[PATCH net-next 5/7] net/mlx5: E-Switch, block representors during reconfiguration

[Tariq Toukan <tariqt@nvidia.com>]

From: Mark Bloch <mbloch@nvidia.com>

Introduce a simple atomic block state via mlx5_esw_reps_block() and
mlx5_esw_reps_unblock(). Internally, mlx5_esw_mark_reps() spins a
cmpxchg between the UNBLOCKED and BLOCKED states. All E-Switch
reconfiguration paths (mode set, enable, disable, VF/SF add/del, LAG
reload) now bracket their work with this guard so representor changes
won't race with the ongoing E-Switch update, yet we remain
non-blocking and avoid new locks.

A spinlock is out because the protected work can sleep (RDMA ops,
devcom, netdev callbacks). A mutex won't work either: esw_mode_change()
has to drop the guard mid-flight so mlx5_rescan_drivers_locked() can
reload mlx5_ib, which calls back into mlx5_eswitch_register_vport_reps()
on the same thread. Beyond that, any real lock would create an ABBA
cycle: the LAG side holds the LAG lock when it calls reps_block(), and
the mlx5_ib side holds RDMA locks when it calls register_vport_reps(),
and those two subsystems talk to each other. The atomic CAS loop avoids
all of this - no lock ordering, no sleep restrictions, and the owner
can drop the guard and let a nested caller win the next transition
before reclaiming it.

With this infrastructure in place, downstream patches can safely tie
representor load/unload to the mlx5_ib module's lifecycle. Loading
mlx5_ib while the device is in switchdev mode has failed to bring up
the IB representors for years; those patches will finally fix that.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch.c | 13 ++++
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  6 ++
 .../mellanox/mlx5/core/eswitch_offloads.c     | 77 +++++++++++++++++--
 .../net/ethernet/mellanox/mlx5/core/lag/lag.c |  2 +
 .../ethernet/mellanox/mlx5/core/sf/devlink.c  |  5 ++
 include/linux/mlx5/eswitch.h                  |  5 ++
 6 files changed, 100 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index d315484390c8..a7701c9d776a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1700,6 +1700,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 		mlx5_lag_disable_change(esw->dev);
 
 	atomic_inc(&esw->generation);
+	mlx5_esw_reps_block(esw);
 
 	if (!mlx5_esw_is_fdb_created(esw)) {
 		ret = mlx5_eswitch_enable_locked(esw, num_vfs);
@@ -1723,6 +1724,8 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 		}
 	}
 
+	mlx5_esw_reps_unblock(esw);
+
 	if (toggle_lag)
 		mlx5_lag_enable_change(esw->dev);
 
@@ -1747,6 +1750,8 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 		 esw->esw_funcs.num_vfs, esw->esw_funcs.num_ec_vfs, esw->enabled_vports);
 	atomic_inc(&esw->generation);
 
+	mlx5_esw_reps_block(esw);
+
 	if (!mlx5_core_is_ecpf(esw->dev)) {
 		mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
 		if (clear_vf)
@@ -1757,6 +1762,8 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 			mlx5_eswitch_clear_ec_vf_vports_info(esw);
 	}
 
+	mlx5_esw_reps_unblock(esw);
+
 	if (esw->mode == MLX5_ESWITCH_OFFLOADS) {
 		struct devlink *devlink = priv_to_devlink(esw->dev);
 
@@ -1812,7 +1819,11 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
 	devl_assert_locked(priv_to_devlink(esw->dev));
 	atomic_inc(&esw->generation);
 	mlx5_lag_disable_change(esw->dev);
+
+	mlx5_esw_reps_block(esw);
 	mlx5_eswitch_disable_locked(esw);
+	mlx5_esw_reps_unblock(esw);
+
 	esw->mode = MLX5_ESWITCH_LEGACY;
 	mlx5_lag_enable_change(esw->dev);
 }
@@ -2075,6 +2086,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	init_rwsem(&esw->mode_lock);
 	refcount_set(&esw->qos.refcnt, 0);
 	atomic_set(&esw->generation, 0);
+	atomic_set(&esw->offloads.reps_conf_state,
+		   MLX5_ESW_OFFLOADS_REP_TYPE_UNBLOCKED);
 
 	esw->enabled_vports = 0;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index e3ab8a30c174..256ac3ad37bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -315,6 +315,7 @@ struct mlx5_esw_offload {
 	DECLARE_HASHTABLE(termtbl_tbl, 8);
 	struct mutex termtbl_mutex; /* protects termtbl hash */
 	struct xarray vhca_map;
+	atomic_t reps_conf_state;
 	const struct mlx5_eswitch_rep_ops *rep_ops[NUM_REP_TYPES];
 	u8 inline_mode;
 	atomic64_t num_flows;
@@ -949,6 +950,8 @@ mlx5_esw_lag_demux_fg_create(struct mlx5_eswitch *esw,
 struct mlx5_flow_handle *
 mlx5_esw_lag_demux_rule_create(struct mlx5_eswitch *esw, u16 vport_num,
 			       struct mlx5_flow_table *lag_ft);
+void mlx5_esw_reps_block(struct mlx5_eswitch *esw);
+void mlx5_esw_reps_unblock(struct mlx5_eswitch *esw);
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
@@ -1026,6 +1029,9 @@ mlx5_esw_host_functions_enabled(const struct mlx5_core_dev *dev)
 	return true;
 }
 
+static inline void mlx5_esw_reps_block(struct mlx5_eswitch *esw) {}
+static inline void mlx5_esw_reps_unblock(struct mlx5_eswitch *esw) {}
+
 static inline bool
 mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 988595e1b425..4b626ffcfa8e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2410,23 +2410,56 @@ static int esw_create_restore_table(struct mlx5_eswitch *esw)
 	return err;
 }
 
+static void mlx5_esw_assert_reps_blocked(struct mlx5_eswitch *esw)
+{
+	if (atomic_read(&esw->offloads.reps_conf_state) ==
+	    MLX5_ESW_OFFLOADS_REP_TYPE_BLOCKED)
+		return;
+
+	esw_warn(esw->dev, "reps state machine violated: expected BLOCKED\n");
+}
+
+static void mlx5_esw_mark_reps(struct mlx5_eswitch *esw,
+			       enum mlx5_esw_offloads_rep_type_state old,
+			       enum mlx5_esw_offloads_rep_type_state new)
+{
+	atomic_t *reps_conf_state = &esw->offloads.reps_conf_state;
+
+	do {
+		atomic_cond_read_relaxed(reps_conf_state, VAL == old);
+	} while (atomic_cmpxchg(reps_conf_state, old, new) != old);
+}
+
+void mlx5_esw_reps_block(struct mlx5_eswitch *esw)
+{
+	mlx5_esw_mark_reps(esw, MLX5_ESW_OFFLOADS_REP_TYPE_UNBLOCKED,
+			   MLX5_ESW_OFFLOADS_REP_TYPE_BLOCKED);
+}
+
+void mlx5_esw_reps_unblock(struct mlx5_eswitch *esw)
+{
+	mlx5_esw_mark_reps(esw, MLX5_ESW_OFFLOADS_REP_TYPE_BLOCKED,
+			   MLX5_ESW_OFFLOADS_REP_TYPE_UNBLOCKED);
+}
+
 static void esw_mode_change(struct mlx5_eswitch *esw, u16 mode)
 {
+	mlx5_esw_reps_unblock(esw);
 	mlx5_devcom_comp_lock(esw->dev->priv.hca_devcom_comp);
 	if (esw->dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV ||
 	    mlx5_core_mp_enabled(esw->dev)) {
 		esw->mode = mode;
-		mlx5_rescan_drivers_locked(esw->dev);
-		mlx5_devcom_comp_unlock(esw->dev->priv.hca_devcom_comp);
-		return;
+		goto out;
 	}
 
 	esw->dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
 	mlx5_rescan_drivers_locked(esw->dev);
 	esw->mode = mode;
 	esw->dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
+out:
 	mlx5_rescan_drivers_locked(esw->dev);
 	mlx5_devcom_comp_unlock(esw->dev->priv.hca_devcom_comp);
+	mlx5_esw_reps_block(esw);
 }
 
 static void mlx5_esw_fdb_drop_destroy(struct mlx5_eswitch *esw)
@@ -2761,6 +2794,8 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
 				   struct mlx5_eswitch_rep *rep, u8 rep_type)
 {
+	mlx5_esw_assert_reps_blocked(esw);
+
 	if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
 			   REP_REGISTERED, REP_LOADED) == REP_REGISTERED)
 		return esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
@@ -2771,6 +2806,8 @@ static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
 static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
 				      struct mlx5_eswitch_rep *rep, u8 rep_type)
 {
+	mlx5_esw_assert_reps_blocked(esw);
+
 	if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
 			   REP_LOADED, REP_REGISTERED) == REP_LOADED) {
 		if (rep_type == REP_ETH)
@@ -3673,6 +3710,7 @@ static void esw_vfs_changed_event_handler(struct mlx5_eswitch *esw)
 	if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_disabled)
 		goto free;
 
+	mlx5_esw_reps_block(esw);
 	/* Number of VFs can only change from "0 to x" or "x to 0". */
 	if (esw->esw_funcs.num_vfs > 0) {
 		mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
@@ -3682,9 +3720,11 @@ static void esw_vfs_changed_event_handler(struct mlx5_eswitch *esw)
 		err = mlx5_eswitch_load_vf_vports(esw, new_num_vfs,
 						  MLX5_VPORT_UC_ADDR_CHANGE);
 		if (err)
-			goto free;
+			goto unblock;
 	}
 	esw->esw_funcs.num_vfs = new_num_vfs;
+unblock:
+	mlx5_esw_reps_unblock(esw);
 free:
 	kvfree(out);
 }
@@ -4164,6 +4204,7 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 		goto unlock;
 	}
 
+	mlx5_esw_reps_block(esw);
 	esw->eswitch_operation_in_progress = true;
 	up_write(&esw->mode_lock);
 
@@ -4203,6 +4244,7 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 		mlx5_devlink_netdev_netns_immutable_set(devlink, false);
 	down_write(&esw->mode_lock);
 	esw->eswitch_operation_in_progress = false;
+	mlx5_esw_reps_unblock(esw);
 unlock:
 	mlx5_esw_unlock(esw);
 enable_lag:
@@ -4474,9 +4516,10 @@ mlx5_eswitch_vport_has_rep(const struct mlx5_eswitch *esw, u16 vport_num)
 	return true;
 }
 
-void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
-				      const struct mlx5_eswitch_rep_ops *ops,
-				      u8 rep_type)
+static void
+mlx5_eswitch_register_vport_reps_blocked(struct mlx5_eswitch *esw,
+					 const struct mlx5_eswitch_rep_ops *ops,
+					 u8 rep_type)
 {
 	struct mlx5_eswitch_rep_data *rep_data;
 	struct mlx5_eswitch_rep *rep;
@@ -4491,9 +4534,20 @@ void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
 		}
 	}
 }
+
+void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
+				      const struct mlx5_eswitch_rep_ops *ops,
+				      u8 rep_type)
+{
+	mlx5_esw_reps_block(esw);
+	mlx5_eswitch_register_vport_reps_blocked(esw, ops, rep_type);
+	mlx5_esw_reps_unblock(esw);
+}
 EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
 
-void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
+static void
+mlx5_eswitch_unregister_vport_reps_blocked(struct mlx5_eswitch *esw,
+					   u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
 	unsigned long i;
@@ -4504,6 +4558,13 @@ void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
 	mlx5_esw_for_each_rep(esw, i, rep)
 		atomic_set(&rep->rep_data[rep_type].state, REP_UNREGISTERED);
 }
+
+void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
+{
+	mlx5_esw_reps_block(esw);
+	mlx5_eswitch_unregister_vport_reps_blocked(esw, rep_type);
+	mlx5_esw_reps_unblock(esw);
+}
 EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);
 
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index c402a8463081..ff2e6f6caa0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1105,7 +1105,9 @@ int mlx5_lag_reload_ib_reps(struct mlx5_lag *ldev, u32 flags)
 			struct mlx5_eswitch *esw;
 
 			esw = pf->dev->priv.eswitch;
+			mlx5_esw_reps_block(esw);
 			ret = mlx5_eswitch_reload_ib_reps(esw);
+			mlx5_esw_reps_unblock(esw);
 			if (ret)
 				return ret;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index 8503e532f423..2fc69897e35b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -245,8 +245,10 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
 	if (IS_ERR(sf))
 		return PTR_ERR(sf);
 
+	mlx5_esw_reps_block(esw);
 	err = mlx5_eswitch_load_sf_vport(esw, sf->hw_fn_id, MLX5_VPORT_UC_ADDR_CHANGE,
 					 &sf->dl_port, new_attr->controller, new_attr->sfnum);
+	mlx5_esw_reps_unblock(esw);
 	if (err)
 		goto esw_err;
 	*dl_port = &sf->dl_port.dl_port;
@@ -367,7 +369,10 @@ int mlx5_devlink_sf_port_del(struct devlink *devlink,
 	struct mlx5_sf_table *table = dev->priv.sf_table;
 	struct mlx5_sf *sf = mlx5_sf_by_dl_port(dl_port);
 
+	mlx5_esw_reps_block(dev->priv.eswitch);
 	mlx5_sf_del(table, sf);
+	mlx5_esw_reps_unblock(dev->priv.eswitch);
+
 	return 0;
 }
 
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index 67256e776566..786b1ea83843 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -29,6 +29,11 @@ enum {
 	REP_LOADED,
 };
 
+enum mlx5_esw_offloads_rep_type_state {
+	MLX5_ESW_OFFLOADS_REP_TYPE_UNBLOCKED,
+	MLX5_ESW_OFFLOADS_REP_TYPE_BLOCKED,
+};
+
 enum mlx5_switchdev_event {
 	MLX5_SWITCHDEV_EVENT_PAIR,
 	MLX5_SWITCHDEV_EVENT_UNPAIR,
-- 
2.44.0