diff options
| author | Marc Zyngier <marc.zyngier@arm.com> | 2013-10-08 17:38:13 (GMT) |
|---|---|---|
| committer | Christoffer Dall <christoffer.dall@linaro.org> | 2013-10-17 22:26:50 (GMT) |
| commit | 58d5ec8f8ee318b26b29207874fbaee626973952 (patch) | |
| tree | bf3fdfd27af3c947c51fa4335009a45433a629f2 /arch | |
| parent | d570142674890fe10b3d7d86aa105e3dfce1ddfa (diff) | |
| download | linux-58d5ec8f8ee318b26b29207874fbaee626973952.tar.xz | |
ARM: KVM: Yield CPU when vcpu executes a WFE
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.
This creates contention, and the observed slowdown is 40x for
hackbench. No, this isn't a typo.
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.
Quick test to estimate the performance: hackbench 1 process 1000
2xA15 host (baseline): 1.843s
2xA15 guest w/o patch: 2.083s
4xA15 guest w/o patch: 80.212s
8xA15 guest w/o patch: Could not be bothered to find out
2xA15 guest w/ patch: 2.102s
4xA15 guest w/ patch: 3.205s
8xA15 guest w/ patch: 6.887s
So we go from a 40x degradation to 1.5x in the 2x overcommit case,
which is vaguely more acceptable.
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Diffstat (limited to 'arch')
| -rw-r--r-- | arch/arm/include/asm/kvm_arm.h | 4 | ||||
| -rw-r--r-- | arch/arm/kvm/Kconfig | 1 | ||||
| -rw-r--r-- | arch/arm/kvm/handle_exit.c | 6 |
3 files changed, 9 insertions, 2 deletions
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index d556f03..fe395b7 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -67,7 +67,7 @@ */ #define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \ HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \ - HCR_SWIO | HCR_TIDCP) + HCR_TWE | HCR_SWIO | HCR_TIDCP) #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF) /* System Control Register (SCTLR) bits */ @@ -208,6 +208,8 @@ #define HSR_EC_DABT (0x24) #define HSR_EC_DABT_HYP (0x25) +#define HSR_WFI_IS_WFE (1U << 0) + #define HSR_HVC_IMM_MASK ((1UL << 16) - 1) #define HSR_DABT_S1PTW (1U << 7) diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index ebf5015..466bd29 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -20,6 +20,7 @@ config KVM bool "Kernel-based Virtual Machine (KVM) support" select PREEMPT_NOTIFIERS select ANON_INODES + select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO select KVM_ARM_HOST depends on ARM_VIRT_EXT && ARM_LPAE diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index df4c82d..c4c496f 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -84,7 +84,11 @@ static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run) { trace_kvm_wfi(*vcpu_pc(vcpu)); - kvm_vcpu_block(vcpu); + if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) + kvm_vcpu_on_spin(vcpu); + else + kvm_vcpu_block(vcpu); + return 1; } |