Merge tag 'kvm-4.9-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "All architectures:
   - move `make kvmconfig` stubs from x86
   - use 64 bits for debugfs stats

  ARM:
   - Important fixes for not using an in-kernel irqchip
   - handle SError exceptions and present them to guests if appropriate
   - proxying of GICV access at EL2 if guest mappings are unsafe
   - GICv3 on AArch32 on ARMv8
   - preparations for GICv3 save/restore, including ABI docs
   - cleanups and a bit of optimizations

  MIPS:
   - A couple of fixes in preparation for supporting MIPS EVA host
     kernels
   - MIPS SMP host & TLB invalidation fixes

  PPC:
   - Fix the bug which caused guests to falsely report lockups
   - other minor fixes
   - a small optimization

  s390:
   - Lazy enablement of runtime instrumentation
   - up to 255 CPUs for nested guests
   - rework of machine check deliver
   - cleanups and fixes

  x86:
   - IOMMU part of AMD's AVIC for vmexit-less interrupt delivery
   - Hyper-V TSC page
   - per-vcpu tsc_offset in debugfs
   - accelerated INS/OUTS in nVMX
   - cleanups and fixes"

* tag 'kvm-4.9-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (140 commits)
  KVM: MIPS: Drop dubious EntryHi optimisation
  KVM: MIPS: Invalidate TLB by regenerating ASIDs
  KVM: MIPS: Split kernel/user ASID regeneration
  KVM: MIPS: Drop other CPU ASIDs on guest MMU changes
  KVM: arm/arm64: vgic: Don't flush/sync without a working vgic
  KVM: arm64: Require in-kernel irqchip for PMU support
  KVM: PPC: Book3s PR: Allow access to unprivileged MMCR2 register
  KVM: PPC: Book3S PR: Support 64kB page size on POWER8E and POWER8NVL
  KVM: PPC: Book3S: Remove duplicate setting of the B field in tlbie
  KVM: PPC: BookE: Fix a sanity check
  KVM: PPC: Book3S HV: Take out virtual core piggybacking code
  KVM: PPC: Book3S: Treat VTB as a per-subcore register, not per-thread
  ARM: gic-v3: Work around definition of gic_write_bpr1
  KVM: nVMX: Fix the NMI IDT-vectoring handling
  KVM: VMX: Enable MSR-BASED TPR shadow even if APICv is inactive
  KVM: nVMX: Fix reload apic access page warning
  kvmconfig: add virtio-gpu to config fragment
  config: move x86 kvm_guest.config to a common location
  arm64: KVM: Remove duplicating init code for setting VMID
  ARM: KVM: Support vgic-v3
  ...

1 files changed, 105 insertions, 66 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 699f8726539a..6c633de84dd7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1367,7 +1367,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 
 static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
 {
-	u64 curr_offset = kvm_x86_ops->read_tsc_offset(vcpu);
+	u64 curr_offset = vcpu->arch.tsc_offset;
 	vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
 }
 
@@ -1413,6 +1413,12 @@ u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
 }
 EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
 
+static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+{
+	kvm_x86_ops->write_tsc_offset(vcpu, offset);
+	vcpu->arch.tsc_offset = offset;
+}
+
 void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -1425,7 +1431,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
 	offset = kvm_compute_tsc_offset(vcpu, data);
-	ns = get_kernel_ns();
+	ns = ktime_get_boot_ns();
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 
 	if (vcpu->arch.virtual_tsc_khz) {
@@ -1522,7 +1528,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 
 	if (guest_cpuid_has_tsc_adjust(vcpu) && !msr->host_initiated)
 		update_ia32_tsc_adjust_msr(vcpu, offset);
-	kvm_x86_ops->write_tsc_offset(vcpu, offset);
+	kvm_vcpu_write_tsc_offset(vcpu, offset);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
 	spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
@@ -1716,6 +1722,88 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 #endif
 }
 
+static u64 __get_kvmclock_ns(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
+	struct kvm_arch *ka = &kvm->arch;
+	s64 ns;
+
+	if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) {
+		u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc());
+		ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc);
+	} else {
+		ns = ktime_get_boot_ns() + ka->kvmclock_offset;
+	}
+
+	return ns;
+}
+
+u64 get_kvmclock_ns(struct kvm *kvm)
+{
+	unsigned long flags;
+	s64 ns;
+
+	local_irq_save(flags);
+	ns = __get_kvmclock_ns(kvm);
+	local_irq_restore(flags);
+
+	return ns;
+}
+
+static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
+{
+	struct kvm_vcpu_arch *vcpu = &v->arch;
+	struct pvclock_vcpu_time_info guest_hv_clock;
+
+	if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
+		&guest_hv_clock, sizeof(guest_hv_clock))))
+		return;
+
+	/* This VCPU is paused, but it's legal for a guest to read another
+	 * VCPU's kvmclock, so we really have to follow the specification where
+	 * it says that version is odd if data is being modified, and even after
+	 * it is consistent.
+	 *
+	 * Version field updates must be kept separate.  This is because
+	 * kvm_write_guest_cached might use a "rep movs" instruction, and
+	 * writes within a string instruction are weakly ordered.  So there
+	 * are three writes overall.
+	 *
+	 * As a small optimization, only write the version field in the first
+	 * and third write.  The vcpu->pv_time cache is still valid, because the
+	 * version field is the first in the struct.
+	 */
+	BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
+
+	vcpu->hv_clock.version = guest_hv_clock.version + 1;
+	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+				&vcpu->hv_clock,
+				sizeof(vcpu->hv_clock.version));
+
+	smp_wmb();
+
+	/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
+	vcpu->hv_clock.flags |= (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
+
+	if (vcpu->pvclock_set_guest_stopped_request) {
+		vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
+		vcpu->pvclock_set_guest_stopped_request = false;
+	}
+
+	trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
+
+	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+				&vcpu->hv_clock,
+				sizeof(vcpu->hv_clock));
+
+	smp_wmb();
+
+	vcpu->hv_clock.version++;
+	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+				&vcpu->hv_clock,
+				sizeof(vcpu->hv_clock.version));
+}
+
 static int kvm_guest_time_update(struct kvm_vcpu *v)
 {
 	unsigned long flags, tgt_tsc_khz;
@@ -1723,7 +1811,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	struct kvm_arch *ka = &v->kvm->arch;
 	s64 kernel_ns;
 	u64 tsc_timestamp, host_tsc;
-	struct pvclock_vcpu_time_info guest_hv_clock;
 	u8 pvclock_flags;
 	bool use_master_clock;
 
@@ -1752,7 +1839,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	}
 	if (!use_master_clock) {
 		host_tsc = rdtsc();
-		kernel_ns = get_kernel_ns();
+		kernel_ns = ktime_get_boot_ns();
 	}
 
 	tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
@@ -1777,8 +1864,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	local_irq_restore(flags);
 
-	if (!vcpu->pv_time_enabled)
-		return 0;
+	/* With all the info we got, fill in the values */
 
 	if (kvm_has_tsc_control)
 		tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz);
@@ -1790,64 +1876,21 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		vcpu->hw_tsc_khz = tgt_tsc_khz;
 	}
 
-	/* With all the info we got, fill in the values */
 	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
 	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
 	vcpu->last_guest_tsc = tsc_timestamp;
 
-	if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
-		&guest_hv_clock, sizeof(guest_hv_clock))))
-		return 0;
-
-	/* This VCPU is paused, but it's legal for a guest to read another
-	 * VCPU's kvmclock, so we really have to follow the specification where
-	 * it says that version is odd if data is being modified, and even after
-	 * it is consistent.
-	 *
-	 * Version field updates must be kept separate.  This is because
-	 * kvm_write_guest_cached might use a "rep movs" instruction, and
-	 * writes within a string instruction are weakly ordered.  So there
-	 * are three writes overall.
-	 *
-	 * As a small optimization, only write the version field in the first
-	 * and third write.  The vcpu->pv_time cache is still valid, because the
-	 * version field is the first in the struct.
-	 */
-	BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
-
-	vcpu->hv_clock.version = guest_hv_clock.version + 1;
-	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
-				&vcpu->hv_clock,
-				sizeof(vcpu->hv_clock.version));
-
-	smp_wmb();
-
-	/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
-	pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
-
-	if (vcpu->pvclock_set_guest_stopped_request) {
-		pvclock_flags |= PVCLOCK_GUEST_STOPPED;
-		vcpu->pvclock_set_guest_stopped_request = false;
-	}
-
 	/* If the host uses TSC clocksource, then it is stable */
+	pvclock_flags = 0;
 	if (use_master_clock)
 		pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
 
 	vcpu->hv_clock.flags = pvclock_flags;
 
-	trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
-
-	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
-				&vcpu->hv_clock,
-				sizeof(vcpu->hv_clock));
-
-	smp_wmb();
-
-	vcpu->hv_clock.version++;
-	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
-				&vcpu->hv_clock,
-				sizeof(vcpu->hv_clock.version));
+	if (vcpu->pv_time_enabled)
+		kvm_setup_pvclock_page(v);
+	if (v == kvm_get_vcpu(v->kvm, 0))
+		kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
 }
 
@@ -2746,7 +2789,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		if (check_tsc_unstable()) {
 			u64 offset = kvm_compute_tsc_offset(vcpu,
 						vcpu->arch.last_guest_tsc);
-			kvm_x86_ops->write_tsc_offset(vcpu, offset);
+			kvm_vcpu_write_tsc_offset(vcpu, offset);
 			vcpu->arch.tsc_catchup = 1;
 		}
 		if (kvm_lapic_hv_timer_in_use(vcpu) &&
@@ -4039,7 +4082,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	case KVM_SET_CLOCK: {
 		struct kvm_clock_data user_ns;
 		u64 now_ns;
-		s64 delta;
 
 		r = -EFAULT;
 		if (copy_from_user(&user_ns, argp, sizeof(user_ns)))
@@ -4051,10 +4093,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 		r = 0;
 		local_irq_disable();
-		now_ns = get_kernel_ns();
-		delta = user_ns.clock - now_ns;
+		now_ns = __get_kvmclock_ns(kvm);
+		kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
 		local_irq_enable();
-		kvm->arch.kvmclock_offset = delta;
 		kvm_gen_update_masterclock(kvm);
 		break;
 	}
@@ -4062,10 +4103,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		struct kvm_clock_data user_ns;
 		u64 now_ns;
 
-		local_irq_disable();
-		now_ns = get_kernel_ns();
-		user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
-		local_irq_enable();
+		now_ns = get_kvmclock_ns(kvm);
+		user_ns.clock = now_ns;
 		user_ns.flags = 0;
 		memset(&user_ns.pad, 0, sizeof(user_ns.pad));
 
@@ -6700,7 +6739,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	kvm_put_guest_xcr0(vcpu);
 
-	/* Interrupt is enabled by handle_external_intr() */
 	kvm_x86_ops->handle_external_intr(vcpu);
 
 	++vcpu->stat.exits;
@@ -7530,7 +7568,7 @@ int kvm_arch_hardware_enable(void)
 	 * before any KVM threads can be running.  Unfortunately, we can't
 	 * bring the TSCs fully up to date with real time, as we aren't yet far
 	 * enough into CPU bringup that we know how much real time has actually
-	 * elapsed; our helper function, get_kernel_ns() will be using boot
+	 * elapsed; our helper function, ktime_get_boot_ns() will be using boot
 	 * variables that haven't been updated yet.
 	 *
 	 * So we simply find the maximum observed TSC above, then record the
@@ -7765,6 +7803,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	mutex_init(&kvm->arch.apic_map_lock);
 	spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
 
+	kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
 	pvclock_update_vm_gtod_copy(kvm);
 
 	INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);