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. */ -- 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
