From 330c7272c40e965b8ab510d1022acd6e6a32e9c8 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 13 Feb 2018 08:52:00 -0800 Subject: net: Make dn_ptr depend on CONFIG_DECNET Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5eef6c8e2741..d2ef35e00626 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1800,7 +1800,9 @@ struct net_device { #endif void *atalk_ptr; struct in_device __rcu *ip_ptr; +#if IS_ENABLED(CONFIG_DECNET) struct dn_dev __rcu *dn_ptr; +#endif struct inet6_dev __rcu *ip6_ptr; void *ax25_ptr; struct wireless_dev *ieee80211_ptr; -- cgit v1.2.3 From 19ff13f2a411d99af67d8e51867d54b86e1bf017 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 13 Feb 2018 08:52:01 -0800 Subject: net: Make ax25_ptr depend on CONFIG_AX25 Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d2ef35e00626..936dc2c9dca1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1804,7 +1804,9 @@ struct net_device { struct dn_dev __rcu *dn_ptr; #endif struct inet6_dev __rcu *ip6_ptr; +#if IS_ENABLED(CONFIG_AX25) void *ax25_ptr; +#endif struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; #if IS_ENABLED(CONFIG_MPLS_ROUTING) -- cgit v1.2.3 From 89e58148fbf2e4cbd84006e263061c19a2b47adf Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 13 Feb 2018 08:52:02 -0800 Subject: net: Make atalk_ptr depend on ATALK or IRDA Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 936dc2c9dca1..dbe6344b727a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1798,7 +1798,9 @@ struct net_device { #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif +#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; +#endif struct in_device __rcu *ip_ptr; #if IS_ENABLED(CONFIG_DECNET) struct dn_dev __rcu *dn_ptr; -- cgit v1.2.3 From 1ec54cb44e6731c3cb251bcf9251d65a4b4f6306 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 6 Mar 2018 10:56:31 +0100 Subject: net: unpollute priv_flags space the ipvlan device driver defines and uses 2 bits inside the priv_flags net_device field. Such bits and the related helper are used only inside the ipvlan device driver, and the core networking does not need to be aware of them. This change moves netif_is_ipvlan* helper in the ipvlan driver and re-implement them looking for ipvlan specific symbols instead of using priv_flags. Overall this frees two bits inside priv_flags - and move the following ones to avoid gaps - without any intended functional change. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/netdevice.h | 32 ++++++++------------------------ 1 file changed, 8 insertions(+), 24 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dbe6344b727a..95a613a7cc1c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1381,8 +1381,6 @@ struct net_device_ops { * @IFF_MACVLAN: Macvlan device * @IFF_XMIT_DST_RELEASE_PERM: IFF_XMIT_DST_RELEASE not taking into account * underlying stacked devices - * @IFF_IPVLAN_MASTER: IPvlan master device - * @IFF_IPVLAN_SLAVE: IPvlan slave device * @IFF_L3MDEV_MASTER: device is an L3 master device * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master @@ -1412,16 +1410,14 @@ enum netdev_priv_flags { IFF_LIVE_ADDR_CHANGE = 1<<15, IFF_MACVLAN = 1<<16, IFF_XMIT_DST_RELEASE_PERM = 1<<17, - IFF_IPVLAN_MASTER = 1<<18, - IFF_IPVLAN_SLAVE = 1<<19, - IFF_L3MDEV_MASTER = 1<<20, - IFF_NO_QUEUE = 1<<21, - IFF_OPENVSWITCH = 1<<22, - IFF_L3MDEV_SLAVE = 1<<23, - IFF_TEAM = 1<<24, - IFF_RXFH_CONFIGURED = 1<<25, - IFF_PHONY_HEADROOM = 1<<26, - IFF_MACSEC = 1<<27, + IFF_L3MDEV_MASTER = 1<<18, + IFF_NO_QUEUE = 1<<19, + IFF_OPENVSWITCH = 1<<20, + IFF_L3MDEV_SLAVE = 1<<21, + IFF_TEAM = 1<<22, + IFF_RXFH_CONFIGURED = 1<<23, + IFF_PHONY_HEADROOM = 1<<24, + IFF_MACSEC = 1<<25, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1442,8 +1438,6 @@ enum netdev_priv_flags { #define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE #define IFF_MACVLAN IFF_MACVLAN #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM -#define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER -#define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE #define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER #define IFF_NO_QUEUE IFF_NO_QUEUE #define IFF_OPENVSWITCH IFF_OPENVSWITCH @@ -4223,16 +4217,6 @@ 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(const struct net_device *dev) -{ - return dev->priv_flags & IFF_IPVLAN_SLAVE; -} - -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(const struct net_device *dev) { return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING; -- cgit v1.2.3 From 79134e6ce2c9d1a00eab4d98cb48f975dd2474cb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Mar 2018 12:51:41 -0800 Subject: net: do not create fallback tunnels for non-default namespaces fallback tunnels (like tunl0, gre0, gretap0, erspan0, sit0, ip6tnl0, ip6gre0) are automatically created when the corresponding module is loaded. These tunnels are also automatically created when a new network namespace is created, at a great cost. In many cases, netns are used for isolation purposes, and these extra network devices are a waste of resources. We are using thousands of netns per host, and hit the netns creation/delete bottleneck a lot. (Many thanks to Kirill for recent work on this) Add a new sysctl so that we can opt-out from this automatic creation. Note that these tunnels are still created for the initial namespace, to be the least intrusive for typical setups. Tested: lpk43:~# cat add_del_unshare.sh for i in `seq 1 40` do (for j in `seq 1 100` ; do unshare -n /bin/true >/dev/null ; done) & done wait lpk43:~# echo 0 >/proc/sys/net/core/fb_tunnels_only_for_init_net lpk43:~# time ./add_del_unshare.sh real 0m37.521s user 0m0.886s sys 7m7.084s lpk43:~# echo 1 >/proc/sys/net/core/fb_tunnels_only_for_init_net lpk43:~# time ./add_del_unshare.sh real 0m4.761s user 0m0.851s sys 1m8.343s lpk43:~# 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 95a613a7cc1c..9711108c3916 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -585,6 +585,13 @@ struct netdev_queue { #endif } ____cacheline_aligned_in_smp; +extern int sysctl_fb_tunnels_only_for_init_net; + +static inline bool net_has_fallback_tunnels(const struct net *net) +{ + return net == &init_net || !sysctl_fb_tunnels_only_for_init_net; +} + static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) { #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) -- cgit v1.2.3 From f5426250a6ecfd1e9b2d5e0daf07565f664aa67d Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 9 Mar 2018 10:39:24 +0100 Subject: net: introduce IFF_NO_RX_HANDLER Some network devices - notably ipvlan slave - are not compatible with any kind of rx_handler. Currently the hook can be installed but any configuration (bridge, bond, macsec, ...) is nonfunctional. This change allocates a priv_flag bit to mark such devices and explicitly forbid installing a rx_handler if such bit is set. The new bit is used by ipvlan slave device. Signed-off-by: Paolo Abeni 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 9711108c3916..5fbb9f1da7fd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1397,6 +1397,7 @@ struct net_device_ops { * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external * entity (i.e. the master device for bridged veth) * @IFF_MACSEC: device is a MACsec device + * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1425,6 +1426,7 @@ enum netdev_priv_flags { IFF_RXFH_CONFIGURED = 1<<23, IFF_PHONY_HEADROOM = 1<<24, IFF_MACSEC = 1<<25, + IFF_NO_RX_HANDLER = 1<<26, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1452,6 +1454,7 @@ enum netdev_priv_flags { #define IFF_TEAM IFF_TEAM #define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED #define IFF_MACSEC IFF_MACSEC +#define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER /** * struct net_device - The DEVICE structure. -- cgit v1.2.3 From be9fc0971a5c27b791608cf9705a04fe96dbd395 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 13 Mar 2018 12:44:53 +0100 Subject: net: fix sysctl_fb_tunnels_only_for_init_net link error The new variable is only available when CONFIG_SYSCTL is enabled, otherwise we get a link error: net/ipv4/ip_tunnel.o: In function `ip_tunnel_init_net': ip_tunnel.c:(.text+0x278b): undefined reference to `sysctl_fb_tunnels_only_for_init_net' net/ipv6/sit.o: In function `sit_init_net': sit.c:(.init.text+0x4c): undefined reference to `sysctl_fb_tunnels_only_for_init_net' net/ipv6/ip6_tunnel.o: In function `ip6_tnl_init_net': ip6_tunnel.c:(.init.text+0x39): undefined reference to `sysctl_fb_tunnels_only_for_init_net' This adds an extra condition, keeping the traditional behavior when CONFIG_SYSCTL is disabled. Fixes: 79134e6ce2c9 ("net: do not create fallback tunnels for non-default namespaces") Signed-off-by: Arnd Bergmann 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 5fbb9f1da7fd..913b1cc882cf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -589,7 +589,9 @@ extern int sysctl_fb_tunnels_only_for_init_net; static inline bool net_has_fallback_tunnels(const struct net *net) { - return net == &init_net || !sysctl_fb_tunnels_only_for_init_net; + return net == &init_net || + !IS_ENABLED(CONFIG_SYSCTL) || + !sysctl_fb_tunnels_only_for_init_net; } static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) -- cgit v1.2.3 From ede2762d93ff16e0974f7446516b46b1022db213 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 23 Mar 2018 19:47:19 +0300 Subject: net: Make NETDEV_XXX commands enum { } This patch is preparation to drop NETDEV_UNREGISTER_FINAL. Since the cmd is used in usnic_ib_netdev_event_to_string() to get cmd name, after plain removing NETDEV_UNREGISTER_FINAL from everywhere, we'd have holes in event2str[] in this function. Instead of that, let's make NETDEV_XXX commands names available for everyone, and to define netdev_cmd_to_name() in the way we won't have to shaffle names after their numbers are changed. Signed-off-by: Kirill Tkhai Signed-off-by: David S. Miller --- include/linux/netdevice.h | 69 ++++++++++++++++++++++++----------------------- 1 file changed, 36 insertions(+), 33 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 913b1cc882cf..dd5a04c971d5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2312,43 +2312,46 @@ struct netdev_lag_lower_state_info { #include -/* netdevice notifier chain. Please remember to update the rtnetlink - * notification exclusion list in rtnetlink_event() when adding new - * types. +/* netdevice notifier chain. Please remember to update netdev_cmd_to_name() + * and the rtnetlink notification exclusion list in rtnetlink_event() when + * adding new types. */ -#define NETDEV_UP 0x0001 /* For now you can't veto a device up/down */ -#define NETDEV_DOWN 0x0002 -#define NETDEV_REBOOT 0x0003 /* Tell a protocol stack a network interface +enum netdev_cmd { + NETDEV_UP = 1, /* For now you can't veto a device up/down */ + NETDEV_DOWN, + NETDEV_REBOOT, /* Tell a protocol stack a network interface detected a hardware crash and restarted - we can use this eg to kick tcp sessions once done */ -#define NETDEV_CHANGE 0x0004 /* Notify device state change */ -#define NETDEV_REGISTER 0x0005 -#define NETDEV_UNREGISTER 0x0006 -#define NETDEV_CHANGEMTU 0x0007 /* notify after mtu change happened */ -#define NETDEV_CHANGEADDR 0x0008 -#define NETDEV_GOING_DOWN 0x0009 -#define NETDEV_CHANGENAME 0x000A -#define NETDEV_FEAT_CHANGE 0x000B -#define NETDEV_BONDING_FAILOVER 0x000C -#define NETDEV_PRE_UP 0x000D -#define NETDEV_PRE_TYPE_CHANGE 0x000E -#define NETDEV_POST_TYPE_CHANGE 0x000F -#define NETDEV_POST_INIT 0x0010 -#define NETDEV_UNREGISTER_FINAL 0x0011 -#define NETDEV_RELEASE 0x0012 -#define NETDEV_NOTIFY_PEERS 0x0013 -#define NETDEV_JOIN 0x0014 -#define NETDEV_CHANGEUPPER 0x0015 -#define NETDEV_RESEND_IGMP 0x0016 -#define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ -#define NETDEV_CHANGEINFODATA 0x0018 -#define NETDEV_BONDING_INFO 0x0019 -#define NETDEV_PRECHANGEUPPER 0x001A -#define NETDEV_CHANGELOWERSTATE 0x001B -#define NETDEV_UDP_TUNNEL_PUSH_INFO 0x001C -#define NETDEV_UDP_TUNNEL_DROP_INFO 0x001D -#define NETDEV_CHANGE_TX_QUEUE_LEN 0x001E + NETDEV_CHANGE, /* Notify device state change */ + NETDEV_REGISTER, + NETDEV_UNREGISTER, + NETDEV_CHANGEMTU, /* notify after mtu change happened */ + NETDEV_CHANGEADDR, + NETDEV_GOING_DOWN, + NETDEV_CHANGENAME, + NETDEV_FEAT_CHANGE, + NETDEV_BONDING_FAILOVER, + NETDEV_PRE_UP, + NETDEV_PRE_TYPE_CHANGE, + NETDEV_POST_TYPE_CHANGE, + NETDEV_POST_INIT, + NETDEV_UNREGISTER_FINAL, + NETDEV_RELEASE, + NETDEV_NOTIFY_PEERS, + NETDEV_JOIN, + NETDEV_CHANGEUPPER, + NETDEV_RESEND_IGMP, + NETDEV_PRECHANGEMTU, /* notify before mtu change happened */ + NETDEV_CHANGEINFODATA, + NETDEV_BONDING_INFO, + NETDEV_PRECHANGEUPPER, + NETDEV_CHANGELOWERSTATE, + NETDEV_UDP_TUNNEL_PUSH_INFO, + NETDEV_UDP_TUNNEL_DROP_INFO, + NETDEV_CHANGE_TX_QUEUE_LEN, +}; +const char *netdev_cmd_to_name(enum netdev_cmd cmd); int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 070f2d7e264acd6316fc24092b7f51a18c75ac9c Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 23 Mar 2018 19:47:39 +0300 Subject: net: Drop NETDEV_UNREGISTER_FINAL Last user is gone after bdf5bd7f2132 "rds: tcp: remove register_netdevice_notifier infrastructure.", so we can remove this netdevice command. This allows to delete rtnl_lock() in netdev_run_todo(), which is hot path for net namespace unregistration. dev_change_net_namespace() and netdev_wait_allrefs() have rcu_barrier() before NETDEV_UNREGISTER_FINAL call, and the source commits say they were introduced to delemit the call with NETDEV_UNREGISTER, but this patch leaves them on the places, since they require additional analysis, whether we need in them for something else. Signed-off-by: Kirill Tkhai 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 dd5a04c971d5..2a2d9cf50aa2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2336,7 +2336,6 @@ enum netdev_cmd { NETDEV_PRE_TYPE_CHANGE, NETDEV_POST_TYPE_CHANGE, NETDEV_POST_INIT, - NETDEV_UNREGISTER_FINAL, NETDEV_RELEASE, NETDEV_NOTIFY_PEERS, NETDEV_JOIN, -- cgit v1.2.3 From 9daae9bd47cff82a2a06aca23c458d6c79d09d52 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Wed, 28 Mar 2018 17:46:54 +0300 Subject: net: Call add/kill vid ndo on vlan filter feature toggling NETIF_F_HW_VLAN_[CS]TAG_FILTER features require more than just a bit flip in dev->features in order to keep the driver in a consistent state. These features notify the driver of each added/removed vlan, but toggling of vlan-filter does not notify the driver accordingly for each of the existing vlans. This patch implements a similar solution to NETIF_F_RX_UDP_TUNNEL_PORT behavior (which notifies the driver about UDP ports in the same manner that vids are reported). Each toggling of the features propagates to the 8021q module, which iterates over the vlans and call add/kill ndo accordingly. Signed-off-by: Gal Pressman Reviewed-by: Tariq Toukan 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 2a2d9cf50aa2..da44dab492e3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2349,6 +2349,10 @@ enum netdev_cmd { NETDEV_UDP_TUNNEL_PUSH_INFO, NETDEV_UDP_TUNNEL_DROP_INFO, NETDEV_CHANGE_TX_QUEUE_LEN, + NETDEV_CVLAN_FILTER_PUSH_INFO, + NETDEV_CVLAN_FILTER_DROP_INFO, + NETDEV_SVLAN_FILTER_PUSH_INFO, + NETDEV_SVLAN_FILTER_DROP_INFO, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); -- cgit v1.2.3 From e679c9c1dbfdba07b2a979a076cca74b773be8ce Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 28 Mar 2018 15:44:16 -0700 Subject: sfp/phylink: move module EEPROM ethtool access into netdev core ethtool Provide a pointer to the SFP bus in struct net_device, so that the ethtool module EEPROM methods can access the SFP directly, rather than needing every user to provide a hook for it. Reviewed-by: Andrew Lunn Signed-off-by: Russell King Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: Russell King Signed-off-by: Florian Fainelli 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 da44dab492e3..cf44503ea81a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -58,6 +58,7 @@ struct device; struct phy_device; struct dsa_port; +struct sfp_bus; /* 802.11 specific */ struct wireless_dev; /* 802.15.4 specific */ @@ -1662,6 +1663,7 @@ enum netdev_priv_flags { * @priomap: XXX: need comments on this one * @phydev: Physical device may attach itself * for hardware timestamping + * @sfp_bus: attached &struct sfp_bus structure. * * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount @@ -1945,6 +1947,7 @@ struct net_device { struct netprio_map __rcu *priomap; #endif struct phy_device *phydev; + struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; struct lock_class_key *qdisc_running_key; bool proto_down; -- cgit v1.2.3