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

Author: torvalds

Documentation/core-api/index.rst

@@ -102,6 +102,7 @@ more memory-management documentation in Documentation/mm/index.rst.
    dma-api-howto
    dma-attributes
    dma-isa-lpc
+   swiotlb
    mm-api
    genalloc
    pin_user_pages

Documentation/core-api/swiotlb.rst

@@ -1152,34 +1152,37 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	 */
 	if (dev_use_swiotlb(dev, size, dir) &&
 	    iova_offset(iovad, phys | size)) {
-		void *padding_start;
-		size_t padding_size, aligned_size;
-
 		if (!is_swiotlb_active(dev)) {
 			dev_warn_once(dev, "DMA bounce buffers are inactive, unable to map unaligned transaction.\n");
 			return DMA_MAPPING_ERROR;
 		}
 
 		trace_swiotlb_bounced(dev, phys, size);
 
-		aligned_size = iova_align(iovad, size);
-		phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size,
+		phys = swiotlb_tbl_map_single(dev, phys, size,
 					      iova_mask(iovad), dir, attrs);
 
 		if (phys == DMA_MAPPING_ERROR)
 			return DMA_MAPPING_ERROR;
 
-		/* Cleanup the padding area. */
-		padding_start = phys_to_virt(phys);
-		padding_size = aligned_size;
+		/*
+		 * Untrusted devices should not see padding areas with random
+		 * leftover kernel data, so zero the pre- and post-padding.
+		 * swiotlb_tbl_map_single() has initialized the bounce buffer
+		 * proper to the contents of the original memory buffer.
+		 */
+		if (dev_is_untrusted(dev)) {
+			size_t start, virt = (size_t)phys_to_virt(phys);
 
-		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-		    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) {
-			padding_start += size;
-			padding_size -= size;
-		}
+			/* Pre-padding */
+			start = iova_align_down(iovad, virt);
+			memset((void *)start, 0, virt - start);
 
-		memset(padding_start, 0, padding_size);
+			/* Post-padding */
+			start = virt + size;
+			memset((void *)start, 0,
+			       iova_align(iovad, start) - start);
+		}
 	}
 
 	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
@@ -1718,7 +1721,8 @@ static size_t iommu_dma_max_mapping_size(struct device *dev)
 }
 
 static const struct dma_map_ops iommu_dma_ops = {
-	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED,
+	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED |
+				  DMA_F_CAN_SKIP_SYNC,
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
 	.alloc_pages_op		= dma_common_alloc_pages,

drivers/iommu/dma-iommu.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/engleder/tsnep_main.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/freescale/dpaa2/dpaa2-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;

drivers/net/ethernet/intel/i40e/i40e_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;

drivers/net/ethernet/intel/ice/ice_xsk.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) {

drivers/net/ethernet/intel/igc/igc_main.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))) {

drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.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);