[PATCH v3] gfs2: fix quota init duplicate scan

gfs2_quota_init() checks for duplicate quota_change IDs while holding
qd_lock and the quota hash bucket bitlock. That path used
gfs2_qd_search_bucket(), which takes a lockref reference via
lockref_get_not_dead().

On PREEMPT_RT this may sleep, which is not allowed under the bucket
bitlock, triggering "sleeping function called from invalid context".

Use a no-ref bucket lookup in this path, then continue duplicate
handling without taking a lockref there.

Refactor gfs2_qd_search_bucket() to build on top of the no-ref helper
so lookup traversal stays in one place.

This patch fixes a bug reported by syzbot.

Reported-by: [email protected]
Closes: https://syzkaller.appspot.com/bug?extid=642d0561f78362d67d3f
Tested-by: [email protected]
Signed-off-by: Jie Wang <[email protected]>
---
v3:
- Keep spin_unlock_bucket(hash) in the if (old_qd) path.
- Drop the extra spin_lock_bucket(hash) before insertion.
 
 fs/gfs2/quota.c | 33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 5290865f27f1..934397248fe7 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -254,9 +254,13 @@ static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, str
 	return NULL;
 }
 
-static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash,
-						     const struct gfs2_sbd *sdp,
-						     struct kqid qid)
+/*
+ * Lookup variant for callers which already hold qd_lock + bucket lock.
+ */
+static struct gfs2_quota_data *
+gfs2_qd_search_bucket_noref(unsigned int hash,
+			    const struct gfs2_sbd *sdp,
+			    struct kqid qid)
 {
 	struct gfs2_quota_data *qd;
 	struct hlist_bl_node *h;
@@ -264,12 +268,22 @@ static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash,
 	hlist_bl_for_each_entry_rcu(qd, h, &qd_hash_table[hash], qd_hlist) {
 		if (!qid_eq(qd->qd_id, qid))
 			continue;
-		if (qd->qd_sbd != sdp)
-			continue;
-		if (lockref_get_not_dead(&qd->qd_lockref)) {
-			list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru);
+		if (qd->qd_sbd == sdp)
 			return qd;
-		}
+	}
+
+	return NULL;
+}
+
+static struct gfs2_quota_data *
+gfs2_qd_search_bucket(unsigned int hash, const struct gfs2_sbd *sdp, struct kqid qid)
+{
+	struct gfs2_quota_data *qd;
+
+	qd = gfs2_qd_search_bucket_noref(hash, sdp, qid);
+	if (qd && lockref_get_not_dead(&qd->qd_lockref)) {
+		list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru);
+		return qd;
 	}
 
 	return NULL;
@@ -1458,7 +1472,7 @@ int gfs2_quota_init(struct gfs2_sbd *sdp)
 
 			spin_lock(&qd_lock);
 			spin_lock_bucket(hash);
-			old_qd = gfs2_qd_search_bucket(hash, sdp, qc_id);
+			old_qd = gfs2_qd_search_bucket_noref(hash, sdp, qc_id);
 			if (old_qd) {
 				fs_err(sdp, "Corruption found in quota_change%u"
 					    "file: duplicate identifier in "
@@ -1467,7 +1481,6 @@ int gfs2_quota_init(struct gfs2_sbd *sdp)
 
 				spin_unlock_bucket(hash);
 				spin_unlock(&qd_lock);
-				qd_put(old_qd);
 
 				gfs2_glock_put(qd->qd_gl);
 				kmem_cache_free(gfs2_quotad_cachep, qd);
-- 
2.34.1