[PATCH v2] x86/PoD: tighten conditions for checking super page

[PATCH v2] x86/PoD: tighten conditions for checking super page

[Jan Beulich]

[-- Attachment #1: Type: text/plain, Size: 1976 bytes --]

Since calling the function isn't cheap, try to avoid the call when we
know up front it won't help; see the code comment for details on those
conditions.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
---
v2: Adjust conditions and body of the if() to make them easier
    understandable, without altering behavior (requested by George).

--- a/xen/arch/x86/mm/p2m-pod.c
+++ b/xen/arch/x86/mm/p2m-pod.c
@@ -528,7 +528,6 @@ p2m_pod_decrease_reservation(struct doma
     if ( unlikely(d->is_dying) )
         goto out_unlock;
 
-recount:
     pod = nonpod = ram = 0;
 
     /* Figure out if we need to steal some freed memory for our cache */
@@ -568,15 +567,20 @@ recount:
         goto out_entry_check;
     }
 
-    /* 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)))
+    /*
+     * 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.
+     * No need to do this though if
+     * - order >= SUPERPAGE_ORDER (the loop below will take care of this)
+     * - not all of the pages were RAM (now knowing order < SUPERPAGE_ORDER)
+     */
+    if ( steal_for_cache && order < SUPERPAGE_ORDER && ram == (1 << order) &&
+         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;
+        pod = 1 << order;
+        ram = nonpod = 0;
+        ASSERT(steal_for_cache == (p2m->pod.entry_count > p2m->pod.count));
     }
 
     /* Process as long as:




[-- Attachment #2: x86-PoD-emerg-avoid-check-super.patch --]
[-- Type: text/plain, Size: 2025 bytes --]

x86/PoD: tighten conditions for checking super page

Since calling the function isn't cheap, try to avoid the call when we
know up front it won't help; see the code comment for details on those
conditions.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
---
v2: Adjust conditions and body of the if() to make them easier
    understandable, without altering behavior (requested by George).

--- a/xen/arch/x86/mm/p2m-pod.c
+++ b/xen/arch/x86/mm/p2m-pod.c
@@ -528,7 +528,6 @@ p2m_pod_decrease_reservation(struct doma
     if ( unlikely(d->is_dying) )
         goto out_unlock;
 
-recount:
     pod = nonpod = ram = 0;
 
     /* Figure out if we need to steal some freed memory for our cache */
@@ -568,15 +567,20 @@ recount:
         goto out_entry_check;
     }
 
-    /* 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)))
+    /*
+     * 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.
+     * No need to do this though if
+     * - order >= SUPERPAGE_ORDER (the loop below will take care of this)
+     * - not all of the pages were RAM (now knowing order < SUPERPAGE_ORDER)
+     */
+    if ( steal_for_cache && order < SUPERPAGE_ORDER && ram == (1 << order) &&
+         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;
+        pod = 1 << order;
+        ram = nonpod = 0;
+        ASSERT(steal_for_cache == (p2m->pod.entry_count > p2m->pod.count));
     }
 
     /* Process as long as:

[-- Attachment #3: Type: text/plain, Size: 126 bytes --]

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

Re: [PATCH v2] x86/PoD: tighten conditions for checking super page

[George Dunlap]

On 09/11/15 14:48, Jan Beulich wrote:
> Since calling the function isn't cheap, try to avoid the call when we
> know up front it won't help; see the code comment for details on those
> conditions.
> 
> Signed-off-by: Jan Beulich <jbeulich@suse.com>

Reviewed-by: George Dunlap <george.dunlap@citrix.com>

Sorry for the delay.