All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Matlack <dmatlack@google.com>
To: Ben Gardon <bgardon@google.com>
Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	Paolo Bonzini <pbonzini@redhat.com>, Peter Xu <peterx@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	Peter Shier <pshier@google.com>,
	Mingwei Zhang <mizhang@google.com>,
	Yulei Zhang <yulei.kernel@gmail.com>,
	Wanpeng Li <kernellwp@gmail.com>,
	Xiao Guangrong <xiaoguangrong.eric@gmail.com>,
	Kai Huang <kai.huang@intel.com>,
	Keqian Zhu <zhukeqian1@huawei.com>,
	David Hildenbrand <david@redhat.com>
Subject: Re: [RFC 05/19] KVM: x86/mmu: Remove redundant flushes when disabling dirty logging
Date: Thu, 11 Nov 2021 18:55:34 +0000	[thread overview]
Message-ID: <YY1nJqWpA0KeP2JB@google.com> (raw)
In-Reply-To: <20211110223010.1392399-6-bgardon@google.com>

On Wed, Nov 10, 2021 at 02:29:56PM -0800, Ben Gardon wrote:
> tdp_mmu_zap_spte_atomic flushes on every zap already, so no need to
> flush again after it's done.
> 
> 
> Signed-off-by: Ben Gardon <bgardon@google.com>

Reviewed-by: David Matlack <dmatlack@google.com>

> ---
>  arch/x86/kvm/mmu/mmu.c     |  4 +---
>  arch/x86/kvm/mmu/tdp_mmu.c | 21 ++++++---------------
>  arch/x86/kvm/mmu/tdp_mmu.h |  5 ++---
>  3 files changed, 9 insertions(+), 21 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 354d2ca92df4..baa94acab516 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -5870,9 +5870,7 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
>  
>  	if (is_tdp_mmu_enabled(kvm)) {
>  		read_lock(&kvm->mmu_lock);
> -		flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush);
> -		if (flush)
> -			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
> +		kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot);
>  		read_unlock(&kvm->mmu_lock);
>  	}
>  }
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index c2a9f7acf8ef..1ece645e737f 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -1438,10 +1438,9 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
>   * Clear leaf entries which could be replaced by large mappings, for
>   * GFNs within the slot.
>   */
> -static bool zap_collapsible_spte_range(struct kvm *kvm,
> +static void zap_collapsible_spte_range(struct kvm *kvm,
>  				       struct kvm_mmu_page *root,
> -				       const struct kvm_memory_slot *slot,
> -				       bool flush)
> +				       const struct kvm_memory_slot *slot)
>  {
>  	gfn_t start = slot->base_gfn;
>  	gfn_t end = start + slot->npages;
> @@ -1452,10 +1451,8 @@ static bool zap_collapsible_spte_range(struct kvm *kvm,
>  
>  	tdp_root_for_each_pte(iter, root, start, end) {
>  retry:
> -		if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) {
> -			flush = false;
> +		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
>  			continue;
> -		}
>  
>  		if (!is_shadow_present_pte(iter.old_spte) ||
>  		    !is_last_spte(iter.old_spte, iter.level))
> @@ -1475,30 +1472,24 @@ static bool zap_collapsible_spte_range(struct kvm *kvm,
>  			iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
>  			goto retry;
>  		}
> -		flush = true;
>  	}
>  
>  	rcu_read_unlock();
> -
> -	return flush;
>  }
>  
>  /*
>   * Clear non-leaf entries (and free associated page tables) which could
>   * be replaced by large mappings, for GFNs within the slot.
>   */
> -bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
> -				       const struct kvm_memory_slot *slot,
> -				       bool flush)
> +void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
> +				       const struct kvm_memory_slot *slot)
>  {
>  	struct kvm_mmu_page *root;
>  
>  	lockdep_assert_held_read(&kvm->mmu_lock);
>  
>  	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
> -		flush = zap_collapsible_spte_range(kvm, root, slot, flush);
> -
> -	return flush;
> +		zap_collapsible_spte_range(kvm, root, slot);
>  }
>  
>  /*
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
> index 476b133544dd..3899004a5d91 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.h
> +++ b/arch/x86/kvm/mmu/tdp_mmu.h
> @@ -64,9 +64,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
>  				       struct kvm_memory_slot *slot,
>  				       gfn_t gfn, unsigned long mask,
>  				       bool wrprot);
> -bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
> -				       const struct kvm_memory_slot *slot,
> -				       bool flush);
> +void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
> +				       const struct kvm_memory_slot *slot);
>  
>  bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
>  				   struct kvm_memory_slot *slot, gfn_t gfn,
> -- 
> 2.34.0.rc0.344.g81b53c2807-goog
> 

  reply	other threads:[~2021-11-11 18:55 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-10 22:29 [RFC 00/19] KVM: x86/mmu: Optimize disabling dirty logging Ben Gardon
2021-11-10 22:29 ` [RFC 01/19] KVM: x86/mmu: Fix TLB flush range when handling disconnected pt Ben Gardon
2021-11-11 17:44   ` David Matlack
2021-11-10 22:29 ` [RFC 02/19] KVM: x86/mmu: Batch TLB flushes for a single zap Ben Gardon
2021-11-11 18:06   ` David Matlack
2021-11-12 23:53   ` Sean Christopherson
2021-11-10 22:29 ` [RFC 03/19] KVM: x86/mmu: Factor flush and free up when zapping under MMU write lock Ben Gardon
2021-11-11 18:31   ` David Matlack
2021-11-10 22:29 ` [RFC 04/19] KVM: x86/mmu: Yield while processing disconnected_sps Ben Gardon
2021-11-11 18:50   ` David Matlack
2021-11-10 22:29 ` [RFC 05/19] KVM: x86/mmu: Remove redundant flushes when disabling dirty logging Ben Gardon
2021-11-11 18:55   ` David Matlack [this message]
2021-11-10 22:29 ` [RFC 06/19] KVM: x86/mmu: Introduce vcpu_make_spte Ben Gardon
2021-11-10 22:29 ` [RFC 07/19] KVM: x86/mmu: Factor wrprot for nested PML out of make_spte Ben Gardon
2021-11-18  2:12   ` Sean Christopherson
2021-11-18 17:43     ` Ben Gardon
2021-11-18 18:04       ` Paolo Bonzini
2021-11-10 22:29 ` [RFC 08/19] KVM: x86/mmu: Factor mt_mask " Ben Gardon
2021-11-10 22:30 ` [RFC 09/19] KVM: x86/mmu: Remove need for a vcpu from kvm_slot_page_track_is_active Ben Gardon
2021-11-10 22:30 ` [RFC 10/19] KVM: x86/mmu: Remove need for a vcpu from mmu_try_to_unsync_pages Ben Gardon
2021-11-10 22:30 ` [RFC 11/19] KVM: x86/mmu: Factor shadow_zero_check out of make_spte Ben Gardon
2021-11-10 22:44   ` Paolo Bonzini
2021-11-10 23:49     ` Ben Gardon
2021-11-11  1:18       ` Sean Christopherson
2021-11-11  1:44         ` Sean Christopherson
2021-11-11  7:06         ` Paolo Bonzini
2021-11-18  2:05   ` Sean Christopherson
2021-11-18  3:29     ` Sean Christopherson
2021-11-18 16:37       ` Sean Christopherson
2021-11-18 17:19         ` Paolo Bonzini
2021-11-18 18:02           ` Sean Christopherson
2021-11-18 18:07             ` Paolo Bonzini
2021-11-18 18:14               ` Sean Christopherson
2021-11-10 22:30 ` [RFC 12/19] KVM: x86/mmu: Replace vcpu argument with kvm pointer in make_spte Ben Gardon
2021-11-10 22:30 ` [RFC 13/19] KVM: x86/mmu: Factor out the meat of reset_tdp_shadow_zero_bits_mask Ben Gardon
2021-11-10 22:30 ` [RFC 14/19] KVM: x86/mmu: Propagate memslot const qualifier Ben Gardon
2021-11-10 22:30 ` [RFC 15/19] KVM: x86/MMU: Refactor vmx_get_mt_mask Ben Gardon
2021-11-10 22:30 ` [RFC 16/19] KVM: x86/mmu: Factor out part of vmx_get_mt_mask which does not depend on vcpu Ben Gardon
2021-11-10 22:30 ` [RFC 17/19] KVM: x86/mmu: Add try_get_mt_mask to x86_ops Ben Gardon
2021-11-10 22:30 ` [RFC 18/19] KVM: x86/mmu: Make kvm_is_mmio_pfn usable outside of spte.c Ben Gardon
2021-11-10 22:30 ` [RFC 19/19] KVM: x86/mmu: Promote pages in-place when disabling dirty logging Ben Gardon
2021-11-15 21:24 ` [RFC 00/19] KVM: x86/mmu: Optimize " Ben Gardon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=YY1nJqWpA0KeP2JB@google.com \
    --to=dmatlack@google.com \
    --cc=bgardon@google.com \
    --cc=david@redhat.com \
    --cc=kai.huang@intel.com \
    --cc=kernellwp@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mizhang@google.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=pshier@google.com \
    --cc=seanjc@google.com \
    --cc=xiaoguangrong.eric@gmail.com \
    --cc=yulei.kernel@gmail.com \
    --cc=zhukeqian1@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.