iommu/dma: Centralise iommu_setup_dma_ops()

It's somewhat hard to see, but arm64's arch_setup_dma_ops() should only
ever call iommu_setup_dma_ops() after a successful iommu_probe_device(),
which means there should be no harm in achieving the same order of
operations by running it off the back of iommu_probe_device() itself.
This then puts it in line with the x86 and s390 .probe_finalize bodges,
letting us pull it all into the main flow properly. As a bonus this lets
us fold in and de-scope the PCI workaround setup as well.

At this point we can also then pull the call up inside the group mutex,
and avoid having to think about whether iommu_group_store_type() could
theoretically race and free the domain if iommu_setup_dma_ops() ran just
*before* iommu_device_use_default_domain() claims it... Furthermore we
replace one .probe_finalize call completely, since the only remaining
implementations are now one which only needs to run once for the initial
boot-time probe, and two which themselves render that path unreachable.

This leaves us a big step closer to realistically being able to unpick
the variety of different things that iommu_setup_dma_ops() has been
muddling together, and further streamline iommu-dma into core API flows
in future.

Reviewed-by: Lu Baolu <[e-mail]> # For Intel IOMMU
Reviewed-by: Jason Gunthorpe <[e-mail]>
Tested-by: Hanjun Guo <[e-mail]>
Signed-off-by: Robin Murphy <[e-mail]>
Acked-by: Catalin Marinas <[e-mail]>
Link: https://lore.kernel.org/r/bebe[e-mail]
Signed-off-by: Joerg Roedel <[e-mail]>

arch/arm64/mm/dma-mapping.c

···
 		   ARCH_DMA_MINALIGN, cls);
 
 	dev->dma_coherent = coherent;
-	if (device_iommu_mapped(dev))
-		iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1);
 
 	xen_setup_dma_ops(dev);
 }

drivers/iommu/amd/iommu.c

···
 	return iommu_dev;
 }
 
-static void amd_iommu_probe_finalize(struct device *dev)
-{
-	/* Domains are initialized for this device - have a look what we ended up with */
-	set_dma_ops(dev, NULL);
-	iommu_setup_dma_ops(dev, 0, U64_MAX);
-}
-
 static void amd_iommu_release_device(struct device *dev)
 {
 	struct amd_iommu *iommu;
···
 	.domain_alloc_user = amd_iommu_domain_alloc_user,
 	.probe_device = amd_iommu_probe_device,
 	.release_device = amd_iommu_release_device,
-	.probe_finalize = amd_iommu_probe_finalize,
 	.device_group = amd_iommu_device_group,
 	.get_resv_regions = amd_iommu_get_resv_regions,
 	.is_attach_deferred = amd_iommu_is_attach_deferred,

drivers/iommu/dma-iommu.c

···
 	.max_mapping_size       = iommu_dma_max_mapping_size,
 };
 
-/*
- * The IOMMU core code allocates the default DMA domain, which the underlying
- * IOMMU driver needs to support via the dma-iommu layer.
- */
-void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit)
+void iommu_setup_dma_ops(struct device *dev)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 
-	if (!domain)
-		goto out_err;
+	if (dev_is_pci(dev))
+		dev->iommu->pci_32bit_workaround = !iommu_dma_forcedac;
 
-	/*
-	 * The IOMMU core code allocates the default DMA domain, which the
-	 * underlying IOMMU driver needs to support via the dma-iommu layer.
-	 */
 	if (iommu_is_dma_domain(domain)) {
 		if (iommu_dma_init_domain(domain, dev))
 			goto out_err;
 		dev->dma_ops = &iommu_dma_ops;
+	} else if (dev->dma_ops == &iommu_dma_ops) {
+		/* Clean up if we've switched *from* a DMA domain */
+		dev->dma_ops = NULL;
 	}
 
 	return;
···
 	 pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
 		 dev_name(dev));
 }
-EXPORT_SYMBOL_GPL(iommu_setup_dma_ops);
 
 static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 		phys_addr_t msi_addr, struct iommu_domain *domain)

drivers/iommu/dma-iommu.h

···
 
 #ifdef CONFIG_IOMMU_DMA
 
+void iommu_setup_dma_ops(struct device *dev);
+
 int iommu_get_dma_cookie(struct iommu_domain *domain);
 void iommu_put_dma_cookie(struct iommu_domain *domain);
 
···
 void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list);
 
 extern bool iommu_dma_forcedac;
-static inline void iommu_dma_set_pci_32bit_workaround(struct device *dev)
-{
-	dev->iommu->pci_32bit_workaround = !iommu_dma_forcedac;
-}
 
 #else /* CONFIG_IOMMU_DMA */
+
+static inline void iommu_setup_dma_ops(struct device *dev)
+{
+}
 
 static inline int iommu_dma_init_fq(struct iommu_domain *domain)
 {
···
 }
 
 static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
-{
-}
-
-static inline void iommu_dma_set_pci_32bit_workaround(struct device *dev)
 {
 }
 

drivers/iommu/intel/iommu.c

···
 	set_dma_ops(dev, NULL);
 }
 
-static void intel_iommu_probe_finalize(struct device *dev)
-{
-	set_dma_ops(dev, NULL);
-	iommu_setup_dma_ops(dev, 0, U64_MAX);
-}
-
 static void intel_iommu_get_resv_regions(struct device *device,
 					 struct list_head *head)
 {
···
 	.domain_alloc		= intel_iommu_domain_alloc,
 	.domain_alloc_user	= intel_iommu_domain_alloc_user,
 	.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,
 	.device_group		= intel_iommu_device_group,

drivers/iommu/iommu.c

···
 		if (list_empty(&group->entry))
 			list_add_tail(&group->entry, group_list);
 	}
-	mutex_unlock(&group->mutex);
 
-	if (dev_is_pci(dev))
-		iommu_dma_set_pci_32bit_workaround(dev);
+	if (group->default_domain)
+		iommu_setup_dma_ops(dev);
+
+	mutex_unlock(&group->mutex);
 
 	return 0;
 
···
 			mutex_unlock(&group->mutex);
 			return ret;
 		}
+		for_each_group_device(group, gdev)
+			iommu_setup_dma_ops(gdev->dev);
 		mutex_unlock(&group->mutex);
 
 		/*
···
 	if (ret)
 		goto out_unlock;
 
-	/*
-	 * Release the mutex here because ops->probe_finalize() call-back of
-	 * some vendor IOMMU drivers calls arm_iommu_attach_device() which
-	 * in-turn might call back into IOMMU core code, where it tries to take
-	 * group->mutex, resulting in a deadlock.
-	 */
-	mutex_unlock(&group->mutex);
-
 	/* Make sure dma_ops is appropriatley set */
 	for_each_group_device(group, gdev)
-		iommu_group_do_probe_finalize(gdev->dev);
-	return count;
+		iommu_setup_dma_ops(gdev->dev);
 
 out_unlock:
 	mutex_unlock(&group->mutex);

drivers/iommu/s390-iommu.c

···
 	return size;
 }
 
-static void s390_iommu_probe_finalize(struct device *dev)
-{
-	iommu_setup_dma_ops(dev, 0, U64_MAX);
-}
-
 struct zpci_iommu_ctrs *zpci_get_iommu_ctrs(struct zpci_dev *zdev)
 {
 	if (!zdev || !zdev->s390_domain)
···
 	.capable = s390_iommu_capable,
 	.domain_alloc_paging = s390_domain_alloc_paging,
 	.probe_device = s390_iommu_probe_device,
-	.probe_finalize = s390_iommu_probe_finalize,
 	.release_device = s390_iommu_release_device,
 	.device_group = generic_device_group,
 	.pgsize_bitmap = SZ_4K,

drivers/iommu/virtio-iommu.c

···
 	return ERR_PTR(ret);
 }
 
-static void viommu_probe_finalize(struct device *dev)
-{
-#ifndef CONFIG_ARCH_HAS_SETUP_DMA_OPS
-	/* First clear the DMA ops in case we're switching from a DMA domain */
-	set_dma_ops(dev, NULL);
-	iommu_setup_dma_ops(dev, 0, U64_MAX);
-#endif
-}
-
 static void viommu_release_device(struct device *dev)
 {
 	struct viommu_endpoint *vdev = dev_iommu_priv_get(dev);
···
 	.capable		= viommu_capable,
 	.domain_alloc		= viommu_domain_alloc,
 	.probe_device		= viommu_probe_device,
-	.probe_finalize		= viommu_probe_finalize,
 	.release_device		= viommu_release_device,
 	.device_group		= viommu_device_group,
 	.get_resv_regions	= viommu_get_resv_regions,

include/linux/iommu.h

···
 #ifdef CONFIG_IOMMU_DMA
 #include <linux/msi.h>
 
-/* Setup call for arch DMA mapping code */
-void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit);
-
 int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base);
 
 int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr);
···
 
 struct msi_desc;
 struct msi_msg;
-
-static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit)
-{
-}
 
 static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
 {