net/mlx5e: SHAMPO, Fix header mapping for 64K pages

HW-GRO is broken on mlx5 for 64K page sizes. The patch in the fixes tag
didn't take into account larger page sizes when doing an align down
of max_ksm_entries. For 64K page size, max_ksm_entries is 0 which will skip
mapping header pages via WQE UMR. This breaks header-data split
and will result in the following syndrome:

mlx5_core 0000:00:08.0 eth2: Error cqe on cqn 0x4c9, ci 0x0, qn 0x1133, opcode 0xe, syndrome 0x4, vendor syndrome 0x32
00000000: 00 00 00 00 04 4a 00 00 00 00 00 00 20 00 93 32
00000010: 55 00 00 00 fb cc 00 00 00 00 00 00 07 18 00 00
00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 4a
00000030: 00 00 3b c7 93 01 32 04 00 00 00 00 00 00 bf e0
mlx5_core 0000:00:08.0 eth2: ERR CQE on RQ: 0x1133

Furthermore, the function that fills in WQE UMRs for the headers
(mlx5e_build_shampo_hd_umr()) only supports mapping page sizes that
fit in a single UMR WQE.

This patch goes back to the old non-aligned max_ksm_entries value and it
changes mlx5e_build_shampo_hd_umr() to support mapping a large page over
multiple UMR WQEs.

This means that mlx5e_build_shampo_hd_umr() can now leave a page only
partially mapped. The caller, mlx5e_alloc_rx_hd_mpwqe(), ensures that
there are enough UMR WQEs to cover complete pages by working on
ksm_entries that are multiples of MLX5E_SHAMPO_WQ_HEADER_PER_PAGE.

Fixes: 8a0ee54 ("net/mlx5e: SHAMPO, Simplify UMR allocation for headers")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/1762238915-1027590-2-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: dtatulea

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

@@ -671,33 +671,32 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 	u16 pi, header_offset, err, wqe_bbs;
 	u32 lkey = rq->mdev->mlx5e_res.hw_objs.mkey;
 	struct mlx5e_umr_wqe *umr_wqe;
-	int headroom, i = 0;
+	int headroom, i;
 
 	headroom = rq->buff.headroom;
 	wqe_bbs = MLX5E_KSM_UMR_WQEBBS(ksm_entries);
 	pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs);
 	umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi);
 	build_ksm_umr(sq, umr_wqe, shampo->mkey_be, index, ksm_entries);
 
-	WARN_ON_ONCE(ksm_entries & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1));
-	while (i < ksm_entries) {
-		struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index);
+	for (i = 0; i < ksm_entries; i++, index++) {
+		struct mlx5e_frag_page *frag_page;
 		u64 addr;
 
-		err = mlx5e_page_alloc_fragmented(rq->hd_page_pool, frag_page);
-		if (unlikely(err))
-			goto err_unmap;
+		frag_page = mlx5e_shampo_hd_to_frag_page(rq, index);
+		header_offset = mlx5e_shampo_hd_offset(index);
+		if (!header_offset) {
+			err = mlx5e_page_alloc_fragmented(rq->hd_page_pool,
+							  frag_page);
+			if (err)
+				goto err_unmap;
+		}
 
 		addr = page_pool_get_dma_addr_netmem(frag_page->netmem);
-
-		for (int j = 0; j < MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; j++) {
-			header_offset = mlx5e_shampo_hd_offset(index++);
-
-			umr_wqe->inline_ksms[i++] = (struct mlx5_ksm) {
-				.key = cpu_to_be32(lkey),
-				.va  = cpu_to_be64(addr + header_offset + headroom),
-			};
-		}
+		umr_wqe->inline_ksms[i] = (struct mlx5_ksm) {
+			.key = cpu_to_be32(lkey),
+			.va  = cpu_to_be64(addr + header_offset + headroom),
+		};
 	}
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
@@ -713,7 +712,7 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 	return 0;
 
 err_unmap:
-	while (--i) {
+	while (--i >= 0) {
 		--index;
 		header_offset = mlx5e_shampo_hd_offset(index);
 		if (!header_offset) {
@@ -735,8 +734,7 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq)
 	struct mlx5e_icosq *sq = rq->icosq;
 	int i, err, max_ksm_entries, len;
 
-	max_ksm_entries = ALIGN_DOWN(MLX5E_MAX_KSM_PER_WQE(rq->mdev),
-				     MLX5E_SHAMPO_WQ_HEADER_PER_PAGE);
+	max_ksm_entries = MLX5E_MAX_KSM_PER_WQE(rq->mdev);
 	ksm_entries = bitmap_find_window(shampo->bitmap,
 					 shampo->hd_per_wqe,
 					 shampo->hd_per_wq, shampo->pi);