!1389 [sync] PR-1312: quota: fix race condition between dqput() and dquot_mark_dquot_dirty()

Merge Pull Request from: @openeuler-sync-bot 
 

Origin pull request: 
https://gitee.com/openeuler/kernel/pulls/1312 
 
PR sync from: Baokun Li <libaokun1@huawei.com>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/7ATD3RNUBURBEYA34VGOOZB53J377OZQ/ 
Baokun Li (5):
  quota: factor out dquot_write_dquot()
  quota: rename dquot_active() to inode_quota_active()
  quota: add new helper dquot_active()
  quota: fix dqput() to follow the guarantees dquot_srcu should provide
  quota: simplify drop_dquot_ref()


-- 
2.31.1
 
 
Link:https://gitee.com/openeuler/kernel/pulls/1389 

Reviewed-by: Jialin Zhang <zhangjialin11@huawei.com> 
Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> 

fs/quota/dquot.c

@@ -225,13 +225,22 @@ static void put_quota_format(struct quota_format_type *fmt)
 
 /*
  * Dquot List Management:
- * The quota code uses four lists for dquot management: the inuse_list,
- * free_dquots, dqi_dirty_list, and dquot_hash[] array. A single dquot
- * structure may be on some of those lists, depending on its current state.
+ * The quota code uses five lists for dquot management: the inuse_list,
+ * releasing_dquots, free_dquots, dqi_dirty_list, and dquot_hash[] array.
+ * A single dquot structure may be on some of those lists, depending on
+ * its current state.
  *
  * All dquots are placed to the end of inuse_list when first created, and this
  * list is used for invalidate operation, which must look at every dquot.
  *
+ * When the last reference of a dquot will be dropped, the dquot will be
+ * added to releasing_dquots. We'd then queue work item which would call
+ * synchronize_srcu() and after that perform the final cleanup of all the
+ * dquots on the list. Both releasing_dquots and free_dquots use the
+ * dq_free list_head in the dquot struct. When a dquot is removed from
+ * releasing_dquots, a reference count is always subtracted, and if
+ * dq_count == 0 at that point, the dquot will be added to the free_dquots.
+ *
  * Unused dquots (dq_count == 0) are added to the free_dquots list when freed,
  * and this list is searched whenever we need an available dquot.  Dquots are
  * removed from the list as soon as they are used again, and
@@ -250,6 +259,7 @@ static void put_quota_format(struct quota_format_type *fmt)
 
 static LIST_HEAD(inuse_list);
 static LIST_HEAD(free_dquots);
+static LIST_HEAD(releasing_dquots);
 static unsigned int dq_hash_bits, dq_hash_mask;
 static struct hlist_head *dquot_hash;
 
@@ -260,6 +270,9 @@ static qsize_t inode_get_rsv_space(struct inode *inode);
 static qsize_t __inode_get_rsv_space(struct inode *inode);
 static int __dquot_initialize(struct inode *inode, int type);
 
+static void quota_release_workfn(struct work_struct *work);
+static DECLARE_DELAYED_WORK(quota_release_work, quota_release_workfn);
+
 static inline unsigned int
 hashfn(const struct super_block *sb, struct kqid qid)
 {
@@ -307,12 +320,18 @@ static inline void put_dquot_last(struct dquot *dquot)
 	dqstats_inc(DQST_FREE_DQUOTS);
 }
 
+static inline void put_releasing_dquots(struct dquot *dquot)
+{
+	list_add_tail(&dquot->dq_free, &releasing_dquots);
+}
+
 static inline void remove_free_dquot(struct dquot *dquot)
 {
 	if (list_empty(&dquot->dq_free))
 		return;
 	list_del_init(&dquot->dq_free);
-	dqstats_dec(DQST_FREE_DQUOTS);
+	if (!atomic_read(&dquot->dq_count))
+		dqstats_dec(DQST_FREE_DQUOTS);
 }
 
 static inline void put_inuse(struct dquot *dquot)
@@ -338,6 +357,11 @@ static void wait_on_dquot(struct dquot *dquot)
 	mutex_unlock(&dquot->dq_lock);
 }
 
+static inline int dquot_active(struct dquot *dquot)
+{
+	return test_bit(DQ_ACTIVE_B, &dquot->dq_flags);
+}
+
 static inline int dquot_dirty(struct dquot *dquot)
 {
 	return test_bit(DQ_MOD_B, &dquot->dq_flags);
@@ -353,14 +377,14 @@ int dquot_mark_dquot_dirty(struct dquot *dquot)
 {
 	int ret = 1;
 
-	if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags))
+	if (!dquot_active(dquot))
 		return 0;
 
 	if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY)
 		return test_and_set_bit(DQ_MOD_B, &dquot->dq_flags);
 
 	/* If quota is dirty already, we don't have to acquire dq_list_lock */
-	if (test_bit(DQ_MOD_B, &dquot->dq_flags))
+	if (dquot_dirty(dquot))
 		return 1;
 
 	spin_lock(&dq_list_lock);
@@ -442,7 +466,7 @@ int dquot_acquire(struct dquot *dquot)
 	smp_mb__before_atomic();
 	set_bit(DQ_READ_B, &dquot->dq_flags);
 	/* Instantiate dquot if needed */
-	if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && !dquot->dq_off) {
+	if (!dquot_active(dquot) && !dquot->dq_off) {
 		ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot);
 		/* Write the info if needed */
 		if (info_dirty(&dqopt->info[dquot->dq_id.type])) {
@@ -484,7 +508,7 @@ int dquot_commit(struct dquot *dquot)
 		goto out_lock;
 	/* Inactive dquot can be only if there was error during read/init
 	 * => we have better not writing it */
-	if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags))
+	if (dquot_active(dquot))
 		ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot);
 	else
 		ret = -EIO;
@@ -549,6 +573,8 @@ static void invalidate_dquots(struct super_block *sb, int type)
 	struct dquot *dquot, *tmp;
 
 restart:
+	flush_delayed_work(&quota_release_work);
+
 	spin_lock(&dq_list_lock);
 	list_for_each_entry_safe(dquot, tmp, &inuse_list, dq_inuse) {
 		if (dquot->dq_sb != sb)
@@ -557,6 +583,12 @@ static void invalidate_dquots(struct super_block *sb, int type)
 			continue;
 		/* Wait for dquot users */
 		if (atomic_read(&dquot->dq_count)) {
+			/* dquot in releasing_dquots, flush and retry */
+			if (!list_empty(&dquot->dq_free)) {
+				spin_unlock(&dq_list_lock);
+				goto restart;
+			}
+
 			dqgrab(dquot);
 			spin_unlock(&dq_list_lock);
 			/*
@@ -599,7 +631,7 @@ int dquot_scan_active(struct super_block *sb,
 
 	spin_lock(&dq_list_lock);
 	list_for_each_entry(dquot, &inuse_list, dq_inuse) {
-		if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags))
+		if (!dquot_active(dquot))
 			continue;
 		if (dquot->dq_sb != sb)
 			continue;
@@ -614,7 +646,7 @@ int dquot_scan_active(struct super_block *sb,
 		 * outstanding call and recheck the DQ_ACTIVE_B after that.
 		 */
 		wait_on_dquot(dquot);
-		if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+		if (dquot_active(dquot)) {
 			ret = fn(dquot, priv);
 			if (ret < 0)
 				goto out;
@@ -630,6 +662,18 @@ int dquot_scan_active(struct super_block *sb,
 }
 EXPORT_SYMBOL(dquot_scan_active);
 
+static inline int dquot_write_dquot(struct dquot *dquot)
+{
+	int ret = dquot->dq_sb->dq_op->write_dquot(dquot);
+	if (ret < 0) {
+		quota_error(dquot->dq_sb, "Can't write quota structure "
+			    "(error %d). Quota may get out of sync!", ret);
+		/* Clear dirty bit anyway to avoid infinite loop. */
+		clear_dquot_dirty(dquot);
+	}
+	return ret;
+}
+
 /* Write all dquot structures to quota files */
 int dquot_writeback_dquots(struct super_block *sb, int type)
 {
@@ -653,23 +697,16 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
 			dquot = list_first_entry(&dirty, struct dquot,
 						 dq_dirty);
 
-			WARN_ON(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags));
+			WARN_ON(!dquot_active(dquot));
 
 			/* Now we have active dquot from which someone is
  			 * holding reference so we can safely just increase
 			 * use count */
 			dqgrab(dquot);
 			spin_unlock(&dq_list_lock);
-			err = sb->dq_op->write_dquot(dquot);
-			if (err) {
-				/*
-				 * Clear dirty bit anyway to avoid infinite
-				 * loop here.
-				 */
-				clear_dquot_dirty(dquot);
-				if (!ret)
-					ret = err;
-			}
+			err = dquot_write_dquot(dquot);
+			if (err && !ret)
+				ret = err;
 			dqput(dquot);
 			spin_lock(&dq_list_lock);
 		}
@@ -762,13 +799,54 @@ static struct shrinker dqcache_shrinker = {
 	.seeks = DEFAULT_SEEKS,
 };
 
+/*
+ * Safely release dquot and put reference to dquot.
+ */
+static void quota_release_workfn(struct work_struct *work)
+{
+	struct dquot *dquot;
+	struct list_head rls_head;
+
+	spin_lock(&dq_list_lock);
+	/* Exchange the list head to avoid livelock. */
+	list_replace_init(&releasing_dquots, &rls_head);
+	spin_unlock(&dq_list_lock);
+
+restart:
+	synchronize_srcu(&dquot_srcu);
+	spin_lock(&dq_list_lock);
+	while (!list_empty(&rls_head)) {
+		dquot = list_first_entry(&rls_head, struct dquot, dq_free);
+		/* Dquot got used again? */
+		if (atomic_read(&dquot->dq_count) > 1) {
+			remove_free_dquot(dquot);
+			atomic_dec(&dquot->dq_count);
+			continue;
+		}
+		if (dquot_dirty(dquot)) {
+			spin_unlock(&dq_list_lock);
+			/* Commit dquot before releasing */
+			dquot_write_dquot(dquot);
+			goto restart;
+		}
+		if (dquot_active(dquot)) {
+			spin_unlock(&dq_list_lock);
+			dquot->dq_sb->dq_op->release_dquot(dquot);
+			goto restart;
+		}
+		/* Dquot is inactive and clean, now move it to free list */
+		remove_free_dquot(dquot);
+		atomic_dec(&dquot->dq_count);
+		put_dquot_last(dquot);
+	}
+	spin_unlock(&dq_list_lock);
+}
+
 /*
  * Put reference to dquot
  */
 void dqput(struct dquot *dquot)
 {
-	int ret;
-
 	if (!dquot)
 		return;
 #ifdef CONFIG_QUOTA_DEBUG
@@ -780,7 +858,7 @@ void dqput(struct dquot *dquot)
 	}
 #endif
 	dqstats_inc(DQST_DROPS);
-we_slept:
+
 	spin_lock(&dq_list_lock);
 	if (atomic_read(&dquot->dq_count) > 1) {
 		/* We have more than one user... nothing to do */
@@ -792,35 +870,15 @@ void dqput(struct dquot *dquot)
 		spin_unlock(&dq_list_lock);
 		return;
 	}
+
 	/* Need to release dquot? */
-	if (dquot_dirty(dquot)) {
-		spin_unlock(&dq_list_lock);
-		/* Commit dquot before releasing */
-		ret = dquot->dq_sb->dq_op->write_dquot(dquot);
-		if (ret < 0) {
-			quota_error(dquot->dq_sb, "Can't write quota structure"
-				    " (error %d). Quota may get out of sync!",
-				    ret);
-			/*
-			 * We clear dirty bit anyway, so that we avoid
-			 * infinite loop here
-			 */
-			clear_dquot_dirty(dquot);
-		}
-		goto we_slept;
-	}
-	if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
-		spin_unlock(&dq_list_lock);
-		dquot->dq_sb->dq_op->release_dquot(dquot);
-		goto we_slept;
-	}
-	atomic_dec(&dquot->dq_count);
 #ifdef CONFIG_QUOTA_DEBUG
 	/* sanity check */
 	BUG_ON(!list_empty(&dquot->dq_free));
 #endif
-	put_dquot_last(dquot);
+	put_releasing_dquots(dquot);
 	spin_unlock(&dq_list_lock);
+	queue_delayed_work(system_unbound_wq, &quota_release_work, 1);
 }
 EXPORT_SYMBOL(dqput);
 
@@ -910,7 +968,7 @@ struct dquot *dqget(struct super_block *sb, struct kqid qid)
 	 * already finished or it will be canceled due to dq_count > 1 test */
 	wait_on_dquot(dquot);
 	/* Read the dquot / allocate space in quota file */
-	if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+	if (!dquot_active(dquot)) {
 		int err;
 
 		err = sb->dq_op->acquire_dquot(dquot);
@@ -1016,59 +1074,7 @@ static int add_dquot_ref(struct super_block *sb, int type)
 	return err;
 }
 
-/*
- * Remove references to dquots from inode and add dquot to list for freeing
- * if we have the last reference to dquot
- */
-static void remove_inode_dquot_ref(struct inode *inode, int type,
-				   struct list_head *tofree_head)
-{
-	struct dquot **dquots = i_dquot(inode);
-	struct dquot *dquot = dquots[type];
-
-	if (!dquot)
-		return;
-
-	dquots[type] = NULL;
-	if (list_empty(&dquot->dq_free)) {
-		/*
-		 * The inode still has reference to dquot so it can't be in the
-		 * free list
-		 */
-		spin_lock(&dq_list_lock);
-		list_add(&dquot->dq_free, tofree_head);
-		spin_unlock(&dq_list_lock);
-	} else {
-		/*
-		 * Dquot is already in a list to put so we won't drop the last
-		 * reference here.
-		 */
-		dqput(dquot);
-	}
-}
-
-/*
- * Free list of dquots
- * Dquots are removed from inodes and no new references can be got so we are
- * the only ones holding reference
- */
-static void put_dquot_list(struct list_head *tofree_head)
-{
-	struct list_head *act_head;
-	struct dquot *dquot;
-
-	act_head = tofree_head->next;
-	while (act_head != tofree_head) {
-		dquot = list_entry(act_head, struct dquot, dq_free);
-		act_head = act_head->next;
-		/* Remove dquot from the list so we won't have problems... */
-		list_del_init(&dquot->dq_free);
-		dqput(dquot);
-	}
-}
-
-static void remove_dquot_ref(struct super_block *sb, int type,
-		struct list_head *tofree_head)
+static void remove_dquot_ref(struct super_block *sb, int type)
 {
 	struct inode *inode;
 #ifdef CONFIG_QUOTA_DEBUG
@@ -1085,11 +1091,16 @@ static void remove_dquot_ref(struct super_block *sb, int type,
 		 */
 		spin_lock(&dq_data_lock);
 		if (!IS_NOQUOTA(inode)) {
+			struct dquot **dquots = i_dquot(inode);
+			struct dquot *dquot = dquots[type];
+
 #ifdef CONFIG_QUOTA_DEBUG
 			if (unlikely(inode_get_rsv_space(inode) > 0))
 				reserved = 1;
 #endif
-			remove_inode_dquot_ref(inode, type, tofree_head);
+			dquots[type] = NULL;
+			if (dquot)
+				dqput(dquot);
 		}
 		spin_unlock(&dq_data_lock);
 	}
@@ -1106,13 +1117,8 @@ static void remove_dquot_ref(struct super_block *sb, int type,
 /* Gather all references from inodes and drop them */
 static void drop_dquot_ref(struct super_block *sb, int type)
 {
-	LIST_HEAD(tofree_head);
-
-	if (sb->dq_op) {
-		remove_dquot_ref(sb, type, &tofree_head);
-		synchronize_srcu(&dquot_srcu);
-		put_dquot_list(&tofree_head);
-	}
+	if (sb->dq_op)
+		remove_dquot_ref(sb, type);
 }
 
 static inline
@@ -1427,7 +1433,7 @@ static int info_bdq_free(struct dquot *dquot, qsize_t space)
 	return QUOTA_NL_NOWARN;
 }
 
-static int dquot_active(const struct inode *inode)
+static int inode_quota_active(const struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
 
@@ -1450,7 +1456,7 @@ static int __dquot_initialize(struct inode *inode, int type)
 	qsize_t rsv;
 	int ret = 0;
 
-	if (!dquot_active(inode))
+	if (!inode_quota_active(inode))
 		return 0;
 
 	dquots = i_dquot(inode);
@@ -1558,7 +1564,7 @@ bool dquot_initialize_needed(struct inode *inode)
 	struct dquot **dquots;
 	int i;
 
-	if (!dquot_active(inode))
+	if (!inode_quota_active(inode))
 		return false;
 
 	dquots = i_dquot(inode);
@@ -1669,7 +1675,7 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
 	int reserve = flags & DQUOT_SPACE_RESERVE;
 	struct dquot **dquots;
 
-	if (!dquot_active(inode)) {
+	if (!inode_quota_active(inode)) {
 		if (reserve) {
 			spin_lock(&inode->i_lock);
 			*inode_reserved_space(inode) += number;
@@ -1739,7 +1745,7 @@ int dquot_alloc_inode(struct inode *inode)
 	struct dquot_warn warn[MAXQUOTAS];
 	struct dquot * const *dquots;
 
-	if (!dquot_active(inode))
+	if (!inode_quota_active(inode))
 		return 0;
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
 		warn[cnt].w_type = QUOTA_NL_NOWARN;
@@ -1782,7 +1788,7 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 	struct dquot **dquots;
 	int cnt, index;
 
-	if (!dquot_active(inode)) {
+	if (!inode_quota_active(inode)) {
 		spin_lock(&inode->i_lock);
 		*inode_reserved_space(inode) -= number;
 		__inode_add_bytes(inode, number);
@@ -1824,7 +1830,7 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number)
 	struct dquot **dquots;
 	int cnt, index;
 
-	if (!dquot_active(inode)) {
+	if (!inode_quota_active(inode)) {
 		spin_lock(&inode->i_lock);
 		*inode_reserved_space(inode) += number;
 		__inode_sub_bytes(inode, number);
@@ -1868,7 +1874,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
 	struct dquot **dquots;
 	int reserve = flags & DQUOT_SPACE_RESERVE, index;
 
-	if (!dquot_active(inode)) {
+	if (!inode_quota_active(inode)) {
 		if (reserve) {
 			spin_lock(&inode->i_lock);
 			*inode_reserved_space(inode) -= number;
@@ -1923,7 +1929,7 @@ void dquot_free_inode(struct inode *inode)
 	struct dquot * const *dquots;
 	int index;
 
-	if (!dquot_active(inode))
+	if (!inode_quota_active(inode))
 		return;
 
 	dquots = i_dquot(inode);
@@ -2094,7 +2100,7 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr)
 	struct super_block *sb = inode->i_sb;
 	int ret;
 
-	if (!dquot_active(inode))
+	if (!inode_quota_active(inode))
 		return 0;
 
 	if (iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)){