Linux Virtualization - Jan 2014 - [PATCH net-next v5 0/6] 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.

Michael Dalton (6):
  net: allow > 0 order atomic page alloc in skb_page_frag_refill
  virtio-net: use per-receive queue page frag alloc for mergeable bufs
  virtio-net: auto-tune mergeable rx buffer size for improved
    performance
  net-sysfs: add support for device-specific rx queue sysfs attributes
  lib: Ensure EWMA does not store wrong intermediate values
  virtio-net: initial rx sysfs support, export mergeable rx buffer size

 drivers/net/virtio_net.c  | 196 +++++++++++++++++++++++++++++++++-------------
 include/linux/netdevice.h |  35 ++++++++-
 lib/average.c             |   6 +-
 net/core/dev.c            |  12 +--
 net/core/net-sysfs.c      |  50 +++++++-----
 net/core/sock.c           |   4 +-
 6 files changed, 213 insertions(+), 90 deletions(-)

-- 
1.8.5.2

skb_page_frag_refill currently permits only order-0 page allocs
unless GFP_WAIT is used. Change skb_page_frag_refill to attempt
higher-order page allocations whether or not GFP_WAIT is used. If
memory cannot be allocated, the allocator will fall back to
successively smaller page allocs (down to order-0 page allocs).

This change brings skb_page_frag_refill in line with the existing
page allocation strategy employed by netdev_alloc_frag, which attempts
higher-order page allocations whether or not GFP_WAIT is set, falling
back to successively lower-order page allocations on failure. Part
of migration of virtio-net to per-receive queue page frag allocators.

Acked-by: Michael S. Tsirkin <mst at redhat.com>
Acked-by: Eric Dumazet <edumazet at google.com>
Signed-off-by: Michael Dalton <mwdalton at google.com>
---
 net/core/sock.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 85ad6f0..b3f7ee3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1836,9 +1836,7 @@ bool skb_page_frag_refill(unsigned int sz, struct
page_frag *pfrag, gfp_t prio)
 		put_page(pfrag->page);
 	}
 
-	/* We restrict high order allocations to users that can afford to wait */
-	order = (prio & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0;
-
+	order = SKB_FRAG_PAGE_ORDER;
 	do {
 		gfp_t gfp = prio;
 
-- 
1.8.5.2

The virtio-net driver currently uses netdev_alloc_frag() for GFP_ATOMIC
mergeable rx buffer allocations. This commit migrates virtio-net to use
per-receive queue page frags for GFP_ATOMIC allocation. This change unifies
mergeable rx buffer memory allocation, which now will use skb_refill_frag()
for both atomic and GFP-WAIT buffer allocations.

To address fragmentation concerns, if after buffer allocation there
is too little space left in the page frag to allocate a subsequent
buffer, the remaining space is added to the current allocated buffer
so that the remaining space can be used to store packet data.

Acked-by: Michael S. Tsirkin <mst at redhat.com>
Signed-off-by: Michael Dalton <mwdalton at google.com>
---
v1->v2: Use GFP_COLD for RX buffer allocations (as in netdev_alloc_frag()).
        Remove per-netdev GFP_KERNEL page_frag allocator.

 drivers/net/virtio_net.c | 69 ++++++++++++++++++++++++------------------------
 1 file changed, 35 insertions(+), 34 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7b17240..36cbf06 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -78,6 +78,9 @@ struct receive_queue {
 	/* Chain pages by the private ptr. */
 	struct page *pages;
 
+	/* Page frag for packet buffer allocation. */
+	struct page_frag alloc_frag;
+
 	/* RX: fragments + linear part + virtio header */
 	struct scatterlist sg[MAX_SKB_FRAGS + 2];
 
@@ -126,11 +129,6 @@ 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;
 
@@ -336,8 +334,8 @@ static struct sk_buff *receive_mergeable(struct net_device
*dev,
 	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_t(unsigned int, len, MERGE_BUFFER_LEN);
+	struct sk_buff *head_skb = page_to_skb(rq, page, offset, len, truesize);
 	struct sk_buff *curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
@@ -353,11 +351,6 @@ static struct sk_buff *receive_mergeable(struct net_device
*dev,
 			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;
-		}
 
 		page = virt_to_head_page(buf);
 		--rq->num;
@@ -376,19 +369,20 @@ static struct sk_buff *receive_mergeable(struct net_device
*dev,
 			head_skb->truesize += nskb->truesize;
 			num_skb_frags = 0;
 		}
+		truesize = max_t(unsigned int, len, MERGE_BUFFER_LEN);
 		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);
 		}
 	}
 
@@ -578,25 +572,24 @@ static int add_recvbuf_big(struct receive_queue *rq, gfp_t
gfp)
 
 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;
 	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)
+	if (unlikely(!skb_page_frag_refill(MERGE_BUFFER_LEN, alloc_frag, gfp)))
 		return -ENOMEM;
+	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
+	get_page(alloc_frag->page);
+	len = MERGE_BUFFER_LEN;
+	alloc_frag->offset += len;
+	hole = alloc_frag->size - alloc_frag->offset;
+	if (hole < MERGE_BUFFER_LEN) {
+		len += hole;
+		alloc_frag->offset += hole;
+	}
 
-	sg_init_one(rq->sg, buf, MERGE_BUFFER_LEN);
+	sg_init_one(rq->sg, buf, len);
 	err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, buf, gfp);
 	if (err < 0)
 		put_page(virt_to_head_page(buf));
@@ -617,6 +610,7 @@ 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);
@@ -1377,6 +1371,14 @@ 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;
@@ -1705,9 +1707,8 @@ 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:
@@ -1724,6 +1725,8 @@ static void remove_vq_common(struct virtnet_info *vi)
 
 	free_receive_bufs(vi);
 
+	free_receive_page_frags(vi);
+
 	virtnet_del_vqs(vi);
 }
 
@@ -1741,8 +1744,6 @@ 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);
 
-- 
1.8.5.2

Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag
allocators") changed the mergeable receive buffer size from PAGE_SIZE to
MTU-size, introducing a single-stream regression for benchmarks with large
average packet size. There is no single optimal buffer size for all
workloads.  For workloads with packet size <= MTU bytes, MTU + virtio-net
header-sized buffers are preferred as larger buffers reduce the TCP window
due to SKB truesize. However, single-stream workloads with large average
packet sizes have higher throughput if larger (e.g., PAGE_SIZE) buffers
are used.

This commit auto-tunes the mergeable receiver buffer packet size by
choosing the packet buffer size based on an EWMA of the recent packet
sizes for the receive queue. Packet buffer sizes range from MTU_SIZE +
virtio-net header len to PAGE_SIZE. This improves throughput for
large packet workloads, as any workload with average packet size >PAGE_SIZE
will use PAGE_SIZE buffers.

These optimizations interact positively with recent commit
ba275241030c ("virtio-net: coalesce rx frags when possible during
rx"),
which coalesces adjacent RX SKB fragments in virtio_net. The coalescing
optimizations benefit buffers of any size.

Benchmarks taken from an average of 5 netperf 30-second TCP_STREAM runs
between two QEMU VMs on a single physical machine. Each VM has two VCPUs
with all offloads & vhost enabled. All VMs and vhost threads run in a
single 4 CPU cgroup cpuset, using cgroups to ensure that other processes
in the system will not be scheduled on the benchmark CPUs. Trunk includes
SKB rx frag coalescing.

net-next w/ virtio_net before 2613af0ed18a (PAGE_SIZE bufs): 14642.85Gb/s
net-next (MTU-size bufs):  13170.01Gb/s
net-next + auto-tune: 14555.94Gb/s

Jason Wang also reported a throughput increase on mlx4 from 22Gb/s
using MTU-sized buffers to about 26Gb/s using auto-tuning.

Acked-by: Michael S. Tsirkin <mst at redhat.com>
Signed-off-by: Michael Dalton <mwdalton at google.com>
---
v2->v3: Remove per-receive queue metadata ring. Encode packet buffer
        base address and truesize into an unsigned long by requiring a
        minimum packet size alignment of 256. Permit attempts to fill
        an already-full RX ring (reverting the change in v2).
v1->v2: Add per-receive queue metadata ring to track precise truesize for
        mergeable receive buffers. Remove all truesize approximation. Never
        try to fill a full RX ring (required for metadata ring in v2).

 drivers/net/virtio_net.c | 99 ++++++++++++++++++++++++++++++++++++------------
 1 file changed, 74 insertions(+), 25 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 36cbf06..3e82311 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 {
@@ -78,6 +86,9 @@ 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;
 
@@ -219,6 +230,23 @@ 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 * 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)
+{
+	return (unsigned long)buf | (truesize / MERGEABLE_BUFFER_ALIGN);
+}
+
 /* Called from bottom half context */
 static struct sk_buff *page_to_skb(struct receive_queue *rq,
 				   struct page *page, unsigned int offset,
@@ -327,31 +355,33 @@ 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);
-	unsigned int truesize = max_t(unsigned int, 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;
 		}
 
+		buf = mergeable_ctx_to_buf_address(ctx);
 		page = virt_to_head_page(buf);
 		--rq->num;
 
@@ -369,7 +399,7 @@ static struct sk_buff *receive_mergeable(struct net_device
*dev,
 			head_skb->truesize += nskb->truesize;
 			num_skb_frags = 0;
 		}
-		truesize = max_t(unsigned int, len, MERGE_BUFFER_LEN);
+		truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
 		if (curr_skb != head_skb) {
 			head_skb->data_len += len;
 			head_skb->len += len;
@@ -386,19 +416,20 @@ static struct sk_buff *receive_mergeable(struct net_device
*dev,
 		}
 	}
 
+	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);
 		--rq->num;
 	}
@@ -419,17 +450,20 @@ 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
@@ -572,25 +606,36 @@ static int add_recvbuf_big(struct receive_queue *rq, gfp_t
gfp)
 
 static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
 {
+	const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
 	struct page_frag *alloc_frag = &rq->alloc_frag;
 	char *buf;
+	unsigned long ctx;
 	int err;
 	unsigned int len, hole;
 
-	if (unlikely(!skb_page_frag_refill(MERGE_BUFFER_LEN, alloc_frag, gfp)))
+	len = hdr_len + clamp_t(unsigned int, ewma_read(&rq->mrg_avg_pkt_len),
+				GOOD_PACKET_LEN, PAGE_SIZE - hdr_len);
+	len = ALIGN(len, MERGEABLE_BUFFER_ALIGN);
+	if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
 		return -ENOMEM;
+
 	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
+	ctx = mergeable_buf_to_ctx(buf, len);
 	get_page(alloc_frag->page);
-	len = MERGE_BUFFER_LEN;
 	alloc_frag->offset += len;
 	hole = alloc_frag->size - alloc_frag->offset;
-	if (hole < MERGE_BUFFER_LEN) {
+	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, buf, gfp);
+	err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, (void *)ctx, gfp);
 	if (err < 0)
 		put_page(virt_to_head_page(buf));
 
@@ -1394,12 +1439,15 @@ 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);
+			}
 			--vi->rq[i].num;
 		}
 		BUG_ON(vi->rq[i].num != 0);
@@ -1509,6 +1557,7 @@ 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));
 	}
 
-- 
1.8.5.2

Extend existing support for netdevice receive queue sysfs attributes to
permit a device-specific attribute group. Initial use case for this
support will be to allow the virtio-net device to export per-receive
queue mergeable receive buffer size.

Signed-off-by: Michael Dalton <mwdalton at google.com>
---
v4->v5: Handle sysfs_create_group failure. Call sysfs_remove_group when
        removing a RX queue kobj if a device-specific group exists.
v3->v4: Simplify by removing loop in get_netdev_rx_queue_index.

 include/linux/netdevice.h | 35 +++++++++++++++++++++++++++++----
 net/core/dev.c            | 12 ++++++------
 net/core/net-sysfs.c      | 50 +++++++++++++++++++++++++++--------------------
 3 files changed, 66 insertions(+), 31 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5c88ab1..38929bc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -668,15 +668,28 @@ extern struct rps_sock_flow_table __rcu
*rps_sock_flow_table;
 bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
 			 u16 filter_id);
 #endif
+#endif /* CONFIG_RPS */
 
 /* This structure contains an instance of an RX queue. */
 struct netdev_rx_queue {
+#ifdef CONFIG_RPS
 	struct rps_map __rcu		*rps_map;
 	struct rps_dev_flow_table __rcu	*rps_flow_table;
+#endif
 	struct kobject			kobj;
 	struct net_device		*dev;
 } ____cacheline_aligned_in_smp;
-#endif /* CONFIG_RPS */
+
+/*
+ * RX queue sysfs structures and functions.
+ */
+struct rx_queue_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct netdev_rx_queue *queue,
+	    struct rx_queue_attribute *attr, char *buf);
+	ssize_t (*store)(struct netdev_rx_queue *queue,
+	    struct rx_queue_attribute *attr, const char *buf, size_t len);
+};
 
 #ifdef CONFIG_XPS
 /*
@@ -1313,7 +1326,7 @@ struct net_device {
 						   unicast) */
 
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	struct netdev_rx_queue	*_rx;
 
 	/* Number of RX queues allocated at register_netdev() time */
@@ -1424,6 +1437,8 @@ struct net_device {
 	struct device		dev;
 	/* space for optional device, statistics, and wireless sysfs groups */
 	const struct attribute_group *sysfs_groups[4];
+	/* space for optional per-rx queue attributes */
+	const struct attribute_group *sysfs_rx_queue_group;
 
 	/* rtnetlink link ops */
 	const struct rtnl_link_ops *rtnl_link_ops;
@@ -2374,7 +2389,7 @@ static inline bool netif_is_multiqueue(const struct
net_device *dev)
 
 int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq);
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq);
 #else
 static inline int netif_set_real_num_rx_queues(struct net_device *dev,
@@ -2393,7 +2408,7 @@ static inline int netif_copy_real_num_queues(struct
net_device *to_dev,
 					   from_dev->real_num_tx_queues);
 	if (err)
 		return err;
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	return netif_set_real_num_rx_queues(to_dev,
 					    from_dev->real_num_rx_queues);
 #else
@@ -2401,6 +2416,18 @@ static inline int netif_copy_real_num_queues(struct
net_device *to_dev,
 #endif
 }
 
+#ifdef CONFIG_SYSFS
+static inline unsigned int get_netdev_rx_queue_index(
+		struct netdev_rx_queue *queue)
+{
+	struct net_device *dev = queue->dev;
+	int index = queue - dev->_rx;
+
+	BUG_ON(index >= dev->num_rx_queues);
+	return index;
+}
+#endif
+
 #define DEFAULT_MAX_NUM_RSS_QUEUES	(8)
 int netif_get_num_default_rss_queues(void);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 20c834e..4be7931 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2080,7 +2080,7 @@ int netif_set_real_num_tx_queues(struct net_device *dev,
unsigned int txq)
 }
 EXPORT_SYMBOL(netif_set_real_num_tx_queues);
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 /**
  *	netif_set_real_num_rx_queues - set actual number of RX queues used
  *	@dev: Network device
@@ -5727,7 +5727,7 @@ void netif_stacked_transfer_operstate(const struct
net_device *rootdev,
 }
 EXPORT_SYMBOL(netif_stacked_transfer_operstate);
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 static int netif_alloc_rx_queues(struct net_device *dev)
 {
 	unsigned int i, count = dev->num_rx_queues;
@@ -6272,7 +6272,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const
char *name,
 		return NULL;
 	}
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	if (rxqs < 1) {
 		pr_err("alloc_netdev: Unable to allocate device with zero RX
queues\n");
 		return NULL;
@@ -6328,7 +6328,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const
char *name,
 	if (netif_alloc_netdev_queues(dev))
 		goto free_all;
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	dev->num_rx_queues = rxqs;
 	dev->real_num_rx_queues = rxqs;
 	if (netif_alloc_rx_queues(dev))
@@ -6348,7 +6348,7 @@ free_all:
 free_pcpu:
 	free_percpu(dev->pcpu_refcnt);
 	netif_free_tx_queues(dev);
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	kfree(dev->_rx);
 #endif
 
@@ -6373,7 +6373,7 @@ void free_netdev(struct net_device *dev)
 	release_net(dev_net(dev));
 
 	netif_free_tx_queues(dev);
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	kfree(dev->_rx);
 #endif
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 49843bf..7eeadee 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -498,17 +498,7 @@ static struct attribute_group wireless_group = {
 #define net_class_groups	NULL
 #endif /* CONFIG_SYSFS */
 
-#ifdef CONFIG_RPS
-/*
- * RX queue sysfs structures and functions.
- */
-struct rx_queue_attribute {
-	struct attribute attr;
-	ssize_t (*show)(struct netdev_rx_queue *queue,
-	    struct rx_queue_attribute *attr, char *buf);
-	ssize_t (*store)(struct netdev_rx_queue *queue,
-	    struct rx_queue_attribute *attr, const char *buf, size_t len);
-};
+#ifdef CONFIG_SYSFS
 #define to_rx_queue_attr(_attr) container_of(_attr,		\
     struct rx_queue_attribute, attr)
 
@@ -543,6 +533,7 @@ static const struct sysfs_ops rx_queue_sysfs_ops = {
 	.store = rx_queue_attr_store,
 };
 
+#ifdef CONFIG_RPS
 static ssize_t show_rps_map(struct netdev_rx_queue *queue,
 			    struct rx_queue_attribute *attribute, char *buf)
 {
@@ -718,16 +709,20 @@ static struct rx_queue_attribute rps_cpus_attribute 
static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute  
__ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR,
 	    show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt);
+#endif /* CONFIG_RPS */
 
 static struct attribute *rx_queue_default_attrs[] = {
+#ifdef CONFIG_RPS
 	&rps_cpus_attribute.attr,
 	&rps_dev_flow_table_cnt_attribute.attr,
+#endif
 	NULL
 };
 
 static void rx_queue_release(struct kobject *kobj)
 {
 	struct netdev_rx_queue *queue = to_rx_queue(kobj);
+#ifdef CONFIG_RPS
 	struct rps_map *map;
 	struct rps_dev_flow_table *flow_table;
 
@@ -743,6 +738,7 @@ static void rx_queue_release(struct kobject *kobj)
 		RCU_INIT_POINTER(queue->rps_flow_table, NULL);
 		call_rcu(&flow_table->rcu, rps_dev_flow_table_release);
 	}
+#endif
 
 	memset(kobj, 0, sizeof(*kobj));
 	dev_put(queue->dev);
@@ -763,25 +759,36 @@ static int rx_queue_add_kobject(struct net_device *net,
int index)
 	kobj->kset = net->queues_kset;
 	error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL,
 	    "rx-%u", index);
-	if (error) {
-		kobject_put(kobj);
-		return error;
+	if (error)
+		goto exit;
+
+	if (net->sysfs_rx_queue_group) {
+		error = sysfs_create_group(kobj, net->sysfs_rx_queue_group);
+		if (error)
+			goto exit;
 	}
 
 	kobject_uevent(kobj, KOBJ_ADD);
 	dev_hold(queue->dev);
 
 	return error;
+exit:
+	kobject_put(kobj);
+	return error;
 }
-#endif /* CONFIG_RPS */
+#endif /* CONFIG_SYFS */
 
 int
 net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num)
 {
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	int i;
 	int error = 0;
 
+#ifndef CONFIG_RPS
+	if (!net->sysfs_rx_queue_group)
+		return 0;
+#endif
 	for (i = old_num; i < new_num; i++) {
 		error = rx_queue_add_kobject(net, i);
 		if (error) {
@@ -790,8 +797,12 @@ net_rx_queue_update_kobjects(struct net_device *net, int
old_num, int new_num)
 		}
 	}
 
-	while (--i >= new_num)
+	while (--i >= new_num) {
+		if (net->sysfs_rx_queue_group)
+			sysfs_remove_group(&net->_rx[i].kobj,
+					   net->sysfs_rx_queue_group);
 		kobject_put(&net->_rx[i].kobj);
+	}
 
 	return error;
 #else
@@ -1155,9 +1166,6 @@ static int register_queue_kobjects(struct net_device *net)
 	    NULL, &net->dev.kobj);
 	if (!net->queues_kset)
 		return -ENOMEM;
-#endif
-
-#ifdef CONFIG_RPS
 	real_rx = net->real_num_rx_queues;
 #endif
 	real_tx = net->real_num_tx_queues;
@@ -1184,7 +1192,7 @@ static void remove_queue_kobjects(struct net_device *net)
 {
 	int real_rx = 0, real_tx = 0;
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	real_rx = net->real_num_rx_queues;
 #endif
 	real_tx = net->real_num_tx_queues;
-- 
1.8.5.2

To ensure ewma_read() without a lock returns a valid but possibly
out of date average, modify ewma_add() by using ACCESS_ONCE to prevent
intermediate wrong values from being written to avg->internal.

Suggested-by: Eric Dumazet <eric.dumazet at gmail.com>
Acked-by: Michael S. Tsirkin <mst at redhat.com>
Acked-by: Eric Dumazet <edumazet at google.com>
Signed-off-by: Michael Dalton <mwdalton at google.com>
---
 lib/average.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/lib/average.c b/lib/average.c
index 99a67e6..114d1be 100644
--- a/lib/average.c
+++ b/lib/average.c
@@ -53,8 +53,10 @@ EXPORT_SYMBOL(ewma_init);
  */
 struct ewma *ewma_add(struct ewma *avg, unsigned long val)
 {
-	avg->internal = avg->internal  ?
-		(((avg->internal << avg->weight) - avg->internal) +
+	unsigned long internal = ACCESS_ONCE(avg->internal);
+
+	ACCESS_ONCE(avg->internal) = internal ?
+		(((internal << avg->weight) - internal) +
 			(val << avg->factor)) >> avg->weight :
 		(val << avg->factor);
 	return avg;
-- 
1.8.5.2

Add initial support for per-rx queue sysfs attributes to virtio-net. If
mergeable packet buffers are enabled, adds a read-only mergeable packet
buffer size sysfs attribute for each RX queue.

Suggested-by: Michael S. Tsirkin <mst at redhat.com>
Acked-by: Michael S. Tsirkin <mst at redhat.com>
Signed-off-by: Michael Dalton <mwdalton at google.com>
---
v3->v4: Remove seqcount due to EWMA changes in patch 5.
        Add missing Suggested-By. 

 drivers/net/virtio_net.c | 46 ++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 42 insertions(+), 4 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3e82311..968eacd 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -604,18 +604,25 @@ static int add_recvbuf_big(struct receive_queue *rq, gfp_t
gfp)
 	return err;
 }
 
-static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
+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 page_frag *alloc_frag = &rq->alloc_frag;
 	char *buf;
 	unsigned long ctx;
 	int err;
 	unsigned int len, hole;
 
-	len = hdr_len + clamp_t(unsigned int, ewma_read(&rq->mrg_avg_pkt_len),
-				GOOD_PACKET_LEN, PAGE_SIZE - hdr_len);
-	len = ALIGN(len, MERGEABLE_BUFFER_ALIGN);
+	len = get_mergeable_buf_len(&rq->mrg_avg_pkt_len);
 	if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
 		return -ENOMEM;
 
@@ -1594,6 +1601,33 @@ 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;
@@ -1708,6 +1742,10 @@ 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);
 
-- 
1.8.5.2

This series does not apply cleanly to net-next.