Merge tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - optimize DMA sync calls when they are no-ops (Alexander Lobakin)

 - fix swiotlb padding for untrusted devices (Michael Kelley)

 - add documentation for swiotb (Michael Kelley)

* tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping:
  dma: fix DMA sync for drivers not calling dma_set_mask*()
  xsk: use generic DMA sync shortcut instead of a custom one
  page_pool: check for DMA sync shortcut earlier
  page_pool: don't use driver-set flags field directly
  page_pool: make sure frag API fields don't span between cachelines
  iommu/dma: avoid expensive indirect calls for sync operations
  dma: avoid redundant calls for sync operations
  dma: compile-out DMA sync op calls when not used
  iommu/dma: fix zeroing of bounce buffer padding used by untrusted devices
  swiotlb: remove alloc_size argument to swiotlb_tbl_map_single()
  Documentation/core-api: add swiotlb documentation

10 files changed, 11 insertions, 11 deletions

diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 4b15af6b7122..44da335d66bd 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/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
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c
index 051748b997f3..a466c2379146 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c
+++ b/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 */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index a85b425794df..4e885df789ef 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -482,7 +482,7 @@ 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;
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index aa81d1162b81..7541f223bf4f 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -878,7 +878,7 @@ 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;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index b5bcabab7a1d..12f004f46082 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2812,7 +2812,7 @@ 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) {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 397cb773fabb..3e3b471e53f0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -303,7 +303,7 @@ 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))) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index b8dd74453655..1b7132fa70de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/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);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d601b5faaed5..b5333da20e8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/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 {
diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c b/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c
index 45be6954d5aa..01cfa9cc1b5e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c
+++ b/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) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 2e9a2da605f6..b3afc7cb7d72 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -5361,7 +5361,7 @@ read_again:
 
 		/* 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);