diff mbox series

[v2] KVM: x86: Support the vCPU preemption check with nopvspin and realtime hint

Message ID 1646639969-44226-1-git-send-email-lirongqing@baidu.com (mailing list archive)
State New, archived
Headers show
Series [v2] KVM: x86: Support the vCPU preemption check with nopvspin and realtime hint | expand

Commit Message

Li RongQing March 7, 2022, 7:59 a.m. UTC 
If guest kernel is configured with nopvspin, or guest find its has
dedicated pCPUs from realtime hint feature, the pvspinlock will be
disabled, and vCPU preemption check is disabled too.

but KVM still can emulating HLT for vCPU for both cases, and check
if vCPU is preempted or not, and can boost performance

Like unixbench, single copy, guest kernel with nopvspin:

Testcase                                  Base    with patch
System Benchmarks Index Values            INDEX     INDEX
Dhrystone 2 using register variables     3278.4    3277.7
Double-Precision Whetstone                822.8     825.8
Execl Throughput                         1296.5     941.1
File Copy 1024 bufsize 2000 maxblocks    2124.2    2142.7
File Copy 256 bufsize 500 maxblocks      1335.9    1353.6
File Copy 4096 bufsize 8000 maxblocks    4256.3    4760.3
Pipe Throughput                          1050.1    1054.0
Pipe-based Context Switching              243.3     352.0
Process Creation                          820.1     814.4
Shell Scripts (1 concurrent)             2169.0    2086.0
Shell Scripts (8 concurrent)             7710.3    7576.3
System Call Overhead                      672.4     673.9
                                      ========    =======
System Benchmarks Index Score             1467.2   1483.0

Co-developed-by: Wang GuangJu <wangguangju@baidu.com>
Signed-off-by: Wang GuangJu <wangguangju@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
---
diff mbox series

Patch

diff v1: move the vcpu_is_preempted setting into kvm_guest_init,
to reduce a check of kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)

 arch/x86/kernel/kvm.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d77481ec..3da39da 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -764,6 +764,9 @@  static void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		has_steal_clock = 1;
 		static_call_update(pv_steal_clock, kvm_steal_clock);
+
+		pv_ops.lock.vcpu_is_preempted =
+			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -1081,10 +1084,6 @@  void __init kvm_spinlock_init(void)
 	pv_ops.lock.wait = kvm_wait;
 	pv_ops.lock.kick = kvm_kick_cpu;
 
-	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
-		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.