Linux-libre 4.7.1-gnupck-4.7.1-gnu

11 files changed, 3140 insertions, 628 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index 2ad7f6785..5989f7cb5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -50,3 +50,11 @@ config MLXSW_SPECTRUM
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called mlxsw_spectrum.
+
+config MLXSW_SPECTRUM_DCB
+	bool "Data Center Bridging (DCB) support"
+	depends on MLXSW_SPECTRUM && DCB
+	default y
+	---help---
+	  Say Y here if you want to use Data Center Bridging (DCB) in the
+	  driver.
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 584cac444..9b5ebf84c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -8,3 +8,4 @@ mlxsw_switchx2-objs		:= switchx2.o
 obj-$(CONFIG_MLXSW_SPECTRUM)	+= mlxsw_spectrum.o
 mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_switchdev.o
+mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index f69f62805..b0a0b01bb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -44,7 +44,7 @@
 #include <linux/seq_file.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/netdevice.h>
-#include <linux/wait.h>
+#include <linux/completion.h>
 #include <linux/skbuff.h>
 #include <linux/etherdevice.h>
 #include <linux/types.h>
@@ -55,6 +55,7 @@
 #include <linux/mutex.h>
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
+#include <linux/workqueue.h>
 #include <asm/byteorder.h>
 #include <net/devlink.h>
 
@@ -73,6 +74,8 @@ static const char mlxsw_core_driver_name[] = "mlxsw_core";
 
 static struct dentry *mlxsw_core_dbg_root;
 
+static struct workqueue_struct *mlxsw_wq;
+
 struct mlxsw_core_pcpu_stats {
 	u64			trap_rx_packets[MLXSW_TRAP_ID_MAX];
 	u64			trap_rx_bytes[MLXSW_TRAP_ID_MAX];
@@ -93,11 +96,9 @@ struct mlxsw_core {
 	struct list_head rx_listener_list;
 	struct list_head event_listener_list;
 	struct {
-		struct sk_buff *resp_skb;
-		u64 tid;
-		wait_queue_head_t wait;
-		bool trans_active;
-		struct mutex lock; /* One EMAD transaction at a time. */
+		atomic64_t tid;
+		struct list_head trans_list;
+		spinlock_t trans_list_lock; /* protects trans_list writes */
 		bool use_emad;
 	} emad;
 	struct mlxsw_core_pcpu_stats __percpu *pcpu_stats;
@@ -114,6 +115,12 @@ struct mlxsw_core {
 	/* driver_priv has to be always the last item */
 };
 
+void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->driver_priv;
+}
+EXPORT_SYMBOL(mlxsw_core_driver_priv);
+
 struct mlxsw_rx_listener_item {
 	struct list_head list;
 	struct mlxsw_rx_listener rxl;
@@ -284,7 +291,7 @@ static void mlxsw_emad_pack_reg_tlv(char *reg_tlv,
 static void mlxsw_emad_pack_op_tlv(char *op_tlv,
 				   const struct mlxsw_reg_info *reg,
 				   enum mlxsw_core_reg_access_type type,
-				   struct mlxsw_core *mlxsw_core)
+				   u64 tid)
 {
 	mlxsw_emad_op_tlv_type_set(op_tlv, MLXSW_EMAD_TLV_TYPE_OP);
 	mlxsw_emad_op_tlv_len_set(op_tlv, MLXSW_EMAD_OP_TLV_LEN);
@@ -300,7 +307,7 @@ static void mlxsw_emad_pack_op_tlv(char *op_tlv,
 					     MLXSW_EMAD_OP_TLV_METHOD_WRITE);
 	mlxsw_emad_op_tlv_class_set(op_tlv,
 				    MLXSW_EMAD_OP_TLV_CLASS_REG_ACCESS);
-	mlxsw_emad_op_tlv_tid_set(op_tlv, mlxsw_core->emad.tid);
+	mlxsw_emad_op_tlv_tid_set(op_tlv, tid);
 }
 
 static int mlxsw_emad_construct_eth_hdr(struct sk_buff *skb)
@@ -322,7 +329,7 @@ static void mlxsw_emad_construct(struct sk_buff *skb,
 				 const struct mlxsw_reg_info *reg,
 				 char *payload,
 				 enum mlxsw_core_reg_access_type type,
-				 struct mlxsw_core *mlxsw_core)
+				 u64 tid)
 {
 	char *buf;
 
@@ -333,7 +340,7 @@ static void mlxsw_emad_construct(struct sk_buff *skb,
 	mlxsw_emad_pack_reg_tlv(buf, reg, payload);
 
 	buf = skb_push(skb, MLXSW_EMAD_OP_TLV_LEN * sizeof(u32));
-	mlxsw_emad_pack_op_tlv(buf, reg, type, mlxsw_core);
+	mlxsw_emad_pack_op_tlv(buf, reg, type, tid);
 
 	mlxsw_emad_construct_eth_hdr(skb);
 }
@@ -370,58 +377,16 @@ static bool mlxsw_emad_is_resp(const struct sk_buff *skb)
 	return (mlxsw_emad_op_tlv_r_get(op_tlv) == MLXSW_EMAD_OP_TLV_RESPONSE);
 }
 
-#define MLXSW_EMAD_TIMEOUT_MS 200
-
-static int __mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,
-				 struct sk_buff *skb,
-				 const struct mlxsw_tx_info *tx_info)
-{
-	int err;
-	int ret;
-
-	mlxsw_core->emad.trans_active = true;
-
-	err = mlxsw_core_skb_transmit(mlxsw_core->driver_priv, skb, tx_info);
-	if (err) {
-		dev_err(mlxsw_core->bus_info->dev, "Failed to transmit EMAD (tid=%llx)\n",
-			mlxsw_core->emad.tid);
-		dev_kfree_skb(skb);
-		goto trans_inactive_out;
-	}
-
-	ret = wait_event_timeout(mlxsw_core->emad.wait,
-				 !(mlxsw_core->emad.trans_active),
-				 msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_MS));
-	if (!ret) {
-		dev_warn(mlxsw_core->bus_info->dev, "EMAD timed-out (tid=%llx)\n",
-			 mlxsw_core->emad.tid);
-		err = -EIO;
-		goto trans_inactive_out;
-	}
-
-	return 0;
-
-trans_inactive_out:
-	mlxsw_core->emad.trans_active = false;
-	return err;
-}
-
-static int mlxsw_emad_process_status(struct mlxsw_core *mlxsw_core,
-				     char *op_tlv)
+static int mlxsw_emad_process_status(char *op_tlv,
+				     enum mlxsw_emad_op_tlv_status *p_status)
 {
-	enum mlxsw_emad_op_tlv_status status;
-	u64 tid;
+	*p_status = mlxsw_emad_op_tlv_status_get(op_tlv);
 
-	status = mlxsw_emad_op_tlv_status_get(op_tlv);
-	tid = mlxsw_emad_op_tlv_tid_get(op_tlv);
-
-	switch (status) {
+	switch (*p_status) {
 	case MLXSW_EMAD_OP_TLV_STATUS_SUCCESS:
 		return 0;
 	case MLXSW_EMAD_OP_TLV_STATUS_BUSY:
 	case MLXSW_EMAD_OP_TLV_STATUS_MESSAGE_RECEIPT_ACK:
-		dev_warn(mlxsw_core->bus_info->dev, "Reg access status again (tid=%llx,status=%x(%s))\n",
-			 tid, status, mlxsw_emad_op_tlv_status_str(status));
 		return -EAGAIN;
 	case MLXSW_EMAD_OP_TLV_STATUS_VERSION_NOT_SUPPORTED:
 	case MLXSW_EMAD_OP_TLV_STATUS_UNKNOWN_TLV:
@@ -432,70 +397,150 @@ static int mlxsw_emad_process_status(struct mlxsw_core *mlxsw_core,
 	case MLXSW_EMAD_OP_TLV_STATUS_RESOURCE_NOT_AVAILABLE:
 	case MLXSW_EMAD_OP_TLV_STATUS_INTERNAL_ERROR:
 	default:
-		dev_err(mlxsw_core->bus_info->dev, "Reg access status failed (tid=%llx,status=%x(%s))\n",
-			tid, status, mlxsw_emad_op_tlv_status_str(status));
 		return -EIO;
 	}
 }
 
-static int mlxsw_emad_process_status_skb(struct mlxsw_core *mlxsw_core,
-					 struct sk_buff *skb)
+static int
+mlxsw_emad_process_status_skb(struct sk_buff *skb,
+			      enum mlxsw_emad_op_tlv_status *p_status)
+{
+	return mlxsw_emad_process_status(mlxsw_emad_op_tlv(skb), p_status);
+}
+
+struct mlxsw_reg_trans {
+	struct list_head list;
+	struct list_head bulk_list;
+	struct mlxsw_core *core;
+	struct sk_buff *tx_skb;
+	struct mlxsw_tx_info tx_info;
+	struct delayed_work timeout_dw;
+	unsigned int retries;
+	u64 tid;
+	struct completion completion;
+	atomic_t active;
+	mlxsw_reg_trans_cb_t *cb;
+	unsigned long cb_priv;
+	const struct mlxsw_reg_info *reg;
+	enum mlxsw_core_reg_access_type type;
+	int err;
+	enum mlxsw_emad_op_tlv_status emad_status;
+	struct rcu_head rcu;
+};
+
+#define MLXSW_EMAD_TIMEOUT_MS 200
+
+static void mlxsw_emad_trans_timeout_schedule(struct mlxsw_reg_trans *trans)
 {
-	return mlxsw_emad_process_status(mlxsw_core, mlxsw_emad_op_tlv(skb));
+	unsigned long timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_MS);
+
+	mlxsw_core_schedule_dw(&trans->timeout_dw, timeout);
 }
 
 static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,
-			       struct sk_buff *skb,
-			       const struct mlxsw_tx_info *tx_info)
+			       struct mlxsw_reg_trans *trans)
 {
-	struct sk_buff *trans_skb;
-	int n_retry;
+	struct sk_buff *skb;
 	int err;
 
-	n_retry = 0;
-retry:
-	/* We copy the EMAD to a new skb, since we might need
-	 * to retransmit it in case of failure.
-	 */
-	trans_skb = skb_copy(skb, GFP_KERNEL);
-	if (!trans_skb) {
-		err = -ENOMEM;
-		goto out;
+	skb = skb_copy(trans->tx_skb, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	atomic_set(&trans->active, 1);
+	err = mlxsw_core_skb_transmit(mlxsw_core, skb, &trans->tx_info);
+	if (err) {
+		dev_kfree_skb(skb);
+		return err;
 	}
+	mlxsw_emad_trans_timeout_schedule(trans);
+	return 0;
+}
 
-	err = __mlxsw_emad_transmit(mlxsw_core, trans_skb, tx_info);
-	if (!err) {
-		struct sk_buff *resp_skb = mlxsw_core->emad.resp_skb;
+static void mlxsw_emad_trans_finish(struct mlxsw_reg_trans *trans, int err)
+{
+	struct mlxsw_core *mlxsw_core = trans->core;
+
+	dev_kfree_skb(trans->tx_skb);
+	spin_lock_bh(&mlxsw_core->emad.trans_list_lock);
+	list_del_rcu(&trans->list);
+	spin_unlock_bh(&mlxsw_core->emad.trans_list_lock);
+	trans->err = err;
+	complete(&trans->completion);
+}
 
-		err = mlxsw_emad_process_status_skb(mlxsw_core, resp_skb);
-		if (err)
-			dev_kfree_skb(resp_skb);
-		if (!err || err != -EAGAIN)
-			goto out;
+static void mlxsw_emad_transmit_retry(struct mlxsw_core *mlxsw_core,
+				      struct mlxsw_reg_trans *trans)
+{
+	int err;
+
+	if (trans->retries < MLXSW_EMAD_MAX_RETRY) {
+		trans->retries++;
+		err = mlxsw_emad_transmit(trans->core, trans);
+		if (err == 0)
+			return;
+	} else {
+		err = -EIO;
 	}
-	if (n_retry++ < MLXSW_EMAD_MAX_RETRY)
-		goto retry;
+	mlxsw_emad_trans_finish(trans, err);
+}
 
-out:
-	dev_kfree_skb(skb);
-	mlxsw_core->emad.tid++;
-	return err;
+static void mlxsw_emad_trans_timeout_work(struct work_struct *work)
+{
+	struct mlxsw_reg_trans *trans = container_of(work,
+						     struct mlxsw_reg_trans,
+						     timeout_dw.work);
+
+	if (!atomic_dec_and_test(&trans->active))
+		return;
+
+	mlxsw_emad_transmit_retry(trans->core, trans);
+}
+
+static void mlxsw_emad_process_response(struct mlxsw_core *mlxsw_core,
+					struct mlxsw_reg_trans *trans,
+					struct sk_buff *skb)
+{
+	int err;
+
+	if (!atomic_dec_and_test(&trans->active))
+		return;
+
+	err = mlxsw_emad_process_status_skb(skb, &trans->emad_status);
+	if (err == -EAGAIN) {
+		mlxsw_emad_transmit_retry(mlxsw_core, trans);
+	} else {
+		if (err == 0) {
+			char *op_tlv = mlxsw_emad_op_tlv(skb);
+
+			if (trans->cb)
+				trans->cb(mlxsw_core,
+					  mlxsw_emad_reg_payload(op_tlv),
+					  trans->reg->len, trans->cb_priv);
+		}
+		mlxsw_emad_trans_finish(trans, err);
+	}
 }
 
+/* called with rcu read lock held */
 static void mlxsw_emad_rx_listener_func(struct sk_buff *skb, u8 local_port,
 					void *priv)
 {
 	struct mlxsw_core *mlxsw_core = priv;
+	struct mlxsw_reg_trans *trans;
 
-	if (mlxsw_emad_is_resp(skb) &&
-	    mlxsw_core->emad.trans_active &&
-	    mlxsw_emad_get_tid(skb) == mlxsw_core->emad.tid) {
-		mlxsw_core->emad.resp_skb = skb;
-		mlxsw_core->emad.trans_active = false;
-		wake_up(&mlxsw_core->emad.wait);
-	} else {
-		dev_kfree_skb(skb);
+	if (!mlxsw_emad_is_resp(skb))
+		goto free_skb;
+
+	list_for_each_entry_rcu(trans, &mlxsw_core->emad.trans_list, list) {
+		if (mlxsw_emad_get_tid(skb) == trans->tid) {
+			mlxsw_emad_process_response(mlxsw_core, trans, skb);
+			break;
+		}
 	}
+
+free_skb:
+	dev_kfree_skb(skb);
 }
 
 static const struct mlxsw_rx_listener mlxsw_emad_rx_listener = {
@@ -522,18 +567,19 @@ static int mlxsw_emad_traps_set(struct mlxsw_core *mlxsw_core)
 
 static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 {
+	u64 tid;
 	int err;
 
 	/* Set the upper 32 bits of the transaction ID field to a random
 	 * number. This allows us to discard EMADs addressed to other
 	 * devices.
 	 */
-	get_random_bytes(&mlxsw_core->emad.tid, 4);
-	mlxsw_core->emad.tid = mlxsw_core->emad.tid << 32;
+	get_random_bytes(&tid, 4);
+	tid <<= 32;
+	atomic64_set(&mlxsw_core->emad.tid, tid);
 
-	init_waitqueue_head(&mlxsw_core->emad.wait);
-	mlxsw_core->emad.trans_active = false;
-	mutex_init(&mlxsw_core->emad.lock);
+	INIT_LIST_HEAD(&mlxsw_core->emad.trans_list);
+	spin_lock_init(&mlxsw_core->emad.trans_list_lock);
 
 	err = mlxsw_core_rx_listener_register(mlxsw_core,
 					      &mlxsw_emad_rx_listener,
@@ -591,6 +637,59 @@ static struct sk_buff *mlxsw_emad_alloc(const struct mlxsw_core *mlxsw_core,
 	return skb;
 }
 
+static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core,
+				 const struct mlxsw_reg_info *reg,
+				 char *payload,
+				 enum mlxsw_core_reg_access_type type,
+				 struct mlxsw_reg_trans *trans,
+				 struct list_head *bulk_list,
+				 mlxsw_reg_trans_cb_t *cb,
+				 unsigned long cb_priv, u64 tid)
+{
+	struct sk_buff *skb;
+	int err;
+
+	dev_dbg(mlxsw_core->bus_info->dev, "EMAD reg access (tid=%llx,reg_id=%x(%s),type=%s)\n",
+		trans->tid, reg->id, mlxsw_reg_id_str(reg->id),
+		mlxsw_core_reg_access_type_str(type));
+
+	skb = mlxsw_emad_alloc(mlxsw_core, reg->len);
+	if (!skb)
+		return -ENOMEM;
+
+	list_add_tail(&trans->bulk_list, bulk_list);
+	trans->core = mlxsw_core;
+	trans->tx_skb = skb;
+	trans->tx_info.local_port = MLXSW_PORT_CPU_PORT;
+	trans->tx_info.is_emad = true;
+	INIT_DELAYED_WORK(&trans->timeout_dw, mlxsw_emad_trans_timeout_work);
+	trans->tid = tid;
+	init_completion(&trans->completion);
+	trans->cb = cb;
+	trans->cb_priv = cb_priv;
+	trans->reg = reg;
+	trans->type = type;
+
+	mlxsw_emad_construct(skb, reg, payload, type, trans->tid);
+	mlxsw_core->driver->txhdr_construct(skb, &trans->tx_info);
+
+	spin_lock_bh(&mlxsw_core->emad.trans_list_lock);
+	list_add_tail_rcu(&trans->list, &mlxsw_core->emad.trans_list);
+	spin_unlock_bh(&mlxsw_core->emad.trans_list_lock);
+	err = mlxsw_emad_transmit(mlxsw_core, trans);
+	if (err)
+		goto err_out;
+	return 0;
+
+err_out:
+	spin_lock_bh(&mlxsw_core->emad.trans_list_lock);
+	list_del_rcu(&trans->list);
+	spin_unlock_bh(&mlxsw_core->emad.trans_list_lock);
+	list_del(&trans->bulk_list);
+	dev_kfree_skb(trans->tx_skb);
+	return err;
+}
+
 /*****************
  * Core functions
  *****************/
@@ -680,24 +779,6 @@ static const struct file_operations mlxsw_core_rx_stats_dbg_ops = {
 	.llseek = seq_lseek
 };
 
-static void mlxsw_core_buf_dump_dbg(struct mlxsw_core *mlxsw_core,
-				    const char *buf, size_t size)
-{
-	__be32 *m = (__be32 *) buf;
-	int i;
-	int count = size / sizeof(__be32);
-
-	for (i = count - 1; i >= 0; i--)
-		if (m[i])
-			break;
-	i++;
-	count = i ? i : 1;
-	for (i = 0; i < count; i += 4)
-		dev_dbg(mlxsw_core->bus_info->dev, "%04x - %08x %08x %08x %08x\n",
-			i * 4, be32_to_cpu(m[i]), be32_to_cpu(m[i + 1]),
-			be32_to_cpu(m[i + 2]), be32_to_cpu(m[i + 3]));
-}
-
 int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver)
 {
 	spin_lock(&mlxsw_core_driver_list_lock);
@@ -795,8 +876,7 @@ static int mlxsw_devlink_port_split(struct devlink *devlink,
 		return -EINVAL;
 	if (!mlxsw_core->driver->port_split)
 		return -EOPNOTSUPP;
-	return mlxsw_core->driver->port_split(mlxsw_core->driver_priv,
-					      port_index, count);
+	return mlxsw_core->driver->port_split(mlxsw_core, port_index, count);
 }
 
 static int mlxsw_devlink_port_unsplit(struct devlink *devlink,
@@ -808,13 +888,171 @@ static int mlxsw_devlink_port_unsplit(struct devlink *devlink,
 		return -EINVAL;
 	if (!mlxsw_core->driver->port_unsplit)
 		return -EOPNOTSUPP;
-	return mlxsw_core->driver->port_unsplit(mlxsw_core->driver_priv,
-						port_index);
+	return mlxsw_core->driver->port_unsplit(mlxsw_core, port_index);
+}
+
+static int
+mlxsw_devlink_sb_pool_get(struct devlink *devlink,
+			  unsigned int sb_index, u16 pool_index,
+			  struct devlink_sb_pool_info *pool_info)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+
+	if (!mlxsw_driver->sb_pool_get)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->sb_pool_get(mlxsw_core, sb_index,
+					 pool_index, pool_info);
+}
+
+static int
+mlxsw_devlink_sb_pool_set(struct devlink *devlink,
+			  unsigned int sb_index, u16 pool_index, u32 size,
+			  enum devlink_sb_threshold_type threshold_type)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+
+	if (!mlxsw_driver->sb_pool_set)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->sb_pool_set(mlxsw_core, sb_index,
+					 pool_index, size, threshold_type);
+}
+
+static void *__dl_port(struct devlink_port *devlink_port)
+{
+	return container_of(devlink_port, struct mlxsw_core_port, devlink_port);
+}
+
+static int mlxsw_devlink_sb_port_pool_get(struct devlink_port *devlink_port,
+					  unsigned int sb_index, u16 pool_index,
+					  u32 *p_threshold)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+	struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
+
+	if (!mlxsw_driver->sb_port_pool_get)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->sb_port_pool_get(mlxsw_core_port, sb_index,
+					      pool_index, p_threshold);
+}
+
+static int mlxsw_devlink_sb_port_pool_set(struct devlink_port *devlink_port,
+					  unsigned int sb_index, u16 pool_index,
+					  u32 threshold)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+	struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
+
+	if (!mlxsw_driver->sb_port_pool_set)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->sb_port_pool_set(mlxsw_core_port, sb_index,
+					      pool_index, threshold);
+}
+
+static int
+mlxsw_devlink_sb_tc_pool_bind_get(struct devlink_port *devlink_port,
+				  unsigned int sb_index, u16 tc_index,
+				  enum devlink_sb_pool_type pool_type,
+				  u16 *p_pool_index, u32 *p_threshold)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+	struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
+
+	if (!mlxsw_driver->sb_tc_pool_bind_get)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->sb_tc_pool_bind_get(mlxsw_core_port, sb_index,
+						 tc_index, pool_type,
+						 p_pool_index, p_threshold);
+}
+
+static int
+mlxsw_devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
+				  unsigned int sb_index, u16 tc_index,
+				  enum devlink_sb_pool_type pool_type,
+				  u16 pool_index, u32 threshold)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+	struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
+
+	if (!mlxsw_driver->sb_tc_pool_bind_set)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->sb_tc_pool_bind_set(mlxsw_core_port, sb_index,
+						 tc_index, pool_type,
+						 pool_index, threshold);
+}
+
+static int mlxsw_devlink_sb_occ_snapshot(struct devlink *devlink,
+					 unsigned int sb_index)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+
+	if (!mlxsw_driver->sb_occ_snapshot)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->sb_occ_snapshot(mlxsw_core, sb_index);
+}
+
+static int mlxsw_devlink_sb_occ_max_clear(struct devlink *devlink,
+					  unsigned int sb_index)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+
+	if (!mlxsw_driver->sb_occ_max_clear)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->sb_occ_max_clear(mlxsw_core, sb_index);
+}
+
+static int
+mlxsw_devlink_sb_occ_port_pool_get(struct devlink_port *devlink_port,
+				   unsigned int sb_index, u16 pool_index,
+				   u32 *p_cur, u32 *p_max)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+	struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
+
+	if (!mlxsw_driver->sb_occ_port_pool_get)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->sb_occ_port_pool_get(mlxsw_core_port, sb_index,
+						  pool_index, p_cur, p_max);
+}
+
+static int
+mlxsw_devlink_sb_occ_tc_port_bind_get(struct devlink_port *devlink_port,
+				      unsigned int sb_index, u16 tc_index,
+				      enum devlink_sb_pool_type pool_type,
+				      u32 *p_cur, u32 *p_max)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+	struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
+
+	if (!mlxsw_driver->sb_occ_tc_port_bind_get)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->sb_occ_tc_port_bind_get(mlxsw_core_port,
+						     sb_index, tc_index,
+						     pool_type, p_cur, p_max);
 }
 
 static const struct devlink_ops mlxsw_devlink_ops = {
-	.port_split	= mlxsw_devlink_port_split,
-	.port_unsplit	= mlxsw_devlink_port_unsplit,
+	.port_split			= mlxsw_devlink_port_split,
+	.port_unsplit			= mlxsw_devlink_port_unsplit,
+	.sb_pool_get			= mlxsw_devlink_sb_pool_get,
+	.sb_pool_set			= mlxsw_devlink_sb_pool_set,
+	.sb_port_pool_get		= mlxsw_devlink_sb_port_pool_get,
+	.sb_port_pool_set		= mlxsw_devlink_sb_port_pool_set,
+	.sb_tc_pool_bind_get		= mlxsw_devlink_sb_tc_pool_bind_get,
+	.sb_tc_pool_bind_set		= mlxsw_devlink_sb_tc_pool_bind_set,
+	.sb_occ_snapshot		= mlxsw_devlink_sb_occ_snapshot,
+	.sb_occ_max_clear		= mlxsw_devlink_sb_occ_max_clear,
+	.sb_occ_port_pool_get		= mlxsw_devlink_sb_occ_port_pool_get,
+	.sb_occ_tc_port_bind_get	= mlxsw_devlink_sb_occ_tc_port_bind_get,
 };
 
 int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
@@ -880,8 +1118,7 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_devlink_register;
 
-	err = mlxsw_driver->init(mlxsw_core->driver_priv, mlxsw_core,
-				 mlxsw_bus_info);
+	err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info);
 	if (err)
 		goto err_driver_init;
 
@@ -892,7 +1129,7 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	return 0;
 
 err_debugfs_init:
-	mlxsw_core->driver->fini(mlxsw_core->driver_priv);
+	mlxsw_core->driver->fini(mlxsw_core);
 err_driver_init:
 	devlink_unregister(devlink);
 err_devlink_register:
@@ -918,7 +1155,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
 	mlxsw_core_debugfs_fini(mlxsw_core);
-	mlxsw_core->driver->fini(mlxsw_core->driver_priv);
+	mlxsw_core->driver->fini(mlxsw_core);
 	devlink_unregister(devlink);
 	mlxsw_emad_fini(mlxsw_core);
 	mlxsw_core->bus->fini(mlxsw_core->bus_priv);
@@ -929,26 +1166,17 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
 }
 EXPORT_SYMBOL(mlxsw_core_bus_device_unregister);
 
-static struct mlxsw_core *__mlxsw_core_get(void *driver_priv)
-{
-	return container_of(driver_priv, struct mlxsw_core, driver_priv);
-}
-
-bool mlxsw_core_skb_transmit_busy(void *driver_priv,
+bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core,
 				  const struct mlxsw_tx_info *tx_info)
 {
-	struct mlxsw_core *mlxsw_core = __mlxsw_core_get(driver_priv);
-
 	return mlxsw_core->bus->skb_transmit_busy(mlxsw_core->bus_priv,
 						  tx_info);
 }
 EXPORT_SYMBOL(mlxsw_core_skb_transmit_busy);
 
-int mlxsw_core_skb_transmit(void *driver_priv, struct sk_buff *skb,
+int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 			    const struct mlxsw_tx_info *tx_info)
 {
-	struct mlxsw_core *mlxsw_core = __mlxsw_core_get(driver_priv);
-
 	return mlxsw_core->bus->skb_transmit(mlxsw_core->bus_priv, skb,
 					     tx_info);
 }
@@ -1108,56 +1336,112 @@ void mlxsw_core_event_listener_unregister(struct mlxsw_core *mlxsw_core,
 }
 EXPORT_SYMBOL(mlxsw_core_event_listener_unregister);
 
+static u64 mlxsw_core_tid_get(struct mlxsw_core *mlxsw_core)
+{
+	return atomic64_inc_return(&mlxsw_core->emad.tid);
+}
+
 static int mlxsw_core_reg_access_emad(struct mlxsw_core *mlxsw_core,
 				      const struct mlxsw_reg_info *reg,
 				      char *payload,
-				      enum mlxsw_core_reg_access_type type)
+				      enum mlxsw_core_reg_access_type type,
+				      struct list_head *bulk_list,
+				      mlxsw_reg_trans_cb_t *cb,
+				      unsigned long cb_priv)
 {
+	u64 tid = mlxsw_core_tid_get(mlxsw_core);
+	struct mlxsw_reg_trans *trans;
 	int err;
-	char *op_tlv;
-	struct sk_buff *skb;
-	struct mlxsw_tx_info tx_info = {
-		.local_port = MLXSW_PORT_CPU_PORT,
-		.is_emad = true,
-	};
 
-	skb = mlxsw_emad_alloc(mlxsw_core, reg->len);
-	if (!skb)
+	trans = kzalloc(sizeof(*trans), GFP_KERNEL);
+	if (!trans)
 		return -ENOMEM;
 
-	mlxsw_emad_construct(skb, reg, payload, type, mlxsw_core);
-	mlxsw_core->driver->txhdr_construct(skb, &tx_info);
+	err = mlxsw_emad_reg_access(mlxsw_core, reg, payload, type, trans,
+				    bulk_list, cb, cb_priv, tid);
+	if (err) {
+		kfree(trans);
+		return err;
+	}
+	return 0;
+}
 
-	dev_dbg(mlxsw_core->bus_info->dev, "EMAD send (tid=%llx)\n",
-		mlxsw_core->emad.tid);
-	mlxsw_core_buf_dump_dbg(mlxsw_core, skb->data, skb->len);
+int mlxsw_reg_trans_query(struct mlxsw_core *mlxsw_core,
+			  const struct mlxsw_reg_info *reg, char *payload,
+			  struct list_head *bulk_list,
+			  mlxsw_reg_trans_cb_t *cb, unsigned long cb_priv)
+{
+	return mlxsw_core_reg_access_emad(mlxsw_core, reg, payload,
+					  MLXSW_CORE_REG_ACCESS_TYPE_QUERY,
+					  bulk_list, cb, cb_priv);
+}
+EXPORT_SYMBOL(mlxsw_reg_trans_query);
 
-	err = mlxsw_emad_transmit(mlxsw_core, skb, &tx_info);
-	if (!err) {
-		op_tlv = mlxsw_emad_op_tlv(mlxsw_core->emad.resp_skb);
-		memcpy(payload, mlxsw_emad_reg_payload(op_tlv),
-		       reg->len);
+int mlxsw_reg_trans_write(struct mlxsw_core *mlxsw_core,
+			  const struct mlxsw_reg_info *reg, char *payload,
+			  struct list_head *bulk_list,
+			  mlxsw_reg_trans_cb_t *cb, unsigned long cb_priv)
+{
+	return mlxsw_core_reg_access_emad(mlxsw_core, reg, payload,
+					  MLXSW_CORE_REG_ACCESS_TYPE_WRITE,
+					  bulk_list, cb, cb_priv);
+}
+EXPORT_SYMBOL(mlxsw_reg_trans_write);
 
-		dev_dbg(mlxsw_core->bus_info->dev, "EMAD recv (tid=%llx)\n",
-			mlxsw_core->emad.tid - 1);
-		mlxsw_core_buf_dump_dbg(mlxsw_core,
-					mlxsw_core->emad.resp_skb->data,
-					mlxsw_core->emad.resp_skb->len);
+static int mlxsw_reg_trans_wait(struct mlxsw_reg_trans *trans)
+{
+	struct mlxsw_core *mlxsw_core = trans->core;
+	int err;
 
-		dev_kfree_skb(mlxsw_core->emad.resp_skb);
-	}
+	wait_for_completion(&trans->completion);
+	cancel_delayed_work_sync(&trans->timeout_dw);
+	err = trans->err;
 
+	if (trans->retries)
+		dev_warn(mlxsw_core->bus_info->dev, "EMAD retries (%d/%d) (tid=%llx)\n",
+			 trans->retries, MLXSW_EMAD_MAX_RETRY, trans->tid);
+	if (err)
+		dev_err(mlxsw_core->bus_info->dev, "EMAD reg access failed (tid=%llx,reg_id=%x(%s),type=%s,status=%x(%s))\n",
+			trans->tid, trans->reg->id,
+			mlxsw_reg_id_str(trans->reg->id),
+			mlxsw_core_reg_access_type_str(trans->type),
+			trans->emad_status,
+			mlxsw_emad_op_tlv_status_str(trans->emad_status));
+
+	list_del(&trans->bulk_list);
+	kfree_rcu(trans, rcu);
 	return err;
 }
 
+int mlxsw_reg_trans_bulk_wait(struct list_head *bulk_list)
+{
+	struct mlxsw_reg_trans *trans;
+	struct mlxsw_reg_trans *tmp;
+	int sum_err = 0;
+	int err;
+
+	list_for_each_entry_safe(trans, tmp, bulk_list, bulk_list) {
+		err = mlxsw_reg_trans_wait(trans);
+		if (err && sum_err == 0)
+			sum_err = err; /* first error to be returned */
+	}
+	return sum_err;
+}
+EXPORT_SYMBOL(mlxsw_reg_trans_bulk_wait);
+
 static int mlxsw_core_reg_access_cmd(struct mlxsw_core *mlxsw_core,
 				     const struct mlxsw_reg_info *reg,
 				     char *payload,
 				     enum mlxsw_core_reg_access_type type)
 {
+	enum mlxsw_emad_op_tlv_status status;
 	int err, n_retry;
 	char *in_mbox, *out_mbox, *tmp;
 
+	dev_dbg(mlxsw_core->bus_info->dev, "Reg cmd access (reg_id=%x(%s),type=%s)\n",
+		reg->id, mlxsw_reg_id_str(reg->id),
+		mlxsw_core_reg_access_type_str(type));
+
 	in_mbox = mlxsw_cmd_mbox_alloc();
 	if (!in_mbox)
 		return -ENOMEM;
@@ -1168,7 +1452,8 @@ static int mlxsw_core_reg_access_cmd(struct mlxsw_core *mlxsw_core,
 		goto free_in_mbox;
 	}
 
-	mlxsw_emad_pack_op_tlv(in_mbox, reg, type, mlxsw_core);
+	mlxsw_emad_pack_op_tlv(in_mbox, reg, type,
+			       mlxsw_core_tid_get(mlxsw_core));
 	tmp = in_mbox + MLXSW_EMAD_OP_TLV_LEN * sizeof(u32);
 	mlxsw_emad_pack_reg_tlv(tmp, reg, payload);
 
@@ -1176,60 +1461,61 @@ static int mlxsw_core_reg_access_cmd(struct mlxsw_core *mlxsw_core,
 retry:
 	err = mlxsw_cmd_access_reg(mlxsw_core, in_mbox, out_mbox);
 	if (!err) {
-		err = mlxsw_emad_process_status(mlxsw_core, out_mbox);
-		if (err == -EAGAIN && n_retry++ < MLXSW_EMAD_MAX_RETRY)
-			goto retry;
+		err = mlxsw_emad_process_status(out_mbox, &status);
+		if (err) {
+			if (err == -EAGAIN && n_retry++ < MLXSW_EMAD_MAX_RETRY)
+				goto retry;
+			dev_err(mlxsw_core->bus_info->dev, "Reg cmd access status failed (status=%x(%s))\n",
+				status, mlxsw_emad_op_tlv_status_str(status));
+		}
 	}
 
 	if (!err)
 		memcpy(payload, mlxsw_emad_reg_payload(out_mbox),
 		       reg->len);
 
-	mlxsw_core->emad.tid++;
 	mlxsw_cmd_mbox_free(out_mbox);
 free_in_mbox:
 	mlxsw_cmd_mbox_free(in_mbox);
+	if (err)
+		dev_err(mlxsw_core->bus_info->dev, "Reg cmd access failed (reg_id=%x(%s),type=%s)\n",
+			reg->id, mlxsw_reg_id_str(reg->id),
+			mlxsw_core_reg_access_type_str(type));
 	return err;
 }
 
+static void mlxsw_core_reg_access_cb(struct mlxsw_core *mlxsw_core,
+				     char *payload, size_t payload_len,
+				     unsigned long cb_priv)
+{
+	char *orig_payload = (char *) cb_priv;
+
+	memcpy(orig_payload, payload, payload_len);
+}
+
 static int mlxsw_core_reg_access(struct mlxsw_core *mlxsw_core,
 				 const struct mlxsw_reg_info *reg,
 				 char *payload,
 				 enum mlxsw_core_reg_access_type type)
 {
-	u64 cur_tid;
+	LIST_HEAD(bulk_list);
 	int err;
 
-	if (mutex_lock_interruptible(&mlxsw_core->emad.lock)) {
-		dev_err(mlxsw_core->bus_info->dev, "Reg access interrupted (reg_id=%x(%s),type=%s)\n",
-			reg->id, mlxsw_reg_id_str(reg->id),
-			mlxsw_core_reg_access_type_str(type));
-		return -EINTR;
-	}
-
-	cur_tid = mlxsw_core->emad.tid;
-	dev_dbg(mlxsw_core->bus_info->dev, "Reg access (tid=%llx,reg_id=%x(%s),type=%s)\n",
-		cur_tid, reg->id, mlxsw_reg_id_str(reg->id),
-		mlxsw_core_reg_access_type_str(type));
-
 	/* During initialization EMAD interface is not available to us,
 	 * so we default to command interface. We switch to EMAD interface
 	 * after setting the appropriate traps.
 	 */
 	if (!mlxsw_core->emad.use_emad)
-		err = mlxsw_core_reg_access_cmd(mlxsw_core, reg,
-						payload, type);
-	else
-		err = mlxsw_core_reg_access_emad(mlxsw_core, reg,
+		return mlxsw_core_reg_access_cmd(mlxsw_core, reg,
 						 payload, type);
 
+	err = mlxsw_core_reg_access_emad(mlxsw_core, reg,
+					 payload, type, &bulk_list,
+					 mlxsw_core_reg_access_cb,
+					 (unsigned long) payload);
 	if (err)
-		dev_err(mlxsw_core->bus_info->dev, "Reg access failed (tid=%llx,reg_id=%x(%s),type=%s)\n",
-			cur_tid, reg->id, mlxsw_reg_id_str(reg->id),
-			mlxsw_core_reg_access_type_str(type));
-
-	mutex_unlock(&mlxsw_core->emad.lock);
-	return err;
+		return err;
+	return mlxsw_reg_trans_bulk_wait(&bulk_list);
 }
 
 int mlxsw_reg_query(struct mlxsw_core *mlxsw_core,
@@ -1358,6 +1644,46 @@ void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core,
 }
 EXPORT_SYMBOL(mlxsw_core_lag_mapping_clear);
 
+int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core,
+			 struct mlxsw_core_port *mlxsw_core_port, u8 local_port,
+			 struct net_device *dev, bool split, u32 split_group)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_core);
+	struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
+
+	if (split)
+		devlink_port_split_set(devlink_port, split_group);
+	devlink_port_type_eth_set(devlink_port, dev);
+	return devlink_port_register(devlink, devlink_port, local_port);
+}
+EXPORT_SYMBOL(mlxsw_core_port_init);
+
+void mlxsw_core_port_fini(struct mlxsw_core_port *mlxsw_core_port)
+{
+	struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
+
+	devlink_port_unregister(devlink_port);
+}
+EXPORT_SYMBOL(mlxsw_core_port_fini);
+
+static void mlxsw_core_buf_dump_dbg(struct mlxsw_core *mlxsw_core,
+				    const char *buf, size_t size)
+{
+	__be32 *m = (__be32 *) buf;
+	int i;
+	int count = size / sizeof(__be32);
+
+	for (i = count - 1; i >= 0; i--)
+		if (m[i])
+			break;
+	i++;
+	count = i ? i : 1;
+	for (i = 0; i < count; i += 4)
+		dev_dbg(mlxsw_core->bus_info->dev, "%04x - %08x %08x %08x %08x\n",
+			i * 4, be32_to_cpu(m[i]), be32_to_cpu(m[i + 1]),
+			be32_to_cpu(m[i + 2]), be32_to_cpu(m[i + 3]));
+}
+
 int mlxsw_cmd_exec(struct mlxsw_core *mlxsw_core, u16 opcode, u8 opcode_mod,
 		   u32 in_mod, bool out_mbox_direct,
 		   char *in_mbox, size_t in_mbox_size,
@@ -1400,17 +1726,35 @@ int mlxsw_cmd_exec(struct mlxsw_core *mlxsw_core, u16 opcode, u8 opcode_mod,
 }
 EXPORT_SYMBOL(mlxsw_cmd_exec);
 
+int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay)
+{
+	return queue_delayed_work(mlxsw_wq, dwork, delay);
+}
+EXPORT_SYMBOL(mlxsw_core_schedule_dw);
+
 static int __init mlxsw_core_module_init(void)
 {
-	mlxsw_core_dbg_root = debugfs_create_dir(mlxsw_core_driver_name, NULL);
-	if (!mlxsw_core_dbg_root)
+	int err;
+
+	mlxsw_wq = create_workqueue(mlxsw_core_driver_name);
+	if (!mlxsw_wq)
 		return -ENOMEM;
+	mlxsw_core_dbg_root = debugfs_create_dir(mlxsw_core_driver_name, NULL);
+	if (!mlxsw_core_dbg_root) {
+		err = -ENOMEM;
+		goto err_debugfs_create_dir;
+	}
 	return 0;
+
+err_debugfs_create_dir:
+	destroy_workqueue(mlxsw_wq);
+	return err;
 }
 
 static void __exit mlxsw_core_module_exit(void)
 {
 	debugfs_remove_recursive(mlxsw_core_dbg_root);
+	destroy_workqueue(mlxsw_wq);
 }
 
 module_init(mlxsw_core_module_init);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index c73d1c079..436bc49df 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -43,6 +43,8 @@
 #include <linux/gfp.h>
 #include <linux/types.h>
 #include <linux/skbuff.h>
+#include <linux/workqueue.h>
+#include <net/devlink.h>
 
 #include "trap.h"
 #include "reg.h"
@@ -61,6 +63,8 @@ struct mlxsw_driver;
 struct mlxsw_bus;
 struct mlxsw_bus_info;
 
+void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core);
+
 int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver);
 void mlxsw_core_driver_unregister(struct mlxsw_driver *mlxsw_driver);
 
@@ -74,10 +78,9 @@ struct mlxsw_tx_info {
 	bool is_emad;
 };
 
-bool mlxsw_core_skb_transmit_busy(void *driver_priv,
+bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core,
 				  const struct mlxsw_tx_info *tx_info);
-
-int mlxsw_core_skb_transmit(void *driver_priv, struct sk_buff *skb,
+int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 			    const struct mlxsw_tx_info *tx_info);
 
 struct mlxsw_rx_listener {
@@ -106,6 +109,19 @@ void mlxsw_core_event_listener_unregister(struct mlxsw_core *mlxsw_core,
 					  const struct mlxsw_event_listener *el,
 					  void *priv);
 
+typedef void mlxsw_reg_trans_cb_t(struct mlxsw_core *mlxsw_core, char *payload,
+				  size_t payload_len, unsigned long cb_priv);
+
+int mlxsw_reg_trans_query(struct mlxsw_core *mlxsw_core,
+			  const struct mlxsw_reg_info *reg, char *payload,
+			  struct list_head *bulk_list,
+			  mlxsw_reg_trans_cb_t *cb, unsigned long cb_priv);
+int mlxsw_reg_trans_write(struct mlxsw_core *mlxsw_core,
+			  const struct mlxsw_reg_info *reg, char *payload,
+			  struct list_head *bulk_list,
+			  mlxsw_reg_trans_cb_t *cb, unsigned long cb_priv);
+int mlxsw_reg_trans_bulk_wait(struct list_head *bulk_list);
+
 int mlxsw_reg_query(struct mlxsw_core *mlxsw_core,
 		    const struct mlxsw_reg_info *reg, char *payload);
 int mlxsw_reg_write(struct mlxsw_core *mlxsw_core,
@@ -131,6 +147,26 @@ u8 mlxsw_core_lag_mapping_get(struct mlxsw_core *mlxsw_core,
 void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core,
 				  u16 lag_id, u8 local_port);
 
+struct mlxsw_core_port {
+	struct devlink_port devlink_port;
+};
+
+static inline void *
+mlxsw_core_port_driver_priv(struct mlxsw_core_port *mlxsw_core_port)
+{
+	/* mlxsw_core_port is ensured to always be the first field in driver
+	 * port structure.
+	 */
+	return mlxsw_core_port;
+}
+
+int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core,
+			 struct mlxsw_core_port *mlxsw_core_port, u8 local_port,
+			 struct net_device *dev, bool split, u32 split_group);
+void mlxsw_core_port_fini(struct mlxsw_core_port *mlxsw_core_port);
+
+int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay);
+
 #define MLXSW_CONFIG_PROFILE_SWID_COUNT 8
 
 struct mlxsw_swid_config {
@@ -183,11 +219,43 @@ struct mlxsw_driver {
 	const char *kind;
 	struct module *owner;
 	size_t priv_size;
-	int (*init)(void *driver_priv, struct mlxsw_core *mlxsw_core,
+	int (*init)(struct mlxsw_core *mlxsw_core,
 		    const struct mlxsw_bus_info *mlxsw_bus_info);
-	void (*fini)(void *driver_priv);
-	int (*port_split)(void *driver_priv, u8 local_port, unsigned int count);
-	int (*port_unsplit)(void *driver_priv, u8 local_port);
+	void (*fini)(struct mlxsw_core *mlxsw_core);
+	int (*port_split)(struct mlxsw_core *mlxsw_core, u8 local_port,
+			  unsigned int count);
+	int (*port_unsplit)(struct mlxsw_core *mlxsw_core, u8 local_port);
+	int (*sb_pool_get)(struct mlxsw_core *mlxsw_core,
+			   unsigned int sb_index, u16 pool_index,
+			   struct devlink_sb_pool_info *pool_info);
+	int (*sb_pool_set)(struct mlxsw_core *mlxsw_core,
+			   unsigned int sb_index, u16 pool_index, u32 size,
+			   enum devlink_sb_threshold_type threshold_type);
+	int (*sb_port_pool_get)(struct mlxsw_core_port *mlxsw_core_port,
+				unsigned int sb_index, u16 pool_index,
+				u32 *p_threshold);
+	int (*sb_port_pool_set)(struct mlxsw_core_port *mlxsw_core_port,
+				unsigned int sb_index, u16 pool_index,
+				u32 threshold);
+	int (*sb_tc_pool_bind_get)(struct mlxsw_core_port *mlxsw_core_port,
+				   unsigned int sb_index, u16 tc_index,
+				   enum devlink_sb_pool_type pool_type,
+				   u16 *p_pool_index, u32 *p_threshold);
+	int (*sb_tc_pool_bind_set)(struct mlxsw_core_port *mlxsw_core_port,
+				   unsigned int sb_index, u16 tc_index,
+				   enum devlink_sb_pool_type pool_type,
+				   u16 pool_index, u32 threshold);
+	int (*sb_occ_snapshot)(struct mlxsw_core *mlxsw_core,
+			       unsigned int sb_index);
+	int (*sb_occ_max_clear)(struct mlxsw_core *mlxsw_core,
+				unsigned int sb_index);
+	int (*sb_occ_port_pool_get)(struct mlxsw_core_port *mlxsw_core_port,
+				    unsigned int sb_index, u16 pool_index,
+				    u32 *p_cur, u32 *p_max);
+	int (*sb_occ_tc_port_bind_get)(struct mlxsw_core_port *mlxsw_core_port,
+				       unsigned int sb_index, u16 tc_index,
+				       enum devlink_sb_pool_type pool_type,
+				       u32 *p_cur, u32 *p_max);
 	void (*txhdr_construct)(struct sk_buff *skb,
 				const struct mlxsw_tx_info *tx_info);
 	u8 txhdr_len;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index ffe4c0305..57d48da70 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -1805,6 +1805,184 @@ static inline void mlxsw_reg_spvmlr_pack(char *payload, u8 local_port,
 	}
 }
 
+/* QTCT - QoS Switch Traffic Class Table
+ * -------------------------------------
+ * Configures the mapping between the packet switch priority and the
+ * traffic class on the transmit port.
+ */
+#define MLXSW_REG_QTCT_ID 0x400A
+#define MLXSW_REG_QTCT_LEN 0x08
+
+static const struct mlxsw_reg_info mlxsw_reg_qtct = {
+	.id = MLXSW_REG_QTCT_ID,
+	.len = MLXSW_REG_QTCT_LEN,
+};
+
+/* reg_qtct_local_port
+ * Local port number.
+ * Access: Index
+ *
+ * Note: CPU port is not supported.
+ */
+MLXSW_ITEM32(reg, qtct, local_port, 0x00, 16, 8);
+
+/* reg_qtct_sub_port
+ * Virtual port within the physical port.
+ * Should be set to 0 when virtual ports are not enabled on the port.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qtct, sub_port, 0x00, 8, 8);
+
+/* reg_qtct_switch_prio
+ * Switch priority.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qtct, switch_prio, 0x00, 0, 4);
+
+/* reg_qtct_tclass
+ * Traffic class.
+ * Default values:
+ * switch_prio 0 : tclass 1
+ * switch_prio 1 : tclass 0
+ * switch_prio i : tclass i, for i > 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qtct, tclass, 0x04, 0, 4);
+
+static inline void mlxsw_reg_qtct_pack(char *payload, u8 local_port,
+				       u8 switch_prio, u8 tclass)
+{
+	MLXSW_REG_ZERO(qtct, payload);
+	mlxsw_reg_qtct_local_port_set(payload, local_port);
+	mlxsw_reg_qtct_switch_prio_set(payload, switch_prio);
+	mlxsw_reg_qtct_tclass_set(payload, tclass);
+}
+
+/* QEEC - QoS ETS Element Configuration Register
+ * ---------------------------------------------
+ * Configures the ETS elements.
+ */
+#define MLXSW_REG_QEEC_ID 0x400D
+#define MLXSW_REG_QEEC_LEN 0x1C
+
+static const struct mlxsw_reg_info mlxsw_reg_qeec = {
+	.id = MLXSW_REG_QEEC_ID,
+	.len = MLXSW_REG_QEEC_LEN,
+};
+
+/* reg_qeec_local_port
+ * Local port number.
+ * Access: Index
+ *
+ * Note: CPU port is supported.
+ */
+MLXSW_ITEM32(reg, qeec, local_port, 0x00, 16, 8);
+
+enum mlxsw_reg_qeec_hr {
+	MLXSW_REG_QEEC_HIERARCY_PORT,
+	MLXSW_REG_QEEC_HIERARCY_GROUP,
+	MLXSW_REG_QEEC_HIERARCY_SUBGROUP,
+	MLXSW_REG_QEEC_HIERARCY_TC,
+};
+
+/* reg_qeec_element_hierarchy
+ * 0 - Port
+ * 1 - Group
+ * 2 - Subgroup
+ * 3 - Traffic Class
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qeec, element_hierarchy, 0x04, 16, 4);
+
+/* reg_qeec_element_index
+ * The index of the element in the hierarchy.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qeec, element_index, 0x04, 0, 8);
+
+/* reg_qeec_next_element_index
+ * The index of the next (lower) element in the hierarchy.
+ * Access: RW
+ *
+ * Note: Reserved for element_hierarchy 0.
+ */
+MLXSW_ITEM32(reg, qeec, next_element_index, 0x08, 0, 8);
+
+enum {
+	MLXSW_REG_QEEC_BYTES_MODE,
+	MLXSW_REG_QEEC_PACKETS_MODE,
+};
+
+/* reg_qeec_pb
+ * Packets or bytes mode.
+ * 0 - Bytes mode
+ * 1 - Packets mode
+ * Access: RW
+ *
+ * Note: Used for max shaper configuration. For Spectrum, packets mode
+ * is supported only for traffic classes of CPU port.
+ */
+MLXSW_ITEM32(reg, qeec, pb, 0x0C, 28, 1);
+
+/* reg_qeec_mase
+ * Max shaper configuration enable. Enables configuration of the max
+ * shaper on this ETS element.
+ * 0 - Disable
+ * 1 - Enable
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qeec, mase, 0x10, 31, 1);
+
+/* A large max rate will disable the max shaper. */
+#define MLXSW_REG_QEEC_MAS_DIS	200000000	/* Kbps */
+
+/* reg_qeec_max_shaper_rate
+ * Max shaper information rate.
+ * For CPU port, can only be configured for port hierarchy.
+ * When in bytes mode, value is specified in units of 1000bps.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qeec, max_shaper_rate, 0x10, 0, 28);
+
+/* reg_qeec_de
+ * DWRR configuration enable. Enables configuration of the dwrr and
+ * dwrr_weight.
+ * 0 - Disable
+ * 1 - Enable
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qeec, de, 0x18, 31, 1);
+
+/* reg_qeec_dwrr
+ * Transmission selection algorithm to use on the link going down from
+ * the ETS element.
+ * 0 - Strict priority
+ * 1 - DWRR
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qeec, dwrr, 0x18, 15, 1);
+
+/* reg_qeec_dwrr_weight
+ * DWRR weight on the link going down from the ETS element. The
+ * percentage of bandwidth guaranteed to an ETS element within
+ * its hierarchy. The sum of all weights across all ETS elements
+ * within one hierarchy should be equal to 100. Reserved when
+ * transmission selection algorithm is strict priority.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qeec, dwrr_weight, 0x18, 0, 8);
+
+static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port,
+				       enum mlxsw_reg_qeec_hr hr, u8 index,
+				       u8 next_index)
+{
+	MLXSW_REG_ZERO(qeec, payload);
+	mlxsw_reg_qeec_local_port_set(payload, local_port);
+	mlxsw_reg_qeec_element_hierarchy_set(payload, hr);
+	mlxsw_reg_qeec_element_index_set(payload, index);
+	mlxsw_reg_qeec_next_element_index_set(payload, next_index);
+}
+
 /* PMLP - Ports Module to Local Port Register
  * ------------------------------------------
  * Configures the assignment of modules to local ports.
@@ -2141,6 +2319,145 @@ static inline void mlxsw_reg_paos_pack(char *payload, u8 local_port,
 	mlxsw_reg_paos_e_set(payload, 1);
 }
 
+/* PFCC - Ports Flow Control Configuration Register
+ * ------------------------------------------------
+ * Configures and retrieves the per port flow control configuration.
+ */
+#define MLXSW_REG_PFCC_ID 0x5007
+#define MLXSW_REG_PFCC_LEN 0x20
+
+static const struct mlxsw_reg_info mlxsw_reg_pfcc = {
+	.id = MLXSW_REG_PFCC_ID,
+	.len = MLXSW_REG_PFCC_LEN,
+};
+
+/* reg_pfcc_local_port
+ * Local port number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pfcc, local_port, 0x00, 16, 8);
+
+/* reg_pfcc_pnat
+ * Port number access type. Determines the way local_port is interpreted:
+ * 0 - Local port number.
+ * 1 - IB / label port number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pfcc, pnat, 0x00, 14, 2);
+
+/* reg_pfcc_shl_cap
+ * Send to higher layers capabilities:
+ * 0 - No capability of sending Pause and PFC frames to higher layers.
+ * 1 - Device has capability of sending Pause and PFC frames to higher
+ *     layers.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, pfcc, shl_cap, 0x00, 1, 1);
+
+/* reg_pfcc_shl_opr
+ * Send to higher layers operation:
+ * 0 - Pause and PFC frames are handled by the port (default).
+ * 1 - Pause and PFC frames are handled by the port and also sent to
+ *     higher layers. Only valid if shl_cap = 1.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pfcc, shl_opr, 0x00, 0, 1);
+
+/* reg_pfcc_ppan
+ * Pause policy auto negotiation.
+ * 0 - Disabled. Generate / ignore Pause frames based on pptx / pprtx.
+ * 1 - Enabled. When auto-negotiation is performed, set the Pause policy
+ *     based on the auto-negotiation resolution.
+ * Access: RW
+ *
+ * Note: The auto-negotiation advertisement is set according to pptx and
+ * pprtx. When PFC is set on Tx / Rx, ppan must be set to 0.
+ */
+MLXSW_ITEM32(reg, pfcc, ppan, 0x04, 28, 4);
+
+/* reg_pfcc_prio_mask_tx
+ * Bit per priority indicating if Tx flow control policy should be
+ * updated based on bit pfctx.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, pfcc, prio_mask_tx, 0x04, 16, 8);
+
+/* reg_pfcc_prio_mask_rx
+ * Bit per priority indicating if Rx flow control policy should be
+ * updated based on bit pfcrx.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, pfcc, prio_mask_rx, 0x04, 0, 8);
+
+/* reg_pfcc_pptx
+ * Admin Pause policy on Tx.
+ * 0 - Never generate Pause frames (default).
+ * 1 - Generate Pause frames according to Rx buffer threshold.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pfcc, pptx, 0x08, 31, 1);
+
+/* reg_pfcc_aptx
+ * Active (operational) Pause policy on Tx.
+ * 0 - Never generate Pause frames.
+ * 1 - Generate Pause frames according to Rx buffer threshold.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, pfcc, aptx, 0x08, 30, 1);
+
+/* reg_pfcc_pfctx
+ * Priority based flow control policy on Tx[7:0]. Per-priority bit mask:
+ * 0 - Never generate priority Pause frames on the specified priority
+ *     (default).
+ * 1 - Generate priority Pause frames according to Rx buffer threshold on
+ *     the specified priority.
+ * Access: RW
+ *
+ * Note: pfctx and pptx must be mutually exclusive.
+ */
+MLXSW_ITEM32(reg, pfcc, pfctx, 0x08, 16, 8);
+
+/* reg_pfcc_pprx
+ * Admin Pause policy on Rx.
+ * 0 - Ignore received Pause frames (default).
+ * 1 - Respect received Pause frames.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pfcc, pprx, 0x0C, 31, 1);
+
+/* reg_pfcc_aprx
+ * Active (operational) Pause policy on Rx.
+ * 0 - Ignore received Pause frames.
+ * 1 - Respect received Pause frames.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, pfcc, aprx, 0x0C, 30, 1);
+
+/* reg_pfcc_pfcrx
+ * Priority based flow control policy on Rx[7:0]. Per-priority bit mask:
+ * 0 - Ignore incoming priority Pause frames on the specified priority
+ *     (default).
+ * 1 - Respect incoming priority Pause frames on the specified priority.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pfcc, pfcrx, 0x0C, 16, 8);
+
+#define MLXSW_REG_PFCC_ALL_PRIO 0xFF
+
+static inline void mlxsw_reg_pfcc_prio_pack(char *payload, u8 pfc_en)
+{
+	mlxsw_reg_pfcc_prio_mask_tx_set(payload, MLXSW_REG_PFCC_ALL_PRIO);
+	mlxsw_reg_pfcc_prio_mask_rx_set(payload, MLXSW_REG_PFCC_ALL_PRIO);
+	mlxsw_reg_pfcc_pfctx_set(payload, pfc_en);
+	mlxsw_reg_pfcc_pfcrx_set(payload, pfc_en);
+}
+
+static inline void mlxsw_reg_pfcc_pack(char *payload, u8 local_port)
+{
+	MLXSW_REG_ZERO(pfcc, payload);
+	mlxsw_reg_pfcc_local_port_set(payload, local_port);
+}
+
 /* PPCNT - Ports Performance Counters Register
  * -------------------------------------------
  * The PPCNT register retrieves per port performance counters.
@@ -2180,6 +2497,11 @@ MLXSW_ITEM32(reg, ppcnt, local_port, 0x00, 16, 8);
  */
 MLXSW_ITEM32(reg, ppcnt, pnat, 0x00, 14, 2);
 
+enum mlxsw_reg_ppcnt_grp {
+	MLXSW_REG_PPCNT_IEEE_8023_CNT = 0x0,
+	MLXSW_REG_PPCNT_PRIO_CNT = 0x10,
+};
+
 /* reg_ppcnt_grp
  * Performance counter group.
  * Group 63 indicates all groups. Only valid on Set() operation with
@@ -2215,6 +2537,8 @@ MLXSW_ITEM32(reg, ppcnt, clr, 0x04, 31, 1);
  */
 MLXSW_ITEM32(reg, ppcnt, prio_tc, 0x04, 0, 5);
 
+/* Ethernet IEEE 802.3 Counter Group */
+
 /* reg_ppcnt_a_frames_transmitted_ok
  * Access: RO
  */
@@ -2329,15 +2653,160 @@ MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_received,
 MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_transmitted,
 	     0x08 + 0x90, 0, 64);
 
-static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port)
+/* Ethernet Per Priority Group Counters */
+
+/* reg_ppcnt_rx_octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, rx_octets, 0x08 + 0x00, 0, 64);
+
+/* reg_ppcnt_rx_frames
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, rx_frames, 0x08 + 0x20, 0, 64);
+
+/* reg_ppcnt_tx_octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, tx_octets, 0x08 + 0x28, 0, 64);
+
+/* reg_ppcnt_tx_frames
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, tx_frames, 0x08 + 0x48, 0, 64);
+
+/* reg_ppcnt_rx_pause
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, rx_pause, 0x08 + 0x50, 0, 64);
+
+/* reg_ppcnt_rx_pause_duration
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, rx_pause_duration, 0x08 + 0x58, 0, 64);
+
+/* reg_ppcnt_tx_pause
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, tx_pause, 0x08 + 0x60, 0, 64);
+
+/* reg_ppcnt_tx_pause_duration
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, tx_pause_duration, 0x08 + 0x68, 0, 64);
+
+/* reg_ppcnt_rx_pause_transition
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, tx_pause_transition, 0x08 + 0x70, 0, 64);
+
+static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port,
+					enum mlxsw_reg_ppcnt_grp grp,
+					u8 prio_tc)
 {
 	MLXSW_REG_ZERO(ppcnt, payload);
 	mlxsw_reg_ppcnt_swid_set(payload, 0);
 	mlxsw_reg_ppcnt_local_port_set(payload, local_port);
 	mlxsw_reg_ppcnt_pnat_set(payload, 0);
-	mlxsw_reg_ppcnt_grp_set(payload, 0);
+	mlxsw_reg_ppcnt_grp_set(payload, grp);
 	mlxsw_reg_ppcnt_clr_set(payload, 0);
-	mlxsw_reg_ppcnt_prio_tc_set(payload, 0);
+	mlxsw_reg_ppcnt_prio_tc_set(payload, prio_tc);
+}
+
+/* PPTB - Port Prio To Buffer Register
+ * -----------------------------------
+ * Configures the switch priority to buffer table.
+ */
+#define MLXSW_REG_PPTB_ID 0x500B
+#define MLXSW_REG_PPTB_LEN 0x10
+
+static const struct mlxsw_reg_info mlxsw_reg_pptb = {
+	.id = MLXSW_REG_PPTB_ID,
+	.len = MLXSW_REG_PPTB_LEN,
+};
+
+enum {
+	MLXSW_REG_PPTB_MM_UM,
+	MLXSW_REG_PPTB_MM_UNICAST,
+	MLXSW_REG_PPTB_MM_MULTICAST,
+};
+
+/* reg_pptb_mm
+ * Mapping mode.
+ * 0 - Map both unicast and multicast packets to the same buffer.
+ * 1 - Map only unicast packets.
+ * 2 - Map only multicast packets.
+ * Access: Index
+ *
+ * Note: SwitchX-2 only supports the first option.
+ */
+MLXSW_ITEM32(reg, pptb, mm, 0x00, 28, 2);
+
+/* reg_pptb_local_port
+ * Local port number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pptb, local_port, 0x00, 16, 8);
+
+/* reg_pptb_um
+ * Enables the update of the untagged_buf field.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pptb, um, 0x00, 8, 1);
+
+/* reg_pptb_pm
+ * Enables the update of the prio_to_buff field.
+ * Bit <i> is a flag for updating the mapping for switch priority <i>.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pptb, pm, 0x00, 0, 8);
+
+/* reg_pptb_prio_to_buff
+ * Mapping of switch priority <i> to one of the allocated receive port
+ * buffers.
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, pptb, prio_to_buff, 0x04, 0x04, 4);
+
+/* reg_pptb_pm_msb
+ * Enables the update of the prio_to_buff field.
+ * Bit <i> is a flag for updating the mapping for switch priority <i+8>.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pptb, pm_msb, 0x08, 24, 8);
+
+/* reg_pptb_untagged_buff
+ * Mapping of untagged frames to one of the allocated receive port buffers.
+ * Access: RW
+ *
+ * Note: In SwitchX-2 this field must be mapped to buffer 8. Reserved for
+ * Spectrum, as it maps untagged packets based on the default switch priority.
+ */
+MLXSW_ITEM32(reg, pptb, untagged_buff, 0x08, 0, 4);
+
+/* reg_pptb_prio_to_buff_msb
+ * Mapping of switch priority <i+8> to one of the allocated receive port
+ * buffers.
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, pptb, prio_to_buff_msb, 0x0C, 0x04, 4);
+
+#define MLXSW_REG_PPTB_ALL_PRIO 0xFF
+
+static inline void mlxsw_reg_pptb_pack(char *payload, u8 local_port)
+{
+	MLXSW_REG_ZERO(pptb, payload);
+	mlxsw_reg_pptb_mm_set(payload, MLXSW_REG_PPTB_MM_UM);
+	mlxsw_reg_pptb_local_port_set(payload, local_port);
+	mlxsw_reg_pptb_pm_set(payload, MLXSW_REG_PPTB_ALL_PRIO);
+	mlxsw_reg_pptb_pm_msb_set(payload, MLXSW_REG_PPTB_ALL_PRIO);
+}
+
+static inline void mlxsw_reg_pptb_prio_to_buff_pack(char *payload, u8 prio,
+						    u8 buff)
+{
+	mlxsw_reg_pptb_prio_to_buff_set(payload, prio, buff);
+	mlxsw_reg_pptb_prio_to_buff_msb_set(payload, prio, buff);
 }
 
 /* PBMC - Port Buffer Management Control Register
@@ -2346,7 +2815,7 @@ static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port)
  * allocation for different Prios, and the Pause threshold management.
  */
 #define MLXSW_REG_PBMC_ID 0x500C
-#define MLXSW_REG_PBMC_LEN 0x68
+#define MLXSW_REG_PBMC_LEN 0x6C
 
 static const struct mlxsw_reg_info mlxsw_reg_pbmc = {
 	.id = MLXSW_REG_PBMC_ID,
@@ -2374,6 +2843,8 @@ MLXSW_ITEM32(reg, pbmc, xoff_timer_value, 0x04, 16, 16);
  */
 MLXSW_ITEM32(reg, pbmc, xoff_refresh, 0x04, 0, 16);
 
+#define MLXSW_REG_PBMC_PORT_SHARED_BUF_IDX 11
+
 /* reg_pbmc_buf_lossy
  * The field indicates if the buffer is lossy.
  * 0 - Lossless
@@ -2398,6 +2869,30 @@ MLXSW_ITEM32_INDEXED(reg, pbmc, buf_epsb, 0x0C, 24, 1, 0x08, 0x00, false);
  */
 MLXSW_ITEM32_INDEXED(reg, pbmc, buf_size, 0x0C, 0, 16, 0x08, 0x00, false);
 
+/* reg_pbmc_buf_xoff_threshold
+ * Once the amount of data in the buffer goes above this value, device
+ * starts sending PFC frames for all priorities associated with the
+ * buffer. Units are represented in cells. Reserved in case of lossy
+ * buffer.
+ * Access: RW
+ *
+ * Note: In Spectrum, reserved for buffer[9].
+ */
+MLXSW_ITEM32_INDEXED(reg, pbmc, buf_xoff_threshold, 0x0C, 16, 16,
+		     0x08, 0x04, false);
+
+/* reg_pbmc_buf_xon_threshold
+ * When the amount of data in the buffer goes below this value, device
+ * stops sending PFC frames for the priorities associated with the
+ * buffer. Units are represented in cells. Reserved in case of lossy
+ * buffer.
+ * Access: RW
+ *
+ * Note: In Spectrum, reserved for buffer[9].
+ */
+MLXSW_ITEM32_INDEXED(reg, pbmc, buf_xon_threshold, 0x0C, 0, 16,
+		     0x08, 0x04, false);
+
 static inline void mlxsw_reg_pbmc_pack(char *payload, u8 local_port,
 				       u16 xoff_timer_value, u16 xoff_refresh)
 {
@@ -2416,6 +2911,17 @@ static inline void mlxsw_reg_pbmc_lossy_buffer_pack(char *payload,
 	mlxsw_reg_pbmc_buf_size_set(payload, buf_index, size);
 }
 
+static inline void mlxsw_reg_pbmc_lossless_buffer_pack(char *payload,
+						       int buf_index, u16 size,
+						       u16 threshold)
+{
+	mlxsw_reg_pbmc_buf_lossy_set(payload, buf_index, 0);
+	mlxsw_reg_pbmc_buf_epsb_set(payload, buf_index, 0);
+	mlxsw_reg_pbmc_buf_size_set(payload, buf_index, size);
+	mlxsw_reg_pbmc_buf_xoff_threshold_set(payload, buf_index, threshold);
+	mlxsw_reg_pbmc_buf_xon_threshold_set(payload, buf_index, threshold);
+}
+
 /* PSPA - Port Switch Partition Allocation
  * ---------------------------------------
  * Controls the association of a port with a switch partition and enables
@@ -2985,9 +3491,10 @@ static const struct mlxsw_reg_info mlxsw_reg_sbpr = {
 	.len = MLXSW_REG_SBPR_LEN,
 };
 
-enum mlxsw_reg_sbpr_dir {
-	MLXSW_REG_SBPR_DIR_INGRESS,
-	MLXSW_REG_SBPR_DIR_EGRESS,
+/* shared direstion enum for SBPR, SBCM, SBPM */
+enum mlxsw_reg_sbxx_dir {
+	MLXSW_REG_SBXX_DIR_INGRESS,
+	MLXSW_REG_SBXX_DIR_EGRESS,
 };
 
 /* reg_sbpr_dir
@@ -3020,7 +3527,7 @@ enum mlxsw_reg_sbpr_mode {
 MLXSW_ITEM32(reg, sbpr, mode, 0x08, 0, 4);
 
 static inline void mlxsw_reg_sbpr_pack(char *payload, u8 pool,
-				       enum mlxsw_reg_sbpr_dir dir,
+				       enum mlxsw_reg_sbxx_dir dir,
 				       enum mlxsw_reg_sbpr_mode mode, u32 size)
 {
 	MLXSW_REG_ZERO(sbpr, payload);
@@ -3062,11 +3569,6 @@ MLXSW_ITEM32(reg, sbcm, local_port, 0x00, 16, 8);
  */
 MLXSW_ITEM32(reg, sbcm, pg_buff, 0x00, 8, 6);
 
-enum mlxsw_reg_sbcm_dir {
-	MLXSW_REG_SBCM_DIR_INGRESS,
-	MLXSW_REG_SBCM_DIR_EGRESS,
-};
-
 /* reg_sbcm_dir
  * Direction.
  * Access: Index
@@ -3079,6 +3581,10 @@ MLXSW_ITEM32(reg, sbcm, dir, 0x00, 0, 2);
  */
 MLXSW_ITEM32(reg, sbcm, min_buff, 0x18, 0, 24);
 
+/* shared max_buff limits for dynamic threshold for SBCM, SBPM */
+#define MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN 1
+#define MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX 14
+
 /* reg_sbcm_max_buff
  * When the pool associated to the port-pg/tclass is configured to
  * static, Maximum buffer size for the limiter configured in cells.
@@ -3099,7 +3605,7 @@ MLXSW_ITEM32(reg, sbcm, max_buff, 0x1C, 0, 24);
 MLXSW_ITEM32(reg, sbcm, pool, 0x24, 0, 4);
 
 static inline void mlxsw_reg_sbcm_pack(char *payload, u8 local_port, u8 pg_buff,
-				       enum mlxsw_reg_sbcm_dir dir,
+				       enum mlxsw_reg_sbxx_dir dir,
 				       u32 min_buff, u32 max_buff, u8 pool)
 {
 	MLXSW_REG_ZERO(sbcm, payload);
@@ -3111,8 +3617,8 @@ static inline void mlxsw_reg_sbcm_pack(char *payload, u8 local_port, u8 pg_buff,
 	mlxsw_reg_sbcm_pool_set(payload, pool);
 }
 
-/* SBPM - Shared Buffer Class Management Register
- * ----------------------------------------------
+/* SBPM - Shared Buffer Port Management Register
+ * ---------------------------------------------
  * The SBPM register configures and retrieves the shared buffer allocation
  * and configuration according to Port-Pool, including the definition
  * of the associated quota.
@@ -3139,17 +3645,33 @@ MLXSW_ITEM32(reg, sbpm, local_port, 0x00, 16, 8);
  */
 MLXSW_ITEM32(reg, sbpm, pool, 0x00, 8, 4);
 
-enum mlxsw_reg_sbpm_dir {
-	MLXSW_REG_SBPM_DIR_INGRESS,
-	MLXSW_REG_SBPM_DIR_EGRESS,
-};
-
 /* reg_sbpm_dir
  * Direction.
  * Access: Index
  */
 MLXSW_ITEM32(reg, sbpm, dir, 0x00, 0, 2);
 
+/* reg_sbpm_buff_occupancy
+ * Current buffer occupancy in cells.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, sbpm, buff_occupancy, 0x10, 0, 24);
+
+/* reg_sbpm_clr
+ * Clear Max Buffer Occupancy
+ * When this bit is set, max_buff_occupancy field is cleared (and a
+ * new max value is tracked from the time the clear was performed).
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, sbpm, clr, 0x14, 31, 1);
+
+/* reg_sbpm_max_buff_occupancy
+ * Maximum value of buffer occupancy in cells monitored. Cleared by
+ * writing to the clr field.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, sbpm, max_buff_occupancy, 0x14, 0, 24);
+
 /* reg_sbpm_min_buff
  * Minimum buffer size for the limiter, in cells.
  * Access: RW
@@ -3170,17 +3692,25 @@ MLXSW_ITEM32(reg, sbpm, min_buff, 0x18, 0, 24);
 MLXSW_ITEM32(reg, sbpm, max_buff, 0x1C, 0, 24);
 
 static inline void mlxsw_reg_sbpm_pack(char *payload, u8 local_port, u8 pool,
-				       enum mlxsw_reg_sbpm_dir dir,
+				       enum mlxsw_reg_sbxx_dir dir, bool clr,
 				       u32 min_buff, u32 max_buff)
 {
 	MLXSW_REG_ZERO(sbpm, payload);
 	mlxsw_reg_sbpm_local_port_set(payload, local_port);
 	mlxsw_reg_sbpm_pool_set(payload, pool);
 	mlxsw_reg_sbpm_dir_set(payload, dir);
+	mlxsw_reg_sbpm_clr_set(payload, clr);
 	mlxsw_reg_sbpm_min_buff_set(payload, min_buff);
 	mlxsw_reg_sbpm_max_buff_set(payload, max_buff);
 }
 
+static inline void mlxsw_reg_sbpm_unpack(char *payload, u32 *p_buff_occupancy,
+					 u32 *p_max_buff_occupancy)
+{
+	*p_buff_occupancy = mlxsw_reg_sbpm_buff_occupancy_get(payload);
+	*p_max_buff_occupancy = mlxsw_reg_sbpm_max_buff_occupancy_get(payload);
+}
+
 /* SBMM - Shared Buffer Multicast Management Register
  * --------------------------------------------------
  * The SBMM register configures and retrieves the shared buffer allocation
@@ -3236,6 +3766,104 @@ static inline void mlxsw_reg_sbmm_pack(char *payload, u8 prio, u32 min_buff,
 	mlxsw_reg_sbmm_pool_set(payload, pool);
 }
 
+/* SBSR - Shared Buffer Status Register
+ * ------------------------------------
+ * The SBSR register retrieves the shared buffer occupancy according to
+ * Port-Pool. Note that this register enables reading a large amount of data.
+ * It is the user's responsibility to limit the amount of data to ensure the
+ * response can match the maximum transfer unit. In case the response exceeds
+ * the maximum transport unit, it will be truncated with no special notice.
+ */
+#define MLXSW_REG_SBSR_ID 0xB005
+#define MLXSW_REG_SBSR_BASE_LEN 0x5C /* base length, without records */
+#define MLXSW_REG_SBSR_REC_LEN 0x8 /* record length */
+#define MLXSW_REG_SBSR_REC_MAX_COUNT 120
+#define MLXSW_REG_SBSR_LEN (MLXSW_REG_SBSR_BASE_LEN +	\
+			    MLXSW_REG_SBSR_REC_LEN *	\
+			    MLXSW_REG_SBSR_REC_MAX_COUNT)
+
+static const struct mlxsw_reg_info mlxsw_reg_sbsr = {
+	.id = MLXSW_REG_SBSR_ID,
+	.len = MLXSW_REG_SBSR_LEN,
+};
+
+/* reg_sbsr_clr
+ * Clear Max Buffer Occupancy. When this bit is set, the max_buff_occupancy
+ * field is cleared (and a new max value is tracked from the time the clear
+ * was performed).
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, sbsr, clr, 0x00, 31, 1);
+
+/* reg_sbsr_ingress_port_mask
+ * Bit vector for all ingress network ports.
+ * Indicates which of the ports (for which the relevant bit is set)
+ * are affected by the set operation. Configuration of any other port
+ * does not change.
+ * Access: Index
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, sbsr, ingress_port_mask, 0x10, 0x20, 1);
+
+/* reg_sbsr_pg_buff_mask
+ * Bit vector for all switch priority groups.
+ * Indicates which of the priorities (for which the relevant bit is set)
+ * are affected by the set operation. Configuration of any other priority
+ * does not change.
+ * Range is 0..cap_max_pg_buffers - 1
+ * Access: Index
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, sbsr, pg_buff_mask, 0x30, 0x4, 1);
+
+/* reg_sbsr_egress_port_mask
+ * Bit vector for all egress network ports.
+ * Indicates which of the ports (for which the relevant bit is set)
+ * are affected by the set operation. Configuration of any other port
+ * does not change.
+ * Access: Index
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, sbsr, egress_port_mask, 0x34, 0x20, 1);
+
+/* reg_sbsr_tclass_mask
+ * Bit vector for all traffic classes.
+ * Indicates which of the traffic classes (for which the relevant bit is
+ * set) are affected by the set operation. Configuration of any other
+ * traffic class does not change.
+ * Range is 0..cap_max_tclass - 1
+ * Access: Index
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, sbsr, tclass_mask, 0x54, 0x8, 1);
+
+static inline void mlxsw_reg_sbsr_pack(char *payload, bool clr)
+{
+	MLXSW_REG_ZERO(sbsr, payload);
+	mlxsw_reg_sbsr_clr_set(payload, clr);
+}
+
+/* reg_sbsr_rec_buff_occupancy
+ * Current buffer occupancy in cells.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sbsr, rec_buff_occupancy, MLXSW_REG_SBSR_BASE_LEN,
+		     0, 24, MLXSW_REG_SBSR_REC_LEN, 0x00, false);
+
+/* reg_sbsr_rec_max_buff_occupancy
+ * Maximum value of buffer occupancy in cells monitored. Cleared by
+ * writing to the clr field.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sbsr, rec_max_buff_occupancy, MLXSW_REG_SBSR_BASE_LEN,
+		     0, 24, MLXSW_REG_SBSR_REC_LEN, 0x04, false);
+
+static inline void mlxsw_reg_sbsr_rec_unpack(char *payload, int rec_index,
+					     u32 *p_buff_occupancy,
+					     u32 *p_max_buff_occupancy)
+{
+	*p_buff_occupancy =
+		mlxsw_reg_sbsr_rec_buff_occupancy_get(payload, rec_index);
+	*p_max_buff_occupancy =
+		mlxsw_reg_sbsr_rec_max_buff_occupancy_get(payload, rec_index);
+}
+
 static inline const char *mlxsw_reg_id_str(u16 reg_id)
 {
 	switch (reg_id) {
@@ -3283,6 +3911,10 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id)
 		return "SFMR";
 	case MLXSW_REG_SPVMLR_ID:
 		return "SPVMLR";
+	case MLXSW_REG_QTCT_ID:
+		return "QTCT";
+	case MLXSW_REG_QEEC_ID:
+		return "QEEC";
 	case MLXSW_REG_PMLP_ID:
 		return "PMLP";
 	case MLXSW_REG_PMTU_ID:
@@ -3293,8 +3925,12 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id)
 		return "PPAD";
 	case MLXSW_REG_PAOS_ID:
 		return "PAOS";
+	case MLXSW_REG_PFCC_ID:
+		return "PFCC";
 	case MLXSW_REG_PPCNT_ID:
 		return "PPCNT";
+	case MLXSW_REG_PPTB_ID:
+		return "PPTB";
 	case MLXSW_REG_PBMC_ID:
 		return "PBMC";
 	case MLXSW_REG_PSPA_ID:
@@ -3323,6 +3959,8 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id)
 		return "SBPM";
 	case MLXSW_REG_SBMM_ID:
 		return "SBMM";
+	case MLXSW_REG_SBSR_ID:
+		return "SBSR";
 	default:
 		return "*UNKNOWN*";
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 668b2f465..374080027 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -49,7 +49,7 @@
 #include <linux/jiffies.h>
 #include <linux/bitops.h>
 #include <linux/list.h>
-#include <net/devlink.h>
+#include <linux/dcbnl.h>
 #include <net/switchdev.h>
 #include <generated/utsrelease.h>
 
@@ -171,23 +171,6 @@ static int mlxsw_sp_port_admin_status_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(paos), paos_pl);
 }
 
-static int mlxsw_sp_port_oper_status_get(struct mlxsw_sp_port *mlxsw_sp_port,
-					 bool *p_is_up)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char paos_pl[MLXSW_REG_PAOS_LEN];
-	u8 oper_status;
-	int err;
-
-	mlxsw_reg_paos_pack(paos_pl, mlxsw_sp_port->local_port, 0);
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(paos), paos_pl);
-	if (err)
-		return err;
-	oper_status = mlxsw_reg_paos_oper_status_get(paos_pl);
-	*p_is_up = oper_status == MLXSW_PORT_ADMIN_STATUS_UP ? true : false;
-	return 0;
-}
-
 static int mlxsw_sp_port_dev_addr_set(struct mlxsw_sp_port *mlxsw_sp_port,
 				      unsigned char *addr)
 {
@@ -247,15 +230,23 @@ static int mlxsw_sp_port_mtu_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl);
 }
 
-static int mlxsw_sp_port_swid_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 swid)
+static int __mlxsw_sp_port_swid_set(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				    u8 swid)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char pspa_pl[MLXSW_REG_PSPA_LEN];
 
-	mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sp_port->local_port);
+	mlxsw_reg_pspa_pack(pspa_pl, swid, local_port);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pspa), pspa_pl);
 }
 
+static int mlxsw_sp_port_swid_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 swid)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+
+	return __mlxsw_sp_port_swid_set(mlxsw_sp, mlxsw_sp_port->local_port,
+					swid);
+}
+
 static int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port,
 				     bool enable)
 {
@@ -307,7 +298,7 @@ mlxsw_sp_port_system_port_mapping_set(struct mlxsw_sp_port *mlxsw_sp_port)
 
 static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
 					 u8 local_port, u8 *p_module,
-					 u8 *p_width)
+					 u8 *p_width, u8 *p_lane)
 {
 	char pmlp_pl[MLXSW_REG_PMLP_LEN];
 	int err;
@@ -318,6 +309,7 @@ static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
 		return err;
 	*p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
 	*p_width = mlxsw_reg_pmlp_width_get(pmlp_pl);
+	*p_lane = mlxsw_reg_pmlp_tx_lane_get(pmlp_pl, 0);
 	return 0;
 }
 
@@ -379,7 +371,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	u64 len;
 	int err;
 
-	if (mlxsw_core_skb_transmit_busy(mlxsw_sp, &tx_info))
+	if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &tx_info))
 		return NETDEV_TX_BUSY;
 
 	if (unlikely(skb_headroom(skb) < MLXSW_TXHDR_LEN)) {
@@ -399,11 +391,15 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	}
 
 	mlxsw_sp_txhdr_construct(skb, &tx_info);
-	len = skb->len;
+	/* TX header is consumed by HW on the way so we shouldn't count its
+	 * bytes as being sent.
+	 */
+	len = skb->len - MLXSW_TXHDR_LEN;
+
 	/* Due to a race we might fail here because of a full queue. In that
 	 * unlikely case we simply drop the packet.
 	 */
-	err = mlxsw_core_skb_transmit(mlxsw_sp, skb, &tx_info);
+	err = mlxsw_core_skb_transmit(mlxsw_sp->core, skb, &tx_info);
 
 	if (!err) {
 		pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats);
@@ -438,16 +434,89 @@ static int mlxsw_sp_port_set_mac_address(struct net_device *dev, void *p)
 	return 0;
 }
 
+static void mlxsw_sp_pg_buf_pack(char *pbmc_pl, int pg_index, int mtu,
+				 bool pause_en, bool pfc_en, u16 delay)
+{
+	u16 pg_size = 2 * MLXSW_SP_BYTES_TO_CELLS(mtu);
+
+	delay = pfc_en ? mlxsw_sp_pfc_delay_get(mtu, delay) :
+			 MLXSW_SP_PAUSE_DELAY;
+
+	if (pause_en || pfc_en)
+		mlxsw_reg_pbmc_lossless_buffer_pack(pbmc_pl, pg_index,
+						    pg_size + delay, pg_size);
+	else
+		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, pg_index, pg_size);
+}
+
+int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
+				 u8 *prio_tc, bool pause_en,
+				 struct ieee_pfc *my_pfc)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 pfc_en = !!my_pfc ? my_pfc->pfc_en : 0;
+	u16 delay = !!my_pfc ? my_pfc->delay : 0;
+	char pbmc_pl[MLXSW_REG_PBMC_LEN];
+	int i, j, err;
+
+	mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port, 0, 0);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
+	if (err)
+		return err;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		bool configure = false;
+		bool pfc = false;
+
+		for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) {
+			if (prio_tc[j] == i) {
+				pfc = pfc_en & BIT(j);
+				configure = true;
+				break;
+			}
+		}
+
+		if (!configure)
+			continue;
+		mlxsw_sp_pg_buf_pack(pbmc_pl, i, mtu, pause_en, pfc, delay);
+	}
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
+}
+
+static int mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				      int mtu, bool pause_en)
+{
+	u8 def_prio_tc[IEEE_8021QAZ_MAX_TCS] = {0};
+	bool dcb_en = !!mlxsw_sp_port->dcb.ets;
+	struct ieee_pfc *my_pfc;
+	u8 *prio_tc;
+
+	prio_tc = dcb_en ? mlxsw_sp_port->dcb.ets->prio_tc : def_prio_tc;
+	my_pfc = dcb_en ? mlxsw_sp_port->dcb.pfc : NULL;
+
+	return __mlxsw_sp_port_headroom_set(mlxsw_sp_port, mtu, prio_tc,
+					    pause_en, my_pfc);
+}
+
 static int mlxsw_sp_port_change_mtu(struct net_device *dev, int mtu)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	bool pause_en = mlxsw_sp_port_is_pause_en(mlxsw_sp_port);
 	int err;
 
-	err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, mtu);
+	err = mlxsw_sp_port_headroom_set(mlxsw_sp_port, mtu, pause_en);
 	if (err)
 		return err;
+	err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, mtu);
+	if (err)
+		goto err_port_mtu_set;
 	dev->mtu = mtu;
 	return 0;
+
+err_port_mtu_set:
+	mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu, pause_en);
+	return err;
 }
 
 static struct rtnl_link_stats64 *
@@ -861,6 +930,27 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev,
 	return 0;
 }
 
+static int mlxsw_sp_port_get_phys_port_name(struct net_device *dev, char *name,
+					    size_t len)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	u8 module = mlxsw_sp_port->mapping.module;
+	u8 width = mlxsw_sp_port->mapping.width;
+	u8 lane = mlxsw_sp_port->mapping.lane;
+	int err;
+
+	if (!mlxsw_sp_port->split)
+		err = snprintf(name, len, "p%d", module + 1);
+	else
+		err = snprintf(name, len, "p%ds%d", module + 1,
+			       lane / width);
+
+	if (err >= len)
+		return -EINVAL;
+
+	return 0;
+}
+
 static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_open		= mlxsw_sp_port_open,
 	.ndo_stop		= mlxsw_sp_port_stop,
@@ -877,6 +967,7 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_bridge_setlink	= switchdev_port_bridge_setlink,
 	.ndo_bridge_getlink	= switchdev_port_bridge_getlink,
 	.ndo_bridge_dellink	= switchdev_port_bridge_dellink,
+	.ndo_get_phys_port_name	= mlxsw_sp_port_get_phys_port_name,
 };
 
 static void mlxsw_sp_port_get_drvinfo(struct net_device *dev,
@@ -897,6 +988,68 @@ static void mlxsw_sp_port_get_drvinfo(struct net_device *dev,
 		sizeof(drvinfo->bus_info));
 }
 
+static void mlxsw_sp_port_get_pauseparam(struct net_device *dev,
+					 struct ethtool_pauseparam *pause)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+
+	pause->rx_pause = mlxsw_sp_port->link.rx_pause;
+	pause->tx_pause = mlxsw_sp_port->link.tx_pause;
+}
+
+static int mlxsw_sp_port_pause_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct ethtool_pauseparam *pause)
+{
+	char pfcc_pl[MLXSW_REG_PFCC_LEN];
+
+	mlxsw_reg_pfcc_pack(pfcc_pl, mlxsw_sp_port->local_port);
+	mlxsw_reg_pfcc_pprx_set(pfcc_pl, pause->rx_pause);
+	mlxsw_reg_pfcc_pptx_set(pfcc_pl, pause->tx_pause);
+
+	return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pfcc),
+			       pfcc_pl);
+}
+
+static int mlxsw_sp_port_set_pauseparam(struct net_device *dev,
+					struct ethtool_pauseparam *pause)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	bool pause_en = pause->tx_pause || pause->rx_pause;
+	int err;
+
+	if (mlxsw_sp_port->dcb.pfc && mlxsw_sp_port->dcb.pfc->pfc_en) {
+		netdev_err(dev, "PFC already enabled on port\n");
+		return -EINVAL;
+	}
+
+	if (pause->autoneg) {
+		netdev_err(dev, "PAUSE frames autonegotiation isn't supported\n");
+		return -EINVAL;
+	}
+
+	err = mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu, pause_en);
+	if (err) {
+		netdev_err(dev, "Failed to configure port's headroom\n");
+		return err;
+	}
+
+	err = mlxsw_sp_port_pause_set(mlxsw_sp_port, pause);
+	if (err) {
+		netdev_err(dev, "Failed to set PAUSE parameters\n");
+		goto err_port_pause_configure;
+	}
+
+	mlxsw_sp_port->link.rx_pause = pause->rx_pause;
+	mlxsw_sp_port->link.tx_pause = pause->tx_pause;
+
+	return 0;
+
+err_port_pause_configure:
+	pause_en = mlxsw_sp_port_is_pause_en(mlxsw_sp_port);
+	mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu, pause_en);
+	return err;
+}
+
 struct mlxsw_sp_port_hw_stats {
 	char str[ETH_GSTRING_LEN];
 	u64 (*getter)(char *payload);
@@ -1032,7 +1185,8 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev,
 	int i;
 	int err;
 
-	mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sp_port->local_port);
+	mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sp_port->local_port,
+			     MLXSW_REG_PPCNT_IEEE_8023_CNT, 0);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ppcnt), ppcnt_pl);
 	for (i = 0; i < MLXSW_SP_PORT_HW_STATS_LEN; i++)
 		data[i] = !err ? mlxsw_sp_port_hw_stats[i].getter(ppcnt_pl) : 0;
@@ -1263,7 +1417,8 @@ static int mlxsw_sp_port_get_settings(struct net_device *dev,
 
 	cmd->supported = mlxsw_sp_from_ptys_supported_port(eth_proto_cap) |
 			 mlxsw_sp_from_ptys_supported_link(eth_proto_cap) |
-			 SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+			 SUPPORTED_Pause | SUPPORTED_Asym_Pause |
+			 SUPPORTED_Autoneg;
 	cmd->advertising = mlxsw_sp_from_ptys_advert_link(eth_proto_admin);
 	mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev),
 					eth_proto_oper, cmd);
@@ -1322,7 +1477,6 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev,
 	u32 eth_proto_new;
 	u32 eth_proto_cap;
 	u32 eth_proto_admin;
-	bool is_up;
 	int err;
 
 	speed = ethtool_cmd_speed(cmd);
@@ -1354,12 +1508,7 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev,
 		return err;
 	}
 
-	err = mlxsw_sp_port_oper_status_get(mlxsw_sp_port, &is_up);
-	if (err) {
-		netdev_err(dev, "Failed to get oper status");
-		return err;
-	}
-	if (!is_up)
+	if (!netif_running(dev))
 		return 0;
 
 	err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
@@ -1380,6 +1529,8 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev,
 static const struct ethtool_ops mlxsw_sp_port_ethtool_ops = {
 	.get_drvinfo		= mlxsw_sp_port_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
+	.get_pauseparam		= mlxsw_sp_port_get_pauseparam,
+	.set_pauseparam		= mlxsw_sp_port_set_pauseparam,
 	.get_strings		= mlxsw_sp_port_get_strings,
 	.set_phys_id		= mlxsw_sp_port_set_phys_id,
 	.get_ethtool_stats	= mlxsw_sp_port_get_stats,
@@ -1402,12 +1553,112 @@ mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 width)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
 }
 
-static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
-				  bool split, u8 module, u8 width)
+int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
+			  enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
+			  bool dwrr, u8 dwrr_weight)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qeec_pl[MLXSW_REG_QEEC_LEN];
+
+	mlxsw_reg_qeec_pack(qeec_pl, mlxsw_sp_port->local_port, hr, index,
+			    next_index);
+	mlxsw_reg_qeec_de_set(qeec_pl, true);
+	mlxsw_reg_qeec_dwrr_set(qeec_pl, dwrr);
+	mlxsw_reg_qeec_dwrr_weight_set(qeec_pl, dwrr_weight);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qeec), qeec_pl);
+}
+
+int mlxsw_sp_port_ets_maxrate_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				  enum mlxsw_reg_qeec_hr hr, u8 index,
+				  u8 next_index, u32 maxrate)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qeec_pl[MLXSW_REG_QEEC_LEN];
+
+	mlxsw_reg_qeec_pack(qeec_pl, mlxsw_sp_port->local_port, hr, index,
+			    next_index);
+	mlxsw_reg_qeec_mase_set(qeec_pl, true);
+	mlxsw_reg_qeec_max_shaper_rate_set(qeec_pl, maxrate);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qeec), qeec_pl);
+}
+
+int mlxsw_sp_port_prio_tc_set(struct mlxsw_sp_port *mlxsw_sp_port,
+			      u8 switch_prio, u8 tclass)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qtct_pl[MLXSW_REG_QTCT_LEN];
+
+	mlxsw_reg_qtct_pack(qtct_pl, mlxsw_sp_port->local_port, switch_prio,
+			    tclass);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qtct), qtct_pl);
+}
+
+static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	int err, i;
+
+	/* Setup the elements hierarcy, so that each TC is linked to
+	 * one subgroup, which are all member in the same group.
+	 */
+	err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
+				    MLXSW_REG_QEEC_HIERARCY_GROUP, 0, 0, false,
+				    0);
+	if (err)
+		return err;
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
+					    MLXSW_REG_QEEC_HIERARCY_SUBGROUP, i,
+					    0, false, 0);
+		if (err)
+			return err;
+	}
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
+					    MLXSW_REG_QEEC_HIERARCY_TC, i, i,
+					    false, 0);
+		if (err)
+			return err;
+	}
+
+	/* Make sure the max shaper is disabled in all hierarcies that
+	 * support it.
+	 */
+	err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
+					    MLXSW_REG_QEEC_HIERARCY_PORT, 0, 0,
+					    MLXSW_REG_QEEC_MAS_DIS);
+	if (err)
+		return err;
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
+						    MLXSW_REG_QEEC_HIERARCY_SUBGROUP,
+						    i, 0,
+						    MLXSW_REG_QEEC_MAS_DIS);
+		if (err)
+			return err;
+	}
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
+						    MLXSW_REG_QEEC_HIERARCY_TC,
+						    i, i,
+						    MLXSW_REG_QEEC_MAS_DIS);
+		if (err)
+			return err;
+	}
+
+	/* Map all priorities to traffic class 0. */
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		err = mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, i, 0);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				bool split, u8 module, u8 width, u8 lane)
 {
-	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
-	struct devlink_port *devlink_port;
 	struct net_device *dev;
 	size_t bytes;
 	int err;
@@ -1420,6 +1671,9 @@ static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	mlxsw_sp_port->mlxsw_sp = mlxsw_sp;
 	mlxsw_sp_port->local_port = local_port;
 	mlxsw_sp_port->split = split;
+	mlxsw_sp_port->mapping.module = module;
+	mlxsw_sp_port->mapping.width = width;
+	mlxsw_sp_port->mapping.lane = lane;
 	bytes = DIV_ROUND_UP(VLAN_N_VID, BITS_PER_BYTE);
 	mlxsw_sp_port->active_vlans = kzalloc(bytes, GFP_KERNEL);
 	if (!mlxsw_sp_port->active_vlans) {
@@ -1460,16 +1714,6 @@ static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	 */
 	dev->hard_header_len += MLXSW_TXHDR_LEN;
 
-	devlink_port = &mlxsw_sp_port->devlink_port;
-	if (mlxsw_sp_port->split)
-		devlink_port_split_set(devlink_port, module);
-	err = devlink_port_register(devlink, devlink_port, local_port);
-	if (err) {
-		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to register devlink port\n",
-			mlxsw_sp_port->local_port);
-		goto err_devlink_port_register;
-	}
-
 	err = mlxsw_sp_port_system_port_mapping_set(mlxsw_sp_port);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set system port mapping\n",
@@ -1509,6 +1753,21 @@ static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_port_buffers_init;
 	}
 
+	err = mlxsw_sp_port_ets_init(mlxsw_sp_port);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to initialize ETS\n",
+			mlxsw_sp_port->local_port);
+		goto err_port_ets_init;
+	}
+
+	/* ETS and buffers must be initialized before DCB. */
+	err = mlxsw_sp_port_dcb_init(mlxsw_sp_port);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to initialize DCB\n",
+			mlxsw_sp_port->local_port);
+		goto err_port_dcb_init;
+	}
+
 	mlxsw_sp_port_switchdev_init(mlxsw_sp_port);
 	err = register_netdev(dev);
 	if (err) {
@@ -1517,7 +1776,14 @@ static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_register_netdev;
 	}
 
-	devlink_port_type_eth_set(devlink_port, dev);
+	err = mlxsw_core_port_init(mlxsw_sp->core, &mlxsw_sp_port->core_port,
+				   mlxsw_sp_port->local_port, dev,
+				   mlxsw_sp_port->split, module);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to init core port\n",
+			mlxsw_sp_port->local_port);
+		goto err_core_port_init;
+	}
 
 	err = mlxsw_sp_port_vlan_init(mlxsw_sp_port);
 	if (err)
@@ -1527,16 +1793,18 @@ static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	return 0;
 
 err_port_vlan_init:
+	mlxsw_core_port_fini(&mlxsw_sp_port->core_port);
+err_core_port_init:
 	unregister_netdev(dev);
 err_register_netdev:
+err_port_dcb_init:
+err_port_ets_init:
 err_port_buffers_init:
 err_port_admin_status_set:
 err_port_mtu_set:
 err_port_speed_by_width_set:
 err_port_swid_set:
 err_port_system_port_mapping_set:
-	devlink_port_unregister(&mlxsw_sp_port->devlink_port);
-err_devlink_port_register:
 err_dev_addr_init:
 	free_percpu(mlxsw_sp_port->pcpu_stats);
 err_alloc_stats:
@@ -1548,28 +1816,6 @@ err_port_active_vlans_alloc:
 	return err;
 }
 
-static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
-				bool split, u8 module, u8 width, u8 lane)
-{
-	int err;
-
-	err = mlxsw_sp_port_module_map(mlxsw_sp, local_port, module, width,
-				       lane);
-	if (err)
-		return err;
-
-	err = __mlxsw_sp_port_create(mlxsw_sp, local_port, split, module,
-				     width);
-	if (err)
-		goto err_port_create;
-
-	return 0;
-
-err_port_create:
-	mlxsw_sp_port_module_unmap(mlxsw_sp, local_port);
-	return err;
-}
-
 static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 {
 	struct net_device *dev = mlxsw_sp_port->dev;
@@ -1590,15 +1836,13 @@ static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
-	struct devlink_port *devlink_port;
 
 	if (!mlxsw_sp_port)
 		return;
 	mlxsw_sp->ports[local_port] = NULL;
-	devlink_port = &mlxsw_sp_port->devlink_port;
-	devlink_port_type_clear(devlink_port);
+	mlxsw_core_port_fini(&mlxsw_sp_port->core_port);
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
-	devlink_port_unregister(devlink_port);
+	mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
 	mlxsw_sp_port_vports_fini(mlxsw_sp_port);
 	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
 	mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
@@ -1620,8 +1864,8 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp)
 
 static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
 {
+	u8 module, width, lane;
 	size_t alloc_size;
-	u8 module, width;
 	int i;
 	int err;
 
@@ -1632,13 +1876,14 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
 
 	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
 		err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &module,
-						    &width);
+						    &width, &lane);
 		if (err)
 			goto err_port_module_info_get;
 		if (!width)
 			continue;
 		mlxsw_sp->port_to_module[i] = module;
-		err = __mlxsw_sp_port_create(mlxsw_sp, i, false, module, width);
+		err = mlxsw_sp_port_create(mlxsw_sp, i, false, module, width,
+					   lane);
 		if (err)
 			goto err_port_create;
 	}
@@ -1659,11 +1904,85 @@ static u8 mlxsw_sp_cluster_base_port_get(u8 local_port)
 	return local_port - offset;
 }
 
-static int mlxsw_sp_port_split(void *priv, u8 local_port, unsigned int count)
+static int mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port,
+				      u8 module, unsigned int count)
 {
-	struct mlxsw_sp *mlxsw_sp = priv;
-	struct mlxsw_sp_port *mlxsw_sp_port;
 	u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count;
+	int err, i;
+
+	for (i = 0; i < count; i++) {
+		err = mlxsw_sp_port_module_map(mlxsw_sp, base_port + i, module,
+					       width, i * width);
+		if (err)
+			goto err_port_module_map;
+	}
+
+	for (i = 0; i < count; i++) {
+		err = __mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i, 0);
+		if (err)
+			goto err_port_swid_set;
+	}
+
+	for (i = 0; i < count; i++) {
+		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true,
+					   module, width, i * width);
+		if (err)
+			goto err_port_create;
+	}
+
+	return 0;
+
+err_port_create:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+	i = count;
+err_port_swid_set:
+	for (i--; i >= 0; i--)
+		__mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i,
+					 MLXSW_PORT_SWID_DISABLED_PORT);
+	i = count;
+err_port_module_map:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_port_module_unmap(mlxsw_sp, base_port + i);
+	return err;
+}
+
+static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp,
+					 u8 base_port, unsigned int count)
+{
+	u8 local_port, module, width = MLXSW_PORT_MODULE_MAX_WIDTH;
+	int i;
+
+	/* Split by four means we need to re-create two ports, otherwise
+	 * only one.
+	 */
+	count = count / 2;
+
+	for (i = 0; i < count; i++) {
+		local_port = base_port + i * 2;
+		module = mlxsw_sp->port_to_module[local_port];
+
+		mlxsw_sp_port_module_map(mlxsw_sp, local_port, module, width,
+					 0);
+	}
+
+	for (i = 0; i < count; i++)
+		__mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i * 2, 0);
+
+	for (i = 0; i < count; i++) {
+		local_port = base_port + i * 2;
+		module = mlxsw_sp->port_to_module[local_port];
+
+		mlxsw_sp_port_create(mlxsw_sp, local_port, false, module,
+				     width, 0);
+	}
+}
+
+static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
+			       unsigned int count)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	struct mlxsw_sp_port *mlxsw_sp_port;
 	u8 module, cur_width, base_port;
 	int i;
 	int err;
@@ -1675,18 +1994,14 @@ static int mlxsw_sp_port_split(void *priv, u8 local_port, unsigned int count)
 		return -EINVAL;
 	}
 
+	module = mlxsw_sp_port->mapping.module;
+	cur_width = mlxsw_sp_port->mapping.width;
+
 	if (count != 2 && count != 4) {
 		netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n");
 		return -EINVAL;
 	}
 
-	err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module,
-					    &cur_width);
-	if (err) {
-		netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n");
-		return err;
-	}
-
 	if (cur_width != MLXSW_PORT_MODULE_MAX_WIDTH) {
 		netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n");
 		return -EINVAL;
@@ -1711,36 +2026,26 @@ static int mlxsw_sp_port_split(void *priv, u8 local_port, unsigned int count)
 	for (i = 0; i < count; i++)
 		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
 
-	for (i = 0; i < count; i++) {
-		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true,
-					   module, width, i * width);
-		if (err) {
-			dev_err(mlxsw_sp->bus_info->dev, "Failed to create split port\n");
-			goto err_port_create;
-		}
+	err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, module, count);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to create split ports\n");
+		goto err_port_split_create;
 	}
 
 	return 0;
 
-err_port_create:
-	for (i--; i >= 0; i--)
-		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
-	for (i = 0; i < count / 2; i++) {
-		module = mlxsw_sp->port_to_module[base_port + i * 2];
-		mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false,
-				     module, MLXSW_PORT_MODULE_MAX_WIDTH, 0);
-	}
+err_port_split_create:
+	mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count);
 	return err;
 }
 
-static int mlxsw_sp_port_unsplit(void *priv, u8 local_port)
+static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
 {
-	struct mlxsw_sp *mlxsw_sp = priv;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
-	u8 module, cur_width, base_port;
+	u8 cur_width, base_port;
 	unsigned int count;
 	int i;
-	int err;
 
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port) {
@@ -1754,12 +2059,7 @@ static int mlxsw_sp_port_unsplit(void *priv, u8 local_port)
 		return -EINVAL;
 	}
 
-	err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module,
-					    &cur_width);
-	if (err) {
-		netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n");
-		return err;
-	}
+	cur_width = mlxsw_sp_port->mapping.width;
 	count = cur_width == 1 ? 4 : 2;
 
 	base_port = mlxsw_sp_cluster_base_port_get(local_port);
@@ -1771,14 +2071,7 @@ static int mlxsw_sp_port_unsplit(void *priv, u8 local_port)
 	for (i = 0; i < count; i++)
 		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
 
-	for (i = 0; i < count / 2; i++) {
-		module = mlxsw_sp->port_to_module[base_port + i * 2];
-		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false,
-					   module, MLXSW_PORT_MODULE_MAX_WIDTH,
-					   0);
-		if (err)
-			dev_err(mlxsw_sp->bus_info->dev, "Failed to reinstantiate port\n");
-	}
+	mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count);
 
 	return 0;
 }
@@ -2080,10 +2373,10 @@ static int mlxsw_sp_lag_init(struct mlxsw_sp *mlxsw_sp)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(slcr), slcr_pl);
 }
 
-static int mlxsw_sp_init(void *priv, struct mlxsw_core *mlxsw_core,
+static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 			 const struct mlxsw_bus_info *mlxsw_bus_info)
 {
-	struct mlxsw_sp *mlxsw_sp = priv;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	int err;
 
 	mlxsw_sp->core = mlxsw_core;
@@ -2144,6 +2437,7 @@ static int mlxsw_sp_init(void *priv, struct mlxsw_core *mlxsw_core,
 
 err_switchdev_init:
 err_lag_init:
+	mlxsw_sp_buffers_fini(mlxsw_sp);
 err_buffers_init:
 err_flood_init:
 	mlxsw_sp_traps_fini(mlxsw_sp);
@@ -2154,11 +2448,12 @@ err_event_register:
 	return err;
 }
 
-static void mlxsw_sp_fini(void *priv)
+static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 {
-	struct mlxsw_sp *mlxsw_sp = priv;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 
 	mlxsw_sp_switchdev_fini(mlxsw_sp);
+	mlxsw_sp_buffers_fini(mlxsw_sp);
 	mlxsw_sp_traps_fini(mlxsw_sp);
 	mlxsw_sp_event_unregister(mlxsw_sp, MLXSW_TRAP_ID_PUDE);
 	mlxsw_sp_ports_remove(mlxsw_sp);
@@ -2201,16 +2496,26 @@ static struct mlxsw_config_profile mlxsw_sp_config_profile = {
 };
 
 static struct mlxsw_driver mlxsw_sp_driver = {
-	.kind			= MLXSW_DEVICE_KIND_SPECTRUM,
-	.owner			= THIS_MODULE,
-	.priv_size		= sizeof(struct mlxsw_sp),
-	.init			= mlxsw_sp_init,
-	.fini			= mlxsw_sp_fini,
-	.port_split		= mlxsw_sp_port_split,
-	.port_unsplit		= mlxsw_sp_port_unsplit,
-	.txhdr_construct	= mlxsw_sp_txhdr_construct,
-	.txhdr_len		= MLXSW_TXHDR_LEN,
-	.profile		= &mlxsw_sp_config_profile,
+	.kind				= MLXSW_DEVICE_KIND_SPECTRUM,
+	.owner				= THIS_MODULE,
+	.priv_size			= sizeof(struct mlxsw_sp),
+	.init				= mlxsw_sp_init,
+	.fini				= mlxsw_sp_fini,
+	.port_split			= mlxsw_sp_port_split,
+	.port_unsplit			= mlxsw_sp_port_unsplit,
+	.sb_pool_get			= mlxsw_sp_sb_pool_get,
+	.sb_pool_set			= mlxsw_sp_sb_pool_set,
+	.sb_port_pool_get		= mlxsw_sp_sb_port_pool_get,
+	.sb_port_pool_set		= mlxsw_sp_sb_port_pool_set,
+	.sb_tc_pool_bind_get		= mlxsw_sp_sb_tc_pool_bind_get,
+	.sb_tc_pool_bind_set		= mlxsw_sp_sb_tc_pool_bind_set,
+	.sb_occ_snapshot		= mlxsw_sp_sb_occ_snapshot,
+	.sb_occ_max_clear		= mlxsw_sp_sb_occ_max_clear,
+	.sb_occ_port_pool_get		= mlxsw_sp_sb_occ_port_pool_get,
+	.sb_occ_tc_port_bind_get	= mlxsw_sp_sb_occ_tc_port_bind_get,
+	.txhdr_construct		= mlxsw_sp_txhdr_construct,
+	.txhdr_len			= MLXSW_TXHDR_LEN,
+	.profile			= &mlxsw_sp_config_profile,
 };
 
 static int
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 4b8abaf06..13b30eaa1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -42,15 +42,15 @@
 #include <linux/bitops.h>
 #include <linux/if_vlan.h>
 #include <linux/list.h>
+#include <linux/dcbnl.h>
 #include <net/switchdev.h>
-#include <net/devlink.h>
 
 #include "port.h"
 #include "core.h"
 
 #define MLXSW_SP_VFID_BASE VLAN_N_VID
 #define MLXSW_SP_VFID_PORT_MAX 512	/* Non-bridged VLAN interfaces */
-#define MLXSW_SP_VFID_BR_MAX 8192	/* Bridged VLAN interfaces */
+#define MLXSW_SP_VFID_BR_MAX 6144	/* Bridged VLAN interfaces */
 #define MLXSW_SP_VFID_MAX (MLXSW_SP_VFID_PORT_MAX + MLXSW_SP_VFID_BR_MAX)
 
 #define MLXSW_SP_LAG_MAX 64
@@ -62,6 +62,24 @@
 
 #define MLXSW_SP_PORT_BASE_SPEED 25000	/* Mb/s */
 
+#define MLXSW_SP_BYTES_PER_CELL 96
+
+#define MLXSW_SP_BYTES_TO_CELLS(b) DIV_ROUND_UP(b, MLXSW_SP_BYTES_PER_CELL)
+#define MLXSW_SP_CELLS_TO_BYTES(c) (c * MLXSW_SP_BYTES_PER_CELL)
+
+/* Maximum delay buffer needed in case of PAUSE frames, in cells.
+ * Assumes 100m cable and maximum MTU.
+ */
+#define MLXSW_SP_PAUSE_DELAY 612
+
+#define MLXSW_SP_CELL_FACTOR 2	/* 2 * cell_size / (IPG + cell_size + 1) */
+
+static inline u16 mlxsw_sp_pfc_delay_get(int mtu, u16 delay)
+{
+	delay = MLXSW_SP_BYTES_TO_CELLS(DIV_ROUND_UP(delay, BITS_PER_BYTE));
+	return MLXSW_SP_CELL_FACTOR * delay + MLXSW_SP_BYTES_TO_CELLS(mtu);
+}
+
 struct mlxsw_sp_port;
 
 struct mlxsw_sp_upper {
@@ -100,6 +118,40 @@ static inline bool mlxsw_sp_fid_is_vfid(u16 fid)
 	return fid >= MLXSW_SP_VFID_BASE;
 }
 
+struct mlxsw_sp_sb_pr {
+	enum mlxsw_reg_sbpr_mode mode;
+	u32 size;
+};
+
+struct mlxsw_cp_sb_occ {
+	u32 cur;
+	u32 max;
+};
+
+struct mlxsw_sp_sb_cm {
+	u32 min_buff;
+	u32 max_buff;
+	u8 pool;
+	struct mlxsw_cp_sb_occ occ;
+};
+
+struct mlxsw_sp_sb_pm {
+	u32 min_buff;
+	u32 max_buff;
+	struct mlxsw_cp_sb_occ occ;
+};
+
+#define MLXSW_SP_SB_POOL_COUNT	4
+#define MLXSW_SP_SB_TC_COUNT	8
+
+struct mlxsw_sp_sb {
+	struct mlxsw_sp_sb_pr prs[2][MLXSW_SP_SB_POOL_COUNT];
+	struct {
+		struct mlxsw_sp_sb_cm cms[2][MLXSW_SP_SB_TC_COUNT];
+		struct mlxsw_sp_sb_pm pms[2][MLXSW_SP_SB_POOL_COUNT];
+	} ports[MLXSW_PORT_MAX_PORTS];
+};
+
 struct mlxsw_sp {
 	struct {
 		struct list_head list;
@@ -130,6 +182,7 @@ struct mlxsw_sp {
 	struct mlxsw_sp_upper master_bridge;
 	struct mlxsw_sp_upper lags[MLXSW_SP_LAG_MAX];
 	u8 port_to_module[MLXSW_PORT_MAX_PORTS];
+	struct mlxsw_sp_sb sb;
 };
 
 static inline struct mlxsw_sp_upper *
@@ -148,6 +201,7 @@ struct mlxsw_sp_port_pcpu_stats {
 };
 
 struct mlxsw_sp_port {
+	struct mlxsw_core_port core_port; /* must be first */
 	struct net_device *dev;
 	struct mlxsw_sp_port_pcpu_stats __percpu *pcpu_stats;
 	struct mlxsw_sp *mlxsw_sp;
@@ -166,14 +220,33 @@ struct mlxsw_sp_port {
 		struct mlxsw_sp_vfid *vfid;
 		u16 vid;
 	} vport;
+	struct {
+		u8 tx_pause:1,
+		   rx_pause:1;
+	} link;
+	struct {
+		struct ieee_ets *ets;
+		struct ieee_maxrate *maxrate;
+		struct ieee_pfc *pfc;
+	} dcb;
+	struct {
+		u8 module;
+		u8 width;
+		u8 lane;
+	} mapping;
 	/* 802.1Q bridge VLANs */
 	unsigned long *active_vlans;
 	unsigned long *untagged_vlans;
 	/* VLAN interfaces */
 	struct list_head vports_list;
-	struct devlink_port devlink_port;
 };
 
+static inline bool
+mlxsw_sp_port_is_pause_en(const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	return mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause;
+}
+
 static inline struct mlxsw_sp_port *
 mlxsw_sp_port_lagged_get(struct mlxsw_sp *mlxsw_sp, u16 lag_id, u8 port_index)
 {
@@ -245,7 +318,39 @@ enum mlxsw_sp_flood_table {
 };
 
 int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_buffers_fini(struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_port_buffers_init(struct mlxsw_sp_port *mlxsw_sp_port);
+int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core,
+			 unsigned int sb_index, u16 pool_index,
+			 struct devlink_sb_pool_info *pool_info);
+int mlxsw_sp_sb_pool_set(struct mlxsw_core *mlxsw_core,
+			 unsigned int sb_index, u16 pool_index, u32 size,
+			 enum devlink_sb_threshold_type threshold_type);
+int mlxsw_sp_sb_port_pool_get(struct mlxsw_core_port *mlxsw_core_port,
+			      unsigned int sb_index, u16 pool_index,
+			      u32 *p_threshold);
+int mlxsw_sp_sb_port_pool_set(struct mlxsw_core_port *mlxsw_core_port,
+			      unsigned int sb_index, u16 pool_index,
+			      u32 threshold);
+int mlxsw_sp_sb_tc_pool_bind_get(struct mlxsw_core_port *mlxsw_core_port,
+				 unsigned int sb_index, u16 tc_index,
+				 enum devlink_sb_pool_type pool_type,
+				 u16 *p_pool_index, u32 *p_threshold);
+int mlxsw_sp_sb_tc_pool_bind_set(struct mlxsw_core_port *mlxsw_core_port,
+				 unsigned int sb_index, u16 tc_index,
+				 enum devlink_sb_pool_type pool_type,
+				 u16 pool_index, u32 threshold);
+int mlxsw_sp_sb_occ_snapshot(struct mlxsw_core *mlxsw_core,
+			     unsigned int sb_index);
+int mlxsw_sp_sb_occ_max_clear(struct mlxsw_core *mlxsw_core,
+			      unsigned int sb_index);
+int mlxsw_sp_sb_occ_port_pool_get(struct mlxsw_core_port *mlxsw_core_port,
+				  unsigned int sb_index, u16 pool_index,
+				  u32 *p_cur, u32 *p_max);
+int mlxsw_sp_sb_occ_tc_port_bind_get(struct mlxsw_core_port *mlxsw_core_port,
+				     unsigned int sb_index, u16 tc_index,
+				     enum devlink_sb_pool_type pool_type,
+				     u32 *p_cur, u32 *p_max);
 
 int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp);
@@ -265,5 +370,33 @@ int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid,
 			     bool set, bool only_uc);
 void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port);
 int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
+int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
+			  enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
+			  bool dwrr, u8 dwrr_weight);
+int mlxsw_sp_port_prio_tc_set(struct mlxsw_sp_port *mlxsw_sp_port,
+			      u8 switch_prio, u8 tclass);
+int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
+				 u8 *prio_tc, bool pause_en,
+				 struct ieee_pfc *my_pfc);
+int mlxsw_sp_port_ets_maxrate_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				  enum mlxsw_reg_qeec_hr hr, u8 index,
+				  u8 next_index, u32 maxrate);
+
+#ifdef CONFIG_MLXSW_SPECTRUM_DCB
+
+int mlxsw_sp_port_dcb_init(struct mlxsw_sp_port *mlxsw_sp_port);
+void mlxsw_sp_port_dcb_fini(struct mlxsw_sp_port *mlxsw_sp_port);
+
+#else
+
+static inline int mlxsw_sp_port_dcb_init(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	return 0;
+}
+
+static inline void mlxsw_sp_port_dcb_fini(struct mlxsw_sp_port *mlxsw_sp_port)
+{}
+
+#endif
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index d59195e3f..074cdda7b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -34,36 +34,140 @@
 
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/dcbnl.h>
+#include <linux/if_ether.h>
+#include <linux/list.h>
 
 #include "spectrum.h"
 #include "core.h"
 #include "port.h"
 #include "reg.h"
 
-struct mlxsw_sp_pb {
-	u8 index;
-	u16 size;
-};
+static struct mlxsw_sp_sb_pr *mlxsw_sp_sb_pr_get(struct mlxsw_sp *mlxsw_sp,
+						 u8 pool,
+						 enum mlxsw_reg_sbxx_dir dir)
+{
+	return &mlxsw_sp->sb.prs[dir][pool];
+}
 
-#define MLXSW_SP_PB(_index, _size)	\
-	{				\
-		.index = _index,	\
-		.size = _size,		\
+static struct mlxsw_sp_sb_cm *mlxsw_sp_sb_cm_get(struct mlxsw_sp *mlxsw_sp,
+						 u8 local_port, u8 pg_buff,
+						 enum mlxsw_reg_sbxx_dir dir)
+{
+	return &mlxsw_sp->sb.ports[local_port].cms[dir][pg_buff];
+}
+
+static struct mlxsw_sp_sb_pm *mlxsw_sp_sb_pm_get(struct mlxsw_sp *mlxsw_sp,
+						 u8 local_port, u8 pool,
+						 enum mlxsw_reg_sbxx_dir dir)
+{
+	return &mlxsw_sp->sb.ports[local_port].pms[dir][pool];
+}
+
+static int mlxsw_sp_sb_pr_write(struct mlxsw_sp *mlxsw_sp, u8 pool,
+				enum mlxsw_reg_sbxx_dir dir,
+				enum mlxsw_reg_sbpr_mode mode, u32 size)
+{
+	char sbpr_pl[MLXSW_REG_SBPR_LEN];
+	struct mlxsw_sp_sb_pr *pr;
+	int err;
+
+	mlxsw_reg_sbpr_pack(sbpr_pl, pool, dir, mode, size);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbpr), sbpr_pl);
+	if (err)
+		return err;
+
+	pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir);
+	pr->mode = mode;
+	pr->size = size;
+	return 0;
+}
+
+static int mlxsw_sp_sb_cm_write(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				u8 pg_buff, enum mlxsw_reg_sbxx_dir dir,
+				u32 min_buff, u32 max_buff, u8 pool)
+{
+	char sbcm_pl[MLXSW_REG_SBCM_LEN];
+	int err;
+
+	mlxsw_reg_sbcm_pack(sbcm_pl, local_port, pg_buff, dir,
+			    min_buff, max_buff, pool);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbcm), sbcm_pl);
+	if (err)
+		return err;
+	if (pg_buff < MLXSW_SP_SB_TC_COUNT) {
+		struct mlxsw_sp_sb_cm *cm;
+
+		cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port, pg_buff, dir);
+		cm->min_buff = min_buff;
+		cm->max_buff = max_buff;
+		cm->pool = pool;
 	}
+	return 0;
+}
+
+static int mlxsw_sp_sb_pm_write(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				u8 pool, enum mlxsw_reg_sbxx_dir dir,
+				u32 min_buff, u32 max_buff)
+{
+	char sbpm_pl[MLXSW_REG_SBPM_LEN];
+	struct mlxsw_sp_sb_pm *pm;
+	int err;
+
+	mlxsw_reg_sbpm_pack(sbpm_pl, local_port, pool, dir, false,
+			    min_buff, max_buff);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbpm), sbpm_pl);
+	if (err)
+		return err;
+
+	pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port, pool, dir);
+	pm->min_buff = min_buff;
+	pm->max_buff = max_buff;
+	return 0;
+}
+
+static int mlxsw_sp_sb_pm_occ_clear(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				    u8 pool, enum mlxsw_reg_sbxx_dir dir,
+				    struct list_head *bulk_list)
+{
+	char sbpm_pl[MLXSW_REG_SBPM_LEN];
+
+	mlxsw_reg_sbpm_pack(sbpm_pl, local_port, pool, dir, true, 0, 0);
+	return mlxsw_reg_trans_query(mlxsw_sp->core, MLXSW_REG(sbpm), sbpm_pl,
+				     bulk_list, NULL, 0);
+}
+
+static void mlxsw_sp_sb_pm_occ_query_cb(struct mlxsw_core *mlxsw_core,
+					char *sbpm_pl, size_t sbpm_pl_len,
+					unsigned long cb_priv)
+{
+	struct mlxsw_sp_sb_pm *pm = (struct mlxsw_sp_sb_pm *) cb_priv;
+
+	mlxsw_reg_sbpm_unpack(sbpm_pl, &pm->occ.cur, &pm->occ.max);
+}
+
+static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				    u8 pool, enum mlxsw_reg_sbxx_dir dir,
+				    struct list_head *bulk_list)
+{
+	char sbpm_pl[MLXSW_REG_SBPM_LEN];
+	struct mlxsw_sp_sb_pm *pm;
+
+	pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port, pool, dir);
+	mlxsw_reg_sbpm_pack(sbpm_pl, local_port, pool, dir, false, 0, 0);
+	return mlxsw_reg_trans_query(mlxsw_sp->core, MLXSW_REG(sbpm), sbpm_pl,
+				     bulk_list,
+				     mlxsw_sp_sb_pm_occ_query_cb,
+				     (unsigned long) pm);
+}
 
-static const struct mlxsw_sp_pb mlxsw_sp_pbs[] = {
-	MLXSW_SP_PB(0, 208),
-	MLXSW_SP_PB(1, 208),
-	MLXSW_SP_PB(2, 208),
-	MLXSW_SP_PB(3, 208),
-	MLXSW_SP_PB(4, 208),
-	MLXSW_SP_PB(5, 208),
-	MLXSW_SP_PB(6, 208),
-	MLXSW_SP_PB(7, 208),
-	MLXSW_SP_PB(9, 208),
+static const u16 mlxsw_sp_pbs[] = {
+	[0] = 2 * MLXSW_SP_BYTES_TO_CELLS(ETH_FRAME_LEN),
+	[9] = 2 * MLXSW_SP_BYTES_TO_CELLS(MLXSW_PORT_MAX_MTU),
 };
 
 #define MLXSW_SP_PBS_LEN ARRAY_SIZE(mlxsw_sp_pbs)
+#define MLXSW_SP_PB_UNUSED 8
 
 static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
@@ -73,194 +177,206 @@ static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port,
 			    0xffff, 0xffff / 2);
 	for (i = 0; i < MLXSW_SP_PBS_LEN; i++) {
-		const struct mlxsw_sp_pb *pb;
-
-		pb = &mlxsw_sp_pbs[i];
-		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, pb->index, pb->size);
+		if (i == MLXSW_SP_PB_UNUSED)
+			continue;
+		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, mlxsw_sp_pbs[i]);
 	}
+	mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl,
+					 MLXSW_REG_PBMC_PORT_SHARED_BUF_IDX, 0);
 	return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core,
 			       MLXSW_REG(pbmc), pbmc_pl);
 }
 
-#define MLXSW_SP_SB_BYTES_PER_CELL 96
+static int mlxsw_sp_port_pb_prio_init(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	char pptb_pl[MLXSW_REG_PPTB_LEN];
+	int i;
 
-struct mlxsw_sp_sb_pool {
-	u8 pool;
-	enum mlxsw_reg_sbpr_dir dir;
-	enum mlxsw_reg_sbpr_mode mode;
-	u32 size;
-};
+	mlxsw_reg_pptb_pack(pptb_pl, mlxsw_sp_port->local_port);
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		mlxsw_reg_pptb_prio_to_buff_pack(pptb_pl, i, 0);
+	return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pptb),
+			       pptb_pl);
+}
+
+static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	int err;
+
+	err = mlxsw_sp_port_pb_init(mlxsw_sp_port);
+	if (err)
+		return err;
+	return mlxsw_sp_port_pb_prio_init(mlxsw_sp_port);
+}
 
-#define MLXSW_SP_SB_POOL_INGRESS_SIZE				\
-	((15000000 - (2 * 20000 * MLXSW_PORT_MAX_PORTS)) /	\
-	 MLXSW_SP_SB_BYTES_PER_CELL)
-#define MLXSW_SP_SB_POOL_EGRESS_SIZE				\
-	((14000000 - (8 * 1500 * MLXSW_PORT_MAX_PORTS)) /	\
-	 MLXSW_SP_SB_BYTES_PER_CELL)
-
-#define MLXSW_SP_SB_POOL(_pool, _dir, _mode, _size)		\
-	{							\
-		.pool = _pool,					\
-		.dir = _dir,					\
-		.mode = _mode,					\
-		.size = _size,					\
+#define MLXSW_SP_SB_PR_INGRESS_SIZE				\
+	(15000000 - (2 * 20000 * MLXSW_PORT_MAX_PORTS))
+#define MLXSW_SP_SB_PR_INGRESS_MNG_SIZE (200 * 1000)
+#define MLXSW_SP_SB_PR_EGRESS_SIZE				\
+	(14000000 - (8 * 1500 * MLXSW_PORT_MAX_PORTS))
+
+#define MLXSW_SP_SB_PR(_mode, _size)	\
+	{				\
+		.mode = _mode,		\
+		.size = _size,		\
 	}
 
-#define MLXSW_SP_SB_POOL_INGRESS(_pool, _size)			\
-	MLXSW_SP_SB_POOL(_pool, MLXSW_REG_SBPR_DIR_INGRESS,	\
-			 MLXSW_REG_SBPR_MODE_DYNAMIC, _size)
-
-#define MLXSW_SP_SB_POOL_EGRESS(_pool, _size)			\
-	MLXSW_SP_SB_POOL(_pool, MLXSW_REG_SBPR_DIR_EGRESS,	\
-			 MLXSW_REG_SBPR_MODE_DYNAMIC, _size)
-
-static const struct mlxsw_sp_sb_pool mlxsw_sp_sb_pools[] = {
-	MLXSW_SP_SB_POOL_INGRESS(0, MLXSW_SP_SB_POOL_INGRESS_SIZE),
-	MLXSW_SP_SB_POOL_INGRESS(1, 0),
-	MLXSW_SP_SB_POOL_INGRESS(2, 0),
-	MLXSW_SP_SB_POOL_INGRESS(3, 0),
-	MLXSW_SP_SB_POOL_EGRESS(0, MLXSW_SP_SB_POOL_EGRESS_SIZE),
-	MLXSW_SP_SB_POOL_EGRESS(1, 0),
-	MLXSW_SP_SB_POOL_EGRESS(2, 0),
-	MLXSW_SP_SB_POOL_EGRESS(2, MLXSW_SP_SB_POOL_EGRESS_SIZE),
+static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs_ingress[] = {
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
+		       MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_INGRESS_SIZE)),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
+		       MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_INGRESS_MNG_SIZE)),
 };
 
-#define MLXSW_SP_SB_POOLS_LEN ARRAY_SIZE(mlxsw_sp_sb_pools)
+#define MLXSW_SP_SB_PRS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs_ingress)
+
+static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs_egress[] = {
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
+		       MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_EGRESS_SIZE)),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
+};
 
-static int mlxsw_sp_sb_pools_init(struct mlxsw_sp *mlxsw_sp)
+#define MLXSW_SP_SB_PRS_EGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs_egress)
+
+static int __mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
+				  enum mlxsw_reg_sbxx_dir dir,
+				  const struct mlxsw_sp_sb_pr *prs,
+				  size_t prs_len)
 {
-	char sbpr_pl[MLXSW_REG_SBPR_LEN];
 	int i;
 	int err;
 
-	for (i = 0; i < MLXSW_SP_SB_POOLS_LEN; i++) {
-		const struct mlxsw_sp_sb_pool *pool;
+	for (i = 0; i < prs_len; i++) {
+		const struct mlxsw_sp_sb_pr *pr;
 
-		pool = &mlxsw_sp_sb_pools[i];
-		mlxsw_reg_sbpr_pack(sbpr_pl, pool->pool, pool->dir,
-				    pool->mode, pool->size);
-		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbpr), sbpr_pl);
+		pr = &prs[i];
+		err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, dir,
+					   pr->mode, pr->size);
 		if (err)
 			return err;
 	}
 	return 0;
 }
 
-struct mlxsw_sp_sb_cm {
-	union {
-		u8 pg;
-		u8 tc;
-	} u;
-	enum mlxsw_reg_sbcm_dir dir;
-	u32 min_buff;
-	u32 max_buff;
-	u8 pool;
-};
+static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp)
+{
+	int err;
 
-#define MLXSW_SP_SB_CM(_pg_tc, _dir, _min_buff, _max_buff, _pool)	\
-	{								\
-		.u.pg = _pg_tc,						\
-		.dir = _dir,						\
-		.min_buff = _min_buff,					\
-		.max_buff = _max_buff,					\
-		.pool = _pool,						\
+	err = __mlxsw_sp_sb_prs_init(mlxsw_sp, MLXSW_REG_SBXX_DIR_INGRESS,
+				     mlxsw_sp_sb_prs_ingress,
+				     MLXSW_SP_SB_PRS_INGRESS_LEN);
+	if (err)
+		return err;
+	return __mlxsw_sp_sb_prs_init(mlxsw_sp, MLXSW_REG_SBXX_DIR_EGRESS,
+				      mlxsw_sp_sb_prs_egress,
+				      MLXSW_SP_SB_PRS_EGRESS_LEN);
+}
+
+#define MLXSW_SP_SB_CM(_min_buff, _max_buff, _pool)	\
+	{						\
+		.min_buff = _min_buff,			\
+		.max_buff = _max_buff,			\
+		.pool = _pool,				\
 	}
 
-#define MLXSW_SP_SB_CM_INGRESS(_pg, _min_buff, _max_buff)		\
-	MLXSW_SP_SB_CM(_pg, MLXSW_REG_SBCM_DIR_INGRESS,			\
-		       _min_buff, _max_buff, 0)
-
-#define MLXSW_SP_SB_CM_EGRESS(_tc, _min_buff, _max_buff)		\
-	MLXSW_SP_SB_CM(_tc, MLXSW_REG_SBCM_DIR_EGRESS,			\
-		       _min_buff, _max_buff, 0)
-
-#define MLXSW_SP_CPU_PORT_SB_CM_EGRESS(_tc)				\
-	MLXSW_SP_SB_CM(_tc, MLXSW_REG_SBCM_DIR_EGRESS, 104, 2, 3)
-
-static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms[] = {
-	MLXSW_SP_SB_CM_INGRESS(0, 10000 / MLXSW_SP_SB_BYTES_PER_CELL, 8),
-	MLXSW_SP_SB_CM_INGRESS(1, 0, 0),
-	MLXSW_SP_SB_CM_INGRESS(2, 0, 0),
-	MLXSW_SP_SB_CM_INGRESS(3, 0, 0),
-	MLXSW_SP_SB_CM_INGRESS(4, 0, 0),
-	MLXSW_SP_SB_CM_INGRESS(5, 0, 0),
-	MLXSW_SP_SB_CM_INGRESS(6, 0, 0),
-	MLXSW_SP_SB_CM_INGRESS(7, 0, 0),
-	MLXSW_SP_SB_CM_INGRESS(9, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff),
-	MLXSW_SP_SB_CM_EGRESS(0, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9),
-	MLXSW_SP_SB_CM_EGRESS(1, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9),
-	MLXSW_SP_SB_CM_EGRESS(2, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9),
-	MLXSW_SP_SB_CM_EGRESS(3, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9),
-	MLXSW_SP_SB_CM_EGRESS(4, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9),
-	MLXSW_SP_SB_CM_EGRESS(5, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9),
-	MLXSW_SP_SB_CM_EGRESS(6, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9),
-	MLXSW_SP_SB_CM_EGRESS(7, 1500 / MLXSW_SP_SB_BYTES_PER_CELL, 9),
-	MLXSW_SP_SB_CM_EGRESS(8, 0, 0),
-	MLXSW_SP_SB_CM_EGRESS(9, 0, 0),
-	MLXSW_SP_SB_CM_EGRESS(10, 0, 0),
-	MLXSW_SP_SB_CM_EGRESS(11, 0, 0),
-	MLXSW_SP_SB_CM_EGRESS(12, 0, 0),
-	MLXSW_SP_SB_CM_EGRESS(13, 0, 0),
-	MLXSW_SP_SB_CM_EGRESS(14, 0, 0),
-	MLXSW_SP_SB_CM_EGRESS(15, 0, 0),
-	MLXSW_SP_SB_CM_EGRESS(16, 1, 0xff),
+static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = {
+	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(10000), 8, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, 0, 0), /* dummy, this PG does not exist */
+	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(20000), 1, 3),
 };
 
-#define MLXSW_SP_SB_CMS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms)
+#define MLXSW_SP_SB_CMS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_ingress)
+
+static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = {
+	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+	MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+	MLXSW_SP_SB_CM(0, 0, 0),
+	MLXSW_SP_SB_CM(0, 0, 0),
+	MLXSW_SP_SB_CM(0, 0, 0),
+	MLXSW_SP_SB_CM(0, 0, 0),
+	MLXSW_SP_SB_CM(0, 0, 0),
+	MLXSW_SP_SB_CM(0, 0, 0),
+	MLXSW_SP_SB_CM(0, 0, 0),
+	MLXSW_SP_SB_CM(0, 0, 0),
+	MLXSW_SP_SB_CM(1, 0xff, 0),
+};
+
+#define MLXSW_SP_SB_CMS_EGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_egress)
+
+#define MLXSW_SP_CPU_PORT_SB_CM MLXSW_SP_SB_CM(0, 0, 0)
 
 static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = {
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(0),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(1),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(2),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(3),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(4),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(5),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(6),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(7),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(8),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(9),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(10),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(11),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(12),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(13),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(14),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(15),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(16),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(17),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(18),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(19),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(20),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(21),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(22),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(23),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(24),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(25),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(26),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(27),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(28),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(29),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(30),
-	MLXSW_SP_CPU_PORT_SB_CM_EGRESS(31),
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_CPU_PORT_SB_CM,
 };
 
 #define MLXSW_SP_CPU_PORT_SB_MCS_LEN \
 	ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms)
 
-static int mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
-				const struct mlxsw_sp_sb_cm *cms,
-				size_t cms_len)
+static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				  enum mlxsw_reg_sbxx_dir dir,
+				  const struct mlxsw_sp_sb_cm *cms,
+				  size_t cms_len)
 {
-	char sbcm_pl[MLXSW_REG_SBCM_LEN];
 	int i;
 	int err;
 
 	for (i = 0; i < cms_len; i++) {
 		const struct mlxsw_sp_sb_cm *cm;
 
+		if (i == 8 && dir == MLXSW_REG_SBXX_DIR_INGRESS)
+			continue; /* PG number 8 does not exist, skip it */
 		cm = &cms[i];
-		mlxsw_reg_sbcm_pack(sbcm_pl, local_port, cm->u.pg, cm->dir,
-				    cm->min_buff, cm->max_buff, cm->pool);
-		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbcm), sbcm_pl);
+		err = mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, i, dir,
+					   cm->min_buff, cm->max_buff,
+					   cm->pool);
 		if (err)
 			return err;
 	}
@@ -269,105 +385,120 @@ static int mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 
 static int mlxsw_sp_port_sb_cms_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	return mlxsw_sp_sb_cms_init(mlxsw_sp_port->mlxsw_sp,
-				    mlxsw_sp_port->local_port, mlxsw_sp_sb_cms,
-				    MLXSW_SP_SB_CMS_LEN);
+	int err;
+
+	err = __mlxsw_sp_sb_cms_init(mlxsw_sp_port->mlxsw_sp,
+				     mlxsw_sp_port->local_port,
+				     MLXSW_REG_SBXX_DIR_INGRESS,
+				     mlxsw_sp_sb_cms_ingress,
+				     MLXSW_SP_SB_CMS_INGRESS_LEN);
+	if (err)
+		return err;
+	return __mlxsw_sp_sb_cms_init(mlxsw_sp_port->mlxsw_sp,
+				      mlxsw_sp_port->local_port,
+				      MLXSW_REG_SBXX_DIR_EGRESS,
+				      mlxsw_sp_sb_cms_egress,
+				      MLXSW_SP_SB_CMS_EGRESS_LEN);
 }
 
 static int mlxsw_sp_cpu_port_sb_cms_init(struct mlxsw_sp *mlxsw_sp)
 {
-	return mlxsw_sp_sb_cms_init(mlxsw_sp, 0, mlxsw_sp_cpu_port_sb_cms,
-				    MLXSW_SP_CPU_PORT_SB_MCS_LEN);
+	return __mlxsw_sp_sb_cms_init(mlxsw_sp, 0, MLXSW_REG_SBXX_DIR_EGRESS,
+				      mlxsw_sp_cpu_port_sb_cms,
+				      MLXSW_SP_CPU_PORT_SB_MCS_LEN);
 }
 
-struct mlxsw_sp_sb_pm {
-	u8 pool;
-	enum mlxsw_reg_sbpm_dir dir;
-	u32 min_buff;
-	u32 max_buff;
+#define MLXSW_SP_SB_PM(_min_buff, _max_buff)	\
+	{					\
+		.min_buff = _min_buff,		\
+		.max_buff = _max_buff,		\
+	}
+
+static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms_ingress[] = {
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX),
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX),
 };
 
-#define MLXSW_SP_SB_PM(_pool, _dir, _min_buff, _max_buff)	\
-	{							\
-		.pool = _pool,					\
-		.dir = _dir,					\
-		.min_buff = _min_buff,				\
-		.max_buff = _max_buff,				\
-	}
+#define MLXSW_SP_SB_PMS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_pms_ingress)
 
-#define MLXSW_SP_SB_PM_INGRESS(_pool, _min_buff, _max_buff)	\
-	MLXSW_SP_SB_PM(_pool, MLXSW_REG_SBPM_DIR_INGRESS,	\
-		       _min_buff, _max_buff)
-
-#define MLXSW_SP_SB_PM_EGRESS(_pool, _min_buff, _max_buff)	\
-	MLXSW_SP_SB_PM(_pool, MLXSW_REG_SBPM_DIR_EGRESS,	\
-		       _min_buff, _max_buff)
-
-static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms[] = {
-	MLXSW_SP_SB_PM_INGRESS(0, 0, 0xff),
-	MLXSW_SP_SB_PM_INGRESS(1, 0, 0),
-	MLXSW_SP_SB_PM_INGRESS(2, 0, 0),
-	MLXSW_SP_SB_PM_INGRESS(3, 0, 0),
-	MLXSW_SP_SB_PM_EGRESS(0, 0, 7),
-	MLXSW_SP_SB_PM_EGRESS(1, 0, 0),
-	MLXSW_SP_SB_PM_EGRESS(2, 0, 0),
-	MLXSW_SP_SB_PM_EGRESS(3, 0, 0),
+static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms_egress[] = {
+	MLXSW_SP_SB_PM(0, 7),
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
 };
 
-#define MLXSW_SP_SB_PMS_LEN ARRAY_SIZE(mlxsw_sp_sb_pms)
+#define MLXSW_SP_SB_PMS_EGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_pms_egress)
 
-static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port)
+static int __mlxsw_sp_port_sb_pms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				       enum mlxsw_reg_sbxx_dir dir,
+				       const struct mlxsw_sp_sb_pm *pms,
+				       size_t pms_len)
 {
-	char sbpm_pl[MLXSW_REG_SBPM_LEN];
 	int i;
 	int err;
 
-	for (i = 0; i < MLXSW_SP_SB_PMS_LEN; i++) {
+	for (i = 0; i < pms_len; i++) {
 		const struct mlxsw_sp_sb_pm *pm;
 
-		pm = &mlxsw_sp_sb_pms[i];
-		mlxsw_reg_sbpm_pack(sbpm_pl, mlxsw_sp_port->local_port,
-				    pm->pool, pm->dir,
-				    pm->min_buff, pm->max_buff);
-		err = mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core,
-				      MLXSW_REG(sbpm), sbpm_pl);
+		pm = &pms[i];
+		err = mlxsw_sp_sb_pm_write(mlxsw_sp, local_port, i, dir,
+					   pm->min_buff, pm->max_buff);
 		if (err)
 			return err;
 	}
 	return 0;
 }
 
+static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	int err;
+
+	err = __mlxsw_sp_port_sb_pms_init(mlxsw_sp_port->mlxsw_sp,
+					  mlxsw_sp_port->local_port,
+					  MLXSW_REG_SBXX_DIR_INGRESS,
+					  mlxsw_sp_sb_pms_ingress,
+					  MLXSW_SP_SB_PMS_INGRESS_LEN);
+	if (err)
+		return err;
+	return __mlxsw_sp_port_sb_pms_init(mlxsw_sp_port->mlxsw_sp,
+					   mlxsw_sp_port->local_port,
+					   MLXSW_REG_SBXX_DIR_EGRESS,
+					   mlxsw_sp_sb_pms_egress,
+					   MLXSW_SP_SB_PMS_EGRESS_LEN);
+}
+
 struct mlxsw_sp_sb_mm {
-	u8 prio;
 	u32 min_buff;
 	u32 max_buff;
 	u8 pool;
 };
 
-#define MLXSW_SP_SB_MM(_prio, _min_buff, _max_buff, _pool)	\
-	{							\
-		.prio = _prio,					\
-		.min_buff = _min_buff,				\
-		.max_buff = _max_buff,				\
-		.pool = _pool,					\
+#define MLXSW_SP_SB_MM(_min_buff, _max_buff, _pool)	\
+	{						\
+		.min_buff = _min_buff,			\
+		.max_buff = _max_buff,			\
+		.pool = _pool,				\
 	}
 
 static const struct mlxsw_sp_sb_mm mlxsw_sp_sb_mms[] = {
-	MLXSW_SP_SB_MM(0, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(1, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(2, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(3, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(4, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(5, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(6, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(7, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(8, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(9, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(10, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(11, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(12, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(13, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
-	MLXSW_SP_SB_MM(14, 20000 / MLXSW_SP_SB_BYTES_PER_CELL, 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+	MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
 };
 
 #define MLXSW_SP_SB_MMS_LEN ARRAY_SIZE(mlxsw_sp_sb_mms)
@@ -382,7 +513,7 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
 		const struct mlxsw_sp_sb_mm *mc;
 
 		mc = &mlxsw_sp_sb_mms[i];
-		mlxsw_reg_sbmm_pack(sbmm_pl, mc->prio, mc->min_buff,
+		mlxsw_reg_sbmm_pack(sbmm_pl, i, mc->min_buff,
 				    mc->max_buff, mc->pool);
 		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbmm), sbmm_pl);
 		if (err)
@@ -391,26 +522,39 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 }
 
+#define MLXSW_SP_SB_SIZE (16 * 1024 * 1024)
+
 int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp)
 {
 	int err;
 
-	err = mlxsw_sp_sb_pools_init(mlxsw_sp);
+	err = mlxsw_sp_sb_prs_init(mlxsw_sp);
 	if (err)
 		return err;
 	err = mlxsw_sp_cpu_port_sb_cms_init(mlxsw_sp);
 	if (err)
 		return err;
 	err = mlxsw_sp_sb_mms_init(mlxsw_sp);
+	if (err)
+		return err;
+	return devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0,
+				   MLXSW_SP_SB_SIZE,
+				   MLXSW_SP_SB_POOL_COUNT,
+				   MLXSW_SP_SB_POOL_COUNT,
+				   MLXSW_SP_SB_TC_COUNT,
+				   MLXSW_SP_SB_TC_COUNT);
+}
 
-	return err;
+void mlxsw_sp_buffers_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	devlink_sb_unregister(priv_to_devlink(mlxsw_sp->core), 0);
 }
 
 int mlxsw_sp_port_buffers_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
 	int err;
 
-	err = mlxsw_sp_port_pb_init(mlxsw_sp_port);
+	err = mlxsw_sp_port_headroom_init(mlxsw_sp_port);
 	if (err)
 		return err;
 	err = mlxsw_sp_port_sb_cms_init(mlxsw_sp_port);
@@ -420,3 +564,394 @@ int mlxsw_sp_port_buffers_init(struct mlxsw_sp_port *mlxsw_sp_port)
 
 	return err;
 }
+
+static u8 pool_get(u16 pool_index)
+{
+	return pool_index % MLXSW_SP_SB_POOL_COUNT;
+}
+
+static u16 pool_index_get(u8 pool, enum mlxsw_reg_sbxx_dir dir)
+{
+	u16 pool_index;
+
+	pool_index = pool;
+	if (dir == MLXSW_REG_SBXX_DIR_EGRESS)
+		pool_index += MLXSW_SP_SB_POOL_COUNT;
+	return pool_index;
+}
+
+static enum mlxsw_reg_sbxx_dir dir_get(u16 pool_index)
+{
+	return pool_index < MLXSW_SP_SB_POOL_COUNT ?
+	       MLXSW_REG_SBXX_DIR_INGRESS : MLXSW_REG_SBXX_DIR_EGRESS;
+}
+
+int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core,
+			 unsigned int sb_index, u16 pool_index,
+			 struct devlink_sb_pool_info *pool_info)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	u8 pool = pool_get(pool_index);
+	enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index);
+	struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir);
+
+	pool_info->pool_type = dir;
+	pool_info->size = MLXSW_SP_CELLS_TO_BYTES(pr->size);
+	pool_info->threshold_type = pr->mode;
+	return 0;
+}
+
+int mlxsw_sp_sb_pool_set(struct mlxsw_core *mlxsw_core,
+			 unsigned int sb_index, u16 pool_index, u32 size,
+			 enum devlink_sb_threshold_type threshold_type)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	u8 pool = pool_get(pool_index);
+	enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index);
+	enum mlxsw_reg_sbpr_mode mode = threshold_type;
+	u32 pool_size = MLXSW_SP_BYTES_TO_CELLS(size);
+
+	return mlxsw_sp_sb_pr_write(mlxsw_sp, pool, dir, mode, pool_size);
+}
+
+#define MLXSW_SP_SB_THRESHOLD_TO_ALPHA_OFFSET (-2) /* 3->1, 16->14 */
+
+static u32 mlxsw_sp_sb_threshold_out(struct mlxsw_sp *mlxsw_sp, u8 pool,
+				     enum mlxsw_reg_sbxx_dir dir, u32 max_buff)
+{
+	struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir);
+
+	if (pr->mode == MLXSW_REG_SBPR_MODE_DYNAMIC)
+		return max_buff - MLXSW_SP_SB_THRESHOLD_TO_ALPHA_OFFSET;
+	return MLXSW_SP_CELLS_TO_BYTES(max_buff);
+}
+
+static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u8 pool,
+				    enum mlxsw_reg_sbxx_dir dir, u32 threshold,
+				    u32 *p_max_buff)
+{
+	struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir);
+
+	if (pr->mode == MLXSW_REG_SBPR_MODE_DYNAMIC) {
+		int val;
+
+		val = threshold + MLXSW_SP_SB_THRESHOLD_TO_ALPHA_OFFSET;
+		if (val < MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN ||
+		    val > MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX)
+			return -EINVAL;
+		*p_max_buff = val;
+	} else {
+		*p_max_buff = MLXSW_SP_BYTES_TO_CELLS(threshold);
+	}
+	return 0;
+}
+
+int mlxsw_sp_sb_port_pool_get(struct mlxsw_core_port *mlxsw_core_port,
+			      unsigned int sb_index, u16 pool_index,
+			      u32 *p_threshold)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port =
+			mlxsw_core_port_driver_priv(mlxsw_core_port);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 local_port = mlxsw_sp_port->local_port;
+	u8 pool = pool_get(pool_index);
+	enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index);
+	struct mlxsw_sp_sb_pm *pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port,
+						       pool, dir);
+
+	*p_threshold = mlxsw_sp_sb_threshold_out(mlxsw_sp, pool, dir,
+						 pm->max_buff);
+	return 0;
+}
+
+int mlxsw_sp_sb_port_pool_set(struct mlxsw_core_port *mlxsw_core_port,
+			      unsigned int sb_index, u16 pool_index,
+			      u32 threshold)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port =
+			mlxsw_core_port_driver_priv(mlxsw_core_port);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 local_port = mlxsw_sp_port->local_port;
+	u8 pool = pool_get(pool_index);
+	enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index);
+	u32 max_buff;
+	int err;
+
+	err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool, dir,
+				       threshold, &max_buff);
+	if (err)
+		return err;
+
+	return mlxsw_sp_sb_pm_write(mlxsw_sp, local_port, pool, dir,
+				    0, max_buff);
+}
+
+int mlxsw_sp_sb_tc_pool_bind_get(struct mlxsw_core_port *mlxsw_core_port,
+				 unsigned int sb_index, u16 tc_index,
+				 enum devlink_sb_pool_type pool_type,
+				 u16 *p_pool_index, u32 *p_threshold)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port =
+			mlxsw_core_port_driver_priv(mlxsw_core_port);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 local_port = mlxsw_sp_port->local_port;
+	u8 pg_buff = tc_index;
+	enum mlxsw_reg_sbxx_dir dir = pool_type;
+	struct mlxsw_sp_sb_cm *cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port,
+						       pg_buff, dir);
+
+	*p_threshold = mlxsw_sp_sb_threshold_out(mlxsw_sp, cm->pool, dir,
+						 cm->max_buff);
+	*p_pool_index = pool_index_get(cm->pool, pool_type);
+	return 0;
+}
+
+int mlxsw_sp_sb_tc_pool_bind_set(struct mlxsw_core_port *mlxsw_core_port,
+				 unsigned int sb_index, u16 tc_index,
+				 enum devlink_sb_pool_type pool_type,
+				 u16 pool_index, u32 threshold)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port =
+			mlxsw_core_port_driver_priv(mlxsw_core_port);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 local_port = mlxsw_sp_port->local_port;
+	u8 pg_buff = tc_index;
+	enum mlxsw_reg_sbxx_dir dir = pool_type;
+	u8 pool = pool_index;
+	u32 max_buff;
+	int err;
+
+	err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool, dir,
+				       threshold, &max_buff);
+	if (err)
+		return err;
+
+	if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS) {
+		if (pool < MLXSW_SP_SB_POOL_COUNT)
+			return -EINVAL;
+		pool -= MLXSW_SP_SB_POOL_COUNT;
+	} else if (pool >= MLXSW_SP_SB_POOL_COUNT) {
+		return -EINVAL;
+	}
+	return mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, pg_buff, dir,
+				    0, max_buff, pool);
+}
+
+#define MASKED_COUNT_MAX \
+	(MLXSW_REG_SBSR_REC_MAX_COUNT / (MLXSW_SP_SB_TC_COUNT * 2))
+
+struct mlxsw_sp_sb_sr_occ_query_cb_ctx {
+	u8 masked_count;
+	u8 local_port_1;
+};
+
+static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core,
+					char *sbsr_pl, size_t sbsr_pl_len,
+					unsigned long cb_priv)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	struct mlxsw_sp_sb_sr_occ_query_cb_ctx cb_ctx;
+	u8 masked_count;
+	u8 local_port;
+	int rec_index = 0;
+	struct mlxsw_sp_sb_cm *cm;
+	int i;
+
+	memcpy(&cb_ctx, &cb_priv, sizeof(cb_ctx));
+
+	masked_count = 0;
+	for (local_port = cb_ctx.local_port_1;
+	     local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+		if (!mlxsw_sp->ports[local_port])
+			continue;
+		for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) {
+			cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port, i,
+						MLXSW_REG_SBXX_DIR_INGRESS);
+			mlxsw_reg_sbsr_rec_unpack(sbsr_pl, rec_index++,
+						  &cm->occ.cur, &cm->occ.max);
+		}
+		if (++masked_count == cb_ctx.masked_count)
+			break;
+	}
+	masked_count = 0;
+	for (local_port = cb_ctx.local_port_1;
+	     local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+		if (!mlxsw_sp->ports[local_port])
+			continue;
+		for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) {
+			cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port, i,
+						MLXSW_REG_SBXX_DIR_EGRESS);
+			mlxsw_reg_sbsr_rec_unpack(sbsr_pl, rec_index++,
+						  &cm->occ.cur, &cm->occ.max);
+		}
+		if (++masked_count == cb_ctx.masked_count)
+			break;
+	}
+}
+
+int mlxsw_sp_sb_occ_snapshot(struct mlxsw_core *mlxsw_core,
+			     unsigned int sb_index)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	struct mlxsw_sp_sb_sr_occ_query_cb_ctx cb_ctx;
+	unsigned long cb_priv;
+	LIST_HEAD(bulk_list);
+	char *sbsr_pl;
+	u8 masked_count;
+	u8 local_port_1;
+	u8 local_port = 0;
+	int i;
+	int err;
+	int err2;
+
+	sbsr_pl = kmalloc(MLXSW_REG_SBSR_LEN, GFP_KERNEL);
+	if (!sbsr_pl)
+		return -ENOMEM;
+
+next_batch:
+	local_port++;
+	local_port_1 = local_port;
+	masked_count = 0;
+	mlxsw_reg_sbsr_pack(sbsr_pl, false);
+	for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) {
+		mlxsw_reg_sbsr_pg_buff_mask_set(sbsr_pl, i, 1);
+		mlxsw_reg_sbsr_tclass_mask_set(sbsr_pl, i, 1);
+	}
+	for (; local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+		if (!mlxsw_sp->ports[local_port])
+			continue;
+		mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
+		mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1);
+		for (i = 0; i < MLXSW_SP_SB_POOL_COUNT; i++) {
+			err = mlxsw_sp_sb_pm_occ_query(mlxsw_sp, local_port, i,
+						       MLXSW_REG_SBXX_DIR_INGRESS,
+						       &bulk_list);
+			if (err)
+				goto out;
+			err = mlxsw_sp_sb_pm_occ_query(mlxsw_sp, local_port, i,
+						       MLXSW_REG_SBXX_DIR_EGRESS,
+						       &bulk_list);
+			if (err)
+				goto out;
+		}
+		if (++masked_count == MASKED_COUNT_MAX)
+			goto do_query;
+	}
+
+do_query:
+	cb_ctx.masked_count = masked_count;
+	cb_ctx.local_port_1 = local_port_1;
+	memcpy(&cb_priv, &cb_ctx, sizeof(cb_ctx));
+	err = mlxsw_reg_trans_query(mlxsw_core, MLXSW_REG(sbsr), sbsr_pl,
+				    &bulk_list, mlxsw_sp_sb_sr_occ_query_cb,
+				    cb_priv);
+	if (err)
+		goto out;
+	if (local_port < MLXSW_PORT_MAX_PORTS)
+		goto next_batch;
+
+out:
+	err2 = mlxsw_reg_trans_bulk_wait(&bulk_list);
+	if (!err)
+		err = err2;
+	kfree(sbsr_pl);
+	return err;
+}
+
+int mlxsw_sp_sb_occ_max_clear(struct mlxsw_core *mlxsw_core,
+			      unsigned int sb_index)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	LIST_HEAD(bulk_list);
+	char *sbsr_pl;
+	unsigned int masked_count;
+	u8 local_port = 0;
+	int i;
+	int err;
+	int err2;
+
+	sbsr_pl = kmalloc(MLXSW_REG_SBSR_LEN, GFP_KERNEL);
+	if (!sbsr_pl)
+		return -ENOMEM;
+
+next_batch:
+	local_port++;
+	masked_count = 0;
+	mlxsw_reg_sbsr_pack(sbsr_pl, true);
+	for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) {
+		mlxsw_reg_sbsr_pg_buff_mask_set(sbsr_pl, i, 1);
+		mlxsw_reg_sbsr_tclass_mask_set(sbsr_pl, i, 1);
+	}
+	for (; local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+		if (!mlxsw_sp->ports[local_port])
+			continue;
+		mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
+		mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1);
+		for (i = 0; i < MLXSW_SP_SB_POOL_COUNT; i++) {
+			err = mlxsw_sp_sb_pm_occ_clear(mlxsw_sp, local_port, i,
+						       MLXSW_REG_SBXX_DIR_INGRESS,
+						       &bulk_list);
+			if (err)
+				goto out;
+			err = mlxsw_sp_sb_pm_occ_clear(mlxsw_sp, local_port, i,
+						       MLXSW_REG_SBXX_DIR_EGRESS,
+						       &bulk_list);
+			if (err)
+				goto out;
+		}
+		if (++masked_count == MASKED_COUNT_MAX)
+			goto do_query;
+	}
+
+do_query:
+	err = mlxsw_reg_trans_query(mlxsw_core, MLXSW_REG(sbsr), sbsr_pl,
+				    &bulk_list, NULL, 0);
+	if (err)
+		goto out;
+	if (local_port < MLXSW_PORT_MAX_PORTS)
+		goto next_batch;
+
+out:
+	err2 = mlxsw_reg_trans_bulk_wait(&bulk_list);
+	if (!err)
+		err = err2;
+	kfree(sbsr_pl);
+	return err;
+}
+
+int mlxsw_sp_sb_occ_port_pool_get(struct mlxsw_core_port *mlxsw_core_port,
+				  unsigned int sb_index, u16 pool_index,
+				  u32 *p_cur, u32 *p_max)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port =
+			mlxsw_core_port_driver_priv(mlxsw_core_port);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 local_port = mlxsw_sp_port->local_port;
+	u8 pool = pool_get(pool_index);
+	enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index);
+	struct mlxsw_sp_sb_pm *pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port,
+						       pool, dir);
+
+	*p_cur = MLXSW_SP_CELLS_TO_BYTES(pm->occ.cur);
+	*p_max = MLXSW_SP_CELLS_TO_BYTES(pm->occ.max);
+	return 0;
+}
+
+int mlxsw_sp_sb_occ_tc_port_bind_get(struct mlxsw_core_port *mlxsw_core_port,
+				     unsigned int sb_index, u16 tc_index,
+				     enum devlink_sb_pool_type pool_type,
+				     u32 *p_cur, u32 *p_max)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port =
+			mlxsw_core_port_driver_priv(mlxsw_core_port);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 local_port = mlxsw_sp_port->local_port;
+	u8 pg_buff = tc_index;
+	enum mlxsw_reg_sbxx_dir dir = pool_type;
+	struct mlxsw_sp_sb_cm *cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port,
+						       pg_buff, dir);
+
+	*p_cur = MLXSW_SP_CELLS_TO_BYTES(cm->occ.cur);
+	*p_max = MLXSW_SP_CELLS_TO_BYTES(cm->occ.max);
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
new file mode 100644
index 000000000..01cfb7512
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
@@ -0,0 +1,484 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/string.h>
+#include <linux/bitops.h>
+#include <net/dcbnl.h>
+
+#include "spectrum.h"
+#include "reg.h"
+
+static u8 mlxsw_sp_dcbnl_getdcbx(struct net_device __always_unused *dev)
+{
+	return DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE;
+}
+
+static u8 mlxsw_sp_dcbnl_setdcbx(struct net_device __always_unused *dev,
+				 u8 mode)
+{
+	return (mode != (DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE)) ? 1 : 0;
+}
+
+static int mlxsw_sp_dcbnl_ieee_getets(struct net_device *dev,
+				      struct ieee_ets *ets)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+
+	memcpy(ets, mlxsw_sp_port->dcb.ets, sizeof(*ets));
+
+	return 0;
+}
+
+static int mlxsw_sp_port_ets_validate(struct mlxsw_sp_port *mlxsw_sp_port,
+				      struct ieee_ets *ets)
+{
+	struct net_device *dev = mlxsw_sp_port->dev;
+	bool has_ets_tc = false;
+	int i, tx_bw_sum = 0;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_STRICT:
+			break;
+		case IEEE_8021QAZ_TSA_ETS:
+			has_ets_tc = true;
+			tx_bw_sum += ets->tc_tx_bw[i];
+			break;
+		default:
+			netdev_err(dev, "Only strict priority and ETS are supported\n");
+			return -EINVAL;
+		}
+
+		if (ets->prio_tc[i] >= IEEE_8021QAZ_MAX_TCS) {
+			netdev_err(dev, "Invalid TC\n");
+			return -EINVAL;
+		}
+	}
+
+	if (has_ets_tc && tx_bw_sum != 100) {
+		netdev_err(dev, "Total ETS bandwidth should equal 100\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_port_pg_prio_map(struct mlxsw_sp_port *mlxsw_sp_port,
+				     u8 *prio_tc)
+{
+	char pptb_pl[MLXSW_REG_PPTB_LEN];
+	int i;
+
+	mlxsw_reg_pptb_pack(pptb_pl, mlxsw_sp_port->local_port);
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		mlxsw_reg_pptb_prio_to_buff_pack(pptb_pl, i, prio_tc[i]);
+
+	return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pptb),
+			       pptb_pl);
+}
+
+static bool mlxsw_sp_ets_has_pg(u8 *prio_tc, u8 pg)
+{
+	int i;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		if (prio_tc[i] == pg)
+			return true;
+	return false;
+}
+
+static int mlxsw_sp_port_pg_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u8 *old_prio_tc, u8 *new_prio_tc)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char pbmc_pl[MLXSW_REG_PBMC_LEN];
+	int err, i;
+
+	mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port, 0, 0);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
+	if (err)
+		return err;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		u8 pg = old_prio_tc[i];
+
+		if (!mlxsw_sp_ets_has_pg(new_prio_tc, pg))
+			mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, pg, 0);
+	}
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
+}
+
+static int mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				      struct ieee_ets *ets)
+{
+	bool pause_en = mlxsw_sp_port_is_pause_en(mlxsw_sp_port);
+	struct ieee_ets *my_ets = mlxsw_sp_port->dcb.ets;
+	struct net_device *dev = mlxsw_sp_port->dev;
+	int err;
+
+	/* Create the required PGs, but don't destroy existing ones, as
+	 * traffic is still directed to them.
+	 */
+	err = __mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu,
+					   ets->prio_tc, pause_en,
+					   mlxsw_sp_port->dcb.pfc);
+	if (err) {
+		netdev_err(dev, "Failed to configure port's headroom\n");
+		return err;
+	}
+
+	err = mlxsw_sp_port_pg_prio_map(mlxsw_sp_port, ets->prio_tc);
+	if (err) {
+		netdev_err(dev, "Failed to set PG-priority mapping\n");
+		goto err_port_prio_pg_map;
+	}
+
+	err = mlxsw_sp_port_pg_destroy(mlxsw_sp_port, my_ets->prio_tc,
+				       ets->prio_tc);
+	if (err)
+		netdev_warn(dev, "Failed to remove ununsed PGs\n");
+
+	return 0;
+
+err_port_prio_pg_map:
+	mlxsw_sp_port_pg_destroy(mlxsw_sp_port, ets->prio_tc, my_ets->prio_tc);
+	return err;
+}
+
+static int __mlxsw_sp_dcbnl_ieee_setets(struct mlxsw_sp_port *mlxsw_sp_port,
+					struct ieee_ets *ets)
+{
+	struct ieee_ets *my_ets = mlxsw_sp_port->dcb.ets;
+	struct net_device *dev = mlxsw_sp_port->dev;
+	int i, err;
+
+	/* Egress configuration. */
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		bool dwrr = ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS;
+		u8 weight = ets->tc_tx_bw[i];
+
+		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
+					    MLXSW_REG_QEEC_HIERARCY_SUBGROUP, i,
+					    0, dwrr, weight);
+		if (err) {
+			netdev_err(dev, "Failed to link subgroup ETS element %d to group\n",
+				   i);
+			goto err_port_ets_set;
+		}
+	}
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		err = mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, i,
+						ets->prio_tc[i]);
+		if (err) {
+			netdev_err(dev, "Failed to map prio %d to TC %d\n", i,
+				   ets->prio_tc[i]);
+			goto err_port_prio_tc_set;
+		}
+	}
+
+	/* Ingress configuration. */
+	err = mlxsw_sp_port_headroom_set(mlxsw_sp_port, ets);
+	if (err)
+		goto err_port_headroom_set;
+
+	return 0;
+
+err_port_headroom_set:
+	i = IEEE_8021QAZ_MAX_TCS;
+err_port_prio_tc_set:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, i, my_ets->prio_tc[i]);
+	i = IEEE_8021QAZ_MAX_TCS;
+err_port_ets_set:
+	for (i--; i >= 0; i--) {
+		bool dwrr = my_ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS;
+		u8 weight = my_ets->tc_tx_bw[i];
+
+		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
+					    MLXSW_REG_QEEC_HIERARCY_SUBGROUP, i,
+					    0, dwrr, weight);
+	}
+	return err;
+}
+
+static int mlxsw_sp_dcbnl_ieee_setets(struct net_device *dev,
+				      struct ieee_ets *ets)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	int err;
+
+	err = mlxsw_sp_port_ets_validate(mlxsw_sp_port, ets);
+	if (err)
+		return err;
+
+	err = __mlxsw_sp_dcbnl_ieee_setets(mlxsw_sp_port, ets);
+	if (err)
+		return err;
+
+	memcpy(mlxsw_sp_port->dcb.ets, ets, sizeof(*ets));
+	mlxsw_sp_port->dcb.ets->ets_cap = IEEE_8021QAZ_MAX_TCS;
+
+	return 0;
+}
+
+static int mlxsw_sp_dcbnl_ieee_getmaxrate(struct net_device *dev,
+					  struct ieee_maxrate *maxrate)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+
+	memcpy(maxrate, mlxsw_sp_port->dcb.maxrate, sizeof(*maxrate));
+
+	return 0;
+}
+
+static int mlxsw_sp_dcbnl_ieee_setmaxrate(struct net_device *dev,
+					  struct ieee_maxrate *maxrate)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct ieee_maxrate *my_maxrate = mlxsw_sp_port->dcb.maxrate;
+	int err, i;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
+						    MLXSW_REG_QEEC_HIERARCY_SUBGROUP,
+						    i, 0,
+						    maxrate->tc_maxrate[i]);
+		if (err) {
+			netdev_err(dev, "Failed to set maxrate for TC %d\n", i);
+			goto err_port_ets_maxrate_set;
+		}
+	}
+
+	memcpy(mlxsw_sp_port->dcb.maxrate, maxrate, sizeof(*maxrate));
+
+	return 0;
+
+err_port_ets_maxrate_set:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
+					      MLXSW_REG_QEEC_HIERARCY_SUBGROUP,
+					      i, 0, my_maxrate->tc_maxrate[i]);
+	return err;
+}
+
+static int mlxsw_sp_port_pfc_cnt_get(struct mlxsw_sp_port *mlxsw_sp_port,
+				     u8 prio)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct ieee_pfc *my_pfc = mlxsw_sp_port->dcb.pfc;
+	char ppcnt_pl[MLXSW_REG_PPCNT_LEN];
+	int err;
+
+	mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sp_port->local_port,
+			     MLXSW_REG_PPCNT_PRIO_CNT, prio);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ppcnt), ppcnt_pl);
+	if (err)
+		return err;
+
+	my_pfc->requests[prio] = mlxsw_reg_ppcnt_tx_pause_get(ppcnt_pl);
+	my_pfc->indications[prio] = mlxsw_reg_ppcnt_rx_pause_get(ppcnt_pl);
+
+	return 0;
+}
+
+static int mlxsw_sp_dcbnl_ieee_getpfc(struct net_device *dev,
+				      struct ieee_pfc *pfc)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	int err, i;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		err = mlxsw_sp_port_pfc_cnt_get(mlxsw_sp_port, i);
+		if (err) {
+			netdev_err(dev, "Failed to get PFC count for priority %d\n",
+				   i);
+			return err;
+		}
+	}
+
+	memcpy(pfc, mlxsw_sp_port->dcb.pfc, sizeof(*pfc));
+
+	return 0;
+}
+
+static int mlxsw_sp_port_pfc_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				 struct ieee_pfc *pfc)
+{
+	char pfcc_pl[MLXSW_REG_PFCC_LEN];
+
+	mlxsw_reg_pfcc_pack(pfcc_pl, mlxsw_sp_port->local_port);
+	mlxsw_reg_pfcc_prio_pack(pfcc_pl, pfc->pfc_en);
+
+	return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pfcc),
+			       pfcc_pl);
+}
+
+static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev,
+				      struct ieee_pfc *pfc)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	int err;
+
+	if ((mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause) &&
+	    pfc->pfc_en) {
+		netdev_err(dev, "PAUSE frames already enabled on port\n");
+		return -EINVAL;
+	}
+
+	err = __mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu,
+					   mlxsw_sp_port->dcb.ets->prio_tc,
+					   false, pfc);
+	if (err) {
+		netdev_err(dev, "Failed to configure port's headroom for PFC\n");
+		return err;
+	}
+
+	err = mlxsw_sp_port_pfc_set(mlxsw_sp_port, pfc);
+	if (err) {
+		netdev_err(dev, "Failed to configure PFC\n");
+		goto err_port_pfc_set;
+	}
+
+	memcpy(mlxsw_sp_port->dcb.pfc, pfc, sizeof(*pfc));
+	mlxsw_sp_port->dcb.pfc->pfc_cap = IEEE_8021QAZ_MAX_TCS;
+
+	return 0;
+
+err_port_pfc_set:
+	__mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu,
+				     mlxsw_sp_port->dcb.ets->prio_tc, false,
+				     mlxsw_sp_port->dcb.pfc);
+	return err;
+}
+
+static const struct dcbnl_rtnl_ops mlxsw_sp_dcbnl_ops = {
+	.ieee_getets		= mlxsw_sp_dcbnl_ieee_getets,
+	.ieee_setets		= mlxsw_sp_dcbnl_ieee_setets,
+	.ieee_getmaxrate	= mlxsw_sp_dcbnl_ieee_getmaxrate,
+	.ieee_setmaxrate	= mlxsw_sp_dcbnl_ieee_setmaxrate,
+	.ieee_getpfc		= mlxsw_sp_dcbnl_ieee_getpfc,
+	.ieee_setpfc		= mlxsw_sp_dcbnl_ieee_setpfc,
+
+	.getdcbx		= mlxsw_sp_dcbnl_getdcbx,
+	.setdcbx		= mlxsw_sp_dcbnl_setdcbx,
+};
+
+static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	mlxsw_sp_port->dcb.ets = kzalloc(sizeof(*mlxsw_sp_port->dcb.ets),
+					 GFP_KERNEL);
+	if (!mlxsw_sp_port->dcb.ets)
+		return -ENOMEM;
+
+	mlxsw_sp_port->dcb.ets->ets_cap = IEEE_8021QAZ_MAX_TCS;
+
+	return 0;
+}
+
+static void mlxsw_sp_port_ets_fini(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	kfree(mlxsw_sp_port->dcb.ets);
+}
+
+static int mlxsw_sp_port_maxrate_init(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	int i;
+
+	mlxsw_sp_port->dcb.maxrate = kmalloc(sizeof(*mlxsw_sp_port->dcb.maxrate),
+					     GFP_KERNEL);
+	if (!mlxsw_sp_port->dcb.maxrate)
+		return -ENOMEM;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		mlxsw_sp_port->dcb.maxrate->tc_maxrate[i] = MLXSW_REG_QEEC_MAS_DIS;
+
+	return 0;
+}
+
+static void mlxsw_sp_port_maxrate_fini(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	kfree(mlxsw_sp_port->dcb.maxrate);
+}
+
+static int mlxsw_sp_port_pfc_init(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	mlxsw_sp_port->dcb.pfc = kzalloc(sizeof(*mlxsw_sp_port->dcb.pfc),
+					 GFP_KERNEL);
+	if (!mlxsw_sp_port->dcb.pfc)
+		return -ENOMEM;
+
+	mlxsw_sp_port->dcb.pfc->pfc_cap = IEEE_8021QAZ_MAX_TCS;
+
+	return 0;
+}
+
+static void mlxsw_sp_port_pfc_fini(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	kfree(mlxsw_sp_port->dcb.pfc);
+}
+
+int mlxsw_sp_port_dcb_init(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	int err;
+
+	err = mlxsw_sp_port_ets_init(mlxsw_sp_port);
+	if (err)
+		return err;
+	err = mlxsw_sp_port_maxrate_init(mlxsw_sp_port);
+	if (err)
+		goto err_port_maxrate_init;
+	err = mlxsw_sp_port_pfc_init(mlxsw_sp_port);
+	if (err)
+		goto err_port_pfc_init;
+
+	mlxsw_sp_port->dev->dcbnl_ops = &mlxsw_sp_dcbnl_ops;
+
+	return 0;
+
+err_port_pfc_init:
+	mlxsw_sp_port_maxrate_fini(mlxsw_sp_port);
+err_port_maxrate_init:
+	mlxsw_sp_port_ets_fini(mlxsw_sp_port);
+	return err;
+}
+
+void mlxsw_sp_port_dcb_fini(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	mlxsw_sp_port_pfc_fini(mlxsw_sp_port);
+	mlxsw_sp_port_maxrate_fini(mlxsw_sp_port);
+	mlxsw_sp_port_ets_fini(mlxsw_sp_port);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 9cd6f4722..3710f19ed 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1438,8 +1438,8 @@ static void mlxsw_sp_fdb_notify_rec_process(struct mlxsw_sp *mlxsw_sp,
 
 static void mlxsw_sp_fdb_notify_work_schedule(struct mlxsw_sp *mlxsw_sp)
 {
-	schedule_delayed_work(&mlxsw_sp->fdb_notify.dw,
-			      msecs_to_jiffies(mlxsw_sp->fdb_notify.interval));
+	mlxsw_core_schedule_dw(&mlxsw_sp->fdb_notify.dw,
+			       msecs_to_jiffies(mlxsw_sp->fdb_notify.interval));
 }
 
 static void mlxsw_sp_fdb_notify_work(struct work_struct *work)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 7a60a2675..25f658b38 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -43,7 +43,6 @@
 #include <linux/device.h>
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
-#include <net/devlink.h>
 #include <net/switchdev.h>
 #include <generated/utsrelease.h>
 
@@ -75,11 +74,11 @@ struct mlxsw_sx_port_pcpu_stats {
 };
 
 struct mlxsw_sx_port {
+	struct mlxsw_core_port core_port; /* must be first */
 	struct net_device *dev;
 	struct mlxsw_sx_port_pcpu_stats __percpu *pcpu_stats;
 	struct mlxsw_sx *mlxsw_sx;
 	u8 local_port;
-	struct devlink_port devlink_port;
 };
 
 /* tx_hdr_version
@@ -303,7 +302,7 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 	u64 len;
 	int err;
 
-	if (mlxsw_core_skb_transmit_busy(mlxsw_sx, &tx_info))
+	if (mlxsw_core_skb_transmit_busy(mlxsw_sx->core, &tx_info))
 		return NETDEV_TX_BUSY;
 
 	if (unlikely(skb_headroom(skb) < MLXSW_TXHDR_LEN)) {
@@ -317,11 +316,14 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 		}
 	}
 	mlxsw_sx_txhdr_construct(skb, &tx_info);
-	len = skb->len;
+	/* TX header is consumed by HW on the way so we shouldn't count its
+	 * bytes as being sent.
+	 */
+	len = skb->len - MLXSW_TXHDR_LEN;
 	/* Due to a race we might fail here because of a full queue. In that
 	 * unlikely case we simply drop the packet.
 	 */
-	err = mlxsw_core_skb_transmit(mlxsw_sx, skb, &tx_info);
+	err = mlxsw_core_skb_transmit(mlxsw_sx->core, skb, &tx_info);
 
 	if (!err) {
 		pcpu_stats = this_cpu_ptr(mlxsw_sx_port->pcpu_stats);
@@ -518,7 +520,8 @@ static void mlxsw_sx_port_get_stats(struct net_device *dev,
 	int i;
 	int err;
 
-	mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sx_port->local_port);
+	mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sx_port->local_port,
+			     MLXSW_REG_PPCNT_IEEE_8023_CNT, 0);
 	err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ppcnt), ppcnt_pl);
 	for (i = 0; i < MLXSW_SX_PORT_HW_STATS_LEN; i++)
 		data[i] = !err ? mlxsw_sx_port_hw_stats[i].getter(ppcnt_pl) : 0;
@@ -955,9 +958,7 @@ mlxsw_sx_port_mac_learning_mode_set(struct mlxsw_sx_port *mlxsw_sx_port,
 
 static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 {
-	struct devlink *devlink = priv_to_devlink(mlxsw_sx->core);
 	struct mlxsw_sx_port *mlxsw_sx_port;
-	struct devlink_port *devlink_port;
 	struct net_device *dev;
 	bool usable;
 	int err;
@@ -1011,14 +1012,6 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 		goto port_not_usable;
 	}
 
-	devlink_port = &mlxsw_sx_port->devlink_port;
-	err = devlink_port_register(devlink, devlink_port, local_port);
-	if (err) {
-		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to register devlink port\n",
-			mlxsw_sx_port->local_port);
-		goto err_devlink_port_register;
-	}
-
 	err = mlxsw_sx_port_system_port_mapping_set(mlxsw_sx_port);
 	if (err) {
 		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set system port mapping\n",
@@ -1076,11 +1069,19 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 		goto err_register_netdev;
 	}
 
-	devlink_port_type_eth_set(devlink_port, dev);
+	err = mlxsw_core_port_init(mlxsw_sx->core, &mlxsw_sx_port->core_port,
+				   mlxsw_sx_port->local_port, dev, false, 0);
+	if (err) {
+		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to init core port\n",
+			mlxsw_sx_port->local_port);
+		goto err_core_port_init;
+	}
 
 	mlxsw_sx->ports[local_port] = mlxsw_sx_port;
 	return 0;
 
+err_core_port_init:
+	unregister_netdev(dev);
 err_register_netdev:
 err_port_mac_learning_mode_set:
 err_port_stp_state_set:
@@ -1089,8 +1090,6 @@ err_port_mtu_set:
 err_port_speed_set:
 err_port_swid_set:
 err_port_system_port_mapping_set:
-	devlink_port_unregister(&mlxsw_sx_port->devlink_port);
-err_devlink_port_register:
 port_not_usable:
 err_port_module_check:
 err_dev_addr_get:
@@ -1103,15 +1102,12 @@ err_alloc_stats:
 static void mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 {
 	struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port];
-	struct devlink_port *devlink_port;
 
 	if (!mlxsw_sx_port)
 		return;
-	devlink_port = &mlxsw_sx_port->devlink_port;
-	devlink_port_type_clear(devlink_port);
+	mlxsw_core_port_fini(&mlxsw_sx_port->core_port);
 	unregister_netdev(mlxsw_sx_port->dev); /* This calls ndo_stop */
 	mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
-	devlink_port_unregister(devlink_port);
 	free_percpu(mlxsw_sx_port->pcpu_stats);
 	free_netdev(mlxsw_sx_port->dev);
 }
@@ -1454,10 +1450,10 @@ static int mlxsw_sx_flood_init(struct mlxsw_sx *mlxsw_sx)
 	return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sgcr), sgcr_pl);
 }
 
-static int mlxsw_sx_init(void *priv, struct mlxsw_core *mlxsw_core,
+static int mlxsw_sx_init(struct mlxsw_core *mlxsw_core,
 			 const struct mlxsw_bus_info *mlxsw_bus_info)
 {
-	struct mlxsw_sx *mlxsw_sx = priv;
+	struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core);
 	int err;
 
 	mlxsw_sx->core = mlxsw_core;
@@ -1504,9 +1500,9 @@ err_event_register:
 	return err;
 }
 
-static void mlxsw_sx_fini(void *priv)
+static void mlxsw_sx_fini(struct mlxsw_core *mlxsw_core)
 {
-	struct mlxsw_sx *mlxsw_sx = priv;
+	struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core);
 
 	mlxsw_sx_traps_fini(mlxsw_sx);
 	mlxsw_sx_event_unregister(mlxsw_sx, MLXSW_TRAP_ID_PUDE);