powerpc/eeh: Don't panic when EEH_MAX_FAILS is exceeded

This patch changes the EEH_MAX_FAILS action from panic to printing an
error message.  Panicking under under this condition is too harsh.
Although performance will be affected and the device may not recover,
the system is still running, which at the very least should allow for a
more graceful shutdown. The patch also removes the msleep() within a
spinlock, which can lead to a deadlock and is not recommended.

Signed-off-by: Mike Mason <mmlnx@us.ibm.com>
Acked-by: Linas Vepstas <linasvepstas@gmail.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index c027f0a70a04d111af01e5242431299fb0f4fbd6..54816d75b5787b8d0f134c4de71f78854fd5d27a 100644 (file)
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -75,9 +75,9 @@
  */
 
 /* 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.
+ * handler after a slot isolation event, it might be broken.
+ * This sets the threshold for how many read attempts we allow
+ * before printing an error message.
  */
 #define EEH_MAX_FAILS  2100000
 
@@ -470,6 +470,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
        unsigned long flags;
        struct pci_dn *pdn;
        int rc = 0;
+       const char *location;
 
        total_mmio_ffs++;
 
@@ -509,18 +510,15 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
        rc = 1;
        if (pdn->eeh_mode & EEH_MODE_ISOLATED) {
                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);
+               if (pdn->eeh_check_count % EEH_MAX_FAILS == 0) {
+                       location = of_get_property(dn, "ibm,loc-code", NULL);
+                       printk (KERN_ERR "EEH: %d reads ignored for recovering device at "
+                               "location=%s driver=%s pci addr=%s\n",
+                               pdn->eeh_check_count, location,
+                               dev->driver->name, pci_name(dev));
+                       printk (KERN_ERR "EEH: Might be infinite loop in %s driver\n",
+                               dev->driver->name);
                        dump_stack();
-                       msleep(5000);
-                       
-                       /* re-read the slot reset state */
-                       if (read_slot_reset_state(pdn, rets) != 0)
-                               rets[0] = -1;   /* reset state unknown */
-
-                       /* 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;
        }