iommu/amd: Build io page-tables with cmpxchg64

This allows to build up the page-tables without holding any
locks. As a consequence it removes the need to pre-populate
dma_ops page-tables.

Signed-off-by: Joerg Roedel <jroedel@suse.de>

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 4c926dadb2816e79a05e2e0801b96cbbcdcb0ae4..ecdd3f7dfb89b2c5181231766ad235137f8ed3d0 100644 (file)
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1206,11 +1206,21 @@ static u64 *alloc_pte(struct protection_domain *domain,
        end_lvl = PAGE_SIZE_LEVEL(page_size);
 
        while (level > end_lvl) {
-               if (!IOMMU_PTE_PRESENT(*pte)) {
+               u64 __pte, __npte;
+
+               __pte = *pte;
+
+               if (!IOMMU_PTE_PRESENT(__pte)) {
                        page = (u64 *)get_zeroed_page(gfp);
                        if (!page)
                                return NULL;
-                       *pte = PM_LEVEL_PDE(level, virt_to_phys(page));
+
+                       __npte = PM_LEVEL_PDE(level, virt_to_phys(page));
+
+                       if (cmpxchg64(pte, __pte, __npte)) {
+                               free_page((unsigned long)page);
+                               continue;
+                       }
                }
 
                /* No level skipping support yet */
@@ -1607,7 +1617,7 @@ static unsigned long dma_ops_alloc_addresses(struct device *dev,
                address = dma_ops_area_alloc(dev, dom, pages,
                                             align_mask, dma_mask);
 
-               if (address == -1 && alloc_new_range(dom, true, GFP_ATOMIC))
+               if (address == -1 && alloc_new_range(dom, false, GFP_ATOMIC))
                        break;
        }