x86/pv: rewrite how building PV dom0 handles domheap mappings

Building a PV dom0 is allocating from the domheap but uses it like the
xenheap. This is clearly wrong. Fix.

Signed-off-by: Hongyan Xia <hongyxia@amazon.com>
---
Changed in v2:
- use lXstart_mfn instead of lXstart_maddr.
- change the pattern on mpt_alloc to be closer to the original.

diff --git a/xen/arch/x86/pv/dom0_build.c b/xen/arch/x86/pv/dom0_build.c
index 2c198ece08cf45a9c52504280394dee50f74ea84..ad0dd5956c762a2bff85be74d641fd1ca74e553f 100644 (file)
--- a/xen/arch/x86/pv/dom0_build.c
+++ b/xen/arch/x86/pv/dom0_build.c
@@ -309,6 +309,10 @@ int __init dom0_construct_pv(struct domain *d,
     l3_pgentry_t *l3tab = NULL, *l3start = NULL;
     l2_pgentry_t *l2tab = NULL, *l2start = NULL;
     l1_pgentry_t *l1tab = NULL, *l1start = NULL;
+    mfn_t l4start_mfn = INVALID_MFN;
+    mfn_t l3start_mfn = INVALID_MFN;
+    mfn_t l2start_mfn = INVALID_MFN;
+    mfn_t l1start_mfn = INVALID_MFN;
 
     /*
      * This fully describes the memory layout of the initial domain. All
@@ -614,19 +618,21 @@ int __init dom0_construct_pv(struct domain *d,
     if ( !is_pv_32bit_domain(d) )
     {
         maddr_to_page(mpt_alloc)->u.inuse.type_info = PGT_l4_page_table;
-        l4start = l4tab = __va(mpt_alloc); mpt_alloc += PAGE_SIZE;
+        l4start_mfn = maddr_to_mfn(mpt_alloc); mpt_alloc += PAGE_SIZE;
+        l4start = l4tab = map_domain_page(l4start_mfn);
         clear_page(l4tab);
-        init_xen_l4_slots(l4tab, _mfn(virt_to_mfn(l4start)),
-                          d, INVALID_MFN, true);
-        v->arch.guest_table = pagetable_from_paddr(__pa(l4start));
+        init_xen_l4_slots(l4tab, l4start_mfn, d, INVALID_MFN, true);
+        v->arch.guest_table = pagetable_from_mfn(l4start_mfn);
     }
     else
     {
         /* Monitor table already created by switch_compat(). */
-        l4start = l4tab = __va(pagetable_get_paddr(v->arch.guest_table));
+        l4start_mfn = pagetable_get_mfn(v->arch.guest_table);
+        l4start = l4tab = map_domain_page(l4start_mfn);
         /* See public/xen.h on why the following is needed. */
         maddr_to_page(mpt_alloc)->u.inuse.type_info = PGT_l3_page_table;
-        l3start = __va(mpt_alloc); mpt_alloc += PAGE_SIZE;
+        l3start_mfn = maddr_to_mfn(mpt_alloc); mpt_alloc += PAGE_SIZE;
+        l3start = map_domain_page(l3start_mfn);
     }
 
     l4tab += l4_table_offset(v_start);
@@ -636,14 +642,18 @@ int __init dom0_construct_pv(struct domain *d,
         if ( !((unsigned long)l1tab & (PAGE_SIZE-1)) )
         {
             maddr_to_page(mpt_alloc)->u.inuse.type_info = PGT_l1_page_table;
-            l1start = l1tab = __va(mpt_alloc); mpt_alloc += PAGE_SIZE;
+            UNMAP_DOMAIN_PAGE(l1start);
+            l1start_mfn = maddr_to_mfn(mpt_alloc); mpt_alloc += PAGE_SIZE;
+            l1start = l1tab = map_domain_page(l1start_mfn);
             clear_page(l1tab);
             if ( count == 0 )
                 l1tab += l1_table_offset(v_start);
             if ( !((unsigned long)l2tab & (PAGE_SIZE-1)) )
             {
                 maddr_to_page(mpt_alloc)->u.inuse.type_info = PGT_l2_page_table;
-                l2start = l2tab = __va(mpt_alloc); mpt_alloc += PAGE_SIZE;
+                UNMAP_DOMAIN_PAGE(l2start);
+                l2start_mfn = maddr_to_mfn(mpt_alloc); mpt_alloc += PAGE_SIZE;
+                l2start = l2tab = map_domain_page(l2start_mfn);
                 clear_page(l2tab);
                 if ( count == 0 )
                     l2tab += l2_table_offset(v_start);
@@ -653,19 +663,22 @@ int __init dom0_construct_pv(struct domain *d,
                     {
                         maddr_to_page(mpt_alloc)->u.inuse.type_info =
                             PGT_l3_page_table;
-                        l3start = __va(mpt_alloc); mpt_alloc += PAGE_SIZE;
+                        UNMAP_DOMAIN_PAGE(l3start);
+                        l3start_mfn = maddr_to_mfn(mpt_alloc);
+                        mpt_alloc += PAGE_SIZE;
+                        l3start = map_domain_page(l3start_mfn);
                     }
                     l3tab = l3start;
                     clear_page(l3tab);
                     if ( count == 0 )
                         l3tab += l3_table_offset(v_start);
-                    *l4tab = l4e_from_paddr(__pa(l3start), L4_PROT);
+                    *l4tab = l4e_from_mfn(l3start_mfn, L4_PROT);
                     l4tab++;
                 }
-                *l3tab = l3e_from_paddr(__pa(l2start), L3_PROT);
+                *l3tab = l3e_from_mfn(l2start_mfn, L3_PROT);
                 l3tab++;
             }
-            *l2tab = l2e_from_paddr(__pa(l1start), L2_PROT);
+            *l2tab = l2e_from_mfn(l1start_mfn, L2_PROT);
             l2tab++;
         }
         if ( count < initrd_pfn || count >= initrd_pfn + PFN_UP(initrd_len) )
@@ -692,9 +705,11 @@ int __init dom0_construct_pv(struct domain *d,
             if ( !l3e_get_intpte(*l3tab) )
             {
                 maddr_to_page(mpt_alloc)->u.inuse.type_info = PGT_l2_page_table;
-                l2tab = __va(mpt_alloc); mpt_alloc += PAGE_SIZE;
-                clear_page(l2tab);
-                *l3tab = l3e_from_paddr(__pa(l2tab), L3_PROT);
+                UNMAP_DOMAIN_PAGE(l2start);
+                l2start_mfn = maddr_to_mfn(mpt_alloc); mpt_alloc += PAGE_SIZE;
+                l2start = map_domain_page(l2start_mfn);
+                clear_page(l2start);
+                *l3tab = l3e_from_mfn(l2start_mfn, L3_PROT);
             }
             if ( i == 3 )
                 l3e_get_page(*l3tab)->u.inuse.type_info |= PGT_pae_xen_l2;
@@ -705,9 +720,15 @@ int __init dom0_construct_pv(struct domain *d,
         unmap_domain_page(l2t);
     }
 
+    UNMAP_DOMAIN_PAGE(l1start);
+    UNMAP_DOMAIN_PAGE(l2start);
+    UNMAP_DOMAIN_PAGE(l3start);
+
     /* Pages that are part of page tables must be read only. */
     mark_pv_pt_pages_rdonly(d, l4start, vpt_start, nr_pt_pages);
 
+    UNMAP_DOMAIN_PAGE(l4start);
+
     /* Mask all upcalls... */
     for ( i = 0; i < XEN_LEGACY_MAX_VCPUS; i++ )
         shared_info(d, vcpu_info[i].evtchn_upcall_mask) = 1;
@@ -869,8 +890,12 @@ int __init dom0_construct_pv(struct domain *d,
      * !CONFIG_VIDEO case so the logic here can be simplified.
      */
     if ( pv_shim )
+    {
+        l4start = map_domain_page(l4start_mfn);
         pv_shim_setup_dom(d, l4start, v_start, vxenstore_start, vconsole_start,
                           vphysmap_start, si);
+        UNMAP_DOMAIN_PAGE(l4start);
+    }
 
     if ( is_pv_32bit_domain(d) )
         xlat_start_info(si, pv_shim ? XLAT_start_info_console_domU