VT-d: replace all-contiguous page tables by superpage mappings

When a page table ends up with all contiguous entries (including all
identical attributes), it can be replaced by a superpage entry at the
next higher level. The page table itself can then be scheduled for
freeing.

The adjustment to LEVEL_MASK is merely to avoid leaving a latent trap
for whenever we (and obviously hardware) start supporting 512G mappings.

Note that cache sync-ing is likely more strict than necessary. This is
both to be on the safe side as well as to maintain the pattern of all
updates of (potentially) live tables being accompanied by a flush (if so
needed).

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Paul Durrant <paul@xen.org>

diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index 745c7bae0dec426ff87633d3a9fd82ef84d577fa..35545bfaef9bae509292d42c02f871cefb06fdd8 100644 (file)
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -2211,14 +2211,35 @@ static int __must_check cf_check intel_iommu_map_page(
      * While the (ab)use of PTE_kind_table here allows to save some work in
      * the function, the main motivation for it is that it avoids a so far
      * unexplained hang during boot (while preparing Dom0) on a Westmere
-     * based laptop.
+     * based laptop.  This also has the intended effect of terminating the
+     * loop when super pages aren't supported anymore at the next level.
      */
-    pt_update_contig_markers(&page->val,
-                             address_level_offset(dfn_to_daddr(dfn), level),
-                             level,
-                             (hd->platform_ops->page_sizes &
-                              (1UL << level_to_offset_bits(level + 1))
-                              ? PTE_kind_leaf : PTE_kind_table));
+    while ( pt_update_contig_markers(&page->val,
+                                     address_level_offset(dfn_to_daddr(dfn), level),
+                                     level,
+                                     (hd->platform_ops->page_sizes &
+                                      (1UL << level_to_offset_bits(level + 1))
+                                       ? PTE_kind_leaf : PTE_kind_table)) )
+    {
+        struct page_info *pg = maddr_to_page(pg_maddr);
+
+        unmap_vtd_domain_page(page);
+
+        new.val &= ~(LEVEL_MASK << level_to_offset_bits(level));
+        dma_set_pte_superpage(new);
+
+        pg_maddr = addr_to_dma_page_maddr(d, dfn_to_daddr(dfn), ++level,
+                                          flush_flags, false);
+        BUG_ON(pg_maddr < PAGE_SIZE);
+
+        page = map_vtd_domain_page(pg_maddr);
+        pte = &page[address_level_offset(dfn_to_daddr(dfn), level)];
+        *pte = new;
+        iommu_sync_cache(pte, sizeof(*pte));
+
+        *flush_flags |= IOMMU_FLUSHF_modified | IOMMU_FLUSHF_all;
+        iommu_queue_free_pgtable(hd, pg);
+    }
 
     spin_unlock(&hd->arch.mapping_lock);
     unmap_vtd_domain_page(page);

diff --git a/xen/drivers/passthrough/vtd/iommu.h b/xen/drivers/passthrough/vtd/iommu.h
index 7c3fe40150fe5962ec5149d232fafba586e5dc46..78aa8a96f5a01b7a5fb01d5ebcb3a934c0a51f29 100644 (file)
--- a/xen/drivers/passthrough/vtd/iommu.h
+++ b/xen/drivers/passthrough/vtd/iommu.h
@@ -232,7 +232,7 @@ struct context_entry {
 
 /* page table handling */
 #define LEVEL_STRIDE       (9)
-#define LEVEL_MASK         ((1 << LEVEL_STRIDE) - 1)
+#define LEVEL_MASK         (PTE_NUM - 1UL)
 #define PTE_NUM            (1 << LEVEL_STRIDE)
 #define level_to_agaw(val) ((val) - 2)
 #define agaw_to_level(val) ((val) + 2)