1 files changed, 204 insertions, 38 deletions

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 1520e7f..3ade415 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -37,15 +37,50 @@ struct iommu_dma_msi_page {
 	phys_addr_t		phys;
 };
 
+enum iommu_dma_cookie_type {
+	IOMMU_DMA_IOVA_COOKIE,
+	IOMMU_DMA_MSI_COOKIE,
+};
+
 struct iommu_dma_cookie {
-	struct iova_domain	iovad;
-	struct list_head	msi_page_list;
-	spinlock_t		msi_lock;
+	enum iommu_dma_cookie_type	type;
+	union {
+		/* Full allocator for IOMMU_DMA_IOVA_COOKIE */
+		struct iova_domain	iovad;
+		/* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */
+		dma_addr_t		msi_iova;
+	};
+	struct list_head		msi_page_list;
+	spinlock_t			msi_lock;
 };
 
+static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
+{
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
+		return cookie->iovad.granule;
+	return PAGE_SIZE;
+}
+
 static inline struct iova_domain *cookie_iovad(struct iommu_domain *domain)
 {
-	return &((struct iommu_dma_cookie *)domain->iova_cookie)->iovad;
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
+		return &cookie->iovad;
+	return NULL;
+}
+
+static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
+{
+	struct iommu_dma_cookie *cookie;
+
+	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
+	if (cookie) {
+		spin_lock_init(&cookie->msi_lock);
+		INIT_LIST_HEAD(&cookie->msi_page_list);
+		cookie->type = type;
+	}
+	return cookie;
 }
 
 int iommu_dma_init(void)
@@ -62,25 +97,53 @@ int iommu_dma_init(void)
  */
 int iommu_get_dma_cookie(struct iommu_domain *domain)
 {
+	if (domain->iova_cookie)
+		return -EEXIST;
+
+	domain->iova_cookie = cookie_alloc(IOMMU_DMA_IOVA_COOKIE);
+	if (!domain->iova_cookie)
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL(iommu_get_dma_cookie);
+
+/**
+ * iommu_get_msi_cookie - Acquire just MSI remapping resources
+ * @domain: IOMMU domain to prepare
+ * @base: Start address of IOVA region for MSI mappings
+ *
+ * Users who manage their own IOVA allocation and do not want DMA API support,
+ * but would still like to take advantage of automatic MSI remapping, can use
+ * this to initialise their own domain appropriately. Users should reserve a
+ * contiguous IOVA region, starting at @base, large enough to accommodate the
+ * number of PAGE_SIZE mappings necessary to cover every MSI doorbell address
+ * used by the devices attached to @domain.
+ */
+int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
+{
 	struct iommu_dma_cookie *cookie;
 
+	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+		return -EINVAL;
+
 	if (domain->iova_cookie)
 		return -EEXIST;
 
-	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
+	cookie = cookie_alloc(IOMMU_DMA_MSI_COOKIE);
 	if (!cookie)
 		return -ENOMEM;
 
-	spin_lock_init(&cookie->msi_lock);
-	INIT_LIST_HEAD(&cookie->msi_page_list);
+	cookie->msi_iova = base;
 	domain->iova_cookie = cookie;
 	return 0;
 }
-EXPORT_SYMBOL(iommu_get_dma_cookie);
+EXPORT_SYMBOL(iommu_get_msi_cookie);
 
 /**
  * iommu_put_dma_cookie - Release a domain's DMA mapping resources
- * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
+ * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() or
+ *          iommu_get_msi_cookie()
  *
  * IOMMU drivers should normally call this from their domain_free callback.
  */
@@ -92,7 +155,7 @@ void iommu_put_dma_cookie(struct iommu_domain *domain)
 	if (!cookie)
 		return;
 
-	if (cookie->iovad.granule)
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule)
 		put_iova_domain(&cookie->iovad);
 
 	list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list) {
@@ -104,21 +167,99 @@ void iommu_put_dma_cookie(struct iommu_domain *domain)
 }
 EXPORT_SYMBOL(iommu_put_dma_cookie);
 
-static void iova_reserve_pci_windows(struct pci_dev *dev,
-		struct iova_domain *iovad)
+/**
+ * iommu_dma_get_resv_regions - Reserved region driver helper
+ * @dev: Device from iommu_get_resv_regions()
+ * @list: Reserved region list from iommu_get_resv_regions()
+ *
+ * IOMMU drivers can use this to implement their .get_resv_regions callback
+ * for general non-IOMMU-specific reservations. Currently, this covers host
+ * bridge windows for PCI devices.
+ */
+void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
 {
-	struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus);
+	struct pci_host_bridge *bridge;
 	struct resource_entry *window;
-	unsigned long lo, hi;
 
+	if (!dev_is_pci(dev))
+		return;
+
+	bridge = pci_find_host_bridge(to_pci_dev(dev)->bus);
 	resource_list_for_each_entry(window, &bridge->windows) {
+		struct iommu_resv_region *region;
+		phys_addr_t start;
+		size_t length;
+
 		if (resource_type(window->res) != IORESOURCE_MEM)
 			continue;
 
-		lo = iova_pfn(iovad, window->res->start - window->offset);
-		hi = iova_pfn(iovad, window->res->end - window->offset);
+		start = window->res->start - window->offset;
+		length = window->res->end - window->res->start + 1;
+		region = iommu_alloc_resv_region(start, length, 0,
+				IOMMU_RESV_RESERVED);
+		if (!region)
+			return;
+
+		list_add_tail(&region->list, list);
+	}
+}
+EXPORT_SYMBOL(iommu_dma_get_resv_regions);
+
+static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
+		phys_addr_t start, phys_addr_t end)
+{
+	struct iova_domain *iovad = &cookie->iovad;
+	struct iommu_dma_msi_page *msi_page;
+	int i, num_pages;
+
+	start -= iova_offset(iovad, start);
+	num_pages = iova_align(iovad, end - start) >> iova_shift(iovad);
+
+	msi_page = kcalloc(num_pages, sizeof(*msi_page), GFP_KERNEL);
+	if (!msi_page)
+		return -ENOMEM;
+
+	for (i = 0; i < num_pages; i++) {
+		msi_page[i].phys = start;
+		msi_page[i].iova = start;
+		INIT_LIST_HEAD(&msi_page[i].list);
+		list_add(&msi_page[i].list, &cookie->msi_page_list);
+		start += iovad->granule;
+	}
+
+	return 0;
+}
+
+static int iova_reserve_iommu_regions(struct device *dev,
+		struct iommu_domain *domain)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	struct iommu_resv_region *region;
+	LIST_HEAD(resv_regions);
+	int ret = 0;
+
+	iommu_get_resv_regions(dev, &resv_regions);
+	list_for_each_entry(region, &resv_regions, list) {
+		unsigned long lo, hi;
+
+		/* We ARE the software that manages these! */
+		if (region->type == IOMMU_RESV_SW_MSI)
+			continue;
+
+		lo = iova_pfn(iovad, region->start);
+		hi = iova_pfn(iovad, region->start + region->length - 1);
 		reserve_iova(iovad, lo, hi);
+
+		if (region->type == IOMMU_RESV_MSI)
+			ret = cookie_init_hw_msi_region(cookie, region->start,
+					region->start + region->length);
+		if (ret)
+			break;
 	}
+	iommu_put_resv_regions(dev, &resv_regions);
+
+	return ret;
 }
 
 /**
@@ -136,11 +277,12 @@ static void iova_reserve_pci_windows(struct pci_dev *dev,
 int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		u64 size, struct device *dev)
 {
-	struct iova_domain *iovad = cookie_iovad(domain);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
 	unsigned long order, base_pfn, end_pfn;
 
-	if (!iovad)
-		return -ENODEV;
+	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
+		return -EINVAL;
 
 	/* Use the smallest supported page size for IOVA granularity */
 	order = __ffs(domain->pgsize_bitmap);
@@ -160,22 +302,37 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		end_pfn = min_t(unsigned long, end_pfn,
 				domain->geometry.aperture_end >> order);
 	}
+	/*
+	 * PCI devices may have larger DMA masks, but still prefer allocating
+	 * within a 32-bit mask to avoid DAC addressing. Such limitations don't
+	 * apply to the typical platform device, so for those we may as well
+	 * leave the cache limit at the top of their range to save an rb_last()
+	 * traversal on every allocation.
+	 */
+	if (dev && dev_is_pci(dev))
+		end_pfn &= DMA_BIT_MASK(32) >> order;
 
-	/* All we can safely do with an existing domain is enlarge it */
+	/* start_pfn is always nonzero for an already-initialised domain */
 	if (iovad->start_pfn) {
 		if (1UL << order != iovad->granule ||
-		    base_pfn != iovad->start_pfn ||
-		    end_pfn < iovad->dma_32bit_pfn) {
+		    base_pfn != iovad->start_pfn) {
 			pr_warn("Incompatible range for DMA domain\n");
 			return -EFAULT;
 		}
-		iovad->dma_32bit_pfn = end_pfn;
-	} else {
-		init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn);
-		if (dev && dev_is_pci(dev))
-			iova_reserve_pci_windows(to_pci_dev(dev), iovad);
+		/*
+		 * If we have devices with different DMA masks, move the free
+		 * area cache limit down for the benefit of the smaller one.
+		 */
+		iovad->dma_32bit_pfn = min(end_pfn, iovad->dma_32bit_pfn);
+
+		return 0;
 	}
-	return 0;
+
+	init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn);
+	if (!dev)
+		return 0;
+
+	return iova_reserve_iommu_regions(dev, domain);
 }
 EXPORT_SYMBOL(iommu_dma_init_domain);
 
@@ -643,11 +800,12 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iommu_dma_msi_page *msi_page;
-	struct iova_domain *iovad = &cookie->iovad;
+	struct iova_domain *iovad = cookie_iovad(domain);
 	struct iova *iova;
 	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+	size_t size = cookie_msi_granule(cookie);
 
-	msi_addr &= ~(phys_addr_t)iova_mask(iovad);
+	msi_addr &= ~(phys_addr_t)(size - 1);
 	list_for_each_entry(msi_page, &cookie->msi_page_list, list)
 		if (msi_page->phys == msi_addr)
 			return msi_page;
@@ -656,13 +814,18 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	if (!msi_page)
 		return NULL;
 
-	iova = __alloc_iova(domain, iovad->granule, dma_get_mask(dev));
-	if (!iova)
-		goto out_free_page;
-
 	msi_page->phys = msi_addr;
-	msi_page->iova = iova_dma_addr(iovad, iova);
-	if (iommu_map(domain, msi_page->iova, msi_addr, iovad->granule, prot))
+	if (iovad) {
+		iova = __alloc_iova(domain, size, dma_get_mask(dev));
+		if (!iova)
+			goto out_free_page;
+		msi_page->iova = iova_dma_addr(iovad, iova);
+	} else {
+		msi_page->iova = cookie->msi_iova;
+		cookie->msi_iova += size;
+	}
+
+	if (iommu_map(domain, msi_page->iova, msi_addr, size, prot))
 		goto out_free_iova;
 
 	INIT_LIST_HEAD(&msi_page->list);
@@ -670,7 +833,10 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	return msi_page;
 
 out_free_iova:
-	__free_iova(iovad, iova);
+	if (iovad)
+		__free_iova(iovad, iova);
+	else
+		cookie->msi_iova -= size;
 out_free_page:
 	kfree(msi_page);
 	return NULL;
@@ -711,7 +877,7 @@ void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg)
 		msg->data = ~0U;
 	} else {
 		msg->address_hi = upper_32_bits(msi_page->iova);
-		msg->address_lo &= iova_mask(&cookie->iovad);
+		msg->address_lo &= cookie_msi_granule(cookie) - 1;
 		msg->address_lo += lower_32_bits(msi_page->iova);
 	}
 }