Re: [PATCH v8 05/14] KVM: Allow range-based TLB invalidation from common code

[Gavin Shan]

On 8/9/23 09:13, Raghavendra Rao Ananta wrote:
> From: David Matlack <dmatlack@xxxxxxxxxx>
>
> Make kvm_flush_remote_tlbs_range() visible in common code and create a
> default implementation that just invalidates the whole TLB.
>
> This paves the way for several future features/cleanups:
>
>   - Introduction of range-based TLBI on ARM.
>   - Eliminating kvm_arch_flush_remote_tlbs_memslot()
>   - Moving the KVM/x86 TDP MMU to common code.
>
> No functional change intended.
>
> Signed-off-by: David Matlack <dmatlack@xxxxxxxxxx>
> Signed-off-by: Raghavendra Rao Ananta <rananta@xxxxxxxxxx>
> Reviewed-by: Gavin Shan <gshan@xxxxxxxxxx>
> Reviewed-by: Shaoqin Huang <shahuang@xxxxxxxxxx>
> Reviewed-by: Anup Patel <anup@xxxxxxxxxxxxxx>
> ---
>   arch/x86/include/asm/kvm_host.h |  2 ++
>   arch/x86/kvm/mmu/mmu.c          |  8 ++++----
>   arch/x86/kvm/mmu/mmu_internal.h |  3 ---
>   include/linux/kvm_host.h        | 12 ++++++++++++
>   virt/kvm/kvm_main.c             | 13 +++++++++++++
>   5 files changed, 31 insertions(+), 7 deletions(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index a2d3cfc2eb75c..b547d17c58f63 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1804,6 +1804,8 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
>   		return -ENOTSUPP;
>   }
>   
> +#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
> +
>   #define kvm_arch_pmi_in_guest(vcpu) \
>   	((vcpu) && (vcpu)->arch.handling_intr_from_guest)
>   
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index ec169f5c7dce2..6adbe6c870982 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -278,16 +278,16 @@ static inline bool kvm_available_flush_remote_tlbs_range(void)
>   	return kvm_x86_ops.flush_remote_tlbs_range;
>   }
>   
> -void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn,
> -				 gfn_t nr_pages)
> +int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn,
> +				      u64 nr_pages)
>   {
>   	int ret = -EOPNOTSUPP;
>   
>   	if (kvm_x86_ops.flush_remote_tlbs_range)
>   		ret = static_call(kvm_x86_flush_remote_tlbs_range)(kvm, start_gfn,
>   								   nr_pages);
> -	if (ret)
> -		kvm_flush_remote_tlbs(kvm);
> +
> +	return ret;
>   }
>   

I guess @start_gfn can be renamed to @gfn, to be consistent with its declaration
in include/linux/kvm_host.h and struct kvm_x86_ops::flush_remote_tlbs_range()

>   static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index);
> diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
> index d39af5639ce97..86cb83bb34804 100644
> --- a/arch/x86/kvm/mmu/mmu_internal.h
> +++ b/arch/x86/kvm/mmu/mmu_internal.h
> @@ -170,9 +170,6 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
>   				    struct kvm_memory_slot *slot, u64 gfn,
>   				    int min_level);
>   
> -void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn,
> -				 gfn_t nr_pages);
> -
>   /* Flush the given page (huge or not) of guest memory. */
>   static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level)
>   {
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index ade5d4500c2ce..f0be5d9c37dd1 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -1359,6 +1359,7 @@ int kvm_vcpu_yield_to(struct kvm_vcpu *target);
>   void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode);
>   
>   void kvm_flush_remote_tlbs(struct kvm *kvm);
> +void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
>   
>   #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
>   int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
> @@ -1488,6 +1489,17 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
>   int kvm_arch_flush_remote_tlbs(struct kvm *kvm);
>   #endif
>   
> +#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
> +static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
> +						    gfn_t gfn, u64 nr_pages)
> +{
> +	return -EOPNOTSUPP;
> +}
> +#else
> +int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
> +				      gfn_t gfn, u64 nr_pages);
> +#endif
> +
>   #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA
>   void kvm_arch_register_noncoherent_dma(struct kvm *kvm);
>   void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm);
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index d6b0507861550..26e91000f579d 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -366,6 +366,19 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
>   }
>   EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
>   
> +void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
> +{
> +	if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages))
> +		return;
> +
> +	/*
> +	 * Fall back to a flushing entire TLBs if the architecture range-based
> +	 * TLB invalidation is unsupported or can't be performed for whatever
> +	 * reason.
> +	 */
> +	kvm_flush_remote_tlbs(kvm);
> +}
> +
>   static void kvm_flush_shadow_all(struct kvm *kvm)
>   {
>   	kvm_arch_flush_shadow_all(kvm);

Thanks,
Gavin