* [PATCH] vhost: fix performance on LE hosts
@ 2015-10-27 9:37 Michael S. Tsirkin
2015-10-27 10:30 ` Greg Kurz
` (2 more replies)
0 siblings, 3 replies; 5+ messages in thread
From: Michael S. Tsirkin @ 2015-10-27 9:37 UTC (permalink / raw)
To: linux-kernel; +Cc: netdev, virtualization, kvm
commit 2751c9882b947292fcfb084c4f604e01724af804 ("vhost: cross-endian
support for legacy devices") introduced a minor regression: even with
cross-endian disabled, and even on LE host, vhost_is_little_endian is
checking is_le flag so there's always a branch.
To fix, simply check virtio_legacy_is_little_endian first.
Cc: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/vhost/vhost.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 4772862..d3f7674 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -183,10 +183,17 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
return vq->acked_features & (1ULL << bit);
}
+#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
{
return vq->is_le;
}
+#else
+static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
+{
+ return virtio_legacy_is_little_endian() || vq->is_le;
+}
+#endif
/* Memory accessors */
static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val)
--
MST
^ permalink raw reply related [flat|nested] 5+ messages in thread* Re: [PATCH] vhost: fix performance on LE hosts
2015-10-27 9:37 [PATCH] vhost: fix performance on LE hosts Michael S. Tsirkin
@ 2015-10-27 10:30 ` Greg Kurz
2015-10-27 13:32 ` David Miller
2015-10-28 3:19 ` David Miller
2 siblings, 0 replies; 5+ messages in thread
From: Greg Kurz @ 2015-10-27 10:30 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: netdev, linux-kernel, kvm, virtualization
On Tue, 27 Oct 2015 11:37:39 +0200
"Michael S. Tsirkin" <mst@redhat.com> wrote:
> commit 2751c9882b947292fcfb084c4f604e01724af804 ("vhost: cross-endian
> support for legacy devices") introduced a minor regression: even with
> cross-endian disabled, and even on LE host, vhost_is_little_endian is
> checking is_le flag so there's always a branch.
>
> To fix, simply check virtio_legacy_is_little_endian first.
>
> Cc: Greg Kurz <gkurz@linux.vnet.ibm.com>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Oops my bad for this oversight...
Reviewed-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
> ---
> drivers/vhost/vhost.h | 7 +++++++
> 1 file changed, 7 insertions(+)
>
> diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
> index 4772862..d3f7674 100644
> --- a/drivers/vhost/vhost.h
> +++ b/drivers/vhost/vhost.h
> @@ -183,10 +183,17 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
> return vq->acked_features & (1ULL << bit);
> }
>
> +#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
> static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
> {
> return vq->is_le;
> }
> +#else
> +static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
> +{
> + return virtio_legacy_is_little_endian() || vq->is_le;
> +}
> +#endif
>
> /* Memory accessors */
> static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val)
^ permalink raw reply [flat|nested] 5+ messages in thread* Re: [PATCH] vhost: fix performance on LE hosts
2015-10-27 9:37 [PATCH] vhost: fix performance on LE hosts Michael S. Tsirkin
2015-10-27 10:30 ` Greg Kurz
@ 2015-10-27 13:32 ` David Miller
2015-10-27 15:52 ` Michael S. Tsirkin
2015-10-28 3:19 ` David Miller
2 siblings, 1 reply; 5+ messages in thread
From: David Miller @ 2015-10-27 13:32 UTC (permalink / raw)
To: mst; +Cc: linux-kernel, gkurz, kvm, virtualization, netdev
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 27 Oct 2015 11:37:39 +0200
> commit 2751c9882b947292fcfb084c4f604e01724af804 ("vhost: cross-endian
> support for legacy devices") introduced a minor regression: even with
> cross-endian disabled, and even on LE host, vhost_is_little_endian is
> checking is_le flag so there's always a branch.
>
> To fix, simply check virtio_legacy_is_little_endian first.
>
> Cc: Greg Kurz <gkurz@linux.vnet.ibm.com>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Michael, do you want me to take this via the 'net' tree?
^ permalink raw reply [flat|nested] 5+ messages in thread* Re: [PATCH] vhost: fix performance on LE hosts
2015-10-27 13:32 ` David Miller
@ 2015-10-27 15:52 ` Michael S. Tsirkin
0 siblings, 0 replies; 5+ messages in thread
From: Michael S. Tsirkin @ 2015-10-27 15:52 UTC (permalink / raw)
To: David Miller; +Cc: netdev, virtualization, linux-kernel, kvm
On Tue, Oct 27, 2015 at 06:32:55AM -0700, David Miller wrote:
> From: "Michael S. Tsirkin" <mst@redhat.com>
> Date: Tue, 27 Oct 2015 11:37:39 +0200
>
> > commit 2751c9882b947292fcfb084c4f604e01724af804 ("vhost: cross-endian
> > support for legacy devices") introduced a minor regression: even with
> > cross-endian disabled, and even on LE host, vhost_is_little_endian is
> > checking is_le flag so there's always a branch.
> >
> > To fix, simply check virtio_legacy_is_little_endian first.
> >
> > Cc: Greg Kurz <gkurz@linux.vnet.ibm.com>
> > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
>
> Michael, do you want me to take this via the 'net' tree?
Sure - especially since it looks like I have nothing else for this merge
window (working on fixing shutdown races, but it's slow going). Thanks
a lot!
--
MST
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] vhost: fix performance on LE hosts
2015-10-27 9:37 [PATCH] vhost: fix performance on LE hosts Michael S. Tsirkin
2015-10-27 10:30 ` Greg Kurz
2015-10-27 13:32 ` David Miller
@ 2015-10-28 3:19 ` David Miller
2 siblings, 0 replies; 5+ messages in thread
From: David Miller @ 2015-10-28 3:19 UTC (permalink / raw)
To: mst; +Cc: netdev, virtualization, linux-kernel, kvm
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 27 Oct 2015 11:37:39 +0200
> commit 2751c9882b947292fcfb084c4f604e01724af804 ("vhost: cross-endian
> support for legacy devices") introduced a minor regression: even with
> cross-endian disabled, and even on LE host, vhost_is_little_endian is
> checking is_le flag so there's always a branch.
>
> To fix, simply check virtio_legacy_is_little_endian first.
>
> Cc: Greg Kurz <gkurz@linux.vnet.ibm.com>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Applied.
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2015-10-28 3:19 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2015-10-27 9:37 [PATCH] vhost: fix performance on LE hosts Michael S. Tsirkin
2015-10-27 10:30 ` Greg Kurz
2015-10-27 13:32 ` David Miller
2015-10-27 15:52 ` Michael S. Tsirkin
2015-10-28 3:19 ` David Miller
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).