[PATCH v5 2/2] kvm: Use huge pages for DAX-backed files

[Barret Rhoden <brho@google.com>]

This change allows KVM to map DAX-backed files made of huge pages with
huge mappings in the EPT/TDP.

DAX pages are not PageTransCompound.  The existing check is trying to
determine if the mapping for the pfn is a huge mapping or not.  For
non-DAX maps, e.g. hugetlbfs, that means checking PageTransCompound.
For DAX, we can check the page table itself.

Note that KVM already faulted in the page (or huge page) in the host's
page table, and we hold the KVM mmu spinlock.  We grabbed that lock in
kvm_mmu_notifier_invalidate_range_end, before checking the mmu seq.

Signed-off-by: Barret Rhoden <brho@google.com>
---
 arch/x86/kvm/mmu/mmu.c | 31 +++++++++++++++++++++++++++----
 1 file changed, 27 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 7269130ea5e2..ea8f6951398b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3328,6 +3328,30 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 	__direct_pte_prefetch(vcpu, sp, sptep);
 }
 
+static bool pfn_is_huge_mapped(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn)
+{
+	struct page *page = pfn_to_page(pfn);
+	unsigned long hva;
+
+	if (!is_zone_device_page(page))
+		return PageTransCompoundMap(page);
+
+	/*
+	 * DAX pages do not use compound pages.  The page should have already
+	 * been mapped into the host-side page table during try_async_pf(), so
+	 * we can check the page tables directly.
+	 */
+	hva = gfn_to_hva(kvm, gfn);
+	if (kvm_is_error_hva(hva))
+		return false;
+
+	/*
+	 * Our caller grabbed the KVM mmu_lock with a successful
+	 * mmu_notifier_retry, so we're safe to walk the page table.
+	 */
+	return dev_pagemap_mapping_shift(hva, current->mm) > PAGE_SHIFT;
+}
+
 static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 					gfn_t gfn, kvm_pfn_t *pfnp,
 					int *levelp)
@@ -3342,8 +3366,8 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	 * here.
 	 */
 	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
-	    !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
-	    PageTransCompoundMap(pfn_to_page(pfn))) {
+	    level == PT_PAGE_TABLE_LEVEL &&
+	    pfn_is_huge_mapped(vcpu->kvm, gfn, pfn)) {
 		unsigned long mask;
 
 		/*
@@ -5957,8 +5981,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 		 * mapping if the indirect sp has level = 1.
 		 */
 		if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
-		    !kvm_is_zone_device_pfn(pfn) &&
-		    PageTransCompoundMap(pfn_to_page(pfn))) {
+		    pfn_is_huge_mapped(kvm, sp->gfn, pfn)) {
 			pte_list_remove(rmap_head, sptep);
 
 			if (kvm_available_flush_tlb_with_range())
-- 
2.24.0.525.g8f36a354ae-goog