Hi Jesse,
The following patch fixes a regression introduced when an SRIOV card
is used as a PF in a 64k base page size configuration.
Reference: https://lkml.org/lkml/2012/2/1/165
Please queue this bugfix patch for the current release cycle.
Thanks,
Vaidy
---
pci: set pci sriov page size before reading SRIOV BAR
For an SRIOV device, PCI_SRIOV_SYS_PGSIZE should be set before
the PCI_SRIOV_BAR are queried. The sys pagesize defaults to 4k,
so this change is required on powerpc box with 64k base page size.
This is a regression caused due to moving SRIOV init to sriov_enable().
| commit afd24ece5c76af87f6fc477f2747b83a764f161c
| Author: Ram Pai <[email protected]>
| PCI: delay configuration of SRIOV capability
| The SRIOV capability, namely page size and total_vfs of a device are
| configured during enumeration phase of the device. This can potentially
| interfere with the PCI operations of the platform, if the IOV capability
| of the device is not enabled.
Signed-off-by: Vaidyanathan Srinivasan <[email protected]>
Acked-by: Ram Pai <[email protected]>
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 0321fa3..0dab5ec 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -347,8 +347,6 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
return rc;
}
- pci_write_config_dword(dev, iov->pos + PCI_SRIOV_SYS_PGSIZE, iov->pgsz);
-
iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE;
pci_cfg_access_lock(dev);
pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
@@ -466,6 +464,7 @@ found:
return -EIO;
pgsz &= ~(pgsz - 1);
+ pci_write_config_dword(dev, pos + PCI_SRIOV_SYS_PGSIZE, pgsz);
nres = 0;
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
On Thu, 2 Feb 2012 23:11:20 +0530
Vaidyanathan Srinivasan <[email protected]> wrote:
> Hi Jesse,
>
> The following patch fixes a regression introduced when an SRIOV card
> is used as a PF in a 64k base page size configuration.
>
> Reference: https://lkml.org/lkml/2012/2/1/165
>
> Please queue this bugfix patch for the current release cycle.
Applied, thanks. Ram please shout if this isn't ok and you'd prefer a
different fix.
Thanks,
--
Jesse Barnes, Intel Open Source Technology Center