On Fri, Aug 9, 2024 at 9:09 AM Peter Xu <peterx@xxxxxxxxxx> wrote:
>
> Use the new pfnmap API to allow huge MMIO mappings for VMs. The rest work
> is done perfectly on the other side (host_pfn_mapping_level()).
I don't think it has to be done in this series, but a future
optimization to consider is having follow_pfnmap just tell the caller
about the mapping level directly. It already found this information as
part of its walk. I think there's a possibility to simplify KVM /
avoid it having to do its own walk again later.
>
>
> Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
> Cc: Sean Christopherson <seanjc@xxxxxxxxxx>
> Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
> ---
> virt/kvm/kvm_main.c | 19 +++++++------------
> 1 file changed, 7 insertions(+), 12 deletions(-)
>
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index d0788d0a72cc..9fb1c527a8e1 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -2862,13 +2862,11 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
> unsigned long addr, bool write_fault,
> bool *writable, kvm_pfn_t *p_pfn)
> {
> + struct follow_pfnmap_args args = { .vma = vma, .address = addr };
> kvm_pfn_t pfn;
> - pte_t *ptep;
> - pte_t pte;
> - spinlock_t *ptl;
> int r;
>
> - r = follow_pte(vma, addr, &ptep, &ptl);
> + r = follow_pfnmap_start(&args);
> if (r) {
> /*
> * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does
> @@ -2883,21 +2881,19 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
> if (r)
> return r;
>
> - r = follow_pte(vma, addr, &ptep, &ptl);
> + r = follow_pfnmap_start(&args);
> if (r)
> return r;
> }
>
> - pte = ptep_get(ptep);
> -
> - if (write_fault && !pte_write(pte)) {
> + if (write_fault && !args.writable) {
> pfn = KVM_PFN_ERR_RO_FAULT;
> goto out;
> }
>
> if (writable)
> - *writable = pte_write(pte);
> - pfn = pte_pfn(pte);
> + *writable = args.writable;
> + pfn = args.pfn;
>
> /*
> * Get a reference here because callers of *hva_to_pfn* and
> @@ -2918,9 +2914,8 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
> */
> if (!kvm_try_get_pfn(pfn))
> r = -EFAULT;
> -
> out:
> - pte_unmap_unlock(ptep, ptl);
> + follow_pfnmap_end(&args);
> *p_pfn = pfn;
>
> return r;
> --
> 2.45.0
>
