Merge branch 'mlx4-XDP-tx-refactor'

Tariq Toukan says:

====================
mlx4 XDP TX refactor

This patchset refactors the XDP forwarding case, so that
its dedicated transmit queues are managed in a complete
separation from the other regular ones.

It also adds ethtool counters for XDP cases.

Series generated against net-next commit:
22ca904 genetlink: fix error return code in genl_register_family()

Thanks,
Tariq.

v3:
* Exposed per ring counters.

v2:
* Added ethtool counters.
* Rebased, now patch 2 reverts Brenden's fix, as the bug no longer exists:
  958b3d3 ("net/mlx4_en: fixup xdp tx irq to match rx")
* Updated commit message of patch 2.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

Author: davem330

drivers/net/ethernet/mellanox/mlx4/en_cq.c

@@ -65,7 +65,7 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 	cq->buf_size = cq->size * mdev->dev->caps.cqe_size;
 
 	cq->ring = ring;
-	cq->is_tx = mode;
+	cq->type = mode;
 	cq->vector = mdev->dev->caps.num_comp_vectors;
 
 	/* Allocate HW buffers on provided NUMA node.
@@ -104,7 +104,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	*cq->mcq.arm_db    = 0;
 	memset(cq->buf, 0, cq->buf_size);
 
-	if (cq->is_tx == RX) {
+	if (cq->type == RX) {
 		if (!mlx4_is_eq_vector_valid(mdev->dev, priv->port,
 					     cq->vector)) {
 			cq->vector = cpumask_first(priv->rx_ring[cq->ring]->affinity_mask);
@@ -127,25 +127,17 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 		/* For TX we use the same irq per
 		ring we assigned for the RX    */
 		struct mlx4_en_cq *rx_cq;
-		int xdp_index;
-
-		/* The xdp tx irq must align with the rx ring that forwards to
-		 * it, so reindex these from 0. This should only happen when
-		 * tx_ring_num is not a multiple of rx_ring_num.
-		 */
-		xdp_index = (priv->xdp_ring_num - priv->tx_ring_num) + cq_idx;
-		if (xdp_index >= 0)
-			cq_idx = xdp_index;
+
 		cq_idx = cq_idx % priv->rx_ring_num;
 		rx_cq = priv->rx_cq[cq_idx];
 		cq->vector = rx_cq->vector;
 	}
 
-	if (!cq->is_tx)
+	if (cq->type == RX)
 		cq->size = priv->rx_ring[cq->ring]->actual_size;
 
-	if ((cq->is_tx && priv->hwtstamp_config.tx_type) ||
-	    (!cq->is_tx && priv->hwtstamp_config.rx_filter))
+	if ((cq->type != RX && priv->hwtstamp_config.tx_type) ||
+	    (cq->type == RX && priv->hwtstamp_config.rx_filter))
 		timestamp_en = 1;
 
 	err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt,
@@ -154,10 +146,10 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	if (err)
 		goto free_eq;
 
-	cq->mcq.comp  = cq->is_tx ? mlx4_en_tx_irq : mlx4_en_rx_irq;
+	cq->mcq.comp  = cq->type != RX ? mlx4_en_tx_irq : mlx4_en_rx_irq;
 	cq->mcq.event = mlx4_en_cq_event;
 
-	if (cq->is_tx)
+	if (cq->type != RX)
 		netif_tx_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq,
 				  NAPI_POLL_WEIGHT);
 	else
@@ -181,7 +173,7 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
 
 	mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
 	if (mlx4_is_eq_vector_valid(mdev->dev, priv->port, cq->vector) &&
-	    cq->is_tx == RX)
+	    cq->type == RX)
 		mlx4_release_eq(priv->mdev->dev, cq->vector);
 	cq->vector = 0;
 	cq->buf_size = 0;
@@ -193,7 +185,7 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
 void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 {
 	napi_disable(&cq->napi);
-	if (!cq->is_tx) {
+	if (cq->type == RX) {
 		napi_hash_del(&cq->napi);
 		synchronize_rcu();
 	}

drivers/net/ethernet/mellanox/mlx4/en_ethtool.c

@@ -49,16 +49,19 @@
 
 static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
 {
-	int i;
+	int i, t;
 	int err = 0;
 
-	for (i = 0; i < priv->tx_ring_num; i++) {
-		priv->tx_cq[i]->moder_cnt = priv->tx_frames;
-		priv->tx_cq[i]->moder_time = priv->tx_usecs;
-		if (priv->port_up) {
-			err = mlx4_en_set_cq_moder(priv, priv->tx_cq[i]);
-			if (err)
-				return err;
+	for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
+		for (i = 0; i < priv->tx_ring_num[t]; i++) {
+			priv->tx_cq[t][i]->moder_cnt = priv->tx_frames;
+			priv->tx_cq[t][i]->moder_time = priv->tx_usecs;
+			if (priv->port_up) {
+				err = mlx4_en_set_cq_moder(priv,
+							   priv->tx_cq[t][i]);
+				if (err)
+					return err;
+			}
 		}
 	}
 
@@ -192,6 +195,10 @@ static const char main_strings[][ETH_GSTRING_LEN] = {
 	"tx_prio_7_packets", "tx_prio_7_bytes",
 	"tx_novlan_packets", "tx_novlan_bytes",
 
+	/* xdp statistics */
+	"rx_xdp_drop",
+	"rx_xdp_tx",
+	"rx_xdp_tx_full",
 };
 
 static const char mlx4_en_test_names[][ETH_GSTRING_LEN]= {
@@ -336,8 +343,8 @@ static int mlx4_en_get_sset_count(struct net_device *dev, int sset)
 	switch (sset) {
 	case ETH_SS_STATS:
 		return bitmap_iterator_count(&it) +
-			(priv->tx_ring_num * 2) +
-			(priv->rx_ring_num * 3);
+			(priv->tx_ring_num[TX] * 2) +
+			(priv->rx_ring_num * (3 + NUM_XDP_STATS));
 	case ETH_SS_TEST:
 		return MLX4_EN_NUM_SELF_TEST - !(priv->mdev->dev->caps.flags
 					& MLX4_DEV_CAP_FLAG_UC_LOOPBACK) * 2;
@@ -397,14 +404,21 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
 		if (bitmap_iterator_test(&it))
 			data[index++] = ((unsigned long *)&priv->pkstats)[i];
 
-	for (i = 0; i < priv->tx_ring_num; i++) {
-		data[index++] = priv->tx_ring[i]->packets;
-		data[index++] = priv->tx_ring[i]->bytes;
+	for (i = 0; i < NUM_XDP_STATS; i++, bitmap_iterator_inc(&it))
+		if (bitmap_iterator_test(&it))
+			data[index++] = ((unsigned long *)&priv->xdp_stats)[i];
+
+	for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+		data[index++] = priv->tx_ring[TX][i]->packets;
+		data[index++] = priv->tx_ring[TX][i]->bytes;
 	}
 	for (i = 0; i < priv->rx_ring_num; i++) {
 		data[index++] = priv->rx_ring[i]->packets;
 		data[index++] = priv->rx_ring[i]->bytes;
 		data[index++] = priv->rx_ring[i]->dropped;
+		data[index++] = priv->rx_ring[i]->xdp_drop;
+		data[index++] = priv->rx_ring[i]->xdp_tx;
+		data[index++] = priv->rx_ring[i]->xdp_tx_full;
 	}
 	spin_unlock_bh(&priv->stats_lock);
 
@@ -467,7 +481,13 @@ static void mlx4_en_get_strings(struct net_device *dev,
 				strcpy(data + (index++) * ETH_GSTRING_LEN,
 				       main_strings[strings]);
 
-		for (i = 0; i < priv->tx_ring_num; i++) {
+		for (i = 0; i < NUM_XDP_STATS; i++, strings++,
+		     bitmap_iterator_inc(&it))
+			if (bitmap_iterator_test(&it))
+				strcpy(data + (index++) * ETH_GSTRING_LEN,
+				       main_strings[strings]);
+
+		for (i = 0; i < priv->tx_ring_num[TX]; i++) {
 			sprintf(data + (index++) * ETH_GSTRING_LEN,
 				"tx%d_packets", i);
 			sprintf(data + (index++) * ETH_GSTRING_LEN,
@@ -480,6 +500,12 @@ static void mlx4_en_get_strings(struct net_device *dev,
 				"rx%d_bytes", i);
 			sprintf(data + (index++) * ETH_GSTRING_LEN,
 				"rx%d_dropped", i);
+			sprintf(data + (index++) * ETH_GSTRING_LEN,
+				"rx%d_xdp_drop", i);
+			sprintf(data + (index++) * ETH_GSTRING_LEN,
+				"rx%d_xdp_tx", i);
+			sprintf(data + (index++) * ETH_GSTRING_LEN,
+				"rx%d_xdp_tx_full", i);
 		}
 		break;
 	case ETH_SS_PRIV_FLAGS:
@@ -1060,7 +1086,7 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
 
 	if (rx_size == (priv->port_up ? priv->rx_ring[0]->actual_size :
 					priv->rx_ring[0]->size) &&
-	    tx_size == priv->tx_ring[0]->size)
+	    tx_size == priv->tx_ring[TX][0]->size)
 		return 0;
 
 	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
@@ -1105,7 +1131,7 @@ static void mlx4_en_get_ringparam(struct net_device *dev,
 	param->tx_max_pending = MLX4_EN_MAX_TX_SIZE;
 	param->rx_pending = priv->port_up ?
 		priv->rx_ring[0]->actual_size : priv->rx_ring[0]->size;
-	param->tx_pending = priv->tx_ring[0]->size;
+	param->tx_pending = priv->tx_ring[TX][0]->size;
 }
 
 static u32 mlx4_en_get_rxfh_indir_size(struct net_device *dev)
@@ -1710,7 +1736,7 @@ static void mlx4_en_get_channels(struct net_device *dev,
 	channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP;
 
 	channel->rx_count = priv->rx_ring_num;
-	channel->tx_count = priv->tx_ring_num / MLX4_EN_NUM_UP;
+	channel->tx_count = priv->tx_ring_num[TX] / MLX4_EN_NUM_UP;
 }
 
 static int mlx4_en_set_channels(struct net_device *dev,
@@ -1721,6 +1747,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	struct mlx4_en_port_profile new_prof;
 	struct mlx4_en_priv *tmp;
 	int port_up = 0;
+	int xdp_count;
 	int err = 0;
 
 	if (channel->other_count || channel->combined_count ||
@@ -1729,20 +1756,25 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	    !channel->tx_count || !channel->rx_count)
 		return -EINVAL;
 
-	if (channel->tx_count * MLX4_EN_NUM_UP <= priv->xdp_ring_num) {
-		en_err(priv, "Minimum %d tx channels required with XDP on\n",
-		       priv->xdp_ring_num / MLX4_EN_NUM_UP + 1);
-		return -EINVAL;
-	}
-
 	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
 	if (!tmp)
 		return -ENOMEM;
 
 	mutex_lock(&mdev->state_lock);
+	xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0;
+	if (channel->tx_count * MLX4_EN_NUM_UP + xdp_count > MAX_TX_RINGS) {
+		err = -EINVAL;
+		en_err(priv,
+		       "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
+		       channel->tx_count * MLX4_EN_NUM_UP + xdp_count,
+		       MAX_TX_RINGS);
+		goto out;
+	}
+
 	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
 	new_prof.num_tx_rings_p_up = channel->tx_count;
-	new_prof.tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP;
+	new_prof.tx_ring_num[TX] = channel->tx_count * MLX4_EN_NUM_UP;
+	new_prof.tx_ring_num[TX_XDP] = xdp_count;
 	new_prof.rx_ring_num = channel->rx_count;
 
 	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
@@ -1756,14 +1788,13 @@ static int mlx4_en_set_channels(struct net_device *dev,
 
 	mlx4_en_safe_replace_resources(priv, tmp);
 
-	netif_set_real_num_tx_queues(dev, priv->tx_ring_num -
-							priv->xdp_ring_num);
+	netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
 	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
 
 	if (dev->num_tc)
 		mlx4_en_setup_tc(dev, MLX4_EN_NUM_UP);
 
-	en_warn(priv, "Using %d TX rings\n", priv->tx_ring_num);
+	en_warn(priv, "Using %d TX rings\n", priv->tx_ring_num[TX]);
 	en_warn(priv, "Using %d RX rings\n", priv->rx_ring_num);
 
 	if (port_up) {
@@ -1774,8 +1805,8 @@ static int mlx4_en_set_channels(struct net_device *dev,
 
 	err = mlx4_en_moderation_update(priv);
 out:
-	kfree(tmp);
 	mutex_unlock(&mdev->state_lock);
+	kfree(tmp);
 	return err;
 }
 
@@ -1823,11 +1854,15 @@ static int mlx4_en_set_priv_flags(struct net_device *dev, u32 flags)
 	int ret = 0;
 
 	if (bf_enabled_new != bf_enabled_old) {
+		int t;
+
 		if (bf_enabled_new) {
 			bool bf_supported = true;
 
-			for (i = 0; i < priv->tx_ring_num; i++)
-				bf_supported &= priv->tx_ring[i]->bf_alloced;
+			for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++)
+				for (i = 0; i < priv->tx_ring_num[t]; i++)
+					bf_supported &=
+						priv->tx_ring[t][i]->bf_alloced;
 
 			if (!bf_supported) {
 				en_err(priv, "BlueFlame is not supported\n");
@@ -1839,8 +1874,10 @@ static int mlx4_en_set_priv_flags(struct net_device *dev, u32 flags)
 			priv->pflags &= ~MLX4_EN_PRIV_FLAGS_BLUEFLAME;
 		}
 
-		for (i = 0; i < priv->tx_ring_num; i++)
-			priv->tx_ring[i]->bf_enabled = bf_enabled_new;
+		for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++)
+			for (i = 0; i < priv->tx_ring_num[t]; i++)
+				priv->tx_ring[t][i]->bf_enabled =
+					bf_enabled_new;
 
 		en_info(priv, "BlueFlame %s\n",
 			bf_enabled_new ?  "Enabled" : "Disabled");

drivers/net/ethernet/mellanox/mlx4/en_main.c

@@ -169,7 +169,7 @@ static int mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 		params->prof[i].tx_ppp = pfctx;
 		params->prof[i].tx_ring_size = MLX4_EN_DEF_TX_RING_SIZE;
 		params->prof[i].rx_ring_size = MLX4_EN_DEF_RX_RING_SIZE;
-		params->prof[i].tx_ring_num = params->num_tx_rings_p_up *
+		params->prof[i].tx_ring_num[TX] = params->num_tx_rings_p_up *
 			MLX4_EN_NUM_UP;
 		params->prof[i].rss_rings = 0;
 		params->prof[i].inline_thold = inline_thold;