net/mlx5e: xsk: Use umr_mode to calculate striding RQ parameters

Instead of passing the unaligned flag, pass an enum that indicates the
UMR mode. The next commit will add the third mode (KLM for certain
configurations of XSK), which will be added to this enum instead of
adding another bool flag everywhere.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

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

@@ -681,6 +681,11 @@ struct mlx5e_hw_gro_data {
 	int second_ip_id;
 };
 
+enum mlx5e_mpwrq_umr_mode {
+	MLX5E_MPWRQ_UMR_MODE_ALIGNED,
+	MLX5E_MPWRQ_UMR_MODE_UNALIGNED,
+};
+
 struct mlx5e_rq {
 	/* data path */
 	union {
@@ -708,7 +713,7 @@ struct mlx5e_rq {
 			u8                     pages_per_wqe;
 			u8                     umr_wqebbs;
 			u8                     mtts_per_wqe;
-			u8                     unaligned;
+			u8                     umr_mode;
 			struct mlx5e_shampo_hd *shampo;
 		} mpwqe;
 	};
@@ -1008,7 +1013,7 @@ struct mlx5e_profile {
 void mlx5e_build_ptys2ethtool_map(void);
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift,
-					    bool unaligned);
+					    enum mlx5e_mpwrq_umr_mode umr_mode);
 
 void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq, u16 len, u16 start, bool close);
 void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);

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

@@ -56,13 +56,23 @@ struct mlx5e_create_sq_param {
 /* Striding RQ dynamic parameters */
 
 u8 mlx5e_mpwrq_page_shift(struct mlx5_core_dev *mdev, struct mlx5e_xsk_param *xsk);
-u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
-u8 mlx5e_mpwrq_pages_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
-u16 mlx5e_mpwrq_umr_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
-u8 mlx5e_mpwrq_umr_wqebbs(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
-u8 mlx5e_mpwrq_mtts_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
-u32 mlx5e_mpwrq_max_num_entries(struct mlx5_core_dev *mdev, bool unaligned);
-u8 mlx5e_mpwrq_max_log_rq_pkts(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
+enum mlx5e_mpwrq_umr_mode
+mlx5e_mpwrq_umr_mode(struct mlx5_core_dev *mdev, struct mlx5e_xsk_param *xsk);
+u8 mlx5e_mpwrq_umr_entry_size(enum mlx5e_mpwrq_umr_mode mode);
+u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift,
+			  enum mlx5e_mpwrq_umr_mode umr_mode);
+u8 mlx5e_mpwrq_pages_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift,
+			     enum mlx5e_mpwrq_umr_mode umr_mode);
+u16 mlx5e_mpwrq_umr_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift,
+			   enum mlx5e_mpwrq_umr_mode umr_mode);
+u8 mlx5e_mpwrq_umr_wqebbs(struct mlx5_core_dev *mdev, u8 page_shift,
+			  enum mlx5e_mpwrq_umr_mode umr_mode);
+u8 mlx5e_mpwrq_mtts_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift,
+			    enum mlx5e_mpwrq_umr_mode umr_mode);
+u32 mlx5e_mpwrq_max_num_entries(struct mlx5_core_dev *mdev,
+				enum mlx5e_mpwrq_umr_mode umr_mode);
+u8 mlx5e_mpwrq_max_log_rq_pkts(struct mlx5_core_dev *mdev, u8 page_shift,
+			       enum mlx5e_mpwrq_umr_mode umr_mode);
 
 /* Parameter calculations */
 

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c

@@ -41,7 +41,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
 	memcpy(umr_wqe, &rq->mpwqe.umr_wqe, sizeof(struct mlx5e_umr_wqe));
 
-	if (unlikely(rq->mpwqe.unaligned)) {
+	if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_UNALIGNED)) {
 		for (i = 0; i < batch; i++) {
 			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
 
@@ -67,7 +67,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 		cpu_to_be32((icosq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) | MLX5_OPCODE_UMR);
 
 	offset = ix * rq->mpwqe.mtts_per_wqe;
-	if (likely(!rq->mpwqe.unaligned))
+	if (likely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_ALIGNED))
 		offset = MLX5_ALIGNED_MTTS_OCTW(offset);
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
 

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

@@ -314,7 +314,9 @@ void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv,
 	/* Limitation for regular RQ. XSK RQ may clamp the queue length in
 	 * mlx5e_mpwqe_get_log_rq_size.
 	 */
-	u8 max_log_mpwrq_pkts = mlx5e_mpwrq_max_log_rq_pkts(priv->mdev, PAGE_SHIFT, false);
+	u8 max_log_mpwrq_pkts = mlx5e_mpwrq_max_log_rq_pkts(priv->mdev,
+							    PAGE_SHIFT,
+							    MLX5E_MPWRQ_UMR_MODE_ALIGNED);
 
 	param->rx_max_pending = 1 << min_t(u8, MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE,
 					   max_log_mpwrq_pkts);

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

@@ -69,7 +69,7 @@
 #include "en/trap.h"
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift,
-					    bool unaligned)
+					    enum mlx5e_mpwrq_umr_mode umr_mode)
 {
 	u16 umr_wqebbs, max_wqebbs;
 	bool striding_rq_umr;
@@ -79,7 +79,7 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_
 	if (!striding_rq_umr)
 		return false;
 
-	umr_wqebbs = mlx5e_mpwrq_umr_wqebbs(mdev, page_shift, unaligned);
+	umr_wqebbs = mlx5e_mpwrq_umr_wqebbs(mdev, page_shift, umr_mode);
 	max_wqebbs = mlx5e_get_max_sq_aligned_wqebbs(mdev);
 	/* Sanity check; should never happen, because mlx5e_mpwrq_umr_wqebbs is
 	 * calculated from mlx5e_get_max_sq_aligned_wqebbs.
@@ -203,6 +203,18 @@ static void mlx5e_disable_blocking_events(struct mlx5e_priv *priv)
 	mlx5_blocking_notifier_unregister(priv->mdev, &priv->blocking_events_nb);
 }
 
+static u16 mlx5e_mpwrq_umr_octowords(u32 entries, enum mlx5e_mpwrq_umr_mode umr_mode)
+{
+	switch (umr_mode) {
+	case MLX5E_MPWRQ_UMR_MODE_ALIGNED:
+		return MLX5_MTT_OCTW(entries);
+	case MLX5E_MPWRQ_UMR_MODE_UNALIGNED:
+		return MLX5_KSM_OCTW(entries);
+	}
+	WARN_ONCE(1, "MPWRQ UMR mode %d is not known\n", umr_mode);
+	return 0;
+}
+
 static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 				       struct mlx5e_icosq *sq,
 				       struct mlx5e_umr_wqe *wqe)
@@ -213,7 +225,7 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 	u8 ds_cnt;
 
 	ds_cnt = DIV_ROUND_UP(mlx5e_mpwrq_umr_wqe_sz(rq->mdev, rq->mpwqe.page_shift,
-						     rq->mpwqe.unaligned),
+						     rq->mpwqe.umr_mode),
 			      MLX5_SEND_WQE_DS);
 
 	cseg->qpn_ds    = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
@@ -221,8 +233,7 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 	cseg->umr_mkey  = rq->mpwqe.umr_mkey_be;
 
 	ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
-	octowords = rq->mpwqe.unaligned ? MLX5_KSM_OCTW(rq->mpwqe.pages_per_wqe) :
-					  MLX5_MTT_OCTW(rq->mpwqe.pages_per_wqe);
+	octowords = mlx5e_mpwrq_umr_octowords(rq->mpwqe.pages_per_wqe, rq->mpwqe.umr_mode);
 	ucseg->xlt_octowords = cpu_to_be16(octowords);
 	ucseg->mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
 }
@@ -283,9 +294,23 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node)
 	return 0;
 }
 
+
+static u8 mlx5e_mpwrq_access_mode(enum mlx5e_mpwrq_umr_mode umr_mode)
+{
+	switch (umr_mode) {
+	case MLX5E_MPWRQ_UMR_MODE_ALIGNED:
+		return MLX5_MKC_ACCESS_MODE_MTT;
+	case MLX5E_MPWRQ_UMR_MODE_UNALIGNED:
+		return MLX5_MKC_ACCESS_MODE_KSM;
+	}
+	WARN_ONCE(1, "MPWRQ UMR mode %d is not known\n", umr_mode);
+	return 0;
+}
+
 static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 				 u32 npages, u8 page_shift, u32 *umr_mkey,
-				 dma_addr_t filler_addr, bool unaligned)
+				 dma_addr_t filler_addr,
+				 enum mlx5e_mpwrq_umr_mode umr_mode)
 {
 	struct mlx5_mtt *mtt;
 	struct mlx5_ksm *ksm;
@@ -296,14 +321,16 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 	int err;
 	int i;
 
-	if (unaligned && !MLX5_CAP_GEN(mdev, fixed_buffer_size)) {
+	if (umr_mode == MLX5E_MPWRQ_UMR_MODE_UNALIGNED &&
+	    !MLX5_CAP_GEN(mdev, fixed_buffer_size)) {
 		mlx5_core_warn(mdev, "Unaligned AF_XDP requires fixed_buffer_size capability\n");
 		return -EINVAL;
 	}
 
+	octwords = mlx5e_mpwrq_umr_octowords(npages, umr_mode);
+
 	inlen = MLX5_FLEXIBLE_INLEN(mdev, MLX5_ST_SZ_BYTES(create_mkey_in),
-				    unaligned ? sizeof(*ksm) : sizeof(*mtt),
-				    npages);
+				    MLX5_OCTWORD, octwords);
 	if (inlen < 0)
 		return inlen;
 
@@ -311,16 +338,13 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 	if (!in)
 		return -ENOMEM;
 
-	octwords = unaligned ? MLX5_KSM_OCTW(npages) : MLX5_MTT_OCTW(npages);
-
 	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
 
 	MLX5_SET(mkc, mkc, free, 1);
 	MLX5_SET(mkc, mkc, umr_en, 1);
 	MLX5_SET(mkc, mkc, lw, 1);
 	MLX5_SET(mkc, mkc, lr, 1);
-	MLX5_SET(mkc, mkc, access_mode_1_0,
-		 unaligned ? MLX5_MKC_ACCESS_MODE_KSM : MLX5_MKC_ACCESS_MODE_MTT);
+	MLX5_SET(mkc, mkc, access_mode_1_0, mlx5e_mpwrq_access_mode(umr_mode));
 	mlx5e_mkey_set_relaxed_ordering(mdev, mkc);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
 	MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.hw_objs.pdn);
@@ -335,19 +359,22 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 	 * the RQ's pool, while the gaps (wqe_overflow) remain mapped
 	 * to the default page.
 	 */
-	if (unaligned) {
+	switch (umr_mode) {
+	case MLX5E_MPWRQ_UMR_MODE_UNALIGNED:
 		ksm = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
 		for (i = 0; i < npages; i++)
 			ksm[i] = (struct mlx5_ksm) {
 				.key = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey),
 				.va = cpu_to_be64(filler_addr),
 			};
-	} else {
+		break;
+	case MLX5E_MPWRQ_UMR_MODE_ALIGNED:
 		mtt = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
 		for (i = 0; i < npages; i++)
 			mtt[i] = (struct mlx5_mtt) {
 				.ptag = cpu_to_be64(filler_addr),
 			};
+		break;
 	}
 
 	err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen);
@@ -396,7 +423,7 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
 	u32 umr_mkey;
 	int err;
 
-	max_num_entries = mlx5e_mpwrq_max_num_entries(mdev, rq->mpwqe.unaligned);
+	max_num_entries = mlx5e_mpwrq_max_num_entries(mdev, rq->mpwqe.umr_mode);
 
 	/* Shouldn't overflow, the result is at most MLX5E_MAX_RQ_NUM_MTTS. */
 	if (WARN_ON_ONCE(check_mul_overflow(wq_size, (u32)rq->mpwqe.mtts_per_wqe,
@@ -408,7 +435,7 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
 
 	err = mlx5e_create_umr_mkey(mdev, num_entries, rq->mpwqe.page_shift,
 				    &umr_mkey, rq->wqe_overflow.addr,
-				    rq->mpwqe.unaligned);
+				    rq->mpwqe.umr_mode);
 	rq->mpwqe.umr_mkey_be = cpu_to_be32(umr_mkey);
 	return err;
 }
@@ -644,16 +671,16 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 		wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
 		rq->mpwqe.page_shift = mlx5e_mpwrq_page_shift(mdev, xsk);
-		rq->mpwqe.unaligned = xsk ? xsk->unaligned : false;
+		rq->mpwqe.umr_mode = mlx5e_mpwrq_umr_mode(mdev, xsk);
 		rq->mpwqe.pages_per_wqe =
 			mlx5e_mpwrq_pages_per_wqe(mdev, rq->mpwqe.page_shift,
-						  rq->mpwqe.unaligned);
+						  rq->mpwqe.umr_mode);
 		rq->mpwqe.umr_wqebbs =
 			mlx5e_mpwrq_umr_wqebbs(mdev, rq->mpwqe.page_shift,
-					       rq->mpwqe.unaligned);
+					       rq->mpwqe.umr_mode);
 		rq->mpwqe.mtts_per_wqe =
 			mlx5e_mpwrq_mtts_per_wqe(mdev, rq->mpwqe.page_shift,
-						 rq->mpwqe.unaligned);
+						 rq->mpwqe.umr_mode);
 
 		pool_size = rq->mpwqe.pages_per_wqe <<
 			mlx5e_mpwqe_get_log_rq_size(mdev, params, xsk);
@@ -5012,7 +5039,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	if (!!MLX5_CAP_ETH(mdev, lro_cap) &&
 	    !MLX5_CAP_ETH(mdev, tunnel_lro_vxlan) &&
 	    !MLX5_CAP_ETH(mdev, tunnel_lro_gre) &&
-	    mlx5e_check_fragmented_striding_rq_cap(mdev, PAGE_SHIFT, false))
+	    mlx5e_check_fragmented_striding_rq_cap(mdev, PAGE_SHIFT,
+						   MLX5E_MPWRQ_UMR_MODE_ALIGNED))
 		netdev->vlan_features    |= NETIF_F_LRO;
 
 	netdev->hw_features       = netdev->vlan_features;

include/linux/mlx5/driver.h

@@ -1288,4 +1288,8 @@ static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev)
 	return mlx5_is_roce_on(dev);
 }
 
+enum {
+	MLX5_OCTWORD = 16,
+};
+
 #endif /* MLX5_DRIVER_H */