From: Hongyan Xia <hongyxia@amazon.com>

When we do not have a direct map, archs_mfn_in_direct_map() will always
return false, thus init_node_heap() will allocate xenheap pages from an
existing node for the metadata of a new node. This means that the
metadata of a new node is in a different node, slowing down heap
allocation.

Since we now have early vmap, vmap the metadata locally in the new node.

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>

----

    Changes in v2:
        * vmap_contig_pages() was renamed to vmap_contig()
        * Fix indentation and coding style

    Changes from Hongyan's version:
        * arch_mfn_in_direct_map() was renamed to
          arch_mfns_in_direct_map()
        * Use vmap_contig_pages() rather than __vmap(...).
        * Add missing include (xen/vmap.h) so it compiles on Arm

diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c
index 52934ec5c1..42b9aaae1c 100644
--- a/xen/common/page_alloc.c
+++ b/xen/common/page_alloc.c
@@ -136,6 +136,7 @@
 #include <xen/sched.h>
 #include <xen/softirq.h>
 #include <xen/spinlock.h>
+#include <xen/vmap.h>
 
 #include <asm/flushtlb.h>
 #include <asm/numa.h>
@@ -604,22 +605,44 @@ static unsigned long init_node_heap(int node, unsigned long mfn,
         needed = 0;
     }
     else if ( *use_tail && nr >= needed &&
-              arch_mfns_in_directmap(mfn + nr - needed, needed) &&
               (!xenheap_bits ||
-               !((mfn + nr - 1) >> (xenheap_bits - PAGE_SHIFT))) )
+              !((mfn + nr - 1) >> (xenheap_bits - PAGE_SHIFT))) )
     {
-        _heap[node] = mfn_to_virt(mfn + nr - needed);
-        avail[node] = mfn_to_virt(mfn + nr - 1) +
-                      PAGE_SIZE - sizeof(**avail) * NR_ZONES;
+        if ( arch_mfns_in_directmap(mfn + nr - needed, needed) )
+        {
+            _heap[node] = mfn_to_virt(mfn + nr - needed);
+            avail[node] = mfn_to_virt(mfn + nr - 1) +
+                          PAGE_SIZE - sizeof(**avail) * NR_ZONES;
+        }
+        else
+        {
+            mfn_t needed_start = _mfn(mfn + nr - needed);
+
+            _heap[node] = vmap_contig(needed_start, needed);
+            BUG_ON(!_heap[node]);
+            avail[node] = (void *)(_heap[node]) + (needed << PAGE_SHIFT) -
+                          sizeof(**avail) * NR_ZONES;
+        }
     }
     else if ( nr >= needed &&
-              arch_mfns_in_directmap(mfn, needed) &&
               (!xenheap_bits ||
-               !((mfn + needed - 1) >> (xenheap_bits - PAGE_SHIFT))) )
+              !((mfn + needed - 1) >> (xenheap_bits - PAGE_SHIFT))) )
     {
-        _heap[node] = mfn_to_virt(mfn);
-        avail[node] = mfn_to_virt(mfn + needed - 1) +
-                      PAGE_SIZE - sizeof(**avail) * NR_ZONES;
+        if ( arch_mfns_in_directmap(mfn, needed) )
+        {
+            _heap[node] = mfn_to_virt(mfn);
+            avail[node] = mfn_to_virt(mfn + needed - 1) +
+                          PAGE_SIZE - sizeof(**avail) * NR_ZONES;
+        }
+        else
+        {
+            mfn_t needed_start = _mfn(mfn);
+
+            _heap[node] = vmap_contig(needed_start, needed);
+            BUG_ON(!_heap[node]);
+            avail[node] = (void *)(_heap[node]) + (needed << PAGE_SHIFT) -
+                          sizeof(**avail) * NR_ZONES;
+        }
         *use_tail = false;
     }
     else if ( get_order_from_bytes(sizeof(**_heap)) ==
-- 
2.40.1