David Ahern reported an oops caused by passing a NULL start device
to pci_acs_path_enabled(). This can happen when a bus is created
for sr-iov devices without an associated bridge. To handle this,
skip over to the parent bus and look for a bridge there. Continue
until we find something or reach the root bus.
This works on my system, but still needs to be tested by David. I'd
like to get this in for 3.6-rc2.
Joerg, I notice that ACS isn't getting enabled on my AMD system on
3.6-rc1. I'll investigate more, but mention it in case you get to
it first. Thanks,
Alex
---
Alex Williamson (2):
amd-iommu: Fix ACS path checking
intel-iommu: Fix ACS path checking
drivers/iommu/amd_iommu.c | 25 ++++++++++++++++++++++---
drivers/iommu/intel-iommu.c | 25 ++++++++++++++++++++++---
2 files changed, 44 insertions(+), 6 deletions(-)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
