[PATCH v6 3/5] x86/kvm: Add "nopvspin" parameter to disable PV spinlocks

[Zhenzhong Duan <zhenzhong.duan@oracle.com>]

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 <zhenzhong.duan@oracle.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Wanpeng Li <wanpengli@tencent.com>
Cc: Jim Mattson <jmattson@google.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
---
 Documentation/admin-guide/kernel-parameters.txt |  5 ++++
 arch/x86/include/asm/qspinlock.h                |  1 +
 arch/x86/kernel/kvm.c                           | 34 ++++++++++++++++++++++---
 kernel/locking/qspinlock.c                      |  7 +++++
 4 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a84a83f..bd49ed2 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5334,6 +5334,11 @@
 			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>]]]
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 444d6fd..d86ab94 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -32,6 +32,7 @@ static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lo
 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
 /**
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 249f14a..e9c76d8 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -825,18 +825,44 @@ __visible bool __kvm_vcpu_is_preempted(long cpu)
  */
 void __init kvm_spinlock_init(void)
 {
-	/* Does host kernel support KVM_FEATURE_PV_UNHALT? */
-	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
+	/*
+	 * PV spinlocks is disabled if no host side support, then native
+	 * qspinlock will be used. As native qspinlock is a fair lock, there is
+	 * lock holder preemption issue using it in a guest, imaging one pCPU
+	 * running 10 vCPUs of same guest contending same lock.
+	 *
+	 * virt_spin_lock() is introduced as an optimization for that scenario
+	 * which is enabled by virt_spin_lock_key key. To use that optimization,
+	 * virt_spin_lock_key isn't disabled here.
+	 */
+	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) {
+		pr_info("PV spinlocks disabled, no host support.\n");
 		return;
+	}
 
+	/*
+	 * Disable PV qspinlock and use native qspinlock when dedicated pCPUs
+	 * are available.
+	 */
 	if (kvm_para_has_hint(KVM_HINTS_REALTIME)) {
+		pr_info("PV spinlocks disabled with KVM_HINTS_REALTIME hints.\n");
+		static_branch_disable(&virt_spin_lock_key);
+		return;
+	}
+
+	if (num_possible_cpus() == 1) {
+		pr_info("PV spinlocks disabled, single CPU.\n");
 		static_branch_disable(&virt_spin_lock_key);
 		return;
 	}
 
-	/* Don't use the pvqspinlock code if there is only 1 vCPU. */
-	if (num_possible_cpus() == 1)
+	if (nopvspin) {
+		pr_info("PV spinlocks disabled, forced by \"nopvspin\" parameter.\n");
+		static_branch_disable(&virt_spin_lock_key);
 		return;
+	}
+
+	pr_info("PV spinlocks enabled\n");
 
 	__pv_init_lock_hash();
 	pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 2473f10..75193d6 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -580,4 +580,11 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 #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
-- 
1.8.3.1