linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Lorenzo Stoakes (Oracle)" <ljs@kernel.org>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	 David Hildenbrand <david@kernel.org>,
	Shakeel Butt <shakeel.butt@linux.dev>,
	 Yosry Ahmed <yosry.ahmed@linux.dev>, Zi Yan <ziy@nvidia.com>,
	 "Liam R. Howlett" <Liam.Howlett@oracle.com>,
	Usama Arif <usama.arif@linux.dev>,
	 Kiryl Shutsemau <kas@kernel.org>,
	Dave Chinner <david@fromorbit.com>,
	 Roman Gushchin <roman.gushchin@linux.dev>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 5/7] mm: list_lru: introduce caller locking for additions and deletions
Date: Tue, 24 Mar 2026 11:55:21 +0000	[thread overview]
Message-ID: <a7cbe907-b8dc-4181-8dcb-a0986a09f1a6@lucifer.local> (raw)
In-Reply-To: <20260318200352.1039011-6-hannes@cmpxchg.org>

On Wed, Mar 18, 2026 at 03:53:23PM -0400, Johannes Weiner wrote:
> Locking is currently internal to the list_lru API. However, a caller
> might want to keep auxiliary state synchronized with the LRU state.
>
> For example, the THP shrinker uses the lock of its custom LRU to keep
> PG_partially_mapped and vmstats consistent.
>
> To allow the THP shrinker to switch to list_lru, provide normal and
> irqsafe locking primitives as well as caller-locked variants of the
> addition and deletion functions.
>
> Reviewed-by: David Hildenbrand (Arm) <david@kernel.org>
> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>

Had a good look through the logic, went to write comments more than once then
realised I didn't need to, so LGTM and:

Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>

> ---
>  include/linux/list_lru.h |  34 +++++++++++++
>  mm/list_lru.c            | 107 +++++++++++++++++++++++++++------------
>  2 files changed, 110 insertions(+), 31 deletions(-)
>
> diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
> index fe739d35a864..4afc02deb44d 100644
> --- a/include/linux/list_lru.h
> +++ b/include/linux/list_lru.h
> @@ -83,6 +83,40 @@ int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru,
>  			 gfp_t gfp);
>  void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent);
>
> +/**
> + * list_lru_lock: lock the sublist for the given node and memcg
> + * @lru: the lru pointer
> + * @nid: the node id of the sublist to lock.
> + * @memcg: the cgroup of the sublist to lock.
> + *
> + * Returns the locked list_lru_one sublist. The caller must call
> + * list_lru_unlock() when done.
> + *
> + * You must ensure that the memcg is not freed during this call (e.g., with
> + * rcu or by taking a css refcnt).
> + *
> + * Return: the locked list_lru_one, or NULL on failure
> + */
> +struct list_lru_one *list_lru_lock(struct list_lru *lru, int nid,
> +		struct mem_cgroup *memcg);
> +
> +/**
> + * list_lru_unlock: unlock a sublist locked by list_lru_lock()
> + * @l: the list_lru_one to unlock
> + */
> +void list_lru_unlock(struct list_lru_one *l);
> +
> +struct list_lru_one *list_lru_lock_irqsave(struct list_lru *lru, int nid,
> +		struct mem_cgroup *memcg, unsigned long *irq_flags);
> +void list_lru_unlock_irqrestore(struct list_lru_one *l,
> +		unsigned long *irq_flags);
> +
> +/* Caller-locked variants, see list_lru_add() etc for documentation */
> +bool __list_lru_add(struct list_lru *lru, struct list_lru_one *l,
> +		struct list_head *item, int nid, struct mem_cgroup *memcg);
> +bool __list_lru_del(struct list_lru *lru, struct list_lru_one *l,
> +		struct list_head *item, int nid);
> +
>  /**
>   * list_lru_add: add an element to the lru list's tail
>   * @lru: the lru pointer
> diff --git a/mm/list_lru.c b/mm/list_lru.c
> index 4d74c2e9c2a5..b817c0f48f73 100644
> --- a/mm/list_lru.c
> +++ b/mm/list_lru.c
> @@ -15,17 +15,23 @@
>  #include "slab.h"
>  #include "internal.h"
>
> -static inline void lock_list_lru(struct list_lru_one *l, bool irq)
> +static inline void lock_list_lru(struct list_lru_one *l, bool irq,
> +				 unsigned long *irq_flags)
>  {
> -	if (irq)
> +	if (irq_flags)
> +		spin_lock_irqsave(&l->lock, *irq_flags);
> +	else if (irq)
>  		spin_lock_irq(&l->lock);
>  	else
>  		spin_lock(&l->lock);
>  }
>
> -static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off)
> +static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off,
> +				   unsigned long *irq_flags)
>  {
> -	if (irq_off)
> +	if (irq_flags)
> +		spin_unlock_irqrestore(&l->lock, *irq_flags);
> +	else if (irq_off)
>  		spin_unlock_irq(&l->lock);
>  	else
>  		spin_unlock(&l->lock);
> @@ -78,7 +84,7 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
>
>  static inline struct list_lru_one *
>  lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
> -		       bool irq, bool skip_empty)
> +		       bool irq, unsigned long *irq_flags, bool skip_empty)
>  {
>  	struct list_lru_one *l;
>
> @@ -86,12 +92,12 @@ lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
>  again:
>  	l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
>  	if (likely(l)) {
> -		lock_list_lru(l, irq);
> +		lock_list_lru(l, irq, irq_flags);
>  		if (likely(READ_ONCE(l->nr_items) != LONG_MIN)) {
>  			rcu_read_unlock();
>  			return l;
>  		}
> -		unlock_list_lru(l, irq);
> +		unlock_list_lru(l, irq, irq_flags);
>  	}
>  	/*
>  	 * Caller may simply bail out if raced with reparenting or
> @@ -132,37 +138,81 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
>
>  static inline struct list_lru_one *
>  lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
> -		       bool irq, bool skip_empty)
> +		       bool irq, unsigned long *irq_flags, bool skip_empty)
>  {
>  	struct list_lru_one *l = &lru->node[nid].lru;
>
> -	lock_list_lru(l, irq);
> +	lock_list_lru(l, irq, irq_flags);
>
>  	return l;
>  }
>  #endif /* CONFIG_MEMCG */
>
> -/* The caller must ensure the memcg lifetime. */
> -bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
> -		  struct mem_cgroup *memcg)
> +struct list_lru_one *list_lru_lock(struct list_lru *lru, int nid,
> +				   struct mem_cgroup *memcg)
>  {
> -	struct list_lru_node *nlru = &lru->node[nid];
> -	struct list_lru_one *l;
> +	return lock_list_lru_of_memcg(lru, nid, memcg, /*irq=*/false,
> +				      /*irq_flags=*/NULL, /*skip_empty=*/false);
> +}
> +
> +void list_lru_unlock(struct list_lru_one *l)
> +{
> +	unlock_list_lru(l, /*irq_off=*/false, /*irq_flags=*/NULL);
> +}
> +
> +struct list_lru_one *list_lru_lock_irqsave(struct list_lru *lru, int nid,
> +					   struct mem_cgroup *memcg,
> +					   unsigned long *flags)
> +{
> +	return lock_list_lru_of_memcg(lru, nid, memcg, /*irq=*/true,
> +				      /*irq_flags=*/flags, /*skip_empty=*/false);
> +}
> +
> +void list_lru_unlock_irqrestore(struct list_lru_one *l, unsigned long *flags)
> +{
> +	unlock_list_lru(l, /*irq_off=*/true, /*irq_flags=*/flags);
> +}
>
> -	l = lock_list_lru_of_memcg(lru, nid, memcg, false, false);
> +bool __list_lru_add(struct list_lru *lru, struct list_lru_one *l,
> +		    struct list_head *item, int nid,
> +		    struct mem_cgroup *memcg)
> +{
>  	if (list_empty(item)) {
>  		list_add_tail(item, &l->list);
>  		/* Set shrinker bit if the first element was added */
>  		if (!l->nr_items++)
>  			set_shrinker_bit(memcg, nid, lru_shrinker_id(lru));
> -		unlock_list_lru(l, false);
> -		atomic_long_inc(&nlru->nr_items);
> +		atomic_long_inc(&lru->node[nid].nr_items);
> +		return true;
> +	}
> +	return false;
> +}
> +
> +bool __list_lru_del(struct list_lru *lru, struct list_lru_one *l,
> +		    struct list_head *item, int nid)
> +{
> +	if (!list_empty(item)) {
> +		list_del_init(item);
> +		l->nr_items--;
> +		atomic_long_dec(&lru->node[nid].nr_items);
>  		return true;
>  	}
> -	unlock_list_lru(l, false);
>  	return false;
>  }
>
> +/* The caller must ensure the memcg lifetime. */
> +bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
> +		  struct mem_cgroup *memcg)
> +{
> +	struct list_lru_one *l;
> +	bool ret;
> +
> +	l = list_lru_lock(lru, nid, memcg);
> +	ret = __list_lru_add(lru, l, item, nid, memcg);
> +	list_lru_unlock(l);
> +	return ret;
> +}
> +
>  bool list_lru_add_obj(struct list_lru *lru, struct list_head *item)
>  {
>  	bool ret;
> @@ -184,19 +234,13 @@ EXPORT_SYMBOL_GPL(list_lru_add_obj);
>  bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
>  		  struct mem_cgroup *memcg)
>  {
> -	struct list_lru_node *nlru = &lru->node[nid];
>  	struct list_lru_one *l;
> +	bool ret;
>
> -	l = lock_list_lru_of_memcg(lru, nid, memcg, false, false);
> -	if (!list_empty(item)) {
> -		list_del_init(item);
> -		l->nr_items--;
> -		unlock_list_lru(l, false);
> -		atomic_long_dec(&nlru->nr_items);
> -		return true;
> -	}
> -	unlock_list_lru(l, false);
> -	return false;
> +	l = list_lru_lock(lru, nid, memcg);
> +	ret = __list_lru_del(lru, l, item, nid);
> +	list_lru_unlock(l);
> +	return ret;
>  }
>
>  bool list_lru_del_obj(struct list_lru *lru, struct list_head *item)
> @@ -269,7 +313,8 @@ __list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
>  	unsigned long isolated = 0;
>
>  restart:
> -	l = lock_list_lru_of_memcg(lru, nid, memcg, irq_off, true);
> +	l = lock_list_lru_of_memcg(lru, nid, memcg, /*irq=*/irq_off,
> +				   /*irq_flags=*/NULL, /*skip_empty=*/true);
>  	if (!l)
>  		return isolated;
>  	list_for_each_safe(item, n, &l->list) {
> @@ -310,7 +355,7 @@ __list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
>  			BUG();
>  		}
>  	}
> -	unlock_list_lru(l, irq_off);
> +	unlock_list_lru(l, irq_off, NULL);
>  out:
>  	return isolated;
>  }
> --
> 2.53.0
>


  parent reply	other threads:[~2026-03-24 11:55 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-18 19:53 [PATCH v3 0/7] mm: switch THP shrinker to list_lru Johannes Weiner
2026-03-18 19:53 ` [PATCH v3 1/7] mm: list_lru: lock_list_lru_of_memcg() cannot return NULL if !skip_empty Johannes Weiner
2026-03-18 20:12   ` Shakeel Butt
2026-03-24 11:30   ` Lorenzo Stoakes (Oracle)
2026-03-18 19:53 ` [PATCH v3 2/7] mm: list_lru: deduplicate unlock_list_lru() Johannes Weiner
2026-03-24 11:32   ` Lorenzo Stoakes (Oracle)
2026-03-18 19:53 ` [PATCH v3 3/7] mm: list_lru: move list dead check to lock_list_lru_of_memcg() Johannes Weiner
2026-03-18 20:20   ` Shakeel Butt
2026-03-24 11:34   ` Lorenzo Stoakes (Oracle)
2026-03-18 19:53 ` [PATCH v3 4/7] mm: list_lru: deduplicate lock_list_lru() Johannes Weiner
2026-03-18 20:22   ` Shakeel Butt
2026-03-24 11:36   ` Lorenzo Stoakes (Oracle)
2026-03-18 19:53 ` [PATCH v3 5/7] mm: list_lru: introduce caller locking for additions and deletions Johannes Weiner
2026-03-18 20:51   ` Shakeel Butt
2026-03-20 16:18     ` Johannes Weiner
2026-03-24 11:55   ` Lorenzo Stoakes (Oracle) [this message]
2026-03-18 19:53 ` [PATCH v3 6/7] mm: list_lru: introduce folio_memcg_list_lru_alloc() Johannes Weiner
2026-03-18 20:52   ` Shakeel Butt
2026-03-18 21:01   ` Shakeel Butt
2026-03-24 12:01   ` Lorenzo Stoakes (Oracle)
2026-03-30 16:54     ` Johannes Weiner
2026-04-01 14:43       ` Lorenzo Stoakes (Oracle)
2026-03-18 19:53 ` [PATCH v3 7/7] mm: switch deferred split shrinker to list_lru Johannes Weiner
2026-03-18 20:26   ` David Hildenbrand (Arm)
2026-03-18 23:18   ` Shakeel Butt
2026-03-24 13:48   ` Lorenzo Stoakes (Oracle)
2026-03-30 16:40     ` Johannes Weiner
2026-04-01 17:33       ` Lorenzo Stoakes (Oracle)
2026-04-06 21:37         ` Johannes Weiner
2026-04-07  9:55           ` Lorenzo Stoakes (Oracle)
2026-03-27  7:51   ` Kairui Song
2026-03-30 16:51     ` Johannes Weiner
2026-03-30 16:37   ` [PATCH v3 7/7] mm: switch deferred split shrinker to list_lru - [s390] panic in __memcg_list_lru_alloc Mikhail Zaslonko
2026-03-30 19:03     ` Andrew Morton
2026-03-30 20:41     ` Johannes Weiner
2026-03-30 20:56       ` Johannes Weiner
2026-03-30 22:46         ` Vasily Gorbik
2026-03-31  8:04         ` Mikhail Zaslonko
2026-03-18 21:00 ` [PATCH v3 0/7] mm: switch THP shrinker to list_lru Lorenzo Stoakes (Oracle)
2026-03-18 22:31   ` Johannes Weiner
2026-03-19  8:47     ` Lorenzo Stoakes (Oracle)
2026-03-19  8:52       ` David Hildenbrand (Arm)
2026-03-19 11:45         ` Lorenzo Stoakes (Oracle)

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=a7cbe907-b8dc-4181-8dcb-a0986a09f1a6@lucifer.local \
    --to=ljs@kernel.org \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=david@fromorbit.com \
    --cc=david@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=kas@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=roman.gushchin@linux.dev \
    --cc=shakeel.butt@linux.dev \
    --cc=usama.arif@linux.dev \
    --cc=yosry.ahmed@linux.dev \
    --cc=ziy@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox