From: Krishna Kumar <krkumar2@in.ibm.com>
To: rusty@rustcorp.com.au, mst@redhat.com
Cc: netdev@vger.kernel.org, kvm@vger.kernel.org, davem@davemloft.net,
Krishna Kumar <krkumar2@in.ibm.com>,
virtualization@lists.linux-foundation.org
Subject: [RFC] [ver3 PATCH 6/6] virtio_net: Convert virtio_net driver to use find_vqs_irq
Date: Fri, 11 Nov 2011 18:37:15 +0530 [thread overview]
Message-ID: <20111111130715.9878.31409.sendpatchset@krkumar2.in.ibm.com> (raw)
In-Reply-To: <20111111130223.9878.59517.sendpatchset@krkumar2.in.ibm.com>
Convert virtio_net driver to use find_vqs_irq(). The TX vq's
share a single irq, while the RX vq's have individual irq's.
The skb_xmit_done handler also checks if any work is required.
Signed-off-by: krkumar2@in.ibm.com
---
drivers/net/virtio_net.c | 29 ++++++++++++++++++++++-------
1 file changed, 22 insertions(+), 7 deletions(-)
diff -ruNp org/drivers/net/virtio_net.c new/drivers/net/virtio_net.c
--- org/drivers/net/virtio_net.c 2011-11-11 16:45:17.000000000 +0530
+++ new/drivers/net/virtio_net.c 2011-11-11 16:48:45.000000000 +0530
@@ -163,11 +163,13 @@ static void skb_xmit_done(struct virtque
struct virtnet_info *vi = vq->vdev->priv;
int qnum = vq->queue_index / 2; /* RX/TX vqs are allocated in pairs */
- /* Suppress further interrupts. */
- virtqueue_disable_cb(vq);
+ if (__netif_subqueue_stopped(vi->dev, qnum)) {
+ /* Suppress further interrupts. */
+ virtqueue_disable_cb(vq);
- /* We were probably waiting for more output buffers. */
- netif_wake_subqueue(vi->dev, qnum);
+ /* We were probably waiting for more output buffers. */
+ netif_wake_subqueue(vi->dev, qnum);
+ }
}
static void set_skb_frag(struct sk_buff *skb, struct page *page,
@@ -1120,6 +1122,7 @@ static void setup_cvq(struct virtnet_inf
static int invoke_find_vqs(struct virtnet_info *vi)
{
+ unsigned long *flags = NULL;
vq_callback_t **callbacks;
struct virtqueue **vqs;
int ret = -ENOMEM;
@@ -1141,6 +1144,14 @@ static int invoke_find_vqs(struct virtne
if (!vqs || !callbacks || !names)
goto err;
+ if (vi->num_queue_pairs > 1) {
+ int num = (total_vqs + BITS_PER_LONG - 1) / BITS_PER_LONG;
+
+ flags = kzalloc(num * sizeof(*flags), GFP_KERNEL);
+ if (!flags)
+ goto err;
+ }
+
/* Allocate/initialize parameters for recv virtqueues */
for (i = 0; i < vi->num_queue_pairs * 2; i += 2) {
callbacks[i] = skb_recv_done;
@@ -1155,6 +1166,8 @@ static int invoke_find_vqs(struct virtne
names[i] = kasprintf(GFP_KERNEL, "output.%d", i / 2);
if (!names[i])
goto err;
+ if (flags)
+ set_bit(i, flags);
}
/* Parameters for control virtqueue, if any */
@@ -1163,9 +1176,9 @@ static int invoke_find_vqs(struct virtne
names[i - 1] = "control";
}
- ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
- (const char **)names);
-
+ ret = vi->vdev->config->find_vqs_irq(vi->vdev, total_vqs, vqs,
+ callbacks, (const char **)names,
+ flags);
if (ret)
goto err;
@@ -1174,6 +1187,8 @@ static int invoke_find_vqs(struct virtne
setup_cvq(vi, vqs, vi->num_queue_pairs * 2);
err:
+ kfree(flags);
+
if (ret && names)
for (i = 0; i < vi->num_queue_pairs * 2; i++)
kfree(names[i]);
next prev parent reply other threads:[~2011-11-11 13:54 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-11-11 13:02 [RFC] [ver3 PATCH 0/6] Implement multiqueue virtio-net Krishna Kumar
2011-11-11 13:02 ` [RFC] [ver3 PATCH 1/6] virtio_net: Introduce VIRTIO_NET_F_MULTIQUEUE Krishna Kumar
2011-11-11 13:03 ` [RFC] [ver3 PATCH 2/6] virtio: Move 'num_queues' to virtqueue Krishna Kumar
2011-11-11 13:04 ` [RFC] [ver3 PATCH 3/6] virtio_net: virtio_net driver changes Krishna Kumar
2011-11-18 1:08 ` Ben Hutchings
2011-11-18 6:24 ` Sasha Levin
2011-11-18 15:40 ` Ben Hutchings
2011-11-18 16:18 ` Sasha Levin
2011-11-18 17:14 ` Ben Hutchings
2011-11-11 13:05 ` [RFC] [ver3 PATCH 4/6] vhost_net: vhost_net changes Krishna Kumar
2011-11-11 13:06 ` [RFC] [ver3 PATCH 5/6] virtio: Implement find_vqs_irq() Krishna Kumar
2011-11-11 13:07 ` Krishna Kumar [this message]
2011-11-11 22:02 ` [RFC] [ver3 PATCH 0/6] Implement multiqueue virtio-net Sasha Levin
2011-11-13 11:40 ` Michael S. Tsirkin
2011-11-13 17:48 ` [PATCH RFC] ndo: ndo_queue_xmit/ndo_flush_xmit (was Re: [RFC] [ver3 PATCH 0/6] Implement multiqueue virtio-net) Michael S. Tsirkin
2011-11-14 16:21 ` Michael S. Tsirkin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20111111130715.9878.31409.sendpatchset@krkumar2.in.ibm.com \
--to=krkumar2@in.ibm.com \
--cc=davem@davemloft.net \
--cc=kvm@vger.kernel.org \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=rusty@rustcorp.com.au \
--cc=virtualization@lists.linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).