[POWERPC] EEH: Power4 systems sometimes need multiple resets.
On detection of an EEH error, some Power4 systems seem to occasionally
want to be reset twice before they report themselves as fully recovered.
This patch re-arranges the code to attempt additional resets if the first
one doesn't take.
Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 4534886..84bc8f7 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -478,7 +478,7 @@
printk (KERN_ERR "EEH: Slot unavailable: rc=%d, rets=%d %d %d\n",
rc, rets[0], rets[1], rets[2]);
- return -1;
+ return -2;
}
/**
@@ -546,11 +546,10 @@
BUID_HI(pdn->phb->buid),
BUID_LO(pdn->phb->buid),
state);
- if (rc) {
- printk (KERN_WARNING "EEH: Unable to reset the failed slot, (%d) #RST=%d dn=%s\n",
+ if (rc)
+ printk (KERN_WARNING "EEH: Unable to reset the failed slot,"
+ " (%d) #RST=%d dn=%s\n",
rc, state, pdn->node->full_name);
- return;
- }
}
/**
@@ -560,11 +559,8 @@
* Return 0 if success, else a non-zero value.
*/
-int
-rtas_set_slot_reset(struct pci_dn *pdn)
+static void __rtas_set_slot_reset(struct pci_dn *pdn)
{
- int i, rc;
-
rtas_pci_slot_reset (pdn, 1);
/* The PCI bus requires that the reset be held high for at least
@@ -585,17 +581,33 @@
* up traffic. */
#define PCI_BUS_SETTLE_TIME_MSEC 1800
msleep (PCI_BUS_SETTLE_TIME_MSEC);
+}
+
+int rtas_set_slot_reset(struct pci_dn *pdn)
+{
+ int i, rc;
+
+ __rtas_set_slot_reset(pdn);
/* Now double check with the firmware to make sure the device is
* ready to be used; if not, wait for recovery. */
for (i=0; i<10; i++) {
rc = eeh_slot_availability (pdn);
- if (rc < 0)
- printk (KERN_ERR "EEH: failed (%d) to reset slot %s\n", rc, pdn->node->full_name);
if (rc == 0)
return 0;
- if (rc < 0)
+
+ if (rc == -2) {
+ printk (KERN_ERR "EEH: failed (%d) to reset slot %s\n",
+ i, pdn->node->full_name);
+ __rtas_set_slot_reset(pdn);
+ continue;
+ }
+
+ if (rc < 0) {
+ printk (KERN_ERR "EEH: unrecoverable slot failure %s\n",
+ pdn->node->full_name);
return -1;
+ }
msleep (rc+100);
}