Adding a DMA pre-handler that utilizes page pool for managing DMA mappings.
When IOMMU is enabled, turning on the page_pool_dma_map module parameter to
select page pool for DMA mapping management gives a significant reduction
in the overhead caused by DMA mappings.

In testing environments with a single core vm and qemu emulated IOMMU,
significant performance improvements can be observed:
  Upstream codebase: 1.76 Gbits/sec
  Upstream codebase with page pool fragmentation support: 1.81 Gbits/sec
  Upstream codebase with page pool fragmentation and DMA support: 19.3
  Gbits/sec

Signed-off-by: Liang Chen <redacted>
---
 drivers/net/virtio_net.c | 55 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ac40b8c66c59..73cc4f9fe4fa 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c

@@ -22,6 +22,7 @@
 #include <net/route.h>
 #include <net/xdp.h>
 #include <net/net_failover.h>
+#include <linux/iommu.h>

 static int napi_weight = NAPI_POLL_WEIGHT;
 module_param(napi_weight, int, 0444);

@@ -33,8 +34,10 @@ module_param(napi_tx, bool, 0644);

 static bool page_pool_enabled;
 static bool page_pool_frag;
+static bool page_pool_dma_map;
 module_param(page_pool_enabled, bool, 0400);
 module_param(page_pool_frag, bool, 0400);
+module_param(page_pool_dma_map, bool, 0400);

 /* FIXME: MTU in config. */
 #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)

@@ -3830,6 +3833,49 @@ static void virtnet_del_vqs(struct virtnet_info *vi)
        virtnet_free_queues(vi);
 }

+static dma_addr_t virtnet_pp_dma_map_page(struct device *dev, struct page *page,
+                                         unsigned long offset, size_t size,
+                                         enum dma_data_direction dir, unsigned long attrs)
+{
+       struct page *head_page;
+
+       if (dir != DMA_FROM_DEVICE)
+               return 0;
+
+       head_page = compound_head(page);
+       return page_pool_get_dma_addr(head_page)
+               + (page - head_page) * PAGE_SIZE
+               + offset;

+       if (WARN_ON(!phys))
+               return false;
+
+       arch_sync_dma_for_cpu(phys, size, dir);
+       return true;
+}
+
+static struct virtqueue_pre_dma_ops virtnet_pp_pre_dma_ops = {
+       .map_page = virtnet_pp_dma_map_page,
+       .unmap_page = virtnet_pp_dma_unmap_page,
+};
+
 static void virtnet_alloc_page_pool(struct receive_queue *rq)
 {
        struct virtio_device *vdev = rq->vq->vdev;

@@ -3845,6 +3891,15 @@ static void virtnet_alloc_page_pool(struct receive_queue *rq)
        if (page_pool_frag)
                pp_params.flags |= PP_FLAG_PAGE_FRAG;

+       /* Consider using page pool DMA support only when DMA API is used. */
+       if (virtio_has_feature(vdev, VIRTIO_F_ACCESS_PLATFORM) &&
+           page_pool_dma_map) {
+               pp_params.flags |= PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+               pp_params.dma_dir = DMA_FROM_DEVICE;
+               pp_params.max_len = PAGE_SIZE << pp_params.order;
+               virtqueue_register_pre_dma_ops(rq->vq, &virtnet_pp_pre_dma_ops);
+       }
+
        rq->page_pool = page_pool_create(&pp_params);
        if (IS_ERR(rq->page_pool)) {
                dev_warn(&vdev->dev, "page pool creation failed: %ld\n",
--

2.31.1