powerpc/eeh: Allow disabling recovery

Currently when we detect an error we automatically invoke the EEH recovery
handler. This can be annoying when debugging EEH problems, or when working
on EEH itself so this patch adds a debugfs knob that will prevent a
recovery event from being queued up when an issue is detected.

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This commit is contained in:
Oliver O'Halloran 2019-02-15 11:48:16 +11:00 committed by Michael Ellerman
parent 67060cb1ff
commit 6b493f6079
3 changed files with 20 additions and 0 deletions

View File

@ -220,6 +220,7 @@ struct eeh_ops {
extern int eeh_subsystem_flags;
extern u32 eeh_max_freezes;
extern bool eeh_debugfs_no_recover;
extern struct eeh_ops *eeh_ops;
extern raw_spinlock_t confirm_error_lock;

View File

@ -111,6 +111,13 @@ EXPORT_SYMBOL(eeh_subsystem_flags);
*/
u32 eeh_max_freezes = 5;
/*
* Controls whether a recovery event should be scheduled when an
* isolated device is discovered. This is only really useful for
* debugging problems with the EEH core.
*/
bool eeh_debugfs_no_recover;
/* Platform dependent EEH operations */
struct eeh_ops *eeh_ops = NULL;
@ -1843,6 +1850,9 @@ static int __init eeh_init_proc(void)
&eeh_enable_dbgfs_ops);
debugfs_create_u32("eeh_max_freezes", 0600,
powerpc_debugfs_root, &eeh_max_freezes);
debugfs_create_bool("eeh_disable_recovery", 0600,
powerpc_debugfs_root,
&eeh_debugfs_no_recover);
eeh_cache_debugfs_init();
#endif
}

View File

@ -126,6 +126,15 @@ int eeh_send_failure_event(struct eeh_pe *pe)
unsigned long flags;
struct eeh_event *event;
/*
* If we've manually supressed recovery events via debugfs
* then just drop it on the floor.
*/
if (eeh_debugfs_no_recover) {
pr_err("EEH: Event dropped due to no_recover setting\n");
return 0;
}
event = kzalloc(sizeof(*event), GFP_ATOMIC);
if (!event) {
pr_err("EEH: out of memory, event not handled\n");