[v8,2/5] iommu/dma: Add a new dma_map_ops of get_merge_boundary()
diff mbox series

Message ID 1563859608-19456-3-git-send-email-yoshihiro.shimoda.uh@renesas.com
State New
Headers show
Series
  • treewide: improve R-Car SDHI performance
Related show

Commit Message

Yoshihiro Shimoda July 23, 2019, 5:26 a.m. UTC
This patch adds a new dma_map_ops of get_merge_boundary() to
expose the DMA merge boundary if the domain type is IOMMU_DOMAIN_DMA.

Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
---
 drivers/iommu/dma-iommu.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

Comments

Sergei Shtylyov July 23, 2019, 8:17 a.m. UTC | #1
Hello!

On 23.07.2019 8:26, Yoshihiro Shimoda wrote:

> This patch adds a new dma_map_ops of get_merge_boundary() to
> expose the DMA merge boundary if the domain type is IOMMU_DOMAIN_DMA.
> 
> Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
> ---
>   drivers/iommu/dma-iommu.c | 11 +++++++++++
>   1 file changed, 11 insertions(+)
> 
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index a7f9c3e..f3e5f2b 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -1085,6 +1085,16 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
>   	return ret;
>   }
>   
> +static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
> +{
> +	struct iommu_domain *domain = iommu_get_dma_domain(dev);
> +
> +	if (domain->type != IOMMU_DOMAIN_DMA)
> +		return 0;	/* can't merge */
> +
> +	return (1 << __ffs(domain->pgsize_bitmap)) - 1;

    Not 1UL?

> +}
> +
>   static const struct dma_map_ops iommu_dma_ops = {
>   	.alloc			= iommu_dma_alloc,
>   	.free			= iommu_dma_free,
[...]

MBR, Sergei
Simon Horman July 25, 2019, 6:33 a.m. UTC | #2
On Tue, Jul 23, 2019 at 11:17:19AM +0300, Sergei Shtylyov wrote:
> Hello!
> 
> On 23.07.2019 8:26, Yoshihiro Shimoda wrote:
> 
> > This patch adds a new dma_map_ops of get_merge_boundary() to
> > expose the DMA merge boundary if the domain type is IOMMU_DOMAIN_DMA.
> > 
> > Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>

Sergei's comment notwithstanding,

Reviewed-by: Simon Horman <horms+renesas@verge.net.au>

> > ---
> >   drivers/iommu/dma-iommu.c | 11 +++++++++++
> >   1 file changed, 11 insertions(+)
> > 
> > diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> > index a7f9c3e..f3e5f2b 100644
> > --- a/drivers/iommu/dma-iommu.c
> > +++ b/drivers/iommu/dma-iommu.c
> > @@ -1085,6 +1085,16 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
> >   	return ret;
> >   }
> > +static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
> > +{
> > +	struct iommu_domain *domain = iommu_get_dma_domain(dev);
> > +
> > +	if (domain->type != IOMMU_DOMAIN_DMA)
> > +		return 0;	/* can't merge */
> > +
> > +	return (1 << __ffs(domain->pgsize_bitmap)) - 1;
> 
>    Not 1UL?
> 
> > +}
> > +
> >   static const struct dma_map_ops iommu_dma_ops = {
> >   	.alloc			= iommu_dma_alloc,
> >   	.free			= iommu_dma_free,
> [...]
> 
> MBR, Sergei
>
Yoshihiro Shimoda July 26, 2019, 7:50 a.m. UTC | #3
Hello!

> From: Sergei Shtylyov, Sent: Tuesday, July 23, 2019 5:17 PM
> 
> Hello!
> 
> On 23.07.2019 8:26, Yoshihiro Shimoda wrote:
> 
> > This patch adds a new dma_map_ops of get_merge_boundary() to
> > expose the DMA merge boundary if the domain type is IOMMU_DOMAIN_DMA.
> >
> > Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
> > ---
> >   drivers/iommu/dma-iommu.c | 11 +++++++++++
> >   1 file changed, 11 insertions(+)
> >
> > diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> > index a7f9c3e..f3e5f2b 100644
> > --- a/drivers/iommu/dma-iommu.c
> > +++ b/drivers/iommu/dma-iommu.c
> > @@ -1085,6 +1085,16 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
> >   	return ret;
> >   }
> >
> > +static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
> > +{
> > +	struct iommu_domain *domain = iommu_get_dma_domain(dev);
> > +
> > +	if (domain->type != IOMMU_DOMAIN_DMA)
> > +		return 0;	/* can't merge */
> > +
> > +	return (1 << __ffs(domain->pgsize_bitmap)) - 1;
> 
>     Not 1UL?

Thank you for your review! I'll fix it.

Best regards,
Yoshihiro Shimoda

> > +}
> > +
> >   static const struct dma_map_ops iommu_dma_ops = {
> >   	.alloc			= iommu_dma_alloc,
> >   	.free			= iommu_dma_free,
> [...]
> 
> MBR, Sergei

Patch
diff mbox series

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index a7f9c3e..f3e5f2b 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1085,6 +1085,16 @@  static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 	return ret;
 }
 
+static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+
+	if (domain->type != IOMMU_DOMAIN_DMA)
+		return 0;	/* can't merge */
+
+	return (1 << __ffs(domain->pgsize_bitmap)) - 1;
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
@@ -1100,6 +1110,7 @@  static const struct dma_map_ops iommu_dma_ops = {
 	.sync_sg_for_device	= iommu_dma_sync_sg_for_device,
 	.map_resource		= iommu_dma_map_resource,
 	.unmap_resource		= iommu_dma_unmap_resource,
+	.get_merge_boundary	= iommu_dma_get_merge_boundary,
 };
 
 /*