On Mon, Oct 17, 2016 at 2:02 PM, Christoph Hellwig <hch@xxxxxx> wrote: > Thanks a lot! I think the current check on when to fall back from > the multi-MSI to the single-MSI case is too narrow and we should > just always fall back. > > Can you see if the patch below fixes your issue (revert the debug patch > first, please)? > > diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c > index ba5f11c..b4b8004 100644 > --- a/drivers/ata/ahci.c > +++ b/drivers/ata/ahci.c > @@ -1436,13 +1436,6 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports, > } > > /* > - * -ENOSPC indicated we don't have enough vectors. Don't bother trying > - * a single vectors for any other error: > - */ > - if (nvec < 0 && nvec != -ENOSPC) > - return nvec; > - > - /* > * If the host is not capable of supporting per-port vectors, fall > * back to single MSI before finally attempting single MSI-X. > */ Sorry Christoph, issue is still there: http://i.imgur.com/smDjT0y.jpg http://i.imgur.com/VV4FGI1.jpg http://i.imgur.com/Xqdayvj.jpg Thanks -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
