From: Vishwanath Seshagiri Date: Tue, 10 Mar 2026 18:31:04 +0000 (-0700) Subject: virtio_net: add page_pool support for buffer allocation X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=24fbd3967f3fdaad5f93e0d35ae870ed25fb2c3a;p=thirdparty%2Flinux.git virtio_net: add page_pool support for buffer allocation 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 Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Link: https://patch.msgid.link/20260310183107.2822016-1-vishs@meta.com Signed-off-by: Jakub Kicinski --- diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 17108c3592166..b2fd90466babd 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -452,6 +452,7 @@ 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 811b90da15a9f..022f60728721a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -26,6 +26,7 @@ #include #include #include +#include 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, @@ -709,12 +704,10 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask) 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 (!rq->page_pool) 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); } static void enable_rx_mode_work(struct virtnet_info *vi) @@ -876,10 +869,16 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, skb = virtnet_build_skb(buf, truesize, p - buf, len); if (unlikely(!skb)) return NULL; + /* Big packets mode chains pages via page->private, which is + * incompatible with the way page_pool uses page->private. + * Currently, big packets mode doesn't use page pools. + */ + if (!rq->page_pool) { + page = (struct page *)page->private; + if (page) + give_pages(rq, page); + } - page = (struct page *)page->private; - if (page) - give_pages(rq, page); goto ok; } @@ -925,133 +924,16 @@ ok: hdr = skb_vnet_common_hdr(skb); memcpy(hdr, hdr_p, hdr_len); if (page_to_free) - put_page(page_to_free); + page_pool_put_page(rq->page_pool, page_to_free, -1, true); return skb; } -static void virtnet_rq_unmap(struct receive_queue *rq, void *buf, u32 len) -{ - struct virtnet_info *vi = rq->vq->vdev->priv; - struct page *page = virt_to_head_page(buf); - struct virtnet_rq_dma *dma; - void *head; - int offset; - - BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); - - head = page_address(page); - - dma = head; - - --dma->ref; - - if (dma->need_sync && len) { - offset = buf - (head + sizeof(*dma)); - - virtqueue_map_sync_single_range_for_cpu(rq->vq, dma->addr, - offset, len, - DMA_FROM_DEVICE); - } - - if (dma->ref) - return; - - virtqueue_unmap_single_attrs(rq->vq, dma->addr, dma->len, - DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); - put_page(page); -} - static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx) { - struct virtnet_info *vi = rq->vq->vdev->priv; - void *buf; - - BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); + BUG_ON(!rq->page_pool); - buf = virtqueue_get_buf_ctx(rq->vq, len, ctx); - if (buf) - virtnet_rq_unmap(rq, buf, *len); - - return buf; -} - -static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len) -{ - struct virtnet_info *vi = rq->vq->vdev->priv; - struct virtnet_rq_dma *dma; - dma_addr_t addr; - u32 offset; - void *head; - - BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); - - head = page_address(rq->alloc_frag.page); - - offset = buf - head; - - dma = head; - - addr = dma->addr - sizeof(*dma) + offset; - - sg_init_table(rq->sg, 1); - sg_fill_dma(rq->sg, addr, len); -} - -static void *virtnet_rq_alloc(struct receive_queue *rq, u32 size, gfp_t gfp) -{ - struct page_frag *alloc_frag = &rq->alloc_frag; - struct virtnet_info *vi = rq->vq->vdev->priv; - struct virtnet_rq_dma *dma; - void *buf, *head; - dma_addr_t addr; - - BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); - - head = page_address(alloc_frag->page); - - dma = head; - - /* new pages */ - if (!alloc_frag->offset) { - if (rq->last_dma) { - /* Now, the new page is allocated, the last dma - * will not be used. So the dma can be unmapped - * if the ref is 0. - */ - virtnet_rq_unmap(rq, rq->last_dma, 0); - rq->last_dma = NULL; - } - - dma->len = alloc_frag->size - sizeof(*dma); - - addr = virtqueue_map_single_attrs(rq->vq, dma + 1, - dma->len, DMA_FROM_DEVICE, 0); - if (virtqueue_map_mapping_error(rq->vq, addr)) - return NULL; - - dma->addr = addr; - dma->need_sync = virtqueue_map_need_sync(rq->vq, addr); - - /* Add a reference to dma to prevent the entire dma from - * being released during error handling. This reference - * will be freed after the pages are no longer used. - */ - get_page(alloc_frag->page); - dma->ref = 1; - alloc_frag->offset = sizeof(*dma); - - rq->last_dma = dma; - } - - ++dma->ref; - - buf = head + alloc_frag->offset; - - get_page(alloc_frag->page); - alloc_frag->offset += size; - - return buf; + return virtqueue_get_buf_ctx(rq->vq, len, ctx); } static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) @@ -1067,9 +949,6 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) return; } - if (!vi->big_packets || vi->mergeable_rx_bufs) - virtnet_rq_unmap(rq, buf, 0); - virtnet_rq_free_buf(vi, rq, buf); } @@ -1335,7 +1214,7 @@ static int xsk_append_merge_buffer(struct virtnet_info *vi, truesize = len; - curr_skb = virtnet_skb_append_frag(head_skb, curr_skb, page, + curr_skb = virtnet_skb_append_frag(rq, head_skb, curr_skb, page, buf, len, truesize); if (!curr_skb) { put_page(page); @@ -1790,7 +1669,7 @@ out: return ret; } -static void put_xdp_frags(struct xdp_buff *xdp) +static void put_xdp_frags(struct receive_queue *rq, struct xdp_buff *xdp) { struct skb_shared_info *shinfo; struct page *xdp_page; @@ -1800,7 +1679,7 @@ static void put_xdp_frags(struct xdp_buff *xdp) shinfo = xdp_get_shared_info_from_buff(xdp); for (i = 0; i < shinfo->nr_frags; i++) { xdp_page = skb_frag_page(&shinfo->frags[i]); - put_page(xdp_page); + page_pool_put_page(rq->page_pool, xdp_page, -1, true); } } } @@ -1892,7 +1771,7 @@ static struct page *xdp_linearize_page(struct net_device *dev, if (page_off + *len + tailroom > PAGE_SIZE) return NULL; - page = alloc_page(GFP_ATOMIC); + page = page_pool_alloc_pages(rq->page_pool, GFP_ATOMIC); if (!page) return NULL; @@ -1915,8 +1794,12 @@ static struct page *xdp_linearize_page(struct net_device *dev, p = virt_to_head_page(buf); off = buf - page_address(p); + if (rq->use_page_pool_dma) + page_pool_dma_sync_for_cpu(rq->page_pool, p, + off, buflen); + if (check_mergeable_len(dev, ctx, buflen)) { - put_page(p); + page_pool_put_page(rq->page_pool, p, -1, true); goto err_buf; } @@ -1924,38 +1807,36 @@ static struct page *xdp_linearize_page(struct net_device *dev, * is sending packet larger than the MTU. */ if ((page_off + buflen + tailroom) > PAGE_SIZE) { - put_page(p); + page_pool_put_page(rq->page_pool, p, -1, true); goto err_buf; } memcpy(page_address(page) + page_off, page_address(p) + off, buflen); page_off += buflen; - put_page(p); + page_pool_put_page(rq->page_pool, p, -1, true); } /* Headroom does not contribute to packet length */ *len = page_off - XDP_PACKET_HEADROOM; return page; err_buf: - __free_pages(page, 0); + page_pool_put_page(rq->page_pool, page, -1, true); return NULL; } static struct sk_buff *receive_small_build_skb(struct virtnet_info *vi, unsigned int xdp_headroom, void *buf, - unsigned int len) + unsigned int len, + unsigned int buflen) { unsigned int header_offset; unsigned int headroom; - unsigned int buflen; struct sk_buff *skb; header_offset = VIRTNET_RX_PAD + xdp_headroom; headroom = vi->hdr_len + header_offset; - buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); skb = virtnet_build_skb(buf, buflen, headroom, len); if (unlikely(!skb)) @@ -1974,6 +1855,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev, void *buf, unsigned int xdp_headroom, unsigned int len, + unsigned int buflen, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { @@ -1982,7 +1864,6 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev, struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset; struct page *page = virt_to_head_page(buf); struct page *xdp_page; - unsigned int buflen; struct xdp_buff xdp; struct sk_buff *skb; unsigned int metasize = 0; @@ -1995,9 +1876,6 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev, if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) goto err_xdp; - buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - if (unlikely(xdp_headroom < virtnet_get_headroom(vi))) { int offset = buf - page_address(page) + header_offset; unsigned int tlen = len + vi->hdr_len; @@ -2015,7 +1893,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev, goto err_xdp; buf = page_address(xdp_page); - put_page(page); + page_pool_put_page(rq->page_pool, page, -1, true); page = xdp_page; } @@ -2047,13 +1925,15 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev, if (metasize) skb_metadata_set(skb, metasize); + skb_mark_for_recycle(skb); + return skb; err_xdp: u64_stats_inc(&stats->xdp_drops); err: u64_stats_inc(&stats->drops); - put_page(page); + page_pool_put_page(rq->page_pool, page, -1, true); xdp_xmit: return NULL; } @@ -2066,7 +1946,8 @@ static struct sk_buff *receive_small(struct net_device *dev, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { - unsigned int xdp_headroom = (unsigned long)ctx; + unsigned int xdp_headroom = mergeable_ctx_to_headroom(ctx); + unsigned int buflen = mergeable_ctx_to_truesize(ctx); struct page *page = virt_to_head_page(buf); struct sk_buff *skb; @@ -2075,6 +1956,13 @@ static struct sk_buff *receive_small(struct net_device *dev, */ buf -= VIRTNET_RX_PAD + xdp_headroom; + if (rq->use_page_pool_dma) { + int offset = buf - page_address(page) + + VIRTNET_RX_PAD + xdp_headroom; + + page_pool_dma_sync_for_cpu(rq->page_pool, page, offset, len); + } + len -= vi->hdr_len; u64_stats_add(&stats->bytes, len); @@ -2092,21 +1980,23 @@ static struct sk_buff *receive_small(struct net_device *dev, xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { skb = receive_small_xdp(dev, vi, rq, xdp_prog, buf, - xdp_headroom, len, xdp_xmit, - stats); + xdp_headroom, len, buflen, + xdp_xmit, stats); rcu_read_unlock(); return skb; } rcu_read_unlock(); } - skb = receive_small_build_skb(vi, xdp_headroom, buf, len); - if (likely(skb)) + skb = receive_small_build_skb(vi, xdp_headroom, buf, len, buflen); + if (likely(skb)) { + skb_mark_for_recycle(skb); return skb; + } err: u64_stats_inc(&stats->drops); - put_page(page); + page_pool_put_page(rq->page_pool, page, -1, true); return NULL; } @@ -2161,7 +2051,7 @@ static void mergeable_buf_free(struct receive_queue *rq, int num_buf, } u64_stats_add(&stats->bytes, len); page = virt_to_head_page(buf); - put_page(page); + page_pool_put_page(rq->page_pool, page, -1, true); } } @@ -2271,8 +2161,12 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev, page = virt_to_head_page(buf); offset = buf - page_address(page); + if (rq->use_page_pool_dma) + page_pool_dma_sync_for_cpu(rq->page_pool, page, + offset, len); + if (check_mergeable_len(dev, ctx, len)) { - put_page(page); + page_pool_put_page(rq->page_pool, page, -1, true); goto err; } @@ -2291,7 +2185,7 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev, return 0; err: - put_xdp_frags(xdp); + put_xdp_frags(rq, xdp); return -EINVAL; } @@ -2356,7 +2250,7 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi, if (*len + xdp_room > PAGE_SIZE) return NULL; - xdp_page = alloc_page(GFP_ATOMIC); + xdp_page = page_pool_alloc_pages(rq->page_pool, GFP_ATOMIC); if (!xdp_page) return NULL; @@ -2366,7 +2260,7 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi, *frame_sz = PAGE_SIZE; - put_page(*page); + page_pool_put_page(rq->page_pool, *page, -1, true); *page = xdp_page; @@ -2412,6 +2306,8 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev, head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz); if (unlikely(!head_skb)) break; + + skb_mark_for_recycle(head_skb); return head_skb; case XDP_TX: @@ -2422,10 +2318,10 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev, break; } - put_xdp_frags(&xdp); + put_xdp_frags(rq, &xdp); err_xdp: - put_page(page); + page_pool_put_page(rq->page_pool, page, -1, true); mergeable_buf_free(rq, num_buf, dev, stats); u64_stats_inc(&stats->xdp_drops); @@ -2433,7 +2329,8 @@ err_xdp: return NULL; } -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) @@ -2448,6 +2345,9 @@ static struct sk_buff *virtnet_skb_append_frag(struct sk_buff *head_skb, if (unlikely(!nskb)) return NULL; + if (head_skb->pp_recycle) + skb_mark_for_recycle(nskb); + if (curr_skb == head_skb) skb_shinfo(curr_skb)->frag_list = nskb; else @@ -2465,7 +2365,10 @@ static struct sk_buff *virtnet_skb_append_frag(struct sk_buff *head_skb, offset = buf - page_address(page); if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) { - put_page(page); + if (head_skb->pp_recycle) + page_pool_put_page(rq->page_pool, page, -1, true); + else + put_page(page); skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1, len, truesize); } else { @@ -2494,6 +2397,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, unsigned int headroom = mergeable_ctx_to_headroom(ctx); head_skb = NULL; + + if (rq->use_page_pool_dma) + page_pool_dma_sync_for_cpu(rq->page_pool, page, offset, len); + u64_stats_add(&stats->bytes, len - vi->hdr_len); if (check_mergeable_len(dev, ctx, len)) @@ -2518,6 +2425,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, if (unlikely(!curr_skb)) goto err_skb; + + skb_mark_for_recycle(head_skb); while (--num_buf) { buf = virtnet_rq_get_buf(rq, &len, &ctx); if (unlikely(!buf)) { @@ -2532,11 +2441,17 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, u64_stats_add(&stats->bytes, len); page = virt_to_head_page(buf); + if (rq->use_page_pool_dma) { + offset = buf - page_address(page); + page_pool_dma_sync_for_cpu(rq->page_pool, page, + offset, len); + } + if (check_mergeable_len(dev, ctx, len)) goto err_skb; truesize = mergeable_ctx_to_truesize(ctx); - curr_skb = virtnet_skb_append_frag(head_skb, curr_skb, page, + curr_skb = virtnet_skb_append_frag(rq, head_skb, curr_skb, page, buf, len, truesize); if (!curr_skb) goto err_skb; @@ -2546,7 +2461,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, return head_skb; err_skb: - put_page(page); + page_pool_put_page(rq->page_pool, page, -1, true); mergeable_buf_free(rq, num_buf, dev, stats); err_buf: @@ -2677,40 +2592,54 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, virtnet_receive_done(vi, rq, skb, flags); } -/* Unlike mergeable buffers, all buffers are allocated to the - * same size, except for the headroom. For this reason we do - * not need to use mergeable_len_to_ctx here - it is enough - * to store the headroom as the context ignoring the truesize. +static int virtnet_rq_submit(struct receive_queue *rq, char *buf, + int len, void *ctx, gfp_t gfp) +{ + if (rq->use_page_pool_dma) { + struct page *page = virt_to_head_page(buf); + dma_addr_t addr = page_pool_get_dma_addr(page) + + (buf - (char *)page_address(page)); + + sg_init_table(rq->sg, 1); + sg_fill_dma(rq->sg, addr, len); + return virtqueue_add_inbuf_premapped(rq->vq, rq->sg, 1, + buf, ctx, gfp); + } + + sg_init_one(rq->sg, buf, len); + return virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp); +} + +/* With page_pool, the actual allocation may exceed the requested size + * when the remaining page fragment can't fit another buffer. Encode + * the actual allocation size in ctx so build_skb() gets the correct + * buflen for truesize accounting. */ 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; + unsigned int alloc_len; + char *buf; + void *ctx; 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); + alloc_len = len; + buf = page_pool_alloc_va(rq->page_pool, &alloc_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); - - 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)); - } + ctx = mergeable_len_to_ctx(alloc_len, xdp_headroom); + err = virtnet_rq_submit(rq, buf, vi->hdr_len + GOOD_PACKET_LEN, ctx, gfp); + if (err < 0) + page_pool_put_page(rq->page_pool, virt_to_head_page(buf), -1, false); return err; } @@ -2783,13 +2712,12 @@ static unsigned int get_mergeable_buf_len(struct receive_queue *rq, static int add_recvbuf_mergeable(struct virtnet_info *vi, struct receive_queue *rq, gfp_t gfp) { - struct page_frag *alloc_frag = &rq->alloc_frag; unsigned int headroom = virtnet_get_headroom(vi); unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; unsigned int room = SKB_DATA_ALIGN(headroom + tailroom); - unsigned int len, hole; - void *ctx; + unsigned int len, alloc_len; char *buf; + void *ctx; int err; /* Extra tailroom is needed to satisfy XDP's assumption. This @@ -2798,39 +2726,22 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi, */ len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len, room); - if (unlikely(!skb_page_frag_refill(len + room, alloc_frag, gfp))) - return -ENOMEM; - - if (!alloc_frag->offset && len + room + sizeof(struct virtnet_rq_dma) > alloc_frag->size) - len -= sizeof(struct virtnet_rq_dma); - - buf = virtnet_rq_alloc(rq, len + room, gfp); + alloc_len = len + room; + buf = page_pool_alloc_va(rq->page_pool, &alloc_len, gfp); if (unlikely(!buf)) return -ENOMEM; buf += headroom; /* advance address leaving hole at front of pkt */ - hole = alloc_frag->size - alloc_frag->offset; - if (hole < len + room) { - /* To avoid internal fragmentation, if there is very likely not - * enough space for another buffer, add the remaining space to - * the current buffer. - * XDP core assumes that frame_size of xdp_buff and the length - * of the frag are PAGE_SIZE, so we disable the hole mechanism. - */ - if (!headroom) - len += hole; - alloc_frag->offset += hole; - } - virtnet_rq_init_one_sg(rq, buf, len); + if (!headroom) + len = alloc_len - room; ctx = mergeable_len_to_ctx(len + room, headroom); - 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)); - } + err = virtnet_rq_submit(rq, buf, len, ctx, gfp); + + if (err < 0) + page_pool_put_page(rq->page_pool, virt_to_head_page(buf), -1, false); return err; } @@ -2984,7 +2895,7 @@ static int virtnet_receive_packets(struct virtnet_info *vi, int packets = 0; void *buf; - if (!vi->big_packets || vi->mergeable_rx_bufs) { + if (rq->page_pool) { void *ctx; while (packets < budget && (buf = virtnet_rq_get_buf(rq, &len, &ctx))) { @@ -3149,7 +3060,10 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) return err; err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL); + vi->rq[qp_index].page_pool ? + MEM_TYPE_PAGE_POOL : + MEM_TYPE_PAGE_SHARED, + vi->rq[qp_index].page_pool); if (err < 0) goto err_xdp_reg_mem_model; @@ -3189,6 +3103,82 @@ static void virtnet_update_settings(struct virtnet_info *vi) vi->duplex = duplex; } +static int virtnet_create_page_pools(struct virtnet_info *vi) +{ + int i, err; + + if (vi->big_packets && !vi->mergeable_rx_bufs) + return 0; + + for (i = 0; i < vi->max_queue_pairs; i++) { + struct receive_queue *rq = &vi->rq[i]; + struct page_pool_params pp_params = { 0 }; + struct device *dma_dev; + + if (rq->page_pool) + continue; + + if (rq->xsk_pool) + continue; + + pp_params.order = 0; + pp_params.pool_size = virtqueue_get_vring_size(rq->vq); + pp_params.nid = dev_to_node(vi->vdev->dev.parent); + pp_params.netdev = vi->dev; + pp_params.napi = &rq->napi; + + /* Use page_pool DMA mapping if backend supports DMA API. + * DMA_SYNC_DEV is needed for non-coherent archs on recycle. + */ + dma_dev = virtqueue_dma_dev(rq->vq); + if (dma_dev) { + pp_params.dev = dma_dev; + 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.offset = 0; + rq->use_page_pool_dma = true; + } else { + /* No DMA API (e.g., VDUSE): page_pool for allocation only. */ + pp_params.flags = 0; + rq->use_page_pool_dma = false; + } + + rq->page_pool = page_pool_create(&pp_params); + if (IS_ERR(rq->page_pool)) { + err = PTR_ERR(rq->page_pool); + rq->page_pool = NULL; + goto err_cleanup; + } + } + return 0; + +err_cleanup: + while (--i >= 0) { + struct receive_queue *rq = &vi->rq[i]; + + if (rq->page_pool) { + page_pool_destroy(rq->page_pool); + rq->page_pool = NULL; + } + } + return err; +} + +static void virtnet_destroy_page_pools(struct virtnet_info *vi) +{ + int i; + + for (i = 0; i < vi->max_queue_pairs; i++) { + struct receive_queue *rq = &vi->rq[i]; + + if (rq->page_pool) { + page_pool_destroy(rq->page_pool); + rq->page_pool = NULL; + } + } +} + static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -5736,6 +5726,10 @@ static int virtnet_restore_up(struct virtio_device *vdev) if (err) return err; + err = virtnet_create_page_pools(vi); + if (err) + goto err_del_vqs; + virtio_device_ready(vdev); enable_rx_mode_work(vi); @@ -5745,12 +5739,24 @@ static int virtnet_restore_up(struct virtio_device *vdev) err = virtnet_open(vi->dev); rtnl_unlock(); if (err) - return err; + goto err_destroy_pools; } netif_tx_lock_bh(vi->dev); netif_device_attach(vi->dev); netif_tx_unlock_bh(vi->dev); + return 0; + +err_destroy_pools: + virtio_reset_device(vdev); + free_unused_bufs(vi); + virtnet_destroy_page_pools(vi); + virtnet_del_vqs(vi); + return err; + +err_del_vqs: + virtio_reset_device(vdev); + virtnet_del_vqs(vi); return err; } @@ -5878,7 +5884,7 @@ static int virtnet_xsk_pool_enable(struct net_device *dev, /* In big_packets mode, xdp cannot work, so there is no need to * initialize xsk of rq. */ - if (vi->big_packets && !vi->mergeable_rx_bufs) + if (!vi->rq[qid].page_pool) return -ENOENT; if (qid >= vi->curr_queue_pairs) @@ -6308,17 +6314,6 @@ static void free_receive_bufs(struct virtnet_info *vi) rtnl_unlock(); } -static void free_receive_page_frags(struct virtnet_info *vi) -{ - int i; - for (i = 0; i < vi->max_queue_pairs; i++) - if (vi->rq[i].alloc_frag.page) { - if (vi->rq[i].last_dma) - virtnet_rq_unmap(&vi->rq[i], vi->rq[i].last_dma, 0); - put_page(vi->rq[i].alloc_frag.page); - } -} - static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf) { struct virtnet_info *vi = vq->vdev->priv; @@ -6422,7 +6417,7 @@ static int virtnet_find_vqs(struct virtnet_info *vi) vqs_info = kzalloc_objs(*vqs_info, total_vqs); if (!vqs_info) goto err_vqs_info; - if (!vi->big_packets || vi->mergeable_rx_bufs) { + if (vi->mergeable_rx_bufs || !vi->big_packets) { ctx = kzalloc_objs(*ctx, total_vqs); if (!ctx) goto err_ctx; @@ -6462,10 +6457,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi) vi->rq[i].min_buf_len = mergeable_min_buf_len(vi, vi->rq[i].vq); vi->sq[i].vq = vqs[txq2vq(i)]; } - /* run here: ret == 0. */ - err_find: kfree(ctx); err_ctx: @@ -6966,6 +6959,14 @@ static int virtnet_probe(struct virtio_device *vdev) goto free; } + /* Create page pools for receive queues. + * Page pools are created at probe time so they can be used + * with premapped DMA addresses throughout the device lifetime. + */ + err = virtnet_create_page_pools(vi); + if (err) + goto free_irq_moder; + #ifdef CONFIG_SYSFS if (vi->mergeable_rx_bufs) dev->sysfs_rx_queue_group = &virtio_net_mrg_rx_group; @@ -6979,7 +6980,7 @@ static int virtnet_probe(struct virtio_device *vdev) vi->failover = net_failover_create(vi->dev); if (IS_ERR(vi->failover)) { err = PTR_ERR(vi->failover); - goto free_vqs; + goto free_page_pools; } } @@ -7096,9 +7097,11 @@ free_unregister_netdev: unregister_netdev(dev); free_failover: net_failover_destroy(vi->failover); -free_vqs: +free_page_pools: + virtnet_destroy_page_pools(vi); +free_irq_moder: + virtnet_free_irq_moder(vi); virtio_reset_device(vdev); - free_receive_page_frags(vi); virtnet_del_vqs(vi); free: free_netdev(dev); @@ -7123,7 +7126,7 @@ static void remove_vq_common(struct virtnet_info *vi) free_receive_bufs(vi); - free_receive_page_frags(vi); + virtnet_destroy_page_pools(vi); virtnet_del_vqs(vi); }