Merge branch 'mlxsw-refactor-qdisc-offload'

Petr Machata says:

====================
mlxsw: Refactor qdisc offload

Currently, mlxsw admits for offload a suitable root qdisc, and its
children. Thus up to two levels of hierarchy are offloaded. Often, this is
enough: one can configure TCs with RED and TCs with a shaper, and can even
see counters for each TC by looking at a qdisc at a sufficiently shallow
position.

While simple, the system has obvious shortcomings. It is not possible to
configure both RED and shaping on one TC. It is not possible to place a
PRIO below root TBF, which would then be offloaded as port shaper. FIFOs
are only offloaded at root or directly below, which is confusing to users,
because RED and TBF of course have their own FIFO.

This patchset is a step towards the end goal of allowing more comprehensive
qdisc tree offload and cleans up the qdisc offload code.

- Patches #1-#4 contain small cleanups.

- Up until now, since mlxsw offloaded only a very simple qdisc
configurations, basically all bookkeeping was done using one container
for the root qdisc, and 8 containers for its children. Patches #5, #6, #8
and #9 gradually introduce a more dynamic structure, where parent-child
relationships are tracked directly at qdiscs, instead of being implicit.

- This tree management assumes only one qdisc is created at a time. In FIFO
handlers, this condition was enforced simply by asserting RTNL lock. But
instead of furthering this RTNL dependence, patch #7 converts the whole
qdisc offload logic to a per-port mutex.

- Patch #10 adds a selftest.
====================

Signed-off-by: David S. Miller <[e-mail]>

drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c

···
 struct mlxsw_sp_qdisc_ops {
 	enum mlxsw_sp_qdisc_type type;
 	int (*check_params)(struct mlxsw_sp_port *mlxsw_sp_port,
-			    struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
 			    void *params);
 	int (*replace)(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle,
 		       struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, void *params);
···
 	 */
 	void (*unoffload)(struct mlxsw_sp_port *mlxsw_sp_port,
 			  struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, void *params);
+	struct mlxsw_sp_qdisc *(*find_class)(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+					     u32 parent);
+	unsigned int num_classes;
 };
 
 struct mlxsw_sp_qdisc {
 	u32 handle;
-	u8 tclass_num;
+	int tclass_num;
 	u8 prio_bitmap;
 	union {
 		struct red_stats red;
···
 	} stats_base;
 
 	struct mlxsw_sp_qdisc_ops *ops;
+	struct mlxsw_sp_qdisc *parent;
+	struct mlxsw_sp_qdisc *qdiscs;
+	unsigned int num_classes;
 };
 
 struct mlxsw_sp_qdisc_state {
 	struct mlxsw_sp_qdisc root_qdisc;
-	struct mlxsw_sp_qdisc tclass_qdiscs[IEEE_8021QAZ_MAX_TCS];
 
 	/* When a PRIO or ETS are added, the invisible FIFOs in their bands are
 	 * created first. When notifications for these FIFOs arrive, it is not
···
 	 */
 	u32 future_handle;
 	bool future_fifos[IEEE_8021QAZ_MAX_TCS];
+	struct mutex lock; /* Protects qdisc state. */
 };
 
 static bool
-mlxsw_sp_qdisc_compare(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, u32 handle,
-		       enum mlxsw_sp_qdisc_type type)
+mlxsw_sp_qdisc_compare(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, u32 handle)
 {
-	return mlxsw_sp_qdisc && mlxsw_sp_qdisc->ops &&
-	       mlxsw_sp_qdisc->ops->type == type &&
-	       mlxsw_sp_qdisc->handle == handle;
+	return mlxsw_sp_qdisc->ops && mlxsw_sp_qdisc->handle == handle;
+}
+
+static struct mlxsw_sp_qdisc *
+mlxsw_sp_qdisc_walk(struct mlxsw_sp_qdisc *qdisc,
+		    struct mlxsw_sp_qdisc *(*pre)(struct mlxsw_sp_qdisc *,
+						  void *),
+		    void *data)
+{
+	struct mlxsw_sp_qdisc *tmp;
+	unsigned int i;
+
+	if (pre) {
+		tmp = pre(qdisc, data);
+		if (tmp)
+			return tmp;
+	}
+
+	if (qdisc->ops) {
+		for (i = 0; i < qdisc->num_classes; i++) {
+			tmp = &qdisc->qdiscs[i];
+			if (qdisc->ops) {
+				tmp = mlxsw_sp_qdisc_walk(tmp, pre, data);
+				if (tmp)
+					return tmp;
+			}
+		}
+	}
+
+	return NULL;
+}
+
+static struct mlxsw_sp_qdisc *
+mlxsw_sp_qdisc_walk_cb_find(struct mlxsw_sp_qdisc *qdisc, void *data)
+{
+	u32 parent = *(u32 *)data;
+
+	if (qdisc->ops && TC_H_MAJ(qdisc->handle) == TC_H_MAJ(parent)) {
+		if (qdisc->ops->find_class)
+			return qdisc->ops->find_class(qdisc, parent);
+	}
+
+	return NULL;
 }
 
 static struct mlxsw_sp_qdisc *
···
 		    bool root_only)
 {
 	struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc;
-	int tclass, child_index;
 
+	if (!qdisc_state)
+		return NULL;
 	if (parent == TC_H_ROOT)
 		return &qdisc_state->root_qdisc;
-
-	if (root_only || !qdisc_state ||
-	    !qdisc_state->root_qdisc.ops ||
-	    TC_H_MAJ(parent) != qdisc_state->root_qdisc.handle ||
-	    TC_H_MIN(parent) > IEEE_8021QAZ_MAX_TCS)
+	if (root_only)
 		return NULL;
+	return mlxsw_sp_qdisc_walk(&qdisc_state->root_qdisc,
+				   mlxsw_sp_qdisc_walk_cb_find, &parent);
+}
 
-	child_index = TC_H_MIN(parent);
-	tclass = MLXSW_SP_PRIO_CHILD_TO_TCLASS(child_index);
-	return &qdisc_state->tclass_qdiscs[tclass];
+static struct mlxsw_sp_qdisc *
+mlxsw_sp_qdisc_walk_cb_find_by_handle(struct mlxsw_sp_qdisc *qdisc, void *data)
+{
+	u32 handle = *(u32 *)data;
+
+	if (qdisc->ops && qdisc->handle == handle)
+		return qdisc;
+	return NULL;
 }
 
 static struct mlxsw_sp_qdisc *
 mlxsw_sp_qdisc_find_by_handle(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle)
 {
 	struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc;
-	int i;
 
-	if (qdisc_state->root_qdisc.handle == handle)
-		return &qdisc_state->root_qdisc;
-
-	if (qdisc_state->root_qdisc.handle == TC_H_UNSPEC)
+	if (!qdisc_state)
 		return NULL;
+	return mlxsw_sp_qdisc_walk(&qdisc_state->root_qdisc,
+				   mlxsw_sp_qdisc_walk_cb_find_by_handle,
+				   &handle);
+}
 
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
-		if (qdisc_state->tclass_qdiscs[i].handle == handle)
-			return &qdisc_state->tclass_qdiscs[i];
+static void
+mlxsw_sp_qdisc_reduce_parent_backlog(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
+{
+	struct mlxsw_sp_qdisc *tmp;
 
-	return NULL;
+	for (tmp = mlxsw_sp_qdisc->parent; tmp; tmp = tmp->parent)
+		tmp->stats_base.backlog -= mlxsw_sp_qdisc->stats_base.backlog;
 }
 
 static int
···
 		err_hdroom = mlxsw_sp_hdroom_configure(mlxsw_sp_port, &hdroom);
 	}
 
-	if (mlxsw_sp_qdisc->ops && mlxsw_sp_qdisc->ops->destroy)
+	if (!mlxsw_sp_qdisc->ops)
+		return 0;
+
+	mlxsw_sp_qdisc_reduce_parent_backlog(mlxsw_sp_qdisc);
+	if (mlxsw_sp_qdisc->ops->destroy)
 		err = mlxsw_sp_qdisc->ops->destroy(mlxsw_sp_port,
 						   mlxsw_sp_qdisc);
+	if (mlxsw_sp_qdisc->ops->clean_stats)
+		mlxsw_sp_qdisc->ops->clean_stats(mlxsw_sp_port, mlxsw_sp_qdisc);
 
 	mlxsw_sp_qdisc->handle = TC_H_UNSPEC;
 	mlxsw_sp_qdisc->ops = NULL;
-
+	mlxsw_sp_qdisc->num_classes = 0;
+	kfree(mlxsw_sp_qdisc->qdiscs);
+	mlxsw_sp_qdisc->qdiscs = NULL;
 	return err_hdroom ?: err;
 }
 
-static int
-mlxsw_sp_qdisc_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle,
-		       struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
-		       struct mlxsw_sp_qdisc_ops *ops, void *params)
+static int mlxsw_sp_qdisc_create(struct mlxsw_sp_port *mlxsw_sp_port,
+				 u32 handle,
+				 struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+				 struct mlxsw_sp_qdisc_ops *ops, void *params)
 {
 	struct mlxsw_sp_qdisc *root_qdisc = &mlxsw_sp_port->qdisc->root_qdisc;
 	struct mlxsw_sp_hdroom orig_hdroom;
+	unsigned int i;
 	int err;
 
-	if (mlxsw_sp_qdisc->ops && mlxsw_sp_qdisc->ops->type != ops->type)
-		/* In case this location contained a different qdisc of the
-		 * same type we can override the old qdisc configuration.
-		 * Otherwise, we need to remove the old qdisc before setting the
-		 * new one.
-		 */
-		mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
+	err = ops->check_params(mlxsw_sp_port, params);
+	if (err)
+		return err;
+
+	if (ops->num_classes) {
+		mlxsw_sp_qdisc->qdiscs = kcalloc(ops->num_classes,
+						 sizeof(*mlxsw_sp_qdisc->qdiscs),
+						 GFP_KERNEL);
+		if (!mlxsw_sp_qdisc->qdiscs)
+			return -ENOMEM;
+
+		for (i = 0; i < ops->num_classes; i++)
+			mlxsw_sp_qdisc->qdiscs[i].parent = mlxsw_sp_qdisc;
+	}
 
 	orig_hdroom = *mlxsw_sp_port->hdroom;
 	if (root_qdisc == mlxsw_sp_qdisc) {
···
 			goto err_hdroom_configure;
 	}
 
-	err = ops->check_params(mlxsw_sp_port, mlxsw_sp_qdisc, params);
+	mlxsw_sp_qdisc->num_classes = ops->num_classes;
+	mlxsw_sp_qdisc->ops = ops;
+	mlxsw_sp_qdisc->handle = handle;
+	err = ops->replace(mlxsw_sp_port, handle, mlxsw_sp_qdisc, params);
 	if (err)
-		goto err_bad_param;
+		goto err_replace;
+
+	return 0;
+
+err_replace:
+	mlxsw_sp_qdisc->handle = TC_H_UNSPEC;
+	mlxsw_sp_qdisc->ops = NULL;
+	mlxsw_sp_qdisc->num_classes = 0;
+	mlxsw_sp_hdroom_configure(mlxsw_sp_port, &orig_hdroom);
+err_hdroom_configure:
+	kfree(mlxsw_sp_qdisc->qdiscs);
+	mlxsw_sp_qdisc->qdiscs = NULL;
+	return err;
+}
+
+static int
+mlxsw_sp_qdisc_change(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle,
+		      struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, void *params)
+{
+	struct mlxsw_sp_qdisc_ops *ops = mlxsw_sp_qdisc->ops;
+	int err;
+
+	err = ops->check_params(mlxsw_sp_port, params);
+	if (err)
+		goto unoffload;
 
 	err = ops->replace(mlxsw_sp_port, handle, mlxsw_sp_qdisc, params);
 	if (err)
-		goto err_config;
+		goto unoffload;
 
 	/* Check if the Qdisc changed. That includes a situation where an
 	 * invisible Qdisc replaces another one, or is being added for the
 	 * first time.
 	 */
-	if (mlxsw_sp_qdisc->handle != handle || handle == TC_H_UNSPEC) {
-		mlxsw_sp_qdisc->ops = ops;
+	if (mlxsw_sp_qdisc->handle != handle) {
 		if (ops->clean_stats)
 			ops->clean_stats(mlxsw_sp_port, mlxsw_sp_qdisc);
 	}
···
 	mlxsw_sp_qdisc->handle = handle;
 	return 0;
 
-err_bad_param:
-err_config:
-	mlxsw_sp_hdroom_configure(mlxsw_sp_port, &orig_hdroom);
-err_hdroom_configure:
-	if (mlxsw_sp_qdisc->handle == handle && ops->unoffload)
+unoffload:
+	if (ops->unoffload)
 		ops->unoffload(mlxsw_sp_port, mlxsw_sp_qdisc, params);
 
 	mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
 	return err;
+}
+
+static int
+mlxsw_sp_qdisc_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle,
+		       struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+		       struct mlxsw_sp_qdisc_ops *ops, void *params)
+{
+	if (mlxsw_sp_qdisc->ops && mlxsw_sp_qdisc->ops->type != ops->type)
+		/* In case this location contained a different qdisc of the
+		 * same type we can override the old qdisc configuration.
+		 * Otherwise, we need to remove the old qdisc before setting the
+		 * new one.
+		 */
+		mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
+
+	if (!mlxsw_sp_qdisc->ops)
+		return mlxsw_sp_qdisc_create(mlxsw_sp_port, handle,
+					     mlxsw_sp_qdisc, ops, params);
+	else
+		return mlxsw_sp_qdisc_change(mlxsw_sp_port, handle,
+					     mlxsw_sp_qdisc, params);
 }
 
 static int
···
 				u64 *p_tx_bytes, u64 *p_tx_packets,
 				u64 *p_drops, u64 *p_backlog)
 {
-	u8 tclass_num = mlxsw_sp_qdisc->tclass_num;
+	int tclass_num = mlxsw_sp_qdisc->tclass_num;
 	struct mlxsw_sp_port_xstats *xstats;
 	u64 tx_bytes, tx_packets;
 
···
 mlxsw_sp_setup_tc_qdisc_red_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 					struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
 {
-	u8 tclass_num = mlxsw_sp_qdisc->tclass_num;
+	int tclass_num = mlxsw_sp_qdisc->tclass_num;
 	struct mlxsw_sp_qdisc_stats *stats_base;
 	struct mlxsw_sp_port_xstats *xstats;
 	struct red_stats *red_base;
···
 mlxsw_sp_qdisc_red_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
 			   struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
 {
-	struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc;
-	struct mlxsw_sp_qdisc *root_qdisc = &qdisc_state->root_qdisc;
-
-	if (root_qdisc != mlxsw_sp_qdisc)
-		root_qdisc->stats_base.backlog -=
-					mlxsw_sp_qdisc->stats_base.backlog;
-
 	return mlxsw_sp_tclass_congestion_disable(mlxsw_sp_port,
 						  mlxsw_sp_qdisc->tclass_num);
 }
 
 static int
 mlxsw_sp_qdisc_red_check_params(struct mlxsw_sp_port *mlxsw_sp_port,
-				struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
 				void *params)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
···
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct tc_red_qopt_offload_params *p = params;
-	u8 tclass_num = mlxsw_sp_qdisc->tclass_num;
+	int tclass_num = mlxsw_sp_qdisc->tclass_num;
 	u32 min, max;
 	u64 prob;
 
···
 			      void *xstats_ptr)
 {
 	struct red_stats *xstats_base = &mlxsw_sp_qdisc->xstats_base.red;
-	u8 tclass_num = mlxsw_sp_qdisc->tclass_num;
+	int tclass_num = mlxsw_sp_qdisc->tclass_num;
 	struct mlxsw_sp_port_xstats *xstats;
 	struct red_stats *res = xstats_ptr;
 	int early_drops, pdrops;
···
 			     struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
 			     struct tc_qopt_offload_stats *stats_ptr)
 {
-	u8 tclass_num = mlxsw_sp_qdisc->tclass_num;
+	int tclass_num = mlxsw_sp_qdisc->tclass_num;
 	struct mlxsw_sp_qdisc_stats *stats_base;
 	struct mlxsw_sp_port_xstats *xstats;
 	u64 overlimits;
···
 	return 0;
 }
 
+static struct mlxsw_sp_qdisc *
+mlxsw_sp_qdisc_leaf_find_class(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+			       u32 parent)
+{
+	return NULL;
+}
+
 #define MLXSW_SP_PORT_DEFAULT_TCLASS 0
 
 static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_red = {
···
 	.get_stats = mlxsw_sp_qdisc_get_red_stats,
 	.get_xstats = mlxsw_sp_qdisc_get_red_xstats,
 	.clean_stats = mlxsw_sp_setup_tc_qdisc_red_clean_stats,
+	.find_class = mlxsw_sp_qdisc_leaf_find_class,
 };
 
-int mlxsw_sp_setup_tc_red(struct mlxsw_sp_port *mlxsw_sp_port,
-			  struct tc_red_qopt_offload *p)
+static int __mlxsw_sp_setup_tc_red(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct tc_red_qopt_offload *p)
 {
 	struct mlxsw_sp_qdisc *mlxsw_sp_qdisc;
 
···
 					      &mlxsw_sp_qdisc_ops_red,
 					      &p->set);
 
-	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle,
-				    MLXSW_SP_QDISC_RED))
+	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle))
 		return -EOPNOTSUPP;
 
 	switch (p->command) {
···
 	default:
 		return -EOPNOTSUPP;
 	}
+}
+
+int mlxsw_sp_setup_tc_red(struct mlxsw_sp_port *mlxsw_sp_port,
+			  struct tc_red_qopt_offload *p)
+{
+	int err;
+
+	mutex_lock(&mlxsw_sp_port->qdisc->lock);
+	err = __mlxsw_sp_setup_tc_red(mlxsw_sp_port, p);
+	mutex_unlock(&mlxsw_sp_port->qdisc->lock);
+
+	return err;
 }
 
 static void
···
 mlxsw_sp_qdisc_tbf_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
 			   struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
 {
-	struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc;
-	struct mlxsw_sp_qdisc *root_qdisc = &qdisc_state->root_qdisc;
-
-	if (root_qdisc != mlxsw_sp_qdisc)
-		root_qdisc->stats_base.backlog -=
-					mlxsw_sp_qdisc->stats_base.backlog;
-
 	return mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
 					     MLXSW_REG_QEEC_HR_SUBGROUP,
 					     mlxsw_sp_qdisc->tclass_num, 0,
···
 
 static int
 mlxsw_sp_qdisc_tbf_check_params(struct mlxsw_sp_port *mlxsw_sp_port,
-				struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
 				void *params)
 {
 	struct tc_tbf_qopt_offload_replace_params *p = params;
···
 	.destroy = mlxsw_sp_qdisc_tbf_destroy,
 	.get_stats = mlxsw_sp_qdisc_get_tbf_stats,
 	.clean_stats = mlxsw_sp_setup_tc_qdisc_leaf_clean_stats,
+	.find_class = mlxsw_sp_qdisc_leaf_find_class,
 };
 
-int mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port,
-			  struct tc_tbf_qopt_offload *p)
+static int __mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct tc_tbf_qopt_offload *p)
 {
 	struct mlxsw_sp_qdisc *mlxsw_sp_qdisc;
 
···
 					      &mlxsw_sp_qdisc_ops_tbf,
 					      &p->replace_params);
 
-	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle,
-				    MLXSW_SP_QDISC_TBF))
+	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle))
 		return -EOPNOTSUPP;
 
 	switch (p->command) {
···
 	}
 }
 
-static int
-mlxsw_sp_qdisc_fifo_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
-			    struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
+int mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port,
+			  struct tc_tbf_qopt_offload *p)
 {
-	struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc;
-	struct mlxsw_sp_qdisc *root_qdisc = &qdisc_state->root_qdisc;
+	int err;
 
-	if (root_qdisc != mlxsw_sp_qdisc)
-		root_qdisc->stats_base.backlog -=
-					mlxsw_sp_qdisc->stats_base.backlog;
-	return 0;
+	mutex_lock(&mlxsw_sp_port->qdisc->lock);
+	err = __mlxsw_sp_setup_tc_tbf(mlxsw_sp_port, p);
+	mutex_unlock(&mlxsw_sp_port->qdisc->lock);
+
+	return err;
 }
 
 static int
 mlxsw_sp_qdisc_fifo_check_params(struct mlxsw_sp_port *mlxsw_sp_port,
-				 struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
 				 void *params)
 {
 	return 0;
···
 	.type = MLXSW_SP_QDISC_FIFO,
 	.check_params = mlxsw_sp_qdisc_fifo_check_params,
 	.replace = mlxsw_sp_qdisc_fifo_replace,
-	.destroy = mlxsw_sp_qdisc_fifo_destroy,
 	.get_stats = mlxsw_sp_qdisc_get_fifo_stats,
 	.clean_stats = mlxsw_sp_setup_tc_qdisc_leaf_clean_stats,
 };
 
-int mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct tc_fifo_qopt_offload *p)
+static int __mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port,
+				    struct tc_fifo_qopt_offload *p)
 {
 	struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc;
 	struct mlxsw_sp_qdisc *mlxsw_sp_qdisc;
-	int tclass, child_index;
+	unsigned int band;
 	u32 parent_handle;
-
-	/* Invisible FIFOs are tracked in future_handle and future_fifos. Make
-	 * sure that not more than one qdisc is created for a port at a time.
-	 * RTNL is a simple proxy for that.
-	 */
-	ASSERT_RTNL();
 
 	mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, false);
 	if (!mlxsw_sp_qdisc && p->handle == TC_H_UNSPEC) {
···
 			qdisc_state->future_handle = parent_handle;
 		}
 
-		child_index = TC_H_MIN(p->parent);
-		tclass = MLXSW_SP_PRIO_CHILD_TO_TCLASS(child_index);
-		if (tclass < IEEE_8021QAZ_MAX_TCS) {
+		band = TC_H_MIN(p->parent) - 1;
+		if (band < IEEE_8021QAZ_MAX_TCS) {
 			if (p->command == TC_FIFO_REPLACE)
-				qdisc_state->future_fifos[tclass] = true;
+				qdisc_state->future_fifos[band] = true;
 			else if (p->command == TC_FIFO_DESTROY)
-				qdisc_state->future_fifos[tclass] = false;
+				qdisc_state->future_fifos[band] = false;
 		}
 	}
 	if (!mlxsw_sp_qdisc)
···
 					      &mlxsw_sp_qdisc_ops_fifo, NULL);
 	}
 
-	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle,
-				    MLXSW_SP_QDISC_FIFO))
+	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle))
 		return -EOPNOTSUPP;
 
 	switch (p->command) {
 	case TC_FIFO_DESTROY:
-		if (p->handle == mlxsw_sp_qdisc->handle)
-			return mlxsw_sp_qdisc_destroy(mlxsw_sp_port,
-						      mlxsw_sp_qdisc);
-		return 0;
+		return mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
 	case TC_FIFO_STATS:
 		return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc,
 						&p->stats);
···
 	return -EOPNOTSUPP;
 }
 
-static int
-__mlxsw_sp_qdisc_ets_destroy(struct mlxsw_sp_port *mlxsw_sp_port)
+int mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port,
+			   struct tc_fifo_qopt_offload *p)
 {
-	struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc;
+	int err;
+
+	mutex_lock(&mlxsw_sp_port->qdisc->lock);
+	err = __mlxsw_sp_setup_tc_fifo(mlxsw_sp_port, p);
+	mutex_unlock(&mlxsw_sp_port->qdisc->lock);
+
+	return err;
+}
+
+static int __mlxsw_sp_qdisc_ets_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
+					struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
+{
 	int i;
 
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+	for (i = 0; i < mlxsw_sp_qdisc->num_classes; i++) {
 		mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, i,
 					  MLXSW_SP_PORT_DEFAULT_TCLASS);
 		mlxsw_sp_port_ets_set(mlxsw_sp_port,
 				      MLXSW_REG_QEEC_HR_SUBGROUP,
 				      i, 0, false, 0);
 		mlxsw_sp_qdisc_destroy(mlxsw_sp_port,
-				       &qdisc_state->tclass_qdiscs[i]);
-		qdisc_state->tclass_qdiscs[i].prio_bitmap = 0;
+				       &mlxsw_sp_qdisc->qdiscs[i]);
+		mlxsw_sp_qdisc->qdiscs[i].prio_bitmap = 0;
 	}
 
 	return 0;
···
 mlxsw_sp_qdisc_prio_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
 			    struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
 {
-	return __mlxsw_sp_qdisc_ets_destroy(mlxsw_sp_port);
+	return __mlxsw_sp_qdisc_ets_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
 }
 
 static int
···
 
 static int
 mlxsw_sp_qdisc_prio_check_params(struct mlxsw_sp_port *mlxsw_sp_port,
-				 struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
 				 void *params)
 {
 	struct tc_prio_qopt_offload_params *p = params;
···
 }
 
 static int
-__mlxsw_sp_qdisc_ets_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle,
-			     unsigned int nbands,
+__mlxsw_sp_qdisc_ets_replace(struct mlxsw_sp_port *mlxsw_sp_port,
+			     struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+			     u32 handle, unsigned int nbands,
 			     const unsigned int *quanta,
 			     const unsigned int *weights,
 			     const u8 *priomap)
···
 
 	for (band = 0; band < nbands; band++) {
 		tclass = MLXSW_SP_PRIO_BAND_TO_TCLASS(band);
-		child_qdisc = &qdisc_state->tclass_qdiscs[tclass];
+		child_qdisc = &mlxsw_sp_qdisc->qdiscs[band];
 		old_priomap = child_qdisc->prio_bitmap;
 		child_qdisc->prio_bitmap = 0;
 
···
 					return err;
 			}
 		}
+
+		child_qdisc->tclass_num = tclass;
+
 		if (old_priomap != child_qdisc->prio_bitmap &&
 		    child_qdisc->ops && child_qdisc->ops->clean_stats) {
 			backlog = child_qdisc->stats_base.backlog;
···
 		}
 
 		if (handle == qdisc_state->future_handle &&
-		    qdisc_state->future_fifos[tclass]) {
+		    qdisc_state->future_fifos[band]) {
 			err = mlxsw_sp_qdisc_replace(mlxsw_sp_port, TC_H_UNSPEC,
 						     child_qdisc,
 						     &mlxsw_sp_qdisc_ops_fifo,
···
 	}
 	for (; band < IEEE_8021QAZ_MAX_TCS; band++) {
 		tclass = MLXSW_SP_PRIO_BAND_TO_TCLASS(band);
-		child_qdisc = &qdisc_state->tclass_qdiscs[tclass];
+		child_qdisc = &mlxsw_sp_qdisc->qdiscs[band];
 		child_qdisc->prio_bitmap = 0;
 		mlxsw_sp_qdisc_destroy(mlxsw_sp_port, child_qdisc);
 		mlxsw_sp_port_ets_set(mlxsw_sp_port,
···
 	struct tc_prio_qopt_offload_params *p = params;
 	unsigned int zeroes[TCQ_ETS_MAX_BANDS] = {0};
 
-	return __mlxsw_sp_qdisc_ets_replace(mlxsw_sp_port, handle, p->bands,
-					    zeroes, zeroes, p->priomap);
+	return __mlxsw_sp_qdisc_ets_replace(mlxsw_sp_port, mlxsw_sp_qdisc,
+					    handle, p->bands, zeroes,
+					    zeroes, p->priomap);
 }
 
 static void
···
 			      struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
 			      struct tc_qopt_offload_stats *stats_ptr)
 {
-	struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc;
 	struct mlxsw_sp_qdisc *tc_qdisc;
 	u64 tx_packets = 0;
 	u64 tx_bytes = 0;
···
 	u64 drops = 0;
 	int i;
 
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
-		tc_qdisc = &qdisc_state->tclass_qdiscs[i];
+	for (i = 0; i < mlxsw_sp_qdisc->num_classes; i++) {
+		tc_qdisc = &mlxsw_sp_qdisc->qdiscs[i];
 		mlxsw_sp_qdisc_collect_tc_stats(mlxsw_sp_port, tc_qdisc,
 						&tx_bytes, &tx_packets,
 						&drops, &backlog);
···
 	mlxsw_sp_qdisc->stats_base.backlog = 0;
 }
 
+static struct mlxsw_sp_qdisc *
+mlxsw_sp_qdisc_prio_find_class(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+			       u32 parent)
+{
+	int child_index = TC_H_MIN(parent);
+	int band = child_index - 1;
+
+	if (band < 0 || band >= mlxsw_sp_qdisc->num_classes)
+		return NULL;
+	return &mlxsw_sp_qdisc->qdiscs[band];
+}
+
 static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_prio = {
 	.type = MLXSW_SP_QDISC_PRIO,
 	.check_params = mlxsw_sp_qdisc_prio_check_params,
···
 	.destroy = mlxsw_sp_qdisc_prio_destroy,
 	.get_stats = mlxsw_sp_qdisc_get_prio_stats,
 	.clean_stats = mlxsw_sp_setup_tc_qdisc_prio_clean_stats,
+	.find_class = mlxsw_sp_qdisc_prio_find_class,
+	.num_classes = IEEE_8021QAZ_MAX_TCS,
 };
 
 static int
 mlxsw_sp_qdisc_ets_check_params(struct mlxsw_sp_port *mlxsw_sp_port,
-				struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
 				void *params)
 {
 	struct tc_ets_qopt_offload_replace_params *p = params;
···
 {
 	struct tc_ets_qopt_offload_replace_params *p = params;
 
-	return __mlxsw_sp_qdisc_ets_replace(mlxsw_sp_port, handle, p->bands,
-					    p->quanta, p->weights, p->priomap);
+	return __mlxsw_sp_qdisc_ets_replace(mlxsw_sp_port, mlxsw_sp_qdisc,
+					    handle, p->bands, p->quanta,
+					    p->weights, p->priomap);
 }
 
 static void
···
 mlxsw_sp_qdisc_ets_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
 			   struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
 {
-	return __mlxsw_sp_qdisc_ets_destroy(mlxsw_sp_port);
+	return __mlxsw_sp_qdisc_ets_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
 }
 
 static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_ets = {
···
 	.destroy = mlxsw_sp_qdisc_ets_destroy,
 	.get_stats = mlxsw_sp_qdisc_get_prio_stats,
 	.clean_stats = mlxsw_sp_setup_tc_qdisc_prio_clean_stats,
+	.find_class = mlxsw_sp_qdisc_prio_find_class,
+	.num_classes = IEEE_8021QAZ_MAX_TCS,
 };
 
 /* Linux allows linking of Qdiscs to arbitrary classes (so long as the resulting
···
 			   struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
 			   u8 band, u32 child_handle)
 {
-	struct mlxsw_sp_qdisc_state *qdisc_state = mlxsw_sp_port->qdisc;
-	int tclass_num = MLXSW_SP_PRIO_BAND_TO_TCLASS(band);
 	struct mlxsw_sp_qdisc *old_qdisc;
 
-	if (band < IEEE_8021QAZ_MAX_TCS &&
-	    qdisc_state->tclass_qdiscs[tclass_num].handle == child_handle)
+	if (band < mlxsw_sp_qdisc->num_classes &&
+	    mlxsw_sp_qdisc->qdiscs[band].handle == child_handle)
 		return 0;
 
 	if (!child_handle) {
···
 	if (old_qdisc)
 		mlxsw_sp_qdisc_destroy(mlxsw_sp_port, old_qdisc);
 
-	mlxsw_sp_qdisc_destroy(mlxsw_sp_port,
-			       &qdisc_state->tclass_qdiscs[tclass_num]);
+	mlxsw_sp_qdisc = mlxsw_sp_qdisc->ops->find_class(mlxsw_sp_qdisc, band);
+	if (!WARN_ON(!mlxsw_sp_qdisc))
+		mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
+
 	return -EOPNOTSUPP;
 }
 
···
 					  p->band, p->child_handle);
 }
 
-int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct tc_prio_qopt_offload *p)
+static int __mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port,
+				    struct tc_prio_qopt_offload *p)
 {
 	struct mlxsw_sp_qdisc *mlxsw_sp_qdisc;
 
···
 					      &mlxsw_sp_qdisc_ops_prio,
 					      &p->replace_params);
 
-	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle,
-				    MLXSW_SP_QDISC_PRIO))
+	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle))
 		return -EOPNOTSUPP;
 
 	switch (p->command) {
···
 	}
 }
 
-int mlxsw_sp_setup_tc_ets(struct mlxsw_sp_port *mlxsw_sp_port,
-			  struct tc_ets_qopt_offload *p)
+int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port,
+			   struct tc_prio_qopt_offload *p)
+{
+	int err;
+
+	mutex_lock(&mlxsw_sp_port->qdisc->lock);
+	err = __mlxsw_sp_setup_tc_prio(mlxsw_sp_port, p);
+	mutex_unlock(&mlxsw_sp_port->qdisc->lock);
+
+	return err;
+}
+
+static int __mlxsw_sp_setup_tc_ets(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct tc_ets_qopt_offload *p)
 {
 	struct mlxsw_sp_qdisc *mlxsw_sp_qdisc;
 
···
 					      &mlxsw_sp_qdisc_ops_ets,
 					      &p->replace_params);
 
-	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle,
-				    MLXSW_SP_QDISC_ETS))
+	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle))
 		return -EOPNOTSUPP;
 
 	switch (p->command) {
···
 	default:
 		return -EOPNOTSUPP;
 	}
+}
+
+int mlxsw_sp_setup_tc_ets(struct mlxsw_sp_port *mlxsw_sp_port,
+			  struct tc_ets_qopt_offload *p)
+{
+	int err;
+
+	mutex_lock(&mlxsw_sp_port->qdisc->lock);
+	err = __mlxsw_sp_setup_tc_ets(mlxsw_sp_port, p);
+	mutex_unlock(&mlxsw_sp_port->qdisc->lock);
+
+	return err;
 }
 
 struct mlxsw_sp_qevent_block {
···
 int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
 	struct mlxsw_sp_qdisc_state *qdisc_state;
-	int i;
 
 	qdisc_state = kzalloc(sizeof(*qdisc_state), GFP_KERNEL);
 	if (!qdisc_state)
 		return -ENOMEM;
 
+	mutex_init(&qdisc_state->lock);
 	qdisc_state->root_qdisc.prio_bitmap = 0xff;
 	qdisc_state->root_qdisc.tclass_num = MLXSW_SP_PORT_DEFAULT_TCLASS;
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
-		qdisc_state->tclass_qdiscs[i].tclass_num = i;
-
 	mlxsw_sp_port->qdisc = qdisc_state;
 	return 0;
 }
 
 void mlxsw_sp_tc_qdisc_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 {
+	mutex_destroy(&mlxsw_sp_port->qdisc->lock);
 	kfree(mlxsw_sp_port->qdisc);
 }

tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh

···
 {
 	install_qdisc
 
+	# Make sure that we get the non-zero value if there is any.
+	local cur=$(busywait 1100 until_counter_is "> 0" \
+			    qdisc_stats_get $swp3 10: .backlog)
+	(( cur == 0 ))
+	check_err $? "backlog of $cur observed on non-busy qdisc"
+	log_test "$QDISC backlog properly cleaned"
+
 	do_red_test 10 $BACKLOG1
 	do_red_test 11 $BACKLOG2