diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/lag.c')
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/lag.c | 267 |
1 files changed, 232 insertions, 35 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 5c043c5cc403..f4dfa55c8c7e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -32,7 +32,9 @@ #include <linux/netdevice.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/eswitch.h> #include <linux/mlx5/vport.h> +#include "lib/devcom.h" #include "mlx5_core.h" #include "eswitch.h" #include "lag.h" @@ -45,7 +47,7 @@ static DEFINE_SPINLOCK(lag_lock); static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1, - u8 remap_port2) + u8 remap_port2, bool shared_fdb) { u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {}; void *lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx); @@ -54,6 +56,7 @@ static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 remap_port1, MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, remap_port1); MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, remap_port2); + MLX5_SET(lagc, lag_ctx, fdb_selection_mode, shared_fdb); return mlx5_cmd_exec_in(dev, create_lag, in); } @@ -224,35 +227,59 @@ void mlx5_modify_lag(struct mlx5_lag *ldev, } static int mlx5_create_lag(struct mlx5_lag *ldev, - struct lag_tracker *tracker) + struct lag_tracker *tracker, + bool shared_fdb) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; + u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; int err; mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1], &ldev->v2p_map[MLX5_LAG_P2]); - mlx5_core_info(dev0, "lag map port 1:%d port 2:%d", - ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2]); + mlx5_core_info(dev0, "lag map port 1:%d port 2:%d shared_fdb:%d", + ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2], + shared_fdb); err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[MLX5_LAG_P1], - ldev->v2p_map[MLX5_LAG_P2]); - if (err) + ldev->v2p_map[MLX5_LAG_P2], shared_fdb); + if (err) { mlx5_core_err(dev0, "Failed to create LAG (%d)\n", err); + return err; + } + + if (shared_fdb) { + err = mlx5_eswitch_offloads_config_single_fdb(dev0->priv.eswitch, + dev1->priv.eswitch); + if (err) + mlx5_core_err(dev0, "Can't enable single FDB mode\n"); + else + mlx5_core_info(dev0, "Operation mode is single FDB\n"); + } + + if (err) { + MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG); + if (mlx5_cmd_exec_in(dev0, destroy_lag, in)) + mlx5_core_err(dev0, + "Failed to deactivate RoCE LAG; driver restart required\n"); + } + return err; } int mlx5_activate_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker, - u8 flags) + u8 flags, + bool shared_fdb) { bool roce_lag = !!(flags & MLX5_LAG_FLAG_ROCE); struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; int err; - err = mlx5_create_lag(ldev, tracker); + err = mlx5_create_lag(ldev, tracker, shared_fdb); if (err) { if (roce_lag) { mlx5_core_err(dev0, @@ -266,6 +293,7 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, } ldev->flags |= flags; + ldev->shared_fdb = shared_fdb; return 0; } @@ -278,6 +306,12 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev) ldev->flags &= ~MLX5_LAG_MODE_FLAGS; + if (ldev->shared_fdb) { + mlx5_eswitch_offloads_destroy_single_fdb(ldev->pf[MLX5_LAG_P1].dev->priv.eswitch, + ldev->pf[MLX5_LAG_P2].dev->priv.eswitch); + ldev->shared_fdb = false; + } + MLX5_SET(destroy_lag_in, in, opcode, MLX5_CMD_OP_DESTROY_LAG); err = mlx5_cmd_exec_in(dev0, destroy_lag, in); if (err) { @@ -333,6 +367,10 @@ static void mlx5_lag_remove_devices(struct mlx5_lag *ldev) if (!ldev->pf[i].dev) continue; + if (ldev->pf[i].dev->priv.flags & + MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) + continue; + ldev->pf[i].dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(ldev->pf[i].dev); } @@ -342,12 +380,15 @@ static void mlx5_disable_lag(struct mlx5_lag *ldev) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; + bool shared_fdb = ldev->shared_fdb; bool roce_lag; int err; roce_lag = __mlx5_lag_is_roce(ldev); - if (roce_lag) { + if (shared_fdb) { + mlx5_lag_remove_devices(ldev); + } else if (roce_lag) { if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) { dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); @@ -359,8 +400,34 @@ static void mlx5_disable_lag(struct mlx5_lag *ldev) if (err) return; - if (roce_lag) + if (shared_fdb || roce_lag) mlx5_lag_add_devices(ldev); + + if (shared_fdb) { + if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) + mlx5_eswitch_reload_reps(dev0->priv.eswitch); + if (!(dev1->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) + mlx5_eswitch_reload_reps(dev1->priv.eswitch); + } +} + +static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) +{ + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; + + if (is_mdev_switchdev_mode(dev0) && + is_mdev_switchdev_mode(dev1) && + mlx5_eswitch_vport_match_metadata_enabled(dev0->priv.eswitch) && + mlx5_eswitch_vport_match_metadata_enabled(dev1->priv.eswitch) && + mlx5_devcom_is_paired(dev0->priv.devcom, + MLX5_DEVCOM_ESW_OFFLOADS) && + MLX5_CAP_GEN(dev1, lag_native_fdb_selection) && + MLX5_CAP_ESW(dev1, root_ft_on_other_esw) && + MLX5_CAP_ESW(dev0, esw_shared_ingress_acl)) + return true; + + return false; } static void mlx5_do_bond(struct mlx5_lag *ldev) @@ -371,14 +438,17 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) bool do_bond, roce_lag; int err; - if (!mlx5_lag_is_ready(ldev)) - return; - - tracker = ldev->tracker; + if (!mlx5_lag_is_ready(ldev)) { + do_bond = false; + } else { + tracker = ldev->tracker; - do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev); + do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev); + } if (do_bond && !__mlx5_lag_is_active(ldev)) { + bool shared_fdb = mlx5_shared_fdb_supported(ldev); + roce_lag = !mlx5_sriov_is_enabled(dev0) && !mlx5_sriov_is_enabled(dev1); @@ -388,23 +458,40 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE; #endif - if (roce_lag) + if (shared_fdb || roce_lag) mlx5_lag_remove_devices(ldev); err = mlx5_activate_lag(ldev, &tracker, roce_lag ? MLX5_LAG_FLAG_ROCE : - MLX5_LAG_FLAG_SRIOV); + MLX5_LAG_FLAG_SRIOV, + shared_fdb); if (err) { - if (roce_lag) + if (shared_fdb || roce_lag) mlx5_lag_add_devices(ldev); return; - } - - if (roce_lag) { + } else if (roce_lag) { dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); mlx5_nic_vport_enable_roce(dev1); + } else if (shared_fdb) { + dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(dev0); + + err = mlx5_eswitch_reload_reps(dev0->priv.eswitch); + if (!err) + err = mlx5_eswitch_reload_reps(dev1->priv.eswitch); + + if (err) { + dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(dev0); + mlx5_deactivate_lag(ldev); + mlx5_lag_add_devices(ldev); + mlx5_eswitch_reload_reps(dev0->priv.eswitch); + mlx5_eswitch_reload_reps(dev1->priv.eswitch); + mlx5_core_err(dev0, "Failed to enable lag\n"); + return; + } } } else if (do_bond && __mlx5_lag_is_active(ldev)) { mlx5_modify_lag(ldev, &tracker); @@ -418,21 +505,48 @@ static void mlx5_queue_bond_work(struct mlx5_lag *ldev, unsigned long delay) queue_delayed_work(ldev->wq, &ldev->bond_work, delay); } +static void mlx5_lag_lock_eswitches(struct mlx5_core_dev *dev0, + struct mlx5_core_dev *dev1) +{ + if (dev0) + mlx5_esw_lock(dev0->priv.eswitch); + if (dev1) + mlx5_esw_lock(dev1->priv.eswitch); +} + +static void mlx5_lag_unlock_eswitches(struct mlx5_core_dev *dev0, + struct mlx5_core_dev *dev1) +{ + if (dev1) + mlx5_esw_unlock(dev1->priv.eswitch); + if (dev0) + mlx5_esw_unlock(dev0->priv.eswitch); +} + static void mlx5_do_bond_work(struct work_struct *work) { struct delayed_work *delayed_work = to_delayed_work(work); struct mlx5_lag *ldev = container_of(delayed_work, struct mlx5_lag, bond_work); + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; int status; status = mlx5_dev_list_trylock(); if (!status) { - /* 1 sec delay. */ mlx5_queue_bond_work(ldev, HZ); return; } + if (ldev->mode_changes_in_progress) { + mlx5_dev_list_unlock(); + mlx5_queue_bond_work(ldev, HZ); + return; + } + + mlx5_lag_lock_eswitches(dev0, dev1); mlx5_do_bond(ldev); + mlx5_lag_unlock_eswitches(dev0, dev1); mlx5_dev_list_unlock(); } @@ -630,7 +744,7 @@ static void mlx5_ldev_remove_mdev(struct mlx5_lag *ldev, } /* Must be called with intf_mutex held */ -static void __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) +static int __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev = NULL; struct mlx5_core_dev *tmp_dev; @@ -638,7 +752,7 @@ static void __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) if (!MLX5_CAP_GEN(dev, vport_group_manager) || !MLX5_CAP_GEN(dev, lag_master) || MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS) - return; + return 0; tmp_dev = mlx5_get_next_phys_dev(dev); if (tmp_dev) @@ -648,15 +762,17 @@ static void __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) ldev = mlx5_lag_dev_alloc(dev); if (!ldev) { mlx5_core_err(dev, "Failed to alloc lag dev\n"); - return; + return 0; } } else { + if (ldev->mode_changes_in_progress) + return -EAGAIN; mlx5_ldev_get(ldev); } mlx5_ldev_add_mdev(ldev, dev); - return; + return 0; } void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev) @@ -667,7 +783,13 @@ void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev) if (!ldev) return; +recheck: mlx5_dev_list_lock(); + if (ldev->mode_changes_in_progress) { + mlx5_dev_list_unlock(); + msleep(100); + goto recheck; + } mlx5_ldev_remove_mdev(ldev, dev); mlx5_dev_list_unlock(); mlx5_ldev_put(ldev); @@ -675,8 +797,16 @@ void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev) void mlx5_lag_add_mdev(struct mlx5_core_dev *dev) { + int err; + +recheck: mlx5_dev_list_lock(); - __mlx5_lag_dev_add_mdev(dev); + err = __mlx5_lag_dev_add_mdev(dev); + if (err) { + mlx5_dev_list_unlock(); + msleep(100); + goto recheck; + } mlx5_dev_list_unlock(); } @@ -690,11 +820,11 @@ void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev, if (!ldev) return; - if (__mlx5_lag_is_active(ldev)) - mlx5_disable_lag(ldev); - mlx5_ldev_remove_netdev(ldev, netdev); ldev->flags &= ~MLX5_LAG_FLAG_READY; + + if (__mlx5_lag_is_active(ldev)) + mlx5_queue_bond_work(ldev, 0); } /* Must be called with intf_mutex held */ @@ -716,6 +846,7 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, if (i >= MLX5_MAX_PORTS) ldev->flags |= MLX5_LAG_FLAG_READY; + mlx5_queue_bond_work(ldev, 0); } bool mlx5_lag_is_roce(struct mlx5_core_dev *dev) @@ -746,6 +877,21 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_lag_is_active); +bool mlx5_lag_is_master(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev; + bool res; + + spin_lock(&lag_lock); + ldev = mlx5_lag_dev(dev); + res = ldev && __mlx5_lag_is_active(ldev) && + dev == ldev->pf[MLX5_LAG_P1].dev; + spin_unlock(&lag_lock); + + return res; +} +EXPORT_SYMBOL(mlx5_lag_is_master); + bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; @@ -760,19 +906,50 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_lag_is_sriov); -void mlx5_lag_update(struct mlx5_core_dev *dev) +bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev; + bool res; + + spin_lock(&lag_lock); + ldev = mlx5_lag_dev(dev); + res = ldev && __mlx5_lag_is_sriov(ldev) && ldev->shared_fdb; + spin_unlock(&lag_lock); + + return res; +} +EXPORT_SYMBOL(mlx5_lag_is_shared_fdb); + +void mlx5_lag_disable_change(struct mlx5_core_dev *dev) { + struct mlx5_core_dev *dev0; + struct mlx5_core_dev *dev1; struct mlx5_lag *ldev; mlx5_dev_list_lock(); + ldev = mlx5_lag_dev(dev); - if (!ldev) - goto unlock; + dev0 = ldev->pf[MLX5_LAG_P1].dev; + dev1 = ldev->pf[MLX5_LAG_P2].dev; - mlx5_do_bond(ldev); + ldev->mode_changes_in_progress++; + if (__mlx5_lag_is_active(ldev)) { + mlx5_lag_lock_eswitches(dev0, dev1); + mlx5_disable_lag(ldev); + mlx5_lag_unlock_eswitches(dev0, dev1); + } + mlx5_dev_list_unlock(); +} -unlock: +void mlx5_lag_enable_change(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev; + + mlx5_dev_list_lock(); + ldev = mlx5_lag_dev(dev); + ldev->mode_changes_in_progress--; mlx5_dev_list_unlock(); + mlx5_queue_bond_work(ldev, 0); } struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev) @@ -827,6 +1004,26 @@ unlock: } EXPORT_SYMBOL(mlx5_lag_get_slave_port); +struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev) +{ + struct mlx5_core_dev *peer_dev = NULL; + struct mlx5_lag *ldev; + + spin_lock(&lag_lock); + ldev = mlx5_lag_dev(dev); + if (!ldev) + goto unlock; + + peer_dev = ldev->pf[MLX5_LAG_P1].dev == dev ? + ldev->pf[MLX5_LAG_P2].dev : + ldev->pf[MLX5_LAG_P1].dev; + +unlock: + spin_unlock(&lag_lock); + return peer_dev; +} +EXPORT_SYMBOL(mlx5_lag_get_peer_mdev); + int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, |