Re: [RFC PATCH v2 5/5] KVM: Unmap pages only when it's indeed protected for NUMA migration

From: Yan Zhao <yan.y.zhao@intel.com>
To: Sean Christopherson <seanjc@google.com>,
	bibo mao <maobibo@loongson.cn>, <linux-mm@kvack.org>,
	<linux-kernel@vger.kernel.org>, <kvm@vger.kernel.org>,
	<pbonzini@redhat.com>, <mike.kravetz@oracle.com>,
	<apopple@nvidia.com>, <jgg@nvidia.com>, <rppt@kernel.org>,
	<akpm@linux-foundation.org>, <kevin.tian@intel.com>,
	<david@redhat.com>
Subject: Re: [RFC PATCH v2 5/5] KVM: Unmap pages only when it's indeed protected for NUMA migration
Date: Mon, 14 Aug 2023 15:44:54 +0800	[thread overview]
Message-ID: <ZNnbdlKb6Y4L4vMx@yzhao56-desk.sh.intel.com> (raw)
In-Reply-To: <ZNnPF4W26ZbAyGto@yzhao56-desk.sh.intel.com>

On Mon, Aug 14, 2023 at 02:52:07PM +0800, Yan Zhao wrote:
> I wonder if we could loose the frequency to check for rescheduling in
> tdp_mmu_iter_cond_resched() if the zap range is wide, e.g.
> 
> if (iter->next_last_level_gfn ==
>     iter->yielded_gfn + KVM_PAGES_PER_HPAGE(PG_LEVEL_2M))
> 	return false;
Correct:

@@ -712,7 +713,8 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm,
        WARN_ON(iter->yielded);

        /* Ensure forward progress has been made before yielding. */
-       if (iter->next_last_level_gfn == iter->yielded_gfn)
+       if (iter->next_last_level_gfn >= iter->yielded_gfn &&
+          iter->next_last_level_gfn < iter->yielded_gfn + KVM_PAGES_PER_HPAGE(PG_LEVEL_2M))
                return false;

        if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {


This can reduce kvm_flush_remote_tlbs() a lot in one kvm_unmap_gfn_range() in KVM x86 TDP MMU.


