On Tue, 24 Feb 2026 20:49:10 -0800, Vishwanath Seshagiri <[email protected]> wrote:
> Use page_pool for RX buffer allocation in mergeable and small buffer
> modes to enable page recycling and avoid repeated page allocator calls.
> skb_mark_for_recycle() enables page reuse in the network stack.
>
> Big packets mode is unchanged because it uses page->private for linked
> list chaining of multiple pages per buffer, which conflicts with
> page_pool's internal use of page->private.
>
> Implement conditional DMA premapping using virtqueue_dma_dev():
> - When non-NULL (vhost, virtio-pci): use PP_FLAG_DMA_MAP with page_pool
> handling DMA mapping, submit via virtqueue_add_inbuf_premapped()
> - When NULL (VDUSE, direct physical): page_pool handles allocation only,
> submit via virtqueue_add_inbuf_ctx()
>
> This preserves the DMA premapping optimization from commit 31f3cd4e5756b
> ("virtio-net: rq submits premapped per-buffer") while adding page_pool
> support as a prerequisite for future zero-copy features (devmem TCP,
> io_uring ZCRX).
>
> Page pools are created in probe and destroyed in remove (not open/close),
> following existing driver behavior where RX buffers remain in virtqueues
> across interface state changes.
>
> Signed-off-by: Vishwanath Seshagiri <[email protected]>
> ---
> Resend for net-next window (no changes from v7).
> - v7:
>
> https://lore.kernel.org/virtualization/[email protected]/
>
> Changes in v7:
> - Replace virtnet_put_page() helper with direct page_pool_put_page()
> calls (Xuan Zhuo)
> - Add virtnet_no_page_pool() helper to consolidate big_packets mode check
> (Michael S. Tsirkin)
> - Add DMA sync_for_cpu for subsequent buffers in xdp_linearize_page() when
> use_page_pool_dma is set (Michael S. Tsirkin)
> - Remove unused pp_params.dev assignment in non-DMA path
> - Add page pool recreation in virtnet_restore_up() for freeze/restore support
> (Chris Mason's
> Review Prompt)
> - v6:
>
> https://lore.kernel.org/virtualization/[email protected]/
>
> Changes in v6:
> - Drop page_pool_frag_offset_add() helper and switch to page_pool_alloc_va();
> page_pool_alloc_netmem() already handles internal fragmentation internally
> (Jakub Kicinski)
> - v5:
>
> https://lore.kernel.org/virtualization/[email protected]/
>
> Benchmark results:
>
> Configuration: pktgen TX -> tap -> vhost-net | virtio-net RX -> XDP_DROP
>
> Small packets (64 bytes, mrg_rxbuf=off):
> 1Q: 853,493 -> 868,923 pps (+1.8%)
> 2Q: 1,655,793 -> 1,696,707 pps (+2.5%)
> 4Q: 3,143,375 -> 3,302,511 pps (+5.1%)
> 8Q: 6,082,590 -> 6,156,894 pps (+1.2%)
>
> Mergeable RX (64 bytes):
> 1Q: 766,168 -> 814,493 pps (+6.3%)
> 2Q: 1,384,871 -> 1,670,639 pps (+20.6%)
> 4Q: 2,773,081 -> 3,080,574 pps (+11.1%)
> 8Q: 5,600,615 -> 6,043,891 pps (+7.9%)
>
> Mergeable RX (1500 bytes):
> 1Q: 741,579 -> 785,442 pps (+5.9%)
> 2Q: 1,310,043 -> 1,534,554 pps (+17.1%)
> 4Q: 2,748,700 -> 2,890,582 pps (+5.2%)
> 8Q: 5,348,589 -> 5,618,664 pps (+5.0%)
>
> drivers/net/Kconfig | 1 +
> drivers/net/virtio_net.c | 467 ++++++++++++++++++++-------------------
> 2 files changed, 243 insertions(+), 225 deletions(-)
>
> diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
> index ac12eaf11755..f1e6b6b0a86f 100644
> --- a/drivers/net/Kconfig
> +++ b/drivers/net/Kconfig
> @@ -450,6 +450,7 @@ config VIRTIO_NET
> depends on VIRTIO
> select NET_FAILOVER
> select DIMLIB
> + select PAGE_POOL
> help
> This is the virtual network driver for virtio. It can be used with
> QEMU based VMMs (like KVM or Xen). Say Y or M.
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index db88dcaefb20..32aede2b1ed5 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -26,6 +26,7 @@
> #include <net/netdev_rx_queue.h>
> #include <net/netdev_queues.h>
> #include <net/xdp_sock_drv.h>
> +#include <net/page_pool/helpers.h>
>
> static int napi_weight = NAPI_POLL_WEIGHT;
> module_param(napi_weight, int, 0444);
> @@ -290,14 +291,6 @@ struct virtnet_interrupt_coalesce {
> u32 max_usecs;
> };
>
> -/* The dma information of pages allocated at a time. */
> -struct virtnet_rq_dma {
> - dma_addr_t addr;
> - u32 ref;
> - u16 len;
> - u16 need_sync;
> -};
> -
> /* Internal representation of a send virtqueue */
> struct send_queue {
> /* Virtqueue associated with this send _queue */
> @@ -356,8 +349,10 @@ struct receive_queue {
> /* Average packet length for mergeable receive buffers. */
> struct ewma_pkt_len mrg_avg_pkt_len;
>
> - /* Page frag for packet buffer allocation. */
> - struct page_frag alloc_frag;
> + struct page_pool *page_pool;
> +
> + /* True if page_pool handles DMA mapping via PP_FLAG_DMA_MAP */
> + bool use_page_pool_dma;
>
> /* RX: fragments + linear part + virtio header */
> struct scatterlist sg[MAX_SKB_FRAGS + 2];
> @@ -370,9 +365,6 @@ struct receive_queue {
>
> struct xdp_rxq_info xdp_rxq;
>
> - /* Record the last dma info to free after new pages is allocated. */
> - struct virtnet_rq_dma *last_dma;
> -
> struct xsk_buff_pool *xsk_pool;
>
> /* xdp rxq used by xsk */
> @@ -521,11 +513,14 @@ static int virtnet_xdp_handler(struct bpf_prog
> *xdp_prog, struct xdp_buff *xdp,
> struct virtnet_rq_stats *stats);
> static void virtnet_receive_done(struct virtnet_info *vi, struct
> receive_queue *rq,
> struct sk_buff *skb, u8 flags);
> -static struct sk_buff *virtnet_skb_append_frag(struct sk_buff *head_skb,
> +static struct sk_buff *virtnet_skb_append_frag(struct receive_queue *rq,
> + struct sk_buff *head_skb,
> struct sk_buff *curr_skb,
> struct page *page, void *buf,
> int len, int truesize);
> static void virtnet_xsk_completed(struct send_queue *sq, int num);
> +static void free_unused_bufs(struct virtnet_info *vi);
> +static void virtnet_del_vqs(struct virtnet_info *vi);
>
> enum virtnet_xmit_type {
> VIRTNET_XMIT_TYPE_SKB,
> @@ -706,15 +701,18 @@ static struct page *get_a_page(struct receive_queue
> *rq, gfp_t gfp_mask)
> return p;
> }
>
> +static bool virtnet_no_page_pool(struct virtnet_info *vi)
> +{
Can we check vi->page_pool?
In virtnet_create_page_pools, we can check
"vi->big_packets && !vi->mergeable_rx_bufs" directly.
Then other calls will be more efficient.
> + return vi->big_packets && !vi->mergeable_rx_bufs;
> +}
> +
> static void virtnet_rq_free_buf(struct virtnet_info *vi,
> struct receive_queue *rq, void *buf)
> {
> - if (vi->mergeable_rx_bufs)
> - put_page(virt_to_head_page(buf));
> - else if (vi->big_packets)
> + if (virtnet_no_page_pool(vi))
> give_pages(rq, buf);
> else
> - put_page(virt_to_head_page(buf));
> + page_pool_put_page(rq->page_pool, virt_to_head_page(buf), -1,
> false);
> }
>
[...]
>
> err_buf:
> @@ -2666,32 +2586,40 @@ static void receive_buf(struct virtnet_info *vi,
> struct receive_queue *rq,
> static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue
> *rq,
> gfp_t gfp)
> {
> - char *buf;
> unsigned int xdp_headroom = virtnet_get_headroom(vi);
> void *ctx = (void *)(unsigned long)xdp_headroom;
> - int len = vi->hdr_len + VIRTNET_RX_PAD + GOOD_PACKET_LEN + xdp_headroom;
> + unsigned int len = vi->hdr_len + VIRTNET_RX_PAD + GOOD_PACKET_LEN +
> xdp_headroom;
> + struct page *page;
> + dma_addr_t addr;
> + char *buf;
> int err;
>
> len = SKB_DATA_ALIGN(len) +
> SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
>
> - if (unlikely(!skb_page_frag_refill(len, &rq->alloc_frag, gfp)))
> - return -ENOMEM;
> -
> - buf = virtnet_rq_alloc(rq, len, gfp);
> + buf = page_pool_alloc_va(rq->page_pool, &len, gfp);
> if (unlikely(!buf))
> return -ENOMEM;
>
> buf += VIRTNET_RX_PAD + xdp_headroom;
>
> - virtnet_rq_init_one_sg(rq, buf, vi->hdr_len + GOOD_PACKET_LEN);
> + if (rq->use_page_pool_dma) {
> + page = virt_to_head_page(buf);
> + addr = page_pool_get_dma_addr(page) +
> + (buf - (char *)page_address(page));
>
> - err = virtqueue_add_inbuf_premapped(rq->vq, rq->sg, 1, buf, ctx, gfp);
> - if (err < 0) {
> - virtnet_rq_unmap(rq, buf, 0);
> - put_page(virt_to_head_page(buf));
> + sg_init_table(rq->sg, 1);
> + sg_fill_dma(rq->sg, addr, vi->hdr_len + GOOD_PACKET_LEN);
> + err = virtqueue_add_inbuf_premapped(rq->vq, rq->sg, 1,
> + buf, ctx, gfp);
> + } else {
> + sg_init_one(rq->sg, buf, vi->hdr_len + GOOD_PACKET_LEN);
> + err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1,
> + buf, ctx, gfp);
> }
Maybe we should introduce a helper to do this, as the merge mode needs this
too.
Thanks.
