Merge branch 'virtio_rx_merging'

Michael Dalton says:

====================
virtio-net: mergeable rx buffer size auto-tuning

The virtio-net device currently uses aligned MTU-sized mergeable receive
packet buffers. Network throughput for workloads with large average
packet size can be improved by posting larger receive packet buffers.
However, due to SKB truesize effects, posting large (e.g, PAGE_SIZE)
buffers reduces the throughput of workloads that do not benefit from GRO
and have no large inbound packets.

This patchset introduces virtio-net mergeable buffer size auto-tuning,
with buffer sizes ranging from aligned MTU-size to PAGE_SIZE. Packet
buffer size is chosen based on a per-receive queue EWMA of incoming
packet size.

To unify mergeable receive buffer memory allocation and improve
SKB frag coalescing, all mergeable buffer memory allocation is
migrated to per-receive queue page frag allocators.

The per-receive queue mergeable packet buffer size is exported via
sysfs, and the network device sysfs layer has been extended to add
support for device-specific per-receive queue sysfs attribute groups.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 143 insertions, 54 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 9bd70aa87bf7..d75f8edf4fb3 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -26,6 +26,7 @@
 #include <linux/if_vlan.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/average.h>
 
 static int napi_weight = NAPI_POLL_WEIGHT;
 module_param(napi_weight, int, 0444);
@@ -36,11 +37,18 @@ module_param(gso, bool, 0444);
 
 /* FIXME: MTU in config. */
 #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
-#define MERGE_BUFFER_LEN (ALIGN(GOOD_PACKET_LEN + \
-                                sizeof(struct virtio_net_hdr_mrg_rxbuf), \
-                                L1_CACHE_BYTES))
 #define GOOD_COPY_LEN	128
 
+/* Weight used for the 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 at once, the weight is chosen so that the EWMA will be
+ * insensitive to short-term, transient changes in packet size.
+ */
+#define RECEIVE_AVG_WEIGHT 64
+
+/* Minimum alignment for mergeable packet buffers. */
+#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, 256)
+
 #define VIRTNET_DRIVER_VERSION "1.0.0"
 
 struct virtnet_stats {
@@ -75,6 +83,12 @@ struct receive_queue {
 	/* Chain pages by the private ptr. */
 	struct page *pages;
 
+	/* Average packet length for mergeable receive buffers. */
+	struct ewma mrg_avg_pkt_len;
+
+	/* Page frag for packet buffer allocation. */
+	struct page_frag alloc_frag;
+
 	/* RX: fragments + linear part + virtio header */
 	struct scatterlist sg[MAX_SKB_FRAGS + 2];
 
@@ -123,11 +137,6 @@ struct virtnet_info {
 	/* Lock for config space updates */
 	struct mutex config_lock;
 
-	/* Page_frag for GFP_KERNEL packet buffer allocation when we run
-	 * low on memory.
-	 */
-	struct page_frag alloc_frag;
-
 	/* Does the affinity hint is set for virtqueues? */
 	bool affinity_hint_set;
 
@@ -218,6 +227,24 @@ static void skb_xmit_done(struct virtqueue *vq)
 	netif_wake_subqueue(vi->dev, vq2txq(vq));
 }
 
+static unsigned int mergeable_ctx_to_buf_truesize(unsigned long mrg_ctx)
+{
+	unsigned int truesize = mrg_ctx & (MERGEABLE_BUFFER_ALIGN - 1);
+	return (truesize + 1) * MERGEABLE_BUFFER_ALIGN;
+}
+
+static void *mergeable_ctx_to_buf_address(unsigned long mrg_ctx)
+{
+	return (void *)(mrg_ctx & -MERGEABLE_BUFFER_ALIGN);
+
+}
+
+static unsigned long mergeable_buf_to_ctx(void *buf, unsigned int truesize)
+{
+	unsigned int size = truesize / MERGEABLE_BUFFER_ALIGN;
+	return (unsigned long)buf | (size - 1);
+}
+
 /* Called from bottom half context */
 static struct sk_buff *page_to_skb(struct receive_queue *rq,
 				   struct page *page, unsigned int offset,
@@ -326,36 +353,33 @@ err:
 
 static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 struct receive_queue *rq,
-					 void *buf,
+					 unsigned long ctx,
 					 unsigned int len)
 {
+	void *buf = mergeable_ctx_to_buf_address(ctx);
 	struct skb_vnet_hdr *hdr = buf;
 	int num_buf = hdr->mhdr.num_buffers;
 	struct page *page = virt_to_head_page(buf);
 	int offset = buf - page_address(page);
-	struct sk_buff *head_skb = page_to_skb(rq, page, offset, len,
-					       MERGE_BUFFER_LEN);
+	unsigned int truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
+
+	struct sk_buff *head_skb = page_to_skb(rq, page, offset, len, truesize);
 	struct sk_buff *curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
 		goto err_skb;
-
 	while (--num_buf) {
 		int num_skb_frags;
 
-		buf = virtqueue_get_buf(rq->vq, &len);
-		if (unlikely(!buf)) {
+		ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
+		if (unlikely(!ctx)) {
 			pr_debug("%s: rx error: %d buffers out of %d missing\n",
 				 dev->name, num_buf, hdr->mhdr.num_buffers);
 			dev->stats.rx_length_errors++;
 			goto err_buf;
 		}
-		if (unlikely(len > MERGE_BUFFER_LEN)) {
-			pr_debug("%s: rx error: merge buffer too long\n",
-				 dev->name);
-			len = MERGE_BUFFER_LEN;
-		}
 
+		buf = mergeable_ctx_to_buf_address(ctx);
 		page = virt_to_head_page(buf);
 
 		num_skb_frags = skb_shinfo(curr_skb)->nr_frags;
@@ -372,35 +396,37 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			head_skb->truesize += nskb->truesize;
 			num_skb_frags = 0;
 		}
+		truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
 		if (curr_skb != head_skb) {
 			head_skb->data_len += len;
 			head_skb->len += len;
-			head_skb->truesize += MERGE_BUFFER_LEN;
+			head_skb->truesize += truesize;
 		}
 		offset = buf - page_address(page);
 		if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) {
 			put_page(page);
 			skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1,
-					     len, MERGE_BUFFER_LEN);
+					     len, truesize);
 		} else {
 			skb_add_rx_frag(curr_skb, num_skb_frags, page,
-					offset, len, MERGE_BUFFER_LEN);
+					offset, len, truesize);
 		}
 	}
 
+	ewma_add(&rq->mrg_avg_pkt_len, head_skb->len);
 	return head_skb;
 
 err_skb:
 	put_page(page);
 	while (--num_buf) {
-		buf = virtqueue_get_buf(rq->vq, &len);
-		if (unlikely(!buf)) {
+		ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
+		if (unlikely(!ctx)) {
 			pr_debug("%s: rx error: %d buffers missing\n",
 				 dev->name, num_buf);
 			dev->stats.rx_length_errors++;
 			break;
 		}
-		page = virt_to_head_page(buf);
+		page = virt_to_head_page(mergeable_ctx_to_buf_address(ctx));
 		put_page(page);
 	}
 err_buf:
@@ -420,17 +446,20 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
 	if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
 		dev->stats.rx_length_errors++;
-		if (vi->mergeable_rx_bufs)
-			put_page(virt_to_head_page(buf));
-		else if (vi->big_packets)
+		if (vi->mergeable_rx_bufs) {
+			unsigned long ctx = (unsigned long)buf;
+			void *base = mergeable_ctx_to_buf_address(ctx);
+			put_page(virt_to_head_page(base));
+		} else if (vi->big_packets) {
 			give_pages(rq, buf);
-		else
+		} else {
 			dev_kfree_skb(buf);
+		}
 		return;
 	}
 
 	if (vi->mergeable_rx_bufs)
-		skb = receive_mergeable(dev, rq, buf, len);
+		skb = receive_mergeable(dev, rq, (unsigned long)buf, len);
 	else if (vi->big_packets)
 		skb = receive_big(dev, rq, buf, len);
 	else
@@ -571,28 +600,45 @@ static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp)
 	return err;
 }
 
+static unsigned int get_mergeable_buf_len(struct ewma *avg_pkt_len)
+{
+	const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+	unsigned int len;
+
+	len = hdr_len + clamp_t(unsigned int, ewma_read(avg_pkt_len),
+			GOOD_PACKET_LEN, PAGE_SIZE - hdr_len);
+	return ALIGN(len, MERGEABLE_BUFFER_ALIGN);
+}
+
 static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
 {
-	struct virtnet_info *vi = rq->vq->vdev->priv;
-	char *buf = NULL;
+	struct page_frag *alloc_frag = &rq->alloc_frag;
+	char *buf;
+	unsigned long ctx;
 	int err;
+	unsigned int len, hole;
 
-	if (gfp & __GFP_WAIT) {
-		if (skb_page_frag_refill(MERGE_BUFFER_LEN, &vi->alloc_frag,
-					 gfp)) {
-			buf = (char *)page_address(vi->alloc_frag.page) +
-			      vi->alloc_frag.offset;
-			get_page(vi->alloc_frag.page);
-			vi->alloc_frag.offset += MERGE_BUFFER_LEN;
-		}
-	} else {
-		buf = netdev_alloc_frag(MERGE_BUFFER_LEN);
-	}
-	if (!buf)
+	len = get_mergeable_buf_len(&rq->mrg_avg_pkt_len);
+	if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
 		return -ENOMEM;
 
-	sg_init_one(rq->sg, buf, MERGE_BUFFER_LEN);
-	err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, buf, gfp);
+	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
+	ctx = mergeable_buf_to_ctx(buf, len);
+	get_page(alloc_frag->page);
+	alloc_frag->offset += len;
+	hole = alloc_frag->size - alloc_frag->offset;
+	if (hole < len) {
+		/* To avoid internal fragmentation, if there is very likely not
+		 * enough space for another buffer, add the remaining space to
+		 * the current buffer. This extra space is not included in
+		 * the truesize stored in ctx.
+		 */
+		len += hole;
+		alloc_frag->offset += hole;
+	}
+
+	sg_init_one(rq->sg, buf, len);
+	err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, (void *)ctx, gfp);
 	if (err < 0)
 		put_page(virt_to_head_page(buf));
 
@@ -612,6 +658,7 @@ static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
 	int err;
 	bool oom;
 
+	gfp |= __GFP_COLD;
 	do {
 		if (vi->mergeable_rx_bufs)
 			err = add_recvbuf_mergeable(rq, gfp);
@@ -1368,6 +1415,14 @@ static void free_receive_bufs(struct virtnet_info *vi)
 	}
 }
 
+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)
+			put_page(vi->rq[i].alloc_frag.page);
+}
+
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
@@ -1383,12 +1438,15 @@ static void free_unused_bufs(struct virtnet_info *vi)
 		struct virtqueue *vq = vi->rq[i].vq;
 
 		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
-			if (vi->mergeable_rx_bufs)
-				put_page(virt_to_head_page(buf));
-			else if (vi->big_packets)
+			if (vi->mergeable_rx_bufs) {
+				unsigned long ctx = (unsigned long)buf;
+				void *base = mergeable_ctx_to_buf_address(ctx);
+				put_page(virt_to_head_page(base));
+			} else if (vi->big_packets) {
 				give_pages(&vi->rq[i], buf);
-			else
+			} else {
 				dev_kfree_skb(buf);
+			}
 		}
 	}
 }
@@ -1496,6 +1554,7 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 			       napi_weight);
 
 		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
+		ewma_init(&vi->rq[i].mrg_avg_pkt_len, 1, RECEIVE_AVG_WEIGHT);
 		sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
 	}
 
@@ -1532,6 +1591,33 @@ err:
 	return ret;
 }
 
+#ifdef CONFIG_SYSFS
+static ssize_t mergeable_rx_buffer_size_show(struct netdev_rx_queue *queue,
+		struct rx_queue_attribute *attribute, char *buf)
+{
+	struct virtnet_info *vi = netdev_priv(queue->dev);
+	unsigned int queue_index = get_netdev_rx_queue_index(queue);
+	struct ewma *avg;
+
+	BUG_ON(queue_index >= vi->max_queue_pairs);
+	avg = &vi->rq[queue_index].mrg_avg_pkt_len;
+	return sprintf(buf, "%u\n", get_mergeable_buf_len(avg));
+}
+
+static struct rx_queue_attribute mergeable_rx_buffer_size_attribute =
+	__ATTR_RO(mergeable_rx_buffer_size);
+
+static struct attribute *virtio_net_mrg_rx_attrs[] = {
+	&mergeable_rx_buffer_size_attribute.attr,
+	NULL
+};
+
+static const struct attribute_group virtio_net_mrg_rx_group = {
+	.name = "virtio_net",
+	.attrs = virtio_net_mrg_rx_attrs
+};
+#endif
+
 static int virtnet_probe(struct virtio_device *vdev)
 {
 	int i, err;
@@ -1646,6 +1732,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (err)
 		goto free_stats;
 
+#ifdef CONFIG_SYSFS
+	if (vi->mergeable_rx_bufs)
+		dev->sysfs_rx_queue_group = &virtio_net_mrg_rx_group;
+#endif
 	netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs);
 	netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs);
 
@@ -1695,9 +1785,8 @@ free_recv_bufs:
 	unregister_netdev(dev);
 free_vqs:
 	cancel_delayed_work_sync(&vi->refill);
+	free_receive_page_frags(vi);
 	virtnet_del_vqs(vi);
-	if (vi->alloc_frag.page)
-		put_page(vi->alloc_frag.page);
 free_stats:
 	free_percpu(vi->stats);
 free:
@@ -1714,6 +1803,8 @@ static void remove_vq_common(struct virtnet_info *vi)
 
 	free_receive_bufs(vi);
 
+	free_receive_page_frags(vi);
+
 	virtnet_del_vqs(vi);
 }
 
@@ -1731,8 +1822,6 @@ static void virtnet_remove(struct virtio_device *vdev)
 	unregister_netdev(vi->dev);
 
 	remove_vq_common(vi);
-	if (vi->alloc_frag.page)
-		put_page(vi->alloc_frag.page);
 
 	flush_work(&vi->config_work);