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>

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index e42d643a20ac9c387f4456f86ee4a071db8a42ef..94cfcf33030aeee1d96b9b7e4b068711dfc32ae2 100644 (file)
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -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;
 

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 8d36c50e906f5fe3a54222c682d55031c79f1363..0996f22b261211f1813e2ddfedaad9137a338434 100644 (file)
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -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
        }

diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c
index 227e57f980df155f789e994d440392ad2d916c1b..19837798bb1da535f8a34a72c2243097358fd6c6 100644 (file)
--- a/arch/powerpc/kernel/eeh_event.c
+++ b/arch/powerpc/kernel/eeh_event.c
@@ -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");