v1.10.3: PSM/PSM2: Disable signal handler hijacking by default

ompi/mpi/java/c/mpi_MPI.c

@@ -12,7 +12,7 @@
  *                         All rights reserved.
  * Copyright (c) 2015      Los Alamos National Security, LLC.  All rights
  *                         reserved.
- * Copyright (c) 2015      Cisco Systems, Inc.  All rights reserved.
+ * Copyright (c) 2015-2016 Cisco Systems, Inc.  All rights reserved.
  * Copyright (c) 2015      Intel, Inc. All rights reserved.
  * Copyright (c) 2015      Research Organization for Information Science
  *                         and Technology (RIST). All rights reserved.
@@ -135,6 +135,10 @@ OBJ_CLASS_INSTANCE(ompi_java_buffer_t,
  */
 jint JNI_OnLoad(JavaVM *vm, void *reserved)
 {
+    // Ensure that PSM signal hijacking is disabled *before* loading
+    // the library (see comment in the function for more detail).
+    opal_init_psm();
+
     libmpi = dlopen("libmpi." OPAL_DYN_LIB_SUFFIX, RTLD_NOW | RTLD_GLOBAL);
 
 #if defined(HAVE_DL_INFO) && defined(HAVE_LIBGEN_H)

opal/runtime/opal.h

@@ -6,18 +6,19 @@
  * Copyright (c) 2004-2007 The University of Tennessee and The University
  *                         of Tennessee Research Foundation.  All rights
  *                         reserved.
- * Copyright (c) 2004-2005 High Performance Computing Center Stuttgart, 
+ * Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
  *                         University of Stuttgart.  All rights reserved.
  * Copyright (c) 2004-2005 The Regents of the University of California.
  *                         All rights reserved.
  * Copyright (c) 2008	   Sun Microsystems, Inc.  All rights reserved.
- * Copyright (c) 2010-2012 Cisco Systems, Inc.  All rights reserved.
+ * Copyright (c) 2010-2016 Cisco Systems, Inc.  All rights reserved.
  * Copyright (c) 2015      Los Alamos National Security, LLC. All rights
  *                         reserved.
+ * Copyright (c) 2014      Intel, Inc. All rights reserved.
  * $COPYRIGHT$
- * 
+ *
  * Additional copyrights may follow
- * 
+ *
  * $HEADER$
  */
 
@@ -53,7 +54,7 @@ OPAL_DECLSPEC extern int opal_cache_line_size;
 OPAL_DECLSPEC int opal_init(int* pargc, char*** pargv);
 
 /**
- * Finalize the OPAL layer, including the MCA system. 
+ * Finalize the OPAL layer, including the MCA system.
  *
  * @retval OPAL_SUCCESS Upon success.
  * @retval OPAL_ERROR Upon failure.
@@ -75,7 +76,14 @@ OPAL_DECLSPEC int opal_finalize(void);
 OPAL_DECLSPEC int opal_init_util(int* pargc, char*** pargv);
 
 /**
- * Finalize the OPAL layer, excluding the MCA system. 
+ * Disable PSM/PSM2 signal hijacking.
+ *
+ * See comment in the function for more detail.
+ */
+OPAL_DECLSPEC int opal_init_psm(void);
+
+/**
+ * Finalize the OPAL layer, excluding the MCA system.
  *
  * @retval OPAL_SUCCESS Upon success.
  * @retval OPAL_ERROR Upon failure.

opal/runtime/opal_init.c

@@ -10,7 +10,7 @@
  *                         University of Stuttgart.  All rights reserved.
  * Copyright (c) 2004-2005 The Regents of the University of California.
  *                         All rights reserved.
- * Copyright (c) 2007-2012 Cisco Systems, Inc.  All rights reserved.
+ * Copyright (c) 2007-2016 Cisco Systems, Inc.  All rights reserved.
  * Copyright (c) 2007      Sun Microsystems, Inc.  All rights reserved.
  * Copyright (c) 2009      Oak Ridge National Labs.  All rights reserved.
  * Copyright (c) 2010-2013 Los Alamos National Security, LLC.
@@ -246,6 +246,34 @@ opal_err2str(int errnum, const char **errmsg)
 }
 
 
+int opal_init_psm(void)
+{
+    /* Very early in the init sequence -- before *ANY* MCA components
+       are opened -- we need to disable some behavior from the PSM and
+       PSM2 libraries (by default): at least some old versions of
+       these libraries hijack signal handlers during their library
+       constructors and then do not un-hijack them when the libraries
+       are unloaded.
+
+       It is a bit of an abstraction break that we have to put
+       vendor/transport-specific code in the OPAL core, but we're
+       out of options, unfortunately.
+
+       NOTE: We only disable this behavior if the corresponding
+       environment variables are not already set (i.e., if the
+       user/environment has indicated a preference for this behavior,
+       we won't override it). */
+    if (NULL == getenv("IPATH_NO_BACKTRACE")) {
+        opal_setenv("IPATH_NO_BACKTRACE", "1", true, &environ);
+    }
+    if (NULL == getenv("HFI_NO_BACKTRACE")) {
+        opal_setenv("HFI_NO_BACKTRACE", "1", true, &environ);
+    }
+
+    return OPAL_SUCCESS;
+}
+
+
 int
 opal_init_util(int* pargc, char*** pargv)
 {
@@ -301,6 +329,10 @@ opal_init_util(int* pargc, char*** pargv)
         goto return_error;
     }
 
+    // Disable PSM signal hijacking (see comment in function for more
+    // details)
+    opal_init_psm();
+
     /* Setup the parameter system */
     if (OPAL_SUCCESS != (ret = mca_base_param_init())) {
         error = "mca_base_param_init";