diff options
Diffstat (limited to 'drivers/net/team')
| -rw-r--r-- | drivers/net/team/Kconfig | 13 | ||||
| -rw-r--r-- | drivers/net/team/Makefile | 1 | ||||
| -rw-r--r-- | drivers/net/team/team.c | 777 | ||||
| -rw-r--r-- | drivers/net/team/team_mode_activebackup.c | 17 | ||||
| -rw-r--r-- | drivers/net/team/team_mode_broadcast.c | 87 | ||||
| -rw-r--r-- | drivers/net/team/team_mode_loadbalance.c | 546 | ||||
| -rw-r--r-- | drivers/net/team/team_mode_roundrobin.c | 13 |
7 files changed, 1189 insertions, 265 deletions
diff --git a/drivers/net/team/Kconfig b/drivers/net/team/Kconfig index 89024d5fc33..6a7260b03a1 100644 --- a/drivers/net/team/Kconfig +++ b/drivers/net/team/Kconfig @@ -15,6 +15,17 @@ menuconfig NET_TEAM if NET_TEAM +config NET_TEAM_MODE_BROADCAST + tristate "Broadcast mode support" + depends on NET_TEAM + ---help--- + Basic mode where packets are transmitted always by all suitable ports. + + All added ports are setup to have team's mac address. + + To compile this team mode as a module, choose M here: the module + will be called team_mode_broadcast. + config NET_TEAM_MODE_ROUNDROBIN tristate "Round-robin mode support" depends on NET_TEAM @@ -22,7 +33,7 @@ config NET_TEAM_MODE_ROUNDROBIN Basic mode where port used for transmitting packets is selected in round-robin fashion using packet counter. - All added ports are setup to have bond's mac address. + All added ports are setup to have team's mac address. To compile this team mode as a module, choose M here: the module will be called team_mode_roundrobin. diff --git a/drivers/net/team/Makefile b/drivers/net/team/Makefile index fb9f4c1c51f..975763014e5 100644 --- a/drivers/net/team/Makefile +++ b/drivers/net/team/Makefile @@ -3,6 +3,7 @@ # obj-$(CONFIG_NET_TEAM) += team.o +obj-$(CONFIG_NET_TEAM_MODE_BROADCAST) += team_mode_broadcast.o obj-$(CONFIG_NET_TEAM_MODE_ROUNDROBIN) += team_mode_roundrobin.o obj-$(CONFIG_NET_TEAM_MODE_ACTIVEBACKUP) += team_mode_activebackup.o obj-$(CONFIG_NET_TEAM_MODE_LOADBALANCE) += team_mode_loadbalance.o diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index c61ae35a53c..87707ab3943 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1,5 +1,5 @@ /* - * net/drivers/team/team.c - Network team device driver + * drivers/net/team/team.c - Network team device driver * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com> * * This program is free software; you can redistribute it and/or modify @@ -18,6 +18,7 @@ #include <linux/ctype.h> #include <linux/notifier.h> #include <linux/netdevice.h> +#include <linux/netpoll.h> #include <linux/if_vlan.h> #include <linux/if_arp.h> #include <linux/socket.h> @@ -26,6 +27,7 @@ #include <net/rtnetlink.h> #include <net/genetlink.h> #include <net/netlink.h> +#include <net/sch_generic.h> #include <linux/if_team.h> #define DRV_NAME "team" @@ -82,14 +84,16 @@ static void team_refresh_port_linkup(struct team_port *port) port->state.linkup; } + /******************* * Options handling *******************/ struct team_option_inst { /* One for each option instance */ struct list_head list; + struct list_head tmp_list; struct team_option *option; - struct team_port *port; /* != NULL if per-port */ + struct team_option_inst_info info; bool changed; bool removed; }; @@ -106,22 +110,6 @@ static struct team_option *__team_find_option(struct team *team, return NULL; } -static int __team_option_inst_add(struct team *team, struct team_option *option, - struct team_port *port) -{ - struct team_option_inst *opt_inst; - - opt_inst = kmalloc(sizeof(*opt_inst), GFP_KERNEL); - if (!opt_inst) - return -ENOMEM; - opt_inst->option = option; - opt_inst->port = port; - opt_inst->changed = true; - opt_inst->removed = false; - list_add_tail(&opt_inst->list, &team->option_inst_list); - return 0; -} - static void __team_option_inst_del(struct team_option_inst *opt_inst) { list_del(&opt_inst->list); @@ -139,14 +127,49 @@ static void __team_option_inst_del_option(struct team *team, } } +static int __team_option_inst_add(struct team *team, struct team_option *option, + struct team_port *port) +{ + struct team_option_inst *opt_inst; + unsigned int array_size; + unsigned int i; + int err; + + array_size = option->array_size; + if (!array_size) + array_size = 1; /* No array but still need one instance */ + + for (i = 0; i < array_size; i++) { + opt_inst = kmalloc(sizeof(*opt_inst), GFP_KERNEL); + if (!opt_inst) + return -ENOMEM; + opt_inst->option = option; + opt_inst->info.port = port; + opt_inst->info.array_index = i; + opt_inst->changed = true; + opt_inst->removed = false; + list_add_tail(&opt_inst->list, &team->option_inst_list); + if (option->init) { + err = option->init(team, &opt_inst->info); + if (err) + return err; + } + + } + return 0; +} + static int __team_option_inst_add_option(struct team *team, struct team_option *option) { struct team_port *port; int err; - if (!option->per_port) - return __team_option_inst_add(team, option, 0); + if (!option->per_port) { + err = __team_option_inst_add(team, option, NULL); + if (err) + goto inst_del_option; + } list_for_each_entry(port, &team->port_list, list) { err = __team_option_inst_add(team, option, port); @@ -180,7 +203,7 @@ static void __team_option_inst_del_port(struct team *team, list_for_each_entry_safe(opt_inst, tmp, &team->option_inst_list, list) { if (opt_inst->option->per_port && - opt_inst->port == port) + opt_inst->info.port == port) __team_option_inst_del(opt_inst); } } @@ -211,7 +234,7 @@ static void __team_option_inst_mark_removed_port(struct team *team, struct team_option_inst *opt_inst; list_for_each_entry(opt_inst, &team->option_inst_list, list) { - if (opt_inst->port == port) { + if (opt_inst->info.port == port) { opt_inst->changed = true; opt_inst->removed = true; } @@ -324,28 +347,12 @@ void team_options_unregister(struct team *team, } EXPORT_SYMBOL(team_options_unregister); -static int team_option_port_add(struct team *team, struct team_port *port) -{ - int err; - - err = __team_option_inst_add_port(team, port); - if (err) - return err; - __team_options_change_check(team); - return 0; -} - -static void team_option_port_del(struct team *team, struct team_port *port) -{ - __team_option_inst_mark_removed_port(team, port); - __team_options_change_check(team); - __team_option_inst_del_port(team, port); -} - static int team_option_get(struct team *team, struct team_option_inst *opt_inst, struct team_gsetter_ctx *ctx) { + if (!opt_inst->option->getter) + return -EOPNOTSUPP; return opt_inst->option->getter(team, ctx); } @@ -353,16 +360,26 @@ static int team_option_set(struct team *team, struct team_option_inst *opt_inst, struct team_gsetter_ctx *ctx) { - int err; + if (!opt_inst->option->setter) + return -EOPNOTSUPP; + return opt_inst->option->setter(team, ctx); +} - err = opt_inst->option->setter(team, ctx); - if (err) - return err; +void team_option_inst_set_change(struct team_option_inst_info *opt_inst_info) +{ + struct team_option_inst *opt_inst; + opt_inst = container_of(opt_inst_info, struct team_option_inst, info); opt_inst->changed = true; +} +EXPORT_SYMBOL(team_option_inst_set_change); + +void team_options_change_check(struct team *team) +{ __team_options_change_check(team); - return err; } +EXPORT_SYMBOL(team_options_change_check); + /**************** * Mode handling @@ -371,13 +388,18 @@ static int team_option_set(struct team *team, static LIST_HEAD(mode_list); static DEFINE_SPINLOCK(mode_list_lock); -static struct team_mode *__find_mode(const char *kind) +struct team_mode_item { + struct list_head list; + const struct team_mode *mode; +}; + +static struct team_mode_item *__find_mode(const char *kind) { - struct team_mode *mode; + struct team_mode_item *mitem; - list_for_each_entry(mode, &mode_list, list) { - if (strcmp(mode->kind, kind) == 0) - return mode; + list_for_each_entry(mitem, &mode_list, list) { + if (strcmp(mitem->mode->kind, kind) == 0) + return mitem; } return NULL; } @@ -392,49 +414,65 @@ static bool is_good_mode_name(const char *name) return true; } -int team_mode_register(struct team_mode *mode) +int team_mode_register(const struct team_mode *mode) { int err = 0; + struct team_mode_item *mitem; if (!is_good_mode_name(mode->kind) || mode->priv_size > TEAM_MODE_PRIV_SIZE) return -EINVAL; + + mitem = kmalloc(sizeof(*mitem), GFP_KERNEL); + if (!mitem) + return -ENOMEM; + spin_lock(&mode_list_lock); if (__find_mode(mode->kind)) { err = -EEXIST; + kfree(mitem); goto unlock; } - list_add_tail(&mode->list, &mode_list); + mitem->mode = mode; + list_add_tail(&mitem->list, &mode_list); unlock: spin_unlock(&mode_list_lock); return err; } EXPORT_SYMBOL(team_mode_register); -int team_mode_unregister(struct team_mode *mode) +void team_mode_unregister(const struct team_mode *mode) { + struct team_mode_item *mitem; + spin_lock(&mode_list_lock); - list_del_init(&mode->list); + mitem = __find_mode(mode->kind); + if (mitem) { + list_del_init(&mitem->list); + kfree(mitem); + } spin_unlock(&mode_list_lock); - return 0; } EXPORT_SYMBOL(team_mode_unregister); -static struct team_mode *team_mode_get(const char *kind) +static const struct team_mode *team_mode_get(const char *kind) { - struct team_mode *mode; + struct team_mode_item *mitem; + const struct team_mode *mode = NULL; spin_lock(&mode_list_lock); - mode = __find_mode(kind); - if (!mode) { + mitem = __find_mode(kind); + if (!mitem) { spin_unlock(&mode_list_lock); request_module("team-mode-%s", kind); spin_lock(&mode_list_lock); - mode = __find_mode(kind); + mitem = __find_mode(kind); } - if (mode) + if (mitem) { + mode = mitem->mode; if (!try_module_get(mode->owner)) mode = NULL; + } spin_unlock(&mode_list_lock); return mode; @@ -458,26 +496,45 @@ rx_handler_result_t team_dummy_receive(struct team *team, return RX_HANDLER_ANOTHER; } -static void team_adjust_ops(struct team *team) +static const struct team_mode __team_no_mode = { + .kind = "*NOMODE*", +}; + +static bool team_is_mode_set(struct team *team) +{ + return team->mode != &__team_no_mode; +} + +static void team_set_no_mode(struct team *team) +{ + team->mode = &__team_no_mode; +} + +static void __team_adjust_ops(struct team *team, int en_port_count) { /* * To avoid checks in rx/tx skb paths, ensure here that non-null and * correct ops are always set. */ - if (list_empty(&team->port_list) || - !team->mode || !team->mode->ops->transmit) + if (!en_port_count || !team_is_mode_set(team) || + !team->mode->ops->transmit) team->ops.transmit = team_dummy_transmit; else team->ops.transmit = team->mode->ops->transmit; - if (list_empty(&team->port_list) || - !team->mode || !team->mode->ops->receive) + if (!en_port_count || !team_is_mode_set(team) || + !team->mode->ops->receive) team->ops.receive = team_dummy_receive; else team->ops.receive = team->mode->ops->receive; } +static void team_adjust_ops(struct team *team) +{ + __team_adjust_ops(team, team->en_port_count); +} + /* * We can benefit from the fact that it's ensured no port is present * at the time of mode change. Therefore no packets are in fly so there's no @@ -487,7 +544,7 @@ static int __team_change_mode(struct team *team, const struct team_mode *new_mode) { /* Check if mode was previously set and do cleanup if so */ - if (team->mode) { + if (team_is_mode_set(team)) { void (*exit_op)(struct team *team) = team->ops.exit; /* Clear ops area so no callback is called any longer */ @@ -497,7 +554,7 @@ static int __team_change_mode(struct team *team, if (exit_op) exit_op(team); team_mode_put(team->mode); - team->mode = NULL; + team_set_no_mode(team); /* zero private data area */ memset(&team->mode_priv, 0, sizeof(struct team) - offsetof(struct team, mode_priv)); @@ -523,7 +580,7 @@ static int __team_change_mode(struct team *team, static int team_change_mode(struct team *team, const char *kind) { - struct team_mode *new_mode; + const struct team_mode *new_mode; struct net_device *dev = team->dev; int err; @@ -532,7 +589,7 @@ static int team_change_mode(struct team *team, const char *kind) return -EBUSY; } - if (team->mode && strcmp(team->mode->kind, kind) == 0) { + if (team_is_mode_set(team) && strcmp(team->mode->kind, kind) == 0) { netdev_err(dev, "Unable to change to the same mode the team is in\n"); return -EINVAL; } @@ -559,8 +616,6 @@ static int team_change_mode(struct team *team, const char *kind) * Rx path frame handler ************************/ -static bool team_port_enabled(struct team_port *port); - /* note: already called with rcu_read_lock */ static rx_handler_result_t team_handle_frame(struct sk_buff **pskb) { @@ -618,11 +673,6 @@ static bool team_port_find(const struct team *team, return false; } -static bool team_port_enabled(struct team_port *port) -{ - return port->index != -1; -} - /* * Enable/disable port by adding to enabled port hashlist and setting * port->index (Might be racy so reader could see incorrect ifindex when @@ -637,6 +687,9 @@ static void team_port_enable(struct team *team, port->index = team->en_port_count++; hlist_add_head_rcu(&port->hlist, team_port_index_hash(team, port->index)); + team_adjust_ops(team); + if (team->ops.port_enabled) + team->ops.port_enabled(team, port); } static void __reconstruct_port_hlist(struct team *team, int rm_index) @@ -656,14 +709,20 @@ static void __reconstruct_port_hlist(struct team *team, int rm_index) static void team_port_disable(struct team *team, struct team_port *port) { - int rm_index = port->index; - if (!team_port_enabled(port)) return; + if (team->ops.port_disabled) + team->ops.port_disabled(team, port); hlist_del_rcu(&port->hlist); - __reconstruct_port_hlist(team, rm_index); - team->en_port_count--; + __reconstruct_port_hlist(team, port->index); port->index = -1; + __team_adjust_ops(team, team->en_port_count - 1); + /* + * Wait until readers see adjusted ops. This ensures that + * readers never see team->en_port_count == 0 + */ + synchronize_rcu(); + team->en_port_count--; } #define TEAM_VLAN_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | \ @@ -675,12 +734,14 @@ static void __team_compute_features(struct team *team) struct team_port *port; u32 vlan_features = TEAM_VLAN_FEATURES; unsigned short max_hard_header_len = ETH_HLEN; + unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE; list_for_each_entry(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, TEAM_VLAN_FEATURES); + dst_release_flag &= port->dev->priv_flags; if (port->dev->hard_header_len > max_hard_header_len) max_hard_header_len = port->dev->hard_header_len; } @@ -688,6 +749,9 @@ static void __team_compute_features(struct team *team) team->dev->vlan_features = vlan_features; team->dev->hard_header_len = max_hard_header_len; + flags = team->dev->priv_flags & ~IFF_XMIT_DST_RELEASE; + team->dev->priv_flags = flags | dst_release_flag; + netdev_change_features(team->dev); } @@ -730,6 +794,58 @@ static void team_port_leave(struct team *team, struct team_port *port) dev_put(team->dev); } +#ifdef CONFIG_NET_POLL_CONTROLLER +static int team_port_enable_netpoll(struct team *team, struct team_port *port) +{ + struct netpoll *np; + int err; + + np = kzalloc(sizeof(*np), GFP_KERNEL); + if (!np) + return -ENOMEM; + + err = __netpoll_setup(np, port->dev); + if (err) { + kfree(np); + return err; + } + port->np = np; + return err; +} + +static void team_port_disable_netpoll(struct team_port *port) +{ + struct netpoll *np = port->np; + + if (!np) + return; + port->np = NULL; + + /* Wait for transmitting packets to finish before freeing. */ + synchronize_rcu_bh(); + __netpoll_cleanup(np); + kfree(np); +} + +static struct netpoll_info *team_netpoll_info(struct team *team) +{ + return team->dev->npinfo; +} + +#else +static int team_port_enable_netpoll(struct team *team, struct team_port *port) +{ + return 0; +} +static void team_port_disable_netpoll(struct team_port *port) +{ +} +static struct netpoll_info *team_netpoll_info(struct team *team) +{ + return NULL; +} +#endif + static void __team_port_change_check(struct team_port *port, bool linkup); static int team_port_add(struct team *team, struct net_device *port_dev) @@ -758,7 +874,8 @@ static int team_port_add(struct team *team, struct net_device *port_dev) return -EBUSY; } - port = kzalloc(sizeof(struct team_port), GFP_KERNEL); + port = kzalloc(sizeof(struct team_port) + team->mode->port_priv_size, + GFP_KERNEL); if (!port) return -ENOMEM; @@ -795,6 +912,15 @@ static int team_port_add(struct team *team, struct net_device *port_dev) goto err_vids_add; } + if (team_netpoll_info(team)) { + err = team_port_enable_netpoll(team, port); + if (err) { + netdev_err(dev, "Failed to enable netpoll on device %s\n", + portname); + goto err_enable_netpoll; + } + } + err = netdev_set_master(port_dev, dev); if (err) { netdev_err(dev, "Device %s failed to set master\n", portname); @@ -809,7 +935,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev) goto err_handler_register; } - err = team_option_port_add(team, port); + err = __team_option_inst_add_port(team, port); if (err) { netdev_err(dev, "Device %s failed to add per-port options\n", portname); @@ -819,9 +945,9 @@ static int team_port_add(struct team *team, struct net_device *port_dev) port->index = -1; team_port_enable(team, port); list_add_tail_rcu(&port->list, &team->port_list); - team_adjust_ops(team); __team_compute_features(team); __team_port_change_check(port, !!netif_carrier_ok(port_dev)); + __team_options_change_check(team); netdev_info(dev, "Port device %s added\n", portname); @@ -834,6 +960,9 @@ err_handler_register: netdev_set_master(port_dev, NULL); err_set_master: + team_port_disable_netpoll(port); + +err_enable_netpoll: vlan_vids_del_by_dev(port_dev, dev); err_vids_add: @@ -865,14 +994,16 @@ static int team_port_del(struct team *team, struct net_device *port_dev) return -ENOENT; } + __team_option_inst_mark_removed_port(team, port); + __team_options_change_check(team); + __team_option_inst_del_port(team, port); port->removed = true; __team_port_change_check(port, false); team_port_disable(team, port); list_del_rcu(&port->list); - team_adjust_ops(team); - team_option_port_del(team, port); netdev_rx_handler_unregister(port_dev); netdev_set_master(port_dev, NULL); + team_port_disable_netpoll(port); vlan_vids_del_by_dev(port_dev, dev); dev_close(port_dev); team_port_leave(team, port); @@ -891,11 +1022,9 @@ static int team_port_del(struct team *team, struct net_device *port_dev) * Net device ops *****************/ -static const char team_no_mode_kind[] = "*NOMODE*"; - static int team_mode_option_get(struct team *team, struct team_gsetter_ctx *ctx) { - ctx->data.str_val = team->mode ? team->mode->kind : team_no_mode_kind; + ctx->data.str_val = team->mode->kind; return 0; } @@ -907,39 +1036,47 @@ static int team_mode_option_set(struct team *team, struct team_gsetter_ctx *ctx) static int team_port_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { - ctx->data.bool_val = team_port_enabled(ctx->port); + struct team_port *port = ctx->info->port; + + ctx->data.bool_val = team_port_enabled(port); return 0; } static int team_port_en_option_set(struct team *team, struct team_gsetter_ctx *ctx) { + struct team_port *port = ctx->info->port; + if (ctx->data.bool_val) - team_port_enable(team, ctx->port); + team_port_enable(team, port); else - team_port_disable(team, ctx->port); + team_port_disable(team, port); return 0; } static int team_user_linkup_option_get(struct team *team, struct team_gsetter_ctx *ctx) { - ctx->data.bool_val = ctx->port->user.linkup; + struct team_port *port = ctx->info->port; + + ctx->data.bool_val = port->user.linkup; return 0; } static int team_user_linkup_option_set(struct team *team, struct team_gsetter_ctx *ctx) { - ctx->port->user.linkup = ctx->data.bool_val; - team_refresh_port_linkup(ctx->port); + struct team_port *port = ctx->info->port; + + port->user.linkup = ctx->data.bool_val; + team_refresh_port_linkup(port); return 0; } static int team_user_linkup_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { - struct team_port *port = ctx->port; + struct team_port *port = ctx->info->port; ctx->data.bool_val = port->user.linkup_enabled; return 0; @@ -948,10 +1085,10 @@ static int team_user_linkup_en_option_get(struct team *team, static int team_user_linkup_en_option_set(struct team *team, struct team_gsetter_ctx *ctx) { - struct team_port *port = ctx->port; + struct team_port *port = ctx->info->port; port->user.linkup_enabled = ctx->data.bool_val; - team_refresh_port_linkup(ctx->port); + team_refresh_port_linkup(port); return 0; } @@ -985,6 +1122,22 @@ static const struct team_option team_options[] = { }, }; +static struct lock_class_key team_netdev_xmit_lock_key; +static struct lock_class_key team_netdev_addr_lock_key; + +static void team_set_lockdep_class_one(struct net_device *dev, + struct netdev_queue *txq, + void *unused) +{ + lockdep_set_class(&txq->_xmit_lock, &team_netdev_xmit_lock_key); +} + +static void team_set_lockdep_class(struct net_device *dev) +{ + lockdep_set_class(&dev->addr_list_lock, &team_netdev_addr_lock_key); + netdev_for_each_tx_queue(dev, team_set_lockdep_class_one, NULL); +} + static int team_init(struct net_device *dev) { struct team *team = netdev_priv(dev); @@ -993,6 +1146,7 @@ static int team_init(struct net_device *dev) team->dev = dev; mutex_init(&team->lock); + team_set_no_mode(team); team->pcpu_stats = alloc_percpu(struct team_pcpu_stats); if (!team->pcpu_stats) @@ -1011,6 +1165,8 @@ static int team_init(struct net_device *dev) goto err_options_register; netif_carrier_off(dev); + team_set_lockdep_class(dev); + return 0; err_options_register: @@ -1079,6 +1235,29 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } +static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb) +{ + /* + * This helper function exists to help dev_pick_tx get the correct + * destination queue. Using a helper function skips a call to + * skb_tx_hash and will put the skbs in the queue we expect on their + * way down to the team driver. + */ + u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; + + /* + * Save the original txq to restore before passing to the driver + */ + qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; + + if (unlikely(txq >= dev->real_num_tx_queues)) { + do { + txq -= dev->real_num_tx_queues; + } while (txq >= dev->real_num_tx_queues); + } + return txq; +} + static void team_change_rx_flags(struct net_device *dev, int change) { struct team *team = netdev_priv(dev); @@ -1116,10 +1295,11 @@ static int team_set_mac_address(struct net_device *dev, void *p) { struct team *team = netdev_priv(dev); struct team_port *port; - struct sockaddr *addr = p; + int err; - dev->addr_assign_type &= ~NET_ADDR_RANDOM; - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); + err = eth_mac_addr(dev, p); + if (err) + return err; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) if (team->ops.port_change_mac) @@ -1240,6 +1420,48 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, uint16_t vid) return 0; } +#ifdef CONFIG_NET_POLL_CONTROLLER +static void team_poll_controller(struct net_device *dev) +{ +} + +static void __team_netpoll_cleanup(struct team *team) +{ + struct team_port *port; + + list_for_each_entry(port, &team->port_list, list) + team_port_disable_netpoll(port); +} + +static void team_netpoll_cleanup(struct net_device *dev) +{ + struct team *team = netdev_priv(dev); + + mutex_lock(&team->lock); + __team_netpoll_cleanup(team); + mutex_unlock(&team->lock); +} + +static int team_netpoll_setup(struct net_device *dev, + struct netpoll_info *npifo) +{ + struct team *team = netdev_priv(dev); + struct team_port *port; + int err = 0; + + mutex_lock(&team->lock); + list_for_each_entry(port, &team->port_list, list) { + err = team_port_enable_netpoll(team, port); + if (err) { + __team_netpoll_cleanup(team); + break; + } + } + mutex_unlock(&team->lock); + return err; +} +#endif + static int team_add_slave(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); @@ -1289,6 +1511,7 @@ static const struct net_device_ops team_netdev_ops = { .ndo_open = team_open, .ndo_stop = team_close, .ndo_start_xmit = team_xmit, + .ndo_select_queue = team_select_queue, .ndo_change_rx_flags = team_change_rx_flags, .ndo_set_rx_mode = team_set_rx_mode, .ndo_set_mac_address = team_set_mac_address, @@ -1296,6 +1519,11 @@ static const struct net_device_ops team_netdev_ops = { .ndo_get_stats64 = team_get_stats64, .ndo_vlan_rx_add_vid = team_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = team_vlan_rx_kill_vid, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = team_poll_controller, + .ndo_netpoll_setup = team_netpoll_setup, + .ndo_netpoll_cleanup = team_netpoll_cleanup, +#endif .ndo_add_slave = team_add_slave, .ndo_del_slave = team_del_slave, .ndo_fix_features = team_fix_features, @@ -1321,7 +1549,7 @@ static void team_setup(struct net_device *dev) * bring us to promisc mode in case a unicast addr is added. * Let this up to underlay drivers. */ - dev->priv_flags |= IFF_UNICAST_FLT; + dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE; dev->features |= NETIF_F_LLTX; dev->features |= NETIF_F_GRO; @@ -1358,12 +1586,24 @@ static int team_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } +static unsigned int team_get_num_tx_queues(void) +{ + return TEAM_DEFAULT_NUM_TX_QUEUES; +} + +static unsigned int team_get_num_rx_queues(void) +{ + return TEAM_DEFAULT_NUM_RX_QUEUES; +} + static struct rtnl_link_ops team_link_ops __read_mostly = { - .kind = DRV_NAME, - .priv_size = sizeof(struct team), - .setup = team_setup, - .newlink = team_newlink, - .validate = team_validate, + .kind = DRV_NAME, + .priv_size = sizeof(struct team), + .setup = team_setup, + .newlink = team_newlink, + .validate = team_validate, + .get_num_tx_queues = team_get_num_tx_queues, + .get_num_rx_queues = team_get_num_rx_queues, }; @@ -1404,7 +1644,7 @@ static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) void *hdr; int err; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -1466,7 +1706,7 @@ static int team_nl_send_generic(struct genl_info *info, struct team *team, struct sk_buff *skb; int err; - skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; @@ -1482,16 +1722,128 @@ err_fill: return err; } -static int team_nl_fill_options_get(struct sk_buff *skb, - u32 pid, u32 seq, int flags, - struct team *team, bool fillall) +typedef int team_nl_send_func_t(struct sk_buff *skb, + struct team *team, u32 pid); + +static int team_nl_send_unicast(struct sk_buff *skb, struct team *team, u32 pid) +{ + return genlmsg_unicast(dev_net(team->dev), skb, pid); +} + +static int team_nl_fill_one_option_get(struct sk_buff *skb, struct team *team, + struct team_option_inst *opt_inst) +{ + struct nlattr *option_item; + struct team_option *option = opt_inst->option; + struct team_option_inst_info *opt_inst_info = &opt_inst->info; + struct team_gsetter_ctx ctx; + int err; + + ctx.info = opt_inst_info; + err = team_option_get(team, opt_inst, &ctx); + if (err) + return err; + + option_item = nla_nest_start(skb, TEAM_ATTR_ITEM_OPTION); + if (!option_item) + return -EMSGSIZE; + + if (nla_put_string(skb, TEAM_ATTR_OPTION_NAME, option->name)) + goto nest_cancel; + if (opt_inst_info->port && + nla_put_u32(skb, TEAM_ATTR_OPTION_PORT_IFINDEX, + opt_inst_info->port->dev->ifindex)) + goto nest_cancel; + if (opt_inst->option->array_size && + nla_put_u32(skb, TEAM_ATTR_OPTION_ARRAY_INDEX, + opt_inst_info->array_index)) + goto nest_cancel; + + switch (option->type) { + case TEAM_OPTION_TYPE_U32: + if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_U32)) + goto nest_cancel; + if (nla_put_u32(skb, TEAM_ATTR_OPTION_DATA, ctx.data.u32_val)) + goto nest_cancel; + break; + case TEAM_OPTION_TYPE_STRING: + if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_STRING)) + goto nest_cancel; + if (nla_put_string(skb, TEAM_ATTR_OPTION_DATA, + ctx.data.str_val)) + goto nest_cancel; + break; + case TEAM_OPTION_TYPE_BINARY: + if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_BINARY)) + goto nest_cancel; + if (nla_put(skb, TEAM_ATTR_OPTION_DATA, ctx.data.bin_val.len, + ctx.data.bin_val.ptr)) + goto nest_cancel; + break; + case TEAM_OPTION_TYPE_BOOL: + if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_FLAG)) + goto nest_cancel; + if (ctx.data.bool_val && + nla_put_flag(skb, TEAM_ATTR_OPTION_DATA)) + goto nest_cancel; + break; + default: + BUG(); + } + if (opt_inst->removed && nla_put_flag(skb, TEAM_ATTR_OPTION_REMOVED)) + goto nest_cancel; + if (opt_inst->changed) { + if (nla_put_flag(skb, TEAM_ATTR_OPTION_CHANGED)) + goto nest_cancel; + opt_inst->changed = false; + } + nla_nest_end(skb, option_item); + return 0; + +nest_cancel: + nla_nest_cancel(skb, option_item); + return -EMSGSIZE; +} + +static int __send_and_alloc_skb(struct sk_buff **pskb, + struct team *team, u32 pid, + team_nl_send_func_t *send_func) +{ + int err; + + if (*pskb) { + err = send_func(*pskb, team, pid); + if (err) + return err; + } + *pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!*pskb) + return -ENOMEM; + return 0; +} + +static int team_nl_send_options_get(struct team *team, u32 pid, u32 seq, + int flags, team_nl_send_func_t *send_func, + struct list_head *sel_opt_inst_list) { struct nlattr *option_list; + struct nlmsghdr *nlh; void *hdr; struct team_option_inst *opt_inst; int err; + struct sk_buff *skb = NULL; + bool incomplete; + int i; - hdr = genlmsg_put(skb, pid, seq, &team_nl_family, flags, + opt_inst = list_first_entry(sel_opt_inst_list, + struct team_option_inst, tmp_list); + +start_again: + err = __send_and_alloc_skb(&skb, team, pid, send_func); + if (err) + return err; + + hdr = genlmsg_put(skb, pid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_OPTIONS_GET); if (IS_ERR(hdr)) return PTR_ERR(hdr); @@ -1500,122 +1852,80 @@ static int team_nl_fill_options_get(struct sk_buff *skb, goto nla_put_failure; option_list = nla_nest_start(skb, TEAM_ATTR_LIST_OPTION); if (!option_list) - return -EMSGSIZE; - - list_for_each_entry(opt_inst, &team->option_inst_list, list) { - struct nlattr *option_item; - struct team_option *option = opt_inst->option; - struct team_gsetter_ctx ctx; + goto nla_put_failure; - /* Include only changed options if fill all mode is not on */ - if (!fillall && !opt_inst->changed) - continue; - option_item = nla_nest_start(skb, TEAM_ATTR_ITEM_OPTION); - if (!option_item) - goto nla_put_failure; - if (nla_put_string(skb, TEAM_ATTR_OPTION_NAME, option->name)) - goto nla_put_failure; - if (opt_inst->changed) { - if (nla_put_flag(skb, TEAM_ATTR_OPTION_CHANGED)) - goto nla_put_failure; - opt_inst->changed = false; - } - if (opt_inst->removed && - nla_put_flag(skb, TEAM_ATTR_OPTION_REMOVED)) - goto nla_put_failure; - if (opt_inst->port && - nla_put_u32(skb, TEAM_ATTR_OPTION_PORT_IFINDEX, - opt_inst->port->dev->ifindex)) - goto nla_put_failure; - ctx.port = opt_inst->port; - switch (option->type) { - case TEAM_OPTION_TYPE_U32: - if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_U32)) - goto nla_put_failure; - err = team_option_get(team, opt_inst, &ctx); - if (err) - goto errout; - if (nla_put_u32(skb, TEAM_ATTR_OPTION_DATA, - ctx.data.u32_val)) - goto nla_put_failure; - break; - case TEAM_OPTION_TYPE_STRING: - if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_STRING)) - goto nla_put_failure; - err = team_option_get(team, opt_inst, &ctx); - if (err) - goto errout; - if (nla_put_string(skb, TEAM_ATTR_OPTION_DATA, - ctx.data.str_val)) - goto nla_put_failure; - break; - case TEAM_OPTION_TYPE_BINARY: - if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_BINARY)) - goto nla_put_failure; - err = team_option_get(team, opt_inst, &ctx); - if (err) - goto errout; - if (nla_put(skb, TEAM_ATTR_OPTION_DATA, - ctx.data.bin_val.len, ctx.data.bin_val.ptr)) - goto nla_put_failure; - break; - case TEAM_OPTION_TYPE_BOOL: - if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_FLAG)) - goto nla_put_failure; - err = team_option_get(team, opt_inst, &ctx); - if (err) - goto errout; - if (ctx.data.bool_val && - nla_put_flag(skb, TEAM_ATTR_OPTION_DATA)) - goto nla_put_failure; - break; - default: - BUG(); + i = 0; + incomplete = false; + list_for_each_entry_from(opt_inst, sel_opt_inst_list, tmp_list) { + err = team_nl_fill_one_option_get(skb, team, opt_inst); + if (err) { + if (err == -EMSGSIZE) { + if (!i) + goto errout; + incomplete = true; + break; + } + goto errout; } - nla_nest_end(skb, option_item); + i++; } nla_nest_end(skb, option_list); - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + if (incomplete) + goto start_again; + +send_done: + nlh = nlmsg_put(skb, pid, seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = __send_and_alloc_skb(&skb, team, pid, send_func); + if (err) + goto errout; + goto send_done; + } + + return send_func(skb, team, pid); nla_put_failure: err = -EMSGSIZE; errout: genlmsg_cancel(skb, hdr); + nlmsg_free(skb); return err; } -static int team_nl_fill_options_get_all(struct sk_buff *skb, - struct genl_info *info, int flags, - struct team *team) -{ - return team_nl_fill_options_get(skb, info->snd_pid, - info->snd_seq, NLM_F_ACK, - team, true); -} - static int team_nl_cmd_options_get(struct sk_buff *skb, struct genl_info *info) { struct team *team; + struct team_option_inst *opt_inst; int err; + LIST_HEAD(sel_opt_inst_list); team = team_nl_team_get(info); if (!team) return -EINVAL; - err = team_nl_send_generic(info, team, team_nl_fill_options_get_all); + list_for_each_entry(opt_inst, &team->option_inst_list, list) + list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list); + err = team_nl_send_options_get(team, info->snd_pid, info->snd_seq, + NLM_F_ACK, team_nl_send_unicast, + &sel_opt_inst_list); team_nl_team_put(team); return err; } +static int team_nl_send_event_options_get(struct team *team, + struct list_head *sel_opt_inst_list); + static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) { struct team *team; int err = 0; int i; struct nlattr *nl_option; + LIST_HEAD(opt_inst_list); team = team_nl_team_get(info); if (!team) @@ -1629,10 +1939,12 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) nla_for_each_nested(nl_option, info->attrs[TEAM_ATTR_LIST_OPTION], i) { struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1]; - struct nlattr *attr_port_ifindex; + struct nlattr *attr; struct nlattr *attr_data; enum team_option_type opt_type; int opt_port_ifindex = 0; /* != 0 for per-port options */ + u32 opt_array_index = 0; + bool opt_is_array = false; struct team_option_inst *opt_inst; char *opt_name; bool opt_found = false; @@ -1674,23 +1986,33 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) } opt_name = nla_data(opt_attrs[TEAM_ATTR_OPTION_NAME]); - attr_port_ifindex = opt_attrs[TEAM_ATTR_OPTION_PORT_IFINDEX]; - if (attr_port_ifindex) - opt_port_ifindex = nla_get_u32(attr_port_ifindex); + attr = opt_attrs[TEAM_ATTR_OPTION_PORT_IFINDEX]; + if (attr) + opt_port_ifindex = nla_get_u32(attr); + + attr = opt_attrs[TEAM_ATTR_OPTION_ARRAY_INDEX]; + if (attr) { + opt_is_array = true; + opt_array_index = nla_get_u32(attr); + } list_for_each_entry(opt_inst, &team->option_inst_list, list) { struct team_option *option = opt_inst->option; struct team_gsetter_ctx ctx; + struct team_option_inst_info *opt_inst_info; int tmp_ifindex; - tmp_ifindex = opt_inst->port ? - opt_inst->port->dev->ifindex : 0; + opt_inst_info = &opt_inst->info; + tmp_ifindex = opt_inst_info->port ? + opt_inst_info->port->dev->ifindex : 0; if (option->type != opt_type || strcmp(option->name, opt_name) || - tmp_ifindex != opt_port_ifindex) + tmp_ifindex != opt_port_ifindex || + (option->array_size && !opt_is_array) || + opt_inst_info->array_index != opt_array_index) continue; opt_found = true; - ctx.port = opt_inst->port; + ctx.info = opt_inst_info; switch (opt_type) { case TEAM_OPTION_TYPE_U32: ctx.data.u32_val = nla_get_u32(attr_data); @@ -1715,6 +2037,8 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) err = team_option_set(team, opt_inst, &ctx); if (err) goto team_put; + opt_inst->changed = true; + list_add(&opt_inst->tmp_list, &opt_inst_list); } if (!opt_found) { err = -ENOENT; @@ -1722,6 +2046,8 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) } } + err = team_nl_send_event_options_get(team, &opt_inst_list); + team_put: team_nl_team_put(team); @@ -1746,7 +2072,7 @@ static int team_nl_fill_port_list_get(struct sk_buff *skb, goto nla_put_failure; port_list = nla_nest_start(skb, TEAM_ATTR_LIST_PORT); if (!port_list) - return -EMSGSIZE; + goto nla_put_failure; list_for_each_entry(port, &team->port_list, list) { struct nlattr *port_item; @@ -1838,27 +2164,18 @@ static struct genl_multicast_group team_change_event_mcgrp = { .name = TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME, }; -static int team_nl_send_event_options_get(struct team *team) +static int team_nl_send_multicast(struct sk_buff *skb, + struct team *team, u32 pid) { - struct sk_buff *skb; - int err; - struct net *net = dev_net(team->dev); - - skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - return -ENOMEM; - - err = team_nl_fill_options_get(skb, 0, 0, 0, team, false); - if (err < 0) - goto err_fill; - - err = genlmsg_multicast_netns(net, skb, 0, team_change_event_mcgrp.id, - GFP_KERNEL); - return err; + return genlmsg_multicast_netns(dev_net(team->dev), skb, 0, + team_change_event_mcgrp.id, GFP_KERNEL); +} -err_fill: - nlmsg_free(skb); - return err; +static int team_nl_send_event_options_get(struct team *team, + struct list_head *sel_opt_inst_list) +{ + return team_nl_send_options_get(team, 0, 0, 0, team_nl_send_multicast, + sel_opt_inst_list); } static int team_nl_send_event_port_list_get(struct team *team) @@ -1867,7 +2184,7 @@ static int team_nl_send_event_port_list_get(struct team *team) int err; struct net *net = dev_net(team->dev); - skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; @@ -1918,10 +2235,17 @@ static void team_nl_fini(void) static void __team_options_change_check(struct team *team) { int err; + struct team_option_inst *opt_inst; + LIST_HEAD(sel_opt_inst_list); - err = team_nl_send_event_options_get(team); + list_for_each_entry(opt_inst, &team->option_inst_list, list) { + if (opt_inst->changed) + list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list); + } + err = team_nl_send_event_options_get(team, &sel_opt_inst_list); if (err) - netdev_warn(team->dev, "Failed to send options change via netlink\n"); + netdev_warn(team->dev, "Failed to send options change via netlink (err %d)\n", + err); } /* rtnl lock is held */ @@ -1965,6 +2289,7 @@ static void team_port_change_check(struct team_port *port, bool linkup) mutex_unlock(&team->lock); } + /************************************ * Net device notifier event handler ************************************/ diff --git a/drivers/net/team/team_mode_activebackup.c b/drivers/net/team/team_mode_activebackup.c index fd6bd03aaa8..6262b4defd9 100644 --- a/drivers/net/team/team_mode_activebackup.c +++ b/drivers/net/team/team_mode_activebackup.c @@ -1,5 +1,5 @@ /* - * net/drivers/team/team_mode_activebackup.c - Active-backup mode for team + * drivers/net/team/team_mode_activebackup.c - Active-backup mode for team * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com> * * This program is free software; you can redistribute it and/or modify @@ -40,11 +40,10 @@ static bool ab_transmit(struct team *team, struct sk_buff *skb) { struct team_port *active_port; - active_port = rcu_dereference(ab_priv(team)->active_port); + active_port = rcu_dereference_bh(ab_priv(team)->active_port); if (unlikely(!active_port)) goto drop; - skb->dev = active_port->dev; - if (dev_queue_xmit(skb)) + if (team_dev_queue_xmit(team, active_port, skb)) return false; return true; @@ -61,8 +60,12 @@ static void ab_port_leave(struct team *team, struct team_port *port) static int ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx) { - if (ab_priv(team)->active_port) - ctx->data.u32_val = ab_priv(team)->active_port->dev->ifindex; + struct team_port *active_port; + + active_port = rcu_dereference_protected(ab_priv(team)->active_port, + lockdep_is_held(&team->lock)); + if (active_port) + ctx->data.u32_val = active_port->dev->ifindex; else ctx->data.u32_val = 0; return 0; @@ -108,7 +111,7 @@ static const struct team_mode_ops ab_mode_ops = { .port_leave = ab_port_leave, }; -static struct team_mode ab_mode = { +static const struct team_mode ab_mode = { .kind = "activebackup", .owner = THIS_MODULE, .priv_size = sizeof(struct ab_priv), diff --git a/drivers/net/team/team_mode_broadcast.c b/drivers/net/team/team_mode_broadcast.c new file mode 100644 index 00000000000..c96e4d2967f --- /dev/null +++ b/drivers/net/team/team_mode_broadcast.c @@ -0,0 +1,87 @@ +/* + * drivers/net/team/team_mode_broadcast.c - Broadcast mode for team + * Copyright (c) 2012 Jiri Pirko <jpirko@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/netdevice.h> +#include <linux/if_team.h> + +static bool bc_transmit(struct team *team, struct sk_buff *skb) +{ + struct team_port *cur; + struct team_port *last = NULL; + struct sk_buff *skb2; + bool ret; + bool sum_ret = false; + + list_for_each_entry_rcu(cur, &team->port_list, list) { + if (team_port_txable(cur)) { + if (last) { + skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2) { + ret = team_dev_queue_xmit(team, last, + skb2); + if (!sum_ret) + sum_ret = ret; + } + } + last = cur; + } + } + if (last) { + ret = team_dev_queue_xmit(team, last, skb); + if (!sum_ret) + sum_ret = ret; + } + return sum_ret; +} + +static int bc_port_enter(struct team *team, struct team_port *port) +{ + return team_port_set_team_mac(port); +} + +static void bc_port_change_mac(struct team *team, struct team_port *port) +{ + team_port_set_team_mac(port); +} + +static const struct team_mode_ops bc_mode_ops = { + .transmit = bc_transmit, + .port_enter = bc_port_enter, + .port_change_mac = bc_port_change_mac, +}; + +static const struct team_mode bc_mode = { + .kind = "broadcast", + .owner = THIS_MODULE, + .ops = &bc_mode_ops, +}; + +static int __init bc_init_module(void) +{ + return team_mode_register(&bc_mode); +} + +static void __exit bc_cleanup_module(void) +{ + team_mode_unregister(&bc_mode); +} + +module_init(bc_init_module); +module_exit(bc_cleanup_module); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>"); +MODULE_DESCRIPTION("Broadcast mode for team"); +MODULE_ALIAS("team-mode-broadcast"); diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c index 86e8183c8e3..cdc31b5ea15 100644 --- a/drivers/net/team/team_mode_loadbalance.c +++ b/drivers/net/team/team_mode_loadbalance.c @@ -17,34 +17,209 @@ #include <linux/filter.h> #include <linux/if_team.h> +struct lb_priv; + +typedef struct team_port *lb_select_tx_port_func_t(struct team *, + struct lb_priv *, + struct sk_buff *, + unsigned char); + +#define LB_TX_HASHTABLE_SIZE 256 /* hash is a char */ + +struct lb_stats { + u64 tx_bytes; +}; + +struct lb_pcpu_stats { + struct lb_stats hash_stats[LB_TX_HASHTABLE_SIZE]; + struct u64_stats_sync syncp; +}; + +struct lb_stats_info { + struct lb_stats stats; + struct lb_stats last_stats; + struct team_option_inst_info *opt_inst_info; +}; + +struct lb_port_mapping { + struct team_port __rcu *port; + struct team_option_inst_info *opt_inst_info; +}; + +struct lb_priv_ex { + struct team *team; + struct lb_port_mapping tx_hash_to_port_mapping[LB_TX_HASHTABLE_SIZE]; + struct sock_fprog *orig_fprog; + struct { + unsigned int refresh_interval; /* in tenths of second */ + struct delayed_work refresh_dw; + struct lb_stats_info info[LB_TX_HASHTABLE_SIZE]; + } stats; +}; + struct lb_priv { struct sk_filter __rcu *fp; - struct sock_fprog *orig_fprog; + lb_select_tx_port_func_t __rcu *select_tx_port_func; + struct lb_pcpu_stats __percpu *pcpu_stats; + struct lb_priv_ex *ex; /* priv extension */ }; -static struct lb_priv *lb_priv(struct team *team) +static struct lb_priv *get_lb_priv(struct team *team) { return (struct lb_priv *) &team->mode_priv; } -static bool lb_transmit(struct team *team, struct sk_buff *skb) +struct lb_port_priv { + struct lb_stats __percpu *pcpu_stats; + struct lb_stats_info stats_info; +}; + +static struct lb_port_priv *get_lb_port_priv(struct team_port *port) +{ + return (struct lb_port_priv *) &port->mode_priv; +} + +#define LB_HTPM_PORT_BY_HASH(lp_priv, hash) \ + (lb_priv)->ex->tx_hash_to_port_mapping[hash].port + +#define LB_HTPM_OPT_INST_INFO_BY_HASH(lp_priv, hash) \ + (lb_priv)->ex->tx_hash_to_port_mapping[hash].opt_inst_info + +static void lb_tx_hash_to_port_mapping_null_port(struct team *team, + struct team_port *port) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + bool changed = false; + int i; + + for (i = 0; i < LB_TX_HASHTABLE_SIZE; i++) { + struct lb_port_mapping *pm; + + pm = &lb_priv->ex->tx_hash_to_port_mapping[i]; + if (rcu_access_pointer(pm->port) == port) { + RCU_INIT_POINTER(pm->port, NULL); + team_option_inst_set_change(pm->opt_inst_info); + changed = true; + } + } + if (changed) + team_options_change_check(team); +} + +/* Basic tx selection based solely by hash */ +static struct team_port *lb_hash_select_tx_port(struct team *team, + struct lb_priv *lb_priv, + struct sk_buff *skb, + unsigned char hash) { - struct sk_filter *fp; - struct team_port *port; - unsigned int hash; int port_index; - fp = rcu_dereference(lb_priv(team)->fp); - if (unlikely(!fp)) - goto drop; - hash = SK_RUN_FILTER(fp, skb); port_index = hash % team->en_port_count; - port = team_get_port_by_index_rcu(team, port_index); + return team_get_port_by_index_rcu(team, port_index); +} + +/* Hash to port mapping select tx port */ +static struct team_port *lb_htpm_select_tx_port(struct team *team, + struct lb_priv *lb_priv, + struct sk_buff *skb, + unsigned char hash) +{ + return rcu_dereference_bh(LB_HTPM_PORT_BY_HASH(lb_priv, hash)); +} + +struct lb_select_tx_port { + char *name; + lb_select_tx_port_func_t *func; +}; + +static const struct lb_select_tx_port lb_select_tx_port_list[] = { + { + .name = "hash", + .func = lb_hash_select_tx_port, + }, + { + .name = "hash_to_port_mapping", + .func = lb_htpm_select_tx_port, + }, +}; +#define LB_SELECT_TX_PORT_LIST_COUNT ARRAY_SIZE(lb_select_tx_port_list) + +static char *lb_select_tx_port_get_name(lb_select_tx_port_func_t *func) +{ + int i; + + for (i = 0; i < LB_SELECT_TX_PORT_LIST_COUNT; i++) { + const struct lb_select_tx_port *item; + + item = &lb_select_tx_port_list[i]; + if (item->func == func) + return item->name; + } + return NULL; +} + +static lb_select_tx_port_func_t *lb_select_tx_port_get_func(const char *name) +{ + int i; + + for (i = 0; i < LB_SELECT_TX_PORT_LIST_COUNT; i++) { + const struct lb_select_tx_port *item; + + item = &lb_select_tx_port_list[i]; + if (!strcmp(item->name, name)) + return item->func; + } + return NULL; +} + +static unsigned int lb_get_skb_hash(struct lb_priv *lb_priv, + struct sk_buff *skb) +{ + struct sk_filter *fp; + uint32_t lhash; + unsigned char *c; + + fp = rcu_dereference_bh(lb_priv->fp); + if (unlikely(!fp)) + return 0; + lhash = SK_RUN_FILTER(fp, skb); + c = (char *) &lhash; + return c[0] ^ c[1] ^ c[2] ^ c[3]; +} + +static void lb_update_tx_stats(unsigned int tx_bytes, struct lb_priv *lb_priv, + struct lb_port_priv *lb_port_priv, + unsigned char hash) +{ + struct lb_pcpu_stats *pcpu_stats; + struct lb_stats *port_stats; + struct lb_stats *hash_stats; + + pcpu_stats = this_cpu_ptr(lb_priv->pcpu_stats); + port_stats = this_cpu_ptr(lb_port_priv->pcpu_stats); + hash_stats = &pcpu_stats->hash_stats[hash]; + u64_stats_update_begin(&pcpu_stats->syncp); + port_stats->tx_bytes += tx_bytes; + hash_stats->tx_bytes += tx_bytes; + u64_stats_update_end(&pcpu_stats->syncp); +} + +static bool lb_transmit(struct team *team, struct sk_buff *skb) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + lb_select_tx_port_func_t *select_tx_port_func; + struct team_port *port; + unsigned char hash; + unsigned int tx_bytes = skb->len; + + hash = lb_get_skb_hash(lb_priv, skb); + select_tx_port_func = rcu_dereference_bh(lb_priv->select_tx_port_func); + port = select_tx_port_func(team, lb_priv, skb, hash); if (unlikely(!port)) goto drop; - skb->dev = port->dev; - if (dev_queue_xmit(skb)) + if (team_dev_queue_xmit(team, port, skb)) return false; + lb_update_tx_stats(tx_bytes, lb_priv, get_lb_port_priv(port), hash); return true; drop: @@ -54,14 +229,16 @@ drop: static int lb_bpf_func_get(struct team *team, struct team_gsetter_ctx *ctx) { - if (!lb_priv(team)->orig_fprog) { + struct lb_priv *lb_priv = get_lb_priv(team); + + if (!lb_priv->ex->orig_fprog) { ctx->data.bin_val.len = 0; ctx->data.bin_val.ptr = NULL; return 0; } - ctx->data.bin_val.len = lb_priv(team)->orig_fprog->len * + ctx->data.bin_val.len = lb_priv->ex->orig_fprog->len * sizeof(struct sock_filter); - ctx->data.bin_val.ptr = lb_priv(team)->orig_fprog->filter; + ctx->data.bin_val.ptr = lb_priv->ex->orig_fprog->filter; return 0; } @@ -94,7 +271,9 @@ static void __fprog_destroy(struct sock_fprog *fprog) static int lb_bpf_func_set(struct team *team, struct team_gsetter_ctx *ctx) { + struct lb_priv *lb_priv = get_lb_priv(team); struct sk_filter *fp = NULL; + struct sk_filter *orig_fp; struct sock_fprog *fprog = NULL; int err; @@ -110,14 +289,238 @@ static int lb_bpf_func_set(struct team *team, struct team_gsetter_ctx *ctx) } } - if (lb_priv(team)->orig_fprog) { + if (lb_priv->ex->orig_fprog) { /* Clear old filter data */ - __fprog_destroy(lb_priv(team)->orig_fprog); - sk_unattached_filter_destroy(lb_priv(team)->fp); + __fprog_destroy(lb_priv->ex->orig_fprog); + orig_fp = rcu_dereference_protected(lb_priv->fp, + lockdep_is_held(&team->lock)); + sk_unattached_filter_destroy(orig_fp); } - rcu_assign_pointer(lb_priv(team)->fp, fp); - lb_priv(team)->orig_fprog = fprog; + rcu_assign_pointer(lb_priv->fp, fp); + lb_priv->ex->orig_fprog = fprog; + return 0; +} + +static int lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + lb_select_tx_port_func_t *func; + char *name; + + func = rcu_dereference_protected(lb_priv->select_tx_port_func, + lockdep_is_held(&team->lock)); + name = lb_select_tx_port_get_name(func); + BUG_ON(!name); + ctx->data.str_val = name; + return 0; +} + +static int lb_tx_method_set(struct team *team, struct team_gsetter_ctx *ctx) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + lb_select_tx_port_func_t *func; + + func = lb_select_tx_port_get_func(ctx->data.str_val); + if (!func) + return -EINVAL; + rcu_assign_pointer(lb_priv->select_tx_port_func, func); + return 0; +} + +static int lb_tx_hash_to_port_mapping_init(struct team *team, + struct team_option_inst_info *info) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + unsigned char hash = info->array_index; + + LB_HTPM_OPT_INST_INFO_BY_HASH(lb_priv, hash) = info; + return 0; +} + +static int lb_tx_hash_to_port_mapping_get(struct team *team, + struct team_gsetter_ctx *ctx) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + struct team_port *port; + unsigned char hash = ctx->info->array_index; + + port = LB_HTPM_PORT_BY_HASH(lb_priv, hash); + ctx->data.u32_val = port ? port->dev->ifindex : 0; + return 0; +} + +static int lb_tx_hash_to_port_mapping_set(struct team *team, + struct team_gsetter_ctx *ctx) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + struct team_port *port; + unsigned char hash = ctx->info->array_index; + + list_for_each_entry(port, &team->port_list, list) { + if (ctx->data.u32_val == port->dev->ifindex && + team_port_enabled(port)) { + rcu_assign_pointer(LB_HTPM_PORT_BY_HASH(lb_priv, hash), + port); + return 0; + } + } + return -ENODEV; +} + +static int lb_hash_stats_init(struct team *team, + struct team_option_inst_info *info) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + unsigned char hash = info->array_index; + + lb_priv->ex->stats.info[hash].opt_inst_info = info; + return 0; +} + +static int lb_hash_stats_get(struct team *team, struct team_gsetter_ctx *ctx) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + unsigned char hash = ctx->info->array_index; + + ctx->data.bin_val.ptr = &lb_priv->ex->stats.info[hash].stats; + ctx->data.bin_val.len = sizeof(struct lb_stats); + return 0; +} + +static int lb_port_stats_init(struct team *team, + struct team_option_inst_info *info) +{ + struct team_port *port = info->port; + struct lb_port_priv *lb_port_priv = get_lb_port_priv(port); + + lb_port_priv->stats_info.opt_inst_info = info; + return 0; +} + +static int lb_port_stats_get(struct team *team, struct team_gsetter_ctx *ctx) +{ + struct team_port *port = ctx->info->port; + struct lb_port_priv *lb_port_priv = get_lb_port_priv(port); + + ctx->data.bin_val.ptr = &lb_port_priv->stats_info.stats; + ctx->data.bin_val.len = sizeof(struct lb_stats); + return 0; +} + +static void __lb_stats_info_refresh_prepare(struct lb_stats_info *s_info) +{ + memcpy(&s_info->last_stats, &s_info->stats, sizeof(struct lb_stats)); + memset(&s_info->stats, 0, sizeof(struct lb_stats)); +} + +static bool __lb_stats_info_refresh_check(struct lb_stats_info *s_info, + struct team *team) +{ + if (memcmp(&s_info->last_stats, &s_info->stats, + sizeof(struct lb_stats))) { + team_option_inst_set_change(s_info->opt_inst_info); + return true; + } + return false; +} + +static void __lb_one_cpu_stats_add(struct lb_stats *acc_stats, + struct lb_stats *cpu_stats, + struct u64_stats_sync *syncp) +{ + unsigned int start; + struct lb_stats tmp; + + do { + start = u64_stats_fetch_begin_bh(syncp); + tmp.tx_bytes = cpu_stats->tx_bytes; + } while (u64_stats_fetch_retry_bh(syncp, start)); + acc_stats->tx_bytes += tmp.tx_bytes; +} + +static void lb_stats_refresh(struct work_struct *work) +{ + struct team *team; + struct lb_priv *lb_priv; + struct lb_priv_ex *lb_priv_ex; + struct lb_pcpu_stats *pcpu_stats; + struct lb_stats *stats; + struct lb_stats_info *s_info; + struct team_port *port; + bool changed = false; + int i; + int j; + + lb_priv_ex = container_of(work, struct lb_priv_ex, + stats.refresh_dw.work); + + team = lb_priv_ex->team; + lb_priv = get_lb_priv(team); + + if (!mutex_trylock(&team->lock)) { + schedule_delayed_work(&lb_priv_ex->stats.refresh_dw, 0); + return; + } + + for (j = 0; j < LB_TX_HASHTABLE_SIZE; j++) { + s_info = &lb_priv->ex->stats.info[j]; + __lb_stats_info_refresh_prepare(s_info); + for_each_possible_cpu(i) { + pcpu_stats = per_cpu_ptr(lb_priv->pcpu_stats, i); + stats = &pcpu_stats->hash_stats[j]; + __lb_one_cpu_stats_add(&s_info->stats, stats, + &pcpu_stats->syncp); + } + changed |= __lb_stats_info_refresh_check(s_info, team); + } + + list_for_each_entry(port, &team->port_list, list) { + struct lb_port_priv *lb_port_priv = get_lb_port_priv(port); + + s_info = &lb_port_priv->stats_info; + __lb_stats_info_refresh_prepare(s_info); + for_each_possible_cpu(i) { + pcpu_stats = per_cpu_ptr(lb_priv->pcpu_stats, i); + stats = per_cpu_ptr(lb_port_priv->pcpu_stats, i); + __lb_one_cpu_stats_add(&s_info->stats, stats, + &pcpu_stats->syncp); + } + changed |= __lb_stats_info_refresh_check(s_info, team); + } + + if (changed) + team_options_change_check(team); + + schedule_delayed_work(&lb_priv_ex->stats.refresh_dw, + (lb_priv_ex->stats.refresh_interval * HZ) / 10); + + mutex_unlock(&team->lock); +} + +static int lb_stats_refresh_interval_get(struct team *team, + struct team_gsetter_ctx *ctx) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + + ctx->data.u32_val = lb_priv->ex->stats.refresh_interval; + return 0; +} + +static int lb_stats_refresh_interval_set(struct team *team, + struct team_gsetter_ctx *ctx) +{ + struct lb_priv *lb_priv = get_lb_priv(team); + unsigned int interval; + + interval = ctx->data.u32_val; + if (lb_priv->ex->stats.refresh_interval == interval) + return 0; + lb_priv->ex->stats.refresh_interval = interval; + if (interval) + schedule_delayed_work(&lb_priv->ex->stats.refresh_dw, 0); + else + cancel_delayed_work(&lb_priv->ex->stats.refresh_dw); return 0; } @@ -128,30 +531,125 @@ static const struct team_option lb_options[] = { .getter = lb_bpf_func_get, .setter = lb_bpf_func_set, }, + { + .name = "lb_tx_method", + .type = TEAM_OPTION_TYPE_STRING, + .getter = lb_tx_method_get, + .setter = lb_tx_method_set, + }, + { + .name = "lb_tx_hash_to_port_mapping", + .array_size = LB_TX_HASHTABLE_SIZE, + .type = TEAM_OPTION_TYPE_U32, + .init = lb_tx_hash_to_port_mapping_init, + .getter = lb_tx_hash_to_port_mapping_get, + .setter = lb_tx_hash_to_port_mapping_set, + }, + { + .name = "lb_hash_stats", + .array_size = LB_TX_HASHTABLE_SIZE, + .type = TEAM_OPTION_TYPE_BINARY, + .init = lb_hash_stats_init, + .getter = lb_hash_stats_get, + }, + { + .name = "lb_port_stats", + .per_port = true, + .type = TEAM_OPTION_TYPE_BINARY, + .init = lb_port_stats_init, + .getter = lb_port_stats_get, + }, + { + .name = "lb_stats_refresh_interval", + .type = TEAM_OPTION_TYPE_U32, + .getter = lb_stats_refresh_interval_get, + .setter = lb_stats_refresh_interval_set, + }, }; static int lb_init(struct team *team) { - return team_options_register(team, lb_options, - ARRAY_SIZE(lb_options)); + struct lb_priv *lb_priv = get_lb_priv(team); + lb_select_tx_port_func_t *func; + int err; + + /* set default tx port selector */ + func = lb_select_tx_port_get_func("hash"); + BUG_ON(!func); + rcu_assign_pointer(lb_priv->select_tx_port_func, func); + + lb_priv->ex = kzalloc(sizeof(*lb_priv->ex), GFP_KERNEL); + if (!lb_priv->ex) + return -ENOMEM; + lb_priv->ex->team = team; + + lb_priv->pcpu_stats = alloc_percpu(struct lb_pcpu_stats); + if (!lb_priv->pcpu_stats) { + err = -ENOMEM; + goto err_alloc_pcpu_stats; + } + + INIT_DELAYED_WORK(&lb_priv->ex->stats.refresh_dw, lb_stats_refresh); + + err = team_options_register(team, lb_options, ARRAY_SIZE(lb_options)); + if (err) + goto err_options_register; + return 0; + +err_options_register: + free_percpu(lb_priv->pcpu_stats); +err_alloc_pcpu_stats: + kfree(lb_priv->ex); + return err; } static void lb_exit(struct team *team) { + struct lb_priv *lb_priv = get_lb_priv(team); + team_options_unregister(team, lb_options, ARRAY_SIZE(lb_options)); + cancel_delayed_work_sync(&lb_priv->ex->stats.refresh_dw); + free_percpu(lb_priv->pcpu_stats); + kfree(lb_priv->ex); +} + +static int lb_port_enter(struct team *team, struct team_port *port) +{ + struct lb_port_priv *lb_port_priv = get_lb_port_priv(port); + + lb_port_priv->pcpu_stats = alloc_percpu(struct lb_stats); + if (!lb_port_priv->pcpu_stats) + return -ENOMEM; + return 0; +} + +static void lb_port_leave(struct team *team, struct team_port *port) +{ + struct lb_port_priv *lb_port_priv = get_lb_port_priv(port); + + free_percpu(lb_port_priv->pcpu_stats); +} + +static void lb_port_disabled(struct team *team, struct team_port *port) +{ + lb_tx_hash_to_port_mapping_null_port(team, port); } static const struct team_mode_ops lb_mode_ops = { .init = lb_init, .exit = lb_exit, + .port_enter = lb_port_enter, + .port_leave = lb_port_leave, + .port_disabled = lb_port_disabled, .transmit = lb_transmit, }; -static struct team_mode lb_mode = { +static const struct team_mode lb_mode = { .kind = "loadbalance", .owner = THIS_MODULE, .priv_size = sizeof(struct lb_priv), + .port_priv_size = sizeof(struct lb_port_priv), .ops = &lb_mode_ops, }; diff --git a/drivers/net/team/team_mode_roundrobin.c b/drivers/net/team/team_mode_roundrobin.c index 6abfbdc96be..ad7ed0ec544 100644 --- a/drivers/net/team/team_mode_roundrobin.c +++ b/drivers/net/team/team_mode_roundrobin.c @@ -1,5 +1,5 @@ /* - * net/drivers/team/team_mode_roundrobin.c - Round-robin mode for team + * drivers/net/team/team_mode_roundrobin.c - Round-robin mode for team * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com> * * This program is free software; you can redistribute it and/or modify @@ -30,16 +30,16 @@ static struct team_port *__get_first_port_up(struct team *team, { struct team_port *cur; - if (port->linkup) + if (team_port_txable(port)) return port; cur = port; list_for_each_entry_continue_rcu(cur, &team->port_list, list) - if (cur->linkup) + if (team_port_txable(port)) return cur; list_for_each_entry_rcu(cur, &team->port_list, list) { if (cur == port) break; - if (cur->linkup) + if (team_port_txable(port)) return cur; } return NULL; @@ -55,8 +55,7 @@ static bool rr_transmit(struct team *team, struct sk_buff *skb) port = __get_first_port_up(team, port); if (unlikely(!port)) goto drop; - skb->dev = port->dev; - if (dev_queue_xmit(skb)) + if (team_dev_queue_xmit(team, port, skb)) return false; return true; @@ -81,7 +80,7 @@ static const struct team_mode_ops rr_mode_ops = { .port_change_mac = rr_port_change_mac, }; -static struct team_mode rr_mode = { +static const struct team_mode rr_mode = { .kind = "roundrobin", .owner = THIS_MODULE, .priv_size = sizeof(struct rr_priv), |