linux-kernel - Re: [PATCH 14/18] KVM: x86/mmu: Stop processing TDP MMU roots for test

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <12ad52ec-f5cc-43ff-9051-040fceeed68b@redhat.com>
Date: Thu, 17 Oct 2024 18:52:33 +0200
From: Paolo Bonzini <pbonzini@...hat.com>
To: Sean Christopherson <seanjc@...gle.com>
Cc: kvm@...r.kernel.org, linux-kernel@...r.kernel.org,
 Yan Zhao <yan.y.zhao@...el.com>, Sagi Shahar <sagis@...gle.com>,
 Alex Bennée <alex.bennee@...aro.org>,
 David Matlack <dmatlack@...gle.com>, James Houghton <jthoughton@...gle.com>
Subject: Re: [PATCH 14/18] KVM: x86/mmu: Stop processing TDP MMU roots for
 test_age if young SPTE found

On 10/11/24 04:10, Sean Christopherson wrote:
> Return immediately if a young SPTE is found when testing, but not updating,
> SPTEs.  The return value is a boolean, i.e. whether there is one young SPTE
> or fifty is irrelevant (ignoring the fact that it's impossible for there to
> be fifty SPTEs, as KVM has a hard limit on the number of valid TDP MMU
> roots).
> 
> Signed-off-by: Sean Christopherson <seanjc@...gle.com>
> ---
>   arch/x86/kvm/mmu/tdp_mmu.c | 84 ++++++++++++++++++--------------------
>   1 file changed, 40 insertions(+), 44 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index e8c061bf94ec..f412bca206c5 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -1192,35 +1192,6 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
>   	return flush;
>   }
>   
> -typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter,
> -			      struct kvm_gfn_range *range);
> -
> -static __always_inline bool kvm_tdp_mmu_handle_gfn(struct kvm *kvm,
> -						   struct kvm_gfn_range *range,
> -						   tdp_handler_t handler)
> -{
> -	struct kvm_mmu_page *root;
> -	struct tdp_iter iter;
> -	bool ret = false;
> -
> -	/*
> -	 * Don't support rescheduling, none of the MMU notifiers that funnel
> -	 * into this helper allow blocking; it'd be dead, wasteful code.  Note,
> -	 * this helper must NOT be used to unmap GFNs, as it processes only
> -	 * valid roots!
> -	 */
> -	for_each_valid_tdp_mmu_root(kvm, root, range->slot->as_id) {
> -		rcu_read_lock();
> -
> -		tdp_root_for_each_leaf_pte(iter, root, range->start, range->end)
> -			ret |= handler(kvm, &iter, range);
> -
> -		rcu_read_unlock();
> -	}
> -
> -	return ret;
> -}
> -
>   /*
>    * Mark the SPTEs range of GFNs [start, end) unaccessed and return non-zero
>    * if any of the GFNs in the range have been accessed.
> @@ -1229,15 +1200,10 @@ static __always_inline bool kvm_tdp_mmu_handle_gfn(struct kvm *kvm,
>    * from the clear_young() or clear_flush_young() notifier, which uses the
>    * return value to determine if the page has been accessed.
>    */
> -static bool age_gfn_range(struct kvm *kvm, struct tdp_iter *iter,
> -			  struct kvm_gfn_range *range)
> +static void kvm_tdp_mmu_age_spte(struct tdp_iter *iter)
>   {
>   	u64 new_spte;
>   
> -	/* If we have a non-accessed entry we don't need to change the pte. */
> -	if (!is_accessed_spte(iter->old_spte))
> -		return false;
> -
>   	if (spte_ad_enabled(iter->old_spte)) {
>   		iter->old_spte = tdp_mmu_clear_spte_bits(iter->sptep,
>   							 iter->old_spte,
> @@ -1253,23 +1219,53 @@ static bool age_gfn_range(struct kvm *kvm, struct tdp_iter *iter,
>   
>   	trace_kvm_tdp_mmu_spte_changed(iter->as_id, iter->gfn, iter->level,
>   				       iter->old_spte, new_spte);
> -	return true;
> +}
> +
> +static bool __kvm_tdp_mmu_age_gfn_range(struct kvm *kvm,
> +					struct kvm_gfn_range *range,
> +					bool test_only)
> +{
> +	struct kvm_mmu_page *root;
> +	struct tdp_iter iter;
> +	bool ret = false;
> +
> +	/*
> +	 * Don't support rescheduling, none of the MMU notifiers that funnel
> +	 * into this helper allow blocking; it'd be dead, wasteful code.  Note,
> +	 * this helper must NOT be used to unmap GFNs, as it processes only
> +	 * valid roots!
> +	 */
> +	for_each_valid_tdp_mmu_root(kvm, root, range->slot->as_id) {
> +		rcu_read_lock();
> +
> +		tdp_root_for_each_leaf_pte(iter, root, range->start, range->end) {
> +			if (!is_accessed_spte(iter.old_spte))
> +				continue;
> +
> +			ret = true;
> +			if (test_only)
> +				break;
> +
> +			kvm_tdp_mmu_age_spte(&iter);
> +		}
> +
> +		rcu_read_unlock();
> +
> +		if (ret && test_only)
> +			break;
> +	}
> +
> +	return ret;
>   }

If you use guard(rcu)() you can avoid the repeated breaks:
  
	for_each_valid_tdp_mmu_root(kvm, root, range->slot->as_id) {
		guard(rcu)();

		tdp_root_for_each_leaf_pte(iter, root, range->start, range->end) {
			if (!is_accessed_spte(iter.old_spte))
				continue;

			ret = true;
			if (test_only)
				return ret;

			kvm_tdp_mmu_age_spte(&iter);
		}
	}

	return ret;

Paolo