+++ /dev/null
-From 101b2472b191ddce8862c72a7517358794a3a98c Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 18 Jun 2024 16:44:56 +0200
-Subject: virtio_net: add support for Byte Queue Limits
-
-From: Jiri Pirko <jiri@nvidia.com>
-
-[ Upstream commit c8bd1f7f3e61fc6c562c806045f3ccd2cc819c01 ]
-
-Add support for Byte Queue Limits (BQL).
-
-Tested on qemu emulated virtio_net device with 1, 2 and 4 queues.
-Tested with fq_codel and pfifo_fast. Super netperf with 50 threads is
-running in background. Netperf TCP_RR results:
-
-NOBQL FQC 1q: 159.56 159.33 158.50 154.31 agv: 157.925
-NOBQL FQC 2q: 184.64 184.96 174.73 174.15 agv: 179.62
-NOBQL FQC 4q: 994.46 441.96 416.50 499.56 agv: 588.12
-NOBQL PFF 1q: 148.68 148.92 145.95 149.48 agv: 148.2575
-NOBQL PFF 2q: 171.86 171.20 170.42 169.42 agv: 170.725
-NOBQL PFF 4q: 1505.23 1137.23 2488.70 3507.99 agv: 2159.7875
- BQL FQC 1q: 1332.80 1297.97 1351.41 1147.57 agv: 1282.4375
- BQL FQC 2q: 768.30 817.72 864.43 974.40 agv: 856.2125
- BQL FQC 4q: 945.66 942.68 878.51 822.82 agv: 897.4175
- BQL PFF 1q: 149.69 151.49 149.40 147.47 agv: 149.5125
- BQL PFF 2q: 2059.32 798.74 1844.12 381.80 agv: 1270.995
- BQL PFF 4q: 1871.98 4420.02 4916.59 13268.16 agv: 6119.1875
-
-Signed-off-by: Jiri Pirko <jiri@nvidia.com>
-Acked-by: Michael S. Tsirkin <mst@redhat.com>
-Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
-Link: https://lore.kernel.org/r/20240618144456.1688998-1-jiri@resnulli.us
-Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-Stable-dep-of: f8321fa75102 ("virtio_net: Fix napi_skb_cache_put warning")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- drivers/net/virtio_net.c | 81 ++++++++++++++++++++++++++++------------
- 1 file changed, 57 insertions(+), 24 deletions(-)
-
-diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
-index ea10db9a09fa2..b1f8b720733e5 100644
---- a/drivers/net/virtio_net.c
-+++ b/drivers/net/virtio_net.c
-@@ -47,7 +47,8 @@ module_param(napi_tx, bool, 0644);
- #define VIRTIO_XDP_TX BIT(0)
- #define VIRTIO_XDP_REDIR BIT(1)
-
--#define VIRTIO_XDP_FLAG BIT(0)
-+#define VIRTIO_XDP_FLAG BIT(0)
-+#define VIRTIO_ORPHAN_FLAG BIT(1)
-
- /* RX packet size EWMA. The average packet size is used to determine the packet
- * buffer size when refilling RX rings. As the entire RX ring may be refilled
-@@ -85,6 +86,8 @@ struct virtnet_stat_desc {
- struct virtnet_sq_free_stats {
- u64 packets;
- u64 bytes;
-+ u64 napi_packets;
-+ u64 napi_bytes;
- };
-
- struct virtnet_sq_stats {
-@@ -506,29 +509,50 @@ static struct xdp_frame *ptr_to_xdp(void *ptr)
- return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG);
- }
-
--static void __free_old_xmit(struct send_queue *sq, bool in_napi,
-- struct virtnet_sq_free_stats *stats)
-+static bool is_orphan_skb(void *ptr)
-+{
-+ return (unsigned long)ptr & VIRTIO_ORPHAN_FLAG;
-+}
-+
-+static void *skb_to_ptr(struct sk_buff *skb, bool orphan)
-+{
-+ return (void *)((unsigned long)skb | (orphan ? VIRTIO_ORPHAN_FLAG : 0));
-+}
-+
-+static struct sk_buff *ptr_to_skb(void *ptr)
-+{
-+ return (struct sk_buff *)((unsigned long)ptr & ~VIRTIO_ORPHAN_FLAG);
-+}
-+
-+static void __free_old_xmit(struct send_queue *sq, struct netdev_queue *txq,
-+ bool in_napi, struct virtnet_sq_free_stats *stats)
- {
- unsigned int len;
- void *ptr;
-
- while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-- ++stats->packets;
--
- if (!is_xdp_frame(ptr)) {
-- struct sk_buff *skb = ptr;
-+ struct sk_buff *skb = ptr_to_skb(ptr);
-
- pr_debug("Sent skb %p\n", skb);
-
-- stats->bytes += skb->len;
-+ if (is_orphan_skb(ptr)) {
-+ stats->packets++;
-+ stats->bytes += skb->len;
-+ } else {
-+ stats->napi_packets++;
-+ stats->napi_bytes += skb->len;
-+ }
- napi_consume_skb(skb, in_napi);
- } else {
- struct xdp_frame *frame = ptr_to_xdp(ptr);
-
-+ stats->packets++;
- stats->bytes += xdp_get_frame_len(frame);
- xdp_return_frame(frame);
- }
- }
-+ netdev_tx_completed_queue(txq, stats->napi_packets, stats->napi_bytes);
- }
-
- /* Converting between virtqueue no. and kernel tx/rx queue no.
-@@ -955,21 +979,22 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
- virtnet_rq_free_buf(vi, rq, buf);
- }
-
--static void free_old_xmit(struct send_queue *sq, bool in_napi)
-+static void free_old_xmit(struct send_queue *sq, struct netdev_queue *txq,
-+ bool in_napi)
- {
- struct virtnet_sq_free_stats stats = {0};
-
-- __free_old_xmit(sq, in_napi, &stats);
-+ __free_old_xmit(sq, txq, in_napi, &stats);
-
- /* Avoid overhead when no packets have been processed
- * happens when called speculatively from start_xmit.
- */
-- if (!stats.packets)
-+ if (!stats.packets && !stats.napi_packets)
- return;
-
- u64_stats_update_begin(&sq->stats.syncp);
-- u64_stats_add(&sq->stats.bytes, stats.bytes);
-- u64_stats_add(&sq->stats.packets, stats.packets);
-+ u64_stats_add(&sq->stats.bytes, stats.bytes + stats.napi_bytes);
-+ u64_stats_add(&sq->stats.packets, stats.packets + stats.napi_packets);
- u64_stats_update_end(&sq->stats.syncp);
- }
-
-@@ -1003,7 +1028,9 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
- * early means 16 slots are typically wasted.
- */
- if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
-- netif_stop_subqueue(dev, qnum);
-+ struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
-+
-+ netif_tx_stop_queue(txq);
- u64_stats_update_begin(&sq->stats.syncp);
- u64_stats_inc(&sq->stats.stop);
- u64_stats_update_end(&sq->stats.syncp);
-@@ -1012,7 +1039,7 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
- 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(sq, false);
-+ free_old_xmit(sq, txq, false);
- if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
- netif_start_subqueue(dev, qnum);
- u64_stats_update_begin(&sq->stats.syncp);
-@@ -1138,7 +1165,8 @@ static int virtnet_xdp_xmit(struct net_device *dev,
- }
-
- /* Free up any pending old buffers before queueing new ones. */
-- __free_old_xmit(sq, false, &stats);
-+ __free_old_xmit(sq, netdev_get_tx_queue(dev, sq - vi->sq),
-+ false, &stats);
-
- for (i = 0; i < n; i++) {
- struct xdp_frame *xdpf = frames[i];
-@@ -2331,7 +2359,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
-
- do {
- virtqueue_disable_cb(sq->vq);
-- free_old_xmit(sq, true);
-+ free_old_xmit(sq, txq, true);
- } while (unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
-
- if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) {
-@@ -2430,6 +2458,7 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
- goto err_xdp_reg_mem_model;
-
- virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
-+ netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index));
- virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
-
- return 0;
-@@ -2489,7 +2518,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
- txq = netdev_get_tx_queue(vi->dev, index);
- __netif_tx_lock(txq, raw_smp_processor_id());
- virtqueue_disable_cb(sq->vq);
-- free_old_xmit(sq, true);
-+ free_old_xmit(sq, txq, true);
-
- if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) {
- if (netif_tx_queue_stopped(txq)) {
-@@ -2523,7 +2552,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
- return 0;
- }
-
--static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
-+static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan)
- {
- struct virtio_net_hdr_mrg_rxbuf *hdr;
- const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
-@@ -2567,7 +2596,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
- return num_sg;
- num_sg++;
- }
-- return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC);
-+ return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg,
-+ skb_to_ptr(skb, orphan), GFP_ATOMIC);
- }
-
- static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
-@@ -2577,24 +2607,25 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
- struct send_queue *sq = &vi->sq[qnum];
- int err;
- struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
-- bool kick = !netdev_xmit_more();
-+ bool xmit_more = netdev_xmit_more();
- bool use_napi = sq->napi.weight;
-+ bool kick;
-
- /* Free up any pending old buffers before queueing new ones. */
- do {
- if (use_napi)
- virtqueue_disable_cb(sq->vq);
-
-- free_old_xmit(sq, false);
-+ free_old_xmit(sq, txq, false);
-
-- } while (use_napi && kick &&
-+ } while (use_napi && !xmit_more &&
- unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
-
- /* timestamp packet in software */
- skb_tx_timestamp(skb);
-
- /* Try to transmit */
-- err = xmit_skb(sq, skb);
-+ err = xmit_skb(sq, skb, !use_napi);
-
- /* This should not happen! */
- if (unlikely(err)) {
-@@ -2616,7 +2647,9 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
-
- check_sq_full_and_disable(vi, dev, sq);
-
-- if (kick || netif_xmit_stopped(txq)) {
-+ kick = use_napi ? __netdev_tx_sent_queue(txq, skb->len, xmit_more) :
-+ !xmit_more || netif_xmit_stopped(txq);
-+ if (kick) {
- if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
- u64_stats_update_begin(&sq->stats.syncp);
- u64_stats_inc(&sq->stats.kicks);
---
-2.43.0
-
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
- drivers/net/virtio_net.c | 8 ++++----
+ drivers/net/virtio_net.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
-diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
-index b1f8b720733e5..cd254a1fd88ec 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
-@@ -2341,7 +2341,7 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
+@@ -2313,7 +2313,7 @@ static int virtnet_receive(struct receiv
return packets;
}
{
struct virtnet_info *vi = rq->vq->vdev->priv;
unsigned int index = vq2rxq(rq->vq);
-@@ -2359,7 +2359,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
+@@ -2331,7 +2331,7 @@ static void virtnet_poll_cleantx(struct
do {
virtqueue_disable_cb(sq->vq);
-- free_old_xmit(sq, txq, true);
-+ free_old_xmit(sq, txq, !!budget);
+- free_old_xmit(sq, true);
+++ free_old_xmit(sq, !!budget);
} while (unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) {
-@@ -2403,7 +2403,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
+@@ -2375,7 +2375,7 @@ static int virtnet_poll(struct napi_stru
unsigned int xdp_xmit = 0;
bool napi_complete;
received = virtnet_receive(rq, budget, &xdp_xmit);
rq->packets_in_napi += received;
-@@ -2518,7 +2518,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
+@@ -2489,7 +2489,7 @@ static int virtnet_poll_tx(struct napi_s
txq = netdev_get_tx_queue(vi->dev, index);
__netif_tx_lock(txq, raw_smp_processor_id());
virtqueue_disable_cb(sq->vq);
-- free_old_xmit(sq, txq, true);
-+ free_old_xmit(sq, txq, !!budget);
+- free_old_xmit(sq, true);
++ free_old_xmit(sq, !!budget);
if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) {
if (netif_tx_queue_stopped(txq)) {
---
-2.43.0
-
projects / thirdparty / kernel / stable-queue.git / commitdiff
