Hi,
We should print a stack backtrace when we get EEH errors, it makes
debugging the cause of the fail easier.
Anton
Signed-off-by: Anton Blanchard <[email protected]>
===== eeh.c 1.29 vs edited =====
--- 1.29/arch/ppc64/kernel/eeh.c Mon Aug 23 18:14:40 2004
+++ edited/eeh.c Mon Aug 30 09:02:41 2004
@@ -447,6 +447,10 @@
spin_unlock_irqrestore(&slot_errbuf_lock, flags);
+ printk(KERN_ERR "EEH: MMIO failure (%d) on device:%s %s\n",
+ rets[0], pci_name(dev), pci_pretty_name(dev));
+ WARN_ON(1);
+
/*
* XXX We should create a separate sysctl for this.
*
@@ -454,14 +458,11 @@
* the system in light of potential corruption, we
* can use it here.
*/
- if (panic_on_oops) {
+ if (panic_on_oops)
panic("EEH: MMIO failure (%d) on device:%s %s\n",
rets[0], pci_name(dev), pci_pretty_name(dev));
- } else {
+ else
__get_cpu_var(ignored_failures)++;
- printk(KERN_INFO "EEH: MMIO failure (%d) on device:%s %s\n",
- rets[0], pci_name(dev), pci_pretty_name(dev));
- }
} else {
__get_cpu_var(false_positives)++;
}