Re: [PATCH v6 01/18] KVM: x86/mmu: Zap invalid roots with mmu_lock held for write at uninit

[Yan Zhao <yan.y.zhao@intel.com>]

On Sun, Dec 22, 2024 at 02:34:28PM -0500, Paolo Bonzini wrote:
> From: Rick Edgecombe <rick.p.edgecombe@intel.com>
> 
> Prepare for a future TDX patch which asserts that atomic zapping
> (i.e. zapping with mmu_lock taken for read) don't operate on mirror roots.
> When tearing down a VM, all roots have to be zapped (including mirro
s/mirro/mirror
> roots once they're in place) so do that with the mmu_lock taken for werite.
s/werite/write

> kvm_mmu_uninit_tdp_mmu() is invoked either before or after executing any
> atomic operations on SPTEs by vCPU threads. Therefore, it will not impact
> vCPU threads performance if kvm_tdp_mmu_zap_invalidated_roots() acquires
> mmu_lock for write to zap invalid roots.
> 
> Co-developed-by: Yan Zhao <yan.y.zhao@intel.com>
> Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
> Message-ID: <20240718211230.1492011-2-rick.p.edgecombe@intel.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>  arch/x86/kvm/mmu/mmu.c     |  2 +-
>  arch/x86/kvm/mmu/tdp_mmu.c | 16 +++++++++++-----
>  arch/x86/kvm/mmu/tdp_mmu.h |  2 +-
>  3 files changed, 13 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 2401606db260..3f749fb5ec6c 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -6467,7 +6467,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
>  	 * lead to use-after-free.
>  	 */
>  	if (tdp_mmu_enabled)
> -		kvm_tdp_mmu_zap_invalidated_roots(kvm);
> +		kvm_tdp_mmu_zap_invalidated_roots(kvm, true);
>  }
>  
>  void kvm_mmu_init_vm(struct kvm *kvm)
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index 2f15e0e33903..1054ccd9b861 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -38,7 +38,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
>  	 * ultimately frees all roots.
>  	 */
>  	kvm_tdp_mmu_invalidate_all_roots(kvm);
> -	kvm_tdp_mmu_zap_invalidated_roots(kvm);
> +	kvm_tdp_mmu_zap_invalidated_roots(kvm, false);
>  
>  	WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
>  	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
> @@ -883,11 +883,14 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
>   * Zap all invalidated roots to ensure all SPTEs are dropped before the "fast
>   * zap" completes.
>   */
> -void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
> +void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared)
>  {
>  	struct kvm_mmu_page *root;
>  
> -	read_lock(&kvm->mmu_lock);
> +	if (shared)
> +		read_lock(&kvm->mmu_lock);
> +	else
> +		write_lock(&kvm->mmu_lock);
>  
>  	for_each_tdp_mmu_root_yield_safe(kvm, root) {
>  		if (!root->tdp_mmu_scheduled_root_to_zap)
> @@ -905,7 +908,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
>  		 * that may be zapped, as such entries are associated with the
>  		 * ASID on both VMX and SVM.
>  		 */
> -		tdp_mmu_zap_root(kvm, root, true);
> +		tdp_mmu_zap_root(kvm, root, shared);
>  
>  		/*
>  		 * The referenced needs to be put *after* zapping the root, as
> @@ -915,7 +918,10 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
>  		kvm_tdp_mmu_put_root(kvm, root);
>  	}
>  
> -	read_unlock(&kvm->mmu_lock);
> +	if (shared)
> +		read_unlock(&kvm->mmu_lock);
> +	else
> +		write_unlock(&kvm->mmu_lock);
>  }
>  
>  /*
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
> index f03ca0dd13d9..6d7cdc462f58 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.h
> +++ b/arch/x86/kvm/mmu/tdp_mmu.h
> @@ -23,7 +23,7 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush);
>  bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
>  void kvm_tdp_mmu_zap_all(struct kvm *kvm);
>  void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
> -void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm);
> +void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared);
>  
>  int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
>  
> -- 
> 2.43.5
> 
>