[PATCH RFC 0/5] virtio pci: virtio 1.0 support

[PATCH RFC 0/5] virtio pci: virtio 1.0 support

[Michael S. Tsirkin]

This is on top of 3.19 master + my bugfix patches, and adds virtio 1.0 support
to virtio pci.
This is 3.20 material I think.

Would like to get feedback on s390 change as it's untested.

Michael S Tsirkin (2):
  pci: add pci_iomap_range
  s390: add pci_iomap_range

Michael S. Tsirkin (2):
  virtio_pci: modern driver
  virtio_pci: macros for PCI layout offsets.

Rusty Russell (1):
  virtio-pci: define layout for virtio 1.0

 arch/s390/include/asm/pci_io.h     |   1 +
 drivers/virtio/virtio_pci_common.h |  29 +-
 include/asm-generic/pci_iomap.h    |  10 +
 include/uapi/linux/virtio_pci.h    |  92 +++++
 tools/virtio/linux/virtio_config.h |  45 +++
 arch/s390/pci/pci.c                |  34 +-
 drivers/virtio/virtio_pci_common.c |  13 +-
 drivers/virtio/virtio_pci_modern.c | 684 +++++++++++++++++++++++++++++++++++++
 lib/pci_iomap.c                    |  35 +-
 tools/virtio/virtio_test.c         |   1 +
 drivers/virtio/Makefile            |   2 +-
 11 files changed, 929 insertions(+), 17 deletions(-)
 create mode 100644 drivers/virtio/virtio_pci_modern.c

-- 
MST

[PATCH RFC 1/5] pci: add pci_iomap_range

[Michael S. Tsirkin]

From: Michael S Tsirkin <mst@redhat.com>

Virtio drivers should map the part of the BAR they need, not necessarily
all of it.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/asm-generic/pci_iomap.h | 10 ++++++++++
 lib/pci_iomap.c                 | 35 ++++++++++++++++++++++++++++++-----
 2 files changed, 40 insertions(+), 5 deletions(-)

diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h
index ce37349..7389c87 100644
--- a/include/asm-generic/pci_iomap.h
+++ b/include/asm-generic/pci_iomap.h
@@ -15,6 +15,9 @@ struct pci_dev;
 #ifdef CONFIG_PCI
 /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
 extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
+				     unsigned long offset,
+				     unsigned long maxlen);
 /* Create a virtual mapping cookie for a port on a given PCI device.
  * Do not call this directly, it exists to make it easier for architectures
  * to override */
@@ -30,6 +33,13 @@ static inline void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned lon
 {
 	return NULL;
 }
+
+static inline void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
+					    unsigned long offset,
+					    unsigned long maxlen)
+{
+	return NULL;
+}
 #endif
 
 #endif /* __ASM_GENERIC_IO_H */
diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c
index 0d83ea8..bcce5f1 100644
--- a/lib/pci_iomap.c
+++ b/lib/pci_iomap.c
@@ -10,10 +10,11 @@
 
 #ifdef CONFIG_PCI
 /**
- * pci_iomap - create a virtual mapping cookie for a PCI BAR
+ * pci_iomap_range - create a virtual mapping cookie for a PCI BAR
  * @dev: PCI device that owns the BAR
  * @bar: BAR number
- * @maxlen: length of the memory to map
+ * @offset: map memory at the given offset in BAR
+ * @maxlen: max length of the memory to map
  *
  * Using this function you will get a __iomem address to your device BAR.
  * You can access it using ioread*() and iowrite*(). These functions hide
@@ -21,16 +22,21 @@
  * you expect from them in the correct way.
  *
  * @maxlen specifies the maximum length to map. If you want to get access to
- * the complete BAR without checking for its length first, pass %0 here.
+ * the complete BAR from offset to the end, pass %0 here.
  * */
-void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
+void __iomem *pci_iomap_range(struct pci_dev *dev,
+			      int bar,
+			      unsigned long offset,
+			      unsigned long maxlen)
 {
 	resource_size_t start = pci_resource_start(dev, bar);
 	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
-	if (!len || !start)
+	if (len <= offset || !start)
 		return NULL;
+	len -= offset;
+	start += offset;
 	if (maxlen && len > maxlen)
 		len = maxlen;
 	if (flags & IORESOURCE_IO)
@@ -43,6 +49,25 @@ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 	/* What? */
 	return NULL;
 }
+EXPORT_SYMBOL(pci_iomap_range);
 
+/**
+ * pci_iomap - create a virtual mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @maxlen: length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR without checking for its length first, pass %0 here.
+ * */
+void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+	return pci_iomap_range(dev, bar, 0, maxlen);
+}
 EXPORT_SYMBOL(pci_iomap);
 #endif /* CONFIG_PCI */
-- 
MST

[PATCH RFC 2/5] s390: add pci_iomap_range

[Michael S. Tsirkin]

From: Michael S Tsirkin <mst@redhat.com>

Virtio drivers should map the part of the range they need, not
necessarily all of it.
To this end, support mapping ranges within BAR on s390.
Since multiple ranges can now be mapped within a BAR, we keep track of
the number of mappings created, and only clear out the mapping for a BAR
when this number reaches 0.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 arch/s390/include/asm/pci_io.h |  1 +
 arch/s390/pci/pci.c            | 34 +++++++++++++++++++++++++++-------
 2 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index d194d54..25228b3 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -16,6 +16,7 @@
 struct zpci_iomap_entry {
 	u32 fh;
 	u8 bar;
+	u16 count;
 };
 
 extern struct zpci_iomap_entry *zpci_iomap_start;
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 2fa7b14..51cb653 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -259,7 +259,10 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
 }
 
 /* Create a virtual mapping cookie for a PCI BAR */
-void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max)
+void __iomem *pci_iomap_range(struct pci_dev *pdev,
+			      int bar,
+			      unsigned long offset,
+			      unsigned long max)
 {
 	struct zpci_dev *zdev =	get_zdev(pdev);
 	u64 addr;
@@ -270,14 +273,27 @@ void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max)
 
 	idx = zdev->bars[bar].map_idx;
 	spin_lock(&zpci_iomap_lock);
-	zpci_iomap_start[idx].fh = zdev->fh;
-	zpci_iomap_start[idx].bar = bar;
+	if (zpci_iomap_start[idx].count++) {
+		BUG_ON(zpci_iomap_start[idx].fh != zdev->fh ||
+		       zpci_iomap_start[idx].bar != bar);
+	} else {
+		zpci_iomap_start[idx].fh = zdev->fh;
+		zpci_iomap_start[idx].bar = bar;
+	}
+	/* Detect overrun */
+	BUG_ON(!zpci_iomap_start[idx].count);
 	spin_unlock(&zpci_iomap_lock);
 
 	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
-	return (void __iomem *) addr;
+	return (void __iomem *) addr + offset;
 }
-EXPORT_SYMBOL_GPL(pci_iomap);
+EXPORT_SYMBOL_GPL(pci_iomap_range);
+
+void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+	return pci_iomap_range(dev, bar, 0, maxlen);
+}
+EXPORT_SYMBOL(pci_iomap);
 
 void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
 {
@@ -285,8 +301,12 @@ void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
 
 	idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48;
 	spin_lock(&zpci_iomap_lock);
-	zpci_iomap_start[idx].fh = 0;
-	zpci_iomap_start[idx].bar = 0;
+	/* Detect underrun */
+	BUG_ON(!zpci_iomap_start[idx].count);
+	if (!--zpci_iomap_start[idx].count) {
+		zpci_iomap_start[idx].fh = 0;
+		zpci_iomap_start[idx].bar = 0;
+	}
 	spin_unlock(&zpci_iomap_lock);
 }
 EXPORT_SYMBOL_GPL(pci_iounmap);
-- 
MST

Re: [PATCH RFC 2/5] s390: add pci_iomap_range

[Sebastian Ott]

On Mon, 15 Dec 2014, Michael S. Tsirkin wrote:
> From: Michael S Tsirkin <mst@redhat.com>
> 
> Virtio drivers should map the part of the range they need, not
> necessarily all of it.
> To this end, support mapping ranges within BAR on s390.
> Since multiple ranges can now be mapped within a BAR, we keep track of
> the number of mappings created, and only clear out the mapping for a BAR
> when this number reaches 0.
> 

I can't say much about the users of this interface but in principle I'm
OK with such a change.

> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> ---
>  arch/s390/include/asm/pci_io.h |  1 +
>  arch/s390/pci/pci.c            | 34 +++++++++++++++++++++++++++-------
>  2 files changed, 28 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
> index d194d54..25228b3 100644
> --- a/arch/s390/include/asm/pci_io.h
> +++ b/arch/s390/include/asm/pci_io.h
> @@ -16,6 +16,7 @@
>  struct zpci_iomap_entry {
>  	u32 fh;
>  	u8 bar;
> +	u16 count;
>  };
> 
>  extern struct zpci_iomap_entry *zpci_iomap_start;
> diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
> index 2fa7b14..51cb653 100644
> --- a/arch/s390/pci/pci.c
> +++ b/arch/s390/pci/pci.c
> @@ -259,7 +259,10 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
>  }
> 
>  /* Create a virtual mapping cookie for a PCI BAR */
> -void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max)
> +void __iomem *pci_iomap_range(struct pci_dev *pdev,
> +			      int bar,
> +			      unsigned long offset,
> +			      unsigned long max)
>  {
>  	struct zpci_dev *zdev =	get_zdev(pdev);
>  	u64 addr;
> @@ -270,14 +273,27 @@ void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max)
> 
>  	idx = zdev->bars[bar].map_idx;
>  	spin_lock(&zpci_iomap_lock);
> -	zpci_iomap_start[idx].fh = zdev->fh;
> -	zpci_iomap_start[idx].bar = bar;
> +	if (zpci_iomap_start[idx].count++) {
> +		BUG_ON(zpci_iomap_start[idx].fh != zdev->fh ||
> +		       zpci_iomap_start[idx].bar != bar);
> +	} else {
> +		zpci_iomap_start[idx].fh = zdev->fh;
> +		zpci_iomap_start[idx].bar = bar;
> +	}
> +	/* Detect overrun */
> +	BUG_ON(!zpci_iomap_start[idx].count);
>  	spin_unlock(&zpci_iomap_lock);
> 
>  	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
> -	return (void __iomem *) addr;
> +	return (void __iomem *) addr + offset;
>  }
> -EXPORT_SYMBOL_GPL(pci_iomap);
> +EXPORT_SYMBOL_GPL(pci_iomap_range);
> +
> +void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
> +{
> +	return pci_iomap_range(dev, bar, 0, maxlen);
> +}
> +EXPORT_SYMBOL(pci_iomap);

This was EXPORT_SYMBOL_GPL. I guess, for this patch, it should stay that
way. ...Hm, everyone else has this stuff as EXPORT_SYMBOL looks like we
should use that too.

Regards,
Sebastian

> 
>  void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
>  {
> @@ -285,8 +301,12 @@ void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
> 
>  	idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48;
>  	spin_lock(&zpci_iomap_lock);
> -	zpci_iomap_start[idx].fh = 0;
> -	zpci_iomap_start[idx].bar = 0;
> +	/* Detect underrun */
> +	BUG_ON(!zpci_iomap_start[idx].count);
> +	if (!--zpci_iomap_start[idx].count) {
> +		zpci_iomap_start[idx].fh = 0;
> +		zpci_iomap_start[idx].bar = 0;
> +	}
>  	spin_unlock(&zpci_iomap_lock);
>  }
>  EXPORT_SYMBOL_GPL(pci_iounmap);
> -- 
> MST
> 
> 

Re: [PATCH RFC 2/5] s390: add pci_iomap_range

[Michael S. Tsirkin]

On Fri, Dec 19, 2014 at 03:13:37PM +0100, Sebastian Ott wrote:
> On Mon, 15 Dec 2014, Michael S. Tsirkin wrote:
> > From: Michael S Tsirkin <mst@redhat.com>
> > 
> > Virtio drivers should map the part of the range they need, not
> > necessarily all of it.
> > To this end, support mapping ranges within BAR on s390.
> > Since multiple ranges can now be mapped within a BAR, we keep track of
> > the number of mappings created, and only clear out the mapping for a BAR
> > when this number reaches 0.
> > 
> 
> I can't say much about the users of this interface but in principle I'm
> OK with such a change.

I don't have an s390 system with pci for testing - could you help me out
by testing this and confirming it doesn't break things?

> > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> > ---
> >  arch/s390/include/asm/pci_io.h |  1 +
> >  arch/s390/pci/pci.c            | 34 +++++++++++++++++++++++++++-------
> >  2 files changed, 28 insertions(+), 7 deletions(-)
> > 
> > diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
> > index d194d54..25228b3 100644
> > --- a/arch/s390/include/asm/pci_io.h
> > +++ b/arch/s390/include/asm/pci_io.h
> > @@ -16,6 +16,7 @@
> >  struct zpci_iomap_entry {
> >  	u32 fh;
> >  	u8 bar;
> > +	u16 count;
> >  };
> > 
> >  extern struct zpci_iomap_entry *zpci_iomap_start;
> > diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
> > index 2fa7b14..51cb653 100644
> > --- a/arch/s390/pci/pci.c
> > +++ b/arch/s390/pci/pci.c
> > @@ -259,7 +259,10 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
> >  }
> > 
> >  /* Create a virtual mapping cookie for a PCI BAR */
> > -void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max)
> > +void __iomem *pci_iomap_range(struct pci_dev *pdev,
> > +			      int bar,
> > +			      unsigned long offset,
> > +			      unsigned long max)
> >  {
> >  	struct zpci_dev *zdev =	get_zdev(pdev);
> >  	u64 addr;
> > @@ -270,14 +273,27 @@ void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max)
> > 
> >  	idx = zdev->bars[bar].map_idx;
> >  	spin_lock(&zpci_iomap_lock);
> > -	zpci_iomap_start[idx].fh = zdev->fh;
> > -	zpci_iomap_start[idx].bar = bar;
> > +	if (zpci_iomap_start[idx].count++) {
> > +		BUG_ON(zpci_iomap_start[idx].fh != zdev->fh ||
> > +		       zpci_iomap_start[idx].bar != bar);
> > +	} else {
> > +		zpci_iomap_start[idx].fh = zdev->fh;
> > +		zpci_iomap_start[idx].bar = bar;
> > +	}
> > +	/* Detect overrun */
> > +	BUG_ON(!zpci_iomap_start[idx].count);
> >  	spin_unlock(&zpci_iomap_lock);
> > 
> >  	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
> > -	return (void __iomem *) addr;
> > +	return (void __iomem *) addr + offset;
> >  }
> > -EXPORT_SYMBOL_GPL(pci_iomap);
> > +EXPORT_SYMBOL_GPL(pci_iomap_range);
> > +
> > +void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
> > +{
> > +	return pci_iomap_range(dev, bar, 0, maxlen);
> > +}
> > +EXPORT_SYMBOL(pci_iomap);
> 
> This was EXPORT_SYMBOL_GPL. I guess, for this patch, it should stay that
> way. ...Hm, everyone else has this stuff as EXPORT_SYMBOL looks like we
> should use that too.
> 
> Regards,
> Sebastian

OK, so you want two patches: one with new functionality,
one switching to EXPORT_SYMBOL?


> > 
> >  void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
> >  {
> > @@ -285,8 +301,12 @@ void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
> > 
> >  	idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48;
> >  	spin_lock(&zpci_iomap_lock);
> > -	zpci_iomap_start[idx].fh = 0;
> > -	zpci_iomap_start[idx].bar = 0;
> > +	/* Detect underrun */
> > +	BUG_ON(!zpci_iomap_start[idx].count);
> > +	if (!--zpci_iomap_start[idx].count) {
> > +		zpci_iomap_start[idx].fh = 0;
> > +		zpci_iomap_start[idx].bar = 0;
> > +	}
> >  	spin_unlock(&zpci_iomap_lock);
> >  }
> >  EXPORT_SYMBOL_GPL(pci_iounmap);
> > -- 
> > MST
> > 
> > 

Re: [PATCH RFC 2/5] s390: add pci_iomap_range

[Sebastian Ott]

On Fri, 19 Dec 2014, Michael S. Tsirkin wrote:
> On Fri, Dec 19, 2014 at 03:13:37PM +0100, Sebastian Ott wrote:
> > On Mon, 15 Dec 2014, Michael S. Tsirkin wrote:
> > > From: Michael S Tsirkin <mst@redhat.com>
> > > 
> > > Virtio drivers should map the part of the range they need, not
> > > necessarily all of it.
> > > To this end, support mapping ranges within BAR on s390.
> > > Since multiple ranges can now be mapped within a BAR, we keep track of
> > > the number of mappings created, and only clear out the mapping for a BAR
> > > when this number reaches 0.
> > > 
> > 
> > I can't say much about the users of this interface but in principle I'm
> > OK with such a change.
> 
> I don't have an s390 system with pci for testing - could you help me out
> by testing this and confirming it doesn't break things?

I did some minor tests and nothing broke...

> 
> > > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> > > ---
> > >  arch/s390/include/asm/pci_io.h |  1 +
> > >  arch/s390/pci/pci.c            | 34 +++++++++++++++++++++++++++-------
> > >  2 files changed, 28 insertions(+), 7 deletions(-)
> > > 
> > > diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
> > > index d194d54..25228b3 100644
> > > --- a/arch/s390/include/asm/pci_io.h
> > > +++ b/arch/s390/include/asm/pci_io.h
> > > @@ -16,6 +16,7 @@
> > >  struct zpci_iomap_entry {
> > >  	u32 fh;
> > >  	u8 bar;
> > > +	u16 count;
> > >  };
> > > 
> > >  extern struct zpci_iomap_entry *zpci_iomap_start;
> > > diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
> > > index 2fa7b14..51cb653 100644
> > > --- a/arch/s390/pci/pci.c
> > > +++ b/arch/s390/pci/pci.c
> > > @@ -259,7 +259,10 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
> > >  }
> > > 
> > >  /* Create a virtual mapping cookie for a PCI BAR */
> > > -void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max)
> > > +void __iomem *pci_iomap_range(struct pci_dev *pdev,
> > > +			      int bar,
> > > +			      unsigned long offset,
> > > +			      unsigned long max)
> > >  {
> > >  	struct zpci_dev *zdev =	get_zdev(pdev);
> > >  	u64 addr;
> > > @@ -270,14 +273,27 @@ void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max)
> > > 
> > >  	idx = zdev->bars[bar].map_idx;
> > >  	spin_lock(&zpci_iomap_lock);
> > > -	zpci_iomap_start[idx].fh = zdev->fh;
> > > -	zpci_iomap_start[idx].bar = bar;
> > > +	if (zpci_iomap_start[idx].count++) {
> > > +		BUG_ON(zpci_iomap_start[idx].fh != zdev->fh ||
> > > +		       zpci_iomap_start[idx].bar != bar);
> > > +	} else {
> > > +		zpci_iomap_start[idx].fh = zdev->fh;
> > > +		zpci_iomap_start[idx].bar = bar;
> > > +	}
> > > +	/* Detect overrun */
> > > +	BUG_ON(!zpci_iomap_start[idx].count);
> > >  	spin_unlock(&zpci_iomap_lock);
> > > 
> > >  	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
> > > -	return (void __iomem *) addr;
> > > +	return (void __iomem *) addr + offset;
> > >  }
> > > -EXPORT_SYMBOL_GPL(pci_iomap);
> > > +EXPORT_SYMBOL_GPL(pci_iomap_range);
> > > +
> > > +void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
> > > +{
> > > +	return pci_iomap_range(dev, bar, 0, maxlen);
> > > +}
> > > +EXPORT_SYMBOL(pci_iomap);
> > 
> > This was EXPORT_SYMBOL_GPL. I guess, for this patch, it should stay that
> > way. ...Hm, everyone else has this stuff as EXPORT_SYMBOL looks like we
> > should use that too.
> > 
> > Regards,
> > Sebastian
> 
> OK, so you want two patches: one with new functionality,
> one switching to EXPORT_SYMBOL?

Either that or at least add a note in the patch description.

Regards,
Sebastian

> 
> 
> > > 
> > >  void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
> > >  {
> > > @@ -285,8 +301,12 @@ void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
> > > 
> > >  	idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48;
> > >  	spin_lock(&zpci_iomap_lock);
> > > -	zpci_iomap_start[idx].fh = 0;
> > > -	zpci_iomap_start[idx].bar = 0;
> > > +	/* Detect underrun */
> > > +	BUG_ON(!zpci_iomap_start[idx].count);
> > > +	if (!--zpci_iomap_start[idx].count) {
> > > +		zpci_iomap_start[idx].fh = 0;
> > > +		zpci_iomap_start[idx].bar = 0;
> > > +	}
> > >  	spin_unlock(&zpci_iomap_lock);
> > >  }
> > >  EXPORT_SYMBOL_GPL(pci_iounmap);
> > > -- 
> > > MST
> > > 
> > > 
> 
> 

[PATCH RFC 3/5] virtio-pci: define layout for virtio 1.0

[Michael S. Tsirkin]

From: Rusty Russell <rusty@rustcorp.com.au>

Based on patches by Michael S. Tsirkin <mst@redhat.com>, but I found it
hard to follow so changed to use structures which are more
self-documenting.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/uapi/linux/virtio_pci.h | 62 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 35b552c..28c2ce0 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -99,4 +99,66 @@
 /* Vector value used to disable MSI for queue */
 #define VIRTIO_MSI_NO_VECTOR            0xffff
 
+#ifndef VIRTIO_PCI_NO_MODERN
+
+/* IDs for different capabilities.  Must all exist. */
+
+/* Common configuration */
+#define VIRTIO_PCI_CAP_COMMON_CFG	1
+/* Notifications */
+#define VIRTIO_PCI_CAP_NOTIFY_CFG	2
+/* ISR access */
+#define VIRTIO_PCI_CAP_ISR_CFG		3
+/* Device specific confiuration */
+#define VIRTIO_PCI_CAP_DEVICE_CFG	4
+
+/* This is the PCI capability header: */
+struct virtio_pci_cap {
+	__u8 cap_vndr;		/* Generic PCI field: PCI_CAP_ID_VNDR */
+	__u8 cap_next;		/* Generic PCI field: next ptr. */
+	__u8 cap_len;		/* Generic PCI field: capability length */
+	__u8 type_and_bar;	/* Upper 3 bits: bar.
+				 * Lower 3 is VIRTIO_PCI_CAP_*_CFG. */
+	__le32 offset;		/* Offset within bar. */
+	__le32 length;		/* Length. */
+};
+
+#define VIRTIO_PCI_CAP_BAR_SHIFT	5
+#define VIRTIO_PCI_CAP_BAR_MASK		0x7
+#define VIRTIO_PCI_CAP_TYPE_SHIFT	0
+#define VIRTIO_PCI_CAP_TYPE_MASK	0x7
+
+struct virtio_pci_notify_cap {
+	struct virtio_pci_cap cap;
+	__le32 notify_off_multiplier;	/* Multiplier for queue_notify_off. */
+};
+
+/* Fields in VIRTIO_PCI_CAP_COMMON_CFG: */
+struct virtio_pci_common_cfg {
+	/* About the whole device. */
+	__le32 device_feature_select;	/* read-write */
+	__le32 device_feature;		/* read-only */
+	__le32 guest_feature_select;	/* read-write */
+	__le32 guest_feature;		/* read-write */
+	__le16 msix_config;		/* read-write */
+	__le16 num_queues;		/* read-only */
+	__u8 device_status;		/* read-write */
+	__u8 config_generation;		/* read-only */
+
+	/* About a specific virtqueue. */
+	__le16 queue_select;		/* read-write */
+	__le16 queue_size;		/* read-write, power of 2. */
+	__le16 queue_msix_vector;	/* read-write */
+	__le16 queue_enable;		/* read-write */
+	__le16 queue_notify_off;	/* read-only */
+	__le32 queue_desc_lo;		/* read-write */
+	__le32 queue_desc_hi;		/* read-write */
+	__le32 queue_avail_lo;		/* read-write */
+	__le32 queue_avail_hi;		/* read-write */
+	__le32 queue_used_lo;		/* read-write */
+	__le32 queue_used_hi;		/* read-write */
+};
+
+#endif /* VIRTIO_PCI_NO_MODERN */
+
 #endif
-- 
MST

[PATCH RFC 4/5] virtio_pci: modern driver

[Michael S. Tsirkin]

It compiles! Must be perfect.

One thing *not* implemented here is separate mappings
for descriptor/avail/used rings. That's nice to have,
will be done later after we have core support.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_pci_common.h |  29 +-
 tools/virtio/linux/virtio_config.h |  45 +++
 drivers/virtio/virtio_pci_common.c |  13 +-
 drivers/virtio/virtio_pci_modern.c | 621 +++++++++++++++++++++++++++++++++++++
 tools/virtio/virtio_test.c         |   1 +
 drivers/virtio/Makefile            |   2 +-
 6 files changed, 706 insertions(+), 5 deletions(-)
 create mode 100644 drivers/virtio/virtio_pci_modern.c

diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index adddb64..1584833 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -53,12 +53,32 @@ struct virtio_pci_device {
 	struct virtio_device vdev;
 	struct pci_dev *pci_dev;
 
+	/* In legacy mode, these two point to within ->legacy. */
+	/* Where to read and clear interrupt */
+	u8 __iomem *isr;
+
+	/* Modern only fields */
+	/* The IO mapping for the PCI config space (non-legacy mode) */
+	struct virtio_pci_common_cfg __iomem *common;
+	/* Device-specific data (non-legacy mode)  */
+	void __iomem *device;
+	/* Base of vq notifications (non-legacy mode). */
+	void __iomem *notify_base;
+
+	/* So we can sanity-check accesses. */
+	size_t notify_len;
+	size_t device_len;
+
+	/* Capability for when we need to map notifications per-vq. */
+	int notify_map_cap;
+
+	/* Multiply queue_notify_off by this value. (non-legacy mode). */
+	u32 notify_offset_multiplier;
+
+	/* Legacy only field */
 	/* the IO mapping for the PCI config space */
 	void __iomem *ioaddr;
 
-	/* the IO mapping for ISR operation */
-	void __iomem *isr;
-
 	/* a list of queues so we can dispatch IRQs */
 	spinlock_t lock;
 	struct list_head virtqueues;
@@ -131,5 +151,8 @@ void virtio_pci_release_dev(struct device *);
 int virtio_pci_legacy_probe(struct pci_dev *pci_dev,
 			    const struct pci_device_id *id);
 void virtio_pci_legacy_remove(struct pci_dev *pci_dev);
+int virtio_pci_modern_probe(struct pci_dev *pci_dev,
+			    const struct pci_device_id *id);
+void virtio_pci_modern_remove(struct pci_dev *pci_dev);
 
 #endif
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index 83b27e8..dafe1c9 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -1,6 +1,51 @@
+#include <linux/virtio_byteorder.h>
+#include <linux/virtio.h>
+
 #define VIRTIO_TRANSPORT_F_START	28
 #define VIRTIO_TRANSPORT_F_END		32
+/*
+ * __virtio_test_bit - helper to test feature bits. For use by transports.
+ *                     Devices should normally use virtio_has_feature,
+ *                     which includes more checks.
+ * @vdev: the device
+ * @fbit: the feature bit
+ */
+static inline bool __virtio_test_bit(const struct virtio_device *vdev,
+				     unsigned int fbit)
+{
+	return vdev->features & (1ULL << fbit);
+}
 
 #define virtio_has_feature(dev, feature) \
 	(__virtio_test_bit((dev), feature))
 
+static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val)
+{
+	return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val)
+{
+	return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val)
+{
+	return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val)
+{
+	return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val)
+{
+	return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
+{
+	return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 59d3685..3821703 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -475,12 +475,23 @@ MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
 static int virtio_pci_probe(struct pci_dev *pci_dev,
 			    const struct pci_device_id *id)
 {
+	int rc;
+
+	rc = virtio_pci_modern_probe(pci_dev, id);
+	if (rc != -ENODEV)
+		return rc;
+
 	return virtio_pci_legacy_probe(pci_dev, id);
 }
 
 static void virtio_pci_remove(struct pci_dev *pci_dev)
 {
-     virtio_pci_legacy_remove(pci_dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+
+	if (vp_dev->ioaddr)
+	     virtio_pci_legacy_remove(pci_dev);
+	else
+	     virtio_pci_modern_remove(pci_dev);
 }
 
 static struct pci_driver virtio_pci_driver = {
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
new file mode 100644
index 0000000..636666c
--- /dev/null
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -0,0 +1,621 @@
+/*
+ * Virtio PCI driver - legacy device support
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ * Copyright Red Hat, Inc. 2014
+ *
+ * Authors:
+ *  Anthony Liguori  <aliguori@us.ibm.com>
+ *  Rusty Russell <rusty@rustcorp.com.au>
+ *  Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#define VIRTIO_PCI_NO_LEGACY
+#include "virtio_pci_common.h"
+
+static void __iomem *map_capability(struct pci_dev *dev, int off,
+				    size_t minlen,
+				    u32 align,
+				    u32 start, u32 size,
+				    size_t *len)
+{
+	u8 type_and_bar, bar;
+	u32 offset, length;
+	void __iomem *p;
+
+	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
+						 type_and_bar),
+			     &type_and_bar);
+	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
+			     &offset);
+	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
+			      &length);
+
+	if (length < minlen) {
+		dev_err(&dev->dev,
+			"virtio_pci: small capability len %u (%zu expected)\n",
+			length, minlen);
+		return NULL;
+	}
+
+	if (offset & (align - 1)) {
+		dev_err(&dev->dev,
+			"virtio_pci: offset %u not aligned to %u\n",
+			offset, align);
+		return NULL;
+	}
+
+	if (length > size)
+		length = size;
+
+	if (len)
+		*len = length;
+
+	bar = (type_and_bar >> VIRTIO_PCI_CAP_BAR_SHIFT) &
+		VIRTIO_PCI_CAP_BAR_MASK;
+
+	if (minlen + offset < minlen ||
+	    minlen + offset > pci_resource_len(dev, bar))
+		dev_err(&dev->dev,
+			"virtio_pci: map virtio %zu@%u "
+			"out of range on bar %i length %lu\n",
+			minlen, offset,
+			bar, (unsigned long)pci_resource_len(dev, bar));
+
+	p = pci_iomap_range(dev, bar, offset, length);
+	if (!p)
+		dev_err(&dev->dev,
+			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
+			length, offset, bar);
+	return p;
+}
+
+static void iowrite64_twopart(u64 val, __le32 __iomem *lo, __le32 __iomem *hi)
+{
+	iowrite32((u32)val, lo);
+	iowrite32(val >> 32, hi);
+}
+
+/* virtio config->get_features() implementation */
+static u64 vp_get_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	u64 features;
+
+	iowrite32(0, &vp_dev->common->device_feature_select);
+	features = ioread32(&vp_dev->common->device_feature);
+	iowrite32(1, &vp_dev->common->device_feature_select);
+	features |= ((u64)ioread32(&vp_dev->common->device_feature) << 32);
+
+	return features;
+}
+
+/* virtio config->finalize_features() implementation */
+static int vp_finalize_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	if (!__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) {
+		dev_err(&vdev->dev, "virtio: device uses modern interface "
+			"but does not have VIRTIO_F_VERSION_1\n");
+		return -EINVAL;
+	}
+
+	iowrite32(0, &vp_dev->common->guest_feature_select);
+	iowrite32((u32)vdev->features, &vp_dev->common->guest_feature);
+	iowrite32(1, &vp_dev->common->guest_feature_select);
+	iowrite32(vdev->features >> 32, &vp_dev->common->guest_feature);
+
+	return 0;
+}
+
+/* virtio config->get() implementation */
+static void vp_get(struct virtio_device *vdev, unsigned offset,
+		   void *buf, unsigned len)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	u8 b;
+	__le16 w;
+	__le32 l;
+
+	switch (len) {
+	case 1:
+		b = ioread8(vp_dev->device + offset);
+		memcpy(buf, &b, sizeof b);
+		break;
+	case 2:
+		w = cpu_to_le16(ioread16(vp_dev->device + offset));
+		memcpy(buf, &w, sizeof w);
+		break;
+	case 4:
+		l = cpu_to_le32(ioread32(vp_dev->device + offset));
+		memcpy(buf, &l, sizeof l);
+		break;
+	case 8:
+		l = cpu_to_le32(ioread32(vp_dev->device + offset));
+		memcpy(buf, &l, sizeof l);
+		l = cpu_to_le32(ioread32(vp_dev->device + offset + sizeof l));
+		memcpy(buf + sizeof l, &l, sizeof l);
+		break;
+	default:
+		BUG();
+	}
+}
+
+/* the config->set() implementation.  it's symmetric to the config->get()
+ * implementation */
+static void vp_set(struct virtio_device *vdev, unsigned offset,
+		   const void *buf, unsigned len)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	u8 b;
+	__le16 w;
+	__le32 l;
+
+	switch (len) {
+	case 1:
+		memcpy(&b, buf, sizeof b);
+		iowrite8(b, vp_dev->device + offset);
+		break;
+	case 2:
+		memcpy(&w, buf, sizeof w);
+		iowrite16(le16_to_cpu(w), vp_dev->device + offset);
+		break;
+	case 4:
+		memcpy(&l, buf, sizeof l);
+		iowrite32(le32_to_cpu(l), vp_dev->device + offset);
+		break;
+	case 8:
+		memcpy(&l, buf, sizeof l);
+		iowrite32(le32_to_cpu(l), vp_dev->device + offset);
+		memcpy(&l, buf + sizeof l, sizeof l);
+		iowrite32(le32_to_cpu(l), vp_dev->device + offset + sizeof l);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static u32 vp_generation(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	return ioread8(&vp_dev->common->config_generation);
+}
+
+/* config->{get,set}_status() implementations */
+static u8 vp_get_status(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	return ioread8(&vp_dev->common->device_status);
+}
+
+static void vp_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	/* We should never be setting status to 0. */
+	BUG_ON(status == 0);
+	iowrite8(status, &vp_dev->common->device_status);
+}
+
+static void vp_reset(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	/* 0 status means a reset. */
+	iowrite8(0, &vp_dev->common->device_status);
+	/* Flush out the status write, and flush in device writes,
+	 * including MSI-X interrupts, if any. */
+	ioread8(&vp_dev->common->device_status);
+	/* Flush pending VQ/configuration callbacks. */
+	vp_synchronize_vectors(vdev);
+}
+
+static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
+{
+	/* Setup the vector used for configuration events */
+	iowrite16(vector, &vp_dev->common->msix_config);
+	/* Verify we had enough resources to assign the vector */
+	/* Will also flush the write out to device */
+	return ioread16(&vp_dev->common->msix_config);
+}
+
+static size_t vring_pci_size(u16 num)
+{
+	/* We only need a cacheline separation. */
+	return PAGE_ALIGN(vring_size(num, SMP_CACHE_BYTES));
+}
+
+static void *alloc_virtqueue_pages(int *num)
+{
+	void *pages;
+
+	/* TODO: allocate each queue chunk individually */
+	for (; *num && vring_pci_size(*num) > PAGE_SIZE; *num /= 2) {
+		pages = alloc_pages_exact(vring_pci_size(*num),
+					  GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN);
+		if (pages)
+			return pages;
+	}
+
+	if (!*num)
+		return NULL;
+
+	/* Try to get a single page. You are my only hope! */
+	return alloc_pages_exact(vring_pci_size(*num), GFP_KERNEL|__GFP_ZERO);
+}
+
+static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+				  struct virtio_pci_vq_info *info,
+				  unsigned index,
+				  void (*callback)(struct virtqueue *vq),
+				  const char *name,
+				  u16 msix_vec)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtqueue *vq;
+	u16 num, off;
+	int err;
+
+	if (index >= ioread16(&cfg->num_queues))
+		return ERR_PTR(-ENOENT);
+
+	/* Select the queue we're interested in */
+	iowrite16(index, &cfg->queue_select);
+
+	/* Check if queue is either not available or already active. */
+	num = ioread16(&cfg->queue_size);
+	if (!num || ioread8(&cfg->queue_enable))
+		return ERR_PTR(-ENOENT);
+
+	if (num & (num - 1)) {
+		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* get offset of notification word for this vq (shouldn't wrap) */
+	off = ioread16(&cfg->queue_notify_off);
+	if ((u64)off * vp_dev->notify_offset_multiplier + 2
+	    > vp_dev->notify_len) {
+		dev_warn(&vp_dev->pci_dev->dev,
+			 "bad notification offset %u (x %u) for queue %u > %zd",
+			 off, vp_dev->notify_offset_multiplier, 
+			 index, vp_dev->notify_len);
+		return ERR_PTR(-EINVAL);
+	}
+
+	info->num = num;
+	info->msix_vector = msix_vec;
+
+	info->queue = alloc_virtqueue_pages(&info->num);
+	if (info->queue == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	/* create the vring */
+	vq = vring_new_virtqueue(index, info->num,
+				 SMP_CACHE_BYTES, &vp_dev->vdev,
+				 true, info->queue, vp_notify, callback, name);
+	if (!vq) {
+		err = -ENOMEM;
+		goto out_activate_queue;
+	}
+
+	/* activate the queue */
+	iowrite16(num, &cfg->queue_size);
+	iowrite64_twopart(virt_to_phys(info->queue),
+			  &cfg->queue_desc_lo, &cfg->queue_desc_hi);
+	iowrite64_twopart(virt_to_phys(virtqueue_get_avail(vq)),
+			  &cfg->queue_avail_lo, &cfg->queue_avail_hi);
+	iowrite64_twopart(virt_to_phys(virtqueue_get_avail(vq)),
+			  &cfg->queue_used_lo, &cfg->queue_used_hi);
+
+	if (vp_dev->notify_map_cap)
+		vq->priv = (void __force *)map_capability(vp_dev->pci_dev,
+					  vp_dev->notify_map_cap, 2, 2,
+					  off * vp_dev->notify_offset_multiplier, 2,
+					  NULL);
+	else
+		vq->priv = (void __force *)vp_dev->notify_base +
+			off * vp_dev->notify_offset_multiplier;
+
+	if (!vq->priv) {
+		err = -ENOMEM;
+		goto out_map;
+	}
+
+	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
+		iowrite16(msix_vec, &cfg->queue_msix_vector);
+		msix_vec = ioread16(&cfg->queue_msix_vector);
+		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
+			err = -EBUSY;
+			goto out_assign;
+		}
+	}
+
+	return vq;
+
+out_assign:
+	if (vp_dev->notify_map_cap)
+		pci_iounmap(vp_dev->pci_dev, (void __force *)vq->priv);
+out_map:
+	vring_del_virtqueue(vq);
+out_activate_queue:
+	free_pages_exact(info->queue, vring_pci_size(info->num));
+	return ERR_PTR(err);
+}
+
+static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+			      struct virtqueue *vqs[],
+			      vq_callback_t *callbacks[],
+			      const char *names[])
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtqueue *vq;
+	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names);
+
+	if (rc)
+		return rc;
+
+	/* Select and activate all queues. Has to be done last: once we do
+	 * this, there's no way to go back except reset.
+	 */
+	list_for_each_entry(vq, &vdev->vqs, list) {
+		iowrite16(vq->index, &vp_dev->common->queue_select);
+		iowrite8(1, &vp_dev->common->queue_enable);
+	}
+
+	return 0;
+}
+
+static void del_vq(struct virtio_pci_vq_info *info)
+{
+	struct virtqueue *vq = info->vq;
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+
+	iowrite16(vq->index, &vp_dev->common->queue_select);
+
+	if (vp_dev->msix_enabled) {
+		iowrite16(VIRTIO_MSI_NO_VECTOR,
+			  &vp_dev->common->queue_msix_vector);
+		/* Flush the write out to device */
+		ioread16(&vp_dev->common->queue_msix_vector);
+	}
+
+	if (vp_dev->notify_map_cap)
+		pci_iounmap(vp_dev->pci_dev, (void __force *)vq->priv);
+
+	vring_del_virtqueue(vq);
+
+	free_pages_exact(info->queue, vring_pci_size(info->num));
+}
+
+static const struct virtio_config_ops virtio_pci_config_ops = {
+	.get		= vp_get,
+	.set		= vp_set,
+	.generation	= vp_generation,
+	.get_status	= vp_get_status,
+	.set_status	= vp_set_status,
+	.reset		= vp_reset,
+	.find_vqs	= vp_modern_find_vqs,
+	.del_vqs	= vp_del_vqs,
+	.get_features	= vp_get_features,
+	.finalize_features = vp_finalize_features,
+	.bus_name	= vp_bus_name,
+	.set_vq_affinity = vp_set_vq_affinity,
+};
+
+/**
+ * virtio_pci_find_capability - walk capabilities to find device info.
+ * @dev: the pci device
+ * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
+ * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
+ *
+ * Returns offset of the capability, or 0.
+ */
+static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
+					     u32 ioresource_types)
+{
+	int pos;
+
+	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
+	     pos > 0;
+	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
+		u8 type_and_bar, type, bar;
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 type_and_bar),
+				     &type_and_bar);
+
+		type = (type_and_bar >> VIRTIO_PCI_CAP_TYPE_SHIFT) &
+			VIRTIO_PCI_CAP_TYPE_MASK;
+		bar = (type_and_bar >> VIRTIO_PCI_CAP_BAR_SHIFT) &
+			VIRTIO_PCI_CAP_BAR_MASK;
+
+		if (type == cfg_type) {
+			if (pci_resource_flags(dev, bar) & ioresource_types)
+				return pos;
+		}
+	}
+	return 0;
+}
+
+/* the PCI probing function */
+int virtio_pci_modern_probe(struct pci_dev *pci_dev,
+			    const struct pci_device_id *id)
+{
+	struct virtio_pci_device *vp_dev;
+	int err, common, isr, notify, device;
+	struct virtio_device_id virtio_id;
+	u32 notify_length;
+
+	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
+	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
+		return -ENODEV;
+
+	if (pci_dev->device < 0x1040) {
+		/* Transitional devices: use the PCI subsystem device id as
+		 * virtio device id, same as legacy driver always did.
+		 */
+		virtio_id.device = pci_dev->subsystem_device;
+	} else {
+		/* Modern devices: simply use PCI device id, but start from 0x1040. */
+		virtio_id.device = pci_dev->device - 0x1040;
+	}
+	virtio_id.vendor = pci_dev->subsystem_vendor;
+
+	if (virtio_device_is_legacy_only(virtio_id))
+		return -ENODEV;
+
+	/* check for a common config: if not, use legacy mode (bar 0). */
+	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
+					    IORESOURCE_IO|IORESOURCE_MEM);
+	if (!common) {
+		dev_info(&pci_dev->dev,
+			 "virtio_pci: leaving for legacy driver\n");
+		return -ENODEV;
+	}
+
+	/* If common is there, these should be too... */
+	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
+					 IORESOURCE_IO|IORESOURCE_MEM);
+	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
+					    IORESOURCE_IO|IORESOURCE_MEM);
+	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
+					    IORESOURCE_IO|IORESOURCE_MEM);
+	if (!isr || !notify || !device) {
+		dev_err(&pci_dev->dev,
+			"virtio_pci: missing capabilities %i/%i/%i/%i\n",
+			common, isr, notify, device);
+		return -EINVAL;
+	}
+
+	/* allocate our structure and fill it out */
+	vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
+	if (!vp_dev)
+		return -ENOMEM;
+
+	vp_dev->vdev.dev.parent = &pci_dev->dev;
+	vp_dev->vdev.dev.release = virtio_pci_release_dev;
+	vp_dev->vdev.config = &virtio_pci_config_ops;
+	vp_dev->pci_dev = pci_dev;
+	INIT_LIST_HEAD(&vp_dev->virtqueues);
+	spin_lock_init(&vp_dev->lock);
+
+	/* Disable MSI/MSIX to bring device to a known good state. */
+	pci_msi_off(pci_dev);
+
+	/* enable the device */
+	err = pci_enable_device(pci_dev);
+	if (err)
+		goto out;
+
+	err = pci_request_regions(pci_dev, "virtio-pci");
+	if (err)
+		goto out_enable_device;
+
+	err = -EINVAL;
+	vp_dev->common = map_capability(pci_dev, common,
+					sizeof(struct virtio_pci_common_cfg), 4,
+					0, sizeof(struct virtio_pci_common_cfg),
+					NULL);
+	if (!vp_dev->common)
+		goto out_req_regions;
+	vp_dev->isr = map_capability(pci_dev, isr, sizeof(u8), 1,
+				     0, 1,
+				     NULL);
+	if (!vp_dev->isr)
+		goto out_map_common;
+
+	/* Read notify_off_multiplier from config space. */
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						notify_off_multiplier),
+			      &vp_dev->notify_offset_multiplier);
+	/* Read notify length from config space. */
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						cap.length),
+			      &notify_length);
+
+	/* We don't know how many VQs we'll map, ahead of the time.
+	 * If notify length is small, map it all now.
+	 * Otherwise, map each VQ individually later.
+	 */
+	if (notify_length <= PAGE_SIZE) {
+		vp_dev->notify_base = map_capability(pci_dev, notify, 2, 2,
+						     0, PAGE_SIZE,
+						     &vp_dev->notify_len);
+		if (!vp_dev->notify_len)
+			goto out_map_isr;
+	} else {
+		vp_dev->notify_map_cap = notify;
+	}
+
+	/* Device capability is only mandatory for devices that have
+	 * device-specific configuration.
+	 * Again, we don't know how much we should map, but PAGE_SIZE
+	 * is more than enough for all existing devices.
+	 */
+	vp_dev->device = map_capability(pci_dev, device, 0, 4,
+					0, PAGE_SIZE,
+					&vp_dev->device_len);
+
+	pci_set_drvdata(pci_dev, vp_dev);
+	pci_set_master(pci_dev);
+
+	vp_dev->vdev.id = virtio_id;
+	vp_dev->config_vector = vp_config_vector;
+	vp_dev->setup_vq = setup_vq;
+	vp_dev->del_vq = del_vq;
+
+	/* finally register the virtio device */
+	err = register_virtio_device(&vp_dev->vdev);
+	if (err)
+		goto out_set_drvdata;
+
+	return 0;
+
+out_set_drvdata:
+	pci_set_drvdata(pci_dev, NULL);
+	if (vp_dev->device)
+		pci_iounmap(pci_dev, vp_dev->device);
+	if (vp_dev->notify_base)
+		pci_iounmap(pci_dev, vp_dev->notify_base);
+out_map_isr:
+	pci_iounmap(pci_dev, vp_dev->isr);
+out_map_common:
+	pci_iounmap(pci_dev, vp_dev->common);
+out_req_regions:
+	pci_release_regions(pci_dev);
+out_enable_device:
+	pci_disable_device(pci_dev);
+out:
+	kfree(vp_dev);
+	return err;
+}
+
+void virtio_pci_modern_remove(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+
+	unregister_virtio_device(&vp_dev->vdev);
+
+	vp_del_vqs(&vp_dev->vdev);
+	pci_set_drvdata(pci_dev, NULL);
+	if (vp_dev->device)
+		pci_iounmap(pci_dev, vp_dev->device);
+	if (vp_dev->notify_base)
+		pci_iounmap(pci_dev, vp_dev->notify_base);
+	pci_iounmap(pci_dev, vp_dev->isr);
+	pci_iounmap(pci_dev, vp_dev->common);
+	pci_release_regions(pci_dev);
+	pci_disable_device(pci_dev);
+	kfree(vp_dev);
+}
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index db3437c..67873c3 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -11,6 +11,7 @@
 #include <sys/types.h>
 #include <fcntl.h>
 #include <stdbool.h>
+#include <linux/virtio_types.h>
 #include <linux/vhost.h>
 #include <linux/virtio.h>
 #include <linux/virtio_ring.h>
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index bf5104b..bd230d1 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
 obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
-virtio_pci-y := virtio_pci_legacy.o virtio_pci_common.o
+virtio_pci-y := virtio_pci_modern.o virtio_pci_legacy.o virtio_pci_common.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
-- 
MST

[PATCH RFC 5/5] virtio_pci: macros for PCI layout offsets.

[Michael S. Tsirkin]

QEMU wants it, so why not?  Trust, but verify.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/uapi/linux/virtio_pci.h    | 30 ++++++++++++++++++
 drivers/virtio/virtio_pci_modern.c | 63 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 93 insertions(+)

diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 28c2ce0..5d546c6 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -159,6 +159,36 @@ struct virtio_pci_common_cfg {
 	__le32 queue_used_hi;		/* read-write */
 };
 
+/* Macro versions of offsets for the Old Timers! */
+#define VIRTIO_PCI_CAP_VNDR		0
+#define VIRTIO_PCI_CAP_NEXT		1
+#define VIRTIO_PCI_CAP_LEN		2
+#define VIRTIO_PCI_CAP_TYPE_AND_BAR	3
+#define VIRTIO_PCI_CAP_OFFSET		4
+#define VIRTIO_PCI_CAP_LENGTH		8
+
+#define VIRTIO_PCI_NOTIFY_CAP_MULT	12
+
+#define VIRTIO_PCI_COMMON_DFSELECT	0
+#define VIRTIO_PCI_COMMON_DF		4
+#define VIRTIO_PCI_COMMON_GFSELECT	8
+#define VIRTIO_PCI_COMMON_GF		12
+#define VIRTIO_PCI_COMMON_MSIX		16
+#define VIRTIO_PCI_COMMON_NUMQ		18
+#define VIRTIO_PCI_COMMON_STATUS	20
+#define VIRTIO_PCI_COMMON_CFGGENERATION	21
+#define VIRTIO_PCI_COMMON_Q_SELECT	22
+#define VIRTIO_PCI_COMMON_Q_SIZE	24
+#define VIRTIO_PCI_COMMON_Q_MSIX	26
+#define VIRTIO_PCI_COMMON_Q_ENABLE	28
+#define VIRTIO_PCI_COMMON_Q_NOFF	30
+#define VIRTIO_PCI_COMMON_Q_DESCLO	32
+#define VIRTIO_PCI_COMMON_Q_DESCHI	36
+#define VIRTIO_PCI_COMMON_Q_AVAILLO	40
+#define VIRTIO_PCI_COMMON_Q_AVAILHI	44
+#define VIRTIO_PCI_COMMON_Q_USEDLO	48
+#define VIRTIO_PCI_COMMON_Q_USEDHI	52
+
 #endif /* VIRTIO_PCI_NO_MODERN */
 
 #endif
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 636666c..5b0c012 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -446,6 +446,67 @@ static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
 	return 0;
 }
 
+/* This is part of the ABI.  Don't screw with it. */
+static inline void check_offsets(void)
+{
+	/* Note: disk space was harmed in compilation of this function. */
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
+		     offsetof(struct virtio_pci_cap, cap_vndr));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
+		     offsetof(struct virtio_pci_cap, cap_next));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
+		     offsetof(struct virtio_pci_cap, cap_len));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_TYPE_AND_BAR !=
+		     offsetof(struct virtio_pci_cap, type_and_bar));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
+		     offsetof(struct virtio_pci_cap, offset));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
+		     offsetof(struct virtio_pci_cap, length));
+	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
+		     offsetof(struct virtio_pci_notify_cap,
+			      notify_off_multiplier));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
+		     offsetof(struct virtio_pci_common_cfg,
+			      device_feature_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
+		     offsetof(struct virtio_pci_common_cfg, device_feature));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
+		     offsetof(struct virtio_pci_common_cfg,
+			      guest_feature_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
+		     offsetof(struct virtio_pci_common_cfg, guest_feature));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
+		     offsetof(struct virtio_pci_common_cfg, msix_config));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
+		     offsetof(struct virtio_pci_common_cfg, num_queues));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
+		     offsetof(struct virtio_pci_common_cfg, device_status));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
+		     offsetof(struct virtio_pci_common_cfg, config_generation));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
+		     offsetof(struct virtio_pci_common_cfg, queue_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
+		     offsetof(struct virtio_pci_common_cfg, queue_size));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
+		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
+		     offsetof(struct virtio_pci_common_cfg, queue_enable));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
+		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
+		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
+		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
+		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
+		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
+		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
+		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
+}
+
 /* the PCI probing function */
 int virtio_pci_modern_probe(struct pci_dev *pci_dev,
 			    const struct pci_device_id *id)
@@ -455,6 +516,8 @@ int virtio_pci_modern_probe(struct pci_dev *pci_dev,
 	struct virtio_device_id virtio_id;
 	u32 notify_length;
 
+	check_offsets();
+
 	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
 	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
 		return -ENODEV;
-- 
MST

[PATCH RFC 0/5] virtio_pci: modern driver

[Michael S. Tsirkin]

Based on Rusty's patches.
Coding style and funny jokes are his.
Bugs and a star wars reference (should be easy to spot) are mine.
Untested, but useful as basis for beginning the qemu work.

TODO:
= 	simplify probing: use a common probe function, probe with modern driver
	first, if that fails - probe with legacy driver.
BUGS:   ATM legacy driver can win and drive a transitional device
        Until this is fixed, to test, disable transitional mode in device

More ideas (optional):
=	allow disabling legacy driver
=	support shared IRQ for config, read ISR
=	allocate VQ ring in chunks, good for large rings
=	use less meory for small VQ ring in chunks, good for large rings

General TODOs:
=	add config generation support
=	move alloc_virtqueue_pages to virtio core, reuse in e.g. ccw

Michael S Tsirkin (1):
  pci: add pci_iomap_range

Michael S. Tsirkin (2):
  virtio_pci: add VIRTIO_PCI_NO_LEGACY
  virtio_pci: modern driver

Rusty Russell (2):
  virtio-pci: define layout for virtio 1.0
  virtio_pci: macros for PCI layout offsets.

 drivers/virtio/virtio_pci_common.h |  23 +-
 include/asm-generic/pci_iomap.h    |   5 +
 include/uapi/linux/virtio_pci.h    | 106 ++++++-
 drivers/virtio/virtio_pci_modern.c | 621 +++++++++++++++++++++++++++++++++++++
 lib/pci_iomap.c                    |  46 ++-
 drivers/virtio/Makefile            |   2 +-
 6 files changed, 788 insertions(+), 15 deletions(-)
 create mode 100644 drivers/virtio/virtio_pci_modern.c

-- 
MST

[PATCH RFC 4/5] virtio_pci: modern driver

[Michael S. Tsirkin]

It compiles! Must be perfect.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_pci_common.h |  23 +-
 include/uapi/linux/virtio_pci.h    |  29 ++
 drivers/virtio/virtio_pci_modern.c | 560 +++++++++++++++++++++++++++++++++++++
 drivers/virtio/Makefile            |   2 +-
 4 files changed, 610 insertions(+), 4 deletions(-)
 create mode 100644 drivers/virtio/virtio_pci_modern.c

diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 38d99ad..1567531 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -53,12 +53,29 @@ struct virtio_pci_device {
 	struct virtio_device vdev;
 	struct pci_dev *pci_dev;
 
+	/* In legacy mode, these two point to within ->legacy. */
+	/* Where to read and clear interrupt */
+	u8 __iomem *isr;
+
+	/* Modern only fields */
+	/* The IO mapping for the PCI config space (non-legacy mode) */
+	struct virtio_pci_common_cfg __iomem *common;
+	/* Device-specific data (non-legacy mode)  */
+	void __iomem *device;
+	/* Base of vq notifications (non-legacy mode). */
+	void __iomem *notify_base;
+
+	/* So we can sanity-check accesses. */
+	size_t notify_len;
+	size_t device_len;
+
+	/* Multiply queue_notify_off by this value. (non-legacy mode). */
+	u32 notify_offset_multiplier;
+
+	/* Legacy only field */
 	/* the IO mapping for the PCI config space */
 	void __iomem *ioaddr;
 
-	/* the IO mapping for ISR operation */
-	void __iomem *isr;
-
 	/* a list of queues so we can dispatch IRQs */
 	spinlock_t lock;
 	struct list_head virtqueues;
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 8423764..601c66b 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -159,6 +159,35 @@ struct virtio_pci_common_cfg {
 	__le32 queue_used_hi;		/* read-write */
 };
 
+/* Macro versions of offsets for the Old Timers! */
+#define VIRTIO_PCI_CAP_VNDR		0
+#define VIRTIO_PCI_CAP_NEXT		1
+#define VIRTIO_PCI_CAP_LEN		2
+#define VIRTIO_PCI_CAP_TYPE_AND_BAR	3
+#define VIRTIO_PCI_CAP_OFFSET		4
+#define VIRTIO_PCI_CAP_LENGTH		8
+
+#define VIRTIO_PCI_NOTIFY_CAP_MULT	12
+
+#define VIRTIO_PCI_COMMON_DFSELECT	0
+#define VIRTIO_PCI_COMMON_DF		4
+#define VIRTIO_PCI_COMMON_GFSELECT	8
+#define VIRTIO_PCI_COMMON_GF		12
+#define VIRTIO_PCI_COMMON_MSIX		16
+#define VIRTIO_PCI_COMMON_NUMQ		18
+#define VIRTIO_PCI_COMMON_STATUS	20
+#define VIRTIO_PCI_COMMON_Q_SELECT	22
+#define VIRTIO_PCI_COMMON_Q_SIZE	24
+#define VIRTIO_PCI_COMMON_Q_MSIX	26
+#define VIRTIO_PCI_COMMON_Q_ENABLE	28
+#define VIRTIO_PCI_COMMON_Q_NOFF	30
+#define VIRTIO_PCI_COMMON_Q_DESCLO	32
+#define VIRTIO_PCI_COMMON_Q_DESCHI	36
+#define VIRTIO_PCI_COMMON_Q_AVAILLO	40
+#define VIRTIO_PCI_COMMON_Q_AVAILHI	44
+#define VIRTIO_PCI_COMMON_Q_USEDLO	48
+#define VIRTIO_PCI_COMMON_Q_USEDHI	52
+
 #endif /* VIRTIO_PCI_NO_MODERN */
 
 #endif
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
new file mode 100644
index 0000000..e6e65e1
--- /dev/null
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -0,0 +1,560 @@
+/*
+ * Virtio PCI driver - legacy device support
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ * Copyright Red Hat, Inc. 2014
+ *
+ * Authors:
+ *  Anthony Liguori  <aliguori@us.ibm.com>
+ *  Rusty Russell <rusty@rustcorp.com.au>
+ *  Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#define VIRTIO_PCI_NO_LEGACY
+#include "virtio_pci_common.h"
+
+/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
+static const struct pci_device_id virtio_pci_id_table[] = {
+	{ PCI_DEVICE(0x1af4, PCI_ANY_ID) },
+	{ 0 }
+};
+
+MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
+
+static void iowrite64_twopart(u64 val, __le32 __iomem *lo, __le32 __iomem *hi)
+{
+	iowrite32((u32)val, lo);
+	iowrite32(val >> 32, hi);
+}
+
+/* virtio config->get_features() implementation */
+static u64 vp_get_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	u64 features;
+
+	iowrite32(0, &vp_dev->common->device_feature_select);
+	features = ioread32(&vp_dev->common->device_feature);
+	iowrite32(1, &vp_dev->common->device_feature_select);
+	features |= ((u64)ioread32(&vp_dev->common->device_feature) << 32);
+
+	return features;
+}
+
+/* virtio config->finalize_features() implementation */
+static int vp_finalize_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	iowrite32(0, &vp_dev->common->guest_feature_select);
+	iowrite32((u32)vdev->features, &vp_dev->common->guest_feature);
+	iowrite32(1, &vp_dev->common->guest_feature_select);
+	iowrite32(vdev->features >> 32, &vp_dev->common->guest_feature);
+
+	return 0;
+}
+
+/* virtio config->get() implementation */
+static void vp_get(struct virtio_device *vdev, unsigned offset,
+		   void *buf, unsigned len)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	u8 b;
+	__le16 w;
+	__le32 l;
+
+	switch (len) {
+	case 1:
+		b = ioread8(vp_dev->device + offset);
+		memcpy(buf, &b, sizeof b);
+		break;
+	case 2:
+		w = cpu_to_le16(ioread16(vp_dev->device + offset));
+		memcpy(buf, &w, sizeof w);
+		break;
+	case 4:
+		l = cpu_to_le32(ioread32(vp_dev->device + offset));
+		memcpy(buf, &l, sizeof l);
+		break;
+	case 8:
+		l = cpu_to_le32(ioread32(vp_dev->device + offset));
+		memcpy(buf, &l, sizeof l);
+		l = cpu_to_le32(ioread32(vp_dev->device + offset + sizeof l));
+		memcpy(buf + sizeof l, &l, sizeof l);
+		break;
+	default:
+		BUG();
+	}
+}
+
+/* the config->set() implementation.  it's symmetric to the config->get()
+ * implementation */
+static void vp_set(struct virtio_device *vdev, unsigned offset,
+		   const void *buf, unsigned len)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	u8 b;
+	__le16 w;
+	__le32 l;
+
+	switch (len) {
+	case 1:
+		memcpy(&b, buf, sizeof b);
+		iowrite8(b, vp_dev->device + offset);
+		break;
+	case 2:
+		memcpy(&w, buf, sizeof w);
+		iowrite16(le16_to_cpu(w), vp_dev->device + offset);
+		break;
+	case 4:
+		memcpy(&l, buf, sizeof l);
+		iowrite32(le32_to_cpu(l), vp_dev->device + offset);
+		break;
+	case 8:
+		memcpy(&l, buf, sizeof l);
+		iowrite32(le32_to_cpu(l), vp_dev->device + offset);
+		memcpy(&l, buf + sizeof l, sizeof l);
+		iowrite32(le32_to_cpu(l), vp_dev->device + offset + sizeof l);
+		break;
+	default:
+		BUG();
+	}
+}
+
+/* config->{get,set}_status() implementations */
+static u8 vp_get_status(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	return ioread8(&vp_dev->common->device_status);
+}
+
+static void vp_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	/* We should never be setting status to 0. */
+	BUG_ON(status == 0);
+	iowrite8(status, &vp_dev->common->device_status);
+}
+
+static void vp_reset(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	/* 0 status means a reset. */
+	iowrite8(0, &vp_dev->common->device_status);
+	/* Flush out the status write, and flush in device writes,
+	 * including MSI-X interrupts, if any. */
+	ioread8(&vp_dev->common->device_status);
+	/* Flush pending VQ/configuration callbacks. */
+	vp_synchronize_vectors(vdev);
+}
+
+static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
+{
+	/* Setup the vector used for configuration events */
+	iowrite16(vector, &vp_dev->common->msix_config);
+	/* Verify we had enough resources to assign the vector */
+	/* Will also flush the write out to device */
+	return ioread16(&vp_dev->common->msix_config);
+}
+
+static size_t vring_pci_size(u16 num)
+{
+	/* We only need a cacheline separation. */
+	return PAGE_ALIGN(vring_size(num, SMP_CACHE_BYTES));
+}
+
+static void *alloc_virtqueue_pages(int *num)
+{
+	void *pages;
+
+	/* TODO: allocate each queue chunk individually */
+	for (; *num && vring_pci_size(*num) > PAGE_SIZE; *num /= 2) {
+		pages = alloc_pages_exact(vring_pci_size(*num),
+					  GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN);
+		if (pages)
+			return pages;
+	}
+
+	if (!*num)
+		return NULL;
+
+	/* Try to get a single page. You are my only hope! */
+	return alloc_pages_exact(vring_pci_size(*num), GFP_KERNEL|__GFP_ZERO);
+}
+
+static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+				  struct virtio_pci_vq_info *info,
+				  unsigned index,
+				  void (*callback)(struct virtqueue *vq),
+				  const char *name,
+				  u16 msix_vec)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtqueue *vq;
+	u16 num, off;
+	int err;
+
+	if (index >= ioread16(&cfg->num_queues))
+		return ERR_PTR(-ENOENT);
+
+	/* Select the queue we're interested in */
+	iowrite16(index, &cfg->queue_select);
+
+	/* Check if queue is either not available or already active. */
+	num = ioread16(&cfg->queue_size);
+	if (!num || ioread8(&cfg->queue_enable))
+		return ERR_PTR(-ENOENT);
+
+	if (num & (num - 1)) {
+		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* get offset of notification word for this vq (shouldn't wrap) */
+	off = ioread16(&cfg->queue_notify_off);
+	if ((u64)off * vp_dev->notify_offset_multiplier + 2
+	    > vp_dev->notify_len) {
+		dev_warn(&vp_dev->pci_dev->dev,
+			 "bad notification offset %u (x %u) for queue %u > %zd",
+			 off, vp_dev->notify_offset_multiplier, 
+			 index, vp_dev->notify_len);
+		return ERR_PTR(-EINVAL);
+	}
+
+	info->num = num;
+	info->msix_vector = msix_vec;
+
+	info->queue = alloc_virtqueue_pages(&info->num);
+	if (info->queue == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	/* create the vring */
+	vq = vring_new_virtqueue(index, info->num,
+				 SMP_CACHE_BYTES, &vp_dev->vdev,
+				 true, info->queue, vp_notify, callback, name);
+	if (!vq) {
+		err = -ENOMEM;
+		goto out_activate_queue;
+	}
+
+	/* activate the queue */
+	iowrite16(num, &cfg->queue_size);
+	iowrite64_twopart(virt_to_phys(info->queue),
+			  &cfg->queue_desc_lo, &cfg->queue_desc_hi);
+	iowrite64_twopart(virt_to_phys(virtqueue_get_avail(vq)),
+			  &cfg->queue_avail_lo, &cfg->queue_avail_hi);
+	iowrite64_twopart(virt_to_phys(virtqueue_get_avail(vq)),
+			  &cfg->queue_used_lo, &cfg->queue_used_hi);
+
+
+	/* TODO: map each vq notification area individually */
+	vq->priv = (void __force *)vp_dev->notify_base +
+		off * vp_dev->notify_offset_multiplier;
+
+	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
+		iowrite16(msix_vec, &cfg->queue_msix_vector);
+		msix_vec = ioread16(&cfg->queue_msix_vector);
+		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
+			err = -EBUSY;
+			goto out_assign;
+		}
+	}
+
+	return vq;
+
+out_assign:
+	vring_del_virtqueue(vq);
+out_activate_queue:
+	free_pages_exact(info->queue, vring_pci_size(info->num));
+	return ERR_PTR(err);
+}
+
+static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+			      struct virtqueue *vqs[],
+			      vq_callback_t *callbacks[],
+			      const char *names[])
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtqueue *vq;
+	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names);
+
+	if (rc)
+		return rc;
+
+	/* Select and activate all queues. Has to be done last: once we do
+	 * this, there's no way to go back except reset.
+	 */
+	list_for_each_entry(vq, &vdev->vqs, list) {
+		iowrite16(vq->index, &vp_dev->common->queue_select);
+		iowrite8(1, &vp_dev->common->queue_enable);
+	}
+
+	return 0;
+}
+
+static void del_vq(struct virtio_pci_vq_info *info)
+{
+	struct virtqueue *vq = info->vq;
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+
+	iowrite16(vq->index, &vp_dev->common->queue_select);
+
+	if (vp_dev->msix_enabled) {
+		iowrite16(VIRTIO_MSI_NO_VECTOR,
+			  &vp_dev->common->queue_msix_vector);
+		/* Flush the write out to device */
+		ioread16(&vp_dev->common->queue_msix_vector);
+	}
+
+	vring_del_virtqueue(vq);
+
+	free_pages_exact(info->queue, vring_pci_size(info->num));
+}
+
+static const struct virtio_config_ops virtio_pci_config_ops = {
+	.get		= vp_get,
+	.set		= vp_set,
+	.get_status	= vp_get_status,
+	.set_status	= vp_set_status,
+	.reset		= vp_reset,
+	.find_vqs	= vp_modern_find_vqs,
+	.del_vqs	= vp_del_vqs,
+	.get_features	= vp_get_features,
+	.finalize_features = vp_finalize_features,
+	.bus_name	= vp_bus_name,
+	.set_vq_affinity = vp_set_vq_affinity,
+};
+
+/**
+ * virtio_pci_find_capability - walk capabilities to find device info.
+ * @dev: the pci device
+ * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
+ * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
+ *
+ * Returns offset of the capability, or 0.
+ */
+static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
+					     u32 ioresource_types)
+{
+	int pos;
+
+	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
+	     pos > 0;
+	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
+		u8 type_and_bar, type, bar;
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 type_and_bar),
+				     &type_and_bar);
+
+		type = (type_and_bar >> VIRTIO_PCI_CAP_TYPE_SHIFT) &
+			VIRTIO_PCI_CAP_TYPE_MASK;
+		bar = (type_and_bar >> VIRTIO_PCI_CAP_BAR_SHIFT) &
+			VIRTIO_PCI_CAP_BAR_MASK;
+
+		if (type == cfg_type) {
+			if (pci_resource_flags(dev, bar) & ioresource_types)
+				return pos;
+		}
+	}
+	return 0;
+}
+
+static void __iomem *map_capability(struct pci_dev *dev, int off, size_t minlen,
+				    size_t *len)
+{
+	u8 type_and_bar, bar;
+	u32 offset, length;
+	void __iomem *p;
+
+	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
+						 type_and_bar),
+			     &type_and_bar);
+	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
+			     &offset);
+	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
+			      &length);
+
+	if (length < minlen) {
+		dev_err(&dev->dev,
+			"virtio_pci: small capability len %u (%zu expected)\n",
+			length, minlen);
+		return NULL;
+	}
+
+	if (len)
+		*len = length;
+
+	bar = (type_and_bar >> VIRTIO_PCI_CAP_BAR_SHIFT) &
+		VIRTIO_PCI_CAP_BAR_MASK;
+
+	/* We want uncachable mapping, even if bar is cachable. */
+	p = pci_iomap_range(dev, bar, offset, length, PAGE_SIZE, true);
+	if (!p)
+		dev_err(&dev->dev,
+			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
+			length, offset, bar);
+	return p;
+}
+
+/* the PCI probing function */
+static int virtio_pci_probe(struct pci_dev *pci_dev,
+			    const struct pci_device_id *id)
+{
+	struct virtio_pci_device *vp_dev;
+	int err, common, isr, notify, device;
+
+	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
+	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
+		return -ENODEV;
+
+	/* allocate our structure and fill it out */
+	vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
+	if (vp_dev == NULL)
+		return -ENOMEM;
+
+	vp_dev->vdev.dev.parent = &pci_dev->dev;
+	vp_dev->vdev.dev.release = virtio_pci_release_dev;
+	vp_dev->vdev.config = &virtio_pci_config_ops;
+	vp_dev->pci_dev = pci_dev;
+	INIT_LIST_HEAD(&vp_dev->virtqueues);
+	spin_lock_init(&vp_dev->lock);
+
+	/* check for a common config: if not, use legacy mode (bar 0). */
+	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
+					    IORESOURCE_IO|IORESOURCE_MEM);
+	if (!common) {
+		dev_info(&pci_dev->dev,
+			 "virtio_pci: leaving for legacy driver\n");
+		return -ENODEV;
+	}
+
+	/* If common is there, these should be too... */
+	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
+					 IORESOURCE_IO|IORESOURCE_MEM);
+	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
+					    IORESOURCE_IO|IORESOURCE_MEM);
+	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
+					    IORESOURCE_IO|IORESOURCE_MEM);
+	if (!isr || !notify || !device) {
+		dev_err(&pci_dev->dev,
+			"virtio_pci: missing capabilities %i/%i/%i/%i\n",
+			common, isr, notify, device);
+		return -EINVAL;
+	}
+
+	/* Disable MSI/MSIX to bring device to a known good state. */
+	pci_msi_off(pci_dev);
+
+	/* enable the device */
+	err = pci_enable_device(pci_dev);
+	if (err)
+		goto out;
+
+	err = pci_request_regions(pci_dev, "virtio-pci");
+	if (err)
+		goto out_enable_device;
+
+	err = -EINVAL;
+	vp_dev->common = map_capability(pci_dev, common,
+					sizeof(struct virtio_pci_common_cfg),
+					NULL);
+	if (!vp_dev->common)
+		goto out_req_regions;
+	vp_dev->isr = map_capability(pci_dev, isr, sizeof(u8), NULL);
+	if (!vp_dev->isr)
+		goto out_map_common;
+
+	/* Read notify_off_multiplier from config space. */
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						notify_off_multiplier),
+			      &vp_dev->notify_offset_multiplier);
+	vp_dev->notify_base = map_capability(pci_dev, notify, sizeof(u8),
+					     &vp_dev->notify_len);
+	if (!vp_dev->notify_len)
+		goto out_map_isr;
+	vp_dev->device = map_capability(pci_dev, device, 0, &vp_dev->device_len);
+	if (!vp_dev->device)
+		goto out_map_notify;
+
+	pci_set_drvdata(pci_dev, vp_dev);
+	pci_set_master(pci_dev);
+
+	if (pci_dev->device < 0x1040) {
+		/* Transitional devices: use the PCI subsystem device id as
+		 * virtio device id, same as legacy driver always did.
+		 */
+		vp_dev->vdev.id.device = pci_dev->subsystem_device;
+	} else {
+		/* Modern devices: simply use PCI device id, but start from 0x1040. */
+		vp_dev->vdev.id.device = pci_dev->device - 0x1040;
+	}
+
+	vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
+	vp_dev->config_vector = vp_config_vector;
+	vp_dev->setup_vq = setup_vq;
+	vp_dev->del_vq = del_vq;
+
+	/* finally register the virtio device */
+	err = register_virtio_device(&vp_dev->vdev);
+	if (err)
+		goto out_set_drvdata;
+
+	return 0;
+
+out_set_drvdata:
+	pci_set_drvdata(pci_dev, NULL);
+	pci_iounmap(pci_dev, vp_dev->device);
+out_map_notify:
+	pci_iounmap(pci_dev, vp_dev->notify_base);
+out_map_isr:
+	pci_iounmap(pci_dev, vp_dev->isr);
+out_map_common:
+	pci_iounmap(pci_dev, vp_dev->common);
+out_req_regions:
+	pci_release_regions(pci_dev);
+out_enable_device:
+	pci_disable_device(pci_dev);
+out:
+	kfree(vp_dev);
+	return err;
+}
+
+static void virtio_pci_remove(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+
+	unregister_virtio_device(&vp_dev->vdev);
+
+	vp_del_vqs(&vp_dev->vdev);
+	pci_set_drvdata(pci_dev, NULL);
+	pci_iounmap(pci_dev, vp_dev->device);
+	pci_iounmap(pci_dev, vp_dev->notify_base);
+	pci_iounmap(pci_dev, vp_dev->isr);
+	pci_iounmap(pci_dev, vp_dev->common);
+	pci_release_regions(pci_dev);
+	pci_disable_device(pci_dev);
+	kfree(vp_dev);
+}
+
+static struct pci_driver virtio_pci_driver = {
+	.name		= "virtio-pci",
+	.id_table	= virtio_pci_id_table,
+	.probe		= virtio_pci_probe,
+	.remove		= virtio_pci_remove,
+#ifdef CONFIG_PM_SLEEP
+	.driver.pm	= &virtio_pci_pm_ops,
+#endif
+};
+
+module_pci_driver(virtio_pci_driver);
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index bf5104b..bd230d1 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
 obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
-virtio_pci-y := virtio_pci_legacy.o virtio_pci_common.o
+virtio_pci-y := virtio_pci_modern.o virtio_pci_legacy.o virtio_pci_common.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
-- 
MST