net/mlx5e: Derive Striding RQ size from MTU

In Striding RQ, each WQE serves multiple packets
(hence called Multi-Packet WQE, MPWQE).
The size of a MPWQE is constant (currently 256KB).

Upon a ringparam set operation, we calculate the number of
MPWQEs per RQ. For this, first it is needed to determine the
number of packets that can reside within a single MPWQE.
In this patch we use the actual MTU size instead of ETH_DATA_LEN
for this calculation.

This implies that a change in MTU might require a change
in Striding RQ ring size.

In addition, this obsoletes some WQEs-to-packets translation
functions and helps delete ~60 LOC.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -63,18 +63,6 @@
 #define MLX5E_MAX_DSCP          64
 #define MLX5E_MAX_NUM_TC	8
 
-#define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE                0x6
-#define MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE                0xa
-#define MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE                0xd
-
-#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE                0x1
-#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE                0xa
-#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE                0xd
-
-#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW            0x2
-#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW            0x3
-#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW            0x6
-
 #define MLX5_RX_HEADROOM NET_SKB_PAD
 #define MLX5_SKB_FRAG_SZ(len)	(SKB_DATA_ALIGN(len) +	\
 				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
@@ -95,9 +83,27 @@
 #define MLX5_MPWRQ_PAGES_PER_WQE		BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)
 
 #define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
-#define MLX5E_REQUIRED_MTTS(wqes)		\
-	(wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
-#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) - 1 <= U16_MAX)
+#define MLX5E_REQUIRED_WQE_MTTS		(ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
+#define MLX5E_REQUIRED_MTTS(wqes)	(wqes * MLX5E_REQUIRED_WQE_MTTS)
+#define MLX5E_MAX_RQ_NUM_MTTS	\
+	((1 << 16) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */
+#define MLX5E_ORDER2_MAX_PACKET_MTU (order_base_2(10 * 1024))
+#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW	\
+		(ilog2(MLX5E_MAX_RQ_NUM_MTTS / MLX5E_REQUIRED_WQE_MTTS))
+#define MLX5E_LOG_MAX_RQ_NUM_PACKETS_MPW \
+	(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW + \
+	 (MLX5_MPWRQ_LOG_WQE_SZ - MLX5E_ORDER2_MAX_PACKET_MTU))
+
+#define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE                0x6
+#define MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE                0xa
+#define MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE                0xd
+
+#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE                0x1
+#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE                0xa
+#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE min_t(u8, 0xd,	\
+					       MLX5E_LOG_MAX_RQ_NUM_PACKETS_MPW)
+
+#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW            0x2
 
 #define MLX5_UMR_ALIGN				(2048)
 #define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(256)
@@ -155,26 +161,6 @@ static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size)
 	}
 }
 
-static inline int mlx5_min_log_rq_size(int wq_type)
-{
-	switch (wq_type) {
-	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW;
-	default:
-		return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
-	}
-}
-
-static inline int mlx5_max_log_rq_size(int wq_type)
-{
-	switch (wq_type) {
-	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		return MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW;
-	default:
-		return MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE;
-	}
-}
-
 static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 {
 	return is_kdump_kernel() ?
@@ -233,7 +219,7 @@ enum mlx5e_priv_flag {
 struct mlx5e_params {
 	u8  log_sq_size;
 	u8  rq_wq_type;
-	u8  log_rq_size;
+	u8  log_rq_mtu_frames;
 	u16 num_channels;
 	u8  num_tc;
 	bool rx_cqe_compress_def;
@@ -849,11 +835,6 @@ void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi);
 
-u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params);
-u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params);
-
 void mlx5e_update_stats(struct mlx5e_priv *priv);
 
 int mlx5e_create_flow_steering(struct mlx5e_priv *priv);

drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c

@@ -220,60 +220,12 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 	mlx5e_ethtool_get_ethtool_stats(priv, stats, data);
 }
 
-static u32 mlx5e_rx_wqes_to_packets(struct mlx5e_priv *priv, int rq_wq_type,
-				    int num_wqe)
-{
-	int packets_per_wqe;
-	int stride_size;
-	int num_strides;
-	int wqe_size;
-
-	if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		return num_wqe;
-
-	stride_size = 1 << mlx5e_mpwqe_get_log_stride_size(priv->mdev, &priv->channels.params);
-	num_strides = 1 << mlx5e_mpwqe_get_log_num_strides(priv->mdev, &priv->channels.params);
-	wqe_size = stride_size * num_strides;
-
-	packets_per_wqe = wqe_size /
-			  ALIGN(ETH_DATA_LEN, stride_size);
-	return (1 << (order_base_2(num_wqe * packets_per_wqe) - 1));
-}
-
-static u32 mlx5e_packets_to_rx_wqes(struct mlx5e_priv *priv, int rq_wq_type,
-				    int num_packets)
-{
-	int packets_per_wqe;
-	int stride_size;
-	int num_strides;
-	int wqe_size;
-	int num_wqes;
-
-	if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		return num_packets;
-
-	stride_size = 1 << mlx5e_mpwqe_get_log_stride_size(priv->mdev, &priv->channels.params);
-	num_strides = 1 << mlx5e_mpwqe_get_log_num_strides(priv->mdev, &priv->channels.params);
-	wqe_size = stride_size * num_strides;
-
-	num_packets = (1 << order_base_2(num_packets));
-
-	packets_per_wqe = wqe_size /
-			  ALIGN(ETH_DATA_LEN, stride_size);
-	num_wqes = DIV_ROUND_UP(num_packets, packets_per_wqe);
-	return 1 << (order_base_2(num_wqes));
-}
-
 void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv,
 				 struct ethtool_ringparam *param)
 {
-	int rq_wq_type = priv->channels.params.rq_wq_type;
-
-	param->rx_max_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
-							 1 << mlx5_max_log_rq_size(rq_wq_type));
+	param->rx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE;
 	param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
-	param->rx_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
-						     1 << priv->channels.params.log_rq_size);
+	param->rx_pending     = 1 << priv->channels.params.log_rq_mtu_frames;
 	param->tx_pending     = 1 << priv->channels.params.log_sq_size;
 }
 
@@ -288,13 +240,9 @@ static void mlx5e_get_ringparam(struct net_device *dev,
 int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
 				struct ethtool_ringparam *param)
 {
-	int rq_wq_type = priv->channels.params.rq_wq_type;
 	struct mlx5e_channels new_channels = {};
-	u32 rx_pending_wqes;
-	u32 min_rq_size;
 	u8 log_rq_size;
 	u8 log_sq_size;
-	u32 num_mtts;
 	int err = 0;
 
 	if (param->rx_jumbo_pending) {
@@ -308,23 +256,10 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
 		return -EINVAL;
 	}
 
-	min_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
-					       1 << mlx5_min_log_rq_size(rq_wq_type));
-	rx_pending_wqes = mlx5e_packets_to_rx_wqes(priv, rq_wq_type,
-						   param->rx_pending);
-
-	if (param->rx_pending < min_rq_size) {
+	if (param->rx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)) {
 		netdev_info(priv->netdev, "%s: rx_pending (%d) < min (%d)\n",
 			    __func__, param->rx_pending,
-			    min_rq_size);
-		return -EINVAL;
-	}
-
-	num_mtts = MLX5E_REQUIRED_MTTS(rx_pending_wqes);
-	if (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
-	    !MLX5E_VALID_NUM_MTTS(num_mtts)) {
-		netdev_info(priv->netdev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n",
-			    __func__, param->rx_pending);
+			    1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE);
 		return -EINVAL;
 	}
 
@@ -335,17 +270,17 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
 		return -EINVAL;
 	}
 
-	log_rq_size = order_base_2(rx_pending_wqes);
+	log_rq_size = order_base_2(param->rx_pending);
 	log_sq_size = order_base_2(param->tx_pending);
 
-	if (log_rq_size == priv->channels.params.log_rq_size &&
+	if (log_rq_size == priv->channels.params.log_rq_mtu_frames &&
 	    log_sq_size == priv->channels.params.log_sq_size)
 		return 0;
 
 	mutex_lock(&priv->state_lock);
 
 	new_channels.params = priv->channels.params;
-	new_channels.params.log_rq_size = log_rq_size;
+	new_channels.params.log_rq_mtu_frames = log_rq_size;
 	new_channels.params.log_sq_size = log_sq_size;
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -78,14 +78,37 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 		MLX5_CAP_ETH(mdev, reg_umr_sq);
 }
 
-u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
+static u32 mlx5e_mpwqe_get_linear_frag_sz(struct mlx5e_params *params)
+{
+	u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+
+	return hw_mtu;
+}
+
+static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
+{
+	u32 linear_frag_sz = mlx5e_mpwqe_get_linear_frag_sz(params);
+
+	return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
+}
+
+static u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params)
+{
+	if (params->log_rq_mtu_frames <
+	    mlx5e_mpwqe_log_pkts_per_wqe(params) + MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW)
+		return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW;
+
+	return params->log_rq_mtu_frames - mlx5e_mpwqe_log_pkts_per_wqe(params);
+}
+
+static u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
 					  struct mlx5e_params *params)
 {
 	return MLX5E_MPWQE_STRIDE_SZ(mdev,
 		MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
 }
 
-u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
+static u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
 					  struct mlx5e_params *params)
 {
 	return MLX5_MPWRQ_LOG_WQE_SZ -
@@ -109,17 +132,13 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params)
 {
 	params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
+	params->log_rq_mtu_frames = is_kdump_kernel() ?
+		MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
+		MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		params->log_rq_size = is_kdump_kernel() ?
-			MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW :
-			MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		params->log_rq_size = is_kdump_kernel() ?
-			MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
-			MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
-
 		/* Extra room needed for build_skb */
 		params->lro_wqe_sz -= mlx5e_get_rq_headroom(params) +
 			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
@@ -127,7 +146,7 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 
 	mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
 		       params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
-		       BIT(params->log_rq_size),
+		       BIT(params->log_rq_mtu_frames),
 		       BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params)),
 		       MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
 }
@@ -351,9 +370,6 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 	u32 *in;
 	int err;
 
-	if (!MLX5E_VALID_NUM_MTTS(npages))
-		return -EINVAL;
-
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -1872,14 +1888,15 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 		MLX5_SET(wq, wq, log_wqe_stride_size,
 			 mlx5e_mpwqe_get_log_stride_size(mdev, params) - 6);
 		MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
+		MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params));
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
+		MLX5_SET(wq, wq, log_wq_sz, params->log_rq_mtu_frames);
 	}
 
 	MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
 	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
-	MLX5_SET(wq, wq, log_wq_sz,        params->log_rq_size);
 	MLX5_SET(wq, wq, pd,               mdev->mlx5e_res.pdn);
 	MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter);
 	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
@@ -1939,16 +1956,17 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 				    struct mlx5e_params *params,
 				    struct mlx5e_cq_param *param)
 {
+	struct mlx5_core_dev *mdev = priv->mdev;
 	void *cqc = param->cqc;
 	u8 log_cq_size;
 
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		log_cq_size = params->log_rq_size +
-			mlx5e_mpwqe_get_log_num_strides(priv->mdev, params);
+		log_cq_size = mlx5e_mpwqe_get_log_rq_size(params) +
+			mlx5e_mpwqe_get_log_num_strides(mdev, params);
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
-		log_cq_size = params->log_rq_size;
+		log_cq_size = params->log_rq_mtu_frames;
 	}
 
 	MLX5_SET(cqc, cqc, log_cq_size, log_cq_size);
@@ -3421,11 +3439,20 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 	mutex_lock(&priv->state_lock);
 
 	params = &priv->channels.params;
-	reset = !params->lro_en &&
-		(params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
 
+	reset = !params->lro_en;
 	reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
 
+	new_channels.params = *params;
+	new_channels.params.sw_mtu = new_mtu;
+
+	if (params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) {
+		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
+		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
+
+		reset = reset && (ppw_old != ppw_new);
+	}
+
 	if (!reset) {
 		params->sw_mtu = new_mtu;
 		mlx5e_set_dev_port_mtu(priv);
@@ -3433,8 +3460,6 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 		goto out;
 	}
 
-	new_channels.params = *params;
-	new_channels.params.sw_mtu = new_mtu;
 	err = mlx5e_open_channels(priv, &new_channels);
 	if (err)
 		goto out;

drivers/net/ethernet/mellanox/mlx5/core/en_rep.c

@@ -880,7 +880,7 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 	params->hard_mtu    = MLX5E_ETH_HARD_MTU;
 	params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
 	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
-	params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+	params->log_rq_mtu_frames = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
 
 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
 	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);

drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c

@@ -61,7 +61,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
 	mlx5e_init_rq_type_params(mdev, params);
 
 	/* RQ size in ipoib by default is 512 */
-	params->log_rq_size = is_kdump_kernel() ?
+	params->log_rq_mtu_frames = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
 		MLX5I_PARAMS_DEFAULT_LOG_RQ_SIZE;
 

drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c

@@ -290,7 +290,7 @@ static void mlx5i_pkey_init(struct mlx5_core_dev *mdev,
 	netdev->ethtool_ops = &mlx5i_pkey_ethtool_ops;
 
 	/* Use dummy rqs */
-	priv->channels.params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+	priv->channels.params.log_rq_mtu_frames = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
 }
 
 /* Called directly before IPoIB netdevice is destroyed to cleanup SW structs */