AMD/IOMMU: avoid recording each level's MFN when walking page table
authorJan Beulich <jbeulich@suse.com>
Fri, 27 Aug 2021 08:53:11 +0000 (10:53 +0200)
committerJan Beulich <jbeulich@suse.com>
Fri, 27 Aug 2021 08:53:11 +0000 (10:53 +0200)
commit706551b29b176c0a3eb853f71408806a843d51fa
tree4cf1910dced21f31f7813e39dce02d2f4d25acc4
parentc5c84e97669dd5c92b59b04b2ab4233605da09dd
AMD/IOMMU: avoid recording each level's MFN when walking page table

Both callers only care about the target (level 1) MFN. I also cannot
see what we might need higher level MFNs for down the road. And even
modern gcc doesn't recognize the optimization potential.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
xen/drivers/passthrough/amd/iommu_map.c