net/mlx5e: RX, Mind the MPWQE gaps when calculating offsets

stable inclusion
from stable-5.10.27
commit 60b5ff15b41d0904a3806dab6f0f147258294d1e
bugzilla: 51493

--------------------------------

[ Upstream commit d5dd03b2 ]

Since cited patch, MLX5E_REQUIRED_WQE_MTTS is not a power of two.
Hence, usage of MLX5E_LOG_ALIGNED_MPWQE_PPW should be replaced,
as it lost some accuracy. Use the designated macro to calculate
the number of required MTTs.

This makes sure the solution in cited patch works properly.

While here, un-inline mlx5e_get_mpwqe_offset(), and remove the
unused RQ parameter.

Fixes: c3c94023 ("net/mlx5e: Add resiliency in Striding RQ mode for packets larger than MTU")
Signed-off-by: NTariq Toukan <tariqt@nvidia.com>
Signed-off-by: NSaeed Mahameed <saeedm@nvidia.com>
Signed-off-by: NSasha Levin <sashal@kernel.org>
Signed-off-by: NChen Jun <chenjun102@huawei.com>
Acked-by: N  Weilong Chen <chenweilong@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

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

@@ -90,14 +90,15 @@ struct page_pool;
 				    MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT : 0)
 #define MLX5_MPWRQ_PAGES_PER_WQE		BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)
 
-#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
+#define MLX5_ALIGN_MTTS(mtts)		(ALIGN(mtts, 8))
+#define MLX5_ALIGNED_MTTS_OCTW(mtts)	((mtts) / 2)
+#define MLX5_MTT_OCTW(mtts)		(MLX5_ALIGNED_MTTS_OCTW(MLX5_ALIGN_MTTS(mtts)))
 /* Add another page to MLX5E_REQUIRED_WQE_MTTS as a buffer between
  * WQEs, This page will absorb write overflow by the hardware, when
  * receiving packets larger than MTU. These oversize packets are
  * dropped by the driver at a later stage.
  */
-#define MLX5E_REQUIRED_WQE_MTTS		(ALIGN(MLX5_MPWRQ_PAGES_PER_WQE + 1, 8))
-#define MLX5E_LOG_ALIGNED_MPWQE_PPW	(ilog2(MLX5E_REQUIRED_WQE_MTTS))
+#define MLX5E_REQUIRED_WQE_MTTS		(MLX5_ALIGN_MTTS(MLX5_MPWRQ_PAGES_PER_WQE + 1))
 #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 */

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

@@ -303,9 +303,9 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
 				     rq->wqe_overflow.addr);
 }
 
-static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
+static u64 mlx5e_get_mpwqe_offset(u16 wqe_ix)
 {
-	return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT;
+	return MLX5E_REQUIRED_MTTS(wqe_ix) << PAGE_SHIFT;
 }
 
 static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
@@ -544,7 +544,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 				mlx5_wq_ll_get_wqe(&rq->mpwqe.wq, i);
 			u32 byte_count =
 				rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz;
-			u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i);
+			u64 dma_offset = mlx5e_get_mpwqe_offset(i);
 
 			wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom);
 			wqe->data[0].byte_count = cpu_to_be32(byte_count);

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

@@ -506,7 +506,6 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	struct mlx5e_icosq *sq = &rq->channel->icosq;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5e_umr_wqe *umr_wqe;
-	u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1);
 	u16 pi;
 	int err;
 	int i;
@@ -537,7 +536,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	umr_wqe->ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			    MLX5_OPCODE_UMR);
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
+	umr_wqe->uctrl.xlt_offset =
+		cpu_to_be16(MLX5_ALIGNED_MTTS_OCTW(MLX5E_REQUIRED_MTTS(ix)));
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type   = MLX5E_ICOSQ_WQE_UMR_RX,