[PATCH] powerpc/pseries: avoid crash in PCI code if mem system not up

[linux-beck.git] / arch / powerpc / platforms / pseries / eeh_event.c

diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
index 9a9961f27480d5736981c5982716ee17fc7c307e..40020c65c89e4da0e2365fac47316593ee712c12 100644 (file)
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -19,7 +19,9 @@
  */
 
 #include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
+#include <linux/workqueue.h>
 #include <asm/eeh_event.h>
 #include <asm/ppc-pci.h>
 
@@ -37,14 +39,18 @@ LIST_HEAD(eeh_eventlist);
 static void eeh_thread_launcher(void *);
 DECLARE_WORK(eeh_event_wq, eeh_thread_launcher, NULL);
 
+/* Serialize reset sequences for a given pci device */
+DEFINE_MUTEX(eeh_event_mutex);
+
 /**
- * eeh_event_handler - dispatch EEH events.  The detection of a frozen
- * slot can occur inside an interrupt, where it can be hard to do
- * anything about it.  The goal of this routine is to pull these
- * detection events out of the context of the interrupt handler, and
- * re-dispatch them for processing at a later time in a normal context.
- *
+ * eeh_event_handler - dispatch EEH events.
  * @dummy - unused
+ *
+ * The detection of a frozen slot can occur inside an interrupt,
+ * where it can be hard to do anything about it.  The goal of this
+ * routine is to pull these detection events out of the context
+ * of the interrupt handler, and re-dispatch them for processing
+ * at a later time in a normal context.
  */
 static int eeh_event_handler(void * dummy)
 {
@@ -64,23 +70,24 @@ static int eeh_event_handler(void * dummy)
                        event = list_entry(eeh_eventlist.next, struct eeh_event, list);
                        list_del(&event->list);
                }
-               
-               if (event)
-                       eeh_mark_slot(event->dn, EEH_MODE_RECOVERING);
-
                spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+
                if (event == NULL)
                        break;
 
+               /* Serialize processing of EEH events */
+               mutex_lock(&eeh_event_mutex);
+               eeh_mark_slot(event->dn, EEH_MODE_RECOVERING);
+
                printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n",
                       pci_name(event->dev));
 
                handle_eeh_events(event);
 
                eeh_clear_slot(event->dn, EEH_MODE_RECOVERING);
-
                pci_dev_put(event->dev);
                kfree(event);
+               mutex_unlock(&eeh_event_mutex);
        }
 
        return 0;
@@ -88,7 +95,6 @@ static int eeh_event_handler(void * dummy)
 
 /**
  * eeh_thread_launcher
- *
  * @dummy - unused
  */
 static void eeh_thread_launcher(void *dummy)
@@ -112,7 +118,15 @@ int eeh_send_failure_event (struct device_node *dn,
 {
        unsigned long flags;
        struct eeh_event *event;
+       char *location;
 
+       if (!mem_init_done) {
+               printk(KERN_ERR "EEH: event during early boot not handled\n");
+               location = (char *) get_property(dn, "ibm,loc-code", NULL);
+               printk(KERN_ERR "EEH: device node = %s\n", dn->full_name);
+               printk(KERN_ERR "EEH: PCI location = %s\n", location);
+               return 1;
+       }
        event = kmalloc(sizeof(*event), GFP_ATOMIC);
        if (event == NULL) {
                printk (KERN_ERR "EEH: out of memory, event not handled\n");