Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull Ceph changes from Sage Weil:
 "On the RBD side, there is a conversion to blk-mq from Christoph,
  several long-standing bug fixes from Ilya, and some cleanup from
  Rickard Strandqvist.

  On the CephFS side there is a long list of fixes from Zheng, including
  improved session handling, a few IO path fixes, some dcache management
  correctness fixes, and several blocking while !TASK_RUNNING fixes.

  The core code gets a few cleanups and Chaitanya has added support for
  TCP_NODELAY (which has been used on the server side for ages but we
  somehow missed on the kernel client).

  There is also an update to MAINTAINERS to fix up some email addresses
  and reflect that Ilya and Zheng are doing most of the maintenance for
  RBD and CephFS these days.  Do not be surprised to see a pull request
  come from one of them in the future if I am unavailable for some
  reason"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (27 commits)
  MAINTAINERS: update Ceph and RBD maintainers
  libceph: kfree() in put_osd() shouldn't depend on authorizer
  libceph: fix double __remove_osd() problem
  rbd: convert to blk-mq
  ceph: return error for traceless reply race
  ceph: fix dentry leaks
  ceph: re-send requests when MDS enters reconnecting stage
  ceph: show nocephx_require_signatures and notcp_nodelay options
  libceph: tcp_nodelay support
  rbd: do not treat standalone as flatten
  ceph: fix atomic_open snapdir
  ceph: properly mark empty directory as complete
  client: include kernel version in client metadata
  ceph: provide seperate {inode,file}_operations for snapdir
  ceph: fix request time stamp encoding
  ceph: fix reading inline data when i_size > PAGE_SIZE
  ceph: avoid block operation when !TASK_RUNNING (ceph_mdsc_close_sessions)
  ceph: avoid block operation when !TASK_RUNNING (ceph_get_caps)
  ceph: avoid block operation when !TASK_RUNNING (ceph_mdsc_sync)
  rbd: fix error paths in rbd_dev_refresh()
  ...

1 files changed, 83 insertions, 110 deletions

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 8a86b62466f7..b40af3203089 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -38,6 +38,7 @@
 #include <linux/kernel.h>
 #include <linux/device.h>
 #include <linux/module.h>
+#include <linux/blk-mq.h>
 #include <linux/fs.h>
 #include <linux/blkdev.h>
 #include <linux/slab.h>
@@ -340,9 +341,7 @@ struct rbd_device {
 
 	char			name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */
 
-	struct list_head	rq_queue;	/* incoming rq queue */
 	spinlock_t		lock;		/* queue, flags, open_count */
-	struct work_struct	rq_work;
 
 	struct rbd_image_header	header;
 	unsigned long		flags;		/* possibly lock protected */
@@ -360,6 +359,9 @@ struct rbd_device {
 	atomic_t		parent_ref;
 	struct rbd_device	*parent;
 
+	/* Block layer tags. */
+	struct blk_mq_tag_set	tag_set;
+
 	/* protects updating the header */
 	struct rw_semaphore     header_rwsem;
 
@@ -1817,7 +1819,8 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 
 	/*
 	 * We support a 64-bit length, but ultimately it has to be
-	 * passed to blk_end_request(), which takes an unsigned int.
+	 * passed to the block layer, which just supports a 32-bit
+	 * length field.
 	 */
 	obj_request->xferred = osd_req->r_reply_op_len[0];
 	rbd_assert(obj_request->xferred < (u64)UINT_MAX);
@@ -2275,7 +2278,10 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
 		more = obj_request->which < img_request->obj_request_count - 1;
 	} else {
 		rbd_assert(img_request->rq != NULL);
-		more = blk_end_request(img_request->rq, result, xferred);
+
+		more = blk_update_request(img_request->rq, result, xferred);
+		if (!more)
+			__blk_mq_end_request(img_request->rq, result);
 	}
 
 	return more;
@@ -3304,8 +3310,10 @@ out:
 	return ret;
 }
 
-static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
+static void rbd_queue_workfn(struct work_struct *work)
 {
+	struct request *rq = blk_mq_rq_from_pdu(work);
+	struct rbd_device *rbd_dev = rq->q->queuedata;
 	struct rbd_img_request *img_request;
 	struct ceph_snap_context *snapc = NULL;
 	u64 offset = (u64)blk_rq_pos(rq) << SECTOR_SHIFT;
@@ -3314,6 +3322,13 @@ static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
 	u64 mapping_size;
 	int result;
 
+	if (rq->cmd_type != REQ_TYPE_FS) {
+		dout("%s: non-fs request type %d\n", __func__,
+			(int) rq->cmd_type);
+		result = -EIO;
+		goto err;
+	}
+
 	if (rq->cmd_flags & REQ_DISCARD)
 		op_type = OBJ_OP_DISCARD;
 	else if (rq->cmd_flags & REQ_WRITE)
@@ -3359,6 +3374,8 @@ static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
 		goto err_rq;	/* Shouldn't happen */
 	}
 
+	blk_mq_start_request(rq);
+
 	down_read(&rbd_dev->header_rwsem);
 	mapping_size = rbd_dev->mapping.size;
 	if (op_type != OBJ_OP_READ) {
@@ -3404,53 +3421,18 @@ err_rq:
 		rbd_warn(rbd_dev, "%s %llx at %llx result %d",
 			 obj_op_name(op_type), length, offset, result);
 	ceph_put_snap_context(snapc);
-	blk_end_request_all(rq, result);
+err:
+	blk_mq_end_request(rq, result);
 }
 
-static void rbd_request_workfn(struct work_struct *work)
+static int rbd_queue_rq(struct blk_mq_hw_ctx *hctx,
+		const struct blk_mq_queue_data *bd)
 {
-	struct rbd_device *rbd_dev =
-	    container_of(work, struct rbd_device, rq_work);
-	struct request *rq, *next;
-	LIST_HEAD(requests);
-
-	spin_lock_irq(&rbd_dev->lock); /* rq->q->queue_lock */
-	list_splice_init(&rbd_dev->rq_queue, &requests);
-	spin_unlock_irq(&rbd_dev->lock);
+	struct request *rq = bd->rq;
+	struct work_struct *work = blk_mq_rq_to_pdu(rq);
 
-	list_for_each_entry_safe(rq, next, &requests, queuelist) {
-		list_del_init(&rq->queuelist);
-		rbd_handle_request(rbd_dev, rq);
-	}
-}
-
-/*
- * Called with q->queue_lock held and interrupts disabled, possibly on
- * the way to schedule().  Do not sleep here!
- */
-static void rbd_request_fn(struct request_queue *q)
-{
-	struct rbd_device *rbd_dev = q->queuedata;
-	struct request *rq;
-	int queued = 0;
-
-	rbd_assert(rbd_dev);
-
-	while ((rq = blk_fetch_request(q))) {
-		/* Ignore any non-FS requests that filter through. */
-		if (rq->cmd_type != REQ_TYPE_FS) {
-			dout("%s: non-fs request type %d\n", __func__,
-				(int) rq->cmd_type);
-			__blk_end_request_all(rq, 0);
-			continue;
-		}
-
-		list_add_tail(&rq->queuelist, &rbd_dev->rq_queue);
-		queued++;
-	}
-
-	if (queued)
-		queue_work(rbd_wq, &rbd_dev->rq_work);
+	queue_work(rbd_wq, work);
+	return BLK_MQ_RQ_QUEUE_OK;
 }
 
 /*
@@ -3511,6 +3493,7 @@ static void rbd_free_disk(struct rbd_device *rbd_dev)
 		del_gendisk(disk);
 		if (disk->queue)
 			blk_cleanup_queue(disk->queue);
+		blk_mq_free_tag_set(&rbd_dev->tag_set);
 	}
 	put_disk(disk);
 }
@@ -3694,7 +3677,7 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev)
 
 	ret = rbd_dev_header_info(rbd_dev);
 	if (ret)
-		return ret;
+		goto out;
 
 	/*
 	 * If there is a parent, see if it has disappeared due to the
@@ -3703,30 +3686,46 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev)
 	if (rbd_dev->parent) {
 		ret = rbd_dev_v2_parent_info(rbd_dev);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	if (rbd_dev->spec->snap_id == CEPH_NOSNAP) {
-		if (rbd_dev->mapping.size != rbd_dev->header.image_size)
-			rbd_dev->mapping.size = rbd_dev->header.image_size;
+		rbd_dev->mapping.size = rbd_dev->header.image_size;
 	} else {
 		/* validate mapped snapshot's EXISTS flag */
 		rbd_exists_validate(rbd_dev);
 	}
 
+out:
 	up_write(&rbd_dev->header_rwsem);
-
-	if (mapping_size != rbd_dev->mapping.size)
+	if (!ret && mapping_size != rbd_dev->mapping.size)
 		rbd_dev_update_size(rbd_dev);
 
+	return ret;
+}
+
+static int rbd_init_request(void *data, struct request *rq,
+		unsigned int hctx_idx, unsigned int request_idx,
+		unsigned int numa_node)
+{
+	struct work_struct *work = blk_mq_rq_to_pdu(rq);
+
+	INIT_WORK(work, rbd_queue_workfn);
 	return 0;
 }
 
+static struct blk_mq_ops rbd_mq_ops = {
+	.queue_rq	= rbd_queue_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_request	= rbd_init_request,
+};
+
 static int rbd_init_disk(struct rbd_device *rbd_dev)
 {
 	struct gendisk *disk;
 	struct request_queue *q;
 	u64 segment_size;
+	int err;
 
 	/* create gendisk info */
 	disk = alloc_disk(single_major ?
@@ -3744,10 +3743,25 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	disk->fops = &rbd_bd_ops;
 	disk->private_data = rbd_dev;
 
-	q = blk_init_queue(rbd_request_fn, &rbd_dev->lock);
-	if (!q)
+	memset(&rbd_dev->tag_set, 0, sizeof(rbd_dev->tag_set));
+	rbd_dev->tag_set.ops = &rbd_mq_ops;
+	rbd_dev->tag_set.queue_depth = BLKDEV_MAX_RQ;
+	rbd_dev->tag_set.numa_node = NUMA_NO_NODE;
+	rbd_dev->tag_set.flags =
+		BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	rbd_dev->tag_set.nr_hw_queues = 1;
+	rbd_dev->tag_set.cmd_size = sizeof(struct work_struct);
+
+	err = blk_mq_alloc_tag_set(&rbd_dev->tag_set);
+	if (err)
 		goto out_disk;
 
+	q = blk_mq_init_queue(&rbd_dev->tag_set);
+	if (IS_ERR(q)) {
+		err = PTR_ERR(q);
+		goto out_tag_set;
+	}
+
 	/* We use the default size, but let's be explicit about it. */
 	blk_queue_physical_block_size(q, SECTOR_SIZE);
 
@@ -3773,10 +3787,11 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	rbd_dev->disk = disk;
 
 	return 0;
+out_tag_set:
+	blk_mq_free_tag_set(&rbd_dev->tag_set);
 out_disk:
 	put_disk(disk);
-
-	return -ENOMEM;
+	return err;
 }
 
 /*
@@ -4033,8 +4048,6 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
 		return NULL;
 
 	spin_lock_init(&rbd_dev->lock);
-	INIT_LIST_HEAD(&rbd_dev->rq_queue);
-	INIT_WORK(&rbd_dev->rq_work, rbd_request_workfn);
 	rbd_dev->flags = 0;
 	atomic_set(&rbd_dev->parent_ref, 0);
 	INIT_LIST_HEAD(&rbd_dev->node);
@@ -4274,32 +4287,22 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 	}
 
 	/*
-	 * We always update the parent overlap.  If it's zero we
-	 * treat it specially.
+	 * We always update the parent overlap.  If it's zero we issue
+	 * a warning, as we will proceed as if there was no parent.
 	 */
-	rbd_dev->parent_overlap = overlap;
 	if (!overlap) {
-
-		/* A null parent_spec indicates it's the initial probe */
-
 		if (parent_spec) {
-			/*
-			 * The overlap has become zero, so the clone
-			 * must have been resized down to 0 at some
-			 * point.  Treat this the same as a flatten.
-			 */
-			rbd_dev_parent_put(rbd_dev);
-			pr_info("%s: clone image now standalone\n",
-				rbd_dev->disk->disk_name);
+			/* refresh, careful to warn just once */
+			if (rbd_dev->parent_overlap)
+				rbd_warn(rbd_dev,
+				    "clone now standalone (overlap became 0)");
 		} else {
-			/*
-			 * For the initial probe, if we find the
-			 * overlap is zero we just pretend there was
-			 * no parent image.
-			 */
-			rbd_warn(rbd_dev, "ignoring parent with overlap 0");
+			/* initial probe */
+			rbd_warn(rbd_dev, "clone is standalone (overlap 0)");
 		}
 	}
+	rbd_dev->parent_overlap = overlap;
+
 out:
 	ret = 0;
 out_err:
@@ -4771,36 +4774,6 @@ static inline size_t next_token(const char **buf)
 }
 
 /*
- * Finds the next token in *buf, and if the provided token buffer is
- * big enough, copies the found token into it.  The result, if
- * copied, is guaranteed to be terminated with '\0'.  Note that *buf
- * must be terminated with '\0' on entry.
- *
- * Returns the length of the token found (not including the '\0').
- * Return value will be 0 if no token is found, and it will be >=
- * token_size if the token would not fit.
- *
- * The *buf pointer will be updated to point beyond the end of the
- * found token.  Note that this occurs even if the token buffer is
- * too small to hold it.
- */
-static inline size_t copy_token(const char **buf,
-				char *token,
-				size_t token_size)
-{
-        size_t len;
-
-	len = next_token(buf);
-	if (len < token_size) {
-		memcpy(token, *buf, len);
-		*(token + len) = '\0';
-	}
-	*buf += len;
-
-        return len;
-}
-
-/*
  * Finds the next token in *buf, dynamically allocates a buffer big
  * enough to hold a copy of it, and copies the token into the new
  * buffer.  The copy is guaranteed to be terminated with '\0'.  Note