KVM: arm64: Walk userspace page tables to compute the THP mapping size

We currently rely on the kvm_is_transparent_hugepage() helper to
discover whether a given page has the potential to be mapped as
a block mapping.

However, this API doesn't really give un everything we want:
- we don't get the size: this is not crucial today as we only
  support PMD-sized THPs, but we'd like to have larger sizes
  in the future
- we're the only user left of the API, and there is a will
  to remove it altogether

To address the above, implement a simple walker using the existing
page table infrastructure, and plumb it into transparent_hugepage_adjust().
No new page sizes are supported in the process.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Link: https://lore.kernel.org/r/20210726153552.1535838-3-maz@kernel.org

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 0625bf2..183c107 100644 (file)
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -433,6 +433,32 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
        return 0;
 }
 
+static struct kvm_pgtable_mm_ops kvm_user_mm_ops = {
+       /* We shouldn't need any other callback to walk the PT */
+       .phys_to_virt           = kvm_host_va,
+};
+
+static int get_user_mapping_size(struct kvm *kvm, u64 addr)
+{
+       struct kvm_pgtable pgt = {
+               .pgd            = (kvm_pte_t *)kvm->mm->pgd,
+               .ia_bits        = VA_BITS,
+               .start_level    = (KVM_PGTABLE_MAX_LEVELS -
+                                  CONFIG_PGTABLE_LEVELS),
+               .mm_ops         = &kvm_user_mm_ops,
+       };
+       kvm_pte_t pte = 0;      /* Keep GCC quiet... */
+       u32 level = ~0;
+       int ret;
+
+       ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level);
+       VM_BUG_ON(ret);
+       VM_BUG_ON(level >= KVM_PGTABLE_MAX_LEVELS);
+       VM_BUG_ON(!(pte & PTE_VALID));
+
+       return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
+}
+
 static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
        .zalloc_page            = stage2_memcache_zalloc_page,
        .zalloc_pages_exact     = kvm_host_zalloc_pages_exact,
@@ -780,7 +806,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
  * Returns the size of the mapping.
  */
 static unsigned long
-transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
+transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
                            unsigned long hva, kvm_pfn_t *pfnp,
                            phys_addr_t *ipap)
 {
@@ -791,8 +817,8 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
         * sure that the HVA and IPA are sufficiently aligned and that the
         * block map is contained within the memslot.
         */
-       if (kvm_is_transparent_hugepage(pfn) &&
-           fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) {
+       if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) &&
+           get_user_mapping_size(kvm, hva) >= PMD_SIZE) {
                /*
                 * The address we faulted on is backed by a transparent huge
                 * page.  However, because we map the compound huge page and
@@ -1051,7 +1077,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
         * backed by a THP and thus use block mapping if possible.
         */
        if (vma_pagesize == PAGE_SIZE && !(force_pte || device))
-               vma_pagesize = transparent_hugepage_adjust(memslot, hva,
+               vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva,
                                                           &pfn, &fault_ipa);
 
        if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {