From: Chengming Zhou <[email protected]>
Now we rely on the "frozen" bit to see if we should manipulate the
slab->slab_list, which will be changed in the following patch.
Instead we introduce another way to keep track of whether slub is on
the per-node partial list, here we reuse the PG_workingset bit.
We use __set_bit and __clear_bit directly instead of the atomic version
for better performance and it's safe since it's protected by the slub
node list_lock.
Signed-off-by: Chengming Zhou <[email protected]>
---
mm/slab.h | 19 +++++++++++++++++++
mm/slub.c | 3 +++
2 files changed, 22 insertions(+)
diff --git a/mm/slab.h b/mm/slab.h
index 8cd3294fedf5..50522b688cfb 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -193,6 +193,25 @@ static inline void __slab_clear_pfmemalloc(struct slab *slab)
__folio_clear_active(slab_folio(slab));
}
+/*
+ * Slub reuse PG_workingset bit to keep track of whether it's on
+ * the per-node partial list.
+ */
+static inline bool slab_test_node_partial(const struct slab *slab)
+{
+ return folio_test_workingset((struct folio *)slab_folio(slab));
+}
+
+static inline void slab_set_node_partial(struct slab *slab)
+{
+ __set_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
+}
+
+static inline void slab_clear_node_partial(struct slab *slab)
+{
+ __clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
+}
+
static inline void *slab_address(const struct slab *slab)
{
return folio_address(slab_folio(slab));
diff --git a/mm/slub.c b/mm/slub.c
index 63d281dfacdb..3fad4edca34b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2127,6 +2127,7 @@ __add_partial(struct kmem_cache_node *n, struct slab *slab, int tail)
list_add_tail(&slab->slab_list, &n->partial);
else
list_add(&slab->slab_list, &n->partial);
+ slab_set_node_partial(slab);
}
static inline void add_partial(struct kmem_cache_node *n,
@@ -2141,6 +2142,7 @@ static inline void remove_partial(struct kmem_cache_node *n,
{
lockdep_assert_held(&n->list_lock);
list_del(&slab->slab_list);
+ slab_clear_node_partial(slab);
n->nr_partial--;
}
@@ -4831,6 +4833,7 @@ static int __kmem_cache_do_shrink(struct kmem_cache *s)
if (free == slab->objects) {
list_move(&slab->slab_list, &discard);
+ slab_clear_node_partial(slab);
n->nr_partial--;
dec_slabs_node(s, node, slab->objects);
} else if (free <= SHRINK_PROMOTE_MAX)
--
2.40.1
On 10/24/23 11:33, [email protected] wrote:
> From: Chengming Zhou <[email protected]>
>
> Now we rely on the "frozen" bit to see if we should manipulate the
> slab->slab_list, which will be changed in the following patch.
>
> Instead we introduce another way to keep track of whether slub is on
> the per-node partial list, here we reuse the PG_workingset bit.
>
> We use __set_bit and __clear_bit directly instead of the atomic version
> for better performance and it's safe since it's protected by the slub
> node list_lock.
>
> Signed-off-by: Chengming Zhou <[email protected]>
> ---
> mm/slab.h | 19 +++++++++++++++++++
> mm/slub.c | 3 +++
> 2 files changed, 22 insertions(+)
>
> diff --git a/mm/slab.h b/mm/slab.h
> index 8cd3294fedf5..50522b688cfb 100644
> --- a/mm/slab.h
> +++ b/mm/slab.h
I think these helper might just go to mm/slub.c as nothing else would use them.
> @@ -193,6 +193,25 @@ static inline void __slab_clear_pfmemalloc(struct slab *slab)
> __folio_clear_active(slab_folio(slab));
> }
>
> +/*
> + * Slub reuse PG_workingset bit to keep track of whether it's on
"SLUB reuses" ...
Looks fine otherwise!
> + * the per-node partial list.
> + */
> +static inline bool slab_test_node_partial(const struct slab *slab)
> +{
> + return folio_test_workingset((struct folio *)slab_folio(slab));
> +}
> +
> +static inline void slab_set_node_partial(struct slab *slab)
> +{
> + __set_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
> +}
> +
> +static inline void slab_clear_node_partial(struct slab *slab)
> +{
> + __clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
> +}
> +
> static inline void *slab_address(const struct slab *slab)
> {
> return folio_address(slab_folio(slab));
> diff --git a/mm/slub.c b/mm/slub.c
> index 63d281dfacdb..3fad4edca34b 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -2127,6 +2127,7 @@ __add_partial(struct kmem_cache_node *n, struct slab *slab, int tail)
> list_add_tail(&slab->slab_list, &n->partial);
> else
> list_add(&slab->slab_list, &n->partial);
> + slab_set_node_partial(slab);
> }
>
> static inline void add_partial(struct kmem_cache_node *n,
> @@ -2141,6 +2142,7 @@ static inline void remove_partial(struct kmem_cache_node *n,
> {
> lockdep_assert_held(&n->list_lock);
> list_del(&slab->slab_list);
> + slab_clear_node_partial(slab);
> n->nr_partial--;
> }
>
> @@ -4831,6 +4833,7 @@ static int __kmem_cache_do_shrink(struct kmem_cache *s)
>
> if (free == slab->objects) {
> list_move(&slab->slab_list, &discard);
> + slab_clear_node_partial(slab);
> n->nr_partial--;
> dec_slabs_node(s, node, slab->objects);
> } else if (free <= SHRINK_PROMOTE_MAX)
On 2023/10/27 23:09, Vlastimil Babka wrote:
> On 10/24/23 11:33, [email protected] wrote:
>> From: Chengming Zhou <[email protected]>
>>
>> Now we rely on the "frozen" bit to see if we should manipulate the
>> slab->slab_list, which will be changed in the following patch.
>>
>> Instead we introduce another way to keep track of whether slub is on
>> the per-node partial list, here we reuse the PG_workingset bit.
>>
>> We use __set_bit and __clear_bit directly instead of the atomic version
>> for better performance and it's safe since it's protected by the slub
>> node list_lock.
>>
>> Signed-off-by: Chengming Zhou <[email protected]>
>> ---
>> mm/slab.h | 19 +++++++++++++++++++
>> mm/slub.c | 3 +++
>> 2 files changed, 22 insertions(+)
>>
>> diff --git a/mm/slab.h b/mm/slab.h
>> index 8cd3294fedf5..50522b688cfb 100644
>> --- a/mm/slab.h
>> +++ b/mm/slab.h
>
> I think these helper might just go to mm/slub.c as nothing else would use them.
>
Ok.
>> @@ -193,6 +193,25 @@ static inline void __slab_clear_pfmemalloc(struct slab *slab)
>> __folio_clear_active(slab_folio(slab));
>> }
>>
>> +/*
>> + * Slub reuse PG_workingset bit to keep track of whether it's on
>
> "SLUB reuses" ...
>
> Looks fine otherwise!
>
Will fix it. Thanks!