intel-iommu: integrate DMA CMA

This adds support for the DMA Contiguous Memory Allocator for
intel-iommu.  This change enables dma_alloc_coherent() to allocate big
contiguous memory.

It is achieved in the same way as nommu_dma_ops currently does, i.e.
trying to allocate memory by dma_alloc_from_contiguous() and
alloc_pages() is used as a fallback.

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 25 insertions, 8 deletions

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index f256ffc02e29..6bb32773c3ac 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -39,6 +39,7 @@
 #include <linux/dmi.h>
 #include <linux/pci-ats.h>
 #include <linux/memblock.h>
+#include <linux/dma-contiguous.h>
 #include <asm/irq_remapping.h>
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
@@ -3193,7 +3194,7 @@ static void *intel_alloc_coherent(struct device *dev, size_t size,
                                   dma_addr_t *dma_handle, gfp_t flags,
                                   struct dma_attrs *attrs)
 {
-        void *vaddr;
+        struct page *page = NULL;
         int order;
 
         size = PAGE_ALIGN(size);
@@ -3208,17 +3209,31 @@ static void *intel_alloc_coherent(struct device *dev, size_t size,
                         flags |= GFP_DMA32;
         }
 
-        vaddr = (void *)__get_free_pages(flags, order);
-        if (!vaddr)
+        if (flags & __GFP_WAIT) {
+                unsigned int count = size >> PAGE_SHIFT;
+
+                page = dma_alloc_from_contiguous(dev, count, order);
+                if (page && iommu_no_mapping(dev) &&
+                    page_to_phys(page) + size > dev->coherent_dma_mask) {
+                        dma_release_from_contiguous(dev, page, count);
+                        page = NULL;
+                }
+        }
+
+        if (!page)
+                page = alloc_pages(flags, order);
+        if (!page)
                 return NULL;
-        memset(vaddr, 0, size);
+        memset(page_address(page), 0, size);
 
-        *dma_handle = __intel_map_single(dev, virt_to_bus(vaddr), size,
+        *dma_handle = __intel_map_single(dev, page_to_phys(page), size,
                                          DMA_BIDIRECTIONAL,
                                          dev->coherent_dma_mask);
         if (*dma_handle)
-                return vaddr;
-        free_pages((unsigned long)vaddr, order);
+                return page_address(page);
+        if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+                __free_pages(page, order);
+
         return NULL;
 }
 
@@ -3226,12 +3241,14 @@ static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
                                 dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
         int order;
+        struct page *page = virt_to_page(vaddr);
 
         size = PAGE_ALIGN(size);
         order = get_order(size);
 
         intel_unmap_page(dev, dma_handle, size, DMA_BIDIRECTIONAL, NULL);
-        free_pages((unsigned long)vaddr, order);
+        if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+                __free_pages(page, order);
 }
 
 static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,