From 02d62e86fe892c59a1259d089d4d16ac76977a37 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 06:30:52 -0800 Subject: net: un-inline sk_busy_loop() There is really little gain from inlining this big function. We'll soon make it even bigger in following patches. This means we no longer need to export napi_by_id() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 67bfac1abfc1..2020a89df12b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -460,15 +460,6 @@ static inline void napi_complete(struct napi_struct *n) return napi_complete_done(n, 0); } -/** - * napi_by_id - lookup a NAPI by napi_id - * @napi_id: hashed napi_id - * - * lookup @napi_id in napi_hash table - * must be called under rcu_read_lock() - */ -struct napi_struct *napi_by_id(unsigned int napi_id); - /** * napi_hash_add - add a NAPI to global hashtable * @napi: napi context -- cgit v1.2.3 From d64b5e85bfe2fe4c790abcbd16d9ae32391ddd7e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 06:31:00 -0800 Subject: net: add netif_tx_napi_add() netif_tx_napi_add() is a variant of netif_napi_add() It should be used by drivers that use a napi structure to exclusively poll TX. We do not want to add this kind of napi in napi_hash[] in following patches, adding generic busy polling to all NAPI drivers. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2020a89df12b..838935d1cdbb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -326,7 +326,8 @@ enum { NAPI_STATE_SCHED, /* Poll is scheduled */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ - NAPI_STATE_HASHED, /* In NAPI hash */ + NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ + NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ }; enum gro_result { @@ -1938,6 +1939,26 @@ static inline void *netdev_priv(const struct net_device *dev) void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight); +/** + * netif_tx_napi_add - initialize a napi context + * @dev: network device + * @napi: napi context + * @poll: polling function + * @weight: default weight + * + * This variant of netif_napi_add() should be used from drivers using NAPI + * to exclusively poll a TX queue. + * This will avoid we add it into napi_hash[], thus polluting this hash table. + */ +static inline void netif_tx_napi_add(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight) +{ + set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); + netif_napi_add(dev, napi, poll, weight); +} + /** * netif_napi_del - remove a napi context * @napi: napi context -- cgit v1.2.3 From 34cbe27e811c591c854a39c0dee1b461bb796953 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 06:31:02 -0800 Subject: net: napi_hash_del() returns a boolean status napi_hash_del() will soon be used from both drivers (if they want) or core networking stack. Callers are responsibles to ensure an RCU grace period is respected before freeing napi structure : napi_hash_del() can signal if this RCU grace period is needed or not. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 838935d1cdbb..e5c33b29471b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -474,9 +474,10 @@ void napi_hash_add(struct napi_struct *napi); * @napi: napi context * * Warning: caller must observe rcu grace period - * before freeing memory containing @napi + * before freeing memory containing @napi, if + * this function returns true. */ -void napi_hash_del(struct napi_struct *napi); +bool napi_hash_del(struct napi_struct *napi); /** * napi_disable - prevent NAPI from scheduling -- cgit v1.2.3 From 93d05d4a320cb16712bb3d57a9658f395d8cecb9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 06:31:03 -0800 Subject: net: provide generic busy polling to all NAPI drivers NAPI drivers no longer need to observe a particular protocol to benefit from busy polling (CONFIG_NET_RX_BUSY_POLL=y) napi_hash_add() and napi_hash_del() are automatically called from core networking stack, respectively from netif_napi_add() and netif_napi_del() This patch depends on free_netdev() and netif_napi_del() being called from process context, which seems to be the norm. Drivers might still prefer to call napi_hash_del() on their own, since they might combine all the rcu grace periods into a single one, knowing their NAPI structures lifetime, while core networking stack has no idea of a possible combining. Once this patch proves to not bring serious regressions, we will cleanup drivers to either remove napi_hash_del() or provide appropriate rcu grace periods combining. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e5c33b29471b..7d2d1d7aaec7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -466,6 +466,9 @@ static inline void napi_complete(struct napi_struct *n) * @napi: napi context * * generate a new napi_id and store a @napi under it in napi_hash + * Used for busy polling (CONFIG_NET_RX_BUSY_POLL) + * Note: This is normally automatically done from netif_napi_add(), + * so might disappear in a future linux version. */ void napi_hash_add(struct napi_struct *napi); @@ -476,6 +479,10 @@ void napi_hash_add(struct napi_struct *napi); * Warning: caller must observe rcu grace period * before freeing memory containing @napi, if * this function returns true. + * Note: core networking stack automatically calls it + * from netif_napi_del() + * Drivers might want to call this helper to combine all + * the needed rcu grace periods into a single one. */ bool napi_hash_del(struct napi_struct *napi); -- cgit v1.2.3 From c0eb454034aab783dc602739237a63b30867f5bd Mon Sep 17 00:00:00 2001 From: KY Srinivasan Date: Tue, 1 Dec 2015 16:43:10 -0800 Subject: hv_netvsc: Don't ask for additional head room in the skb The rndis header is 116 bytes big and can be placed in the default head room that will be available in the skb. Since the netvsc packet is less than 48 bytes, we can use the skb control buffer for the netvsc packet. With these changes we don't need to ask for additional head room. Signed-off-by: K. Y. Srinivasan Reviewed-by: Haiyang Zhang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7d2d1d7aaec7..fcbc5259c630 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -132,7 +132,9 @@ static inline bool dev_xmit_complete(int rc) * used. */ -#if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25) +#if defined(CONFIG_HYPERV_NET) +# define LL_MAX_HEADER 128 +#elif defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25) # if defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 # else -- cgit v1.2.3 From c981e4213e9d2d4ec79501bd607722ec712742a2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:06 +0100 Subject: net: add netif_is_team_master helper Similar to other helpers, caller can use this to find out if device is team master. Signed-off-by: Jiri Pirko 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 fcbc5259c630..2b889be65d88 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1273,6 +1273,7 @@ struct net_device_ops { * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device + * @IFF_TEAM: device is a team device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1299,6 +1300,7 @@ enum netdev_priv_flags { IFF_NO_QUEUE = 1<<21, IFF_OPENVSWITCH = 1<<22, IFF_L3MDEV_SLAVE = 1<<23, + IFF_TEAM = 1<<24, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1325,6 +1327,7 @@ enum netdev_priv_flags { #define IFF_NO_QUEUE IFF_NO_QUEUE #define IFF_OPENVSWITCH IFF_OPENVSWITCH #define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE +#define IFF_TEAM IFF_TEAM /** * struct net_device - The DEVICE structure. @@ -3889,6 +3892,11 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } +static inline bool netif_is_team_master(struct net_device *dev) +{ + return dev->priv_flags & IFF_TEAM; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From f7f019ee6d117de5007d0b10e7960696bbf111eb Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:07 +0100 Subject: net: add netif_is_team_port helper Similar to other helpers, caller can use this to find out if device is team port. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2b889be65d88..b3601f8a9b42 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3897,6 +3897,11 @@ static inline bool netif_is_team_master(struct net_device *dev) return dev->priv_flags & IFF_TEAM; } +static inline bool netif_is_team_port(struct net_device *dev) +{ + return dev->priv_flags & IFF_TEAM_PORT; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From 7be61833042e7757745345eedc7b0efee240c189 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:08 +0100 Subject: net: add netif_is_lag_master helper Some code does not mind if the master is bond or team and treats them the same, as generic LAG. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b3601f8a9b42..3ca083efa560 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3902,6 +3902,11 @@ static inline bool netif_is_team_port(struct net_device *dev) return dev->priv_flags & IFF_TEAM_PORT; } +static inline bool netif_is_lag_master(struct net_device *dev) +{ + return netif_is_bond_master(dev) || netif_is_team_master(dev); +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From e0ba1414f310c83bf425fe26fa2cd5f1befcd6dc Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:09 +0100 Subject: net: add netif_is_lag_port helper Some code does not mind if a device is bond slave or team port and treats them the same, as generic LAG ports. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ca083efa560..1506be58c59a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3907,6 +3907,11 @@ static inline bool netif_is_lag_master(struct net_device *dev) return netif_is_bond_master(dev) || netif_is_team_master(dev); } +static inline bool netif_is_lag_port(struct net_device *dev) +{ + return netif_is_bond_slave(dev) || netif_is_team_port(dev); +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From 6dffb0447c25476f499d205dfceb1972e8dae919 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:10 +0100 Subject: net: propagate upper priv via netdev_master_upper_dev_link Eliminate netdev_master_upper_dev_link_private and pass priv directly as a parameter of netdev_master_upper_dev_link. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1506be58c59a..939b8f3de810 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3619,10 +3619,8 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev); struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); int netdev_master_upper_dev_link(struct net_device *dev, - struct net_device *upper_dev); -int netdev_master_upper_dev_link_private(struct net_device *dev, - struct net_device *upper_dev, - void *private); + struct net_device *upper_dev, + void *upper_priv); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); -- cgit v1.2.3 From 29bf24afb29042f568fa67b1b0eee46796725ed2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:11 +0100 Subject: net: add possibility to pass information about upper device via notifier Sometimes the drivers and other code would find it handy to know some internal information about upper device being changed. So allow upper-code to pass information down to notifier listeners during linking. Signed-off-by: Jiri Pirko 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 939b8f3de810..aea556c64f2c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2163,6 +2163,7 @@ struct netdev_notifier_changeupper_info { struct net_device *upper_dev; /* new upper dev */ bool master; /* is upper dev master */ bool linking; /* is the nofication for link or unlink */ + void *upper_info; /* upper dev info */ }; static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, @@ -3620,7 +3621,7 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, - void *upper_priv); + void *upper_priv, void *upper_info); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); -- cgit v1.2.3 From 764f5e544118508add420724789f46e04dba91eb Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:12 +0100 Subject: net: add info struct for LAG changeupper This struct will be shared by bonding and team to pass internal information to notifier listeners. Signed-off-by: Jiri Pirko 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 aea556c64f2c..3ab90ea0ed03 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2110,6 +2110,19 @@ struct pcpu_sw_netstats { #define netdev_alloc_pcpu_stats(type) \ __netdev_alloc_pcpu_stats(type, GFP_KERNEL); +enum netdev_lag_tx_type { + NETDEV_LAG_TX_TYPE_UNKNOWN, + NETDEV_LAG_TX_TYPE_RANDOM, + NETDEV_LAG_TX_TYPE_BROADCAST, + NETDEV_LAG_TX_TYPE_ROUNDROBIN, + NETDEV_LAG_TX_TYPE_ACTIVEBACKUP, + NETDEV_LAG_TX_TYPE_HASH, +}; + +struct netdev_lag_upper_info { + enum netdev_lag_tx_type tx_type; +}; + #include /* netdevice notifier chain. Please remember to update the rtnetlink -- cgit v1.2.3 From 04d482660a07039fc4e9a42bb3517db236d98f96 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:15 +0100 Subject: net: introduce change lower state notifier When lower device like bonding slave, team/bridge port, etc changes its state, it is useful for others to notice this change. Currently this is implemented specificly for bonding as NETDEV_BONDING_INFO notifier. This patch aims to replace this specific usage and make this more generic to be used for all upper-lower devices. Introduce NETDEV_CHANGELOWERSTATE netdev notifier type and netdev_lower_state_changed() helper. Signed-off-by: Jiri Pirko 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 3ab90ea0ed03..ad69f237aa78 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2158,6 +2158,7 @@ struct netdev_lag_upper_info { #define NETDEV_CHANGEINFODATA 0x0018 #define NETDEV_BONDING_INFO 0x0019 #define NETDEV_PRECHANGEUPPER 0x001A +#define NETDEV_CHANGELOWERSTATE 0x001B int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); @@ -2179,6 +2180,11 @@ struct netdev_notifier_changeupper_info { void *upper_info; /* upper dev info */ }; +struct netdev_notifier_changelowerstate_info { + struct netdev_notifier_info info; /* must be first */ + void *lower_state_info; /* is lower dev state */ +}; + static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { @@ -3640,6 +3646,8 @@ void netdev_upper_dev_unlink(struct net_device *dev, void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); +void netdev_lower_state_changed(struct net_device *lower_dev, + void *lower_state_info); /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 -- cgit v1.2.3 From fb1b2e3ce53aef80b3cef71f3885d584cdbdc6b8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:16 +0100 Subject: net: introduce lower state changed info structure for LAG lowers This is shared info structure for bonding and team. Serves to pass down info about link state and port activity to notification listeners. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ad69f237aa78..fa84b59eb197 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2123,6 +2123,11 @@ struct netdev_lag_upper_info { enum netdev_lag_tx_type tx_type; }; +struct netdev_lag_lower_state_info { + u8 link_up : 1, + tx_enabled : 1; +}; + #include /* netdevice notifier chain. Please remember to update the rtnetlink -- cgit v1.2.3 From b618aaa91b5870e7bd139987ac4b7bf0851142d0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 4 Dec 2015 15:01:31 +0100 Subject: net: constify netif_is_* helpers net_device param As suggested by Eric, these helpers should have const dev param. Suggested-by: Eric Dumazet Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3efe017fe419..1bb21ff0fa64 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3661,7 +3661,7 @@ extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN]; void netdev_rss_key_fill(void *buffer, size_t len); int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(struct net_device *dev)); + bool (*type_check)(const struct net_device *dev)); int skb_checksum_help(struct sk_buff *skb); struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); @@ -3858,32 +3858,32 @@ static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, skb->mac_len = mac_len; } -static inline bool netif_is_macvlan(struct net_device *dev) +static inline bool netif_is_macvlan(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN; } -static inline bool netif_is_macvlan_port(struct net_device *dev) +static inline bool netif_is_macvlan_port(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN_PORT; } -static inline bool netif_is_ipvlan(struct net_device *dev) +static inline bool netif_is_ipvlan(const struct net_device *dev) { return dev->priv_flags & IFF_IPVLAN_SLAVE; } -static inline bool netif_is_ipvlan_port(struct net_device *dev) +static inline bool netif_is_ipvlan_port(const struct net_device *dev) { return dev->priv_flags & IFF_IPVLAN_MASTER; } -static inline bool netif_is_bond_master(struct net_device *dev) +static inline bool netif_is_bond_master(const struct net_device *dev) { return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING; } -static inline bool netif_is_bond_slave(struct net_device *dev) +static inline bool netif_is_bond_slave(const struct net_device *dev) { return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING; } @@ -3918,22 +3918,22 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } -static inline bool netif_is_team_master(struct net_device *dev) +static inline bool netif_is_team_master(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM; } -static inline bool netif_is_team_port(struct net_device *dev) +static inline bool netif_is_team_port(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM_PORT; } -static inline bool netif_is_lag_master(struct net_device *dev) +static inline bool netif_is_lag_master(const struct net_device *dev) { return netif_is_bond_master(dev) || netif_is_team_master(dev); } -static inline bool netif_is_lag_port(struct net_device *dev) +static inline bool netif_is_lag_port(const struct net_device *dev) { return netif_is_bond_slave(dev) || netif_is_team_port(dev); } -- cgit v1.2.3 From a188222b6ed29404ac2d4232d35d1fe0e77af370 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 14 Dec 2015 11:19:43 -0800 Subject: net: Rename NETIF_F_ALL_CSUM to NETIF_F_CSUM_MASK The name NETIF_F_ALL_CSUM is a misnomer. This does not correspond to the set of features for offloading all checksums. This is a mask of the checksum offload related features bits. It is incorrect to set both NETIF_F_HW_CSUM and NETIF_F_IP_CSUM or NETIF_F_IPV6 at the same time for features of a device. This patch: - Changes instances of NETIF_F_ALL_CSUM to NETIF_F_CSUM_MASK (where NETIF_F_ALL_CSUM is being used as a mask). - Changes bonding, sfc/efx, ipvlan, macvlan, vlan, and team drivers to use NEITF_F_HW_CSUM in features list instead of NETIF_F_ALL_CSUM. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1bb21ff0fa64..a54223a113b1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3763,12 +3763,12 @@ static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { if (f1 & NETIF_F_GEN_CSUM) - f1 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + f1 |= (NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); if (f2 & NETIF_F_GEN_CSUM) - f2 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + f2 |= (NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); f1 &= f2; if (f1 & NETIF_F_GEN_CSUM) - f1 &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + f1 &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); return f1; } -- cgit v1.2.3 From c8cd0989bd151fda87bbf10887b3df18021284bc Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 14 Dec 2015 11:19:44 -0800 Subject: net: Eliminate NETIF_F_GEN_CSUM and NETIF_F_V[46]_CSUM These netif flags are unnecessary convolutions. It is more straightforward to just use NETIF_F_HW_CSUM, NETIF_F_IP_CSUM, and NETIF_F_IPV6_CSUM directly. This patch also: - Cleans up can_checksum_protocol - Simplifies netdev_intersect_features Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 40 +++++++++++++++++++++++++--------------- 1 file changed, 25 insertions(+), 15 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a54223a113b1..283984b67cd9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3691,13 +3691,24 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth); static inline bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { - return ((features & NETIF_F_GEN_CSUM) || - ((features & NETIF_F_V4_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_V6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); + if (protocol == htons(ETH_P_FCOE)) + return !!(features & NETIF_F_FCOE_CRC); + + /* Assume this is an IP checksum (not SCTP CRC) */ + + if (features & NETIF_F_HW_CSUM) { + /* Can checksum everything */ + return true; + } + + switch (protocol) { + case htons(ETH_P_IP): + return !!(features & NETIF_F_IP_CSUM); + case htons(ETH_P_IPV6): + return !!(features & NETIF_F_IPV6_CSUM); + default: + return false; + } } #ifdef CONFIG_BUG @@ -3762,15 +3773,14 @@ void linkwatch_run_queue(void); static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { - if (f1 & NETIF_F_GEN_CSUM) - f1 |= (NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); - if (f2 & NETIF_F_GEN_CSUM) - f2 |= (NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); - f1 &= f2; - if (f1 & NETIF_F_GEN_CSUM) - f1 &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); + if ((f1 ^ f2) & NETIF_F_HW_CSUM) { + if (f1 & NETIF_F_HW_CSUM) + f1 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + else + f2 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + } - return f1; + return f1 & f2; } static inline netdev_features_t netdev_get_wanted_features( -- cgit v1.2.3 From 6ae23ad36253a8033c5714c52b691b84456487c5 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 14 Dec 2015 11:19:46 -0800 Subject: net: Add driver helper functions to determine checksum offloadability Add skb_csum_offload_chk driver helper function to determine if a device with limited checksum offload capabilities is able to offload the checksum for a given packet. This patch includes: - The skb_csum_offload_chk function. Returns true if checksum is offloadable, else false. Optionally, in the case that the checksum is not offloable, the function can call skb_checksum_help to resolve the checksum. skb_csum_offload_chk also returns whether the checksum refers to an encapsulated checksum. - Definition of skb_csum_offl_spec structure that caller uses to indicate rules about what it can offload (e.g. IPv4/v6, TCP/UDP only, whether encapsulated checksums can be offloaded, whether checksum with IPv6 extension headers can be offloaded). - Ancilary functions called skb_csum_offload_chk_help, skb_csum_off_chk_help_cmn, skb_csum_off_chk_help_cmn_v4_only. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 78 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 283984b67cd9..9fb6395967de 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2522,6 +2522,71 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, remcsum_unadjust((__sum16 *)ptr, grc->delta); } +struct skb_csum_offl_spec { + __u16 ipv4_okay:1, + ipv6_okay:1, + encap_okay:1, + ip_options_okay:1, + ext_hdrs_okay:1, + tcp_okay:1, + udp_okay:1, + sctp_okay:1, + vlan_okay:1, + no_encapped_ipv6:1, + no_not_encapped:1; +}; + +bool __skb_csum_offload_chk(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec, + bool *csum_encapped, + bool csum_help); + +static inline bool skb_csum_offload_chk(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec, + bool *csum_encapped, + bool csum_help) +{ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return false; + + return __skb_csum_offload_chk(skb, spec, csum_encapped, csum_help); +} + +static inline bool skb_csum_offload_chk_help(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec) +{ + bool csum_encapped; + + return skb_csum_offload_chk(skb, spec, &csum_encapped, true); +} + +static inline bool skb_csum_off_chk_help_cmn(struct sk_buff *skb) +{ + static const struct skb_csum_offl_spec csum_offl_spec = { + .ipv4_okay = 1, + .ip_options_okay = 1, + .ipv6_okay = 1, + .vlan_okay = 1, + .tcp_okay = 1, + .udp_okay = 1, + }; + + return skb_csum_offload_chk_help(skb, &csum_offl_spec); +} + +static inline bool skb_csum_off_chk_help_cmn_v4_only(struct sk_buff *skb) +{ + static const struct skb_csum_offl_spec csum_offl_spec = { + .ipv4_okay = 1, + .ip_options_okay = 1, + .tcp_okay = 1, + .udp_okay = 1, + .vlan_okay = 1, + }; + + return skb_csum_offload_chk_help(skb, &csum_offl_spec); +} + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -3711,6 +3776,19 @@ static inline bool can_checksum_protocol(netdev_features_t features, } } +/* Map an ethertype into IP protocol if possible */ +static inline int eproto_to_ipproto(int eproto) +{ + switch (eproto) { + case htons(ETH_P_IP): + return IPPROTO_IP; + case htons(ETH_P_IPV6): + return IPPROTO_IPV6; + default: + return -1; + } +} + #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev); #else -- cgit v1.2.3 From a8170d2b9e8d38a1f3fa3b40b6f8cd34a87d5382 Mon Sep 17 00:00:00 2001 From: "Singhai, Anjali" Date: Mon, 14 Dec 2015 12:21:17 -0800 Subject: geneve: Add geneve udp port offload for ethernet devices Add ndo_ops to add/del UDP ports to a device that supports geneve offload. v2: Comment fix. Signed-off-by: Anjali Singhai Jain Signed-off-by: Kiran Patil Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9fb6395967de..81b26a543a3c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1013,6 +1013,19 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * a new port starts listening. The operation is protected by the * vxlan_net->sock_lock. * + * void (*ndo_add_geneve_port)(struct net_device *dev, + * sa_family_t sa_family, __be16 port); + * Called by geneve to notify a driver about the UDP port and socket + * address family that geneve is listnening to. It is called only when + * a new port starts listening. The operation is protected by the + * geneve_net->sock_lock. + * + * void (*ndo_del_geneve_port)(struct net_device *dev, + * sa_family_t sa_family, __be16 port); + * Called by geneve to notify the driver about a UDP port and socket + * address family that geneve is not listening to anymore. The operation + * is protected by the geneve_net->sock_lock. + * * void (*ndo_del_vxlan_port)(struct net_device *dev, * sa_family_t sa_family, __be16 port); * Called by vxlan to notify the driver about a UDP port and socket @@ -1217,7 +1230,12 @@ struct net_device_ops { void (*ndo_del_vxlan_port)(struct net_device *dev, sa_family_t sa_family, __be16 port); - + void (*ndo_add_geneve_port)(struct net_device *dev, + sa_family_t sa_family, + __be16 port); + void (*ndo_del_geneve_port)(struct net_device *dev, + sa_family_t sa_family, + __be16 port); void* (*ndo_dfwd_add_station)(struct net_device *pdev, struct net_device *dev); void (*ndo_dfwd_del_station)(struct net_device *pdev, -- cgit v1.2.3 From cdba756f5803a2f0a8bbc6605acc166dd817979e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Jan 2016 06:53:50 -0800 Subject: net: move ndo_features_check() close to ndo_start_xmit() TX fast path uses ndo_start_xmit(), ndo_features_check() and ndo_select_queue(). Move ndo_features_check() close to ndo_start_xmit() to increase data locality. All "struct net_device_ops" should now be using C99 initializers. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c20b814e46a0..8d8e5ca951b4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -812,6 +812,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX) * Required can not be NULL. * + * netdev_features_t (*ndo_fix_features)(struct net_device *dev, + * netdev_features_t features); + * Adjusts the requested feature flags according to device-specific + * constraints, and returns the resulting flags. Must not modify + * the device state. + * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, * void *accel_priv, select_queue_fallback_t fallback); * Called to decide which queue to when device supports multiple @@ -959,12 +965,6 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * Called to release previously enslaved netdev. * * Feature/offload setting functions. - * netdev_features_t (*ndo_fix_features)(struct net_device *dev, - * netdev_features_t features); - * Adjusts the requested feature flags according to device-specific - * constraints, and returns the resulting flags. Must not modify - * the device state. - * * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); * Called to update device configuration to new features. Passed * feature set might be less than what was returned by ndo_fix_features()). @@ -1081,8 +1081,11 @@ struct net_device_ops { void (*ndo_uninit)(struct net_device *dev); int (*ndo_open)(struct net_device *dev); int (*ndo_stop)(struct net_device *dev); - netdev_tx_t (*ndo_start_xmit) (struct sk_buff *skb, - struct net_device *dev); + netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, + struct net_device *dev); + netdev_features_t (*ndo_features_check)(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, void *accel_priv, @@ -1245,9 +1248,6 @@ struct net_device_ops { struct net_device *dev, void *priv); int (*ndo_get_lock_subclass)(struct net_device *dev); - 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 1f211a1b929c804100e138c5d3d656992cfd5622 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 7 Jan 2016 22:29:47 +0100 Subject: net, sched: add clsact qdisc This work adds a generalization of the ingress qdisc as a qdisc holding only classifiers. The clsact qdisc works on ingress, but also on egress. In both cases, it's execution happens without taking the qdisc lock, and the main difference for the egress part compared to prior version of [1] is that this can be applied with _any_ underlying real egress qdisc (also classless ones). Besides solving the use-case of [1], that is, allowing for more programmability on assigning skb->priority for the mqprio case that is supported by most popular 10G+ NICs, it also opens up a lot more flexibility for other tc applications. The main work on classification can already be done at clsact egress time if the use-case allows and state stored for later retrieval f.e. again in skb->priority with major/minors (which is checked by most classful qdiscs before consulting tc_classify()) and/or in other skb fields like skb->tc_index for some light-weight post-processing to get to the eventual classid in case of a classful qdisc. Another use case is that the clsact egress part allows to have a central egress counterpart to the ingress classifiers, so that classifiers can easily share state (e.g. in cls_bpf via eBPF maps) for ingress and egress. Currently, default setups like mq + pfifo_fast would require for this to use, for example, prio qdisc instead (to get a tc_classify() run) and to duplicate the egress classifier for each queue. With clsact, it allows for leaving the setup as is, it can additionally assign skb->priority to put the skb in one of pfifo_fast's bands and it can share state with maps. Moreover, we can access the skb's dst entry (f.e. to retrieve tclassid) w/o the need to perform a skb_dst_force() to hold on to it any longer. In lwt case, we can also use this facility to setup dst metadata via cls_bpf (bpf_skb_set_tunnel_key()) without needing a real egress qdisc just for that (case of IFF_NO_QUEUE devices, for example). The realization can be done without any changes to the scheduler core framework. All it takes is that we have two a-priori defined minors/child classes, where we can mux between ingress and egress classifier list (dev->ingress_cl_list and dev->egress_cl_list, latter stored close to dev->_tx to avoid extra cacheline miss for moderate loads). The egress part is a bit similar modelled to handle_ing() and patched to a noop in case the functionality is not used. Both handlers are now called sch_handle_ingress() and sch_handle_egress(), code sharing among the two doesn't seem practical as there are various minor differences in both paths, so that making them conditional in a single handler would rather slow things down. Full compatibility to ingress qdisc is provided as well. Since both piggyback on TC_H_CLSACT, only one of them (ingress/clsact) can exist per netdevice, and thus ingress qdisc specific behaviour can be retained for user space. This means, either a user does 'tc qdisc add dev foo ingress' and configures ingress qdisc as usual, or the 'tc qdisc add dev foo clsact' alternative, where both, ingress and egress classifier can be configured as in the below example. ingress qdisc supports attaching classifier to any minor number whereas clsact has two fixed minors for muxing between the lists, therefore to not break user space setups, they are better done as two separate qdiscs. I decided to extend the sch_ingress module with clsact functionality so that commonly used code can be reused, the module is being aliased with sch_clsact so that it can be auto-loaded properly. Alternative would have been to add a flag when initializing ingress to alter its behaviour plus aliasing to a different name (as it's more than just ingress). However, the first would end up, based on the flag, choosing the new/old behaviour by calling different function implementations to handle each anyway, the latter would require to register ingress qdisc once again under different alias. So, this really begs to provide a minimal, cleaner approach to have Qdisc_ops and Qdisc_class_ops by its own that share callbacks used by both. Example, adding qdisc: # tc qdisc add dev foo clsact # tc qdisc show dev foo qdisc mq 0: root qdisc pfifo_fast 0: parent :1 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :2 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :3 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :4 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc clsact ffff: parent ffff:fff1 Adding filters (deleting, etc works analogous by specifying ingress/egress): # tc filter add dev foo ingress bpf da obj bar.o sec ingress # tc filter add dev foo egress bpf da obj bar.o sec egress # tc filter show dev foo ingress filter protocol all pref 49152 bpf filter protocol all pref 49152 bpf handle 0x1 bar.o:[ingress] direct-action # tc filter show dev foo egress filter protocol all pref 49152 bpf filter protocol all pref 49152 bpf handle 0x1 bar.o:[egress] direct-action A 'tc filter show dev foo' or 'tc filter show dev foo parent ffff:' will show an empty list for clsact. Either using the parent names (ingress/egress) or specifying the full major/minor will then show the related filter lists. Prior work on a mqprio prequeue() facility [1] was done mainly by John Fastabend. [1] http://patchwork.ozlabs.org/patch/512949/ Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8d8e5ca951b4..2285596e7045 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1739,7 +1739,9 @@ struct net_device { #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_maps; #endif - +#ifdef CONFIG_NET_CLS_ACT + struct tcf_proto __rcu *egress_cl_list; +#endif #ifdef CONFIG_NET_SWITCHDEV u32 offload_fwd_mark; #endif -- cgit v1.2.3 From b6a0e72ad3cffabaf30b856deb58fbe64a0f36a8 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 11 Jan 2016 10:19:10 -0800 Subject: net: Fix typo in netdev_intersect_features Obviously need to 'or in NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM. Fixes: c8cd0989bd151f ("net: Eliminate NETIF_F_GEN_CSUM and NETIF_F_V[46]_CSUM") Reported-by: Jack Morgenstein Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2285596e7045..5ac140dcb789 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3873,9 +3873,9 @@ static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, { if ((f1 ^ f2) & NETIF_F_HW_CSUM) { if (f1 & NETIF_F_HW_CSUM) - f1 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + f1 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); else - f2 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + f2 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } return f1 & f2; -- cgit v1.2.3