From f257d6dcda0187693407e0c2e5dab69bdab3223f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Fri, 19 Apr 2019 22:18:17 -0700
Subject: KVM: Directly return result from kvm_arch_check_processor_compat()

Add a wrapper to invoke kvm_arch_check_processor_compat() so that the
boilerplate ugliness of checking virtualization support on all CPUs is
hidden from the arch specific code.  x86's implementation in particular
is quite heinous, as it unnecessarily propagates the out-param pattern
into kvm_x86_ops.

While the x86 specific issue could be resolved solely by changing
kvm_x86_ops, make the change for all architectures as returning a value
directly is prettier and technically more robust, e.g. s390 doesn't set
the out param, which could lead to subtle breakage in the (highly
unlikely) scenario where the out-param was not pre-initialized by the
caller.

Opportunistically annotate svm_check_processor_compat() with __init.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 79fa4426509c..5e9fd7ad8018 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -870,7 +870,7 @@ int kvm_arch_hardware_enable(void);
 void kvm_arch_hardware_disable(void);
 int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
-void kvm_arch_check_processor_compat(void *rtn);
+int kvm_arch_check_processor_compat(void);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
-- 
cgit v1.2.3


From b51700632e0e53254733ff706e5bdca22d19dbe5 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpengli@tencent.com>
Date: Tue, 21 May 2019 14:06:53 +0800
Subject: KVM: X86: Provide a capability to disable cstate msr read intercepts
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allow guest reads CORE cstate when exposing host CPU power management capabilities
to the guest. PKG cstate is restricted to avoid a guest to get the whole package
information in multi-tenant scenario.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 1 +
 arch/x86/include/asm/kvm_host.h   | 1 +
 arch/x86/kvm/vmx/vmx.c            | 6 ++++++
 arch/x86/kvm/x86.c                | 5 ++++-
 arch/x86/kvm/x86.h                | 5 +++++
 include/uapi/linux/kvm.h          | 4 +++-
 tools/include/uapi/linux/kvm.h    | 4 +++-
 7 files changed, 23 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 33cd92dd6aa5..91fd86fcc49f 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4894,6 +4894,7 @@ Valid bits in args[0] are
 #define KVM_X86_DISABLE_EXITS_MWAIT            (1 << 0)
 #define KVM_X86_DISABLE_EXITS_HLT              (1 << 1)
 #define KVM_X86_DISABLE_EXITS_PAUSE            (1 << 2)
+#define KVM_X86_DISABLE_EXITS_CSTATE           (1 << 3)
 
 Enabling this capability on a VM provides userspace with a way to no
 longer intercept some instructions for improved latency in some
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 15e973d9b840..aeadbc770eb2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -882,6 +882,7 @@ struct kvm_arch {
 	bool mwait_in_guest;
 	bool hlt_in_guest;
 	bool pause_in_guest;
+	bool cstate_in_guest;
 
 	unsigned long irq_sources_bitmap;
 	s64 kvmclock_offset;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 0861c71a4379..da24f1858acc 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6637,6 +6637,12 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
 	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
 	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+	if (kvm_cstate_in_guest(kvm)) {
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
+	}
 	vmx->msr_bitmap_mode = 0;
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8aa6b5a75e7a..17e9533f51eb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3098,7 +3098,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_CLOCK_TSC_STABLE;
 		break;
 	case KVM_CAP_X86_DISABLE_EXITS:
-		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE;
+		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE |
+		      KVM_X86_DISABLE_EXITS_CSTATE;
 		if(kvm_can_mwait_in_guest())
 			r |= KVM_X86_DISABLE_EXITS_MWAIT;
 		break;
@@ -4615,6 +4616,8 @@ split_irqchip_unlock:
 			kvm->arch.hlt_in_guest = true;
 		if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
 			kvm->arch.pause_in_guest = true;
+		if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE)
+			kvm->arch.cstate_in_guest = true;
 		r = 0;
 		break;
 	case KVM_CAP_MSR_PLATFORM_INFO:
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index a470ff0868c5..275b3b646023 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -333,6 +333,11 @@ static inline bool kvm_pause_in_guest(struct kvm *kvm)
 	return kvm->arch.pause_in_guest;
 }
 
+static inline bool kvm_cstate_in_guest(struct kvm *kvm)
+{
+	return kvm->arch.cstate_in_guest;
+}
+
 DECLARE_PER_CPU(struct kvm_vcpu *, current_vcpu);
 
 static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 2fe12b40d503..c2152f3dd02d 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -696,9 +696,11 @@ struct kvm_ioeventfd {
 #define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
 #define KVM_X86_DISABLE_EXITS_HLT            (1 << 1)
 #define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
+#define KVM_X86_DISABLE_EXITS_CSTATE         (1 << 3)
 #define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
                                               KVM_X86_DISABLE_EXITS_HLT | \
-                                              KVM_X86_DISABLE_EXITS_PAUSE)
+                                              KVM_X86_DISABLE_EXITS_PAUSE | \
+                                              KVM_X86_DISABLE_EXITS_CSTATE)
 
 /* for KVM_ENABLE_CAP */
 struct kvm_enable_cap {
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 6d4ea4b6c922..ef3303f72c46 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -696,9 +696,11 @@ struct kvm_ioeventfd {
 #define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
 #define KVM_X86_DISABLE_EXITS_HLT            (1 << 1)
 #define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
+#define KVM_X86_DISABLE_EXITS_CSTATE         (1 << 3)
 #define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
                                               KVM_X86_DISABLE_EXITS_HLT | \
-                                              KVM_X86_DISABLE_EXITS_PAUSE)
+                                              KVM_X86_DISABLE_EXITS_PAUSE | \
+                                              KVM_X86_DISABLE_EXITS_CSTATE)
 
 /* for KVM_ENABLE_CAP */
 struct kvm_enable_cap {
-- 
cgit v1.2.3


From 0d9ce162cf46c99628cc5da9510b959c7976735b Mon Sep 17 00:00:00 2001
From: Junaid Shahid <junaids@google.com>
Date: Thu, 3 Jan 2019 17:14:28 -0800
Subject: kvm: Convert kvm_lock to a mutex

It doesn't seem as if there is any particular need for kvm_lock to be a
spinlock, so convert the lock to a mutex so that sleepable functions (in
particular cond_resched()) can be called while holding it.

Signed-off-by: Junaid Shahid <junaids@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/locking.txt |  4 +---
 arch/s390/kvm/kvm-s390.c              |  4 ++--
 arch/x86/kvm/mmu.c                    |  4 ++--
 arch/x86/kvm/x86.c                    | 14 +++++++-------
 include/linux/kvm_host.h              |  2 +-
 virt/kvm/kvm_main.c                   | 30 +++++++++++++++---------------
 6 files changed, 28 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index 1bb8bcaf8497..635cd6eaf714 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -15,8 +15,6 @@ The acquisition orders for mutexes are as follows:
 
 On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock.
 
-For spinlocks, kvm_lock is taken outside kvm->mmu_lock.
-
 Everything else is a leaf: no other lock is taken inside the critical
 sections.
 
@@ -169,7 +167,7 @@ which time it will be set using the Dirty tracking mechanism described above.
 ------------
 
 Name:		kvm_lock
-Type:		spinlock_t
+Type:		mutex
 Arch:		any
 Protects:	- vm_list
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 7936af0a971f..0fef9192f6ac 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2423,13 +2423,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.sca = (struct bsca_block *) get_zeroed_page(alloc_flags);
 	if (!kvm->arch.sca)
 		goto out_err;
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	sca_offset += 16;
 	if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
 		sca_offset = 0;
 	kvm->arch.sca = (struct bsca_block *)
 			((char *) kvm->arch.sca + sca_offset);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	sprintf(debug_name, "kvm-%u", current->pid);
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 95ac393e2959..3384c539d150 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -5956,7 +5956,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	int nr_to_scan = sc->nr_to_scan;
 	unsigned long freed = 0;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		int idx;
@@ -5998,7 +5998,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		break;
 	}
 
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 	return freed;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 10feed6a01eb..6200d5a51f13 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6719,7 +6719,7 @@ static void kvm_hyperv_tsc_notifier(void)
 	struct kvm_vcpu *vcpu;
 	int cpu;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_make_mclock_inprogress_request(kvm);
 
@@ -6745,7 +6745,7 @@ static void kvm_hyperv_tsc_notifier(void)
 
 		spin_unlock(&ka->pvclock_gtod_sync_lock);
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 }
 #endif
 
@@ -6796,17 +6796,17 @@ static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu)
 
 	smp_call_function_single(cpu, tsc_khz_changed, freq, 1);
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->cpu != cpu)
 				continue;
 			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
-			if (vcpu->cpu != smp_processor_id())
+			if (vcpu->cpu != raw_smp_processor_id())
 				send_ipi = 1;
 		}
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	if (freq->old < freq->new && send_ipi) {
 		/*
@@ -6929,12 +6929,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 	atomic_set(&kvm_guest_has_master_clock, 0);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 }
 
 static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 5e9fd7ad8018..abafddb9fe2c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -162,7 +162,7 @@ static inline bool is_error_page(struct page *page)
 
 extern struct kmem_cache *kvm_vcpu_cache;
 
-extern spinlock_t kvm_lock;
+extern struct mutex kvm_lock;
 extern struct list_head vm_list;
 
 struct kvm_io_range {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index b2579841263f..9613987ef4c8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -98,7 +98,7 @@ EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
  *	kvm->lock --> kvm->slots_lock --> kvm->irq_lock
  */
 
-DEFINE_SPINLOCK(kvm_lock);
+DEFINE_MUTEX(kvm_lock);
 static DEFINE_RAW_SPINLOCK(kvm_count_lock);
 LIST_HEAD(vm_list);
 
@@ -683,9 +683,9 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	if (r)
 		goto out_err;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	preempt_notifier_inc();
 
@@ -731,9 +731,9 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
 	kvm_destroy_vm_debugfs(kvm);
 	kvm_arch_sync_events(kvm);
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		struct kvm_io_bus *bus = kvm_get_bus(kvm, i);
@@ -4034,13 +4034,13 @@ static int vm_stat_get(void *_offset, u64 *val)
 	u64 tmp_val;
 
 	*val = 0;
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vm_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
 		*val += tmp_val;
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 	return 0;
 }
 
@@ -4053,12 +4053,12 @@ static int vm_stat_clear(void *_offset, u64 val)
 	if (val)
 		return -EINVAL;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vm_stat_clear_per_vm((void *)&stat_tmp, 0);
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	return 0;
 }
@@ -4073,13 +4073,13 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 	u64 tmp_val;
 
 	*val = 0;
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vcpu_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
 		*val += tmp_val;
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 	return 0;
 }
 
@@ -4092,12 +4092,12 @@ static int vcpu_stat_clear(void *_offset, u64 val)
 	if (val)
 		return -EINVAL;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		stat_tmp.kvm = kvm;
 		vcpu_stat_clear_per_vm((void *)&stat_tmp, 0);
 	}
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	return 0;
 }
@@ -4118,7 +4118,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	if (!kvm_dev.this_device || !kvm)
 		return;
 
-	spin_lock(&kvm_lock);
+	mutex_lock(&kvm_lock);
 	if (type == KVM_EVENT_CREATE_VM) {
 		kvm_createvm_count++;
 		kvm_active_vms++;
@@ -4127,7 +4127,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	}
 	created = kvm_createvm_count;
 	active = kvm_active_vms;
-	spin_unlock(&kvm_lock);
+	mutex_unlock(&kvm_lock);
 
 	env = kzalloc(sizeof(*env), GFP_KERNEL_ACCOUNT);
 	if (!env)
-- 
cgit v1.2.3


From f85f6e7bc9682a6d8b342c010cd6aa58521fdeec Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpengli@tencent.com>
Date: Tue, 11 Jun 2019 20:23:48 +0800
Subject: KVM: X86: Yield to IPI target if necessary
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When sending a call-function IPI-many to vCPUs, yield if any of
the IPI target vCPUs was preempted, we just select the first
preempted target vCPU which we found since the state of target
vCPUs can change underneath and to avoid race conditions.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/hypercalls.txt | 11 +++++++++++
 arch/x86/include/uapi/asm/kvm_para.h     |  1 +
 arch/x86/kernel/kvm.c                    | 21 +++++++++++++++++++++
 include/uapi/linux/kvm_para.h            |  1 +
 4 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/hypercalls.txt b/Documentation/virtual/kvm/hypercalls.txt
index da24c138c8d1..da210651f714 100644
--- a/Documentation/virtual/kvm/hypercalls.txt
+++ b/Documentation/virtual/kvm/hypercalls.txt
@@ -141,3 +141,14 @@ a0 corresponds to the APIC ID in the third argument (a2), bit 1
 corresponds to the APIC ID a2+1, and so on.
 
 Returns the number of CPUs to which the IPIs were delivered successfully.
+
+7. KVM_HC_SCHED_YIELD
+------------------------
+Architecture: x86
+Status: active
+Purpose: Hypercall used to yield if the IPI target vCPU is preempted
+
+a0: destination APIC ID
+
+Usage example: When sending a call-function IPI-many to vCPUs, yield if
+any of the IPI target vCPUs was preempted.
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 21d5f0240595..2a8e0b6b9805 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -30,6 +30,7 @@
 #define KVM_FEATURE_ASYNC_PF_VMEXIT	10
 #define KVM_FEATURE_PV_SEND_IPI	11
 #define KVM_FEATURE_POLL_CONTROL	12
+#define KVM_FEATURE_PV_SCHED_YIELD	13
 
 #define KVM_HINTS_REALTIME      0
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5169b8cc35bb..82caf01b63dd 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -527,6 +527,21 @@ static void kvm_setup_pv_ipi(void)
 	pr_info("KVM setup pv IPIs\n");
 }
 
+static void kvm_smp_send_call_func_ipi(const struct cpumask *mask)
+{
+	int cpu;
+
+	native_send_call_func_ipi(mask);
+
+	/* Make sure other vCPUs get a chance to run if they need to. */
+	for_each_cpu(cpu, mask) {
+		if (vcpu_is_preempted(cpu)) {
+			kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu));
+			break;
+		}
+	}
+}
+
 static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
 {
 	native_smp_prepare_cpus(max_cpus);
@@ -638,6 +653,12 @@ static void __init kvm_guest_init(void)
 #ifdef CONFIG_SMP
 	smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
+	if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
+	    !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
+	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+		smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi;
+		pr_info("KVM setup pv sched yield\n");
+	}
 	if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
 				      kvm_cpu_online, kvm_cpu_down_prepare) < 0)
 		pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n");
diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h
index 6c0ce49931e5..8b86609849b9 100644
--- a/include/uapi/linux/kvm_para.h
+++ b/include/uapi/linux/kvm_para.h
@@ -28,6 +28,7 @@
 #define KVM_HC_MIPS_CONSOLE_OUTPUT	8
 #define KVM_HC_CLOCK_PAIRING		9
 #define KVM_HC_SEND_IPI		10
+#define KVM_HC_SCHED_YIELD		11
 
 /*
  * hypercalls use architecture specific
-- 
cgit v1.2.3


From 418e5ca88cc18b7e9eaafa40eac26397ccd66a71 Mon Sep 17 00:00:00 2001
From: Andrew Murray <andrew.murray@arm.com>
Date: Mon, 17 Jun 2019 20:01:01 +0100
Subject: KVM: arm/arm64: Rename kvm_pmu_{enable/disable}_counter functions

The kvm_pmu_{enable/disable}_counter functions can enable/disable
multiple counters at once as they operate on a bitmask. Let's
make this clearer by renaming the function.

Suggested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Julien Thierry <julien.thierry@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm64/kvm/sys_regs.c |  4 ++--
 include/kvm/arm_pmu.h     |  8 ++++----
 virt/kvm/arm/pmu.c        | 12 ++++++------
 3 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index ce933f296049..0a7665c189ff 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -865,12 +865,12 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		if (r->Op2 & 0x1) {
 			/* accessing PMCNTENSET_EL0 */
 			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
-			kvm_pmu_enable_counter(vcpu, val);
+			kvm_pmu_enable_counter_mask(vcpu, val);
 			kvm_vcpu_pmu_restore_guest(vcpu);
 		} else {
 			/* accessing PMCNTENCLR_EL0 */
 			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
-			kvm_pmu_disable_counter(vcpu, val);
+			kvm_pmu_disable_counter_mask(vcpu, val);
 		}
 	} else {
 		p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask;
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 84a9db156be7..45e5205750b4 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -35,8 +35,8 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu);
 void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu);
-void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val);
-void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu);
 bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu);
@@ -72,8 +72,8 @@ static inline u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 }
 static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {}
-static inline void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val) {}
-static inline void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {}
 static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index da740764a7ee..99e51ee8fd9e 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -124,13 +124,13 @@ u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 }
 
 /**
- * kvm_pmu_enable_counter - enable selected PMU counter
+ * kvm_pmu_enable_counter_mask - enable selected PMU counters
  * @vcpu: The vcpu pointer
  * @val: the value guest writes to PMCNTENSET register
  *
  * Call perf_event_enable to start counting the perf event
  */
-void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val)
+void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
@@ -153,13 +153,13 @@ void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val)
 }
 
 /**
- * kvm_pmu_disable_counter - disable selected PMU counter
+ * kvm_pmu_disable_counter_mask - disable selected PMU counters
  * @vcpu: The vcpu pointer
  * @val: the value guest writes to PMCNTENCLR register
  *
  * Call perf_event_disable to stop counting the perf event
  */
-void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val)
+void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
@@ -336,10 +336,10 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 
 	mask = kvm_pmu_valid_counter_mask(vcpu);
 	if (val & ARMV8_PMU_PMCR_E) {
-		kvm_pmu_enable_counter(vcpu,
+		kvm_pmu_enable_counter_mask(vcpu,
 		       __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask);
 	} else {
-		kvm_pmu_disable_counter(vcpu, mask);
+		kvm_pmu_disable_counter_mask(vcpu, mask);
 	}
 
 	if (val & ARMV8_PMU_PMCR_C)
-- 
cgit v1.2.3


From 218907cbc2b82419c70180610163c987d4764b27 Mon Sep 17 00:00:00 2001
From: Andrew Murray <andrew.murray@arm.com>
Date: Mon, 17 Jun 2019 20:01:04 +0100
Subject: KVM: arm/arm64: Remove pmc->bitmask

We currently use pmc->bitmask to determine the width of the pmc - however
it's superfluous as the pmc index already describes if the pmc is a cycle
counter or event counter. The architecture clearly describes the widths of
these counters.

Let's remove the bitmask to simplify the code.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 include/kvm/arm_pmu.h |  1 -
 virt/kvm/arm/pmu.c    | 30 ++++++++++++++++++++----------
 2 files changed, 20 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 45e5205750b4..48a15d4b820e 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -17,7 +17,6 @@
 struct kvm_pmc {
 	u8 idx;	/* index into the pmu->pmc array */
 	struct perf_event *perf_event;
-	u64 bitmask;
 };
 
 struct kvm_pmu {
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index f77643f4274c..24c6cf869a16 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -14,6 +14,18 @@
 #include <kvm/arm_vgic.h>
 
 static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
+
+/**
+ * kvm_pmu_idx_is_64bit - determine if select_idx is a 64bit counter
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ */
+static bool kvm_pmu_idx_is_64bit(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	return (select_idx == ARMV8_PMU_CYCLE_IDX &&
+		__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_LC);
+}
+
 /**
  * kvm_pmu_get_counter_value - get PMU counter value
  * @vcpu: The vcpu pointer
@@ -36,7 +48,10 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 		counter += perf_event_read_value(pmc->perf_event, &enabled,
 						 &running);
 
-	return counter & pmc->bitmask;
+	if (!kvm_pmu_idx_is_64bit(vcpu, select_idx))
+		counter = lower_32_bits(counter);
+
+	return counter;
 }
 
 /**
@@ -102,7 +117,6 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
 	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
 		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
 		pmu->pmc[i].idx = i;
-		pmu->pmc[i].bitmask = 0xffffffffUL;
 	}
 }
 
@@ -337,8 +351,6 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
  */
 void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 {
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc;
 	u64 mask;
 	int i;
 
@@ -357,11 +369,6 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 		for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++)
 			kvm_pmu_set_counter_value(vcpu, i, 0);
 	}
-
-	if (val & ARMV8_PMU_PMCR_LC) {
-		pmc = &pmu->pmc[ARMV8_PMU_CYCLE_IDX];
-		pmc->bitmask = 0xffffffffffffffffUL;
-	}
 }
 
 static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
@@ -409,7 +416,10 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 
 	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
 	/* The initial sample period (overflow count) of an event. */
-	attr.sample_period = (-counter) & pmc->bitmask;
+	if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
+		attr.sample_period = (-counter) & GENMASK(63, 0);
+	else
+		attr.sample_period = (-counter) & GENMASK(31, 0);
 
 	event = perf_event_create_kernel_counter(&attr, -1, current,
 						 kvm_pmu_perf_overflow, pmc);
-- 
cgit v1.2.3


From 80f393a23be68e2f8a0f74258d6155438c200bbd Mon Sep 17 00:00:00 2001
From: Andrew Murray <andrew.murray@arm.com>
Date: Mon, 17 Jun 2019 20:01:05 +0100
Subject: KVM: arm/arm64: Support chained PMU counters

ARMv8 provides support for chained PMU counters, where an event type
of 0x001E is set for odd-numbered counters, the event counter will
increment by one for each overflow of the preceding even-numbered
counter. Let's emulate this in KVM by creating a 64 bit perf counter
when a user chains two emulated counters together.

For chained events we only support generating an overflow interrupt
on the high counter. We use the attributes of the low counter to
determine the attributes of the perf event.

Suggested-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Julien Thierry <julien.thierry@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 include/kvm/arm_pmu.h |   2 +
 virt/kvm/arm/pmu.c    | 252 ++++++++++++++++++++++++++++++++++++++++++--------
 2 files changed, 217 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 48a15d4b820e..16c769a7f979 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -11,6 +11,7 @@
 #include <asm/perf_event.h>
 
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
+#define ARMV8_PMU_MAX_COUNTER_PAIRS	((ARMV8_PMU_MAX_COUNTERS + 1) >> 1)
 
 #ifdef CONFIG_KVM_ARM_PMU
 
@@ -22,6 +23,7 @@ struct kvm_pmc {
 struct kvm_pmu {
 	int irq_num;
 	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
+	DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
 	bool ready;
 	bool created;
 	bool irq_level;
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 24c6cf869a16..3dd8238ed246 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -15,6 +15,8 @@
 
 static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
 
+#define PERF_ATTR_CFG1_KVM_PMU_CHAINED 0x1
+
 /**
  * kvm_pmu_idx_is_64bit - determine if select_idx is a 64bit counter
  * @vcpu: The vcpu pointer
@@ -26,29 +28,126 @@ static bool kvm_pmu_idx_is_64bit(struct kvm_vcpu *vcpu, u64 select_idx)
 		__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_LC);
 }
 
+static struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu;
+	struct kvm_vcpu_arch *vcpu_arch;
+
+	pmc -= pmc->idx;
+	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
+	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
+	return container_of(vcpu_arch, struct kvm_vcpu, arch);
+}
+
 /**
- * kvm_pmu_get_counter_value - get PMU counter value
+ * kvm_pmu_pmc_is_chained - determine if the pmc is chained
+ * @pmc: The PMU counter pointer
+ */
+static bool kvm_pmu_pmc_is_chained(struct kvm_pmc *pmc)
+{
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+
+	return test_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+}
+
+/**
+ * kvm_pmu_idx_is_high_counter - determine if select_idx is a high/low counter
+ * @select_idx: The counter index
+ */
+static bool kvm_pmu_idx_is_high_counter(u64 select_idx)
+{
+	return select_idx & 0x1;
+}
+
+/**
+ * kvm_pmu_get_canonical_pmc - obtain the canonical pmc
+ * @pmc: The PMU counter pointer
+ *
+ * When a pair of PMCs are chained together we use the low counter (canonical)
+ * to hold the underlying perf event.
+ */
+static struct kvm_pmc *kvm_pmu_get_canonical_pmc(struct kvm_pmc *pmc)
+{
+	if (kvm_pmu_pmc_is_chained(pmc) &&
+	    kvm_pmu_idx_is_high_counter(pmc->idx))
+		return pmc - 1;
+
+	return pmc;
+}
+
+/**
+ * kvm_pmu_idx_has_chain_evtype - determine if the event type is chain
  * @vcpu: The vcpu pointer
  * @select_idx: The counter index
  */
-u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
+static bool kvm_pmu_idx_has_chain_evtype(struct kvm_vcpu *vcpu, u64 select_idx)
 {
-	u64 counter, reg, enabled, running;
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+	u64 eventsel, reg;
 
-	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
-	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
-	counter = __vcpu_sys_reg(vcpu, reg);
+	select_idx |= 0x1;
+
+	if (select_idx == ARMV8_PMU_CYCLE_IDX)
+		return false;
+
+	reg = PMEVTYPER0_EL0 + select_idx;
+	eventsel = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_EVENT;
+
+	return eventsel == ARMV8_PMUV3_PERFCTR_CHAIN;
+}
+
+/**
+ * kvm_pmu_get_pair_counter_value - get PMU counter value
+ * @vcpu: The vcpu pointer
+ * @pmc: The PMU counter pointer
+ */
+static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu,
+					  struct kvm_pmc *pmc)
+{
+	u64 counter, counter_high, reg, enabled, running;
 
-	/* The real counter value is equal to the value of counter register plus
+	if (kvm_pmu_pmc_is_chained(pmc)) {
+		pmc = kvm_pmu_get_canonical_pmc(pmc);
+		reg = PMEVCNTR0_EL0 + pmc->idx;
+
+		counter = __vcpu_sys_reg(vcpu, reg);
+		counter_high = __vcpu_sys_reg(vcpu, reg + 1);
+
+		counter = lower_32_bits(counter) | (counter_high << 32);
+	} else {
+		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+		      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
+		counter = __vcpu_sys_reg(vcpu, reg);
+	}
+
+	/*
+	 * The real counter value is equal to the value of counter register plus
 	 * the value perf event counts.
 	 */
 	if (pmc->perf_event)
 		counter += perf_event_read_value(pmc->perf_event, &enabled,
 						 &running);
 
-	if (!kvm_pmu_idx_is_64bit(vcpu, select_idx))
+	return counter;
+}
+
+/**
+ * kvm_pmu_get_counter_value - get PMU counter value
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ */
+u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	u64 counter;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+
+	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+
+	if (kvm_pmu_pmc_is_chained(pmc) &&
+	    kvm_pmu_idx_is_high_counter(select_idx))
+		counter = upper_32_bits(counter);
+
+	else if (!kvm_pmu_idx_is_64bit(vcpu, select_idx))
 		counter = lower_32_bits(counter);
 
 	return counter;
@@ -78,6 +177,7 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
  */
 static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
 {
+	pmc = kvm_pmu_get_canonical_pmc(pmc);
 	if (pmc->perf_event) {
 		perf_event_disable(pmc->perf_event);
 		perf_event_release_kernel(pmc->perf_event);
@@ -95,13 +195,23 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 {
 	u64 counter, reg;
 
-	if (pmc->perf_event) {
-		counter = kvm_pmu_get_counter_value(vcpu, pmc->idx);
+	pmc = kvm_pmu_get_canonical_pmc(pmc);
+	if (!pmc->perf_event)
+		return;
+
+	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+
+	if (kvm_pmu_pmc_is_chained(pmc)) {
+		reg = PMEVCNTR0_EL0 + pmc->idx;
+		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
+		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+	} else {
 		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
 		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
-		__vcpu_sys_reg(vcpu, reg) = counter;
-		kvm_pmu_release_perf_event(pmc);
+		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
 	}
+
+	kvm_pmu_release_perf_event(pmc);
 }
 
 /**
@@ -118,6 +228,8 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
 		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
 		pmu->pmc[i].idx = i;
 	}
+
+	bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
 }
 
 /**
@@ -166,6 +278,18 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 			continue;
 
 		pmc = &pmu->pmc[i];
+
+		/*
+		 * For high counters of chained events we must recreate the
+		 * perf event with the long (64bit) attribute set.
+		 */
+		if (kvm_pmu_pmc_is_chained(pmc) &&
+		    kvm_pmu_idx_is_high_counter(i)) {
+			kvm_pmu_create_perf_event(vcpu, i);
+			continue;
+		}
+
+		/* At this point, pmc must be the canonical */
 		if (pmc->perf_event) {
 			perf_event_enable(pmc->perf_event);
 			if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE)
@@ -195,6 +319,18 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 			continue;
 
 		pmc = &pmu->pmc[i];
+
+		/*
+		 * For high counters of chained events we must recreate the
+		 * perf event with the long (64bit) attribute unset.
+		 */
+		if (kvm_pmu_pmc_is_chained(pmc) &&
+		    kvm_pmu_idx_is_high_counter(i)) {
+			kvm_pmu_create_perf_event(vcpu, i);
+			continue;
+		}
+
+		/* At this point, pmc must be the canonical */
 		if (pmc->perf_event)
 			perf_event_disable(pmc->perf_event);
 	}
@@ -284,17 +420,6 @@ void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu)
 	kvm_pmu_update_state(vcpu);
 }
 
-static inline struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
-{
-	struct kvm_pmu *pmu;
-	struct kvm_vcpu_arch *vcpu_arch;
-
-	pmc -= pmc->idx;
-	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
-	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
-	return container_of(vcpu_arch, struct kvm_vcpu, arch);
-}
-
 /**
  * When the perf event overflows, set the overflow status and inform the vcpu.
  */
@@ -385,13 +510,20 @@ static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
 static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 {
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+	struct kvm_pmc *pmc;
 	struct perf_event *event;
 	struct perf_event_attr attr;
 	u64 eventsel, counter, reg, data;
 
-	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
-	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx;
+	/*
+	 * For chained counters the event type and filtering attributes are
+	 * obtained from the low/even counter. We also use this counter to
+	 * determine if the event is enabled/disabled.
+	 */
+	pmc = kvm_pmu_get_canonical_pmc(&pmu->pmc[select_idx]);
+
+	reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + pmc->idx;
 	data = __vcpu_sys_reg(vcpu, reg);
 
 	kvm_pmu_stop_counter(vcpu, pmc);
@@ -399,30 +531,47 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 
 	/* Software increment event does't need to be backed by a perf event */
 	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR &&
-	    select_idx != ARMV8_PMU_CYCLE_IDX)
+	    pmc->idx != ARMV8_PMU_CYCLE_IDX)
 		return;
 
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.type = PERF_TYPE_RAW;
 	attr.size = sizeof(attr);
 	attr.pinned = 1;
-	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, select_idx);
+	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, pmc->idx);
 	attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0;
 	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
 	attr.exclude_hv = 1; /* Don't count EL2 events */
 	attr.exclude_host = 1; /* Don't count host events */
-	attr.config = (select_idx == ARMV8_PMU_CYCLE_IDX) ?
+	attr.config = (pmc->idx == ARMV8_PMU_CYCLE_IDX) ?
 		ARMV8_PMUV3_PERFCTR_CPU_CYCLES : eventsel;
 
-	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
-	/* The initial sample period (overflow count) of an event. */
-	if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
+	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+
+	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
+		/**
+		 * The initial sample period (overflow count) of an event. For
+		 * chained counters we only support overflow interrupts on the
+		 * high counter.
+		 */
 		attr.sample_period = (-counter) & GENMASK(63, 0);
-	else
-		attr.sample_period = (-counter) & GENMASK(31, 0);
+		event = perf_event_create_kernel_counter(&attr, -1, current,
+							 kvm_pmu_perf_overflow,
+							 pmc + 1);
+
+		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
+			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
+	} else {
+		/* The initial sample period (overflow count) of an event. */
+		if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
+			attr.sample_period = (-counter) & GENMASK(63, 0);
+		else
+			attr.sample_period = (-counter) & GENMASK(31, 0);
 
-	event = perf_event_create_kernel_counter(&attr, -1, current,
+		event = perf_event_create_kernel_counter(&attr, -1, current,
 						 kvm_pmu_perf_overflow, pmc);
+	}
+
 	if (IS_ERR(event)) {
 		pr_err_once("kvm: pmu event creation failed %ld\n",
 			    PTR_ERR(event));
@@ -432,6 +581,33 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 	pmc->perf_event = event;
 }
 
+/**
+ * kvm_pmu_update_pmc_chained - update chained bitmap
+ * @vcpu: The vcpu pointer
+ * @select_idx: The number of selected counter
+ *
+ * Update the chained bitmap based on the event type written in the
+ * typer register.
+ */
+static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+
+	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
+		/*
+		 * During promotion from !chained to chained we must ensure
+		 * the adjacent counter is stopped and its event destroyed
+		 */
+		if (!kvm_pmu_pmc_is_chained(pmc))
+			kvm_pmu_stop_counter(vcpu, pmc);
+
+		set_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+	} else {
+		clear_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+	}
+}
+
 /**
  * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
  * @vcpu: The vcpu pointer
@@ -451,6 +627,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx;
 
 	__vcpu_sys_reg(vcpu, reg) = event_type;
+
+	kvm_pmu_update_pmc_chained(vcpu, select_idx);
 	kvm_pmu_create_perf_event(vcpu, select_idx);
 }
 
-- 
cgit v1.2.3


From cdc238eb72f6b94b6c33b98c07b9fc3ac5e57b18 Mon Sep 17 00:00:00 2001
From: Yi Wang <wang.yi59@zte.com.cn>
Date: Wed, 10 Jul 2019 08:24:03 +0800
Subject: kvm: x86: Fix -Wmissing-prototypes warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We get a warning when build kernel W=1:

arch/x86/kvm/../../../virt/kvm/eventfd.c:48:1: warning: no previous prototype for ‘kvm_arch_irqfd_allowed’ [-Wmissing-prototypes]
 kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
 ^

The reason is kvm_arch_irqfd_allowed() is declared in arch/x86/kvm/irq.h,
which is not included by eventfd.c. Considering kvm_arch_irqfd_allowed()
is a weakly defined function in eventfd.c, remove the declaration to
kvm_host.h can fix this.

Signed-off-by: Yi Wang <wang.yi59@zte.com.cn>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/irq.h       | 1 -
 include/linux/kvm_host.h | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index fd210cdd4983..d5005cc26521 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -114,7 +114,6 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
 	return mode != KVM_IRQCHIP_NONE;
 }
 
-bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index abafddb9fe2c..b91829ee3db1 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -993,6 +993,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian);
 int kvm_request_irq_source_id(struct kvm *kvm);
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
+bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
 
 /*
  * search_memslots() and __gfn_to_memslot() are here because they are
-- 
cgit v1.2.3


From 66bb8a065f5aedd4551d8d3fbce582972f65c2e1 Mon Sep 17 00:00:00 2001
From: Eric Hankland <ehankland@google.com>
Date: Wed, 10 Jul 2019 18:25:15 -0700
Subject: KVM: x86: PMU Event Filter

Some events can provide a guest with information about other guests or the
host (e.g. L3 cache stats); providing the capability to restrict access
to a "safe" set of events would limit the potential for the PMU to be used
in any side channel attacks. This change introduces a new VM ioctl that
sets an event filter. If the guest attempts to program a counter for
any blacklisted or non-whitelisted event, the kernel counter won't be
created, so any RDPMC/RDMSR will show 0 instances of that event.

Signed-off-by: Eric Hankland <ehankland@google.com>
[Lots of changes. All remaining bugs are probably mine. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 26 ++++++++++++++++
 arch/x86/include/asm/kvm_host.h   |  2 ++
 arch/x86/include/uapi/asm/kvm.h   | 10 +++++++
 arch/x86/kvm/pmu.c                | 63 +++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/pmu.h                |  1 +
 arch/x86/kvm/x86.c                |  5 ++++
 include/uapi/linux/kvm.h          |  3 ++
 7 files changed, 110 insertions(+)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 91fd86fcc49f..38b0d4451a24 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4065,6 +4065,32 @@ KVM_ARM_VCPU_FINALIZE call.
 See KVM_ARM_VCPU_INIT for details of vcpu features that require finalization
 using this ioctl.
 
+4.120 KVM_SET_PMU_EVENT_FILTER
+
+Capability: KVM_CAP_PMU_EVENT_FILTER
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_pmu_event_filter (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_pmu_event_filter {
+       __u32 action;
+       __u32 nevents;
+       __u64 events[0];
+};
+
+This ioctl restricts the set of PMU events that the guest can program.
+The argument holds a list of events which will be allowed or denied.
+The eventsel+umask of each event the guest attempts to program is compared
+against the events field to determine whether the guest should have access.
+This only affects general purpose counters; fixed purpose counters can
+be disabled by changing the perfmon CPUID leaf.
+
+Valid values for 'action':
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
+
 5. The kvm_run structure
 ------------------------
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f46a12a5cf2e..34d017bd1d1b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -933,6 +933,8 @@ struct kvm_arch {
 
 	bool guest_can_read_msr_platform_info;
 	bool exception_payload_enabled;
+
+	struct kvm_pmu_event_filter *pmu_event_filter;
 };
 
 struct kvm_vm_stat {
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index f9b021e16ebc..46588f5d6283 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -422,4 +422,14 @@ struct kvm_nested_state {
 	__u8 data[0];
 };
 
+/* for KVM_CAP_PMU_EVENT_FILTER */
+struct kvm_pmu_event_filter {
+       __u32 action;
+       __u32 nevents;
+       __u64 events[0];
+};
+
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index dd745b58ffd8..9d92c4d3cd44 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -22,6 +22,9 @@
 #include "lapic.h"
 #include "pmu.h"
 
+/* This keeps the total size of the filter under 4k. */
+#define KVM_PMU_EVENT_FILTER_MAX_EVENTS 63
+
 /* NOTE:
  * - Each perf counter is defined as "struct kvm_pmc";
  * - There are two types of perf counters: general purpose (gp) and fixed.
@@ -144,6 +147,10 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 {
 	unsigned config, type = PERF_TYPE_RAW;
 	u8 event_select, unit_mask;
+	struct kvm *kvm = pmc->vcpu->kvm;
+	struct kvm_pmu_event_filter *filter;
+	int i;
+	bool allow_event = true;
 
 	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
 		printk_once("kvm pmu: pin control bit is ignored\n");
@@ -155,6 +162,22 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
 		return;
 
+	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
+	if (filter) {
+		for (i = 0; i < filter->nevents; i++)
+			if (filter->events[i] ==
+			    (eventsel & AMD64_RAW_EVENT_MASK_NB))
+				break;
+		if (filter->action == KVM_PMU_EVENT_ALLOW &&
+		    i == filter->nevents)
+			allow_event = false;
+		if (filter->action == KVM_PMU_EVENT_DENY &&
+		    i < filter->nevents)
+			allow_event = false;
+	}
+	if (!allow_event)
+		return;
+
 	event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
 	unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 
@@ -351,3 +374,43 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_pmu_reset(vcpu);
 }
+
+int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
+{
+	struct kvm_pmu_event_filter tmp, *filter;
+	size_t size;
+	int r;
+
+	if (copy_from_user(&tmp, argp, sizeof(tmp)))
+		return -EFAULT;
+
+	if (tmp.action != KVM_PMU_EVENT_ALLOW &&
+	    tmp.action != KVM_PMU_EVENT_DENY)
+		return -EINVAL;
+
+	if (tmp.nevents > KVM_PMU_EVENT_FILTER_MAX_EVENTS)
+		return -E2BIG;
+
+	size = struct_size(filter, events, tmp.nevents);
+	filter = kmalloc(size, GFP_KERNEL_ACCOUNT);
+	if (!filter)
+		return -ENOMEM;
+
+	r = -EFAULT;
+	if (copy_from_user(filter, argp, size))
+		goto cleanup;
+
+	/* Ensure nevents can't be changed between the user copies. */
+	*filter = tmp;
+
+	mutex_lock(&kvm->lock);
+	rcu_swap_protected(kvm->arch.pmu_event_filter, filter,
+			   mutex_is_locked(&kvm->lock));
+	mutex_unlock(&kvm->lock);
+
+	synchronize_srcu_expedited(&kvm->srcu);
+ 	r = 0;
+cleanup:
+	kfree(filter);
+ 	return r;
+}
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 22dff661145a..58265f761c3b 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -118,6 +118,7 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu);
 void kvm_pmu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_init(struct kvm_vcpu *vcpu);
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
+int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp);
 
 bool is_vmware_backdoor_pmc(u32 pmc_idx);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2e302e977dac..81faceba8cec 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3132,6 +3132,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SET_BOOT_CPU_ID:
  	case KVM_CAP_SPLIT_IRQCHIP:
 	case KVM_CAP_IMMEDIATE_EXIT:
+	case KVM_CAP_PMU_EVENT_FILTER:
 	case KVM_CAP_GET_MSR_FEATURES:
 	case KVM_CAP_MSR_PLATFORM_INFO:
 	case KVM_CAP_EXCEPTION_PAYLOAD:
@@ -4978,6 +4979,9 @@ set_identity_unlock:
 		r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd);
 		break;
 	}
+	case KVM_SET_PMU_EVENT_FILTER:
+		r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
+		break;
 	default:
 		r = -ENOTTY;
 	}
@@ -9428,6 +9432,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
+	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);
 	kvm_page_track_cleanup(kvm);
 	kvm_hv_destroy_vm(kvm);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index c2152f3dd02d..a7c19540ce21 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -995,6 +995,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_SVE 170
 #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172
+#define KVM_CAP_PMU_EVENT_FILTER 173
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1329,6 +1330,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
 /* Available with KVM_CAP_PPC_GET_CPU_CHAR */
 #define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
+/* Available with KVM_CAP_PMU_EVENT_FILTER */
+#define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct kvm_pmu_event_filter)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
-- 
cgit v1.2.3