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

Pull KVM fixes from Radim Krčmář:
 "ARM fixes:
   - Wrong indentation in the PMU code from the merge window
   - A long-time bug occuring with running ntpd on the host, candidate
     for stable
   - Properly handle (and warn about) the unsupported configuration of
     running on systems with less than 40 bits of PA space
   - More fixes to the PM and hotplug notifier stuff from the merge
     window

  x86:
   - leak of guest xcr0 (typically shows up as SIGILL)
   - new maintainer (who is sending the pull request too)
   - fix for merge window regression
   - fix for guest CPUID"

Paolo Bonzini points out:
 "For the record, this tag is signed by me because I prepared the pull
  request.  Further pull requests for 4.6 will be signed and sent out by
  Radim directly"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: mask CPUID(0xD,0x1).EAX against host value
  kvm: x86: do not leak guest xcr0 into host interrupt handlers
  KVM: MMU: fix permission_fault()
  KVM: new maintainer on the block
  arm64: KVM: unregister notifiers in hyp mode teardown path
  arm64: KVM: Warn when PARange is less than 40 bits
  KVM: arm/arm64: Handle forward time correction gracefully
  arm64: KVM: Add braces to multi-line if statement in virtual PMU code

MAINTAINERS

@@ -6252,8 +6252,8 @@ S:	Maintained
 F:	tools/testing/selftests
 
 KERNEL VIRTUAL MACHINE (KVM)
-M:	Gleb Natapov <gleb@kernel.org>
 M:	Paolo Bonzini <pbonzini@redhat.com>
+M:	Radim Krčmář <rkrcmar@redhat.com>
 L:	kvm@vger.kernel.org
 W:	http://www.linux-kvm.org
 T:	git git://git.kernel.org/pub/scm/virt/kvm/kvm.git

arch/arm/kvm/arm.c

@@ -1112,10 +1112,17 @@ static void __init hyp_cpu_pm_init(void)
 {
 	cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
 }
+static void __init hyp_cpu_pm_exit(void)
+{
+	cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
+}
 #else
 static inline void hyp_cpu_pm_init(void)
 {
 }
+static inline void hyp_cpu_pm_exit(void)
+{
+}
 #endif
 
 static void teardown_common_resources(void)
@@ -1141,9 +1148,7 @@ static int init_subsystems(void)
 	/*
 	 * Register CPU Hotplug notifier
 	 */
-	cpu_notifier_register_begin();
-	err = __register_cpu_notifier(&hyp_init_cpu_nb);
-	cpu_notifier_register_done();
+	err = register_cpu_notifier(&hyp_init_cpu_nb);
 	if (err) {
 		kvm_err("Cannot register KVM init CPU notifier (%d)\n", err);
 		return err;
@@ -1193,6 +1198,8 @@ static void teardown_hyp_mode(void)
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu)
 		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+	unregister_cpu_notifier(&hyp_init_cpu_nb);
+	hyp_cpu_pm_exit();
 }
 
 static int init_vhe_mode(void)

arch/arm64/include/asm/kvm_arm.h

@@ -151,8 +151,7 @@
  */
 #define VTCR_EL2_FLAGS		(VTCR_EL2_TG0_64K | VTCR_EL2_SH0_INNER | \
 				 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
-				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B | \
-				 VTCR_EL2_RES1)
+				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_RES1)
 #define VTTBR_X		(38 - VTCR_EL2_T0SZ_40B)
 #else
 /*
@@ -163,8 +162,7 @@
  */
 #define VTCR_EL2_FLAGS		(VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \
 				 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
-				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B | \
-				 VTCR_EL2_RES1)
+				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_RES1)
 #define VTTBR_X		(37 - VTCR_EL2_T0SZ_40B)
 #endif
 

arch/arm64/include/asm/kvm_asm.h

@@ -54,7 +54,7 @@ extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
-extern void __init_stage2_translation(void);
+extern u32 __init_stage2_translation(void);
 
 #endif
 

arch/arm64/include/asm/kvm_host.h

@@ -369,11 +369,12 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
 int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 
-/* #define kvm_call_hyp(f, ...) __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__) */
-
 static inline void __cpu_init_stage2(void)
 {
-	kvm_call_hyp(__init_stage2_translation);
+	u32 parange = kvm_call_hyp(__init_stage2_translation);
+
+	WARN_ONCE(parange < 40,
+		  "PARange is %d bits, unsupported configuration!", parange);
 }
 
 #endif /* __ARM64_KVM_HOST_H__ */

arch/arm64/kvm/hyp/s2-setup.c

@@ -20,9 +20,10 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_hyp.h>
 
-void __hyp_text __init_stage2_translation(void)
+u32 __hyp_text __init_stage2_translation(void)
 {
 	u64 val = VTCR_EL2_FLAGS;
+	u64 parange;
 	u64 tmp;
 
 	/*
@@ -30,7 +31,39 @@ void __hyp_text __init_stage2_translation(void)
 	 * bits in VTCR_EL2. Amusingly, the PARange is 4 bits, while
 	 * PS is only 3. Fortunately, bit 19 is RES0 in VTCR_EL2...
 	 */
-	val |= (read_sysreg(id_aa64mmfr0_el1) & 7) << 16;
+	parange = read_sysreg(id_aa64mmfr0_el1) & 7;
+	val |= parange << 16;
+
+	/* Compute the actual PARange... */
+	switch (parange) {
+	case 0:
+		parange = 32;
+		break;
+	case 1:
+		parange = 36;
+		break;
+	case 2:
+		parange = 40;
+		break;
+	case 3:
+		parange = 42;
+		break;
+	case 4:
+		parange = 44;
+		break;
+	case 5:
+	default:
+		parange = 48;
+		break;
+	}
+
+	/*
+	 * ... and clamp it to 40 bits, unless we have some braindead
+	 * HW that implements less than that. In all cases, we'll
+	 * return that value for the rest of the kernel to decide what
+	 * to do.
+	 */
+	val |= 64 - (parange > 40 ? 40 : parange);
 
 	/*
 	 * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS
@@ -42,4 +75,6 @@ void __hyp_text __init_stage2_translation(void)
 			VTCR_EL2_VS_8BIT;
 
 	write_sysreg(val, vtcr_el2);
+
+	return parange;
 }

arch/x86/kvm/cpuid.c

@@ -534,6 +534,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			do_cpuid_1_ent(&entry[i], function, idx);
 			if (idx == 1) {
 				entry[i].eax &= kvm_cpuid_D_1_eax_x86_features;
+				cpuid_mask(&entry[i].eax, CPUID_D_1_EAX);
 				entry[i].ebx = 0;
 				if (entry[i].eax & (F(XSAVES)|F(XSAVEC)))
 					entry[i].ebx =

arch/x86/kvm/mmu.h

@@ -173,10 +173,9 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	int index = (pfec >> 1) +
 		    (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
 	bool fault = (mmu->permissions[index] >> pte_access) & 1;
+	u32 errcode = PFERR_PRESENT_MASK;
 
 	WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK));
-	pfec |= PFERR_PRESENT_MASK;
-
 	if (unlikely(mmu->pkru_mask)) {
 		u32 pkru_bits, offset;
 
@@ -189,15 +188,15 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		pkru_bits = (kvm_read_pkru(vcpu) >> (pte_pkey * 2)) & 3;
 
 		/* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */
-		offset = pfec - 1 +
+		offset = (pfec & ~1) +
 			((pte_access & PT_USER_MASK) << (PFERR_RSVD_BIT - PT_USER_SHIFT));
 
 		pkru_bits &= mmu->pkru_mask >> offset;
-		pfec |= -pkru_bits & PFERR_PK_MASK;
+		errcode |= -pkru_bits & PFERR_PK_MASK;
 		fault |= (pkru_bits != 0);
 	}
 
-	return -(uint32_t)fault & pfec;
+	return -(u32)fault & errcode;
 }
 
 void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);

arch/x86/kvm/paging_tmpl.h

@@ -360,7 +360,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 			goto error;
 
 		if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) {
-			errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
+			errcode = PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
 			goto error;
 		}
 

arch/x86/kvm/x86.c

@@ -700,7 +700,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 		if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
 			return 1;
 	}
-	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
 
 	if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
@@ -6590,8 +6589,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->prepare_guest_switch(vcpu);
 	if (vcpu->fpu_active)
 		kvm_load_guest_fpu(vcpu);
-	kvm_load_guest_xcr0(vcpu);
-
 	vcpu->mode = IN_GUEST_MODE;
 
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
@@ -6618,6 +6615,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto cancel_injection;
 	}
 
+	kvm_load_guest_xcr0(vcpu);
+
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
@@ -6667,6 +6666,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
+	kvm_put_guest_xcr0(vcpu);
+
 	/* Interrupt is enabled by handle_external_intr() */
 	kvm_x86_ops->handle_external_intr(vcpu);
 
@@ -7314,7 +7315,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	 * and assume host would use all available bits.
 	 * Guest xcr0 would be loaded later.
 	 */
-	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
@@ -7323,8 +7323,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	kvm_put_guest_xcr0(vcpu);
-
 	if (!vcpu->guest_fpu_loaded) {
 		vcpu->fpu_counter = 0;
 		return;

virt/kvm/arm/arch_timer.c

@@ -91,6 +91,8 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
 	vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired);
 	vcpu->arch.timer_cpu.armed = false;
 
+	WARN_ON(!kvm_timer_should_fire(vcpu));
+
 	/*
 	 * If the vcpu is blocked we want to wake it up so that it will see
 	 * the timer has expired when entering the guest.
@@ -98,10 +100,46 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
 	kvm_vcpu_kick(vcpu);
 }
 
+static u64 kvm_timer_compute_delta(struct kvm_vcpu *vcpu)
+{
+	cycle_t cval, now;
+
+	cval = vcpu->arch.timer_cpu.cntv_cval;
+	now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+
+	if (now < cval) {
+		u64 ns;
+
+		ns = cyclecounter_cyc2ns(timecounter->cc,
+					 cval - now,
+					 timecounter->mask,
+					 &timecounter->frac);
+		return ns;
+	}
+
+	return 0;
+}
+
 static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt)
 {
 	struct arch_timer_cpu *timer;
+	struct kvm_vcpu *vcpu;
+	u64 ns;
+
 	timer = container_of(hrt, struct arch_timer_cpu, timer);
+	vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu);
+
+	/*
+	 * Check that the timer has really expired from the guest's
+	 * PoV (NTP on the host may have forced it to expire
+	 * early). If we should have slept longer, restart it.
+	 */
+	ns = kvm_timer_compute_delta(vcpu);
+	if (unlikely(ns)) {
+		hrtimer_forward_now(hrt, ns_to_ktime(ns));
+		return HRTIMER_RESTART;
+	}
+
 	queue_work(wqueue, &timer->expired);
 	return HRTIMER_NORESTART;
 }
@@ -176,8 +214,6 @@ static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
 void kvm_timer_schedule(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
-	u64 ns;
-	cycle_t cval, now;
 
 	BUG_ON(timer_is_armed(timer));
 
@@ -197,14 +233,7 @@ void kvm_timer_schedule(struct kvm_vcpu *vcpu)
 		return;
 
 	/*  The timer has not yet expired, schedule a background timer */
-	cval = timer->cntv_cval;
-	now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
-
-	ns = cyclecounter_cyc2ns(timecounter->cc,
-				 cval - now,
-				 timecounter->mask,
-				 &timecounter->frac);
-	timer_arm(timer, ns);
+	timer_arm(timer, kvm_timer_compute_delta(vcpu));
 }
 
 void kvm_timer_unschedule(struct kvm_vcpu *vcpu)

virt/kvm/arm/pmu.c

@@ -193,11 +193,12 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
 {
 	u64 reg = 0;
 
-	if ((vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
+	if ((vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) {
 		reg = vcpu_sys_reg(vcpu, PMOVSSET_EL0);
 		reg &= vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
 		reg &= vcpu_sys_reg(vcpu, PMINTENSET_EL1);
 		reg &= kvm_pmu_valid_counter_mask(vcpu);
+	}
 
 	return reg;
 }