iommupt: Add the Intel VT-d second stage page table format

The VT-d second stage format is almost the same as the x86 PAE format,
except the bit encodings in the PTE are different and a few new PTE
features, like force coherency are present.

Among all the formats it is unique in not having a designated present bit.

Comparing the performance of several operations to the existing version:

iommu_map()
   pgsz  ,avg new,old ns, min new,old ns  , min % (+ve is better)
     2^12,     53,66    ,      50,64      ,  21.21
     2^21,     59,70    ,      56,67      ,  16.16
     2^30,     54,66    ,      52,63      ,  17.17
 256*2^12,    384,524   ,     337,516     ,  34.34
 256*2^21,    387,632   ,     336,626     ,  46.46
 256*2^30,    376,629   ,     323,623     ,  48.48

iommu_unmap()
   pgsz  ,avg new,old ns, min new,old ns  , min % (+ve is better)
     2^12,     67,86    ,      63,84      ,  25.25
     2^21,     64,84    ,      59,80      ,  26.26
     2^30,     59,78    ,      56,74      ,  24.24
 256*2^12,    216,335   ,     198,317     ,  37.37
 256*2^21,    245,350   ,     232,344     ,  32.32
 256*2^30,    248,345   ,     226,339     ,  33.33

Cc: Tina Zhang <tina.zhang@intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

2 files changed, 29 insertions, 0 deletions

diff --git a/include/linux/generic_pt/common.h b/include/linux/generic_pt/common.h
index 883069e32952..6a9a1acb5aad 100644
--- a/include/linux/generic_pt/common.h
+++ b/include/linux/generic_pt/common.h
@@ -157,6 +157,24 @@ enum {
 	PT_FEAT_AMDV1_FORCE_COHERENCE,
 };
 
+struct pt_vtdss {
+	struct pt_common common;
+};
+
+enum {
+	/*
+	 * The PTEs are set to prevent cache incoherent traffic, such as PCI no
+	 * snoop. This is set either at creation time or before the first map
+	 * operation.
+	 */
+	PT_FEAT_VTDSS_FORCE_COHERENCE = PT_FEAT_FMT_START,
+	/*
+	 * Prevent creating read-only PTEs. Used to work around HW errata
+	 * ERRATA_772415_SPR17.
+	 */
+	PT_FEAT_VTDSS_FORCE_WRITEABLE,
+};
+
 struct pt_x86_64 {
 	struct pt_common common;
 };
diff --git a/include/linux/generic_pt/iommu.h b/include/linux/generic_pt/iommu.h
index 21132e342a79..cfe05a77f86b 100644
--- a/include/linux/generic_pt/iommu.h
+++ b/include/linux/generic_pt/iommu.h
@@ -262,6 +262,17 @@ IOMMU_FORMAT(amdv1, amdpt);
 struct pt_iommu_amdv1_mock_hw_info;
 IOMMU_PROTOTYPES(amdv1_mock);
 
+struct pt_iommu_vtdss_cfg {
+	struct pt_iommu_cfg common;
+};
+
+struct pt_iommu_vtdss_hw_info {
+	u64 ssptptr;
+	u8 aw;
+};
+
+IOMMU_FORMAT(vtdss, vtdss_pt);
+
 struct pt_iommu_x86_64_cfg {
 	struct pt_iommu_cfg common;
 };