* Re: [PATCH v2 2/2] KVM: Pre-allocate 1 cpumask variable per cpu for both pv tlb and pv ipis
@ 2020-02-11 2:26 linmiaohe
0 siblings, 0 replies; 7+ messages in thread
From: linmiaohe @ 2020-02-11 2:26 UTC (permalink / raw)
To: Wanpeng Li
Cc: Paolo Bonzini, Sean Christopherson, Wanpeng Li, Vitaly Kuznetsov,
Jim Mattson, Joerg Roedel, LKML, kvm
Hi:
>From: Wanpeng Li <wanpengli@tencent.com>
>
>This patch fixes it by pre-allocate 1 cpumask variable per cpu and use it for both pv tlb and pv ipis..
>
>Reported-by: Nick Desaulniers <ndesaulniers@google.com>
>Acked-by: Nick Desaulniers <ndesaulniers@google.com>
>Cc: Peter Zijlstra <peterz@infradead.org>
>Cc: Nick Desaulniers <ndesaulniers@google.com>
>Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Looks fine for me. Thanks.
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v2 2/2] KVM: Pre-allocate 1 cpumask variable per cpu for both pv tlb and pv ipis
2020-02-17 17:11 ` Paolo Bonzini
@ 2020-02-18 1:23 ` Wanpeng Li
0 siblings, 0 replies; 7+ messages in thread
From: Wanpeng Li @ 2020-02-18 1:23 UTC (permalink / raw)
To: Paolo Bonzini
Cc: LKML, kvm, Sean Christopherson, Wanpeng Li, Vitaly Kuznetsov,
Jim Mattson, Joerg Roedel
On Tue, 18 Feb 2020 at 01:11, Paolo Bonzini <pbonzini@redhat.com> wrote:
>
> On 10/02/20 07:38, Wanpeng Li wrote:
> > From: Wanpeng Li <wanpengli@tencent.com>
> >
> > Nick Desaulniers Reported:
> >
> > When building with:
> > $ make CC=clang arch/x86/ CFLAGS=-Wframe-larger-than=1000
> > The following warning is observed:
> > arch/x86/kernel/kvm.c:494:13: warning: stack frame size of 1064 bytes in
> > function 'kvm_send_ipi_mask_allbutself' [-Wframe-larger-than=]
> > static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int
> > vector)
> > ^
> > Debugging with:
> > https://github.com/ClangBuiltLinux/frame-larger-than
> > via:
> > $ python3 frame_larger_than.py arch/x86/kernel/kvm.o \
> > kvm_send_ipi_mask_allbutself
> > points to the stack allocated `struct cpumask newmask` in
> > `kvm_send_ipi_mask_allbutself`. The size of a `struct cpumask` is
> > potentially large, as it's CONFIG_NR_CPUS divided by BITS_PER_LONG for
> > the target architecture. CONFIG_NR_CPUS for X86_64 can be as high as
> > 8192, making a single instance of a `struct cpumask` 1024 B.
> >
> > This patch fixes it by pre-allocate 1 cpumask variable per cpu and use it for
> > both pv tlb and pv ipis..
> >
> > Reported-by: Nick Desaulniers <ndesaulniers@google.com>
> > Acked-by: Nick Desaulniers <ndesaulniers@google.com>
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Cc: Nick Desaulniers <ndesaulniers@google.com>
> > Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
> > ---
> > v1 -> v2:
> > * remove '!alloc' check
> > * use new pv check helpers
> >
> > arch/x86/kernel/kvm.c | 33 +++++++++++++++++++++------------
> > 1 file changed, 21 insertions(+), 12 deletions(-)
> >
> > diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> > index 76ea8c4..377b224 100644
> > --- a/arch/x86/kernel/kvm.c
> > +++ b/arch/x86/kernel/kvm.c
> > @@ -432,6 +432,8 @@ static bool pv_tlb_flush_supported(void)
> > kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
> > }
> >
> > +static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
> > +
> > #ifdef CONFIG_SMP
> >
> > static bool pv_ipi_supported(void)
> > @@ -510,12 +512,12 @@ static void kvm_send_ipi_mask(const struct
> > cpumask *mask, int vector)
> > static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask,
> > int vector)
> > {
> > unsigned int this_cpu = smp_processor_id();
> > - struct cpumask new_mask;
> > + struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
> > const struct cpumask *local_mask;
> >
> > - cpumask_copy(&new_mask, mask);
> > - cpumask_clear_cpu(this_cpu, &new_mask);
> > - local_mask = &new_mask;
> > + cpumask_copy(new_mask, mask);
> > + cpumask_clear_cpu(this_cpu, new_mask);
> > + local_mask = new_mask;
> > __send_ipi_mask(local_mask, vector);
> > }
> >
> > @@ -595,7 +597,6 @@ static void __init kvm_apf_trap_init(void)
> > update_intr_gate(X86_TRAP_PF, async_page_fault);
> > }
> >
> > -static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
> >
> > static void kvm_flush_tlb_others(const struct cpumask *cpumask,
> > const struct flush_tlb_info *info)
> > @@ -603,7 +604,7 @@ static void kvm_flush_tlb_others(const struct
> > cpumask *cpumask,
> > u8 state;
> > int cpu;
> > struct kvm_steal_time *src;
> > - struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
> > + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
> >
> > cpumask_copy(flushmask, cpumask);
> > /*
> > @@ -642,6 +643,7 @@ static void __init kvm_guest_init(void)
> > if (pv_tlb_flush_supported()) {
> > pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
> > pv_ops.mmu.tlb_remove_table = tlb_remove_table;
> > + pr_info("KVM setup pv remote TLB flush\n");
> > }
> >
> > if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
> > @@ -748,24 +750,31 @@ static __init int activate_jump_labels(void)
> > }
> > arch_initcall(activate_jump_labels);
> >
> > -static __init int kvm_setup_pv_tlb_flush(void)
> > +static __init int kvm_alloc_cpumask(void)
> > {
> > int cpu;
> > + bool alloc = false;
> >
> > if (!kvm_para_available() || nopv)
> > return 0;
> >
> > - if (pv_tlb_flush_supported()) {
> > + if (pv_tlb_flush_supported())
> > + alloc = true;
> > +
> > +#if defined(CONFIG_SMP)
> > + if (pv_ipi_supported())
> > + alloc = true;
> > +#endif
> > +
> > + if (alloc)
> > for_each_possible_cpu(cpu) {
> > - zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
> > + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
> > GFP_KERNEL, cpu_to_node(cpu));
> > }
> > - pr_info("KVM setup pv remote TLB flush\n");
> > - }
> >
> > return 0;
> > }
> > -arch_initcall(kvm_setup_pv_tlb_flush);
> > +arch_initcall(kvm_alloc_cpumask);
> >
> > #ifdef CONFIG_PARAVIRT_SPINLOCKS
> >
> > --
> > 2.7.4
> >
>
> Also has messed up whitespace, can you resend please?
My fault, just resend all of them.
Wanpeng
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v2 2/2] KVM: Pre-allocate 1 cpumask variable per cpu for both pv tlb and pv ipis
2020-02-10 6:38 Wanpeng Li
2020-02-17 12:46 ` Vitaly Kuznetsov
@ 2020-02-17 17:11 ` Paolo Bonzini
2020-02-18 1:23 ` Wanpeng Li
1 sibling, 1 reply; 7+ messages in thread
From: Paolo Bonzini @ 2020-02-17 17:11 UTC (permalink / raw)
To: Wanpeng Li, LKML, kvm
Cc: Sean Christopherson, Wanpeng Li, Vitaly Kuznetsov, Jim Mattson,
Joerg Roedel
On 10/02/20 07:38, Wanpeng Li wrote:
> From: Wanpeng Li <wanpengli@tencent.com>
>
> Nick Desaulniers Reported:
>
> When building with:
> $ make CC=clang arch/x86/ CFLAGS=-Wframe-larger-than=1000
> The following warning is observed:
> arch/x86/kernel/kvm.c:494:13: warning: stack frame size of 1064 bytes in
> function 'kvm_send_ipi_mask_allbutself' [-Wframe-larger-than=]
> static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int
> vector)
> ^
> Debugging with:
> https://github.com/ClangBuiltLinux/frame-larger-than
> via:
> $ python3 frame_larger_than.py arch/x86/kernel/kvm.o \
> kvm_send_ipi_mask_allbutself
> points to the stack allocated `struct cpumask newmask` in
> `kvm_send_ipi_mask_allbutself`. The size of a `struct cpumask` is
> potentially large, as it's CONFIG_NR_CPUS divided by BITS_PER_LONG for
> the target architecture. CONFIG_NR_CPUS for X86_64 can be as high as
> 8192, making a single instance of a `struct cpumask` 1024 B.
>
> This patch fixes it by pre-allocate 1 cpumask variable per cpu and use it for
> both pv tlb and pv ipis..
>
> Reported-by: Nick Desaulniers <ndesaulniers@google.com>
> Acked-by: Nick Desaulniers <ndesaulniers@google.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Nick Desaulniers <ndesaulniers@google.com>
> Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
> ---
> v1 -> v2:
> * remove '!alloc' check
> * use new pv check helpers
>
> arch/x86/kernel/kvm.c | 33 +++++++++++++++++++++------------
> 1 file changed, 21 insertions(+), 12 deletions(-)
>
> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> index 76ea8c4..377b224 100644
> --- a/arch/x86/kernel/kvm.c
> +++ b/arch/x86/kernel/kvm.c
> @@ -432,6 +432,8 @@ static bool pv_tlb_flush_supported(void)
> kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
> }
>
> +static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
> +
> #ifdef CONFIG_SMP
>
> static bool pv_ipi_supported(void)
> @@ -510,12 +512,12 @@ static void kvm_send_ipi_mask(const struct
> cpumask *mask, int vector)
> static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask,
> int vector)
> {
> unsigned int this_cpu = smp_processor_id();
> - struct cpumask new_mask;
> + struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
> const struct cpumask *local_mask;
>
> - cpumask_copy(&new_mask, mask);
> - cpumask_clear_cpu(this_cpu, &new_mask);
> - local_mask = &new_mask;
> + cpumask_copy(new_mask, mask);
> + cpumask_clear_cpu(this_cpu, new_mask);
> + local_mask = new_mask;
> __send_ipi_mask(local_mask, vector);
> }
>
> @@ -595,7 +597,6 @@ static void __init kvm_apf_trap_init(void)
> update_intr_gate(X86_TRAP_PF, async_page_fault);
> }
>
> -static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
>
> static void kvm_flush_tlb_others(const struct cpumask *cpumask,
> const struct flush_tlb_info *info)
> @@ -603,7 +604,7 @@ static void kvm_flush_tlb_others(const struct
> cpumask *cpumask,
> u8 state;
> int cpu;
> struct kvm_steal_time *src;
> - struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
> + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
>
> cpumask_copy(flushmask, cpumask);
> /*
> @@ -642,6 +643,7 @@ static void __init kvm_guest_init(void)
> if (pv_tlb_flush_supported()) {
> pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
> pv_ops.mmu.tlb_remove_table = tlb_remove_table;
> + pr_info("KVM setup pv remote TLB flush\n");
> }
>
> if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
> @@ -748,24 +750,31 @@ static __init int activate_jump_labels(void)
> }
> arch_initcall(activate_jump_labels);
>
> -static __init int kvm_setup_pv_tlb_flush(void)
> +static __init int kvm_alloc_cpumask(void)
> {
> int cpu;
> + bool alloc = false;
>
> if (!kvm_para_available() || nopv)
> return 0;
>
> - if (pv_tlb_flush_supported()) {
> + if (pv_tlb_flush_supported())
> + alloc = true;
> +
> +#if defined(CONFIG_SMP)
> + if (pv_ipi_supported())
> + alloc = true;
> +#endif
> +
> + if (alloc)
> for_each_possible_cpu(cpu) {
> - zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
> + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
> GFP_KERNEL, cpu_to_node(cpu));
> }
> - pr_info("KVM setup pv remote TLB flush\n");
> - }
>
> return 0;
> }
> -arch_initcall(kvm_setup_pv_tlb_flush);
> +arch_initcall(kvm_alloc_cpumask);
>
> #ifdef CONFIG_PARAVIRT_SPINLOCKS
>
> --
> 2.7.4
>
Also has messed up whitespace, can you resend please?
Paolo
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v2 2/2] KVM: Pre-allocate 1 cpumask variable per cpu for both pv tlb and pv ipis
2020-02-17 13:15 ` Wanpeng Li
@ 2020-02-17 14:16 ` Vitaly Kuznetsov
0 siblings, 0 replies; 7+ messages in thread
From: Vitaly Kuznetsov @ 2020-02-17 14:16 UTC (permalink / raw)
To: Wanpeng Li
Cc: Paolo Bonzini, Sean Christopherson, Wanpeng Li, Jim Mattson,
Joerg Roedel, LKML, kvm
Wanpeng Li <kernellwp@gmail.com> writes:
> On Mon, 17 Feb 2020 at 20:46, Vitaly Kuznetsov <vkuznets@redhat.com> wrote:
>>
>> Wanpeng Li <kernellwp@gmail.com> writes:
>>
>> > From: Wanpeng Li <wanpengli@tencent.com>
>> >
>> > Nick Desaulniers Reported:
>> >
>> > When building with:
>> > $ make CC=clang arch/x86/ CFLAGS=-Wframe-larger-than=1000
>> > The following warning is observed:
>> > arch/x86/kernel/kvm.c:494:13: warning: stack frame size of 1064 bytes in
>> > function 'kvm_send_ipi_mask_allbutself' [-Wframe-larger-than=]
>> > static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int
>> > vector)
>> > ^
>> > Debugging with:
>> > https://github.com/ClangBuiltLinux/frame-larger-than
>> > via:
>> > $ python3 frame_larger_than.py arch/x86/kernel/kvm.o \
>> > kvm_send_ipi_mask_allbutself
>> > points to the stack allocated `struct cpumask newmask` in
>> > `kvm_send_ipi_mask_allbutself`. The size of a `struct cpumask` is
>> > potentially large, as it's CONFIG_NR_CPUS divided by BITS_PER_LONG for
>> > the target architecture. CONFIG_NR_CPUS for X86_64 can be as high as
>> > 8192, making a single instance of a `struct cpumask` 1024 B.
>> >
>> > This patch fixes it by pre-allocate 1 cpumask variable per cpu and use it for
>> > both pv tlb and pv ipis..
>> >
>> > Reported-by: Nick Desaulniers <ndesaulniers@google.com>
>> > Acked-by: Nick Desaulniers <ndesaulniers@google.com>
>> > Cc: Peter Zijlstra <peterz@infradead.org>
>> > Cc: Nick Desaulniers <ndesaulniers@google.com>
>> > Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
>> > ---
>> > v1 -> v2:
>> > * remove '!alloc' check
>> > * use new pv check helpers
>> >
>> > arch/x86/kernel/kvm.c | 33 +++++++++++++++++++++------------
>> > 1 file changed, 21 insertions(+), 12 deletions(-)
>> >
>> > diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
>> > index 76ea8c4..377b224 100644
>> > --- a/arch/x86/kernel/kvm.c
>> > +++ b/arch/x86/kernel/kvm.c
>> > @@ -432,6 +432,8 @@ static bool pv_tlb_flush_supported(void)
>> > kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
>> > }
>> >
>> > +static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
>> > +
>> > #ifdef CONFIG_SMP
>> >
>> > static bool pv_ipi_supported(void)
>> > @@ -510,12 +512,12 @@ static void kvm_send_ipi_mask(const struct
>> > cpumask *mask, int vector)
>> > static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask,
>> > int vector)
>> > {
>> > unsigned int this_cpu = smp_processor_id();
>> > - struct cpumask new_mask;
>> > + struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
>> > const struct cpumask *local_mask;
>> >
>> > - cpumask_copy(&new_mask, mask);
>> > - cpumask_clear_cpu(this_cpu, &new_mask);
>> > - local_mask = &new_mask;
>> > + cpumask_copy(new_mask, mask);
>> > + cpumask_clear_cpu(this_cpu, new_mask);
>> > + local_mask = new_mask;
>> > __send_ipi_mask(local_mask, vector);
>> > }
>> >
>> > @@ -595,7 +597,6 @@ static void __init kvm_apf_trap_init(void)
>> > update_intr_gate(X86_TRAP_PF, async_page_fault);
>> > }
>> >
>> > -static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
>> >
>> > static void kvm_flush_tlb_others(const struct cpumask *cpumask,
>> > const struct flush_tlb_info *info)
>> > @@ -603,7 +604,7 @@ static void kvm_flush_tlb_others(const struct
>> > cpumask *cpumask,
>> > u8 state;
>> > int cpu;
>> > struct kvm_steal_time *src;
>> > - struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
>> > + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
>> >
>> > cpumask_copy(flushmask, cpumask);
>> > /*
>> > @@ -642,6 +643,7 @@ static void __init kvm_guest_init(void)
>> > if (pv_tlb_flush_supported()) {
>> > pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
>> > pv_ops.mmu.tlb_remove_table = tlb_remove_table;
>> > + pr_info("KVM setup pv remote TLB flush\n");
>>
>> Nit: to be consistent with __send_ipi_mask() the message should be
>> somthing like
>>
>> "KVM: switch to using PV TLB flush"
>
> There is a lot of native ops we replace by pv ops in kvm.c, I use "KVM
> setup xxx" there, like pv ipis, pv tlb flush, pv sched yield, should
> we keep consistent as before?
>
Oh, I see, it's either one or another :-) Personally, I prefer when
subsystem is delimited with ':' so if we were to change them all I'd
prefer the "KVM: switch to using PV TLB flush" (__send_ipi_mask()
style). But this looks more like a separate patch idea, we can discuss
our personal preferences there :-)
--
Vitaly
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v2 2/2] KVM: Pre-allocate 1 cpumask variable per cpu for both pv tlb and pv ipis
2020-02-17 12:46 ` Vitaly Kuznetsov
@ 2020-02-17 13:15 ` Wanpeng Li
2020-02-17 14:16 ` Vitaly Kuznetsov
0 siblings, 1 reply; 7+ messages in thread
From: Wanpeng Li @ 2020-02-17 13:15 UTC (permalink / raw)
To: Vitaly Kuznetsov
Cc: Paolo Bonzini, Sean Christopherson, Wanpeng Li, Jim Mattson,
Joerg Roedel, LKML, kvm
On Mon, 17 Feb 2020 at 20:46, Vitaly Kuznetsov <vkuznets@redhat.com> wrote:
>
> Wanpeng Li <kernellwp@gmail.com> writes:
>
> > From: Wanpeng Li <wanpengli@tencent.com>
> >
> > Nick Desaulniers Reported:
> >
> > When building with:
> > $ make CC=clang arch/x86/ CFLAGS=-Wframe-larger-than=1000
> > The following warning is observed:
> > arch/x86/kernel/kvm.c:494:13: warning: stack frame size of 1064 bytes in
> > function 'kvm_send_ipi_mask_allbutself' [-Wframe-larger-than=]
> > static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int
> > vector)
> > ^
> > Debugging with:
> > https://github.com/ClangBuiltLinux/frame-larger-than
> > via:
> > $ python3 frame_larger_than.py arch/x86/kernel/kvm.o \
> > kvm_send_ipi_mask_allbutself
> > points to the stack allocated `struct cpumask newmask` in
> > `kvm_send_ipi_mask_allbutself`. The size of a `struct cpumask` is
> > potentially large, as it's CONFIG_NR_CPUS divided by BITS_PER_LONG for
> > the target architecture. CONFIG_NR_CPUS for X86_64 can be as high as
> > 8192, making a single instance of a `struct cpumask` 1024 B.
> >
> > This patch fixes it by pre-allocate 1 cpumask variable per cpu and use it for
> > both pv tlb and pv ipis..
> >
> > Reported-by: Nick Desaulniers <ndesaulniers@google.com>
> > Acked-by: Nick Desaulniers <ndesaulniers@google.com>
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Cc: Nick Desaulniers <ndesaulniers@google.com>
> > Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
> > ---
> > v1 -> v2:
> > * remove '!alloc' check
> > * use new pv check helpers
> >
> > arch/x86/kernel/kvm.c | 33 +++++++++++++++++++++------------
> > 1 file changed, 21 insertions(+), 12 deletions(-)
> >
> > diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> > index 76ea8c4..377b224 100644
> > --- a/arch/x86/kernel/kvm.c
> > +++ b/arch/x86/kernel/kvm.c
> > @@ -432,6 +432,8 @@ static bool pv_tlb_flush_supported(void)
> > kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
> > }
> >
> > +static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
> > +
> > #ifdef CONFIG_SMP
> >
> > static bool pv_ipi_supported(void)
> > @@ -510,12 +512,12 @@ static void kvm_send_ipi_mask(const struct
> > cpumask *mask, int vector)
> > static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask,
> > int vector)
> > {
> > unsigned int this_cpu = smp_processor_id();
> > - struct cpumask new_mask;
> > + struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
> > const struct cpumask *local_mask;
> >
> > - cpumask_copy(&new_mask, mask);
> > - cpumask_clear_cpu(this_cpu, &new_mask);
> > - local_mask = &new_mask;
> > + cpumask_copy(new_mask, mask);
> > + cpumask_clear_cpu(this_cpu, new_mask);
> > + local_mask = new_mask;
> > __send_ipi_mask(local_mask, vector);
> > }
> >
> > @@ -595,7 +597,6 @@ static void __init kvm_apf_trap_init(void)
> > update_intr_gate(X86_TRAP_PF, async_page_fault);
> > }
> >
> > -static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
> >
> > static void kvm_flush_tlb_others(const struct cpumask *cpumask,
> > const struct flush_tlb_info *info)
> > @@ -603,7 +604,7 @@ static void kvm_flush_tlb_others(const struct
> > cpumask *cpumask,
> > u8 state;
> > int cpu;
> > struct kvm_steal_time *src;
> > - struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
> > + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
> >
> > cpumask_copy(flushmask, cpumask);
> > /*
> > @@ -642,6 +643,7 @@ static void __init kvm_guest_init(void)
> > if (pv_tlb_flush_supported()) {
> > pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
> > pv_ops.mmu.tlb_remove_table = tlb_remove_table;
> > + pr_info("KVM setup pv remote TLB flush\n");
>
> Nit: to be consistent with __send_ipi_mask() the message should be
> somthing like
>
> "KVM: switch to using PV TLB flush"
There is a lot of native ops we replace by pv ops in kvm.c, I use "KVM
setup xxx" there, like pv ipis, pv tlb flush, pv sched yield, should
we keep consistent as before?
Wanpeng
>
> > }
> >
> > if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
> > @@ -748,24 +750,31 @@ static __init int activate_jump_labels(void)
> > }
> > arch_initcall(activate_jump_labels);
> >
> > -static __init int kvm_setup_pv_tlb_flush(void)
> > +static __init int kvm_alloc_cpumask(void)
> > {
> > int cpu;
> > + bool alloc = false;
> >
> > if (!kvm_para_available() || nopv)
> > return 0;
> >
> > - if (pv_tlb_flush_supported()) {
> > + if (pv_tlb_flush_supported())
> > + alloc = true;
> > +
> > +#if defined(CONFIG_SMP)
> > + if (pv_ipi_supported())
> > + alloc = true;
> > +#endif
> > +
> > + if (alloc)
> > for_each_possible_cpu(cpu) {
> > - zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
> > + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
> > GFP_KERNEL, cpu_to_node(cpu));
> > }
> > - pr_info("KVM setup pv remote TLB flush\n");
> > - }
> >
> > return 0;
> > }
> > -arch_initcall(kvm_setup_pv_tlb_flush);
> > +arch_initcall(kvm_alloc_cpumask);
> >
> > #ifdef CONFIG_PARAVIRT_SPINLOCKS
> >
> > --
> > 2.7.4
> >
>
> Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
>
> --
> Vitaly
>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v2 2/2] KVM: Pre-allocate 1 cpumask variable per cpu for both pv tlb and pv ipis
2020-02-10 6:38 Wanpeng Li
@ 2020-02-17 12:46 ` Vitaly Kuznetsov
2020-02-17 13:15 ` Wanpeng Li
2020-02-17 17:11 ` Paolo Bonzini
1 sibling, 1 reply; 7+ messages in thread
From: Vitaly Kuznetsov @ 2020-02-17 12:46 UTC (permalink / raw)
To: Wanpeng Li
Cc: Paolo Bonzini, Sean Christopherson, Wanpeng Li, Jim Mattson,
Joerg Roedel, LKML, kvm
Wanpeng Li <kernellwp@gmail.com> writes:
> From: Wanpeng Li <wanpengli@tencent.com>
>
> Nick Desaulniers Reported:
>
> When building with:
> $ make CC=clang arch/x86/ CFLAGS=-Wframe-larger-than=1000
> The following warning is observed:
> arch/x86/kernel/kvm.c:494:13: warning: stack frame size of 1064 bytes in
> function 'kvm_send_ipi_mask_allbutself' [-Wframe-larger-than=]
> static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int
> vector)
> ^
> Debugging with:
> https://github.com/ClangBuiltLinux/frame-larger-than
> via:
> $ python3 frame_larger_than.py arch/x86/kernel/kvm.o \
> kvm_send_ipi_mask_allbutself
> points to the stack allocated `struct cpumask newmask` in
> `kvm_send_ipi_mask_allbutself`. The size of a `struct cpumask` is
> potentially large, as it's CONFIG_NR_CPUS divided by BITS_PER_LONG for
> the target architecture. CONFIG_NR_CPUS for X86_64 can be as high as
> 8192, making a single instance of a `struct cpumask` 1024 B.
>
> This patch fixes it by pre-allocate 1 cpumask variable per cpu and use it for
> both pv tlb and pv ipis..
>
> Reported-by: Nick Desaulniers <ndesaulniers@google.com>
> Acked-by: Nick Desaulniers <ndesaulniers@google.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Nick Desaulniers <ndesaulniers@google.com>
> Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
> ---
> v1 -> v2:
> * remove '!alloc' check
> * use new pv check helpers
>
> arch/x86/kernel/kvm.c | 33 +++++++++++++++++++++------------
> 1 file changed, 21 insertions(+), 12 deletions(-)
>
> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> index 76ea8c4..377b224 100644
> --- a/arch/x86/kernel/kvm.c
> +++ b/arch/x86/kernel/kvm.c
> @@ -432,6 +432,8 @@ static bool pv_tlb_flush_supported(void)
> kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
> }
>
> +static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
> +
> #ifdef CONFIG_SMP
>
> static bool pv_ipi_supported(void)
> @@ -510,12 +512,12 @@ static void kvm_send_ipi_mask(const struct
> cpumask *mask, int vector)
> static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask,
> int vector)
> {
> unsigned int this_cpu = smp_processor_id();
> - struct cpumask new_mask;
> + struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
> const struct cpumask *local_mask;
>
> - cpumask_copy(&new_mask, mask);
> - cpumask_clear_cpu(this_cpu, &new_mask);
> - local_mask = &new_mask;
> + cpumask_copy(new_mask, mask);
> + cpumask_clear_cpu(this_cpu, new_mask);
> + local_mask = new_mask;
> __send_ipi_mask(local_mask, vector);
> }
>
> @@ -595,7 +597,6 @@ static void __init kvm_apf_trap_init(void)
> update_intr_gate(X86_TRAP_PF, async_page_fault);
> }
>
> -static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
>
> static void kvm_flush_tlb_others(const struct cpumask *cpumask,
> const struct flush_tlb_info *info)
> @@ -603,7 +604,7 @@ static void kvm_flush_tlb_others(const struct
> cpumask *cpumask,
> u8 state;
> int cpu;
> struct kvm_steal_time *src;
> - struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
> + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
>
> cpumask_copy(flushmask, cpumask);
> /*
> @@ -642,6 +643,7 @@ static void __init kvm_guest_init(void)
> if (pv_tlb_flush_supported()) {
> pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
> pv_ops.mmu.tlb_remove_table = tlb_remove_table;
> + pr_info("KVM setup pv remote TLB flush\n");
Nit: to be consistent with __send_ipi_mask() the message should be
somthing like
"KVM: switch to using PV TLB flush"
> }
>
> if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
> @@ -748,24 +750,31 @@ static __init int activate_jump_labels(void)
> }
> arch_initcall(activate_jump_labels);
>
> -static __init int kvm_setup_pv_tlb_flush(void)
> +static __init int kvm_alloc_cpumask(void)
> {
> int cpu;
> + bool alloc = false;
>
> if (!kvm_para_available() || nopv)
> return 0;
>
> - if (pv_tlb_flush_supported()) {
> + if (pv_tlb_flush_supported())
> + alloc = true;
> +
> +#if defined(CONFIG_SMP)
> + if (pv_ipi_supported())
> + alloc = true;
> +#endif
> +
> + if (alloc)
> for_each_possible_cpu(cpu) {
> - zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
> + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
> GFP_KERNEL, cpu_to_node(cpu));
> }
> - pr_info("KVM setup pv remote TLB flush\n");
> - }
>
> return 0;
> }
> -arch_initcall(kvm_setup_pv_tlb_flush);
> +arch_initcall(kvm_alloc_cpumask);
>
> #ifdef CONFIG_PARAVIRT_SPINLOCKS
>
> --
> 2.7.4
>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
--
Vitaly
^ permalink raw reply [flat|nested] 7+ messages in thread
* [PATCH v2 2/2] KVM: Pre-allocate 1 cpumask variable per cpu for both pv tlb and pv ipis
@ 2020-02-10 6:38 Wanpeng Li
2020-02-17 12:46 ` Vitaly Kuznetsov
2020-02-17 17:11 ` Paolo Bonzini
0 siblings, 2 replies; 7+ messages in thread
From: Wanpeng Li @ 2020-02-10 6:38 UTC (permalink / raw)
To: LKML, kvm
Cc: Paolo Bonzini, Sean Christopherson, Wanpeng Li, Vitaly Kuznetsov,
Jim Mattson, Joerg Roedel
From: Wanpeng Li <wanpengli@tencent.com>
Nick Desaulniers Reported:
When building with:
$ make CC=clang arch/x86/ CFLAGS=-Wframe-larger-than=1000
The following warning is observed:
arch/x86/kernel/kvm.c:494:13: warning: stack frame size of 1064 bytes in
function 'kvm_send_ipi_mask_allbutself' [-Wframe-larger-than=]
static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int
vector)
^
Debugging with:
https://github.com/ClangBuiltLinux/frame-larger-than
via:
$ python3 frame_larger_than.py arch/x86/kernel/kvm.o \
kvm_send_ipi_mask_allbutself
points to the stack allocated `struct cpumask newmask` in
`kvm_send_ipi_mask_allbutself`. The size of a `struct cpumask` is
potentially large, as it's CONFIG_NR_CPUS divided by BITS_PER_LONG for
the target architecture. CONFIG_NR_CPUS for X86_64 can be as high as
8192, making a single instance of a `struct cpumask` 1024 B.
This patch fixes it by pre-allocate 1 cpumask variable per cpu and use it for
both pv tlb and pv ipis..
Reported-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
v1 -> v2:
* remove '!alloc' check
* use new pv check helpers
arch/x86/kernel/kvm.c | 33 +++++++++++++++++++++------------
1 file changed, 21 insertions(+), 12 deletions(-)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 76ea8c4..377b224 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -432,6 +432,8 @@ static bool pv_tlb_flush_supported(void)
kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
}
+static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
+
#ifdef CONFIG_SMP
static bool pv_ipi_supported(void)
@@ -510,12 +512,12 @@ static void kvm_send_ipi_mask(const struct
cpumask *mask, int vector)
static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask,
int vector)
{
unsigned int this_cpu = smp_processor_id();
- struct cpumask new_mask;
+ struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
const struct cpumask *local_mask;
- cpumask_copy(&new_mask, mask);
- cpumask_clear_cpu(this_cpu, &new_mask);
- local_mask = &new_mask;
+ cpumask_copy(new_mask, mask);
+ cpumask_clear_cpu(this_cpu, new_mask);
+ local_mask = new_mask;
__send_ipi_mask(local_mask, vector);
}
@@ -595,7 +597,6 @@ static void __init kvm_apf_trap_init(void)
update_intr_gate(X86_TRAP_PF, async_page_fault);
}
-static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
static void kvm_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
@@ -603,7 +604,7 @@ static void kvm_flush_tlb_others(const struct
cpumask *cpumask,
u8 state;
int cpu;
struct kvm_steal_time *src;
- struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
+ struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
cpumask_copy(flushmask, cpumask);
/*
@@ -642,6 +643,7 @@ static void __init kvm_guest_init(void)
if (pv_tlb_flush_supported()) {
pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
pv_ops.mmu.tlb_remove_table = tlb_remove_table;
+ pr_info("KVM setup pv remote TLB flush\n");
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -748,24 +750,31 @@ static __init int activate_jump_labels(void)
}
arch_initcall(activate_jump_labels);
-static __init int kvm_setup_pv_tlb_flush(void)
+static __init int kvm_alloc_cpumask(void)
{
int cpu;
+ bool alloc = false;
if (!kvm_para_available() || nopv)
return 0;
- if (pv_tlb_flush_supported()) {
+ if (pv_tlb_flush_supported())
+ alloc = true;
+
+#if defined(CONFIG_SMP)
+ if (pv_ipi_supported())
+ alloc = true;
+#endif
+
+ if (alloc)
for_each_possible_cpu(cpu) {
- zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
+ zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
GFP_KERNEL, cpu_to_node(cpu));
}
- pr_info("KVM setup pv remote TLB flush\n");
- }
return 0;
}
-arch_initcall(kvm_setup_pv_tlb_flush);
+arch_initcall(kvm_alloc_cpumask);
#ifdef CONFIG_PARAVIRT_SPINLOCKS
--
2.7.4
^ permalink raw reply related [flat|nested] 7+ messages in thread
end of thread, other threads:[~2020-02-18 1:23 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-02-11 2:26 [PATCH v2 2/2] KVM: Pre-allocate 1 cpumask variable per cpu for both pv tlb and pv ipis linmiaohe
-- strict thread matches above, loose matches on Subject: below --
2020-02-10 6:38 Wanpeng Li
2020-02-17 12:46 ` Vitaly Kuznetsov
2020-02-17 13:15 ` Wanpeng Li
2020-02-17 14:16 ` Vitaly Kuznetsov
2020-02-17 17:11 ` Paolo Bonzini
2020-02-18 1:23 ` Wanpeng Li
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).