iommu/vt-d: Use second level for GPA->HPA translation

The IOMMU VT-d implementation uses the first level for GPA->HPA translation
by default. Although both the first level and the second level could handle
the DMA translation, they're different in some way. For example, the second
level translation has separate controls for the Access/Dirty page tracking.
With the first level translation, there's no such control. On the other
hand, the second level translation has the page-level control for forcing
snoop, but the first level only has global control with pasid granularity.

This uses the second level for GPA->HPA translation so that we can provide
a consistent hardware interface for use cases like dirty page tracking for
live migration.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20210926114535.923263-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20211014053839.727419-6-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index ec9ceb2dcf57efd26067e98aa24536d496977cbd..1c26a7a012ce1c6c13594e13de28c5952da9cfb4 100644 (file)
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1991,9 +1991,18 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
  * Check and return whether first level is used by default for
  * DMA translation.
  */
-static bool first_level_by_default(void)
+static bool first_level_by_default(unsigned int type)
 {
-       return scalable_mode_support() && intel_cap_flts_sanity();
+       /* Only SL is available in legacy mode */
+       if (!scalable_mode_support())
+               return false;
+
+       /* Only level (either FL or SL) is available, just use it */
+       if (intel_cap_flts_sanity() ^ intel_cap_slts_sanity())
+               return intel_cap_flts_sanity();
+
+       /* Both levels are available, decide it based on domain type */
+       return type != IOMMU_DOMAIN_UNMANAGED;
 }
 
 static struct dmar_domain *alloc_domain(unsigned int type)
@@ -2006,7 +2015,7 @@ static struct dmar_domain *alloc_domain(unsigned int type)
 
        memset(domain, 0, sizeof(*domain));
        domain->nid = NUMA_NO_NODE;
-       if (first_level_by_default())
+       if (first_level_by_default(type))
                domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
        domain->has_iotlb_device = false;
        INIT_LIST_HEAD(&domain->devices);