Re: [PATCH 03/13] set iommu agaw

[Mark McLoughlin <markmc@redhat.com>]

On Tue, 2008-12-02 at 22:22 +0800, Han, Weidong wrote:
> agaw may be different across iommus.
> 
> Signed-off-by: Weidong Han <weidong.han@intel.com>
> ---
>  drivers/pci/dmar.c            |   14 ++++++++++++++
>  include/linux/dma_remapping.h |    2 ++
>  include/linux/intel-iommu.h   |    1 +
>  3 files changed, 17 insertions(+), 0 deletions(-)
> 
> diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
> index 691b3ad..ebcc7c2 100644
> --- a/drivers/pci/dmar.c
> +++ b/drivers/pci/dmar.c
> @@ -491,6 +491,8 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
>  	int map_size;
>  	u32 ver;
>  	static int iommu_allocated = 0;
> +	unsigned long sagaw;
> +	int agaw;
>  
>  	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
>  	if (!iommu)
> @@ -506,6 +508,18 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
>  	iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG);
>  	iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
>  
> +	/* set agaw, "SAGAW" may be different across iommus */
> +	sagaw = cap_sagaw(iommu->cap);
> +	for (agaw = width_to_agaw(DEFAULT_DOMAIN_ADDRESS_WIDTH);
> +	     agaw >= 0; agaw--)
> +		if (test_bit(agaw, &sagaw))
> +			break;
> +	if (agaw < 0) {
> +		printk(KERN_ERR "IOMMU: unsupported sagaw %lx\n", sagaw);
> +		goto error;
> +	}
> +	iommu->agaw = agaw;

Could we add something like intel_iommu_calculate_agaw() and keep the
agaw code internal to intel-iommu.c?

Also, "unsupported sagaw" expands to "unsupported supported adjusted
guest address width" which doesn't make much sense :-)

"unsupported address width" would be sufficient, I think.

Cheers,
Mark.