Linux Virtualization - Jun 2015 - [PATCH RFC] vhost: add ioctl to query nregions upper limit

Userspace currently simply tries to give vhost as many regions
as it happens to have, but you only have the mem table
when you have initialized a large part of VM, so graceful
failure is very hard to support.

The result is that userspace tends to fail catastrophically.

Instead, add a new ioctl so userspace can find out how much kernel
supports, up front. This returns a positive value that we commit to.

Also, document our contract with legacy userspace: when running on an
old kernel, you get -1 and you can assume at least 64 slots.  Since 0
value's left unused, let's make that mean that the current userspace
behaviour (trial and error) is required, just in case we want it back.

Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
Cc: Igor Mammedov <imammedo at redhat.com>
Cc: Paolo Bonzini <pbonzini at redhat.com>
---
 include/uapi/linux/vhost.h | 17 ++++++++++++++++-
 drivers/vhost/vhost.c      |  5 +++++
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index ab373191..f71fa6d 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -80,7 +80,7 @@ struct vhost_memory {
  * Allows subsequent call to VHOST_OWNER_SET to succeed. */
 #define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
 
-/* Set up/modify memory layout */
+/* Set up/modify memory layout: see also VHOST_GET_MEM_MAX_NREGIONS below. */
 #define VHOST_SET_MEM_TABLE	_IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
 
 /* Write logging setup. */
@@ -127,6 +127,21 @@ struct vhost_memory {
 /* Set eventfd to signal an error */
 #define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
 
+/* Query upper limit on nregions in VHOST_SET_MEM_TABLE arguments.
+ * Returns:
+ * 	0 < value <= MAX_INT - gives the upper limit, higher values will fail
+ * 	0 - there's no static limit: try and see if it works
+ * 	-1 - on failure
+ */
+#define VHOST_GET_MEM_MAX_NREGIONS   _IO(VHOST_VIRTIO, 0x23)
+
+/* Returned by VHOST_GET_MEM_MAX_NREGIONS to mean there's no static limit:
+ * try and it'll work if you are lucky. */
+#define VHOST_MEM_MAX_NREGIONS_NONE 0
+/* We support at least as many nregions in VHOST_SET_MEM_TABLE:
+ * for use on legacy kernels without VHOST_GET_MEM_MAX_NREGIONS support. */
+#define VHOST_MEM_MAX_NREGIONS_DEFAULT 64
+
 /* VHOST_NET specific defines */
 
 /* Attach virtio net ring to a raw socket, or tap device.
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 9e8e004..3b68f9d 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -917,6 +917,11 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int
ioctl, void __user *argp)
 	long r;
 	int i, fd;
 
+	if (ioctl == VHOST_GET_MEM_MAX_NREGIONS) {
+		r = VHOST_MEMORY_MAX_NREGIONS;
+		goto done;
+	}
+
 	/* If you are not the owner, you can become one */
 	if (ioctl == VHOST_SET_OWNER) {
 		r = vhost_dev_set_owner(d);
-- 
MST

On Wed, 24 Jun 2015 15:49:27 +0200
"Michael S. Tsirkin" <mst at redhat.com> wrote:
> Userspace currently simply tries to give vhost as many regions
> as it happens to have, but you only have the mem table
> when you have initialized a large part of VM, so graceful
> failure is very hard to support.
> 
> The result is that userspace tends to fail catastrophically.
> 
> Instead, add a new ioctl so userspace can find out how much kernel
> supports, up front. This returns a positive value that we commit to.
> 
> Also, document our contract with legacy userspace: when running on an
> old kernel, you get -1 and you can assume at least 64 slots.  Since 0
> value's left unused, let's make that mean that the current
userspace
> behaviour (trial and error) is required, just in case we want it back.
> 
> Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
> Cc: Igor Mammedov <imammedo at redhat.com>
> Cc: Paolo Bonzini <pbonzini at redhat.com>
> ---
>  include/uapi/linux/vhost.h | 17 ++++++++++++++++-
>  drivers/vhost/vhost.c      |  5 +++++
>  2 files changed, 21 insertions(+), 1 deletion(-)
> 
> diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
> index ab373191..f71fa6d 100644
> --- a/include/uapi/linux/vhost.h
> +++ b/include/uapi/linux/vhost.h
> @@ -80,7 +80,7 @@ struct vhost_memory {
>   * Allows subsequent call to VHOST_OWNER_SET to succeed. */
>  #define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
>  
> -/* Set up/modify memory layout */
> +/* Set up/modify memory layout: see also VHOST_GET_MEM_MAX_NREGIONS below.
*/
>  #define VHOST_SET_MEM_TABLE	_IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
>  
>  /* Write logging setup. */
> @@ -127,6 +127,21 @@ struct vhost_memory {
>  /* Set eventfd to signal an error */
>  #define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct
vhost_vring_file)
>  
> +/* Query upper limit on nregions in VHOST_SET_MEM_TABLE arguments.
> + * Returns:
> + * 	0 < value <= MAX_INT - gives the upper limit, higher values will
fail
> + * 	0 - there's no static limit: try and see if it works
> + * 	-1 - on failure
> + */
> +#define VHOST_GET_MEM_MAX_NREGIONS   _IO(VHOST_VIRTIO, 0x23)
> +
> +/* Returned by VHOST_GET_MEM_MAX_NREGIONS to mean there's no static
limit:
> + * try and it'll work if you are lucky. */
> +#define VHOST_MEM_MAX_NREGIONS_NONE 0
is it needed? we always have a limit,
or don't have IOCTL => -1 => old try and see way
> +/* We support at least as many nregions in VHOST_SET_MEM_TABLE:
> + * for use on legacy kernels without VHOST_GET_MEM_MAX_NREGIONS support.
*/
> +#define VHOST_MEM_MAX_NREGIONS_DEFAULT 64
^^^ not used below,
if it's for legacy then perhaps s/DEFAULT/LEGACY/ 
> +
>  /* VHOST_NET specific defines */
>  
>  /* Attach virtio net ring to a raw socket, or tap device.
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index 9e8e004..3b68f9d 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -917,6 +917,11 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int
ioctl, void __user *argp)
>  	long r;
>  	int i, fd;
>  
> +	if (ioctl == VHOST_GET_MEM_MAX_NREGIONS) {
> +		r = VHOST_MEMORY_MAX_NREGIONS;
> +		goto done;
> +	}
> +
>  	/* If you are not the owner, you can become one */
>  	if (ioctl == VHOST_SET_OWNER) {
>  		r = vhost_dev_set_owner(d);

On Wed, Jun 24, 2015 at 04:07:27PM +0200, Igor Mammedov
wrote:
> On Wed, 24 Jun 2015 15:49:27 +0200
> "Michael S. Tsirkin" <mst at redhat.com> wrote:
> 
> > Userspace currently simply tries to give vhost as many regions
> > as it happens to have, but you only have the mem table
> > when you have initialized a large part of VM, so graceful
> > failure is very hard to support.
> > 
> > The result is that userspace tends to fail catastrophically.
> > 
> > Instead, add a new ioctl so userspace can find out how much kernel
> > supports, up front. This returns a positive value that we commit to.
> > 
> > Also, document our contract with legacy userspace: when running on an
> > old kernel, you get -1 and you can assume at least 64 slots.  Since 0
> > value's left unused, let's make that mean that the current
userspace
> > behaviour (trial and error) is required, just in case we want it back.
> > 
> > Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
> > Cc: Igor Mammedov <imammedo at redhat.com>
> > Cc: Paolo Bonzini <pbonzini at redhat.com>
> > ---
> >  include/uapi/linux/vhost.h | 17 ++++++++++++++++-
> >  drivers/vhost/vhost.c      |  5 +++++
> >  2 files changed, 21 insertions(+), 1 deletion(-)
> > 
> > diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
> > index ab373191..f71fa6d 100644
> > --- a/include/uapi/linux/vhost.h
> > +++ b/include/uapi/linux/vhost.h
> > @@ -80,7 +80,7 @@ struct vhost_memory {
> >   * Allows subsequent call to VHOST_OWNER_SET to succeed. */
> >  #define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
> >  
> > -/* Set up/modify memory layout */
> > +/* Set up/modify memory layout: see also VHOST_GET_MEM_MAX_NREGIONS
below. */
> >  #define VHOST_SET_MEM_TABLE	_IOW(VHOST_VIRTIO, 0x03, struct
vhost_memory)
> >  
> >  /* Write logging setup. */
> > @@ -127,6 +127,21 @@ struct vhost_memory {
> >  /* Set eventfd to signal an error */
> >  #define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct
vhost_vring_file)
> >  
> > +/* Query upper limit on nregions in VHOST_SET_MEM_TABLE arguments.
> > + * Returns:
> > + * 	0 < value <= MAX_INT - gives the upper limit, higher values
will fail
> > + * 	0 - there's no static limit: try and see if it works
> > + * 	-1 - on failure
> > + */
> > +#define VHOST_GET_MEM_MAX_NREGIONS   _IO(VHOST_VIRTIO, 0x23)
> > +
> > +/* Returned by VHOST_GET_MEM_MAX_NREGIONS to mean there's no
static limit:
> > + * try and it'll work if you are lucky. */
> > +#define VHOST_MEM_MAX_NREGIONS_NONE 0
> is it needed? we always have a limit,
> or don't have IOCTL => -1 => old try and see way
> 
> > +/* We support at least as many nregions in VHOST_SET_MEM_TABLE:
> > + * for use on legacy kernels without VHOST_GET_MEM_MAX_NREGIONS
support. */
> > +#define VHOST_MEM_MAX_NREGIONS_DEFAULT 64
> ^^^ not used below,
> if it's for legacy then perhaps s/DEFAULT/LEGACY/ 
The assumption was that userspace detecting old kernels will just use 64,
this means we do want a flag to get the old way.

OTOH if you won't think it's useful, let me know.
> > +
> >  /* VHOST_NET specific defines */
> >  
> >  /* Attach virtio net ring to a raw socket, or tap device.
> > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> > index 9e8e004..3b68f9d 100644
> > --- a/drivers/vhost/vhost.c
> > +++ b/drivers/vhost/vhost.c
> > @@ -917,6 +917,11 @@ long vhost_dev_ioctl(struct vhost_dev *d,
unsigned int ioctl, void __user *argp)
> >  	long r;
> >  	int i, fd;
> >  
> > +	if (ioctl == VHOST_GET_MEM_MAX_NREGIONS) {
> > +		r = VHOST_MEMORY_MAX_NREGIONS;
> > +		goto done;
> > +	}
> > +
> >  	/* If you are not the owner, you can become one */
> >  	if (ioctl == VHOST_SET_OWNER) {
> >  		r = vhost_dev_set_owner(d);