summaryrefslogtreecommitdiff
path: root/virt
diff options
context:
space:
mode:
authorVladimir Davydov <vdavydov@parallels.com>2015-09-09 15:35:41 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-09-10 13:29:01 -0700
commit1d7715c676a1566c2e4c3e77d16b1f9bb4909025 (patch)
tree81d2fb1c256280de7faa19dc2e269b6c8c4bcfc8 /virt
parent80ae2fdceba8313b0433f899bdd9c6c463291a17 (diff)
mmu-notifier: add clear_young callback
In the scope of the idle memory tracking feature, which is introduced by the following patch, we need to clear the referenced/accessed bit not only in primary, but also in secondary ptes. The latter is required in order to estimate wss of KVM VMs. At the same time we want to avoid flushing tlb, because it is quite expensive and it won't really affect the final result. Currently, there is no function for clearing pte young bit that would meet our requirements, so this patch introduces one. To achieve that we have to add a new mmu-notifier callback, clear_young, since there is no method for testing-and-clearing a secondary pte w/o flushing tlb. The new method is not mandatory and currently only implemented by KVM. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com> Acked-by: Paolo Bonzini <pbonzini@redhat.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Greg Thelen <gthelen@google.com> Cc: Michel Lespinasse <walken@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'virt')
-rw-r--r--virt/kvm/kvm_main.c31
1 files changed, 31 insertions, 0 deletions
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d8db2f8fce9c..268fc0a5a932 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -387,6 +387,36 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
return young;
}
+static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int young, idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+ /*
+ * Even though we do not flush TLB, this will still adversely
+ * affect performance on pre-Haswell Intel EPT, where there is
+ * no EPT Access Bit to clear so that we have to tear down EPT
+ * tables instead. If we find this unacceptable, we can always
+ * add a parameter to kvm_age_hva so that it effectively doesn't
+ * do anything on clear_young.
+ *
+ * Also note that currently we never issue secondary TLB flushes
+ * from clear_young, leaving this job up to the regular system
+ * cadence. If we find this inaccurate, we might come up with a
+ * more sophisticated heuristic later.
+ */
+ young = kvm_age_hva(kvm, start, end);
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ return young;
+}
+
static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long address)
@@ -419,6 +449,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
.invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,
.invalidate_range_end = kvm_mmu_notifier_invalidate_range_end,
.clear_flush_young = kvm_mmu_notifier_clear_flush_young,
+ .clear_young = kvm_mmu_notifier_clear_young,
.test_young = kvm_mmu_notifier_test_young,
.change_pte = kvm_mmu_notifier_change_pte,
.release = kvm_mmu_notifier_release,