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 <zhenzhong.duan@oracle.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.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>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index fb95fad81c79a065e728202a34a3dabac5653cb4..6a8934ffdaf6dde699245751208131161adc30c4 100644 (file)
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/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>]]]

diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 444d6fd9a6d8991bc152721720bb47fc3b258e46..d86ab942219c4277385cc256bbcf4794f38a80df 100644 (file)
--- a/arch/x86/include/asm/qspinlock.h
+++ b/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
 /**

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 4ef21a87f1d3d7bbfd304008ad2e0a741ea60dfe..d9995931ea18458a0bdd525ae9c6e8613fc2fda0 100644 (file)
--- a/arch/x86/kernel/kvm.c
+++ b/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 */

diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index b9515fcc9b297147a34adbe62b0d86d6168e7fac..cbff6ba53d563634791e27ad8d11e7a683065679 100644 (file)
--- a/kernel/locking/qspinlock.c
+++ b/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