net/mlx5e: Fix calculations related to max MPWQE size

Before commit 76c31e5f ("net/mlx5e: Use FW limitation for max MPW
WQEBBs"), the maximum size of MPWQE in WQEBBs was hardcoded as a driver
constant. That commit started using the firmware capability that can
further limit the size, however, it unintentionally changed a few
things:

1. The calculation of MLX5E_MAX_KLM_PER_WQE used the size in DS, which
was replaced by the size in WQEBBs, making the resulting value 4 times
smaller.

2. MLX5E_TX_MPW_MAX_WQEBBS used to be aligned to the cache line size
(either 64 or 128 bytes, i.e. 1 or 2 WQEBBs), but it's no longer the
case if the firmware capability is smaller than the driver maximum.

Fix both issues by using the correct units for MLX5E_MAX_KLM_PER_WQE and
by aligning mlx5e_get_sw_max_sq_mpw_wqebbs after taking the minimum.

Besides fixing the arithmetics in calculation of MLX5E_MAX_KLM_PER_WQE,
also use appropriate constants: `size of BSF * num of DS per WQEBB *
number of WQEBBs` (the calculation before the blamed commit) doesn't
make much sense to calculate the WQE size in bytes, so just use `size of
WQEBB * number of WQEBBs`.

While at it, replace the types that hold the number of WQEBBs by u8.
These values don't exceed 16, and it allows to fill holes in two
structs.

Fixes: 76c31e5f ("net/mlx5e: Use FW limitation for max MPW WQEBBs")
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

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

@@ -174,8 +174,8 @@ struct page_pool;
 	ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_ALIGNMENT)
 
 #define MLX5E_MAX_KLM_PER_WQE(mdev) \
-	MLX5E_KLM_ENTRIES_PER_WQE(mlx5e_get_sw_max_sq_mpw_wqebbs(mlx5e_get_max_sq_wqebbs(mdev)) \
-				   << MLX5_MKEY_BSF_OCTO_SIZE)
+	MLX5E_KLM_ENTRIES_PER_WQE(MLX5_SEND_WQE_BB * \
+		mlx5e_get_sw_max_sq_mpw_wqebbs(mlx5e_get_max_sq_wqebbs(mdev)))
 
 #define MLX5E_MSG_LEVEL			NETIF_MSG_LINK
 
@@ -233,7 +233,7 @@ static inline u16 mlx5e_get_max_sq_wqebbs(struct mlx5_core_dev *mdev)
 		     MLX5_CAP_GEN(mdev, max_wqe_sz_sq) / MLX5_SEND_WQE_BB);
 }
 
-static inline u16 mlx5e_get_sw_max_sq_mpw_wqebbs(u16 max_sq_wqebbs)
+static inline u8 mlx5e_get_sw_max_sq_mpw_wqebbs(u8 max_sq_wqebbs)
 {
 /* The return value will be multiplied by MLX5_SEND_WQEBB_NUM_DS.
  * Since max_sq_wqebbs may be up to MLX5_SEND_WQE_MAX_WQEBBS == 16,
@@ -242,11 +242,12 @@ static inline u16 mlx5e_get_sw_max_sq_mpw_wqebbs(u16 max_sq_wqebbs)
  * than MLX5_SEND_WQE_MAX_WQEBBS to let a full-session WQE be
  * cache-aligned.
  */
-#if L1_CACHE_BYTES < 128
-	return min_t(u16, max_sq_wqebbs, MLX5_SEND_WQE_MAX_WQEBBS - 1);
-#else
-	return min_t(u16, max_sq_wqebbs, MLX5_SEND_WQE_MAX_WQEBBS - 2);
+	u8 wqebbs = min_t(u8, max_sq_wqebbs, MLX5_SEND_WQE_MAX_WQEBBS - 1);
+
+#if L1_CACHE_BYTES >= 128
+	wqebbs = ALIGN_DOWN(wqebbs, 2);
 #endif
+	return wqebbs;
 }
 
 struct mlx5e_tx_wqe {
@@ -455,7 +456,7 @@ struct mlx5e_txqsq {
 	struct netdev_queue       *txq;
 	u32                        sqn;
 	u16                        stop_room;
-	u16                        max_sq_mpw_wqebbs;
+	u8                         max_sq_mpw_wqebbs;
 	u8                         min_inline_mode;
 	struct device             *pdev;
 	__be32                     mkey_be;
@@ -570,7 +571,7 @@ struct mlx5e_xdpsq {
 	struct device             *pdev;
 	__be32                     mkey_be;
 	u16                        stop_room;
-	u16                        max_sq_mpw_wqebbs;
+	u8                         max_sq_mpw_wqebbs;
 	u8                         min_inline_mode;
 	unsigned long              state;
 	unsigned int               hw_mtu;