[PATCH 6/6] KVM: x86/mmu: explicitly check nx_hugepage in disallowed_hugepage_adjust()

[Sean Christopherson]

From: Mingwei Zhang <mizhang@xxxxxxxxxx>

Explicitly check if a NX huge page is disallowed when determining if a page
fault needs to be forced to use a smaller sized page. KVM incorrectly
assumes that the NX huge page mitigation is the only scenario where KVM
will create a shadow page instead of a huge page. Any scenario that causes
KVM to zap leaf SPTEs may result in having a SP that can be made huge
without violating the NX huge page mitigation. E.g. disabling of dirty
logging, zapping from mmu_notifier due to page migration, guest MTRR
changes that affect the viability of a huge page, etc...

Fixes: b8e8c8303ff2 ("kvm: mmu: ITLB_MULTIHIT mitigation")
Signed-off-by: Mingwei Zhang <mizhang@xxxxxxxxxx>
[sean: add barrier comments, use spte_to_sp()]
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
---
 arch/x86/kvm/mmu/mmu.c     | 17 +++++++++++++++--
 arch/x86/kvm/mmu/tdp_mmu.c |  6 ++++++
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8b4f3550710a..c6f018c6d2f5 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2908,6 +2908,19 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
 	    cur_level == fault->goal_level &&
 	    is_shadow_present_pte(spte) &&
 	    !is_large_pte(spte)) {
+		u64 page_mask;
+
+		/*
+		 * Ensure nx_huge_page_disallowed is read after checking for a
+		 * present shadow page.  A different vCPU may be concurrently
+		 * installing the shadow page if mmu_lock is held for read.
+		 * Pairs with the smp_wmb() in kvm_tdp_mmu_map().
+		 */
+		smp_rmb();
+
+		if (!spte_to_sp(spte)->nx_huge_page_disallowed)
+			return;
+
 		/*
 		 * A small SPTE exists for this pfn, but FNAME(fetch)
 		 * and __direct_map would like to create a large PTE
@@ -2915,8 +2928,8 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
 		 * patching back for them into pfn the next 9 bits of
 		 * the address.
 		 */
-		u64 page_mask = KVM_PAGES_PER_HPAGE(cur_level) -
-				KVM_PAGES_PER_HPAGE(cur_level - 1);
+		page_mask = KVM_PAGES_PER_HPAGE(cur_level) -
+			    KVM_PAGES_PER_HPAGE(cur_level - 1);
 		fault->pfn |= fault->gfn & page_mask;
 		fault->goal_level--;
 	}
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index d0e6b341652c..5cae5cdcfcbc 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1185,6 +1185,12 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 			tdp_mmu_init_child_sp(sp, &iter);
 
 			sp->nx_huge_page_disallowed = fault->huge_page_disallowed;
+			/*
+			 * Ensure nx_huge_page_disallowed is visible before the
+			 * SP is marked present, as mmu_lock is held for read.
+			 * Pairs with the smp_rmb() in disallowed_hugepage_adjust().
+			 */
+			smp_wmb();
 
 			if (tdp_mmu_link_sp(kvm, &iter, sp, true)) {
 				tdp_mmu_free_sp(sp);
-- 
2.35.1.1178.g4f1659d476-goog