Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Imran Khan <imran.f.khan@oracle.com>
To:     tj@kernel.org, viro@zeniv.linux.org.uk, gregkh@linuxfoundation.org
Cc:     matthew.wilcox@oracle.com, konrad.wilk@oracle.com,
        linux-kernel@vger.kernel.org
Subject: [PATCH RESEND v4 2/4] kernfs: Change kernfs_notify_list to llist.
Date:   Thu,  2 Jun 2022 16:39:05 +1000
Message-Id: <20220602063907.136569-3-imran.f.khan@oracle.com>
In-Reply-To: <20220602063907.136569-1-imran.f.khan@oracle.com>
References: <20220602063907.136569-1-imran.f.khan@oracle.com>
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?7wHkL/XWqs8BDNql3F40cwrsIjpEx3RTrs1GT+4glF1c6/c1xaXAZ+o64kx/?=
 =?us-ascii?Q?I+XYF11MX92ceyQ0M2zbgSnBf0uyzRFQ6slseTc7mIqeM7VdcCVxLXQA69p4?=
 =?us-ascii?Q?qaFONBsmF3nUadMfszNh0FJgZQMQ7slP8azbh3ZtVK6TAF+xUpZ5z9BPxXHe?=
 =?us-ascii?Q?Kre9nG/zEZn8Uzpg48qnAV47qrVrdQAcfwKpe23wYENcbCaOWjWR5uFu1zDP?=
 =?us-ascii?Q?zzqFhvJWZYwd7qeVTeLa31ly97jz+CsB9/2qesLcO1c6UYL7khUakJpS80md?=
 =?us-ascii?Q?VQae6IQ/ihETwh8wv0LKDah2CduJgdEx0GDS1p/xbyvbffLnqXQ6RCYG2wGo?=
 =?us-ascii?Q?FknMgZRbEMF2rvbJRzkdkGBN3zgBmTTi7EmicDSJKDwMTV7gn5gcUPorEkJu?=
 =?us-ascii?Q?XMyfsph7yzz29aqoPqbNSD2E+fBU1JodObAQhevQBQPxoq0TCSWg2RipB3z+?=
 =?us-ascii?Q?AYDLqNE84INS0DgDbL+Etpi63pq1nBdm+XUKzlaN4/S/5g5FED1Ae8WFmJOh?=
 =?us-ascii?Q?G2w/2ZOPuztsRrQziKkpPR9BhlF43FI1oggv6/4fd3zBsfwvPqiS+lB/5j2s?=
 =?us-ascii?Q?rFa4nwl9Kl344dDSARQISbcZglD6QviO+GnG9Qr1/fu7FaydKtfLkvi9LZ6k?=
 =?us-ascii?Q?Gu2u7b50vBUzQUH4ggLzpBN8wrQAXuxeQ3urTOzTPv5Jk8wUOu3/xIDuDRXB?=
 =?us-ascii?Q?XLZnilK6Qm9Uhn2t29D3sKHq7Zs0lWkP2fZ4kBY0L98kZBUiPH9Ka+YKW5tD?=
 =?us-ascii?Q?qZT8NcexhjQS85kLU72I0EsFNnuWHAmfwQHjLdaATGpOLfEwxQSZXaLk4tbz?=
 =?us-ascii?Q?WSJ0SZ1rGepzXOzVs5VAWF5gb5ORTM/tLMG+abLt4rjnNSkTq9aMBAY6EHPy?=
 =?us-ascii?Q?NiwAd5T2XGYF98/HKqJO80aZokMbccti+unhFHp8KwdvjvPX69c/TDl6i7j/?=
 =?us-ascii?Q?TqSU1hr/vdJDlhUTDyiQ5KQAfOMckIO5IUndyW28G/wvsB2UEzdNhA20gs93?=
 =?us-ascii?Q?7zR8hUsM51RpmSl1Ij+5liFP+2w6zqlubYweYH39UP58tcBtfECG6E1wFg3d?=
 =?us-ascii?Q?bcn2QSUUPqSGraOsYvYE8BvhU16MoqGRXfVl3E3eItpYbnK2LlzEG848QQnq?=
 =?us-ascii?Q?lU37jwWcumbJzmjv2QKzulYQYjvlazoQZ/+hAayLSJgeGrVEURgAPF7TCD/x?=
 =?us-ascii?Q?QBngQ99+7XIww0XQmmUdFuCiPMbHfkUUXBWwZmdJx1dSNwQFaVejrQ40/n8e?=
 =?us-ascii?Q?XID+plhm1lf6drojjkMAMclt7QPE4ApMFapZ6EiZCalFbh5W5bQDNHlNqrnc?=
 =?us-ascii?Q?EaG67y1WpoTL5voDsv3pZDOqJmxM0V7SR/MSbrhnQFRJuDkan1K09ZoozdZx?=
 =?us-ascii?Q?pt8knzEcRsxARY6UydMvMGNQ8J9Qf6yq0ZEm/EsXllmWSyn1ZKmiYYgMGntS?=
 =?us-ascii?Q?d3/RjC89GdaH/yIFJ6K6WnnOVG0lVqTpQOkJXgXALIHP4YPU6nWs+xXiTMLX?=
 =?us-ascii?Q?QlDdLWOMPJW2tYPBw2muJ/cER+dnLea5N51/2dUOeQpMwSepIdpWQiTFAHgZ?=
 =?us-ascii?Q?KUFw4rv8923milcTr9PPgyy//UJXyD7UuQO0oYQgjKCYYtV58L1twVsu+jhg?=
 =?us-ascii?Q?n3Rp3gvRh9HOyan0XvLJ+ot8C7XjTjdP0mz3XCDc6EAPywTP+VVbLWcl4Xzd?=
 =?us-ascii?Q?5Gog7qizkOftf6zzYMVMw7h+TZB8sLss7e+Rry0ZV5MjZ5xBE/In2DjaFY4Q?=
 =?us-ascii?Q?ik8Mt9CZTk1E9fP8cv2Ag9dCWk/IOyY=3D?=
X-OriginatorOrg: oracle.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 975cfaab-bb2e-427e-3d7e-08da4462a2c0
X-MS-Exchange-CrossTenant-AuthSource: CO1PR10MB4468.namprd10.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 02 Jun 2022 06:39:25.6382
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 4e2c6054-71cb-48f1-bd6c-3a9705aca71b
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: 6Tfjb0aGVphkKsxuW2dxlq/H67d7Qn9U7Bi0q3TPb3vrbc8kVlv4XsqZo1V8ZAm+T5+9oMaJVY+h6WgrmTzb/Q==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: PH0PR10MB5845
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.517,18.0.874
 definitions=2022-06-02_01:2022-06-01,2022-06-02 signatures=0
X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 suspectscore=0 bulkscore=0
 mlxlogscore=999 malwarescore=0 mlxscore=0 spamscore=0 phishscore=0
 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1
 engine=8.12.0-2204290000 definitions=main-2206020024
X-Proofpoint-ORIG-GUID: g7ncAuIb5h74LUzEv8SsMQiguc4qsphs
X-Proofpoint-GUID: g7ncAuIb5h74LUzEv8SsMQiguc4qsphs
X-Spam-Status: No, score=-2.8 required=5.0 tests=BAYES_00,DKIM_SIGNED,
        DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,RCVD_IN_DNSWL_LOW,
        RCVD_IN_MSPIKE_H2,SPF_HELO_NONE,SPF_NONE,T_SCC_BODY_TEXT_LINE
        autolearn=ham autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

At present kernfs_notify_list is implemented as a singly linked
list of kernfs_node(s), where last element points to itself and
value of ->attr.next tells if node is present on the list or not.
Both addition and deletion to list happen under kernfs_notify_lock.

Change kernfs_notify_list to llist so that addition to list can heppen
locklessly. We still need kernfs_notify_lock for consumers (kernfs_notify\
_workfn) because there can be multiple concurrent work items.

Suggested by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Imran Khan <imran.f.khan@oracle.com>
Acked-by: Tejun Heo <tj@kernel.org>
---
 fs/kernfs/file.c       | 47 ++++++++++++++++++------------------------
 include/linux/kernfs.h |  2 +-
 2 files changed, 21 insertions(+), 28 deletions(-)

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 63f1a8f3efb6..b21c8e3b6a8d 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -38,18 +38,16 @@ struct kernfs_open_node {
 	struct list_head	files; /* goes through kernfs_open_file.list */
 };
 
-/*
- * kernfs_notify() may be called from any context and bounces notifications
- * through a work item.  To minimize space overhead in kernfs_node, the
- * pending queue is implemented as a singly linked list of kernfs_nodes.
- * The list is terminated with the self pointer so that whether a
- * kernfs_node is on the list or not can be determined by testing the next
- * pointer for NULL.
+/**
+ * attribute_to_node - get kernfs_node object corresponding to a kernfs attribute
+ * @ptr:	&struct kernfs_elem_attr
+ * @type:	struct kernfs_node
+ * @member:	name of member (i.e attr)
  */
-#define KERNFS_NOTIFY_EOL			((void *)&kernfs_notify_list)
+#define attribute_to_node(ptr, type, member)	\
+	container_of(ptr, type, member)
 
-static DEFINE_SPINLOCK(kernfs_notify_lock);
-static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL;
+static LLIST_HEAD(kernfs_notify_list);
 
 /**
  * kernfs_deref_open_node - Get kernfs_open_node corresponding to @kn.
@@ -928,18 +926,16 @@ static void kernfs_notify_workfn(struct work_struct *work)
 	struct kernfs_node *kn;
 	struct kernfs_super_info *info;
 	struct kernfs_root *root;
+	struct llist_node *free;
+	struct kernfs_elem_attr *attr;
 repeat:
 	/* pop one off the notify_list */
-	spin_lock_irq(&kernfs_notify_lock);
-	kn = kernfs_notify_list;
-	if (kn == KERNFS_NOTIFY_EOL) {
-		spin_unlock_irq(&kernfs_notify_lock);
+	free = llist_del_first(&kernfs_notify_list);
+	if (free == NULL)
 		return;
-	}
-	kernfs_notify_list = kn->attr.notify_next;
-	kn->attr.notify_next = NULL;
-	spin_unlock_irq(&kernfs_notify_lock);
 
+	attr = llist_entry(free, struct kernfs_elem_attr, notify_next);
+	kn = attribute_to_node(attr, struct kernfs_node, attr);
 	root = kernfs_root(kn);
 	/* kick fsnotify */
 	down_write(&root->kernfs_rwsem);
@@ -995,12 +991,14 @@ static void kernfs_notify_workfn(struct work_struct *work)
 void kernfs_notify(struct kernfs_node *kn)
 {
 	static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn);
-	unsigned long flags;
 	struct kernfs_open_node *on;
 
 	if (WARN_ON(kernfs_type(kn) != KERNFS_FILE))
 		return;
 
+	/* Because we are using llist for kernfs_notify_list */
+	WARN_ON_ONCE(in_nmi());
+
 	/* kick poll immediately */
 	rcu_read_lock();
 	on = rcu_dereference(kn->attr.open);
@@ -1011,14 +1009,9 @@ void kernfs_notify(struct kernfs_node *kn)
 	rcu_read_unlock();
 
 	/* schedule work to kick fsnotify */
-	spin_lock_irqsave(&kernfs_notify_lock, flags);
-	if (!kn->attr.notify_next) {
-		kernfs_get(kn);
-		kn->attr.notify_next = kernfs_notify_list;
-		kernfs_notify_list = kn;
-		schedule_work(&kernfs_notify_work);
-	}
-	spin_unlock_irqrestore(&kernfs_notify_lock, flags);
+	kernfs_get(kn);
+	llist_add(&kn->attr.notify_next, &kernfs_notify_list);
+	schedule_work(&kernfs_notify_work);
 }
 EXPORT_SYMBOL_GPL(kernfs_notify);
 
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 13f54f078a52..2dd9c8df0f4f 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -116,7 +116,7 @@ struct kernfs_elem_attr {
 	const struct kernfs_ops	*ops;
 	struct kernfs_open_node __rcu	*open;
 	loff_t			size;
-	struct kernfs_node	*notify_next;	/* for kernfs_notify() */
+	struct llist_node	notify_next;	/* for kernfs_notify() */
 };
 
 /*
-- 
2.30.2