Merge pull request #1171 from hjelmn/v2.x_patcher_threads

rcache: fix deadlock in multi-threaded environments

Author: jsquyres

opal/mca/btl/vader/btl_vader_module.c

@@ -12,7 +12,7 @@
  *                         All rights reserved.
  * Copyright (c) 2006-2007 Voltaire. All rights reserved.
  * Copyright (c) 2009      Cisco Systems, Inc.  All rights reserved.
- * Copyright (c) 2010-2015 Los Alamos National Security, LLC. All rights
+ * Copyright (c) 2010-2016 Los Alamos National Security, LLC. All rights
  *                         reserved.
  * Copyright (c) 2014-2015 Intel, Inc. All rights reserved.
  * Copyright (c) 2014-2015 Research Organization for Information Science
@@ -528,6 +528,17 @@ static void mca_btl_vader_endpoint_constructor (mca_btl_vader_endpoint_t *ep)
     ep->fifo = NULL;
 }
 
+#if OPAL_BTL_VADER_HAVE_XPMEM
+static int mca_btl_vader_endpoint_rcache_cleanup (mca_mpool_base_registration_t *reg, void *ctx)
+{
+    struct mca_rcache_base_module_t *rcache = (struct mca_rcache_base_module_t *) ctx;
+    /* otherwise dereg will fail on assert */
+    reg->ref_count = 0;
+    (void) rcache->rcache_delete (rcache, reg);
+    return OPAL_SUCCESS;
+}
+#endif
+
 static void mca_btl_vader_endpoint_destructor (mca_btl_vader_endpoint_t *ep)
 {
     OBJ_DESTRUCT(&ep->pending_frags);
@@ -537,21 +548,10 @@ static void mca_btl_vader_endpoint_destructor (mca_btl_vader_endpoint_t *ep)
     if (MCA_BTL_VADER_XPMEM == mca_btl_vader_component.single_copy_mechanism) {
         if (ep->segment_data.xpmem.rcache) {
             /* clean out the registration cache */
-            const int nregs = 100;
-            mca_mpool_base_registration_t *regs[nregs];
-            int reg_cnt;
-
-            do {
-                reg_cnt = ep->segment_data.xpmem.rcache->rcache_find_all(ep->segment_data.xpmem.rcache, 0, (size_t)-1,
-                                                                          regs, nregs);
-
-                for (int i = 0 ; i < reg_cnt ; ++i) {
-                    /* otherwise dereg will fail on assert */
-                    regs[i]->ref_count = 0;
-                    OBJ_RELEASE(regs[i]);
-                }
-            } while (reg_cnt == nregs);
-
+            (void) ep->segment_data.xpmem.rcache->rcache_iterate (ep->segment_data.xpmem.rcache,
+                                                                  NULL, (size_t) -1,
+                                                                  mca_btl_vader_endpoint_rcache_cleanup,
+                                                                  (void *) ep->segment_data.xpmem.rcache);
             ep->segment_data.xpmem.rcache = NULL;
         }
 

opal/mca/mpool/grdma/mpool_grdma.h

@@ -11,7 +11,7 @@
  * Copyright (c) 2004-2005 The Regents of the University of California.
  *                         All rights reserved.
  * Copyright (c) 2006      Voltaire. All rights reserved.
- * Copyright (c) 2011-2015 Los Alamos National Security, LLC. All rights
+ * Copyright (c) 2011-2016 Los Alamos National Security, LLC. All rights
  *                         reserved.
  *
  * $COPYRIGHT$
@@ -28,6 +28,7 @@
 
 #include "opal_config.h"
 #include "opal/class/opal_list.h"
+#include "opal/class/opal_lifo.h"
 #include "opal/mca/event/event.h"
 #include "opal/mca/mpool/mpool.h"
 #if HAVE_SYS_MMAN_H
@@ -42,7 +43,7 @@ struct mca_mpool_grdma_pool_t {
     opal_list_item_t super;
     char *pool_name;
     opal_list_t lru_list;
-    opal_list_t gc_list;
+    opal_lifo_t gc_lifo;
     struct mca_rcache_base_module_t *rcache;
 };
 typedef struct mca_mpool_grdma_pool_t mca_mpool_grdma_pool_t;