1 files changed, 78 insertions, 47 deletions

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index d991d40f797f..a2e96a5fd9a7 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -19,9 +19,11 @@
 #include <linux/iova.h>
 #include <linux/irq.h>
 #include <linux/mm.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
+#include <linux/crash_dump.h>
 
 struct iommu_dma_msi_page {
 	struct list_head	list;
@@ -43,7 +45,6 @@ struct iommu_dma_cookie {
 		dma_addr_t		msi_iova;
 	};
 	struct list_head		msi_page_list;
-	spinlock_t			msi_lock;
 
 	/* Domain for flush queue callback; NULL if flush queue not in use */
 	struct iommu_domain		*fq_domain;
@@ -62,7 +63,6 @@ static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
 
 	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
 	if (cookie) {
-		spin_lock_init(&cookie->msi_lock);
 		INIT_LIST_HEAD(&cookie->msi_page_list);
 		cookie->type = type;
 	}
@@ -303,13 +303,15 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		u64 size, struct device *dev)
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
-	struct iova_domain *iovad = &cookie->iovad;
 	unsigned long order, base_pfn;
+	struct iova_domain *iovad;
 	int attr;
 
 	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
 		return -EINVAL;
 
+	iovad = &cookie->iovad;
+
 	/* Use the smallest supported page size for IOVA granularity */
 	order = __ffs(domain->pgsize_bitmap);
 	base_pfn = max_t(unsigned long, 1, base >> order);
@@ -351,6 +353,21 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	return iova_reserve_iommu_regions(dev, domain);
 }
 
+static int iommu_dma_deferred_attach(struct device *dev,
+		struct iommu_domain *domain)
+{
+	const struct iommu_ops *ops = domain->ops;
+
+	if (!is_kdump_kernel())
+		return 0;
+
+	if (unlikely(ops->is_attach_deferred &&
+			ops->is_attach_deferred(domain, dev)))
+		return iommu_attach_device(domain, dev);
+
+	return 0;
+}
+
 /**
  * dma_info_to_prot - Translate DMA API directions and attributes to IOMMU API
  *                    page flags.
@@ -381,7 +398,7 @@ static int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
 }
 
 static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
-		size_t size, dma_addr_t dma_limit, struct device *dev)
+		size_t size, u64 dma_limit, struct device *dev)
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
@@ -403,11 +420,10 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
 		iova_len = roundup_pow_of_two(iova_len);
 
-	if (dev->bus_dma_mask)
-		dma_limit &= dev->bus_dma_mask;
+	dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit);
 
 	if (domain->geometry.force_aperture)
-		dma_limit = min(dma_limit, domain->geometry.aperture_end);
+		dma_limit = min(dma_limit, (u64)domain->geometry.aperture_end);
 
 	/* Try to get PCI devices a SAC address */
 	if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
@@ -444,18 +460,23 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	size_t iova_off = iova_offset(iovad, dma_addr);
+	struct iommu_iotlb_gather iotlb_gather;
+	size_t unmapped;
 
 	dma_addr -= iova_off;
 	size = iova_align(iovad, size + iova_off);
+	iommu_iotlb_gather_init(&iotlb_gather);
+
+	unmapped = iommu_unmap_fast(domain, dma_addr, size, &iotlb_gather);
+	WARN_ON(unmapped != size);
 
-	WARN_ON(iommu_unmap_fast(domain, dma_addr, size) != size);
 	if (!cookie->fq_domain)
-		iommu_tlb_sync(domain);
+		iommu_tlb_sync(domain, &iotlb_gather);
 	iommu_dma_free_iova(cookie, dma_addr, size);
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
-		size_t size, int prot)
+		size_t size, int prot, u64 dma_mask)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
@@ -463,13 +484,16 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 	size_t iova_off = iova_offset(iovad, phys);
 	dma_addr_t iova;
 
+	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
+		return DMA_MAPPING_ERROR;
+
 	size = iova_align(iovad, size + iova_off);
 
-	iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
+	iova = iommu_dma_alloc_iova(domain, size, dma_mask, dev);
 	if (!iova)
 		return DMA_MAPPING_ERROR;
 
-	if (iommu_map(domain, iova, phys - iova_off, size, prot)) {
+	if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) {
 		iommu_dma_free_iova(cookie, iova, size);
 		return DMA_MAPPING_ERROR;
 	}
@@ -541,15 +565,6 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	return pages;
 }
 
-static struct page **__iommu_dma_get_pages(void *cpu_addr)
-{
-	struct vm_struct *area = find_vm_area(cpu_addr);
-
-	if (!area || !area->pages)
-		return NULL;
-	return area->pages;
-}
-
 /**
  * iommu_dma_alloc_remap - Allocate and map a buffer contiguous in IOVA space
  * @dev: Device to allocate memory for. Must be a real device
@@ -581,6 +596,9 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 
 	*dma_handle = DMA_MAPPING_ERROR;
 
+	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
+		return NULL;
+
 	min_size = alloc_sizes & -alloc_sizes;
 	if (min_size < PAGE_SIZE) {
 		min_size = PAGE_SIZE;
@@ -613,11 +631,11 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 			arch_dma_prep_coherent(sg_page(sg), sg->length);
 	}
 
-	if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, ioprot)
+	if (iommu_map_sg_atomic(domain, iova, sgt.sgl, sgt.orig_nents, ioprot)
 			< size)
 		goto out_free_sg;
 
-	vaddr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
+	vaddr = dma_common_pages_remap(pages, size, prot,
 			__builtin_return_address(0));
 	if (!vaddr)
 		goto out_unmap;
@@ -661,7 +679,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev,
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	arch_sync_dma_for_cpu(dev, phys, size, dir);
+	arch_sync_dma_for_cpu(phys, size, dir);
 }
 
 static void iommu_dma_sync_single_for_device(struct device *dev,
@@ -673,7 +691,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev,
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	arch_sync_dma_for_device(dev, phys, size, dir);
+	arch_sync_dma_for_device(phys, size, dir);
 }
 
 static void iommu_dma_sync_sg_for_cpu(struct device *dev,
@@ -687,7 +705,7 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,
 		return;
 
 	for_each_sg(sgl, sg, nelems, i)
-		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+		arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
 }
 
 static void iommu_dma_sync_sg_for_device(struct device *dev,
@@ -701,7 +719,7 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,
 		return;
 
 	for_each_sg(sgl, sg, nelems, i)
-		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+		arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
 }
 
 static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
@@ -713,10 +731,10 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	int prot = dma_info_to_prot(dir, coherent, attrs);
 	dma_addr_t dma_handle;
 
-	dma_handle =__iommu_dma_map(dev, phys, size, prot);
+	dma_handle = __iommu_dma_map(dev, phys, size, prot, dma_get_mask(dev));
 	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    dma_handle != DMA_MAPPING_ERROR)
-		arch_sync_dma_for_device(dev, phys, size, dir);
+		arch_sync_dma_for_device(phys, size, dir);
 	return dma_handle;
 }
 
@@ -823,6 +841,9 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	unsigned long mask = dma_get_seg_boundary(dev);
 	int i;
 
+	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
+		return 0;
+
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
 
@@ -873,7 +894,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	 * We'll leave any physical concatenation to the IOMMU driver's
 	 * implementation - it knows better than we do.
 	 */
-	if (iommu_map_sg(domain, iova, sg, nents, prot) < iova_len)
+	if (iommu_map_sg_atomic(domain, iova, sg, nents, prot) < iova_len)
 		goto out_free_iova;
 
 	return __finalise_sg(dev, sg, nents, iova);
@@ -913,7 +934,8 @@ static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	return __iommu_dma_map(dev, phys, size,
-			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO);
+			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
+			dma_get_mask(dev));
 }
 
 static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
@@ -938,10 +960,10 @@ static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
 		 * If it the address is remapped, then it's either non-coherent
 		 * or highmem CMA, or an iommu_dma_alloc_remap() construction.
 		 */
-		pages = __iommu_dma_get_pages(cpu_addr);
+		pages = dma_common_find_pages(cpu_addr);
 		if (!pages)
 			page = vmalloc_to_page(cpu_addr);
-		dma_common_free_remap(cpu_addr, alloc_size, VM_USERMAP);
+		dma_common_free_remap(cpu_addr, alloc_size);
 	} else {
 		/* Lowmem means a coherent atomic or CMA allocation */
 		page = virt_to_page(cpu_addr);
@@ -965,18 +987,21 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
 {
 	bool coherent = dev_is_dma_coherent(dev);
 	size_t alloc_size = PAGE_ALIGN(size);
+	int node = dev_to_node(dev);
 	struct page *page = NULL;
 	void *cpu_addr;
 
 	page = dma_alloc_contiguous(dev, alloc_size, gfp);
 	if (!page)
+		page = alloc_pages_node(node, gfp, get_order(alloc_size));
+	if (!page)
 		return NULL;
 
 	if (IS_ENABLED(CONFIG_DMA_REMAP) && (!coherent || PageHighMem(page))) {
 		pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
 
 		cpu_addr = dma_common_contiguous_remap(page, alloc_size,
-				VM_USERMAP, prot, __builtin_return_address(0));
+				prot, __builtin_return_address(0));
 		if (!cpu_addr)
 			goto out_free_pages;
 
@@ -1016,7 +1041,8 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	if (!cpu_addr)
 		return NULL;
 
-	*handle = __iommu_dma_map(dev, page_to_phys(page), size, ioprot);
+	*handle = __iommu_dma_map(dev, page_to_phys(page), size, ioprot,
+			dev->coherent_dma_mask);
 	if (*handle == DMA_MAPPING_ERROR) {
 		__iommu_dma_free(dev, size, cpu_addr);
 		return NULL;
@@ -1042,7 +1068,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		return -ENXIO;
 
 	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
-		struct page **pages = __iommu_dma_get_pages(cpu_addr);
+		struct page **pages = dma_common_find_pages(cpu_addr);
 
 		if (pages)
 			return __iommu_dma_mmap(pages, size, vma);
@@ -1064,7 +1090,7 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 	int ret;
 
 	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
-		struct page **pages = __iommu_dma_get_pages(cpu_addr);
+		struct page **pages = dma_common_find_pages(cpu_addr);
 
 		if (pages) {
 			return sg_alloc_table_from_pages(sgt, pages,
@@ -1083,6 +1109,13 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 	return ret;
 }
 
+static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+
+	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
@@ -1098,6 +1131,7 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.sync_sg_for_device	= iommu_dma_sync_sg_for_device,
 	.map_resource		= iommu_dma_map_resource,
 	.unmap_resource		= iommu_dma_unmap_resource,
+	.get_merge_boundary	= iommu_dma_get_merge_boundary,
 };
 
 /*
@@ -1141,7 +1175,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 		if (msi_page->phys == msi_addr)
 			return msi_page;
 
-	msi_page = kzalloc(sizeof(*msi_page), GFP_ATOMIC);
+	msi_page = kzalloc(sizeof(*msi_page), GFP_KERNEL);
 	if (!msi_page)
 		return NULL;
 
@@ -1169,25 +1203,22 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
 {
 	struct device *dev = msi_desc_to_dev(desc);
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-	struct iommu_dma_cookie *cookie;
 	struct iommu_dma_msi_page *msi_page;
-	unsigned long flags;
+	static DEFINE_MUTEX(msi_prepare_lock); /* see below */
 
 	if (!domain || !domain->iova_cookie) {
 		desc->iommu_cookie = NULL;
 		return 0;
 	}
 
-	cookie = domain->iova_cookie;
-
 	/*
-	 * We disable IRQs to rule out a possible inversion against
-	 * irq_desc_lock if, say, someone tries to retarget the affinity
-	 * of an MSI from within an IPI handler.
+	 * In fact the whole prepare operation should already be serialised by
+	 * irq_domain_mutex further up the callchain, but that's pretty subtle
+	 * on its own, so consider this locking as failsafe documentation...
 	 */
-	spin_lock_irqsave(&cookie->msi_lock, flags);
+	mutex_lock(&msi_prepare_lock);
 	msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain);
-	spin_unlock_irqrestore(&cookie->msi_lock, flags);
+	mutex_unlock(&msi_prepare_lock);
 
 	msi_desc_set_iommu_cookie(desc, msi_page);