Adding upstream version 6.7.7.upstream/6.7.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 36 insertions, 19 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f7901cb4d2..c57e181bba 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3425,8 +3425,8 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_mmu_page *sp;
 	int ret = RET_PF_INVALID;
-	u64 spte = 0ull;
-	u64 *sptep = NULL;
+	u64 spte;
+	u64 *sptep;
 	uint retry_count = 0;
 
 	if (!page_fault_can_be_fast(fault))
@@ -3442,6 +3442,14 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 		else
 			sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte);
 
+		/*
+		 * It's entirely possible for the mapping to have been zapped
+		 * by a different task, but the root page should always be
+		 * available as the vCPU holds a reference to its root(s).
+		 */
+		if (WARN_ON_ONCE(!sptep))
+			spte = REMOVED_SPTE;
+
 		if (!is_shadow_present_pte(spte))
 			break;
 
@@ -4479,21 +4487,28 @@ out_unlock:
 }
 #endif
 
-int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma)
 {
 	/*
-	 * If the guest's MTRRs may be used to compute the "real" memtype,
-	 * restrict the mapping level to ensure KVM uses a consistent memtype
-	 * across the entire mapping.  If the host MTRRs are ignored by TDP
-	 * (shadow_memtype_mask is non-zero), and the VM has non-coherent DMA
-	 * (DMA doesn't snoop CPU caches), KVM's ABI is to honor the memtype
-	 * from the guest's MTRRs so that guest accesses to memory that is
-	 * DMA'd aren't cached against the guest's wishes.
+	 * If host MTRRs are ignored (shadow_memtype_mask is non-zero), and the
+	 * VM has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is
+	 * to honor the memtype from the guest's MTRRs so that guest accesses
+	 * to memory that is DMA'd aren't cached against the guest's wishes.
 	 *
 	 * Note, KVM may still ultimately ignore guest MTRRs for certain PFNs,
 	 * e.g. KVM will force UC memtype for host MMIO.
 	 */
-	if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+	return vm_has_noncoherent_dma && shadow_memtype_mask;
+}
+
+int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+{
+	/*
+	 * If the guest's MTRRs may be used to compute the "real" memtype,
+	 * restrict the mapping level to ensure KVM uses a consistent memtype
+	 * across the entire mapping.
+	 */
+	if (kvm_mmu_honors_guest_mtrrs(vcpu->kvm)) {
 		for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) {
 			int page_num = KVM_PAGES_PER_HPAGE(fault->max_level);
 			gfn_t base = gfn_round_for_level(fault->gfn,
@@ -6785,11 +6800,7 @@ static unsigned long mmu_shrink_count(struct shrinker *shrink,
 	return percpu_counter_read_positive(&kvm_total_used_mmu_pages);
 }
 
-static struct shrinker mmu_shrinker = {
-	.count_objects = mmu_shrink_count,
-	.scan_objects = mmu_shrink_scan,
-	.seeks = DEFAULT_SEEKS * 10,
-};
+static struct shrinker *mmu_shrinker;
 
 static void mmu_destroy_caches(void)
 {
@@ -6922,10 +6933,16 @@ int kvm_mmu_vendor_module_init(void)
 	if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL))
 		goto out;
 
-	ret = register_shrinker(&mmu_shrinker, "x86-mmu");
-	if (ret)
+	mmu_shrinker = shrinker_alloc(0, "x86-mmu");
+	if (!mmu_shrinker)
 		goto out_shrinker;
 
+	mmu_shrinker->count_objects = mmu_shrink_count;
+	mmu_shrinker->scan_objects = mmu_shrink_scan;
+	mmu_shrinker->seeks = DEFAULT_SEEKS * 10;
+
+	shrinker_register(mmu_shrinker);
+
 	return 0;
 
 out_shrinker:
@@ -6947,7 +6964,7 @@ void kvm_mmu_vendor_module_exit(void)
 {
 	mmu_destroy_caches();
 	percpu_counter_destroy(&kvm_total_used_mmu_pages);
-	unregister_shrinker(&mmu_shrinker);
+	shrinker_free(mmu_shrinker);
 }
 
 /*