xen,pod: Try to reclaim superpages when ballooning down

Windows balloon drivers can typically only get 4k pages from the kernel,
and so hand them back at that level.  Try to regain superpages by checking
the superpage frame that the 4k page is in to see if we can reclaim the whole
thing for the PoD cache.

This also modifies p2m_pod_zero_check_superpage() to return SUPERPAGE_PAGES on
success.

v2:
 - Rewritten to simply to the check as in demand-fault case, without needing
   to know that the p2m entry is a superpage.
 - Also, took out the re-writing of the reclaim loop, leaving it optimized for
   4k pages (by far the most common case), and simplifying the patch.
v3:
 - Add SoB

Signed-off-by: George Dunlap <george.dunlap@eu.citrix.com>
Acked-by: Tim Deegan <tim@xen.org>
Committed-by: Tim Deegan <tim@xen.org>

diff --git a/xen/arch/x86/mm/p2m-pod.c b/xen/arch/x86/mm/p2m-pod.c
index 19ccc3b745ff703d697186c623b3299d4612bf45..dbdf966645aa0624aa76ed59742b3a31eb9fa3c9 100644 (file)
--- a/xen/arch/x86/mm/p2m-pod.c
+++ b/xen/arch/x86/mm/p2m-pod.c
@@ -488,6 +488,10 @@ p2m_pod_offline_or_broken_replace(struct page_info *p)
     return;
 }
 
+static int
+p2m_pod_zero_check_superpage(struct p2m_domain *p2m, unsigned long gfn);
+
+
 /* This function is needed for two reasons:
  * + To properly handle clearing of PoD entries
  * + To "steal back" memory being freed for the PoD cache, rather than
@@ -505,8 +509,8 @@ p2m_pod_decrease_reservation(struct domain *d,
     int i;
     struct p2m_domain *p2m = p2m_get_hostp2m(d);
 
-    int steal_for_cache = 0;
-    int pod = 0, nonpod = 0, ram = 0;
+    int steal_for_cache;
+    int pod, nonpod, ram;
 
     gfn_lock(p2m, gpfn, order);
     pod_lock(p2m);    
@@ -516,13 +520,15 @@ p2m_pod_decrease_reservation(struct domain *d,
     if ( p2m->pod.entry_count == 0 )
         goto out_unlock;
 
-    /* Figure out if we need to steal some freed memory for our cache */
-    steal_for_cache =  ( p2m->pod.entry_count > p2m->pod.count );
-
     if ( unlikely(d->is_dying) )
         goto out_unlock;
 
-    /* See what's in here. */
+recount:
+    pod = nonpod = ram = 0;
+
+    /* Figure out if we need to steal some freed memory for our cache */
+    steal_for_cache =  ( p2m->pod.entry_count > p2m->pod.count );
+
     /* FIXME: Add contiguous; query for PSE entries? */
     for ( i=0; i<(1<<order); i++)
     {
@@ -556,7 +562,16 @@ p2m_pod_decrease_reservation(struct domain *d,
         goto out_entry_check;
     }
 
-    /* FIXME: Steal contig 2-meg regions for cache */
+    /* Try to grab entire superpages if possible.  Since the common case is for drivers
+     * to pass back singleton pages, see if we can take the whole page back and mark the
+     * rest PoD. */
+    if ( steal_for_cache
+         && p2m_pod_zero_check_superpage(p2m, gpfn & ~(SUPERPAGE_PAGES-1)))
+    {
+        /* Since order may be arbitrary, we may have taken more or less
+         * than we were actually asked to; so just re-count from scratch */
+        goto recount;
+    }
 
     /* Process as long as:
      * + There are PoD entries to handle, or
@@ -758,6 +773,8 @@ p2m_pod_zero_check_superpage(struct p2m_domain *p2m, unsigned long gfn)
     p2m_pod_cache_add(p2m, mfn_to_page(mfn0), PAGE_ORDER_2M);
     p2m->pod.entry_count += SUPERPAGE_PAGES;
 
+    ret = SUPERPAGE_PAGES;
+
 out_reset:
     if ( reset )
         set_p2m_entry(p2m, gfn, mfn0, 9, type0, p2m->default_access);