coll/basic: fix segmentation fault in neighborhood collectives if the degree

of the topology is higher than the communicator size

It is possible to have a topology degree higher than the size of the communicator.
For example, a periodic cartesian communicator on MPI_COMM_SELF. This will leave
the neighborhood collectives with a request buffer that is too small.

This commits introduces a semantic change :
from now, c_topo must be set before invoking coll_select

ompi/mca/coll/basic/coll_basic_module.c

@@ -13,6 +13,8 @@
  * Copyright (c) 2012      Sandia National Laboratories. All rights reserved.
  * Copyright (c) 2013      Los Alamos National Security, LLC. All rights
  *                         reserved.
+ * Copyright (c) 2014      Research Organization for Information Science
+ *                         and Technology (RIST). All rights reserved.
  * $COPYRIGHT$
  * 
  * Additional copyrights may follow
@@ -28,6 +30,8 @@
 #include "mpi.h"
 #include "ompi/mca/coll/coll.h"
 #include "ompi/mca/coll/base/base.h"
+#include "ompi/mca/topo/topo.h"
+#include "ompi/mca/topo/base/base.h"
 #include "coll_basic.h"
 
 
@@ -70,7 +74,36 @@ mca_coll_basic_comm_query(struct ompi_communicator_t *comm,
     } else {
         size = ompi_comm_size(comm);
     }
-    basic_module->mccb_num_reqs = size * 2;
+    size *= 2;
+    if (OMPI_COMM_IS_CART(comm)) {
+        int cart_size;
+        mca_topo_base_comm_cart_2_2_0_t *cart;
+        assert (NULL != comm->c_topo);
+        cart = comm->c_topo->mtc.cart;
+        cart_size = cart->ndims * 4;
+        if (cart_size > size) {
+            size = cart_size;
+        }
+    } else if (OMPI_COMM_IS_GRAPH(comm)) {
+        int rank, degree;
+        assert (NULL != comm->c_topo);
+        rank = ompi_comm_rank (comm);
+        mca_topo_base_graph_neighbors_count (comm, rank, &degree);
+        degree *= 2;
+        if (degree > size) {
+            size = degree;
+        }
+    } else if (OMPI_COMM_IS_DIST_GRAPH(comm)) {
+        int dist_graph_size;
+        mca_topo_base_comm_dist_graph_2_2_0_t *dist_graph;
+        assert (NULL != comm->c_topo);
+        dist_graph = comm->c_topo->mtc.dist_graph;
+        dist_graph_size = dist_graph->indegree + dist_graph->outdegree;
+        if (dist_graph_size > size) {
+            size = dist_graph_size;
+        }
+    }
+    basic_module->mccb_num_reqs = size;
     basic_module->mccb_reqs = (ompi_request_t**) 
         malloc(sizeof(ompi_request_t *) * basic_module->mccb_num_reqs);
 

ompi/mca/topo/base/topo_base_cart_create.c

@@ -162,20 +162,24 @@ int mca_topo_base_cart_create(mca_topo_base_module_t *topo,
         return MPI_ERR_INTERN;
     }
 
+    assert(NULL == new_comm->c_topo);
+    assert(!(new_comm->c_flags & OMPI_COMM_CART));
+    new_comm->c_topo           = topo;
+    new_comm->c_topo->mtc.cart = cart;
+    new_comm->c_topo->reorder  = reorder;
+    new_comm->c_flags         |= OMPI_COMM_CART;
     ret = ompi_comm_enable(old_comm, new_comm,
                            new_rank, num_procs, topo_procs);
     if (OMPI_SUCCESS != ret) {
         /* something wrong happened during setting the communicator */
+        new_comm->c_topo = NULL;
+        new_comm->c_flags &= ~OMPI_COMM_CART;
         free(topo_procs);
         OBJ_RELEASE(cart);
         ompi_comm_free (&new_comm);
         return ret;
     }
 
-    new_comm->c_topo           = topo;
-    new_comm->c_topo->mtc.cart = cart;
-    new_comm->c_topo->reorder  = reorder;
-    new_comm->c_flags         |= OMPI_COMM_CART;
     *comm_topo = new_comm;
 
     if( MPI_UNDEFINED == new_rank ) {

ompi/mca/topo/base/topo_base_dist_graph_create.c

@@ -288,28 +288,71 @@ int mca_topo_base_dist_graph_create(mca_topo_base_module_t* module,
 {
     int err;
 
-    if( OMPI_SUCCESS != (err = ompi_comm_create(comm_old,
-                                                comm_old->c_local_group,
-                                                newcomm)) ) {
-        OBJ_RELEASE(module);
-        return err;
+    ompi_proc_t **topo_procs = NULL;
+    int num_procs, ret, rank, i;
+    ompi_communicator_t *new_comm;
+    mca_topo_base_comm_dist_graph_2_2_0_t* topo;
+    num_procs = ompi_comm_size(comm_old);
+    rank = ompi_comm_rank(comm_old);
+    topo_procs = (ompi_proc_t**)malloc(num_procs * sizeof(ompi_proc_t *));
+    if(OMPI_GROUP_IS_DENSE(comm_old->c_local_group)) {
+        memcpy(topo_procs, 
+               comm_old->c_local_group->grp_proc_pointers,
+               num_procs * sizeof(ompi_proc_t *));
+    } else {
+        for(i = 0 ; i < num_procs; i++) {
+            topo_procs[i] = ompi_group_peer_lookup(comm_old->c_local_group,i);
+        }
+    }
+    new_comm = ompi_comm_allocate(num_procs, 0);
+    if (NULL == new_comm) {
+        free(topo_procs);
+        return OMPI_ERR_OUT_OF_RESOURCE;
     }
-
-    assert(NULL == (*newcomm)->c_topo);
-    (*newcomm)->c_topo             = module;
-    (*newcomm)->c_topo->reorder    = reorder;
-    (*newcomm)->c_flags           |= OMPI_COMM_DIST_GRAPH;
-
     err = mca_topo_base_dist_graph_distribute(module,
-                                              *newcomm, 
+                                              comm_old, 
                                               n, nodes,
                                               degrees, targets, 
                                               weights,
-                                              &((*newcomm)->c_topo->mtc.dist_graph));
+                                              &topo);
     if( OMPI_SUCCESS != err ) {
+        free(topo_procs);
         ompi_comm_free(newcomm);
+        return err;
     }
-    return err;
+
+    assert(NULL == new_comm->c_topo);
+    new_comm->c_topo             = module;
+    new_comm->c_topo->reorder    = reorder;
+    new_comm->c_flags           |= OMPI_COMM_DIST_GRAPH;
+    new_comm->c_topo->mtc.dist_graph = topo;
+
+    ret = ompi_comm_enable(comm_old, new_comm,
+                           rank, num_procs, topo_procs);
+    if (OMPI_SUCCESS != ret) {
+        if ( NULL != topo->in ) {
+            free(topo->in);
+        }
+        if ( NULL != topo->out ) {
+            free(topo->out);
+        }
+        if ( NULL != topo->inw ) {
+            free(topo->inw);
+        }
+        if ( NULL != topo->outw ) {
+            free(topo->outw);
+        }
+        free(topo);
+        free(topo_procs);
+        new_comm->c_topo             = NULL;
+        new_comm->c_flags           &= ~OMPI_COMM_DIST_GRAPH;
+        new_comm->c_topo->mtc.dist_graph = NULL;
+        ompi_comm_free (&new_comm);
+        return ret;
+    }
+    *newcomm = new_comm;
+
+    return OMPI_SUCCESS;
 }
 
 static void mca_topo_base_comm_dist_graph_2_2_0_construct(mca_topo_base_comm_dist_graph_2_2_0_t * dist_graph) {

ompi/mca/topo/base/topo_base_graph_create.c

@@ -10,7 +10,7 @@
  * Copyright (c) 2004-2005 The Regents of the University of California.
  *                         All rights reserved.
  * Copyright (c) 2012-2013 Inria.  All rights reserved.
- * Copyright (c) 2014 Cisco Systems, Inc.  All rights reserved.
+ * Copyright (c) 2014      Cisco Systems, Inc.  All rights reserved.
  * Copyright (c) 2014      Research Organization for Information Science
  *                         and Technology (RIST). All rights reserved.
  * $COPYRIGHT$
@@ -123,19 +123,22 @@ int mca_topo_base_graph_create(mca_topo_base_module_t *topo,
         return OMPI_ERR_OUT_OF_RESOURCE;
     }
 
+    new_comm->c_topo            = topo;
+    new_comm->c_topo->mtc.graph = graph;
+    new_comm->c_flags          |= OMPI_COMM_GRAPH;
+    new_comm->c_topo->reorder   = reorder;
+
     ret = ompi_comm_enable(old_comm, new_comm,
                            new_rank, num_procs, topo_procs);
     if (OMPI_SUCCESS != ret) {
+        new_comm->c_topo            = NULL;
+        new_comm->c_flags          &= ~OMPI_COMM_GRAPH;
         free(topo_procs);
         OBJ_RELEASE(graph);
         ompi_comm_free (&new_comm);
         return ret;
     }
     
-    new_comm->c_topo            = topo;
-    new_comm->c_topo->mtc.graph = graph;
-    new_comm->c_flags          |= OMPI_COMM_GRAPH;
-    new_comm->c_topo->reorder   = reorder;
     *comm_topo = new_comm;
 
     if( MPI_UNDEFINED == new_rank ) {