From: Paul Mackerras <paulus@samba.org>
To: Alexander Graf <agraf@suse.de>
Cc: linuxppc-dev@ozlabs.org, kvm@vger.kernel.org, kvm-ppc@vger.kernel.org
Subject: [PATCH v3 12/14] KVM: Add barriers to allow mmu_notifier_retry to be used locklessly
Date: Tue, 13 Dec 2011 09:37:21 +1100 [thread overview]
Message-ID: <20111212223720.GM18868@bloggs.ozlabs.ibm.com> (raw)
In-Reply-To: <20111212222347.GA18868@bloggs.ozlabs.ibm.com>
This adds an smp_wmb in kvm_mmu_notifier_invalidate_range_end() and an
smp_rmb in mmu_notifier_retry() so that mmu_notifier_retry() will give
the correct answer when called without kvm->mmu_lock being held.
PowerPC Book3S HV KVM wants to use a bitlock per guest page rather than
a single global spinlock in order to improve the scalability of updates
to the guest MMU hashed page table, and so needs this.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
include/linux/kvm_host.h | 14 +++++++++-----
virt/kvm/kvm_main.c | 6 +++---
2 files changed, 12 insertions(+), 8 deletions(-)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8c5c303..ec79a45 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -700,12 +700,16 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se
if (unlikely(vcpu->kvm->mmu_notifier_count))
return 1;
/*
- * Both reads happen under the mmu_lock and both values are
- * modified under mmu_lock, so there's no need of smb_rmb()
- * here in between, otherwise mmu_notifier_count should be
- * read before mmu_notifier_seq, see
- * mmu_notifier_invalidate_range_end write side.
+ * Ensure the read of mmu_notifier_count happens before the read
+ * of mmu_notifier_seq. This interacts with the smp_wmb() in
+ * mmu_notifier_invalidate_range_end to make sure that the caller
+ * either sees the old (non-zero) value of mmu_notifier_count or
+ * the new (incremented) value of mmu_notifier_seq.
+ * PowerPC Book3s HV KVM calls this under a per-page lock
+ * rather than under kvm->mmu_lock, for scalability, so
+ * can't rely on kvm->mmu_lock to keep things ordered.
*/
+ smp_rmb();
if (vcpu->kvm->mmu_notifier_seq != mmu_seq)
return 1;
return 0;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e289486..c144132 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -357,11 +357,11 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
* been freed.
*/
kvm->mmu_notifier_seq++;
+ smp_wmb();
/*
* The above sequence increase must be visible before the
- * below count decrease but both values are read by the kvm
- * page fault under mmu_lock spinlock so we don't need to add
- * a smb_wmb() here in between the two.
+ * below count decrease, which is ensured by the smp_wmb above
+ * in conjunction with the smp_rmb in mmu_notifier_retry().
*/
kvm->mmu_notifier_count--;
spin_unlock(&kvm->mmu_lock);
--
1.7.7.3
next prev parent reply other threads:[~2011-12-12 22:37 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-12-12 22:23 [PATCH v3 00/14] KVM: PPC: Update Book3S HV memory handling Paul Mackerras
2011-12-12 22:24 ` [PATCH v3 01/14] KVM: PPC: Make wakeups work again for Book3S HV guests Paul Mackerras
2011-12-12 22:26 ` [PATCH v3 02/14] KVM: PPC: Move kvm_vcpu_ioctl_[gs]et_one_reg down to platform-specific code Paul Mackerras
2011-12-12 22:27 ` [PATCH v3 03/14] KVM: PPC: Keep a record of HV guest view of hashed page table entries Paul Mackerras
2011-12-12 22:28 ` [PATCH v3 04/14] KVM: PPC: Keep page physical addresses in per-slot arrays Paul Mackerras
2011-12-19 15:10 ` Alexander Graf
2011-12-12 22:28 ` [PATCH v3 05/14] KVM: PPC: Add an interface for pinning guest pages in Book3s HV guests Paul Mackerras
2011-12-12 22:30 ` [PATCH v3 06/14] KVM: PPC: Make the H_ENTER hcall more reliable Paul Mackerras
2011-12-12 22:31 ` [PATCH v3 07/14] KVM: PPC: Only get pages when actually needed, not in prepare_memory_region() Paul Mackerras
2011-12-12 22:31 ` [PATCH v3 08/14] KVM: PPC: Allow use of small pages to back Book3S HV guests Paul Mackerras
2011-12-12 22:32 ` [PATCH v3 09/14] KVM: PPC: Allow I/O mappings in memory slots Paul Mackerras
2011-12-12 22:33 ` [PATCH v3 10/14] KVM: PPC: Maintain a doubly-linked list of guest HPTEs for each gfn Paul Mackerras
2011-12-12 22:36 ` [PATCH v3 11/14] KVM: PPC: Implement MMIO emulation support for Book3S HV guests Paul Mackerras
2011-12-12 22:37 ` Paul Mackerras [this message]
2011-12-19 17:18 ` [PATCH v3 12/14] KVM: Add barriers to allow mmu_notifier_retry to be used locklessly Alexander Graf
2011-12-19 17:21 ` Avi Kivity
2011-12-12 22:38 ` [PATCH v3 13/14] KVM: PPC: Implement MMU notifiers for Book3S HV guests Paul Mackerras
2011-12-12 22:38 ` [PATCH v3 14/14] KVM: PPC: Allow for read-only pages backing a Book3S HV guest Paul Mackerras
2011-12-19 17:39 ` [PATCH v3 00/14] KVM: PPC: Update Book3S HV memory handling Alexander Graf
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=20111212223720.GM18868@bloggs.ozlabs.ibm.com \
--to=paulus@samba.org \
--cc=agraf@suse.de \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linuxppc-dev@ozlabs.org \
/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).