[PATCH] powerpc/pseries: Increment fail counter in PCI recovery

When a PCI device driver does not support PCI error recovery,
the powerpc/pseries code takes a walk through a branch of code
that resets the failure counter. Because of this, if a broken
PCI card is present, the kernel will attempt to reset it an
infinite number of times. (This is annoying but mostly harmless:
each reset takes about 10-20 seconds, and uses almost no CPU time).

This patch preserves the failure count across resets.
Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>

arch/powerpc/platforms/pseries/eeh_driver.c

@@ -201,7 +201,11 @@ static void eeh_report_failure(struct pci_dev *dev, void *userdata)
 
 static int eeh_reset_device (struct pci_dn *pe_dn, struct pci_bus *bus)
 {
-	int rc;
+	int cnt, rc;
+
+	/* pcibios will clear the counter; save the value */
+	cnt = pe_dn->eeh_freeze_count;
+
 	if (bus)
 		pcibios_remove_pci_devices(bus);
 
@@ -240,6 +244,7 @@ static int eeh_reset_device (struct pci_dn *pe_dn, struct pci_bus *bus)
 		ssleep (5);
 		pcibios_add_pci_devices(bus);
 	}
+	pe_dn->eeh_freeze_count = cnt;
 
 	return 0;
 }