arm64: IOMMU-backed DMA mapping

index a98a7b2..9210159 100644
@@ -3233,6 +3233,8 @@ static struct iova *intel_alloc_iova(struct device *dev,
 
 	/* Restrict dma_mask to the width that the iommu can handle */
 	dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
+	/* Ensure we reserve the whole size-aligned region */
+	nrpages = __roundup_pow_of_two(nrpages);
 
 	if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) {
 		/*

index b7c3d92..29f2efc 100644
@@ -120,19 +120,14 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 	}
 }
 
-/* Computes the padding size required, to make the
- * the start address naturally aligned on its size
+/*
+ * Computes the padding size required, to make the start address
+ * naturally aligned on the power-of-two order of its size
  */
-static int
-iova_get_pad_size(int size, unsigned int limit_pfn)
+static unsigned int
+iova_get_pad_size(unsigned int size, unsigned int limit_pfn)
 {
-	unsigned int pad_size = 0;
-	unsigned int order = ilog2(size);
-
-	if (order)
-		pad_size = (limit_pfn + 1) % (1 << order);
-
-	return pad_size;
+	return (limit_pfn + 1 - size) & (__roundup_pow_of_two(size) - 1);
 }
 
 static int __alloc_and_insert_iova_range(struct iova_domain *iovad,

@@ -265,12 +260,6 @@ alloc_iova(struct iova_domain *iovad, unsigned long size,
 	if (!new_iova)
 		return NULL;
 
-	/* If size aligned is set then round the size to
-	 * to next power of two.
-	 */
-	if (size_aligned)
-		size = __roundup_pow_of_two(size);
-
 	ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn,
 			new_iova, size_aligned);
 

538 lines not on this page · raw message

84 lines not on this page · raw message

index dc767f7..19eee27 100644
@@ -81,6 +81,7 @@ struct iommu_domain {
 	iommu_fault_handler_t handler;
 	void *handler_token;
 	struct iommu_domain_geometry geometry;
+	void *dma_api_cookie;
 };
 
 enum iommu_cap {

index d16a1ce..c89012e 100644
@@ -526,3 +526,431 @@ static int __init dma_debug_do_init(void)
 	return 0;
 }
 fs_initcall(dma_debug_do_init);
+
+
+#ifdef CONFIG_IOMMU_DMA
+#include <linux/dma-iommu.h>
+#include <linux/platform_device.h>
+#include <linux/amba/bus.h>
+
+/* Thankfully, all cache ops are by VA so we can ignore phys here */
+static void flush_page(const void *virt, phys_addr_t phys)
+{
+	__dma_flush_range(virt, virt + PAGE_SIZE);
+}
+
+static void *__iommu_alloc_attrs(struct device *dev, size_t size,
+				 dma_addr_t *handle, gfp_t gfp,
+				 struct dma_attrs *attrs)
+{
+	bool coherent = is_device_dma_coherent(dev);
+	int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent);
+	void *addr;
+
+	if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
+		return NULL;
+
+	/*
+	 * Some drivers rely on this, and we may not want to potentially
+	 * expose stale kernel data to devices anyway.
+	 */
+	gfp |= __GFP_ZERO;
+
+	if (gfp & __GFP_WAIT) {
+		struct page **pages;
+		pgprot_t pgprot = coherent ? __pgprot(PROT_NORMAL) :
+					     __pgprot(PROT_NORMAL_NC);
+
+		pgprot = __get_dma_pgprot(attrs, pgprot, coherent);
+		pages = iommu_dma_alloc(dev, size, gfp, ioprot,	handle,
+					coherent ? NULL : flush_page);
+		if (!pages)
+			return NULL;
+
+		addr = dma_common_pages_remap(pages, size, VM_USERMAP, pgprot,
+					      __builtin_return_address(0));
+		if (!addr)
+			iommu_dma_free(dev, pages, size, handle);
+	} else {
+		struct page *page;
+		/*
+		 * In atomic context we can't remap anything, so we'll only
+		 * get the virtually contiguous buffer we need by way of a
+		 * physically contiguous allocation.
+		 */
+		if (coherent) {
+			page = alloc_pages(gfp, get_order(size));
+			addr = page ? page_address(page) : NULL;
+		} else {
+			addr = __alloc_from_pool(size, &page, gfp);
+		}
+		if (!addr)
+			return NULL;
+
+		*handle = iommu_dma_map_page(dev, page, 0, size, ioprot);
+		if (iommu_dma_mapping_error(dev, *handle)) {
+			if (coherent)
+				__free_pages(page, get_order(size));
+			else
+				__free_from_pool(addr, size);
+			addr = NULL;
+		}
+	}
+	return addr;
+}
+
+static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+			       dma_addr_t handle, struct dma_attrs *attrs)
+{
+	/*
+	 * @cpu_addr will be one of 3 things depending on how it was allocated:
+	 * - A remapped array of pages from iommu_dma_alloc(), for all
+	 *   non-atomic allocations.
+	 * - A non-cacheable alias from the atomic pool, for atomic
+	 *   allocations by non-coherent devices.
+	 * - A normal lowmem address, for atomic allocations by
+	 *   coherent devices.
+	 * Hence how dodgy the below logic looks...
+	 */
+	if (__in_atomic_pool(cpu_addr, size)) {
+		iommu_dma_unmap_page(dev, handle, size, 0, NULL);
+		__free_from_pool(cpu_addr, size);
+	} else if (is_vmalloc_addr(cpu_addr)){
+		struct vm_struct *area = find_vm_area(cpu_addr);
+
+		if (WARN_ON(!area || !area->pages))
+			return;
+		iommu_dma_free(dev, area->pages, size, &handle);
+		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
+	} else {
+		iommu_dma_unmap_page(dev, handle, size, 0, NULL);
+		__free_pages(virt_to_page(cpu_addr), get_order(size));
+	}
+}
+
+static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+			      void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			      struct dma_attrs *attrs)
+{
+	struct vm_struct *area;
+	int ret;
+
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
+					     is_device_dma_coherent(dev));
+
+	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	area = find_vm_area(cpu_addr);
+	if (WARN_ON(!area || !area->pages))
+		return -ENXIO;
+
+	return iommu_dma_mmap(area->pages, size, vma);
+}
+
+static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
+			       void *cpu_addr, dma_addr_t dma_addr,
+			       size_t size, struct dma_attrs *attrs)
+{
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (WARN_ON(!area || !area->pages))
+		return -ENXIO;
+
+	return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size,
+					 GFP_KERNEL);
+}
+
+static void __iommu_sync_single_for_cpu(struct device *dev,
+					dma_addr_t dev_addr, size_t size,
+					enum dma_data_direction dir)
+{
+	phys_addr_t phys;
+
+	if (is_device_dma_coherent(dev))
+		return;
+
+	phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
+	__dma_unmap_area(phys_to_virt(phys), size, dir);
+}
+
+static void __iommu_sync_single_for_device(struct device *dev,
+					   dma_addr_t dev_addr, size_t size,
+					   enum dma_data_direction dir)
+{
+	phys_addr_t phys;
+
+	if (is_device_dma_coherent(dev))
+		return;
+
+	phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
+	__dma_map_area(phys_to_virt(phys), size, dir);
+}
+
+static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
+				   unsigned long offset, size_t size,
+				   enum dma_data_direction dir,
+				   struct dma_attrs *attrs)
+{
+	bool coherent = is_device_dma_coherent(dev);
+	int prot = dma_direction_to_prot(dir, coherent);
+	dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
+
+	if (!iommu_dma_mapping_error(dev, dev_addr) &&
+	    !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+		__iommu_sync_single_for_device(dev, dev_addr, size, dir);
+
+	return dev_addr;
+}
+
+static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr,
+			       size_t size, enum dma_data_direction dir,
+			       struct dma_attrs *attrs)
+{
+	if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+		__iommu_sync_single_for_cpu(dev, dev_addr, size, dir);
+
+	iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static void __iommu_sync_sg_for_cpu(struct device *dev,
+				    struct scatterlist *sgl, int nelems,
+				    enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	if (is_device_dma_coherent(dev))
+		return;
+
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_unmap_area(sg_virt(sg), sg->length, dir);
+}
+
+static void __iommu_sync_sg_for_device(struct device *dev,
+				       struct scatterlist *sgl, int nelems,
+				       enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	if (is_device_dma_coherent(dev))
+		return;
+
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_map_area(sg_virt(sg), sg->length, dir);
+}
+
+static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+				int nelems, enum dma_data_direction dir,
+				struct dma_attrs *attrs)
+{
+	bool coherent = is_device_dma_coherent(dev);
+
+	if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+		__iommu_sync_sg_for_device(dev, sgl, nelems, dir);
+
+	return iommu_dma_map_sg(dev, sgl, nelems,
+			dma_direction_to_prot(dir, coherent));
+}
+
+static void __iommu_unmap_sg_attrs(struct device *dev,
+				   struct scatterlist *sgl, int nelems,
+				   enum dma_data_direction dir,
+				   struct dma_attrs *attrs)
+{
+	if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+		__iommu_sync_sg_for_cpu(dev, sgl, nelems, dir);
+
+	iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs);
+}
+
+static struct dma_map_ops iommu_dma_ops = {
+	.alloc = __iommu_alloc_attrs,
+	.free = __iommu_free_attrs,
+	.mmap = __iommu_mmap_attrs,
+	.get_sgtable = __iommu_get_sgtable,
+	.map_page = __iommu_map_page,
+	.unmap_page = __iommu_unmap_page,
+	.map_sg = __iommu_map_sg_attrs,
+	.unmap_sg = __iommu_unmap_sg_attrs,
+	.sync_single_for_cpu = __iommu_sync_single_for_cpu,
+	.sync_single_for_device = __iommu_sync_single_for_device,
+	.sync_sg_for_cpu = __iommu_sync_sg_for_cpu,
+	.sync_sg_for_device = __iommu_sync_sg_for_device,
+	.dma_supported = iommu_dma_supported,
+	.mapping_error = iommu_dma_mapping_error,
+};
+
+/*
+ * TODO: Right now __iommu_setup_dma_ops() gets called too early to do
+ * everything it needs to - the device isn't yet fully created, and the
+ * IOMMU driver hasn't seen it yet, so we need this delayed attachment
+ * dance. Once IOMMU probe ordering is sorted to move the
+ * arch_setup_dma_ops() call later, all the notifier bits below become
+ * unnecessary, and will go away.
+ */
+struct iommu_dma_notifier_data {
+	struct list_head list;
+	struct device *dev;
+	struct iommu_domain *dma_domain;
+};
+static LIST_HEAD(iommu_dma_masters);
+static DEFINE_MUTEX(iommu_dma_notifier_lock);
+
+static int __iommu_attach_notifier(struct notifier_block *nb,
+				   unsigned long action, void *data)
+{
+	struct iommu_dma_notifier_data *master, *tmp;
+
+	if (action != BUS_NOTIFY_ADD_DEVICE)
+		return 0;
+	/*
+	 * We expect the list to only contain the most recent addition
+	 * (which should be the same device as in @data) so just process
+	 * the whole thing blindly. If any previous attachments did happen
+	 * to fail, they get a free retry since the domains are still live.
+	 */
+	mutex_lock(&iommu_dma_notifier_lock);
+	list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) {
+		if (iommu_attach_device(master->dma_domain, master->dev)) {
+			pr_warn("Failed to attach device %s to IOMMU mapping; retaining platform DMA ops\n",
+				dev_name(master->dev));
+		} else {
+			master->dev->archdata.dma_ops = &iommu_dma_ops;
+			list_del(&master->list);
+			kfree(master);
+		}
+	}
+	mutex_unlock(&iommu_dma_notifier_lock);
+	return 0;
+}
+
+static int register_iommu_dma_ops_notifier(struct bus_type *bus)
+{
+	int ret;
+	struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL);
+
+	/*
+	 * The device must be attached to a domain before the driver probe
+	 * routine gets a chance to start allocating DMA buffers. However,
+	 * the IOMMU driver also needs a chance to configure the iommu_group
+	 * via its add_device callback first, so we need to make the attach
+	 * happen between those two points. Since the IOMMU core uses a bus
+	 * notifier with default priority for add_device, do the same but
+	 * with a lower priority to ensure the appropriate ordering.
+	 */
+	nb->notifier_call = __iommu_attach_notifier;
+	nb->priority = -100;
+
+	ret = bus_register_notifier(bus, nb);
+	if (ret) {
+		pr_warn("Failed to register DMA domain notifier; IOMMU DMA ops unavailable on bus '%s'\n",
+			bus->name);
+		kfree(nb);
+	}
+	return ret;
+}
+
+static int queue_iommu_attach(struct iommu_domain *domain, struct device *dev)
+{
+	struct iommu_dma_notifier_data *iommudata = NULL;
+
+	iommudata = kzalloc(sizeof(*iommudata), GFP_KERNEL);
+	if (!iommudata)
+		return -ENOMEM;
+
+	iommudata->dev = dev;
+	iommudata->dma_domain = domain;
+
+	mutex_lock(&iommu_dma_notifier_lock);
+	list_add(&iommudata->list, &iommu_dma_masters);
+	mutex_unlock(&iommu_dma_notifier_lock);
+	return 0;
+}
+
+static int __init arm64_iommu_dma_init(void)
+{
+	int ret;
+
+	ret = iommu_dma_init();
+	if (!ret)
+		ret = register_iommu_dma_ops_notifier(&platform_bus_type);
+	if (!ret)
+		ret = register_iommu_dma_ops_notifier(&amba_bustype);
+	return ret;
+}
+arch_initcall(arm64_iommu_dma_init);
+
+/* Hijack some domain feature flags for the stop-gap meddling below */
+#define __IOMMU_DOMAIN_ARM64		(1U << 31)
+#define __IOMMU_DOMAIN_ARM64_IOVA	(1U << 30)
+
+static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+				  const struct iommu_ops *ops)
+{
+	struct iommu_domain *domain;
+	int err;
+
+	if (!ops)
+		return;
+	/*
+	 * In a perfect world, everything happened in the right order up to
+	 * here, and the IOMMU core has already attached the device to an
+	 * appropriate default domain for us to set up...
+	 */
+	domain = iommu_get_domain_for_dev(dev);
+	if (!domain) {
+		/*
+		 * Urgh. Reliable default domains for platform devices can't
+		 * happen anyway without some sensible way of handling
+		 * non-trivial groups. So until then, HORRIBLE HACKS!
+		 */
+		domain = ops->domain_alloc(IOMMU_DOMAIN_DMA);
+		if (!domain)
+			domain = ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED);
+		if (!domain)
+			goto out_no_domain;
+
+		domain->ops = ops;
+		domain->type = IOMMU_DOMAIN_DMA | __IOMMU_DOMAIN_ARM64;
+		if (!domain->dma_api_cookie) {
+			domain->type |= __IOMMU_DOMAIN_ARM64_IOVA;
+			if (iommu_get_dma_cookie(domain))
+				goto out_put_domain;
+		}
+	}
+
+	if (iommu_dma_init_domain(domain, dma_base, size)) {
+		pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n",
+			size, dev_name(dev));
+		goto out_put_domain;
+	}
+
+	if (dev->iommu_group)
+		err = iommu_attach_device(domain, dev);
+	else
+		err = queue_iommu_attach(domain, dev);
+
+	if (!err) {
+		dev->archdata.dma_ops = &iommu_dma_ops;
+		return;
+	}
+
+out_put_domain:
+	if (domain->type & __IOMMU_DOMAIN_ARM64_IOVA)
+		iommu_put_dma_cookie(domain);
+	if (domain->type & __IOMMU_DOMAIN_ARM64)
+		ops->domain_free(domain);
+out_no_domain:
+	pr_warn("Failed to set up IOMMU domain for device %s\n", dev_name(dev));
+}
+
+#else
+
+static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+				  struct iommu_ops *iommu)
+{ }
+
+#endif  /* CONFIG_IOMMU_DMA */

index f0d6d0b..7f9edcb 100644
@@ -56,16 +56,15 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 		return __generic_dma_ops(dev);
 }
 
-static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				      struct iommu_ops *iommu, bool coherent)
-{
-	if (!acpi_disabled && !dev->archdata.dma_ops)
-		dev->archdata.dma_ops = dma_ops;
-
-	dev->archdata.dma_coherent = coherent;
-}
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+			struct iommu_ops *iommu, bool coherent);
 #define arch_setup_dma_ops	arch_setup_dma_ops
 
+#ifdef CONFIG_IOMMU_DMA
+void arch_teardown_dma_ops(struct device *dev);
+#define arch_teardown_dma_ops	arch_teardown_dma_ops
+#endif
+
 /* do not use this function in a driver */
 static inline bool is_device_dma_coherent(struct device *dev)
 {

index c89012e..bdab211 100644
@@ -947,6 +947,20 @@ out_no_domain:
 	pr_warn("Failed to set up IOMMU domain for device %s\n", dev_name(dev));
 }
 
+void arch_teardown_dma_ops(struct device *dev)
+{
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+
+	if (domain) {
+		iommu_detach_device(domain, dev);
+		if (domain->type & __IOMMU_DOMAIN_ARM64_IOVA)
+			iommu_put_dma_cookie(domain);
+		if (domain->type & __IOMMU_DOMAIN_ARM64)
+			iommu_domain_free(domain);
+		dev->archdata.dma_ops = NULL;
+	}
+}
+
 #else
 
 static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,

@@ -954,3 +968,13 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 { }
 
 #endif  /* CONFIG_IOMMU_DMA */
+
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+			struct iommu_ops *iommu, bool coherent)
+{
+	if (!acpi_disabled && !dev->archdata.dma_ops)
+		dev->archdata.dma_ops = dma_ops;
+
+	dev->archdata.dma_coherent = coherent;
+	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
+}