Improve error handling when slave SBE fails to boot

If we fail to boot the slave SBE we should mark it in the istep errlog to ensure that we fail the istep and perform a reconfig loop. Change-Id: I70e67b5b3e1e35e0ee76eb1f158435ee44a436ef Reviewed-on: http://ralgit01.raleigh.ibm.com/gerrit1/56882 Reviewed-by: Martin Gloff <mgloff@us.ibm.com> Tested-by: Jenkins Server <pfd-jenkins+hostboot@us.ibm.com> Tested-by: Jenkins OP Build CI <op-jenkins+hostboot@us.ibm.com> Tested-by: Jenkins OP HW <op-hw-jenkins+hostboot@us.ibm.com> Tested-by: FSP CI Jenkins <fsp-CI-jenkins+hostboot@us.ibm.com> Reviewed-by: Roland Veloz <rveloz@us.ibm.com> Reviewed-by: Daniel M. Crowell <dcrowell@us.ibm.com>
open-power · Apr 10, 2018 · a4e9bdd · a4e9bdd
1 parent 7ee5536
commit a4e9bdd
Show file tree

Hide file tree

Showing 2 changed files with 27 additions and 0 deletions.
diff --git a/src/include/usr/isteps/istep_reasoncodes.H b/src/include/usr/isteps/istep_reasoncodes.H
@@ -114,6 +114,7 @@ namespace ISTEP
         RC_P9N_DD1_NOT_SUPPORTED                 = ISTEP_COMP_ID | 0x35,
         RC_PREVENT_REBOOT_IN_MFG_TERM_MODE       = ISTEP_COMP_ID | 0x36,
         RC_FAILED_WRITE_SPR                      = ISTEP_COMP_ID | 0x37,
+        RC_FAILED_TO_BOOT_SBE                    = ISTEP_COMP_ID | 0x38,
     };
 
 };

diff --git a/src/usr/isteps/istep08/call_proc_check_slave_sbe_seeprom_complete.C b/src/usr/isteps/istep08/call_proc_check_slave_sbe_seeprom_complete.C
@@ -173,6 +173,32 @@ void* call_proc_check_slave_sbe_seeprom_complete( void *io_pArgs )
                       " completed ok for proc 0x%.8X",
                       TARGETING::get_huid(l_cpu_target));
         }
+        else
+        {
+            TRACFCOMP(ISTEPS_TRACE::g_trac_isteps_trace,
+                      "FAILURE : proc_check_slave_sbe_seeprom_complete"
+                      "SBE for proc 0x%.8X did not reach runtime",
+                      TARGETING::get_huid(l_cpu_target));
+           /*@
+            * @reasoncode RC_FAILED_TO_BOOT_SBE
+            * @severity   ERRORLOG::ERRL_SEV_UNRECOVERABLE
+            * @moduleid   MOD_CHECK_SLAVE_SBE_SEEPROM_COMPLETE
+            * @userdata1  HUID of proc that failed to boot its SBE
+            * @userdata2  Unused
+            * @devdesc    Failed to boot a slave SBE
+            * @custdesc   Processor Error
+            */
+            l_errl = new ERRORLOG::ErrlEntry(ERRORLOG::ERRL_SEV_UNRECOVERABLE,
+                                            MOD_CHECK_SLAVE_SBE_SEEPROM_COMPLETE,
+                                            RC_FAILED_TO_BOOT_SBE,
+                                            TARGETING::get_huid(l_cpu_target),
+                                            0);
+            l_errl->collectTrace( "ISTEPS_TRACE", 256 );
+            l_stepError.addErrorDetails( l_errl);
+            errlCommit(l_errl, ISTEP_COMP_ID);
+
+
+        }
 
 /* @TODO-RTC:100963 This should only be called when the SBE has completely
               crashed. There is a path in OpenPower where HB may get an