Add a gfp_zero flag to 'struct kvm_mmu_memory_cache' and use it to
control __GFP_ZERO instead of hardcoding a call to kmem_cache_zalloc().
A future patch needs such a flag for the __get_free_page() path, as
gfn arrays do not need/want the allocator to zero the memory. Convert
the kmem_cache paths to __GFP_ZERO now so as to avoid a weird and
inconsistent API in the future.
No functional change intended.
Signed-off-by: Sean Christopherson <[email protected]>
---
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/mmu/mmu.c | 7 ++++++-
2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e7a427547557..fb99e6776e27 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -251,6 +251,7 @@ struct kvm_kernel_irq_routing_entry;
*/
struct kvm_mmu_memory_cache {
int nobjs;
+ gfp_t gfp_zero;
struct kmem_cache *kmem_cache;
void *objects[KVM_NR_MEM_OBJS];
};
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d245acece3cd..6b0ec9060786 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1063,8 +1063,10 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
gfp_t gfp_flags)
{
+ gfp_flags |= mc->gfp_zero;
+
if (mc->kmem_cache)
- return kmem_cache_zalloc(mc->kmem_cache, gfp_flags);
+ return kmem_cache_alloc(mc->kmem_cache, gfp_flags);
else
return (void *)__get_free_page(gfp_flags);
}
@@ -5680,7 +5682,10 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
int ret;
vcpu->arch.mmu_pte_list_desc_cache.kmem_cache = pte_list_desc_cache;
+ vcpu->arch.mmu_pte_list_desc_cache.gfp_zero = __GFP_ZERO;
+
vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache;
+ vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO;
vcpu->arch.mmu = &vcpu->arch.root_mmu;
vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
--
2.26.0
On Fri, Jun 5, 2020 at 2:39 PM Sean Christopherson
<[email protected]> wrote:
>
> Add a gfp_zero flag to 'struct kvm_mmu_memory_cache' and use it to
> control __GFP_ZERO instead of hardcoding a call to kmem_cache_zalloc().
> A future patch needs such a flag for the __get_free_page() path, as
> gfn arrays do not need/want the allocator to zero the memory. Convert
> the kmem_cache paths to __GFP_ZERO now so as to avoid a weird and
> inconsistent API in the future.
>
> No functional change intended.
>
> Signed-off-by: Sean Christopherson <[email protected]>
Reviewed-by: Ben Gardon <[email protected]>
> ---
> arch/x86/include/asm/kvm_host.h | 1 +
> arch/x86/kvm/mmu/mmu.c | 7 ++++++-
> 2 files changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index e7a427547557..fb99e6776e27 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -251,6 +251,7 @@ struct kvm_kernel_irq_routing_entry;
> */
> struct kvm_mmu_memory_cache {
> int nobjs;
> + gfp_t gfp_zero;
This would make more sense to me if it could be used for general extra
gfp flags and was called gfp_flags or something, or it was a boolean
that was later translated into the flag being set. Storing the
gfp_zero flag here is a little counter-intuitive. Probably not worth
changing unless you're sending out a v2 for some other reason.
> struct kmem_cache *kmem_cache;
> void *objects[KVM_NR_MEM_OBJS];
> };
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index d245acece3cd..6b0ec9060786 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -1063,8 +1063,10 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
> static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
> gfp_t gfp_flags)
> {
> + gfp_flags |= mc->gfp_zero;
> +
> if (mc->kmem_cache)
> - return kmem_cache_zalloc(mc->kmem_cache, gfp_flags);
> + return kmem_cache_alloc(mc->kmem_cache, gfp_flags);
> else
> return (void *)__get_free_page(gfp_flags);
> }
> @@ -5680,7 +5682,10 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
> int ret;
>
> vcpu->arch.mmu_pte_list_desc_cache.kmem_cache = pte_list_desc_cache;
> + vcpu->arch.mmu_pte_list_desc_cache.gfp_zero = __GFP_ZERO;
> +
> vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache;
> + vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO;
>
> vcpu->arch.mmu = &vcpu->arch.root_mmu;
> vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
> --
> 2.26.0
>
On Wed, Jun 10, 2020 at 11:57:32AM -0700, Ben Gardon wrote:
> > ---
> > arch/x86/include/asm/kvm_host.h | 1 +
> > arch/x86/kvm/mmu/mmu.c | 7 ++++++-
> > 2 files changed, 7 insertions(+), 1 deletion(-)
> >
> > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> > index e7a427547557..fb99e6776e27 100644
> > --- a/arch/x86/include/asm/kvm_host.h
> > +++ b/arch/x86/include/asm/kvm_host.h
> > @@ -251,6 +251,7 @@ struct kvm_kernel_irq_routing_entry;
> > */
> > struct kvm_mmu_memory_cache {
> > int nobjs;
> > + gfp_t gfp_zero;
> This would make more sense to me if it could be used for general extra
> gfp flags and was called gfp_flags or something, or it was a boolean
> that was later translated into the flag being set. Storing the
> gfp_zero flag here is a little counter-intuitive. Probably not worth
> changing unless you're sending out a v2 for some other reason.
Ideally, this would be a generic gfp_flags field, but that's basically a
non-starter for patch 5, which uses GFP_ATOMIC for the "oh crap the cache
is empty" error handling. Allowing arbitrary flags would be a mess.
I went with storing a full gfp_t because that produces more optimal code.
This isn't a super critical path and it's only a few cycles, but it seems
worthwhile given the frequency with which this code will be called, and
since this happens under mmu_lock.
348 gfp_flags |= mc->gfp_zero;
0x00000000000058ab <+59>: mov 0x4(%rbx),%eax
0x00000000000058ae <+62>: or $0x400cc0,%eax
versus
349 gfp_flags |= __GFP_ZERO;
0x00000000000058a7 <+55>: cmpb $0x1,0x4(%rbx)
0x00000000000058ab <+59>: mov 0x8(%rbx),%rdi <-- unrelated interleaved code
0x00000000000058af <+63>: sbb %eax,%eax
0x00000000000058b1 <+65>: xor %al,%al
0x00000000000058b3 <+67>: add $0x400dc0,%eax