diff mbox series

[RFC,v2,1/6] slub: Keep track of whether slub is on the per-node partial list

Message ID 20231021144317.3400916-2-chengming.zhou@linux.dev
State New
Headers
Series slub: Delay freezing of CPU partial slabs |

Commit Message

Chengming Zhou Oct. 21, 2023, 2:43 p.m. UTC 
  From: Chengming Zhou <zhouchengming@bytedance.com>

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.

Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
---
 include/linux/page-flags.h |  2 ++
 mm/slab.h                  | 19 +++++++++++++++++++
 mm/slub.c                  |  3 +++
 3 files changed, 24 insertions(+)

Comments

Matthew Wilcox Oct. 23, 2023, 12:32 p.m. UTC | #1 
On Sat, Oct 21, 2023 at 02:43:12PM +0000, chengming.zhou@linux.dev wrote:
> +++ b/include/linux/page-flags.h
> @@ -478,6 +478,8 @@ PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
>  	TESTCLEARFLAG(Active, active, PF_HEAD)
>  PAGEFLAG(Workingset, workingset, PF_HEAD)
>  	TESTCLEARFLAG(Workingset, workingset, PF_HEAD)
> +	__SETPAGEFLAG(Workingset, workingset, PF_HEAD)
> +	__CLEARPAGEFLAG(Workingset, workingset, PF_HEAD)

This makes me nervous.  The __ versions can only be used when there are
guaranteed to be no other accesses to the flags.  It's never going to
be the case that we want code to call __folio_set_workingset().

_Assuming_ that it's safe to use the non-atomic flag setting, I'd
rather see this done as ...

static inline void slab_set_node_partial(struct slab *slab)
{
	__folio_set_workingset(slab_folio(slab));
	__set_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
}
Matthew Wilcox Oct. 23, 2023, 4:22 p.m. UTC | #2 
On Mon, Oct 23, 2023 at 01:32:27PM +0100, Matthew Wilcox wrote:
> _Assuming_ that it's safe to use the non-atomic flag setting, I'd
> rather see this done as ...
> 
> static inline void slab_set_node_partial(struct slab *slab)
> {
> 	__folio_set_workingset(slab_folio(slab));

Ugh, I meant to delete this line.  I meant to just write the next line.

> 	__set_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
> }
Chengming Zhou Oct. 24, 2023, 1:57 a.m. UTC | #3 
On 2023/10/24 00:22, Matthew Wilcox wrote:
> On Mon, Oct 23, 2023 at 01:32:27PM +0100, Matthew Wilcox wrote:
>> _Assuming_ that it's safe to use the non-atomic flag setting, I'd
>> rather see this done as ...
>>
>> static inline void slab_set_node_partial(struct slab *slab)
>> {
>> 	__folio_set_workingset(slab_folio(slab));
> 
> Ugh, I meant to delete this line.  I meant to just write the next line.
> 
>> 	__set_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
>> }

Yes, it's safe to use the non-atomic version here, since it's protected
by the slub per-node list_lock and we want better performance here.

Ok, will change to directly use __set_bit() and __clear_bit() instead of
polluting the "workingset" interfaces there.

Thanks.
diff mbox series

Patch

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a88e64acebfe..e8b1be71d722 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -478,6 +478,8 @@  PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
 	TESTCLEARFLAG(Active, active, PF_HEAD)
 PAGEFLAG(Workingset, workingset, PF_HEAD)
 	TESTCLEARFLAG(Workingset, workingset, PF_HEAD)
+	__SETPAGEFLAG(Workingset, workingset, PF_HEAD)
+	__CLEARPAGEFLAG(Workingset, workingset, PF_HEAD)
 __PAGEFLAG(Slab, slab, PF_NO_TAIL)
 PAGEFLAG(Checked, checked, PF_NO_COMPOUND)	   /* Used by some filesystems */
 
diff --git a/mm/slab.h b/mm/slab.h
index 8cd3294fedf5..9cff64cae8de 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)
+{
+	__folio_set_workingset(slab_folio(slab));
+}
+
+static inline void slab_clear_node_partial(struct slab *slab)
+{
+	__folio_clear_workingset(slab_folio(slab));
+}
+
 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)