The patch titled
Subject: mmu-notifier: add clear_young callback
has been added to the -mm tree. Its filename is
mmu-notifier-add-clear_young-callback.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mmu-notifier-add-clear_young-callback.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mmu-notifier-add-clear_young-callback.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Subject: 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@xxxxxxxxxxxxx>
Reviewed-by: Andres Lagar-Cavilla <andreslc@xxxxxxxxxx>
Acked-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Raghavendra K T <raghavendra.kt@xxxxxxxxxxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Cc: Greg Thelen <gthelen@xxxxxxxxxx>
Cc: Michel Lespinasse <walken@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Pavel Emelyanov <xemul@xxxxxxxxxxxxx>
Cc: Cyrill Gorcunov <gorcunov@xxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mmu_notifier.h | 44 +++++++++++++++++++++++++++++++++
mm/mmu_notifier.c | 17 ++++++++++++
virt/kvm/kvm_main.c | 18 +++++++++++++
3 files changed, 79 insertions(+)
diff -puN include/linux/mmu_notifier.h~mmu-notifier-add-clear_young-callback include/linux/mmu_notifier.h
--- a/include/linux/mmu_notifier.h~mmu-notifier-add-clear_young-callback
+++ a/include/linux/mmu_notifier.h
@@ -66,6 +66,16 @@ struct mmu_notifier_ops {
unsigned long end);
/*
+ * clear_young is a lightweight version of clear_flush_young. Like the
+ * latter, it is supposed to test-and-clear the young/accessed bitflag
+ * in the secondary pte, but it may omit flushing the secondary tlb.
+ */
+ int (*clear_young)(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end);
+
+ /*
* test_young is called to check the young/accessed bitflag in
* the secondary pte. This is used to know if the page is
* frequently used without actually clearing the flag or tearing
@@ -203,6 +213,9 @@ extern void __mmu_notifier_release(struc
extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
unsigned long start,
unsigned long end);
+extern int __mmu_notifier_clear_young(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end);
extern int __mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address);
extern void __mmu_notifier_change_pte(struct mm_struct *mm,
@@ -231,6 +244,15 @@ static inline int mmu_notifier_clear_flu
return 0;
}
+static inline int mmu_notifier_clear_young(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ if (mm_has_notifiers(mm))
+ return __mmu_notifier_clear_young(mm, start, end);
+ return 0;
+}
+
static inline int mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address)
{
@@ -311,6 +333,28 @@ static inline void mmu_notifier_mm_destr
__young; \
})
+#define ptep_clear_young_notify(__vma, __address, __ptep) \
+({ \
+ int __young; \
+ struct vm_area_struct *___vma = __vma; \
+ unsigned long ___address = __address; \
+ __young = ptep_test_and_clear_young(___vma, ___address, __ptep);\
+ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \
+ ___address + PAGE_SIZE); \
+ __young; \
+})
+
+#define pmdp_clear_young_notify(__vma, __address, __pmdp) \
+({ \
+ int __young; \
+ struct vm_area_struct *___vma = __vma; \
+ unsigned long ___address = __address; \
+ __young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\
+ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \
+ ___address + PMD_SIZE); \
+ __young; \
+})
+
#define ptep_clear_flush_notify(__vma, __address, __ptep) \
({ \
unsigned long ___addr = __address & PAGE_MASK; \
diff -puN mm/mmu_notifier.c~mmu-notifier-add-clear_young-callback mm/mmu_notifier.c
--- a/mm/mmu_notifier.c~mmu-notifier-add-clear_young-callback
+++ a/mm/mmu_notifier.c
@@ -123,6 +123,23 @@ int __mmu_notifier_clear_flush_young(str
return young;
}
+int __mmu_notifier_clear_young(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ struct mmu_notifier *mn;
+ int young = 0, id;
+
+ id = srcu_read_lock(&srcu);
+ hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+ if (mn->ops->clear_young)
+ young |= mn->ops->clear_young(mn, mm, start, end);
+ }
+ srcu_read_unlock(&srcu, id);
+
+ return young;
+}
+
int __mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address)
{
diff -puN virt/kvm/kvm_main.c~mmu-notifier-add-clear_young-callback virt/kvm/kvm_main.c
--- a/virt/kvm/kvm_main.c~mmu-notifier-add-clear_young-callback
+++ a/virt/kvm/kvm_main.c
@@ -387,6 +387,23 @@ static int kvm_mmu_notifier_clear_flush_
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);
+ 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 +436,7 @@ static const struct mmu_notifier_ops kvm
.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,
_
Patches currently in -mm which might be from vdavydov@xxxxxxxxxxxxx are
memcg-export-struct-mem_cgroup.patch
memcg-export-struct-mem_cgroup-fix.patch
memcg-export-struct-mem_cgroup-fix-2.patch
memcg-get-rid-of-mem_cgroup_root_css-for-config_memcg.patch
memcg-get-rid-of-extern-for-functions-in-memcontrolh.patch
memcg-restructure-mem_cgroup_can_attach.patch
memcg-tcp_kmem-check-for-cg_proto-in-sock_update_memcg.patch
memcg-add-page_cgroup_ino-helper.patch
hwpoison-use-page_cgroup_ino-for-filtering-by-memcg.patch
memcg-zap-try_get_mem_cgroup_from_page.patch
proc-add-kpagecgroup-file.patch
mmu-notifier-add-clear_young-callback.patch
proc-add-kpageidle-file.patch
proc-export-idle-flag-via-kpageflags.patch
proc-add-cond_resched-to-proc-kpage-read-write-loop.patch
mm-vmscan-fix-the-page-state-calculation-in-too_many_isolated.patch
mm-swap-zswap-maybe_preload-refactoring.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
