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

Pull KVM update from Paolo Bonzini:
 "3.19 changes for KVM:

   - spring cleaning: removed support for IA64, and for hardware-
     assisted virtualization on the PPC970

   - ARM, PPC, s390 all had only small fixes

  For x86:
   - small performance improvements (though only on weird guests)
   - usual round of hardware-compliancy fixes from Nadav
   - APICv fixes
   - XSAVES support for hosts and guests.  XSAVES hosts were broken
     because the (non-KVM) XSAVES patches inadvertently changed the KVM
     userspace ABI whenever XSAVES was enabled; hence, this part is
     going to stable.  Guest support is just a matter of exposing the
     feature and CPUID leaves support"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (179 commits)
  KVM: move APIC types to arch/x86/
  KVM: PPC: Book3S: Enable in-kernel XICS emulation by default
  KVM: PPC: Book3S HV: Improve H_CONFER implementation
  KVM: PPC: Book3S HV: Fix endianness of instruction obtained from HEIR register
  KVM: PPC: Book3S HV: Remove code for PPC970 processors
  KVM: PPC: Book3S HV: Tracepoints for KVM HV guest interactions
  KVM: PPC: Book3S HV: Simplify locking around stolen time calculations
  arch: powerpc: kvm: book3s_paired_singles.c: Remove unused function
  arch: powerpc: kvm: book3s_pr.c: Remove unused function
  arch: powerpc: kvm: book3s.c: Remove some unused functions
  arch: powerpc: kvm: book3s_32_mmu.c: Remove unused function
  KVM: PPC: Book3S HV: Check wait conditions before sleeping in kvmppc_vcore_blocked
  KVM: PPC: Book3S HV: ptes are big endian
  KVM: PPC: Book3S HV: Fix inaccuracies in ICP emulation for H_IPI
  KVM: PPC: Book3S HV: Fix KSM memory corruption
  KVM: PPC: Book3S HV: Fix an issue where guest is paused on receiving HMI
  KVM: PPC: Book3S HV: Fix computation of tlbie operand
  KVM: PPC: Book3S HV: Add missing HPTE unlock
  KVM: PPC: BookE: Improve irq inject tracepoint
  arm/arm64: KVM: Require in-kernel vgic for the arch timers
  ...

5 files changed, 186 insertions, 43 deletions

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9e193c8..2d6d910 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -213,6 +213,11 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	int err;
 	struct kvm_vcpu *vcpu;
 
+	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) {
+		err = -EBUSY;
+		goto out;
+	}
+
 	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
 	if (!vcpu) {
 		err = -ENOMEM;
@@ -263,6 +268,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	/* Force users to call KVM_ARM_VCPU_INIT */
 	vcpu->arch.target = -1;
+	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
 
 	/* Set up the timer */
 	kvm_timer_vcpu_init(vcpu);
@@ -419,6 +425,7 @@ static void update_vttbr(struct kvm *kvm)
 
 static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
 	int ret;
 
 	if (likely(vcpu->arch.has_run_once))
@@ -427,15 +434,23 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.has_run_once = true;
 
 	/*
-	 * Initialize the VGIC before running a vcpu the first time on
-	 * this VM.
+	 * Map the VGIC hardware resources before running a vcpu the first
+	 * time on this VM.
 	 */
-	if (unlikely(!vgic_initialized(vcpu->kvm))) {
-		ret = kvm_vgic_init(vcpu->kvm);
+	if (unlikely(!vgic_ready(kvm))) {
+		ret = kvm_vgic_map_resources(kvm);
 		if (ret)
 			return ret;
 	}
 
+	/*
+	 * Enable the arch timers only if we have an in-kernel VGIC
+	 * and it has been properly initialized, since we cannot handle
+	 * interrupts from the virtual timer with a userspace gic.
+	 */
+	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
+		kvm_timer_enable(kvm);
+
 	return 0;
 }
 
@@ -649,6 +664,48 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 	return -EINVAL;
 }
 
+static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
+			       const struct kvm_vcpu_init *init)
+{
+	unsigned int i;
+	int phys_target = kvm_target_cpu();
+
+	if (init->target != phys_target)
+		return -EINVAL;
+
+	/*
+	 * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must
+	 * use the same target.
+	 */
+	if (vcpu->arch.target != -1 && vcpu->arch.target != init->target)
+		return -EINVAL;
+
+	/* -ENOENT for unknown features, -EINVAL for invalid combinations. */
+	for (i = 0; i < sizeof(init->features) * 8; i++) {
+		bool set = (init->features[i / 32] & (1 << (i % 32)));
+
+		if (set && i >= KVM_VCPU_MAX_FEATURES)
+			return -ENOENT;
+
+		/*
+		 * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must
+		 * use the same feature set.
+		 */
+		if (vcpu->arch.target != -1 && i < KVM_VCPU_MAX_FEATURES &&
+		    test_bit(i, vcpu->arch.features) != set)
+			return -EINVAL;
+
+		if (set)
+			set_bit(i, vcpu->arch.features);
+	}
+
+	vcpu->arch.target = phys_target;
+
+	/* Now we know what it is, we can reset it. */
+	return kvm_reset_vcpu(vcpu);
+}
+
+
 static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 					 struct kvm_vcpu_init *init)
 {
@@ -659,10 +716,21 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 		return ret;
 
 	/*
+	 * Ensure a rebooted VM will fault in RAM pages and detect if the
+	 * guest MMU is turned off and flush the caches as needed.
+	 */
+	if (vcpu->arch.has_run_once)
+		stage2_unmap_vm(vcpu->kvm);
+
+	vcpu_reset_hcr(vcpu);
+
+	/*
 	 * Handle the "start in power-off" case by marking the VCPU as paused.
 	 */
-	if (__test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
+	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
 		vcpu->arch.pause = true;
+	else
+		vcpu->arch.pause = false;
 
 	return 0;
 }
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index cc0b787..384bab6 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.hcr = HCR_GUEST_MASK;
 	return 0;
 }
 
@@ -274,31 +273,6 @@ int __attribute_const__ kvm_target_cpu(void)
 	}
 }
 
-int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
-			const struct kvm_vcpu_init *init)
-{
-	unsigned int i;
-
-	/* We can only cope with guest==host and only on A15/A7 (for now). */
-	if (init->target != kvm_target_cpu())
-		return -EINVAL;
-
-	vcpu->arch.target = init->target;
-	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
-
-	/* -ENOENT for unknown features, -EINVAL for invalid combinations. */
-	for (i = 0; i < sizeof(init->features) * 8; i++) {
-		if (test_bit(i, (void *)init->features)) {
-			if (i >= KVM_VCPU_MAX_FEATURES)
-				return -ENOENT;
-			set_bit(i, vcpu->arch.features);
-		}
-	}
-
-	/* Now we know what it is, we can reset it. */
-	return kvm_reset_vcpu(vcpu);
-}
-
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
 {
 	int target = kvm_target_cpu();
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 4cb5a93..5d3bfc0 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -187,15 +187,18 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	}
 
 	rt = vcpu->arch.mmio_decode.rt;
-	data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), mmio.len);
 
-	trace_kvm_mmio((mmio.is_write) ? KVM_TRACE_MMIO_WRITE :
-					 KVM_TRACE_MMIO_READ_UNSATISFIED,
-			mmio.len, fault_ipa,
-			(mmio.is_write) ? data : 0);
+	if (mmio.is_write) {
+		data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt),
+					       mmio.len);
 
-	if (mmio.is_write)
+		trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, mmio.len,
+			       fault_ipa, data);
 		mmio_write_buf(mmio.data, mmio.len, data);
+	} else {
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, mmio.len,
+			       fault_ipa, 0);
+	}
 
 	if (vgic_handle_mmio(vcpu, run, &mmio))
 		return 1;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 8664ff1..1dc9778 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -612,6 +612,71 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	unmap_range(kvm, kvm->arch.pgd, start, size);
 }
 
+static void stage2_unmap_memslot(struct kvm *kvm,
+				 struct kvm_memory_slot *memslot)
+{
+	hva_t hva = memslot->userspace_addr;
+	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = PAGE_SIZE * memslot->npages;
+	hva_t reg_end = hva + size;
+
+	/*
+	 * A memory region could potentially cover multiple VMAs, and any holes
+	 * between them, so iterate over all of them to find out if we should
+	 * unmap any of them.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Take the intersection of this VMA with the memory region
+		 */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (!(vma->vm_flags & VM_PFNMAP)) {
+			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
+			unmap_stage2_range(kvm, gpa, vm_end - vm_start);
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+}
+
+/**
+ * stage2_unmap_vm - Unmap Stage-2 RAM mappings
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the memregions and unmap any reguler RAM
+ * backing memory already mapped to the VM.
+ */
+void stage2_unmap_vm(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots)
+		stage2_unmap_memslot(kvm, memslot);
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
 /**
  * kvm_free_stage2_pgd - free all stage-2 tables
  * @kvm:	The KVM struct pointer for the VM.
@@ -853,6 +918,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct vm_area_struct *vma;
 	pfn_t pfn;
 	pgprot_t mem_type = PAGE_S2;
+	bool fault_ipa_uncached;
 
 	write_fault = kvm_is_write_fault(vcpu);
 	if (fault_status == FSC_PERM && !write_fault) {
@@ -919,6 +985,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (!hugetlb && !force_pte)
 		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
 
+	fault_ipa_uncached = memslot->flags & KVM_MEMSLOT_INCOHERENT;
+
 	if (hugetlb) {
 		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
 		new_pmd = pmd_mkhuge(new_pmd);
@@ -926,7 +994,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			kvm_set_s2pmd_writable(&new_pmd);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE);
+		coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE,
+					  fault_ipa_uncached);
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
 		pte_t new_pte = pfn_pte(pfn, mem_type);
@@ -934,7 +1003,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			kvm_set_s2pte_writable(&new_pte);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
+		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE,
+					  fault_ipa_uncached);
 		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
 			pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
 	}
@@ -1294,11 +1364,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		hva = vm_end;
 	} while (hva < reg_end);
 
-	if (ret) {
-		spin_lock(&kvm->mmu_lock);
+	spin_lock(&kvm->mmu_lock);
+	if (ret)
 		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
-		spin_unlock(&kvm->mmu_lock);
-	}
+	else
+		stage2_flush_memslot(kvm, memslot);
+	spin_unlock(&kvm->mmu_lock);
 	return ret;
 }
 
@@ -1310,6 +1381,15 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			    unsigned long npages)
 {
+	/*
+	 * Readonly memslots are not incoherent with the caches by definition,
+	 * but in practice, they are used mostly to emulate ROMs or NOR flashes
+	 * that the guest may consider devices and hence map as uncached.
+	 * To prevent incoherency issues in these cases, tag all readonly
+	 * regions as incoherent.
+	 */
+	if (slot->flags & KVM_MEM_READONLY)
+		slot->flags |= KVM_MEMSLOT_INCOHERENT;
 	return 0;
 }
 
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 09cf377..58cb324 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -15,6 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/preempt.h>
 #include <linux/kvm_host.h>
 #include <linux/wait.h>
 
@@ -166,6 +167,23 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 
 static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
 {
+	int i;
+	struct kvm_vcpu *tmp;
+
+	/*
+	 * The KVM ABI specifies that a system event exit may call KVM_RUN
+	 * again and may perform shutdown/reboot at a later time that when the
+	 * actual request is made.  Since we are implementing PSCI and a
+	 * caller of PSCI reboot and shutdown expects that the system shuts
+	 * down or reboots immediately, let's make sure that VCPUs are not run
+	 * after this call is handled and before the VCPUs have been
+	 * re-initialized.
+	 */
+	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
+		tmp->arch.pause = true;
+		kvm_vcpu_kick(tmp);
+	}
+
 	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
 	vcpu->run->system_event.type = type;
 	vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;