btrfs: publish allocation data in sysfs

While trying to debug ENOSPC issues, it's helpful to understand what the
kernel's view of the available space is. We export this information
via ioctl, but sysfs files are more easily used.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <clm@fb.com>

4 files changed, 238 insertions, 5 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index c5c888f..f608306 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1151,6 +1151,9 @@ struct btrfs_space_info {
 	spinlock_t lock;
 	struct rw_semaphore groups_sem;
 	wait_queue_head_t wait;
+
+	struct kobject kobj;
+	struct kobject block_group_kobjs[BTRFS_NR_RAID_TYPES];
 };
 
 #define	BTRFS_BLOCK_RSV_GLOBAL		1
@@ -1526,6 +1529,7 @@ struct btrfs_fs_info {
 	int thread_pool_size;
 
 	struct kobject super_kobj;
+	struct kobject *space_info_kobj;
 	struct completion kobj_unregister;
 	int do_barriers;
 	int closing;
@@ -3178,6 +3182,7 @@ struct btrfs_block_group_cache *btrfs_lookup_block_group(
 						 struct btrfs_fs_info *info,
 						 u64 bytenr);
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
+int get_block_group_index(struct btrfs_block_group_cache *cache);
 struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 					struct btrfs_root *root, u32 blocksize,
 					u64 parent, u64 root_objectid,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d15b4fc..e094d02 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -35,6 +35,7 @@
 #include "locking.h"
 #include "free-space-cache.h"
 #include "math.h"
+#include "sysfs.h"
 
 #undef SCRAMBLE_DELAYED_REFS
 
@@ -3408,6 +3409,23 @@ int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr)
 	return readonly;
 }
 
+static const char *alloc_name(u64 flags)
+{
+	switch (flags) {
+	case BTRFS_BLOCK_GROUP_METADATA|BTRFS_BLOCK_GROUP_DATA:
+		return "mixed";
+	case BTRFS_BLOCK_GROUP_METADATA:
+		return "metadata";
+	case BTRFS_BLOCK_GROUP_DATA:
+		return "data";
+	case BTRFS_BLOCK_GROUP_SYSTEM:
+		return "system";
+	default:
+		WARN_ON(1);
+		return "invalid-combination";
+	};
+}
+
 static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 			     u64 total_bytes, u64 bytes_used,
 			     struct btrfs_space_info **space_info)
@@ -3463,11 +3481,21 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 	found->chunk_alloc = 0;
 	found->flush = 0;
 	init_waitqueue_head(&found->wait);
+
+	ret = kobject_init_and_add(&found->kobj, &space_info_ktype,
+				    info->space_info_kobj, "%s",
+				    alloc_name(found->flags));
+	if (ret) {
+		kfree(found);
+		return ret;
+	}
+
 	*space_info = found;
 	list_add_rcu(&found->list, &info->space_info);
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
 		info->data_sinfo = found;
-	return 0;
+
+	return ret;
 }
 
 static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
@@ -6152,11 +6180,29 @@ int __get_raid_index(u64 flags)
 	return BTRFS_RAID_SINGLE; /* BTRFS_BLOCK_GROUP_SINGLE */
 }
 
-static int get_block_group_index(struct btrfs_block_group_cache *cache)
+int get_block_group_index(struct btrfs_block_group_cache *cache)
 {
 	return __get_raid_index(cache->flags);
 }
 
+static const char *btrfs_raid_type_names[BTRFS_NR_RAID_TYPES] = {
+	[BTRFS_RAID_RAID10]	= "raid10",
+	[BTRFS_RAID_RAID1]	= "raid1",
+	[BTRFS_RAID_DUP]	= "dup",
+	[BTRFS_RAID_RAID0]	= "raid0",
+	[BTRFS_RAID_SINGLE]	= "single",
+	[BTRFS_RAID_RAID5]	= "raid5",
+	[BTRFS_RAID_RAID6]	= "raid6",
+};
+
+const char *get_raid_name(enum btrfs_raid_types type)
+{
+	if (type >= BTRFS_NR_RAID_TYPES)
+		return NULL;
+
+	return btrfs_raid_type_names[type];
+}
+
 enum btrfs_loop_type {
 	LOOP_CACHING_NOWAIT = 0,
 	LOOP_CACHING_WAIT = 1,
@@ -8340,6 +8386,8 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 	release_global_block_rsv(info);
 
 	while (!list_empty(&info->space_info)) {
+		int i;
+
 		space_info = list_entry(info->space_info.next,
 					struct btrfs_space_info,
 					list);
@@ -8350,9 +8398,17 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 				dump_space_info(space_info, 0, 0);
 			}
 		}
-		percpu_counter_destroy(&space_info->total_bytes_pinned);
 		list_del(&space_info->list);
-		kfree(space_info);
+		for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
+			struct kobject *kobj;
+			kobj = &space_info->block_group_kobjs[i];
+			if (kobj->parent) {
+				kobject_del(kobj);
+				kobject_put(kobj);
+			}
+		}
+		kobject_del(&space_info->kobj);
+		kobject_put(&space_info->kobj);
 	}
 	return 0;
 }
@@ -8363,6 +8419,19 @@ static void __link_block_group(struct btrfs_space_info *space_info,
 	int index = get_block_group_index(cache);
 
 	down_write(&space_info->groups_sem);
+	if (list_empty(&space_info->block_groups[index])) {
+		struct kobject *kobj = &space_info->block_group_kobjs[index];
+		int ret;
+
+		kobject_get(&space_info->kobj); /* put in release */
+		ret = kobject_init_and_add(kobj, &btrfs_raid_ktype,
+					   &space_info->kobj,
+					   get_raid_name(index));
+		if (ret) {
+			pr_warn("btrfs: failed to add kobject for block cache. ignoring.\n");
+			kobject_put(&space_info->kobj);
+		}
+	}
 	list_add_tail(&cache->list, &space_info->block_groups[index]);
 	up_write(&space_info->groups_sem);
 }
@@ -8803,8 +8872,11 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * are still on the list after taking the semaphore
 	 */
 	list_del_init(&block_group->list);
-	if (list_empty(&block_group->space_info->block_groups[index]))
+	if (list_empty(&block_group->space_info->block_groups[index])) {
+		kobject_del(&block_group->space_info->block_group_kobjs[index]);
+		kobject_put(&block_group->space_info->block_group_kobjs[index]);
 		clear_avail_alloc_bits(root->fs_info, block_group->flags);
+	}
 	up_write(&block_group->space_info->groups_sem);
 
 	if (block_group->cached == BTRFS_CACHE_STARTED)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 562e346..e060958 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -219,6 +219,140 @@ static const struct attribute_group btrfs_feature_attr_group = {
 	.attrs = btrfs_supported_feature_attrs,
 };
 
+static ssize_t btrfs_show_u64(u64 *value_ptr, spinlock_t *lock, char *buf)
+{
+	u64 val;
+	if (lock)
+		spin_lock(lock);
+	val = *value_ptr;
+	if (lock)
+		spin_unlock(lock);
+	return snprintf(buf, PAGE_SIZE, "%llu\n", val);
+}
+
+static ssize_t global_rsv_size_show(struct kobject *kobj,
+				    struct kobj_attribute *ka, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj->parent);
+	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
+	return btrfs_show_u64(&block_rsv->size, &block_rsv->lock, buf);
+}
+BTRFS_ATTR(global_rsv_size, 0444, global_rsv_size_show);
+
+static ssize_t global_rsv_reserved_show(struct kobject *kobj,
+					struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj->parent);
+	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
+	return btrfs_show_u64(&block_rsv->reserved, &block_rsv->lock, buf);
+}
+BTRFS_ATTR(global_rsv_reserved, 0444, global_rsv_reserved_show);
+
+#define to_space_info(_kobj) container_of(_kobj, struct btrfs_space_info, kobj)
+
+static ssize_t raid_bytes_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *buf);
+BTRFS_RAID_ATTR(total_bytes, raid_bytes_show);
+BTRFS_RAID_ATTR(used_bytes, raid_bytes_show);
+
+static ssize_t raid_bytes_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *buf)
+
+{
+	struct btrfs_space_info *sinfo = to_space_info(kobj->parent);
+	struct btrfs_block_group_cache *block_group;
+	int index = kobj - sinfo->block_group_kobjs;
+	u64 val = 0;
+
+	down_read(&sinfo->groups_sem);
+	list_for_each_entry(block_group, &sinfo->block_groups[index], list) {
+		if (&attr->attr == BTRFS_RAID_ATTR_PTR(total_bytes))
+			val += block_group->key.offset;
+		else
+			val += btrfs_block_group_used(&block_group->item);
+	}
+	up_read(&sinfo->groups_sem);
+	return snprintf(buf, PAGE_SIZE, "%llu\n", val);
+}
+
+static struct attribute *raid_attributes[] = {
+	BTRFS_RAID_ATTR_PTR(total_bytes),
+	BTRFS_RAID_ATTR_PTR(used_bytes),
+	NULL
+};
+
+static void release_raid_kobj(struct kobject *kobj)
+{
+	kobject_put(kobj->parent);
+}
+
+struct kobj_type btrfs_raid_ktype = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = release_raid_kobj,
+	.default_attrs = raid_attributes,
+};
+
+#define SPACE_INFO_ATTR(field)						\
+static ssize_t btrfs_space_info_show_##field(struct kobject *kobj,	\
+					     struct kobj_attribute *a,	\
+					     char *buf)			\
+{									\
+	struct btrfs_space_info *sinfo = to_space_info(kobj);		\
+	return btrfs_show_u64(&sinfo->field, &sinfo->lock, buf);	\
+}									\
+BTRFS_ATTR(field, 0444, btrfs_space_info_show_##field)
+
+static ssize_t btrfs_space_info_show_total_bytes_pinned(struct kobject *kobj,
+						       struct kobj_attribute *a,
+						       char *buf)
+{
+	struct btrfs_space_info *sinfo = to_space_info(kobj);
+	s64 val = percpu_counter_sum(&sinfo->total_bytes_pinned);
+	return snprintf(buf, PAGE_SIZE, "%lld\n", val);
+}
+
+SPACE_INFO_ATTR(flags);
+SPACE_INFO_ATTR(total_bytes);
+SPACE_INFO_ATTR(bytes_used);
+SPACE_INFO_ATTR(bytes_pinned);
+SPACE_INFO_ATTR(bytes_reserved);
+SPACE_INFO_ATTR(bytes_may_use);
+SPACE_INFO_ATTR(disk_used);
+SPACE_INFO_ATTR(disk_total);
+BTRFS_ATTR(total_bytes_pinned, 0444, btrfs_space_info_show_total_bytes_pinned);
+
+static struct attribute *space_info_attrs[] = {
+	BTRFS_ATTR_PTR(flags),
+	BTRFS_ATTR_PTR(total_bytes),
+	BTRFS_ATTR_PTR(bytes_used),
+	BTRFS_ATTR_PTR(bytes_pinned),
+	BTRFS_ATTR_PTR(bytes_reserved),
+	BTRFS_ATTR_PTR(bytes_may_use),
+	BTRFS_ATTR_PTR(disk_used),
+	BTRFS_ATTR_PTR(disk_total),
+	BTRFS_ATTR_PTR(total_bytes_pinned),
+	NULL,
+};
+
+static void space_info_release(struct kobject *kobj)
+{
+	struct btrfs_space_info *sinfo = to_space_info(kobj);
+	percpu_counter_destroy(&sinfo->total_bytes_pinned);
+	kfree(sinfo);
+}
+
+struct kobj_type space_info_ktype = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = space_info_release,
+	.default_attrs = space_info_attrs,
+};
+
+static const struct attribute *allocation_attrs[] = {
+	BTRFS_ATTR_PTR(global_rsv_reserved),
+	BTRFS_ATTR_PTR(global_rsv_size),
+	NULL,
+};
+
 static void btrfs_release_super_kobj(struct kobject *kobj)
 {
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
@@ -239,6 +373,9 @@ static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj)
 
 void btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info)
 {
+	sysfs_remove_files(fs_info->space_info_kobj, allocation_attrs);
+	kobject_del(fs_info->space_info_kobj);
+	kobject_put(fs_info->space_info_kobj);
 	kobject_del(&fs_info->super_kobj);
 	kobject_put(&fs_info->super_kobj);
 	wait_for_completion(&fs_info->kobj_unregister);
@@ -391,6 +528,17 @@ int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info)
 	if (error)
 		goto failure;
 
+	fs_info->space_info_kobj = kobject_create_and_add("allocation",
+						  &fs_info->super_kobj);
+	if (!fs_info->space_info_kobj) {
+		error = -ENOMEM;
+		goto failure;
+	}
+
+	error = sysfs_create_files(fs_info->space_info_kobj, allocation_attrs);
+	if (error)
+		goto failure;
+
 	return 0;
 failure:
 	btrfs_sysfs_remove_one(fs_info);
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index c49fd25..f3cea37 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -22,6 +22,12 @@ static struct kobj_attribute btrfs_attr_##_name =			\
 	BTRFS_ATTR_RW(_name, _mode, _show, NULL)
 #define BTRFS_ATTR_PTR(_name)    (&btrfs_attr_##_name.attr)
 
+#define BTRFS_RAID_ATTR(_name, _show)					\
+static struct kobj_attribute btrfs_raid_attr_##_name =			\
+			__INIT_KOBJ_ATTR(_name, 0444, _show, NULL)
+#define BTRFS_RAID_ATTR_PTR(_name)    (&btrfs_raid_attr_##_name.attr)
+
+
 struct btrfs_feature_attr {
 	struct kobj_attribute kobj_attr;
 	enum btrfs_feature_set feature_set;
@@ -53,4 +59,6 @@ static struct btrfs_feature_attr btrfs_attr_##_name = {			     \
 			to_btrfs_feature_attr(attr_to_btrfs_attr(a))
 char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags);
 extern const char * const btrfs_feature_set_names[3];
+extern struct kobj_type space_info_ktype;
+extern struct kobj_type btrfs_raid_ktype;
 #endif /* _BTRFS_SYSFS_H_ */