The bitmap is provided for secondary MMUs to use if they support it. For
test_young(), after it returns, the bitmap represents the pages that
were young in the interval [start, end). For clear_young, it represents
the pages that we wish the secondary MMU to clear the accessed/young bit
for.
If a bitmap is not provided, the mmu_notifier_{test,clear}_young() API
should be unchanged except that if young PTEs are found and the
architecture supports passing in a bitmap, instead of returning 1,
MMU_NOTIFIER_YOUNG_FAST is returned.
This allows MGLRU's look-around logic to work faster, resulting in a 4%
improvement in real workloads[1]. Also introduce MMU_NOTIFIER_YOUNG_FAST
to indicate to main mm that doing look-around is likely to be
beneficial.
If the secondary MMU doesn't support the bitmap, it must return
an int that contains MMU_NOTIFIER_YOUNG_BITMAP_UNRELIABLE.
[1]: https://lore.kernel.org/all/20230609005935.42390-1-yuz...@google.com/
Suggested-by: Yu Zhao <yuz...@google.com>
Signed-off-by: James Houghton <jthough...@google.com>
---
include/linux/mmu_notifier.h | 93 +++++++++++++++++++++++++++++++++---
include/trace/events/kvm.h | 13 +++--
mm/mmu_notifier.c | 20 +++++---
virt/kvm/kvm_main.c | 19 ++++++--
4 files changed, 123 insertions(+), 22 deletions(-)
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index f349e08a9dfe..daaa9db625d3 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -61,6 +61,10 @@ enum mmu_notifier_event {
#define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
+#define MMU_NOTIFIER_YOUNG (1 << 0)
+#define MMU_NOTIFIER_YOUNG_BITMAP_UNRELIABLE (1 << 1)
+#define MMU_NOTIFIER_YOUNG_FAST (1 << 2)
+
struct mmu_notifier_ops {
/*
* Called either by mmu_notifier_unregister or when the mm is
@@ -106,21 +110,36 @@ struct mmu_notifier_ops {
* 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.
+ *
+ * If @bitmap is given but is not supported, return
+ * MMU_NOTIFIER_YOUNG_BITMAP_UNRELIABLE.
+ *
+ * If the walk is done "quickly" and there were young PTEs,
+ * MMU_NOTIFIER_YOUNG_FAST is returned.
*/
int (*clear_young)(struct mmu_notifier *subscription,
struct mm_struct *mm,
unsigned long start,
- unsigned long end);
+ unsigned long end,
+ unsigned long *bitmap);
/*
* 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
* down the secondary mapping on the page.
+ *
+ * If @bitmap is given but is not supported, return
+ * MMU_NOTIFIER_YOUNG_BITMAP_UNRELIABLE.
+ *
+ * If the walk is done "quickly" and there were young PTEs,
+ * MMU_NOTIFIER_YOUNG_FAST is returned.
*/
int (*test_young)(struct mmu_notifier *subscription,
struct mm_struct *mm,
- unsigned long address);
+ unsigned long start,
+ unsigned long end,
+ unsigned long *bitmap);
/*
* change_pte is called in cases that pte mapping to page is changed:
@@ -388,10 +407,11 @@ 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);
+ unsigned long start, unsigned long end,
+ unsigned long *bitmap);
extern int __mmu_notifier_test_young(struct mm_struct *mm,
- unsigned long address);
+ unsigned long start, unsigned long end,
+ unsigned long *bitmap);
extern void __mmu_notifier_change_pte(struct mm_struct *mm,
unsigned long address, pte_t pte);
extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r);
@@ -427,7 +447,25 @@ static inline int mmu_notifier_clear_young(struct
mm_struct *mm,
unsigned long end)
{
if (mm_has_notifiers(mm))
- return __mmu_notifier_clear_young(mm, start, end);
+ return __mmu_notifier_clear_young(mm, start, end, NULL);
+ return 0;
+}
+
+/*
+ * When @bitmap is not provided, clear the young bits in the secondary
+ * MMUs for all of the pages in the interval [start, end).
+ *
+ * If any subscribed secondary MMU does not support @bitmap, this function
+ * will return an integer containing MMU_NOTIFIER_YOUNG_BITMAP_UNRELIABLE.
+ * Some work may have been done in the secondary MMU.
+ */
+static inline int mmu_notifier_clear_young_bitmap(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end,
+ unsigned long *bitmap)
+{
+ if (mm_has_notifiers(mm))
+ return __mmu_notifier_clear_young(mm, start, end, bitmap);
return 0;
}
@@ -435,7 +473,25 @@ static inline int mmu_notifier_test_young(struct mm_struct
*mm,
unsigned long address)
{
if (mm_has_notifiers(mm))
- return __mmu_notifier_test_young(mm, address);
+ return __mmu_notifier_test_young(mm, address, address + 1,
+ NULL);
+ return 0;
+}
+
+/*
+ * When @bitmap is not provided, test the young bits in the secondary
+ * MMUs for all of the pages in the interval [start, end).
+ *
+ * If any subscribed secondary MMU does not support @bitmap, this function
+ * will return an integer containing MMU_NOTIFIER_YOUNG_BITMAP_UNRELIABLE.
+ */
+static inline int mmu_notifier_test_young_bitmap(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end,
+ unsigned long *bitmap)
+{
+ if (mm_has_notifiers(mm))
+ return __mmu_notifier_test_young(mm, start, end, bitmap);
return 0;
}
@@ -644,12 +700,35 @@ static inline int mmu_notifier_clear_flush_young(struct
mm_struct *mm,
return 0;
}
+static inline int mmu_notifier_clear_young(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ return 0;
+}
+
+static inline int mmu_notifier_clear_young_bitmap(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end,
+ unsigned long *bitmap)
+{
+ return 0;
+}
+
static inline int mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address)
{
return 0;
}
+static inline int mmu_notifier_test_young_bitmap(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end,
+ unsigned long *bitmap)
+{
+ return 0;
+}
+
static inline void mmu_notifier_change_pte(struct mm_struct *mm,
unsigned long address, pte_t pte)
{
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 011fba6b5552..e4ace8cfdbba 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -490,18 +490,21 @@ TRACE_EVENT(kvm_age_hva,
);
TRACE_EVENT(kvm_test_age_hva,
- TP_PROTO(unsigned long hva),
- TP_ARGS(hva),
+ TP_PROTO(unsigned long start, unsigned long end),
+ TP_ARGS(start, end),
TP_STRUCT__entry(
- __field( unsigned long, hva )
+ __field( unsigned long, start )
+ __field( unsigned long, end )
),
TP_fast_assign(
- __entry->hva = hva;
+ __entry->start = start;
+ __entry->end = end;
),
- TP_printk("mmu notifier test age hva: %#016lx", __entry->hva)
+ TP_printk("mmu notifier test age hva: %#016lx -- %#016lx",
+ __entry->start, __entry->end)
);
#endif /* _TRACE_KVM_MAIN_H */
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index ec3b068cbbe6..e70c6222944c 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -384,7 +384,8 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
int __mmu_notifier_clear_young(struct mm_struct *mm,
unsigned long start,
- unsigned long end)
+ unsigned long end,
+ unsigned long *bitmap)
{
struct mmu_notifier *subscription;
int young = 0, id;
@@ -395,7 +396,8 @@ int __mmu_notifier_clear_young(struct mm_struct *mm,
srcu_read_lock_held(&srcu)) {
if (subscription->ops->clear_young)
young |= subscription->ops->clear_young(subscription,
- mm, start, end);
+ mm, start, end,
+ bitmap);
}
srcu_read_unlock(&srcu, id);
@@ -403,7 +405,8 @@ int __mmu_notifier_clear_young(struct mm_struct *mm,
}
int __mmu_notifier_test_young(struct mm_struct *mm,
- unsigned long address)
+ unsigned long start, unsigned long end,
+ unsigned long *bitmap)
{
struct mmu_notifier *subscription;
int young = 0, id;
@@ -413,9 +416,14 @@ int __mmu_notifier_test_young(struct mm_struct *mm,
&mm->notifier_subscriptions->list, hlist,
srcu_read_lock_held(&srcu)) {
if (subscription->ops->test_young) {
- young = subscription->ops->test_young(subscription, mm,
- address);
- if (young)
+ young |= subscription->ops->test_young(subscription, mm,
+ start, end,
+ bitmap);
+ if (young && !bitmap)
+ /*
+ * We're not using a bitmap, so there is no
+ * need to check any more secondary MMUs.
+ */
break;
}
}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fb49c2a60200..ca4b1ef9dfc2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -917,10 +917,15 @@ static int kvm_mmu_notifier_clear_flush_young(struct
mmu_notifier *mn,
static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start,
- unsigned long end)
+ unsigned long end,
+ unsigned long *bitmap)
{
trace_kvm_age_hva(start, end);
+ /* We don't support bitmaps. Don't test or clear anything. */
+ if (bitmap)
+ return MMU_NOTIFIER_YOUNG_BITMAP_UNRELIABLE;
+
/*
* Even though we do not flush TLB, this will still adversely
* affect performance on pre-Haswell Intel EPT, where there is
@@ -939,11 +944,17 @@ static int kvm_mmu_notifier_clear_young(struct
mmu_notifier *mn,
static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
struct mm_struct *mm,
- unsigned long address)
+ unsigned long start,
+ unsigned long end,
+ unsigned long *bitmap)
{
- trace_kvm_test_age_hva(address);
+ trace_kvm_test_age_hva(start, end);
+
+ /* We don't support bitmaps. Don't test or clear anything. */
+ if (bitmap)
+ return MMU_NOTIFIER_YOUNG_BITMAP_UNRELIABLE;
- return kvm_handle_hva_range_no_flush(mn, address, address + 1,
+ return kvm_handle_hva_range_no_flush(mn, start, end,
kvm_test_age_gfn);
}
--
2.44.0.478.gd926399ef9-goog
