[Xen-devel] [PATCH 2 of 3] x86/mm: Teach paging to page table-based p2m

[Andres Lagar-Cavilla <andres@xxxxxxxxxxxxxxxx>]

 xen/arch/x86/mm/p2m-pt.c |  56 +++++++++++++++++++++++++++++++++--------------
 1 files changed, 39 insertions(+), 17 deletions(-)


The p2m-pt.c code, used by both shadow and AMD NPT modes, was not aware of
paging types, and the implications those types have on p2m entries. Add support
to the page table-based p2m to understand the paging types. This is a necessary
step towards enabling memory paging on AMD NPT mode, but not yet the full
solution.

Tested not to break neither shadow mode nor "normal" (i.e. no paging) AMD NPT
mode.

Signed-off-by: Andres Lagar-Cavilla <andres@xxxxxxxxxxxxxxxx>

diff -r e4013da987e2 -r d6c3c77ad749 xen/arch/x86/mm/p2m-pt.c
--- a/xen/arch/x86/mm/p2m-pt.c
+++ b/xen/arch/x86/mm/p2m-pt.c
@@ -53,6 +53,20 @@
 #define P2M_BASE_FLAGS \
         (_PAGE_PRESENT | _PAGE_USER | _PAGE_DIRTY | _PAGE_ACCESSED)
 
+#ifdef __x86_64__
+/* l1e_from_pfn is not designed to have INVALID_MFN stored. The 0xff..ff
+ * value tramples over the higher-order bits used for flags (NX, p2mt, 
+ * etc.) This happens for paging entries. Thus we do this clip/unclip
+ * juggle for l1 entries only (no paging superpages!) */
+#define EFF_MFN_WIDTH       (PADDR_BITS-PAGE_SHIFT) /* 40 bits */
+#define clipped_mfn(mfn)    ((mfn) & ((1UL << EFF_MFN_WIDTH) - 1))
+#define unclip_mfn(mfn)     (((mfn) == clipped_mfn(INVALID_MFN)) ? \
+                                INVALID_MFN : (mfn))
+#else
+#define clipped_mfn(mfn)    (mfn)
+#define unclip_mfn(mfn)     (mfn)
+#endif /* __x86_64__ */
+
 static unsigned long p2m_type_to_flags(p2m_type_t t, mfn_t mfn)
 {
     unsigned long flags;
@@ -77,6 +91,9 @@ static unsigned long p2m_type_to_flags(p
     case p2m_invalid:
     case p2m_mmio_dm:
     case p2m_populate_on_demand:
+    case p2m_ram_paging_out:
+    case p2m_ram_paged:
+    case p2m_ram_paging_in:
     default:
         return flags;
     case p2m_ram_ro:
@@ -168,7 +185,7 @@ p2m_next_level(struct p2m_domain *p2m, m
                                       shift, max)) )
         return 0;
 
-    /* PoD: Not present doesn't imply empty. */
+    /* PoD/paging: Not present doesn't imply empty. */
     if ( !l1e_get_flags(*p2m_entry) )
     {
         struct page_info *pg;
@@ -384,8 +401,8 @@ p2m_set_entry(struct p2m_domain *p2m, un
                                    0, L1_PAGETABLE_ENTRIES);
         ASSERT(p2m_entry);
         
-        if ( mfn_valid(mfn) || (p2mt == p2m_mmio_direct) )
-            entry_content = l1e_from_pfn(mfn_x(mfn),
+        if ( mfn_valid(mfn) || (p2mt == p2m_mmio_direct) || 
p2m_is_paging(p2mt) )
+            entry_content = l1e_from_pfn(clipped_mfn(mfn_x(mfn)),
                                          p2m_type_to_flags(p2mt, mfn));
         else
             entry_content = l1e_empty();
@@ -393,7 +410,7 @@ p2m_set_entry(struct p2m_domain *p2m, un
         if ( entry_content.l1 != 0 )
         {
             p2m_add_iommu_flags(&entry_content, 0, iommu_pte_flags);
-            old_mfn = l1e_get_pfn(*p2m_entry);
+            old_mfn = unclip_mfn(l1e_get_pfn(*p2m_entry));
         }
         /* level 1 entry */
         p2m->write_p2m_entry(p2m, gfn, p2m_entry, table_mfn, entry_content, 1);
@@ -615,11 +632,12 @@ pod_retry_l1:
                            sizeof(l1e));
             
     if ( ret == 0 ) {
+        unsigned long l1e_mfn = unclip_mfn(l1e_get_pfn(l1e));
         p2mt = p2m_flags_to_type(l1e_get_flags(l1e));
-        ASSERT(l1e_get_pfn(l1e) != INVALID_MFN || !p2m_is_ram(p2mt));
+        ASSERT( (l1e_mfn != INVALID_MFN || !p2m_is_ram(p2mt)) ||
+                (l1e_mfn == INVALID_MFN && p2m_is_paging(p2mt)) );
 
-        if ( p2m_flags_to_type(l1e_get_flags(l1e))
-             == p2m_populate_on_demand )
+        if ( p2mt == p2m_populate_on_demand )
         {
             /* The read has succeeded, so we know that the mapping
              * exits at this point.  */
@@ -641,7 +659,7 @@ pod_retry_l1:
         }
 
         if ( p2m_is_valid(p2mt) || p2m_is_grant(p2mt) )
-            mfn = _mfn(l1e_get_pfn(l1e));
+            mfn = _mfn(l1e_mfn);
         else 
             /* XXX see above */
             p2mt = p2m_mmio_dm;
@@ -663,6 +681,8 @@ p2m_gfn_to_mfn(struct p2m_domain *p2m, u
     paddr_t addr = ((paddr_t)gfn) << PAGE_SHIFT;
     l2_pgentry_t *l2e;
     l1_pgentry_t *l1e;
+    unsigned long l1e_flags;
+    p2m_type_t l1t;
 
     ASSERT(paging_mode_translate(p2m->domain));
 
@@ -781,10 +801,12 @@ pod_retry_l2:
     l1e = map_domain_page(mfn_x(mfn));
     l1e += l1_table_offset(addr);
 pod_retry_l1:
-    if ( (l1e_get_flags(*l1e) & _PAGE_PRESENT) == 0 )
+    l1e_flags = l1e_get_flags(*l1e);
+    l1t = p2m_flags_to_type(l1e_flags);
+    if ( ((l1e_flags & _PAGE_PRESENT) == 0) && (!p2m_is_paging(l1t)) )
     {
         /* PoD: Try to populate */
-        if ( p2m_flags_to_type(l1e_get_flags(*l1e)) == p2m_populate_on_demand )
+        if ( l1t == p2m_populate_on_demand )
         {
             if ( q != p2m_query ) {
                 if ( !p2m_pod_demand_populate(p2m, gfn, PAGE_ORDER_4K, q) )
@@ -792,15 +814,15 @@ pod_retry_l1:
             } else
                 *t = p2m_populate_on_demand;
         }
-    
+ 
         unmap_domain_page(l1e);
         return _mfn(INVALID_MFN);
     }
-    mfn = _mfn(l1e_get_pfn(*l1e));
-    *t = p2m_flags_to_type(l1e_get_flags(*l1e));
+    mfn = _mfn(unclip_mfn(l1e_get_pfn(*l1e)));
+    *t = l1t;
     unmap_domain_page(l1e);
 
-    ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t));
+    ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t) || p2m_is_paging(*t));
     if ( page_order )
         *page_order = PAGE_ORDER_4K;
     return (p2m_is_valid(*t) || p2m_is_grant(*t)) ? mfn : _mfn(INVALID_MFN);
@@ -914,7 +936,7 @@ static void p2m_change_type_global(struc
                     flags = l1e_get_flags(l1e[i1]);
                     if ( p2m_flags_to_type(flags) != ot )
                         continue;
-                    mfn = l1e_get_pfn(l1e[i1]);
+                    mfn = unclip_mfn(l1e_get_pfn(l1e[i1]));
                     gfn = i1 + (i2 + (i3
 #if CONFIG_PAGING_LEVELS >= 4
                                        + (i4 * L3_PAGETABLE_ENTRIES)
@@ -923,7 +945,7 @@ static void p2m_change_type_global(struc
                            * L2_PAGETABLE_ENTRIES) * L1_PAGETABLE_ENTRIES; 
                     /* create a new 1le entry with the new type */
                     flags = p2m_type_to_flags(nt, _mfn(mfn));
-                    l1e_content = l1e_from_pfn(mfn, flags);
+                    l1e_content = l1e_from_pfn(clipped_mfn(mfn), flags);
                     p2m->write_p2m_entry(p2m, gfn, &l1e[i1],
                                          l1mfn, l1e_content, 1);
                 }
@@ -1073,7 +1095,7 @@ long p2m_pt_audit_p2m(struct p2m_domain 
                                 entry_count++;
                             continue;
                         }
-                        mfn = l1e_get_pfn(l1e[i1]);
+                        mfn = unclip_mfn(l1e_get_pfn(l1e[i1]));
                         ASSERT(mfn_valid(_mfn(mfn)));
                         m2pfn = get_gpfn_from_mfn(mfn);
                         if ( m2pfn != gfn &&

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel