>> Guess I am getting lost in abstraction layers :) >> >> I think you're right, is_error_noslot_pfn() in kvm_pfn_to_page() should >> convert all such errors to KVM_ERR_PTR_BAD_PAGE. >> >> -ENOMEM was a theoretical case at that point either way in my opinion. >> >> So, this would boil down to: >> >> >> From a2cf5d109fc6342df12e361b665c92b73f66cfee Mon Sep 17 00:00:00 2001 >> From: David Hildenbrand <david@xxxxxxxxxx> >> Date: Thu, 3 Aug 2017 22:30:40 +0200 >> Subject: [PATCH v2 1/1] KVM: s390: vsie: use common code functions for >> pinning >> >> We will not see -ENOMEM (gfn_to_hva() will return KVM_ERR_PTR_BAD_PAGE >> for all errors). So we can also get rid of special handling in the >> callers of pin_guest_page() and always assume that it is a g2 error. >> >> As also kvm_s390_inject_program_int() should never fail, we can >> simplify pin_scb(), too. >> >> Signed-off-by: David Hildenbrand <david@xxxxxxxxxx> > > Can you send it as a new patch please? > Sure, will do. -- Thanks, David
