07-eeh-spin-counter.patch
One an EEH event is triggers, all further I/O to a device is blocked (until
reset). Bad device drivers may end up spinning in their interrupt handlers,
trying to read an interrupt status register that will never change state.
This patch moves that spin counter to a per-device structure, and adds
some diagnostic prints to help locate the bad driver.
Signed-off-by: Linas Vepstas <[email protected]>
Index: linux-2.6.14-rc2-git6/arch/ppc64/kernel/eeh.c
===================================================================
--- linux-2.6.14-rc2-git6.orig/arch/ppc64/kernel/eeh.c 2005-09-29 16:29:00.726884805 -0500
+++ linux-2.6.14-rc2-git6/arch/ppc64/kernel/eeh.c 2005-09-29 16:32:05.550949258 -0500
@@ -78,14 +78,12 @@
static struct notifier_block *eeh_notifier_chain;
-/*
- * If a device driver keeps reading an MMIO register in an interrupt
+/* If a device driver keeps reading an MMIO register in an interrupt
* handler after a slot isolation event has occurred, we assume it
* is broken and panic. This sets the threshold for how many read
* attempts we allow before panicking.
*/
-#define EEH_MAX_FAILS 1000
-static atomic_t eeh_fail_count;
+#define EEH_MAX_FAILS 100000
/* RTAS tokens */
static int ibm_set_eeh_option;
@@ -521,7 +519,6 @@
"%s\n", event->reset_state,
pci_name(event->dev));
- atomic_set(&eeh_fail_count, 0);
notifier_call_chain (&eeh_notifier_chain,
EEH_NOTIFY_FREEZE, event);
@@ -657,12 +654,18 @@
spin_lock_irqsave(&confirm_error_lock, flags);
rc = 1;
if (pdn->eeh_mode & EEH_MODE_ISOLATED) {
- atomic_inc(&eeh_fail_count);
- if (atomic_read(&eeh_fail_count) >= EEH_MAX_FAILS) {
+ pdn->eeh_check_count ++;
+ if (pdn->eeh_check_count >= EEH_MAX_FAILS) {
+ printk (KERN_ERR "EEH: Device driver ignored %d bad reads, panicing\n",
+ pdn->eeh_check_count);
+ dump_stack();
+
/* re-read the slot reset state */
if (read_slot_reset_state(pdn, rets) != 0)
rets[0] = -1; /* reset state unknown */
- eeh_panic(dev, rets[0]);
+
+ /* If we are here, then we hit an infinite loop. Stop. */
+ panic("EEH: MMIO halt (%d) on device:%s\n", rets[0], pci_name(dev));
}
goto dn_unlock;
}
@@ -808,6 +811,8 @@
struct pci_dn *pdn = PCI_DN(dn);
pdn->eeh_mode = 0;
+ pdn->eeh_check_count = 0;
+ pdn->eeh_freeze_count = 0;
if (status && strcmp(status, "ok") != 0)
return NULL; /* ignore devices with bad status */
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
| |
 |