iommu/vt-d: Apply per-device dma_ops

Current Intel IOMMU driver sets the system level dma_ops. This causes
each dma API to go through the IOMMU driver even the devices are using
identity mapped domains. This sets per-device dma_ops only if a device
is using a DMA domain. Otherwise, use the default system level dma_ops
for direct dma.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Daniel Drake <drake@endlessm.com>
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Link: https://lore.kernel.org/r/20200506015947.28662-4-baolu.lu@linux.intel.comSigned-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/intel-iommu.c

@@ -2720,17 +2720,6 @@ static int __init si_domain_init(int hw)
 	return 0;
 }
 
-static int identity_mapping(struct device *dev)
-{
-	struct device_domain_info *info;
-
-	info = dev->archdata.iommu;
-	if (info)
-		return (info->domain == si_domain);
-
-	return 0;
-}
-
 static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev)
 {
 	struct dmar_domain *ndomain;
@@ -3315,18 +3304,6 @@ static unsigned long intel_alloc_iova(struct device *dev,
 	return iova_pfn;
 }
 
-/* Check if the dev needs to go through non-identity map and unmap process.*/
-static bool iommu_need_mapping(struct device *dev)
-{
-	if (iommu_dummy(dev))
-		return false;
-
-	if (unlikely(attach_deferred(dev)))
-		do_deferred_attach(dev);
-
-	return !identity_mapping(dev);
-}
-
 static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
 				     size_t size, int dir, u64 dma_mask)
 {
@@ -3340,6 +3317,9 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
 
 	BUG_ON(dir == DMA_NONE);
 
+	if (unlikely(attach_deferred(dev)))
+		do_deferred_attach(dev);
+
 	domain = find_domain(dev);
 	if (!domain)
 		return DMA_MAPPING_ERROR;
@@ -3391,20 +3371,15 @@ static dma_addr_t intel_map_page(struct device *dev, struct page *page,
 				 enum dma_data_direction dir,
 				 unsigned long attrs)
 {
-	if (iommu_need_mapping(dev))
 	return __intel_map_single(dev, page_to_phys(page) + offset,
 				  size, dir, *dev->dma_mask);
-	return dma_direct_map_page(dev, page, offset, size, dir, attrs);
 }
 
 static dma_addr_t intel_map_resource(struct device *dev, phys_addr_t phys_addr,
 				     size_t size, enum dma_data_direction dir,
 				     unsigned long attrs)
 {
-	if (iommu_need_mapping(dev))
-		return __intel_map_single(dev, phys_addr, size, dir,
-				*dev->dma_mask);
-	return dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
+	return __intel_map_single(dev, phys_addr, size, dir, *dev->dma_mask);
 }
 
 static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
@@ -3455,16 +3430,12 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
 			     size_t size, enum dma_data_direction dir,
 			     unsigned long attrs)
 {
-	if (iommu_need_mapping(dev))
 	intel_unmap(dev, dev_addr, size);
-	else
-		dma_direct_unmap_page(dev, dev_addr, size, dir, attrs);
 }
 
 static void intel_unmap_resource(struct device *dev, dma_addr_t dev_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	if (iommu_need_mapping(dev))
 	intel_unmap(dev, dev_addr, size);
 }
 
@@ -3475,8 +3446,8 @@ static void *intel_alloc_coherent(struct device *dev, size_t size,
 	struct page *page = NULL;
 	int order;
 
-	if (!iommu_need_mapping(dev))
-		return dma_direct_alloc(dev, size, dma_handle, flags, attrs);
+	if (unlikely(attach_deferred(dev)))
+		do_deferred_attach(dev);
 
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
@@ -3511,9 +3482,6 @@ static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
 	int order;
 	struct page *page = virt_to_page(vaddr);
 
-	if (!iommu_need_mapping(dev))
-		return dma_direct_free(dev, size, vaddr, dma_handle, attrs);
-
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
 
@@ -3531,9 +3499,6 @@ static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct scatterlist *sg;
 	int i;
 
-	if (!iommu_need_mapping(dev))
-		return dma_direct_unmap_sg(dev, sglist, nelems, dir, attrs);
-
 	for_each_sg(sglist, sg, nelems, i) {
 		nrpages += aligned_nrpages(sg_dma_address(sg), sg_dma_len(sg));
 	}
@@ -3557,8 +3522,9 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
 	struct intel_iommu *iommu;
 
 	BUG_ON(dir == DMA_NONE);
-	if (!iommu_need_mapping(dev))
-		return dma_direct_map_sg(dev, sglist, nelems, dir, attrs);
+
+	if (unlikely(attach_deferred(dev)))
+		do_deferred_attach(dev);
 
 	domain = find_domain(dev);
 	if (!domain)
@@ -3605,8 +3571,6 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
 
 static u64 intel_get_required_mask(struct device *dev)
 {
-	if (!iommu_need_mapping(dev))
-		return dma_direct_get_required_mask(dev);
 	return DMA_BIT_MASK(32);
 }
 
@@ -4888,8 +4852,6 @@ int __init intel_iommu_init(void)
 	}
 	up_write(&dmar_global_lock);
 
-	dma_ops = &intel_dma_ops;
-
 	init_iommu_pm_ops();
 
 	down_read(&dmar_global_lock);
@@ -5479,11 +5441,6 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 	if (translation_pre_enabled(iommu))
 		dev->archdata.iommu = DEFER_DEVICE_DOMAIN_INFO;
 
-	if (device_needs_bounce(dev)) {
-		dev_info(dev, "Use Intel IOMMU bounce page dma_ops\n");
-		set_dma_ops(dev, &bounce_dma_ops);
-	}
-
 	return &iommu->iommu;
 }
 
@@ -5498,7 +5455,19 @@ static void intel_iommu_release_device(struct device *dev)
 
 	dmar_remove_one_dev_info(dev);
 
+	set_dma_ops(dev, NULL);
+}
+
+static void intel_iommu_probe_finalize(struct device *dev)
+{
+	struct iommu_domain *domain;
+
+	domain = iommu_get_domain_for_dev(dev);
 	if (device_needs_bounce(dev))
+		set_dma_ops(dev, &bounce_dma_ops);
+	else if (domain && domain->type == IOMMU_DOMAIN_DMA)
+		set_dma_ops(dev, &intel_dma_ops);
+	else
 		set_dma_ops(dev, NULL);
 }
 
@@ -5830,6 +5799,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.unmap			= intel_iommu_unmap,
 	.iova_to_phys		= intel_iommu_iova_to_phys,
 	.probe_device		= intel_iommu_probe_device,
+	.probe_finalize		= intel_iommu_probe_finalize,
 	.release_device		= intel_iommu_release_device,
 	.get_resv_regions	= intel_iommu_get_resv_regions,
 	.put_resv_regions	= generic_iommu_put_resv_regions,