Pull out the sync operation from viommu_map_pages() by implementing
ops->iotlb_sync_map. This allows the common IOMMU code to map multiple
elements of an sg with a single sync (see iommu_map_sg()). Furthermore,
it is also a requirement for IOMMU_CAP_DEFERRED_FLUSH.

Link: https://lore.kernel.org/lkml/20230726111433.1105665-1-schnelle@linux.ibm.com/
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
---
 drivers/iommu/virtio-iommu.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 3551ed057774..fb73dec5b953 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -843,7 +843,7 @@ static int viommu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			.flags		= cpu_to_le32(flags),
 		};
 
-		ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
+		ret = viommu_add_req(vdomain->viommu, &map, sizeof(map));
 		if (ret) {
 			viommu_del_mappings(vdomain, iova, end);
 			return ret;
@@ -909,9 +909,21 @@ static void viommu_iotlb_sync(struct iommu_domain *domain,
 {
 	struct viommu_domain *vdomain = to_viommu_domain(domain);
 
+	if (!vdomain->nr_endpoints)
+		return;
 	viommu_sync_req(vdomain->viommu);
 }
 
+static int viommu_iotlb_sync_map(struct iommu_domain *domain,
+				 unsigned long iova, size_t size)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	if (!vdomain->nr_endpoints)
+		return 0;
+	return viommu_sync_req(vdomain->viommu);
+}
+
 static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
 {
 	struct iommu_resv_region *entry, *new_entry, *msi = NULL;
@@ -1058,6 +1070,7 @@ static struct iommu_ops viommu_ops = {
 		.unmap_pages		= viommu_unmap_pages,
 		.iova_to_phys		= viommu_iova_to_phys,
 		.iotlb_sync		= viommu_iotlb_sync,
+		.iotlb_sync_map		= viommu_iotlb_sync_map,
 		.free			= viommu_domain_free,
 	}
 };

-- 
2.39.2

Hi Niklas,

Thanks for following up with these patches

On Fri, Aug 25, 2023 at 05:21:25PM +0200, Niklas Schnelle wrote:
> Pull out the sync operation from viommu_map_pages() by implementing
> ops->iotlb_sync_map. This allows the common IOMMU code to map multiple
> elements of an sg with a single sync (see iommu_map_sg()). Furthermore,
> it is also a requirement for IOMMU_CAP_DEFERRED_FLUSH.
> 
> Link: https://lore.kernel.org/lkml/20230726111433.1105665-1-schnelle@linux.ibm.com/
> Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
> ---
>  drivers/iommu/virtio-iommu.c | 15 ++++++++++++++-
>  1 file changed, 14 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
> index 3551ed057774..fb73dec5b953 100644
> --- a/drivers/iommu/virtio-iommu.c
> +++ b/drivers/iommu/virtio-iommu.c
> @@ -843,7 +843,7 @@ static int viommu_map_pages(struct iommu_domain *domain, unsigned long iova,
>  			.flags		= cpu_to_le32(flags),
>  		};
>  
> -		ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
> +		ret = viommu_add_req(vdomain->viommu, &map, sizeof(map));
>  		if (ret) {
>  			viommu_del_mappings(vdomain, iova, end);
>  			return ret;
> @@ -909,9 +909,21 @@ static void viommu_iotlb_sync(struct iommu_domain *domain,
>  {
>  	struct viommu_domain *vdomain = to_viommu_domain(domain);
>  
> +	if (!vdomain->nr_endpoints)
> +		return;

I was wondering about these nr_endpoints checks, which seemed unnecessary:
if map()/unmap() were called with no attached endpoints, then no requests
were added to the queue, and viommu_sync_req() below is a nop.

But at least viommu_iotlb_sync_map() and viommu_flush_iotlb_all() need to
handle being called before the domain is finalized (for example by
iommu_create_device_direct_mappings()). In that case vdomain->viommu is
NULL so if you add a NULL check in viommu_sync_req() then you should be
able to drop the nr_endpoints checks in both patches.

Thanks,
Jean

>  	viommu_sync_req(vdomain->viommu);
>  }
>  
> +static int viommu_iotlb_sync_map(struct iommu_domain *domain,
> +				 unsigned long iova, size_t size)
> +{
> +	struct viommu_domain *vdomain = to_viommu_domain(domain);
> +
> +	if (!vdomain->nr_endpoints)
> +		return 0;
> +	return viommu_sync_req(vdomain->viommu);
> +}
> +
>  static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
>  {
>  	struct iommu_resv_region *entry, *new_entry, *msi = NULL;
> @@ -1058,6 +1070,7 @@ static struct iommu_ops viommu_ops = {
>  		.unmap_pages		= viommu_unmap_pages,
>  		.iova_to_phys		= viommu_iova_to_phys,
>  		.iotlb_sync		= viommu_iotlb_sync,
> +		.iotlb_sync_map		= viommu_iotlb_sync_map,
>  		.free			= viommu_domain_free,
>  	}
>  };
> 
> -- 
> 2.39.2
>