diff options
Diffstat (limited to 'src/usr/errl/errlmanager.C')
| -rw-r--r-- | src/usr/errl/errlmanager.C | 34 |
1 files changed, 33 insertions, 1 deletions
diff --git a/src/usr/errl/errlmanager.C b/src/usr/errl/errlmanager.C index 45de9d1fa..17cc11dd6 100644 --- a/src/usr/errl/errlmanager.C +++ b/src/usr/errl/errlmanager.C @@ -231,6 +231,20 @@ void * ErrlManager::startup ( void* i_self ) return NULL; } +/////////////////////////////////////////////////////////////////////////////// +// ErrlManager::pnorSetupThread() +/////////////////////////////////////////////////////////////////////////////// +void * ErrlManager::pnorSetupThread ( void* i_self ) +{ + TRACFCOMP( g_trac_errl, ENTER_MRK "ErrlManager::pnorSetupThread..." ); + + //Start a thread to deal with PNOR setup + reinterpret_cast<ErrlManager *>(i_self)->setupPnorInfo(); + + TRACFCOMP( g_trac_errl, EXIT_MRK "ErrlManager::pnorSetupThread" ); + return nullptr; +} + /////////////////////////////////////////////////////////////////////////////// // ErrlManager::errlogMsgHndlr() @@ -250,7 +264,25 @@ void ErrlManager::errlogMsgHndlr () case ERRLOG_ACCESS_PNOR_TYPE: { // PNOR is up and running now. - setupPnorInfo(); + // This can fail if there is bad ECC in HBEL (which is + // somewhat common on power faults). Because of this, + // trigger this as separate task so message that kills + //task on bad ECC doesn't bring down the whole daemon + auto l_tid = task_create(ErrlManager::pnorSetupThread, + this); + + // status of the task ( OK or Crashed ) + int l_childsts = 0; + auto l_tidretrc = task_wait_tid( l_tid, &l_childsts, 0); + + if ((static_cast<int16_t>(l_tidretrc) < 0 ) || + (l_childsts != TASK_STATUS_EXITED_CLEAN )) + { + TRACFCOMP(g_trac_errl, ERR_MRK "Failed to setup PNOR; l_tidretrc=0x%x," + " l_childsts=0x%x", l_tidretrc, l_childsts); + //Set iv_pnorAddr to nullptr to prevent writes + iv_pnorAddr = nullptr; + } //We are done with the msg msg_free(theMsg); |
