xsk: use generic DMA sync shortcut instead of a custom one

XSk infra's been using its own DMA sync shortcut to try avoiding
redundant function calls. Now that there is a generic one, remove
the custom implementation and rely on the generic helpers.
xsk_buff_dma_sync_for_cpu() doesn't need the second argument anymore,
remove it.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

drivers/net/ethernet/engleder/tsnep_main.c

@@ -1587,7 +1587,7 @@ static int tsnep_rx_poll_zc(struct tsnep_rx *rx, struct napi_struct *napi,
 		length = __le32_to_cpu(entry->desc_wb->properties) &
 			 TSNEP_DESC_LENGTH_MASK;
 		xsk_buff_set_size(entry->xdp, length - ETH_FCS_LEN);
-		xsk_buff_dma_sync_for_cpu(entry->xdp, rx->xsk_pool);
+		xsk_buff_dma_sync_for_cpu(entry->xdp);
 
 		/* RX metadata with timestamps is in front of actual data,
 		 * subtract metadata size to get length of actual data and

drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c

@@ -55,7 +55,7 @@ static u32 dpaa2_xsk_run_xdp(struct dpaa2_eth_priv *priv,
 	xdp_set_data_meta_invalid(xdp_buff);
 	xdp_buff->rxq = &ch->xdp_rxq;
 
-	xsk_buff_dma_sync_for_cpu(xdp_buff, ch->xsk_pool);
+	xsk_buff_dma_sync_for_cpu(xdp_buff);
 	xdp_act = bpf_prog_run_xdp(xdp_prog, xdp_buff);
 
 	/* xdp.data pointer may have changed */

drivers/net/ethernet/intel/i40e/i40e_xsk.c

@@ -483,7 +483,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 
 		bi = *i40e_rx_bi(rx_ring, next_to_process);
 		xsk_buff_set_size(bi, size);
-		xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool);
+		xsk_buff_dma_sync_for_cpu(bi);
 
 		if (!first)
 			first = bi;

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -879,7 +879,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 				   ICE_RX_FLX_DESC_PKT_LEN_M;
 
 		xsk_buff_set_size(xdp, size);
-		xsk_buff_dma_sync_for_cpu(xdp, xsk_pool);
+		xsk_buff_dma_sync_for_cpu(xdp);
 
 		if (!first) {
 			first = xdp;

drivers/net/ethernet/intel/igc/igc_main.c

@@ -2813,7 +2813,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 		}
 
 		bi->xdp->data_end = bi->xdp->data + size;
-		xsk_buff_dma_sync_for_cpu(bi->xdp, ring->xsk_pool);
+		xsk_buff_dma_sync_for_cpu(bi->xdp);
 
 		res = __igc_xdp_run_prog(adapter, prog, bi->xdp);
 		switch (res) {

drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c

@@ -304,7 +304,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 		}
 
 		bi->xdp->data_end = bi->xdp->data + size;
-		xsk_buff_dma_sync_for_cpu(bi->xdp, rx_ring->xsk_pool);
+		xsk_buff_dma_sync_for_cpu(bi->xdp);
 		xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp);
 
 		if (likely(xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR))) {

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

@@ -270,7 +270,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	/* mxbuf->rq is set on allocation, but cqe is per-packet so set it here */
 	mxbuf->cqe = cqe;
 	xsk_buff_set_size(&mxbuf->xdp, cqe_bcnt);
-	xsk_buff_dma_sync_for_cpu(&mxbuf->xdp, rq->xsk_pool);
+	xsk_buff_dma_sync_for_cpu(&mxbuf->xdp);
 	net_prefetch(mxbuf->xdp.data);
 
 	/* Possible flows:
@@ -319,7 +319,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 	/* mxbuf->rq is set on allocation, but cqe is per-packet so set it here */
 	mxbuf->cqe = cqe;
 	xsk_buff_set_size(&mxbuf->xdp, cqe_bcnt);
-	xsk_buff_dma_sync_for_cpu(&mxbuf->xdp, rq->xsk_pool);
+	xsk_buff_dma_sync_for_cpu(&mxbuf->xdp);
 	net_prefetch(mxbuf->xdp.data);
 
 	prog = rcu_dereference(rq->xdp_prog);

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

@@ -917,7 +917,7 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
 
 	if (!rq->xsk_pool) {
 		count = mlx5e_refill_rx_wqes(rq, head, wqe_bulk);
-	} else if (likely(!rq->xsk_pool->dma_need_sync)) {
+	} else if (likely(!dma_dev_need_sync(rq->pdev))) {
 		mlx5e_xsk_free_rx_wqes(rq, head, wqe_bulk);
 		count = mlx5e_xsk_alloc_rx_wqes_batched(rq, head, wqe_bulk);
 	} else {

drivers/net/ethernet/netronome/nfp/nfd3/xsk.c

@@ -184,7 +184,7 @@ nfp_nfd3_xsk_rx(struct nfp_net_rx_ring *rx_ring, int budget,
 		xrxbuf->xdp->data += meta_len;
 		xrxbuf->xdp->data_end = xrxbuf->xdp->data + pkt_len;
 		xdp_set_data_meta_invalid(xrxbuf->xdp);
-		xsk_buff_dma_sync_for_cpu(xrxbuf->xdp, r_vec->xsk_pool);
+		xsk_buff_dma_sync_for_cpu(xrxbuf->xdp);
 		net_prefetch(xrxbuf->xdp->data);
 
 		if (meta_len) {

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -5352,7 +5352,7 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
 
 		/* RX buffer is good and fit into a XSK pool buffer */
 		buf->xdp->data_end = buf->xdp->data + buf1_len;
-		xsk_buff_dma_sync_for_cpu(buf->xdp, rx_q->xsk_pool);
+		xsk_buff_dma_sync_for_cpu(buf->xdp);
 
 		prog = READ_ONCE(priv->xdp_prog);
 		res = __stmmac_xdp_run_prog(priv, prog, buf->xdp);

include/net/xdp_sock_drv.h

@@ -219,13 +219,10 @@ static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool
 	return meta;
 }
 
-static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
+static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 
-	if (!pool->dma_need_sync)
-		return;
-
 	xp_dma_sync_for_cpu(xskb);
 }
 
@@ -402,7 +399,7 @@ static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool
 	return NULL;
 }
 
-static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
+static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
 {
 }
 

include/net/xsk_buff_pool.h

@@ -43,7 +43,6 @@ struct xsk_dma_map {
 	refcount_t users;
 	struct list_head list; /* Protected by the RTNL_LOCK */
 	u32 dma_pages_cnt;
-	bool dma_need_sync;
 };
 
 struct xsk_buff_pool {
@@ -82,7 +81,6 @@ struct xsk_buff_pool {
 	u8 tx_metadata_len; /* inherited from umem */
 	u8 cached_need_wakeup;
 	bool uses_need_wakeup;
-	bool dma_need_sync;
 	bool unaligned;
 	bool tx_sw_csum;
 	void *addrs;
@@ -155,21 +153,17 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb)
 	return xskb->frame_dma;
 }
 
-void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb);
 static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb)
 {
-	xp_dma_sync_for_cpu_slow(xskb);
+	dma_sync_single_for_cpu(xskb->pool->dev, xskb->dma,
+				xskb->pool->frame_len,
+				DMA_BIDIRECTIONAL);
 }
 
-void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
-				 size_t size);
 static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool,
 					  dma_addr_t dma, size_t size)
 {
-	if (!pool->dma_need_sync)
-		return;
-
-	xp_dma_sync_for_device_slow(pool, dma, size);
+	dma_sync_single_for_device(pool->dev, dma, size, DMA_BIDIRECTIONAL);
 }
 
 /* Masks for xdp_umem_page flags.

net/xdp/xsk_buff_pool.c

@@ -338,7 +338,6 @@ static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_devi
 
 	dma_map->netdev = netdev;
 	dma_map->dev = dev;
-	dma_map->dma_need_sync = false;
 	dma_map->dma_pages_cnt = nr_pages;
 	refcount_set(&dma_map->users, 1);
 	list_add(&dma_map->list, &umem->xsk_dma_list);
@@ -424,7 +423,6 @@ static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_
 
 	pool->dev = dma_map->dev;
 	pool->dma_pages_cnt = dma_map->dma_pages_cnt;
-	pool->dma_need_sync = dma_map->dma_need_sync;
 	memcpy(pool->dma_pages, dma_map->dma_pages,
 	       pool->dma_pages_cnt * sizeof(*pool->dma_pages));
 
@@ -460,8 +458,6 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 			__xp_dma_unmap(dma_map, attrs);
 			return -ENOMEM;
 		}
-		if (dma_need_sync(dev, dma))
-			dma_map->dma_need_sync = true;
 		dma_map->dma_pages[i] = dma;
 	}
 
@@ -557,11 +553,9 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
 	xskb->xdp.data_meta = xskb->xdp.data;
 	xskb->xdp.flags = 0;
 
-	if (pool->dma_need_sync) {
-		dma_sync_single_range_for_device(pool->dev, xskb->dma, 0,
-						 pool->frame_len,
-						 DMA_BIDIRECTIONAL);
-	}
+	if (pool->dev)
+		xp_dma_sync_for_device(pool, xskb->dma, pool->frame_len);
+
 	return &xskb->xdp;
 }
 EXPORT_SYMBOL(xp_alloc);
@@ -633,7 +627,7 @@ u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
 {
 	u32 nb_entries1 = 0, nb_entries2;
 
-	if (unlikely(pool->dma_need_sync)) {
+	if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) {
 		struct xdp_buff *buff;
 
 		/* Slow path */
@@ -693,18 +687,3 @@ dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr)
 		(addr & ~PAGE_MASK);
 }
 EXPORT_SYMBOL(xp_raw_get_dma);
-
-void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb)
-{
-	dma_sync_single_range_for_cpu(xskb->pool->dev, xskb->dma, 0,
-				      xskb->pool->frame_len, DMA_BIDIRECTIONAL);
-}
-EXPORT_SYMBOL(xp_dma_sync_for_cpu_slow);
-
-void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
-				 size_t size)
-{
-	dma_sync_single_range_for_device(pool->dev, dma, 0,
-					 size, DMA_BIDIRECTIONAL);
-}
-EXPORT_SYMBOL(xp_dma_sync_for_device_slow);