From ebb9a03a590e2325f747be43c8db450e92509501 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sun, 10 May 2015 09:47:46 -0700 Subject: [PATCH 01/24] switchdev: s/netdev_switch_/switchdev_/ and s/NETDEV_SWITCH_/SWITCHDEV_/ Turned out that "switchdev" sticks. So just unify all related terms to use this prefix. Signed-off-by: Jiri Pirko Signed-off-by: Scott Feldman Acked-by: Roopa Prabhu Acked-by: Andy Gospodarek Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 4 +- drivers/net/ethernet/rocker/rocker.c | 10 +- drivers/net/team/team.c | 4 +- include/net/switchdev.h | 111 +++++++++++----------- net/bridge/br.c | 22 ++--- net/bridge/br_netlink.c | 6 +- net/bridge/br_stp.c | 2 +- net/core/net-sysfs.c | 2 +- net/core/rtnetlink.c | 2 +- net/ipv4/fib_trie.c | 40 ++++---- net/switchdev/switchdev.c | 134 +++++++++++++-------------- 11 files changed, 166 insertions(+), 171 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2ee13be7551b..a475a0389cc7 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4039,8 +4039,8 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_add_slave = bond_enslave, .ndo_del_slave = bond_release, .ndo_fix_features = bond_fix_features, - .ndo_bridge_setlink = ndo_dflt_netdev_switch_port_bridge_setlink, - .ndo_bridge_dellink = ndo_dflt_netdev_switch_port_bridge_dellink, + .ndo_bridge_setlink = ndo_dflt_switchdev_port_bridge_setlink, + .ndo_bridge_dellink = ndo_dflt_switchdev_port_bridge_dellink, .ndo_features_check = passthru_features_check, }; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 0c6f0a8b42dd..418f62b19545 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -3377,17 +3377,17 @@ static void rocker_port_fdb_learn_work(struct work_struct *work) container_of(work, struct rocker_fdb_learn_work, work); bool removing = (lw->flags & ROCKER_OP_FLAG_REMOVE); bool learned = (lw->flags & ROCKER_OP_FLAG_LEARNED); - struct netdev_switch_notifier_fdb_info info; + struct switchdev_notifier_fdb_info info; info.addr = lw->addr; info.vid = lw->vid; if (learned && removing) - call_netdev_switch_notifiers(NETDEV_SWITCH_FDB_DEL, - lw->dev, &info.info); + call_switchdev_notifiers(SWITCHDEV_FDB_DEL, + lw->dev, &info.info); else if (learned && !removing) - call_netdev_switch_notifiers(NETDEV_SWITCH_FDB_ADD, - lw->dev, &info.info); + call_switchdev_notifiers(SWITCHDEV_FDB_ADD, + lw->dev, &info.info); kfree(work); } diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 6928448f6b7f..cfe84965afb6 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1977,8 +1977,8 @@ static const struct net_device_ops team_netdev_ops = { .ndo_del_slave = team_del_slave, .ndo_fix_features = team_fix_features, .ndo_change_carrier = team_change_carrier, - .ndo_bridge_setlink = ndo_dflt_netdev_switch_port_bridge_setlink, - .ndo_bridge_dellink = ndo_dflt_netdev_switch_port_bridge_dellink, + .ndo_bridge_setlink = ndo_dflt_switchdev_port_bridge_setlink, + .ndo_bridge_dellink = ndo_dflt_switchdev_port_bridge_dellink, .ndo_features_check = passthru_features_check, }; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d2e69ee3019a..cd921fa0d63a 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -43,124 +43,125 @@ struct swdev_ops { u8 tos, u8 type, u32 tb_id); }; -enum netdev_switch_notifier_type { - NETDEV_SWITCH_FDB_ADD = 1, - NETDEV_SWITCH_FDB_DEL, +enum switchdev_notifier_type { + SWITCHDEV_FDB_ADD = 1, + SWITCHDEV_FDB_DEL, }; -struct netdev_switch_notifier_info { +struct switchdev_notifier_info { struct net_device *dev; }; -struct netdev_switch_notifier_fdb_info { - struct netdev_switch_notifier_info info; /* must be first */ +struct switchdev_notifier_fdb_info { + struct switchdev_notifier_info info; /* must be first */ const unsigned char *addr; u16 vid; }; static inline struct net_device * -netdev_switch_notifier_info_to_dev(const struct netdev_switch_notifier_info *info) +switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) { return info->dev; } #ifdef CONFIG_NET_SWITCHDEV -int netdev_switch_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid); -int netdev_switch_port_stp_update(struct net_device *dev, u8 state); -int register_netdev_switch_notifier(struct notifier_block *nb); -int unregister_netdev_switch_notifier(struct notifier_block *nb); -int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, - struct netdev_switch_notifier_info *info); -int netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags); -int netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags); -int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags); -int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags); -int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 nlflags, u32 tb_id); -int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id); -void netdev_switch_fib_ipv4_abort(struct fib_info *fi); +int switchdev_parent_id_get(struct net_device *dev, + struct netdev_phys_item_id *psid); +int switchdev_port_stp_update(struct net_device *dev, u8 state); +int register_switchdev_notifier(struct notifier_block *nb); +int unregister_switchdev_notifier(struct notifier_block *nb); +int call_switchdev_notifiers(unsigned long val, struct net_device *dev, + struct switchdev_notifier_info *info); +int switchdev_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags); +int switchdev_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags); +int ndo_dflt_switchdev_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags); +int ndo_dflt_switchdev_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags); +int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 nlflags, u32 tb_id); +int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id); +void switchdev_fib_ipv4_abort(struct fib_info *fi); #else -static inline int netdev_switch_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) +static inline int switchdev_parent_id_get(struct net_device *dev, + struct netdev_phys_item_id *psid) { return -EOPNOTSUPP; } -static inline int netdev_switch_port_stp_update(struct net_device *dev, - u8 state) +static inline int switchdev_port_stp_update(struct net_device *dev, + u8 state) { return -EOPNOTSUPP; } -static inline int register_netdev_switch_notifier(struct notifier_block *nb) +static inline int register_switchdev_notifier(struct notifier_block *nb) { return 0; } -static inline int unregister_netdev_switch_notifier(struct notifier_block *nb) +static inline int unregister_switchdev_notifier(struct notifier_block *nb) { return 0; } -static inline int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, - struct netdev_switch_notifier_info *info) +static inline int call_switchdev_notifiers(unsigned long val, + struct net_device *dev, + struct switchdev_notifier_info *info) { return NOTIFY_DONE; } -static inline int netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) +static inline int switchdev_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, + u16 flags) { return -EOPNOTSUPP; } -static inline int netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) +static inline int switchdev_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, + u16 flags) { return -EOPNOTSUPP; } -static inline int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) +static inline int ndo_dflt_switchdev_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, + u16 flags) { return 0; } -static inline int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) +static inline int ndo_dflt_switchdev_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, + u16 flags) { return 0; } -static inline int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, - struct fib_info *fi, - u8 tos, u8 type, - u32 nlflags, u32 tb_id) +static inline int switchdev_fib_ipv4_add(u32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, + u32 nlflags, u32 tb_id) { return 0; } -static inline int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, - struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) +static inline int switchdev_fib_ipv4_del(u32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) { return 0; } -static inline void netdev_switch_fib_ipv4_abort(struct fib_info *fi) +static inline void switchdev_fib_ipv4_abort(struct fib_info *fi) { } diff --git a/net/bridge/br.c b/net/bridge/br.c index 02c24cf63c34..a1abe4936fe1 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -121,13 +121,13 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; -static int br_netdev_switch_event(struct notifier_block *unused, - unsigned long event, void *ptr) +static int br_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) { - struct net_device *dev = netdev_switch_notifier_info_to_dev(ptr); + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; - struct netdev_switch_notifier_fdb_info *fdb_info; + struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; rtnl_lock(); @@ -138,14 +138,14 @@ static int br_netdev_switch_event(struct notifier_block *unused, br = p->br; switch (event) { - case NETDEV_SWITCH_FDB_ADD: + case SWITCHDEV_FDB_ADD: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, fdb_info->vid); if (err) err = notifier_from_errno(err); break; - case NETDEV_SWITCH_FDB_DEL: + case SWITCHDEV_FDB_DEL: fdb_info = ptr; err = br_fdb_external_learn_del(br, p, fdb_info->addr, fdb_info->vid); @@ -159,8 +159,8 @@ out: return err; } -static struct notifier_block br_netdev_switch_notifier = { - .notifier_call = br_netdev_switch_event, +static struct notifier_block br_switchdev_notifier = { + .notifier_call = br_switchdev_event, }; static void __net_exit br_net_exit(struct net *net) @@ -214,7 +214,7 @@ static int __init br_init(void) if (err) goto err_out3; - err = register_netdev_switch_notifier(&br_netdev_switch_notifier); + err = register_switchdev_notifier(&br_switchdev_notifier); if (err) goto err_out4; @@ -235,7 +235,7 @@ static int __init br_init(void) return 0; err_out5: - unregister_netdev_switch_notifier(&br_netdev_switch_notifier); + unregister_switchdev_notifier(&br_switchdev_notifier); err_out4: unregister_netdevice_notifier(&br_device_notifier); err_out3: @@ -253,7 +253,7 @@ static void __exit br_deinit(void) { stp_proto_unregister(&br_stp_proto); br_netlink_fini(); - unregister_netdev_switch_notifier(&br_netdev_switch_notifier); + unregister_switchdev_notifier(&br_switchdev_notifier); unregister_netdevice_notifier(&br_device_notifier); brioctl_set(NULL); unregister_pernet_subsys(&br_net_ops); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4b5c236998ff..dc234533e204 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -631,8 +631,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) if (p && !(flags & BRIDGE_FLAGS_SELF)) { /* set bridge attributes in hardware if supported */ - ret_offload = netdev_switch_port_bridge_setlink(dev, nlh, - flags); + ret_offload = switchdev_port_bridge_setlink(dev, nlh, flags); if (ret_offload && ret_offload != -EOPNOTSUPP) br_warn(p->br, "error setting attrs on port %u(%s)\n", (unsigned int)p->port_no, p->dev->name); @@ -671,8 +670,7 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) if (p && !(flags & BRIDGE_FLAGS_SELF)) { /* del bridge attributes in hardware */ - ret_offload = netdev_switch_port_bridge_dellink(dev, nlh, - flags); + ret_offload = switchdev_port_bridge_dellink(dev, nlh, flags); if (ret_offload && ret_offload != -EOPNOTSUPP) br_warn(p->br, "error deleting attrs on port %u (%s)\n", (unsigned int)p->port_no, p->dev->name); diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index fb3ebe615513..28e3f4bc01e0 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -42,7 +42,7 @@ void br_set_state(struct net_bridge_port *p, unsigned int state) int err; p->state = state; - err = netdev_switch_port_stp_update(p->dev, state); + err = switchdev_port_stp_update(p->dev, state); if (err && err != -EOPNOTSUPP) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4238d6da5c60..be86a7ce9282 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -460,7 +460,7 @@ static ssize_t phys_switch_id_show(struct device *dev, if (dev_isalive(netdev)) { struct netdev_phys_item_id ppid; - ret = netdev_switch_parent_id_get(netdev, &ppid); + ret = switchdev_parent_id_get(netdev, &ppid); if (!ret) ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 83e08323fdcd..fcd41fcd7e70 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1006,7 +1006,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) int err; struct netdev_phys_item_id psid; - err = netdev_switch_parent_id_get(dev, &psid); + err = switchdev_parent_id_get(dev, &psid); if (err) { if (err == -EOPNOTSUPP) return 0; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e13fcc602da2..03444c6ae342 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1165,13 +1165,13 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; - err = netdev_switch_fib_ipv4_add(key, plen, fi, - new_fa->fa_tos, - cfg->fc_type, - cfg->fc_nlflags, - tb->tb_id); + err = switchdev_fib_ipv4_add(key, plen, fi, + new_fa->fa_tos, + cfg->fc_type, + cfg->fc_nlflags, + tb->tb_id); if (err) { - netdev_switch_fib_ipv4_abort(fi); + switchdev_fib_ipv4_abort(fi); kmem_cache_free(fn_alias_kmem, new_fa); goto out; } @@ -1215,12 +1215,10 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->tb_id = tb->tb_id; /* (Optionally) offload fib entry to switch hardware. */ - err = netdev_switch_fib_ipv4_add(key, plen, fi, tos, - cfg->fc_type, - cfg->fc_nlflags, - tb->tb_id); + err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type, + cfg->fc_nlflags, tb->tb_id); if (err) { - netdev_switch_fib_ipv4_abort(fi); + switchdev_fib_ipv4_abort(fi); goto out_free_new_fa; } @@ -1239,7 +1237,7 @@ succeeded: return 0; out_sw_fib_del: - netdev_switch_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id); + switchdev_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: @@ -1517,8 +1515,8 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) if (!fa_to_delete) return -ESRCH; - netdev_switch_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos, - cfg->fc_type, tb->tb_id); + switchdev_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos, + cfg->fc_type, tb->tb_id); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); @@ -1767,10 +1765,9 @@ void fib_table_flush_external(struct fib_table *tb) if (!fi || !(fi->fib_flags & RTNH_F_EXTERNAL)) continue; - netdev_switch_fib_ipv4_del(n->key, - KEYLENGTH - fa->fa_slen, - fi, fa->fa_tos, - fa->fa_type, tb->tb_id); + switchdev_fib_ipv4_del(n->key, KEYLENGTH - fa->fa_slen, + fi, fa->fa_tos, fa->fa_type, + tb->tb_id); } /* update leaf slen */ @@ -1835,10 +1832,9 @@ int fib_table_flush(struct fib_table *tb) continue; } - netdev_switch_fib_ipv4_del(n->key, - KEYLENGTH - fa->fa_slen, - fi, fa->fa_tos, - fa->fa_type, tb->tb_id); + switchdev_fib_ipv4_del(n->key, KEYLENGTH - fa->fa_slen, + fi, fa->fa_tos, fa->fa_type, + tb->tb_id); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 46568b85c333..52613ed49a8c 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -19,14 +19,14 @@ #include /** - * netdev_switch_parent_id_get - Get ID of a switch + * switchdev_parent_id_get - Get ID of a switch * @dev: port device * @psid: switch ID * * Get ID of a switch this port is part of. */ -int netdev_switch_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) +int switchdev_parent_id_get(struct net_device *dev, + struct netdev_phys_item_id *psid) { const struct swdev_ops *ops = dev->swdev_ops; @@ -34,17 +34,17 @@ int netdev_switch_parent_id_get(struct net_device *dev, return -EOPNOTSUPP; return ops->swdev_parent_id_get(dev, psid); } -EXPORT_SYMBOL_GPL(netdev_switch_parent_id_get); +EXPORT_SYMBOL_GPL(switchdev_parent_id_get); /** - * netdev_switch_port_stp_update - Notify switch device port of STP + * switchdev_port_stp_update - Notify switch device port of STP * state change * @dev: port device * @state: port STP state * * Notify switch device port of bridge port STP state change. */ -int netdev_switch_port_stp_update(struct net_device *dev, u8 state) +int switchdev_port_stp_update(struct net_device *dev, u8 state) { const struct swdev_ops *ops = dev->swdev_ops; struct net_device *lower_dev; @@ -55,57 +55,57 @@ int netdev_switch_port_stp_update(struct net_device *dev, u8 state) return ops->swdev_port_stp_update(dev, state); netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = netdev_switch_port_stp_update(lower_dev, state); + err = switchdev_port_stp_update(lower_dev, state); if (err && err != -EOPNOTSUPP) return err; } return err; } -EXPORT_SYMBOL_GPL(netdev_switch_port_stp_update); +EXPORT_SYMBOL_GPL(switchdev_port_stp_update); -static DEFINE_MUTEX(netdev_switch_mutex); -static RAW_NOTIFIER_HEAD(netdev_switch_notif_chain); +static DEFINE_MUTEX(switchdev_mutex); +static RAW_NOTIFIER_HEAD(switchdev_notif_chain); /** - * register_netdev_switch_notifier - Register notifier + * register_switchdev_notifier - Register notifier * @nb: notifier_block * * Register switch device notifier. This should be used by code * which needs to monitor events happening in particular device. * Return values are same as for atomic_notifier_chain_register(). */ -int register_netdev_switch_notifier(struct notifier_block *nb) +int register_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&netdev_switch_mutex); - err = raw_notifier_chain_register(&netdev_switch_notif_chain, nb); - mutex_unlock(&netdev_switch_mutex); + mutex_lock(&switchdev_mutex); + err = raw_notifier_chain_register(&switchdev_notif_chain, nb); + mutex_unlock(&switchdev_mutex); return err; } -EXPORT_SYMBOL_GPL(register_netdev_switch_notifier); +EXPORT_SYMBOL_GPL(register_switchdev_notifier); /** - * unregister_netdev_switch_notifier - Unregister notifier + * unregister_switchdev_notifier - Unregister notifier * @nb: notifier_block * * Unregister switch device notifier. * Return values are same as for atomic_notifier_chain_unregister(). */ -int unregister_netdev_switch_notifier(struct notifier_block *nb) +int unregister_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&netdev_switch_mutex); - err = raw_notifier_chain_unregister(&netdev_switch_notif_chain, nb); - mutex_unlock(&netdev_switch_mutex); + mutex_lock(&switchdev_mutex); + err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb); + mutex_unlock(&switchdev_mutex); return err; } -EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier); +EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); /** - * call_netdev_switch_notifiers - Call notifiers + * call_switchdev_notifiers - Call notifiers * @val: value passed unmodified to notifier function * @dev: port device * @info: notifier information data @@ -114,21 +114,21 @@ EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier); * when it needs to propagate hardware event. * Return values are same as for atomic_notifier_call_chain(). */ -int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, - struct netdev_switch_notifier_info *info) +int call_switchdev_notifiers(unsigned long val, struct net_device *dev, + struct switchdev_notifier_info *info) { int err; info->dev = dev; - mutex_lock(&netdev_switch_mutex); - err = raw_notifier_call_chain(&netdev_switch_notif_chain, val, info); - mutex_unlock(&netdev_switch_mutex); + mutex_lock(&switchdev_mutex); + err = raw_notifier_call_chain(&switchdev_notif_chain, val, info); + mutex_unlock(&switchdev_mutex); return err; } -EXPORT_SYMBOL_GPL(call_netdev_switch_notifiers); +EXPORT_SYMBOL_GPL(call_switchdev_notifiers); /** - * netdev_switch_port_bridge_setlink - Notify switch device port of bridge + * switchdev_port_bridge_setlink - Notify switch device port of bridge * port attributes * * @dev: port device @@ -137,8 +137,8 @@ EXPORT_SYMBOL_GPL(call_netdev_switch_notifiers); * * Notify switch device port of bridge port attributes */ -int netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) +int switchdev_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) { const struct net_device_ops *ops = dev->netdev_ops; @@ -150,10 +150,10 @@ int netdev_switch_port_bridge_setlink(struct net_device *dev, return ops->ndo_bridge_setlink(dev, nlh, flags); } -EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_setlink); +EXPORT_SYMBOL_GPL(switchdev_port_bridge_setlink); /** - * netdev_switch_port_bridge_dellink - Notify switch device port of bridge + * switchdev_port_bridge_dellink - Notify switch device port of bridge * port attribute delete * * @dev: port device @@ -162,8 +162,8 @@ EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_setlink); * * Notify switch device port of bridge port attribute delete */ -int netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) +int switchdev_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) { const struct net_device_ops *ops = dev->netdev_ops; @@ -175,11 +175,11 @@ int netdev_switch_port_bridge_dellink(struct net_device *dev, return ops->ndo_bridge_dellink(dev, nlh, flags); } -EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_dellink); +EXPORT_SYMBOL_GPL(switchdev_port_bridge_dellink); /** - * ndo_dflt_netdev_switch_port_bridge_setlink - default ndo bridge setlink - * op for master devices + * ndo_dflt_switchdev_port_bridge_setlink - default ndo bridge setlink + * op for master devices * * @dev: port device * @nlh: netlink msg with bridge port attributes @@ -187,8 +187,8 @@ EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_dellink); * * Notify master device slaves of bridge port attributes */ -int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) +int ndo_dflt_switchdev_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) { struct net_device *lower_dev; struct list_head *iter; @@ -198,18 +198,18 @@ int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, return ret; netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = netdev_switch_port_bridge_setlink(lower_dev, nlh, flags); + err = switchdev_port_bridge_setlink(lower_dev, nlh, flags); if (err && err != -EOPNOTSUPP) ret = err; } return ret; } -EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_setlink); +EXPORT_SYMBOL_GPL(ndo_dflt_switchdev_port_bridge_setlink); /** - * ndo_dflt_netdev_switch_port_bridge_dellink - default ndo bridge dellink - * op for master devices + * ndo_dflt_switchdev_port_bridge_dellink - default ndo bridge dellink + * op for master devices * * @dev: port device * @nlh: netlink msg with bridge port attributes @@ -217,8 +217,8 @@ EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_setlink); * * Notify master device slaves of bridge port attribute deletes */ -int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) +int ndo_dflt_switchdev_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) { struct net_device *lower_dev; struct list_head *iter; @@ -228,16 +228,16 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, return ret; netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = netdev_switch_port_bridge_dellink(lower_dev, nlh, flags); + err = switchdev_port_bridge_dellink(lower_dev, nlh, flags); if (err && err != -EOPNOTSUPP) ret = err; } return ret; } -EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_dellink); +EXPORT_SYMBOL_GPL(ndo_dflt_switchdev_port_bridge_dellink); -static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev) +static struct net_device *switchdev_get_lowest_dev(struct net_device *dev) { const struct swdev_ops *ops = dev->swdev_ops; struct net_device *lower_dev; @@ -253,7 +253,7 @@ static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev) return dev; netdev_for_each_lower_dev(dev, lower_dev, iter) { - port_dev = netdev_switch_get_lowest_dev(lower_dev); + port_dev = switchdev_get_lowest_dev(lower_dev); if (port_dev) return port_dev; } @@ -261,7 +261,7 @@ static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev) return NULL; } -static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi) +static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) { struct netdev_phys_item_id psid; struct netdev_phys_item_id prev_psid; @@ -276,11 +276,11 @@ static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi) if (!nh->nh_dev) return NULL; - dev = netdev_switch_get_lowest_dev(nh->nh_dev); + dev = switchdev_get_lowest_dev(nh->nh_dev); if (!dev) return NULL; - if (netdev_switch_parent_id_get(dev, &psid)) + if (switchdev_parent_id_get(dev, &psid)) return NULL; if (nhsel > 0) { @@ -297,7 +297,7 @@ static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi) } /** - * netdev_switch_fib_ipv4_add - Add IPv4 route entry to switch + * switchdev_fib_ipv4_add - Add IPv4 route entry to switch * * @dst: route's IPv4 destination address * @dst_len: destination address length (prefix length) @@ -309,8 +309,8 @@ static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi) * * Add IPv4 route entry to switch device. */ -int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 nlflags, u32 tb_id) +int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 nlflags, u32 tb_id) { struct net_device *dev; const struct swdev_ops *ops; @@ -328,7 +328,7 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, if (fi->fib_net->ipv4.fib_offload_disabled) return 0; - dev = netdev_switch_get_dev_by_nhs(fi); + dev = switchdev_get_dev_by_nhs(fi); if (!dev) return 0; ops = dev->swdev_ops; @@ -343,10 +343,10 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, return err; } -EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_add); +EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_add); /** - * netdev_switch_fib_ipv4_del - Delete IPv4 route entry from switch + * switchdev_fib_ipv4_del - Delete IPv4 route entry from switch * * @dst: route's IPv4 destination address * @dst_len: destination address length (prefix length) @@ -357,8 +357,8 @@ EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_add); * * Delete IPv4 route entry from switch device. */ -int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) +int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) { struct net_device *dev; const struct swdev_ops *ops; @@ -367,7 +367,7 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, if (!(fi->fib_flags & RTNH_F_EXTERNAL)) return 0; - dev = netdev_switch_get_dev_by_nhs(fi); + dev = switchdev_get_dev_by_nhs(fi); if (!dev) return 0; ops = dev->swdev_ops; @@ -381,14 +381,14 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, return err; } -EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_del); +EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_del); /** - * netdev_switch_fib_ipv4_abort - Abort an IPv4 FIB operation + * switchdev_fib_ipv4_abort - Abort an IPv4 FIB operation * * @fi: route FIB info structure */ -void netdev_switch_fib_ipv4_abort(struct fib_info *fi) +void switchdev_fib_ipv4_abort(struct fib_info *fi) { /* There was a problem installing this route to the offload * device. For now, until we come up with more refined @@ -401,4 +401,4 @@ void netdev_switch_fib_ipv4_abort(struct fib_info *fi) fib_flush_external(fi->fib_net); fi->fib_net->ipv4.fib_offload_disabled = true; } -EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_abort); +EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_abort); From 9d47c0a2d958e06322c88245749278633d333cca Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sun, 10 May 2015 09:47:47 -0700 Subject: [PATCH 02/24] switchdev: s/swdev_/switchdev_/ Turned out that "switchdev" sticks. So just unify all related terms to use this prefix. Signed-off-by: Jiri Pirko Signed-off-by: Scott Feldman Acked-by: Roopa Prabhu Acked-by: Andy Gospodarek Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 37 ++++++++++++------------- include/linux/netdevice.h | 2 +- include/net/switchdev.h | 30 ++++++++++----------- net/dsa/slave.c | 8 +++--- net/switchdev/switchdev.c | 40 ++++++++++++++-------------- 5 files changed, 59 insertions(+), 58 deletions(-) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 418f62b19545..7473874daf1f 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4221,8 +4221,8 @@ static const struct net_device_ops rocker_port_netdev_ops = { * swdev interface ********************/ -static int rocker_port_swdev_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) +static int rocker_port_switchdev_parent_id_get(struct net_device *dev, + struct netdev_phys_item_id *psid) { struct rocker_port *rocker_port = netdev_priv(dev); struct rocker *rocker = rocker_port->rocker; @@ -4232,18 +4232,19 @@ static int rocker_port_swdev_parent_id_get(struct net_device *dev, return 0; } -static int rocker_port_swdev_port_stp_update(struct net_device *dev, u8 state) +static int rocker_port_switchdev_port_stp_update(struct net_device *dev, + u8 state) { struct rocker_port *rocker_port = netdev_priv(dev); return rocker_port_stp_update(rocker_port, state); } -static int rocker_port_swdev_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) +static int rocker_port_switchdev_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) { struct rocker_port *rocker_port = netdev_priv(dev); int flags = 0; @@ -4252,10 +4253,10 @@ static int rocker_port_swdev_fib_ipv4_add(struct net_device *dev, fi, tb_id, flags); } -static int rocker_port_swdev_fib_ipv4_del(struct net_device *dev, - __be32 dst, int dst_len, - struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) +static int rocker_port_switchdev_fib_ipv4_del(struct net_device *dev, + __be32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) { struct rocker_port *rocker_port = netdev_priv(dev); int flags = ROCKER_OP_FLAG_REMOVE; @@ -4264,11 +4265,11 @@ static int rocker_port_swdev_fib_ipv4_del(struct net_device *dev, fi, tb_id, flags); } -static const struct swdev_ops rocker_port_swdev_ops = { - .swdev_parent_id_get = rocker_port_swdev_parent_id_get, - .swdev_port_stp_update = rocker_port_swdev_port_stp_update, - .swdev_fib_ipv4_add = rocker_port_swdev_fib_ipv4_add, - .swdev_fib_ipv4_del = rocker_port_swdev_fib_ipv4_del, +static const struct switchdev_ops rocker_port_switchdev_ops = { + .switchdev_parent_id_get = rocker_port_switchdev_parent_id_get, + .switchdev_port_stp_update = rocker_port_switchdev_port_stp_update, + .switchdev_fib_ipv4_add = rocker_port_switchdev_fib_ipv4_add, + .switchdev_fib_ipv4_del = rocker_port_switchdev_fib_ipv4_del, }; /******************** @@ -4623,7 +4624,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) rocker_port_dev_addr_init(rocker, rocker_port); dev->netdev_ops = &rocker_port_netdev_ops; dev->ethtool_ops = &rocker_port_ethtool_ops; - dev->swdev_ops = &rocker_port_swdev_ops; + dev->switchdev_ops = &rocker_port_switchdev_ops; netif_napi_add(dev, &rocker_port->napi_tx, rocker_port_poll_tx, NAPI_POLL_WEIGHT); netif_napi_add(dev, &rocker_port->napi_rx, rocker_port_poll_rx, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a6d706b2a947..2b39235b9f13 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1567,7 +1567,7 @@ struct net_device { const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_SWITCHDEV - const struct swdev_ops *swdev_ops; + const struct switchdev_ops *switchdev_ops; #endif const struct header_ops *header_ops; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index cd921fa0d63a..97b556daeef7 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -19,28 +19,28 @@ struct fib_info; /** * struct switchdev_ops - switchdev operations * - * @swdev_parent_id_get: Called to get an ID of the switch chip this port + * @switchdev_parent_id_get: 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. * - * @swdev_port_stp_update: Called to notify switch device port of bridge + * @switchdev_port_stp_update: Called to notify switch device port of bridge * port STP state change. * - * @swdev_fib_ipv4_add: Called to add/modify IPv4 route to switch device. + * @switchdev_fib_ipv4_add: Called to add/modify IPv4 route to switch device. * - * @swdev_fib_ipv4_del: Called to delete IPv4 route from switch device. + * @switchdev_fib_ipv4_del: Called to delete IPv4 route from switch device. */ -struct swdev_ops { - int (*swdev_parent_id_get)(struct net_device *dev, - struct netdev_phys_item_id *psid); - int (*swdev_port_stp_update)(struct net_device *dev, u8 state); - int (*swdev_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 (*swdev_fib_ipv4_del)(struct net_device *dev, __be32 dst, - int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id); +struct switchdev_ops { + int (*switchdev_parent_id_get)(struct net_device *dev, + struct netdev_phys_item_id *psid); + int (*switchdev_port_stp_update)(struct net_device *dev, u8 state); + int (*switchdev_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 (*switchdev_fib_ipv4_del)(struct net_device *dev, __be32 dst, + int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id); }; enum switchdev_notifier_type { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 03e041addea3..1546acf6ebd3 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -675,9 +675,9 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_get_iflink = dsa_slave_get_iflink, }; -static const struct swdev_ops dsa_slave_swdev_ops = { - .swdev_parent_id_get = dsa_slave_parent_id_get, - .swdev_port_stp_update = dsa_slave_stp_update, +static const struct switchdev_ops dsa_slave_switchdev_ops = { + .switchdev_parent_id_get = dsa_slave_parent_id_get, + .switchdev_port_stp_update = dsa_slave_stp_update, }; static void dsa_slave_adjust_link(struct net_device *dev) @@ -866,7 +866,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, eth_hw_addr_inherit(slave_dev, master); slave_dev->tx_queue_len = 0; slave_dev->netdev_ops = &dsa_slave_netdev_ops; - slave_dev->swdev_ops = &dsa_slave_swdev_ops; + slave_dev->switchdev_ops = &dsa_slave_switchdev_ops; netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, NULL); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 52613ed49a8c..b7f44a23def5 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -28,11 +28,11 @@ int switchdev_parent_id_get(struct net_device *dev, struct netdev_phys_item_id *psid) { - const struct swdev_ops *ops = dev->swdev_ops; + const struct switchdev_ops *ops = dev->switchdev_ops; - if (!ops || !ops->swdev_parent_id_get) + if (!ops || !ops->switchdev_parent_id_get) return -EOPNOTSUPP; - return ops->swdev_parent_id_get(dev, psid); + return ops->switchdev_parent_id_get(dev, psid); } EXPORT_SYMBOL_GPL(switchdev_parent_id_get); @@ -46,13 +46,13 @@ EXPORT_SYMBOL_GPL(switchdev_parent_id_get); */ int switchdev_port_stp_update(struct net_device *dev, u8 state) { - const struct swdev_ops *ops = dev->swdev_ops; + const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; - if (ops && ops->swdev_port_stp_update) - return ops->swdev_port_stp_update(dev, state); + if (ops && ops->switchdev_port_stp_update) + return ops->switchdev_port_stp_update(dev, state); netdev_for_each_lower_dev(dev, lower_dev, iter) { err = switchdev_port_stp_update(lower_dev, state); @@ -239,17 +239,17 @@ EXPORT_SYMBOL_GPL(ndo_dflt_switchdev_port_bridge_dellink); static struct net_device *switchdev_get_lowest_dev(struct net_device *dev) { - const struct swdev_ops *ops = dev->swdev_ops; + const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; struct net_device *port_dev; struct list_head *iter; /* Recusively search down until we find a sw port dev. - * (A sw port dev supports swdev_parent_id_get). + * (A sw port dev supports switchdev_parent_id_get). */ if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD && - ops && ops->swdev_parent_id_get) + ops && ops->switchdev_parent_id_get) return dev; netdev_for_each_lower_dev(dev, lower_dev, iter) { @@ -313,7 +313,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 nlflags, u32 tb_id) { struct net_device *dev; - const struct swdev_ops *ops; + const struct switchdev_ops *ops; int err = 0; /* Don't offload route if using custom ip rules or if @@ -331,12 +331,12 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, dev = switchdev_get_dev_by_nhs(fi); if (!dev) return 0; - ops = dev->swdev_ops; + ops = dev->switchdev_ops; - if (ops->swdev_fib_ipv4_add) { - err = ops->swdev_fib_ipv4_add(dev, htonl(dst), dst_len, - fi, tos, type, nlflags, - tb_id); + if (ops->switchdev_fib_ipv4_add) { + err = ops->switchdev_fib_ipv4_add(dev, htonl(dst), dst_len, + fi, tos, type, nlflags, + tb_id); if (!err) fi->fib_flags |= RTNH_F_EXTERNAL; } @@ -361,7 +361,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id) { struct net_device *dev; - const struct swdev_ops *ops; + const struct switchdev_ops *ops; int err = 0; if (!(fi->fib_flags & RTNH_F_EXTERNAL)) @@ -370,11 +370,11 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, dev = switchdev_get_dev_by_nhs(fi); if (!dev) return 0; - ops = dev->swdev_ops; + ops = dev->switchdev_ops; - if (ops->swdev_fib_ipv4_del) { - err = ops->swdev_fib_ipv4_del(dev, htonl(dst), dst_len, - fi, tos, type, tb_id); + if (ops->switchdev_fib_ipv4_del) { + err = ops->switchdev_fib_ipv4_del(dev, htonl(dst), dst_len, + fi, tos, type, tb_id); if (!err) fi->fib_flags &= ~RTNH_F_EXTERNAL; } From 3094333d9089d43e8b8f0418676fa6ae06c27b51 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:48 -0700 Subject: [PATCH 03/24] switchdev: introduce get/set attrs ops Add two new swdev ops for get/set switch port attributes. Most swdev interactions on a port are gets or sets on port attributes, so rather than adding ops for each attribute, let's define clean get/set ops for all attributes, and then we can have clear, consistent rules on how attributes propagate on stacked devs. Add the basic algorithms for get/set attr ops. Use the same recusive algo to walk lower devs we've used for STP updates, for example. For get, compare attr value for each lower dev and only return success if attr values match across all lower devs. For sets, set the same attr value for all lower devs. We'll use a two-phase prepare-commit transaction model for sets. In the first phase, the driver(s) are asked if attr set is OK. If all OK, the commit attr set in second phase. A driver would NACK the prepare phase if it can't set the attr due to lack of resources or support, within it's control. RTNL lock must be held across both phases because we'll recurse all lower devs first in prepare phase, and then recurse all lower devs again in commit phase. If any lower dev fails the prepare phase, we need to abort the transaction for all lower devs. If lower dev recusion isn't desired, allow a flag SWITCHDEV_F_NO_RECURSE to indicate get/set only work on port (lowest) device. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 43 ++++++++++ net/switchdev/switchdev.c | 169 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 212 insertions(+) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 97b556daeef7..282043844bcf 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -14,6 +14,25 @@ #include #include +#define SWITCHDEV_F_NO_RECURSE BIT(0) + +enum switchdev_trans { + SWITCHDEV_TRANS_NONE, + SWITCHDEV_TRANS_PREPARE, + SWITCHDEV_TRANS_ABORT, + SWITCHDEV_TRANS_COMMIT, +}; + +enum switchdev_attr_id { + SWITCHDEV_ATTR_UNDEFINED, +}; + +struct switchdev_attr { + enum switchdev_attr_id id; + enum switchdev_trans trans; + u32 flags; +}; + struct fib_info; /** @@ -23,6 +42,10 @@ struct fib_info; * is part of. If driver implements this, it indicates that it * represents a port of a switch chip. * + * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr). + * + * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). + * * @switchdev_port_stp_update: Called to notify switch device port of bridge * port STP state change. * @@ -33,6 +56,10 @@ struct fib_info; struct switchdev_ops { int (*switchdev_parent_id_get)(struct net_device *dev, struct netdev_phys_item_id *psid); + int (*switchdev_port_attr_get)(struct net_device *dev, + struct switchdev_attr *attr); + int (*switchdev_port_attr_set)(struct net_device *dev, + struct switchdev_attr *attr); int (*switchdev_port_stp_update)(struct net_device *dev, u8 state); int (*switchdev_fib_ipv4_add)(struct net_device *dev, __be32 dst, int dst_len, struct fib_info *fi, @@ -68,6 +95,10 @@ switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) int switchdev_parent_id_get(struct net_device *dev, struct netdev_phys_item_id *psid); +int switchdev_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr); +int switchdev_port_attr_set(struct net_device *dev, + struct switchdev_attr *attr); int switchdev_port_stp_update(struct net_device *dev, u8 state); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); @@ -95,6 +126,18 @@ static inline int switchdev_parent_id_get(struct net_device *dev, return -EOPNOTSUPP; } +static inline int switchdev_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr) +{ + return -EOPNOTSUPP; +} + +static inline int switchdev_port_attr_set(struct net_device *dev, + struct switchdev_attr *attr) +{ + return -EOPNOTSUPP; +} + static inline int switchdev_port_stp_update(struct net_device *dev, u8 state) { diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index b7f44a23def5..8f47187dc185 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -36,6 +36,175 @@ int switchdev_parent_id_get(struct net_device *dev, } EXPORT_SYMBOL_GPL(switchdev_parent_id_get); +/** + * switchdev_port_attr_get - Get port attribute + * + * @dev: port device + * @attr: attribute to get + */ +int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) +{ + const struct switchdev_ops *ops = dev->switchdev_ops; + struct net_device *lower_dev; + struct list_head *iter; + struct switchdev_attr first = { + .id = SWITCHDEV_ATTR_UNDEFINED + }; + int err = -EOPNOTSUPP; + + if (ops && ops->switchdev_port_attr_get) + return ops->switchdev_port_attr_get(dev, attr); + + if (attr->flags & SWITCHDEV_F_NO_RECURSE) + return err; + + /* Switch device port(s) may be stacked under + * bond/team/vlan dev, so recurse down to get attr on + * each port. Return -ENODATA if attr values don't + * compare across ports. + */ + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = switchdev_port_attr_get(lower_dev, attr); + if (err) + break; + if (first.id == SWITCHDEV_ATTR_UNDEFINED) + first = *attr; + else if (memcmp(&first, attr, sizeof(*attr))) + return -ENODATA; + } + + return err; +} +EXPORT_SYMBOL_GPL(switchdev_port_attr_get); + +static int __switchdev_port_attr_set(struct net_device *dev, + struct switchdev_attr *attr) +{ + const struct switchdev_ops *ops = dev->switchdev_ops; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (ops && ops->switchdev_port_attr_set) + return ops->switchdev_port_attr_set(dev, attr); + + if (attr->flags & SWITCHDEV_F_NO_RECURSE) + return err; + + /* Switch device port(s) may be stacked under + * bond/team/vlan dev, so recurse down to set attr on + * each port. + */ + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = __switchdev_port_attr_set(lower_dev, attr); + if (err) + break; + } + + return err; +} + +struct switchdev_attr_set_work { + struct work_struct work; + struct net_device *dev; + struct switchdev_attr attr; +}; + +static void switchdev_port_attr_set_work(struct work_struct *work) +{ + struct switchdev_attr_set_work *asw = + container_of(work, struct switchdev_attr_set_work, work); + int err; + + rtnl_lock(); + err = switchdev_port_attr_set(asw->dev, &asw->attr); + BUG_ON(err); + rtnl_unlock(); + + dev_put(asw->dev); + kfree(work); +} + +static int switchdev_port_attr_set_defer(struct net_device *dev, + struct switchdev_attr *attr) +{ + struct switchdev_attr_set_work *asw; + + asw = kmalloc(sizeof(*asw), GFP_ATOMIC); + if (!asw) + return -ENOMEM; + + INIT_WORK(&asw->work, switchdev_port_attr_set_work); + + dev_hold(dev); + asw->dev = dev; + memcpy(&asw->attr, attr, sizeof(asw->attr)); + + schedule_work(&asw->work); + + return 0; +} + +/** + * switchdev_port_attr_set - Set port attribute + * + * @dev: port device + * @attr: attribute to set + * + * Use a 2-phase prepare-commit transaction model to ensure + * system is not left in a partially updated state due to + * failure from driver/device. + */ +int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) +{ + int err; + + if (!rtnl_is_locked()) { + /* Running prepare-commit transaction across stacked + * devices requires nothing moves, so if rtnl_lock is + * not held, schedule a worker thread to hold rtnl_lock + * while setting attr. + */ + + return switchdev_port_attr_set_defer(dev, attr); + } + + /* Phase I: prepare for attr set. Driver/device should fail + * here if there are going to be issues in the commit phase, + * such as lack of resources or support. The driver/device + * should reserve resources needed for the commit phase here, + * but should not commit the attr. + */ + + attr->trans = SWITCHDEV_TRANS_PREPARE; + err = __switchdev_port_attr_set(dev, attr); + if (err) { + /* Prepare phase failed: abort the transaction. Any + * resources reserved in the prepare phase are + * released. + */ + + attr->trans = SWITCHDEV_TRANS_ABORT; + __switchdev_port_attr_set(dev, attr); + + return err; + } + + /* Phase II: commit attr set. This cannot fail as a fault + * of driver/device. If it does, it's a bug in the driver/device + * because the driver said everythings was OK in phase I. + */ + + attr->trans = SWITCHDEV_TRANS_COMMIT; + err = __switchdev_port_attr_set(dev, attr); + BUG_ON(err); + + return err; +} +EXPORT_SYMBOL_GPL(switchdev_port_attr_set); + /** * switchdev_port_stp_update - Notify switch device port of STP * state change From f8e20a9f87d33865cc1d67f13da0db8d457fc3c9 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:49 -0700 Subject: [PATCH 04/24] switchdev: convert parent_id_get to switchdev attr get Switch ID is just a gettable port attribute. Convert switchdev op switchdev_parent_id_get to a switchdev attr. Note: for sysfs and netlink interfaces, SWITCHDEV_ATTR_PORT_PARENT_ID is called with SWITCHDEV_F_NO_RECUSE to limit switch ID user-visiblity to only port netdevs. So when a port is stacked under bond/bridge, the user can only query switch id via the switch ports, but not via the upper devices Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 17 +++++++++---- include/net/switchdev.h | 18 +++---------- net/core/net-sysfs.c | 10 +++++--- net/core/rtnetlink.c | 9 ++++--- net/dsa/slave.c | 16 ++++++++---- net/switchdev/switchdev.c | 38 ++++++++-------------------- 6 files changed, 51 insertions(+), 57 deletions(-) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 7473874daf1f..24282991d9fd 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4221,14 +4221,21 @@ static const struct net_device_ops rocker_port_netdev_ops = { * swdev interface ********************/ -static int rocker_port_switchdev_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) +static int rocker_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr) { struct rocker_port *rocker_port = netdev_priv(dev); struct rocker *rocker = rocker_port->rocker; - psid->id_len = sizeof(rocker->hw.id); - memcpy(&psid->id, &rocker->hw.id, psid->id_len); + switch (attr->id) { + case SWITCHDEV_ATTR_PORT_PARENT_ID: + attr->ppid.id_len = sizeof(rocker->hw.id); + memcpy(&attr->ppid.id, &rocker->hw.id, attr->ppid.id_len); + break; + default: + return -EOPNOTSUPP; + } + return 0; } @@ -4266,7 +4273,7 @@ static int rocker_port_switchdev_fib_ipv4_del(struct net_device *dev, } static const struct switchdev_ops rocker_port_switchdev_ops = { - .switchdev_parent_id_get = rocker_port_switchdev_parent_id_get, + .switchdev_port_attr_get = rocker_port_attr_get, .switchdev_port_stp_update = rocker_port_switchdev_port_stp_update, .switchdev_fib_ipv4_add = rocker_port_switchdev_fib_ipv4_add, .switchdev_fib_ipv4_del = rocker_port_switchdev_fib_ipv4_del, diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 282043844bcf..93316e7ab372 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -25,12 +25,16 @@ enum switchdev_trans { enum switchdev_attr_id { SWITCHDEV_ATTR_UNDEFINED, + SWITCHDEV_ATTR_PORT_PARENT_ID, }; struct switchdev_attr { enum switchdev_attr_id id; enum switchdev_trans trans; u32 flags; + union { + struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ + }; }; struct fib_info; @@ -38,10 +42,6 @@ struct fib_info; /** * struct switchdev_ops - switchdev operations * - * @switchdev_parent_id_get: 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. - * * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr). * * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). @@ -54,8 +54,6 @@ struct fib_info; * @switchdev_fib_ipv4_del: Called to delete IPv4 route from switch device. */ struct switchdev_ops { - int (*switchdev_parent_id_get)(struct net_device *dev, - struct netdev_phys_item_id *psid); int (*switchdev_port_attr_get)(struct net_device *dev, struct switchdev_attr *attr); int (*switchdev_port_attr_set)(struct net_device *dev, @@ -93,8 +91,6 @@ switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) #ifdef CONFIG_NET_SWITCHDEV -int switchdev_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid); int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, @@ -120,12 +116,6 @@ void switchdev_fib_ipv4_abort(struct fib_info *fi); #else -static inline int switchdev_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) -{ - return -EOPNOTSUPP; -} - static inline int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index be86a7ce9282..5a9ce96f6d27 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -458,11 +458,15 @@ static ssize_t phys_switch_id_show(struct device *dev, return restart_syscall(); if (dev_isalive(netdev)) { - struct netdev_phys_item_id ppid; + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .flags = SWITCHDEV_F_NO_RECURSE, + }; - ret = switchdev_parent_id_get(netdev, &ppid); + ret = switchdev_port_attr_get(netdev, &attr); if (!ret) - ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); + ret = sprintf(buf, "%*phN\n", attr.ppid.id_len, + attr.ppid.id); } rtnl_unlock(); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index fcd41fcd7e70..c6c6b2c34926 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1004,16 +1004,19 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev) static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { int err; - struct netdev_phys_item_id psid; + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .flags = SWITCHDEV_F_NO_RECURSE, + }; - err = switchdev_parent_id_get(dev, &psid); + err = switchdev_port_attr_get(dev, &attr); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } - if (nla_put(skb, IFLA_PHYS_SWITCH_ID, psid.id_len, psid.id)) + if (nla_put(skb, IFLA_PHYS_SWITCH_ID, attr.ppid.id_len, attr.ppid.id)) return -EMSGSIZE; return 0; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1546acf6ebd3..de705b674ac9 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -382,14 +382,20 @@ static int dsa_slave_bridge_port_leave(struct net_device *dev) return ret; } -static int dsa_slave_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) +static int dsa_slave_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - psid->id_len = sizeof(ds->index); - memcpy(&psid->id, &ds->index, psid->id_len); + switch (attr->id) { + case SWITCHDEV_ATTR_PORT_PARENT_ID: + attr->ppid.id_len = sizeof(ds->index); + memcpy(&attr->ppid.id, &ds->index, attr->ppid.id_len); + break; + default: + return -EOPNOTSUPP; + } return 0; } @@ -676,7 +682,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = { }; static const struct switchdev_ops dsa_slave_switchdev_ops = { - .switchdev_parent_id_get = dsa_slave_parent_id_get, + .switchdev_port_attr_get = dsa_slave_port_attr_get, .switchdev_port_stp_update = dsa_slave_stp_update, }; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8f47187dc185..117fd0797abd 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -18,24 +18,6 @@ #include #include -/** - * switchdev_parent_id_get - Get ID of a switch - * @dev: port device - * @psid: switch ID - * - * Get ID of a switch this port is part of. - */ -int switchdev_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) -{ - const struct switchdev_ops *ops = dev->switchdev_ops; - - if (!ops || !ops->switchdev_parent_id_get) - return -EOPNOTSUPP; - return ops->switchdev_parent_id_get(dev, psid); -} -EXPORT_SYMBOL_GPL(switchdev_parent_id_get); - /** * switchdev_port_attr_get - Get port attribute * @@ -414,11 +396,10 @@ static struct net_device *switchdev_get_lowest_dev(struct net_device *dev) struct list_head *iter; /* Recusively search down until we find a sw port dev. - * (A sw port dev supports switchdev_parent_id_get). + * (A sw port dev supports switchdev_port_attr_get). */ - if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD && - ops && ops->switchdev_parent_id_get) + if (ops && ops->switchdev_port_attr_get) return dev; netdev_for_each_lower_dev(dev, lower_dev, iter) { @@ -432,8 +413,10 @@ static struct net_device *switchdev_get_lowest_dev(struct net_device *dev) static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) { - struct netdev_phys_item_id psid; - struct netdev_phys_item_id prev_psid; + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + }; + struct switchdev_attr prev_attr; struct net_device *dev = NULL; int nhsel; @@ -449,17 +432,18 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) if (!dev) return NULL; - if (switchdev_parent_id_get(dev, &psid)) + if (switchdev_port_attr_get(dev, &attr)) return NULL; if (nhsel > 0) { - if (prev_psid.id_len != psid.id_len) + if (prev_attr.ppid.id_len != attr.ppid.id_len) return NULL; - if (memcmp(prev_psid.id, psid.id, psid.id_len)) + if (memcmp(prev_attr.ppid.id, attr.ppid.id, + attr.ppid.id_len)) return NULL; } - prev_psid = psid; + prev_attr = attr; } return dev; From c4f20321d9680760a291991d77bc5b6d0eb2ed78 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:50 -0700 Subject: [PATCH 05/24] rocker: support prepare-commit transaction model For rocker, support prepare-commit transaction model for setting attributes (and for adding objects). This requires rocker to preallocate memory needed for the commit up front in the prepare phase. Since rtnl_lock is held between prepare-commit, store the allocated memory on a queue hanging off of the rocker_port. Also, in prepare phase, do everything right up to calling into HW. The same code paths are tranversed in the driver for both prepare and commit phases. In some cases, any state modified in the prepare phase must be reverted before returning so the commit phase makes the same decisions. As a consequence of holding rtnl_lock in process context for all attr sets (and obj adds), all memory is GFP_KERNEL allocated and we don't need to busy spin waiting for the device to complete the command. So the bulk of this patch is simplifying the memory allocations to only use GFP_KERNEL and to remove the nowait flag and busy spin loop. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 700 +++++++++++++++++---------- 1 file changed, 451 insertions(+), 249 deletions(-) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 24282991d9fd..fa0fa545c0d1 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -225,6 +225,7 @@ struct rocker_port { struct napi_struct napi_rx; struct rocker_dma_ring_info tx_ring; struct rocker_dma_ring_info rx_ring; + struct list_head trans_mem; }; struct rocker { @@ -325,16 +326,83 @@ static bool rocker_port_is_bridged(struct rocker_port *rocker_port) return !!rocker_port->bridge_dev; } +static void *__rocker_port_mem_alloc(struct rocker_port *rocker_port, + enum switchdev_trans trans, size_t size) +{ + struct list_head *elem = NULL; + + /* If in transaction prepare phase, allocate the memory + * and enqueue it on a per-port list. If in transaction + * commit phase, dequeue the memory from the per-port list + * rather than re-allocating the memory. The idea is the + * driver code paths for prepare and commit are identical + * so the memory allocated in the prepare phase is the + * memory used in the commit phase. + */ + + switch (trans) { + case SWITCHDEV_TRANS_PREPARE: + elem = kzalloc(size + sizeof(*elem), GFP_KERNEL); + if (!elem) + return NULL; + list_add_tail(elem, &rocker_port->trans_mem); + break; + case SWITCHDEV_TRANS_COMMIT: + BUG_ON(list_empty(&rocker_port->trans_mem)); + elem = rocker_port->trans_mem.next; + list_del_init(elem); + break; + case SWITCHDEV_TRANS_NONE: + elem = kzalloc(size + sizeof(*elem), GFP_KERNEL); + if (elem) + INIT_LIST_HEAD(elem); + break; + default: + break; + } + + return elem ? elem + 1 : NULL; +} + +static void *rocker_port_kzalloc(struct rocker_port *rocker_port, + enum switchdev_trans trans, size_t size) +{ + return __rocker_port_mem_alloc(rocker_port, trans, size); +} + +static void *rocker_port_kcalloc(struct rocker_port *rocker_port, + enum switchdev_trans trans, size_t n, + size_t size) +{ + return __rocker_port_mem_alloc(rocker_port, trans, n * size); +} + +static void rocker_port_kfree(struct rocker_port *rocker_port, + enum switchdev_trans trans, const void *mem) +{ + struct list_head *elem; + + /* Frees are ignored if in transaction prepare phase. The + * memory remains on the per-port list until freed in the + * commit phase. + */ + + if (trans == SWITCHDEV_TRANS_PREPARE) + return; + + elem = (struct list_head *)mem - 1; + BUG_ON(!list_empty(elem)); + kfree(elem); +} + struct rocker_wait { wait_queue_head_t wait; bool done; - bool nowait; }; static void rocker_wait_reset(struct rocker_wait *wait) { wait->done = false; - wait->nowait = false; } static void rocker_wait_init(struct rocker_wait *wait) @@ -343,20 +411,23 @@ static void rocker_wait_init(struct rocker_wait *wait) rocker_wait_reset(wait); } -static struct rocker_wait *rocker_wait_create(gfp_t gfp) +static struct rocker_wait *rocker_wait_create(struct rocker_port *rocker_port, + enum switchdev_trans trans) { struct rocker_wait *wait; - wait = kmalloc(sizeof(*wait), gfp); + wait = rocker_port_kzalloc(rocker_port, trans, sizeof(*wait)); if (!wait) return NULL; rocker_wait_init(wait); return wait; } -static void rocker_wait_destroy(struct rocker_wait *work) +static void rocker_wait_destroy(struct rocker_port *rocker_port, + enum switchdev_trans trans, + struct rocker_wait *wait) { - kfree(work); + rocker_port_kfree(rocker_port, trans, wait); } static bool rocker_wait_event_timeout(struct rocker_wait *wait, @@ -1317,12 +1388,7 @@ static irqreturn_t rocker_cmd_irq_handler(int irq, void *dev_id) spin_lock(&rocker->cmd_ring_lock); while ((desc_info = rocker_desc_tail_get(&rocker->cmd_ring))) { wait = rocker_desc_cookie_ptr_get(desc_info); - if (wait->nowait) { - rocker_desc_gen_clear(desc_info); - rocker_wait_destroy(wait); - } else { - rocker_wait_wake_up(wait); - } + rocker_wait_wake_up(wait); credits++; } spin_unlock(&rocker->cmd_ring_lock); @@ -1374,22 +1440,44 @@ static int rocker_event_link_change(struct rocker *rocker, } #define ROCKER_OP_FLAG_REMOVE BIT(0) -#define ROCKER_OP_FLAG_NOWAIT BIT(1) -#define ROCKER_OP_FLAG_LEARNED BIT(2) -#define ROCKER_OP_FLAG_REFRESH BIT(3) +#define ROCKER_OP_FLAG_LEARNED BIT(1) +#define ROCKER_OP_FLAG_REFRESH BIT(2) static int rocker_port_fdb(struct rocker_port *rocker_port, + enum switchdev_trans trans, const unsigned char *addr, __be16 vlan_id, int flags); +struct rocker_mac_vlan_seen_work { + struct work_struct work; + struct rocker_port *rocker_port; + int flags; + unsigned char addr[ETH_ALEN]; + __be16 vlan_id; +}; + +static void rocker_event_mac_vlan_seen_work(struct work_struct *work) +{ + struct rocker_mac_vlan_seen_work *sw = + container_of(work, struct rocker_mac_vlan_seen_work, work); + + rtnl_lock(); + rocker_port_fdb(sw->rocker_port, SWITCHDEV_TRANS_NONE, + sw->addr, sw->vlan_id, sw->flags); + rtnl_unlock(); + + kfree(work); +} + static int rocker_event_mac_vlan_seen(struct rocker *rocker, const struct rocker_tlv *info) { + struct rocker_mac_vlan_seen_work *sw; struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAC_VLAN_MAX + 1]; unsigned int port_number; struct rocker_port *rocker_port; unsigned char *addr; - int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_LEARNED; + int flags = ROCKER_OP_FLAG_LEARNED; __be16 vlan_id; rocker_tlv_parse_nested(attrs, ROCKER_TLV_EVENT_MAC_VLAN_MAX, info); @@ -1411,7 +1499,20 @@ static int rocker_event_mac_vlan_seen(struct rocker *rocker, rocker_port->stp_state != BR_STATE_FORWARDING) return 0; - return rocker_port_fdb(rocker_port, addr, vlan_id, flags); + sw = kmalloc(sizeof(*sw), GFP_ATOMIC); + if (!sw) + return -ENOMEM; + + INIT_WORK(&sw->work, rocker_event_mac_vlan_seen_work); + + sw->rocker_port = rocker_port; + sw->flags = flags; + ether_addr_copy(sw->addr, addr); + sw->vlan_id = vlan_id; + + schedule_work(&sw->work); + + return 0; } static int rocker_event_process(struct rocker *rocker, @@ -1494,41 +1595,44 @@ typedef int (*rocker_cmd_cb_t)(struct rocker *rocker, static int rocker_cmd_exec(struct rocker *rocker, struct rocker_port *rocker_port, + enum switchdev_trans trans, rocker_cmd_cb_t prepare, void *prepare_priv, - rocker_cmd_cb_t process, void *process_priv, - bool nowait) + rocker_cmd_cb_t process, void *process_priv) { struct rocker_desc_info *desc_info; struct rocker_wait *wait; unsigned long flags; int err; - wait = rocker_wait_create(nowait ? GFP_ATOMIC : GFP_KERNEL); + wait = rocker_wait_create(rocker_port, trans); if (!wait) return -ENOMEM; - wait->nowait = nowait; spin_lock_irqsave(&rocker->cmd_ring_lock, flags); + desc_info = rocker_desc_head_get(&rocker->cmd_ring); if (!desc_info) { spin_unlock_irqrestore(&rocker->cmd_ring_lock, flags); err = -EAGAIN; goto out; } + err = prepare(rocker, rocker_port, desc_info, prepare_priv); if (err) { spin_unlock_irqrestore(&rocker->cmd_ring_lock, flags); goto out; } + rocker_desc_cookie_ptr_set(desc_info, wait); - rocker_desc_head_set(rocker, &rocker->cmd_ring, desc_info); + + if (trans != SWITCHDEV_TRANS_PREPARE) + rocker_desc_head_set(rocker, &rocker->cmd_ring, desc_info); + spin_unlock_irqrestore(&rocker->cmd_ring_lock, flags); - if (nowait) - return 0; - - if (!rocker_wait_event_timeout(wait, HZ / 10)) - return -EIO; + if (trans != SWITCHDEV_TRANS_PREPARE) + if (!rocker_wait_event_timeout(wait, HZ / 10)) + return -EIO; err = rocker_desc_err(desc_info); if (err) @@ -1539,7 +1643,7 @@ static int rocker_cmd_exec(struct rocker *rocker, rocker_desc_gen_clear(desc_info); out: - rocker_wait_destroy(wait); + rocker_wait_destroy(rocker_port, trans, wait); return err; } @@ -1762,41 +1866,46 @@ static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port, struct ethtool_cmd *ecmd) { return rocker_cmd_exec(rocker_port->rocker, rocker_port, + SWITCHDEV_TRANS_NONE, rocker_cmd_get_port_settings_prep, NULL, rocker_cmd_get_port_settings_ethtool_proc, - ecmd, false); + ecmd); } static int rocker_cmd_get_port_settings_macaddr(struct rocker_port *rocker_port, unsigned char *macaddr) { return rocker_cmd_exec(rocker_port->rocker, rocker_port, + SWITCHDEV_TRANS_NONE, rocker_cmd_get_port_settings_prep, NULL, rocker_cmd_get_port_settings_macaddr_proc, - macaddr, false); + macaddr); } static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port, struct ethtool_cmd *ecmd) { return rocker_cmd_exec(rocker_port->rocker, rocker_port, + SWITCHDEV_TRANS_NONE, rocker_cmd_set_port_settings_ethtool_prep, - ecmd, NULL, NULL, false); + ecmd, NULL, NULL); } static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port, unsigned char *macaddr) { return rocker_cmd_exec(rocker_port->rocker, rocker_port, + SWITCHDEV_TRANS_NONE, rocker_cmd_set_port_settings_macaddr_prep, - macaddr, NULL, NULL, false); + macaddr, NULL, NULL); } -static int rocker_port_set_learning(struct rocker_port *rocker_port) +static int rocker_port_set_learning(struct rocker_port *rocker_port, + enum switchdev_trans trans) { - return rocker_cmd_exec(rocker_port->rocker, rocker_port, + return rocker_cmd_exec(rocker_port->rocker, rocker_port, trans, rocker_cmd_set_port_learning_prep, - NULL, NULL, NULL, false); + NULL, NULL, NULL); } static int rocker_cmd_flow_tbl_add_ig_port(struct rocker_desc_info *desc_info, @@ -2308,8 +2417,8 @@ rocker_flow_tbl_find(struct rocker *rocker, struct rocker_flow_tbl_entry *match) } static int rocker_flow_tbl_add(struct rocker_port *rocker_port, - struct rocker_flow_tbl_entry *match, - bool nowait) + enum switchdev_trans trans, + struct rocker_flow_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; struct rocker_flow_tbl_entry *found; @@ -2324,8 +2433,9 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port, if (found) { match->cookie = found->cookie; - hash_del(&found->entry); - kfree(found); + if (trans != SWITCHDEV_TRANS_PREPARE) + hash_del(&found->entry); + rocker_port_kfree(rocker_port, trans, found); found = match; found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_MOD; } else { @@ -2334,18 +2444,19 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port, found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_ADD; } - hash_add(rocker->flow_tbl, &found->entry, found->key_crc32); + if (trans != SWITCHDEV_TRANS_PREPARE) + hash_add(rocker->flow_tbl, &found->entry, found->key_crc32); spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags); - return rocker_cmd_exec(rocker, rocker_port, + return rocker_cmd_exec(rocker, rocker_port, trans, rocker_cmd_flow_tbl_add, - found, NULL, NULL, nowait); + found, NULL, NULL); } static int rocker_flow_tbl_del(struct rocker_port *rocker_port, - struct rocker_flow_tbl_entry *match, - bool nowait) + enum switchdev_trans trans, + struct rocker_flow_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; struct rocker_flow_tbl_entry *found; @@ -2360,47 +2471,43 @@ static int rocker_flow_tbl_del(struct rocker_port *rocker_port, found = rocker_flow_tbl_find(rocker, match); if (found) { - hash_del(&found->entry); + if (trans != SWITCHDEV_TRANS_PREPARE) + hash_del(&found->entry); found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_DEL; } spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags); - kfree(match); + rocker_port_kfree(rocker_port, trans, match); if (found) { - err = rocker_cmd_exec(rocker, rocker_port, + err = rocker_cmd_exec(rocker, rocker_port, trans, rocker_cmd_flow_tbl_del, - found, NULL, NULL, nowait); - kfree(found); + found, NULL, NULL); + rocker_port_kfree(rocker_port, trans, found); } return err; } -static gfp_t rocker_op_flags_gfp(int flags) -{ - return flags & ROCKER_OP_FLAG_NOWAIT ? GFP_ATOMIC : GFP_KERNEL; -} - static int rocker_flow_tbl_do(struct rocker_port *rocker_port, - int flags, struct rocker_flow_tbl_entry *entry) + enum switchdev_trans trans, int flags, + struct rocker_flow_tbl_entry *entry) { - bool nowait = flags & ROCKER_OP_FLAG_NOWAIT; - if (flags & ROCKER_OP_FLAG_REMOVE) - return rocker_flow_tbl_del(rocker_port, entry, nowait); + return rocker_flow_tbl_del(rocker_port, trans, entry); else - return rocker_flow_tbl_add(rocker_port, entry, nowait); + return rocker_flow_tbl_add(rocker_port, trans, entry); } static int rocker_flow_tbl_ig_port(struct rocker_port *rocker_port, - int flags, u32 in_pport, u32 in_pport_mask, + enum switchdev_trans trans, int flags, + u32 in_pport, u32 in_pport_mask, enum rocker_of_dpa_table_id goto_tbl) { struct rocker_flow_tbl_entry *entry; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2410,18 +2517,19 @@ static int rocker_flow_tbl_ig_port(struct rocker_port *rocker_port, entry->key.ig_port.in_pport_mask = in_pport_mask; entry->key.ig_port.goto_tbl = goto_tbl; - return rocker_flow_tbl_do(rocker_port, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans, flags, entry); } static int rocker_flow_tbl_vlan(struct rocker_port *rocker_port, - int flags, u32 in_pport, - __be16 vlan_id, __be16 vlan_id_mask, + enum switchdev_trans trans, int flags, + u32 in_pport, __be16 vlan_id, + __be16 vlan_id_mask, enum rocker_of_dpa_table_id goto_tbl, bool untagged, __be16 new_vlan_id) { struct rocker_flow_tbl_entry *entry; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2435,10 +2543,11 @@ static int rocker_flow_tbl_vlan(struct rocker_port *rocker_port, entry->key.vlan.untagged = untagged; entry->key.vlan.new_vlan_id = new_vlan_id; - return rocker_flow_tbl_do(rocker_port, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans, flags, entry); } static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port, + enum switchdev_trans trans, u32 in_pport, u32 in_pport_mask, __be16 eth_type, const u8 *eth_dst, const u8 *eth_dst_mask, __be16 vlan_id, @@ -2447,7 +2556,7 @@ static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port, { struct rocker_flow_tbl_entry *entry; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2471,11 +2580,11 @@ static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port, entry->key.term_mac.vlan_id_mask = vlan_id_mask; entry->key.term_mac.copy_to_cpu = copy_to_cpu; - return rocker_flow_tbl_do(rocker_port, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans, flags, entry); } static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port, - int flags, + enum switchdev_trans trans, int flags, const u8 *eth_dst, const u8 *eth_dst_mask, __be16 vlan_id, u32 tunnel_id, enum rocker_of_dpa_table_id goto_tbl, @@ -2487,7 +2596,7 @@ static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port, bool dflt = !eth_dst || (eth_dst && eth_dst_mask); bool wild = false; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2525,10 +2634,11 @@ static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port, entry->key.bridge.group_id = group_id; entry->key.bridge.copy_to_cpu = copy_to_cpu; - return rocker_flow_tbl_do(rocker_port, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans, flags, entry); } static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port, + enum switchdev_trans trans, __be16 eth_type, __be32 dst, __be32 dst_mask, u32 priority, enum rocker_of_dpa_table_id goto_tbl, @@ -2536,7 +2646,7 @@ static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port, { struct rocker_flow_tbl_entry *entry; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2550,24 +2660,23 @@ static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port, entry->key_len = offsetof(struct rocker_flow_tbl_key, ucast_routing.group_id); - return rocker_flow_tbl_do(rocker_port, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans, flags, entry); } static int rocker_flow_tbl_acl(struct rocker_port *rocker_port, - int flags, u32 in_pport, - u32 in_pport_mask, + enum switchdev_trans trans, int flags, + u32 in_pport, u32 in_pport_mask, const u8 *eth_src, const u8 *eth_src_mask, const u8 *eth_dst, const u8 *eth_dst_mask, - __be16 eth_type, - __be16 vlan_id, __be16 vlan_id_mask, - u8 ip_proto, u8 ip_proto_mask, - u8 ip_tos, u8 ip_tos_mask, + __be16 eth_type, __be16 vlan_id, + __be16 vlan_id_mask, u8 ip_proto, + u8 ip_proto_mask, u8 ip_tos, u8 ip_tos_mask, u32 group_id) { u32 priority; struct rocker_flow_tbl_entry *entry; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2602,7 +2711,7 @@ static int rocker_flow_tbl_acl(struct rocker_port *rocker_port, entry->key.acl.ip_tos_mask = ip_tos_mask; entry->key.acl.group_id = group_id; - return rocker_flow_tbl_do(rocker_port, flags, entry); + return rocker_flow_tbl_do(rocker_port, trans, flags, entry); } static struct rocker_group_tbl_entry * @@ -2620,22 +2729,24 @@ rocker_group_tbl_find(struct rocker *rocker, return NULL; } -static void rocker_group_tbl_entry_free(struct rocker_group_tbl_entry *entry) +static void rocker_group_tbl_entry_free(struct rocker_port *rocker_port, + enum switchdev_trans trans, + struct rocker_group_tbl_entry *entry) { switch (ROCKER_GROUP_TYPE_GET(entry->group_id)) { case ROCKER_OF_DPA_GROUP_TYPE_L2_FLOOD: case ROCKER_OF_DPA_GROUP_TYPE_L2_MCAST: - kfree(entry->group_ids); + rocker_port_kfree(rocker_port, trans, entry->group_ids); break; default: break; } - kfree(entry); + rocker_port_kfree(rocker_port, trans, entry); } static int rocker_group_tbl_add(struct rocker_port *rocker_port, - struct rocker_group_tbl_entry *match, - bool nowait) + enum switchdev_trans trans, + struct rocker_group_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; struct rocker_group_tbl_entry *found; @@ -2646,8 +2757,9 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port, found = rocker_group_tbl_find(rocker, match); if (found) { - hash_del(&found->entry); - rocker_group_tbl_entry_free(found); + if (trans != SWITCHDEV_TRANS_PREPARE) + hash_del(&found->entry); + rocker_group_tbl_entry_free(rocker_port, trans, found); found = match; found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_MOD; } else { @@ -2655,18 +2767,19 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port, found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_ADD; } - hash_add(rocker->group_tbl, &found->entry, found->group_id); + if (trans != SWITCHDEV_TRANS_PREPARE) + hash_add(rocker->group_tbl, &found->entry, found->group_id); spin_unlock_irqrestore(&rocker->group_tbl_lock, flags); - return rocker_cmd_exec(rocker, rocker_port, + return rocker_cmd_exec(rocker, rocker_port, trans, rocker_cmd_group_tbl_add, - found, NULL, NULL, nowait); + found, NULL, NULL); } static int rocker_group_tbl_del(struct rocker_port *rocker_port, - struct rocker_group_tbl_entry *match, - bool nowait) + enum switchdev_trans trans, + struct rocker_group_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; struct rocker_group_tbl_entry *found; @@ -2678,93 +2791,95 @@ static int rocker_group_tbl_del(struct rocker_port *rocker_port, found = rocker_group_tbl_find(rocker, match); if (found) { - hash_del(&found->entry); + if (trans != SWITCHDEV_TRANS_PREPARE) + hash_del(&found->entry); found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_DEL; } spin_unlock_irqrestore(&rocker->group_tbl_lock, flags); - rocker_group_tbl_entry_free(match); + rocker_group_tbl_entry_free(rocker_port, trans, match); if (found) { - err = rocker_cmd_exec(rocker, rocker_port, + err = rocker_cmd_exec(rocker, rocker_port, trans, rocker_cmd_group_tbl_del, - found, NULL, NULL, nowait); - rocker_group_tbl_entry_free(found); + found, NULL, NULL); + rocker_group_tbl_entry_free(rocker_port, trans, found); } return err; } static int rocker_group_tbl_do(struct rocker_port *rocker_port, - int flags, struct rocker_group_tbl_entry *entry) + enum switchdev_trans trans, int flags, + struct rocker_group_tbl_entry *entry) { - bool nowait = flags & ROCKER_OP_FLAG_NOWAIT; - if (flags & ROCKER_OP_FLAG_REMOVE) - return rocker_group_tbl_del(rocker_port, entry, nowait); + return rocker_group_tbl_del(rocker_port, trans, entry); else - return rocker_group_tbl_add(rocker_port, entry, nowait); + return rocker_group_tbl_add(rocker_port, trans, entry); } static int rocker_group_l2_interface(struct rocker_port *rocker_port, - int flags, __be16 vlan_id, - u32 out_pport, int pop_vlan) + enum switchdev_trans trans, int flags, + __be16 vlan_id, u32 out_pport, + int pop_vlan) { struct rocker_group_tbl_entry *entry; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; entry->group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_pport); entry->l2_interface.pop_vlan = pop_vlan; - return rocker_group_tbl_do(rocker_port, flags, entry); + return rocker_group_tbl_do(rocker_port, trans, flags, entry); } static int rocker_group_l2_fan_out(struct rocker_port *rocker_port, + enum switchdev_trans trans, int flags, u8 group_count, u32 *group_ids, u32 group_id) { struct rocker_group_tbl_entry *entry; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; entry->group_id = group_id; entry->group_count = group_count; - entry->group_ids = kcalloc(group_count, sizeof(u32), - rocker_op_flags_gfp(flags)); + entry->group_ids = rocker_port_kcalloc(rocker_port, trans, group_count, + sizeof(u32)); if (!entry->group_ids) { - kfree(entry); + rocker_port_kfree(rocker_port, trans, entry); return -ENOMEM; } memcpy(entry->group_ids, group_ids, group_count * sizeof(u32)); - return rocker_group_tbl_do(rocker_port, flags, entry); + return rocker_group_tbl_do(rocker_port, trans, flags, entry); } static int rocker_group_l2_flood(struct rocker_port *rocker_port, - int flags, __be16 vlan_id, - u8 group_count, u32 *group_ids, - u32 group_id) + enum switchdev_trans trans, int flags, + __be16 vlan_id, u8 group_count, + u32 *group_ids, u32 group_id) { - return rocker_group_l2_fan_out(rocker_port, flags, + return rocker_group_l2_fan_out(rocker_port, trans, flags, group_count, group_ids, group_id); } static int rocker_group_l3_unicast(struct rocker_port *rocker_port, - int flags, u32 index, u8 *src_mac, - u8 *dst_mac, __be16 vlan_id, - bool ttl_check, u32 pport) + enum switchdev_trans trans, int flags, + u32 index, u8 *src_mac, u8 *dst_mac, + __be16 vlan_id, bool ttl_check, u32 pport) { struct rocker_group_tbl_entry *entry; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2777,7 +2892,7 @@ static int rocker_group_l3_unicast(struct rocker_port *rocker_port, entry->l3_unicast.ttl_check = ttl_check; entry->l3_unicast.group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, pport); - return rocker_group_tbl_do(rocker_port, flags, entry); + return rocker_group_tbl_do(rocker_port, trans, flags, entry); } static struct rocker_neigh_tbl_entry * @@ -2802,17 +2917,17 @@ static void _rocker_neigh_add(struct rocker *rocker, be32_to_cpu(entry->ip_addr)); } -static void _rocker_neigh_del(struct rocker *rocker, +static void _rocker_neigh_del(struct rocker_port *rocker_port, + enum switchdev_trans trans, struct rocker_neigh_tbl_entry *entry) { if (--entry->ref_count == 0) { hash_del(&entry->entry); - kfree(entry); + rocker_port_kfree(rocker_port, trans, entry); } } -static void _rocker_neigh_update(struct rocker *rocker, - struct rocker_neigh_tbl_entry *entry, +static void _rocker_neigh_update(struct rocker_neigh_tbl_entry *entry, u8 *eth_dst, bool ttl_check) { if (eth_dst) { @@ -2824,6 +2939,7 @@ static void _rocker_neigh_update(struct rocker *rocker, } static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, + enum switchdev_trans trans, int flags, __be32 ip_addr, u8 *eth_dst) { struct rocker *rocker = rocker_port->rocker; @@ -2840,7 +2956,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, bool removing; int err = 0; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2860,9 +2976,9 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, _rocker_neigh_add(rocker, entry); } else if (removing) { memcpy(entry, found, sizeof(*entry)); - _rocker_neigh_del(rocker, found); + _rocker_neigh_del(rocker_port, trans, found); } else if (updating) { - _rocker_neigh_update(rocker, found, eth_dst, true); + _rocker_neigh_update(found, eth_dst, true); memcpy(entry, found, sizeof(*entry)); } else { err = -ENOENT; @@ -2879,7 +2995,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, * other routes' nexthops. */ - err = rocker_group_l3_unicast(rocker_port, flags, + err = rocker_group_l3_unicast(rocker_port, trans, flags, entry->index, rocker_port->dev->dev_addr, entry->eth_dst, @@ -2895,7 +3011,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, if (adding || removing) { group_id = ROCKER_GROUP_L3_UNICAST(entry->index); - err = rocker_flow_tbl_ucast4_routing(rocker_port, + err = rocker_flow_tbl_ucast4_routing(rocker_port, trans, eth_type, ip_addr, inet_make_mask(32), priority, goto_tbl, @@ -2909,13 +3025,13 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, err_out: if (!adding) - kfree(entry); + rocker_port_kfree(rocker_port, trans, entry); return err; } static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port, - __be32 ip_addr) + enum switchdev_trans trans, __be32 ip_addr) { struct net_device *dev = rocker_port->dev; struct neighbour *n = __ipv4_neigh_lookup(dev, (__force u32)ip_addr); @@ -2932,14 +3048,16 @@ static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port, */ if (n->nud_state & NUD_VALID) - err = rocker_port_ipv4_neigh(rocker_port, 0, ip_addr, n->ha); + err = rocker_port_ipv4_neigh(rocker_port, trans, 0, + ip_addr, n->ha); else neigh_event_send(n, NULL); return err; } -static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags, +static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, + enum switchdev_trans trans, int flags, __be32 ip_addr, u32 *index) { struct rocker *rocker = rocker_port->rocker; @@ -2952,7 +3070,7 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags, bool resolved = true; int err = 0; - entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags)); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return -ENOMEM; @@ -2973,9 +3091,9 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags, *index = entry->index; resolved = false; } else if (removing) { - _rocker_neigh_del(rocker, found); + _rocker_neigh_del(rocker_port, trans, found); } else if (updating) { - _rocker_neigh_update(rocker, found, NULL, false); + _rocker_neigh_update(found, NULL, false); resolved = !is_zero_ether_addr(found->eth_dst); } else { err = -ENOENT; @@ -2984,7 +3102,7 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags, spin_unlock_irqrestore(&rocker->neigh_tbl_lock, lock_flags); if (!adding) - kfree(entry); + rocker_port_kfree(rocker_port, trans, entry); if (err) return err; @@ -2992,12 +3110,13 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags, /* Resolved means neigh ip_addr is resolved to neigh mac. */ if (!resolved) - err = rocker_port_ipv4_resolve(rocker_port, ip_addr); + err = rocker_port_ipv4_resolve(rocker_port, trans, ip_addr); return err; } static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, + enum switchdev_trans trans, int flags, __be16 vlan_id) { struct rocker_port *p; @@ -3008,8 +3127,8 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, int err = 0; int i; - group_ids = kcalloc(rocker->port_count, sizeof(u32), - rocker_op_flags_gfp(flags)); + group_ids = rocker_port_kcalloc(rocker_port, trans, rocker->port_count, + sizeof(u32)); if (!group_ids) return -ENOMEM; @@ -3032,21 +3151,20 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, if (group_count == 0) goto no_ports_in_vlan; - err = rocker_group_l2_flood(rocker_port, flags, vlan_id, - group_count, group_ids, - group_id); + err = rocker_group_l2_flood(rocker_port, trans, flags, vlan_id, + group_count, group_ids, group_id); if (err) netdev_err(rocker_port->dev, "Error (%d) port VLAN l2 flood group\n", err); no_ports_in_vlan: - kfree(group_ids); + rocker_port_kfree(rocker_port, trans, group_ids); return err; } static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port, - int flags, __be16 vlan_id, - bool pop_vlan) + enum switchdev_trans trans, int flags, + __be16 vlan_id, bool pop_vlan) { struct rocker *rocker = rocker_port->rocker; struct rocker_port *p; @@ -3063,9 +3181,8 @@ static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port, if (rocker_port->stp_state == BR_STATE_LEARNING || rocker_port->stp_state == BR_STATE_FORWARDING) { out_pport = rocker_port->pport; - err = rocker_group_l2_interface(rocker_port, flags, - vlan_id, out_pport, - pop_vlan); + err = rocker_group_l2_interface(rocker_port, trans, flags, + vlan_id, out_pport, pop_vlan); if (err) { netdev_err(rocker_port->dev, "Error (%d) port VLAN l2 group for pport %d\n", @@ -3089,9 +3206,8 @@ static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port, return 0; out_pport = 0; - err = rocker_group_l2_interface(rocker_port, flags, - vlan_id, out_pport, - pop_vlan); + err = rocker_group_l2_interface(rocker_port, trans, flags, + vlan_id, out_pport, pop_vlan); if (err) { netdev_err(rocker_port->dev, "Error (%d) port VLAN l2 group for CPU port\n", err); @@ -3147,8 +3263,8 @@ static struct rocker_ctrl { }; static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, - int flags, struct rocker_ctrl *ctrl, - __be16 vlan_id) + enum switchdev_trans trans, int flags, + struct rocker_ctrl *ctrl, __be16 vlan_id) { u32 in_pport = rocker_port->pport; u32 in_pport_mask = 0xffffffff; @@ -3163,7 +3279,7 @@ static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, u32 group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_pport); int err; - err = rocker_flow_tbl_acl(rocker_port, flags, + err = rocker_flow_tbl_acl(rocker_port, trans, flags, in_pport, in_pport_mask, eth_src, eth_src_mask, ctrl->eth_dst, ctrl->eth_dst_mask, @@ -3180,7 +3296,8 @@ static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, } static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port, - int flags, struct rocker_ctrl *ctrl, + enum switchdev_trans trans, int flags, + struct rocker_ctrl *ctrl, __be16 vlan_id) { enum rocker_of_dpa_table_id goto_tbl = @@ -3192,7 +3309,7 @@ static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port, if (!rocker_port_is_bridged(rocker_port)) return 0; - err = rocker_flow_tbl_bridge(rocker_port, flags, + err = rocker_flow_tbl_bridge(rocker_port, trans, flags, ctrl->eth_dst, ctrl->eth_dst_mask, vlan_id, tunnel_id, goto_tbl, group_id, ctrl->copy_to_cpu); @@ -3204,8 +3321,8 @@ static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port, } static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port, - int flags, struct rocker_ctrl *ctrl, - __be16 vlan_id) + enum switchdev_trans trans, int flags, + struct rocker_ctrl *ctrl, __be16 vlan_id) { u32 in_pport_mask = 0xffffffff; __be16 vlan_id_mask = htons(0xffff); @@ -3214,7 +3331,7 @@ static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port, if (ntohs(vlan_id) == 0) vlan_id = rocker_port->internal_vlan_id; - err = rocker_flow_tbl_term_mac(rocker_port, + err = rocker_flow_tbl_term_mac(rocker_port, trans, rocker_port->pport, in_pport_mask, ctrl->eth_type, ctrl->eth_dst, ctrl->eth_dst_mask, vlan_id, @@ -3227,32 +3344,34 @@ static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port, return err; } -static int rocker_port_ctrl_vlan(struct rocker_port *rocker_port, int flags, +static int rocker_port_ctrl_vlan(struct rocker_port *rocker_port, + enum switchdev_trans trans, int flags, struct rocker_ctrl *ctrl, __be16 vlan_id) { if (ctrl->acl) - return rocker_port_ctrl_vlan_acl(rocker_port, flags, + return rocker_port_ctrl_vlan_acl(rocker_port, trans, flags, ctrl, vlan_id); if (ctrl->bridge) - return rocker_port_ctrl_vlan_bridge(rocker_port, flags, + return rocker_port_ctrl_vlan_bridge(rocker_port, trans, flags, ctrl, vlan_id); if (ctrl->term) - return rocker_port_ctrl_vlan_term(rocker_port, flags, + return rocker_port_ctrl_vlan_term(rocker_port, trans, flags, ctrl, vlan_id); return -EOPNOTSUPP; } static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port, - int flags, __be16 vlan_id) + enum switchdev_trans trans, int flags, + __be16 vlan_id) { int err = 0; int i; for (i = 0; i < ROCKER_CTRL_MAX; i++) { if (rocker_port->ctrls[i]) { - err = rocker_port_ctrl_vlan(rocker_port, flags, + err = rocker_port_ctrl_vlan(rocker_port, trans, flags, &rocker_ctrls[i], vlan_id); if (err) return err; @@ -3262,7 +3381,8 @@ static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port, return err; } -static int rocker_port_ctrl(struct rocker_port *rocker_port, int flags, +static int rocker_port_ctrl(struct rocker_port *rocker_port, + enum switchdev_trans trans, int flags, struct rocker_ctrl *ctrl) { u16 vid; @@ -3271,7 +3391,7 @@ static int rocker_port_ctrl(struct rocker_port *rocker_port, int flags, for (vid = 1; vid < VLAN_N_VID; vid++) { if (!test_bit(vid, rocker_port->vlan_bitmap)) continue; - err = rocker_port_ctrl_vlan(rocker_port, flags, + err = rocker_port_ctrl_vlan(rocker_port, trans, flags, ctrl, htons(vid)); if (err) break; @@ -3280,8 +3400,8 @@ static int rocker_port_ctrl(struct rocker_port *rocker_port, int flags, return err; } -static int rocker_port_vlan(struct rocker_port *rocker_port, int flags, - u16 vid) +static int rocker_port_vlan(struct rocker_port *rocker_port, + enum switchdev_trans trans, int flags, u16 vid) { enum rocker_of_dpa_table_id goto_tbl = ROCKER_OF_DPA_TABLE_ID_TERMINATION_MAC; @@ -3303,7 +3423,7 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, int flags, return 0; /* already removed */ if (adding) { - err = rocker_port_ctrl_vlan_add(rocker_port, flags, + err = rocker_port_ctrl_vlan_add(rocker_port, trans, flags, internal_vlan_id); if (err) { netdev_err(rocker_port->dev, @@ -3312,7 +3432,7 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, int flags, } } - err = rocker_port_vlan_l2_groups(rocker_port, flags, + err = rocker_port_vlan_l2_groups(rocker_port, trans, flags, internal_vlan_id, untagged); if (err) { netdev_err(rocker_port->dev, @@ -3320,7 +3440,7 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, int flags, return err; } - err = rocker_port_vlan_flood_group(rocker_port, flags, + err = rocker_port_vlan_flood_group(rocker_port, trans, flags, internal_vlan_id); if (err) { netdev_err(rocker_port->dev, @@ -3328,7 +3448,7 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, int flags, return err; } - err = rocker_flow_tbl_vlan(rocker_port, flags, + err = rocker_flow_tbl_vlan(rocker_port, trans, flags, in_pport, vlan_id, vlan_id_mask, goto_tbl, untagged, internal_vlan_id); if (err) @@ -3338,7 +3458,8 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, int flags, return err; } -static int rocker_port_ig_tbl(struct rocker_port *rocker_port, int flags) +static int rocker_port_ig_tbl(struct rocker_port *rocker_port, + enum switchdev_trans trans, int flags) { enum rocker_of_dpa_table_id goto_tbl; u32 in_pport; @@ -3353,7 +3474,7 @@ static int rocker_port_ig_tbl(struct rocker_port *rocker_port, int flags) in_pport_mask = 0xffff0000; goto_tbl = ROCKER_OF_DPA_TABLE_ID_VLAN; - err = rocker_flow_tbl_ig_port(rocker_port, flags, + err = rocker_flow_tbl_ig_port(rocker_port, trans, flags, in_pport, in_pport_mask, goto_tbl); if (err) @@ -3365,7 +3486,8 @@ static int rocker_port_ig_tbl(struct rocker_port *rocker_port, int flags) struct rocker_fdb_learn_work { struct work_struct work; - struct net_device *dev; + struct rocker_port *rocker_port; + enum switchdev_trans trans; int flags; u8 addr[ETH_ALEN]; u16 vid; @@ -3384,16 +3506,17 @@ static void rocker_port_fdb_learn_work(struct work_struct *work) if (learned && removing) call_switchdev_notifiers(SWITCHDEV_FDB_DEL, - lw->dev, &info.info); + lw->rocker_port->dev, &info.info); else if (learned && !removing) call_switchdev_notifiers(SWITCHDEV_FDB_ADD, - lw->dev, &info.info); + lw->rocker_port->dev, &info.info); - kfree(work); + rocker_port_kfree(lw->rocker_port, lw->trans, work); } static int rocker_port_fdb_learn(struct rocker_port *rocker_port, - int flags, const u8 *addr, __be16 vlan_id) + enum switchdev_trans trans, int flags, + const u8 *addr, __be16 vlan_id) { struct rocker_fdb_learn_work *lw; enum rocker_of_dpa_table_id goto_tbl = @@ -3409,8 +3532,8 @@ static int rocker_port_fdb_learn(struct rocker_port *rocker_port, group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_pport); if (!(flags & ROCKER_OP_FLAG_REFRESH)) { - err = rocker_flow_tbl_bridge(rocker_port, flags, addr, NULL, - vlan_id, tunnel_id, goto_tbl, + err = rocker_flow_tbl_bridge(rocker_port, trans, flags, addr, + NULL, vlan_id, tunnel_id, goto_tbl, group_id, copy_to_cpu); if (err) return err; @@ -3422,18 +3545,22 @@ static int rocker_port_fdb_learn(struct rocker_port *rocker_port, if (!rocker_port_is_bridged(rocker_port)) return 0; - lw = kmalloc(sizeof(*lw), rocker_op_flags_gfp(flags)); + lw = rocker_port_kzalloc(rocker_port, trans, sizeof(*lw)); if (!lw) return -ENOMEM; INIT_WORK(&lw->work, rocker_port_fdb_learn_work); - lw->dev = rocker_port->dev; + lw->rocker_port = rocker_port; + lw->trans = trans; lw->flags = flags; ether_addr_copy(lw->addr, addr); lw->vid = rocker_port_vlan_to_vid(rocker_port, vlan_id); - schedule_work(&lw->work); + if (trans == SWITCHDEV_TRANS_PREPARE) + rocker_port_kfree(rocker_port, trans, lw); + else + schedule_work(&lw->work); return 0; } @@ -3451,6 +3578,7 @@ rocker_fdb_tbl_find(struct rocker *rocker, struct rocker_fdb_tbl_entry *match) } static int rocker_port_fdb(struct rocker_port *rocker_port, + enum switchdev_trans trans, const unsigned char *addr, __be16 vlan_id, int flags) { @@ -3460,7 +3588,7 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, bool removing = (flags & ROCKER_OP_FLAG_REMOVE); unsigned long lock_flags; - fdb = kzalloc(sizeof(*fdb), rocker_op_flags_gfp(flags)); + fdb = rocker_port_kzalloc(rocker_port, trans, sizeof(*fdb)); if (!fdb) return -ENOMEM; @@ -3475,7 +3603,7 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, found = rocker_fdb_tbl_find(rocker, fdb); if (removing && found) { - kfree(fdb); + rocker_port_kfree(rocker_port, trans, fdb); hash_del(&found->entry); } else if (!removing && !found) { hash_add(rocker->fdb_tbl, &fdb->entry, fdb->key_crc32); @@ -3485,22 +3613,23 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, /* Check if adding and already exists, or removing and can't find */ if (!found != !removing) { - kfree(fdb); + rocker_port_kfree(rocker_port, trans, fdb); if (!found && removing) return 0; /* Refreshing existing to update aging timers */ flags |= ROCKER_OP_FLAG_REFRESH; } - return rocker_port_fdb_learn(rocker_port, flags, addr, vlan_id); + return rocker_port_fdb_learn(rocker_port, trans, flags, addr, vlan_id); } -static int rocker_port_fdb_flush(struct rocker_port *rocker_port) +static int rocker_port_fdb_flush(struct rocker_port *rocker_port, + enum switchdev_trans trans) { struct rocker *rocker = rocker_port->rocker; struct rocker_fdb_tbl_entry *found; unsigned long lock_flags; - int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE; + int flags = ROCKER_OP_FLAG_REMOVE; struct hlist_node *tmp; int bkt; int err = 0; @@ -3516,7 +3645,7 @@ static int rocker_port_fdb_flush(struct rocker_port *rocker_port) continue; if (!found->learned) continue; - err = rocker_port_fdb_learn(rocker_port, flags, + err = rocker_port_fdb_learn(rocker_port, trans, flags, found->key.addr, found->key.vlan_id); if (err) @@ -3531,7 +3660,8 @@ err_out: } static int rocker_port_router_mac(struct rocker_port *rocker_port, - int flags, __be16 vlan_id) + enum switchdev_trans trans, int flags, + __be16 vlan_id) { u32 in_pport_mask = 0xffffffff; __be16 eth_type; @@ -3544,7 +3674,7 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port, vlan_id = rocker_port->internal_vlan_id; eth_type = htons(ETH_P_IP); - err = rocker_flow_tbl_term_mac(rocker_port, + err = rocker_flow_tbl_term_mac(rocker_port, trans, rocker_port->pport, in_pport_mask, eth_type, rocker_port->dev->dev_addr, dst_mac_mask, vlan_id, vlan_id_mask, @@ -3553,7 +3683,7 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port, return err; eth_type = htons(ETH_P_IPV6); - err = rocker_flow_tbl_term_mac(rocker_port, + err = rocker_flow_tbl_term_mac(rocker_port, trans, rocker_port->pport, in_pport_mask, eth_type, rocker_port->dev->dev_addr, dst_mac_mask, vlan_id, vlan_id_mask, @@ -3562,13 +3692,14 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port, return err; } -static int rocker_port_fwding(struct rocker_port *rocker_port) +static int rocker_port_fwding(struct rocker_port *rocker_port, + enum switchdev_trans trans) { bool pop_vlan; u32 out_pport; __be16 vlan_id; u16 vid; - int flags = ROCKER_OP_FLAG_NOWAIT; + int flags = 0; int err; /* Port will be forwarding-enabled if its STP state is LEARNING @@ -3588,9 +3719,8 @@ static int rocker_port_fwding(struct rocker_port *rocker_port) continue; vlan_id = htons(vid); pop_vlan = rocker_vlan_id_is_internal(vlan_id); - err = rocker_group_l2_interface(rocker_port, flags, - vlan_id, out_pport, - pop_vlan); + err = rocker_group_l2_interface(rocker_port, trans, flags, + vlan_id, out_pport, pop_vlan); if (err) { netdev_err(rocker_port->dev, "Error (%d) port VLAN l2 group for pport %d\n", @@ -3602,13 +3732,21 @@ static int rocker_port_fwding(struct rocker_port *rocker_port) return 0; } -static int rocker_port_stp_update(struct rocker_port *rocker_port, u8 state) +static int rocker_port_stp_update(struct rocker_port *rocker_port, + enum switchdev_trans trans, u8 state) { bool want[ROCKER_CTRL_MAX] = { 0, }; + bool prev_ctrls[ROCKER_CTRL_MAX]; + u8 prev_state; int flags; int err; int i; + if (trans == SWITCHDEV_TRANS_PREPARE) { + memcpy(prev_ctrls, rocker_port->ctrls, sizeof(prev_ctrls)); + prev_state = rocker_port->stp_state; + } + if (rocker_port->stp_state == state) return 0; @@ -3636,41 +3774,50 @@ static int rocker_port_stp_update(struct rocker_port *rocker_port, u8 state) for (i = 0; i < ROCKER_CTRL_MAX; i++) { if (want[i] != rocker_port->ctrls[i]) { - flags = ROCKER_OP_FLAG_NOWAIT | - (want[i] ? 0 : ROCKER_OP_FLAG_REMOVE); - err = rocker_port_ctrl(rocker_port, flags, + flags = (want[i] ? 0 : ROCKER_OP_FLAG_REMOVE); + err = rocker_port_ctrl(rocker_port, trans, flags, &rocker_ctrls[i]); if (err) - return err; + goto err_out; rocker_port->ctrls[i] = want[i]; } } - err = rocker_port_fdb_flush(rocker_port); + err = rocker_port_fdb_flush(rocker_port, trans); if (err) - return err; + goto err_out; - return rocker_port_fwding(rocker_port); + err = rocker_port_fwding(rocker_port, trans); + +err_out: + if (trans == SWITCHDEV_TRANS_PREPARE) { + memcpy(rocker_port->ctrls, prev_ctrls, sizeof(prev_ctrls)); + rocker_port->stp_state = prev_state; + } + + return err; } -static int rocker_port_fwd_enable(struct rocker_port *rocker_port) +static int rocker_port_fwd_enable(struct rocker_port *rocker_port, + enum switchdev_trans trans) { if (rocker_port_is_bridged(rocker_port)) /* bridge STP will enable port */ return 0; /* port is not bridged, so simulate going to FORWARDING state */ - return rocker_port_stp_update(rocker_port, BR_STATE_FORWARDING); + return rocker_port_stp_update(rocker_port, trans, BR_STATE_FORWARDING); } -static int rocker_port_fwd_disable(struct rocker_port *rocker_port) +static int rocker_port_fwd_disable(struct rocker_port *rocker_port, + enum switchdev_trans trans) { if (rocker_port_is_bridged(rocker_port)) /* bridge STP will disable port */ return 0; /* port is not bridged, so simulate going to DISABLED state */ - return rocker_port_stp_update(rocker_port, BR_STATE_DISABLED); + return rocker_port_stp_update(rocker_port, trans, BR_STATE_DISABLED); } static struct rocker_internal_vlan_tbl_entry * @@ -3688,6 +3835,7 @@ rocker_internal_vlan_tbl_find(struct rocker *rocker, int ifindex) } static __be16 rocker_port_internal_vlan_id_get(struct rocker_port *rocker_port, + enum switchdev_trans trans, int ifindex) { struct rocker *rocker = rocker_port->rocker; @@ -3696,7 +3844,7 @@ static __be16 rocker_port_internal_vlan_id_get(struct rocker_port *rocker_port, unsigned long lock_flags; int i; - entry = kzalloc(sizeof(*entry), GFP_KERNEL); + entry = rocker_port_kzalloc(rocker_port, trans, sizeof(*entry)); if (!entry) return 0; @@ -3706,7 +3854,7 @@ static __be16 rocker_port_internal_vlan_id_get(struct rocker_port *rocker_port, found = rocker_internal_vlan_tbl_find(rocker, ifindex); if (found) { - kfree(entry); + rocker_port_kfree(rocker_port, trans, entry); goto found; } @@ -3730,6 +3878,7 @@ found: } static void rocker_port_internal_vlan_id_put(struct rocker_port *rocker_port, + enum switchdev_trans trans, int ifindex) { struct rocker *rocker = rocker_port->rocker; @@ -3751,14 +3900,15 @@ static void rocker_port_internal_vlan_id_put(struct rocker_port *rocker_port, bit = ntohs(found->vlan_id) - ROCKER_INTERNAL_VLAN_ID_BASE; clear_bit(bit, rocker->internal_vlan_bitmap); hash_del(&found->entry); - kfree(found); + rocker_port_kfree(rocker_port, trans, found); } not_found: spin_unlock_irqrestore(&rocker->internal_vlan_tbl_lock, lock_flags); } -static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, __be32 dst, +static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, + enum switchdev_trans trans, __be32 dst, int dst_len, struct fib_info *fi, u32 tb_id, int flags) { @@ -3782,7 +3932,7 @@ static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, __be32 dst, has_gw = !!nh->nh_gw; if (has_gw && nh_on_port) { - err = rocker_port_ipv4_nh(rocker_port, flags, + err = rocker_port_ipv4_nh(rocker_port, trans, flags, nh->nh_gw, &index); if (err) return err; @@ -3793,7 +3943,7 @@ static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, __be32 dst, group_id = ROCKER_GROUP_L2_INTERFACE(internal_vlan_id, 0); } - err = rocker_flow_tbl_ucast4_routing(rocker_port, eth_type, dst, + err = rocker_flow_tbl_ucast4_routing(rocker_port, trans, eth_type, dst, dst_mask, priority, goto_tbl, group_id, flags); if (err) @@ -3832,7 +3982,7 @@ static int rocker_port_open(struct net_device *dev) goto err_request_rx_irq; } - err = rocker_port_fwd_enable(rocker_port); + err = rocker_port_fwd_enable(rocker_port, SWITCHDEV_TRANS_NONE); if (err) goto err_fwd_enable; @@ -3859,7 +4009,7 @@ static int rocker_port_stop(struct net_device *dev) rocker_port_set_enable(rocker_port, false); napi_disable(&rocker_port->napi_rx); napi_disable(&rocker_port->napi_tx); - rocker_port_fwd_disable(rocker_port); + rocker_port_fwd_disable(rocker_port, SWITCHDEV_TRANS_NONE); free_irq(rocker_msix_rx_vector(rocker_port), rocker_port); free_irq(rocker_msix_tx_vector(rocker_port), rocker_port); rocker_port_dma_rings_fini(rocker_port); @@ -4012,11 +4162,12 @@ static int rocker_port_vlan_rx_add_vid(struct net_device *dev, struct rocker_port *rocker_port = netdev_priv(dev); int err; - err = rocker_port_vlan(rocker_port, 0, vid); + err = rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, 0, vid); if (err) return err; - return rocker_port_router_mac(rocker_port, 0, htons(vid)); + return rocker_port_router_mac(rocker_port, SWITCHDEV_TRANS_NONE, + 0, htons(vid)); } static int rocker_port_vlan_rx_kill_vid(struct net_device *dev, @@ -4025,12 +4176,13 @@ static int rocker_port_vlan_rx_kill_vid(struct net_device *dev, struct rocker_port *rocker_port = netdev_priv(dev); int err; - err = rocker_port_router_mac(rocker_port, ROCKER_OP_FLAG_REMOVE, - htons(vid)); + err = rocker_port_router_mac(rocker_port, SWITCHDEV_TRANS_NONE, + ROCKER_OP_FLAG_REMOVE, htons(vid)); if (err) return err; - return rocker_port_vlan(rocker_port, ROCKER_OP_FLAG_REMOVE, vid); + return rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, + ROCKER_OP_FLAG_REMOVE, vid); } static int rocker_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], @@ -4045,7 +4197,8 @@ static int rocker_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], if (!rocker_port_is_bridged(rocker_port)) return -EINVAL; - return rocker_port_fdb(rocker_port, addr, vlan_id, flags); + return rocker_port_fdb(rocker_port, SWITCHDEV_TRANS_NONE, + addr, vlan_id, flags); } static int rocker_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], @@ -4059,7 +4212,8 @@ static int rocker_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], if (!rocker_port_is_bridged(rocker_port)) return -EINVAL; - return rocker_port_fdb(rocker_port, addr, vlan_id, flags); + return rocker_port_fdb(rocker_port, SWITCHDEV_TRANS_NONE, + addr, vlan_id, flags); } static int rocker_fdb_fill_info(struct sk_buff *skb, @@ -4155,7 +4309,8 @@ static int rocker_port_bridge_setlink(struct net_device *dev, rocker_port->brport_flags |= BR_LEARNING; else rocker_port->brport_flags &= ~BR_LEARNING; - err = rocker_port_set_learning(rocker_port); + err = rocker_port_set_learning(rocker_port, + SWITCHDEV_TRANS_NONE); if (err) return err; } @@ -4195,9 +4350,10 @@ static int rocker_port_get_phys_port_name(struct net_device *dev, int err; err = rocker_cmd_exec(rocker_port->rocker, rocker_port, + SWITCHDEV_TRANS_NONE, rocker_cmd_get_port_settings_prep, NULL, rocker_cmd_get_port_settings_phys_name_proc, - &name, false); + &name); return err ? -EOPNOTSUPP : 0; } @@ -4244,7 +4400,43 @@ static int rocker_port_switchdev_port_stp_update(struct net_device *dev, { struct rocker_port *rocker_port = netdev_priv(dev); - return rocker_port_stp_update(rocker_port, state); + return rocker_port_stp_update(rocker_port, SWITCHDEV_TRANS_NONE, state); +} + +static void rocker_port_trans_abort(struct rocker_port *rocker_port) +{ + struct list_head *mem, *tmp; + + list_for_each_safe(mem, tmp, &rocker_port->trans_mem) { + list_del(mem); + kfree(mem); + } +} + +static int rocker_port_attr_set(struct net_device *dev, + struct switchdev_attr *attr) +{ + struct rocker_port *rocker_port = netdev_priv(dev); + int err = 0; + + switch (attr->trans) { + case SWITCHDEV_TRANS_PREPARE: + BUG_ON(!list_empty(&rocker_port->trans_mem)); + break; + case SWITCHDEV_TRANS_ABORT: + rocker_port_trans_abort(rocker_port); + return 0; + default: + break; + } + + switch (attr->id) { + default: + err = -EOPNOTSUPP; + break; + } + + return err; } static int rocker_port_switchdev_fib_ipv4_add(struct net_device *dev, @@ -4256,8 +4448,8 @@ static int rocker_port_switchdev_fib_ipv4_add(struct net_device *dev, struct rocker_port *rocker_port = netdev_priv(dev); int flags = 0; - return rocker_port_fib_ipv4(rocker_port, dst, dst_len, - fi, tb_id, flags); + return rocker_port_fib_ipv4(rocker_port, SWITCHDEV_TRANS_NONE, + dst, dst_len, fi, tb_id, flags); } static int rocker_port_switchdev_fib_ipv4_del(struct net_device *dev, @@ -4268,8 +4460,8 @@ static int rocker_port_switchdev_fib_ipv4_del(struct net_device *dev, struct rocker_port *rocker_port = netdev_priv(dev); int flags = ROCKER_OP_FLAG_REMOVE; - return rocker_port_fib_ipv4(rocker_port, dst, dst_len, - fi, tb_id, flags); + return rocker_port_fib_ipv4(rocker_port, SWITCHDEV_TRANS_NONE, + dst, dst_len, fi, tb_id, flags); } static const struct switchdev_ops rocker_port_switchdev_ops = { @@ -4407,9 +4599,10 @@ static int rocker_cmd_get_port_stats_ethtool(struct rocker_port *rocker_port, void *priv) { return rocker_cmd_exec(rocker_port->rocker, rocker_port, + SWITCHDEV_TRANS_NONE, rocker_cmd_get_port_stats_prep, NULL, rocker_cmd_get_port_stats_ethtool_proc, - priv, false); + priv); } static void rocker_port_get_stats(struct net_device *dev, @@ -4591,7 +4784,8 @@ static void rocker_remove_ports(struct rocker *rocker) for (i = 0; i < rocker->port_count; i++) { rocker_port = rocker->ports[i]; - rocker_port_ig_tbl(rocker_port, ROCKER_OP_FLAG_REMOVE); + rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE, + ROCKER_OP_FLAG_REMOVE); unregister_netdev(rocker_port->dev); } kfree(rocker->ports); @@ -4627,6 +4821,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) rocker_port->port_number = port_number; rocker_port->pport = port_number + 1; rocker_port->brport_flags = BR_LEARNING | BR_LEARNING_SYNC; + INIT_LIST_HEAD(&rocker_port->trans_mem); rocker_port_dev_addr_init(rocker, rocker_port); dev->netdev_ops = &rocker_port_netdev_ops; @@ -4649,11 +4844,13 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) } rocker->ports[port_number] = rocker_port; - rocker_port_set_learning(rocker_port); + rocker_port_set_learning(rocker_port, SWITCHDEV_TRANS_NONE); rocker_port->internal_vlan_id = - rocker_port_internal_vlan_id_get(rocker_port, dev->ifindex); - err = rocker_port_ig_tbl(rocker_port, 0); + rocker_port_internal_vlan_id_get(rocker_port, + SWITCHDEV_TRANS_NONE, + dev->ifindex); + err = rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE, 0); if (err) { dev_err(&pdev->dev, "install ig port table failed\n"); goto err_port_ig_tbl; @@ -4900,43 +5097,47 @@ static int rocker_port_bridge_join(struct rocker_port *rocker_port, { int err; - rocker_port_internal_vlan_id_put(rocker_port, + rocker_port_internal_vlan_id_put(rocker_port, SWITCHDEV_TRANS_NONE, rocker_port->dev->ifindex); rocker_port->bridge_dev = bridge; /* Use bridge internal VLAN ID for untagged pkts */ - err = rocker_port_vlan(rocker_port, ROCKER_OP_FLAG_REMOVE, 0); + err = rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, + ROCKER_OP_FLAG_REMOVE, 0); if (err) return err; rocker_port->internal_vlan_id = rocker_port_internal_vlan_id_get(rocker_port, + SWITCHDEV_TRANS_NONE, bridge->ifindex); - return rocker_port_vlan(rocker_port, 0, 0); + return rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, 0, 0); } static int rocker_port_bridge_leave(struct rocker_port *rocker_port) { int err; - rocker_port_internal_vlan_id_put(rocker_port, + rocker_port_internal_vlan_id_put(rocker_port, SWITCHDEV_TRANS_NONE, rocker_port->bridge_dev->ifindex); rocker_port->bridge_dev = NULL; /* Use port internal VLAN ID for untagged pkts */ - err = rocker_port_vlan(rocker_port, ROCKER_OP_FLAG_REMOVE, 0); + err = rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, + ROCKER_OP_FLAG_REMOVE, 0); if (err) return err; rocker_port->internal_vlan_id = rocker_port_internal_vlan_id_get(rocker_port, + SWITCHDEV_TRANS_NONE, rocker_port->dev->ifindex); - err = rocker_port_vlan(rocker_port, 0, 0); + err = rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, 0, 0); if (err) return err; if (rocker_port->dev->flags & IFF_UP) - err = rocker_port_fwd_enable(rocker_port); + err = rocker_port_fwd_enable(rocker_port, SWITCHDEV_TRANS_NONE); return err; } @@ -4998,7 +5199,8 @@ static int rocker_neigh_update(struct net_device *dev, struct neighbour *n) int flags = (n->nud_state & NUD_VALID) ? 0 : ROCKER_OP_FLAG_REMOVE; __be32 ip_addr = *(__be32 *)n->primary_key; - return rocker_port_ipv4_neigh(rocker_port, flags, ip_addr, n->ha); + return rocker_port_ipv4_neigh(rocker_port, SWITCHDEV_TRANS_NONE, + flags, ip_addr, n->ha); } static int rocker_netevent_event(struct notifier_block *unused, From 3563606258cf3b8f02eabddb1cb45a94c44d9611 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:51 -0700 Subject: [PATCH 06/24] switchdev: convert STP update to switchdev attr set STP update is just a settable port attribute, so convert switchdev_port_stp_update to an attr set. For DSA, the prepare phase is skipped and STP updates are only done in the commit phase. This is because currently the DSA drivers don't need to allocate any memory for STP updates and the STP update will not fail to HW (unless something horrible goes wrong on the MDIO bus, in which case the prepare phase wouldn't have been able to predict anyway). Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 14 +++++--------- include/net/switchdev.h | 13 ++----------- net/bridge/br_stp.c | 6 +++++- net/dsa/slave.c | 20 +++++++++++++++++++- net/switchdev/switchdev.c | 28 ---------------------------- 5 files changed, 31 insertions(+), 50 deletions(-) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index fa0fa545c0d1..36827d39a70a 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4395,14 +4395,6 @@ static int rocker_port_attr_get(struct net_device *dev, return 0; } -static int rocker_port_switchdev_port_stp_update(struct net_device *dev, - u8 state) -{ - struct rocker_port *rocker_port = netdev_priv(dev); - - return rocker_port_stp_update(rocker_port, SWITCHDEV_TRANS_NONE, state); -} - static void rocker_port_trans_abort(struct rocker_port *rocker_port) { struct list_head *mem, *tmp; @@ -4431,6 +4423,10 @@ static int rocker_port_attr_set(struct net_device *dev, } switch (attr->id) { + case SWITCHDEV_ATTR_PORT_STP_STATE: + err = rocker_port_stp_update(rocker_port, attr->trans, + attr->stp_state); + break; default: err = -EOPNOTSUPP; break; @@ -4466,7 +4462,7 @@ static int rocker_port_switchdev_fib_ipv4_del(struct net_device *dev, static const struct switchdev_ops rocker_port_switchdev_ops = { .switchdev_port_attr_get = rocker_port_attr_get, - .switchdev_port_stp_update = rocker_port_switchdev_port_stp_update, + .switchdev_port_attr_set = rocker_port_attr_set, .switchdev_fib_ipv4_add = rocker_port_switchdev_fib_ipv4_add, .switchdev_fib_ipv4_del = rocker_port_switchdev_fib_ipv4_del, }; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 93316e7ab372..aec5e49661a2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -26,6 +26,7 @@ enum switchdev_trans { enum switchdev_attr_id { SWITCHDEV_ATTR_UNDEFINED, SWITCHDEV_ATTR_PORT_PARENT_ID, + SWITCHDEV_ATTR_PORT_STP_STATE, }; struct switchdev_attr { @@ -34,6 +35,7 @@ struct switchdev_attr { u32 flags; union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ + u8 stp_state; /* PORT_STP_STATE */ }; }; @@ -46,9 +48,6 @@ struct fib_info; * * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). * - * @switchdev_port_stp_update: Called to notify switch device port of bridge - * port STP state change. - * * @switchdev_fib_ipv4_add: Called to add/modify IPv4 route to switch device. * * @switchdev_fib_ipv4_del: Called to delete IPv4 route from switch device. @@ -58,7 +57,6 @@ struct switchdev_ops { struct switchdev_attr *attr); int (*switchdev_port_attr_set)(struct net_device *dev, struct switchdev_attr *attr); - int (*switchdev_port_stp_update)(struct net_device *dev, u8 state); int (*switchdev_fib_ipv4_add)(struct net_device *dev, __be32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 nlflags, @@ -95,7 +93,6 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); -int switchdev_port_stp_update(struct net_device *dev, u8 state); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, @@ -128,12 +125,6 @@ static inline int switchdev_port_attr_set(struct net_device *dev, return -EOPNOTSUPP; } -static inline int switchdev_port_stp_update(struct net_device *dev, - u8 state) -{ - return -EOPNOTSUPP; -} - static inline int register_switchdev_notifier(struct notifier_block *nb) { return 0; diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 28e3f4bc01e0..b9300da31565 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -39,10 +39,14 @@ void br_log_state(const struct net_bridge_port *p) void br_set_state(struct net_bridge_port *p, unsigned int state) { + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_STP_STATE, + .stp_state = state, + }; int err; p->state = state; - err = switchdev_port_stp_update(p->dev, state); + err = switchdev_port_attr_set(p->dev, &attr); if (err && err != -EOPNOTSUPP) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index de705b674ac9..3fb5210e318c 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -345,6 +345,24 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state) return ret; } +static int dsa_slave_port_attr_set(struct net_device *dev, + struct switchdev_attr *attr) +{ + int ret = 0; + + switch (attr->id) { + case SWITCHDEV_ATTR_PORT_STP_STATE: + if (attr->trans == SWITCHDEV_TRANS_COMMIT) + ret = dsa_slave_stp_update(dev, attr->stp_state); + break; + default: + ret = -EOPNOTSUPP; + break; + } + + return ret; +} + static int dsa_slave_bridge_port_join(struct net_device *dev, struct net_device *br) { @@ -683,7 +701,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = { static const struct switchdev_ops dsa_slave_switchdev_ops = { .switchdev_port_attr_get = dsa_slave_port_attr_get, - .switchdev_port_stp_update = dsa_slave_stp_update, + .switchdev_port_attr_set = dsa_slave_port_attr_set, }; static void dsa_slave_adjust_link(struct net_device *dev) diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 117fd0797abd..a3c359004902 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -187,34 +187,6 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) } EXPORT_SYMBOL_GPL(switchdev_port_attr_set); -/** - * switchdev_port_stp_update - Notify switch device port of STP - * state change - * @dev: port device - * @state: port STP state - * - * Notify switch device port of bridge port STP state change. - */ -int switchdev_port_stp_update(struct net_device *dev, u8 state) -{ - const struct switchdev_ops *ops = dev->switchdev_ops; - struct net_device *lower_dev; - struct list_head *iter; - int err = -EOPNOTSUPP; - - if (ops && ops->switchdev_port_stp_update) - return ops->switchdev_port_stp_update(dev, state); - - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_stp_update(lower_dev, state); - if (err && err != -EOPNOTSUPP) - return err; - } - - return err; -} -EXPORT_SYMBOL_GPL(switchdev_port_stp_update); - static DEFINE_MUTEX(switchdev_mutex); static RAW_NOTIFIER_HEAD(switchdev_notif_chain); From 491d0f1533ac750260406dbf84cdad44fd3d8a29 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:52 -0700 Subject: [PATCH 07/24] switchdev: introduce switchdev add/del obj ops Like switchdev attr get/set, add new switchdev obj add/del. switchdev objs will be things like VLANs or FIB entries, so add/del fits better for objects than get/set used for attributes. Use same two-phase prepare-commit transaction model as in attr set. Signed-off-by: Scott Feldman Acked-by: Sridhar Samudrala Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 31 +++++++++++ net/switchdev/switchdev.c | 107 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 138 insertions(+) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index aec5e49661a2..4f43300df72c 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -41,6 +41,15 @@ struct switchdev_attr { struct fib_info; +enum switchdev_obj_id { + SWITCHDEV_OBJ_UNDEFINED, +}; + +struct switchdev_obj { + enum switchdev_obj_id id; + enum switchdev_trans trans; +}; + /** * struct switchdev_ops - switchdev operations * @@ -48,6 +57,10 @@ struct fib_info; * * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). * + * @switchdev_port_obj_add: Add an object to port (see switchdev_obj). + * + * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj). + * * @switchdev_fib_ipv4_add: Called to add/modify IPv4 route to switch device. * * @switchdev_fib_ipv4_del: Called to delete IPv4 route from switch device. @@ -57,6 +70,10 @@ struct switchdev_ops { struct switchdev_attr *attr); int (*switchdev_port_attr_set)(struct net_device *dev, struct switchdev_attr *attr); + int (*switchdev_port_obj_add)(struct net_device *dev, + struct switchdev_obj *obj); + int (*switchdev_port_obj_del)(struct net_device *dev, + struct switchdev_obj *obj); int (*switchdev_fib_ipv4_add)(struct net_device *dev, __be32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 nlflags, @@ -93,6 +110,8 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); +int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj); +int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, @@ -125,6 +144,18 @@ static inline int switchdev_port_attr_set(struct net_device *dev, return -EOPNOTSUPP; } +static inline int switchdev_port_obj_add(struct net_device *dev, + struct switchdev_obj *obj) +{ + return -EOPNOTSUPP; +} + +static inline int switchdev_port_obj_del(struct net_device *dev, + struct switchdev_obj *obj) +{ + return -EOPNOTSUPP; +} + static inline int register_switchdev_notifier(struct notifier_block *nb) { return 0; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index a3c359004902..3d4d99a70b80 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -187,6 +187,113 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) } EXPORT_SYMBOL_GPL(switchdev_port_attr_set); +int __switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) +{ + const struct switchdev_ops *ops = dev->switchdev_ops; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (ops && ops->switchdev_port_obj_add) + return ops->switchdev_port_obj_add(dev, obj); + + /* Switch device port(s) may be stacked under + * bond/team/vlan dev, so recurse down to add object on + * each port. + */ + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = __switchdev_port_obj_add(lower_dev, obj); + if (err) + break; + } + + return err; +} + +/** + * switchdev_port_obj_add - Add port object + * + * @dev: port device + * @obj: object to add + * + * Use a 2-phase prepare-commit transaction model to ensure + * system is not left in a partially updated state due to + * failure from driver/device. + * + * rtnl_lock must be held. + */ +int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) +{ + int err; + + ASSERT_RTNL(); + + /* Phase I: prepare for obj add. Driver/device should fail + * here if there are going to be issues in the commit phase, + * such as lack of resources or support. The driver/device + * should reserve resources needed for the commit phase here, + * but should not commit the obj. + */ + + obj->trans = SWITCHDEV_TRANS_PREPARE; + err = __switchdev_port_obj_add(dev, obj); + if (err) { + /* Prepare phase failed: abort the transaction. Any + * resources reserved in the prepare phase are + * released. + */ + + obj->trans = SWITCHDEV_TRANS_ABORT; + __switchdev_port_obj_add(dev, obj); + + return err; + } + + /* Phase II: commit obj add. This cannot fail as a fault + * of driver/device. If it does, it's a bug in the driver/device + * because the driver said everythings was OK in phase I. + */ + + obj->trans = SWITCHDEV_TRANS_COMMIT; + err = __switchdev_port_obj_add(dev, obj); + WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); + + return err; +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_add); + +/** + * switchdev_port_obj_del - Delete port object + * + * @dev: port device + * @obj: object to delete + */ +int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj) +{ + const struct switchdev_ops *ops = dev->switchdev_ops; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (ops && ops->switchdev_port_obj_del) + return ops->switchdev_port_obj_del(dev, obj); + + /* Switch device port(s) may be stacked under + * bond/team/vlan dev, so recurse down to delete object on + * each port. + */ + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = switchdev_port_obj_del(lower_dev, obj); + if (err) + break; + } + + return err; +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_del); + static DEFINE_MUTEX(switchdev_mutex); static RAW_NOTIFIER_HEAD(switchdev_notif_chain); From 6fc3016da7c1587aa59e71f8c4dbc4cf1343eab2 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:53 -0700 Subject: [PATCH 08/24] switchdev: add port vlan obj VLAN obj has flags (PVID and untagged) as well as start and end vid ranges. The switchdev driver can optimize programing the device using the ranges. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 4f43300df72c..e598c2d45786 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -43,11 +43,19 @@ struct fib_info; enum switchdev_obj_id { SWITCHDEV_OBJ_UNDEFINED, + SWITCHDEV_OBJ_PORT_VLAN, }; struct switchdev_obj { enum switchdev_obj_id id; enum switchdev_trans trans; + union { + struct switchdev_obj_vlan { /* PORT_VLAN */ + u16 flags; + u16 vid_start; + u16 vid_end; + } vlan; + }; }; /** From 9228ad26abeec99caf139e6d641e0199c95fd677 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:54 -0700 Subject: [PATCH 09/24] rocker: use switchdev add/del obj for bridge port vlans Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 130 +++++++++++++++++++++++++-- 1 file changed, 123 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 36827d39a70a..84084806231a 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -3415,20 +3415,22 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, internal_vlan_id = rocker_port_vid_to_vlan(rocker_port, vid, &untagged); - if (adding && test_and_set_bit(ntohs(internal_vlan_id), - rocker_port->vlan_bitmap)) + if (adding && test_bit(ntohs(internal_vlan_id), + rocker_port->vlan_bitmap)) return 0; /* already added */ - else if (!adding && !test_and_clear_bit(ntohs(internal_vlan_id), - rocker_port->vlan_bitmap)) + else if (!adding && !test_bit(ntohs(internal_vlan_id), + rocker_port->vlan_bitmap)) return 0; /* already removed */ + change_bit(ntohs(internal_vlan_id), rocker_port->vlan_bitmap); + if (adding) { err = rocker_port_ctrl_vlan_add(rocker_port, trans, flags, internal_vlan_id); if (err) { netdev_err(rocker_port->dev, "Error (%d) port ctrl vlan add\n", err); - return err; + goto err_out; } } @@ -3437,7 +3439,7 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, if (err) { netdev_err(rocker_port->dev, "Error (%d) port VLAN l2 groups\n", err); - return err; + goto err_out; } err = rocker_port_vlan_flood_group(rocker_port, trans, flags, @@ -3445,7 +3447,7 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, if (err) { netdev_err(rocker_port->dev, "Error (%d) port VLAN l2 flood group\n", err); - return err; + goto err_out; } err = rocker_flow_tbl_vlan(rocker_port, trans, flags, @@ -3455,6 +3457,10 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, netdev_err(rocker_port->dev, "Error (%d) port VLAN table\n", err); +err_out: + if (trans == SWITCHDEV_TRANS_PREPARE) + change_bit(ntohs(internal_vlan_id), rocker_port->vlan_bitmap); + return err; } @@ -4435,6 +4441,114 @@ static int rocker_port_attr_set(struct net_device *dev, return err; } +static int rocker_port_vlan_add(struct rocker_port *rocker_port, + enum switchdev_trans trans, u16 vid, u16 flags) +{ + int err; + + /* XXX deal with flags for PVID and untagged */ + + err = rocker_port_vlan(rocker_port, trans, 0, vid); + if (err) + return err; + + return rocker_port_router_mac(rocker_port, trans, 0, htons(vid)); +} + +static int rocker_port_vlans_add(struct rocker_port *rocker_port, + enum switchdev_trans trans, + struct switchdev_obj_vlan *vlan) +{ + u16 vid; + int err; + + for (vid = vlan->vid_start; vid <= vlan->vid_end; vid++) { + err = rocker_port_vlan_add(rocker_port, trans, + vid, vlan->flags); + if (err) + return err; + } + + return 0; +} + +static int rocker_port_obj_add(struct net_device *dev, + struct switchdev_obj *obj) +{ + struct rocker_port *rocker_port = netdev_priv(dev); + int err = 0; + + switch (obj->trans) { + case SWITCHDEV_TRANS_PREPARE: + BUG_ON(!list_empty(&rocker_port->trans_mem)); + break; + case SWITCHDEV_TRANS_ABORT: + rocker_port_trans_abort(rocker_port); + return 0; + default: + break; + } + + switch (obj->id) { + case SWITCHDEV_OBJ_PORT_VLAN: + err = rocker_port_vlans_add(rocker_port, obj->trans, + &obj->vlan); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int rocker_port_vlan_del(struct rocker_port *rocker_port, + u16 vid, u16 flags) +{ + int err; + + err = rocker_port_router_mac(rocker_port, SWITCHDEV_TRANS_NONE, + ROCKER_OP_FLAG_REMOVE, htons(vid)); + if (err) + return err; + + return rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, + ROCKER_OP_FLAG_REMOVE, vid); +} + +static int rocker_port_vlans_del(struct rocker_port *rocker_port, + struct switchdev_obj_vlan *vlan) +{ + u16 vid; + int err; + + for (vid = vlan->vid_start; vid <= vlan->vid_end; vid++) { + err = rocker_port_vlan_del(rocker_port, vid, vlan->flags); + if (err) + return err; + } + + return 0; +} + +static int rocker_port_obj_del(struct net_device *dev, + struct switchdev_obj *obj) +{ + struct rocker_port *rocker_port = netdev_priv(dev); + int err = 0; + + switch (obj->id) { + case SWITCHDEV_OBJ_PORT_VLAN: + err = rocker_port_vlans_del(rocker_port, &obj->vlan); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + static int rocker_port_switchdev_fib_ipv4_add(struct net_device *dev, __be32 dst, int dst_len, struct fib_info *fi, @@ -4463,6 +4577,8 @@ static int rocker_port_switchdev_fib_ipv4_del(struct net_device *dev, static const struct switchdev_ops rocker_port_switchdev_ops = { .switchdev_port_attr_get = rocker_port_attr_get, .switchdev_port_attr_set = rocker_port_attr_set, + .switchdev_port_obj_add = rocker_port_obj_add, + .switchdev_port_obj_del = rocker_port_obj_del, .switchdev_fib_ipv4_add = rocker_port_switchdev_fib_ipv4_add, .switchdev_fib_ipv4_del = rocker_port_switchdev_fib_ipv4_del, }; From 6004c86718998aee1337efd3b087d6e17284632d Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:55 -0700 Subject: [PATCH 10/24] switchdev: add bridge port flags attr rocker: use switchdev get/set attr for bridge port flags Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 25 +++++++++++++++++++++++++ include/net/switchdev.h | 2 ++ 2 files changed, 27 insertions(+) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 84084806231a..ceb6a6436144 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4394,6 +4394,9 @@ static int rocker_port_attr_get(struct net_device *dev, attr->ppid.id_len = sizeof(rocker->hw.id); memcpy(&attr->ppid.id, &rocker->hw.id, attr->ppid.id_len); break; + case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS: + attr->brport_flags = rocker_port->brport_flags; + break; default: return -EOPNOTSUPP; } @@ -4411,6 +4414,24 @@ static void rocker_port_trans_abort(struct rocker_port *rocker_port) } } +static int rocker_port_brport_flags_set(struct rocker_port *rocker_port, + enum switchdev_trans trans, + unsigned long brport_flags) +{ + unsigned long orig_flags; + int err = 0; + + orig_flags = rocker_port->brport_flags; + rocker_port->brport_flags = brport_flags; + if ((orig_flags ^ rocker_port->brport_flags) & BR_LEARNING) + err = rocker_port_set_learning(rocker_port, trans); + + if (trans == SWITCHDEV_TRANS_PREPARE) + rocker_port->brport_flags = orig_flags; + + return err; +} + static int rocker_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) { @@ -4433,6 +4454,10 @@ static int rocker_port_attr_set(struct net_device *dev, err = rocker_port_stp_update(rocker_port, attr->trans, attr->stp_state); break; + case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS: + err = rocker_port_brport_flags_set(rocker_port, attr->trans, + attr->brport_flags); + break; default: err = -EOPNOTSUPP; break; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index e598c2d45786..6cf6de1a90b4 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -27,6 +27,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_UNDEFINED, SWITCHDEV_ATTR_PORT_PARENT_ID, SWITCHDEV_ATTR_PORT_STP_STATE, + SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, }; struct switchdev_attr { @@ -36,6 +37,7 @@ struct switchdev_attr { union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ + unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ }; }; From 47f8328bb1a4115413e35b9b20d04b061ed544f8 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:56 -0700 Subject: [PATCH 11/24] switchdev: add new switchdev bridge setlink Add new switchdev_port_bridge_setlink that can be used by drivers implementing .ndo_bridge_setlink to set switchdev bridge attributes. Basically turn the raw rtnl_bridge_setlink netlink into switchdev attr sets. Proper netlink attr policy checking is done on the protinfo part of the netlink msg. Currently, for protinfo, only bridge port attrs BR_LEARNING and BR_LEARNING_SYNC are parsed and passed to port driver. For afspec, VLAN objs are passed so switchdev driver can set VLANs assigned to SELF. To illustrate with iproute2 cmd, we have: bridge vlan add vid 10 dev sw1p1 self master To add VLAN 10 to port sw1p1 for both the bridge (master) and the device (self). Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/switchdev/switchdev.c | 151 +++++++++++++++++++++++++++++++++++--- 1 file changed, 140 insertions(+), 11 deletions(-) diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 3d4d99a70b80..b01791a9b56d 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -357,28 +358,156 @@ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); +static int switchdev_port_br_setflag(struct net_device *dev, + struct nlattr *nlattr, + unsigned long brport_flag) +{ + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + }; + u8 flag = nla_get_u8(nlattr); + int err; + + err = switchdev_port_attr_get(dev, &attr); + if (err) + return err; + + if (flag) + attr.brport_flags |= brport_flag; + else + attr.brport_flags &= ~brport_flag; + + return switchdev_port_attr_set(dev, &attr); +} + +static const struct nla_policy +switchdev_port_bridge_policy[IFLA_BRPORT_MAX + 1] = { + [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, + [IFLA_BRPORT_COST] = { .type = NLA_U32 }, + [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, + [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, + [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, + [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, + [IFLA_BRPORT_FAST_LEAVE] = { .type = NLA_U8 }, + [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, + [IFLA_BRPORT_LEARNING_SYNC] = { .type = NLA_U8 }, + [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, +}; + +static int switchdev_port_br_setlink_protinfo(struct net_device *dev, + struct nlattr *protinfo) +{ + struct nlattr *attr; + int rem; + int err; + + err = nla_validate_nested(protinfo, IFLA_BRPORT_MAX, + switchdev_port_bridge_policy); + if (err) + return err; + + nla_for_each_nested(attr, protinfo, rem) { + switch (nla_type(attr)) { + case IFLA_BRPORT_LEARNING: + err = switchdev_port_br_setflag(dev, attr, + BR_LEARNING); + break; + case IFLA_BRPORT_LEARNING_SYNC: + err = switchdev_port_br_setflag(dev, attr, + BR_LEARNING_SYNC); + break; + default: + err = -EOPNOTSUPP; + break; + } + if (err) + return err; + } + + return 0; +} + +static int switchdev_port_br_afspec(struct net_device *dev, + struct nlattr *afspec, + int (*f)(struct net_device *dev, + struct switchdev_obj *obj)) +{ + struct nlattr *attr; + struct bridge_vlan_info *vinfo; + struct switchdev_obj obj = { + .id = SWITCHDEV_OBJ_PORT_VLAN, + }; + int rem; + int err; + + nla_for_each_nested(attr, afspec, rem) { + if (nla_type(attr) != IFLA_BRIDGE_VLAN_INFO) + continue; + if (nla_len(attr) != sizeof(struct bridge_vlan_info)) + return -EINVAL; + vinfo = nla_data(attr); + obj.vlan.flags = vinfo->flags; + if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { + if (obj.vlan.vid_start) + return -EINVAL; + obj.vlan.vid_start = vinfo->vid; + } else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) { + if (!obj.vlan.vid_start) + return -EINVAL; + obj.vlan.vid_end = vinfo->vid; + if (obj.vlan.vid_end <= obj.vlan.vid_start) + return -EINVAL; + err = f(dev, &obj); + if (err) + return err; + memset(&obj.vlan, 0, sizeof(obj.vlan)); + } else { + if (obj.vlan.vid_start) + return -EINVAL; + obj.vlan.vid_start = vinfo->vid; + obj.vlan.vid_end = vinfo->vid; + err = f(dev, &obj); + if (err) + return err; + memset(&obj.vlan, 0, sizeof(obj.vlan)); + } + } + + return 0; +} + /** - * switchdev_port_bridge_setlink - Notify switch device port of bridge - * port attributes + * switchdev_port_bridge_setlink - Set bridge port attributes * * @dev: port device - * @nlh: netlink msg with bridge port attributes - * @flags: bridge setlink flags + * @nlh: netlink header + * @flags: netlink flags * - * Notify switch device port of bridge port attributes + * Called for SELF on rtnl_bridge_setlink to set bridge port + * attributes. */ int switchdev_port_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { - const struct net_device_ops *ops = dev->netdev_ops; + struct nlattr *protinfo; + struct nlattr *afspec; + int err = 0; - if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) - return 0; + protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), + IFLA_PROTINFO); + if (protinfo) { + err = switchdev_port_br_setlink_protinfo(dev, protinfo); + if (err) + return err; + } - if (!ops->ndo_bridge_setlink) - return -EOPNOTSUPP; + afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), + IFLA_AF_SPEC); + if (afspec) + err = switchdev_port_br_afspec(dev, afspec, + switchdev_port_obj_add); - return ops->ndo_bridge_setlink(dev, nlh, flags); + return err; } EXPORT_SYMBOL_GPL(switchdev_port_bridge_setlink); From fc8f40d8644f15f0fd5fbc49012802a00f36ad55 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:57 -0700 Subject: [PATCH 12/24] switchdev: cut over to new switchdev_port_bridge_setlink Rocker, bonding, and team can now use the switchdev bridge setlink to parse raw netlink; no need to duplicate this code in each driver. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- drivers/net/ethernet/rocker/rocker.c | 42 +--------------------------- drivers/net/team/team.c | 2 +- 3 files changed, 3 insertions(+), 43 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index a475a0389cc7..6b1b5dd985f0 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4039,7 +4039,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_add_slave = bond_enslave, .ndo_del_slave = bond_release, .ndo_fix_features = bond_fix_features, - .ndo_bridge_setlink = ndo_dflt_switchdev_port_bridge_setlink, + .ndo_bridge_setlink = switchdev_port_bridge_setlink, .ndo_bridge_dellink = ndo_dflt_switchdev_port_bridge_dellink, .ndo_features_check = passthru_features_check, }; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index ceb6a6436144..e94089e87e94 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4295,46 +4295,6 @@ skip: return idx; } -static int rocker_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) -{ - struct rocker_port *rocker_port = netdev_priv(dev); - struct nlattr *protinfo; - struct nlattr *attr; - int err; - - protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), - IFLA_PROTINFO); - if (protinfo) { - attr = nla_find_nested(protinfo, IFLA_BRPORT_LEARNING); - if (attr) { - if (nla_len(attr) < sizeof(u8)) - return -EINVAL; - - if (nla_get_u8(attr)) - rocker_port->brport_flags |= BR_LEARNING; - else - rocker_port->brport_flags &= ~BR_LEARNING; - err = rocker_port_set_learning(rocker_port, - SWITCHDEV_TRANS_NONE); - if (err) - return err; - } - attr = nla_find_nested(protinfo, IFLA_BRPORT_LEARNING_SYNC); - if (attr) { - if (nla_len(attr) < sizeof(u8)) - return -EINVAL; - - if (nla_get_u8(attr)) - rocker_port->brport_flags |= BR_LEARNING_SYNC; - else - rocker_port->brport_flags &= ~BR_LEARNING_SYNC; - } - } - - return 0; -} - static int rocker_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) @@ -4374,7 +4334,7 @@ static const struct net_device_ops rocker_port_netdev_ops = { .ndo_fdb_add = rocker_port_fdb_add, .ndo_fdb_del = rocker_port_fdb_del, .ndo_fdb_dump = rocker_port_fdb_dump, - .ndo_bridge_setlink = rocker_port_bridge_setlink, + .ndo_bridge_setlink = switchdev_port_bridge_setlink, .ndo_bridge_getlink = rocker_port_bridge_getlink, .ndo_get_phys_port_name = rocker_port_get_phys_port_name, }; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index cfe84965afb6..e6c4df2e63c7 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1977,7 +1977,7 @@ static const struct net_device_ops team_netdev_ops = { .ndo_del_slave = team_del_slave, .ndo_fix_features = team_fix_features, .ndo_change_carrier = team_change_carrier, - .ndo_bridge_setlink = ndo_dflt_switchdev_port_bridge_setlink, + .ndo_bridge_setlink = switchdev_port_bridge_setlink, .ndo_bridge_dellink = ndo_dflt_switchdev_port_bridge_dellink, .ndo_features_check = passthru_features_check, }; From e71f220b342d78cfb8ee9f1b60f1351f7183f2a5 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:58 -0700 Subject: [PATCH 13/24] switchdev: remove old switchdev_port_bridge_setlink New attr-based bridge_setlink can recurse lower devs and recover on err, so remove old wrapper (including ndo_dflt_switchdev_port_bridge_setlink). Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 9 --------- net/switchdev/switchdev.c | 30 ------------------------------ 2 files changed, 39 deletions(-) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 6cf6de1a90b4..ce5ceb2dc677 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -132,8 +132,6 @@ int switchdev_port_bridge_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); int ndo_dflt_switchdev_port_bridge_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); -int ndo_dflt_switchdev_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags); int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 nlflags, u32 tb_id); int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, @@ -204,13 +202,6 @@ static inline int ndo_dflt_switchdev_port_bridge_dellink(struct net_device *dev, return 0; } -static inline int ndo_dflt_switchdev_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) -{ - return 0; -} - static inline int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index b01791a9b56d..dcdec9de9137 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -536,36 +536,6 @@ int switchdev_port_bridge_dellink(struct net_device *dev, } EXPORT_SYMBOL_GPL(switchdev_port_bridge_dellink); -/** - * ndo_dflt_switchdev_port_bridge_setlink - default ndo bridge setlink - * op for master devices - * - * @dev: port device - * @nlh: netlink msg with bridge port attributes - * @flags: bridge setlink flags - * - * Notify master device slaves of bridge port attributes - */ -int ndo_dflt_switchdev_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) -{ - struct net_device *lower_dev; - struct list_head *iter; - int ret = 0, err = 0; - - if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) - return ret; - - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_bridge_setlink(lower_dev, nlh, flags); - if (err && err != -EOPNOTSUPP) - ret = err; - } - - return ret; -} -EXPORT_SYMBOL_GPL(ndo_dflt_switchdev_port_bridge_setlink); - /** * ndo_dflt_switchdev_port_bridge_dellink - default ndo bridge dellink * op for master devices From 41c498b9359e360f08723b7605ec0c40926ec415 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:47:59 -0700 Subject: [PATCH 14/24] bridge: restore br_setlink back to original This is revert of: commit 68e331c785b8 ("bridge: offload bridge port attributes to switch asic if feature flag set") Restore br_setlink back to original and don't call into SELF port driver. rtnetlink.c:bridge_setlink() already does a call into port driver for SELF. bridge set link cmd defaults to MASTER. From man page for bridge link set cmd: self link setting is configured on specified physical device master link setting is configured on the software bridge (default) The link setting has two values: the device-side value and the software bridge-side value. These are independent and settable using the bridge link set cmd by specifying some combination of [master] | [self]. Furthermore, the device-side and bridge-side settings have their own initial value, viewable from bridge -d link show cmd. Restoring br_setlink back to original makes rocker (the only in-kernel user of SELF link settings) work as first implement: two-sided values. It's true that when both MASTER and SELF are specified from the command, two netlink notifications are generated, one for each side of the settings. The user-space app can distiquish between the two notifications by observing the MASTER or SELF flag. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/bridge/br_netlink.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index dc234533e204..e9b943574542 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -586,7 +586,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) struct nlattr *afspec; struct net_bridge_port *p; struct nlattr *tb[IFLA_BRPORT_MAX + 1]; - int err = 0, ret_offload = 0; + int err = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); @@ -628,15 +628,6 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) afspec, RTM_SETLINK); } - if (p && !(flags & BRIDGE_FLAGS_SELF)) { - /* set bridge attributes in hardware if supported - */ - ret_offload = switchdev_port_bridge_setlink(dev, nlh, flags); - if (ret_offload && ret_offload != -EOPNOTSUPP) - br_warn(p->br, "error setting attrs on port %u(%s)\n", - (unsigned int)p->port_no, p->dev->name); - } - if (err == 0) br_ifinfo_notify(RTM_NEWLINK, p); out: From 5c34e0221423aeabc0b085adc5fccda3f91e2c49 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:48:00 -0700 Subject: [PATCH 15/24] switchdev: add new switchdev_port_bridge_dellink Same change as setlink. Provide the wrapper op for SELF ndo_bridge_dellink and call into the switchdev driver to delete afspec VLANs. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 6 ++++++ net/switchdev/switchdev.c | 24 ++++++++++++------------ 2 files changed, 18 insertions(+), 12 deletions(-) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index ce5ceb2dc677..8ffadca9e760 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -164,6 +164,12 @@ static inline int switchdev_port_obj_del(struct net_device *dev, return -EOPNOTSUPP; } +static inline int switchdev_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags) +{ + return -EOPNOTSUPP; +} + static inline int register_switchdev_notifier(struct notifier_block *nb) { return 0; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index dcdec9de9137..8ce678e397b4 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -512,27 +512,27 @@ int switchdev_port_bridge_setlink(struct net_device *dev, EXPORT_SYMBOL_GPL(switchdev_port_bridge_setlink); /** - * switchdev_port_bridge_dellink - Notify switch device port of bridge - * port attribute delete + * switchdev_port_bridge_dellink - Set bridge port attributes * * @dev: port device - * @nlh: netlink msg with bridge port attributes - * @flags: bridge setlink flags + * @nlh: netlink header + * @flags: netlink flags * - * Notify switch device port of bridge port attribute delete + * Called for SELF on rtnl_bridge_dellink to set bridge port + * attributes. */ int switchdev_port_bridge_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { - const struct net_device_ops *ops = dev->netdev_ops; + struct nlattr *afspec; - if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) - return 0; + afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), + IFLA_AF_SPEC); + if (afspec) + return switchdev_port_br_afspec(dev, afspec, + switchdev_port_obj_del); - if (!ops->ndo_bridge_dellink) - return -EOPNOTSUPP; - - return ops->ndo_bridge_dellink(dev, nlh, flags); + return 0; } EXPORT_SYMBOL_GPL(switchdev_port_bridge_dellink); From 54ba5a0bbc739ae77a217d7340149e6f35934c4b Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:48:01 -0700 Subject: [PATCH 16/24] switchdev: cut over to new switchdev_port_bridge_dellink Rocker, bonding and team and switch over to the new switchdev_port_bridge_dellink to avoid duplicating code in each driver. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- drivers/net/ethernet/rocker/rocker.c | 1 + drivers/net/team/team.c | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 6b1b5dd985f0..8459ca8fec50 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4040,7 +4040,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_del_slave = bond_release, .ndo_fix_features = bond_fix_features, .ndo_bridge_setlink = switchdev_port_bridge_setlink, - .ndo_bridge_dellink = ndo_dflt_switchdev_port_bridge_dellink, + .ndo_bridge_dellink = switchdev_port_bridge_dellink, .ndo_features_check = passthru_features_check, }; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index e94089e87e94..17a4c5504b1b 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4336,6 +4336,7 @@ static const struct net_device_ops rocker_port_netdev_ops = { .ndo_fdb_dump = rocker_port_fdb_dump, .ndo_bridge_setlink = switchdev_port_bridge_setlink, .ndo_bridge_getlink = rocker_port_bridge_getlink, + .ndo_bridge_dellink = switchdev_port_bridge_dellink, .ndo_get_phys_port_name = rocker_port_get_phys_port_name, }; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index e6c4df2e63c7..028375391d6f 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1978,7 +1978,7 @@ static const struct net_device_ops team_netdev_ops = { .ndo_fix_features = team_fix_features, .ndo_change_carrier = team_change_carrier, .ndo_bridge_setlink = switchdev_port_bridge_setlink, - .ndo_bridge_dellink = ndo_dflt_switchdev_port_bridge_dellink, + .ndo_bridge_dellink = switchdev_port_bridge_dellink, .ndo_features_check = passthru_features_check, }; From 87a5dae59e7abaad911ab719caa5548dd6df5557 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:48:02 -0700 Subject: [PATCH 17/24] switchdev: remove unused switchdev_port_bridge_dellink Now we can remove old wrappers for dellink. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 15 --------------- net/switchdev/switchdev.c | 30 ------------------------------ 2 files changed, 45 deletions(-) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 8ffadca9e760..397b1e6e04f6 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -130,8 +130,6 @@ int switchdev_port_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); int switchdev_port_bridge_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); -int ndo_dflt_switchdev_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags); int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 nlflags, u32 tb_id); int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, @@ -164,12 +162,6 @@ static inline int switchdev_port_obj_del(struct net_device *dev, return -EOPNOTSUPP; } -static inline int switchdev_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) -{ - return -EOPNOTSUPP; -} - static inline int register_switchdev_notifier(struct notifier_block *nb) { return 0; @@ -201,13 +193,6 @@ static inline int switchdev_port_bridge_dellink(struct net_device *dev, return -EOPNOTSUPP; } -static inline int ndo_dflt_switchdev_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) -{ - return 0; -} - static inline int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8ce678e397b4..0e15b6f6bb56 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -536,36 +536,6 @@ int switchdev_port_bridge_dellink(struct net_device *dev, } EXPORT_SYMBOL_GPL(switchdev_port_bridge_dellink); -/** - * ndo_dflt_switchdev_port_bridge_dellink - default ndo bridge dellink - * op for master devices - * - * @dev: port device - * @nlh: netlink msg with bridge port attributes - * @flags: bridge dellink flags - * - * Notify master device slaves of bridge port attribute deletes - */ -int ndo_dflt_switchdev_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) -{ - struct net_device *lower_dev; - struct list_head *iter; - int ret = 0, err = 0; - - if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD)) - return ret; - - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_bridge_dellink(lower_dev, nlh, flags); - if (err && err != -EOPNOTSUPP) - ret = err; - } - - return ret; -} -EXPORT_SYMBOL_GPL(ndo_dflt_switchdev_port_bridge_dellink); - static struct net_device *switchdev_get_lowest_dev(struct net_device *dev) { const struct switchdev_ops *ops = dev->switchdev_ops; From 8508025c598bdee33d9afa153e9c00c7771e7d63 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:48:03 -0700 Subject: [PATCH 18/24] bridge: revert br_dellink change back to original This is revert of: commit 68e331c785b8 ("bridge: offload bridge port attributes to switch asic if feature flag set") Restore br_dellink back to original and don't call into SELF port driver. rtnetlink.c:bridge_dellink() already does a call into port driver for SELF. bridge vlan add/del cmd defaults to MASTER. From man page for bridge vlan add/del cmd: self the vlan is configured on the specified physical device. Required if the device is the bridge device. master the vlan is configured on the software bridge (default). Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/bridge/br_netlink.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e9b943574542..6b67ed3831de 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -639,7 +639,7 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct nlattr *afspec; struct net_bridge_port *p; - int err = 0, ret_offload = 0; + int err = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!afspec) @@ -658,15 +658,6 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) */ br_ifinfo_notify(RTM_NEWLINK, p); - if (p && !(flags & BRIDGE_FLAGS_SELF)) { - /* del bridge attributes in hardware - */ - ret_offload = switchdev_port_bridge_dellink(dev, nlh, flags); - if (ret_offload && ret_offload != -EOPNOTSUPP) - br_warn(p->br, "error deleting attrs on port %u (%s)\n", - (unsigned int)p->port_no, p->dev->name); - } - return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[]) From 8793d0a664a8a2c5e18e929c1f995c784c105705 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:48:04 -0700 Subject: [PATCH 19/24] switchdev: add new switchdev_port_bridge_getlink Like bridge_setlink, add switchdev wrapper to handle bridge_getlink and call into port driver to get port attrs. For now, only BR_LEARNING and BR_LEARNING_SYNC are returned. To add more, we'll probably want to break away from ndo_dflt_bridge_getlink() and build the netlink skb directly in the switchdev code. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 10 ++++++++++ net/switchdev/switchdev.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 397b1e6e04f6..e081d67f973a 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -126,6 +126,9 @@ int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info); +int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u32 filter_mask, + int nlflags); int switchdev_port_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); int switchdev_port_bridge_dellink(struct net_device *dev, @@ -179,6 +182,13 @@ static inline int call_switchdev_notifiers(unsigned long val, return NOTIFY_DONE; } +static inline int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, + u32 seq, struct net_device *dev, + u32 filter_mask, int nlflags) +{ + return -EOPNOTSUPP; +} + static inline int switchdev_port_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 0e15b6f6bb56..9210355ec965 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -358,6 +358,34 @@ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); +/** + * switchdev_port_bridge_getlink - Get bridge port attributes + * + * @dev: port device + * + * Called for SELF on rtnl_bridge_getlink to get bridge port + * attributes. + */ +int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u32 filter_mask, + int nlflags) +{ + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + }; + u16 mode = BRIDGE_MODE_UNDEF; + u32 mask = BR_LEARNING | BR_LEARNING_SYNC; + int err; + + err = switchdev_port_attr_get(dev, &attr); + if (err) + return err; + + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode, + attr.brport_flags, mask, nlflags); +} +EXPORT_SYMBOL_GPL(switchdev_port_bridge_getlink); + static int switchdev_port_br_setflag(struct net_device *dev, struct nlattr *nlattr, unsigned long brport_flag) From 85fdb956726ff2af609e2f6ea7be781e4db74a07 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:48:05 -0700 Subject: [PATCH 20/24] switchdev: cut over to new switchdev_port_bridge_getlink Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 1 + drivers/net/ethernet/rocker/rocker.c | 15 +-------------- drivers/net/team/team.c | 1 + 3 files changed, 3 insertions(+), 14 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 8459ca8fec50..147642dae3d0 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4040,6 +4040,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_del_slave = bond_release, .ndo_fix_features = bond_fix_features, .ndo_bridge_setlink = switchdev_port_bridge_setlink, + .ndo_bridge_getlink = switchdev_port_bridge_getlink, .ndo_bridge_dellink = switchdev_port_bridge_dellink, .ndo_features_check = passthru_features_check, }; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 17a4c5504b1b..56ee316db1a1 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4295,19 +4295,6 @@ skip: return idx; } -static int rocker_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, - u32 filter_mask, int nlflags) -{ - struct rocker_port *rocker_port = netdev_priv(dev); - u16 mode = BRIDGE_MODE_UNDEF; - u32 mask = BR_LEARNING | BR_LEARNING_SYNC; - - return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode, - rocker_port->brport_flags, mask, - nlflags); -} - static int rocker_port_get_phys_port_name(struct net_device *dev, char *buf, size_t len) { @@ -4334,8 +4321,8 @@ static const struct net_device_ops rocker_port_netdev_ops = { .ndo_fdb_add = rocker_port_fdb_add, .ndo_fdb_del = rocker_port_fdb_del, .ndo_fdb_dump = rocker_port_fdb_dump, + .ndo_bridge_getlink = switchdev_port_bridge_getlink, .ndo_bridge_setlink = switchdev_port_bridge_setlink, - .ndo_bridge_getlink = rocker_port_bridge_getlink, .ndo_bridge_dellink = switchdev_port_bridge_dellink, .ndo_get_phys_port_name = rocker_port_get_phys_port_name, }; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 028375391d6f..bda32be596ef 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1978,6 +1978,7 @@ static const struct net_device_ops team_netdev_ops = { .ndo_fix_features = team_fix_features, .ndo_change_carrier = team_change_carrier, .ndo_bridge_setlink = switchdev_port_bridge_setlink, + .ndo_bridge_getlink = switchdev_port_bridge_getlink, .ndo_bridge_dellink = switchdev_port_bridge_dellink, .ndo_features_check = passthru_features_check, }; From 58c2cb16b116d7feace621bd6b647bbabacfa225 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:48:06 -0700 Subject: [PATCH 21/24] switchdev: convert fib_ipv4_add/del over to switchdev_port_obj_add/del The IPv4 FIB ops convert nicely to the switchdev objs and we're left with only four switchdev ops: port get/set and port add/del. Other objs will follow, such as FDB. So go ahead and convert IPv4 FIB over to switchdev obj for consistency, anticipating more objs to come. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 41 +++++++++--------------- include/net/switchdev.h | 21 ++++++------- net/switchdev/switchdev.c | 47 ++++++++++++++++++---------- 3 files changed, 54 insertions(+), 55 deletions(-) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 56ee316db1a1..1c906504cfe2 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4449,6 +4449,7 @@ static int rocker_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) { struct rocker_port *rocker_port = netdev_priv(dev); + struct switchdev_obj_ipv4_fib *fib4; int err = 0; switch (obj->trans) { @@ -4467,6 +4468,12 @@ static int rocker_port_obj_add(struct net_device *dev, err = rocker_port_vlans_add(rocker_port, obj->trans, &obj->vlan); break; + case SWITCHDEV_OBJ_IPV4_FIB: + fib4 = &obj->ipv4_fib; + err = rocker_port_fib_ipv4(rocker_port, obj->trans, + fib4->dst, fib4->dst_len, + fib4->fi, fib4->tb_id, 0); + break; default: err = -EOPNOTSUPP; break; @@ -4508,12 +4515,19 @@ static int rocker_port_obj_del(struct net_device *dev, struct switchdev_obj *obj) { struct rocker_port *rocker_port = netdev_priv(dev); + struct switchdev_obj_ipv4_fib *fib4; int err = 0; switch (obj->id) { case SWITCHDEV_OBJ_PORT_VLAN: err = rocker_port_vlans_del(rocker_port, &obj->vlan); break; + case SWITCHDEV_OBJ_IPV4_FIB: + fib4 = &obj->ipv4_fib; + err = rocker_port_fib_ipv4(rocker_port, SWITCHDEV_TRANS_NONE, + fib4->dst, fib4->dst_len, fib4->fi, + fib4->tb_id, ROCKER_OP_FLAG_REMOVE); + break; default: err = -EOPNOTSUPP; break; @@ -4522,38 +4536,11 @@ static int rocker_port_obj_del(struct net_device *dev, return err; } -static int rocker_port_switchdev_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) -{ - struct rocker_port *rocker_port = netdev_priv(dev); - int flags = 0; - - return rocker_port_fib_ipv4(rocker_port, SWITCHDEV_TRANS_NONE, - dst, dst_len, fi, tb_id, flags); -} - -static int rocker_port_switchdev_fib_ipv4_del(struct net_device *dev, - __be32 dst, int dst_len, - struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) -{ - struct rocker_port *rocker_port = netdev_priv(dev); - int flags = ROCKER_OP_FLAG_REMOVE; - - return rocker_port_fib_ipv4(rocker_port, SWITCHDEV_TRANS_NONE, - dst, dst_len, fi, tb_id, flags); -} - static const struct switchdev_ops rocker_port_switchdev_ops = { .switchdev_port_attr_get = rocker_port_attr_get, .switchdev_port_attr_set = rocker_port_attr_set, .switchdev_port_obj_add = rocker_port_obj_add, .switchdev_port_obj_del = rocker_port_obj_del, - .switchdev_fib_ipv4_add = rocker_port_switchdev_fib_ipv4_add, - .switchdev_fib_ipv4_del = rocker_port_switchdev_fib_ipv4_del, }; /******************** diff --git a/include/net/switchdev.h b/include/net/switchdev.h index e081d67f973a..3b217b4cca27 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -46,6 +46,7 @@ struct fib_info; enum switchdev_obj_id { SWITCHDEV_OBJ_UNDEFINED, SWITCHDEV_OBJ_PORT_VLAN, + SWITCHDEV_OBJ_IPV4_FIB, }; struct switchdev_obj { @@ -57,6 +58,15 @@ struct switchdev_obj { u16 vid_start; u16 vid_end; } vlan; + struct switchdev_obj_ipv4_fib { /* IPV4_FIB */ + u32 dst; + int dst_len; + struct fib_info *fi; + u8 tos; + u8 type; + u32 nlflags; + u32 tb_id; + } ipv4_fib; }; }; @@ -70,10 +80,6 @@ struct switchdev_obj { * @switchdev_port_obj_add: Add an object to port (see switchdev_obj). * * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj). - * - * @switchdev_fib_ipv4_add: Called to add/modify IPv4 route to switch device. - * - * @switchdev_fib_ipv4_del: Called to delete IPv4 route from switch device. */ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, @@ -84,13 +90,6 @@ struct switchdev_ops { struct switchdev_obj *obj); int (*switchdev_port_obj_del)(struct net_device *dev, struct switchdev_obj *obj); - int (*switchdev_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 (*switchdev_fib_ipv4_del)(struct net_device *dev, __be32 dst, - int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id); }; enum switchdev_notifier_type { diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 9210355ec965..65d49d4477b9 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -641,8 +641,19 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 nlflags, u32 tb_id) { + struct switchdev_obj fib_obj = { + .id = SWITCHDEV_OBJ_IPV4_FIB, + .ipv4_fib = { + .dst = htonl(dst), + .dst_len = dst_len, + .fi = fi, + .tos = tos, + .type = type, + .nlflags = nlflags, + .tb_id = tb_id, + }, + }; struct net_device *dev; - const struct switchdev_ops *ops; int err = 0; /* Don't offload route if using custom ip rules or if @@ -660,15 +671,10 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, dev = switchdev_get_dev_by_nhs(fi); if (!dev) return 0; - ops = dev->switchdev_ops; - if (ops->switchdev_fib_ipv4_add) { - err = ops->switchdev_fib_ipv4_add(dev, htonl(dst), dst_len, - fi, tos, type, nlflags, - tb_id); - if (!err) - fi->fib_flags |= RTNH_F_EXTERNAL; - } + err = switchdev_port_obj_add(dev, &fib_obj); + if (!err) + fi->fib_flags |= RTNH_F_EXTERNAL; return err; } @@ -689,8 +695,19 @@ EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_add); int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id) { + struct switchdev_obj fib_obj = { + .id = SWITCHDEV_OBJ_IPV4_FIB, + .ipv4_fib = { + .dst = htonl(dst), + .dst_len = dst_len, + .fi = fi, + .tos = tos, + .type = type, + .nlflags = 0, + .tb_id = tb_id, + }, + }; struct net_device *dev; - const struct switchdev_ops *ops; int err = 0; if (!(fi->fib_flags & RTNH_F_EXTERNAL)) @@ -699,14 +716,10 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, dev = switchdev_get_dev_by_nhs(fi); if (!dev) return 0; - ops = dev->switchdev_ops; - if (ops->switchdev_fib_ipv4_del) { - err = ops->switchdev_fib_ipv4_del(dev, htonl(dst), dst_len, - fi, tos, type, tb_id); - if (!err) - fi->fib_flags &= ~RTNH_F_EXTERNAL; - } + err = switchdev_port_obj_del(dev, &fib_obj); + if (!err) + fi->fib_flags &= ~RTNH_F_EXTERNAL; return err; } From 7889cbee8357aaed85898d028829dfb4f75bae2c Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:48:07 -0700 Subject: [PATCH 22/24] switchdev: remove NETIF_F_HW_SWITCH_OFFLOAD feature flag Roopa said remove the feature flag for this series and she'll work on bringing it back if needed at a later date. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 5 +---- drivers/net/ethernet/rocker/rocker.c | 3 +-- drivers/net/team/team.c | 2 +- include/linux/netdev_features.h | 5 +---- net/core/ethtool.c | 1 - 5 files changed, 4 insertions(+), 12 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 147642dae3d0..a2e25de98bde 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1015,10 +1015,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev, netdev_features_t mask; struct slave *slave; - /* If any slave has the offload feature flag set, - * set the offload flag on the bond. - */ - mask = features | NETIF_F_HW_SWITCH_OFFLOAD; + mask = features; features &= ~NETIF_F_ONE_FOR_ALL; features |= NETIF_F_ALL_FOR_ALL; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 1c906504cfe2..9715e3322706 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4906,8 +4906,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) rocker_carrier_init(rocker_port); dev->features |= NETIF_F_NETNS_LOCAL | - NETIF_F_HW_VLAN_CTAG_FILTER | - NETIF_F_HW_SWITCH_OFFLOAD; + NETIF_F_HW_VLAN_CTAG_FILTER; err = register_netdev(dev); if (err) { diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index bda32be596ef..1ec035a53c3d 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1924,7 +1924,7 @@ static netdev_features_t team_fix_features(struct net_device *dev, struct team *team = netdev_priv(dev); netdev_features_t mask; - mask = features | NETIF_F_HW_SWITCH_OFFLOAD; + mask = features; features &= ~NETIF_F_ONE_FOR_ALL; features |= NETIF_F_ALL_FOR_ALL; diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 7d59dc6ab789..9672781c593d 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -66,7 +66,6 @@ enum { NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ NETIF_F_BUSY_POLL_BIT, /* Busy poll */ - NETIF_F_HW_SWITCH_OFFLOAD_BIT, /* HW switch offload */ /* * Add your fresh new feature above and remember to update @@ -125,7 +124,6 @@ enum { #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) -#define NETIF_F_HW_SWITCH_OFFLOAD __NETIF_F(HW_SWITCH_OFFLOAD) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ @@ -161,8 +159,7 @@ enum { */ #define NETIF_F_ONE_FOR_ALL (NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \ NETIF_F_SG | NETIF_F_HIGHDMA | \ - NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED | \ - NETIF_F_HW_SWITCH_OFFLOAD) + NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED) /* * If one device doesn't support one of these features, then disable it diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 1d00b8922902..eb0c3ace7458 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -98,7 +98,6 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RXALL_BIT] = "rx-all", [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", [NETIF_F_BUSY_POLL_BIT] = "busy-poll", - [NETIF_F_HW_SWITCH_OFFLOAD_BIT] = "hw-switch-offload", }; static const char From 4725ceb9b70115b210a01d73318ce4430e4f0125 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:48:08 -0700 Subject: [PATCH 23/24] rocker: make checkpatch -f clean Well almost clean: ignore the CHECKs for space after cast operator and some longer-than-80 char cases where for readability it's better to keep as-is. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker.c | 19 +++++++++---------- drivers/net/ethernet/rocker/rocker.h | 28 ++++++++++++++-------------- 2 files changed, 23 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 9715e3322706..1fc006b446c1 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -181,7 +181,7 @@ struct rocker_desc_info { size_t data_size; size_t tlv_size; struct rocker_desc *desc; - DEFINE_DMA_UNMAP_ADDR(mapaddr); + dma_addr_t mapaddr; }; struct rocker_dma_ring_info { @@ -237,21 +237,21 @@ struct rocker { struct { u64 id; } hw; - spinlock_t cmd_ring_lock; + spinlock_t cmd_ring_lock; /* for cmd ring accesses */ struct rocker_dma_ring_info cmd_ring; struct rocker_dma_ring_info event_ring; DECLARE_HASHTABLE(flow_tbl, 16); - spinlock_t flow_tbl_lock; + spinlock_t flow_tbl_lock; /* for flow tbl accesses */ u64 flow_tbl_next_cookie; DECLARE_HASHTABLE(group_tbl, 16); - spinlock_t group_tbl_lock; + spinlock_t group_tbl_lock; /* for group tbl accesses */ DECLARE_HASHTABLE(fdb_tbl, 16); - spinlock_t fdb_tbl_lock; + spinlock_t fdb_tbl_lock; /* for fdb tbl accesses */ unsigned long internal_vlan_bitmap[ROCKER_INTERNAL_VLAN_BITMAP_LEN]; DECLARE_HASHTABLE(internal_vlan_tbl, 8); - spinlock_t internal_vlan_tbl_lock; + spinlock_t internal_vlan_tbl_lock; /* for vlan tbl accesses */ DECLARE_HASHTABLE(neigh_tbl, 16); - spinlock_t neigh_tbl_lock; + spinlock_t neigh_tbl_lock; /* for neigh tbl accesses */ u32 neigh_tbl_next_index; }; @@ -4688,8 +4688,6 @@ static void rocker_port_get_stats(struct net_device *dev, for (i = 0; i < ARRAY_SIZE(rocker_port_stats); ++i) data[i] = 0; } - - return; } static int rocker_port_get_sset_count(struct net_device *netdev, int sset) @@ -4743,8 +4741,9 @@ static int rocker_port_poll_tx(struct napi_struct *napi, int budget) if (err == 0) { rocker_port->dev->stats.tx_packets++; rocker_port->dev->stats.tx_bytes += skb->len; - } else + } else { rocker_port->dev->stats.tx_errors++; + } dev_kfree_skb_any(skb); credits++; diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h index a4e9591d7457..c61fbf968036 100644 --- a/drivers/net/ethernet/rocker/rocker.h +++ b/drivers/net/ethernet/rocker/rocker.h @@ -65,9 +65,9 @@ enum { #define ROCKER_TEST_DMA_CTRL 0x0034 /* Rocker test register ctrl */ -#define ROCKER_TEST_DMA_CTRL_CLEAR (1 << 0) -#define ROCKER_TEST_DMA_CTRL_FILL (1 << 1) -#define ROCKER_TEST_DMA_CTRL_INVERT (1 << 2) +#define ROCKER_TEST_DMA_CTRL_CLEAR BIT(0) +#define ROCKER_TEST_DMA_CTRL_FILL BIT(1) +#define ROCKER_TEST_DMA_CTRL_INVERT BIT(2) /* Rocker DMA ring register offsets */ #define ROCKER_DMA_DESC_ADDR(x) (0x1000 + (x) * 32) /* 8-byte */ @@ -79,7 +79,7 @@ enum { #define ROCKER_DMA_DESC_RES1(x) (0x101c + (x) * 32) /* Rocker dma ctrl register bits */ -#define ROCKER_DMA_DESC_CTRL_RESET (1 << 0) +#define ROCKER_DMA_DESC_CTRL_RESET BIT(0) /* Rocker DMA ring types */ enum rocker_dma_type { @@ -111,7 +111,7 @@ struct rocker_desc { u16 comp_err; }; -#define ROCKER_DMA_DESC_COMP_ERR_GEN (1 << 15) +#define ROCKER_DMA_DESC_COMP_ERR_GEN BIT(15) /* Rocker DMA TLV struct */ struct rocker_tlv { @@ -237,14 +237,14 @@ enum { ROCKER_TLV_RX_MAX = __ROCKER_TLV_RX_MAX - 1, }; -#define ROCKER_RX_FLAGS_IPV4 (1 << 0) -#define ROCKER_RX_FLAGS_IPV6 (1 << 1) -#define ROCKER_RX_FLAGS_CSUM_CALC (1 << 2) -#define ROCKER_RX_FLAGS_IPV4_CSUM_GOOD (1 << 3) -#define ROCKER_RX_FLAGS_IP_FRAG (1 << 4) -#define ROCKER_RX_FLAGS_TCP (1 << 5) -#define ROCKER_RX_FLAGS_UDP (1 << 6) -#define ROCKER_RX_FLAGS_TCP_UDP_CSUM_GOOD (1 << 7) +#define ROCKER_RX_FLAGS_IPV4 BIT(0) +#define ROCKER_RX_FLAGS_IPV6 BIT(1) +#define ROCKER_RX_FLAGS_CSUM_CALC BIT(2) +#define ROCKER_RX_FLAGS_IPV4_CSUM_GOOD BIT(3) +#define ROCKER_RX_FLAGS_IP_FRAG BIT(4) +#define ROCKER_RX_FLAGS_TCP BIT(5) +#define ROCKER_RX_FLAGS_UDP BIT(6) +#define ROCKER_RX_FLAGS_TCP_UDP_CSUM_GOOD BIT(7) enum { ROCKER_TLV_TX_UNSPEC, @@ -460,6 +460,6 @@ enum rocker_of_dpa_overlay_type { #define ROCKER_SWITCH_ID 0x0320 /* 8-byte */ /* Rocker control bits */ -#define ROCKER_CONTROL_RESET (1 << 0) +#define ROCKER_CONTROL_RESET BIT(0) #endif From 4ceec22d6d89360ff7ebbf53dd3ab4e29e3d8a09 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 10 May 2015 09:48:09 -0700 Subject: [PATCH 24/24] switchdev: bring documentation up-to-date Much need updated of switchdev documentation to cover what's been implmented to-date. There are some XXX comments in the text for unimplemented or broken items. I'd like to keep these in there (poor-man's TODO list) and update the document once each issue is resolved. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 396 +++++++++++++++++++++---- 1 file changed, 346 insertions(+), 50 deletions(-) diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index f981a9295a39..b3e18c8fd040 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -1,59 +1,355 @@ -Switch (and switch-ish) device drivers HOWTO -=========================== +Ethernet switch device driver model (switchdev) +=============================================== +Copyright (c) 2014 Jiri Pirko +Copyright (c) 2014-2015 Scott Feldman -Please note that the word "switch" is here used in very generic meaning. -This include devices supporting L2/L3 but also various flow offloading chips, -including switches embedded into SR-IOV NICs. -Lets describe a topology a bit. Imagine the following example: +The Ethernet switch device driver model (switchdev) is an in-kernel driver +model for switch devices which offload the forwarding (data) plane from the +kernel. - +----------------------------+ +---------------+ - | SOME switch chip | | CPU | - +----------------------------+ +---------------+ - port1 port2 port3 port4 MNGMNT | PCI-E | - | | | | | +---------------+ - PHY PHY | | | | NIC0 NIC1 - | | | | | | - | | +- PCI-E -+ | | - | +------- MII -------+ | - +------------- MII ------------+ +Figure 1 is a block diagram showing the components of the switchdev model for +an example setup using a data-center-class switch ASIC chip. Other setups +with SR-IOV or soft switches, such as OVS, are possible. -In this example, there are two independent lines between the switch silicon -and CPU. NIC0 and NIC1 drivers are not aware of a switch presence. They are -separate from the switch driver. SOME switch chip is by managed by a driver -via PCI-E device MNGMNT. Note that MNGMNT device, NIC0 and NIC1 may be -connected to some other type of bus. -Now, for the previous example show the representation in kernel: +                             User-space tools                                  +                                                                               +       user space                   |                                          +      +-------------------------------------------------------------------+    +       kernel                       | Netlink                                  +                                    |                                          +                     +--------------+-------------------------------+          +                     |         Network stack                        |          +                     |           (Linux)                            |          +                     |                                              |          +                     +----------------------------------------------+          +                                                                               + sw1p2 sw1p4 sw1p6 +                      sw1p1  + sw1p3 +  sw1p5 +         eth1              +                        +    |    +    |    +    |            +                +                        |    |    |    |    |    |            |                +                     +--+----+----+----+-+--+----+---+  +-----+-----+          +                     |         Switch driver         |  |    mgmt   |          +                     |        (this document)        |  |   driver  |          +                     |                               |  |           |          +                     +--------------+----------------+  +-----------+          +                                    |                                          +       kernel                       | HW bus (eg PCI)                          +      +-------------------------------------------------------------------+    +       hardware                     |                                          +                     +--------------+---+------------+                         +                     |         Switch device (sw1)   |                         +                     |  +----+                       +--------+                +                     |  |    v offloaded data path   | mgmt port               +                     |  |    |                       |                         +                     +--|----|----+----+----+----+---+                         +                        |    |    |    |    |    |                             +                        +    +    +    +    +    +                             +                       p1   p2   p3   p4   p5   p6 +                                        +                             front-panel ports                                 +                                                                               - +----------------------------+ +---------------+ - | SOME switch chip | | CPU | - +----------------------------+ +---------------+ - sw0p0 sw0p1 sw0p2 sw0p3 MNGMNT | PCI-E | - | | | | | +---------------+ - PHY PHY | | | | eth0 eth1 - | | | | | | - | | +- PCI-E -+ | | - | +------- MII -------+ | - +------------- MII ------------+ + Fig 1. -Lets call the example switch driver for SOME switch chip "SOMEswitch". This -driver takes care of PCI-E device MNGMNT. There is a netdevice instance sw0pX -created for each port of a switch. These netdevices are instances -of "SOMEswitch" driver. sw0pX netdevices serve as a "representation" -of the switch chip. eth0 and eth1 are instances of some other existing driver. -The only difference of the switch-port netdevice from the ordinary netdevice -is that is implements couple more NDOs: +Include Files +------------- - ndo_switch_parent_id_get - This returns the same ID for two port netdevices - of the same physical switch chip. This is - mandatory to be implemented by all switch drivers - and serves the caller for recognition of a port - netdevice. - ndo_switch_parent_* - Functions that serve for a manipulation of the switch - chip itself (it can be though of as a "parent" of the - port, therefore the name). They are not port-specific. - Caller might use arbitrary port netdevice of the same - switch and it will make no difference. - ndo_switch_port_* - Functions that serve for a port-specific manipulation. +#include +#include + + +Configuration +------------- + +Use "depends NET_SWITCHDEV" in driver's Kconfig to ensure switchdev model +support is built for driver. + + +Switch Ports +------------ + +On switchdev driver initialization, the driver will allocate and register a +struct net_device (using register_netdev()) for each enumerated physical switch +port, called the port netdev. A port netdev is the software representation of +the physical port and provides a conduit for control traffic to/from the +controller (the kernel) and the network, as well as an anchor point for higher +level constructs such as bridges, bonds, VLANs, tunnels, and L3 routers. Using +standard netdev tools (iproute2, ethtool, etc), the port netdev can also +provide to the user access to the physical properties of the switch port such +as PHY link state and I/O statistics. + +There is (currently) no higher-level kernel object for the switch beyond the +port netdevs. All of the switchdev driver ops are netdev ops or switchdev ops. + +A switch management port is outside the scope of the switchdev driver model. +Typically, the management port is not participating in offloaded data plane and +is loaded with a different driver, such as a NIC driver, on the management port +device. + +Port Netdev Naming +^^^^^^^^^^^^^^^^^^ + +Udev rules should be used for port netdev naming, using some unique attribute +of the port as a key, for example the port MAC address or the port PHYS name. +Hard-coding of kernel netdev names within the driver is discouraged; let the +kernel pick the default netdev name, and let udev set the final name based on a +port attribute. + +Using port PHYS name (ndo_get_phys_port_name) for the key is particularly +useful for dynically-named ports where the device names it's ports based on +external configuration. For example, if a physical 40G port is split logically +into 4 10G ports, resulting in 4 port netdevs, the device can give a unique +name for each port using port PHYS name. The udev rule would be: + +SUBSYSTEM=="net", ACTION=="add", DRIVER="", ATTR{phys_port_name}!="", \ + NAME="$attr{phys_port_name}" + +Suggested naming convention is "swXpYsZ", where X is the switch name or ID, Y +is the port name or ID, and Z is the sub-port name or ID. For example, sw1p1s0 +would be sub-port 0 on port 1 on switch 1. + +Switch ID +^^^^^^^^^ + +The switchdev driver must implement the switchdev op switchdev_port_attr_get for +SWITCHDEV_ATTR_PORT_PARENT_ID for each port netdev, returning the same physical ID +for each port of a switch. The ID must be unique between switches on the same +system. The ID does not need to be unique between switches on different +systems. + +The switch ID is used to locate ports on a switch and to know if aggregated +ports belong to the same switch. + +Port Features +^^^^^^^^^^^^^ + +NETIF_F_NETNS_LOCAL + +If the switchdev driver (and device) only supports offloading of the default +network namespace (netns), the driver should set this feature flag to prevent +the port netdev from being moved out of the default netns. A netns-aware +driver/device would not set this flag and be resposible for partitioning +hardware to preserve netns containment. This means hardware cannot forward +traffic from a port in one namespace to another port in another namespace. + +Port Topology +^^^^^^^^^^^^^ + +The port netdevs representing the physical switch ports can be organized into +higher-level switching constructs. The default construct is a standalone +router port, used to offload L3 forwarding. Two or more ports can be bonded +together to form a LAG. Two or more ports (or LAGs) can be bridged to bridge +to L2 networks. VLANs can be applied to sub-divide L2 networks. L2-over-L3 +tunnels can be built on ports. These constructs are built using standard Linux +tools such as the bridge driver, the bonding/team drivers, and netlink-based +tools such as iproute2. + +The switchdev driver can know a particular port's position in the topology by +monitoring NETDEV_CHANGEUPPER notifications. For example, a port moved into a +bond will see it's upper master change. If that bond is moved into a bridge, +the bond's upper master will change. And so on. The driver will track such +movements to know what position a port is in in the overall topology by +registering for netdevice events and acting on NETDEV_CHANGEUPPER. + +L2 Forwarding Offload +--------------------- + +The idea is to offload the L2 data forwarding (switching) path from the kernel +to the switchdev device by mirroring bridge FDB entries down to the device. An +FDB entry is the {port, MAC, VLAN} tuple forwarding destination. + +To offloading L2 bridging, the switchdev driver/device should support: + + - Static FDB entries installed on a bridge port + - Notification of learned/forgotten src mac/vlans from device + - STP state changes on the port + - VLAN flooding of multicast/broadcast and unknown unicast packets + +Static FDB Entries +^^^^^^^^^^^^^^^^^^ + +The switchdev driver should implement ndo_fdb_add, ndo_fdb_del and ndo_fdb_dump +to support static FDB entries installed to the device. Static bridge FDB +entries are installed, for example, using iproute2 bridge cmd: + + bridge fdb add ADDR dev DEV [vlan VID] [self] + +Note: by default, the bridge does not filter on VLAN and only bridges untagged +traffic. To enable VLAN support, turn on VLAN filtering: + + echo 1 >/sys/class/net//bridge/vlan_filtering + +Notification of Learned/Forgotten Source MAC/VLANs +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The switch device will learn/forget source MAC address/VLAN on ingress packets +and notify the switch driver of the mac/vlan/port tuples. The switch driver, +in turn, will notify the bridge driver using the switchdev notifier call: + + err = call_switchdev_notifiers(val, dev, info); + +Where val is SWITCHDEV_FDB_ADD when learning and SWITCHDEV_FDB_DEL when forgetting, and +info points to a struct switchdev_notifier_fdb_info. On SWITCHDEV_FDB_ADD, the bridge +driver will install the FDB entry into the bridge's FDB and mark the entry as +NTF_EXT_LEARNED. The iproute2 bridge command will label these entries +"offload": + + $ bridge fdb + 52:54:00:12:35:01 dev sw1p1 master br0 permanent + 00:02:00:00:02:00 dev sw1p1 master br0 offload + 00:02:00:00:02:00 dev sw1p1 self + 52:54:00:12:35:02 dev sw1p2 master br0 permanent + 00:02:00:00:03:00 dev sw1p2 master br0 offload + 00:02:00:00:03:00 dev sw1p2 self + 33:33:00:00:00:01 dev eth0 self permanent + 01:00:5e:00:00:01 dev eth0 self permanent + 33:33:ff:00:00:00 dev eth0 self permanent + 01:80:c2:00:00:0e dev eth0 self permanent + 33:33:00:00:00:01 dev br0 self permanent + 01:00:5e:00:00:01 dev br0 self permanent + 33:33:ff:12:35:01 dev br0 self permanent + +Learning on the port should be disabled on the bridge using the bridge command: + + bridge link set dev DEV learning off + +Learning on the device port should be enabled, as well as learning_sync: + + bridge link set dev DEV learning on self + bridge link set dev DEV learning_sync on self + +Learning_sync attribute enables syncing of the learned/forgotton FDB entry to +the bridge's FDB. It's possible, but not optimal, to enable learning on the +device port and on the bridge port, and disable learning_sync. + +To support learning and learning_sync port attributes, the driver implements +switchdev op switchdev_port_attr_get/set for SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS. The driver +should initialize the attributes to the hardware defaults. + +FDB Ageing +^^^^^^^^^^ + +There are two FDB ageing models supported: 1) ageing by the device, and 2) +ageing by the kernel. Ageing by the device is preferred if many FDB entries +are supported. The driver calls call_switchdev_notifiers(SWITCHDEV_FDB_DEL, ...) to +age out the FDB entry. In this model, ageing by the kernel should be turned +off. XXX: how to turn off ageing in kernel on a per-port basis or otherwise +prevent the kernel from ageing out the FDB entry? + +In the kernel ageing model, the standard bridge ageing mechanism is used to age +out stale FDB entries. To keep an FDB entry "alive", the driver should refresh +the FDB entry by calling call_switchdev_notifiers(SWITCHDEV_FDB_ADD, ...). The +notification will reset the FDB entry's last-used time to now. The driver +should rate limit refresh notifications, for example, no more than once a +second. If the FDB entry expires, ndo_fdb_del is called to remove entry from +the device. XXX: this last part isn't currently correct: ndo_fdb_del isn't +called, so the stale entry remains in device...this need to get fixed. + +FDB Flush +^^^^^^^^^ + +XXX: Unimplemented. Need to support FDB flush by bridge driver for port and +remove both static and learned FDB entries. + +STP State Change on Port +^^^^^^^^^^^^^^^^^^^^^^^^ + +Internally or with a third-party STP protocol implementation (e.g. mstpd), the +bridge driver maintains the STP state for ports, and will notify the switch +driver of STP state change on a port using the switchdev op switchdev_attr_port_set for +SWITCHDEV_ATTR_PORT_STP_UPDATE. + +State is one of BR_STATE_*. The switch driver can use STP state updates to +update ingress packet filter list for the port. For example, if port is +DISABLED, no packets should pass, but if port moves to BLOCKED, then STP BPDUs +and other IEEE 01:80:c2:xx:xx:xx link-local multicast packets can pass. + +Note that STP BDPUs are untagged and STP state applies to all VLANs on the port +so packet filters should be applied consistently across untagged and tagged +VLANs on the port. + +Flooding L2 domain +^^^^^^^^^^^^^^^^^^ + +For a given L2 VLAN domain, the switch device should flood multicast/broadcast +and unknown unicast packets to all ports in domain, if allowed by port's +current STP state. The switch driver, knowing which ports are within which +vlan L2 domain, can program the switch device for flooding. The packet should +also be sent to the port netdev for processing by the bridge driver. The +bridge should not reflood the packet to the same ports the device flooded. +XXX: the mechanism to avoid duplicate flood packets is being discuseed. + +It is possible for the switch device to not handle flooding and push the +packets up to the bridge driver for flooding. This is not ideal as the number +of ports scale in the L2 domain as the device is much more efficient at +flooding packets that software. + +IGMP Snooping +^^^^^^^^^^^^^ + +XXX: complete this section + + +L3 routing +---------- + +Offloading L3 routing requires that device be programmed with FIB entries from +the kernel, with the device doing the FIB lookup and forwarding. The device +does a longest prefix match (LPM) on FIB entries matching route prefix and +forwards the packet to the matching FIB entry's nexthop(s) egress ports. To +program the device, the switchdev driver is called with add/delete ops for IPv4 +and IPv6 FIB entries. For IPv4, the driver implements switchdev ops: + + int (*switchdev_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 (*switchdev_fib_ipv4_del)(struct net_device *dev, + __be32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, + u32 tb_id); + +to add/delete IPv4 dst/dest_len prefix on table tb_id. The *fi structure holds +details on the route and route's nexthops. *dev is one of the port netdevs +mentioned in the routes next hop list. If the output port netdevs referenced +in the route's nexthop list don't all have the same switch ID, the driver is +not called to add/delete the FIB entry. + +Routes offloaded to the device are labeled with "offload" in the ip route +listing: + + $ ip route show + default via 192.168.0.2 dev eth0 + 11.0.0.0/30 dev sw1p1 proto kernel scope link src 11.0.0.2 offload + 11.0.0.4/30 via 11.0.0.1 dev sw1p1 proto zebra metric 20 offload + 11.0.0.8/30 dev sw1p2 proto kernel scope link src 11.0.0.10 offload + 11.0.0.12/30 via 11.0.0.9 dev sw1p2 proto zebra metric 20 offload + 12.0.0.2 proto zebra metric 30 offload + nexthop via 11.0.0.1 dev sw1p1 weight 1 + nexthop via 11.0.0.9 dev sw1p2 weight 1 + 12.0.0.3 via 11.0.0.1 dev sw1p1 proto zebra metric 20 offload + 12.0.0.4 via 11.0.0.9 dev sw1p2 proto zebra metric 20 offload + 192.168.0.0/24 dev eth0 proto kernel scope link src 192.168.0.15 + +XXX: add/del IPv6 FIB API + +Nexthop Resolution +^^^^^^^^^^^^^^^^^^ + +The FIB entry's nexthop list contains the nexthop tuple (gateway, dev), but for +the switch device to forward the packet with the correct dst mac address, the +nexthop gateways must be resolved to the neighbor's mac address. Neighbor mac +address discovery comes via the ARP (or ND) process and is available via the +arp_tbl neighbor table. To resolve the routes nexthop gateways, the driver +should trigger the kernel's neighbor resolution process. See the rocker +driver's rocker_port_ipv4_resolve() for an example. + +The driver can monitor for updates to arp_tbl using the netevent notifier +NETEVENT_NEIGH_UPDATE. The device can be programmed with resolved nexthops +for the routes as arp_tbl updates.