Skip to contentSkip to conversation

pci: disable MSI on VIA K8M800

PATCH Applied Tejun Heo 3 participants 5 messages May 23, 2010 – May 28, 2010 PCI

lore
Share & tools
lore

Tejun Heo

author
#0 lore raw

PATCH 1/1 pci: disable MSI on VIA K8M800

MSI delivery from on-board ahci controller doesn't work on K8M800. At this point, it's unclear whether the culprit is with the ahci controller or the host bridge. Given the track record and considering the rather minimal impact of MSI, disabling it seems reasonable.

---
Maybe we should whitelist working ones from via rather than the other way around. :-(

 drivers/pci/quirks.c |    1 +
 1 file changed, 1 insertion(+)
drivers/pci/quirks.c +1 -0
index 27c0e6e..18a661d 100644
@@ -2112,6 +2112,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_RS480, quirk_disabl
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT3336, quirk_disable_all_msi);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT3351, quirk_disable_all_msi);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT3364, quirk_disable_all_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8380_0, quirk_disable_all_msi);
 
 /* Disable MSI on chipsets that are known to not support it */
 static void __devinit quirk_disable_msi(struct pci_dev *dev)
#1 lore raw

From: Tejun Heo <[email protected]>
Date: Sun, 23 May 2010 10:22:55 +0200

Quoted 11 lines

MSI delivery from on-board ahci controller doesn't work on K8M800. At this point, it's unclear whether the culprit is with the ahci controller or the host bridge. Given the track record and considering the rather minimal impact of MSI, disabling it seems reasonable.

---
Maybe we should whitelist working ones from via rather than the other way around. :-(

Correctness first, of course, but saying the impact of MSI is minimal ignores the fact that no hardware multiqueue networking at all is possible without it. :-)

author
#2 lore raw
Quoted 3 lines · David Miller

Correctness first, of course, but saying the impact of MSI is minimal ignores the fact that no hardware multiqueue networking at all is possible without it. :-)

If you're trying to do hw multiqueue networking on via chipset, you gotta be on something *really* good. Come on. Share it with me. :-)

Signature · 1 line
tejun
#3 lore raw

From: Tejun Heo <[email protected]>
Date: Sun, 23 May 2010 10:56:58 +0200

Quoted 7 lines · David Miller
Quoted 3 lines

Correctness first, of course, but saying the impact of MSI is minimal ignores the fact that no hardware multiqueue networking at all is possible without it. :-)

If you're trying to do hw multiqueue networking on via chipset, you gotta be on something *really* good. Come on. Share it with me. :-)

Fair enough. :)

Applied
#4 lore raw
In reply to Tejun Heo
Quoted 9 lines · On Sun, 23 May 2010 10:22:55 +0200 Tejun Heo <[email protected]> wrote:

MSI delivery from on-board ahci controller doesn't work on K8M800. At this point, it's unclear whether the culprit is with the ahci controller or the host bridge. Given the track record and considering the rather minimal impact of MSI, disabling it seems reasonable.

---

Applied to my for-linus branch, thanks.

Signature · 1 line
Jesse Barnes, Intel Open Source Technology Center