diff options
Diffstat (limited to 'net/switchdev/switchdev.c')
| -rw-r--r-- | net/switchdev/switchdev.c | 327 |
1 files changed, 233 insertions, 94 deletions
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 6e4a4f9ad927..73e3895175cf 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -15,8 +15,10 @@ #include <linux/mutex.h> #include <linux/notifier.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> #include <linux/if_bridge.h> #include <linux/list.h> +#include <linux/workqueue.h> #include <net/ip_fib.h> #include <net/switchdev.h> @@ -92,6 +94,85 @@ static void switchdev_trans_items_warn_destroy(struct net_device *dev, switchdev_trans_items_destroy(trans); } +static LIST_HEAD(deferred); +static DEFINE_SPINLOCK(deferred_lock); + +typedef void switchdev_deferred_func_t(struct net_device *dev, + const void *data); + +struct switchdev_deferred_item { + struct list_head list; + struct net_device *dev; + switchdev_deferred_func_t *func; + unsigned long data[0]; +}; + +static struct switchdev_deferred_item *switchdev_deferred_dequeue(void) +{ + struct switchdev_deferred_item *dfitem; + + spin_lock_bh(&deferred_lock); + if (list_empty(&deferred)) { + dfitem = NULL; + goto unlock; + } + dfitem = list_first_entry(&deferred, + struct switchdev_deferred_item, list); + list_del(&dfitem->list); +unlock: + spin_unlock_bh(&deferred_lock); + return dfitem; +} + +/** + * switchdev_deferred_process - Process ops in deferred queue + * + * Called to flush the ops currently queued in deferred ops queue. + * rtnl_lock must be held. + */ +void switchdev_deferred_process(void) +{ + struct switchdev_deferred_item *dfitem; + + ASSERT_RTNL(); + + while ((dfitem = switchdev_deferred_dequeue())) { + dfitem->func(dfitem->dev, dfitem->data); + dev_put(dfitem->dev); + kfree(dfitem); + } +} +EXPORT_SYMBOL_GPL(switchdev_deferred_process); + +static void switchdev_deferred_process_work(struct work_struct *work) +{ + rtnl_lock(); + switchdev_deferred_process(); + rtnl_unlock(); +} + +static DECLARE_WORK(deferred_process_work, switchdev_deferred_process_work); + +static int switchdev_deferred_enqueue(struct net_device *dev, + const void *data, size_t data_len, + switchdev_deferred_func_t *func) +{ + struct switchdev_deferred_item *dfitem; + + dfitem = kmalloc(sizeof(*dfitem) + data_len, GFP_ATOMIC); + if (!dfitem) + return -ENOMEM; + dfitem->dev = dev; + dfitem->func = func; + memcpy(dfitem->data, data, data_len); + dev_hold(dev); + spin_lock_bh(&deferred_lock); + list_add_tail(&dfitem->list, &deferred); + spin_unlock_bh(&deferred_lock); + schedule_work(&deferred_process_work); + return 0; +} + /** * switchdev_port_attr_get - Get port attribute * @@ -135,7 +216,7 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) EXPORT_SYMBOL_GPL(switchdev_port_attr_get); static int __switchdev_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr, + const struct switchdev_attr *attr, struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; @@ -147,7 +228,7 @@ static int __switchdev_port_attr_set(struct net_device *dev, return ops->switchdev_port_attr_set(dev, attr, trans); if (attr->flags & SWITCHDEV_F_NO_RECURSE) - return err; + goto done; /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to set attr on @@ -156,81 +237,26 @@ static int __switchdev_port_attr_set(struct net_device *dev, netdev_for_each_lower_dev(dev, lower_dev, iter) { err = __switchdev_port_attr_set(lower_dev, attr, trans); + if (err == -EOPNOTSUPP && + attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP) + continue; 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); - if (err && err != -EOPNOTSUPP) - netdev_err(asw->dev, "failed (err=%d) to set attribute (id=%d)\n", - err, asw->attr.id); - 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); +done: + if (err == -EOPNOTSUPP && attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP) + err = 0; - return 0; + return err; } -/** - * 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) +static int switchdev_port_attr_set_now(struct net_device *dev, + const struct switchdev_attr *attr) { struct switchdev_trans trans; 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); - } - switchdev_trans_init(&trans); /* Phase I: prepare for attr set. Driver/device should fail @@ -267,6 +293,47 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) return err; } + +static void switchdev_port_attr_set_deferred(struct net_device *dev, + const void *data) +{ + const struct switchdev_attr *attr = data; + int err; + + err = switchdev_port_attr_set_now(dev, attr); + if (err && err != -EOPNOTSUPP) + netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n", + err, attr->id); +} + +static int switchdev_port_attr_set_defer(struct net_device *dev, + const struct switchdev_attr *attr) +{ + return switchdev_deferred_enqueue(dev, attr, sizeof(*attr), + switchdev_port_attr_set_deferred); +} + +/** + * 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. + * + * rtnl_lock must be held and must not be in atomic section, + * in case SWITCHDEV_F_DEFER flag is not set. + */ +int switchdev_port_attr_set(struct net_device *dev, + const struct switchdev_attr *attr) +{ + if (attr->flags & SWITCHDEV_F_DEFER) + return switchdev_port_attr_set_defer(dev, attr); + ASSERT_RTNL(); + return switchdev_port_attr_set_now(dev, attr); +} EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static int __switchdev_port_obj_add(struct net_device *dev, @@ -295,21 +362,8 @@ static int __switchdev_port_obj_add(struct net_device *dev, return err; } -/** - * switchdev_port_obj_add - Add port object - * - * @dev: port device - * @id: object ID - * @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, - const struct switchdev_obj *obj) +static int switchdev_port_obj_add_now(struct net_device *dev, + const struct switchdev_obj *obj) { struct switchdev_trans trans; int err; @@ -351,18 +405,53 @@ int switchdev_port_obj_add(struct net_device *dev, return err; } -EXPORT_SYMBOL_GPL(switchdev_port_obj_add); + +static void switchdev_port_obj_add_deferred(struct net_device *dev, + const void *data) +{ + const struct switchdev_obj *obj = data; + int err; + + err = switchdev_port_obj_add_now(dev, obj); + if (err && err != -EOPNOTSUPP) + netdev_err(dev, "failed (err=%d) to add object (id=%d)\n", + err, obj->id); +} + +static int switchdev_port_obj_add_defer(struct net_device *dev, + const struct switchdev_obj *obj) +{ + return switchdev_deferred_enqueue(dev, obj, sizeof(*obj), + switchdev_port_obj_add_deferred); +} /** - * switchdev_port_obj_del - Delete port object + * switchdev_port_obj_add - Add port object * * @dev: port device * @id: object ID - * @obj: object to delete + * @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 and must not be in atomic section, + * in case SWITCHDEV_F_DEFER flag is not set. */ -int switchdev_port_obj_del(struct net_device *dev, +int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj) { + if (obj->flags & SWITCHDEV_F_DEFER) + return switchdev_port_obj_add_defer(dev, obj); + ASSERT_RTNL(); + return switchdev_port_obj_add_now(dev, obj); +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_add); + +static int switchdev_port_obj_del_now(struct net_device *dev, + const struct switchdev_obj *obj) +{ const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; struct list_head *iter; @@ -377,13 +466,51 @@ int switchdev_port_obj_del(struct net_device *dev, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_obj_del(lower_dev, obj); + err = switchdev_port_obj_del_now(lower_dev, obj); if (err) break; } return err; } + +static void switchdev_port_obj_del_deferred(struct net_device *dev, + const void *data) +{ + const struct switchdev_obj *obj = data; + int err; + + err = switchdev_port_obj_del_now(dev, obj); + if (err && err != -EOPNOTSUPP) + netdev_err(dev, "failed (err=%d) to del object (id=%d)\n", + err, obj->id); +} + +static int switchdev_port_obj_del_defer(struct net_device *dev, + const struct switchdev_obj *obj) +{ + return switchdev_deferred_enqueue(dev, obj, sizeof(*obj), + switchdev_port_obj_del_deferred); +} + +/** + * switchdev_port_obj_del - Delete port object + * + * @dev: port device + * @id: object ID + * @obj: object to delete + * + * rtnl_lock must be held and must not be in atomic section, + * in case SWITCHDEV_F_DEFER flag is not set. + */ +int switchdev_port_obj_del(struct net_device *dev, + const struct switchdev_obj *obj) +{ + if (obj->flags & SWITCHDEV_F_DEFER) + return switchdev_port_obj_del_defer(dev, obj); + ASSERT_RTNL(); + return switchdev_port_obj_del_now(dev, obj); +} EXPORT_SYMBOL_GPL(switchdev_port_obj_del); /** @@ -393,6 +520,8 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_del); * @id: object ID * @obj: object to dump * @cb: function to call with a filled object + * + * rtnl_lock must be held. */ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb) @@ -402,6 +531,8 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, struct list_head *iter; int err = -EOPNOTSUPP; + ASSERT_RTNL(); + if (ops && ops->switchdev_port_obj_dump) return ops->switchdev_port_obj_dump(dev, obj, cb); @@ -720,6 +851,9 @@ static int switchdev_port_br_afspec(struct net_device *dev, if (vlan.vid_begin) return -EINVAL; vlan.vid_begin = vinfo->vid; + /* don't allow range of pvids */ + if (vlan.flags & BRIDGE_VLAN_INFO_PVID) + return -EINVAL; } else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) { if (!vlan.vid_begin) return -EINVAL; @@ -822,10 +956,10 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], { struct switchdev_obj_port_fdb fdb = { .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, - .addr = addr, .vid = vid, }; + ether_addr_copy(fdb.addr, addr); return switchdev_port_obj_add(dev, &fdb.obj); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_add); @@ -847,10 +981,10 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], { struct switchdev_obj_port_fdb fdb = { .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, - .addr = addr, .vid = vid, }; + ether_addr_copy(fdb.addr, addr); return switchdev_port_obj_del(dev, &fdb.obj); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); @@ -967,6 +1101,8 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) struct net_device *dev = NULL; int nhsel; + ASSERT_RTNL(); + /* For this route, all nexthop devs must be on the same switch. */ for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) { @@ -1012,7 +1148,6 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, .obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB, .dst = dst, .dst_len = dst_len, - .fi = fi, .tos = tos, .type = type, .nlflags = nlflags, @@ -1021,6 +1156,8 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, struct net_device *dev; int err = 0; + memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi)); + /* Don't offload route if using custom ip rules or if * IPv4 FIB offloading has been disabled completely. */ @@ -1064,7 +1201,6 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, .obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB, .dst = dst, .dst_len = dst_len, - .fi = fi, .tos = tos, .type = type, .nlflags = 0, @@ -1073,6 +1209,8 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, struct net_device *dev; int err = 0; + memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi)); + if (!(fi->fib_flags & RTNH_F_OFFLOAD)) return 0; @@ -1195,10 +1333,11 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, u32 mark = dev->ifindex; u32 reset_mark = 0; - if (group_dev && joining) { - mark = switchdev_port_fwd_mark_get(dev, group_dev); - } else if (group_dev && !joining) { - if (dev->offload_fwd_mark == mark) + if (group_dev) { + ASSERT_RTNL(); + if (joining) + mark = switchdev_port_fwd_mark_get(dev, group_dev); + else if (dev->offload_fwd_mark == mark) /* Ohoh, this port was the mark reference port, * but it's leaving the group, so reset the * mark for the remaining ports in the group. |