[RFC PATCH v2] xen: free_domheap_pages: delay page scrub to idle loop

[Bob Liu <lliubbo@gmail.com>]

Because of page scrub, it's very slow to destroy a domain with large
memory.
It took around 10 minutes when destroy a guest of nearly 1 TB of memory.

[root@ca-test111 ~]# time xm des 5
real    10m51.582s
user    0m0.115s
sys     0m0.039s
[root@ca-test111 ~]#

There are two meanings to improve this situation.
1. Delay the page scrub in free_domheap_pages(), so that 'xl destroy xxx' can
return earlier.

2. But the real scrub time doesn't get improved a lot, we should consider put the
scrub job on all idle cpus in parallel. An obvious solution is add page to
a global list during free_domheap_pages(), and then whenever a cpu enter
idle_loop() it will try to isolate a page and scrub/free it.
Unfortunately this solution didn't work as expected in my testing, because
introduce a global list which also means we need a lock to protect that list.
The cost is too heavy!

So I use a percpu scrub page list in this patch, the tradeoff is we may not use
all idle cpus. It depends on free_domheap_pages() runs on which cpu.

Signed-off-by: Bob Liu <bob.liu@oracle.com>
---
 xen/arch/x86/domain.c   |    1 +
 xen/common/page_alloc.c |   32 +++++++++++++++++++++++++++++++-
 xen/include/xen/mm.h    |    1 +
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index 6fddd4c..f3f1260 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -119,6 +119,7 @@ static void idle_loop(void)
         (*pm_idle)();
         do_tasklet();
         do_softirq();
+        scrub_free_pages();
     }
 }
 
diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c
index 601319c..b2a0fc5 100644
--- a/xen/common/page_alloc.c
+++ b/xen/common/page_alloc.c
@@ -79,6 +79,8 @@ PAGE_LIST_HEAD(page_offlined_list);
 /* Broken page list, protected by heap_lock. */
 PAGE_LIST_HEAD(page_broken_list);
 
+DEFINE_PER_CPU(struct page_list_head , page_scrub_list);
+
 /*************************
  * BOOT-TIME ALLOCATOR
  */
@@ -633,6 +635,9 @@ static struct page_info *alloc_heap_pages(
                     goto found;
         } while ( zone-- > zone_lo ); /* careful: unsigned zone may wrap */
 
+        if ( scrub_free_pages() )
+            continue;
+
         if ( memflags & MEMF_exact_node )
             goto not_found;
 
@@ -1417,6 +1422,23 @@ void free_xenheap_pages(void *v, unsigned int order)
 #endif
 
 
+unsigned long scrub_free_pages(void)
+{
+    struct page_info *pg;
+    unsigned long nr_scrubed = 0;
+
+    /* Scrub around 400M memory every time */
+    while ( nr_scrubed < 100000 )
+    {
+        pg = page_list_remove_head( &this_cpu(page_scrub_list) );
+        if (!pg)
+            break;
+        scrub_one_page(pg);
+        free_heap_pages(pg, 0);
+        nr_scrubed++;
+    }
+    return nr_scrubed;
+}
 
 /*************************
  * DOMAIN-HEAP SUB-ALLOCATOR
@@ -1564,8 +1586,15 @@ void free_domheap_pages(struct page_info *pg, unsigned int order)
          * domain has died we assume responsibility for erasure.
          */
         if ( unlikely(d->is_dying) )
+        {
+            /*
+             * Add page to page_scrub_list to speed up domain destroy, those
+             * pages will be zeroed later by scrub_page_tasklet.
+             */
             for ( i = 0; i < (1 << order); i++ )
-                scrub_one_page(&pg[i]);
+                page_list_add_tail( &pg[i], &this_cpu(page_scrub_list) );
+            goto out;
+        }
 
         free_heap_pages(pg, order);
     }
@@ -1583,6 +1612,7 @@ void free_domheap_pages(struct page_info *pg, unsigned int order)
         drop_dom_ref = 0;
     }
 
+out:
     if ( drop_dom_ref )
         put_domain(d);
 }
diff --git a/xen/include/xen/mm.h b/xen/include/xen/mm.h
index b183189..3560335 100644
--- a/xen/include/xen/mm.h
+++ b/xen/include/xen/mm.h
@@ -355,6 +355,7 @@ static inline unsigned int get_order_from_pages(unsigned long nr_pages)
 }
 
 void scrub_one_page(struct page_info *);
+unsigned long scrub_free_pages(void);
 
 int xenmem_add_to_physmap_one(struct domain *d, unsigned int space,
                               domid_t foreign_domid,
-- 
1.7.10.4