Merge branch 'cve-2019-3016' into kvm-next-5.6

From Boris Ostrovsky:

The KVM hypervisor may provide a guest with ability to defer remote TLB
flush when the remote VCPU is not running. When this feature is used,
the TLB flush will happen only when the remote VPCU is scheduled to run
again. This will avoid unnecessary (and expensive) IPIs.

Under certain circumstances, when a guest initiates such deferred action,
the hypervisor may miss the request. It is also possible that the guest
may mistakenly assume that it has already marked remote VCPU as needing
a flush when in fact that request had already been processed by the
hypervisor. In both cases this will result in an invalid translation
being present in a vCPU, potentially allowing accesses to memory locations
in that guest's address space that should not be accessible.

Note that only intra-guest memory is vulnerable.

The five patches address both of these problems:
1. The first patch makes sure the hypervisor doesn't accidentally clear
a guest's remote flush request
2. The rest of the patches prevent the race between hypervisor
acknowledging a remote flush request and guest issuing a new one.

Conflicts:
	arch/x86/kvm/x86.c [move from kvm_arch_vcpu_free to kvm_arch_vcpu_destroy]

2 files changed, 45 insertions, 28 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 69e31dbdfdc2..329d01c689b7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -690,10 +690,10 @@ struct kvm_vcpu_arch {
 	bool pvclock_set_guest_stopped_request;
 
 	struct {
+		u8 preempted;
 		u64 msr_val;
 		u64 last_steal;
-		struct gfn_to_hva_cache stime;
-		struct kvm_steal_time steal;
+		struct gfn_to_pfn_cache cache;
 	} st;
 
 	u64 tsc_offset;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7e118883d8f1..0b0b143f0ab6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2648,45 +2648,47 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
 
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
+	struct kvm_host_map map;
+	struct kvm_steal_time *st;
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
+	/* -EAGAIN is returned in atomic context so we can just return. */
+	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT,
+			&map, &vcpu->arch.st.cache, false))
 		return;
 
+	st = map.hva +
+		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+
 	/*
 	 * Doing a TLB flush here, on the guest's behalf, can avoid
 	 * expensive IPIs.
 	 */
 	trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
-		vcpu->arch.st.steal.preempted & KVM_VCPU_FLUSH_TLB);
-	if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB)
+		st->preempted & KVM_VCPU_FLUSH_TLB);
+	if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
 		kvm_vcpu_flush_tlb(vcpu, false);
 
-	if (vcpu->arch.st.steal.version & 1)
-		vcpu->arch.st.steal.version += 1;  /* first time write, random junk */
+	vcpu->arch.st.preempted = 0;
 
-	vcpu->arch.st.steal.version += 1;
+	if (st->version & 1)
+		st->version += 1;  /* first time write, random junk */
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+	st->version += 1;
 
 	smp_wmb();
 
-	vcpu->arch.st.steal.steal += current->sched_info.run_delay -
+	st->steal += current->sched_info.run_delay -
 		vcpu->arch.st.last_steal;
 	vcpu->arch.st.last_steal = current->sched_info.run_delay;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
-
 	smp_wmb();
 
-	vcpu->arch.st.steal.version += 1;
+	st->version += 1;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false);
 }
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
@@ -2853,11 +2855,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (data & KVM_STEAL_RESERVED_MASK)
 			return 1;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
-						data & KVM_STEAL_VALID_BITS,
-						sizeof(struct kvm_steal_time)))
-			return 1;
-
 		vcpu->arch.st.msr_val = data;
 
 		if (!(data & KVM_MSR_ENABLED))
@@ -3567,15 +3564,25 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 {
+	struct kvm_host_map map;
+	struct kvm_steal_time *st;
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED;
+	if (vcpu->arch.st.preempted)
+		return;
+
+	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map,
+			&vcpu->arch.st.cache, true))
+		return;
+
+	st = map.hva +
+		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+
+	st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;
 
-	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
-			&vcpu->arch.st.steal.preempted,
-			offsetof(struct kvm_steal_time, preempted),
-			sizeof(vcpu->arch.st.steal.preempted));
+	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -9325,8 +9332,11 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+	struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache;
 	int idx;
 
+	kvm_release_pfn(cache->pfn, cache->dirty, cache);
+
 	kvmclock_reset(vcpu);
 
 	kvm_x86_ops->vcpu_free(vcpu);
@@ -9855,11 +9865,18 @@ out_free:
 
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 {
+	struct kvm_vcpu *vcpu;
+	int i;
+
 	/*
 	 * memslots->generation has been incremented.
 	 * mmio generation may have reached its maximum value.
 	 */
 	kvm_mmu_invalidate_mmio_sptes(kvm, gen);
+
+	/* Force re-initialization of steal_time cache */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vcpu_kick(vcpu);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,