[dpdk-stable] patch 'vhost: fix shadow update' has been queued to stable release 19.11.3

[luca.boccassi at gmail.com]

Hi,

FYI, your patch has been queued to stable release 19.11.3

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 05/21/20. So please
shout if anyone has objections.

Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.

Thanks.

Luca Boccassi

---
>From 2f48b0530563e5ce5f383212d0da5fad758cab82 Mon Sep 17 00:00:00 2001
From: Marvin Liu <yong.liu at intel.com>
Date: Fri, 17 Apr 2020 10:39:05 +0800
Subject: [PATCH] vhost: fix shadow update

[ upstream commit 8b13d12a16e7da07326f75bb8b5b82a39bdcbe9e ]

Defer shadow ring update introduces functional issue which has been
described in Eugenio's fix patch.

The current implementation of vhost_net in packed vring tries to fill
the shadow vector before send any actual changes to the guest. While
this can be beneficial for the throughput, it conflicts with some
bufferfloats methods like the linux kernel napi, that stops
transmitting packets if there are too much bytes/buffers in the
driver.

It also introduces performance issue when frontend run much faster than
backend. Frontend may not be able to collect available descs when shadow
update is deferred. That will harm RFC2544 throughput.

Appropriate choice is to remove deferred shadowed update method.
Now shadowed used descs are flushed at the end of dequeue function.

Fixes: 31d6c6a5b820 ("vhost: optimize packed ring dequeue")

Signed-off-by: Marvin Liu <yong.liu at intel.com>
Tested-by: Yinan Wang <yinan.wang at intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin at redhat.com>
---
 lib/librte_vhost/virtio_net.c | 46 ++---------------------------------
 1 file changed, 2 insertions(+), 44 deletions(-)

diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 3f46f5c517..4c7ae29a36 100644
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -382,25 +382,6 @@ vhost_shadow_enqueue_single_packed(struct virtio_net *dev,
 	}
 }
 
-static __rte_always_inline void
-vhost_flush_dequeue_packed(struct virtio_net *dev,
-			   struct vhost_virtqueue *vq)
-{
-	int shadow_count;
-	if (!vq->shadow_used_idx)
-		return;
-
-	shadow_count = vq->last_used_idx - vq->shadow_last_used_idx;
-	if (shadow_count <= 0)
-		shadow_count += vq->size;
-
-	if ((uint32_t)shadow_count >= (vq->size - MAX_PKT_BURST)) {
-		do_data_copy_dequeue(vq);
-		vhost_flush_dequeue_shadow_packed(dev, vq);
-		vhost_vring_call_packed(dev, vq);
-	}
-}
-
 /* avoid write operation when necessary, to lessen cache issues */
 #define ASSIGN_UNLESS_EQUAL(var, val) do {	\
 	if ((var) != (val))			\
@@ -2137,20 +2118,6 @@ virtio_dev_tx_packed_zmbuf(struct virtio_net *dev,
 	return pkt_idx;
 }
 
-static __rte_always_inline bool
-next_desc_is_avail(const struct vhost_virtqueue *vq)
-{
-	bool wrap_counter = vq->avail_wrap_counter;
-	uint16_t next_used_idx = vq->last_used_idx + 1;
-
-	if (next_used_idx >= vq->size) {
-		next_used_idx -= vq->size;
-		wrap_counter ^= 1;
-	}
-
-	return desc_is_avail(&vq->desc_packed[next_used_idx], wrap_counter);
-}
-
 static __rte_noinline uint16_t
 virtio_dev_tx_packed(struct virtio_net *dev,
 		     struct vhost_virtqueue *vq,
@@ -2167,7 +2134,6 @@ virtio_dev_tx_packed(struct virtio_net *dev,
 		if (remained >= PACKED_BATCH_SIZE) {
 			if (!virtio_dev_tx_batch_packed(dev, vq, mbuf_pool,
 							&pkts[pkt_idx])) {
-				vhost_flush_dequeue_packed(dev, vq);
 				pkt_idx += PACKED_BATCH_SIZE;
 				remained -= PACKED_BATCH_SIZE;
 				continue;
@@ -2177,7 +2143,6 @@ virtio_dev_tx_packed(struct virtio_net *dev,
 		if (virtio_dev_tx_single_packed(dev, vq, mbuf_pool,
 						&pkts[pkt_idx]))
 			break;
-		vhost_flush_dequeue_packed(dev, vq);
 		pkt_idx++;
 		remained--;
 
@@ -2186,15 +2151,8 @@ virtio_dev_tx_packed(struct virtio_net *dev,
 	if (vq->shadow_used_idx) {
 		do_data_copy_dequeue(vq);
 
-		if (remained && !next_desc_is_avail(vq)) {
-			/*
-			 * The guest may be waiting to TX some buffers to
-			 * enqueue more to avoid bufferfloat, so we try to
-			 * reduce latency here.
-			 */
-			vhost_flush_dequeue_shadow_packed(dev, vq);
-			vhost_vring_call_packed(dev, vq);
-		}
+		vhost_flush_dequeue_shadow_packed(dev, vq);
+		vhost_vring_call_packed(dev, vq);
 	}
 
 	return pkt_idx;
-- 
2.20.1

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2020-05-19 14:04:48.497459873 +0100
+++ 0099-vhost-fix-shadow-update.patch	2020-05-19 14:04:44.312650112 +0100
@@ -1,8 +1,10 @@
-From 8b13d12a16e7da07326f75bb8b5b82a39bdcbe9e Mon Sep 17 00:00:00 2001
+From 2f48b0530563e5ce5f383212d0da5fad758cab82 Mon Sep 17 00:00:00 2001
 From: Marvin Liu <yong.liu at intel.com>
 Date: Fri, 17 Apr 2020 10:39:05 +0800
 Subject: [PATCH] vhost: fix shadow update
 
+[ upstream commit 8b13d12a16e7da07326f75bb8b5b82a39bdcbe9e ]
+
 Defer shadow ring update introduces functional issue which has been
 described in Eugenio's fix patch.
 
@@ -21,7 +23,6 @@
 Now shadowed used descs are flushed at the end of dequeue function.
 
 Fixes: 31d6c6a5b820 ("vhost: optimize packed ring dequeue")
-Cc: stable at dpdk.org
 
 Signed-off-by: Marvin Liu <yong.liu at intel.com>
 Tested-by: Yinan Wang <yinan.wang at intel.com>
@@ -31,7 +32,7 @@
  1 file changed, 2 insertions(+), 44 deletions(-)
 
 diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
-index 2104159047..4a75319432 100644
+index 3f46f5c517..4c7ae29a36 100644
 --- a/lib/librte_vhost/virtio_net.c
 +++ b/lib/librte_vhost/virtio_net.c
 @@ -382,25 +382,6 @@ vhost_shadow_enqueue_single_packed(struct virtio_net *dev,
@@ -60,7 +61,7 @@
  /* avoid write operation when necessary, to lessen cache issues */
  #define ASSIGN_UNLESS_EQUAL(var, val) do {	\
  	if ((var) != (val))			\
-@@ -2133,20 +2114,6 @@ virtio_dev_tx_packed_zmbuf(struct virtio_net *dev,
+@@ -2137,20 +2118,6 @@ virtio_dev_tx_packed_zmbuf(struct virtio_net *dev,
  	return pkt_idx;
  }
  
@@ -81,7 +82,7 @@
  static __rte_noinline uint16_t
  virtio_dev_tx_packed(struct virtio_net *dev,
  		     struct vhost_virtqueue *vq,
-@@ -2163,7 +2130,6 @@ virtio_dev_tx_packed(struct virtio_net *dev,
+@@ -2167,7 +2134,6 @@ virtio_dev_tx_packed(struct virtio_net *dev,
  		if (remained >= PACKED_BATCH_SIZE) {
  			if (!virtio_dev_tx_batch_packed(dev, vq, mbuf_pool,
  							&pkts[pkt_idx])) {
@@ -89,7 +90,7 @@
  				pkt_idx += PACKED_BATCH_SIZE;
  				remained -= PACKED_BATCH_SIZE;
  				continue;
-@@ -2173,7 +2139,6 @@ virtio_dev_tx_packed(struct virtio_net *dev,
+@@ -2177,7 +2143,6 @@ virtio_dev_tx_packed(struct virtio_net *dev,
  		if (virtio_dev_tx_single_packed(dev, vq, mbuf_pool,
  						&pkts[pkt_idx]))
  			break;
@@ -97,7 +98,7 @@
  		pkt_idx++;
  		remained--;
  
-@@ -2182,15 +2147,8 @@ virtio_dev_tx_packed(struct virtio_net *dev,
+@@ -2186,15 +2151,8 @@ virtio_dev_tx_packed(struct virtio_net *dev,
  	if (vq->shadow_used_idx) {
  		do_data_copy_dequeue(vq);