[for,3.12.y,stable,08/63] arm64: KVM: Yield CPU when vcpu executes a WFE

Message ID 1429853281-6136-9-git-send-email-shannon.zhao@linaro.org
State New
Headers show

Commit Message

Shannon Zhao April 24, 2015, 5:27 a.m.
From: Marc Zyngier <marc.zyngier@arm.com>

commit d241aac798eb042e605f78c31a4122e583b2cd13 upstream.

On an (even slightly) oversubscribed system, spinlocks are quickly
becoming a bottleneck, as some vcpus are spinning, waiting for a
lock to be released, while the vcpu holding the lock may not be
running at all.

The solution is to trap blocking WFEs and tell KVM that we're
now spinning. This ensures that other vpus will get a scheduling
boost, allowing the lock to be released more quickly. Also, using
CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT slightly improves the performance
when the VM is severely overcommited.

Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Shannon Zhao <shannon.zhao@linaro.org>
---
 arch/arm64/include/asm/kvm_arm.h |  8 ++++++--
 arch/arm64/kvm/Kconfig           |  1 +
 arch/arm64/kvm/handle_exit.c     | 18 +++++++++++++-----
 3 files changed, 20 insertions(+), 7 deletions(-)

Patch

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index a5f28e2..c98ef47 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -63,6 +63,7 @@ 
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
  * TSW:		Trap cache operations by set/way
+ * TWE:		Trap WFE
  * TWI:		Trap WFI
  * TIDCP:	Trap L2CTLR/L2ECTLR
  * BSU_IS:	Upgrade barriers to the inner shareable domain
@@ -72,8 +73,9 @@ 
  * FMO:		Override CPSR.F and enable signaling with VF
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
  */
-#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \
-			 HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \
+#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
+			 HCR_BSU_IS | HCR_FB | HCR_TAC | \
+			 HCR_AMO | HCR_IMO | HCR_FMO | \
 			 HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
 
@@ -242,4 +244,6 @@ 
 
 #define ESR_EL2_EC_xABT_xFSR_EXTABT	0x10
 
+#define ESR_EL2_EC_WFI_ISS_WFE	(1 << 0)
+
 #endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 21e9082..4480ab3 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -21,6 +21,7 @@  config KVM
 	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_ARM_HOST
 	select KVM_ARM_VGIC
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 9beaca03..8da5606 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -47,21 +47,29 @@  static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 }
 
 /**
- * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest
+ * kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
+ *		    instruction executed by a guest
+ *
  * @vcpu:	the vcpu pointer
  *
- * Simply call kvm_vcpu_block(), which will halt execution of
+ * WFE: Yield the CPU and come back to this vcpu when the scheduler
+ * decides to.
+ * WFI: Simply call kvm_vcpu_block(), which will halt execution of
  * world-switches and schedule other host processes until there is an
  * incoming IRQ or FIQ to the VM.
  */
-static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	kvm_vcpu_block(vcpu);
+	if (kvm_vcpu_get_hsr(vcpu) & ESR_EL2_EC_WFI_ISS_WFE)
+		kvm_vcpu_on_spin(vcpu);
+	else
+		kvm_vcpu_block(vcpu);
+
 	return 1;
 }
 
 static exit_handle_fn arm_exit_handlers[] = {
-	[ESR_EL2_EC_WFI]	= kvm_handle_wfi,
+	[ESR_EL2_EC_WFI]	= kvm_handle_wfx,
 	[ESR_EL2_EC_CP15_32]	= kvm_handle_cp15_32,
 	[ESR_EL2_EC_CP15_64]	= kvm_handle_cp15_64,
 	[ESR_EL2_EC_CP14_MR]	= kvm_handle_cp14_access,