Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 bug fixes from Ted Ts'o:
"Various bug fixes for ext4. The most important is a fix for the new
extent cache's slab shrinker which can cause significant, user-visible
pauses when the system is under memory pressure."

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
ext4: enable quotas before orphan cleanup
ext4: don't allow quota mount options when quota feature enabled
ext4: fix a warning from sparse check for ext4_dir_llseek
ext4: convert number of blocks to clusters properly
ext4: fix possible memory leak in ext4_remount()
jbd2: fix ERR_PTR dereference in jbd2__journal_start
ext4: use percpu counter for extent cache count
ext4: optimize ext4_es_shrink()

fs/ext4/balloc.c

···
 	brelse(bitmap_bh);
 	printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
 	       ", computed = %llu, %llu\n",
-	       EXT4_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
+	       EXT4_NUM_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
 	       desc_count, bitmap_count);
 	return bitmap_count;
 #else

fs/ext4/dir.c

···
  *
  * For non-htree, ext4_llseek already chooses the proper max offset.
  */
-loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence)
+static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	int dx_dir = is_dx_dir(inode);

fs/ext4/ext4.h

···
 	/* Reclaim extents from extent status tree */
 	struct shrinker s_es_shrinker;
 	struct list_head s_es_lru;
+	struct percpu_counter s_extent_cache_cnt;
 	spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
 };
 

fs/ext4/extents_status.c

···
 			      ext4_lblk_t end);
 static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
 				       int nr_to_scan);
-static int ext4_es_reclaim_extents_count(struct super_block *sb);
 
 int __init ext4_init_es(void)
 {
-	ext4_es_cachep = KMEM_CACHE(extent_status, SLAB_RECLAIM_ACCOUNT);
+	ext4_es_cachep = kmem_cache_create("ext4_extent_status",
+					   sizeof(struct extent_status),
+					   0, (SLAB_RECLAIM_ACCOUNT), NULL);
 	if (ext4_es_cachep == NULL)
 		return -ENOMEM;
 	return 0;
···
 	/*
 	 * We don't count delayed extent because we never try to reclaim them
 	 */
-	if (!ext4_es_is_delayed(es))
+	if (!ext4_es_is_delayed(es)) {
 		EXT4_I(inode)->i_es_lru_nr++;
+		percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+	}
 
 	return es;
 }
···
 	if (!ext4_es_is_delayed(es)) {
 		BUG_ON(EXT4_I(inode)->i_es_lru_nr == 0);
 		EXT4_I(inode)->i_es_lru_nr--;
+		percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
 	}
 
 	kmem_cache_free(ext4_es_cachep, es);
···
 	int nr_to_scan = sc->nr_to_scan;
 	int ret, nr_shrunk = 0;
 
-	trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan);
+	ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
+	trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret);
 
 	if (!nr_to_scan)
-		return ext4_es_reclaim_extents_count(sbi->s_sb);
+		return ret;
 
 	INIT_LIST_HEAD(&scanned);
 
···
 	}
 	list_splice_tail(&scanned, &sbi->s_es_lru);
 	spin_unlock(&sbi->s_es_lru_lock);
-	trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk);
 
-	return ext4_es_reclaim_extents_count(sbi->s_sb);
+	ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
+	trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
+	return ret;
 }
 
 void ext4_es_register_shrinker(struct super_block *sb)
···
 	if (!list_empty(&ei->i_es_lru))
 		list_del_init(&ei->i_es_lru);
 	spin_unlock(&sbi->s_es_lru_lock);
-}
-
-static int ext4_es_reclaim_extents_count(struct super_block *sb)
-{
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_inode_info *ei;
-	struct list_head *cur;
-	int nr_cached = 0;
-
-	spin_lock(&sbi->s_es_lru_lock);
-	list_for_each(cur, &sbi->s_es_lru) {
-		ei = list_entry(cur, struct ext4_inode_info, i_es_lru);
-		read_lock(&ei->i_es_lock);
-		nr_cached += ei->i_es_lru_nr;
-		read_unlock(&ei->i_es_lock);
-	}
-	spin_unlock(&sbi->s_es_lru_lock);
-	trace_ext4_es_reclaim_extents_count(sb, nr_cached);
-	return nr_cached;
 }
 
 static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,

fs/ext4/mballoc.c

···
 			win = offs;
 
 		ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical -
-			EXT4_B2C(sbi, win);
+			EXT4_NUM_B2C(sbi, win);
 		BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
 		BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
 	}
···
 			EXT4_BLOCKS_PER_GROUP(sb);
 		count -= overflow;
 	}
-	count_clusters = EXT4_B2C(sbi, count);
+	count_clusters = EXT4_NUM_B2C(sbi, count);
 	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
 	if (!bitmap_bh) {
 		err = -EIO;
···
 	ext4_group_desc_csum_set(sb, block_group, desc);
 	ext4_unlock_group(sb, block_group);
 	percpu_counter_add(&sbi->s_freeclusters_counter,
-			   EXT4_B2C(sbi, blocks_freed));
+			   EXT4_NUM_B2C(sbi, blocks_freed));
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic_add(EXT4_B2C(sbi, blocks_freed),
+		atomic_add(EXT4_NUM_B2C(sbi, blocks_freed),
 			   &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 

fs/ext4/resize.c

···
 
 		ext4_inode_table_set(sb, gdp, group_data->inode_table);
 		ext4_free_group_clusters_set(sb, gdp,
-					     EXT4_B2C(sbi, group_data->free_blocks_count));
+			EXT4_NUM_B2C(sbi, group_data->free_blocks_count));
 		ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
 		if (ext4_has_group_desc_csum(sb))
 			ext4_itable_unused_set(sb, gdp,
···
 
 	/* Update the free space counts */
 	percpu_counter_add(&sbi->s_freeclusters_counter,
-			   EXT4_B2C(sbi, free_blocks));
+			   EXT4_NUM_B2C(sbi, free_blocks));
 	percpu_counter_add(&sbi->s_freeinodes_counter,
 			   EXT4_INODES_PER_GROUP(sb) * flex_gd->count);
 
···
 	    sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group;
 		flex_group = ext4_flex_group(sbi, group_data[0].group);
-		atomic_add(EXT4_B2C(sbi, free_blocks),
+		atomic_add(EXT4_NUM_B2C(sbi, free_blocks),
 			   &sbi->s_flex_groups[flex_group].free_clusters);
 		atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
 			   &sbi->s_flex_groups[flex_group].free_inodes);

fs/ext4/super.c

···
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_counter_destroy(&sbi->s_extent_cache_cnt);
 	brelse(sbi->s_sbh);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < MAXQUOTAS; i++)
···
 			"quota options when quota turned on");
 		return -1;
 	}
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) {
+		ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options "
+			 "when QUOTA feature is enabled");
+		return -1;
+	}
 	qname = match_strdup(args);
 	if (!qname) {
 		ext4_msg(sb, KERN_ERR,
···
 				 "quota options when quota turned on");
 			return -1;
 		}
+		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+					       EXT4_FEATURE_RO_COMPAT_QUOTA)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Cannot set journaled quota options "
+				 "when QUOTA feature is enabled");
+			return -1;
+		}
 		sbi->s_jquota_fmt = m->mount_opt;
 #endif
 	} else {
···
 			return 0;
 	}
 #ifdef CONFIG_QUOTA
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
+	    (test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) {
+		ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA "
+			 "feature is enabled");
+		return 0;
+	}
 	if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
 		if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
 			clear_opt(sb, USRQUOTA);
···
 	}
 	/* Add the journal blocks as well */
 	if (sbi->s_journal)
-		overhead += EXT4_B2C(sbi, sbi->s_journal->j_maxlen);
+		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
 
 	sbi->s_overhead = overhead;
 	smp_wmb();
···
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
 	}
+	if (!err) {
+		err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0);
+	}
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");
 		goto failed_mount3;
···
 	sb->s_export_op = &ext4_export_ops;
 	sb->s_xattr = ext4_xattr_handlers;
 #ifdef CONFIG_QUOTA
-	sb->s_qcop = &ext4_qctl_operations;
 	sb->dq_op = &ext4_quota_operations;
-
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) {
-		/* Use qctl operations for hidden quota files. */
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA))
 		sb->s_qcop = &ext4_qctl_sysfile_operations;
-	}
+	else
+		sb->s_qcop = &ext4_qctl_operations;
 #endif
 	memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
 
···
 	if (err)
 		goto failed_mount7;
 
+#ifdef CONFIG_QUOTA
+	/* Enable quota usage during mount. */
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
+	    !(sb->s_flags & MS_RDONLY)) {
+		err = ext4_enable_quotas(sb);
+		if (err)
+			goto failed_mount8;
+	}
+#endif  /* CONFIG_QUOTA */
+
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
 	EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
···
 			descr = " writeback data mode";
 	} else
 		descr = "out journal";
-
-#ifdef CONFIG_QUOTA
-	/* Enable quota usage during mount. */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
-	    !(sb->s_flags & MS_RDONLY)) {
-		err = ext4_enable_quotas(sb);
-		if (err)
-			goto failed_mount8;
-	}
-#endif  /* CONFIG_QUOTA */
 
 	if (test_opt(sb, DISCARD)) {
 		struct request_queue *q = bdev_get_queue(sb->s_bdev);
···
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_counter_destroy(&sbi->s_extent_cache_cnt);
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:
···
 			if (!old_opts.s_qf_names[i]) {
 				for (j = 0; j < i; j++)
 					kfree(old_opts.s_qf_names[j]);
+				kfree(orig_data);
 				return -ENOMEM;
 			}
 		} else
···
 
 static int ext4_mark_dquot_dirty(struct dquot *dquot)
 {
+	struct super_block *sb = dquot->dq_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
 	/* Are we journaling quotas? */
-	if (EXT4_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
-	    EXT4_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) ||
+	    sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
 		dquot_mark_dquot_dirty(dquot);
 		return ext4_write_dquot(dquot);
 	} else {

fs/jbd2/transaction.c

···
 	if (err < 0) {
 		jbd2_free_handle(handle);
 		current->journal_info = NULL;
-		handle = ERR_PTR(err);
+		return ERR_PTR(err);
 	}
 	handle->h_type = type;
 	handle->h_line_no = line_no;

include/trace/events/ext4.h

···
 		  __entry->found ? __entry->status : 0)
 );
 
-TRACE_EVENT(ext4_es_reclaim_extents_count,
-	TP_PROTO(struct super_block *sb, int nr_cached),
-
-	TP_ARGS(sb, nr_cached),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	int,	nr_cached		)
-	),
-
-	TP_fast_assign(
-		__entry->dev		= sb->s_dev;
-		__entry->nr_cached	= nr_cached;
-	),
-
-	TP_printk("dev %d,%d cached objects nr %d",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->nr_cached)
-);
-
 TRACE_EVENT(ext4_es_shrink_enter,
-	TP_PROTO(struct super_block *sb, int nr_to_scan),
+	TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt),
 
-	TP_ARGS(sb, nr_to_scan),
+	TP_ARGS(sb, nr_to_scan, cache_cnt),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	int,	nr_to_scan		)
+		__field(	int,	cache_cnt		)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
 		__entry->nr_to_scan	= nr_to_scan;
+		__entry->cache_cnt	= cache_cnt;
 	),
 
-	TP_printk("dev %d,%d nr to scan %d",
+	TP_printk("dev %d,%d nr_to_scan %d cache_cnt %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->nr_to_scan)
+		  __entry->nr_to_scan, __entry->cache_cnt)
 );
 
 TRACE_EVENT(ext4_es_shrink_exit,
-	TP_PROTO(struct super_block *sb, int shrunk_nr),
+	TP_PROTO(struct super_block *sb, int shrunk_nr, int cache_cnt),
 
-	TP_ARGS(sb, shrunk_nr),
+	TP_ARGS(sb, shrunk_nr, cache_cnt),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	int,	shrunk_nr		)
+		__field(	int,	cache_cnt		)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
 		__entry->shrunk_nr	= shrunk_nr;
+		__entry->cache_cnt	= cache_cnt;
 	),
 
-	TP_printk("dev %d,%d nr to scan %d",
+	TP_printk("dev %d,%d shrunk_nr %d cache_cnt %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->shrunk_nr)
+		  __entry->shrunk_nr, __entry->cache_cnt)
 );
 
 #endif /* _TRACE_EXT4_H */