Merge tag 'kvm-s390-20140715' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into kvm-next

This series enables the "KVM_(S|G)ET_MP_STATE" ioctls on s390 to make
the cpu state settable by user space.

This is necessary to avoid races in s390 SIGP/reset handling which
happen because some SIGPs are handled in QEMU, while others are
handled in the kernel. Together with the busy conditions as return
value of SIGP races happen especially in areas like starting and
stopping of CPUs. (For example, there is a program 'cpuplugd', that
runs on several s390 distros which does automatic onlining and
offlining on cpus.)

As soon as the MPSTATE interface is used, user space takes complete
control of the cpu states. Otherwise the kernel will use the old way.

Therefore, the new kernel continues to work fine with old QEMUs.

8 files changed, 98 insertions, 45 deletions

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 5833266407f5..587972ca12c5 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -988,7 +988,7 @@ for vm-wide capabilities.
 4.38 KVM_GET_MP_STATE
 
 Capability: KVM_CAP_MP_STATE
-Architectures: x86, ia64
+Architectures: x86, ia64, s390
 Type: vcpu ioctl
 Parameters: struct kvm_mp_state (out)
 Returns: 0 on success; -1 on error
@@ -1002,24 +1002,32 @@ uniprocessor guests).
 
 Possible values are:
 
- - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running
+ - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running [x86, ia64]
  - KVM_MP_STATE_UNINITIALIZED:   the vcpu is an application processor (AP)
-                                 which has not yet received an INIT signal
+                                 which has not yet received an INIT signal [x86,
+                                 ia64]
  - KVM_MP_STATE_INIT_RECEIVED:   the vcpu has received an INIT signal, and is
-                                 now ready for a SIPI
+                                 now ready for a SIPI [x86, ia64]
  - KVM_MP_STATE_HALTED:          the vcpu has executed a HLT instruction and
-                                 is waiting for an interrupt
+                                 is waiting for an interrupt [x86, ia64]
  - KVM_MP_STATE_SIPI_RECEIVED:   the vcpu has just received a SIPI (vector
-                                 accessible via KVM_GET_VCPU_EVENTS)
+                                 accessible via KVM_GET_VCPU_EVENTS) [x86, ia64]
+ - KVM_MP_STATE_STOPPED:         the vcpu is stopped [s390]
+ - KVM_MP_STATE_CHECK_STOP:      the vcpu is in a special error state [s390]
+ - KVM_MP_STATE_OPERATING:       the vcpu is operating (running or halted)
+                                 [s390]
+ - KVM_MP_STATE_LOAD:            the vcpu is in a special load/startup state
+                                 [s390]
 
-This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
-irqchip, the multiprocessing state must be maintained by userspace.
+On x86 and ia64, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
+in-kernel irqchip, the multiprocessing state must be maintained by userspace on
+these architectures.
 
 
 4.39 KVM_SET_MP_STATE
 
 Capability: KVM_CAP_MP_STATE
-Architectures: x86, ia64
+Architectures: x86, ia64, s390
 Type: vcpu ioctl
 Parameters: struct kvm_mp_state (in)
 Returns: 0 on success; -1 on error
@@ -1027,8 +1035,9 @@ Returns: 0 on success; -1 on error
 Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
 arguments.
 
-This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
-irqchip, the multiprocessing state must be maintained by userspace.
+On x86 and ia64, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
+in-kernel irqchip, the multiprocessing state must be maintained by userspace on
+these architectures.
 
 
 4.40 KVM_SET_IDENTITY_MAP_ADDR
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 4181d7baabba..c2ba0208a0e1 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -418,6 +418,7 @@ struct kvm_arch{
 	int css_support;
 	int use_irqchip;
 	int use_cmma;
+	int user_cpu_state_ctrl;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
 	wait_queue_head_t ipte_wq;
 	spinlock_t start_stop_lock;
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 0161675878a2..59bd8f991b98 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -176,7 +176,8 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP;
 	}
 
-	kvm_s390_vcpu_stop(vcpu);
+	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
+		kvm_s390_vcpu_stop(vcpu);
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index a0b586c1913c..eaf46291d361 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -56,32 +56,26 @@ static int handle_noop(struct kvm_vcpu *vcpu)
 static int handle_stop(struct kvm_vcpu *vcpu)
 {
 	int rc = 0;
+	unsigned int action_bits;
 
 	vcpu->stat.exit_stop_request++;
-	spin_lock_bh(&vcpu->arch.local_int.lock);
-
 	trace_kvm_s390_stop_request(vcpu->arch.local_int.action_bits);
 
-	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
-		kvm_s390_vcpu_stop(vcpu);
-		vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
-		VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
-		rc = -EOPNOTSUPP;
-	}
+	action_bits = vcpu->arch.local_int.action_bits;
 
-	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
-		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
-		/* store status must be called unlocked. Since local_int.lock
-		 * only protects local_int.* and not guest memory we can give
-		 * up the lock here */
-		spin_unlock_bh(&vcpu->arch.local_int.lock);
+	if (!(action_bits & ACTION_STOP_ON_STOP))
+		return 0;
+
+	if (action_bits & ACTION_STORE_ON_STOP) {
 		rc = kvm_s390_vcpu_store_status(vcpu,
 						KVM_S390_STORE_STATUS_NOADDR);
-		if (rc >= 0)
-			rc = -EOPNOTSUPP;
-	} else
-		spin_unlock_bh(&vcpu->arch.local_int.lock);
-	return rc;
+		if (rc)
+			return rc;
+	}
+
+	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
+		kvm_s390_vcpu_stop(vcpu);
+	return -EOPNOTSUPP;
 }
 
 static int handle_validity(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2f3e14fe91a4..fdf88f7a539c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -167,6 +167,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_ENABLE_CAP_VM:
 	case KVM_CAP_VM_ATTRIBUTES:
+	case KVM_CAP_MP_STATE:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
@@ -595,7 +596,8 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->pp = 0;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
-	kvm_s390_vcpu_stop(vcpu);
+	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
+		kvm_s390_vcpu_stop(vcpu);
 	kvm_s390_clear_local_irqs(vcpu);
 }
 
@@ -926,7 +928,7 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
 {
 	int rc = 0;
 
-	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
+	if (!is_vcpu_stopped(vcpu))
 		rc = -EBUSY;
 	else {
 		vcpu->run->psw_mask = psw.mask;
@@ -980,13 +982,34 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	return -EINVAL; /* not implemented yet */
+	/* CHECK_STOP and LOAD are not supported yet */
+	return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
+				       KVM_MP_STATE_OPERATING;
 }
 
 int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	return -EINVAL; /* not implemented yet */
+	int rc = 0;
+
+	/* user space knows about this interface - let it control the state */
+	vcpu->kvm->arch.user_cpu_state_ctrl = 1;
+
+	switch (mp_state->mp_state) {
+	case KVM_MP_STATE_STOPPED:
+		kvm_s390_vcpu_stop(vcpu);
+		break;
+	case KVM_MP_STATE_OPERATING:
+		kvm_s390_vcpu_start(vcpu);
+		break;
+	case KVM_MP_STATE_LOAD:
+	case KVM_MP_STATE_CHECK_STOP:
+		/* fall through - CHECK_STOP and LOAD are not supported yet */
+	default:
+		rc = -ENXIO;
+	}
+
+	return rc;
 }
 
 bool kvm_s390_cmma_enabled(struct kvm *kvm)
@@ -1284,7 +1307,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
-	kvm_s390_vcpu_start(vcpu);
+	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
+		kvm_s390_vcpu_start(vcpu);
+	} else if (is_vcpu_stopped(vcpu)) {
+		pr_err_ratelimited("kvm-s390: can't run stopped vcpu %d\n",
+				   vcpu->vcpu_id);
+		return -EINVAL;
+	}
 
 	switch (kvm_run->exit_reason) {
 	case KVM_EXIT_S390_SIEIC:
@@ -1413,11 +1442,6 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	return kvm_s390_store_status_unloaded(vcpu, addr);
 }
 
-static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
-{
-	return atomic_read(&(vcpu)->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
-}
-
 static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 {
 	kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
@@ -1494,7 +1518,15 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 	spin_lock_bh(&vcpu->kvm->arch.start_stop_lock);
 	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);
 
+	/* Need to lock access to action_bits to avoid a SIGP race condition */
+	spin_lock_bh(&vcpu->arch.local_int.lock);
 	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+
+	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
+	vcpu->arch.local_int.action_bits &=
+				 ~(ACTION_STOP_ON_STOP | ACTION_STORE_ON_STOP);
+	spin_unlock_bh(&vcpu->arch.local_int.lock);
+
 	__disable_ibs_on_vcpu(vcpu);
 
 	for (i = 0; i < online_vcpus; i++) {
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index a8655ed31616..33a0e4bed2a5 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -45,9 +45,9 @@ do { \
 	  d_args); \
 } while (0)
 
-static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
+static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
 {
-	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT;
+	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
 }
 
 static inline int kvm_is_ucontrol(struct kvm *kvm)
@@ -129,6 +129,12 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc)
 	vcpu->arch.sie_block->gpsw.mask |= cc << 44;
 }
 
+/* are cpu states controlled by user space */
+static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm)
+{
+	return kvm->arch.user_cpu_state_ctrl != 0;
+}
+
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
 void kvm_s390_tasklet(unsigned long parm);
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 43079a48cc98..fd7fb5c5ef5d 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -136,6 +136,11 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 	inti->type = KVM_S390_SIGP_STOP;
 
 	spin_lock_bh(&li->lock);
+	if (li->action_bits & ACTION_STOP_ON_STOP) {
+		/* another SIGP STOP is pending */
+		rc = SIGP_CC_BUSY;
+		goto out;
+	}
 	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
 		kfree(inti);
 		if ((action & ACTION_STORE_ON_STOP) != 0)
@@ -144,8 +149,8 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 	}
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
-	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
 	li->action_bits |= action;
+	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
 	if (waitqueue_active(li->wq))
 		wake_up_interruptible(li->wq);
 out:
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e11d8f170a62..9b744af871d7 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -399,13 +399,18 @@ struct kvm_vapic_addr {
 	__u64 vapic_addr;
 };
 
-/* for KVM_SET_MPSTATE */
+/* for KVM_SET_MP_STATE */
 
+/* not all states are valid on all architectures */
 #define KVM_MP_STATE_RUNNABLE          0
 #define KVM_MP_STATE_UNINITIALIZED     1
 #define KVM_MP_STATE_INIT_RECEIVED     2
 #define KVM_MP_STATE_HALTED            3
 #define KVM_MP_STATE_SIPI_RECEIVED     4
+#define KVM_MP_STATE_STOPPED           5
+#define KVM_MP_STATE_CHECK_STOP        6
+#define KVM_MP_STATE_OPERATING         7
+#define KVM_MP_STATE_LOAD              8
 
 struct kvm_mp_state {
 	__u32 mp_state;