subject:"\[RFC PATCH 2\/3\] vfio\-pci\: Allow to mmap sub\-page MMIO BARs if all MMIO BARs are page aligned"

Re: [RFC PATCH 2/3] vfio-pci: Allow to mmap sub-page MMIO BARs if all MMIO BARs are page aligned

2015-12-18 Thread yongji xie




On 2015/12/18 5:46, Alex Williamson wrote:

On Thu, 2015-12-17 at 18:26 +0800, yongji xie wrote:

On 2015/12/17 4:04, Alex Williamson wrote:

On Fri, 2015-12-11 at 16:53 +0800, Yongji Xie wrote:

Current vfio-pci implementation disallows to mmap
sub-page(size < PAGE_SIZE) MMIO BARs because these BARs' mmio
page
may be shared with other BARs.

But we should allow to mmap these sub-page MMIO BARs if all MMIO
BARs
are page aligned which leads the BARs' mmio page would not be
shared
with other BARs.

This patch adds support for this case and we also add a
VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED flag to notify userspace that
platform supports all MMIO BARs to be page aligned.

Signed-off-by: Yongji Xie 
---
   drivers/vfio/pci/vfio_pci.c |   10 +-
   drivers/vfio/pci/vfio_pci_private.h |5 +
   include/uapi/linux/vfio.h   |2 ++
   3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/vfio_pci.c
b/drivers/vfio/pci/vfio_pci.c
index 32b88bd..dbcad99 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -443,6 +443,9 @@ static long vfio_pci_ioctl(void *device_data,
if (vdev->reset_works)
info.flags |= VFIO_DEVICE_FLAGS_RESET;
   
+		if (vfio_pci_bar_page_aligned())

+   info.flags |=
VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED;
+
info.num_regions = VFIO_PCI_NUM_REGIONS;
info.num_irqs = VFIO_PCI_NUM_IRQS;
   
@@ -479,7 +482,8 @@ static long vfio_pci_ioctl(void *device_data,

 VFIO_REGION_INFO_FLAG_WRIT
E;
if (IS_ENABLED(CONFIG_VFIO_PCI_MMAP) &&
pci_resource_flags(pdev,
info.index) &
-   IORESOURCE_MEM && info.size >=
PAGE_SIZE)
+   IORESOURCE_MEM && (info.size >=
PAGE_SIZE ||
+   vfio_pci_bar_page_aligned()))
info.flags |=
VFIO_REGION_INFO_FLAG_MMAP;
break;
case VFIO_PCI_ROM_REGION_INDEX:
@@ -855,6 +859,10 @@ static int vfio_pci_mmap(void *device_data,
struct vm_area_struct *vma)
return -EINVAL;
   
   	phys_len = pci_resource_len(pdev, index);

+
+   if (vfio_pci_bar_page_aligned())
+   phys_len = PAGE_ALIGN(phys_len);
+
req_len = vma->vm_end - vma->vm_start;
pgoff = vma->vm_pgoff &
((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) -
1);
diff --git a/drivers/vfio/pci/vfio_pci_private.h
b/drivers/vfio/pci/vfio_pci_private.h
index 0e7394f..319352a 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -69,6 +69,11 @@ struct vfio_pci_device {
   #define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) ||
is_msix(vdev)))
   #define irq_is(vdev, type) (vdev->irq_type == type)
   
+static inline bool vfio_pci_bar_page_aligned(void)

+{
+   return IS_ENABLED(CONFIG_PPC64);
+}

I really dislike this.  This is a problem for any architecture that
runs on larger pages, and even an annoyance on 4k hosts.  Why are
we
only solving it for PPC64?

Yes, I know it's a problem for other architectures. But I'm not sure
if
other archs prefer
to enforce the alignment of all BARs to be at least PAGE_SIZE which
would result in
some waste of address space.

So I just propose a prototype and add PPC64 support here. And other
archs could decide
to use it or not by themselves.

Can't we do something similar in the core PCI code and detect it?

So you mean we can do it like this:

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index d390fc1..f46c04d 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -320,6 +320,11 @@ static inline resource_size_t
pci_resource_alignment(struct pci_dev *dev,
  return resource_alignment(res);
   }

+static inline bool pci_bar_page_aligned(void)
+{
+   return IS_ENABLED(CONFIG_PPC64);
+}
+
   void pci_enable_acs(struct pci_dev *dev);

   struct pci_dev_reset_methods {

or add a config option to indicate that PCI MMIO BARs should be page
aligned?

Yes, I'm thinking of a boot commandline option, maybe one that PPC64
can default to enabled if it chooses to.  The problem is not unique to
PPC64 and the solution should not be unique either.  I don't want to
need to revisit this for ARM, which we know is going to be similarly
afflicted.  Thanks,

Alex


OK. I will try to fix it by adding a boot commandline option.
It seems to be better than adding a config option. Thanks

Regards
Yongji Xie

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [RFC PATCH 2/3] vfio-pci: Allow to mmap sub-page MMIO BARs if all MMIO BARs are page aligned

2015-12-17 Thread yongji xie




On 2015/12/17 4:04, Alex Williamson wrote:

On Fri, 2015-12-11 at 16:53 +0800, Yongji Xie wrote:

Current vfio-pci implementation disallows to mmap
sub-page(size < PAGE_SIZE) MMIO BARs because these BARs' mmio page
may be shared with other BARs.

But we should allow to mmap these sub-page MMIO BARs if all MMIO BARs
are page aligned which leads the BARs' mmio page would not be shared
with other BARs.

This patch adds support for this case and we also add a
VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED flag to notify userspace that
platform supports all MMIO BARs to be page aligned.

Signed-off-by: Yongji Xie 
---
  drivers/vfio/pci/vfio_pci.c |   10 +-
  drivers/vfio/pci/vfio_pci_private.h |5 +
  include/uapi/linux/vfio.h   |2 ++
  3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/vfio_pci.c
b/drivers/vfio/pci/vfio_pci.c
index 32b88bd..dbcad99 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -443,6 +443,9 @@ static long vfio_pci_ioctl(void *device_data,
if (vdev->reset_works)
info.flags |= VFIO_DEVICE_FLAGS_RESET;
  
+		if (vfio_pci_bar_page_aligned())

+   info.flags |=
VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED;
+
info.num_regions = VFIO_PCI_NUM_REGIONS;
info.num_irqs = VFIO_PCI_NUM_IRQS;
  
@@ -479,7 +482,8 @@ static long vfio_pci_ioctl(void *device_data,

 VFIO_REGION_INFO_FLAG_WRITE;
if (IS_ENABLED(CONFIG_VFIO_PCI_MMAP) &&
pci_resource_flags(pdev, info.index) &
-   IORESOURCE_MEM && info.size >=
PAGE_SIZE)
+   IORESOURCE_MEM && (info.size >=
PAGE_SIZE ||
+   vfio_pci_bar_page_aligned()))
info.flags |=
VFIO_REGION_INFO_FLAG_MMAP;
break;
case VFIO_PCI_ROM_REGION_INDEX:
@@ -855,6 +859,10 @@ static int vfio_pci_mmap(void *device_data,
struct vm_area_struct *vma)
return -EINVAL;
  
  	phys_len = pci_resource_len(pdev, index);

+
+   if (vfio_pci_bar_page_aligned())
+   phys_len = PAGE_ALIGN(phys_len);
+
req_len = vma->vm_end - vma->vm_start;
pgoff = vma->vm_pgoff &
((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
diff --git a/drivers/vfio/pci/vfio_pci_private.h
b/drivers/vfio/pci/vfio_pci_private.h
index 0e7394f..319352a 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -69,6 +69,11 @@ struct vfio_pci_device {
  #define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) ||
is_msix(vdev)))
  #define irq_is(vdev, type) (vdev->irq_type == type)
  
+static inline bool vfio_pci_bar_page_aligned(void)

+{
+   return IS_ENABLED(CONFIG_PPC64);
+}

I really dislike this.  This is a problem for any architecture that
runs on larger pages, and even an annoyance on 4k hosts.  Why are we
only solving it for PPC64?
Yes, I know it's a problem for other architectures. But I'm not sure if 
other archs prefer
to enforce the alignment of all BARs to be at least PAGE_SIZE which 
would result in

some waste of address space.

So I just propose a prototype and add PPC64 support here. And other 
archs could decide

to use it or not by themselves.

Can't we do something similar in the core PCI code and detect it?

So you mean we can do it like this:

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index d390fc1..f46c04d 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -320,6 +320,11 @@ static inline resource_size_t 
pci_resource_alignment(struct pci_dev *dev,

return resource_alignment(res);
 }

+static inline bool pci_bar_page_aligned(void)
+{
+   return IS_ENABLED(CONFIG_PPC64);
+}
+
 void pci_enable_acs(struct pci_dev *dev);

 struct pci_dev_reset_methods {

or add a config option to indicate that PCI MMIO BARs should be page 
aligned? Thanks.


Regards
Yongji Xie

+
  extern void vfio_pci_intx_mask(struct vfio_pci_device *vdev);
  extern void vfio_pci_intx_unmask(struct vfio_pci_device *vdev);
  
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h

index 751b69f..1fc8066 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -171,6 +171,8 @@ struct vfio_device_info {
  #define VFIO_DEVICE_FLAGS_PCI (1 << 1)  /* vfio-pci
device */
  #define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2) /* vfio-platform
device */
  #define VFIO_DEVICE_FLAGS_AMBA  (1 << 3)/* vfio-amba device
*/
+/* Platform support all PCI MMIO BARs to be page aligned */
+#define VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED (1 << 4)
__u32   num_regions;/* Max region index + 1 */
__u32   num_irqs;   /* Max IRQ index + 1 */
  };

Why is this on the device info, shouldn't it be per region?  Do we even
need a flag or can we just set the existing mmap flag

Re: [RFC PATCH 2/3] vfio-pci: Allow to mmap sub-page MMIO BARs if all MMIO BARs are page aligned

2015-12-17 Thread Alex Williamson

On Thu, 2015-12-17 at 18:26 +0800, yongji xie wrote:
> 
> On 2015/12/17 4:04, Alex Williamson wrote:
> > On Fri, 2015-12-11 at 16:53 +0800, Yongji Xie wrote:
> > > Current vfio-pci implementation disallows to mmap
> > > sub-page(size < PAGE_SIZE) MMIO BARs because these BARs' mmio
> > > page
> > > may be shared with other BARs.
> > > 
> > > But we should allow to mmap these sub-page MMIO BARs if all MMIO
> > > BARs
> > > are page aligned which leads the BARs' mmio page would not be
> > > shared
> > > with other BARs.
> > > 
> > > This patch adds support for this case and we also add a
> > > VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED flag to notify userspace that
> > > platform supports all MMIO BARs to be page aligned.
> > > 
> > > Signed-off-by: Yongji Xie 
> > > ---
> > >   drivers/vfio/pci/vfio_pci.c |   10 +-
> > >   drivers/vfio/pci/vfio_pci_private.h |5 +
> > >   include/uapi/linux/vfio.h   |2 ++
> > >   3 files changed, 16 insertions(+), 1 deletion(-)
> > > 
> > > diff --git a/drivers/vfio/pci/vfio_pci.c
> > > b/drivers/vfio/pci/vfio_pci.c
> > > index 32b88bd..dbcad99 100644
> > > --- a/drivers/vfio/pci/vfio_pci.c
> > > +++ b/drivers/vfio/pci/vfio_pci.c
> > > @@ -443,6 +443,9 @@ static long vfio_pci_ioctl(void *device_data,
> > >   if (vdev->reset_works)
> > >   info.flags |= VFIO_DEVICE_FLAGS_RESET;
> > >   
> > > + if (vfio_pci_bar_page_aligned())
> > > + info.flags |=
> > > VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED;
> > > +
> > >   info.num_regions = VFIO_PCI_NUM_REGIONS;
> > >   info.num_irqs = VFIO_PCI_NUM_IRQS;
> > >   
> > > @@ -479,7 +482,8 @@ static long vfio_pci_ioctl(void *device_data,
> > >    VFIO_REGION_INFO_FLAG_WRIT
> > > E;
> > >   if (IS_ENABLED(CONFIG_VFIO_PCI_MMAP) &&
> > >   pci_resource_flags(pdev,
> > > info.index) &
> > > - IORESOURCE_MEM && info.size >=
> > > PAGE_SIZE)
> > > + IORESOURCE_MEM && (info.size >=
> > > PAGE_SIZE ||
> > > + vfio_pci_bar_page_aligned()))
> > >   info.flags |=
> > > VFIO_REGION_INFO_FLAG_MMAP;
> > >   break;
> > >   case VFIO_PCI_ROM_REGION_INDEX:
> > > @@ -855,6 +859,10 @@ static int vfio_pci_mmap(void *device_data,
> > > struct vm_area_struct *vma)
> > >   return -EINVAL;
> > >   
> > >   phys_len = pci_resource_len(pdev, index);
> > > +
> > > + if (vfio_pci_bar_page_aligned())
> > > + phys_len = PAGE_ALIGN(phys_len);
> > > +
> > >   req_len = vma->vm_end - vma->vm_start;
> > >   pgoff = vma->vm_pgoff &
> > >   ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) -
> > > 1);
> > > diff --git a/drivers/vfio/pci/vfio_pci_private.h
> > > b/drivers/vfio/pci/vfio_pci_private.h
> > > index 0e7394f..319352a 100644
> > > --- a/drivers/vfio/pci/vfio_pci_private.h
> > > +++ b/drivers/vfio/pci/vfio_pci_private.h
> > > @@ -69,6 +69,11 @@ struct vfio_pci_device {
> > >   #define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) ||
> > > is_msix(vdev)))
> > >   #define irq_is(vdev, type) (vdev->irq_type == type)
> > >   
> > > +static inline bool vfio_pci_bar_page_aligned(void)
> > > +{
> > > + return IS_ENABLED(CONFIG_PPC64);
> > > +}
> > I really dislike this.  This is a problem for any architecture that
> > runs on larger pages, and even an annoyance on 4k hosts.  Why are
> > we
> > only solving it for PPC64?
> Yes, I know it's a problem for other architectures. But I'm not sure
> if 
> other archs prefer
> to enforce the alignment of all BARs to be at least PAGE_SIZE which 
> would result in
> some waste of address space.
> 
> So I just propose a prototype and add PPC64 support here. And other 
> archs could decide
> to use it or not by themselves.
> > Can't we do something similar in the core PCI code and detect it?
> So you mean we can do it like this:
> 
> diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
> index d390fc1..f46c04d 100644
> --- a/drivers/pci/pci.h
> +++ b/drivers/pci/pci.h
> @@ -320,6 +320,11 @@ static inline resource_size_t 
> pci_resource_alignment(struct pci_dev *dev,
>  return resource_alignment(res);
>   }
> 
> +static inline bool pci_bar_page_aligned(void)
> +{
> +   return IS_ENABLED(CONFIG_PPC64);
> +}
> +
>   void pci_enable_acs(struct pci_dev *dev);
> 
>   struct pci_dev_reset_methods {
> 
> or add a config option to indicate that PCI MMIO BARs should be page 
> aligned? 

Yes, I'm thinking of a boot commandline option, maybe one that PPC64
can default to enabled if it chooses to.  The problem is not unique to
PPC64 and the solution should not be unique either.  I don't want to
need to revisit this for ARM, which we know is going to be similarly
afflicted.  Thanks,

Alex
--
To unsubscribe from this

Re: [RFC PATCH 2/3] vfio-pci: Allow to mmap sub-page MMIO BARs if all MMIO BARs are page aligned

2015-12-16 Thread Alex Williamson

On Fri, 2015-12-11 at 16:53 +0800, Yongji Xie wrote:
> Current vfio-pci implementation disallows to mmap
> sub-page(size < PAGE_SIZE) MMIO BARs because these BARs' mmio page
> may be shared with other BARs.
> 
> But we should allow to mmap these sub-page MMIO BARs if all MMIO BARs
> are page aligned which leads the BARs' mmio page would not be shared
> with other BARs.
> 
> This patch adds support for this case and we also add a
> VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED flag to notify userspace that
> platform supports all MMIO BARs to be page aligned.
> 
> Signed-off-by: Yongji Xie 
> ---
>  drivers/vfio/pci/vfio_pci.c |   10 +-
>  drivers/vfio/pci/vfio_pci_private.h |5 +
>  include/uapi/linux/vfio.h   |2 ++
>  3 files changed, 16 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/vfio/pci/vfio_pci.c
> b/drivers/vfio/pci/vfio_pci.c
> index 32b88bd..dbcad99 100644
> --- a/drivers/vfio/pci/vfio_pci.c
> +++ b/drivers/vfio/pci/vfio_pci.c
> @@ -443,6 +443,9 @@ static long vfio_pci_ioctl(void *device_data,
>   if (vdev->reset_works)
>   info.flags |= VFIO_DEVICE_FLAGS_RESET;
>  
> + if (vfio_pci_bar_page_aligned())
> + info.flags |=
> VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED;
> +
>   info.num_regions = VFIO_PCI_NUM_REGIONS;
>   info.num_irqs = VFIO_PCI_NUM_IRQS;
>  
> @@ -479,7 +482,8 @@ static long vfio_pci_ioctl(void *device_data,
>    VFIO_REGION_INFO_FLAG_WRITE;
>   if (IS_ENABLED(CONFIG_VFIO_PCI_MMAP) &&
>   pci_resource_flags(pdev, info.index) &
> - IORESOURCE_MEM && info.size >=
> PAGE_SIZE)
> + IORESOURCE_MEM && (info.size >=
> PAGE_SIZE ||
> + vfio_pci_bar_page_aligned()))
>   info.flags |=
> VFIO_REGION_INFO_FLAG_MMAP;
>   break;
>   case VFIO_PCI_ROM_REGION_INDEX:
> @@ -855,6 +859,10 @@ static int vfio_pci_mmap(void *device_data,
> struct vm_area_struct *vma)
>   return -EINVAL;
>  
>   phys_len = pci_resource_len(pdev, index);
> +
> + if (vfio_pci_bar_page_aligned())
> + phys_len = PAGE_ALIGN(phys_len);
> +
>   req_len = vma->vm_end - vma->vm_start;
>   pgoff = vma->vm_pgoff &
>   ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
> diff --git a/drivers/vfio/pci/vfio_pci_private.h
> b/drivers/vfio/pci/vfio_pci_private.h
> index 0e7394f..319352a 100644
> --- a/drivers/vfio/pci/vfio_pci_private.h
> +++ b/drivers/vfio/pci/vfio_pci_private.h
> @@ -69,6 +69,11 @@ struct vfio_pci_device {
>  #define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) ||
> is_msix(vdev)))
>  #define irq_is(vdev, type) (vdev->irq_type == type)
>  
> +static inline bool vfio_pci_bar_page_aligned(void)
> +{
> + return IS_ENABLED(CONFIG_PPC64);
> +}

I really dislike this.  This is a problem for any architecture that
runs on larger pages, and even an annoyance on 4k hosts.  Why are we
only solving it for PPC64?  Can't we do something similar in the core
PCI code and detect it?

> +
>  extern void vfio_pci_intx_mask(struct vfio_pci_device *vdev);
>  extern void vfio_pci_intx_unmask(struct vfio_pci_device *vdev);
>  
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 751b69f..1fc8066 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -171,6 +171,8 @@ struct vfio_device_info {
>  #define VFIO_DEVICE_FLAGS_PCI(1 << 1)/* vfio-pci
> device */
>  #define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2)  /* vfio-platform
> device */
>  #define VFIO_DEVICE_FLAGS_AMBA  (1 << 3) /* vfio-amba device
> */
> +/* Platform support all PCI MMIO BARs to be page aligned */
> +#define VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED   (1 << 4)
>   __u32   num_regions;/* Max region index + 1 */
>   __u32   num_irqs;   /* Max IRQ index + 1 */
>  };

Why is this on the device info, shouldn't it be per region?  Do we even
need a flag or can we just set the existing mmap flag with the
clarification that sub-host page size regions can mmap an entire host-
page aligned, sized area in the documentation?  Thanks,

Alex
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[RFC PATCH 2/3] vfio-pci: Allow to mmap sub-page MMIO BARs if all MMIO BARs are page aligned

2015-12-11 Thread Yongji Xie

Current vfio-pci implementation disallows to mmap
sub-page(size < PAGE_SIZE) MMIO BARs because these BARs' mmio page
may be shared with other BARs.

But we should allow to mmap these sub-page MMIO BARs if all MMIO BARs
are page aligned which leads the BARs' mmio page would not be shared
with other BARs.

This patch adds support for this case and we also add a
VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED flag to notify userspace that
platform supports all MMIO BARs to be page aligned.

Signed-off-by: Yongji Xie 
---
 drivers/vfio/pci/vfio_pci.c |   10 +-
 drivers/vfio/pci/vfio_pci_private.h |5 +
 include/uapi/linux/vfio.h   |2 ++
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 32b88bd..dbcad99 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -443,6 +443,9 @@ static long vfio_pci_ioctl(void *device_data,
if (vdev->reset_works)
info.flags |= VFIO_DEVICE_FLAGS_RESET;
 
+   if (vfio_pci_bar_page_aligned())
+   info.flags |= VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED;
+
info.num_regions = VFIO_PCI_NUM_REGIONS;
info.num_irqs = VFIO_PCI_NUM_IRQS;
 
@@ -479,7 +482,8 @@ static long vfio_pci_ioctl(void *device_data,
 VFIO_REGION_INFO_FLAG_WRITE;
if (IS_ENABLED(CONFIG_VFIO_PCI_MMAP) &&
pci_resource_flags(pdev, info.index) &
-   IORESOURCE_MEM && info.size >= PAGE_SIZE)
+   IORESOURCE_MEM && (info.size >= PAGE_SIZE ||
+   vfio_pci_bar_page_aligned()))
info.flags |= VFIO_REGION_INFO_FLAG_MMAP;
break;
case VFIO_PCI_ROM_REGION_INDEX:
@@ -855,6 +859,10 @@ static int vfio_pci_mmap(void *device_data, struct 
vm_area_struct *vma)
return -EINVAL;
 
phys_len = pci_resource_len(pdev, index);
+
+   if (vfio_pci_bar_page_aligned())
+   phys_len = PAGE_ALIGN(phys_len);
+
req_len = vma->vm_end - vma->vm_start;
pgoff = vma->vm_pgoff &
((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
diff --git a/drivers/vfio/pci/vfio_pci_private.h 
b/drivers/vfio/pci/vfio_pci_private.h
index 0e7394f..319352a 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -69,6 +69,11 @@ struct vfio_pci_device {
 #define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev)))
 #define irq_is(vdev, type) (vdev->irq_type == type)
 
+static inline bool vfio_pci_bar_page_aligned(void)
+{
+   return IS_ENABLED(CONFIG_PPC64);
+}
+
 extern void vfio_pci_intx_mask(struct vfio_pci_device *vdev);
 extern void vfio_pci_intx_unmask(struct vfio_pci_device *vdev);
 
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 751b69f..1fc8066 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -171,6 +171,8 @@ struct vfio_device_info {
 #define VFIO_DEVICE_FLAGS_PCI  (1 << 1)/* vfio-pci device */
 #define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2)/* vfio-platform device */
 #define VFIO_DEVICE_FLAGS_AMBA  (1 << 3)   /* vfio-amba device */
+/* Platform support all PCI MMIO BARs to be page aligned */
+#define VFIO_DEVICE_FLAGS_PCI_PAGE_ALIGNED (1 << 4)
__u32   num_regions;/* Max region index + 1 */
__u32   num_irqs;   /* Max IRQ index + 1 */
 };
-- 
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [RFC PATCH 2/3] vfio-pci: Allow to mmap sub-page MMIO BARs if all MMIO BARs are page aligned

Re: [RFC PATCH 2/3] vfio-pci: Allow to mmap sub-page MMIO BARs if all MMIO BARs are page aligned

Re: [RFC PATCH 2/3] vfio-pci: Allow to mmap sub-page MMIO BARs if all MMIO BARs are page aligned

Re: [RFC PATCH 2/3] vfio-pci: Allow to mmap sub-page MMIO BARs if all MMIO BARs are page aligned

[RFC PATCH 2/3] vfio-pci: Allow to mmap sub-page MMIO BARs if all MMIO BARs are page aligned

5 matches

Site Navigation

Mail list logo

Footer information