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

Pull second batch of KVM changes from Paolo Bonzini:
 "This mostly includes the PPC changes for 4.1, which this time cover
  Book3S HV only (debugging aids, minor performance improvements and
  some cleanups).  But there are also bug fixes and small cleanups for
  ARM, x86 and s390.

  The task_migration_notifier revert and real fix is still pending
  review, but I'll send it as soon as possible after -rc1"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (29 commits)
  KVM: arm/arm64: check IRQ number on userland injection
  KVM: arm: irqfd: fix value returned by kvm_irq_map_gsi
  KVM: VMX: Preserve host CR4.MCE value while in guest mode.
  KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
  KVM: PPC: Book3S HV: Translate kvmhv_commence_exit to C
  KVM: PPC: Book3S HV: Streamline guest entry and exit
  KVM: PPC: Book3S HV: Use bitmap of active threads rather than count
  KVM: PPC: Book3S HV: Use decrementer to wake napping threads
  KVM: PPC: Book3S HV: Don't wake thread with no vcpu on guest IPI
  KVM: PPC: Book3S HV: Get rid of vcore nap_count and n_woken
  KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
  KVM: PPC: Book3S HV: Minor cleanups
  KVM: PPC: Book3S HV: Simplify handling of VCPUs that need a VPA update
  KVM: PPC: Book3S HV: Accumulate timing information for real-mode code
  KVM: PPC: Book3S HV: Create debugfs file for each guest's HPT
  KVM: PPC: Book3S HV: Add ICP real mode counters
  KVM: PPC: Book3S HV: Move virtual mode ICP functions to real-mode
  KVM: PPC: Book3S HV: Convert ICS mutex lock to spin lock
  KVM: PPC: Book3S HV: Add guest->host real mode completion counters
  KVM: PPC: Book3S HV: Add helpers for lock/unlock hpte
  ...

4 files changed, 31 insertions, 22 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index d67206a..629af0f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -683,8 +683,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 	unsigned long bitmap = 1;
 	struct kvm_lapic **dst;
 	int i;
-	bool ret = false;
-	bool x2apic_ipi = src && apic_x2apic_mode(src);
+	bool ret, x2apic_ipi;
 
 	*r = -1;
 
@@ -696,16 +695,18 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 	if (irq->shorthand)
 		return false;
 
+	x2apic_ipi = src && apic_x2apic_mode(src);
 	if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST))
 		return false;
 
+	ret = true;
 	rcu_read_lock();
 	map = rcu_dereference(kvm->arch.apic_map);
 
-	if (!map)
+	if (!map) {
+		ret = false;
 		goto out;
-
-	ret = true;
+	}
 
 	if (irq->dest_mode == APIC_DEST_PHYSICAL) {
 		if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 146f295..d43867c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4481,9 +4481,11 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 		pfn = spte_to_pfn(*sptep);
 
 		/*
-		 * Only EPT supported for now; otherwise, one would need to
-		 * find out efficiently whether the guest page tables are
-		 * also using huge pages.
+		 * We cannot do huge page mapping for indirect shadow pages,
+		 * which are found on the last rmap (level = 1) when not using
+		 * tdp; such shadow pages are synced with the page table in
+		 * the guest, and the guest page table is using 4K page size
+		 * mapping if the indirect sp has level = 1.
 		 */
 		if (sp->role.direct &&
 			!kvm_is_reserved_pfn(pfn) &&
@@ -4504,19 +4506,12 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	bool flush = false;
 	unsigned long *rmapp;
 	unsigned long last_index, index;
-	gfn_t gfn_start, gfn_end;
 
 	spin_lock(&kvm->mmu_lock);
 
-	gfn_start = memslot->base_gfn;
-	gfn_end = memslot->base_gfn + memslot->npages - 1;
-
-	if (gfn_start >= gfn_end)
-		goto out;
-
 	rmapp = memslot->arch.rmap[0];
-	last_index = gfn_to_index(gfn_end, memslot->base_gfn,
-					PT_PAGE_TABLE_LEVEL);
+	last_index = gfn_to_index(memslot->base_gfn + memslot->npages - 1,
+				memslot->base_gfn, PT_PAGE_TABLE_LEVEL);
 
 	for (index = 0; index <= last_index; ++index, ++rmapp) {
 		if (*rmapp)
@@ -4534,7 +4529,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	if (flush)
 		kvm_flush_remote_tlbs(kvm);
 
-out:
 	spin_unlock(&kvm->mmu_lock);
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f5e8dce..f7b6168 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3622,8 +3622,16 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long hw_cr4 = cr4 | (to_vmx(vcpu)->rmode.vm86_active ?
-		    KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
+	/*
+	 * Pass through host's Machine Check Enable value to hw_cr4, which
+	 * is in force while we are in guest mode.  Do not let guests control
+	 * this bit, even if host CR4.MCE == 0.
+	 */
+	unsigned long hw_cr4 =
+		(cr4_read_shadow() & X86_CR4_MCE) |
+		(cr4 & ~X86_CR4_MCE) |
+		(to_vmx(vcpu)->rmode.vm86_active ?
+		 KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
 
 	if (cr4 & X86_CR4_VMXE) {
 		/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e1a8126..ed31c31 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5799,7 +5799,6 @@ int kvm_arch_init(void *opaque)
 	kvm_set_mmio_spte_mask();
 
 	kvm_x86_ops = ops;
-	kvm_init_msr_list();
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0);
@@ -7253,7 +7252,14 @@ void kvm_arch_hardware_disable(void)
 
 int kvm_arch_hardware_setup(void)
 {
-	return kvm_x86_ops->hardware_setup();
+	int r;
+
+	r = kvm_x86_ops->hardware_setup();
+	if (r != 0)
+		return r;
+
+	kvm_init_msr_list();
+	return 0;
 }
 
 void kvm_arch_hardware_unsetup(void)