From: James Houghton <jthoughton@google.com>
To: Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
David Matlack <dmatlack@google.com>,
David Rientjes <rientjes@google.com>,
James Houghton <jthoughton@google.com>,
Jason Gunthorpe <jgg@ziepe.ca>, Jonathan Corbet <corbet@lwn.net>,
Marc Zyngier <maz@kernel.org>,
Oliver Upton <oliver.upton@linux.dev>,
Wei Xu <weixugc@google.com>, Yu Zhao <yuzhao@google.com>,
Axel Rasmussen <axelrasmussen@google.com>,
kvm@vger.kernel.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH v7 15/18] KVM: x86/mmu: Locklessly harvest access information from shadow MMU
Date: Thu, 26 Sep 2024 01:35:03 +0000 [thread overview]
Message-ID: <20240926013506.860253-16-jthoughton@google.com> (raw)
In-Reply-To: <20240926013506.860253-1-jthoughton@google.com>
Move where the lock is taken for the shadow MMU case to only take the
lock when !range->arg.fast_only (i.e., for the non-fast_only aging MMU
notifiers).
Signed-off-by: James Houghton <jthoughton@google.com>
---
arch/x86/kvm/mmu/mmu.c | 27 ++++++++++++++++-----------
1 file changed, 16 insertions(+), 11 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index a63497bbcc61..f47bd88b55e3 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1822,16 +1822,24 @@ static bool __kvm_rmap_age_gfn_range(struct kvm *kvm,
static bool kvm_rmap_age_gfn_range(struct kvm *kvm,
struct kvm_gfn_range *range, bool test_only)
{
+ bool young;
+
/*
* We can always locklessly test if an spte is young. Because marking
* non-A/D sptes for access tracking without holding the mmu_lock is
* not currently supported, we cannot always locklessly clear.
+ *
+ * For fast_only, we must not take the mmu_lock, so locklessly age in
+ * that case even though we will not be able to clear the age for
+ * non-A/D sptes.
*/
- if (test_only)
+ if (test_only || range->arg.fast_only)
return kvm_rmap_age_gfn_range_lockless(kvm, range, test_only);
- lockdep_assert_held_write(&kvm->mmu_lock);
- return __kvm_rmap_age_gfn_range(kvm, range, test_only);
+ write_lock(&kvm->mmu_lock);
+ young = __kvm_rmap_age_gfn_range(kvm, range, test_only);
+ write_unlock(&kvm->mmu_lock);
+ return young;
}
static bool kvm_has_shadow_mmu_sptes(struct kvm *kvm)
@@ -1846,11 +1854,8 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
if (tdp_mmu_enabled)
young = kvm_tdp_mmu_age_gfn_range(kvm, range);
- if (kvm_has_shadow_mmu_sptes(kvm)) {
- write_lock(&kvm->mmu_lock);
+ if (kvm_has_shadow_mmu_sptes(kvm))
young |= kvm_rmap_age_gfn_range(kvm, range, false);
- write_unlock(&kvm->mmu_lock);
- }
return young;
}
@@ -1862,11 +1867,11 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
if (tdp_mmu_enabled)
young = kvm_tdp_mmu_test_age_gfn(kvm, range);
- if (!young && kvm_has_shadow_mmu_sptes(kvm)) {
- write_lock(&kvm->mmu_lock);
+ if (young)
+ return young;
+
+ if (kvm_has_shadow_mmu_sptes(kvm))
young |= kvm_rmap_age_gfn_range(kvm, range, true);
- write_unlock(&kvm->mmu_lock);
- }
return young;
}
--
2.46.0.792.g87dc391469-goog
next prev parent reply other threads:[~2024-09-26 1:35 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-26 1:34 [PATCH v7 00/18] mm: multi-gen LRU: Walk secondary MMU page tables while aging James Houghton
2024-09-26 1:34 ` [PATCH v7 01/18] KVM: Remove kvm_handle_hva_range helper functions James Houghton
2024-09-26 1:34 ` [PATCH v7 02/18] KVM: Add lockless memslot walk to KVM James Houghton
2024-09-26 1:34 ` [PATCH v7 03/18] KVM: x86/mmu: Factor out spte atomic bit clearing routine James Houghton
2024-09-26 1:34 ` [PATCH v7 04/18] KVM: x86/mmu: Relax locking for kvm_test_age_gfn and kvm_age_gfn James Houghton
2024-09-26 1:55 ` James Houghton
2024-10-03 20:05 ` James Houghton
2024-09-26 1:34 ` [PATCH v7 05/18] KVM: x86/mmu: Rearrange kvm_{test_,}age_gfn James Houghton
2024-09-26 1:34 ` [PATCH v7 06/18] KVM: x86/mmu: Only check gfn age in shadow MMU if indirect_shadow_pages > 0 James Houghton
2024-09-26 1:34 ` [PATCH v7 07/18] KVM: x86/mmu: Refactor low level rmap helpers to prep for walking w/o mmu_lock James Houghton
2024-09-26 1:34 ` [PATCH v7 08/18] KVM: x86/mmu: Add infrastructure to allow walking rmaps outside of mmu_lock James Houghton
2024-09-26 1:34 ` [PATCH v7 09/18] KVM: x86/mmu: Add support for lockless walks of rmap SPTEs James Houghton
2024-09-26 1:34 ` [PATCH v7 10/18] KVM: x86/mmu: Support rmap walks without holding mmu_lock when aging gfns James Houghton
2024-09-26 1:34 ` [PATCH v7 11/18] mm: Add missing mmu_notifier_clear_young for !MMU_NOTIFIER James Houghton
2024-09-26 1:35 ` [PATCH v7 12/18] mm: Add has_fast_aging to struct mmu_notifier James Houghton
2024-09-26 1:35 ` [PATCH v7 13/18] mm: Add fast_only bool to test_young and clear_young MMU notifiers James Houghton
2024-09-26 1:35 ` [PATCH v7 14/18] KVM: Pass fast_only to kvm_{test_,}age_gfn James Houghton
2024-09-26 1:35 ` James Houghton [this message]
2024-09-26 1:35 ` [PATCH v7 16/18] KVM: x86/mmu: Enable has_fast_aging James Houghton
2024-09-26 1:35 ` [PATCH v7 17/18] mm: multi-gen LRU: Have secondary MMUs participate in aging James Houghton
2024-09-26 1:35 ` [PATCH v7 18/18] KVM: selftests: Add multi-gen LRU aging to access_tracking_perf_test James Houghton
2024-10-14 23:22 ` [PATCH v7 00/18] mm: multi-gen LRU: Walk secondary MMU page tables while aging Sean Christopherson
2024-10-15 0:07 ` James Houghton
2024-10-15 22:47 ` Yu Zhao
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=20240926013506.860253-16-jthoughton@google.com \
--to=jthoughton@google.com \
--cc=akpm@linux-foundation.org \
--cc=axelrasmussen@google.com \
--cc=corbet@lwn.net \
--cc=dmatlack@google.com \
--cc=jgg@ziepe.ca \
--cc=kvm@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=maz@kernel.org \
--cc=oliver.upton@linux.dev \
--cc=pbonzini@redhat.com \
--cc=rientjes@google.com \
--cc=seanjc@google.com \
--cc=weixugc@google.com \
--cc=yuzhao@google.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).