mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Qi Zheng <qi.zheng@linux.dev>
To: Chris Mason <mason@kernel.org>,
	hughd@google.com, david@kernel.org,
	baolin.wang@linux.alibaba.com, akpm@linux-foundation.org,
	qinyuntan@linux.alibaba.com, shakeel.butt@linux.dev,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/1] mm/shmem: don't use the memcg of an uncharged folio
Date: Fri, 20 Nov 2026 15:10:36 +0800	[thread overview]
Message-ID: <73a452ad-4346-4f77-a2f6-4c801562c050@linux.dev> (raw)
In-Reply-To: <20261119193656.88678-2-mason@kernel.org>



On 11/20/26 3:36 AM, Chris Mason wrote:
> The shrinker for unused huge tmpfs folios can dereference a NULL memcg
> if it races with the migration of the folio at the end of a file.
> 
> folio_memcg_list_lru_alloc() assumes that folio_memcg() is never NULL.
> But it is NULL until the folio is charged, and a migration target can be
> in the page cache before charging.
> 
> shmem_unused_huge_shrink() looks the folio up without the folio lock,
> so we can race with migration:
> 
>      __migrate_folio()               shmem_unused_huge_shrink()
>      =================               ==========================
>      __folio_migrate_mapping()
>        xas_store(newfolio)
>                                      filemap_get_entry()
>                                        returns newfolio
>                                      folio_trylock() fails
>                                      shmem_unused_huge_requeue()
>                                        folio_memcg_list_lru_alloc()
>                                          folio_memcg() is NULL
>                                          memcg->kmemcg_id
>      folio_migrate_flags()
>        mem_cgroup_migrate()
>          commit_charge(newfolio)

Thanks for catching this!

Some nits below.

> 
> Fix it by keeping the original objcg around while the inode is isolated.
> 
> Fixes: 743e7d025d2f ("mm: shmem: make unused huge shrinker memcg aware")
> Signed-off-by: Chris Mason <mason@kernel.org>
> ---
>   mm/shmem.c | 29 ++++++++++++++++++++++-------
>   1 file changed, 22 insertions(+), 7 deletions(-)
> 
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 10cef89b00b0..4465a43d6f74 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -758,6 +758,13 @@ shmem_unused_huge_alloc_lru(struct shmem_sb_info *sbinfo, struct folio *folio,
>   {
>   	int ret;
>   
> +	/*
> +	 * A migration target is in the page cache before it is charged. Once
> +	 * charged, its objcg can't change while we hold a folio reference.
> +	 */
> +	if (!mem_cgroup_disabled() && !folio_memcg_charged(folio))
> +		return ERR_PTR(-EAGAIN);
> +
>   	ret = folio_memcg_list_lru_alloc(folio, &sbinfo->shrinklist, gfp);
>   	if (ret)
>   		return ERR_PTR(ret);
> @@ -887,12 +894,11 @@ static enum lru_status shmem_unused_huge_isolate(struct list_head *item,
>   		return LRU_REMOVED;
>   	}
>   
> +	/* keep shrinklist_objcg, requeue may need it */
>   	list_lru_isolate(lru, item);
> -	objcg = shmem_get_and_clear_objcg(info);
>   	set_shmem_unused_huge_isolated(info);
>   	list_add_tail(&info->shrinklist, &scan->list);
>   	spin_unlock(&info->lock);
> -	obj_cgroup_put(objcg);
>   
>   	return LRU_REMOVED;
>   }
> @@ -928,32 +934,41 @@ static bool is_shmem_unused_huge_match(struct folio *folio,
>   static void shmem_unused_huge_drop(struct inode *inode)
>   {
>   	struct shmem_inode_info *info = SHMEM_I(inode);
> +	struct obj_cgroup *objcg;
>   
>   	spin_lock(&info->lock);
>   	list_del_init(&info->shrinklist);
> +	objcg = shmem_get_and_clear_objcg(info);
>   	spin_unlock(&info->lock);
> +
> +	obj_cgroup_put(objcg);
>   }
>   
>   static void shmem_unused_huge_requeue(struct inode *inode, struct folio *folio)
>   {
>   	struct shmem_inode_info *info = SHMEM_I(inode);
>   	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
> -	struct obj_cgroup *objcg;
> +	struct obj_cgroup *objcg, *old_objcg;
>   	int nid = folio_nid(folio);
>   
>   	objcg = shmem_unused_huge_alloc_lru(sbinfo, folio, GFP_NOWAIT);
> -	if (IS_ERR(objcg)) {
> -		shmem_unused_huge_drop(inode);
> -		return;
> -	}

Maybe it's better to just return early in the failure path.

How about this:

+static void shmem_unused_huge_requeue_locked(struct shmem_inode_info *info,
+		struct shmem_sb_info *sbinfo, int nid)
+{
+	lockdep_assert_held(&info->lock);
+
+	list_del_init(&info->shrinklist);
+	shmem_unused_huge_lru_add(sbinfo, &info->shrinklist, nid,
+				  info->shrinklist_objcg);
+	info->shrinklist_nid = nid;
  }

  static void shmem_unused_huge_requeue(struct inode *inode, struct 
folio *folio)
@@ -943,17 +975,18 @@ static void shmem_unused_huge_requeue(struct inode 
*inode, struct folio *folio)

  	objcg = shmem_unused_huge_alloc_lru(sbinfo, folio, GFP_NOWAIT);
  	if (IS_ERR(objcg)) {
-		shmem_unused_huge_drop(inode);
+		spin_lock(&info->lock);
+		shmem_unused_huge_requeue_locked(info, sbinfo, nid);
+		spin_unlock(&info->lock);
  		return;
  	}

  	spin_lock(&info->lock);
-	/* Requeue the inode to shrinklist */
-	list_del_init(&info->shrinklist);
-	shmem_unused_huge_lru_add(sbinfo, &info->shrinklist, nid, objcg);
-	info->shrinklist_objcg = objcg;
-	info->shrinklist_nid = nid;
+	swap(info->shrinklist_objcg, objcg);
+	shmem_unused_huge_requeue_locked(info, sbinfo, nid);
  	spin_unlock(&info->lock);
+
+	obj_cgroup_put(objcg);
  }

Thanks,
Qi

>   
>   	spin_lock(&info->lock);
> +	old_objcg = shmem_get_and_clear_objcg(info);
> +	/* The lists for old_objcg exist, the inode was queued under it */
> +	if (IS_ERR(objcg)) {
> +		objcg = old_objcg;
> +		old_objcg = NULL;
> +	}
> +
>   	/* Requeue the inode to shrinklist */
>   	list_del_init(&info->shrinklist);
>   	shmem_unused_huge_lru_add(sbinfo, &info->shrinklist, nid, objcg);
>   	info->shrinklist_objcg = objcg;
>   	info->shrinklist_nid = nid;
>   	spin_unlock(&info->lock);
> +
> +	obj_cgroup_put(old_objcg);
>   }
>   
>   static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,


      reply	other threads:[~2026-11-20  7:10 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-19 19:36 [PATCH 0/1] " Chris Mason
2026-11-19 19:36 ` [PATCH 1/1] " Chris Mason
2026-11-20  7:10   ` Qi Zheng [this message]

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=73a452ad-4346-4f77-a2f6-4c801562c050@linux.dev \
    --to=qi.zheng@linux.dev \
    --cc=akpm@linux-foundation.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=david@kernel.org \
    --cc=hughd@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mason@kernel.org \
    --cc=qinyuntan@linux.alibaba.com \
    --cc=shakeel.butt@linux.dev \
    /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

all inboxes | Powered by JetHome®