AMD/IOMMU: free all-empty page tables

When a page table ends up with no present entries left, it can be
replaced by a non-present entry at the next higher level. The page table
itself can then be scheduled for freeing.

Note that while its output isn't used there yet,
pt_update_contig_markers() right away needs to be called in all places
where entries get updated, not just the one where entries get cleared.

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

diff --git a/xen/drivers/passthrough/amd/iommu_map.c b/xen/drivers/passthrough/amd/iommu_map.c
index 7d4e0ba5878c82c10d9b344e862b3c1f722045cb..a50a6b79ab8638354b26dcc89c32a3db2fe40b61 100644 (file)
--- a/xen/drivers/passthrough/amd/iommu_map.c
+++ b/xen/drivers/passthrough/amd/iommu_map.c
@@ -21,6 +21,7 @@
 
 #include "iommu.h"
 
+#define CONTIG_MASK IOMMU_PTE_CONTIG_MASK
 #include <asm/pt-contig-markers.h>
 
 /* Given pfn and page table level, return pde index */
@@ -35,16 +36,20 @@ static unsigned int pfn_to_pde_idx(unsigned long pfn, unsigned int level)
 
 static union amd_iommu_pte clear_iommu_pte_present(unsigned long l1_mfn,
                                                    unsigned long dfn,
-                                                   unsigned int level)
+                                                   unsigned int level,
+                                                   bool *free)
 {
     union amd_iommu_pte *table, *pte, old;
+    unsigned int idx = pfn_to_pde_idx(dfn, level);
 
     table = map_domain_page(_mfn(l1_mfn));
-    pte = &table[pfn_to_pde_idx(dfn, level)];
+    pte = &table[idx];
     old = *pte;
 
     write_atomic(&pte->raw, 0);
 
+    *free = pt_update_contig_markers(&table->raw, idx, level, PTE_kind_null);
+
     unmap_domain_page(table);
 
     return old;
@@ -87,7 +92,11 @@ static union amd_iommu_pte set_iommu_pte_present(unsigned long pt_mfn,
     if ( !old.pr || old.next_level ||
          old.mfn != next_mfn ||
          old.iw != iw || old.ir != ir )
+    {
         set_iommu_pde_present(pde, next_mfn, 0, iw, ir);
+        pt_update_contig_markers(&table->raw, pfn_to_pde_idx(dfn, level),
+                                 level, PTE_kind_leaf);
+    }
     else
         old.pr = false; /* signal "no change" to the caller */
 
@@ -326,6 +335,9 @@ static int iommu_pde_from_dfn(struct domain *d, unsigned long dfn,
             smp_wmb();
             set_iommu_pde_present(pde, next_table_mfn, next_level, true,
                                   true);
+            pt_update_contig_markers(&next_table_vaddr->raw,
+                                     pfn_to_pde_idx(dfn, level),
+                                     level, PTE_kind_table);
 
             *flush_flags |= IOMMU_FLUSHF_modified;
         }
@@ -351,6 +363,9 @@ static int iommu_pde_from_dfn(struct domain *d, unsigned long dfn,
                 next_table_mfn = mfn_x(page_to_mfn(table));
                 set_iommu_pde_present(pde, next_table_mfn, next_level, true,
                                       true);
+                pt_update_contig_markers(&next_table_vaddr->raw,
+                                         pfn_to_pde_idx(dfn, level),
+                                         level, PTE_kind_table);
             }
             else /* should never reach here */
             {
@@ -487,8 +502,24 @@ int cf_check amd_iommu_unmap_page(
 
     if ( pt_mfn )
     {
+        bool free;
+
         /* Mark PTE as 'page not present'. */
-        old = clear_iommu_pte_present(pt_mfn, dfn_x(dfn), level);
+        old = clear_iommu_pte_present(pt_mfn, dfn_x(dfn), level, &free);
+
+        while ( unlikely(free) && ++level < hd->arch.amd.paging_mode )
+        {
+            struct page_info *pg = mfn_to_page(_mfn(pt_mfn));
+
+            if ( iommu_pde_from_dfn(d, dfn_x(dfn), level, &pt_mfn,
+                                    flush_flags, false) )
+                BUG();
+            BUG_ON(!pt_mfn);
+
+            clear_iommu_pte_present(pt_mfn, dfn_x(dfn), level, &free);
+            *flush_flags |= IOMMU_FLUSHF_all;
+            iommu_queue_free_pgtable(hd, pg);
+        }
     }
 
     spin_unlock(&hd->arch.mapping_lock);