Re: [PATCH] sb_edac: Fix detection on SNB machines

[Borislav Petkov <bp@alien8.de>]

On Sun, Feb 08, 2015 at 08:54:06AM -0800, Andy Lutomirski wrote:
> If there isn't an obvious fix, I'd be okay with reverting, too.  The

I think the obvious fix is this:

diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 63aa6730e89e..1acf57ba4c86 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -2447,7 +2447,7 @@ static int sbridge_probe(struct pci_dev *pdev, const struct pci_device_id *id)
                rc = sbridge_get_all_devices(&num_mc, pci_dev_descr_ibridge_table);
                type = IVY_BRIDGE;
                break;
-       case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA:
+       case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0:
                rc = sbridge_get_all_devices(&num_mc, pci_dev_descr_sbridge_table);
                type = SANDY_BRIDGE;
                break;
---

because you changed it to match the

	PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0

device in the id_table but sbridge_probe() still matches against

	PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA

when it is about to call sbridge_get_all_devices() to get the rest of
the SNB PCI devices. Currently, it simply doesn't match any of the case
options in the switch-case statement there.

And this is what I'm seeing here: we match the 0x3ca8 device in
sbridge_probe() but it gets handed in 0x3ca0 due to your change.

I'll run this tomorrow to confirm but this looks like the correct fix to
me. And it makes sense for a change :)

Thanks.

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.
--