Merge tag 'iommu-fixes-v4.7-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU fixes from Joerg Roedel:
 "Two Fixes:

   - Intel VT-d fix for a suspend/resume issue, introduced with the
     scalability improvements in this cycle.

   - AMD IOMMU fix for systems that have unity mappings defined.  There
     was a race where translation got enabled before the unity mappings
     were in place.  This issue was seen on some HP servers"

* tag 'iommu-fixes-v4.7-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/amd: Fix unity mapping initialization race
  iommu/vt-d: Fix infinite loop in free_all_cpu_cached_iovas

2 files changed, 14 insertions, 4 deletions

diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index d091defc3426..59741ead7e15 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1568,13 +1568,23 @@ static int __init amd_iommu_init_pci(void)
                         break;
         }
 
+        /*
+         * Order is important here to make sure any unity map requirements are
+         * fulfilled. The unity mappings are created and written to the device
+         * table during the amd_iommu_init_api() call.
+         *
+         * After that we call init_device_table_dma() to make sure any
+         * uninitialized DTE will block DMA, and in the end we flush the caches
+         * of all IOMMUs to make sure the changes to the device table are
+         * active.
+         */
+        ret = amd_iommu_init_api();
+
         init_device_table_dma();
 
         for_each_iommu(iommu)
                 iommu_flush_all_caches(iommu);
 
-        ret = amd_iommu_init_api();
-
         if (!ret)
                 print_iommu_info();
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index cfe410eedaf0..323dac9900ba 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4602,13 +4602,13 @@ static void free_all_cpu_cached_iovas(unsigned int cpu)
         for (i = 0; i < g_num_of_iommus; i++) {
                 struct intel_iommu *iommu = g_iommus[i];
                 struct dmar_domain *domain;
-                u16 did;
+                int did;
 
                 if (!iommu)
                         continue;
 
                 for (did = 0; did < cap_ndoms(iommu->cap); did++) {
-                        domain = get_iommu_domain(iommu, did);
+                        domain = get_iommu_domain(iommu, (u16)did);
 
                         if (!domain)
                                 continue;