[kernel,5/5] vfio/spapr_tce: Advertise and allow a huge DMA windows at 4GB
diff mbox series

Message ID 20200218073650.16149-6-aik@ozlabs.ru
State Not Applicable
Headers show
Series
  • powerpc/powenv/ioda: Allow huge DMA window at 4GB
Related show

Commit Message

Alexey Kardashevskiy Feb. 18, 2020, 7:36 a.m. UTC
So far the only option for a big 64big DMA window was a window located
at 0x800.0000.0000.0000 (1<<59) which creates problems for devices
supporting smaller DMA masks.

This exploits a POWER9 PHB option to allow the second DMA window to map
at 0 and advertises it with a 4GB offset to avoid overlap with
the default 32bit window.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 include/uapi/linux/vfio.h           |  2 ++
 drivers/vfio/vfio_iommu_spapr_tce.c | 10 ++++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

Comments

Alex Williamson Feb. 20, 2020, 6:19 p.m. UTC | #1
On Tue, 18 Feb 2020 18:36:50 +1100
Alexey Kardashevskiy <aik@ozlabs.ru> wrote:

> So far the only option for a big 64big DMA window was a window located
> at 0x800.0000.0000.0000 (1<<59) which creates problems for devices
> supporting smaller DMA masks.
> 
> This exploits a POWER9 PHB option to allow the second DMA window to map
> at 0 and advertises it with a 4GB offset to avoid overlap with
> the default 32bit window.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
>  include/uapi/linux/vfio.h           |  2 ++
>  drivers/vfio/vfio_iommu_spapr_tce.c | 10 ++++++++--
>  2 files changed, 10 insertions(+), 2 deletions(-)
> 
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 9e843a147ead..c7f89d47335a 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -831,9 +831,11 @@ struct vfio_iommu_spapr_tce_info {
>  	__u32 argsz;
>  	__u32 flags;
>  #define VFIO_IOMMU_SPAPR_INFO_DDW	(1 << 0)	/* DDW supported */
> +#define VFIO_IOMMU_SPAPR_INFO_DDW_START	(1 << 1)	/* DDW offset */
>  	__u32 dma32_window_start;	/* 32 bit window start (bytes) */
>  	__u32 dma32_window_size;	/* 32 bit window size (bytes) */
>  	struct vfio_iommu_spapr_tce_ddw_info ddw;
> +	__u64 dma64_window_start;
>  };
>  
>  #define VFIO_IOMMU_SPAPR_TCE_GET_INFO	_IO(VFIO_TYPE, VFIO_BASE + 12)
> diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> index 16b3adc508db..4f22be3c4aa2 100644
> --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -691,7 +691,7 @@ static long tce_iommu_create_window(struct tce_container *container,
>  	container->tables[num] = tbl;
>  
>  	/* Return start address assigned by platform in create_table() */
> -	*start_addr = tbl->it_offset << tbl->it_page_shift;
> +	*start_addr = tbl->it_dmaoff << tbl->it_page_shift;
>  
>  	return 0;
>  
> @@ -842,7 +842,13 @@ static long tce_iommu_ioctl(void *iommu_data,
>  			info.ddw.levels = table_group->max_levels;
>  		}
>  
> -		ddwsz = offsetofend(struct vfio_iommu_spapr_tce_info, ddw);
> +		ddwsz = offsetofend(struct vfio_iommu_spapr_tce_info,
> +				dma64_window_start);

This breaks existing users, now they no longer get the ddw struct
unless their argsz also includes the new dma64 window field.

> +
> +		if (info.argsz >= ddwsz) {
> +			info.flags |= VFIO_IOMMU_SPAPR_INFO_DDW_START;
> +			info.dma64_window_start = table_group->tce64_start;
> +		}

This is inconsistent with ddw where we set the flag regardless of
argsz, but obviously only provide the field to the user if they've
provided room for it.  Thanks,

Alex

>  
>  		if (info.argsz >= ddwsz)
>  			minsz = ddwsz;

Patch
diff mbox series

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 9e843a147ead..c7f89d47335a 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -831,9 +831,11 @@  struct vfio_iommu_spapr_tce_info {
 	__u32 argsz;
 	__u32 flags;
 #define VFIO_IOMMU_SPAPR_INFO_DDW	(1 << 0)	/* DDW supported */
+#define VFIO_IOMMU_SPAPR_INFO_DDW_START	(1 << 1)	/* DDW offset */
 	__u32 dma32_window_start;	/* 32 bit window start (bytes) */
 	__u32 dma32_window_size;	/* 32 bit window size (bytes) */
 	struct vfio_iommu_spapr_tce_ddw_info ddw;
+	__u64 dma64_window_start;
 };
 
 #define VFIO_IOMMU_SPAPR_TCE_GET_INFO	_IO(VFIO_TYPE, VFIO_BASE + 12)
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 16b3adc508db..4f22be3c4aa2 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -691,7 +691,7 @@  static long tce_iommu_create_window(struct tce_container *container,
 	container->tables[num] = tbl;
 
 	/* Return start address assigned by platform in create_table() */
-	*start_addr = tbl->it_offset << tbl->it_page_shift;
+	*start_addr = tbl->it_dmaoff << tbl->it_page_shift;
 
 	return 0;
 
@@ -842,7 +842,13 @@  static long tce_iommu_ioctl(void *iommu_data,
 			info.ddw.levels = table_group->max_levels;
 		}
 
-		ddwsz = offsetofend(struct vfio_iommu_spapr_tce_info, ddw);
+		ddwsz = offsetofend(struct vfio_iommu_spapr_tce_info,
+				dma64_window_start);
+
+		if (info.argsz >= ddwsz) {
+			info.flags |= VFIO_IOMMU_SPAPR_INFO_DDW_START;
+			info.dma64_window_start = table_group->tce64_start;
+		}
 
 		if (info.argsz >= ddwsz)
 			minsz = ddwsz;