iommu: Introduce iotlb_sync_map callback

Introduce iotlb_sync_map() callback that is invoked in the end of
iommu_map(). This new callback allows IOMMU drivers to avoid syncing
after mapping of each contiguous chunk and sync only when the whole
mapping is completed, optimizing performance of the mapping operation.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/iommu.c

@@ -1585,13 +1585,14 @@ static size_t iommu_pgsize(struct iommu_domain *domain,
 int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	      phys_addr_t paddr, size_t size, int prot)
 {
+	const struct iommu_ops *ops = domain->ops;
 	unsigned long orig_iova = iova;
 	unsigned int min_pagesz;
 	size_t orig_size = size;
 	phys_addr_t orig_paddr = paddr;
 	int ret = 0;
 
-	if (unlikely(domain->ops->map == NULL ||
+	if (unlikely(ops->map == NULL ||
 		     domain->pgsize_bitmap == 0UL))
 		return -ENODEV;
 
@@ -1620,7 +1621,7 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n",
 			 iova, &paddr, pgsize);
 
-		ret = domain->ops->map(domain, iova, paddr, pgsize, prot);
+		ret = ops->map(domain, iova, paddr, pgsize, prot);
 		if (ret)
 			break;
 
@@ -1629,6 +1630,9 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		size -= pgsize;
 	}
 
+	if (ops->iotlb_sync_map)
+		ops->iotlb_sync_map(domain);
+
 	/* unroll mapping in case something went wrong */
 	if (ret)
 		iommu_unmap(domain, orig_iova, orig_size - size);

include/linux/iommu.h

@@ -201,6 +201,7 @@ struct iommu_ops {
 	void (*flush_iotlb_all)(struct iommu_domain *domain);
 	void (*iotlb_range_add)(struct iommu_domain *domain,
 				unsigned long iova, size_t size);
+	void (*iotlb_sync_map)(struct iommu_domain *domain);
 	void (*iotlb_sync)(struct iommu_domain *domain);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
 	int (*add_device)(struct device *dev);