[PATCH 1/2] kvm-s390: Implement the directed yield (diag 9c) hypervisor call for KVM

[Christian Borntraeger <borntraeger@de.ibm.com>]

From: Konstantin Weitz <WEITZKON@de.ibm.com>

This patch implements the directed yield hypercall found on other
System z hypervisors. It delegates execution time to the virtual cpu
specified in the instruction's parameter.

Useful to avoid long spinlock waits in the guest.

Christian Borntraeger: moved common code in virt/kvm/

Signed-off-by: Konstantin Weitz <WEITZKON@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/s390/include/asm/kvm_host.h |    1 +
 arch/s390/kvm/diag.c             |   25 +++++++++++++++++++++++
 arch/s390/kvm/kvm-s390.c         |    1 +
 include/linux/kvm_host.h         |    1 +
 virt/kvm/kvm_main.c              |   42 +++++++++++++++++++++++---------------
 5 files changed, 54 insertions(+), 16 deletions(-)

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 7343872..dd17537 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -148,6 +148,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_sigp_restart;
 	u32 diagnose_10;
 	u32 diagnose_44;
+	u32 diagnose_9c;
 };
 
 struct kvm_s390_io_info {
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index a353f0e..2d2ae32 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -53,6 +53,29 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_vcpu *tcpu;
+	int tid;
+	int i;
+
+	tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
+	vcpu->stat.diagnose_9c++;
+	VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d", tid);
+
+	if (tid == vcpu->vcpu_id)
+		return 0;
+
+	kvm_for_each_vcpu(i, tcpu, kvm)
+		if (tcpu->vcpu_id == tid) {
+			kvm_vcpu_yield_to(tcpu);
+			break;
+		}
+
+	return 0;
+}
+
 static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 {
 	unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
@@ -89,6 +112,8 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
 		return diag_release_pages(vcpu);
 	case 0x44:
 		return __diag_time_slice_end(vcpu);
+	case 0x9c:
+		return __diag_time_slice_end_directed(vcpu);
 	case 0x308:
 		return __diag_ipl_functions(vcpu);
 	default:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 044ca7e..0054cb0 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -74,6 +74,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
 	{ "diagnose_10", VCPU_STAT(diagnose_10) },
 	{ "diagnose_44", VCPU_STAT(diagnose_44) },
+	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
 	{ NULL }
 };
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 186ffab..2322b21 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -461,6 +461,7 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
 
 void kvm_vcpu_block(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
+bool kvm_vcpu_yield_to(struct kvm_vcpu *target);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
 void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9eb7936..99a38a4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1543,6 +1543,31 @@ void kvm_resched(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_resched);
 
+bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
+{
+	struct pid *pid;
+	struct task_struct *task = NULL;
+
+	rcu_read_lock();
+	pid = rcu_dereference(target->pid);
+	if (pid)
+		task = get_pid_task(target->pid, PIDTYPE_PID);
+	rcu_read_unlock();
+	if (!task)
+		return false;
+	if (task->flags & PF_VCPU) {
+		put_task_struct(task);
+		return false;
+	}
+	if (yield_to(task, 1)) {
+		put_task_struct(task);
+		return true;
+	}
+	put_task_struct(task);
+	return false;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
+
 void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 {
 	struct kvm *kvm = me->kvm;
@@ -1561,8 +1586,6 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 	 */
 	for (pass = 0; pass < 2 && !yielded; pass++) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
-			struct task_struct *task = NULL;
-			struct pid *pid;
 			if (!pass && i < last_boosted_vcpu) {
 				i = last_boosted_vcpu;
 				continue;
@@ -1572,24 +1595,11 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			if (waitqueue_active(&vcpu->wq))
 				continue;
-			rcu_read_lock();
-			pid = rcu_dereference(vcpu->pid);
-			if (pid)
-				task = get_pid_task(vcpu->pid, PIDTYPE_PID);
-			rcu_read_unlock();
-			if (!task)
-				continue;
-			if (task->flags & PF_VCPU) {
-				put_task_struct(task);
-				continue;
-			}
-			if (yield_to(task, 1)) {
-				put_task_struct(task);
+			if (kvm_vcpu_yield_to(vcpu)) {
 				kvm->last_boosted_vcpu = i;
 				yielded = 1;
 				break;
 			}
-			put_task_struct(task);
 		}
 	}
 }
-- 
1.7.9.6