Re: [PATCH v2] PCI: vmd: Offset Client VMD MSI/X vectors

[Bjorn Helgaas <helgaas@kernel.org>]

Hi Jon,

This refers to "MSI/X" (subject, commit log of this patch, as well as
other recent patches).  I don't know if that means what the spec calls
"MSI-X", or if you mean something like "MSI or MSI-X" (there is one
reference in vmd.c to "MSI/MSI-X").

I'd sort of rather avoid adding "MSI/X" to the PCI lexicon because of
this ambiguity.

If it's not important to the meaning or if it's clear from context
that "MSI" is a generic term for "either MSI or MSI-X", I'm ok with
using that.

Bjorn

On Mon, Sep 14, 2020 at 01:32:55PM -0400, Jon Derrick wrote:
> Client VMD platforms have a software-triggered MSI/X vector 0 that will
> not forward hardware-remapped MSI/X vectors from the sub-device domain.
> This causes an issue with VMD platforms that use AHCI behind VMD and
> have a single MSI/X vector mapping to vector 0. Add an MSI/X vector
> offset for these platforms.
> 
> Signed-off-by: Jon Derrick <jonathan.derrick@intel.com>
> ---
>  drivers/pci/controller/vmd.c | 35 +++++++++++++++++++++++++----------
>  1 file changed, 25 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
> index f69ef8c89f72..f8195bad79d1 100644
> --- a/drivers/pci/controller/vmd.c
> +++ b/drivers/pci/controller/vmd.c
> @@ -53,6 +53,12 @@ enum vmd_features {
>  	 * vendor-specific capability space
>  	 */
>  	VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP	= (1 << 2),
> +
> +	/*
> +	 * Device may use MSI/X vector 0 for software triggering and will not
> +	 * be used for MSI/X remapping
> +	 */
> +	VMD_FEAT_OFFSET_FIRST_VECTOR		= (1 << 3),
...