[PATCH v5 03/15] x86/pv: Rewrite how building PV dom0 handles domheap mappings

[Alejandro Vallejo <alejandro.vallejo@cloud.com>]

From: Hongyan Xia <hongyxia@amazon.com>

Building a PV dom0 is allocating from the domheap but uses it like the
xenheap. Use the pages as they should be.

Signed-off-by: Hongyan Xia <hongyxia@amazon.com>
Signed-off-by: Julien Grall <jgrall@amazon.com>
Signed-off-by: Elias El Yandouzi <eliasely@amazon.com>
Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
---
v4->v5:
  * Bugfix: Don't map l4start with a mapcache and unmap with another.
            This is a revert to how it originally was in the series.
            i.e: UNMAP_DOMAIN_PAGE(l4start) before overriding current
                 and then re-mapping on the idle PTs if needed.
  * Simplify UNMAP_MAP_AND_ADVANCE removing the do-while(). It's not
    needed with the ({ x }) expression. Assignments return the
    assigned value, so the last line was not needed either.

v3->v4:
  * Reduce the scope of l{1,2,4}start_mfn variables
  * Make the macro `UNMAP_MAP_AND_ADVANCE` return the new virtual
address

v2->v3:
  * Fold following patch 'x86/pv: Map L4 page table for shim domain'

v1->v2:
  * Clarify the commit message
  * Break the patch in two parts

Changes since Hongyan's version:
  * Rebase
  * Remove spurious newline
---
 xen/arch/x86/pv/dom0_build.c | 61 +++++++++++++++++++++++++-----------
 1 file changed, 42 insertions(+), 19 deletions(-)

diff --git a/xen/arch/x86/pv/dom0_build.c b/xen/arch/x86/pv/dom0_build.c
index 08a4534d5c19..649412590e72 100644
--- a/xen/arch/x86/pv/dom0_build.c
+++ b/xen/arch/x86/pv/dom0_build.c
@@ -384,6 +384,8 @@ static int __init dom0_construct(struct boot_info *bi, 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 l3start_mfn = INVALID_MFN;
+    mfn_t l4start_mfn = INVALID_MFN;
 
     /*
      * This fully describes the memory layout of the initial domain. All
@@ -738,22 +740,30 @@ static int __init dom0_construct(struct boot_info *bi, struct domain *d)
         v->arch.pv.event_callback_cs    = FLAT_COMPAT_KERNEL_CS;
     }
 
+#define UNMAP_MAP_AND_ADVANCE(mfn_var, virt_var, maddr) ({  \
+    unmap_domain_page(virt_var);                            \
+    mfn_var = maddr_to_mfn(maddr);                          \
+    maddr += PAGE_SIZE;                                     \
+    virt_var = map_domain_page(mfn_var);                    \
+})
+
     if ( !compat )
     {
         maddr_to_page(mpt_alloc)->u.inuse.type_info = PGT_l4_page_table;
-        l4start = l4tab = __va(mpt_alloc); mpt_alloc += PAGE_SIZE;
+        l4tab = UNMAP_MAP_AND_ADVANCE(l4start_mfn, l4start, mpt_alloc);
         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;
+        UNMAP_MAP_AND_ADVANCE(l3start_mfn, l3start, mpt_alloc);
     }
 
     l4tab += l4_table_offset(v_start);
@@ -762,15 +772,17 @@ static int __init dom0_construct(struct boot_info *bi, struct domain *d)
     {
         if ( !((unsigned long)l1tab & (PAGE_SIZE-1)) )
         {
+            mfn_t l1start_mfn;
             maddr_to_page(mpt_alloc)->u.inuse.type_info = PGT_l1_page_table;
-            l1start = l1tab = __va(mpt_alloc); mpt_alloc += PAGE_SIZE;
+            l1tab = UNMAP_MAP_AND_ADVANCE(l1start_mfn, l1start, mpt_alloc);
             clear_page(l1tab);
             if ( count == 0 )
                 l1tab += l1_table_offset(v_start);
             if ( !((unsigned long)l2tab & (PAGE_SIZE-1)) )
             {
+                mfn_t l2start_mfn;
                 maddr_to_page(mpt_alloc)->u.inuse.type_info = PGT_l2_page_table;
-                l2start = l2tab = __va(mpt_alloc); mpt_alloc += PAGE_SIZE;
+                l2tab = UNMAP_MAP_AND_ADVANCE(l2start_mfn, l2start, mpt_alloc);
                 clear_page(l2tab);
                 if ( count == 0 )
                     l2tab += l2_table_offset(v_start);
@@ -780,19 +792,19 @@ static int __init dom0_construct(struct boot_info *bi, 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_MAP_AND_ADVANCE(l3start_mfn, l3start, mpt_alloc);
                     }
                     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) )
@@ -811,30 +823,37 @@ static int __init dom0_construct(struct boot_info *bi, struct domain *d)
 
     if ( compat )
     {
-        l2_pgentry_t *l2t;
-
         /* Ensure the first four L3 entries are all populated. */
         for ( i = 0, l3tab = l3start; i < 4; ++i, ++l3tab )
         {
             if ( !l3e_get_intpte(*l3tab) )
             {
+                mfn_t l2start_mfn;
                 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_MAP_AND_ADVANCE(l2start_mfn, l2start, mpt_alloc);
+                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;
         }
 
-        l2t = map_l2t_from_l3e(l3start[3]);
-        init_xen_pae_l2_slots(l2t, d);
-        unmap_domain_page(l2t);
+        UNMAP_DOMAIN_PAGE(l2start);
+        l2start = map_l2t_from_l3e(l3start[3]);
+        init_xen_pae_l2_slots(l2start, d);
     }
 
+#undef UNMAP_MAP_AND_ADVANCE
+
+    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, &flush_flags);
 
+    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;
@@ -1003,8 +1022,12 @@ static int __init dom0_construct(struct boot_info *bi, 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);
+    }
 
 #ifdef CONFIG_COMPAT
     if ( compat )
-- 
2.47.1