- v9:
https://lore.kernel.org/virtualization/20260302041005.1627210-1-
[email protected]/
Changes in v9:
- Fix virtnet_skb_append_frag() for XSK callers (Michael S. Tsirkin)
- v8:
https://lore.kernel.org/virtualization/e824c5a3-cfe0-4d11-958f-
[email protected]/
Changes in v8:
- Remove virtnet_no_page_pool() helper, replace with direct !rq-
>page_pool
checks or inlined conditions (Xuan Zhuo)
- Extract virtnet_rq_submit() helper to consolidate DMA/non-DMA buffer
submission in add_recvbuf_small() and add_recvbuf_mergeable()
- Add skb_mark_for_recycle(nskb) for overflow frag_list skbs in
virtnet_skb_append_frag() to ensure page_pool pages are returned to
the pool instead of freed via put_page()
- Rebase on net-next (kzalloc_objs API)
- v7:
https://lore.kernel.org/virtualization/20260210014305.3236342-1-
[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/20260208175410.1910001-1-
[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/20260206002715.1885869-1-
[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 | 466 ++++++++++++++++++++-------------------
2 files changed, 237 insertions(+), 230 deletions(-)
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 17108c359216..b2fd90466bab 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 72d6a9c6a5a2..d722031604bf 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,
@@ -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 @@ static struct sk_buff *page_to_skb(struct
virtnet_info *vi,
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);
-
- 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;
+ BUG_ON(!rq->page_pool);
- 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);
@@ -1771,7 +1650,7 @@ 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 receive_queue *rq, struct xdp_buff
*xdp)
{
struct skb_shared_info *shinfo;
struct page *xdp_page;
@@ -1781,7 +1660,7 @@ 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);
}
}
}
@@ -1873,7 +1752,7 @@ 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;
@@ -1896,8 +1775,12 @@ 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;
}
@@ -1905,21 +1788,21 @@ 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;
}
@@ -1996,7 +1879,7 @@ 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;
}
@@ -2028,13 +1911,15 @@ 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;
}
@@ -2056,6 +1941,13 @@ 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);
@@ -2082,12 +1974,14 @@ 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);
+ page_pool_put_page(rq->page_pool, page, -1, true);
return NULL;
}
@@ -2142,7 +2036,7 @@ 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);
}
}
@@ -2252,8 +2146,12 @@ 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;
}
@@ -2272,7 +2170,7 @@ 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;
}
@@ -2337,7 +2235,7 @@ 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;
@@ -2347,7 +2245,7 @@ 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;
@@ -2393,6 +2291,8 @@ 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:
@@ -2403,10 +2303,10 @@ 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);
@@ -2414,7 +2314,8 @@ 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)
@@ -2429,6 +2330,9 @@ 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
@@ -2446,7 +2350,10 @@ 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 {
@@ -2475,6 +2382,10 @@ 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))
@@ -2499,6 +2410,8 @@ 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)) {
@@ -2513,11 +2426,17 @@ 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;
@@ -2527,7 +2446,7 @@ 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:
@@ -2658,6 +2577,24 @@ static void receive_buf(struct virtnet_info
*vi, struct receive_queue *rq,
virtnet_receive_done(vi, rq, skb, flags);
}
+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);
+}
+
/* 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
@@ -2666,32 +2603,27 @@ 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;
+ unsigned int alloc_len;
+ 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;
-
