Merge branch 'net-atlantic-QoS-implementation'

Igor Russkikh says:

====================
net: atlantic: QoS implementation

This patch series adds support for mqprio rate limiters and multi-TC:
 * max_rate is supported on both A1 and A2;
 * min_rate is supported on A2 only;

This is a joint work of Mark and Dmitry.

To implement this feature, a couple of rearrangements and code
improvements were done, in areas of TC/ring management, allocation
control, etc.

One of the problems we faced is conflicting ptp functionality, which
consumes a whole traffic class due to hardware limitations.
Patches below have a more detailed description on how PTP and multi-TC
co-exist right now.

v2:
 * accommodated review comments (-Wmissing-prototypes and
   -Wunused-but-set-variable findings);
 * added user notification in case of conflicting multi-TC<->PTP
   configuration;
 * added automatic PTP disabling, if a conflicting configuration is
   detected;
 * removed module param, which was used for PTP disabling in v1;

v1: https://patchwork.ozlabs.org/cover/1294380/
====================
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c

@@ -88,13 +88,13 @@ static const char aq_ethtool_stat_names[][ETH_GSTRING_LEN] = {
 	"InDroppedDma",
 };
 
-static const char aq_ethtool_queue_stat_names[][ETH_GSTRING_LEN] = {
-	"Queue[%d] InPackets",
-	"Queue[%d] OutPackets",
-	"Queue[%d] Restarts",
-	"Queue[%d] InJumboPackets",
-	"Queue[%d] InLroPackets",
-	"Queue[%d] InErrors",
+static const char * const aq_ethtool_queue_stat_names[] = {
+	"%sQueue[%d] InPackets",
+	"%sQueue[%d] OutPackets",
+	"%sQueue[%d] Restarts",
+	"%sQueue[%d] InJumboPackets",
+	"%sQueue[%d] InLroPackets",
+	"%sQueue[%d] InErrors",
 };
 
 #if IS_ENABLED(CONFIG_MACSEC)
@@ -166,7 +166,8 @@ static u32 aq_ethtool_n_stats(struct net_device *ndev)
 	struct aq_nic_s *nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(nic);
 	u32 n_stats = ARRAY_SIZE(aq_ethtool_stat_names) +
-		      ARRAY_SIZE(aq_ethtool_queue_stat_names) * cfg->vecs;
+		      ARRAY_SIZE(aq_ethtool_queue_stat_names) * cfg->vecs *
+			cfg->tcs;
 
 #if IS_ENABLED(CONFIG_MACSEC)
 	if (nic->macsec_cfg) {
@@ -223,7 +224,7 @@ static void aq_ethtool_get_drvinfo(struct net_device *ndev,
 static void aq_ethtool_get_strings(struct net_device *ndev,
 				   u32 stringset, u8 *data)
 {
-	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_s *nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg;
 	u8 *p = data;
 	int i, si;
@@ -231,24 +232,35 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 	int sa;
 #endif
 
-	cfg = aq_nic_get_cfg(aq_nic);
+	cfg = aq_nic_get_cfg(nic);
 
 	switch (stringset) {
-	case ETH_SS_STATS:
+	case ETH_SS_STATS: {
+		const int stat_cnt = ARRAY_SIZE(aq_ethtool_queue_stat_names);
+		char tc_string[8];
+		int tc;
+
+		memset(tc_string, 0, sizeof(tc_string));
 		memcpy(p, aq_ethtool_stat_names,
 		       sizeof(aq_ethtool_stat_names));
 		p = p + sizeof(aq_ethtool_stat_names);
-		for (i = 0; i < cfg->vecs; i++) {
-			for (si = 0;
-				si < ARRAY_SIZE(aq_ethtool_queue_stat_names);
-				si++) {
-				snprintf(p, ETH_GSTRING_LEN,
-					 aq_ethtool_queue_stat_names[si], i);
-				p += ETH_GSTRING_LEN;
+
+		for (tc = 0; tc < cfg->tcs; tc++) {
+			if (cfg->is_qos)
+				snprintf(tc_string, 8, "TC%d ", tc);
+
+			for (i = 0; i < cfg->vecs; i++) {
+				for (si = 0; si < stat_cnt; si++) {
+					snprintf(p, ETH_GSTRING_LEN,
+					     aq_ethtool_queue_stat_names[si],
+					     tc_string,
+					     AQ_NIC_CFG_TCVEC2RING(cfg, tc, i));
+					p += ETH_GSTRING_LEN;
+				}
 			}
 		}
 #if IS_ENABLED(CONFIG_MACSEC)
-		if (!aq_nic->macsec_cfg)
+		if (!nic->macsec_cfg)
 			break;
 
 		memcpy(p, aq_macsec_stat_names, sizeof(aq_macsec_stat_names));
@@ -256,7 +268,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 		for (i = 0; i < AQ_MACSEC_MAX_SC; i++) {
 			struct aq_macsec_txsc *aq_txsc;
 
-			if (!(test_bit(i, &aq_nic->macsec_cfg->txsc_idx_busy)))
+			if (!(test_bit(i, &nic->macsec_cfg->txsc_idx_busy)))
 				continue;
 
 			for (si = 0;
@@ -266,7 +278,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 					 aq_macsec_txsc_stat_names[si], i);
 				p += ETH_GSTRING_LEN;
 			}
-			aq_txsc = &aq_nic->macsec_cfg->aq_txsc[i];
+			aq_txsc = &nic->macsec_cfg->aq_txsc[i];
 			for (sa = 0; sa < MACSEC_NUM_AN; sa++) {
 				if (!(test_bit(sa, &aq_txsc->tx_sa_idx_busy)))
 					continue;
@@ -283,10 +295,10 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 		for (i = 0; i < AQ_MACSEC_MAX_SC; i++) {
 			struct aq_macsec_rxsc *aq_rxsc;
 
-			if (!(test_bit(i, &aq_nic->macsec_cfg->rxsc_idx_busy)))
+			if (!(test_bit(i, &nic->macsec_cfg->rxsc_idx_busy)))
 				continue;
 
-			aq_rxsc = &aq_nic->macsec_cfg->aq_rxsc[i];
+			aq_rxsc = &nic->macsec_cfg->aq_rxsc[i];
 			for (sa = 0; sa < MACSEC_NUM_AN; sa++) {
 				if (!(test_bit(sa, &aq_rxsc->rx_sa_idx_busy)))
 					continue;
@@ -302,6 +314,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 		}
 #endif
 		break;
+	}
 	case ETH_SS_PRIV_FLAGS:
 		memcpy(p, aq_ethtool_priv_flag_names,
 		       sizeof(aq_ethtool_priv_flag_names));
@@ -780,8 +793,6 @@ static int aq_set_ringparam(struct net_device *ndev,
 		dev_close(ndev);
 	}
 
-	aq_nic_free_vectors(aq_nic);
-
 	cfg->rxds = max(ring->rx_pending, hw_caps->rxds_min);
 	cfg->rxds = min(cfg->rxds, hw_caps->rxds_max);
 	cfg->rxds = ALIGN(cfg->rxds, AQ_HW_RXD_MULTIPLE);
@@ -790,15 +801,10 @@ static int aq_set_ringparam(struct net_device *ndev,
 	cfg->txds = min(cfg->txds, hw_caps->txds_max);
 	cfg->txds = ALIGN(cfg->txds, AQ_HW_TXD_MULTIPLE);
 
-	for (aq_nic->aq_vecs = 0; aq_nic->aq_vecs < cfg->vecs;
-	     aq_nic->aq_vecs++) {
-		aq_nic->aq_vec[aq_nic->aq_vecs] =
-		    aq_vec_alloc(aq_nic, aq_nic->aq_vecs, cfg);
-		if (unlikely(!aq_nic->aq_vec[aq_nic->aq_vecs])) {
-			err = -ENOMEM;
-			goto err_exit;
-		}
-	}
+	err = aq_nic_realloc_vectors(aq_nic);
+	if (err)
+		goto err_exit;
+
 	if (ndev_running)
 		err = dev_open(ndev, NULL);
 

drivers/net/ethernet/aquantia/atlantic/aq_filters.c

@@ -153,6 +153,8 @@ aq_check_approve_fvlan(struct aq_nic_s *aq_nic,
 		       struct aq_hw_rx_fltrs_s *rx_fltrs,
 		       struct ethtool_rx_flow_spec *fsp)
 {
+	struct aq_nic_cfg_s *cfg = &aq_nic->aq_nic_cfg;
+
 	if (fsp->location < AQ_RX_FIRST_LOC_FVLANID ||
 	    fsp->location > AQ_RX_LAST_LOC_FVLANID) {
 		netdev_err(aq_nic->ndev,
@@ -170,10 +172,10 @@ aq_check_approve_fvlan(struct aq_nic_s *aq_nic,
 		return -EINVAL;
 	}
 
-	if (fsp->ring_cookie > aq_nic->aq_nic_cfg.num_rss_queues) {
+	if (fsp->ring_cookie > cfg->num_rss_queues * cfg->tcs) {
 		netdev_err(aq_nic->ndev,
 			   "ethtool: queue number must be in range [0, %d]",
-			   aq_nic->aq_nic_cfg.num_rss_queues - 1);
+			   cfg->num_rss_queues * cfg->tcs - 1);
 		return -EINVAL;
 	}
 	return 0;
@@ -262,6 +264,7 @@ static bool __must_check
 aq_rule_is_not_correct(struct aq_nic_s *aq_nic,
 		       struct ethtool_rx_flow_spec *fsp)
 {
+	struct aq_nic_cfg_s *cfg = &aq_nic->aq_nic_cfg;
 	bool rule_is_not_correct = false;
 
 	if (!aq_nic) {
@@ -274,11 +277,11 @@ aq_rule_is_not_correct(struct aq_nic_s *aq_nic,
 	} else if (aq_check_filter(aq_nic, fsp)) {
 		rule_is_not_correct = true;
 	} else if (fsp->ring_cookie != RX_CLS_FLOW_DISC) {
-		if (fsp->ring_cookie >= aq_nic->aq_nic_cfg.num_rss_queues) {
+		if (fsp->ring_cookie >= cfg->num_rss_queues * cfg->tcs) {
 			netdev_err(aq_nic->ndev,
 				   "ethtool: The specified action is invalid.\n"
 				   "Maximum allowable value action is %u.\n",
-				   aq_nic->aq_nic_cfg.num_rss_queues - 1);
+				   cfg->num_rss_queues * cfg->tcs - 1);
 			rule_is_not_correct = true;
 		}
 	}

drivers/net/ethernet/aquantia/atlantic/aq_hw.h

@@ -18,6 +18,12 @@
 #define AQ_HW_MAC_COUNTER_HZ   312500000ll
 #define AQ_HW_PHY_COUNTER_HZ   160000000ll
 
+enum aq_tc_mode {
+	AQ_TC_MODE_INVALID = -1,
+	AQ_TC_MODE_8TCS,
+	AQ_TC_MODE_4TCS,
+};
+
 #define AQ_RX_FIRST_LOC_FVLANID     0U
 #define AQ_RX_LAST_LOC_FVLANID	   15U
 #define AQ_RX_FIRST_LOC_FETHERT    16U
@@ -29,6 +35,9 @@
 			(AQ_RX_LAST_LOC_FVLANID - AQ_RX_FIRST_LOC_FVLANID + 1U)
 #define AQ_RX_QUEUE_NOT_ASSIGNED   0xFFU
 
+/* Used for rate to Mbps conversion */
+#define AQ_MBPS_DIVISOR         125000 /* 1000000 / 8 */
+
 /* NIC H/W capabilities */
 struct aq_hw_caps_s {
 	u64 hw_features;
@@ -46,7 +55,7 @@ struct aq_hw_caps_s {
 	u32 mac_regs_count;
 	u32 hw_alive_check_addr;
 	u8 msix_irqs;
-	u8 tcs;
+	u8 tcs_max;
 	u8 rxd_alignment;
 	u8 rxd_size;
 	u8 txd_alignment;
@@ -118,8 +127,11 @@ struct aq_stats_s {
 #define AQ_HW_TXD_MULTIPLE 8U
 #define AQ_HW_RXD_MULTIPLE 8U
 
+#define AQ_HW_QUEUES_MAX                32U
 #define AQ_HW_MULTICAST_ADDRESS_MAX     32U
 
+#define AQ_HW_PTP_TC                    2U
+
 #define AQ_HW_LED_BLINK    0x2U
 #define AQ_HW_LED_DEFAULT  0x0U
 
@@ -268,6 +280,8 @@ struct aq_hw_ops {
 	int (*hw_rss_hash_set)(struct aq_hw_s *self,
 			       struct aq_rss_parameters *rss_params);
 
+	int (*hw_tc_rate_limit_set)(struct aq_hw_s *self);
+
 	int (*hw_get_regs)(struct aq_hw_s *self,
 			   const struct aq_hw_caps_s *aq_hw_caps,
 			   u32 *regs_buff);
@@ -279,10 +293,6 @@ struct aq_hw_ops {
 	int (*hw_set_offload)(struct aq_hw_s *self,
 			      struct aq_nic_cfg_s *aq_nic_cfg);
 
-	int (*hw_tx_tc_mode_get)(struct aq_hw_s *self, u32 *tc_mode);
-
-	int (*hw_rx_tc_mode_get)(struct aq_hw_s *self, u32 *tc_mode);
-
 	int (*hw_ring_hwts_rx_fill)(struct aq_hw_s *self,
 				    struct aq_ring_s *aq_ring);
 

drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c

@@ -79,3 +79,29 @@ int aq_hw_err_from_flags(struct aq_hw_s *hw)
 err_exit:
 	return err;
 }
+
+int aq_hw_num_tcs(struct aq_hw_s *hw)
+{
+	switch (hw->aq_nic_cfg->tc_mode) {
+	case AQ_TC_MODE_8TCS:
+		return 8;
+	case AQ_TC_MODE_4TCS:
+		return 4;
+	default:
+		break;
+	}
+
+	return 1;
+}
+
+int aq_hw_q_per_tc(struct aq_hw_s *hw)
+{
+	switch (hw->aq_nic_cfg->tc_mode) {
+	case AQ_TC_MODE_8TCS:
+		return 4;
+	case AQ_TC_MODE_4TCS:
+		return 8;
+	default:
+		return 4;
+	}
+}

drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h

@@ -34,5 +34,7 @@ u32 aq_hw_read_reg(struct aq_hw_s *hw, u32 reg);
 void aq_hw_write_reg(struct aq_hw_s *hw, u32 reg, u32 value);
 u64 aq_hw_read_reg64(struct aq_hw_s *hw, u32 reg);
 int aq_hw_err_from_flags(struct aq_hw_s *hw);
+int aq_hw_num_tcs(struct aq_hw_s *hw);
+int aq_hw_q_per_tc(struct aq_hw_s *hw);
 
 #endif /* AQ_HW_UTILS_H */

drivers/net/ethernet/aquantia/atlantic/aq_macsec.c

@@ -478,7 +478,7 @@ static int aq_mdo_add_secy(struct macsec_context *ctx)
 
 	set_bit(txsc_idx, &cfg->txsc_idx_busy);
 
-	return 0;
+	return ret;
 }
 
 static int aq_mdo_upd_secy(struct macsec_context *ctx)

drivers/net/ethernet/aquantia/atlantic/aq_main.c

@@ -12,11 +12,13 @@
 #include "aq_ethtool.h"
 #include "aq_ptp.h"
 #include "aq_filters.h"
+#include "aq_hw_utils.h"
 
 #include <linux/netdevice.h>
 #include <linux/module.h>
 #include <linux/ip.h>
 #include <linux/udp.h>
+#include <net/pkt_cls.h>
 
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR(AQ_CFG_DRV_AUTHOR);
@@ -38,7 +40,7 @@ struct net_device *aq_ndev_alloc(void)
 	struct net_device *ndev = NULL;
 	struct aq_nic_s *aq_nic = NULL;
 
-	ndev = alloc_etherdev_mq(sizeof(struct aq_nic_s), AQ_CFG_VECS_MAX);
+	ndev = alloc_etherdev_mq(sizeof(struct aq_nic_s), AQ_HW_QUEUES_MAX);
 	if (!ndev)
 		return NULL;
 
@@ -330,6 +332,73 @@ static int aq_ndo_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto,
 	return 0;
 }
 
+static int aq_validate_mqprio_opt(struct aq_nic_s *self,
+				  struct tc_mqprio_qopt_offload *mqprio,
+				  const unsigned int num_tc)
+{
+	const bool has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
+	struct aq_nic_cfg_s *aq_nic_cfg = aq_nic_get_cfg(self);
+	const unsigned int tcs_max = min_t(u8, aq_nic_cfg->aq_hw_caps->tcs_max,
+					   AQ_CFG_TCS_MAX);
+
+	if (num_tc > tcs_max) {
+		netdev_err(self->ndev, "Too many TCs requested\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (num_tc != 0 && !is_power_of_2(num_tc)) {
+		netdev_err(self->ndev, "TC count should be power of 2\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (has_min_rate && !ATL_HW_IS_CHIP_FEATURE(self->aq_hw, ANTIGUA)) {
+		netdev_err(self->ndev, "Min tx rate is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int aq_ndo_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			   void *type_data)
+{
+	struct tc_mqprio_qopt_offload *mqprio = type_data;
+	struct aq_nic_s *aq_nic = netdev_priv(dev);
+	bool has_min_rate;
+	bool has_max_rate;
+	int err;
+	int i;
+
+	if (type != TC_SETUP_QDISC_MQPRIO)
+		return -EOPNOTSUPP;
+
+	has_min_rate = !!(mqprio->flags & TC_MQPRIO_F_MIN_RATE);
+	has_max_rate = !!(mqprio->flags & TC_MQPRIO_F_MAX_RATE);
+
+	err = aq_validate_mqprio_opt(aq_nic, mqprio, mqprio->qopt.num_tc);
+	if (err)
+		return err;
+
+	for (i = 0; i < mqprio->qopt.num_tc; i++) {
+		if (has_max_rate) {
+			u64 max_rate = mqprio->max_rate[i];
+
+			do_div(max_rate, AQ_MBPS_DIVISOR);
+			aq_nic_setup_tc_max_rate(aq_nic, i, (u32)max_rate);
+		}
+
+		if (has_min_rate) {
+			u64 min_rate = mqprio->min_rate[i];
+
+			do_div(min_rate, AQ_MBPS_DIVISOR);
+			aq_nic_setup_tc_min_rate(aq_nic, i, (u32)min_rate);
+		}
+	}
+
+	return aq_nic_setup_tc_mqprio(aq_nic, mqprio->qopt.num_tc,
+				      mqprio->qopt.prio_tc_map);
+}
+
 static const struct net_device_ops aq_ndev_ops = {
 	.ndo_open = aq_ndev_open,
 	.ndo_stop = aq_ndev_close,
@@ -341,6 +410,7 @@ static const struct net_device_ops aq_ndev_ops = {
 	.ndo_do_ioctl = aq_ndev_ioctl,
 	.ndo_vlan_rx_add_vid = aq_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = aq_ndo_vlan_rx_kill_vid,
+	.ndo_setup_tc = aq_ndo_setup_tc,
 };
 
 static int __init aq_ndev_init_module(void)

drivers/net/ethernet/aquantia/atlantic/aq_nic.c

@@ -26,6 +26,7 @@
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <net/ip.h>
+#include <net/pkt_cls.h>
 
 static unsigned int aq_itr = AQ_CFG_INTERRUPT_MODERATION_AUTO;
 module_param_named(aq_itr, aq_itr, uint, 0644);
@@ -64,10 +65,38 @@ static void aq_nic_rss_init(struct aq_nic_s *self, unsigned int num_rss_queues)
 		rss_params->indirection_table[i] = i & (num_rss_queues - 1);
 }
 
+/* Recalculate the number of vectors */
+static void aq_nic_cfg_update_num_vecs(struct aq_nic_s *self)
+{
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+
+	cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
+	cfg->vecs = min(cfg->vecs, num_online_cpus());
+	if (self->irqvecs > AQ_HW_SERVICE_IRQS)
+		cfg->vecs = min(cfg->vecs, self->irqvecs - AQ_HW_SERVICE_IRQS);
+	/* cfg->vecs should be power of 2 for RSS */
+	cfg->vecs = rounddown_pow_of_two(cfg->vecs);
+
+	if (ATL_HW_IS_CHIP_FEATURE(self->aq_hw, ANTIGUA)) {
+		if (cfg->tcs > 2)
+			cfg->vecs = min(cfg->vecs, 4U);
+	}
+
+	if (cfg->vecs <= 4)
+		cfg->tc_mode = AQ_TC_MODE_8TCS;
+	else
+		cfg->tc_mode = AQ_TC_MODE_4TCS;
+
+	/*rss rings */
+	cfg->num_rss_queues = min(cfg->vecs, AQ_CFG_NUM_RSS_QUEUES_DEF);
+	aq_nic_rss_init(self, cfg->num_rss_queues);
+}
+
 /* Checks hw_caps and 'corrects' aq_nic_cfg in runtime */
 void aq_nic_cfg_start(struct aq_nic_s *self)
 {
 	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+	int i;
 
 	cfg->tcs = AQ_CFG_TCS_DEF;
 
@@ -79,7 +108,6 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 
 	cfg->rxpageorder = AQ_CFG_RX_PAGEORDER;
 	cfg->is_rss = AQ_CFG_IS_RSS_DEF;
-	cfg->num_rss_queues = AQ_CFG_NUM_RSS_QUEUES_DEF;
 	cfg->aq_rss.base_cpu_number = AQ_CFG_RSS_BASE_CPU_NUM_DEF;
 	cfg->fc.req = AQ_CFG_FC_MODE;
 	cfg->wol = AQ_CFG_WOL_MODES;
@@ -89,29 +117,13 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 	cfg->is_autoneg = AQ_CFG_IS_AUTONEG_DEF;
 
 	cfg->is_lro = AQ_CFG_IS_LRO_DEF;
+	cfg->is_ptp = true;
 
 	/*descriptors */
 	cfg->rxds = min(cfg->aq_hw_caps->rxds_max, AQ_CFG_RXDS_DEF);
 	cfg->txds = min(cfg->aq_hw_caps->txds_max, AQ_CFG_TXDS_DEF);
 
-	/*rss rings */
-	cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
-	cfg->vecs = min(cfg->vecs, num_online_cpus());
-	if (self->irqvecs > AQ_HW_SERVICE_IRQS)
-		cfg->vecs = min(cfg->vecs, self->irqvecs - AQ_HW_SERVICE_IRQS);
-	/* cfg->vecs should be power of 2 for RSS */
-	if (cfg->vecs >= 8U)
-		cfg->vecs = 8U;
-	else if (cfg->vecs >= 4U)
-		cfg->vecs = 4U;
-	else if (cfg->vecs >= 2U)
-		cfg->vecs = 2U;
-	else
-		cfg->vecs = 1U;
-
-	cfg->num_rss_queues = min(cfg->vecs, AQ_CFG_NUM_RSS_QUEUES_DEF);
-
-	aq_nic_rss_init(self, cfg->num_rss_queues);
+	aq_nic_cfg_update_num_vecs(self);
 
 	cfg->irq_type = aq_pci_func_get_irq_type(self);
 
@@ -136,6 +148,9 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 	cfg->is_vlan_rx_strip = !!(cfg->features & NETIF_F_HW_VLAN_CTAG_RX);
 	cfg->is_vlan_tx_insert = !!(cfg->features & NETIF_F_HW_VLAN_CTAG_TX);
 	cfg->is_vlan_force_promisc = true;
+
+	for (i = 0; i < sizeof(cfg->prio_tc_map); i++)
+		cfg->prio_tc_map[i] = cfg->tcs * i / 8;
 }
 
 static int aq_nic_update_link_status(struct aq_nic_s *self)
@@ -181,6 +196,9 @@ static int aq_nic_update_link_status(struct aq_nic_s *self)
 #if IS_ENABLED(CONFIG_MACSEC)
 		aq_macsec_enable(self);
 #endif
+		if (self->aq_hw_ops->hw_tc_rate_limit_set)
+			self->aq_hw_ops->hw_tc_rate_limit_set(self->aq_hw);
+
 		netif_tx_wake_all_queues(self->ndev);
 	}
 	if (netif_carrier_ok(self->ndev) && !self->link_status.mbps) {
@@ -399,21 +417,29 @@ int aq_nic_init(struct aq_nic_s *self)
 		err = aq_phy_init(self->aq_hw);
 	}
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
+	for (i = 0U; i < self->aq_vecs; i++) {
+		aq_vec = self->aq_vec[i];
+		err = aq_vec_ring_alloc(aq_vec, self, i,
+					aq_nic_get_cfg(self));
+		if (err)
+			goto err_exit;
+
 		aq_vec_init(aq_vec, self->aq_hw_ops, self->aq_hw);
+	}
 
-	err = aq_ptp_init(self, self->irqvecs - 1);
-	if (err < 0)
-		goto err_exit;
+	if (aq_nic_get_cfg(self)->is_ptp) {
+		err = aq_ptp_init(self, self->irqvecs - 1);
+		if (err < 0)
+			goto err_exit;
 
-	err = aq_ptp_ring_alloc(self);
-	if (err < 0)
-		goto err_exit;
+		err = aq_ptp_ring_alloc(self);
+		if (err < 0)
+			goto err_exit;
 
-	err = aq_ptp_ring_init(self);
-	if (err < 0)
-		goto err_exit;
+		err = aq_ptp_ring_init(self);
+		if (err < 0)
+			goto err_exit;
+	}
 
 	netif_carrier_off(self->ndev);
 
@@ -424,9 +450,12 @@ int aq_nic_init(struct aq_nic_s *self)
 int aq_nic_start(struct aq_nic_s *self)
 {
 	struct aq_vec_s *aq_vec = NULL;
+	struct aq_nic_cfg_s *cfg;
 	unsigned int i = 0U;
 	int err = 0;
 
+	cfg = aq_nic_get_cfg(self);
+
 	err = self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
 						     self->mc_list.ar,
 						     self->mc_list.count);
@@ -464,7 +493,7 @@ int aq_nic_start(struct aq_nic_s *self)
 	timer_setup(&self->service_timer, aq_nic_service_timer_cb, 0);
 	aq_nic_service_timer_cb(&self->service_timer);
 
-	if (self->aq_nic_cfg.is_polling) {
+	if (cfg->is_polling) {
 		timer_setup(&self->polling_timer, aq_nic_polling_timer_cb, 0);
 		mod_timer(&self->polling_timer, jiffies +
 			  AQ_CFG_POLLING_TIMER_INTERVAL);
@@ -482,16 +511,16 @@ int aq_nic_start(struct aq_nic_s *self)
 		if (err < 0)
 			goto err_exit;
 
-		if (self->aq_nic_cfg.link_irq_vec) {
+		if (cfg->link_irq_vec) {
 			int irqvec = pci_irq_vector(self->pdev,
-						   self->aq_nic_cfg.link_irq_vec);
+						    cfg->link_irq_vec);
 			err = request_threaded_irq(irqvec, NULL,
 						   aq_linkstate_threaded_isr,
 						   IRQF_SHARED | IRQF_ONESHOT,
 						   self->ndev->name, self);
 			if (err < 0)
 				goto err_exit;
-			self->msix_entry_mask |= (1 << self->aq_nic_cfg.link_irq_vec);
+			self->msix_entry_mask |= (1 << cfg->link_irq_vec);
 		}
 
 		err = self->aq_hw_ops->hw_irq_enable(self->aq_hw,
@@ -500,14 +529,21 @@ int aq_nic_start(struct aq_nic_s *self)
 			goto err_exit;
 	}
 
-	err = netif_set_real_num_tx_queues(self->ndev, self->aq_vecs);
+	err = netif_set_real_num_tx_queues(self->ndev,
+					   self->aq_vecs * cfg->tcs);
 	if (err < 0)
 		goto err_exit;
 
-	err = netif_set_real_num_rx_queues(self->ndev, self->aq_vecs);
+	err = netif_set_real_num_rx_queues(self->ndev,
+					   self->aq_vecs * cfg->tcs);
 	if (err < 0)
 		goto err_exit;
 
+	for (i = 0; i < cfg->tcs; i++) {
+		u16 offset = self->aq_vecs * i;
+
+		netdev_set_tc_queue(self->ndev, i, self->aq_vecs, offset);
+	}
 	netif_tx_start_all_queues(self->ndev);
 
 err_exit:
@@ -518,6 +554,8 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb,
 			    struct aq_ring_s *ring)
 {
 	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(self);
+	struct device *dev = aq_nic_get_dev(self);
 	struct aq_ring_buff_s *first = NULL;
 	u8 ipver = ip_hdr(skb)->version;
 	struct aq_ring_buff_s *dx_buff;
@@ -559,7 +597,7 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb,
 		need_context_tag = true;
 	}
 
-	if (self->aq_nic_cfg.is_vlan_tx_insert && skb_vlan_tag_present(skb)) {
+	if (cfg->is_vlan_tx_insert && skb_vlan_tag_present(skb)) {
 		dx_buff->vlan_tx_tag = skb_vlan_tag_get(skb);
 		dx_buff->len_pkt = skb->len;
 		dx_buff->is_vlan = 1U;
@@ -574,12 +612,12 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb,
 	}
 
 	dx_buff->len = skb_headlen(skb);
-	dx_buff->pa = dma_map_single(aq_nic_get_dev(self),
+	dx_buff->pa = dma_map_single(dev,
 				     skb->data,
 				     dx_buff->len,
 				     DMA_TO_DEVICE);
 
-	if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) {
+	if (unlikely(dma_mapping_error(dev, dx_buff->pa))) {
 		ret = 0;
 		goto exit;
 	}
@@ -611,13 +649,13 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb,
 			else
 				buff_size = frag_len;
 
-			frag_pa = skb_frag_dma_map(aq_nic_get_dev(self),
+			frag_pa = skb_frag_dma_map(dev,
 						   frag,
 						   buff_offset,
 						   buff_size,
 						   DMA_TO_DEVICE);
 
-			if (unlikely(dma_mapping_error(aq_nic_get_dev(self),
+			if (unlikely(dma_mapping_error(dev,
 						       frag_pa)))
 				goto mapping_error;
 
@@ -651,12 +689,12 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb,
 		if (!(dx_buff->is_gso_tcp || dx_buff->is_gso_udp) &&
 		    !dx_buff->is_vlan && dx_buff->pa) {
 			if (unlikely(dx_buff->is_sop)) {
-				dma_unmap_single(aq_nic_get_dev(self),
+				dma_unmap_single(dev,
 						 dx_buff->pa,
 						 dx_buff->len,
 						 DMA_TO_DEVICE);
 			} else {
-				dma_unmap_page(aq_nic_get_dev(self),
+				dma_unmap_page(dev,
 					       dx_buff->pa,
 					       dx_buff->len,
 					       DMA_TO_DEVICE);
@@ -670,15 +708,16 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb,
 
 int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 {
-	unsigned int vec = skb->queue_mapping % self->aq_nic_cfg.vecs;
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(self);
+	unsigned int vec = skb->queue_mapping % cfg->vecs;
+	unsigned int tc = skb->queue_mapping / cfg->vecs;
 	struct aq_ring_s *ring = NULL;
 	unsigned int frags = 0U;
 	int err = NETDEV_TX_OK;
-	unsigned int tc = 0U;
 
 	frags = skb_shinfo(skb)->nr_frags + 1;
 
-	ring = self->aq_ring_tx[AQ_NIC_TCVEC2RING(self, tc, vec)];
+	ring = self->aq_ring_tx[AQ_NIC_CFG_TCVEC2RING(cfg, tc, vec)];
 
 	if (frags > AQ_CFG_SKB_FRAGS_MAX) {
 		dev_kfree_skb_any(skb);
@@ -687,13 +726,14 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 
 	aq_ring_update_queue_state(ring);
 
-	if (self->aq_nic_cfg.priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET)) {
+	if (cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET)) {
 		err = NETDEV_TX_BUSY;
 		goto err_exit;
 	}
 
 	/* Above status update may stop the queue. Check this. */
-	if (__netif_subqueue_stopped(self->ndev, ring->idx)) {
+	if (__netif_subqueue_stopped(self->ndev,
+				     AQ_NIC_RING2QMAP(self, ring->idx))) {
 		err = NETDEV_TX_BUSY;
 		goto err_exit;
 	}
@@ -823,6 +863,7 @@ u64 *aq_nic_get_stats(struct aq_nic_s *self, u64 *data)
 	struct aq_stats_s *stats;
 	unsigned int count = 0U;
 	unsigned int i = 0U;
+	unsigned int tc;
 
 	if (self->aq_fw_ops->update_stats) {
 		mutex_lock(&self->fwreq_mutex);
@@ -861,10 +902,13 @@ u64 *aq_nic_get_stats(struct aq_nic_s *self, u64 *data)
 
 	data += i;
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		aq_vec && self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) {
-		data += count;
-		aq_vec_get_sw_stats(aq_vec, data, &count);
+	for (tc = 0U; tc < self->aq_nic_cfg.tcs; tc++) {
+		for (i = 0U, aq_vec = self->aq_vec[0];
+		     aq_vec && self->aq_vecs > i;
+		     ++i, aq_vec = self->aq_vec[i]) {
+			data += count;
+			aq_vec_get_sw_stats(aq_vec, tc, data, &count);
+		}
 	}
 
 	data += count;
@@ -1145,9 +1189,11 @@ void aq_nic_deinit(struct aq_nic_s *self, bool link_down)
 	if (!self)
 		goto err_exit;
 
-	for (i = 0U, aq_vec = self->aq_vec[0];
-		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
+	for (i = 0U; i < self->aq_vecs; i++) {
+		aq_vec = self->aq_vec[i];
 		aq_vec_deinit(aq_vec);
+		aq_vec_ring_free(aq_vec);
+	}
 
 	aq_ptp_unregister(self);
 	aq_ptp_ring_deinit(self);
@@ -1180,6 +1226,22 @@ void aq_nic_free_vectors(struct aq_nic_s *self)
 err_exit:;
 }
 
+int aq_nic_realloc_vectors(struct aq_nic_s *self)
+{
+	struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(self);
+
+	aq_nic_free_vectors(self);
+
+	for (self->aq_vecs = 0; self->aq_vecs < cfg->vecs; self->aq_vecs++) {
+		self->aq_vec[self->aq_vecs] = aq_vec_alloc(self, self->aq_vecs,
+							   cfg);
+		if (unlikely(!self->aq_vec[self->aq_vecs]))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 void aq_nic_shutdown(struct aq_nic_s *self)
 {
 	int err = 0;
@@ -1245,3 +1307,98 @@ void aq_nic_release_filter(struct aq_nic_s *self, enum aq_rx_filter_type type,
 		break;
 	}
 }
+
+int aq_nic_setup_tc_mqprio(struct aq_nic_s *self, u32 tcs, u8 *prio_tc_map)
+{
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+	const unsigned int prev_vecs = cfg->vecs;
+	bool ndev_running;
+	int err = 0;
+	int i;
+
+	/* if already the same configuration or
+	 * disable request (tcs is 0) and we already is disabled
+	 */
+	if (tcs == cfg->tcs || (tcs == 0 && !cfg->is_qos))
+		return 0;
+
+	ndev_running = netif_running(self->ndev);
+	if (ndev_running)
+		dev_close(self->ndev);
+
+	cfg->tcs = tcs;
+	if (cfg->tcs == 0)
+		cfg->tcs = 1;
+	if (prio_tc_map)
+		memcpy(cfg->prio_tc_map, prio_tc_map, sizeof(cfg->prio_tc_map));
+	else
+		for (i = 0; i < sizeof(cfg->prio_tc_map); i++)
+			cfg->prio_tc_map[i] = cfg->tcs * i / 8;
+
+	cfg->is_qos = (tcs != 0 ? true : false);
+	cfg->is_ptp = (cfg->tcs <= AQ_HW_PTP_TC);
+	if (!cfg->is_ptp)
+		netdev_warn(self->ndev, "%s\n",
+			    "PTP is auto disabled due to requested TC count.");
+
+	netdev_set_num_tc(self->ndev, cfg->tcs);
+
+	/* Changing the number of TCs might change the number of vectors */
+	aq_nic_cfg_update_num_vecs(self);
+	if (prev_vecs != cfg->vecs) {
+		err = aq_nic_realloc_vectors(self);
+		if (err)
+			goto err_exit;
+	}
+
+	if (ndev_running)
+		err = dev_open(self->ndev, NULL);
+
+err_exit:
+	return err;
+}
+
+int aq_nic_setup_tc_max_rate(struct aq_nic_s *self, const unsigned int tc,
+			     const u32 max_rate)
+{
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+
+	if (tc >= AQ_CFG_TCS_MAX)
+		return -EINVAL;
+
+	if (max_rate && max_rate < 10) {
+		netdev_warn(self->ndev,
+			"Setting %s to the minimum usable value of %dMbps.\n",
+			"max rate", 10);
+		cfg->tc_max_rate[tc] = 10;
+	} else {
+		cfg->tc_max_rate[tc] = max_rate;
+	}
+
+	return 0;
+}
+
+int aq_nic_setup_tc_min_rate(struct aq_nic_s *self, const unsigned int tc,
+			     const u32 min_rate)
+{
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+
+	if (tc >= AQ_CFG_TCS_MAX)
+		return -EINVAL;
+
+	if (min_rate)
+		set_bit(tc, &cfg->tc_min_rate_msk);
+	else
+		clear_bit(tc, &cfg->tc_min_rate_msk);
+
+	if (min_rate && min_rate < 20) {
+		netdev_warn(self->ndev,
+			"Setting %s to the minimum usable value of %dMbps.\n",
+			"min rate", 20);
+		cfg->tc_min_rate[tc] = 20;
+	} else {
+		cfg->tc_min_rate[tc] = min_rate;
+	}
+
+	return 0;
+}

drivers/net/ethernet/aquantia/atlantic/aq_nic.h

@@ -59,8 +59,15 @@ struct aq_nic_cfg_s {
 	bool is_polling;
 	bool is_rss;
 	bool is_lro;
+	bool is_qos;
+	bool is_ptp;
+	enum aq_tc_mode tc_mode;
 	u32 priv_flags;
 	u8  tcs;
+	u8 prio_tc_map[8];
+	u32 tc_max_rate[AQ_CFG_TCS_MAX];
+	unsigned long tc_min_rate_msk;
+	u32 tc_min_rate[AQ_CFG_TCS_MAX];
 	struct aq_rss_parameters aq_rss;
 	u32 eee_speeds;
 };
@@ -77,8 +84,16 @@ struct aq_nic_cfg_s {
 #define AQ_NIC_WOL_MODES        (WAKE_MAGIC |\
 				 WAKE_PHY)
 
-#define AQ_NIC_TCVEC2RING(_NIC_, _TC_, _VEC_) \
-	((_TC_) * AQ_CFG_TCS_MAX + (_VEC_))
+#define AQ_NIC_CFG_RING_PER_TC(_NIC_CFG_) \
+	(((_NIC_CFG_)->tc_mode == AQ_TC_MODE_4TCS) ? 8 : 4)
+
+#define AQ_NIC_CFG_TCVEC2RING(_NIC_CFG_, _TC_, _VEC_) \
+	((_TC_) * AQ_NIC_CFG_RING_PER_TC(_NIC_CFG_) + (_VEC_))
+
+#define AQ_NIC_RING2QMAP(_NIC_, _ID_) \
+	((_ID_) / AQ_NIC_CFG_RING_PER_TC(&(_NIC_)->aq_nic_cfg) * \
+		(_NIC_)->aq_vecs + \
+	((_ID_) % AQ_NIC_CFG_RING_PER_TC(&(_NIC_)->aq_nic_cfg)))
 
 struct aq_hw_rx_fl2 {
 	struct aq_rx_filter_vlan aq_vlans[AQ_VLAN_MAX_FILTERS];
@@ -104,7 +119,7 @@ struct aq_nic_s {
 	atomic_t flags;
 	u32 msg_enable;
 	struct aq_vec_s *aq_vec[AQ_CFG_VECS_MAX];
-	struct aq_ring_s *aq_ring_tx[AQ_CFG_VECS_MAX * AQ_CFG_TCS_MAX];
+	struct aq_ring_s *aq_ring_tx[AQ_HW_QUEUES_MAX];
 	struct aq_hw_s *aq_hw;
 	struct net_device *ndev;
 	unsigned int aq_vecs;
@@ -164,6 +179,7 @@ void aq_nic_deinit(struct aq_nic_s *self, bool link_down);
 void aq_nic_set_power(struct aq_nic_s *self);
 void aq_nic_free_hot_resources(struct aq_nic_s *self);
 void aq_nic_free_vectors(struct aq_nic_s *self);
+int aq_nic_realloc_vectors(struct aq_nic_s *self);
 int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu);
 int aq_nic_set_mac(struct aq_nic_s *self, struct net_device *ndev);
 int aq_nic_set_packet_filter(struct aq_nic_s *self, unsigned int flags);
@@ -181,4 +197,9 @@ void aq_nic_shutdown(struct aq_nic_s *self);
 u8 aq_nic_reserve_filter(struct aq_nic_s *self, enum aq_rx_filter_type type);
 void aq_nic_release_filter(struct aq_nic_s *self, enum aq_rx_filter_type type,
 			   u32 location);
+int aq_nic_setup_tc_mqprio(struct aq_nic_s *self, u32 tcs, u8 *prio_tc_map);
+int aq_nic_setup_tc_max_rate(struct aq_nic_s *self, const unsigned int tc,
+			     const u32 max_rate);
+int aq_nic_setup_tc_min_rate(struct aq_nic_s *self, const unsigned int tc,
+			     const u32 min_rate);
 #endif /* AQ_NIC_H */

drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c

@@ -431,6 +431,9 @@ static int atl_resume_common(struct device *dev, bool deep)
 	netif_tx_start_all_queues(nic->ndev);
 
 err_exit:
+	if (ret < 0)
+		aq_nic_deinit(nic, true);
+
 	rtnl_unlock();
 
 	return ret;

drivers/net/ethernet/aquantia/atlantic/aq_ptp.c

@@ -945,26 +945,29 @@ void aq_ptp_ring_deinit(struct aq_nic_s *aq_nic)
 #define PTP_4TC_RING_IDX            16
 #define PTP_HWST_RING_IDX           31
 
+/* Index must be 8 (8 TCs) or 16 (4 TCs).
+ * It depends on Traffic Class mode.
+ */
+static unsigned int ptp_ring_idx(const enum aq_tc_mode tc_mode)
+{
+	if (tc_mode == AQ_TC_MODE_8TCS)
+		return PTP_8TC_RING_IDX;
+
+	return PTP_4TC_RING_IDX;
+}
+
 int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic)
 {
 	struct aq_ptp_s *aq_ptp = aq_nic->aq_ptp;
 	unsigned int tx_ring_idx, rx_ring_idx;
 	struct aq_ring_s *hwts;
-	u32 tx_tc_mode, rx_tc_mode;
 	struct aq_ring_s *ring;
 	int err;
 
 	if (!aq_ptp)
 		return 0;
 
-	/* Index must to be 8 (8 TCs) or 16 (4 TCs).
-	 * It depends from Traffic Class mode.
-	 */
-	aq_nic->aq_hw_ops->hw_tx_tc_mode_get(aq_nic->aq_hw, &tx_tc_mode);
-	if (tx_tc_mode == 0)
-		tx_ring_idx = PTP_8TC_RING_IDX;
-	else
-		tx_ring_idx = PTP_4TC_RING_IDX;
+	tx_ring_idx = ptp_ring_idx(aq_nic->aq_nic_cfg.tc_mode);
 
 	ring = aq_ring_tx_alloc(&aq_ptp->ptp_tx, aq_nic,
 				tx_ring_idx, &aq_nic->aq_nic_cfg);
@@ -973,11 +976,7 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic)
 		goto err_exit;
 	}
 
-	aq_nic->aq_hw_ops->hw_rx_tc_mode_get(aq_nic->aq_hw, &rx_tc_mode);
-	if (rx_tc_mode == 0)
-		rx_ring_idx = PTP_8TC_RING_IDX;
-	else
-		rx_ring_idx = PTP_4TC_RING_IDX;
+	rx_ring_idx = ptp_ring_idx(aq_nic->aq_nic_cfg.tc_mode);
 
 	ring = aq_ring_rx_alloc(&aq_ptp->ptp_rx, aq_nic,
 				rx_ring_idx, &aq_nic->aq_nic_cfg);

drivers/net/ethernet/aquantia/atlantic/aq_ring.c

@@ -232,8 +232,11 @@ void aq_ring_queue_wake(struct aq_ring_s *ring)
 {
 	struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic);
 
-	if (__netif_subqueue_stopped(ndev, ring->idx)) {
-		netif_wake_subqueue(ndev, ring->idx);
+	if (__netif_subqueue_stopped(ndev,
+				     AQ_NIC_RING2QMAP(ring->aq_nic,
+						      ring->idx))) {
+		netif_wake_subqueue(ndev,
+				    AQ_NIC_RING2QMAP(ring->aq_nic, ring->idx));
 		ring->stats.tx.queue_restarts++;
 	}
 }
@@ -242,8 +245,11 @@ void aq_ring_queue_stop(struct aq_ring_s *ring)
 {
 	struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic);
 
-	if (!__netif_subqueue_stopped(ndev, ring->idx))
-		netif_stop_subqueue(ndev, ring->idx);
+	if (!__netif_subqueue_stopped(ndev,
+				      AQ_NIC_RING2QMAP(ring->aq_nic,
+						       ring->idx)))
+		netif_stop_subqueue(ndev,
+				    AQ_NIC_RING2QMAP(ring->aq_nic, ring->idx));
 }
 
 bool aq_ring_tx_clean(struct aq_ring_s *self)
@@ -466,7 +472,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 			     buff->is_hash_l4 ? PKT_HASH_TYPE_L4 :
 			     PKT_HASH_TYPE_NONE);
 		/* Send all PTP traffic to 0 queue */
-		skb_record_rx_queue(skb, is_ptp_ring ? 0 : self->idx);
+		skb_record_rx_queue(skb,
+				    is_ptp_ring ? 0
+						: AQ_NIC_RING2QMAP(self->aq_nic,
+								   self->idx));
 
 		++self->stats.rx.packets;
 		self->stats.rx.bytes += skb->len;

drivers/net/ethernet/aquantia/atlantic/aq_vec.c

@@ -103,16 +103,11 @@ static int aq_vec_poll(struct napi_struct *napi, int budget)
 struct aq_vec_s *aq_vec_alloc(struct aq_nic_s *aq_nic, unsigned int idx,
 			      struct aq_nic_cfg_s *aq_nic_cfg)
 {
-	struct aq_ring_s *ring = NULL;
 	struct aq_vec_s *self = NULL;
-	unsigned int i = 0U;
-	int err = 0;
 
 	self = kzalloc(sizeof(*self), GFP_KERNEL);
-	if (!self) {
-		err = -ENOMEM;
+	if (!self)
 		goto err_exit;
-	}
 
 	self->aq_nic = aq_nic;
 	self->aq_ring_param.vec_idx = idx;
@@ -128,10 +123,20 @@ struct aq_vec_s *aq_vec_alloc(struct aq_nic_s *aq_nic, unsigned int idx,
 	netif_napi_add(aq_nic_get_ndev(aq_nic), &self->napi,
 		       aq_vec_poll, AQ_CFG_NAPI_WEIGHT);
 
+err_exit:
+	return self;
+}
+
+int aq_vec_ring_alloc(struct aq_vec_s *self, struct aq_nic_s *aq_nic,
+		      unsigned int idx, struct aq_nic_cfg_s *aq_nic_cfg)
+{
+	struct aq_ring_s *ring = NULL;
+	unsigned int i = 0U;
+	int err = 0;
+
 	for (i = 0; i < aq_nic_cfg->tcs; ++i) {
-		unsigned int idx_ring = AQ_NIC_TCVEC2RING(self->nic,
-						self->tx_rings,
-						self->aq_ring_param.vec_idx);
+		const unsigned int idx_ring = AQ_NIC_CFG_TCVEC2RING(aq_nic_cfg,
+								    i, idx);
 
 		ring = aq_ring_tx_alloc(&self->ring[i][AQ_VEC_TX_ID], aq_nic,
 					idx_ring, aq_nic_cfg);
@@ -156,11 +161,11 @@ struct aq_vec_s *aq_vec_alloc(struct aq_nic_s *aq_nic, unsigned int idx,
 
 err_exit:
 	if (err < 0) {
-		aq_vec_free(self);
+		aq_vec_ring_free(self);
 		self = NULL;
 	}
 
-	return self;
+	return err;
 }
 
 int aq_vec_init(struct aq_vec_s *self, const struct aq_hw_ops *aq_hw_ops,
@@ -269,6 +274,18 @@ err_exit:;
 }
 
 void aq_vec_free(struct aq_vec_s *self)
+{
+	if (!self)
+		goto err_exit;
+
+	netif_napi_del(&self->napi);
+
+	kfree(self);
+
+err_exit:;
+}
+
+void aq_vec_ring_free(struct aq_vec_s *self)
 {
 	struct aq_ring_s *ring = NULL;
 	unsigned int i = 0U;
@@ -279,13 +296,12 @@ void aq_vec_free(struct aq_vec_s *self)
 	for (i = 0U, ring = self->ring[0];
 		self->tx_rings > i; ++i, ring = self->ring[i]) {
 		aq_ring_free(&ring[AQ_VEC_TX_ID]);
-		aq_ring_free(&ring[AQ_VEC_RX_ID]);
+		if (i < self->rx_rings)
+			aq_ring_free(&ring[AQ_VEC_RX_ID]);
 	}
 
-	netif_napi_del(&self->napi);
-
-	kfree(self);
-
+	self->tx_rings = 0;
+	self->rx_rings = 0;
 err_exit:;
 }
 
@@ -333,16 +349,14 @@ cpumask_t *aq_vec_get_affinity_mask(struct aq_vec_s *self)
 	return &self->aq_ring_param.affinity_mask;
 }
 
-void aq_vec_add_stats(struct aq_vec_s *self,
-		      struct aq_ring_stats_rx_s *stats_rx,
-		      struct aq_ring_stats_tx_s *stats_tx)
+static void aq_vec_add_stats(struct aq_vec_s *self,
+			     const unsigned int tc,
+			     struct aq_ring_stats_rx_s *stats_rx,
+			     struct aq_ring_stats_tx_s *stats_tx)
 {
-	struct aq_ring_s *ring = NULL;
-	unsigned int r = 0U;
+	struct aq_ring_s *ring = self->ring[tc];
 
-	for (r = 0U, ring = self->ring[0];
-		self->tx_rings > r; ++r, ring = self->ring[r]) {
-		struct aq_ring_stats_tx_s *tx = &ring[AQ_VEC_TX_ID].stats.tx;
+	if (tc < self->rx_rings) {
 		struct aq_ring_stats_rx_s *rx = &ring[AQ_VEC_RX_ID].stats.rx;
 
 		stats_rx->packets += rx->packets;
@@ -353,6 +367,10 @@ void aq_vec_add_stats(struct aq_vec_s *self,
 		stats_rx->pg_losts += rx->pg_losts;
 		stats_rx->pg_flips += rx->pg_flips;
 		stats_rx->pg_reuses += rx->pg_reuses;
+	}
+
+	if (tc < self->tx_rings) {
+		struct aq_ring_stats_tx_s *tx = &ring[AQ_VEC_TX_ID].stats.tx;
 
 		stats_tx->packets += tx->packets;
 		stats_tx->bytes += tx->bytes;
@@ -361,7 +379,8 @@ void aq_vec_add_stats(struct aq_vec_s *self,
 	}
 }
 
-int aq_vec_get_sw_stats(struct aq_vec_s *self, u64 *data, unsigned int *p_count)
+int aq_vec_get_sw_stats(struct aq_vec_s *self, const unsigned int tc, u64 *data,
+			unsigned int *p_count)
 {
 	struct aq_ring_stats_rx_s stats_rx;
 	struct aq_ring_stats_tx_s stats_tx;
@@ -369,7 +388,8 @@ int aq_vec_get_sw_stats(struct aq_vec_s *self, u64 *data, unsigned int *p_count)
 
 	memset(&stats_rx, 0U, sizeof(struct aq_ring_stats_rx_s));
 	memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s));
-	aq_vec_add_stats(self, &stats_rx, &stats_tx);
+
+	aq_vec_add_stats(self, tc, &stats_rx, &stats_tx);
 
 	/* This data should mimic aq_ethtool_queue_stat_names structure
 	 */

drivers/net/ethernet/aquantia/atlantic/aq_vec.h

@@ -25,17 +25,17 @@ irqreturn_t aq_vec_isr(int irq, void *private);
 irqreturn_t aq_vec_isr_legacy(int irq, void *private);
 struct aq_vec_s *aq_vec_alloc(struct aq_nic_s *aq_nic, unsigned int idx,
 			      struct aq_nic_cfg_s *aq_nic_cfg);
+int aq_vec_ring_alloc(struct aq_vec_s *self, struct aq_nic_s *aq_nic,
+		      unsigned int idx, struct aq_nic_cfg_s *aq_nic_cfg);
 int aq_vec_init(struct aq_vec_s *self, const struct aq_hw_ops *aq_hw_ops,
 		struct aq_hw_s *aq_hw);
 void aq_vec_deinit(struct aq_vec_s *self);
 void aq_vec_free(struct aq_vec_s *self);
+void aq_vec_ring_free(struct aq_vec_s *self);
 int aq_vec_start(struct aq_vec_s *self);
 void aq_vec_stop(struct aq_vec_s *self);
 cpumask_t *aq_vec_get_affinity_mask(struct aq_vec_s *self);
-int aq_vec_get_sw_stats(struct aq_vec_s *self, u64 *data,
+int aq_vec_get_sw_stats(struct aq_vec_s *self, const unsigned int tc, u64 *data,
 			unsigned int *p_count);
-void aq_vec_add_stats(struct aq_vec_s *self,
-		      struct aq_ring_stats_rx_s *stats_rx,
-		      struct aq_ring_stats_tx_s *stats_tx);
 
 #endif /* AQ_VEC_H */

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c

@@ -21,7 +21,7 @@
 	.msix_irqs = 4U,		  \
 	.irq_mask = ~0U,		  \
 	.vecs = HW_ATL_A0_RSS_MAX,	  \
-	.tcs = HW_ATL_A0_TC_MAX,	  \
+	.tcs_max = HW_ATL_A0_TC_MAX,	  \
 	.rxd_alignment = 1U,		  \
 	.rxd_size = HW_ATL_A0_RXD_SIZE,   \
 	.rxds_max = HW_ATL_A0_MAX_RXD,    \
@@ -136,10 +136,10 @@ static int hw_atl_a0_hw_qos_set(struct aq_hw_s *self)
 	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
 	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
 
-	hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF, 0U);
-	hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, 0x64, 0U);
-	hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, 0U);
-	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, 0U);
+	hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0U, 0xFFF);
+	hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, 0U, 0x64);
+	hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0U, 0x50);
+	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0U, 0x1E);
 
 	/* Tx buf size */
 	buff_size = HW_ATL_A0_TXBUF_MAX;

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c

@@ -23,7 +23,7 @@
 	.msix_irqs = 8U,		  \
 	.irq_mask = ~0U,		  \
 	.vecs = HW_ATL_B0_RSS_MAX,	  \
-	.tcs = HW_ATL_B0_TC_MAX,	  \
+	.tcs_max = HW_ATL_B0_TC_MAX,	  \
 	.rxd_alignment = 1U,		  \
 	.rxd_size = HW_ATL_B0_RXD_SIZE,   \
 	.rxds_max = HW_ATL_B0_MAX_RXD,    \
@@ -46,7 +46,8 @@
 			NETIF_F_HW_VLAN_CTAG_RX |     \
 			NETIF_F_HW_VLAN_CTAG_TX |     \
 			NETIF_F_GSO_UDP_L4      |     \
-			NETIF_F_GSO_PARTIAL,          \
+			NETIF_F_GSO_PARTIAL |         \
+			NETIF_F_HW_TC,                \
 	.hw_priv_flags = IFF_UNICAST_FLT, \
 	.flow_control = true,		  \
 	.mtu = HW_ATL_B0_MTU_JUMBO,	  \
@@ -114,12 +115,34 @@ static int hw_atl_b0_set_fc(struct aq_hw_s *self, u32 fc, u32 tc)
 	return 0;
 }
 
+static int hw_atl_b0_tc_ptp_set(struct aq_hw_s *self)
+{
+	/* Init TC2 for PTP_TX */
+	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, HW_ATL_B0_PTP_TXBUF_SIZE,
+					       AQ_HW_PTP_TC);
+
+	/* Init TC2 for PTP_RX */
+	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, HW_ATL_B0_PTP_RXBUF_SIZE,
+					       AQ_HW_PTP_TC);
+	/* No flow control for PTP */
+	hw_atl_rpb_rx_xoff_en_per_tc_set(self, 0U, AQ_HW_PTP_TC);
+
+	return aq_hw_err_from_flags(self);
+}
+
 static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 {
-	unsigned int i_priority = 0U;
-	u32 buff_size = 0U;
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+	u32 tx_buff_size = HW_ATL_B0_TXBUF_MAX;
+	u32 rx_buff_size = HW_ATL_B0_RXBUF_MAX;
+	unsigned int prio = 0U;
 	u32 tc = 0U;
 
+	if (cfg->is_ptp) {
+		tx_buff_size -= HW_ATL_B0_PTP_TXBUF_SIZE;
+		rx_buff_size -= HW_ATL_B0_PTP_RXBUF_SIZE;
+	}
+
 	/* TPS Descriptor rate init */
 	hw_atl_tps_tx_pkt_shed_desc_rate_curr_time_res_set(self, 0x0U);
 	hw_atl_tps_tx_pkt_shed_desc_rate_lim_set(self, 0xA);
@@ -127,63 +150,39 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self)
 	/* TPS VM init */
 	hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(self, 0U);
 
-	/* TPS TC credits init */
-	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
-	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
-
-	tc = 0;
-
-	/* TX Packet Scheduler Data TC0 */
-	hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF, tc);
-	hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, 0x64, tc);
-	hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
-	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
-
-	/* Tx buf size TC0 */
-	buff_size = HW_ATL_B0_TXBUF_MAX - HW_ATL_B0_PTP_TXBUF_SIZE;
-
-	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, buff_size, tc);
-	hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self,
-						   (buff_size *
-						   (1024 / 32U) * 66U) /
-						   100U, tc);
-	hw_atl_tpb_tx_buff_lo_threshold_per_tc_set(self,
-						   (buff_size *
-						   (1024 / 32U) * 50U) /
-						   100U, tc);
-	/* Init TC2 for PTP_TX */
-	tc = 2;
+	tx_buff_size /= cfg->tcs;
+	rx_buff_size /= cfg->tcs;
+	for (tc = 0; tc < cfg->tcs; tc++) {
+		u32 threshold = 0U;
 
-	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, HW_ATL_B0_PTP_TXBUF_SIZE,
-					       tc);
+		/* Tx buf size TC0 */
+		hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
 
-	/* QoS Rx buf size per TC */
-	tc = 0;
-	buff_size = HW_ATL_B0_RXBUF_MAX - HW_ATL_B0_PTP_RXBUF_SIZE;
+		threshold = (tx_buff_size * (1024 / 32U) * 66U) / 100U;
+		hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self, threshold, tc);
 
-	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, buff_size, tc);
-	hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self,
-						   (buff_size *
-						   (1024U / 32U) * 66U) /
-						   100U, tc);
-	hw_atl_rpb_rx_buff_lo_threshold_per_tc_set(self,
-						   (buff_size *
-						   (1024U / 32U) * 50U) /
-						   100U, tc);
+		threshold = (tx_buff_size * (1024 / 32U) * 50U) / 100U;
+		hw_atl_tpb_tx_buff_lo_threshold_per_tc_set(self, threshold, tc);
 
-	hw_atl_b0_set_fc(self, self->aq_nic_cfg->fc.req, tc);
+		/* QoS Rx buf size per TC */
+		hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, rx_buff_size, tc);
 
-	/* Init TC2 for PTP_RX */
-	tc = 2;
+		threshold = (rx_buff_size * (1024U / 32U) * 66U) / 100U;
+		hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self, threshold, tc);
 
-	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, HW_ATL_B0_PTP_RXBUF_SIZE,
-					       tc);
-	/* No flow control for PTP */
-	hw_atl_rpb_rx_xoff_en_per_tc_set(self, 0U, tc);
+		threshold = (rx_buff_size * (1024U / 32U) * 50U) / 100U;
+		hw_atl_rpb_rx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+
+		hw_atl_b0_set_fc(self, self->aq_nic_cfg->fc.req, tc);
+	}
+
+	if (cfg->is_ptp)
+		hw_atl_b0_tc_ptp_set(self);
 
 	/* QoS 802.1p priority -> TC mapping */
-	for (i_priority = 8U; i_priority--;)
-		hw_atl_rpf_rpb_user_priority_tc_map_set(self, i_priority, 0U);
+	for (prio = 0; prio < 8; ++prio)
+		hw_atl_rpf_rpb_user_priority_tc_map_set(self, prio,
+							cfg->prio_tc_map[prio]);
 
 	return aq_hw_err_from_flags(self);
 }
@@ -311,10 +310,124 @@ int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
+static int hw_atl_b0_hw_init_tx_tc_rate_limit(struct aq_hw_s *self)
+{
+	static const u32 max_weight = BIT(HW_ATL_TPS_DATA_TCTWEIGHT_WIDTH) - 1;
+	/* Scale factor is based on the number of bits in fractional portion */
+	static const u32 scale = BIT(HW_ATL_TPS_DESC_RATE_Y_WIDTH);
+	static const u32 frac_msk = HW_ATL_TPS_DESC_RATE_Y_MSK >>
+				    HW_ATL_TPS_DESC_RATE_Y_SHIFT;
+	const u32 link_speed = self->aq_link_status.mbps;
+	struct aq_nic_cfg_s *nic_cfg = self->aq_nic_cfg;
+	unsigned long num_min_rated_tcs = 0;
+	u32 tc_weight[AQ_CFG_TCS_MAX];
+	u32 fixed_max_credit;
+	u8 min_rate_msk = 0;
+	u32 sum_weight = 0;
+	int tc;
+
+	/* By default max_credit is based upon MTU (in unit of 64b) */
+	fixed_max_credit = nic_cfg->aq_hw_caps->mtu / 64;
+
+	if (link_speed) {
+		min_rate_msk = nic_cfg->tc_min_rate_msk &
+			       (BIT(nic_cfg->tcs) - 1);
+		num_min_rated_tcs = hweight8(min_rate_msk);
+	}
+
+	/* First, calculate weights where min_rate is specified */
+	if (num_min_rated_tcs) {
+		for (tc = 0; tc != nic_cfg->tcs; tc++) {
+			if (!nic_cfg->tc_min_rate[tc]) {
+				tc_weight[tc] = 0;
+				continue;
+			}
+
+			tc_weight[tc] = (-1L + link_speed +
+					 nic_cfg->tc_min_rate[tc] *
+					 max_weight) /
+					link_speed;
+			tc_weight[tc] = min(tc_weight[tc], max_weight);
+			sum_weight += tc_weight[tc];
+		}
+	}
+
+	/* WSP, if min_rate is set for at least one TC.
+	 * RR otherwise.
+	 */
+	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, min_rate_msk ? 1U : 0U);
+	/* Data TC Arbiter takes precedence over Descriptor TC Arbiter,
+	 * leave Descriptor TC Arbiter as RR.
+	 */
+	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
+
+	hw_atl_tps_tx_desc_rate_mode_set(self, nic_cfg->is_qos ? 1U : 0U);
+
+	for (tc = 0; tc != nic_cfg->tcs; tc++) {
+		const u32 en = (nic_cfg->tc_max_rate[tc] != 0) ? 1U : 0U;
+		const u32 desc = AQ_NIC_CFG_TCVEC2RING(nic_cfg, tc, 0);
+		u32 weight, max_credit;
+
+		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, tc,
+							      fixed_max_credit);
+		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, tc, 0x1E);
+
+		if (num_min_rated_tcs) {
+			weight = tc_weight[tc];
+
+			if (!weight && sum_weight < max_weight)
+				weight = (max_weight - sum_weight) /
+					 (nic_cfg->tcs - num_min_rated_tcs);
+			else if (!weight)
+				weight = 0x64;
+
+			max_credit = max(8 * weight, fixed_max_credit);
+		} else {
+			weight = 0x64;
+			max_credit = 0xFFF;
+		}
+
+		hw_atl_tps_tx_pkt_shed_tc_data_weight_set(self, tc, weight);
+		hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(self, tc,
+							      max_credit);
+
+		hw_atl_tps_tx_desc_rate_en_set(self, desc, en);
+
+		if (en) {
+			/* Nominal rate is always 10G */
+			const u32 rate = 10000U * scale /
+					 nic_cfg->tc_max_rate[tc];
+			const u32 rate_int = rate >>
+					     HW_ATL_TPS_DESC_RATE_Y_WIDTH;
+			const u32 rate_frac = rate & frac_msk;
+
+			hw_atl_tps_tx_desc_rate_x_set(self, desc, rate_int);
+			hw_atl_tps_tx_desc_rate_y_set(self, desc, rate_frac);
+		} else {
+			/* A value of 1 indicates the queue is not
+			 * rate controlled.
+			 */
+			hw_atl_tps_tx_desc_rate_x_set(self, desc, 1U);
+			hw_atl_tps_tx_desc_rate_y_set(self, desc, 0U);
+		}
+	}
+	for (tc = nic_cfg->tcs; tc != AQ_CFG_TCS_MAX; tc++) {
+		const u32 desc = AQ_NIC_CFG_TCVEC2RING(nic_cfg, tc, 0);
+
+		hw_atl_tps_tx_desc_rate_en_set(self, desc, 0U);
+		hw_atl_tps_tx_desc_rate_x_set(self, desc, 1U);
+		hw_atl_tps_tx_desc_rate_y_set(self, desc, 0U);
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
 static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
 {
+	struct aq_nic_cfg_s *nic_cfg = self->aq_nic_cfg;
+
 	/* Tx TC/Queue number config */
-	hw_atl_tpb_tps_tx_tc_mode_set(self, 1U);
+	hw_atl_tpb_tps_tx_tc_mode_set(self, nic_cfg->tc_mode);
 
 	hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U);
@@ -334,20 +447,32 @@ static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
 	return aq_hw_err_from_flags(self);
 }
 
+void hw_atl_b0_hw_init_rx_rss_ctrl1(struct aq_hw_s *self)
+{
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+	u32 rss_ctrl1 = HW_ATL_RSS_DISABLED;
+
+	if (cfg->is_rss)
+		rss_ctrl1 = (cfg->tc_mode == AQ_TC_MODE_8TCS) ?
+			    HW_ATL_RSS_ENABLED_8TCS_2INDEX_BITS :
+			    HW_ATL_RSS_ENABLED_4TCS_3INDEX_BITS;
+
+	hw_atl_reg_rx_flr_rss_control1set(self, rss_ctrl1);
+}
+
 static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self)
 {
 	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
 	int i;
 
 	/* Rx TC/RSS number config */
-	hw_atl_rpb_rpf_rx_traf_class_mode_set(self, 1U);
+	hw_atl_rpb_rpf_rx_traf_class_mode_set(self, cfg->tc_mode);
 
 	/* Rx flow control */
 	hw_atl_rpb_rx_flow_ctl_mode_set(self, 1U);
 
 	/* RSS Ring selection */
-	hw_atl_reg_rx_flr_rss_control1set(self, cfg->is_rss ?
-					0xB3333333U : 0x00000000U);
+	hw_atl_b0_hw_init_rx_rss_ctrl1(self);
 
 	/* Multicast filters */
 	for (i = HW_ATL_B0_MAC_MAX; i--;) {
@@ -1078,18 +1203,6 @@ int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring)
 	return aq_hw_err_from_flags(self);
 }
 
-static int hw_atl_b0_tx_tc_mode_get(struct aq_hw_s *self, u32 *tc_mode)
-{
-	*tc_mode = hw_atl_tpb_tps_tx_tc_mode_get(self);
-	return aq_hw_err_from_flags(self);
-}
-
-static int hw_atl_b0_rx_tc_mode_get(struct aq_hw_s *self, u32 *tc_mode)
-{
-	*tc_mode = hw_atl_rpb_rpf_rx_traf_class_mode_get(self);
-	return aq_hw_err_from_flags(self);
-}
-
 #define get_ptp_ts_val_u64(self, indx) \
 	((u64)(hw_atl_pcs_ptp_clock_get(self, indx) & 0xffff))
 
@@ -1503,13 +1616,11 @@ const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_interrupt_moderation_set = hw_atl_b0_hw_interrupt_moderation_set,
 	.hw_rss_set                  = hw_atl_b0_hw_rss_set,
 	.hw_rss_hash_set             = hw_atl_b0_hw_rss_hash_set,
+	.hw_tc_rate_limit_set        = hw_atl_b0_hw_init_tx_tc_rate_limit,
 	.hw_get_regs                 = hw_atl_utils_hw_get_regs,
 	.hw_get_hw_stats             = hw_atl_utils_get_hw_stats,
 	.hw_get_fw_version           = hw_atl_utils_get_fw_version,
 
-	.hw_tx_tc_mode_get       = hw_atl_b0_tx_tc_mode_get,
-	.hw_rx_tc_mode_get       = hw_atl_b0_rx_tc_mode_get,
-
 	.hw_ring_hwts_rx_fill        = hw_atl_b0_hw_ring_hwts_rx_fill,
 	.hw_ring_hwts_rx_receive     = hw_atl_b0_hw_ring_hwts_rx_receive,
 

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h

@@ -58,6 +58,8 @@ int hw_atl_b0_hw_ring_tx_head_update(struct aq_hw_s *self,
 int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self, struct aq_ring_s *ring);
 int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring);
 
+void hw_atl_b0_hw_init_rx_rss_ctrl1(struct aq_hw_s *self);
+
 int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr);
 
 int hw_atl_b0_hw_start(struct aq_hw_s *self);

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h

@@ -75,7 +75,7 @@
 #define HW_ATL_B0_RSS_HASHKEY_BITS 320U
 
 #define HW_ATL_B0_TCRSS_4_8  1
-#define HW_ATL_B0_TC_MAX 1U
+#define HW_ATL_B0_TC_MAX 8U
 #define HW_ATL_B0_RSS_MAX 8U
 
 #define HW_ATL_B0_LRO_RXD_MAX 16U
@@ -151,6 +151,10 @@
 #define HW_ATL_B0_MAX_RXD 8184U
 #define HW_ATL_B0_MAX_TXD 8184U
 
+#define HW_ATL_RSS_DISABLED 0x00000000U
+#define HW_ATL_RSS_ENABLED_8TCS_2INDEX_BITS 0xA2222222U
+#define HW_ATL_RSS_ENABLED_4TCS_3INDEX_BITS 0x80003333U
+
 /* HW layer capabilities */
 
 #endif /* HW_ATL_B0_INTERNAL_H */

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c

@@ -754,7 +754,7 @@ void hw_atl_rpfl2_accept_all_mc_packets_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl_rpf_rpb_user_priority_tc_map_set(struct aq_hw_s *aq_hw,
-					     u32 user_priority_tc_map, u32 tc)
+					     u32 user_priority, u32 tc)
 {
 /* register address for bitfield rx_tc_up{t}[2:0] */
 	static u32 rpf_rpb_rx_tc_upt_adr[8] = {
@@ -773,10 +773,9 @@ void hw_atl_rpf_rpb_user_priority_tc_map_set(struct aq_hw_s *aq_hw,
 			0U, 4U, 8U, 12U, 16U, 20U, 24U, 28U
 		};
 
-	aq_hw_write_reg_bit(aq_hw, rpf_rpb_rx_tc_upt_adr[tc],
-			    rpf_rpb_rx_tc_upt_msk[tc],
-			    rpf_rpb_rx_tc_upt_shft[tc],
-			    user_priority_tc_map);
+	aq_hw_write_reg_bit(aq_hw, rpf_rpb_rx_tc_upt_adr[user_priority],
+			    rpf_rpb_rx_tc_upt_msk[user_priority],
+			    rpf_rpb_rx_tc_upt_shft[user_priority], tc);
 }
 
 void hw_atl_rpf_rss_key_addr_set(struct aq_hw_s *aq_hw, u32 rss_key_addr)
@@ -1464,8 +1463,8 @@ void hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(struct aq_hw_s *aq_hw,
-						   u32 max_credit,
-						   u32 tc)
+						   const u32 tc,
+						   const u32 max_credit)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DESC_TCTCREDIT_MAX_ADR(tc),
 			    HW_ATL_TPS_DESC_TCTCREDIT_MAX_MSK,
@@ -1474,13 +1473,13 @@ void hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(struct aq_hw_s *aq_hw,
-					       u32 tx_pkt_shed_desc_tc_weight,
-					       u32 tc)
+					       const u32 tc,
+					       const u32 weight)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DESC_TCTWEIGHT_ADR(tc),
 			    HW_ATL_TPS_DESC_TCTWEIGHT_MSK,
 			    HW_ATL_TPS_DESC_TCTWEIGHT_SHIFT,
-			    tx_pkt_shed_desc_tc_weight);
+			    weight);
 }
 
 void hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(struct aq_hw_s *aq_hw,
@@ -1493,8 +1492,8 @@ void hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
-						   u32 max_credit,
-						   u32 tc)
+						   const u32 tc,
+						   const u32 max_credit)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DATA_TCTCREDIT_MAX_ADR(tc),
 			    HW_ATL_TPS_DATA_TCTCREDIT_MAX_MSK,
@@ -1503,13 +1502,49 @@ void hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
-					       u32 tx_pkt_shed_tc_data_weight,
-					       u32 tc)
+					       const u32 tc,
+					       const u32 weight)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DATA_TCTWEIGHT_ADR(tc),
 			    HW_ATL_TPS_DATA_TCTWEIGHT_MSK,
 			    HW_ATL_TPS_DATA_TCTWEIGHT_SHIFT,
-			    tx_pkt_shed_tc_data_weight);
+			    weight);
+}
+
+void hw_atl_tps_tx_desc_rate_mode_set(struct aq_hw_s *aq_hw,
+				      const u32 rate_mode)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_TX_DESC_RATE_MODE_ADR,
+			    HW_ATL_TPS_TX_DESC_RATE_MODE_MSK,
+			    HW_ATL_TPS_TX_DESC_RATE_MODE_SHIFT,
+			    rate_mode);
+}
+
+void hw_atl_tps_tx_desc_rate_en_set(struct aq_hw_s *aq_hw, const u32 desc,
+				    const u32 enable)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DESC_RATE_EN_ADR(desc),
+			    HW_ATL_TPS_DESC_RATE_EN_MSK,
+			    HW_ATL_TPS_DESC_RATE_EN_SHIFT,
+			    enable);
+}
+
+void hw_atl_tps_tx_desc_rate_x_set(struct aq_hw_s *aq_hw, const u32 desc,
+				   const u32 rate_int)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DESC_RATE_X_ADR(desc),
+			    HW_ATL_TPS_DESC_RATE_X_MSK,
+			    HW_ATL_TPS_DESC_RATE_X_SHIFT,
+			    rate_int);
+}
+
+void hw_atl_tps_tx_desc_rate_y_set(struct aq_hw_s *aq_hw, const u32 desc,
+				   const u32 rate_frac)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPS_DESC_RATE_Y_ADR(desc),
+			    HW_ATL_TPS_DESC_RATE_Y_MSK,
+			    HW_ATL_TPS_DESC_RATE_Y_SHIFT,
+			    rate_frac);
 }
 
 /* tx */

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h

@@ -688,13 +688,13 @@ void hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(struct aq_hw_s *aq_hw,
 
 /* set tx packet scheduler descriptor tc max credit */
 void hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(struct aq_hw_s *aq_hw,
-						   u32 max_credit,
-					    u32 tc);
+						   const u32 tc,
+						   const u32 max_credit);
 
 /* set tx packet scheduler descriptor tc weight */
 void hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(struct aq_hw_s *aq_hw,
-					       u32 tx_pkt_shed_desc_tc_weight,
-					u32 tc);
+					       const u32 tc,
+					       const u32 weight);
 
 /* set tx packet scheduler descriptor vm arbitration mode */
 void hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(struct aq_hw_s *aq_hw,
@@ -702,13 +702,29 @@ void hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(struct aq_hw_s *aq_hw,
 
 /* set tx packet scheduler tc data max credit */
 void hw_atl_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
-						   u32 max_credit,
-					    u32 tc);
+						   const u32 tc,
+						   const u32 max_credit);
 
 /* set tx packet scheduler tc data weight */
 void hw_atl_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
-					       u32 tx_pkt_shed_tc_data_weight,
-					u32 tc);
+					       const u32 tc,
+					       const u32 weight);
+
+/* set tx descriptor rate mode */
+void hw_atl_tps_tx_desc_rate_mode_set(struct aq_hw_s *aq_hw,
+				      const u32 rate_mode);
+
+/* set tx packet scheduler descriptor rate enable */
+void hw_atl_tps_tx_desc_rate_en_set(struct aq_hw_s *aq_hw, const u32 desc,
+				    const u32 enable);
+
+/* set tx packet scheduler descriptor rate integral value */
+void hw_atl_tps_tx_desc_rate_x_set(struct aq_hw_s *aq_hw, const u32 desc,
+				   const u32 rate_int);
+
+/* set tx packet scheduler descriptor rate fractional value */
+void hw_atl_tps_tx_desc_rate_y_set(struct aq_hw_s *aq_hw, const u32 desc,
+				   const u32 rate_frac);
 
 /* tx */
 

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h

@@ -2038,6 +2038,42 @@
 /* default value of bitfield lso_tcp_flag_mid[b:0] */
 #define HW_ATL_THM_LSO_TCP_FLAG_MID_DEFAULT 0x0
 
+/* tx tx_tc_mode bitfield definitions
+ * preprocessor definitions for the bitfield "tx_tc_mode".
+ * port="pif_tpb_tx_tc_mode_i,pif_tps_tx_tc_mode_i"
+ */
+
+/* register address for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_ADDR 0x00007900
+/* bitmask for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_MSK 0x00000100
+/* inverted bitmask for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_MSKN 0xFFFFFEFF
+/* lower bit position of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_SHIFT 8
+/* width of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_WIDTH 1
+/* default value of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_DEFAULT 0x0
+
+/* tx tx_desc_rate_mode bitfield definitions
+ * preprocessor definitions for the bitfield "tx_desc_rate_mode".
+ * port="pif_tps_desc_rate_mode_i"
+ */
+
+/* register address for bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_ADR 0x00007900
+/* bitmask for bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_MSK 0x00000080
+/* inverted bitmask for bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_MSKN 0xFFFFFF7F
+/* lower bit position of bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_SHIFT 7
+/* width of bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_WIDTH 1
+/* default value of bitfield tx_desc_rate_mode */
+#define HW_ATL_TPS_TX_DESC_RATE_MODE_DEFAULT 0x0
+
 /* tx tx_buf_en bitfield definitions
  * preprocessor definitions for the bitfield "tx_buf_en".
  * port="pif_tpb_tx_buf_en_i"
@@ -2056,19 +2092,6 @@
 /* default value of bitfield tx_buf_en */
 #define HW_ATL_TPB_TX_BUF_EN_DEFAULT 0x0
 
-/* register address for bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_ADDR 0x00007900
-/* bitmask for bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_MSK 0x00000100
-/* inverted bitmask for bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_MSKN 0xFFFFFEFF
-/* lower bit position of bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_SHIFT 8
-/* width of bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_WIDTH 1
-/* default value of bitfield tx_tc_mode */
-#define HW_ATL_TPB_TX_TC_MODE_DEFAULT 0x0
-
 /* tx tx{b}_hi_thresh[c:0] bitfield definitions
  * preprocessor definitions for the bitfield "tx{b}_hi_thresh[c:0]".
  * parameter: buffer {b} | stride size 0x10 | range [0, 7]
@@ -2270,6 +2293,58 @@
 /* default value of bitfield data_tc_arb_mode */
 #define HW_ATL_TPS_DATA_TC_ARB_MODE_DEFAULT 0x0
 
+/* tx desc{r}_rate_en bitfield definitions
+ * preprocessor definitions for the bitfield "desc{r}_rate_en".
+ * port="pif_tps_desc_rate_en_i[0]"
+ */
+
+/* register address for bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_ADR(desc) (0x00007408 + (desc) * 0x10)
+/* bitmask for bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_MSK 0x80000000
+/* inverted bitmask for bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_MSKN 0x7FFFFFFF
+/* lower bit position of bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_SHIFT 31
+/* width of bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_WIDTH 1
+/* default value of bitfield desc{r}_rate_en */
+#define HW_ATL_TPS_DESC_RATE_EN_DEFAULT 0x0
+
+/* tx desc{r}_rate_x bitfield definitions
+ * preprocessor definitions for the bitfield "desc{r}_rate_x".
+ * port="pif_tps_desc0_rate_x"
+ */
+/* register address for bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_ADR(desc) (0x00007408 + (desc) * 0x10)
+/* bitmask for bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_MSK 0x03FF0000
+/* inverted bitmask for bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_MSKN 0xFC00FFFF
+/* lower bit position of bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_SHIFT 16
+/* width of bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_WIDTH 10
+/* default value of bitfield desc{r}_rate_x */
+#define HW_ATL_TPS_DESC_RATE_X_DEFAULT 0x0
+
+/* tx desc{r}_rate_y bitfield definitions
+ * preprocessor definitions for the bitfield "desc{r}_rate_y".
+ * port="pif_tps_desc0_rate_y"
+ */
+/* register address for bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_ADR(desc) (0x00007408 + (desc) * 0x10)
+/* bitmask for bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_MSK 0x00003FFF
+/* inverted bitmask for bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_MSKN 0xFFFFC000
+/* lower bit position of bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_SHIFT 0
+/* width of bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_WIDTH 14
+/* default value of bitfield desc{r}_rate_y */
+#define HW_ATL_TPS_DESC_RATE_Y_DEFAULT 0x0
+
 /* tx desc_rate_ta_rst bitfield definitions
  * preprocessor definitions for the bitfield "desc_rate_ta_rst".
  * port="pif_tps_desc_rate_ta_rst_i"

drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c

@@ -10,6 +10,7 @@
 #include "hw_atl/hw_atl_b0.h"
 #include "hw_atl/hw_atl_utils.h"
 #include "hw_atl/hw_atl_llh.h"
+#include "hw_atl/hw_atl_llh_internal.h"
 #include "hw_atl2_utils.h"
 #include "hw_atl2_llh.h"
 #include "hw_atl2_internal.h"
@@ -23,7 +24,7 @@ static int hw_atl2_act_rslvr_table_set(struct aq_hw_s *self, u8 location,
 	.msix_irqs = 8U,		  \
 	.irq_mask = ~0U,		  \
 	.vecs = HW_ATL2_RSS_MAX,	  \
-	.tcs = HW_ATL2_TC_MAX,	  \
+	.tcs_max = HW_ATL2_TC_MAX,	  \
 	.rxd_alignment = 1U,		  \
 	.rxd_size = HW_ATL2_RXD_SIZE,   \
 	.rxds_max = HW_ATL2_MAX_RXD,    \
@@ -47,7 +48,8 @@ static int hw_atl2_act_rslvr_table_set(struct aq_hw_s *self, u8 location,
 			NETIF_F_HW_VLAN_CTAG_RX |     \
 			NETIF_F_HW_VLAN_CTAG_TX |     \
 			NETIF_F_GSO_UDP_L4      |     \
-			NETIF_F_GSO_PARTIAL,          \
+			NETIF_F_GSO_PARTIAL     |     \
+			NETIF_F_HW_TC,                \
 	.hw_priv_flags = IFF_UNICAST_FLT, \
 	.flow_control = true,		  \
 	.mtu = HW_ATL2_MTU_JUMBO,	  \
@@ -91,16 +93,49 @@ static int hw_atl2_hw_reset(struct aq_hw_s *self)
 
 static int hw_atl2_hw_queue_to_tc_map_set(struct aq_hw_s *self)
 {
-	if (!hw_atl_rpb_rpf_rx_traf_class_mode_get(self)) {
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(0), 0x11110000);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(8), 0x33332222);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(16), 0x55554444);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(24), 0x77776666);
-	} else {
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(0), 0x00000000);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(8), 0x11111111);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(16), 0x22222222);
-		aq_hw_write_reg(self, HW_ATL2_RX_Q_TC_MAP_ADR(24), 0x33333333);
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+	unsigned int tcs, q_per_tc;
+	unsigned int tc, q;
+	u32 rx_map = 0;
+	u32 tx_map = 0;
+
+	hw_atl2_tpb_tx_tc_q_rand_map_en_set(self, 1U);
+
+	switch (cfg->tc_mode) {
+	case AQ_TC_MODE_8TCS:
+		tcs = 8;
+		q_per_tc = 4;
+		break;
+	case AQ_TC_MODE_4TCS:
+		tcs = 4;
+		q_per_tc = 8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	for (tc = 0; tc != tcs; tc++) {
+		unsigned int tc_q_offset = tc * q_per_tc;
+
+		for (q = tc_q_offset; q != tc_q_offset + q_per_tc; q++) {
+			rx_map |= tc << HW_ATL2_RX_Q_TC_MAP_SHIFT(q);
+			if (HW_ATL2_RX_Q_TC_MAP_ADR(q) !=
+			    HW_ATL2_RX_Q_TC_MAP_ADR(q + 1)) {
+				aq_hw_write_reg(self,
+						HW_ATL2_RX_Q_TC_MAP_ADR(q),
+						rx_map);
+				rx_map = 0;
+			}
+
+			tx_map |= tc << HW_ATL2_TX_Q_TC_MAP_SHIFT(q);
+			if (HW_ATL2_TX_Q_TC_MAP_ADR(q) !=
+			    HW_ATL2_TX_Q_TC_MAP_ADR(q + 1)) {
+				aq_hw_write_reg(self,
+						HW_ATL2_TX_Q_TC_MAP_ADR(q),
+						tx_map);
+				tx_map = 0;
+			}
+		}
 	}
 
 	return aq_hw_err_from_flags(self);
@@ -112,7 +147,6 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 	u32 tx_buff_size = HW_ATL2_TXBUF_MAX;
 	u32 rx_buff_size = HW_ATL2_RXBUF_MAX;
 	unsigned int prio = 0U;
-	u32 threshold = 0U;
 	u32 tc = 0U;
 
 	/* TPS Descriptor rate init */
@@ -122,42 +156,36 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 	/* TPS VM init */
 	hw_atl_tps_tx_pkt_shed_desc_vm_arb_mode_set(self, 0U);
 
-	/* TPS TC credits init */
-	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
-	hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, 0U);
+	tx_buff_size /= cfg->tcs;
+	rx_buff_size /= cfg->tcs;
+	for (tc = 0; tc < cfg->tcs; tc++) {
+		u32 threshold = 0U;
 
-	tc = 0;
+		/* Tx buf size TC0 */
+		hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
 
-	/* TX Packet Scheduler Data TC0 */
-	hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(self, 0xFFF0, tc);
-	hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(self, 0x640, tc);
-	hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, 0x50, tc);
-	hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, 0x1E, tc);
+		threshold = (tx_buff_size * (1024 / 32U) * 66U) / 100U;
+		hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self, threshold, tc);
 
-	/* Tx buf size TC0 */
-	hw_atl_tpb_tx_pkt_buff_size_per_tc_set(self, tx_buff_size, tc);
+		threshold = (tx_buff_size * (1024 / 32U) * 50U) / 100U;
+		hw_atl_tpb_tx_buff_lo_threshold_per_tc_set(self, threshold, tc);
 
-	threshold = (tx_buff_size * (1024 / 32U) * 66U) / 100U;
-	hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(self, threshold, tc);
+		/* QoS Rx buf size per TC */
+		hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, rx_buff_size, tc);
 
-	threshold = (tx_buff_size * (1024 / 32U) * 50U) / 100U;
-	hw_atl_tpb_tx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+		threshold = (rx_buff_size * (1024U / 32U) * 66U) / 100U;
+		hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self, threshold, tc);
 
-	/* QoS Rx buf size per TC */
-	hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, rx_buff_size, tc);
-
-	threshold = (rx_buff_size * (1024U / 32U) * 66U) / 100U;
-	hw_atl_rpb_rx_buff_hi_threshold_per_tc_set(self, threshold, tc);
-
-	threshold = (rx_buff_size * (1024U / 32U) * 50U) / 100U;
-	hw_atl_rpb_rx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+		threshold = (rx_buff_size * (1024U / 32U) * 50U) / 100U;
+		hw_atl_rpb_rx_buff_lo_threshold_per_tc_set(self, threshold, tc);
+	}
 
 	/* QoS 802.1p priority -> TC mapping */
 	for (prio = 0; prio < 8; ++prio)
 		hw_atl_rpf_rpb_user_priority_tc_map_set(self, prio,
-							cfg->tcs * prio / 8);
+							cfg->prio_tc_map[prio]);
 
-	/* ATL2 Apply legacy ring to TC mapping */
+	/* ATL2 Apply ring to TC mapping */
 	hw_atl2_hw_queue_to_tc_map_set(self);
 
 	return aq_hw_err_from_flags(self);
@@ -166,19 +194,149 @@ static int hw_atl2_hw_qos_set(struct aq_hw_s *self)
 static int hw_atl2_hw_rss_set(struct aq_hw_s *self,
 			      struct aq_rss_parameters *rss_params)
 {
-	u8 *indirection_table =	rss_params->indirection_table;
+	u8 *indirection_table = rss_params->indirection_table;
+	const u32 num_tcs = aq_hw_num_tcs(self);
+	u32 rpf_redir2_enable;
+	int tc;
 	int i;
 
-	for (i = HW_ATL2_RSS_REDIRECTION_MAX; i--;)
-		hw_atl2_new_rpf_rss_redir_set(self, 0, i, indirection_table[i]);
+	rpf_redir2_enable = num_tcs > 4 ? 1 : 0;
+
+	hw_atl2_rpf_redirection_table2_select_set(self, rpf_redir2_enable);
+
+	for (i = HW_ATL2_RSS_REDIRECTION_MAX; i--;) {
+		for (tc = 0; tc != num_tcs; tc++) {
+			hw_atl2_new_rpf_rss_redir_set(self, tc, i,
+						      tc *
+						      aq_hw_q_per_tc(self) +
+						      indirection_table[i]);
+		}
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
+static int hw_atl2_hw_init_tx_tc_rate_limit(struct aq_hw_s *self)
+{
+	static const u32 max_weight = BIT(HW_ATL2_TPS_DATA_TCTWEIGHT_WIDTH) - 1;
+	/* Scale factor is based on the number of bits in fractional portion */
+	static const u32 scale = BIT(HW_ATL_TPS_DESC_RATE_Y_WIDTH);
+	static const u32 frac_msk = HW_ATL_TPS_DESC_RATE_Y_MSK >>
+				    HW_ATL_TPS_DESC_RATE_Y_SHIFT;
+	const u32 link_speed = self->aq_link_status.mbps;
+	struct aq_nic_cfg_s *nic_cfg = self->aq_nic_cfg;
+	unsigned long num_min_rated_tcs = 0;
+	u32 tc_weight[AQ_CFG_TCS_MAX];
+	u32 fixed_max_credit_4b;
+	u32 fixed_max_credit;
+	u8 min_rate_msk = 0;
+	u32 sum_weight = 0;
+	int tc;
+
+	/* By default max_credit is based upon MTU (in unit of 64b) */
+	fixed_max_credit = nic_cfg->aq_hw_caps->mtu / 64;
+	/* in unit of 4b */
+	fixed_max_credit_4b = nic_cfg->aq_hw_caps->mtu / 4;
+
+	if (link_speed) {
+		min_rate_msk = nic_cfg->tc_min_rate_msk &
+			       (BIT(nic_cfg->tcs) - 1);
+		num_min_rated_tcs = hweight8(min_rate_msk);
+	}
+
+	/* First, calculate weights where min_rate is specified */
+	if (num_min_rated_tcs) {
+		for (tc = 0; tc != nic_cfg->tcs; tc++) {
+			if (!nic_cfg->tc_min_rate[tc]) {
+				tc_weight[tc] = 0;
+				continue;
+			}
+
+			tc_weight[tc] = (-1L + link_speed +
+					 nic_cfg->tc_min_rate[tc] *
+					 max_weight) /
+					link_speed;
+			tc_weight[tc] = min(tc_weight[tc], max_weight);
+			sum_weight += tc_weight[tc];
+		}
+	}
+
+	/* WSP, if min_rate is set for at least one TC.
+	 * RR otherwise.
+	 */
+	hw_atl2_tps_tx_pkt_shed_data_arb_mode_set(self, min_rate_msk ? 1U : 0U);
+	/* Data TC Arbiter takes precedence over Descriptor TC Arbiter,
+	 * leave Descriptor TC Arbiter as RR.
+	 */
+	hw_atl_tps_tx_pkt_shed_desc_tc_arb_mode_set(self, 0U);
+
+	hw_atl_tps_tx_desc_rate_mode_set(self, nic_cfg->is_qos ? 1U : 0U);
+
+	for (tc = 0; tc != nic_cfg->tcs; tc++) {
+		const u32 en = (nic_cfg->tc_max_rate[tc] != 0) ? 1U : 0U;
+		const u32 desc = AQ_NIC_CFG_TCVEC2RING(nic_cfg, tc, 0);
+		u32 weight, max_credit;
+
+		hw_atl_tps_tx_pkt_shed_desc_tc_max_credit_set(self, tc,
+							      fixed_max_credit);
+		hw_atl_tps_tx_pkt_shed_desc_tc_weight_set(self, tc, 0x1E);
+
+		if (num_min_rated_tcs) {
+			weight = tc_weight[tc];
+
+			if (!weight && sum_weight < max_weight)
+				weight = (max_weight - sum_weight) /
+					 (nic_cfg->tcs - num_min_rated_tcs);
+			else if (!weight)
+				weight = 0x640;
+
+			max_credit = max(2 * weight, fixed_max_credit_4b);
+		} else {
+			weight = 0x640;
+			max_credit = 0xFFF0;
+		}
+
+		hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(self, tc, weight);
+		hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(self, tc,
+							       max_credit);
+
+		hw_atl_tps_tx_desc_rate_en_set(self, desc, en);
+
+		if (en) {
+			/* Nominal rate is always 10G */
+			const u32 rate = 10000U * scale /
+					 nic_cfg->tc_max_rate[tc];
+			const u32 rate_int = rate >>
+					     HW_ATL_TPS_DESC_RATE_Y_WIDTH;
+			const u32 rate_frac = rate & frac_msk;
+
+			hw_atl_tps_tx_desc_rate_x_set(self, desc, rate_int);
+			hw_atl_tps_tx_desc_rate_y_set(self, desc, rate_frac);
+		} else {
+			/* A value of 1 indicates the queue is not
+			 * rate controlled.
+			 */
+			hw_atl_tps_tx_desc_rate_x_set(self, desc, 1U);
+			hw_atl_tps_tx_desc_rate_y_set(self, desc, 0U);
+		}
+	}
+	for (tc = nic_cfg->tcs; tc != AQ_CFG_TCS_MAX; tc++) {
+		const u32 desc = AQ_NIC_CFG_TCVEC2RING(nic_cfg, tc, 0);
+
+		hw_atl_tps_tx_desc_rate_en_set(self, desc, 0U);
+		hw_atl_tps_tx_desc_rate_x_set(self, desc, 1U);
+		hw_atl_tps_tx_desc_rate_y_set(self, desc, 0U);
+	}
 
 	return aq_hw_err_from_flags(self);
 }
 
 static int hw_atl2_hw_init_tx_path(struct aq_hw_s *self)
 {
+	struct aq_nic_cfg_s *nic_cfg = self->aq_nic_cfg;
+
 	/* Tx TC/RSS number config */
-	hw_atl_tpb_tps_tx_tc_mode_set(self, 1U);
+	hw_atl_tpb_tps_tx_tc_mode_set(self, nic_cfg->tc_mode);
 
 	hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U);
@@ -201,13 +359,29 @@ static int hw_atl2_hw_init_tx_path(struct aq_hw_s *self)
 static void hw_atl2_hw_init_new_rx_filters(struct aq_hw_s *self)
 {
 	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	u8 *prio_tc_map = self->aq_nic_cfg->prio_tc_map;
+	u16 action;
 	u8 index;
+	int i;
 
+	/* Action Resolver Table (ART) is used by RPF to decide which action
+	 * to take with a packet based upon input tag and tag mask, where:
+	 *  - input tag is a combination of 3-bit VLan Prio (PTP) and
+	 *    29-bit concatenation of all tags from filter block;
+	 *  - tag mask is a mask used for matching against input tag.
+	 * The input_tag is compared with the all the Requested_tags in the
+	 * Record table to find a match. Action field of the selected matched
+	 * REC entry is used for further processing. If multiple entries match,
+	 * the lowest REC entry, Action field will be selected.
+	 */
 	hw_atl2_rpf_act_rslvr_section_en_set(self, 0xFFFF);
 	hw_atl2_rpfl2_uc_flr_tag_set(self, HW_ATL2_RPF_TAG_BASE_UC,
 				     HW_ATL2_MAC_UC);
 	hw_atl2_rpfl2_bc_flr_tag_set(self, HW_ATL2_RPF_TAG_BASE_UC);
 
+	/* FW reserves the beginning of ART, thus all driver entries must
+	 * start from the offset specified in FW caps.
+	 */
 	index = priv->art_base_index + HW_ATL2_RPF_L2_PROMISC_OFF_INDEX;
 	hw_atl2_act_rslvr_table_set(self, index, 0,
 				    HW_ATL2_RPF_TAG_UC_MASK |
@@ -220,33 +394,17 @@ static void hw_atl2_hw_init_new_rx_filters(struct aq_hw_s *self)
 					HW_ATL2_RPF_TAG_UNTAG_MASK,
 				    HW_ATL2_ACTION_DROP);
 
-	index = priv->art_base_index + HW_ATL2_RPF_VLAN_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_BASE_VLAN,
-				    HW_ATL2_RPF_TAG_VLAN_MASK,
-				    HW_ATL2_ACTION_ASSIGN_TC(0));
-
-	index = priv->art_base_index + HW_ATL2_RPF_MAC_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_BASE_UC,
-				    HW_ATL2_RPF_TAG_UC_MASK,
-				    HW_ATL2_ACTION_ASSIGN_TC(0));
-
-	index = priv->art_base_index + HW_ATL2_RPF_ALLMC_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_BASE_ALLMC,
-				    HW_ATL2_RPF_TAG_ALLMC_MASK,
-				    HW_ATL2_ACTION_ASSIGN_TC(0));
+	/* Configure ART to map given VLan Prio (PCP) to the TC index for
+	 * RSS redirection table.
+	 */
+	for (i = 0; i < 8; i++) {
+		action = HW_ATL2_ACTION_ASSIGN_TC(prio_tc_map[i]);
 
-	index = priv->art_base_index + HW_ATL2_RPF_UNTAG_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, HW_ATL2_RPF_TAG_UNTAG_MASK,
-				    HW_ATL2_RPF_TAG_UNTAG_MASK,
-				    HW_ATL2_ACTION_ASSIGN_TC(0));
-
-	index = priv->art_base_index + HW_ATL2_RPF_VLAN_PROMISC_ON_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, 0, HW_ATL2_RPF_TAG_VLAN_MASK,
-				    HW_ATL2_ACTION_DISABLE);
-
-	index = priv->art_base_index + HW_ATL2_RPF_L2_PROMISC_ON_INDEX;
-	hw_atl2_act_rslvr_table_set(self, index, 0, HW_ATL2_RPF_TAG_UC_MASK,
-				    HW_ATL2_ACTION_DISABLE);
+		index = priv->art_base_index + HW_ATL2_RPF_PCP_TO_TC_INDEX + i;
+		hw_atl2_act_rslvr_table_set(self, index,
+					    i << HW_ATL2_RPF_TAG_PCP_OFFSET,
+					    HW_ATL2_RPF_TAG_PCP_MASK, action);
+	}
 }
 
 static void hw_atl2_hw_new_rx_filter_vlan_promisc(struct aq_hw_s *self,
@@ -309,7 +467,7 @@ static int hw_atl2_hw_init_rx_path(struct aq_hw_s *self)
 	int i;
 
 	/* Rx TC/RSS number config */
-	hw_atl_rpb_rpf_rx_traf_class_mode_set(self, 1U);
+	hw_atl_rpb_rpf_rx_traf_class_mode_set(self, cfg->tc_mode);
 
 	/* Rx flow control */
 	hw_atl_rpb_rx_flow_ctl_mode_set(self, 1U);
@@ -317,9 +475,7 @@ static int hw_atl2_hw_init_rx_path(struct aq_hw_s *self)
 	hw_atl2_rpf_rss_hash_type_set(self, HW_ATL2_RPF_RSS_HASH_TYPE_ALL);
 
 	/* RSS Ring selection */
-	hw_atl_reg_rx_flr_rss_control1set(self, cfg->is_rss ?
-						HW_ATL_RSS_ENABLED_3INDEX_BITS :
-						HW_ATL_RSS_DISABLED);
+	hw_atl_b0_hw_init_rx_rss_ctrl1(self);
 
 	/* Multicast filters */
 	for (i = HW_ATL2_MAC_MAX; i--;) {
@@ -678,6 +834,7 @@ const struct aq_hw_ops hw_atl2_ops = {
 	.hw_interrupt_moderation_set = hw_atl2_hw_interrupt_moderation_set,
 	.hw_rss_set                  = hw_atl2_hw_rss_set,
 	.hw_rss_hash_set             = hw_atl_b0_hw_rss_hash_set,
+	.hw_tc_rate_limit_set        = hw_atl2_hw_init_tx_tc_rate_limit,
 	.hw_get_hw_stats             = hw_atl2_utils_get_hw_stats,
 	.hw_get_fw_version           = hw_atl2_utils_get_fw_version,
 	.hw_set_offload              = hw_atl_b0_hw_offload_set,

drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_internal.h

@@ -31,7 +31,7 @@
 
 #define HW_ATL2_RSS_REDIRECTION_MAX 64U
 
-#define HW_ATL2_TC_MAX 1U
+#define HW_ATL2_TC_MAX 8U
 #define HW_ATL2_RSS_MAX 8U
 
 #define HW_ATL2_INTR_MODER_MAX  0x1FF
@@ -82,13 +82,6 @@ enum HW_ATL2_RPF_ART_INDEX {
 	HW_ATL2_RPF_VLAN_USER_INDEX	= HW_ATL2_RPF_ET_PCP_USER_INDEX + 16,
 	HW_ATL2_RPF_PCP_TO_TC_INDEX	= HW_ATL2_RPF_VLAN_USER_INDEX +
 					  HW_ATL_VLAN_MAX_FILTERS,
-	HW_ATL2_RPF_VLAN_INDEX		= HW_ATL2_RPF_PCP_TO_TC_INDEX +
-					  AQ_CFG_TCS_MAX,
-	HW_ATL2_RPF_MAC_INDEX,
-	HW_ATL2_RPF_ALLMC_INDEX,
-	HW_ATL2_RPF_UNTAG_INDEX,
-	HW_ATL2_RPF_VLAN_PROMISC_ON_INDEX,
-	HW_ATL2_RPF_L2_PROMISC_ON_INDEX,
 };
 
 #define HW_ATL2_ACTION(ACTION, RSS, INDEX, VALID) \
@@ -124,9 +117,6 @@ enum HW_ATL2_RPF_RSS_HASH_TYPE {
 					HW_ATL2_RPF_RSS_HASH_TYPE_IPV6_EX_UDP,
 };
 
-#define HW_ATL_RSS_DISABLED 0x00000000U
-#define HW_ATL_RSS_ENABLED_3INDEX_BITS 0xB3333333U
-
 #define HW_ATL_MCAST_FLT_ANY_TO_HOST 0x00010FFFU
 
 struct hw_atl2_priv {

drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.c

@@ -7,6 +7,14 @@
 #include "hw_atl2_llh_internal.h"
 #include "aq_hw_utils.h"
 
+void hw_atl2_rpf_redirection_table2_select_set(struct aq_hw_s *aq_hw,
+					       u32 select)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_ADR,
+			    HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_MSK,
+			    HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_SHIFT, select);
+}
+
 void hw_atl2_rpf_rss_hash_type_set(struct aq_hw_s *aq_hw, u32 rss_hash_type)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_ADR,
@@ -60,6 +68,15 @@ void hw_atl2_rpf_vlan_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag, u32 filter)
 
 /* TX */
 
+void hw_atl2_tpb_tx_tc_q_rand_map_en_set(struct aq_hw_s *aq_hw,
+					 const u32 tc_q_rand_map_en)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_ADR,
+			    HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_MSK,
+			    HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_SHIFT,
+			    tc_q_rand_map_en);
+}
+
 void hw_atl2_tpb_tx_buf_clk_gate_en_set(struct aq_hw_s *aq_hw, u32 clk_gate_en)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_ADR,
@@ -76,9 +93,18 @@ void hw_atl2_reg_tx_intr_moder_ctrl_set(struct aq_hw_s *aq_hw,
 			tx_intr_moderation_ctl);
 }
 
+void hw_atl2_tps_tx_pkt_shed_data_arb_mode_set(struct aq_hw_s *aq_hw,
+					       const u32 data_arb_mode)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPS_DATA_TC_ARB_MODE_ADR,
+			    HW_ATL2_TPS_DATA_TC_ARB_MODE_MSK,
+			    HW_ATL2_TPS_DATA_TC_ARB_MODE_SHIFT,
+			    data_arb_mode);
+}
+
 void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
-						    u32 max_credit,
-						    u32 tc)
+						    const u32 tc,
+						    const u32 max_credit)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPS_DATA_TCTCREDIT_MAX_ADR(tc),
 			    HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSK,
@@ -87,13 +113,13 @@ void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
 }
 
 void hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
-						u32 tx_pkt_shed_tc_data_weight,
-						u32 tc)
+						const u32 tc,
+						const u32 weight)
 {
 	aq_hw_write_reg_bit(aq_hw, HW_ATL2_TPS_DATA_TCTWEIGHT_ADR(tc),
 			    HW_ATL2_TPS_DATA_TCTWEIGHT_MSK,
 			    HW_ATL2_TPS_DATA_TCTWEIGHT_SHIFT,
-			    tx_pkt_shed_tc_data_weight);
+			    weight);
 }
 
 u32 hw_atl2_get_hw_version(struct aq_hw_s *aq_hw)

drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh.h

@@ -15,6 +15,10 @@ void hw_atl2_reg_tx_intr_moder_ctrl_set(struct aq_hw_s *aq_hw,
 					u32 tx_intr_moderation_ctl,
 					u32 queue);
 
+/* Set Redirection Table 2 Select */
+void hw_atl2_rpf_redirection_table2_select_set(struct aq_hw_s *aq_hw,
+					       u32 select);
+
 /** Set RSS HASH type */
 void hw_atl2_rpf_rss_hash_type_set(struct aq_hw_s *aq_hw, u32 rss_hash_type);
 
@@ -34,18 +38,25 @@ void hw_atl2_new_rpf_rss_redir_set(struct aq_hw_s *aq_hw, u32 tc, u32 index,
 /* Set VLAN filter tag */
 void hw_atl2_rpf_vlan_flr_tag_set(struct aq_hw_s *aq_hw, u32 tag, u32 filter);
 
+/* set tx random TC-queue mapping enable bit */
+void hw_atl2_tpb_tx_tc_q_rand_map_en_set(struct aq_hw_s *aq_hw,
+					 const u32 tc_q_rand_map_en);
+
 /* set tx buffer clock gate enable */
 void hw_atl2_tpb_tx_buf_clk_gate_en_set(struct aq_hw_s *aq_hw, u32 clk_gate_en);
 
+void hw_atl2_tps_tx_pkt_shed_data_arb_mode_set(struct aq_hw_s *aq_hw,
+					       const u32 data_arb_mode);
+
 /* set tx packet scheduler tc data max credit */
 void hw_atl2_tps_tx_pkt_shed_tc_data_max_credit_set(struct aq_hw_s *aq_hw,
-						    u32 max_credit,
-						    u32 tc);
+						    const u32 tc,
+						    const u32 max_credit);
 
 /* set tx packet scheduler tc data weight */
 void hw_atl2_tps_tx_pkt_shed_tc_data_weight_set(struct aq_hw_s *aq_hw,
-						u32 tx_pkt_shed_tc_data_weight,
-						u32 tc);
+						const u32 tc,
+						const u32 weight);
 
 u32 hw_atl2_get_hw_version(struct aq_hw_s *aq_hw);
 

drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_llh_internal.h

@@ -6,6 +6,16 @@
 #ifndef HW_ATL2_LLH_INTERNAL_H
 #define HW_ATL2_LLH_INTERNAL_H
 
+/* RX pif_rpf_redir_2_en_i Bitfield Definitions
+ * PORT="pif_rpf_redir_2_en_i"
+ */
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_ADR 0x000054C8
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_MSK 0x00001000
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_MSKN 0xFFFFEFFF
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_SHIFT 12
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_WIDTH 1
+#define HW_ATL2_RPF_PIF_RPF_REDIR2_ENI_DEFAULT 0x0
+
 /* RX pif_rpf_rss_hash_type_i Bitfield Definitions
  */
 #define HW_ATL2_RPF_PIF_RPF_RSS_HASH_TYPEI_ADR 0x000054C8
@@ -122,6 +132,24 @@
 /* Default value of bitfield rx_q{Q}_tc_map[2:0] */
 #define HW_ATL2_RX_Q_TC_MAP_DEFAULT 0x0
 
+/* tx tx_tc_q_rand_map_en bitfield definitions
+ * preprocessor definitions for the bitfield "tx_tc_q_rand_map_en".
+ * port="pif_tpb_tx_tc_q_rand_map_en_i"
+ */
+
+/* register address for bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_ADR 0x00007900
+/* bitmask for bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_MSK 0x00000200
+/* inverted bitmask for bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_MSKN 0xFFFFFDFF
+/* lower bit position of bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_SHIFT 9
+/* width of bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_WIDTH 1
+/* default value of bitfield tx_tc_q_rand_map_en */
+#define HW_ATL2_TPB_TX_TC_Q_RAND_MAP_EN_DEFAULT 0x0
+
 /* tx tx_buffer_clk_gate_en bitfield definitions
  * preprocessor definitions for the bitfield "tx_buffer_clk_gate_en".
  * port="pif_tpb_tx_buffer_clk_gate_en_i"
@@ -140,42 +168,77 @@
 /* default value of bitfield tx_buffer_clk_gate_en */
 #define HW_ATL2_TPB_TX_BUF_CLK_GATE_EN_DEFAULT 0x0
 
-/* tx data_tc{t}_credit_max[b:0] bitfield definitions
- * preprocessor definitions for the bitfield "data_tc{t}_credit_max[b:0]".
+/* tx tx_q_tc_map{q} bitfield definitions
+ * preprocessor definitions for the bitfield "tx_q_tc_map{q}".
+ * parameter: queue {q} | bit-level stride | range [0, 31]
+ * port="pif_tpb_tx_q_tc_map0_i[2:0]"
+ */
+
+/* register address for bitfield tx_q_tc_map{q} */
+#define HW_ATL2_TX_Q_TC_MAP_ADR(queue) \
+	(((queue) < 32) ? 0x0000799C + ((queue) / 4) * 4 : 0)
+/* lower bit position of bitfield tx_q_tc_map{q} */
+#define HW_ATL2_TX_Q_TC_MAP_SHIFT(queue) \
+	(((queue) < 32) ? ((queue) * 8) % 32 : 0)
+/* width of bitfield tx_q_tc_map{q} */
+#define HW_ATL2_TX_Q_TC_MAP_WIDTH 3
+/* default value of bitfield tx_q_tc_map{q} */
+#define HW_ATL2_TX_Q_TC_MAP_DEFAULT 0x0
+
+/* tx data_tc_arb_mode bitfield definitions
+ * preprocessor definitions for the bitfield "data_tc_arb_mode".
+ * port="pif_tps_data_tc_arb_mode_i"
+ */
+
+/* register address for bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_ADR 0x00007100
+/* bitmask for bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_MSK 0x00000003
+/* inverted bitmask for bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_MSKN 0xfffffffc
+/* lower bit position of bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_SHIFT 0
+/* width of bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_WIDTH 2
+/* default value of bitfield data_tc_arb_mode */
+#define HW_ATL2_TPS_DATA_TC_ARB_MODE_DEFAULT 0x0
+
+/* tx data_tc{t}_credit_max[f:0] bitfield definitions
+ * preprocessor definitions for the bitfield "data_tc{t}_credit_max[f:0]".
  * parameter: tc {t} | stride size 0x4 | range [0, 7]
- * port="pif_tps_data_tc0_credit_max_i[11:0]"
+ * port="pif_tps_data_tc0_credit_max_i[15:0]"
  */
 
-/* register address for bitfield data_tc{t}_credit_max[b:0] */
+/* register address for bitfield data_tc{t}_credit_max[f:0] */
 #define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_ADR(tc) (0x00007110 + (tc) * 0x4)
-/* bitmask for bitfield data_tc{t}_credit_max[b:0] */
-#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSK 0x0fff0000
-/* inverted bitmask for bitfield data_tc{t}_credit_max[b:0] */
-#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSKN 0xf000ffff
-/* lower bit position of bitfield data_tc{t}_credit_max[b:0] */
+/* bitmask for bitfield data_tc{t}_credit_max[f:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSK 0xffff0000
+/* inverted bitmask for bitfield data_tc{t}_credit_max[f:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_MSKN 0x0000ffff
+/* lower bit position of bitfield data_tc{t}_credit_max[f:0] */
 #define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_SHIFT 16
-/* width of bitfield data_tc{t}_credit_max[b:0] */
-#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_WIDTH 12
-/* default value of bitfield data_tc{t}_credit_max[b:0] */
+/* width of bitfield data_tc{t}_credit_max[f:0] */
+#define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_WIDTH 16
+/* default value of bitfield data_tc{t}_credit_max[f:0] */
 #define HW_ATL2_TPS_DATA_TCTCREDIT_MAX_DEFAULT 0x0
 
-/* tx data_tc{t}_weight[8:0] bitfield definitions
- * preprocessor definitions for the bitfield "data_tc{t}_weight[8:0]".
+/* tx data_tc{t}_weight[e:0] bitfield definitions
+ * preprocessor definitions for the bitfield "data_tc{t}_weight[e:0]".
  * parameter: tc {t} | stride size 0x4 | range [0, 7]
- * port="pif_tps_data_tc0_weight_i[8:0]"
+ * port="pif_tps_data_tc0_weight_i[14:0]"
  */
 
-/* register address for bitfield data_tc{t}_weight[8:0] */
+/* register address for bitfield data_tc{t}_weight[e:0] */
 #define HW_ATL2_TPS_DATA_TCTWEIGHT_ADR(tc) (0x00007110 + (tc) * 0x4)
-/* bitmask for bitfield data_tc{t}_weight[8:0] */
-#define HW_ATL2_TPS_DATA_TCTWEIGHT_MSK 0x000001ff
-/* inverted bitmask for bitfield data_tc{t}_weight[8:0] */
-#define HW_ATL2_TPS_DATA_TCTWEIGHT_MSKN 0xfffffe00
-/* lower bit position of bitfield data_tc{t}_weight[8:0] */
+/* bitmask for bitfield data_tc{t}_weight[e:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_MSK 0x00007fff
+/* inverted bitmask for bitfield data_tc{t}_weight[e:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_MSKN 0xffff8000
+/* lower bit position of bitfield data_tc{t}_weight[e:0] */
 #define HW_ATL2_TPS_DATA_TCTWEIGHT_SHIFT 0
-/* width of bitfield data_tc{t}_weight[8:0] */
-#define HW_ATL2_TPS_DATA_TCTWEIGHT_WIDTH 9
-/* default value of bitfield data_tc{t}_weight[8:0] */
+/* width of bitfield data_tc{t}_weight[e:0] */
+#define HW_ATL2_TPS_DATA_TCTWEIGHT_WIDTH 15
+/* default value of bitfield data_tc{t}_weight[e:0] */
 #define HW_ATL2_TPS_DATA_TCTWEIGHT_DEFAULT 0x0
 
 /* tx interrupt moderation control register definitions