[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] [PATCH v4 5/7] mm: make MEMF_no_refcount pages safe to assign



Currently it is unsafe to assign a domheap page allocated with
MEMF_no_refcount to a domain because the domain't 'tot_pages' will not
be incremented, but will be decrement when the page is freed (since
free_domheap_pages() has no way of telling that the increment was skipped).

This patch allocates a new 'count_info' bit for a PGC_no_refcount flag
which is then used to mark domheap pages allocated with MEMF_no_refcount.
This then allows free_domheap_pages() to skip decrementing tot_pages when
appropriate and hence makes the pages safe to assign.

NOTE: The patch sets MEMF_no_refcount directly in alloc_domheap_pages()
      rather than in assign_pages() because the latter is called with
      MEMF_no_refcount by memory_exchange() as an optimization, to avoid
      too many calls to domain_adjust_tot_pages() (which acquires and
      releases the global 'heap_lock').

Signed-off-by: Paul Durrant <pdurrant@xxxxxxxxxx>
---
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Cc: George Dunlap <George.Dunlap@xxxxxxxxxxxxx>
Cc: Ian Jackson <ian.jackson@xxxxxxxxxxxxx>
Cc: Jan Beulich <jbeulich@xxxxxxxx>
Cc: Julien Grall <julien@xxxxxxx>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
Cc: Stefano Stabellini <sstabellini@xxxxxxxxxx>
Cc: Wei Liu <wl@xxxxxxx>
Cc: Volodymyr Babchuk <Volodymyr_Babchuk@xxxxxxxx>
Cc: "Roger Pau Monné" <roger.pau@xxxxxxxxxx>

v4:
 - New in v4
---
 xen/common/page_alloc.c  | 39 ++++++++++++++++++++++++++++-----------
 xen/include/asm-arm/mm.h |  5 ++++-
 xen/include/asm-x86/mm.h |  7 +++++--
 3 files changed, 37 insertions(+), 14 deletions(-)

diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c
index 919a270587..6103f14a4e 100644
--- a/xen/common/page_alloc.c
+++ b/xen/common/page_alloc.c
@@ -460,6 +460,9 @@ unsigned long domain_adjust_tot_pages(struct domain *d, 
long pages)
 {
     long dom_before, dom_after, dom_claimed, sys_before, sys_after;
 
+    if ( !pages )
+        goto out;
+
     ASSERT(spin_is_locked(&d->page_alloc_lock));
     d->tot_pages += pages;
 
@@ -1389,6 +1392,8 @@ static void free_heap_pages(
 
     for ( i = 0; i < (1 << order); i++ )
     {
+        ASSERT(!(pg[i].count_info & PGC_no_refcount));
+
         /*
          * Cannot assume that count_info == 0, as there are some corner cases
          * where it isn't the case and yet it isn't a bug:
@@ -2314,11 +2319,6 @@ struct page_info *alloc_domheap_pages(
 
     if ( memflags & MEMF_no_owner )
         memflags |= MEMF_no_refcount;
-    else if ( (memflags & MEMF_no_refcount) && d )
-    {
-        ASSERT(!(memflags & MEMF_no_refcount));
-        return NULL;
-    }
 
     if ( !dma_bitsize )
         memflags &= ~MEMF_no_dma;
@@ -2331,11 +2331,20 @@ struct page_info *alloc_domheap_pages(
                                   memflags, d)) == NULL)) )
          return NULL;
 
-    if ( d && !(memflags & MEMF_no_owner) &&
-         assign_pages(d, pg, order, memflags) )
+    if ( d && !(memflags & MEMF_no_owner) )
     {
-        free_heap_pages(pg, order, memflags & MEMF_no_scrub);
-        return NULL;
+        if ( assign_pages(d, pg, order, memflags) )
+        {
+            free_heap_pages(pg, order, memflags & MEMF_no_scrub);
+            return NULL;
+        }
+        if ( memflags & MEMF_no_refcount )
+        {
+            unsigned long i;
+
+            for ( i = 0; i < (1 << order); i++ )
+                pg[i].count_info |= PGC_no_refcount;
+        }
     }
 
     return pg;
@@ -2368,24 +2377,32 @@ void free_domheap_pages(struct page_info *pg, unsigned 
int order)
 
         if ( likely(d) && likely(d != dom_cow) )
         {
+            long pages = 0;
+
             /* NB. May recursively lock from relinquish_memory(). */
             spin_lock_recursive(&d->page_alloc_lock);
 
             for ( i = 0; i < (1 << order); i++ )
             {
+                unsigned long count_info = pg[i].count_info;
+
                 if ( pg[i].u.inuse.type_info & PGT_count_mask )
                 {
                     printk(XENLOG_ERR
                            "pg[%u] MFN %"PRI_mfn" c=%#lx o=%u v=%#lx t=%#x\n",
                            i, mfn_x(page_to_mfn(pg + i)),
-                           pg[i].count_info, pg[i].v.free.order,
+                           count_info, pg[i].v.free.order,
                            pg[i].u.free.val, pg[i].tlbflush_timestamp);
                     BUG();
                 }
                 arch_free_heap_page(d, &pg[i]);
+                if ( count_info & PGC_no_refcount )
+                    pg[i].count_info &= ~PGC_no_refcount;
+                else
+                    pages--;
             }
 
-            drop_dom_ref = !domain_adjust_tot_pages(d, -(1 << order));
+            drop_dom_ref = !domain_adjust_tot_pages(d, pages);
 
             spin_unlock_recursive(&d->page_alloc_lock);
 
diff --git a/xen/include/asm-arm/mm.h b/xen/include/asm-arm/mm.h
index 333efd3a60..1076cc9713 100644
--- a/xen/include/asm-arm/mm.h
+++ b/xen/include/asm-arm/mm.h
@@ -119,9 +119,12 @@ struct page_info
 #define PGC_state_offlined PG_mask(2, 9)
 #define PGC_state_free    PG_mask(3, 9)
 #define page_state_is(pg, st) (((pg)->count_info&PGC_state) == PGC_state_##st)
+/* Page is not reference counted */
+#define _PGC_no_refcount  PG_shift(10)
+#define PGC_no_refcount   PG_mask(1, 10)
 
 /* Count of references to this frame. */
-#define PGC_count_width   PG_shift(9)
+#define PGC_count_width   PG_shift(10)
 #define PGC_count_mask    ((1UL<<PGC_count_width)-1)
 
 /*
diff --git a/xen/include/asm-x86/mm.h b/xen/include/asm-x86/mm.h
index 2ca8882ad0..e75feea15e 100644
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -77,9 +77,12 @@
 #define PGC_state_offlined PG_mask(2, 9)
 #define PGC_state_free    PG_mask(3, 9)
 #define page_state_is(pg, st) (((pg)->count_info&PGC_state) == PGC_state_##st)
+/* Page is not reference counted */
+#define _PGC_no_refcount  PG_shift(10)
+#define PGC_no_refcount   PG_mask(1, 10)
 
- /* Count of references to this frame. */
-#define PGC_count_width   PG_shift(9)
+/* Count of references to this frame. */
+#define PGC_count_width   PG_shift(10)
 #define PGC_count_mask    ((1UL<<PGC_count_width)-1)
 
 /*
-- 
2.20.1


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.