Merge branch 'quota_scaling' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull quota scaling updates from Jan Kara:
 "This contains changes to make the quota subsystem more scalable.

  Reportedly it improves number of files created per second on ext4
  filesystem on fast storage by about a factor of 2x"

* 'quota_scaling' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs: (28 commits)
  quota: Add lock annotations to struct members
  quota: Reduce contention on dq_data_lock
  fs: Provide __inode_get_bytes()
  quota: Inline dquot_[re]claim_reserved_space() into callsite
  quota: Inline inode_{incr,decr}_space() into callsites
  quota: Inline functions into their callsites
  ext4: Disable dirty list tracking of dquots when journalling quotas
  quota: Allow disabling tracking of dirty dquots in a list
  quota: Remove dq_wait_unused from dquot
  quota: Move locking into clear_dquot_dirty()
  quota: Do not dirty bad dquots
  quota: Fix possible corruption of dqi_flags
  quota: Propagate ->quota_read errors from v2_read_file_info()
  quota: Fix error codes in v2_read_file_info()
  quota: Push dqio_sem down to ->read_file_info()
  quota: Push dqio_sem down to ->write_file_info()
  quota: Push dqio_sem down to ->get_next_id()
  quota: Push dqio_sem down to ->release_dqblk()
  quota: Remove locking for writing to the old quota format
  quota: Do not acquire dqio_sem for dquot overwrites in v2 format
  ...

9 files changed, 392 insertions, 311 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c9e7be5..93aece6 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5215,7 +5215,7 @@ static int ext4_statfs_project(struct super_block *sb,
 	dquot = dqget(sb, qid);
 	if (IS_ERR(dquot))
 		return PTR_ERR(dquot);
-	spin_lock(&dq_data_lock);
+	spin_lock(&dquot->dq_dqb_lock);
 
 	limit = (dquot->dq_dqb.dqb_bsoftlimit ?
 		 dquot->dq_dqb.dqb_bsoftlimit :
@@ -5238,7 +5238,7 @@ static int ext4_statfs_project(struct super_block *sb,
 			 (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
 	}
 
-	spin_unlock(&dq_data_lock);
+	spin_unlock(&dquot->dq_dqb_lock);
 	dqput(dquot);
 	return 0;
 }
@@ -5284,18 +5284,13 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0;
 }
 
-/* Helper function for writing quotas on sync - we need to start transaction
- * before quota file is locked for write. Otherwise the are possible deadlocks:
- * Process 1                         Process 2
- * ext4_create()                     quota_sync()
- *   jbd2_journal_start()                  write_dquot()
- *   dquot_initialize()                         down(dqio_mutex)
- *     down(dqio_mutex)                    jbd2_journal_start()
- *
- */
 
 #ifdef CONFIG_QUOTA
 
+/*
+ * Helper functions so that transaction is started before we acquire dqio_sem
+ * to keep correct lock ordering of transaction > dqio_sem
+ */
 static inline struct inode *dquot_to_inode(struct dquot *dquot)
 {
 	return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type];
@@ -5430,6 +5425,13 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 			ext4_msg(sb, KERN_WARNING,
 				"Quota file not on filesystem root. "
 				"Journaled quota will not work");
+		sb_dqopt(sb)->flags |= DQUOT_NOLIST_DIRTY;
+	} else {
+		/*
+		 * Clear the flag just in case mount options changed since
+		 * last time.
+		 */
+		sb_dqopt(sb)->flags &= ~DQUOT_NOLIST_DIRTY;
 	}
 
 	/*
@@ -5526,7 +5528,7 @@ static int ext4_enable_quotas(struct super_block *sb)
 		test_opt(sb, PRJQUOTA),
 	};
 
-	sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
+	sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY;
 	for (type = 0; type < EXT4_MAXQUOTAS; type++) {
 		if (qf_inums[type]) {
 			err = ext4_quota_enable(sb, type, QFMT_VFS_V1,
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index cec495a..c94b6ba 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -33,7 +33,7 @@
  * Locking of quotas with OCFS2 is rather complex. Here are rules that
  * should be obeyed by all the functions:
  * - any write of quota structure (either to local or global file) is protected
- *   by dqio_mutex or dquot->dq_lock.
+ *   by dqio_sem or dquot->dq_lock.
  * - any modification of global quota file holds inode cluster lock, i_mutex,
  *   and ip_alloc_sem of the global quota file (achieved by
  *   ocfs2_lock_global_qf). It also has to hold qinfo_lock.
@@ -42,9 +42,9 @@
  *
  * A rough sketch of locking dependencies (lf = local file, gf = global file):
  * Normal filesystem operation:
- *   start_trans -> dqio_mutex -> write to lf
+ *   start_trans -> dqio_sem -> write to lf
  * Syncing of local and global file:
- *   ocfs2_lock_global_qf -> start_trans -> dqio_mutex -> qinfo_lock ->
+ *   ocfs2_lock_global_qf -> start_trans -> dqio_sem -> qinfo_lock ->
  *     write to gf
  *						       -> write to lf
  * Acquire dquot for the first time:
@@ -60,7 +60,7 @@
  * Recovery:
  *   inode cluster lock of recovered lf
  *     -> read bitmaps -> ip_alloc_sem of lf
- *     -> ocfs2_lock_global_qf -> start_trans -> dqio_mutex -> qinfo_lock ->
+ *     -> ocfs2_lock_global_qf -> start_trans -> dqio_sem -> qinfo_lock ->
  *        write to gf
  */
 
@@ -443,13 +443,17 @@ static int __ocfs2_global_write_info(struct super_block *sb, int type)
 int ocfs2_global_write_info(struct super_block *sb, int type)
 {
 	int err;
-	struct ocfs2_mem_dqinfo *info = sb_dqinfo(sb, type)->dqi_priv;
+	struct quota_info *dqopt = sb_dqopt(sb);
+	struct ocfs2_mem_dqinfo *info = dqopt->info[type].dqi_priv;
 
+	down_write(&dqopt->dqio_sem);
 	err = ocfs2_qinfo_lock(info, 1);
 	if (err < 0)
-		return err;
+		goto out_sem;
 	err = __ocfs2_global_write_info(sb, type);
 	ocfs2_qinfo_unlock(info, 1);
+out_sem:
+	up_write(&dqopt->dqio_sem);
 	return err;
 }
 
@@ -500,7 +504,7 @@ int __ocfs2_sync_dquot(struct dquot *dquot, int freeing)
 	/* Update space and inode usage. Get also other information from
 	 * global quota file so that we don't overwrite any changes there.
 	 * We are */
-	spin_lock(&dq_data_lock);
+	spin_lock(&dquot->dq_dqb_lock);
 	spacechange = dquot->dq_dqb.dqb_curspace -
 					OCFS2_DQUOT(dquot)->dq_origspace;
 	inodechange = dquot->dq_dqb.dqb_curinodes -
@@ -556,7 +560,7 @@ int __ocfs2_sync_dquot(struct dquot *dquot, int freeing)
 	__clear_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
 	OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
 	OCFS2_DQUOT(dquot)->dq_originodes = dquot->dq_dqb.dqb_curinodes;
-	spin_unlock(&dq_data_lock);
+	spin_unlock(&dquot->dq_dqb_lock);
 	err = ocfs2_qinfo_lock(info, freeing);
 	if (err < 0) {
 		mlog(ML_ERROR, "Failed to lock quota info, losing quota write"
@@ -611,7 +615,7 @@ static int ocfs2_sync_dquot_helper(struct dquot *dquot, unsigned long type)
 		mlog_errno(status);
 		goto out_ilock;
 	}
-	mutex_lock(&sb_dqopt(sb)->dqio_mutex);
+	down_write(&sb_dqopt(sb)->dqio_sem);
 	status = ocfs2_sync_dquot(dquot);
 	if (status < 0)
 		mlog_errno(status);
@@ -619,7 +623,7 @@ static int ocfs2_sync_dquot_helper(struct dquot *dquot, unsigned long type)
 	status = ocfs2_local_write_dquot(dquot);
 	if (status < 0)
 		mlog_errno(status);
-	mutex_unlock(&sb_dqopt(sb)->dqio_mutex);
+	up_write(&sb_dqopt(sb)->dqio_sem);
 	ocfs2_commit_trans(osb, handle);
 out_ilock:
 	ocfs2_unlock_global_qf(oinfo, 1);
@@ -666,9 +670,9 @@ static int ocfs2_write_dquot(struct dquot *dquot)
 		mlog_errno(status);
 		goto out;
 	}
-	mutex_lock(&sb_dqopt(dquot->dq_sb)->dqio_mutex);
+	down_write(&sb_dqopt(dquot->dq_sb)->dqio_sem);
 	status = ocfs2_local_write_dquot(dquot);
-	mutex_unlock(&sb_dqopt(dquot->dq_sb)->dqio_mutex);
+	up_write(&sb_dqopt(dquot->dq_sb)->dqio_sem);
 	ocfs2_commit_trans(osb, handle);
 out:
 	return status;
@@ -920,10 +924,10 @@ static int ocfs2_mark_dquot_dirty(struct dquot *dquot)
 
 	/* In case user set some limits, sync dquot immediately to global
 	 * quota file so that information propagates quicker */
-	spin_lock(&dq_data_lock);
+	spin_lock(&dquot->dq_dqb_lock);
 	if (dquot->dq_flags & mask)
 		sync = 1;
-	spin_unlock(&dq_data_lock);
+	spin_unlock(&dquot->dq_dqb_lock);
 	/* This is a slight hack but we can't afford getting global quota
 	 * lock if we already have a transaction started. */
 	if (!sync || journal_current_handle()) {
@@ -939,7 +943,7 @@ static int ocfs2_mark_dquot_dirty(struct dquot *dquot)
 		mlog_errno(status);
 		goto out_ilock;
 	}
-	mutex_lock(&sb_dqopt(sb)->dqio_mutex);
+	down_write(&sb_dqopt(sb)->dqio_sem);
 	status = ocfs2_sync_dquot(dquot);
 	if (status < 0) {
 		mlog_errno(status);
@@ -948,7 +952,7 @@ static int ocfs2_mark_dquot_dirty(struct dquot *dquot)
 	/* Now write updated local dquot structure */
 	status = ocfs2_local_write_dquot(dquot);
 out_dlock:
-	mutex_unlock(&sb_dqopt(sb)->dqio_mutex);
+	up_write(&sb_dqopt(sb)->dqio_sem);
 	ocfs2_commit_trans(osb, handle);
 out_ilock:
 	ocfs2_unlock_global_qf(oinfo, 1);
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 32c5a40..aa700fd 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -520,8 +520,8 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode,
 				mlog_errno(status);
 				goto out_drop_lock;
 			}
-			mutex_lock(&sb_dqopt(sb)->dqio_mutex);
-			spin_lock(&dq_data_lock);
+			down_write(&sb_dqopt(sb)->dqio_sem);
+			spin_lock(&dquot->dq_dqb_lock);
 			/* Add usage from quota entry into quota changes
 			 * of our node. Auxiliary variables are important
 			 * due to signedness */
@@ -529,7 +529,7 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode,
 			inodechange = le64_to_cpu(dqblk->dqb_inodemod);
 			dquot->dq_dqb.dqb_curspace += spacechange;
 			dquot->dq_dqb.dqb_curinodes += inodechange;
-			spin_unlock(&dq_data_lock);
+			spin_unlock(&dquot->dq_dqb_lock);
 			/* We want to drop reference held by the crashed
 			 * node. Since we have our own reference we know
 			 * global structure actually won't be freed. */
@@ -553,7 +553,7 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode,
 			unlock_buffer(qbh);
 			ocfs2_journal_dirty(handle, qbh);
 out_commit:
-			mutex_unlock(&sb_dqopt(sb)->dqio_mutex);
+			up_write(&sb_dqopt(sb)->dqio_sem);
 			ocfs2_commit_trans(OCFS2_SB(sb), handle);
 out_drop_lock:
 			ocfs2_unlock_global_qf(oinfo, 1);
@@ -691,9 +691,6 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 	struct ocfs2_quota_recovery *rec;
 	int locked = 0;
 
-	/* We don't need the lock and we have to acquire quota file locks
-	 * which will later depend on this lock */
-	mutex_unlock(&sb_dqopt(sb)->dqio_mutex);
 	info->dqi_max_spc_limit = 0x7fffffffffffffffLL;
 	info->dqi_max_ino_limit = 0x7fffffffffffffffLL;
 	oinfo = kmalloc(sizeof(struct ocfs2_mem_dqinfo), GFP_NOFS);
@@ -772,7 +769,6 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 		goto out_err;
 	}
 
-	mutex_lock(&sb_dqopt(sb)->dqio_mutex);
 	return 0;
 out_err:
 	if (oinfo) {
@@ -786,7 +782,6 @@ out_err:
 		kfree(oinfo);
 	}
 	brelse(bh);
-	mutex_lock(&sb_dqopt(sb)->dqio_mutex);
 	return -1;
 }
 
@@ -882,12 +877,12 @@ static void olq_set_dquot(struct buffer_head *bh, void *private)
 
 	dqblk->dqb_id = cpu_to_le64(from_kqid(&init_user_ns,
 					      od->dq_dquot.dq_id));
-	spin_lock(&dq_data_lock);
+	spin_lock(&od->dq_dquot.dq_dqb_lock);
 	dqblk->dqb_spacemod = cpu_to_le64(od->dq_dquot.dq_dqb.dqb_curspace -
 					  od->dq_origspace);
 	dqblk->dqb_inodemod = cpu_to_le64(od->dq_dquot.dq_dqb.dqb_curinodes -
 					  od->dq_originodes);
-	spin_unlock(&dq_data_lock);
+	spin_unlock(&od->dq_dquot.dq_dqb_lock);
 	trace_olq_set_dquot(
 		(unsigned long long)le64_to_cpu(dqblk->dqb_spacemod),
 		(unsigned long long)le64_to_cpu(dqblk->dqb_inodemod),
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 566e6ef..8381db9 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -82,16 +82,19 @@
 #include <linux/uaccess.h>
 
 /*
- * There are three quota SMP locks. dq_list_lock protects all lists with quotas
- * and quota formats.
- * dq_data_lock protects data from dq_dqb and also mem_dqinfo structures and
- * also guards consistency of dquot->dq_dqb with inode->i_blocks, i_bytes.
- * i_blocks and i_bytes updates itself are guarded by i_lock acquired directly
- * in inode_add_bytes() and inode_sub_bytes(). dq_state_lock protects
- * modifications of quota state (on quotaon and quotaoff) and readers who care
- * about latest values take it as well.
+ * There are five quota SMP locks:
+ * * dq_list_lock protects all lists with quotas and quota formats.
+ * * dquot->dq_dqb_lock protects data from dq_dqb
+ * * inode->i_lock protects inode->i_blocks, i_bytes and also guards
+ *   consistency of dquot->dq_dqb with inode->i_blocks, i_bytes so that
+ *   dquot_transfer() can stabilize amount it transfers
+ * * dq_data_lock protects mem_dqinfo structures and modifications of dquot
+ *   pointers in the inode
+ * * dq_state_lock protects modifications of quota state (on quotaon and
+ *   quotaoff) and readers who care about latest values take it as well.
  *
- * The spinlock ordering is hence: dq_data_lock > dq_list_lock > i_lock,
+ * The spinlock ordering is hence:
+ *   dq_data_lock > dq_list_lock > i_lock > dquot->dq_dqb_lock,
  *   dq_list_lock > dq_state_lock
  *
  * Note that some things (eg. sb pointer, type, id) doesn't change during
@@ -110,17 +113,14 @@
  * sure they cannot race with quotaon which first sets S_NOQUOTA flag and
  * then drops all pointers to dquots from an inode.
  *
- * Each dquot has its dq_lock mutex. Locked dquots might not be referenced
- * from inodes (dquot_alloc_space() and such don't check the dq_lock).
- * Currently dquot is locked only when it is being read to memory (or space for
- * it is being allocated) on the first dqget() and when it is being released on
- * the last dqput(). The allocation and release oparations are serialized by
- * the dq_lock and by checking the use count in dquot_release().  Write
- * operations on dquots don't hold dq_lock as they copy data under dq_data_lock
- * spinlock to internal buffers before writing.
+ * Each dquot has its dq_lock mutex.  Dquot is locked when it is being read to
+ * memory (or space for it is being allocated) on the first dqget(), when it is
+ * being written out, and when it is being released on the last dqput(). The
+ * allocation and release operations are serialized by the dq_lock and by
+ * checking the use count in dquot_release().
  *
  * Lock ordering (including related VFS locks) is the following:
- *   s_umount > i_mutex > journal_lock > dquot->dq_lock > dqio_mutex
+ *   s_umount > i_mutex > journal_lock > dquot->dq_lock > dqio_sem
  */
 
 static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_list_lock);
@@ -129,6 +129,8 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_data_lock);
 EXPORT_SYMBOL(dq_data_lock);
 DEFINE_STATIC_SRCU(dquot_srcu);
 
+static DECLARE_WAIT_QUEUE_HEAD(dquot_ref_wq);
+
 void __quota_error(struct super_block *sb, const char *func,
 		   const char *fmt, ...)
 {
@@ -247,6 +249,7 @@ struct dqstats dqstats;
 EXPORT_SYMBOL(dqstats);
 
 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 inline unsigned int
@@ -342,6 +345,12 @@ int dquot_mark_dquot_dirty(struct dquot *dquot)
 {
 	int ret = 1;
 
+	if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags))
+		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))
 		return 1;
@@ -381,18 +390,26 @@ static inline void dqput_all(struct dquot **dquot)
 		dqput(dquot[cnt]);
 }
 
-/* This function needs dq_list_lock */
 static inline int clear_dquot_dirty(struct dquot *dquot)
 {
-	if (!test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags))
+	if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY)
+		return test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags);
+
+	spin_lock(&dq_list_lock);
+	if (!test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags)) {
+		spin_unlock(&dq_list_lock);
 		return 0;
+	}
 	list_del_init(&dquot->dq_dirty);
+	spin_unlock(&dq_list_lock);
 	return 1;
 }
 
 void mark_info_dirty(struct super_block *sb, int type)
 {
-	set_bit(DQF_INFO_DIRTY_B, &sb_dqopt(sb)->info[type].dqi_flags);
+	spin_lock(&dq_data_lock);
+	sb_dqopt(sb)->info[type].dqi_flags |= DQF_INFO_DIRTY;
+	spin_unlock(&dq_data_lock);
 }
 EXPORT_SYMBOL(mark_info_dirty);
 
@@ -406,7 +423,6 @@ int dquot_acquire(struct dquot *dquot)
 	struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
 
 	mutex_lock(&dquot->dq_lock);
-	mutex_lock(&dqopt->dqio_mutex);
 	if (!test_bit(DQ_READ_B, &dquot->dq_flags))
 		ret = dqopt->ops[dquot->dq_id.type]->read_dqblk(dquot);
 	if (ret < 0)
@@ -436,7 +452,6 @@ int dquot_acquire(struct dquot *dquot)
 	smp_mb__before_atomic();
 	set_bit(DQ_ACTIVE_B, &dquot->dq_flags);
 out_iolock:
-	mutex_unlock(&dqopt->dqio_mutex);
 	mutex_unlock(&dquot->dq_lock);
 	return ret;
 }
@@ -450,21 +465,17 @@ int dquot_commit(struct dquot *dquot)
 	int ret = 0;
 	struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
 
-	mutex_lock(&dqopt->dqio_mutex);
-	spin_lock(&dq_list_lock);
-	if (!clear_dquot_dirty(dquot)) {
-		spin_unlock(&dq_list_lock);
-		goto out_sem;
-	}
-	spin_unlock(&dq_list_lock);
+	mutex_lock(&dquot->dq_lock);
+	if (!clear_dquot_dirty(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))
 		ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot);
 	else
 		ret = -EIO;
-out_sem:
-	mutex_unlock(&dqopt->dqio_mutex);
+out_lock:
+	mutex_unlock(&dquot->dq_lock);
 	return ret;
 }
 EXPORT_SYMBOL(dquot_commit);
@@ -481,7 +492,6 @@ int dquot_release(struct dquot *dquot)
 	/* Check whether we are not racing with some other dqget() */
 	if (atomic_read(&dquot->dq_count) > 1)
 		goto out_dqlock;
-	mutex_lock(&dqopt->dqio_mutex);
 	if (dqopt->ops[dquot->dq_id.type]->release_dqblk) {
 		ret = dqopt->ops[dquot->dq_id.type]->release_dqblk(dquot);
 		/* Write the info */
@@ -493,7 +503,6 @@ int dquot_release(struct dquot *dquot)
 			ret = ret2;
 	}
 	clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
-	mutex_unlock(&dqopt->dqio_mutex);
 out_dqlock:
 	mutex_unlock(&dquot->dq_lock);
 	return ret;
@@ -530,22 +539,18 @@ restart:
 			continue;
 		/* Wait for dquot users */
 		if (atomic_read(&dquot->dq_count)) {
-			DEFINE_WAIT(wait);
-
 			dqgrab(dquot);
-			prepare_to_wait(&dquot->dq_wait_unused, &wait,
-					TASK_UNINTERRUPTIBLE);
 			spin_unlock(&dq_list_lock);
-			/* Once dqput() wakes us up, we know it's time to free
+			/*
+			 * Once dqput() wakes us up, we know it's time to free
 			 * the dquot.
 			 * IMPORTANT: we rely on the fact that there is always
 			 * at most one process waiting for dquot to free.
 			 * Otherwise dq_count would be > 1 and we would never
 			 * wake up.
 			 */
-			if (atomic_read(&dquot->dq_count) > 1)
-				schedule();
-			finish_wait(&dquot->dq_wait_unused, &wait);
+			wait_event(dquot_ref_wq,
+				   atomic_read(&dquot->dq_count) == 1);
 			dqput(dquot);
 			/* At this moment dquot() need not exist (it could be
 			 * reclaimed by prune_dqcache(). Hence we must
@@ -629,11 +634,9 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
 		while (!list_empty(dirty)) {
 			dquot = list_first_entry(dirty, struct dquot,
 						 dq_dirty);
-			/* Dirty and inactive can be only bad dquot... */
-			if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
-				clear_dquot_dirty(dquot);
-				continue;
-			}
+
+			WARN_ON(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags));
+
 			/* Now we have active dquot from which someone is
  			 * holding reference so we can safely just increase
 			 * use count */
@@ -759,12 +762,12 @@ we_slept:
 		/* Releasing dquot during quotaoff phase? */
 		if (!sb_has_quota_active(dquot->dq_sb, dquot->dq_id.type) &&
 		    atomic_read(&dquot->dq_count) == 1)
-			wake_up(&dquot->dq_wait_unused);
+			wake_up(&dquot_ref_wq);
 		spin_unlock(&dq_list_lock);
 		return;
 	}
 	/* Need to release dquot? */
-	if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && dquot_dirty(dquot)) {
+	if (dquot_dirty(dquot)) {
 		spin_unlock(&dq_list_lock);
 		/* Commit dquot before releasing */
 		ret = dquot->dq_sb->dq_op->write_dquot(dquot);
@@ -776,14 +779,10 @@ we_slept:
 			 * We clear dirty bit anyway, so that we avoid
 			 * infinite loop here
 			 */
-			spin_lock(&dq_list_lock);
 			clear_dquot_dirty(dquot);
-			spin_unlock(&dq_list_lock);
 		}
 		goto we_slept;
 	}
-	/* Clear flag in case dquot was inactive (something bad happened) */
-	clear_dquot_dirty(dquot);
 	if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
 		spin_unlock(&dq_list_lock);
 		dquot->dq_sb->dq_op->release_dquot(dquot);
@@ -818,10 +817,10 @@ static struct dquot *get_empty_dquot(struct super_block *sb, int type)
 	INIT_LIST_HEAD(&dquot->dq_inuse);
 	INIT_HLIST_NODE(&dquot->dq_hash);
 	INIT_LIST_HEAD(&dquot->dq_dirty);
-	init_waitqueue_head(&dquot->dq_wait_unused);
 	dquot->dq_sb = sb;
 	dquot->dq_id = make_kqid_invalid(type);
 	atomic_set(&dquot->dq_count, 1);
+	spin_lock_init(&dquot->dq_dqb_lock);
 
 	return dquot;
 }
@@ -1079,42 +1078,6 @@ static void drop_dquot_ref(struct super_block *sb, int type)
 	}
 }
 
-static inline void dquot_incr_inodes(struct dquot *dquot, qsize_t number)
-{
-	dquot->dq_dqb.dqb_curinodes += number;
-}
-
-static inline void dquot_incr_space(struct dquot *dquot, qsize_t number)
-{
-	dquot->dq_dqb.dqb_curspace += number;
-}
-
-static inline void dquot_resv_space(struct dquot *dquot, qsize_t number)
-{
-	dquot->dq_dqb.dqb_rsvspace += number;
-}
-
-/*
- * Claim reserved quota space
- */
-static void dquot_claim_reserved_space(struct dquot *dquot, qsize_t number)
-{
-	if (dquot->dq_dqb.dqb_rsvspace < number) {
-		WARN_ON_ONCE(1);
-		number = dquot->dq_dqb.dqb_rsvspace;
-	}
-	dquot->dq_dqb.dqb_curspace += number;
-	dquot->dq_dqb.dqb_rsvspace -= number;
-}
-
-static void dquot_reclaim_reserved_space(struct dquot *dquot, qsize_t number)
-{
-	if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number))
-		number = dquot->dq_dqb.dqb_curspace;
-	dquot->dq_dqb.dqb_rsvspace += number;
-	dquot->dq_dqb.dqb_curspace -= number;
-}
-
 static inline
 void dquot_free_reserved_space(struct dquot *dquot, qsize_t number)
 {
@@ -1278,21 +1241,24 @@ static int ignore_hardlimit(struct dquot *dquot)
 		!(info->dqi_flags & DQF_ROOT_SQUASH));
 }
 
-/* needs dq_data_lock */
-static int check_idq(struct dquot *dquot, qsize_t inodes,
-		     struct dquot_warn *warn)
+static int dquot_add_inodes(struct dquot *dquot, qsize_t inodes,
+			    struct dquot_warn *warn)
 {
-	qsize_t newinodes = dquot->dq_dqb.dqb_curinodes + inodes;
+	qsize_t newinodes;
+	int ret = 0;
 
+	spin_lock(&dquot->dq_dqb_lock);
+	newinodes = dquot->dq_dqb.dqb_curinodes + inodes;
 	if (!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_id.type) ||
 	    test_bit(DQ_FAKE_B, &dquot->dq_flags))
-		return 0;
+		goto add;
 
 	if (dquot->dq_dqb.dqb_ihardlimit &&
 	    newinodes > dquot->dq_dqb.dqb_ihardlimit &&
             !ignore_hardlimit(dquot)) {
 		prepare_warning(warn, dquot, QUOTA_NL_IHARDWARN);
-		return -EDQUOT;
+		ret = -EDQUOT;
+		goto out;
 	}
 
 	if (dquot->dq_dqb.dqb_isoftlimit &&
@@ -1301,7 +1267,8 @@ static int check_idq(struct dquot *dquot, qsize_t inodes,
 	    ktime_get_real_seconds() >= dquot->dq_dqb.dqb_itime &&
             !ignore_hardlimit(dquot)) {
 		prepare_warning(warn, dquot, QUOTA_NL_ISOFTLONGWARN);
-		return -EDQUOT;
+		ret = -EDQUOT;
+		goto out;
 	}
 
 	if (dquot->dq_dqb.dqb_isoftlimit &&
@@ -1311,30 +1278,40 @@ static int check_idq(struct dquot *dquot, qsize_t inodes,
 		dquot->dq_dqb.dqb_itime = ktime_get_real_seconds() +
 		    sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type].dqi_igrace;
 	}
+add:
+	dquot->dq_dqb.dqb_curinodes = newinodes;
 
-	return 0;
+out:
+	spin_unlock(&dquot->dq_dqb_lock);
+	return ret;
 }
 
-/* needs dq_data_lock */
-static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc,
-		     struct dquot_warn *warn)
+static int dquot_add_space(struct dquot *dquot, qsize_t space,
+			   qsize_t rsv_space, unsigned int flags,
+			   struct dquot_warn *warn)
 {
 	qsize_t tspace;
 	struct super_block *sb = dquot->dq_sb;
+	int ret = 0;
 
+	spin_lock(&dquot->dq_dqb_lock);
 	if (!sb_has_quota_limits_enabled(sb, dquot->dq_id.type) ||
 	    test_bit(DQ_FAKE_B, &dquot->dq_flags))
-		return 0;
+		goto add;
 
 	tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace
-		+ space;
+		+ space + rsv_space;
+
+	if (flags & DQUOT_SPACE_NOFAIL)
+		goto add;
 
 	if (dquot->dq_dqb.dqb_bhardlimit &&
 	    tspace > dquot->dq_dqb.dqb_bhardlimit &&
             !ignore_hardlimit(dquot)) {
-		if (!prealloc)
+		if (flags & DQUOT_SPACE_WARN)
 			prepare_warning(warn, dquot, QUOTA_NL_BHARDWARN);
-		return -EDQUOT;
+		ret = -EDQUOT;
+		goto out;
 	}
 
 	if (dquot->dq_dqb.dqb_bsoftlimit &&
@@ -1342,28 +1319,34 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc,
 	    dquot->dq_dqb.dqb_btime &&
 	    ktime_get_real_seconds() >= dquot->dq_dqb.dqb_btime &&
             !ignore_hardlimit(dquot)) {
-		if (!prealloc)
+		if (flags & DQUOT_SPACE_WARN)
 			prepare_warning(warn, dquot, QUOTA_NL_BSOFTLONGWARN);
-		return -EDQUOT;
+		ret = -EDQUOT;
+		goto out;
 	}
 
 	if (dquot->dq_dqb.dqb_bsoftlimit &&
 	    tspace > dquot->dq_dqb.dqb_bsoftlimit &&
 	    dquot->dq_dqb.dqb_btime == 0) {
-		if (!prealloc) {
+		if (flags & DQUOT_SPACE_WARN) {
 			prepare_warning(warn, dquot, QUOTA_NL_BSOFTWARN);
 			dquot->dq_dqb.dqb_btime = ktime_get_real_seconds() +
 			    sb_dqopt(sb)->info[dquot->dq_id.type].dqi_bgrace;
-		}
-		else
+		} else {
 			/*
 			 * We don't allow preallocation to exceed softlimit so exceeding will
 			 * be always printed
 			 */
-			return -EDQUOT;
+			ret = -EDQUOT;
+			goto out;
+		}
 	}
-
-	return 0;
+add:
+	dquot->dq_dqb.dqb_rsvspace += rsv_space;
+	dquot->dq_dqb.dqb_curspace += space;
+out:
+	spin_unlock(&dquot->dq_dqb_lock);
+	return ret;
 }
 
 static int info_idq_free(struct dquot *dquot, qsize_t inodes)
@@ -1502,8 +1485,15 @@ static int __dquot_initialize(struct inode *inode, int type)
 			 * did a write before quota was turned on
 			 */
 			rsv = inode_get_rsv_space(inode);
-			if (unlikely(rsv))
-				dquot_resv_space(dquots[cnt], rsv);
+			if (unlikely(rsv)) {
+				spin_lock(&inode->i_lock);
+				/* Get reservation again under proper lock */
+				rsv = __inode_get_rsv_space(inode);
+				spin_lock(&dquots[cnt]->dq_dqb_lock);
+				dquots[cnt]->dq_dqb.dqb_rsvspace += rsv;
+				spin_unlock(&dquots[cnt]->dq_dqb_lock);
+				spin_unlock(&inode->i_lock);
+			}
 		}
 	}
 out_lock:
@@ -1598,39 +1588,12 @@ static qsize_t *inode_reserved_space(struct inode * inode)
 	return inode->i_sb->dq_op->get_reserved_space(inode);
 }
 
-void inode_add_rsv_space(struct inode *inode, qsize_t number)
-{
-	spin_lock(&inode->i_lock);
-	*inode_reserved_space(inode) += number;
-	spin_unlock(&inode->i_lock);
-}
-EXPORT_SYMBOL(inode_add_rsv_space);
-
-void inode_claim_rsv_space(struct inode *inode, qsize_t number)
+static qsize_t __inode_get_rsv_space(struct inode *inode)
 {
-	spin_lock(&inode->i_lock);
-	*inode_reserved_space(inode) -= number;
-	__inode_add_bytes(inode, number);
-	spin_unlock(&inode->i_lock);
-}
-EXPORT_SYMBOL(inode_claim_rsv_space);
-
-void inode_reclaim_rsv_space(struct inode *inode, qsize_t number)
-{
-	spin_lock(&inode->i_lock);
-	*inode_reserved_space(inode) += number;
-	__inode_sub_bytes(inode, number);
-	spin_unlock(&inode->i_lock);
-}
-EXPORT_SYMBOL(inode_reclaim_rsv_space);
-
-void inode_sub_rsv_space(struct inode *inode, qsize_t number)
-{
-	spin_lock(&inode->i_lock);
-	*inode_reserved_space(inode) -= number;
-	spin_unlock(&inode->i_lock);
+	if (!inode->i_sb->dq_op->get_reserved_space)
+		return 0;
+	return *inode_reserved_space(inode);
 }
-EXPORT_SYMBOL(inode_sub_rsv_space);
 
 static qsize_t inode_get_rsv_space(struct inode *inode)
 {
@@ -1639,28 +1602,11 @@ static qsize_t inode_get_rsv_space(struct inode *inode)
 	if (!inode->i_sb->dq_op->get_reserved_space)
 		return 0;
 	spin_lock(&inode->i_lock);
-	ret = *inode_reserved_space(inode);
+	ret = __inode_get_rsv_space(inode);
 	spin_unlock(&inode->i_lock);
 	return ret;
 }
 
-static void inode_incr_space(struct inode *inode, qsize_t number,
-				int reserve)
-{
-	if (reserve)
-		inode_add_rsv_space(inode, number);
-	else
-		inode_add_bytes(inode, number);
-}
-
-static void inode_decr_space(struct inode *inode, qsize_t number, int reserve)
-{
-	if (reserve)
-		inode_sub_rsv_space(inode, number);
-	else
-		inode_sub_bytes(inode, number);
-}
-
 /*
  * This functions updates i_blocks+i_bytes fields and quota information
  * (together with appropriate checks).
@@ -1682,7 +1628,13 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
 	struct dquot **dquots;
 
 	if (!dquot_active(inode)) {
-		inode_incr_space(inode, number, reserve);
+		if (reserve) {
+			spin_lock(&inode->i_lock);
+			*inode_reserved_space(inode) += number;
+			spin_unlock(&inode->i_lock);
+		} else {
+			inode_add_bytes(inode, number);
+		}
 		goto out;
 	}
 
@@ -1691,27 +1643,41 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
 
 	dquots = i_dquot(inode);
 	index = srcu_read_lock(&dquot_srcu);
-	spin_lock(&dq_data_lock);
+	spin_lock(&inode->i_lock);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 		if (!dquots[cnt])
 			continue;
-		ret = check_bdq(dquots[cnt], number,
-				!(flags & DQUOT_SPACE_WARN), &warn[cnt]);
-		if (ret && !(flags & DQUOT_SPACE_NOFAIL)) {
-			spin_unlock(&dq_data_lock);
+		if (flags & DQUOT_SPACE_RESERVE) {
+			ret = dquot_add_space(dquots[cnt], 0, number, flags,
+					      &warn[cnt]);
+		} else {
+			ret = dquot_add_space(dquots[cnt], number, 0, flags,
+					      &warn[cnt]);
+		}
+		if (ret) {
+			/* Back out changes we already did */
+			for (cnt--; cnt >= 0; cnt--) {
+				if (!dquots[cnt])
+					continue;
+				spin_lock(&dquots[cnt]->dq_dqb_lock);
+				if (flags & DQUOT_SPACE_RESERVE) {
+					dquots[cnt]->dq_dqb.dqb_rsvspace -=
+									number;
+				} else {
+					dquots[cnt]->dq_dqb.dqb_curspace -=
+									number;
+				}
+				spin_unlock(&dquots[cnt]->dq_dqb_lock);
+			}
+			spin_unlock(&inode->i_lock);
 			goto out_flush_warn;
 		}
 	}
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (!dquots[cnt])
-			continue;
-		if (reserve)
-			dquot_resv_space(dquots[cnt], number);
-		else
-			dquot_incr_space(dquots[cnt], number);
-	}
-	inode_incr_space(inode, number, reserve);
-	spin_unlock(&dq_data_lock);
+	if (reserve)
+		*inode_reserved_space(inode) += number;
+	else
+		__inode_add_bytes(inode, number);
+	spin_unlock(&inode->i_lock);
 
 	if (reserve)
 		goto out_flush_warn;
@@ -1740,23 +1706,26 @@ int dquot_alloc_inode(struct inode *inode)
 
 	dquots = i_dquot(inode);
 	index = srcu_read_lock(&dquot_srcu);
-	spin_lock(&dq_data_lock);
+	spin_lock(&inode->i_lock);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 		if (!dquots[cnt])
 			continue;
-		ret = check_idq(dquots[cnt], 1, &warn[cnt]);
-		if (ret)
+		ret = dquot_add_inodes(dquots[cnt], 1, &warn[cnt]);
+		if (ret) {
+			for (cnt--; cnt >= 0; cnt--) {
+				if (!dquots[cnt])
+					continue;
+				/* Back out changes we already did */
+				spin_lock(&dquots[cnt]->dq_dqb_lock);
+				dquots[cnt]->dq_dqb.dqb_curinodes--;
+				spin_unlock(&dquots[cnt]->dq_dqb_lock);
+			}
 			goto warn_put_all;
-	}
-
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (!dquots[cnt])
-			continue;
-		dquot_incr_inodes(dquots[cnt], 1);
+		}
 	}
 
 warn_put_all:
-	spin_unlock(&dq_data_lock);
+	spin_unlock(&inode->i_lock);
 	if (ret == 0)
 		mark_all_dquot_dirty(dquots);
 	srcu_read_unlock(&dquot_srcu, index);
@@ -1774,21 +1743,33 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 	int cnt, index;
 
 	if (!dquot_active(inode)) {
-		inode_claim_rsv_space(inode, number);
+		spin_lock(&inode->i_lock);
+		*inode_reserved_space(inode) -= number;
+		__inode_add_bytes(inode, number);
+		spin_unlock(&inode->i_lock);
 		return 0;
 	}
 
 	dquots = i_dquot(inode);
 	index = srcu_read_lock(&dquot_srcu);
-	spin_lock(&dq_data_lock);
+	spin_lock(&inode->i_lock);
 	/* Claim reserved quotas to allocated quotas */
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (dquots[cnt])
-			dquot_claim_reserved_space(dquots[cnt], number);
+		if (dquots[cnt]) {
+			struct dquot *dquot = dquots[cnt];
+
+			spin_lock(&dquot->dq_dqb_lock);
+			if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number))
+				number = dquot->dq_dqb.dqb_rsvspace;
+			dquot->dq_dqb.dqb_curspace += number;
+			dquot->dq_dqb.dqb_rsvspace -= number;
+			spin_unlock(&dquot->dq_dqb_lock);
+		}
 	}
 	/* Update inode bytes */
-	inode_claim_rsv_space(inode, number);
-	spin_unlock(&dq_data_lock);
+	*inode_reserved_space(inode) -= number;
+	__inode_add_bytes(inode, number);
+	spin_unlock(&inode->i_lock);
 	mark_all_dquot_dirty(dquots);
 	srcu_read_unlock(&dquot_srcu, index);
 	return 0;
@@ -1804,21 +1785,33 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number)
 	int cnt, index;
 
 	if (!dquot_active(inode)) {
-		inode_reclaim_rsv_space(inode, number);
+		spin_lock(&inode->i_lock);
+		*inode_reserved_space(inode) += number;
+		__inode_sub_bytes(inode, number);
+		spin_unlock(&inode->i_lock);
 		return;
 	}
 
 	dquots = i_dquot(inode);
 	index = srcu_read_lock(&dquot_srcu);
-	spin_lock(&dq_data_lock);
+	spin_lock(&inode->i_lock);
 	/* Claim reserved quotas to allocated quotas */
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (dquots[cnt])
-			dquot_reclaim_reserved_space(dquots[cnt], number);
+		if (dquots[cnt]) {
+			struct dquot *dquot = dquots[cnt];
+
+			spin_lock(&dquot->dq_dqb_lock);
+			if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number))
+				number = dquot->dq_dqb.dqb_curspace;
+			dquot->dq_dqb.dqb_rsvspace += number;
+			dquot->dq_dqb.dqb_curspace -= number;
+			spin_unlock(&dquot->dq_dqb_lock);
+		}
 	}
 	/* Update inode bytes */
-	inode_reclaim_rsv_space(inode, number);
-	spin_unlock(&dq_data_lock);
+	*inode_reserved_space(inode) += number;
+	__inode_sub_bytes(inode, number);
+	spin_unlock(&inode->i_lock);
 	mark_all_dquot_dirty(dquots);
 	srcu_read_unlock(&dquot_srcu, index);
 	return;
@@ -1836,19 +1829,26 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
 	int reserve = flags & DQUOT_SPACE_RESERVE, index;
 
 	if (!dquot_active(inode)) {
-		inode_decr_space(inode, number, reserve);
+		if (reserve) {
+			spin_lock(&inode->i_lock);
+			*inode_reserved_space(inode) -= number;
+			spin_unlock(&inode->i_lock);
+		} else {
+			inode_sub_bytes(inode, number);
+		}
 		return;
 	}
 
 	dquots = i_dquot(inode);
 	index = srcu_read_lock(&dquot_srcu);
-	spin_lock(&dq_data_lock);
+	spin_lock(&inode->i_lock);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 		int wtype;
 
 		warn[cnt].w_type = QUOTA_NL_NOWARN;
 		if (!dquots[cnt])
 			continue;
+		spin_lock(&dquots[cnt]->dq_dqb_lock);
 		wtype = info_bdq_free(dquots[cnt], number);
 		if (wtype != QUOTA_NL_NOWARN)
 			prepare_warning(&warn[cnt], dquots[cnt], wtype);
@@ -1856,9 +1856,13 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
 			dquot_free_reserved_space(dquots[cnt], number);
 		else
 			dquot_decr_space(dquots[cnt], number);
+		spin_unlock(&dquots[cnt]->dq_dqb_lock);
 	}
-	inode_decr_space(inode, number, reserve);
-	spin_unlock(&dq_data_lock);
+	if (reserve)
+		*inode_reserved_space(inode) -= number;
+	else
+		__inode_sub_bytes(inode, number);
+	spin_unlock(&inode->i_lock);
 
 	if (reserve)
 		goto out_unlock;
@@ -1884,19 +1888,21 @@ void dquot_free_inode(struct inode *inode)
 
 	dquots = i_dquot(inode);
 	index = srcu_read_lock(&dquot_srcu);
-	spin_lock(&dq_data_lock);
+	spin_lock(&inode->i_lock);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 		int wtype;
 
 		warn[cnt].w_type = QUOTA_NL_NOWARN;
 		if (!dquots[cnt])
 			continue;
+		spin_lock(&dquots[cnt]->dq_dqb_lock);
 		wtype = info_idq_free(dquots[cnt], 1);
 		if (wtype != QUOTA_NL_NOWARN)
 			prepare_warning(&warn[cnt], dquots[cnt], wtype);
 		dquot_decr_inodes(dquots[cnt], 1);
+		spin_unlock(&dquots[cnt]->dq_dqb_lock);
 	}
-	spin_unlock(&dq_data_lock);
+	spin_unlock(&inode->i_lock);
 	mark_all_dquot_dirty(dquots);
 	srcu_read_unlock(&dquot_srcu, index);
 	flush_warnings(warn);
@@ -1917,7 +1923,7 @@ EXPORT_SYMBOL(dquot_free_inode);
  */
 int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 {
-	qsize_t space, cur_space;
+	qsize_t cur_space;
 	qsize_t rsv_space = 0;
 	qsize_t inode_usage = 1;
 	struct dquot *transfer_from[MAXQUOTAS] = {};
@@ -1944,14 +1950,18 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 	}
 
 	spin_lock(&dq_data_lock);
+	spin_lock(&inode->i_lock);
 	if (IS_NOQUOTA(inode)) {	/* File without quota accounting? */
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&dq_data_lock);
 		return 0;
 	}
-	cur_space = inode_get_bytes(inode);
-	rsv_space = inode_get_rsv_space(inode);
-	space = cur_space + rsv_space;
-	/* Build the transfer_from list and check the limits */
+	cur_space = __inode_get_bytes(inode);
+	rsv_space = __inode_get_rsv_space(inode);
+	/*
+	 * Build the transfer_from list, check limits, and update usage in
+	 * the target structures.
+	 */
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 		/*
 		 * Skip changes for same uid or gid or for turned off quota-type.
@@ -1963,28 +1973,33 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 			continue;
 		is_valid[cnt] = 1;
 		transfer_from[cnt] = i_dquot(inode)[cnt];
-		ret = check_idq(transfer_to[cnt], inode_usage, &warn_to[cnt]);
+		ret = dquot_add_inodes(transfer_to[cnt], inode_usage,
+				       &warn_to[cnt]);
 		if (ret)
 			goto over_quota;
-		ret = check_bdq(transfer_to[cnt], space, 0, &warn_to[cnt]);
-		if (ret)
+		ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, 0,
+				      &warn_to[cnt]);
+		if (ret) {
+			dquot_decr_inodes(transfer_to[cnt], inode_usage);
 			goto over_quota;
+		}
 	}
 
-	/*
-	 * Finally perform the needed transfer from transfer_from to transfer_to
-	 */
+	/* Decrease usage for source structures and update quota pointers */
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 		if (!is_valid[cnt])
 			continue;
 		/* Due to IO error we might not have transfer_from[] structure */
 		if (transfer_from[cnt]) {
 			int wtype;
+
+			spin_lock(&transfer_from[cnt]->dq_dqb_lock);
 			wtype = info_idq_free(transfer_from[cnt], inode_usage);
 			if (wtype != QUOTA_NL_NOWARN)
 				prepare_warning(&warn_from_inodes[cnt],
 						transfer_from[cnt], wtype);
-			wtype = info_bdq_free(transfer_from[cnt], space);
+			wtype = info_bdq_free(transfer_from[cnt],
+					      cur_space + rsv_space);
 			if (wtype != QUOTA_NL_NOWARN)
 				prepare_warning(&warn_from_space[cnt],
 						transfer_from[cnt], wtype);
@@ -1992,14 +2007,11 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 			dquot_decr_space(transfer_from[cnt], cur_space);
 			dquot_free_reserved_space(transfer_from[cnt],
 						  rsv_space);
+			spin_unlock(&transfer_from[cnt]->dq_dqb_lock);
 		}
-
-		dquot_incr_inodes(transfer_to[cnt], inode_usage);
-		dquot_incr_space(transfer_to[cnt], cur_space);
-		dquot_resv_space(transfer_to[cnt], rsv_space);
-
 		i_dquot(inode)[cnt] = transfer_to[cnt];
 	}
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&dq_data_lock);
 
 	mark_all_dquot_dirty(transfer_from);
@@ -2013,6 +2025,17 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 			transfer_to[cnt] = transfer_from[cnt];
 	return 0;
 over_quota:
+	/* Back out changes we already did */
+	for (cnt--; cnt >= 0; cnt--) {
+		if (!is_valid[cnt])
+			continue;
+		spin_lock(&transfer_to[cnt]->dq_dqb_lock);
+		dquot_decr_inodes(transfer_to[cnt], inode_usage);
+		dquot_decr_space(transfer_to[cnt], cur_space);
+		dquot_free_reserved_space(transfer_to[cnt], rsv_space);
+		spin_unlock(&transfer_to[cnt]->dq_dqb_lock);
+	}
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&dq_data_lock);
 	flush_warnings(warn_to);
 	return ret;
@@ -2066,29 +2089,21 @@ EXPORT_SYMBOL(dquot_transfer);
  */
 int dquot_commit_info(struct super_block *sb, int type)
 {
-	int ret;
 	struct quota_info *dqopt = sb_dqopt(sb);
 
-	mutex_lock(&dqopt->dqio_mutex);
-	ret = dqopt->ops[type]->write_file_info(sb, type);
-	mutex_unlock(&dqopt->dqio_mutex);
-	return ret;
+	return dqopt->ops[type]->write_file_info(sb, type);
 }
 EXPORT_SYMBOL(dquot_commit_info);
 
 int dquot_get_next_id(struct super_block *sb, struct kqid *qid)
 {
 	struct quota_info *dqopt = sb_dqopt(sb);
-	int err;
 
 	if (!sb_has_quota_active(sb, qid->type))
 		return -ESRCH;
 	if (!dqopt->ops[qid->type]->get_next_id)
 		return -ENOSYS;
-	mutex_lock(&dqopt->dqio_mutex);
-	err = dqopt->ops[qid->type]->get_next_id(sb, qid);
-	mutex_unlock(&dqopt->dqio_mutex);
-	return err;
+	return dqopt->ops[qid->type]->get_next_id(sb, qid);
 }
 EXPORT_SYMBOL(dquot_get_next_id);
 
@@ -2337,15 +2352,14 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
 	dqopt->info[type].dqi_format = fmt;
 	dqopt->info[type].dqi_fmt_id = format_id;
 	INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list);
-	mutex_lock(&dqopt->dqio_mutex);
 	error = dqopt->ops[type]->read_file_info(sb, type);
-	if (error < 0) {
-		mutex_unlock(&dqopt->dqio_mutex);
+	if (error < 0)
 		goto out_file_init;
-	}
-	if (dqopt->flags & DQUOT_QUOTA_SYS_FILE)
+	if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) {
+		spin_lock(&dq_data_lock);
 		dqopt->info[type].dqi_flags |= DQF_SYS_FILE;
-	mutex_unlock(&dqopt->dqio_mutex);
+		spin_unlock(&dq_data_lock);
+	}
 	spin_lock(&dq_state_lock);
 	dqopt->flags |= dquot_state_flag(flags, type);
 	spin_unlock(&dq_state_lock);
@@ -2572,7 +2586,7 @@ static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 	struct mem_dqblk *dm = &dquot->dq_dqb;
 
 	memset(di, 0, sizeof(*di));
-	spin_lock(&dq_data_lock);
+	spin_lock(&dquot->dq_dqb_lock);
 	di->d_spc_hardlimit = dm->dqb_bhardlimit;
 	di->d_spc_softlimit = dm->dqb_bsoftlimit;
 	di->d_ino_hardlimit = dm->dqb_ihardlimit;
@@ -2581,7 +2595,7 @@ static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 	di->d_ino_count = dm->dqb_curinodes;
 	di->d_spc_timer = dm->dqb_btime;
 	di->d_ino_timer = dm->dqb_itime;
-	spin_unlock(&dq_data_lock);
+	spin_unlock(&dquot->dq_dqb_lock);
 }
 
 int dquot_get_dqblk(struct super_block *sb, struct kqid qid,
@@ -2645,7 +2659,7 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 	     (di->d_ino_hardlimit > dqi->dqi_max_ino_limit)))
 		return -ERANGE;
 
-	spin_lock(&dq_data_lock);
+	spin_lock(&dquot->dq_dqb_lock);
 	if (di->d_fieldmask & QC_SPACE) {
 		dm->dqb_curspace = di->d_space - dm->dqb_rsvspace;
 		check_blim = 1;
@@ -2711,7 +2725,7 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 		clear_bit(DQ_FAKE_B, &dquot->dq_flags);
 	else
 		set_bit(DQ_FAKE_B, &dquot->dq_flags);
-	spin_unlock(&dq_data_lock);
+	spin_unlock(&dquot->dq_dqb_lock);
 	mark_dquot_dirty(dquot);
 
 	return 0;
diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c
index 0738972..bb3f59b 100644
--- a/fs/quota/quota_tree.c
+++ b/fs/quota/quota_tree.c
@@ -379,7 +379,7 @@ int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
 	if (!ddquot)
 		return -ENOMEM;
 
-	/* dq_off is guarded by dqio_mutex */
+	/* dq_off is guarded by dqio_sem */
 	if (!dquot->dq_off) {
 		ret = dq_insert_tree(info, dquot);
 		if (ret < 0) {
@@ -389,9 +389,9 @@ int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
 			return ret;
 		}
 	}
-	spin_lock(&dq_data_lock);
+	spin_lock(&dquot->dq_dqb_lock);
 	info->dqi_ops->mem2disk_dqblk(ddquot, dquot);
-	spin_unlock(&dq_data_lock);
+	spin_unlock(&dquot->dq_dqb_lock);
 	ret = sb->s_op->quota_write(sb, type, ddquot, info->dqi_entry_size,
 				    dquot->dq_off);
 	if (ret != info->dqi_entry_size) {
@@ -649,14 +649,14 @@ int qtree_read_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
 		kfree(ddquot);
 		goto out;
 	}
-	spin_lock(&dq_data_lock);
+	spin_lock(&dquot->dq_dqb_lock);
 	info->dqi_ops->disk2mem_dqblk(dquot, ddquot);
 	if (!dquot->dq_dqb.dqb_bhardlimit &&
 	    !dquot->dq_dqb.dqb_bsoftlimit &&
 	    !dquot->dq_dqb.dqb_ihardlimit &&
 	    !dquot->dq_dqb.dqb_isoftlimit)
 		set_bit(DQ_FAKE_B, &dquot->dq_flags);
-	spin_unlock(&dq_data_lock);
+	spin_unlock(&dquot->dq_dqb_lock);
 	kfree(ddquot);
 out:
 	dqstats_inc(DQST_READS);
diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c
index 8fe79be..7ac5298 100644
--- a/fs/quota/quota_v1.c
+++ b/fs/quota/quota_v1.c
@@ -56,8 +56,9 @@ static int v1_read_dqblk(struct dquot *dquot)
 {
 	int type = dquot->dq_id.type;
 	struct v1_disk_dqblk dqblk;
+	struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
 
-	if (!sb_dqopt(dquot->dq_sb)->files[type])
+	if (!dqopt->files[type])
 		return -EINVAL;
 
 	/* Set structure to 0s in case read fails/is after end of file */
@@ -160,6 +161,7 @@ static int v1_read_file_info(struct super_block *sb, int type)
 	struct v1_disk_dqblk dqblk;
 	int ret;
 
+	down_read(&dqopt->dqio_sem);
 	ret = sb->s_op->quota_read(sb, type, (char *)&dqblk,
 				sizeof(struct v1_disk_dqblk), v1_dqoff(0));
 	if (ret != sizeof(struct v1_disk_dqblk)) {
@@ -176,6 +178,7 @@ static int v1_read_file_info(struct super_block *sb, int type)
 	dqopt->info[type].dqi_bgrace =
 			dqblk.dqb_btime ? dqblk.dqb_btime : MAX_DQ_TIME;
 out:
+	up_read(&dqopt->dqio_sem);
 	return ret;
 }
 
@@ -185,7 +188,7 @@ static int v1_write_file_info(struct super_block *sb, int type)
 	struct v1_disk_dqblk dqblk;
 	int ret;
 
-	dqopt->info[type].dqi_flags &= ~DQF_INFO_DIRTY;
+	down_write(&dqopt->dqio_sem);
 	ret = sb->s_op->quota_read(sb, type, (char *)&dqblk,
 				sizeof(struct v1_disk_dqblk), v1_dqoff(0));
 	if (ret != sizeof(struct v1_disk_dqblk)) {
@@ -193,8 +196,11 @@ static int v1_write_file_info(struct super_block *sb, int type)
 			ret = -EIO;
 		goto out;
 	}
+	spin_lock(&dq_data_lock);
+	dqopt->info[type].dqi_flags &= ~DQF_INFO_DIRTY;
 	dqblk.dqb_itime = dqopt->info[type].dqi_igrace;
 	dqblk.dqb_btime = dqopt->info[type].dqi_bgrace;
+	spin_unlock(&dq_data_lock);
 	ret = sb->s_op->quota_write(sb, type, (char *)&dqblk,
 	      sizeof(struct v1_disk_dqblk), v1_dqoff(0));
 	if (ret == sizeof(struct v1_disk_dqblk))
@@ -202,6 +208,7 @@ static int v1_write_file_info(struct super_block *sb, int type)
 	else if (ret > 0)
 		ret = -EIO;
 out:
+	up_write(&dqopt->dqio_sem);
 	return ret;
 }
 
diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c
index 2259329..c0187cd 100644
--- a/fs/quota/quota_v2.c
+++ b/fs/quota/quota_v2.c
@@ -65,9 +65,11 @@ static int v2_read_header(struct super_block *sb, int type,
 	if (size != sizeof(struct v2_disk_dqheader)) {
 		quota_error(sb, "Failed header read: expected=%zd got=%zd",
 			    sizeof(struct v2_disk_dqheader), size);
-		return 0;
+		if (size < 0)
+			return size;
+		return -EIO;
 	}
-	return 1;
+	return 0;
 }
 
 /* Check whether given file is really vfsv0 quotafile */
@@ -77,7 +79,7 @@ static int v2_check_quota_file(struct super_block *sb, int type)
 	static const uint quota_magics[] = V2_INITQMAGICS;
 	static const uint quota_versions[] = V2_INITQVERSIONS;
  
-	if (!v2_read_header(sb, type, &dqhead))
+	if (v2_read_header(sb, type, &dqhead))
 		return 0;
 	if (le32_to_cpu(dqhead.dqh_magic) != quota_magics[type] ||
 	    le32_to_cpu(dqhead.dqh_version) > quota_versions[type])
@@ -90,28 +92,39 @@ static int v2_read_file_info(struct super_block *sb, int type)
 {
 	struct v2_disk_dqinfo dinfo;
 	struct v2_disk_dqheader dqhead;
-	struct mem_dqinfo *info = sb_dqinfo(sb, type);
+	struct quota_info *dqopt = sb_dqopt(sb);
+	struct mem_dqinfo *info = &dqopt->info[type];
 	struct qtree_mem_dqinfo *qinfo;
 	ssize_t size;
 	unsigned int version;
+	int ret;
 
-	if (!v2_read_header(sb, type, &dqhead))
-		return -1;
+	down_read(&dqopt->dqio_sem);
+	ret = v2_read_header(sb, type, &dqhead);
+	if (ret < 0)
+		goto out;
 	version = le32_to_cpu(dqhead.dqh_version);
 	if ((info->dqi_fmt_id == QFMT_VFS_V0 && version != 0) ||
-	    (info->dqi_fmt_id == QFMT_VFS_V1 && version != 1))
-		return -1;
+	    (info->dqi_fmt_id == QFMT_VFS_V1 && version != 1)) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	size = sb->s_op->quota_read(sb, type, (char *)&dinfo,
 	       sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF);
 	if (size != sizeof(struct v2_disk_dqinfo)) {
 		quota_error(sb, "Can't read info structure");
-		return -1;
+		if (size < 0)
+			ret = size;
+		else
+			ret = -EIO;
+		goto out;
 	}
 	info->dqi_priv = kmalloc(sizeof(struct qtree_mem_dqinfo), GFP_NOFS);
-	if (!info->dqi_priv)
-		return -ENOMEM;
-
+	if (!info->dqi_priv) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	qinfo = info->dqi_priv;
 	if (version == 0) {
 		/* limits are stored as unsigned 32-bit data */
@@ -145,17 +158,22 @@ static int v2_read_file_info(struct super_block *sb, int type)
 		qinfo->dqi_entry_size = sizeof(struct v2r1_disk_dqblk);
 		qinfo->dqi_ops = &v2r1_qtree_ops;
 	}
-	return 0;
+	ret = 0;
+out:
+	up_read(&dqopt->dqio_sem);
+	return ret;
 }
 
 /* Write information header to quota file */
 static int v2_write_file_info(struct super_block *sb, int type)
 {
 	struct v2_disk_dqinfo dinfo;
-	struct mem_dqinfo *info = sb_dqinfo(sb, type);
+	struct quota_info *dqopt = sb_dqopt(sb);
+	struct mem_dqinfo *info = &dqopt->info[type];
 	struct qtree_mem_dqinfo *qinfo = info->dqi_priv;
 	ssize_t size;
 
+	down_write(&dqopt->dqio_sem);
 	spin_lock(&dq_data_lock);
 	info->dqi_flags &= ~DQF_INFO_DIRTY;
 	dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace);
@@ -168,6 +186,7 @@ static int v2_write_file_info(struct super_block *sb, int type)
 	dinfo.dqi_free_entry = cpu_to_le32(qinfo->dqi_free_entry);
 	size = sb->s_op->quota_write(sb, type, (char *)&dinfo,
 	       sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF);
+	up_write(&dqopt->dqio_sem);
 	if (size != sizeof(struct v2_disk_dqinfo)) {
 		quota_error(sb, "Can't write info structure");
 		return -1;
@@ -283,17 +302,51 @@ static int v2r1_is_id(void *dp, struct dquot *dquot)
 
 static int v2_read_dquot(struct dquot *dquot)
 {
-	return qtree_read_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot);
+	struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
+	int ret;
+
+	down_read(&dqopt->dqio_sem);
+	ret = qtree_read_dquot(
+			sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv,
+			dquot);
+	up_read(&dqopt->dqio_sem);
+	return ret;
 }
 
 static int v2_write_dquot(struct dquot *dquot)
 {
-	return qtree_write_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot);
+	struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
+	int ret;
+	bool alloc = false;
+
+	/*
+	 * If space for dquot is already allocated, we don't need any
+	 * protection as we'll only overwrite the place of dquot. We are
+	 * still protected by concurrent writes of the same dquot by
+	 * dquot->dq_lock.
+	 */
+	if (!dquot->dq_off) {
+		alloc = true;
+		down_write(&dqopt->dqio_sem);
+	}
+	ret = qtree_write_dquot(
+			sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv,
+			dquot);
+	if (alloc)
+		up_write(&dqopt->dqio_sem);
+	return ret;
 }
 
 static int v2_release_dquot(struct dquot *dquot)
 {
-	return qtree_release_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot);
+	struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
+	int ret;
+
+	down_write(&dqopt->dqio_sem);
+	ret = qtree_release_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot);
+	up_write(&dqopt->dqio_sem);
+
+	return ret;
 }
 
 static int v2_free_file_info(struct super_block *sb, int type)
@@ -304,7 +357,13 @@ static int v2_free_file_info(struct super_block *sb, int type)
 
 static int v2_get_next_id(struct super_block *sb, struct kqid *qid)
 {
-	return qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid);
+	struct quota_info *dqopt = sb_dqopt(sb);
+	int ret;
+
+	down_read(&dqopt->dqio_sem);
+	ret = qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid);
+	up_read(&dqopt->dqio_sem);
+	return ret;
 }
 
 static const struct quota_format_ops v2_format_ops = {
diff --git a/fs/stat.c b/fs/stat.c
index c356108..8a6aa8c 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -710,7 +710,7 @@ loff_t inode_get_bytes(struct inode *inode)
 	loff_t ret;
 
 	spin_lock(&inode->i_lock);
-	ret = (((loff_t)inode->i_blocks) << 9) + inode->i_bytes;
+	ret = __inode_get_bytes(inode);
 	spin_unlock(&inode->i_lock);
 	return ret;
 }
diff --git a/fs/super.c b/fs/super.c
index 6bc3352..221cfa1 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -242,7 +242,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 	atomic_set(&s->s_active, 1);
 	mutex_init(&s->s_vfs_rename_mutex);
 	lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);
-	mutex_init(&s->s_dquot.dqio_mutex);
+	init_rwsem(&s->s_dquot.dqio_sem);
 	s->s_maxbytes = MAX_NON_LFS;
 	s->s_op = &default_op;
 	s->s_time_gran = 1000000000;