| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <30b7a2a4-43cf-4c31-84ab-4e64d733a93c@meta.com>
Date: Thu, 29 Jan 2026 09:20:50 -0800
From: Vishwanath Seshagiri <vishs@...a.com>
To: Jason Wang <jasowang@...hat.com>
Cc: "Michael S . Tsirkin" <mst@...hat.com>,
Xuan Zhuo <xuanzhuo@...ux.alibaba.com>,
Eugenio Pérez
<eperezma@...hat.com>,
Andrew Lunn <andrew+netdev@...n.ch>,
"David S . Miller" <davem@...emloft.net>,
Eric Dumazet
<edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>, David Wei <dw@...idwei.uk>,
netdev@...r.kernel.org, virtualization@...ts.linux.dev,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 net-next 1/2] virtio_net: add page_pool support for
buffer allocation
On 1/28/26 6:54 PM, Jason Wang wrote:
> On Thu, Jan 29, 2026 at 5:20 AM Vishwanath Seshagiri <vishs@...a.com> 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.
>>
>> The rx_mode_work_enabled flag prevents virtnet_rx_mode_work() from
>> sending control virtqueue commands while ndo_close is tearing down
>> device state, avoiding virtqueue corruption during concurrent operations.
>>
>> Signed-off-by: Vishwanath Seshagiri <vishs@...a.com>
>> ---
>> drivers/net/Kconfig | 1 +
>> drivers/net/virtio_net.c | 353 ++++++++++++++++++++++-----------------
>> 2 files changed, 203 insertions(+), 151 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..df2a5fc5187e 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);
>> @@ -359,6 +360,11 @@ struct receive_queue {
>> /* 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];
>>
>> @@ -521,11 +527,13 @@ 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);
>>
>> enum virtnet_xmit_type {
>> VIRTNET_XMIT_TYPE_SKB,
>> @@ -706,15 +714,21 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
>> return p;
>> }
>>
>> +static void virtnet_put_page(struct receive_queue *rq, struct page *page,
>> + bool allow_direct)
>> +{
>> + page_pool_put_page(rq->page_pool, page, -1, allow_direct);
>> +}
>> +
>> 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));
>> + virtnet_put_page(rq, virt_to_head_page(buf), false);
>> else if (vi->big_packets)
>> give_pages(rq, buf);
>> else
>> - put_page(virt_to_head_page(buf));
>> + virtnet_put_page(rq, virt_to_head_page(buf), false);
>> }
>>
>> static void enable_rx_mode_work(struct virtnet_info *vi)
>> @@ -877,9 +891,6 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
>> if (unlikely(!skb))
>> return NULL;
>>
>> - page = (struct page *)page->private;
>> - if (page)
>> - give_pages(rq, page);
>
> Note that the page_to_skb() will be used by the big mode. So this
> change may break big mode.
Good catch. I incorrectly removed it, and will restore it for
big_packets mode in v3.
>
>> goto ok;
>> }
>>
>> @@ -914,18 +925,14 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
>> skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset,
>> frag_size, truesize);
>> len -= frag_size;
>> - page = (struct page *)page->private;
>
> And this.
Same as above. will restore in v3.
>
>> offset = 0;
>> }
>>
>> - if (page)
>> - give_pages(rq, page);
>> -
>> ok:
>> hdr = skb_vnet_common_hdr(skb);
>> memcpy(hdr, hdr_p, hdr_len);
>> if (page_to_free)
>> - put_page(page_to_free);
>> + virtnet_put_page(rq, page_to_free, true);
>>
>> return skb;
>> }
>> @@ -965,93 +972,10 @@ static void virtnet_rq_unmap(struct receive_queue *rq, void *buf, u32 len)
>> 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);
>> -
>> - 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 +991,6 @@ 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 +1256,7 @@ 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);
>> @@ -1771,7 +1692,7 @@ static int virtnet_xdp_xmit(struct net_device *dev,
>> return ret;
>> }
>>
>> -static void put_xdp_frags(struct xdp_buff *xdp)
>> +static void put_xdp_frags(struct xdp_buff *xdp, struct receive_queue *rq)
>> {
>> struct skb_shared_info *shinfo;
>> struct page *xdp_page;
>> @@ -1781,7 +1702,7 @@ 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);
>> + virtnet_put_page(rq, xdp_page, true);
>> }
>> }
>> }
>> @@ -1897,7 +1818,7 @@ static struct page *xdp_linearize_page(struct net_device *dev,
>> off = buf - page_address(p);
>>
>> if (check_mergeable_len(dev, ctx, buflen)) {
>> - put_page(p);
>> + virtnet_put_page(rq, p, true);
>> goto err_buf;
>> }
>>
>> @@ -1905,14 +1826,14 @@ 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);
>> + virtnet_put_page(rq, p, true);
>> goto err_buf;
>> }
>>
>> memcpy(page_address(page) + page_off,
>> page_address(p) + off, buflen);
>> page_off += buflen;
>> - put_page(p);
>> + virtnet_put_page(rq, p, true);
>> }
>>
>> /* Headroom does not contribute to packet length */
>> @@ -1962,7 +1883,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
>> unsigned int headroom = vi->hdr_len + header_offset;
>> struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset;
>> struct page *page = virt_to_head_page(buf);
>> - struct page *xdp_page;
>> + struct page *xdp_page = NULL;
>> unsigned int buflen;
>> struct xdp_buff xdp;
>> struct sk_buff *skb;
>> @@ -1996,7 +1917,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
>> goto err_xdp;
>>
>> buf = page_address(xdp_page);
>> - put_page(page);
>> + virtnet_put_page(rq, page, true);
>> page = xdp_page;
>> }
>>
>> @@ -2028,13 +1949,19 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
>> if (metasize)
>> skb_metadata_set(skb, metasize);
>>
>> + if (!xdp_page)
>> + skb_mark_for_recycle(skb);
>
> I wonder would it better to use page pool in xdp_linearize_page() as
> well to simply the codes here?
Allocating the linearization page from the page_pool would eliminate the
need for the xdp_page tracking, and simplify skb_mark_for_recycle. I
will update v3 to use page_pool_alloc_pages() in xdp_linearize_page().
>
>> +
>> return skb;
>>
>> err_xdp:
>> u64_stats_inc(&stats->xdp_drops);
>> err:
>> u64_stats_inc(&stats->drops);
>> - put_page(page);
>> + if (xdp_page)
>> + put_page(page);
>> + else
>> + virtnet_put_page(rq, page, true);
>
> And here, and the similar path in mergeable XDP handling.
Same as above. Will change it in v3.
>
>> xdp_xmit:
>> return NULL;
>> }
>> @@ -2082,12 +2009,14 @@ static struct sk_buff *receive_small(struct net_device *dev,
>> }
>>
>> skb = receive_small_build_skb(vi, xdp_headroom, buf, len);
>> - if (likely(skb))
>> + if (likely(skb)) {
>> + skb_mark_for_recycle(skb);
>> return skb;
>> + }
>>
>> err:
>> u64_stats_inc(&stats->drops);
>> - put_page(page);
>> + virtnet_put_page(rq, page, true);
>> return NULL;
>> }
>>
>> @@ -2142,7 +2071,7 @@ 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);
>> + virtnet_put_page(rq, page, true);
>> }
>> }
>>
>> @@ -2253,7 +2182,7 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev,
>> offset = buf - page_address(page);
>>
>> if (check_mergeable_len(dev, ctx, len)) {
>> - put_page(page);
>> + virtnet_put_page(rq, page, true);
>> goto err;
>> }
>>
>> @@ -2272,7 +2201,7 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev,
>> return 0;
>>
>> err:
>> - put_xdp_frags(xdp);
>> + put_xdp_frags(xdp, rq);
>> return -EINVAL;
>> }
>>
>> @@ -2347,7 +2276,7 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi,
>>
>> *frame_sz = PAGE_SIZE;
>>
>> - put_page(*page);
>> + virtnet_put_page(rq, *page, true);
>>
>> *page = xdp_page;
>>
>> @@ -2369,6 +2298,7 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev,
>> struct page *page = virt_to_head_page(buf);
>> int offset = buf - page_address(page);
>> unsigned int xdp_frags_truesz = 0;
>> + struct page *org_page = page;
>> struct sk_buff *head_skb;
>> unsigned int frame_sz;
>> struct xdp_buff xdp;
>> @@ -2393,6 +2323,8 @@ 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;
>> + if (page == org_page)
>> + skb_mark_for_recycle(head_skb);
>> return head_skb;
>>
>> case XDP_TX:
>> @@ -2403,10 +2335,13 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev,
>> break;
>> }
>>
>> - put_xdp_frags(&xdp);
>> + put_xdp_frags(&xdp, rq);
>>
>> err_xdp:
>> - put_page(page);
>> + if (page != org_page)
>> + put_page(page);
>> + else
>> + virtnet_put_page(rq, page, true);
>> mergeable_buf_free(rq, num_buf, dev, stats);
>>
>> u64_stats_inc(&stats->xdp_drops);
>> @@ -2414,7 +2349,8 @@ static struct sk_buff *receive_mergeable_xdp(struct net_device *dev,
>> 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)
>> @@ -2446,7 +2382,7 @@ 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);
>> + virtnet_put_page(rq, page, true);
>> skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1,
>> len, truesize);
>> } else {
>> @@ -2495,10 +2431,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
>> }
>>
>> head_skb = page_to_skb(vi, rq, page, offset, len, truesize, headroom);
>> + if (unlikely(!head_skb))
>> + goto err_skb;
>> +
>> curr_skb = head_skb;
>>
>> - if (unlikely(!curr_skb))
>> - goto err_skb;
>
> This change sees to be useless?
Moved it around when making changes. Will revert in v3.
>
>> + skb_mark_for_recycle(head_skb);
>> while (--num_buf) {
>> buf = virtnet_rq_get_buf(rq, &len, &ctx);
>> if (unlikely(!buf)) {
>> @@ -2517,7 +2455,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
>> 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;
>> @@ -2527,7 +2465,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
>> return head_skb;
>>
>> err_skb:
>> - put_page(page);
>> + virtnet_put_page(rq, page, true);
>> mergeable_buf_free(rq, num_buf, dev, stats);
>>
>> err_buf:
>> @@ -2666,6 +2604,8 @@ 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)
>> {
>> + unsigned int offset;
>> + struct page *page;
>> char *buf;
>> unsigned int xdp_headroom = virtnet_get_headroom(vi);
>> void *ctx = (void *)(unsigned long)xdp_headroom;
>> @@ -2675,23 +2615,30 @@ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
>> 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);
>> - if (unlikely(!buf))
>> + page = page_pool_alloc_frag(rq->page_pool, &offset, len, gfp);
>> + if (unlikely(!page))
>> return -ENOMEM;
>>
>> + buf = page_address(page) + offset;
>> buf += VIRTNET_RX_PAD + xdp_headroom;
>>
>> - virtnet_rq_init_one_sg(rq, buf, vi->hdr_len + GOOD_PACKET_LEN);
>> + sg_init_table(rq->sg, 1);
>>
>> - 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));
>> + if (rq->use_page_pool_dma) {
>> + dma_addr_t addr = page_pool_get_dma_addr(page) + offset;
>> +
>> + addr += VIRTNET_RX_PAD + xdp_headroom;
>> + 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_set_buf(&rq->sg[0], buf, vi->hdr_len + GOOD_PACKET_LEN);
>> + err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
>> }
>>
>> + if (err < 0)
>> + page_pool_put_page(rq->page_pool, virt_to_head_page(buf),
>> + -1, false);
>> return err;
>> }
>>
>> @@ -2764,11 +2711,12 @@ 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;
>> + unsigned int offset;
>> + struct page *page;
>> void *ctx;
>> char *buf;
>> int err;
>> @@ -2779,18 +2727,14 @@ 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);
>> - if (unlikely(!buf))
>> + page = page_pool_alloc_frag(rq->page_pool, &offset, len + room, gfp);
>> + if (unlikely(!page))
>> return -ENOMEM;
>>
>> + buf = page_address(page) + offset;
>> buf += headroom; /* advance address leaving hole at front of pkt */
>> - hole = alloc_frag->size - alloc_frag->offset;
>> +
>> + hole = PAGE_SIZE - (offset + len + room);
>> if (hole < len + room) {
>> /* To avoid internal fragmentation, if there is very likely not
>> * enough space for another buffer, add the remaining space to
>> @@ -2800,18 +2744,27 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
>> */
>> if (!headroom)
>> len += hole;
>> - alloc_frag->offset += hole;
>> }
>>
>> - virtnet_rq_init_one_sg(rq, buf, len);
>> -
>> 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));
>> +
>> + sg_init_table(rq->sg, 1);
>> +
>> + if (rq->use_page_pool_dma) {
>> + dma_addr_t addr = page_pool_get_dma_addr(page) + offset;
>> +
>> + addr += headroom;
>> + sg_fill_dma(rq->sg, addr, len);
>> + err = virtqueue_add_inbuf_premapped(rq->vq, rq->sg, 1, buf,
>> + ctx, gfp);
>> + } else {
>> + sg_set_buf(&rq->sg[0], buf, len);
>> + err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
>> }
>>
>> + if (err < 0)
>> + page_pool_put_page(rq->page_pool, virt_to_head_page(buf),
>> + -1, false);
>> return err;
>> }
>>
>> @@ -3128,7 +3081,10 @@ 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;
>>
>> @@ -3168,6 +3124,81 @@ 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;
>> +
>> + for (i = 0; i < vi->curr_queue_pairs; i++) {
>
> This should be max_queue_paris, or page pools for new enabled queue
> pairs need to be created on demand during set_queues().
Will fix it to max_queue_pairs in v3, and update my testing env since
this broke the ci as well.
>
>> + 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;
>> +
>> + if (!vi->mergeable_rx_bufs && vi->big_packets)
>> + 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;
>> +
>> + /* Check if backend supports DMA API (e.g., vhost, virtio-pci).
>> + * If so, use page_pool's DMA mapping for premapped buffers.
>> + * Otherwise (e.g., VDUSE), page_pool only handles allocation.
>> + */
>> + dma_dev = virtqueue_dma_dev(rq->vq);
>> + if (dma_dev) {
>> + pp_params.dev = dma_dev;
>> + pp_params.flags = PP_FLAG_DMA_MAP;
>> + pp_params.dma_dir = DMA_FROM_DEVICE;
>> + rq->use_page_pool_dma = true;
>> + } else {
>> + pp_params.dev = vi->vdev->dev.parent;
>> + 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);
>> @@ -3771,6 +3802,8 @@ static int virtnet_close(struct net_device *dev)
>> */
>> cancel_work_sync(&vi->config_work);
>>
>> + vi->rx_mode_work_enabled = false;
>> +
>> for (i = 0; i < vi->max_queue_pairs; i++) {
>> virtnet_disable_queue_pair(vi, i);
>> virtnet_cancel_dim(vi, &vi->rq[i].dim);
>> @@ -3807,6 +3840,11 @@ static void virtnet_rx_mode_work(struct work_struct *work)
>>
>> rtnl_lock();
>>
>> + if (!vi->rx_mode_work_enabled) {
>> + rtnl_unlock();
>> + return;
>> + }
>
> Is this a separated fix? I don't see the connection to the page pool.
It happened when I was trying to send traffic to the vm once the
interface went down. There are already helpers that handle this flag
with proper locking. I will remove it in v3.
>
>> +
>> *promisc_allmulti = !!(dev->flags & IFF_PROMISC);
>> sg_init_one(sg, promisc_allmulti, sizeof(*promisc_allmulti));
>>
>> @@ -6945,6 +6983,14 @@ 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;
>> @@ -6958,7 +7004,7 @@ 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;
>> }
>> }
>>
>> @@ -7075,7 +7121,10 @@ static int virtnet_probe(struct virtio_device *vdev)
>> 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);
>> @@ -7104,6 +7153,8 @@ static void remove_vq_common(struct virtnet_info *vi)
>>
>> free_receive_page_frags(vi);
>>
>> + virtnet_destroy_page_pools(vi);
>> +
>> virtnet_del_vqs(vi);
>> }
>>
>> --
>> 2.47.3
>>
>
> Thanks
>
Powered by blists - more mailing lists