From 8d4b475e9d0f100c3920d8bf7d392a6dac88583e Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 2 Nov 2022 23:55:43 -0700 Subject: net/mlx5e: Fix usage of DMA sync API DMA sync functions should use the same direction that was used by DMA mapping. Use DMA_BIDIRECTIONAL for XDP_TX from regular RQ, which reuses the same mapping that was used for RX, and DMA_TO_DEVICE for XDP_TX from XSK RQ and XDP_REDIRECT, which establish a new mapping in this direction. On the RX side, use the same direction that was used when setting up the mapping (DMA_BIDIRECTIONAL for XDP, DMA_FROM_DEVICE otherwise). Also don't skip sync for device when establishing a DMA_FROM_DEVICE mapping for RX, as some architectures (ARM) may require invalidating caches before the device can use the mapping. It doesn't break the bugfix made in commit 0b7cfa4082fb ("net/mlx5e: Fix page DMA map/unmap attributes"), since the bug happened on unmap. Fixes: 0b7cfa4082fb ("net/mlx5e: Fix page DMA map/unmap attributes") Fixes: b5503b994ed5 ("net/mlx5e: XDP TX forwarding support") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Gal Pressman Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 27 +++++++++++++------------ 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core/en_rx.c') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 58084650151f..a61a43fc8d5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -266,7 +266,7 @@ static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq, union mlx5e_alloc_uni addr = page_pool_get_dma_addr(au->page); /* Non-XSK always uses PAGE_SIZE. */ - dma_sync_single_for_device(rq->pdev, addr, PAGE_SIZE, DMA_FROM_DEVICE); + dma_sync_single_for_device(rq->pdev, addr, PAGE_SIZE, rq->buff.map_dir); return true; } @@ -282,8 +282,7 @@ static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq, union mlx5e_alloc_u return -ENOMEM; /* Non-XSK always uses PAGE_SIZE. */ - addr = dma_map_page_attrs(rq->pdev, au->page, 0, PAGE_SIZE, - rq->buff.map_dir, DMA_ATTR_SKIP_CPU_SYNC); + addr = dma_map_page(rq->pdev, au->page, 0, PAGE_SIZE, rq->buff.map_dir); if (unlikely(dma_mapping_error(rq->pdev, addr))) { page_pool_recycle_direct(rq->page_pool, au->page); au->page = NULL; @@ -427,14 +426,15 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb, { dma_addr_t addr = page_pool_get_dma_addr(au->page); - dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len, + rq->buff.map_dir); page_ref_inc(au->page); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, au->page, frag_offset, len, truesize); } static inline void -mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb, +mlx5e_copy_skb_header(struct mlx5e_rq *rq, struct sk_buff *skb, struct page *page, dma_addr_t addr, int offset_from, int dma_offset, u32 headlen) { @@ -442,7 +442,8 @@ mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb, /* Aligning len to sizeof(long) optimizes memcpy performance */ unsigned int len = ALIGN(headlen, sizeof(long)); - dma_sync_single_for_cpu(pdev, addr + dma_offset, len, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(rq->pdev, addr + dma_offset, len, + rq->buff.map_dir); skb_copy_to_linear_data(skb, from, len); } @@ -1538,7 +1539,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi, addr = page_pool_get_dma_addr(au->page); dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset, - frag_size, DMA_FROM_DEVICE); + frag_size, rq->buff.map_dir); net_prefetch(data); prog = rcu_dereference(rq->xdp_prog); @@ -1587,7 +1588,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi addr = page_pool_get_dma_addr(au->page); dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset, - rq->buff.frame0_sz, DMA_FROM_DEVICE); + rq->buff.frame0_sz, rq->buff.map_dir); net_prefetchw(va); /* xdp_frame data area */ net_prefetch(va + rx_headroom); @@ -1608,7 +1609,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi addr = page_pool_get_dma_addr(au->page); dma_sync_single_for_cpu(rq->pdev, addr + wi->offset, - frag_consumed_bytes, DMA_FROM_DEVICE); + frag_consumed_bytes, rq->buff.map_dir); if (!xdp_buff_has_frags(&xdp)) { /* Init on the first fragment to avoid cold cache access @@ -1905,7 +1906,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w mlx5e_fill_skb_data(skb, rq, au, byte_cnt, frag_offset); /* copy header */ addr = page_pool_get_dma_addr(head_au->page); - mlx5e_copy_skb_header(rq->pdev, skb, head_au->page, addr, + mlx5e_copy_skb_header(rq, skb, head_au->page, addr, head_offset, head_offset, headlen); /* skb linear part was allocated with headlen and aligned to long */ skb->tail += headlen; @@ -1939,7 +1940,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, addr = page_pool_get_dma_addr(au->page); dma_sync_single_range_for_cpu(rq->pdev, addr, head_offset, - frag_size, DMA_FROM_DEVICE); + frag_size, rq->buff.map_dir); net_prefetch(data); prog = rcu_dereference(rq->xdp_prog); @@ -1987,7 +1988,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, if (likely(frag_size <= BIT(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE))) { /* build SKB around header */ - dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, DMA_FROM_DEVICE); + dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, rq->buff.map_dir); prefetchw(hdr); prefetch(data); skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size, 0); @@ -2009,7 +2010,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, } prefetchw(skb->data); - mlx5e_copy_skb_header(rq->pdev, skb, head->page, head->addr, + mlx5e_copy_skb_header(rq, skb, head->page, head->addr, head_offset + rx_headroom, rx_headroom, head_size); /* skb linear part was allocated with headlen and aligned to long */ -- cgit v1.2.3-59-g8ed1b