From 3d3ea5af5c0b382bc9d9aed378fd814fb5d4a011 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Sat, 27 May 2017 10:14:34 -0400 Subject: [PATCH 1/2] rtnl: Add support for netdev event to link messages When netdev events happen, a rtnetlink_event() handler will send messages for every event in it's white list. These messages contain current information about a particular device, but they do not include the iformation about which event just happened. So, it is impossible to tell what just happend for these events. This patch adds a new extension to RTM_NEWLINK message called IFLA_EVENT that would have an encoding of event that triggered this message. This would allow the the message consumer to easily determine if it needs to perform certain actions. Signed-off-by: Vladislav Yasevich Acked-by: David Ahern Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 3 +- include/uapi/linux/if_link.h | 11 ++++++ net/core/dev.c | 2 +- net/core/rtnetlink.c | 65 +++++++++++++++++++++++++++++++----- 4 files changed, 70 insertions(+), 11 deletions(-) diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 57e54847b0b9..dea59c8eec54 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -18,7 +18,8 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags); struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, - unsigned change, gfp_t flags); + unsigned change, u32 event, + gfp_t flags); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 15ac20382aba..8ed679fe603f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -157,6 +157,7 @@ enum { IFLA_GSO_MAX_SIZE, IFLA_PAD, IFLA_XDP, + IFLA_EVENT, __IFLA_MAX }; @@ -911,4 +912,14 @@ enum { #define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1) +enum { + IFLA_EVENT_NONE, + IFLA_EVENT_REBOOT, /* internal reset / reboot */ + IFLA_EVENT_FEATURES, /* change in offload features */ + IFLA_EVENT_BONDING_FAILOVER, /* change in active slave */ + IFLA_EVENT_NOTIFY_PEERS, /* re-sent grat. arp/ndisc */ + IFLA_EVENT_IGMP_RESEND, /* re-sent IGMP JOIN */ + IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */ +}; + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/net/core/dev.c b/net/core/dev.c index 3d98fbf4cbb0..06e0a7492df8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7084,7 +7084,7 @@ static void rollback_registered_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, + skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL); /* diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 64953af4a3b1..9da53e43750c 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -941,6 +941,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + rtnl_xdp_size() /* IFLA_XDP */ + + nla_total_size(4) /* IFLA_EVENT */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } @@ -1282,9 +1283,40 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) return err; } +static u32 rtnl_get_event(unsigned long event) +{ + u32 rtnl_event_type = IFLA_EVENT_NONE; + + switch (event) { + case NETDEV_REBOOT: + rtnl_event_type = IFLA_EVENT_REBOOT; + break; + case NETDEV_FEAT_CHANGE: + rtnl_event_type = IFLA_EVENT_FEATURES; + break; + case NETDEV_BONDING_FAILOVER: + rtnl_event_type = IFLA_EVENT_BONDING_FAILOVER; + break; + case NETDEV_NOTIFY_PEERS: + rtnl_event_type = IFLA_EVENT_NOTIFY_PEERS; + break; + case NETDEV_RESEND_IGMP: + rtnl_event_type = IFLA_EVENT_IGMP_RESEND; + break; + case NETDEV_CHANGEINFODATA: + rtnl_event_type = IFLA_EVENT_BONDING_OPTIONS; + break; + default: + break; + } + + return rtnl_event_type; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, - unsigned int flags, u32 ext_filter_mask) + unsigned int flags, u32 ext_filter_mask, + u32 event) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -1333,6 +1365,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) goto nla_put_failure; + if (event != IFLA_EVENT_NONE) { + if (nla_put_u32(skb, IFLA_EVENT, event)) + goto nla_put_failure; + } + if (rtnl_fill_link_ifmap(skb, dev)) goto nla_put_failure; @@ -1467,6 +1504,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_LINK_NETNSID] = { .type = NLA_S32 }, [IFLA_PROTO_DOWN] = { .type = NLA_U8 }, [IFLA_XDP] = { .type = NLA_NESTED }, + [IFLA_EVENT] = { .type = NLA_U32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -1626,7 +1664,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, flags, - ext_filter_mask); + ext_filter_mask, 0); if (err < 0) { if (likely(skb->len)) @@ -2736,7 +2774,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, 0, 0, ext_filter_mask); + nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -2808,7 +2846,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) } struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, - unsigned int change, gfp_t flags) + unsigned int change, + u32 event, gfp_t flags) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -2819,7 +2858,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, if (skb == NULL) goto errout; - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -2840,18 +2879,25 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags) rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags); } -void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, - gfp_t flags) +static void rtmsg_ifinfo_event(int type, struct net_device *dev, + unsigned int change, u32 event, + gfp_t flags) { struct sk_buff *skb; if (dev->reg_state != NETREG_REGISTERED) return; - skb = rtmsg_ifinfo_build_skb(type, dev, change, flags); + skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags); if (skb) rtmsg_ifinfo_send(skb, dev, flags); } + +void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, + gfp_t flags) +{ + rtmsg_ifinfo_event(type, dev, change, IFLA_EVENT_NONE, flags); +} EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, @@ -4168,7 +4214,8 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_NOTIFY_PEERS: case NETDEV_RESEND_IGMP: case NETDEV_CHANGEINFODATA: - rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); + rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event), + GFP_KERNEL); break; default: break; From 7a7e96e09d463c7c3d51a51c539ae4352085ed18 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Sat, 27 May 2017 10:14:35 -0400 Subject: [PATCH 2/2] bonding: Prevent duplicate userspace notification Whenever a user changes bonding options, a NETDEV_CHANGEINFODATA notificatin is generated which results in a rtnelink message to be sent. While runnig 'ip monitor', we can actually see 2 messages, one a result of the event, and the other a result of state change that is generated bo netdev_state_change(). However, this is not always the case. If bonding changes were done via sysfs or ifenslave (old ioctl interface), then only 1 message is seen. This patch removes duplicate messages in the case of using netlink to configure bonding. It introduceds a separte function that triggers a netdev event and uses that function in the syfs and ioctl cases. This was discovered while auditing all the different envents and continues the effort of cleaning up duplicated netlink messages. CC: David Ahern CC: Jiri Pirko Signed-off-by: Vladislav Yasevich Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 3 ++- drivers/net/bonding/bond_options.c | 27 +++++++++++++++++++++++++-- include/net/bond_options.h | 2 ++ 3 files changed, 29 insertions(+), 3 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2359478b977f..d4484d1a8164 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3488,7 +3488,8 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd case BOND_CHANGE_ACTIVE_OLD: case SIOCBONDCHANGEACTIVE: bond_opt_initstr(&newval, slave_dev->name); - res = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval); + res = __bond_opt_set_notify(bond, BOND_OPT_ACTIVE_SLAVE, + &newval); break; default: res = -EOPNOTSUPP; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 1bcbb8913e17..8ca683396fcc 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -673,7 +673,30 @@ int __bond_opt_set(struct bonding *bond, out: if (ret) bond_opt_error_interpret(bond, opt, ret, val); - else if (bond->dev->reg_state == NETREG_REGISTERED) + + return ret; +} +/** + * __bond_opt_set_notify - set a bonding option + * @bond: target bond device + * @option: option to set + * @val: value to set it to + * + * This function is used to change the bond's option value and trigger + * a notification to user sapce. It can be used for both enabling/changing + * an option and for disabling it. RTNL lock must be obtained before calling + * this function. + */ +int __bond_opt_set_notify(struct bonding *bond, + unsigned int option, struct bond_opt_value *val) +{ + int ret = -ENOENT; + + ASSERT_RTNL(); + + ret = __bond_opt_set(bond, option, val); + + if (!ret && (bond->dev->reg_state == NETREG_REGISTERED)) call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev); return ret; @@ -696,7 +719,7 @@ int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf) if (!rtnl_trylock()) return restart_syscall(); bond_opt_initstr(&optval, buf); - ret = __bond_opt_set(bond, option, &optval); + ret = __bond_opt_set_notify(bond, option, &optval); rtnl_unlock(); return ret; diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 1797235cd590..d79d28f5318c 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -104,6 +104,8 @@ struct bond_option { int __bond_opt_set(struct bonding *bond, unsigned int option, struct bond_opt_value *val); +int __bond_opt_set_notify(struct bonding *bond, unsigned int option, + struct bond_opt_value *val); int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt,