From efd7ef1c1929d7a0329d4349252863c04d6f1729 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 11 Mar 2015 23:04:08 -0500 Subject: net: Kill hold_net release_net hold_net and release_net were an idea that turned out to be useless. The code has been disabled since 2008. Kill the code it is long past due. Signed-off-by: "Eric W. Biederman" Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1354ae83efc8..cede40d9cac9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1864,8 +1864,7 @@ static inline void dev_net_set(struct net_device *dev, struct net *net) { #ifdef CONFIG_NET_NS - release_net(dev->nd_net); - dev->nd_net = hold_net(net); + dev->nd_net = net; #endif } -- cgit v1.2.3 From 0c5c9fb55106333e773de8c9dd321fa8240caeb3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 11 Mar 2015 23:06:44 -0500 Subject: net: Introduce possible_net_t Having to say > #ifdef CONFIG_NET_NS > struct net *net; > #endif in structures is a little bit wordy and a little bit error prone. Instead it is possible to say: > typedef struct { > #ifdef CONFIG_NET_NS > struct net *net; > #endif > } possible_net_t; And then in a header say: > possible_net_t net; Which is cleaner and easier to use and easier to test, as the possible_net_t is always there no matter what the compile options. Further this allows read_pnet and write_pnet to be functions in all cases which is better at catching typos. This change adds possible_net_t, updates the definitions of read_pnet and write_pnet, updates optional struct net * variables that write_pnet uses on to have the type possible_net_t, and finally fixes up the b0rked users of read_pnet and write_pnet. Signed-off-by: "Eric W. Biederman" Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cede40d9cac9..ddab1a2a07a0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1721,9 +1721,7 @@ struct net_device { struct netpoll_info __rcu *npinfo; #endif -#ifdef CONFIG_NET_NS - struct net *nd_net; -#endif + possible_net_t nd_net; /* mid-layer private */ union { @@ -1863,9 +1861,7 @@ struct net *dev_net(const struct net_device *dev) static inline void dev_net_set(struct net_device *dev, struct net *net) { -#ifdef CONFIG_NET_NS - dev->nd_net = net; -#endif + write_pnet(&dev->nd_net, net); } static inline bool netdev_uses_dsa(struct net_device *dev) -- cgit v1.2.3 From 4170604feec780d00e7511c24fa0f6e5c2e4ed75 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 15 Mar 2015 21:07:14 -0700 Subject: switchdev: add swdev ops As discussed at netconf, introduce swdev_ops as first step to move switchdev ops from ndo to swdev. This will keep switchdev from cluttering up ndo ops space. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ddab1a2a07a0..9e8a2a933c68 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1577,6 +1577,9 @@ struct net_device { const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; const struct forwarding_accel_ops *fwd_ops; +#ifdef CONFIG_NET_SWITCHDEV + const struct swdev_ops *swdev_ops; +#endif const struct header_ops *header_ops; -- cgit v1.2.3 From 812a1c3ff3ee9d5100e0e71edb06681014e84a9b Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 15 Mar 2015 21:07:16 -0700 Subject: netdev: remove ndo ops for switchdev Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 38 -------------------------------------- 1 file changed, 38 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9e8a2a933c68..dd1d069758be 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -768,8 +768,6 @@ struct netdev_phys_item_id { typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); -struct fib_info; - /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1024,23 +1022,6 @@ struct fib_info; * be otherwise expressed by feature flags. The check is called with * the set of features that the stack has calculated and it returns * those the driver believes to be appropriate. - * - * int (*ndo_switch_parent_id_get)(struct net_device *dev, - * struct netdev_phys_item_id *psid); - * Called to get an ID of the switch chip this port is part of. - * If driver implements this, it indicates that it represents a port - * of a switch chip. - * int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state); - * Called to notify switch device port of bridge port STP - * state change. - * int (*ndo_sw_parent_fib_ipv4_add)(struct net_device *dev, __be32 dst, - * int dst_len, struct fib_info *fi, - * u8 tos, u8 type, u32 nlflags, u32 tb_id); - * Called to add/modify IPv4 route to switch device. - * int (*ndo_sw_parent_fib_ipv4_del)(struct net_device *dev, __be32 dst, - * int dst_len, struct fib_info *fi, - * u8 tos, u8 type, u32 tb_id); - * Called to delete IPv4 route from switch device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1197,25 +1178,6 @@ struct net_device_ops { netdev_features_t (*ndo_features_check) (struct sk_buff *skb, struct net_device *dev, netdev_features_t features); -#ifdef CONFIG_NET_SWITCHDEV - int (*ndo_switch_parent_id_get)(struct net_device *dev, - struct netdev_phys_item_id *psid); - int (*ndo_switch_port_stp_update)(struct net_device *dev, - u8 state); - int (*ndo_switch_fib_ipv4_add)(struct net_device *dev, - __be32 dst, - int dst_len, - struct fib_info *fi, - u8 tos, u8 type, - u32 nlflags, - u32 tb_id); - int (*ndo_switch_fib_ipv4_del)(struct net_device *dev, - __be32 dst, - int dst_len, - struct fib_info *fi, - u8 tos, u8 type, - u32 tb_id); -#endif }; /** -- cgit v1.2.3 From 822b3b2ebfff8e9b3d006086c527738a7ca00cd0 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 18 Mar 2015 14:57:33 +0200 Subject: net: Add max rate tx queue attribute This adds a tx_maxrate attribute to the tx queue sysfs entry allowing for max-rate limiting. Along with DCB-ETS and BQL this provides another knob to tune queue performance. The limit units are Mbps. By default it is disabled. To disable the rate limitation after it has been set for a queue, it should be set to zero. Signed-off-by: John Fastabend Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dd1d069758be..76c5de4978a8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -587,6 +587,7 @@ struct netdev_queue { #ifdef CONFIG_BQL struct dql dql; #endif + unsigned long tx_maxrate; } ____cacheline_aligned_in_smp; static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) @@ -1022,6 +1023,10 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * be otherwise expressed by feature flags. The check is called with * the set of features that the stack has calculated and it returns * those the driver believes to be appropriate. + * int (*ndo_set_tx_maxrate)(struct net_device *dev, + * int queue_index, u32 maxrate); + * Called when a user wants to set a max-rate limitation of specific + * TX queue. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1178,6 +1183,9 @@ struct net_device_ops { netdev_features_t (*ndo_features_check) (struct sk_buff *skb, struct net_device *dev, netdev_features_t features); + int (*ndo_set_tx_maxrate)(struct net_device *dev, + int queue_index, + u32 maxrate); }; /** -- cgit v1.2.3 From db24a9044ee191c397dcd1c6574f56d67d7c8df5 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 17 Mar 2015 20:23:15 -0600 Subject: net: add support for phys_port_name Similar to port id allow netdevices to specify port names and export the name via sysfs. Drivers can implement the netdevice operation to assist udev in having sane default names for the devices using the rule: $ cat /etc/udev/rules.d/80-net-setup-link.rules SUBSYSTEM=="net", ACTION=="add", ATTR{phys_port_name}!="", NAME="$attr{phys_port_name}" Use of phys_name versus phys_id was suggested-by Jiri Pirko. Signed-off-by: David Ahern Acked-by: Jiri Pirko Acked-by: Scott Feldman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 76c5de4978a8..ec8f9b5f6500 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1164,6 +1164,8 @@ struct net_device_ops { bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); + int (*ndo_get_phys_port_name)(struct net_device *dev, + char *name, size_t len); void (*ndo_add_vxlan_port)(struct net_device *dev, sa_family_t sa_family, __be16 port); @@ -2947,6 +2949,8 @@ int dev_set_mac_address(struct net_device *, struct sockaddr *); int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); +int dev_get_phys_port_name(struct net_device *dev, + char *name, size_t len); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -- cgit v1.2.3 From 99c4a26a159b28fa46a3e746a9b41b297e73d261 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 18 Mar 2015 22:52:33 -0400 Subject: net: Fix high overhead of vlan sub-device teardown. When a networking device is taken down that has a non-trivial number of VLAN devices configured under it, we eat a full synchronize_net() for every such VLAN device. This is because of the call chain: NETDEV_DOWN notifier --> vlan_device_event() --> dev_change_flags() --> __dev_change_flags() --> __dev_close() --> __dev_close_many() --> dev_deactivate_many() --> synchronize_net() This is kind of rediculous because we already have infrastructure for batching doing operation X to a list of net devices so that we only incur one sync. So make use of that by exporting dev_close_many() and adjusting it's interfaace so that the caller can fully manage the batch list. Use this in vlan_device_event() and all the overhead goes away. Reported-by: Salam Noureddine 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 ec8f9b5f6500..76951c5fbedf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2156,6 +2156,7 @@ struct net_device *__dev_get_by_name(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev); int dev_close(struct net_device *dev); +int dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); -- cgit v1.2.3 From 0117ec1970c5fa9c566045e7df8db76acc8f150e Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 23 Mar 2015 18:40:02 +0100 Subject: net: remove never used forwarding_accel_ops pointer from net_device Cc: John Fastabend Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5ae69e7df867..08c4ab37189f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1342,7 +1342,6 @@ enum netdev_priv_flags { * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @ethtool_ops: Management operations - * @fwd_ops: Management operations * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * @@ -1551,7 +1550,6 @@ struct net_device { #endif const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; - const struct forwarding_accel_ops *fwd_ops; #ifdef CONFIG_NET_SWITCHDEV const struct swdev_ops *swdev_ops; #endif -- cgit v1.2.3 From e38f30256b36700aa63aa709dc091bf6eb69c257 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 27 Mar 2015 14:31:13 +0900 Subject: net: Introduce passthru_features_check As there are a number of (especially virtual) devices that don't need the multiple vlan check, introduce passthru_features_check() for convenience. Signed-off-by: Toshiaki Makita Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 08c4ab37189f..967bb4c8caf1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3657,6 +3657,9 @@ 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 passthru_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features); netdev_features_t netif_skb_features(struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) -- cgit v1.2.3 From a54acb3a6f853e8394c4cb7b6a4d93c88f13eefd Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 2 Apr 2015 17:07:00 +0200 Subject: dev: introduce dev_get_iflink() The goal of this patch is to prepare the removal of the iflink field. It introduces a new ndo function, which will be implemented by virtual interfaces. There is no functional change into this patch. All readers of iflink field now call dev_get_iflink(). Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 967bb4c8caf1..788eb7a622ad 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1030,6 +1030,8 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int queue_index, u32 maxrate); * Called when a user wants to set a max-rate limitation of specific * TX queue. + * int (*ndo_get_iflink)(const struct net_device *dev); + * Called to get the iflink value of this device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1191,6 +1193,7 @@ struct net_device_ops { int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); + int (*ndo_get_iflink)(const struct net_device *dev); }; /** @@ -2149,6 +2152,7 @@ void __dev_remove_pack(struct packet_type *pt); void dev_add_offload(struct packet_offload *po); void dev_remove_offload(struct packet_offload *po); +int dev_get_iflink(const struct net_device *dev); struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, unsigned short mask); struct net_device *dev_get_by_name(struct net *net, const char *name); -- cgit v1.2.3 From 7a66bbc96ce9ad8261fa5f7f6ae65370eb6866ee Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 2 Apr 2015 17:07:09 +0200 Subject: net: remove iflink field from struct net_device Now that all users of iflink have the ndo_get_iflink handler available, it's possible to remove this field. By default, dev_get_iflink() returns the ifindex of the interface. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 788eb7a622ad..846a1f5bc9db 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1538,7 +1538,7 @@ struct net_device { netdev_features_t mpls_features; int ifindex; - int iflink; + int group; struct net_device_stats stats; @@ -1741,7 +1741,6 @@ struct net_device { #endif struct phy_device *phydev; struct lock_class_key *qdisc_tx_busylock; - int group; struct pm_qos_request pm_qos_req; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From e79d8429aac95a5cbe4c235795c7cd554c91f924 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 3 Apr 2015 22:17:17 +1030 Subject: netdevice: document NETDEV_TX_BUSY deprecation. This paraphrases DaveM (and steals some of his words) explaining why a device shouldn't return NETDEV_TX_BUSY, even though it looks so inviting to driver authors. See http://www.spinics.net/lists/netdev/msg322350.html Inspired-by: David Miller Signed-off-by: Rusty Russell Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 846a1f5bc9db..a710d22b174f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -795,7 +795,10 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, * struct net_device *dev); * Called when a packet needs to be transmitted. - * Must return NETDEV_TX_OK , NETDEV_TX_BUSY. + * Returns NETDEV_TX_OK. Can return NETDEV_TX_BUSY, but you should stop + * the queue before that can happen; it's for obsolete devices and weird + * corner cases, but the stack really does a non-trivial amount + * of useless work if you return NETDEV_TX_BUSY. * (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX) * Required can not be NULL. * -- cgit v1.2.3 From 7026b1ddb6b8d4e6ee33dc2bd06c0ca8746fa7ab Mon Sep 17 00:00:00 2001 From: David Miller Date: Sun, 5 Apr 2015 22:19:04 -0400 Subject: netfilter: Pass socket pointer down through okfn(). On the output paths in particular, we have to sometimes deal with two socket contexts. First, and usually skb->sk, is the local socket that generated the frame. And second, is potentially the socket used to control a tunneling socket, such as one the encapsulates using UDP. We do not want to disassociate skb->sk when encapsulating in order to fix this, because that would break socket memory accounting. The most extreme case where this can cause huge problems is an AF_PACKET socket transmitting over a vxlan device. We hit code paths doing checks that assume they are dealing with an ipv4 socket, but are actually operating upon the AF_PACKET one. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 41bf58a2b936..45823db2efb0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2165,8 +2165,12 @@ int dev_open(struct net_device *dev); int dev_close(struct net_device *dev); int dev_close_many(struct list_head *head, bool unlink); 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_loopback_xmit(struct sock *sk, struct sk_buff *newskb); +int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb); +static inline int dev_queue_xmit(struct sk_buff *skb) +{ + return dev_queue_xmit_sk(skb->sk, 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); @@ -2927,7 +2931,11 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); -int netif_receive_skb(struct sk_buff *skb); +int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb); +static inline int netif_receive_skb(struct sk_buff *skb) +{ + return netif_receive_skb_sk(skb->sk, skb); +} gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); -- cgit v1.2.3 From 388069d30240e9524ad69ce6cc692fff2a5a7829 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 7 Apr 2015 12:10:16 +0200 Subject: netdevice.h: remove iflink description Also move 'group' description to match the order of the net_device structure. Fixes: 7a66bbc96ce9 ("net: remove iflink field from struct net_device") Reported-by: Fengguang Wu Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 45823db2efb0..bf6d9df34d7b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1328,7 +1328,7 @@ enum netdev_priv_flags { * @mpls_features: Mask of features inheritable by MPLS * * @ifindex: interface index - * @iflink: unique device identifier + * @group: The group, that the device belongs to * * @stats: Statistics struct, which was left as a legacy, use * rtnl_link_stats64 instead @@ -1488,7 +1488,6 @@ enum netdev_priv_flags { * * @qdisc_tx_busylock: XXX: need comments on this one * - * @group: The group, that the device belongs to * @pm_qos_req: Power Management QoS object * * FIXME: cleanup struct net_device such that network protocol info -- cgit v1.2.3 From 01a3d796813d6302af9f828f34b73d21a4b96c9a Mon Sep 17 00:00:00 2001 From: Vlad Zolotarov Date: Mon, 30 Mar 2015 21:35:23 +0300 Subject: if_link: Add an additional parameter to ifla_vf_info for RSS querying Add configuration setting for drivers to allow/block an RSS Redirection Table and a Hash Key querying for discrete VFs. On some devices VF share the mentioned above information with PF and querying it may adduce a theoretical security risk. We want to let a system administrator to decide if he/she wants to take this risk or not. Signed-off-by: Vlad Zolotarov Tested-by: Phil Schmitt Signed-off-by: Jeff Kirsher --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bf6d9df34d7b..13acb3d8ecdd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -878,6 +878,11 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); * int (*ndo_set_vf_port)(struct net_device *dev, int vf, * struct nlattr *port[]); + * + * Enable or disable the VF ability to query its RSS Redirection Table and + * Hash Key. This is needed since on some devices VF share this information + * with PF and querying it may adduce a theoretical security risk. + * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); * int (*ndo_setup_tc)(struct net_device *dev, u8 tc) * Called to setup 'tc' number of traffic classes in the net device. This @@ -1099,6 +1104,9 @@ struct net_device_ops { struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + int (*ndo_set_vf_rss_query_en)( + struct net_device *dev, + int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, u8 tc); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); -- cgit v1.2.3 From e2c6544829f8df396a0a233c86d5ee78f405ffef Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 10 Apr 2015 15:52:37 +0200 Subject: e1000e: Move pm_qos_req to e1000e adapter e1000e is the only driver requiring pm_qos_req, instead of causing every device to waste up to 240 bytes. Allocate it for the specific driver. Signed-off-by: Thomas Graf Acked-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 13acb3d8ecdd..733d24f16cf8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1751,7 +1751,6 @@ struct net_device { #endif struct phy_device *phydev; struct lock_class_key *qdisc_tx_busylock; - struct pm_qos_request pm_qos_req; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From 14ffbbb8dab670393a8718adb7b0a385b23fa7bc Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 10 Apr 2015 15:52:38 +0200 Subject: net_device: Reorder members to fill holes Some trivial reorders while preserving the RX/TX cache lines split to fill a couple of holes. Signed-off-by: Thomas Graf Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 45 +++++++++++++++++++++------------------------ 1 file changed, 21 insertions(+), 24 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 733d24f16cf8..b5679aed660b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1313,6 +1313,8 @@ enum netdev_priv_flags { * @base_addr: Device I/O address * @irq: Device IRQ number * + * @carrier_changes: Stats to monitor carrier on<->off transitions + * * @state: Generic network queuing layer state, see netdev_state_t * @dev_list: The global list of network devices * @napi_list: List entry, that is used for polling napi devices @@ -1346,8 +1348,6 @@ enum netdev_priv_flags { * @tx_dropped: Dropped packets by core network, * do not use this in drivers * - * @carrier_changes: Stats to monitor carrier on<->off transitions - * * @wireless_handlers: List of functions to handle Wireless Extensions, * instead of ioctl, * see for details. @@ -1390,14 +1390,14 @@ enum netdev_priv_flags { * @dev_port: Used to differentiate devices that share * the same function * @addr_list_lock: XXX: need comments on this one - * @uc: unicast mac addresses - * @mc: multicast mac addresses - * @dev_addrs: list of device hw addresses - * @queues_kset: Group of all Kobjects in the Tx and RX queues * @uc_promisc: Counter, that indicates, that promiscuous mode * has been enabled due to the need to listen to * additional unicast addresses in a device that * does not implement ndo_set_rx_mode() + * @uc: unicast mac addresses + * @mc: multicast mac addresses + * @dev_addrs: list of device hw addresses + * @queues_kset: Group of all Kobjects in the Tx and RX queues * @promiscuity: Number of times, the NIC is told to work in * Promiscuous mode, if it becomes 0 the NIC will * exit from working in Promiscuous mode @@ -1427,6 +1427,12 @@ enum netdev_priv_flags { * @ingress_queue: XXX: need comments on this one * @broadcast: hw bcast address * + * @rx_cpu_rmap: CPU reverse-mapping for RX completion interrupts, + * indexed by RX queue number. Assigned by driver. + * This must only be set if the ndo_rx_flow_steer + * operation is defined + * @index_hlist: Device index hash chain + * * @_tx: Array of TX queues * @num_tx_queues: Number of TX queues allocated at alloc_netdev_mq() time * @real_num_tx_queues: Number of TX queues currently active in device @@ -1436,11 +1442,6 @@ enum netdev_priv_flags { * * @xps_maps: XXX: need comments on this one * - * @rx_cpu_rmap: CPU reverse-mapping for RX completion interrupts, - * indexed by RX queue number. Assigned by driver. - * This must only be set if the ndo_rx_flow_steer - * operation is defined - * * @trans_start: Time (in jiffies) of last Tx * @watchdog_timeo: Represents the timeout that is used by * the watchdog ( see dev_watchdog() ) @@ -1448,7 +1449,6 @@ enum netdev_priv_flags { * * @pcpu_refcnt: Number of references to this device * @todo_list: Delayed register/unregister - * @index_hlist: Device index hash chain * @link_watch_list: XXX: need comments on this one * * @reg_state: Register/unregister state machine @@ -1515,6 +1515,8 @@ struct net_device { unsigned long base_addr; int irq; + atomic_t carrier_changes; + /* * Some hardware also needs these fields (state,dev_list, * napi_list,unreg_list,close_list) but they are not @@ -1555,8 +1557,6 @@ struct net_device { atomic_long_t rx_dropped; atomic_long_t tx_dropped; - atomic_t carrier_changes; - #ifdef CONFIG_WIRELESS_EXT const struct iw_handler_def * wireless_handlers; struct iw_public_data * wireless_data; @@ -1596,6 +1596,8 @@ struct net_device { unsigned short dev_id; unsigned short dev_port; spinlock_t addr_list_lock; + unsigned char name_assign_type; + bool uc_promisc; struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; struct netdev_hw_addr_list dev_addrs; @@ -1603,10 +1605,6 @@ struct net_device { #ifdef CONFIG_SYSFS struct kset *queues_kset; #endif - - unsigned char name_assign_type; - - bool uc_promisc; unsigned int promiscuity; unsigned int allmulti; @@ -1653,7 +1651,10 @@ struct net_device { struct netdev_queue __rcu *ingress_queue; unsigned char broadcast[MAX_ADDR_LEN]; - +#ifdef CONFIG_RFS_ACCEL + struct cpu_rmap *rx_cpu_rmap; +#endif + struct hlist_node index_hlist; /* * Cache lines mostly used on transmit path @@ -1664,13 +1665,11 @@ struct net_device { struct Qdisc *qdisc; unsigned long tx_queue_len; spinlock_t tx_global_lock; + int watchdog_timeo; #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_maps; #endif -#ifdef CONFIG_RFS_ACCEL - struct cpu_rmap *rx_cpu_rmap; -#endif /* These may be needed for future network-power-down code. */ @@ -1680,13 +1679,11 @@ struct net_device { */ unsigned long trans_start; - int watchdog_timeo; struct timer_list watchdog_timer; int __percpu *pcpu_refcnt; struct list_head todo_list; - struct hlist_node index_hlist; struct list_head link_watch_list; enum { NETREG_UNINITIALIZED=0, -- cgit v1.2.3 From 8b86a61da37cbbcf4bd6e87fda494a59b1cf16c4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 17 Apr 2015 15:45:04 +0200 Subject: net: remove unused 'dev' argument from netif_needs_gso() In commit 04ffcb255f22 ("net: Add ndo_gso_check") Tom originally added the 'dev' argument to be able to call ndo_gso_check(). Then later, when generalizing this in commit 5f35227ea34b ("net: Generalize ndo_gso_check to ndo_features_check") Jesse removed the call to ndo_gso_check() in netif_needs_gso() by calling the new ndo_features_check() in a different place. This made the 'dev' argument unused. Remove the unused argument and go back to the code as before. Cc: Tom Herbert Cc: Jesse Gross Signed-off-by: Johannes Berg 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 b5679aed660b..bcbde799ec69 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3713,7 +3713,7 @@ static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features) (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST)); } -static inline bool netif_needs_gso(struct net_device *dev, struct sk_buff *skb, +static inline bool netif_needs_gso(struct sk_buff *skb, netdev_features_t features) { return skb_is_gso(skb) && (!skb_gso_ok(skb, features) || -- cgit v1.2.3