Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "x86:
   - Fixes for the new scalable MMU
   - Fixes for migration of nested hypervisors on AMD
   - Fix for clang integrated assembler
   - Fix for left shift by 64 (UBSAN)
   - Small cleanups
   - Straggler SEV-ES patch

  ARM:
   - VM init cleanups
   - PSCI relay cleanups
   - Kill CONFIG_KVM_ARM_PMU
   - Fixup __init annotations
   - Fixup reg_to_encoding()
   - Fix spurious PMCR_EL0 access

  Misc:
   - selftests cleanups"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (38 commits)
  KVM: x86: __kvm_vcpu_halt can be static
  KVM: SVM: Add support for booting APs in an SEV-ES guest
  KVM: nSVM: cancel KVM_REQ_GET_NESTED_STATE_PAGES on nested vmexit
  KVM: nSVM: mark vmcb as dirty when forcingly leaving the guest mode
  KVM: nSVM: correctly restore nested_run_pending on migration
  KVM: x86/mmu: Clarify TDP MMU page list invariants
  KVM: x86/mmu: Ensure TDP MMU roots are freed after yield
  kvm: check tlbs_dirty directly
  KVM: x86: change in pv_eoi_get_pending() to make code more readable
  MAINTAINERS: Really update email address for Sean Christopherson
  KVM: x86: fix shift out of bounds reported by UBSAN
  KVM: selftests: Implement perf_test_util more conventionally
  KVM: selftests: Use vm_create_with_vcpus in create_vm
  KVM: selftests: Factor out guest mode code
  KVM/SVM: Remove leftover __svm_vcpu_run prototype from svm.c
  KVM: SVM: Add register operand to vmsave call in sev_es_vcpu_load
  KVM: x86/mmu: Optimize not-present/MMIO SPTE check in get_mmio_spte()
  KVM: x86/mmu: Use raw level to index into MMIO walks' sptes array
  KVM: x86/mmu: Get root level from walkers when retrieving MMIO SPTE
  KVM: x86/mmu: Use -1 to flag an undefined spte in get_mmio_spte()
  ...

1 files changed, 30 insertions, 23 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c478904af518..6d16481aa29d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3493,26 +3493,25 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
  * Return the level of the lowest level SPTE added to sptes.
  * That SPTE may be non-present.
  */
-static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level)
 {
 	struct kvm_shadow_walk_iterator iterator;
-	int leaf = vcpu->arch.mmu->root_level;
+	int leaf = -1;
 	u64 spte;
 
-
 	walk_shadow_page_lockless_begin(vcpu);
 
-	for (shadow_walk_init(&iterator, vcpu, addr);
+	for (shadow_walk_init(&iterator, vcpu, addr),
+	     *root_level = iterator.level;
 	     shadow_walk_okay(&iterator);
 	     __shadow_walk_next(&iterator, spte)) {
 		leaf = iterator.level;
 		spte = mmu_spte_get_lockless(iterator.sptep);
 
-		sptes[leaf - 1] = spte;
+		sptes[leaf] = spte;
 
 		if (!is_shadow_present_pte(spte))
 			break;
-
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -3520,14 +3519,12 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
 	return leaf;
 }
 
-/* return true if reserved bit is detected on spte. */
+/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
 static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
-	u64 sptes[PT64_ROOT_MAX_LEVEL];
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
 	struct rsvd_bits_validate *rsvd_check;
-	int root = vcpu->arch.mmu->shadow_root_level;
-	int leaf;
-	int level;
+	int root, leaf, level;
 	bool reserved = false;
 
 	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) {
@@ -3536,35 +3533,45 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 	}
 
 	if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa))
-		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes);
+		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
 	else
-		leaf = get_walk(vcpu, addr, sptes);
+		leaf = get_walk(vcpu, addr, sptes, &root);
+
+	if (unlikely(leaf < 0)) {
+		*sptep = 0ull;
+		return reserved;
+	}
+
+	*sptep = sptes[leaf];
+
+	/*
+	 * Skip reserved bits checks on the terminal leaf if it's not a valid
+	 * SPTE.  Note, this also (intentionally) skips MMIO SPTEs, which, by
+	 * design, always have reserved bits set.  The purpose of the checks is
+	 * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs.
+	 */
+	if (!is_shadow_present_pte(sptes[leaf]))
+		leaf++;
 
 	rsvd_check = &vcpu->arch.mmu->shadow_zero_check;
 
-	for (level = root; level >= leaf; level--) {
-		if (!is_shadow_present_pte(sptes[level - 1]))
-			break;
+	for (level = root; level >= leaf; level--)
 		/*
 		 * Use a bitwise-OR instead of a logical-OR to aggregate the
 		 * reserved bit and EPT's invalid memtype/XWR checks to avoid
 		 * adding a Jcc in the loop.
 		 */
-		reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level - 1]) |
-			    __is_rsvd_bits_set(rsvd_check, sptes[level - 1],
-					       level);
-	}
+		reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) |
+			    __is_rsvd_bits_set(rsvd_check, sptes[level], level);
 
 	if (reserved) {
 		pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n",
 		       __func__, addr);
 		for (level = root; level >= leaf; level--)
 			pr_err("------ spte 0x%llx level %d.\n",
-			       sptes[level - 1], level);
+			       sptes[level], level);
 	}
 
-	*sptep = sptes[leaf - 1];
-
 	return reserved;
 }