From 58d5ec8f8ee318b26b29207874fbaee626973952 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 8 Oct 2013 18:38:13 +0100 Subject: 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 Signed-off-by: Christoffer Dall --- arch/arm/include/asm/kvm_arm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/arm/include/asm/kvm_arm.h') diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index d556f03bca1..fe395b7b1ce 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) -- cgit v1.2.3-70-g09d2 From 86ed81aa2e1ce05a4e7f0819f0dfc34e8d8fb910 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Tue, 15 Oct 2013 18:10:42 -0700 Subject: KVM: ARM: Update comments for kvm_handle_wfi Update comments to reflect what is really going on and add the TWE bit to the comments in kvm_arm.h. Also renames the function to kvm_handle_wfx like is done on arm64 for consistency and uber-correctness. Signed-off-by: Christoffer Dall --- arch/arm/include/asm/kvm_arm.h | 1 + arch/arm/kvm/handle_exit.c | 14 ++++++++------ 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'arch/arm/include/asm/kvm_arm.h') diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index fe395b7b1ce..1d3153c7eb4 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -57,6 +57,7 @@ * TSC: Trap SMC * TSW: Trap cache operations by set/way * TWI: Trap WFI + * TWE: Trap WFE * TIDCP: Trap L2CTLR/L2ECTLR * BSU_IS: Upgrade barriers to the inner shareable domain * FB: Force broadcast of all maintainance operations diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index c4c496f7619..a92079011a8 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -73,15 +73,17 @@ static int handle_dabt_hyp(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 WFI or WFE instructions trapped in guests * @vcpu: the vcpu pointer * @run: the kvm_run structure pointer * - * Simply sets the wait_for_interrupts flag on the vcpu structure, which will - * halt execution of world-switches and schedule other host processes until - * there is an incoming IRQ or FIQ to the VM. + * 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) { trace_kvm_wfi(*vcpu_pc(vcpu)); if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) @@ -93,7 +95,7 @@ static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run) } static exit_handle_fn arm_exit_handlers[] = { - [HSR_EC_WFI] = kvm_handle_wfi, + [HSR_EC_WFI] = kvm_handle_wfx, [HSR_EC_CP15_32] = kvm_handle_cp15_32, [HSR_EC_CP15_64] = kvm_handle_cp15_64, [HSR_EC_CP14_MR] = kvm_handle_cp14_access, -- cgit v1.2.3-70-g09d2