x86/kvm: Add "nopvspin" parameter to disable PV spinlocks

There are cases where a guest tries to switch spinlocks to bare metal
behavior (e.g. by setting "xen_nopvspin" on XEN platform and
"hv_nopvspin" on HYPER_V).

That feature is missed on KVM, add a new parameter "nopvspin" to disable
PV spinlocks for KVM guest.

The new 'nopvspin' parameter will also replace Xen and Hyper-V specific
parameters in future patches.

Define variable nopvsin as global because it will be used in future
patches as above.

Signed-off-by: Zhenzhong Duan <[email protected]>
Reviewed-by: Vitaly Kuznetsov <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krcmar <[email protected]>
Cc: Sean Christopherson <[email protected]>
Cc: Vitaly Kuznetsov <[email protected]>
Cc: Wanpeng Li <[email protected]>
Cc: Jim Mattson <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Will Deacon <[email protected]>
Signed-off-by: Paolo Bonzini <[email protected]>

Author: Zhenzhong Duan

Documentation/admin-guide/kernel-parameters.txt

@@ -5739,6 +5739,11 @@
 			as generic guest with no PV drivers. Currently support
 			XEN HVM, KVM, HYPER_V and VMWARE guest.
 
+	nopvspin	[X86,KVM]
+			Disables the qspinlock slow path using PV optimizations
+			which allow the hypervisor to 'idle' the guest on lock
+			contention.
+
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]

arch/x86/include/asm/qspinlock.h

@@ -32,6 +32,7 @@ extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
 extern void __pv_init_lock_hash(void);
 extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
 extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+extern bool nopvspin;
 
 #define	queued_spin_unlock queued_spin_unlock
 /**

arch/x86/kernel/kvm.c

@@ -871,18 +871,36 @@ asm(
  */
 void __init kvm_spinlock_init(void)
 {
-	/* Does host kernel support KVM_FEATURE_PV_UNHALT? */
-	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
+	/*
+	 * In case host doesn't support KVM_FEATURE_PV_UNHALT there is still an
+	 * advantage of keeping virt_spin_lock_key enabled: virt_spin_lock() is
+	 * preferred over native qspinlock when vCPU is preempted.
+	 */
+	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) {
+		pr_info("PV spinlocks disabled, no host support\n");
 		return;
+	}
 
+	/*
+	 * Disable PV spinlocks and use native qspinlock when dedicated pCPUs
+	 * are available.
+	 */
 	if (kvm_para_has_hint(KVM_HINTS_REALTIME)) {
-		static_branch_disable(&virt_spin_lock_key);
-		return;
+		pr_info("PV spinlocks disabled with KVM_HINTS_REALTIME hints\n");
+		goto out;
 	}
 
-	/* Don't use the pvqspinlock code if there is only 1 vCPU. */
-	if (num_possible_cpus() == 1)
-		return;
+	if (num_possible_cpus() == 1) {
+		pr_info("PV spinlocks disabled, single CPU\n");
+		goto out;
+	}
+
+	if (nopvspin) {
+		pr_info("PV spinlocks disabled, forced by \"nopvspin\" parameter\n");
+		goto out;
+	}
+
+	pr_info("PV spinlocks enabled\n");
 
 	__pv_init_lock_hash();
 	pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
@@ -895,6 +913,13 @@ void __init kvm_spinlock_init(void)
 		pv_ops.lock.vcpu_is_preempted =
 			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
 	}
+	/*
+	 * When PV spinlock is enabled which is preferred over
+	 * virt_spin_lock(), virt_spin_lock_key's value is meaningless.
+	 * Just disable it anyway.
+	 */
+out:
+	static_branch_disable(&virt_spin_lock_key);
 }
 
 #endif	/* CONFIG_PARAVIRT_SPINLOCKS */

kernel/locking/qspinlock.c

@@ -581,4 +581,11 @@ EXPORT_SYMBOL(queued_spin_lock_slowpath);
 #include "qspinlock_paravirt.h"
 #include "qspinlock.c"
 
+bool nopvspin __initdata;
+static __init int parse_nopvspin(char *arg)
+{
+	nopvspin = true;
+	return 0;
+}
+early_param("nopvspin", parse_nopvspin);
 #endif