summaryrefslogtreecommitdiff
path: root/drivers/net/virtio_net.c
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2023-03-17 16:29:25 -0700
committerJakub Kicinski <kuba@kernel.org>2023-03-17 16:29:25 -0700
commit1118aa4c70a6978afb0c4391ad29826c14b842b3 (patch)
tree7286d535c06b720d45f0427f9060b42bf8ab1425 /drivers/net/virtio_net.c
parent79a22238b4f22c45cadd3b4040d644f4de320d1b (diff)
parent478a351ce0d69cef2d2bf2a686a09b356b63a66c (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
net/wireless/nl80211.c b27f07c50a73 ("wifi: nl80211: fix puncturing bitmap policy") cbbaf2bb829b ("wifi: nl80211: add a command to enable/disable HW timestamping") https://lore.kernel.org/all/20230314105421.3608efae@canb.auug.org.au tools/testing/selftests/net/Makefile 62199e3f1658 ("selftests: net: Add VXLAN MDB test") 13715acf8ab5 ("selftest: Add test for bind() conflicts.") Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'drivers/net/virtio_net.c')
-rw-r--r--drivers/net/virtio_net.c171
1 files changed, 95 insertions, 76 deletions
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index e85b03988733..e2560b6f7980 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -447,7 +447,8 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx)
static struct sk_buff *page_to_skb(struct virtnet_info *vi,
struct receive_queue *rq,
struct page *page, unsigned int offset,
- unsigned int len, unsigned int truesize)
+ unsigned int len, unsigned int truesize,
+ unsigned int headroom)
{
struct sk_buff *skb;
struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -465,11 +466,11 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
else
hdr_padded_len = sizeof(struct padded_vnet_hdr);
- buf = p;
+ buf = p - headroom;
len -= hdr_len;
offset += hdr_padded_len;
p += hdr_padded_len;
- tailroom = truesize - hdr_padded_len - len;
+ tailroom = truesize - headroom - hdr_padded_len - len;
shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
@@ -546,6 +547,87 @@ ok:
return skb;
}
+static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
+{
+ unsigned int len;
+ unsigned int packets = 0;
+ unsigned int bytes = 0;
+ void *ptr;
+
+ while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+ if (likely(!is_xdp_frame(ptr))) {
+ struct sk_buff *skb = ptr;
+
+ pr_debug("Sent skb %p\n", skb);
+
+ bytes += skb->len;
+ napi_consume_skb(skb, in_napi);
+ } else {
+ struct xdp_frame *frame = ptr_to_xdp(ptr);
+
+ bytes += xdp_get_frame_len(frame);
+ xdp_return_frame(frame);
+ }
+ packets++;
+ }
+
+ /* Avoid overhead when no packets have been processed
+ * happens when called speculatively from start_xmit.
+ */
+ if (!packets)
+ return;
+
+ u64_stats_update_begin(&sq->stats.syncp);
+ sq->stats.bytes += bytes;
+ sq->stats.packets += packets;
+ u64_stats_update_end(&sq->stats.syncp);
+}
+
+static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
+{
+ if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
+ return false;
+ else if (q < vi->curr_queue_pairs)
+ return true;
+ else
+ return false;
+}
+
+static void check_sq_full_and_disable(struct virtnet_info *vi,
+ struct net_device *dev,
+ struct send_queue *sq)
+{
+ bool use_napi = sq->napi.weight;
+ int qnum;
+
+ qnum = sq - vi->sq;
+
+ /* If running out of space, stop queue to avoid getting packets that we
+ * are then unable to transmit.
+ * An alternative would be to force queuing layer to requeue the skb by
+ * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be
+ * returned in a normal path of operation: it means that driver is not
+ * maintaining the TX queue stop/start state properly, and causes
+ * the stack to do a non-trivial amount of useless work.
+ * Since most packets only take 1 or 2 ring slots, stopping the queue
+ * early means 16 slots are typically wasted.
+ */
+ if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
+ netif_stop_subqueue(dev, qnum);
+ if (use_napi) {
+ if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
+ virtqueue_napi_schedule(&sq->napi, sq->vq);
+ } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
+ /* More just got used, free them then recheck. */
+ free_old_xmit_skbs(sq, false);
+ if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
+ netif_start_subqueue(dev, qnum);
+ virtqueue_disable_cb(sq->vq);
+ }
+ }
+ }
+}
+
static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
struct send_queue *sq,
struct xdp_frame *xdpf)
@@ -687,6 +769,9 @@ static int virtnet_xdp_xmit(struct net_device *dev,
}
ret = nxmit;
+ if (!is_xdp_raw_buffer_queue(vi, sq - vi->sq))
+ check_sq_full_and_disable(vi, dev, sq);
+
if (flags & XDP_XMIT_FLUSH) {
if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq))
kicks = 1;
@@ -926,7 +1011,7 @@ static struct sk_buff *receive_big(struct net_device *dev,
{
struct page *page = buf;
struct sk_buff *skb =
- page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
+ page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, 0);
stats->bytes += len - vi->hdr_len;
if (unlikely(!skb))
@@ -1189,9 +1274,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
switch (act) {
case XDP_PASS:
+ head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz);
+ if (unlikely(!head_skb))
+ goto err_xdp_frags;
+
if (unlikely(xdp_page != page))
put_page(page);
- head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz);
rcu_read_unlock();
return head_skb;
case XDP_TX:
@@ -1249,7 +1337,7 @@ err_xdp_frags:
rcu_read_unlock();
skip_xdp:
- head_skb = page_to_skb(vi, rq, page, offset, len, truesize);
+ head_skb = page_to_skb(vi, rq, page, offset, len, truesize, headroom);
curr_skb = head_skb;
if (unlikely(!curr_skb))
@@ -1715,52 +1803,6 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
return stats.packets;
}
-static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
-{
- unsigned int len;
- unsigned int packets = 0;
- unsigned int bytes = 0;
- void *ptr;
-
- while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
- if (likely(!is_xdp_frame(ptr))) {
- struct sk_buff *skb = ptr;
-
- pr_debug("Sent skb %p\n", skb);
-
- bytes += skb->len;
- napi_consume_skb(skb, in_napi);
- } else {
- struct xdp_frame *frame = ptr_to_xdp(ptr);
-
- bytes += xdp_get_frame_len(frame);
- xdp_return_frame(frame);
- }
- packets++;
- }
-
- /* Avoid overhead when no packets have been processed
- * happens when called speculatively from start_xmit.
- */
- if (!packets)
- return;
-
- u64_stats_update_begin(&sq->stats.syncp);
- sq->stats.bytes += bytes;
- sq->stats.packets += packets;
- u64_stats_update_end(&sq->stats.syncp);
-}
-
-static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
-{
- if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
- return false;
- else if (q < vi->curr_queue_pairs)
- return true;
- else
- return false;
-}
-
static void virtnet_poll_cleantx(struct receive_queue *rq)
{
struct virtnet_info *vi = rq->vq->vdev->priv;
@@ -1990,30 +2032,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
nf_reset_ct(skb);
}
- /* If running out of space, stop queue to avoid getting packets that we
- * are then unable to transmit.
- * An alternative would be to force queuing layer to requeue the skb by
- * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be
- * returned in a normal path of operation: it means that driver is not
- * maintaining the TX queue stop/start state properly, and causes
- * the stack to do a non-trivial amount of useless work.
- * Since most packets only take 1 or 2 ring slots, stopping the queue
- * early means 16 slots are typically wasted.
- */
- if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
- netif_stop_subqueue(dev, qnum);
- if (use_napi) {
- if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
- virtqueue_napi_schedule(&sq->napi, sq->vq);
- } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
- /* More just got used, free them then recheck. */
- free_old_xmit_skbs(sq, false);
- if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
- netif_start_subqueue(dev, qnum);
- virtqueue_disable_cb(sq->vq);
- }
- }
- }
+ check_sq_full_and_disable(vi, dev, sq);
if (kick || netif_xmit_stopped(txq)) {
if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {