From: Sean Christopherson <sean.j.christopherson@intel.com>
To: "Paolo Bonzini" <pbonzini@redhat.com>,
"Radim Krčmář" <rkrcmar@redhat.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
James Harvey <jamespharvey20@gmail.com>,
Alex Willamson <alex.williamson@redhat.com>
Subject: [PATCH 06/11] KVM: x86/mmu: Revert "Revert "KVM: MMU: zap pages in batch""
Date: Thu, 12 Sep 2019 19:46:07 -0700 [thread overview]
Message-ID: <20190913024612.28392-7-sean.j.christopherson@intel.com> (raw)
In-Reply-To: <20190913024612.28392-1-sean.j.christopherson@intel.com>
Now that the fast invalidate mechanism has been reintroduced, restore
the performance tweaks for fast invalidation that existed prior to its
removal.
Paraphrashing the original changelog:
Zap at least 10 shadow pages before releasing mmu_lock to reduce the
overhead associated with re-acquiring the lock.
Note: "10" is an arbitrary number, speculated to be high enough so
that a vCPU isn't stuck zapping obsolete pages for an extended period,
but small enough so that other vCPUs aren't starved waiting for
mmu_lock.
This reverts commit 43d2b14b105fb00b8864c7b0ee7043cc1cc4a969.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
---
arch/x86/kvm/mmu.c | 35 +++++++++--------------------------
1 file changed, 9 insertions(+), 26 deletions(-)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 0bf20afc3e73..827414b12dbd 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -5670,12 +5670,12 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
return alloc_mmu_pages(vcpu);
}
-
+#define BATCH_ZAP_PAGES 10
static void kvm_zap_obsolete_pages(struct kvm *kvm)
{
struct kvm_mmu_page *sp, *node;
LIST_HEAD(invalid_list);
- int ign;
+ int nr_zapped, batch = 0;
restart:
list_for_each_entry_safe_reverse(sp, node,
@@ -5688,28 +5688,6 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm)
break;
/*
- * Do not repeatedly zap a root page to avoid unnecessary
- * KVM_REQ_MMU_RELOAD, otherwise we may not be able to
- * progress:
- * vcpu 0 vcpu 1
- * call vcpu_enter_guest():
- * 1): handle KVM_REQ_MMU_RELOAD
- * and require mmu-lock to
- * load mmu
- * repeat:
- * 1): zap root page and
- * send KVM_REQ_MMU_RELOAD
- *
- * 2): if (cond_resched_lock(mmu-lock))
- *
- * 2): hold mmu-lock and load mmu
- *
- * 3): see KVM_REQ_MMU_RELOAD bit
- * on vcpu->requests is set
- * then return 1 to call
- * vcpu_enter_guest() again.
- * goto repeat;
- *
* Since we are reversely walking the list and the invalid
* list will be moved to the head, skip the invalid page
* can help us to avoid the infinity list walking.
@@ -5717,14 +5695,19 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm)
if (sp->role.invalid)
continue;
- if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+ if (batch >= BATCH_ZAP_PAGES &&
+ (need_resched() || spin_needbreak(&kvm->mmu_lock))) {
+ batch = 0;
kvm_mmu_commit_zap_page(kvm, &invalid_list);
cond_resched_lock(&kvm->mmu_lock);
goto restart;
}
- if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign))
+ if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list,
+ &nr_zapped)) {
+ batch += nr_zapped;
goto restart;
+ }
}
kvm_mmu_commit_zap_page(kvm, &invalid_list);
--
2.22.0
next prev parent reply other threads:[~2019-09-13 2:46 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-13 2:46 [PATCH 00/11] KVM: x86/mmu: Restore fast invalidate/zap flow Sean Christopherson
2019-09-13 2:46 ` [PATCH 01/11] KVM: x86/mmu: Reintroduce fast invalidate/zap for flushing memslot Sean Christopherson
2019-09-13 2:46 ` [PATCH 02/11] KVM: x86/mmu: Treat invalid shadow pages as obsolete Sean Christopherson
2019-09-13 2:46 ` [PATCH 03/11] KVM: x86/mmu: Use fast invalidate mechanism to zap MMIO sptes Sean Christopherson
2019-09-13 2:46 ` [PATCH 04/11] KVM: x86/mmu: Revert "Revert "KVM: MMU: show mmu_valid_gen in shadow page related tracepoints"" Sean Christopherson
2019-09-13 2:46 ` [PATCH 05/11] KVM: x86/mmu: Revert "Revert "KVM: MMU: add tracepoint for kvm_mmu_invalidate_all_pages"" Sean Christopherson
2019-09-13 2:46 ` Sean Christopherson [this message]
2019-09-13 2:46 ` [PATCH 07/11] KVM: x86/mmu: Revert "Revert "KVM: MMU: collapse TLB flushes when zap all pages"" Sean Christopherson
2019-09-13 2:46 ` [PATCH 08/11] KVM: x86/mmu: Revert "Revert "KVM: MMU: reclaim the zapped-obsolete page first"" Sean Christopherson
2019-09-13 2:46 ` [PATCH 09/11] KVM: x86/mmu: Revert "KVM: x86/mmu: Remove is_obsolete() call" Sean Christopherson
2019-09-13 2:46 ` [PATCH 10/11] KVM: x86/mmu: Explicitly track only a single invalid mmu generation Sean Christopherson
2019-09-13 2:46 ` [PATCH 11/11] KVM: x86/mmu: Skip invalid pages during zapping iff root_count is zero Sean Christopherson
2019-09-13 22:11 ` [PATCH 00/11] KVM: x86/mmu: Restore fast invalidate/zap flow Paolo Bonzini
2019-09-16 17:07 ` Alex Williamson
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=20190913024612.28392-7-sean.j.christopherson@intel.com \
--to=sean.j.christopherson@intel.com \
--cc=alex.williamson@redhat.com \
--cc=jamespharvey20@gmail.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=rkrcmar@redhat.com \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).