mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Joseph Qi <joseph.qi@linux.alibaba.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	Mark Fasheh <mark@fasheh.com>, Joel Becker <jlbec@evilplan.org>,
	Heming Zhao <heming.zhao@suse.com>
Cc: ocfs2-devel@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: [PATCH v2 2/3] ocfs2: cluster: avoid lock order inversion in o2hb_region_pin() from drop_item
Date: Wed, 22 Jul 2026 20:49:32 +0800	[thread overview]
Message-ID: <20260722124933.430554-3-joseph.qi@linux.alibaba.com> (raw)
In-Reply-To: <20260722124933.430554-1-joseph.qi@linux.alibaba.com>

o2hb_heartbeat_group_drop_item() is called from configfs rmdir with the
parent directory's inode_lock held.  It calls o2hb_region_pin() ->
o2nm_depend_item() -> configfs_depend_item(), which acquires the configfs
root inode_lock.  This creates a parent -> root inode_lock nesting that
could deadlock against paths taking root -> parent (e.g. subsystem
unregistration).

Fix this by using configfs_depend_item_unlocked() when o2hb_region_pin()
is called from a configfs callback context.  This variant skips the root
inode_lock when caller and target are in the same subsystem, which is
safe because VFS already holds a lock preventing unregistration.

Add o2nm_depend_item_unlocked() wrapper and a from_callback parameter to
o2hb_region_pin() to select the appropriate variant.

Fixes: 58a3158a5d17 ("ocfs2/cluster: Pin/unpin o2hb regions")
Signed-off-by: Joseph Qi <joseph.qi@linux.alibaba.com>
---
 fs/ocfs2/cluster/heartbeat.c   | 17 ++++++++++-------
 fs/ocfs2/cluster/nodemanager.c |  6 ++++++
 fs/ocfs2/cluster/nodemanager.h |  1 +
 3 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 5ca1d9c0c6575..b9395835523e2 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -146,7 +146,7 @@ static unsigned int o2hb_dependent_users;
  * In global heartbeat mode, we pin/unpin all o2hb regions. This solution
  * works for both file system and userdlm domains.
  */
-static int o2hb_region_pin(const char *region_uuid);
+static int o2hb_region_pin(const char *region_uuid, bool from_callback);
 static void o2hb_region_unpin(const char *region_uuid);
 
 /* Only sets a new threshold if there are no active regions.
@@ -2188,7 +2188,7 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group,
 
 	if (bitmap_weight(o2hb_quorum_region_bitmap,
 			   O2NM_MAX_REGIONS) <= O2HB_PIN_CUT_OFF)
-		o2hb_region_pin(NULL);
+		o2hb_region_pin(NULL, true);
 
 unlock:
 	spin_unlock(&o2hb_live_lock);
@@ -2330,7 +2330,7 @@ EXPORT_SYMBOL_GPL(o2hb_setup_callback);
  * In local, we only pin the matching region. In global we pin all the active
  * regions.
  */
-static int o2hb_region_pin(const char *region_uuid)
+static int o2hb_region_pin(const char *region_uuid, bool from_callback)
 {
 	int ret = 0, found;
 	struct o2hb_region *reg, *pinned;
@@ -2385,7 +2385,10 @@ static int o2hb_region_pin(const char *region_uuid)
 		spin_unlock(&o2hb_live_lock);
 
 		/* Ignore ENOENT only for local hb (userdlm domain) */
-		ret = o2nm_depend_item(&pinned->hr_item);
+		if (from_callback)
+			ret = o2nm_depend_item_unlocked(&pinned->hr_item);
+		else
+			ret = o2nm_depend_item(&pinned->hr_item);
 
 		spin_lock(&o2hb_live_lock);
 		if (!ret) {
@@ -2483,8 +2486,8 @@ static int o2hb_region_inc_user(const char *region_uuid)
 
 	/* local heartbeat */
 	if (!o2hb_global_heartbeat_active()) {
-	    ret = o2hb_region_pin(region_uuid);
-	    goto unlock;
+		ret = o2hb_region_pin(region_uuid, false);
+		goto unlock;
 	}
 
 	/*
@@ -2497,7 +2500,7 @@ static int o2hb_region_inc_user(const char *region_uuid)
 
 	if (bitmap_weight(o2hb_quorum_region_bitmap,
 			   O2NM_MAX_REGIONS) <= O2HB_PIN_CUT_OFF)
-		ret = o2hb_region_pin(NULL);
+		ret = o2hb_region_pin(NULL, false);
 
 unlock:
 	spin_unlock(&o2hb_live_lock);
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index e1f8f577ce5d6..ebdf0bdbb8c69 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -778,6 +778,12 @@ int o2nm_depend_item(struct config_item *item)
 	return configfs_depend_item(&o2nm_cluster_group.cs_subsys, item);
 }
 
+int o2nm_depend_item_unlocked(struct config_item *item)
+{
+	return configfs_depend_item_unlocked(&o2nm_cluster_group.cs_subsys,
+					     item);
+}
+
 void o2nm_undepend_item(struct config_item *item)
 {
 	configfs_undepend_item(item);
diff --git a/fs/ocfs2/cluster/nodemanager.h b/fs/ocfs2/cluster/nodemanager.h
index 39006005427b6..ca3483fb54504 100644
--- a/fs/ocfs2/cluster/nodemanager.h
+++ b/fs/ocfs2/cluster/nodemanager.h
@@ -64,6 +64,7 @@ void o2nm_node_get(struct o2nm_node *node);
 void o2nm_node_put(struct o2nm_node *node);
 
 int o2nm_depend_item(struct config_item *item);
+int o2nm_depend_item_unlocked(struct config_item *item);
 void o2nm_undepend_item(struct config_item *item);
 int o2nm_depend_node(u8 node_num);
 void o2nm_undepend_node(u8 node_num);
-- 
2.39.3


  parent reply	other threads:[~2026-07-22 12:49 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-07-22 12:49 [PATCH v2 0/3] ocfs2: cluster: o2hb_region_pin() fixes Joseph Qi
2026-07-22 12:49 ` [PATCH v2 1/3] ocfs2: cluster: don't sleep while holding o2hb_live_lock in o2hb_region_pin() Joseph Qi
2026-07-22 12:49 ` Joseph Qi [this message]
2026-07-22 12:49 ` [PATCH v2 3/3] ocfs2: cluster: fix o2hb_dependent_users leak on pin failure Joseph Qi
2026-07-22 23:43 ` [PATCH v2 0/3] ocfs2: cluster: o2hb_region_pin() fixes Andrew Morton
2026-07-23  1:13   ` Joseph Qi

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=20260722124933.430554-3-joseph.qi@linux.alibaba.com \
    --to=joseph.qi@linux.alibaba.com \
    --cc=akpm@linux-foundation.org \
    --cc=heming.zhao@suse.com \
    --cc=jlbec@evilplan.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark@fasheh.com \
    --cc=ocfs2-devel@lists.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®