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
  ...

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,

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);

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 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 		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),

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);

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;
 }
 

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 = {

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;
 }

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;

include/linux/fs.h

@@ -3015,6 +3015,10 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes);
 void inode_add_bytes(struct inode *inode, loff_t bytes);
 void __inode_sub_bytes(struct inode *inode, loff_t bytes);
 void inode_sub_bytes(struct inode *inode, loff_t bytes);
+static inline loff_t __inode_get_bytes(struct inode *inode)
+{
+	return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes;
+}
 loff_t inode_get_bytes(struct inode *inode);
 void inode_set_bytes(struct inode *inode, loff_t bytes);
 const char *simple_get_link(struct dentry *, struct inode *,

include/linux/quota.h

@@ -223,12 +223,12 @@ struct mem_dqinfo {
 	struct quota_format_type *dqi_format;
 	int dqi_fmt_id;		/* Id of the dqi_format - used when turning
 				 * quotas on after remount RW */
-	struct list_head dqi_dirty_list;	/* List of dirty dquots */
-	unsigned long dqi_flags;
-	unsigned int dqi_bgrace;
-	unsigned int dqi_igrace;
-	qsize_t dqi_max_spc_limit;
-	qsize_t dqi_max_ino_limit;
+	struct list_head dqi_dirty_list;	/* List of dirty dquots [dq_list_lock] */
+	unsigned long dqi_flags;	/* DFQ_ flags [dq_data_lock] */
+	unsigned int dqi_bgrace;	/* Space grace time [dq_data_lock] */
+	unsigned int dqi_igrace;	/* Inode grace time [dq_data_lock] */
+	qsize_t dqi_max_spc_limit;	/* Maximum space limit [static] */
+	qsize_t dqi_max_ino_limit;	/* Maximum inode limit [static] */
 	void *dqi_priv;
 };
 
@@ -293,18 +293,18 @@ static inline void dqstats_dec(unsigned int type)
 				 * clear them when it sees fit. */
 
 struct dquot {
-	struct hlist_node dq_hash;	/* Hash list in memory */
-	struct list_head dq_inuse;	/* List of all quotas */
-	struct list_head dq_free;	/* Free list element */
-	struct list_head dq_dirty;	/* List of dirty dquots */
+	struct hlist_node dq_hash;	/* Hash list in memory [dq_list_lock] */
+	struct list_head dq_inuse;	/* List of all quotas [dq_list_lock] */
+	struct list_head dq_free;	/* Free list element [dq_list_lock] */
+	struct list_head dq_dirty;	/* List of dirty dquots [dq_list_lock] */
 	struct mutex dq_lock;		/* dquot IO lock */
+	spinlock_t dq_dqb_lock;		/* Lock protecting dq_dqb changes */
 	atomic_t dq_count;		/* Use count */
-	wait_queue_head_t dq_wait_unused;	/* Wait queue for dquot to become unused */
 	struct super_block *dq_sb;	/* superblock this applies to */
 	struct kqid dq_id;		/* ID this applies to (uid, gid, projid) */
-	loff_t dq_off;			/* Offset of dquot on disk */
+	loff_t dq_off;			/* Offset of dquot on disk [dq_lock, stable once set] */
 	unsigned long dq_flags;		/* See DQ_* */
-	struct mem_dqblk dq_dqb;	/* Diskquota usage */
+	struct mem_dqblk dq_dqb;	/* Diskquota usage [dq_dqb_lock] */
 };
 
 /* Operations which must be implemented by each quota format */
@@ -491,6 +491,9 @@ enum {
 						 */
 #define DQUOT_NEGATIVE_USAGE	(1 << (DQUOT_STATE_LAST + 1))
 					       /* Allow negative quota usage */
+/* Do not track dirty dquots in a list */
+#define DQUOT_NOLIST_DIRTY	(1 << (DQUOT_STATE_LAST + 2))
+
 static inline unsigned int dquot_state_flag(unsigned int flags, int type)
 {
 	return flags << type;
@@ -521,7 +524,7 @@ static inline void quota_send_warning(struct kqid qid, dev_t dev,
 
 struct quota_info {
 	unsigned int flags;			/* Flags for diskquotas on this device */
-	struct mutex dqio_mutex;		/* lock device while I/O in progress */
+	struct rw_semaphore dqio_sem;		/* Lock quota file while I/O in progress */
 	struct inode *files[MAXQUOTAS];		/* inodes of quotafiles */
 	struct mem_dqinfo info[MAXQUOTAS];	/* Information for each quota type */
 	const struct quota_format_ops *ops[MAXQUOTAS];	/* Operations for each type */

include/linux/quotaops.h

@@ -38,11 +38,6 @@ void __quota_error(struct super_block *sb, const char *func,
 /*
  * declaration of quota_function calls in kernel.
  */
-void inode_add_rsv_space(struct inode *inode, qsize_t number);
-void inode_claim_rsv_space(struct inode *inode, qsize_t number);
-void inode_sub_rsv_space(struct inode *inode, qsize_t number);
-void inode_reclaim_rsv_space(struct inode *inode, qsize_t number);
-
 int dquot_initialize(struct inode *inode);
 bool dquot_initialize_needed(struct inode *inode);
 void dquot_drop(struct inode *inode);