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

Pull KVM fixes from Paolo Bonzini:
 "Fixes for PPC and s390"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: PPC: Book3S HV: Restore SPRG3 in kvmhv_p9_guest_entry()
  KVM: PPC: Book3S HV: Fix lockdep warning when entering guest on POWER9
  KVM: PPC: Book3S HV: XIVE: Fix page offset when clearing ESB pages
  KVM: PPC: Book3S HV: XIVE: Take the srcu read lock when accessing memslots
  KVM: PPC: Book3S HV: XIVE: Do not clear IRQ data of passthrough interrupts
  KVM: PPC: Book3S HV: XIVE: Introduce a new mutex for the XIVE device
  KVM: PPC: Book3S HV: XIVE: Fix the enforced limit on the vCPU identifier
  KVM: PPC: Book3S HV: XIVE: Do not test the EQ flag validity when resetting
  KVM: PPC: Book3S HV: XIVE: Clear file mapping when device is released
  KVM: PPC: Book3S HV: Don't take kvm->lock around kvm_for_each_vcpu
  KVM: PPC: Book3S: Use new mutex to synchronize access to rtas token list
  KVM: PPC: Book3S HV: Use new mutex to synchronize MMU setup
  KVM: PPC: Book3S HV: Avoid touching arch.mmu_ready in XIVE release functions
  KVM: s390: Do not report unusabled IDs via KVM_CAP_MAX_VCPU_ID
  kvm: fix compile on s390 part 2

Author: torvalds

arch/mips/kvm/mips.c

@@ -1122,6 +1122,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
+	case KVM_CAP_MAX_VCPU_ID:
+		r = KVM_MAX_VCPU_ID;
+		break;
 	case KVM_CAP_MIPS_FPU:
 		/* We don't handle systems with inconsistent cpu_has_fpu */
 		r = !!raw_cpu_has_fpu;

arch/powerpc/include/asm/kvm_host.h

@@ -309,6 +309,7 @@ struct kvm_arch {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct list_head spapr_tce_tables;
 	struct list_head rtas_tokens;
+	struct mutex rtas_token_lock;
 	DECLARE_BITMAP(enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
 #endif
 #ifdef CONFIG_KVM_MPIC
@@ -325,6 +326,7 @@ struct kvm_arch {
 #endif
 	struct kvmppc_ops *kvm_ops;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	struct mutex mmu_setup_lock;	/* nests inside vcpu mutexes */
 	u64 l1_ptcr;
 	int max_nested_lpid;
 	struct kvm_nested_guest *nested_guests[KVM_MAX_NESTED_GUESTS];

arch/powerpc/kvm/book3s.c

@@ -902,6 +902,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 #ifdef CONFIG_PPC64
 	INIT_LIST_HEAD_RCU(&kvm->arch.spapr_tce_tables);
 	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
+	mutex_init(&kvm->arch.rtas_token_lock);
 #endif
 
 	return kvm->arch.kvm_ops->init_vm(kvm);

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -63,7 +63,7 @@ struct kvm_resize_hpt {
 	struct work_struct work;
 	u32 order;
 
-	/* These fields protected by kvm->lock */
+	/* These fields protected by kvm->arch.mmu_setup_lock */
 
 	/* Possible values and their usage:
 	 *  <0     an error occurred during allocation,
@@ -73,7 +73,7 @@ struct kvm_resize_hpt {
 	int error;
 
 	/* Private to the work thread, until error != -EBUSY,
-	 * then protected by kvm->lock.
+	 * then protected by kvm->arch.mmu_setup_lock.
 	 */
 	struct kvm_hpt_info hpt;
 };
@@ -139,7 +139,7 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
 	long err = -EBUSY;
 	struct kvm_hpt_info info;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 	if (kvm->arch.mmu_ready) {
 		kvm->arch.mmu_ready = 0;
 		/* order mmu_ready vs. vcpus_running */
@@ -183,7 +183,7 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
 		/* Ensure that each vcpu will flush its TLB on next entry. */
 		cpumask_setall(&kvm->arch.need_tlb_flush);
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return err;
 }
 
@@ -1447,7 +1447,7 @@ static void resize_hpt_pivot(struct kvm_resize_hpt *resize)
 
 static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize)
 {
-	if (WARN_ON(!mutex_is_locked(&kvm->lock)))
+	if (WARN_ON(!mutex_is_locked(&kvm->arch.mmu_setup_lock)))
 		return;
 
 	if (!resize)
@@ -1474,14 +1474,14 @@ static void resize_hpt_prepare_work(struct work_struct *work)
 	if (WARN_ON(resize->error != -EBUSY))
 		return;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 
 	/* Request is still current? */
 	if (kvm->arch.resize_hpt == resize) {
 		/* We may request large allocations here:
-		 * do not sleep with kvm->lock held for a while.
+		 * do not sleep with kvm->arch.mmu_setup_lock held for a while.
 		 */
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.mmu_setup_lock);
 
 		resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n",
 				 resize->order);
@@ -1494,9 +1494,9 @@ static void resize_hpt_prepare_work(struct work_struct *work)
 		if (WARN_ON(err == -EBUSY))
 			err = -EINPROGRESS;
 
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.mmu_setup_lock);
 		/* It is possible that kvm->arch.resize_hpt != resize
-		 * after we grab kvm->lock again.
+		 * after we grab kvm->arch.mmu_setup_lock again.
 		 */
 	}
 
@@ -1505,7 +1505,7 @@ static void resize_hpt_prepare_work(struct work_struct *work)
 	if (kvm->arch.resize_hpt != resize)
 		resize_hpt_release(kvm, resize);
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 }
 
 long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
@@ -1522,7 +1522,7 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
 	if (shift && ((shift < 18) || (shift > 46)))
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 
 	resize = kvm->arch.resize_hpt;
 
@@ -1565,7 +1565,7 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
 	ret = 100; /* estimated time in ms */
 
 out:
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return ret;
 }
 
@@ -1588,7 +1588,7 @@ long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm,
 	if (shift && ((shift < 18) || (shift > 46)))
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 
 	resize = kvm->arch.resize_hpt;
 
@@ -1625,7 +1625,7 @@ long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm,
 	smp_mb();
 out_no_hpt:
 	resize_hpt_release(kvm, resize);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return ret;
 }
 
@@ -1868,15 +1868,15 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 		return -EINVAL;
 
 	/* lock out vcpus from running while we're doing this */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 	mmu_ready = kvm->arch.mmu_ready;
 	if (mmu_ready) {
 		kvm->arch.mmu_ready = 0;	/* temporarily */
 		/* order mmu_ready vs. vcpus_running */
 		smp_mb();
 		if (atomic_read(&kvm->arch.vcpus_running)) {
 			kvm->arch.mmu_ready = 1;
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->arch.mmu_setup_lock);
 			return -EBUSY;
 		}
 	}
@@ -1963,7 +1963,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 	/* Order HPTE updates vs. mmu_ready */
 	smp_wmb();
 	kvm->arch.mmu_ready = mmu_ready;
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 
 	if (err)
 		return err;

arch/powerpc/kvm/book3s_hv.c

@@ -446,12 +446,7 @@ static void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 
 static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
 {
-	struct kvm_vcpu *ret;
-
-	mutex_lock(&kvm->lock);
-	ret = kvm_get_vcpu_by_id(kvm, id);
-	mutex_unlock(&kvm->lock);
-	return ret;
+	return kvm_get_vcpu_by_id(kvm, id);
 }
 
 static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
@@ -1583,7 +1578,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	u64 mask;
 
-	mutex_lock(&kvm->lock);
 	spin_lock(&vc->lock);
 	/*
 	 * If ILE (interrupt little-endian) has changed, update the
@@ -1623,7 +1617,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
 		mask &= 0xFFFFFFFF;
 	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
 	spin_unlock(&vc->lock);
-	mutex_unlock(&kvm->lock);
 }
 
 static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
@@ -2338,11 +2331,17 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 			pr_devel("KVM: collision on id %u", id);
 			vcore = NULL;
 		} else if (!vcore) {
+			/*
+			 * Take mmu_setup_lock for mutual exclusion
+			 * with kvmppc_update_lpcr().
+			 */
 			err = -ENOMEM;
 			vcore = kvmppc_vcore_create(kvm,
 					id & ~(kvm->arch.smt_mode - 1));
+			mutex_lock(&kvm->arch.mmu_setup_lock);
 			kvm->arch.vcores[core] = vcore;
 			kvm->arch.online_vcores++;
+			mutex_unlock(&kvm->arch.mmu_setup_lock);
 		}
 	}
 	mutex_unlock(&kvm->lock);
@@ -3663,6 +3662,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	vc->in_guest = 0;
 
 	mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - mftb());
+	mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
 
 	kvmhv_load_host_pmu();
 
@@ -3859,7 +3859,7 @@ static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu)
 	int r = 0;
 	struct kvm *kvm = vcpu->kvm;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 	if (!kvm->arch.mmu_ready) {
 		if (!kvm_is_radix(kvm))
 			r = kvmppc_hv_setup_htab_rma(vcpu);
@@ -3869,7 +3869,7 @@ static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu)
 			kvm->arch.mmu_ready = 1;
 		}
 	}
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return r;
 }
 
@@ -4091,16 +4091,20 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
 		kvmppc_check_need_tlb_flush(kvm, pcpu, nested);
 	}
 
-	trace_hardirqs_on();
 	guest_enter_irqoff();
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 
 	this_cpu_disable_ftrace();
 
+	/* Tell lockdep that we're about to enable interrupts */
+	trace_hardirqs_on();
+
 	trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr);
 	vcpu->arch.trap = trap;
 
+	trace_hardirqs_off();
+
 	this_cpu_enable_ftrace();
 
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
@@ -4110,7 +4114,6 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
 		isync();
 	}
 
-	trace_hardirqs_off();
 	set_irq_happened(trap);
 
 	kvmppc_set_host_core(pcpu);
@@ -4478,7 +4481,8 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 
 /*
  * Update LPCR values in kvm->arch and in vcores.
- * Caller must hold kvm->lock.
+ * Caller must hold kvm->arch.mmu_setup_lock (for mutual exclusion
+ * of kvm->arch.lpcr update).
  */
 void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
 {
@@ -4530,7 +4534,7 @@ void kvmppc_setup_partition_table(struct kvm *kvm)
 
 /*
  * Set up HPT (hashed page table) and RMA (real-mode area).
- * Must be called with kvm->lock held.
+ * Must be called with kvm->arch.mmu_setup_lock held.
  */
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
@@ -4618,7 +4622,10 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	goto out_srcu;
 }
 
-/* Must be called with kvm->lock held and mmu_ready = 0 and no vcpus running */
+/*
+ * Must be called with kvm->arch.mmu_setup_lock held and
+ * mmu_ready = 0 and no vcpus running.
+ */
 int kvmppc_switch_mmu_to_hpt(struct kvm *kvm)
 {
 	if (nesting_enabled(kvm))
@@ -4635,7 +4642,10 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm)
 	return 0;
 }
 
-/* Must be called with kvm->lock held and mmu_ready = 0 and no vcpus running */
+/*
+ * Must be called with kvm->arch.mmu_setup_lock held and
+ * mmu_ready = 0 and no vcpus running.
+ */
 int kvmppc_switch_mmu_to_radix(struct kvm *kvm)
 {
 	int err;
@@ -4740,6 +4750,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 	char buf[32];
 	int ret;
 
+	mutex_init(&kvm->arch.mmu_setup_lock);
+
 	/* Allocate the guest's logical partition ID */
 
 	lpid = kvmppc_alloc_lpid();
@@ -5265,7 +5277,7 @@ static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg)
 	if (kvmhv_on_pseries() && !radix)
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 	if (radix != kvm_is_radix(kvm)) {
 		if (kvm->arch.mmu_ready) {
 			kvm->arch.mmu_ready = 0;
@@ -5293,7 +5305,7 @@ static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg)
 	err = 0;
 
  out_unlock:
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return err;
 }