[06/11] libceph: journaling: introduce api for journal appending
diff mbox series

Message ID 1543841435-13652-7-git-send-email-dongsheng.yang@easystack.cn
State New
Headers show
Series
  • [01/11] libceph: support prefix and suffix in bio_iter
Related show

Commit Message

Dongsheng Yang Dec. 3, 2018, 12:50 p.m. UTC
This commit introduce 3 APIs for journal recording:

(1) ceph_journaler_allocate_tag()
    This api allocate a new tag for user to get a unified
tag_tid. Then each event appended by this user will be tagged
by this tag_tid.

(2) ceph_journaler_append()
    This api allow user to append event to journal objects.

(3) ceph_journaler_client_committed()
    This api will notify journaling that a event is already
committed, you can remove it from journal if there is no other
client refre to it.

Signed-off-by: Dongsheng Yang <dongsheng.yang@easystack.cn>
---
 include/linux/ceph/journaler.h |  12 +
 net/ceph/journaler.c           | 678 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 690 insertions(+)

Patch
diff mbox series

diff --git a/include/linux/ceph/journaler.h b/include/linux/ceph/journaler.h
index acc1c6f..a8c1838 100644
--- a/include/linux/ceph/journaler.h
+++ b/include/linux/ceph/journaler.h
@@ -132,6 +132,7 @@  struct ceph_journaler {
 
 	struct workqueue_struct	*task_wq;
 	struct workqueue_struct	*finish_wq;
+	struct workqueue_struct	*notify_wq;
 	struct work_struct	notify_update_work;
 	struct work_struct	commit_work;
 	struct work_struct	finish_work;
@@ -161,4 +162,15 @@  int ceph_journaler_get_cached_client(struct ceph_journaler *journaler, char *cli
 				     struct ceph_journaler_client **client_result);
 // replaying
 int ceph_journaler_start_replay(struct ceph_journaler *journaler);
+
+// recording
+int ceph_journaler_append(struct ceph_journaler *journaler,
+			  uint64_t tag_tid, uint64_t *commit_tid,
+			  struct ceph_journaler_ctx *ctx);
+void ceph_journaler_client_committed(struct ceph_journaler *journaler,
+				     uint64_t commit_tid);
+int ceph_journaler_allocate_tag(struct ceph_journaler *journaler,
+				uint64_t tag_class, void *buf,
+				uint32_t buf_len,
+				struct ceph_journaler_tag *tag);
 #endif
diff --git a/net/ceph/journaler.c b/net/ceph/journaler.c
index 3b73725..e0dce2a 100644
--- a/net/ceph/journaler.c
+++ b/net/ceph/journaler.c
@@ -28,6 +28,11 @@  static char *object_oid_prefix(int pool_id, const char *journal_id)
 }
 
 static void watch_cb_func(struct work_struct *work);
+static void journaler_flush(struct work_struct *work);
+static void journaler_finish(struct work_struct *work);
+static void journaler_client_commit(struct work_struct *work);
+static void journaler_notify_update(struct work_struct *work);
+static void journaler_overflow(struct work_struct *work);
 
 struct ceph_journaler *ceph_journaler_create(struct ceph_osd_client *osdc,
 					     struct ceph_object_locator *oloc,
@@ -98,6 +103,11 @@  struct ceph_journaler *ceph_journaler_create(struct ceph_osd_client *osdc,
 	spin_lock_init(&journaler->finish_lock);
 
 	INIT_WORK(&journaler->watch_cb_work, watch_cb_func);
+	INIT_WORK(&journaler->flush_work, journaler_flush);
+	INIT_WORK(&journaler->finish_work, journaler_finish);
+	INIT_WORK(&journaler->commit_work, journaler_client_commit);
+	INIT_WORK(&journaler->notify_update_work, journaler_notify_update);
+	INIT_WORK(&journaler->overflow_work, journaler_overflow);
 
 	return journaler;
 
@@ -1046,3 +1056,671 @@  int ceph_journaler_start_replay(struct ceph_journaler *journaler)
 	return ret;
 }
 EXPORT_SYMBOL(ceph_journaler_start_replay);
+
+// recording
+// TODO use kmem_cache for it.
+struct journaler_write_ctx {
+	struct list_head node;
+
+	struct ceph_journaler *journaler;
+	struct ceph_journaler_future *future;
+	struct ceph_journaler_ctx *journaler_ctx;
+
+	uint64_t splay_offset;
+	uint64_t object_num;
+
+	struct page *req_page;
+	struct ceph_bio_iter *bio_iter;
+};
+
+static int allocate_entry_tid(struct ceph_journaler *journaler,
+			      uint64_t tag_tid, uint64_t *entry_tid)
+{
+	struct entry_tid *pos = NULL;
+
+	spin_lock(&journaler->entry_tid_lock);
+	list_for_each_entry(pos, &journaler->entry_tids, node) {
+		if (pos->tag_tid == tag_tid) {
+			*entry_tid = pos->entry_tid++;
+			spin_unlock(&journaler->entry_tid_lock);
+			return 0;
+		}
+	}
+	pos = kzalloc(sizeof(struct entry_tid), GFP_KERNEL);
+	WARN_ON(pos == NULL);
+	if (!pos) {
+		spin_unlock(&journaler->entry_tid_lock);
+		pr_err("failed to allocate new entry.");
+		return -ENOMEM;
+	}
+
+	pos->tag_tid = tag_tid;
+	pos->entry_tid = 0;
+	INIT_LIST_HEAD(&pos->node);
+
+	list_add_tail(&pos->node, &journaler->entry_tids);
+	*entry_tid = pos->entry_tid++;
+	spin_unlock(&journaler->entry_tid_lock);
+
+	return 0;
+}
+
+static uint64_t get_object(struct ceph_journaler *journaler, uint64_t splay_offset)
+{
+	return splay_offset + (journaler->splay_width * journaler->active_set);
+}
+
+static struct ceph_journaler_future *create_future(uint64_t tag_tid,
+						   uint64_t entry_tid,
+						   uint64_t commit_tid)
+{
+	struct ceph_journaler_future *future = NULL;
+
+	future = kzalloc(sizeof(struct ceph_journaler_future), GFP_KERNEL);
+	if (!future)
+		return NULL;
+
+	future->tag_tid = tag_tid;
+	future->entry_tid = entry_tid;
+	future->commit_tid = commit_tid;
+
+	future->safe = false;
+	future->consistent = false;
+
+	future->ctx = NULL;
+	future->wait = NULL;
+
+	return future;
+}
+
+static void set_prev_future(struct ceph_journaler *journaler,
+			    struct ceph_journaler_future *future)
+{
+	if (journaler->prev_future == NULL) {
+		future->consistent = true;
+	} else if (journaler->prev_future->consistent &&
+		   journaler->prev_future->safe) {
+		future->consistent = true;
+	} else {
+		journaler->prev_future->wait = future;
+	}
+	journaler->prev_future = future;
+}
+
+static struct ceph_journaler_entry *create_entry(uint64_t tag_tid,
+						 uint64_t entry_tid,
+						 struct ceph_bio_iter *bio_iter)
+{
+	struct ceph_journaler_entry *entry = NULL;
+
+	entry = kzalloc(sizeof(struct ceph_journaler_entry), GFP_KERNEL);
+	if (!entry)
+		return NULL;
+	entry->tag_tid = tag_tid;
+	entry->entry_tid = entry_tid;
+	entry->bio_iter = bio_iter;
+	entry->data_len = bio_iter->bio_len +
+			  bio_iter->prefix_len + bio_iter->suffix_len;
+
+	return entry;
+}
+
+static void journaler_entry_encode_prefix(struct ceph_journaler_entry *entry,
+					  void **p, void *end)
+{
+	ceph_encode_64(p, PREAMBLE);
+	ceph_encode_8(p, (uint8_t)1);
+	ceph_encode_64(p, entry->entry_tid);
+	ceph_encode_64(p, entry->tag_tid);
+
+	ceph_encode_32(p, entry->data_len);
+}
+
+static uint32_t crc_bio(uint32_t crc, struct bio *bio)
+{
+	struct bio_vec bv;
+	struct bvec_iter iter;
+	char *buf = NULL;
+	u64 offset = 0;
+
+next:
+	bio_for_each_segment(bv, bio, iter) {
+		buf = page_address(bv.bv_page) + bv.bv_offset;
+		crc = crc32c(crc, buf, bv.bv_len);
+		offset += bv.bv_len;
+	}
+
+	if (bio->bi_next) {
+		bio = bio->bi_next;
+		goto next;
+	}
+
+	return crc;
+}
+
+static void journaler_finish(struct work_struct *work)
+{
+	struct ceph_journaler *journaler = container_of(work, struct ceph_journaler,
+						        finish_work);
+	struct ceph_journaler_ctx *ctx_pos, *next;
+
+	spin_lock(&journaler->finish_lock);
+	list_for_each_entry_safe(ctx_pos, next, &journaler->ctx_list, node) {
+		list_del(&ctx_pos->node);
+		ctx_pos->callback(ctx_pos);
+	}
+	spin_unlock(&journaler->finish_lock);
+}
+
+static void future_consistent(struct ceph_journaler *journaler,
+			      struct ceph_journaler_future *future);
+static void future_finish(struct ceph_journaler *journaler,
+			  struct ceph_journaler_future *future) {
+	struct ceph_journaler_ctx *journaler_ctx = future->ctx;
+
+	if (future->safe && future->consistent) {
+		spin_lock(&journaler->finish_lock);
+        	list_add_tail(&journaler_ctx->node, &journaler->ctx_list);
+        	spin_unlock(&journaler->finish_lock);
+
+        	queue_work(journaler->finish_wq, &journaler->finish_work);
+
+		if (future->wait)
+			future_consistent(journaler, future->wait);
+	}
+}
+
+static void future_consistent(struct ceph_journaler *journaler,
+			      struct ceph_journaler_future *future) {
+	future->consistent = true;
+	future_finish(journaler, future);
+}
+
+static void future_safe(struct ceph_journaler *journaler,
+			struct ceph_journaler_future *future) {
+	future->safe = true;
+	future_finish(journaler, future);
+}
+
+static void journaler_notify_update(struct work_struct *work)
+{
+	struct ceph_journaler *journaler = container_of(work,
+							struct ceph_journaler,
+						        notify_update_work);
+	int ret = 0;
+
+	ret = ceph_osdc_notify(journaler->osdc, &journaler->header_oid,
+				&journaler->header_oloc, NULL, 0,
+				5000, NULL, NULL);
+	if (ret)
+		pr_err("notify_update failed: %d", ret);
+}
+
+static bool advance_object_set(struct ceph_journaler *journaler)
+{
+	int ret = 0;
+	int i = 0;
+	struct object_recorder *obj_recorder;
+	uint64_t active_set = 0;
+
+	spin_lock(&journaler->advancing_lock);
+	if (journaler->advancing) {
+		spin_unlock(&journaler->advancing_lock);
+		return false;
+	}
+
+	// make sure all inflight appending finish
+	for (i = 0; i < journaler->splay_width; i++) {
+		obj_recorder = &journaler->obj_recorders[i];
+		spin_lock(&obj_recorder->lock);
+		if (obj_recorder->inflight_append) {
+			spin_unlock(&obj_recorder->lock);
+			spin_unlock(&journaler->advancing_lock);
+			return false;
+		}
+		spin_unlock(&obj_recorder->lock);
+	}
+
+	journaler->advancing = true;
+
+	active_set = journaler->active_set + 1;
+	spin_unlock(&journaler->advancing_lock);
+
+	ret = ceph_cls_journaler_set_active_set(journaler->osdc,
+			&journaler->header_oid, &journaler->header_oloc,
+			active_set);
+	if (ret) {
+		pr_err("error in set active_set: %d", ret);
+	}
+
+	queue_work(journaler->task_wq, &journaler->notify_update_work);
+
+	return true;
+}
+
+static void journaler_overflow(struct work_struct *work)
+{
+	struct ceph_journaler *journaler = container_of(work,
+						        struct ceph_journaler,
+						        overflow_work);
+	if (advance_object_set(journaler)) {
+		queue_work(journaler->task_wq, &journaler->flush_work);
+	}
+}
+
+static void journaler_write_callback(struct ceph_osd_request *osd_req)
+{
+	struct journaler_write_ctx *ctx = osd_req->r_priv;
+	struct ceph_journaler *journaler = ctx->journaler;
+	struct ceph_journaler_ctx *journaler_ctx = ctx->journaler_ctx;
+	struct ceph_journaler_future *future = ctx->future;
+	int ret = osd_req->r_result;
+	struct object_recorder *obj_recorder = &journaler->obj_recorders[ctx->splay_offset];
+
+	__free_page(ctx->req_page);
+	ceph_osdc_put_request(osd_req);
+
+	if (ret == -EOVERFLOW) {
+		spin_lock(&obj_recorder->lock);
+		if (!obj_recorder->overflowed)
+			obj_recorder->overflowed = true;
+		list_add_tail(&ctx->node, &obj_recorder->overflow_list);
+		if (--obj_recorder->inflight_append == 0)
+			queue_work(journaler->task_wq, &journaler->overflow_work);
+		spin_unlock(&obj_recorder->lock);
+		return;
+	}
+
+	spin_lock(&obj_recorder->lock);
+	--obj_recorder->inflight_append;
+	spin_unlock(&obj_recorder->lock);
+
+	ret = add_commit_entry(journaler, ctx->future->commit_tid, ctx->object_num,
+			       ctx->future->tag_tid, ctx->future->entry_tid);
+	if (ret) {
+		pr_err("failed to add_commit_entry");
+	}
+
+	journaler_ctx->result = ret;
+	future_safe(journaler, future);
+	kfree(ctx);
+
+	if (journaler_ctx->bio_iter->prefix_page)
+		__free_page(journaler_ctx->bio_iter->prefix_page);
+	if (journaler_ctx->bio_iter->suffix_page)
+		__free_page(journaler_ctx->bio_iter->suffix_page);
+}
+
+static int ceph_journaler_obj_write(struct ceph_journaler *journaler,
+				    struct ceph_object_id *oid,
+				    struct ceph_object_locator *oloc,
+				    struct journaler_write_ctx *ctx)
+
+{
+	struct ceph_osd_client *osdc = journaler->osdc;
+	struct ceph_osd_request *req;
+	void *p;
+	int ret;
+
+	req = ceph_osdc_alloc_request(osdc, NULL, 2, false, GFP_NOIO);
+	if (!req)
+		return -ENOMEM;
+
+	ceph_oid_copy(&req->r_base_oid, oid);
+	ceph_oloc_copy(&req->r_base_oloc, oloc);
+	req->r_flags = CEPH_OSD_FLAG_WRITE;
+	req->r_callback = journaler_write_callback;
+	req->r_priv = ctx;
+
+	// guard_append
+	ctx->req_page = alloc_page(GFP_NOIO);
+	if (!ctx->req_page) {
+		ret = -ENOMEM;
+		goto out_req;
+	}
+
+	p = page_address(ctx->req_page);
+	ceph_encode_64(&p, 1 << journaler->order);
+
+	ret = osd_req_op_cls_init(req, 0, "journal", "guard_append");
+	if (ret)
+		goto out_free_page;
+
+	osd_req_op_cls_request_data_pages(req, 0, &ctx->req_page, 8, 0, false, false);
+
+	// append_data
+	osd_req_op_extent_init(req, 1, CEPH_OSD_OP_APPEND, 0,
+		ctx->bio_iter->prefix_len + ctx->bio_iter->bio_len + ctx->bio_iter->suffix_len, 0, 0);
+	osd_req_op_extent_osd_data_bio(req, 1, ctx->bio_iter,
+		ctx->bio_iter->prefix_len + ctx->bio_iter->bio_len + ctx->bio_iter->suffix_len);
+	ret = ceph_osdc_alloc_messages(req, GFP_KERNEL);
+	if (ret)
+		goto out_free_page;
+
+	ceph_osdc_start_request(osdc, req, false);
+	return 0;
+
+out_free_page:
+	__free_page(ctx->req_page);
+out_req:
+	ceph_osdc_put_request(req);
+	return ret;
+}
+
+static int send_append_request(struct ceph_journaler *journaler,
+			       uint64_t object_num,
+			       struct journaler_write_ctx *ctx)
+{
+	struct ceph_object_id object_oid;
+	int ret = 0;
+
+	ceph_oid_init(&object_oid);
+	ret = ceph_oid_aprintf(&object_oid, GFP_KERNEL, "%s%llu",
+				journaler->object_oid_prefix, object_num);
+	if (ret) {
+		pr_err("failed to initialize object id: %d", ret);
+		goto out;
+	}
+
+	ret = ceph_journaler_obj_write(journaler, &object_oid,
+				       &journaler->data_oloc, ctx);
+out:
+	ceph_oid_destroy(&object_oid);
+	return ret;
+}
+
+static void journaler_flush(struct work_struct *work)
+{
+	struct ceph_journaler *journaler = container_of(work,
+							struct ceph_journaler,
+							flush_work);
+	int i = 0;
+	int ret = 0;
+	struct object_recorder *obj_recorder;
+	struct journaler_write_ctx *ctx;
+	int req_num = 0;
+	LIST_HEAD(tmp);
+
+	if (journaler->advancing) {
+		return;
+	}
+
+	for (i = 0; i < journaler->splay_width; i++) {
+		req_num = 0;
+		INIT_LIST_HEAD(&tmp);
+		obj_recorder = &journaler->obj_recorders[i];
+		spin_lock(&obj_recorder->lock);
+		list_splice_tail_init(&obj_recorder->overflow_list, &tmp);
+		list_splice_tail_init(&obj_recorder->append_list, &tmp);
+		spin_unlock(&obj_recorder->lock);
+
+		list_for_each_entry(ctx, &tmp, node) {
+			ctx->object_num = get_object(journaler, obj_recorder->splay_offset);
+			ret = send_append_request(journaler, ctx->object_num, ctx);
+			if (ret) {
+				// TODO
+				pr_err("failed to send append request: %d", ret);
+			}
+			req_num++;
+		}
+
+		spin_lock(&obj_recorder->lock);
+		obj_recorder->inflight_append += req_num;
+		spin_unlock(&obj_recorder->lock);
+	}
+}
+
+static int ceph_journaler_object_append(struct ceph_journaler *journaler,
+					uint64_t splay_offset, 
+					struct ceph_journaler_future *future,
+					struct ceph_journaler_entry *entry,
+					struct ceph_journaler_ctx *journaler_ctx)
+{
+	void *buf = NULL;
+	void *end = NULL;
+	int ret = 0;
+	uint32_t crc = 0;
+	struct ceph_bio_iter *bio_iter = journaler_ctx->bio_iter;
+	struct journaler_write_ctx *ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	struct object_recorder *obj_recorder;
+
+	if (!ctx) {
+		return -ENOMEM;
+	}
+
+	// PEAMBLE(8) + version(1) + entry_tid(8) + tag_tid(8) + string_len(4) = 29
+	bio_iter->prefix_offset = bio_iter->prefix_offset - 29;
+	bio_iter->prefix_len = bio_iter->prefix_len + 29;
+	buf = page_address(bio_iter->prefix_page) + bio_iter->prefix_offset;
+	end = buf + 29;
+
+	ctx->journaler = journaler;
+	ctx->future = future;
+	ctx->journaler_ctx = journaler_ctx;
+	ctx->splay_offset = splay_offset;
+	INIT_LIST_HEAD(&ctx->node);
+
+	journaler_entry_encode_prefix(entry, &buf, end);
+
+	// size of crc is 4
+	bio_iter->suffix_page = alloc_page(GFP_KERNEL);
+	bio_iter->suffix_offset = 0;
+	bio_iter->suffix_len = 4;
+
+	buf = page_address(bio_iter->suffix_page);
+	end = buf + 4;
+
+	crc = crc32c(crc, page_address(bio_iter->prefix_page) + bio_iter->prefix_offset,
+		     bio_iter->prefix_len);
+	if (bio_iter->bio_len)
+		crc = crc_bio(crc, bio_iter->bio);
+
+	ceph_encode_32(&buf, crc);
+	ctx->bio_iter = bio_iter;
+
+	obj_recorder = &journaler->obj_recorders[ctx->splay_offset];
+	spin_lock(&obj_recorder->lock);
+	list_add_tail(&ctx->node, &obj_recorder->append_list);
+	queue_work(journaler->task_wq, &journaler->flush_work);
+	spin_unlock(&obj_recorder->lock);
+
+	return ret;
+}
+
+int ceph_journaler_append(struct ceph_journaler *journaler, uint64_t tag_tid,
+			  uint64_t *commit_tid, struct ceph_journaler_ctx *ctx)
+{
+	uint8_t splay_width;
+	uint8_t splay_offset;
+	uint64_t object_num;
+	uint64_t entry_tid;
+	struct ceph_journaler_future *future;
+	struct ceph_journaler_entry *entry;
+	struct object_recorder *obj_recorder;
+	int ret = 0;
+
+	spin_lock(&journaler->meta_lock);
+	ret = allocate_entry_tid(journaler, tag_tid, &entry_tid);
+	if (ret) {
+		goto unlock;
+	}
+
+	splay_width = journaler->splay_width;
+	splay_offset = entry_tid % splay_width;
+	obj_recorder = &journaler->obj_recorders[splay_width];
+
+	object_num = get_object(journaler, splay_offset);
+	*commit_tid = allocate_commit_tid(journaler);
+
+	future = create_future(tag_tid, entry_tid, *commit_tid);
+	if (!future) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	future->ctx = ctx;
+	set_prev_future(journaler, future);
+
+	entry = create_entry(tag_tid, entry_tid, ctx->bio_iter);
+	if (!entry) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+	spin_unlock(&journaler->meta_lock);
+
+	ret = ceph_journaler_object_append(journaler, splay_offset, future, entry, ctx);
+	return ret;
+
+unlock:
+	spin_unlock(&journaler->meta_lock);
+	return ret;
+}
+EXPORT_SYMBOL(ceph_journaler_append);
+
+static void journaler_client_commit(struct work_struct *work)
+{
+	struct ceph_journaler *journaler = container_of(work, struct ceph_journaler,
+							commit_work);
+
+	struct list_head object_positions;
+	struct ceph_journaler_object_pos *pos = NULL, *next = NULL;
+	int ret = 0;
+
+	INIT_LIST_HEAD(&object_positions);
+	spin_lock(&journaler->commit_lock);
+	list_for_each_entry_safe(pos, next, &journaler->object_positions_pending,
+				 node) {
+		struct ceph_journaler_object_pos *new_pos = NULL;
+
+		ret = copy_object_pos(pos, &new_pos);
+		list_add_tail(&new_pos->node, &object_positions);
+	}
+	spin_unlock(&journaler->commit_lock);
+
+	ret = ceph_cls_journaler_client_committed(journaler->osdc,
+		&journaler->header_oid, &journaler->header_oloc,
+		journaler->client, &object_positions);
+
+	if (ret) {
+		pr_err("error in client committed: %d", ret);
+	}
+
+	list_for_each_entry_safe(pos, next, &object_positions, node) {
+		list_del(&pos->node);
+		kfree(pos);
+	}
+
+	queue_work(journaler->notify_wq, &journaler->notify_update_work);
+	return;
+}
+
+// hold journaler->commit_lock
+static int add_object_position(struct commit_entry *entry,
+			       struct list_head *object_positions,
+			       uint64_t splay_width)
+{
+	struct ceph_journaler_object_pos *position = NULL;
+	uint8_t splay_offset = entry->object_num % splay_width;
+	bool found = false;
+	int ret = 0;
+	
+	list_for_each_entry(position, object_positions, node) {
+		if (splay_offset == position->object_num % splay_width) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		position = kzalloc(sizeof(*position), GFP_KERNEL);
+
+		if (!position) {
+			pr_err("failed to allocate position");
+			return -ENOMEM;
+		}
+		list_add(&position->node, object_positions);
+	} else {
+		list_move(&position->node, object_positions);
+	}
+
+	position->object_num = entry->object_num;
+	position->tag_tid = entry->tag_tid;
+	position->entry_tid = entry->entry_tid;
+
+	return ret;
+}
+
+void ceph_journaler_client_committed(struct ceph_journaler *journaler, uint64_t commit_tid)
+{
+	struct commit_entry *entry = NULL;
+	bool update_client_commit = true;
+	struct rb_node *n;
+	LIST_HEAD(object_positions);
+
+	spin_lock(&journaler->commit_lock);
+	for (n = rb_first(&journaler->commit_entries); n; n = rb_next(n)) {
+		entry = rb_entry(n, struct commit_entry, r_node);
+		if (entry->commit_tid == commit_tid) {
+			entry->committed = true;
+			break;
+		}
+		if (entry->committed == false)
+			update_client_commit = false;
+	}
+
+	if (update_client_commit) {
+		for (n = rb_first(&journaler->commit_entries); n;) {
+			entry = rb_entry(n, struct commit_entry, r_node);
+			n = rb_next(n);
+
+			if (entry->commit_tid > commit_tid)
+				break;
+			add_object_position(entry,
+				&journaler->object_positions_pending,
+				journaler->splay_width);
+			erase_commit_entry(&journaler->commit_entries, entry);
+			kfree(entry);
+		}
+	}
+	spin_unlock(&journaler->commit_lock);
+
+	if (update_client_commit) {
+		queue_work(journaler->task_wq, &journaler->commit_work);
+	}
+}
+EXPORT_SYMBOL(ceph_journaler_client_committed);
+
+int ceph_journaler_allocate_tag(struct ceph_journaler *journaler,
+				uint64_t tag_class, void *buf,
+				uint32_t buf_len,
+				struct ceph_journaler_tag *tag)
+{
+	uint64_t tag_tid = 0;
+	int ret = 0;
+
+	ret = ceph_cls_journaler_get_next_tag_tid(journaler->osdc,
+					&journaler->header_oid,
+					&journaler->header_oloc,
+					&tag_tid);
+	if (ret)
+		goto out;
+
+	ret = ceph_cls_journaler_tag_create(journaler->osdc,
+					&journaler->header_oid,
+					&journaler->header_oloc,
+					tag_tid, tag_class,
+					buf, buf_len);
+	if (ret)
+		goto out;
+
+	ret = ceph_cls_journaler_get_tag(journaler->osdc,
+					&journaler->header_oid,
+					&journaler->header_oloc,
+					tag_tid, tag);
+	if (ret)
+		goto out;
+
+out:
+	return ret;
+}
+EXPORT_SYMBOL(ceph_journaler_allocate_tag);