Re: [PATCH v4 8/8] KVM: Make kvm_make_vcpus_request_mask() use pre-allocated cpu_kick_mask
From: Sean Christopherson
Date: Thu Sep 02 2021 - 17:19:42 EST
On Fri, Aug 27, 2021, Vitaly Kuznetsov wrote:
> kvm_make_vcpus_request_mask() already disables preemption so just like
> kvm_make_all_cpus_request_except() it can be switched to using
> pre-allocated per-cpu cpumasks. This allows for improvements for both
> users of the function: in Hyper-V emulation code 'tlb_flush' can now be
> dropped from 'struct kvm_vcpu_hv' and kvm_make_scan_ioapic_request_mask()
> gets rid of dynamic allocation.
>
> cpumask_available() check in kvm_make_vcpu_request() can now be dropped as
> it checks for an impossible condition: kvm_init() makes sure per-cpu masks
> are allocated.
>
> Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
> ---
> arch/x86/include/asm/kvm_host.h | 1 -
> arch/x86/kvm/hyperv.c | 5 +----
> arch/x86/kvm/x86.c | 8 +-------
> include/linux/kvm_host.h | 2 +-
> virt/kvm/kvm_main.c | 18 +++++++-----------
> 5 files changed, 10 insertions(+), 24 deletions(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 09b256db394a..846552fa2012 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -569,7 +569,6 @@ struct kvm_vcpu_hv {
> struct kvm_hyperv_exit exit;
> struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT];
> DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
> - cpumask_t tlb_flush;
> bool enforce_cpuid;
> struct {
> u32 features_eax; /* HYPERV_CPUID_FEATURES.EAX */
> diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
> index 5704bfe53ee0..f76e7228f687 100644
> --- a/arch/x86/kvm/hyperv.c
> +++ b/arch/x86/kvm/hyperv.c
> @@ -1755,7 +1755,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
> int i;
> gpa_t gpa;
> struct kvm *kvm = vcpu->kvm;
> - struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
> struct hv_tlb_flush_ex flush_ex;
> struct hv_tlb_flush flush;
> u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
> @@ -1837,8 +1836,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
> }
> }
>
> - cpumask_clear(&hv_vcpu->tlb_flush);
> -
> /*
> * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't
> * analyze it here, flush TLB regardless of the specified address space.
> @@ -1850,7 +1847,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
> vp_bitmap, vcpu_bitmap);
>
> kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST,
> - vcpu_mask, &hv_vcpu->tlb_flush);
> + vcpu_mask);
> }
>
> ret_success:
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index a4752dcc2a75..91c1e6c98b0f 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -9224,14 +9224,8 @@ static void process_smi(struct kvm_vcpu *vcpu)
> void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
> unsigned long *vcpu_bitmap)
> {
> - cpumask_var_t cpus;
> -
> - zalloc_cpumask_var(&cpus, GFP_ATOMIC);
> -
> kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC,
> - vcpu_bitmap, cpus);
> -
> - free_cpumask_var(cpus);
> + vcpu_bitmap);
This can opportunistically all go on a single line.
> }
>
> void kvm_make_scan_ioapic_request(struct kvm *kvm)
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 2f149ed140f7..1ee85de0bf74 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -160,7 +160,7 @@ static inline bool is_error_page(struct page *page)
> #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0)
>
> bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
> - unsigned long *vcpu_bitmap, cpumask_var_t tmp);
> + unsigned long *vcpu_bitmap);
> bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
> bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req,
> struct kvm_vcpu *except);
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 2f5fe4f54a51..dc52a04f0586 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -274,14 +274,6 @@ static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu,
> if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
> return;
>
> - /*
> - * tmp can be "unavailable" if cpumasks are allocated off stack as
> - * allocation of the mask is deliberately not fatal and is handled by
> - * falling back to kicking all online CPUs.
> - */
> - if (!cpumask_available(tmp))
> - return;
Hmm, maybe convert the param to an explicit "struct cpumask *" to try and convey
that cpumask_available() doesn't need to be checked?
And I believe you can also do:
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dc52a04f0586..bfd2ecbd97a8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -247,15 +247,8 @@ static void ack_flush(void *_completed)
{
}
-static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait)
+static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait)
{
- const struct cpumask *cpus;
-
- if (likely(cpumask_available(tmp)))
- cpus = tmp;
- else
- cpus = cpu_online_mask;
-
if (cpumask_empty(cpus))
return false;
> -
> /*
> * Note, the vCPU could get migrated to a different pCPU at any point
> * after kvm_request_needs_ipi(), which could result in sending an IPI
> @@ -300,22 +292,26 @@ static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu,
> }
>
> bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
> - unsigned long *vcpu_bitmap, cpumask_var_t tmp)
> + unsigned long *vcpu_bitmap)
> {
> struct kvm_vcpu *vcpu;
> + struct cpumask *cpus;
> int i, me;
> bool called;
>
> me = get_cpu();
>
> + cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask);
> + cpumask_clear(cpus);
> +
> for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) {
> vcpu = kvm_get_vcpu(kvm, i);
> if (!vcpu)
> continue;
> - kvm_make_vcpu_request(kvm, vcpu, req, tmp, me);
> + kvm_make_vcpu_request(kvm, vcpu, req, cpus, me);
> }
>
> - called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT));
> + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
> put_cpu();
>
> return called;
> --
> 2.31.1
>