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

Pull KVM fixes from Paolo Bonzini:
 "ARM and x86 fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: nVMX: VMX instructions: fix segment checks when L1 is in long mode.
  KVM: LAPIC: cap __delay at lapic_timer_advance_ns
  KVM: x86: move nsec_to_cycles from x86.c to x86.h
  pvclock: Get rid of __pvclock_read_cycles in function pvclock_read_flags
  pvclock: Cleanup to remove function pvclock_get_nsec_offset
  pvclock: Add CPU barriers to get correct version value
  KVM: arm/arm64: Stop leaking vcpu pid references
  arm64: KVM: fix build with CONFIG_ARM_PMU disabled

7 files changed, 39 insertions, 37 deletions

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 893941ec98dc..f1bde7c4e736 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -263,6 +263,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_vgic_vcpu_destroy(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
+	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index fdcc04020636..7c1c89598688 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -69,29 +69,22 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 }
 
 static __always_inline
-u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src)
-{
-	u64 delta = rdtsc_ordered() - src->tsc_timestamp;
-	return pvclock_scale_delta(delta, src->tsc_to_system_mul,
-				   src->tsc_shift);
-}
-
-static __always_inline
 unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 			       cycle_t *cycles, u8 *flags)
 {
 	unsigned version;
-	cycle_t ret, offset;
-	u8 ret_flags;
+	cycle_t offset;
+	u64 delta;
 
 	version = src->version;
+	/* Make the latest version visible */
+	smp_rmb();
 
-	offset = pvclock_get_nsec_offset(src);
-	ret = src->system_time + offset;
-	ret_flags = src->flags;
-
-	*cycles = ret;
-	*flags = ret_flags;
+	delta = rdtsc_ordered() - src->tsc_timestamp;
+	offset = pvclock_scale_delta(delta, src->tsc_to_system_mul,
+				   src->tsc_shift);
+	*cycles = src->system_time + offset;
+	*flags = src->flags;
 	return version;
 }
 
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 99bfc025111d..06c58ce46762 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -61,11 +61,16 @@ void pvclock_resume(void)
 u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
 {
 	unsigned version;
-	cycle_t ret;
 	u8 flags;
 
 	do {
-		version = __pvclock_read_cycles(src, &ret, &flags);
+		version = src->version;
+		/* Make the latest version visible */
+		smp_rmb();
+
+		flags = src->flags;
+		/* Make sure that the version double-check is last. */
+		smp_rmb();
 	} while ((src->version & 1) || version != src->version);
 
 	return flags & valid_flags;
@@ -80,6 +85,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 
 	do {
 		version = __pvclock_read_cycles(src, &ret, &flags);
+		/* Make sure that the version double-check is last. */
+		smp_rmb();
 	} while ((src->version & 1) || version != src->version);
 
 	if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index bbb5b283ff63..a397200281c1 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1310,7 +1310,8 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 
 	/* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
 	if (guest_tsc < tsc_deadline)
-		__delay(tsc_deadline - guest_tsc);
+		__delay(min(tsc_deadline - guest_tsc,
+			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
 }
 
 static void start_apic_timer(struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 003618e324ce..64a79f271276 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6671,7 +6671,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 
 	/* Checks for #GP/#SS exceptions. */
 	exn = false;
-	if (is_protmode(vcpu)) {
+	if (is_long_mode(vcpu)) {
+		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
+		 * non-canonical form. This is the only check on the memory
+		 * destination for long mode!
+		 */
+		exn = is_noncanonical_address(*ret);
+	} else if (is_protmode(vcpu)) {
 		/* Protected mode: apply checks for segment validity in the
 		 * following order:
 		 * - segment type check (#GP(0) may be thrown)
@@ -6688,17 +6694,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 			 * execute-only code segment
 			 */
 			exn = ((s.type & 0xa) == 8);
-	}
-	if (exn) {
-		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
-		return 1;
-	}
-	if (is_long_mode(vcpu)) {
-		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
-		 * non-canonical form. This is an only check for long mode.
-		 */
-		exn = is_noncanonical_address(*ret);
-	} else if (is_protmode(vcpu)) {
+		if (exn) {
+			kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+			return 1;
+		}
 		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
 		 */
 		exn = (s.unusable != 0);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 902d9da12392..7da5dd2057a9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1244,12 +1244,6 @@ static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0);
 static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
 static unsigned long max_tsc_khz;
 
-static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
-{
-	return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
-				   vcpu->arch.virtual_tsc_shift);
-}
-
 static u32 adjust_tsc_khz(u32 khz, s32 ppm)
 {
 	u64 v = (u64)khz * (1000000 + ppm);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 7ce3634ab5fe..a82ca466b62e 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -2,6 +2,7 @@
 #define ARCH_X86_KVM_X86_H
 
 #include <linux/kvm_host.h>
+#include <asm/pvclock.h>
 #include "kvm_cache_regs.h"
 
 #define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL
@@ -195,6 +196,12 @@ extern unsigned int lapic_timer_advance_ns;
 
 extern struct static_key kvm_no_apic_vcpu;
 
+static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
+{
+	return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
+				   vcpu->arch.virtual_tsc_shift);
+}
+
 /* Same "calling convention" as do_div:
  * - divide (n << 32) by base
  * - put result in n