Commit 42405456 authored Apr 28, 2006 by Linas Vepstas Committed by Paul Mackerras May 19, 2006

[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>

parent 877fbae3

arch/powerpc/platforms/pseries/eeh_driver.c

+6 −1

Original line number	Diff line number	Diff line
		@@ -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;
		}