Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull second round of block driver updates from Jens Axboe:
 "As mentioned in the original pull request, the bcache bits were pulled
  because of their dependency on the immutable bio vecs.  Kent re-did
  this part and resubmitted it, so here's the 2nd round of (mostly)
  driver updates for 3.13.  It contains:

 - The bcache work from Kent.

 - Conversion of virtio-blk to blk-mq.  This removes the bio and request
   path, and substitutes with the blk-mq path instead.  The end result
   almost 200 deleted lines.  Patch is acked by Asias and Christoph, who
   both did a bunch of testing.

 - A removal of bootmem.h include from Grygorii Strashko, part of a
   larger series of his killing the dependency on that header file.

 - Removal of __cpuinit from blk-mq from Paul Gortmaker"

* 'for-linus' of git://git.kernel.dk/linux-block: (56 commits)
  virtio_blk: blk-mq support
  blk-mq: remove newly added instances of __cpuinit
  bcache: defensively handle format strings
  bcache: Bypass torture test
  bcache: Delete some slower inline asm
  bcache: Use ida for bcache block dev minor
  bcache: Fix sysfs splat on shutdown with flash only devs
  bcache: Better full stripe scanning
  bcache: Have btree_split() insert into parent directly
  bcache: Move spinlock into struct time_stats
  bcache: Kill sequential_merge option
  bcache: Kill bch_next_recurse_key()
  bcache: Avoid deadlocking in garbage collection
  bcache: Incremental gc
  bcache: Add make_btree_freeing_key()
  bcache: Add btree_node_write_sync()
  bcache: PRECEDING_KEY()
  bcache: bch_(btree|extent)_ptr_invalid()
  bcache: Don't bother with bucket refcount for btree node allocations
  bcache: Debug code improvements
  ...

block/blk-ioc.c

@@ -6,7 +6,6 @@
 #include <linux/init.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
-#include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
 #include <linux/slab.h>
 
 #include "blk.h"

block/blk-mq-cpu.c

@@ -13,8 +13,8 @@
 static LIST_HEAD(blk_mq_cpu_notify_list);
 static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock);
 
-static int __cpuinit blk_mq_main_cpu_notify(struct notifier_block *self,
-					    unsigned long action, void *hcpu)
+static int blk_mq_main_cpu_notify(struct notifier_block *self,
+				  unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned long) hcpu;
 	struct blk_mq_cpu_notifier *notify;
@@ -28,8 +28,8 @@ static int __cpuinit blk_mq_main_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static void __cpuinit blk_mq_cpu_notify(void *data, unsigned long action,
-					unsigned int cpu)
+static void blk_mq_cpu_notify(void *data, unsigned long action,
+			      unsigned int cpu)
 {
 	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
 		/*

block/blk-mq.c

@@ -1444,7 +1444,7 @@ void blk_mq_free_queue(struct request_queue *q)
 EXPORT_SYMBOL(blk_mq_free_queue);
 
 /* Basically redo blk_mq_init_queue with queue frozen */
-static void __cpuinit blk_mq_queue_reinit(struct request_queue *q)
+static void blk_mq_queue_reinit(struct request_queue *q)
 {
 	blk_mq_freeze_queue(q);
 
@@ -1461,8 +1461,8 @@ static void __cpuinit blk_mq_queue_reinit(struct request_queue *q)
 	blk_mq_unfreeze_queue(q);
 }
 
-static int __cpuinit blk_mq_queue_reinit_notify(struct notifier_block *nb,
-		unsigned long action, void *hcpu)
+static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
+				      unsigned long action, void *hcpu)
 {
 	struct request_queue *q;
 

drivers/block/virtio_blk.c

@@ -11,12 +11,11 @@
 #include <linux/string_helpers.h>
 #include <scsi/scsi_cmnd.h>
 #include <linux/idr.h>
+#include <linux/blk-mq.h>
+#include <linux/numa.h>
 
 #define PART_BITS 4
 
-static bool use_bio;
-module_param(use_bio, bool, S_IRUGO);
-
 static int major;
 static DEFINE_IDA(vd_index_ida);
 
@@ -26,13 +25,11 @@ struct virtio_blk
 {
 	struct virtio_device *vdev;
 	struct virtqueue *vq;
-	wait_queue_head_t queue_wait;
+	spinlock_t vq_lock;
 
 	/* The disk structure for the kernel. */
 	struct gendisk *disk;
 
-	mempool_t *pool;
-
 	/* Process context for config space updates */
 	struct work_struct config_work;
 
@@ -47,31 +44,17 @@ struct virtio_blk
 
 	/* Ida index - used to track minor number allocations. */
 	int index;
-
-	/* Scatterlist: can be too big for stack. */
-	struct scatterlist sg[/*sg_elems*/];
 };
 
 struct virtblk_req
 {
 	struct request *req;
-	struct bio *bio;
 	struct virtio_blk_outhdr out_hdr;
 	struct virtio_scsi_inhdr in_hdr;
-	struct work_struct work;
-	struct virtio_blk *vblk;
-	int flags;
 	u8 status;
 	struct scatterlist sg[];
 };
 
-enum {
-	VBLK_IS_FLUSH		= 1,
-	VBLK_REQ_FLUSH		= 2,
-	VBLK_REQ_DATA		= 4,
-	VBLK_REQ_FUA		= 8,
-};
-
 static inline int virtblk_result(struct virtblk_req *vbr)
 {
 	switch (vbr->status) {
@@ -84,22 +67,6 @@ static inline int virtblk_result(struct virtblk_req *vbr)
 	}
 }
 
-static inline struct virtblk_req *virtblk_alloc_req(struct virtio_blk *vblk,
-						    gfp_t gfp_mask)
-{
-	struct virtblk_req *vbr;
-
-	vbr = mempool_alloc(vblk->pool, gfp_mask);
-	if (!vbr)
-		return NULL;
-
-	vbr->vblk = vblk;
-	if (use_bio)
-		sg_init_table(vbr->sg, vblk->sg_elems);
-
-	return vbr;
-}
-
 static int __virtblk_add_req(struct virtqueue *vq,
 			     struct virtblk_req *vbr,
 			     struct scatterlist *data_sg,
@@ -143,83 +110,8 @@ static int __virtblk_add_req(struct virtqueue *vq,
 	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
 }
 
-static void virtblk_add_req(struct virtblk_req *vbr, bool have_data)
-{
-	struct virtio_blk *vblk = vbr->vblk;
-	DEFINE_WAIT(wait);
-	int ret;
-
-	spin_lock_irq(vblk->disk->queue->queue_lock);
-	while (unlikely((ret = __virtblk_add_req(vblk->vq, vbr, vbr->sg,
-						 have_data)) < 0)) {
-		prepare_to_wait_exclusive(&vblk->queue_wait, &wait,
-					  TASK_UNINTERRUPTIBLE);
-
-		spin_unlock_irq(vblk->disk->queue->queue_lock);
-		io_schedule();
-		spin_lock_irq(vblk->disk->queue->queue_lock);
-
-		finish_wait(&vblk->queue_wait, &wait);
-	}
-
-	virtqueue_kick(vblk->vq);
-	spin_unlock_irq(vblk->disk->queue->queue_lock);
-}
-
-static void virtblk_bio_send_flush(struct virtblk_req *vbr)
-{
-	vbr->flags |= VBLK_IS_FLUSH;
-	vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
-	vbr->out_hdr.sector = 0;
-	vbr->out_hdr.ioprio = 0;
-
-	virtblk_add_req(vbr, false);
-}
-
-static void virtblk_bio_send_data(struct virtblk_req *vbr)
-{
-	struct virtio_blk *vblk = vbr->vblk;
-	struct bio *bio = vbr->bio;
-	bool have_data;
-
-	vbr->flags &= ~VBLK_IS_FLUSH;
-	vbr->out_hdr.type = 0;
-	vbr->out_hdr.sector = bio->bi_sector;
-	vbr->out_hdr.ioprio = bio_prio(bio);
-
-	if (blk_bio_map_sg(vblk->disk->queue, bio, vbr->sg)) {
-		have_data = true;
-		if (bio->bi_rw & REQ_WRITE)
-			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
-		else
-			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
-	} else
-		have_data = false;
-
-	virtblk_add_req(vbr, have_data);
-}
-
-static void virtblk_bio_send_data_work(struct work_struct *work)
-{
-	struct virtblk_req *vbr;
-
-	vbr = container_of(work, struct virtblk_req, work);
-
-	virtblk_bio_send_data(vbr);
-}
-
-static void virtblk_bio_send_flush_work(struct work_struct *work)
-{
-	struct virtblk_req *vbr;
-
-	vbr = container_of(work, struct virtblk_req, work);
-
-	virtblk_bio_send_flush(vbr);
-}
-
 static inline void virtblk_request_done(struct virtblk_req *vbr)
 {
-	struct virtio_blk *vblk = vbr->vblk;
 	struct request *req = vbr->req;
 	int error = virtblk_result(vbr);
 
@@ -231,92 +123,45 @@ static inline void virtblk_request_done(struct virtblk_req *vbr)
 		req->errors = (error != 0);
 	}
 
-	__blk_end_request_all(req, error);
-	mempool_free(vbr, vblk->pool);
-}
-
-static inline void virtblk_bio_flush_done(struct virtblk_req *vbr)
-{
-	struct virtio_blk *vblk = vbr->vblk;
-
-	if (vbr->flags & VBLK_REQ_DATA) {
-		/* Send out the actual write data */
-		INIT_WORK(&vbr->work, virtblk_bio_send_data_work);
-		queue_work(virtblk_wq, &vbr->work);
-	} else {
-		bio_endio(vbr->bio, virtblk_result(vbr));
-		mempool_free(vbr, vblk->pool);
-	}
-}
-
-static inline void virtblk_bio_data_done(struct virtblk_req *vbr)
-{
-	struct virtio_blk *vblk = vbr->vblk;
-
-	if (unlikely(vbr->flags & VBLK_REQ_FUA)) {
-		/* Send out a flush before end the bio */
-		vbr->flags &= ~VBLK_REQ_DATA;
-		INIT_WORK(&vbr->work, virtblk_bio_send_flush_work);
-		queue_work(virtblk_wq, &vbr->work);
-	} else {
-		bio_endio(vbr->bio, virtblk_result(vbr));
-		mempool_free(vbr, vblk->pool);
-	}
-}
-
-static inline void virtblk_bio_done(struct virtblk_req *vbr)
-{
-	if (unlikely(vbr->flags & VBLK_IS_FLUSH))
-		virtblk_bio_flush_done(vbr);
-	else
-		virtblk_bio_data_done(vbr);
+	blk_mq_end_io(req, error);
 }
 
 static void virtblk_done(struct virtqueue *vq)
 {
 	struct virtio_blk *vblk = vq->vdev->priv;
-	bool bio_done = false, req_done = false;
+	bool req_done = false;
 	struct virtblk_req *vbr;
 	unsigned long flags;
 	unsigned int len;
 
-	spin_lock_irqsave(vblk->disk->queue->queue_lock, flags);
+	spin_lock_irqsave(&vblk->vq_lock, flags);
 	do {
 		virtqueue_disable_cb(vq);
 		while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) {
-			if (vbr->bio) {
-				virtblk_bio_done(vbr);
-				bio_done = true;
-			} else {
-				virtblk_request_done(vbr);
-				req_done = true;
-			}
+			virtblk_request_done(vbr);
+			req_done = true;
 		}
 		if (unlikely(virtqueue_is_broken(vq)))
 			break;
 	} while (!virtqueue_enable_cb(vq));
+	spin_unlock_irqrestore(&vblk->vq_lock, flags);
+
 	/* In case queue is stopped waiting for more buffers. */
 	if (req_done)
-		blk_start_queue(vblk->disk->queue);
-	spin_unlock_irqrestore(vblk->disk->queue->queue_lock, flags);
-
-	if (bio_done)
-		wake_up(&vblk->queue_wait);
+		blk_mq_start_stopped_hw_queues(vblk->disk->queue);
 }
 
-static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
-		   struct request *req)
+static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 {
+	struct virtio_blk *vblk = hctx->queue->queuedata;
+	struct virtblk_req *vbr = req->special;
+	unsigned long flags;
 	unsigned int num;
-	struct virtblk_req *vbr;
+	const bool last = (req->cmd_flags & REQ_END) != 0;
 
-	vbr = virtblk_alloc_req(vblk, GFP_ATOMIC);
-	if (!vbr)
-		/* When another request finishes we'll try again. */
-		return false;
+	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
 	vbr->req = req;
-	vbr->bio = NULL;
 	if (req->cmd_flags & REQ_FLUSH) {
 		vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
 		vbr->out_hdr.sector = 0;
@@ -344,7 +189,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 		}
 	}
 
-	num = blk_rq_map_sg(q, vbr->req, vblk->sg);
+	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
 	if (num) {
 		if (rq_data_dir(vbr->req) == WRITE)
 			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
@@ -352,63 +197,18 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
 	}
 
-	if (__virtblk_add_req(vblk->vq, vbr, vblk->sg, num) < 0) {
-		mempool_free(vbr, vblk->pool);
-		return false;
-	}
-
-	return true;
-}
-
-static void virtblk_request(struct request_queue *q)
-{
-	struct virtio_blk *vblk = q->queuedata;
-	struct request *req;
-	unsigned int issued = 0;
-
-	while ((req = blk_peek_request(q)) != NULL) {
-		BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
-
-		/* If this request fails, stop queue and wait for something to
-		   finish to restart it. */
-		if (!do_req(q, vblk, req)) {
-			blk_stop_queue(q);
-			break;
-		}
-		blk_start_request(req);
-		issued++;
-	}
-
-	if (issued)
+	spin_lock_irqsave(&vblk->vq_lock, flags);
+	if (__virtblk_add_req(vblk->vq, vbr, vbr->sg, num) < 0) {
+		spin_unlock_irqrestore(&vblk->vq_lock, flags);
+		blk_mq_stop_hw_queue(hctx);
 		virtqueue_kick(vblk->vq);
-}
-
-static void virtblk_make_request(struct request_queue *q, struct bio *bio)
-{
-	struct virtio_blk *vblk = q->queuedata;
-	struct virtblk_req *vbr;
-
-	BUG_ON(bio->bi_phys_segments + 2 > vblk->sg_elems);
-
-	vbr = virtblk_alloc_req(vblk, GFP_NOIO);
-	if (!vbr) {
-		bio_endio(bio, -ENOMEM);
-		return;
+		return BLK_MQ_RQ_QUEUE_BUSY;
 	}
+	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 
-	vbr->bio = bio;
-	vbr->flags = 0;
-	if (bio->bi_rw & REQ_FLUSH)
-		vbr->flags |= VBLK_REQ_FLUSH;
-	if (bio->bi_rw & REQ_FUA)
-		vbr->flags |= VBLK_REQ_FUA;
-	if (bio->bi_size)
-		vbr->flags |= VBLK_REQ_DATA;
-
-	if (unlikely(vbr->flags & VBLK_REQ_FLUSH))
-		virtblk_bio_send_flush(vbr);
-	else
-		virtblk_bio_send_data(vbr);
+	if (last)
+		virtqueue_kick(vblk->vq);
+	return BLK_MQ_RQ_QUEUE_OK;
 }
 
 /* return id (s/n) string for *disk to *id_str
@@ -673,12 +473,35 @@ static const struct device_attribute dev_attr_cache_type_rw =
 	__ATTR(cache_type, S_IRUGO|S_IWUSR,
 	       virtblk_cache_type_show, virtblk_cache_type_store);
 
+static struct blk_mq_ops virtio_mq_ops = {
+	.queue_rq	= virtio_queue_rq,
+	.map_queue	= blk_mq_map_queue,
+	.alloc_hctx	= blk_mq_alloc_single_hw_queue,
+	.free_hctx	= blk_mq_free_single_hw_queue,
+};
+
+static struct blk_mq_reg virtio_mq_reg = {
+	.ops		= &virtio_mq_ops,
+	.nr_hw_queues	= 1,
+	.queue_depth	= 64,
+	.numa_node	= NUMA_NO_NODE,
+	.flags		= BLK_MQ_F_SHOULD_MERGE,
+};
+
+static void virtblk_init_vbr(void *data, struct blk_mq_hw_ctx *hctx,
+			     struct request *rq, unsigned int nr)
+{
+	struct virtio_blk *vblk = data;
+	struct virtblk_req *vbr = rq->special;
+
+	sg_init_table(vbr->sg, vblk->sg_elems);
+}
+
 static int virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
 	struct request_queue *q;
 	int err, index;
-	int pool_size;
 
 	u64 cap;
 	u32 v, blk_size, sg_elems, opt_io_size;
@@ -702,17 +525,14 @@ static int virtblk_probe(struct virtio_device *vdev)
 
 	/* We need an extra sg elements at head and tail. */
 	sg_elems += 2;
-	vdev->priv = vblk = kmalloc(sizeof(*vblk) +
-				    sizeof(vblk->sg[0]) * sg_elems, GFP_KERNEL);
+	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
 	if (!vblk) {
 		err = -ENOMEM;
 		goto out_free_index;
 	}
 
-	init_waitqueue_head(&vblk->queue_wait);
 	vblk->vdev = vdev;
 	vblk->sg_elems = sg_elems;
-	sg_init_table(vblk->sg, vblk->sg_elems);
 	mutex_init(&vblk->config_lock);
 
 	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
@@ -721,31 +541,27 @@ static int virtblk_probe(struct virtio_device *vdev)
 	err = init_vq(vblk);
 	if (err)
 		goto out_free_vblk;
-
-	pool_size = sizeof(struct virtblk_req);
-	if (use_bio)
-		pool_size += sizeof(struct scatterlist) * sg_elems;
-	vblk->pool = mempool_create_kmalloc_pool(1, pool_size);
-	if (!vblk->pool) {
-		err = -ENOMEM;
-		goto out_free_vq;
-	}
+	spin_lock_init(&vblk->vq_lock);
 
 	/* FIXME: How many partitions?  How long is a piece of string? */
 	vblk->disk = alloc_disk(1 << PART_BITS);
 	if (!vblk->disk) {
 		err = -ENOMEM;
-		goto out_mempool;
+		goto out_free_vq;
 	}
 
-	q = vblk->disk->queue = blk_init_queue(virtblk_request, NULL);
+	virtio_mq_reg.cmd_size =
+		sizeof(struct virtblk_req) +
+		sizeof(struct scatterlist) * sg_elems;
+
+	q = vblk->disk->queue = blk_mq_init_queue(&virtio_mq_reg, vblk);
 	if (!q) {
 		err = -ENOMEM;
 		goto out_put_disk;
 	}
 
-	if (use_bio)
-		blk_queue_make_request(q, virtblk_make_request);
+	blk_mq_init_commands(q, virtblk_init_vbr, vblk);
+
 	q->queuedata = vblk;
 
 	virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN);
@@ -848,8 +664,6 @@ static int virtblk_probe(struct virtio_device *vdev)
 	blk_cleanup_queue(vblk->disk->queue);
 out_put_disk:
 	put_disk(vblk->disk);
-out_mempool:
-	mempool_destroy(vblk->pool);
 out_free_vq:
 	vdev->config->del_vqs(vdev);
 out_free_vblk:
@@ -881,7 +695,6 @@ static void virtblk_remove(struct virtio_device *vdev)
 
 	refc = atomic_read(&disk_to_dev(vblk->disk)->kobj.kref.refcount);
 	put_disk(vblk->disk);
-	mempool_destroy(vblk->pool);
 	vdev->config->del_vqs(vdev);
 	kfree(vblk);
 
@@ -905,10 +718,7 @@ static int virtblk_freeze(struct virtio_device *vdev)
 
 	flush_work(&vblk->config_work);
 
-	spin_lock_irq(vblk->disk->queue->queue_lock);
-	blk_stop_queue(vblk->disk->queue);
-	spin_unlock_irq(vblk->disk->queue->queue_lock);
-	blk_sync_queue(vblk->disk->queue);
+	blk_mq_stop_hw_queues(vblk->disk->queue);
 
 	vdev->config->del_vqs(vdev);
 	return 0;
@@ -921,11 +731,9 @@ static int virtblk_restore(struct virtio_device *vdev)
 
 	vblk->config_enable = true;
 	ret = init_vq(vdev->priv);
-	if (!ret) {
-		spin_lock_irq(vblk->disk->queue->queue_lock);
-		blk_start_queue(vblk->disk->queue);
-		spin_unlock_irq(vblk->disk->queue->queue_lock);
-	}
+	if (!ret)
+		blk_mq_start_stopped_hw_queues(vblk->disk->queue);
+
 	return ret;
 }
 #endif

drivers/md/bcache/Kconfig

@@ -13,15 +13,8 @@ config BCACHE_DEBUG
 	---help---
 	Don't select this option unless you're a developer
 
-	Enables extra debugging tools (primarily a fuzz tester)
-
-config BCACHE_EDEBUG
-	bool "Extended runtime checks"
-	depends on BCACHE
-	---help---
-	Don't select this option unless you're a developer
-
-	Enables extra runtime checks which significantly affect performance
+	Enables extra debugging tools, allows expensive runtime checks to be
+	turned on.
 
 config BCACHE_CLOSURES_DEBUG
 	bool "Debug closures"

drivers/md/bcache/alloc.c

@@ -63,13 +63,12 @@
 #include "bcache.h"
 #include "btree.h"
 
+#include <linux/blkdev.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/random.h>
 #include <trace/events/bcache.h>
 
-#define MAX_IN_FLIGHT_DISCARDS		8U
-
 /* Bucket heap / gen */
 
 uint8_t bch_inc_gen(struct cache *ca, struct bucket *b)
@@ -121,75 +120,6 @@ void bch_rescale_priorities(struct cache_set *c, int sectors)
 	mutex_unlock(&c->bucket_lock);
 }
 
-/* Discard/TRIM */
-
-struct discard {
-	struct list_head	list;
-	struct work_struct	work;
-	struct cache		*ca;
-	long			bucket;
-
-	struct bio		bio;
-	struct bio_vec		bv;
-};
-
-static void discard_finish(struct work_struct *w)
-{
-	struct discard *d = container_of(w, struct discard, work);
-	struct cache *ca = d->ca;
-	char buf[BDEVNAME_SIZE];
-
-	if (!test_bit(BIO_UPTODATE, &d->bio.bi_flags)) {
-		pr_notice("discard error on %s, disabling",
-			 bdevname(ca->bdev, buf));
-		d->ca->discard = 0;
-	}
-
-	mutex_lock(&ca->set->bucket_lock);
-
-	fifo_push(&ca->free, d->bucket);
-	list_add(&d->list, &ca->discards);
-	atomic_dec(&ca->discards_in_flight);
-
-	mutex_unlock(&ca->set->bucket_lock);
-
-	closure_wake_up(&ca->set->bucket_wait);
-	wake_up_process(ca->alloc_thread);
-
-	closure_put(&ca->set->cl);
-}
-
-static void discard_endio(struct bio *bio, int error)
-{
-	struct discard *d = container_of(bio, struct discard, bio);
-	schedule_work(&d->work);
-}
-
-static void do_discard(struct cache *ca, long bucket)
-{
-	struct discard *d = list_first_entry(&ca->discards,
-					     struct discard, list);
-
-	list_del(&d->list);
-	d->bucket = bucket;
-
-	atomic_inc(&ca->discards_in_flight);
-	closure_get(&ca->set->cl);
-
-	bio_init(&d->bio);
-
-	d->bio.bi_sector	= bucket_to_sector(ca->set, d->bucket);
-	d->bio.bi_bdev		= ca->bdev;
-	d->bio.bi_rw		= REQ_WRITE|REQ_DISCARD;
-	d->bio.bi_max_vecs	= 1;
-	d->bio.bi_io_vec	= d->bio.bi_inline_vecs;
-	d->bio.bi_size		= bucket_bytes(ca);
-	d->bio.bi_end_io	= discard_endio;
-	bio_set_prio(&d->bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
-
-	submit_bio(0, &d->bio);
-}
-
 /* Allocation */
 
 static inline bool can_inc_bucket_gen(struct bucket *b)
@@ -280,7 +210,7 @@ static void invalidate_buckets_lru(struct cache *ca)
 			 * multiple times when it can't do anything
 			 */
 			ca->invalidate_needs_gc = 1;
-			bch_queue_gc(ca->set);
+			wake_up_gc(ca->set);
 			return;
 		}
 
@@ -305,7 +235,7 @@ static void invalidate_buckets_fifo(struct cache *ca)
 
 		if (++checked >= ca->sb.nbuckets) {
 			ca->invalidate_needs_gc = 1;
-			bch_queue_gc(ca->set);
+			wake_up_gc(ca->set);
 			return;
 		}
 	}
@@ -330,7 +260,7 @@ static void invalidate_buckets_random(struct cache *ca)
 
 		if (++checked >= ca->sb.nbuckets / 2) {
 			ca->invalidate_needs_gc = 1;
-			bch_queue_gc(ca->set);
+			wake_up_gc(ca->set);
 			return;
 		}
 	}
@@ -398,16 +328,18 @@ static int bch_allocator_thread(void *arg)
 			else
 				break;
 
-			allocator_wait(ca, (int) fifo_free(&ca->free) >
-				       atomic_read(&ca->discards_in_flight));
-
 			if (ca->discard) {
-				allocator_wait(ca, !list_empty(&ca->discards));
-				do_discard(ca, bucket);
-			} else {
-				fifo_push(&ca->free, bucket);
-				closure_wake_up(&ca->set->bucket_wait);
+				mutex_unlock(&ca->set->bucket_lock);
+				blkdev_issue_discard(ca->bdev,
+					bucket_to_sector(ca->set, bucket),
+					ca->sb.block_size, GFP_KERNEL, 0);
+				mutex_lock(&ca->set->bucket_lock);
 			}
+
+			allocator_wait(ca, !fifo_full(&ca->free));
+
+			fifo_push(&ca->free, bucket);
+			wake_up(&ca->set->bucket_wait);
 		}
 
 		/*
@@ -433,16 +365,40 @@ static int bch_allocator_thread(void *arg)
 	}
 }
 
-long bch_bucket_alloc(struct cache *ca, unsigned watermark, struct closure *cl)
+long bch_bucket_alloc(struct cache *ca, unsigned watermark, bool wait)
 {
-	long r = -1;
-again:
+	DEFINE_WAIT(w);
+	struct bucket *b;
+	long r;
+
+	/* fastpath */
+	if (fifo_used(&ca->free) > ca->watermark[watermark]) {
+		fifo_pop(&ca->free, r);
+		goto out;
+	}
+
+	if (!wait)
+		return -1;
+
+	while (1) {
+		if (fifo_used(&ca->free) > ca->watermark[watermark]) {
+			fifo_pop(&ca->free, r);
+			break;
+		}
+
+		prepare_to_wait(&ca->set->bucket_wait, &w,
+				TASK_UNINTERRUPTIBLE);
+
+		mutex_unlock(&ca->set->bucket_lock);
+		schedule();
+		mutex_lock(&ca->set->bucket_lock);
+	}
+
+	finish_wait(&ca->set->bucket_wait, &w);
+out:
 	wake_up_process(ca->alloc_thread);
 
-	if (fifo_used(&ca->free) > ca->watermark[watermark] &&
-	    fifo_pop(&ca->free, r)) {
-		struct bucket *b = ca->buckets + r;
-#ifdef CONFIG_BCACHE_EDEBUG
+	if (expensive_debug_checks(ca->set)) {
 		size_t iter;
 		long i;
 
@@ -455,36 +411,23 @@ long bch_bucket_alloc(struct cache *ca, unsigned watermark, struct closure *cl)
 			BUG_ON(i == r);
 		fifo_for_each(i, &ca->unused, iter)
 			BUG_ON(i == r);
-#endif
-		BUG_ON(atomic_read(&b->pin) != 1);
-
-		SET_GC_SECTORS_USED(b, ca->sb.bucket_size);
-
-		if (watermark <= WATERMARK_METADATA) {
-			SET_GC_MARK(b, GC_MARK_METADATA);
-			b->prio = BTREE_PRIO;
-		} else {
-			SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
-			b->prio = INITIAL_PRIO;
-		}
-
-		return r;
 	}
 
-	trace_bcache_alloc_fail(ca);
+	b = ca->buckets + r;
 
-	if (cl) {
-		closure_wait(&ca->set->bucket_wait, cl);
+	BUG_ON(atomic_read(&b->pin) != 1);
 
-		if (closure_blocking(cl)) {
-			mutex_unlock(&ca->set->bucket_lock);
-			closure_sync(cl);
-			mutex_lock(&ca->set->bucket_lock);
-			goto again;
-		}
+	SET_GC_SECTORS_USED(b, ca->sb.bucket_size);
+
+	if (watermark <= WATERMARK_METADATA) {
+		SET_GC_MARK(b, GC_MARK_METADATA);
+		b->prio = BTREE_PRIO;
+	} else {
+		SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
+		b->prio = INITIAL_PRIO;
 	}
 
-	return -1;
+	return r;
 }
 
 void bch_bucket_free(struct cache_set *c, struct bkey *k)
@@ -501,7 +444,7 @@ void bch_bucket_free(struct cache_set *c, struct bkey *k)
 }
 
 int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
-			   struct bkey *k, int n, struct closure *cl)
+			   struct bkey *k, int n, bool wait)
 {
 	int i;
 
@@ -514,7 +457,7 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
 
 	for (i = 0; i < n; i++) {
 		struct cache *ca = c->cache_by_alloc[i];
-		long b = bch_bucket_alloc(ca, watermark, cl);
+		long b = bch_bucket_alloc(ca, watermark, wait);
 
 		if (b == -1)
 			goto err;
@@ -529,22 +472,202 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
 	return 0;
 err:
 	bch_bucket_free(c, k);
-	__bkey_put(c, k);
+	bkey_put(c, k);
 	return -1;
 }
 
 int bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
-			 struct bkey *k, int n, struct closure *cl)
+			 struct bkey *k, int n, bool wait)
 {
 	int ret;
 	mutex_lock(&c->bucket_lock);
-	ret = __bch_bucket_alloc_set(c, watermark, k, n, cl);
+	ret = __bch_bucket_alloc_set(c, watermark, k, n, wait);
 	mutex_unlock(&c->bucket_lock);
 	return ret;
 }
 
+/* Sector allocator */
+
+struct open_bucket {
+	struct list_head	list;
+	unsigned		last_write_point;
+	unsigned		sectors_free;
+	BKEY_PADDED(key);
+};
+
+/*
+ * We keep multiple buckets open for writes, and try to segregate different
+ * write streams for better cache utilization: first we look for a bucket where
+ * the last write to it was sequential with the current write, and failing that
+ * we look for a bucket that was last used by the same task.
+ *
+ * The ideas is if you've got multiple tasks pulling data into the cache at the
+ * same time, you'll get better cache utilization if you try to segregate their
+ * data and preserve locality.
+ *
+ * For example, say you've starting Firefox at the same time you're copying a
+ * bunch of files. Firefox will likely end up being fairly hot and stay in the
+ * cache awhile, but the data you copied might not be; if you wrote all that
+ * data to the same buckets it'd get invalidated at the same time.
+ *
+ * Both of those tasks will be doing fairly random IO so we can't rely on
+ * detecting sequential IO to segregate their data, but going off of the task
+ * should be a sane heuristic.
+ */
+static struct open_bucket *pick_data_bucket(struct cache_set *c,
+					    const struct bkey *search,
+					    unsigned write_point,
+					    struct bkey *alloc)
+{
+	struct open_bucket *ret, *ret_task = NULL;
+
+	list_for_each_entry_reverse(ret, &c->data_buckets, list)
+		if (!bkey_cmp(&ret->key, search))
+			goto found;
+		else if (ret->last_write_point == write_point)
+			ret_task = ret;
+
+	ret = ret_task ?: list_first_entry(&c->data_buckets,
+					   struct open_bucket, list);
+found:
+	if (!ret->sectors_free && KEY_PTRS(alloc)) {
+		ret->sectors_free = c->sb.bucket_size;
+		bkey_copy(&ret->key, alloc);
+		bkey_init(alloc);
+	}
+
+	if (!ret->sectors_free)
+		ret = NULL;
+
+	return ret;
+}
+
+/*
+ * Allocates some space in the cache to write to, and k to point to the newly
+ * allocated space, and updates KEY_SIZE(k) and KEY_OFFSET(k) (to point to the
+ * end of the newly allocated space).
+ *
+ * May allocate fewer sectors than @sectors, KEY_SIZE(k) indicates how many
+ * sectors were actually allocated.
+ *
+ * If s->writeback is true, will not fail.
+ */
+bool bch_alloc_sectors(struct cache_set *c, struct bkey *k, unsigned sectors,
+		       unsigned write_point, unsigned write_prio, bool wait)
+{
+	struct open_bucket *b;
+	BKEY_PADDED(key) alloc;
+	unsigned i;
+
+	/*
+	 * We might have to allocate a new bucket, which we can't do with a
+	 * spinlock held. So if we have to allocate, we drop the lock, allocate
+	 * and then retry. KEY_PTRS() indicates whether alloc points to
+	 * allocated bucket(s).
+	 */
+
+	bkey_init(&alloc.key);
+	spin_lock(&c->data_bucket_lock);
+
+	while (!(b = pick_data_bucket(c, k, write_point, &alloc.key))) {
+		unsigned watermark = write_prio
+			? WATERMARK_MOVINGGC
+			: WATERMARK_NONE;
+
+		spin_unlock(&c->data_bucket_lock);
+
+		if (bch_bucket_alloc_set(c, watermark, &alloc.key, 1, wait))
+			return false;
+
+		spin_lock(&c->data_bucket_lock);
+	}
+
+	/*
+	 * If we had to allocate, we might race and not need to allocate the
+	 * second time we call find_data_bucket(). If we allocated a bucket but
+	 * didn't use it, drop the refcount bch_bucket_alloc_set() took:
+	 */
+	if (KEY_PTRS(&alloc.key))
+		bkey_put(c, &alloc.key);
+
+	for (i = 0; i < KEY_PTRS(&b->key); i++)
+		EBUG_ON(ptr_stale(c, &b->key, i));
+
+	/* Set up the pointer to the space we're allocating: */
+
+	for (i = 0; i < KEY_PTRS(&b->key); i++)
+		k->ptr[i] = b->key.ptr[i];
+
+	sectors = min(sectors, b->sectors_free);
+
+	SET_KEY_OFFSET(k, KEY_OFFSET(k) + sectors);
+	SET_KEY_SIZE(k, sectors);
+	SET_KEY_PTRS(k, KEY_PTRS(&b->key));
+
+	/*
+	 * Move b to the end of the lru, and keep track of what this bucket was
+	 * last used for:
+	 */
+	list_move_tail(&b->list, &c->data_buckets);
+	bkey_copy_key(&b->key, k);
+	b->last_write_point = write_point;
+
+	b->sectors_free	-= sectors;
+
+	for (i = 0; i < KEY_PTRS(&b->key); i++) {
+		SET_PTR_OFFSET(&b->key, i, PTR_OFFSET(&b->key, i) + sectors);
+
+		atomic_long_add(sectors,
+				&PTR_CACHE(c, &b->key, i)->sectors_written);
+	}
+
+	if (b->sectors_free < c->sb.block_size)
+		b->sectors_free = 0;
+
+	/*
+	 * k takes refcounts on the buckets it points to until it's inserted
+	 * into the btree, but if we're done with this bucket we just transfer
+	 * get_data_bucket()'s refcount.
+	 */
+	if (b->sectors_free)
+		for (i = 0; i < KEY_PTRS(&b->key); i++)
+			atomic_inc(&PTR_BUCKET(c, &b->key, i)->pin);
+
+	spin_unlock(&c->data_bucket_lock);
+	return true;
+}
+
 /* Init */
 
+void bch_open_buckets_free(struct cache_set *c)
+{
+	struct open_bucket *b;
+
+	while (!list_empty(&c->data_buckets)) {
+		b = list_first_entry(&c->data_buckets,
+				     struct open_bucket, list);
+		list_del(&b->list);
+		kfree(b);
+	}
+}
+
+int bch_open_buckets_alloc(struct cache_set *c)
+{
+	int i;
+
+	spin_lock_init(&c->data_bucket_lock);
+
+	for (i = 0; i < 6; i++) {
+		struct open_bucket *b = kzalloc(sizeof(*b), GFP_KERNEL);
+		if (!b)
+			return -ENOMEM;
+
+		list_add(&b->list, &c->data_buckets);
+	}
+
+	return 0;
+}
+
 int bch_cache_allocator_start(struct cache *ca)
 {
 	struct task_struct *k = kthread_run(bch_allocator_thread,
@@ -556,22 +679,8 @@ int bch_cache_allocator_start(struct cache *ca)
 	return 0;
 }
 
-void bch_cache_allocator_exit(struct cache *ca)
-{
-	struct discard *d;
-
-	while (!list_empty(&ca->discards)) {
-		d = list_first_entry(&ca->discards, struct discard, list);
-		cancel_work_sync(&d->work);
-		list_del(&d->list);
-		kfree(d);
-	}
-}
-
 int bch_cache_allocator_init(struct cache *ca)
 {
-	unsigned i;
-
 	/*
 	 * Reserve:
 	 * Prio/gen writes first
@@ -589,15 +698,5 @@ int bch_cache_allocator_init(struct cache *ca)
 	ca->watermark[WATERMARK_NONE] = ca->free.size / 2 +
 		ca->watermark[WATERMARK_MOVINGGC];
 
-	for (i = 0; i < MAX_IN_FLIGHT_DISCARDS; i++) {
-		struct discard *d = kzalloc(sizeof(*d), GFP_KERNEL);
-		if (!d)
-			return -ENOMEM;
-
-		d->ca = ca;
-		INIT_WORK(&d->work, discard_finish);
-		list_add(&d->list, &ca->discards);
-	}
-
 	return 0;
 }

drivers/md/bcache/bcache.h

@@ -177,6 +177,7 @@
 
 #define pr_fmt(fmt) "bcache: %s() " fmt "\n", __func__
 
+#include <linux/bcache.h>
 #include <linux/bio.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
@@ -210,168 +211,6 @@ BITMASK(GC_MARK,	 struct bucket, gc_mark, 0, 2);
 #define GC_MARK_METADATA	2
 BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 14);
 
-struct bkey {
-	uint64_t	high;
-	uint64_t	low;
-	uint64_t	ptr[];
-};
-
-/* Enough for a key with 6 pointers */
-#define BKEY_PAD		8
-
-#define BKEY_PADDED(key)					\
-	union { struct bkey key; uint64_t key ## _pad[BKEY_PAD]; }
-
-/* Version 0: Cache device
- * Version 1: Backing device
- * Version 2: Seed pointer into btree node checksum
- * Version 3: Cache device with new UUID format
- * Version 4: Backing device with data offset
- */
-#define BCACHE_SB_VERSION_CDEV			0
-#define BCACHE_SB_VERSION_BDEV			1
-#define BCACHE_SB_VERSION_CDEV_WITH_UUID	3
-#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET	4
-#define BCACHE_SB_MAX_VERSION			4
-
-#define SB_SECTOR		8
-#define SB_SIZE			4096
-#define SB_LABEL_SIZE		32
-#define SB_JOURNAL_BUCKETS	256U
-/* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */
-#define MAX_CACHES_PER_SET	8
-
-#define BDEV_DATA_START_DEFAULT	16	/* sectors */
-
-struct cache_sb {
-	uint64_t		csum;
-	uint64_t		offset;	/* sector where this sb was written */
-	uint64_t		version;
-
-	uint8_t			magic[16];
-
-	uint8_t			uuid[16];
-	union {
-		uint8_t		set_uuid[16];
-		uint64_t	set_magic;
-	};
-	uint8_t			label[SB_LABEL_SIZE];
-
-	uint64_t		flags;
-	uint64_t		seq;
-	uint64_t		pad[8];
-
-	union {
-	struct {
-		/* Cache devices */
-		uint64_t	nbuckets;	/* device size */
-
-		uint16_t	block_size;	/* sectors */
-		uint16_t	bucket_size;	/* sectors */
-
-		uint16_t	nr_in_set;
-		uint16_t	nr_this_dev;
-	};
-	struct {
-		/* Backing devices */
-		uint64_t	data_offset;
-
-		/*
-		 * block_size from the cache device section is still used by
-		 * backing devices, so don't add anything here until we fix
-		 * things to not need it for backing devices anymore
-		 */
-	};
-	};
-
-	uint32_t		last_mount;	/* time_t */
-
-	uint16_t		first_bucket;
-	union {
-		uint16_t	njournal_buckets;
-		uint16_t	keys;
-	};
-	uint64_t		d[SB_JOURNAL_BUCKETS];	/* journal buckets */
-};
-
-BITMASK(CACHE_SYNC,		struct cache_sb, flags, 0, 1);
-BITMASK(CACHE_DISCARD,		struct cache_sb, flags, 1, 1);
-BITMASK(CACHE_REPLACEMENT,	struct cache_sb, flags, 2, 3);
-#define CACHE_REPLACEMENT_LRU	0U
-#define CACHE_REPLACEMENT_FIFO	1U
-#define CACHE_REPLACEMENT_RANDOM 2U
-
-BITMASK(BDEV_CACHE_MODE,	struct cache_sb, flags, 0, 4);
-#define CACHE_MODE_WRITETHROUGH	0U
-#define CACHE_MODE_WRITEBACK	1U
-#define CACHE_MODE_WRITEAROUND	2U
-#define CACHE_MODE_NONE		3U
-BITMASK(BDEV_STATE,		struct cache_sb, flags, 61, 2);
-#define BDEV_STATE_NONE		0U
-#define BDEV_STATE_CLEAN	1U
-#define BDEV_STATE_DIRTY	2U
-#define BDEV_STATE_STALE	3U
-
-/* Version 1: Seed pointer into btree node checksum
- */
-#define BCACHE_BSET_VERSION	1
-
-/*
- * This is the on disk format for btree nodes - a btree node on disk is a list
- * of these; within each set the keys are sorted
- */
-struct bset {
-	uint64_t		csum;
-	uint64_t		magic;
-	uint64_t		seq;
-	uint32_t		version;
-	uint32_t		keys;
-
-	union {
-		struct bkey	start[0];
-		uint64_t	d[0];
-	};
-};
-
-/*
- * On disk format for priorities and gens - see super.c near prio_write() for
- * more.
- */
-struct prio_set {
-	uint64_t		csum;
-	uint64_t		magic;
-	uint64_t		seq;
-	uint32_t		version;
-	uint32_t		pad;
-
-	uint64_t		next_bucket;
-
-	struct bucket_disk {
-		uint16_t	prio;
-		uint8_t		gen;
-	} __attribute((packed)) data[];
-};
-
-struct uuid_entry {
-	union {
-		struct {
-			uint8_t		uuid[16];
-			uint8_t		label[32];
-			uint32_t	first_reg;
-			uint32_t	last_reg;
-			uint32_t	invalidated;
-
-			uint32_t	flags;
-			/* Size of flash only volumes */
-			uint64_t	sectors;
-		};
-
-		uint8_t	pad[128];
-	};
-};
-
-BITMASK(UUID_FLASH_ONLY,	struct uuid_entry, flags, 0, 1);
-
 #include "journal.h"
 #include "stats.h"
 struct search;
@@ -384,8 +223,6 @@ struct keybuf_key {
 	void			*private;
 };
 
-typedef bool (keybuf_pred_fn)(struct keybuf *, struct bkey *);
-
 struct keybuf {
 	struct bkey		last_scanned;
 	spinlock_t		lock;
@@ -400,7 +237,7 @@ struct keybuf {
 
 	struct rb_root		keys;
 
-#define KEYBUF_NR		100
+#define KEYBUF_NR		500
 	DECLARE_ARRAY_ALLOCATOR(struct keybuf_key, freelist, KEYBUF_NR);
 };
 
@@ -429,16 +266,15 @@ struct bcache_device {
 
 	struct gendisk		*disk;
 
-	/* If nonzero, we're closing */
-	atomic_t		closing;
-
-	/* If nonzero, we're detaching/unregistering from cache set */
-	atomic_t		detaching;
-	int			flush_done;
+	unsigned long		flags;
+#define BCACHE_DEV_CLOSING	0
+#define BCACHE_DEV_DETACHING	1
+#define BCACHE_DEV_UNLINK_DONE	2
 
-	uint64_t		nr_stripes;
-	unsigned		stripe_size_bits;
+	unsigned		nr_stripes;
+	unsigned		stripe_size;
 	atomic_t		*stripe_sectors_dirty;
+	unsigned long		*full_dirty_stripes;
 
 	unsigned long		sectors_dirty_last;
 	long			sectors_dirty_derivative;
@@ -509,7 +345,7 @@ struct cached_dev {
 
 	/* Limit number of writeback bios in flight */
 	struct semaphore	in_flight;
-	struct closure_with_timer writeback;
+	struct task_struct	*writeback_thread;
 
 	struct keybuf		writeback_keys;
 
@@ -527,8 +363,8 @@ struct cached_dev {
 	unsigned		sequential_cutoff;
 	unsigned		readahead;
 
-	unsigned		sequential_merge:1;
 	unsigned		verify:1;
+	unsigned		bypass_torture_test:1;
 
 	unsigned		partial_stripes_expensive:1;
 	unsigned		writeback_metadata:1;
@@ -620,15 +456,6 @@ struct cache {
 
 	bool			discard; /* Get rid of? */
 
-	/*
-	 * We preallocate structs for issuing discards to buckets, and keep them
-	 * on this list when they're not in use; do_discard() issues discards
-	 * whenever there's work to do and is called by free_some_buckets() and
-	 * when a discard finishes.
-	 */
-	atomic_t		discards_in_flight;
-	struct list_head	discards;
-
 	struct journal_device	journal;
 
 	/* The rest of this all shows up in sysfs */
@@ -649,7 +476,6 @@ struct gc_stat {
 
 	size_t			nkeys;
 	uint64_t		data;	/* sectors */
-	uint64_t		dirty;	/* sectors */
 	unsigned		in_use; /* percent */
 };
 
@@ -744,8 +570,8 @@ struct cache_set {
 	 * basically a lock for this that we can wait on asynchronously. The
 	 * btree_root() macro releases the lock when it returns.
 	 */
-	struct closure		*try_harder;
-	struct closure_waitlist	try_wait;
+	struct task_struct	*try_harder;
+	wait_queue_head_t	try_wait;
 	uint64_t		try_harder_start;
 
 	/*
@@ -759,7 +585,7 @@ struct cache_set {
 	 * written.
 	 */
 	atomic_t		prio_blocked;
-	struct closure_waitlist	bucket_wait;
+	wait_queue_head_t	bucket_wait;
 
 	/*
 	 * For any bio we don't skip we subtract the number of sectors from
@@ -782,7 +608,7 @@ struct cache_set {
 	struct gc_stat		gc_stats;
 	size_t			nbuckets;
 
-	struct closure_with_waitlist gc;
+	struct task_struct	*gc_thread;
 	/* Where in the btree gc currently is */
 	struct bkey		gc_done;
 
@@ -795,11 +621,10 @@ struct cache_set {
 	/* Counts how many sectors bio_insert has added to the cache */
 	atomic_t		sectors_to_gc;
 
-	struct closure		moving_gc;
-	struct closure_waitlist	moving_gc_wait;
+	wait_queue_head_t	moving_gc_wait;
 	struct keybuf		moving_gc_keys;
 	/* Number of moving GC bios in flight */
-	atomic_t		in_flight;
+	struct semaphore	moving_in_flight;
 
 	struct btree		*root;
 
@@ -841,22 +666,27 @@ struct cache_set {
 	unsigned		congested_read_threshold_us;
 	unsigned		congested_write_threshold_us;
 
-	spinlock_t		sort_time_lock;
 	struct time_stats	sort_time;
 	struct time_stats	btree_gc_time;
 	struct time_stats	btree_split_time;
-	spinlock_t		btree_read_time_lock;
 	struct time_stats	btree_read_time;
 	struct time_stats	try_harder_time;
 
 	atomic_long_t		cache_read_races;
 	atomic_long_t		writeback_keys_done;
 	atomic_long_t		writeback_keys_failed;
+
+	enum			{
+		ON_ERROR_UNREGISTER,
+		ON_ERROR_PANIC,
+	}			on_error;
 	unsigned		error_limit;
 	unsigned		error_decay;
+
 	unsigned short		journal_delay_ms;
 	unsigned		verify:1;
 	unsigned		key_merging_disabled:1;
+	unsigned		expensive_debug_checks:1;
 	unsigned		gc_always_rewrite:1;
 	unsigned		shrinker_disabled:1;
 	unsigned		copy_gc_enabled:1;
@@ -865,21 +695,6 @@ struct cache_set {
 	struct hlist_head	bucket_hash[1 << BUCKET_HASH_BITS];
 };
 
-static inline bool key_merging_disabled(struct cache_set *c)
-{
-#ifdef CONFIG_BCACHE_DEBUG
-	return c->key_merging_disabled;
-#else
-	return 0;
-#endif
-}
-
-static inline bool SB_IS_BDEV(const struct cache_sb *sb)
-{
-	return sb->version == BCACHE_SB_VERSION_BDEV
-		|| sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET;
-}
-
 struct bbio {
 	unsigned		submit_time_us;
 	union {
@@ -933,59 +748,6 @@ static inline unsigned local_clock_us(void)
 #define prio_buckets(c)					\
 	DIV_ROUND_UP((size_t) (c)->sb.nbuckets, prios_per_bucket(c))
 
-#define JSET_MAGIC		0x245235c1a3625032ULL
-#define PSET_MAGIC		0x6750e15f87337f91ULL
-#define BSET_MAGIC		0x90135c78b99e07f5ULL
-
-#define jset_magic(c)		((c)->sb.set_magic ^ JSET_MAGIC)
-#define pset_magic(c)		((c)->sb.set_magic ^ PSET_MAGIC)
-#define bset_magic(c)		((c)->sb.set_magic ^ BSET_MAGIC)
-
-/* Bkey fields: all units are in sectors */
-
-#define KEY_FIELD(name, field, offset, size)				\
-	BITMASK(name, struct bkey, field, offset, size)
-
-#define PTR_FIELD(name, offset, size)					\
-	static inline uint64_t name(const struct bkey *k, unsigned i)	\
-	{ return (k->ptr[i] >> offset) & ~(((uint64_t) ~0) << size); }	\
-									\
-	static inline void SET_##name(struct bkey *k, unsigned i, uint64_t v)\
-	{								\
-		k->ptr[i] &= ~(~((uint64_t) ~0 << size) << offset);	\
-		k->ptr[i] |= v << offset;				\
-	}
-
-KEY_FIELD(KEY_PTRS,	high, 60, 3)
-KEY_FIELD(HEADER_SIZE,	high, 58, 2)
-KEY_FIELD(KEY_CSUM,	high, 56, 2)
-KEY_FIELD(KEY_PINNED,	high, 55, 1)
-KEY_FIELD(KEY_DIRTY,	high, 36, 1)
-
-KEY_FIELD(KEY_SIZE,	high, 20, 16)
-KEY_FIELD(KEY_INODE,	high, 0,  20)
-
-/* Next time I change the on disk format, KEY_OFFSET() won't be 64 bits */
-
-static inline uint64_t KEY_OFFSET(const struct bkey *k)
-{
-	return k->low;
-}
-
-static inline void SET_KEY_OFFSET(struct bkey *k, uint64_t v)
-{
-	k->low = v;
-}
-
-PTR_FIELD(PTR_DEV,		51, 12)
-PTR_FIELD(PTR_OFFSET,		8,  43)
-PTR_FIELD(PTR_GEN,		0,  8)
-
-#define PTR_CHECK_DEV		((1 << 12) - 1)
-
-#define PTR(gen, offset, dev)						\
-	((((uint64_t) dev) << 51) | ((uint64_t) offset) << 8 | gen)
-
 static inline size_t sector_to_bucket(struct cache_set *c, sector_t s)
 {
 	return s >> c->bucket_bits;
@@ -1024,27 +786,11 @@ static inline struct bucket *PTR_BUCKET(struct cache_set *c,
 
 /* Btree key macros */
 
-/*
- * The high bit being set is a relic from when we used it to do binary
- * searches - it told you where a key started. It's not used anymore,
- * and can probably be safely dropped.
- */
-#define KEY(dev, sector, len)						\
-((struct bkey) {							\
-	.high = (1ULL << 63) | ((uint64_t) (len) << 20) | (dev),	\
-	.low = (sector)							\
-})
-
 static inline void bkey_init(struct bkey *k)
 {
-	*k = KEY(0, 0, 0);
+	*k = ZERO_KEY;
 }
 
-#define KEY_START(k)		(KEY_OFFSET(k) - KEY_SIZE(k))
-#define START_KEY(k)		KEY(KEY_INODE(k), KEY_START(k), 0)
-#define MAX_KEY			KEY(~(~0 << 20), ((uint64_t) ~0) >> 1, 0)
-#define ZERO_KEY		KEY(0, 0, 0)
-
 /*
  * This is used for various on disk data structures - cache_sb, prio_set, bset,
  * jset: The checksum is _always_ the first 8 bytes of these structs
@@ -1094,14 +840,6 @@ do {									\
 	for (b = (ca)->buckets + (ca)->sb.first_bucket;			\
 	     b < (ca)->buckets + (ca)->sb.nbuckets; b++)
 
-static inline void __bkey_put(struct cache_set *c, struct bkey *k)
-{
-	unsigned i;
-
-	for (i = 0; i < KEY_PTRS(k); i++)
-		atomic_dec_bug(&PTR_BUCKET(c, k, i)->pin);
-}
-
 static inline void cached_dev_put(struct cached_dev *dc)
 {
 	if (atomic_dec_and_test(&dc->count))
@@ -1173,13 +911,15 @@ uint8_t bch_inc_gen(struct cache *, struct bucket *);
 void bch_rescale_priorities(struct cache_set *, int);
 bool bch_bucket_add_unused(struct cache *, struct bucket *);
 
-long bch_bucket_alloc(struct cache *, unsigned, struct closure *);
+long bch_bucket_alloc(struct cache *, unsigned, bool);
 void bch_bucket_free(struct cache_set *, struct bkey *);
 
 int __bch_bucket_alloc_set(struct cache_set *, unsigned,
-			   struct bkey *, int, struct closure *);
+			   struct bkey *, int, bool);
 int bch_bucket_alloc_set(struct cache_set *, unsigned,
-			 struct bkey *, int, struct closure *);
+			 struct bkey *, int, bool);
+bool bch_alloc_sectors(struct cache_set *, struct bkey *, unsigned,
+		       unsigned, unsigned, bool);
 
 __printf(2, 3)
 bool bch_cache_set_error(struct cache_set *, const char *, ...);
@@ -1187,7 +927,7 @@ bool bch_cache_set_error(struct cache_set *, const char *, ...);
 void bch_prio_write(struct cache *);
 void bch_write_bdev_super(struct cached_dev *, struct closure *);
 
-extern struct workqueue_struct *bcache_wq, *bch_gc_wq;
+extern struct workqueue_struct *bcache_wq;
 extern const char * const bch_cache_modes[];
 extern struct mutex bch_register_lock;
 extern struct list_head bch_cache_sets;
@@ -1220,15 +960,14 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *);
 void bch_btree_cache_free(struct cache_set *);
 int bch_btree_cache_alloc(struct cache_set *);
 void bch_moving_init_cache_set(struct cache_set *);
+int bch_open_buckets_alloc(struct cache_set *);
+void bch_open_buckets_free(struct cache_set *);
 
 int bch_cache_allocator_start(struct cache *ca);
-void bch_cache_allocator_exit(struct cache *ca);
 int bch_cache_allocator_init(struct cache *ca);
 
 void bch_debug_exit(void);
 int bch_debug_init(struct kobject *);
-void bch_writeback_exit(void);
-int bch_writeback_init(void);
 void bch_request_exit(void);
 int bch_request_init(void);
 void bch_btree_exit(void);

drivers/md/bcache/bset.c

@@ -14,22 +14,12 @@
 
 /* Keylists */
 
-void bch_keylist_copy(struct keylist *dest, struct keylist *src)
-{
-	*dest = *src;
-
-	if (src->list == src->d) {
-		size_t n = (uint64_t *) src->top - src->d;
-		dest->top = (struct bkey *) &dest->d[n];
-		dest->list = dest->d;
-	}
-}
-
 int bch_keylist_realloc(struct keylist *l, int nptrs, struct cache_set *c)
 {
-	unsigned oldsize = (uint64_t *) l->top - l->list;
-	unsigned newsize = oldsize + 2 + nptrs;
-	uint64_t *new;
+	size_t oldsize = bch_keylist_nkeys(l);
+	size_t newsize = oldsize + 2 + nptrs;
+	uint64_t *old_keys = l->keys_p == l->inline_keys ? NULL : l->keys_p;
+	uint64_t *new_keys;
 
 	/* The journalling code doesn't handle the case where the keys to insert
 	 * is bigger than an empty write: If we just return -ENOMEM here,
@@ -45,24 +35,23 @@ int bch_keylist_realloc(struct keylist *l, int nptrs, struct cache_set *c)
 	    roundup_pow_of_two(oldsize) == newsize)
 		return 0;
 
-	new = krealloc(l->list == l->d ? NULL : l->list,
-		       sizeof(uint64_t) * newsize, GFP_NOIO);
+	new_keys = krealloc(old_keys, sizeof(uint64_t) * newsize, GFP_NOIO);
 
-	if (!new)
+	if (!new_keys)
 		return -ENOMEM;
 
-	if (l->list == l->d)
-		memcpy(new, l->list, sizeof(uint64_t) * KEYLIST_INLINE);
+	if (!old_keys)
+		memcpy(new_keys, l->inline_keys, sizeof(uint64_t) * oldsize);
 
-	l->list = new;
-	l->top = (struct bkey *) (&l->list[oldsize]);
+	l->keys_p = new_keys;
+	l->top_p = new_keys + oldsize;
 
 	return 0;
 }
 
 struct bkey *bch_keylist_pop(struct keylist *l)
 {
-	struct bkey *k = l->bottom;
+	struct bkey *k = l->keys;
 
 	if (k == l->top)
 		return NULL;
@@ -73,21 +62,20 @@ struct bkey *bch_keylist_pop(struct keylist *l)
 	return l->top = k;
 }
 
-/* Pointer validation */
-
-bool __bch_ptr_invalid(struct cache_set *c, int level, const struct bkey *k)
+void bch_keylist_pop_front(struct keylist *l)
 {
-	unsigned i;
-	char buf[80];
+	l->top_p -= bkey_u64s(l->keys);
 
-	if (level && (!KEY_PTRS(k) || !KEY_SIZE(k) || KEY_DIRTY(k)))
-		goto bad;
+	memmove(l->keys,
+		bkey_next(l->keys),
+		bch_keylist_bytes(l));
+}
 
-	if (!level && KEY_SIZE(k) > KEY_OFFSET(k))
-		goto bad;
+/* Pointer validation */
 
-	if (!KEY_SIZE(k))
-		return true;
+static bool __ptr_invalid(struct cache_set *c, const struct bkey *k)
+{
+	unsigned i;
 
 	for (i = 0; i < KEY_PTRS(k); i++)
 		if (ptr_available(c, k, i)) {
@@ -98,13 +86,83 @@ bool __bch_ptr_invalid(struct cache_set *c, int level, const struct bkey *k)
 			if (KEY_SIZE(k) + r > c->sb.bucket_size ||
 			    bucket <  ca->sb.first_bucket ||
 			    bucket >= ca->sb.nbuckets)
-				goto bad;
+				return true;
 		}
 
+	return false;
+}
+
+bool bch_btree_ptr_invalid(struct cache_set *c, const struct bkey *k)
+{
+	char buf[80];
+
+	if (!KEY_PTRS(k) || !KEY_SIZE(k) || KEY_DIRTY(k))
+		goto bad;
+
+	if (__ptr_invalid(c, k))
+		goto bad;
+
+	return false;
+bad:
+	bch_bkey_to_text(buf, sizeof(buf), k);
+	cache_bug(c, "spotted btree ptr %s: %s", buf, bch_ptr_status(c, k));
+	return true;
+}
+
+bool bch_extent_ptr_invalid(struct cache_set *c, const struct bkey *k)
+{
+	char buf[80];
+
+	if (!KEY_SIZE(k))
+		return true;
+
+	if (KEY_SIZE(k) > KEY_OFFSET(k))
+		goto bad;
+
+	if (__ptr_invalid(c, k))
+		goto bad;
+
 	return false;
 bad:
 	bch_bkey_to_text(buf, sizeof(buf), k);
-	cache_bug(c, "spotted bad key %s: %s", buf, bch_ptr_status(c, k));
+	cache_bug(c, "spotted extent %s: %s", buf, bch_ptr_status(c, k));
+	return true;
+}
+
+static bool ptr_bad_expensive_checks(struct btree *b, const struct bkey *k,
+				     unsigned ptr)
+{
+	struct bucket *g = PTR_BUCKET(b->c, k, ptr);
+	char buf[80];
+
+	if (mutex_trylock(&b->c->bucket_lock)) {
+		if (b->level) {
+			if (KEY_DIRTY(k) ||
+			    g->prio != BTREE_PRIO ||
+			    (b->c->gc_mark_valid &&
+			     GC_MARK(g) != GC_MARK_METADATA))
+				goto err;
+
+		} else {
+			if (g->prio == BTREE_PRIO)
+				goto err;
+
+			if (KEY_DIRTY(k) &&
+			    b->c->gc_mark_valid &&
+			    GC_MARK(g) != GC_MARK_DIRTY)
+				goto err;
+		}
+		mutex_unlock(&b->c->bucket_lock);
+	}
+
+	return false;
+err:
+	mutex_unlock(&b->c->bucket_lock);
+	bch_bkey_to_text(buf, sizeof(buf), k);
+	btree_bug(b,
+"inconsistent pointer %s: bucket %zu pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i",
+		  buf, PTR_BUCKET_NR(b->c, k, ptr), atomic_read(&g->pin),
+		  g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen);
 	return true;
 }
 
@@ -118,64 +176,29 @@ bool bch_ptr_bad(struct btree *b, const struct bkey *k)
 	    bch_ptr_invalid(b, k))
 		return true;
 
-	if (KEY_PTRS(k) && PTR_DEV(k, 0) == PTR_CHECK_DEV)
-		return true;
+	for (i = 0; i < KEY_PTRS(k); i++) {
+		if (!ptr_available(b->c, k, i))
+			return true;
 
-	for (i = 0; i < KEY_PTRS(k); i++)
-		if (ptr_available(b->c, k, i)) {
-			g = PTR_BUCKET(b->c, k, i);
-			stale = ptr_stale(b->c, k, i);
+		g = PTR_BUCKET(b->c, k, i);
+		stale = ptr_stale(b->c, k, i);
 
-			btree_bug_on(stale > 96, b,
-				     "key too stale: %i, need_gc %u",
-				     stale, b->c->need_gc);
+		btree_bug_on(stale > 96, b,
+			     "key too stale: %i, need_gc %u",
+			     stale, b->c->need_gc);
 
-			btree_bug_on(stale && KEY_DIRTY(k) && KEY_SIZE(k),
-				     b, "stale dirty pointer");
+		btree_bug_on(stale && KEY_DIRTY(k) && KEY_SIZE(k),
+			     b, "stale dirty pointer");
 
-			if (stale)
-				return true;
+		if (stale)
+			return true;
 
-#ifdef CONFIG_BCACHE_EDEBUG
-			if (!mutex_trylock(&b->c->bucket_lock))
-				continue;
-
-			if (b->level) {
-				if (KEY_DIRTY(k) ||
-				    g->prio != BTREE_PRIO ||
-				    (b->c->gc_mark_valid &&
-				     GC_MARK(g) != GC_MARK_METADATA))
-					goto bug;
-
-			} else {
-				if (g->prio == BTREE_PRIO)
-					goto bug;
-
-				if (KEY_DIRTY(k) &&
-				    b->c->gc_mark_valid &&
-				    GC_MARK(g) != GC_MARK_DIRTY)
-					goto bug;
-			}
-			mutex_unlock(&b->c->bucket_lock);
-#endif
-		}
+		if (expensive_debug_checks(b->c) &&
+		    ptr_bad_expensive_checks(b, k, i))
+			return true;
+	}
 
 	return false;
-#ifdef CONFIG_BCACHE_EDEBUG
-bug:
-	mutex_unlock(&b->c->bucket_lock);
-
-	{
-		char buf[80];
-
-		bch_bkey_to_text(buf, sizeof(buf), k);
-		btree_bug(b,
-"inconsistent pointer %s: bucket %zu pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i",
-			  buf, PTR_BUCKET_NR(b->c, k, i), atomic_read(&g->pin),
-			  g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen);
-	}
-	return true;
-#endif
 }
 
 /* Key/pointer manipulation */
@@ -458,16 +481,8 @@ static struct bkey *table_to_bkey(struct bset_tree *t, unsigned cacheline)
 
 static inline uint64_t shrd128(uint64_t high, uint64_t low, uint8_t shift)
 {
-#ifdef CONFIG_X86_64
-	asm("shrd %[shift],%[high],%[low]"
-	    : [low] "+Rm" (low)
-	    : [high] "R" (high),
-	    [shift] "ci" (shift)
-	    : "cc");
-#else
 	low >>= shift;
 	low  |= (high << 1) << (63U - shift);
-#endif
 	return low;
 }
 
@@ -686,7 +701,7 @@ void bch_bset_init_next(struct btree *b)
 	} else
 		get_random_bytes(&i->seq, sizeof(uint64_t));
 
-	i->magic	= bset_magic(b->c);
+	i->magic	= bset_magic(&b->c->sb);
 	i->version	= 0;
 	i->keys		= 0;
 
@@ -824,16 +839,16 @@ struct bkey *__bch_bset_search(struct btree *b, struct bset_tree *t,
 	} else
 		i = bset_search_write_set(b, t, search);
 
-#ifdef CONFIG_BCACHE_EDEBUG
-	BUG_ON(bset_written(b, t) &&
-	       i.l != t->data->start &&
-	       bkey_cmp(tree_to_prev_bkey(t,
-		  inorder_to_tree(bkey_to_cacheline(t, i.l), t)),
-			search) > 0);
+	if (expensive_debug_checks(b->c)) {
+		BUG_ON(bset_written(b, t) &&
+		       i.l != t->data->start &&
+		       bkey_cmp(tree_to_prev_bkey(t,
+			  inorder_to_tree(bkey_to_cacheline(t, i.l), t)),
+				search) > 0);
 
-	BUG_ON(i.r != end(t->data) &&
-	       bkey_cmp(i.r, search) <= 0);
-#endif
+		BUG_ON(i.r != end(t->data) &&
+		       bkey_cmp(i.r, search) <= 0);
+	}
 
 	while (likely(i.l != i.r) &&
 	       bkey_cmp(i.l, search) <= 0)
@@ -844,6 +859,13 @@ struct bkey *__bch_bset_search(struct btree *b, struct bset_tree *t,
 
 /* Btree iterator */
 
+/*
+ * Returns true if l > r - unless l == r, in which case returns true if l is
+ * older than r.
+ *
+ * Necessary for btree_sort_fixup() - if there are multiple keys that compare
+ * equal in different sets, we have to process them newest to oldest.
+ */
 static inline bool btree_iter_cmp(struct btree_iter_set l,
 				  struct btree_iter_set r)
 {
@@ -867,12 +889,16 @@ void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 }
 
 struct bkey *__bch_btree_iter_init(struct btree *b, struct btree_iter *iter,
-			       struct bkey *search, struct bset_tree *start)
+				   struct bkey *search, struct bset_tree *start)
 {
 	struct bkey *ret = NULL;
 	iter->size = ARRAY_SIZE(iter->data);
 	iter->used = 0;
 
+#ifdef CONFIG_BCACHE_DEBUG
+	iter->b = b;
+#endif
+
 	for (; start <= &b->sets[b->nsets]; start++) {
 		ret = bch_bset_search(b, start, search);
 		bch_btree_iter_push(iter, ret, end(start->data));
@@ -887,6 +913,8 @@ struct bkey *bch_btree_iter_next(struct btree_iter *iter)
 	struct bkey *ret = NULL;
 
 	if (!btree_iter_end(iter)) {
+		bch_btree_iter_next_check(iter);
+
 		ret = iter->data->k;
 		iter->data->k = bkey_next(iter->data->k);
 
@@ -916,14 +944,6 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
 	return ret;
 }
 
-struct bkey *bch_next_recurse_key(struct btree *b, struct bkey *search)
-{
-	struct btree_iter iter;
-
-	bch_btree_iter_init(b, &iter, search);
-	return bch_btree_iter_next_filter(&iter, b, bch_ptr_bad);
-}
-
 /* Mergesort */
 
 static void sort_key_next(struct btree_iter *iter,
@@ -998,7 +1018,6 @@ static void btree_mergesort(struct btree *b, struct bset *out,
 	out->keys = last ? (uint64_t *) bkey_next(last) - out->d : 0;
 
 	pr_debug("sorted %i keys", out->keys);
-	bch_check_key_order(b, out);
 }
 
 static void __btree_sort(struct btree *b, struct btree_iter *iter,
@@ -1029,7 +1048,7 @@ static void __btree_sort(struct btree *b, struct btree_iter *iter,
 		 * memcpy()
 		 */
 
-		out->magic	= bset_magic(b->c);
+		out->magic	= bset_magic(&b->c->sb);
 		out->seq	= b->sets[0].data->seq;
 		out->version	= b->sets[0].data->version;
 		swap(out, b->sets[0].data);
@@ -1050,24 +1069,21 @@ static void __btree_sort(struct btree *b, struct btree_iter *iter,
 	if (b->written)
 		bset_build_written_tree(b);
 
-	if (!start) {
-		spin_lock(&b->c->sort_time_lock);
+	if (!start)
 		bch_time_stats_update(&b->c->sort_time, start_time);
-		spin_unlock(&b->c->sort_time_lock);
-	}
 }
 
 void bch_btree_sort_partial(struct btree *b, unsigned start)
 {
-	size_t oldsize = 0, order = b->page_order, keys = 0;
+	size_t order = b->page_order, keys = 0;
 	struct btree_iter iter;
+	int oldsize = bch_count_data(b);
+
 	__bch_btree_iter_init(b, &iter, NULL, &b->sets[start]);
 
 	BUG_ON(b->sets[b->nsets].data == write_block(b) &&
 	       (b->sets[b->nsets].size || b->nsets));
 
-	if (b->written)
-		oldsize = bch_count_data(b);
 
 	if (start) {
 		unsigned i;
@@ -1083,7 +1099,7 @@ void bch_btree_sort_partial(struct btree *b, unsigned start)
 
 	__btree_sort(b, &iter, start, order, false);
 
-	EBUG_ON(b->written && bch_count_data(b) != oldsize);
+	EBUG_ON(b->written && oldsize >= 0 && bch_count_data(b) != oldsize);
 }
 
 void bch_btree_sort_and_fix_extents(struct btree *b, struct btree_iter *iter)
@@ -1101,9 +1117,7 @@ void bch_btree_sort_into(struct btree *b, struct btree *new)
 
 	btree_mergesort(b, new->sets->data, &iter, false, true);
 
-	spin_lock(&b->c->sort_time_lock);
 	bch_time_stats_update(&b->c->sort_time, start_time);
-	spin_unlock(&b->c->sort_time_lock);
 
 	bkey_copy_key(&new->key, &b->key);
 	new->sets->size = 0;
@@ -1148,16 +1162,16 @@ void bch_btree_sort_lazy(struct btree *b)
 /* Sysfs stuff */
 
 struct bset_stats {
+	struct btree_op op;
 	size_t nodes;
 	size_t sets_written, sets_unwritten;
 	size_t bytes_written, bytes_unwritten;
 	size_t floats, failed;
 };
 
-static int bch_btree_bset_stats(struct btree *b, struct btree_op *op,
-			    struct bset_stats *stats)
+static int btree_bset_stats(struct btree_op *op, struct btree *b)
 {
-	struct bkey *k;
+	struct bset_stats *stats = container_of(op, struct bset_stats, op);
 	unsigned i;
 
 	stats->nodes++;
@@ -1182,30 +1196,19 @@ static int bch_btree_bset_stats(struct btree *b, struct btree_op *op,
 		}
 	}
 
-	if (b->level) {
-		struct btree_iter iter;
-
-		for_each_key_filter(b, k, &iter, bch_ptr_bad) {
-			int ret = btree(bset_stats, k, b, op, stats);
-			if (ret)
-				return ret;
-		}
-	}
-
-	return 0;
+	return MAP_CONTINUE;
 }
 
 int bch_bset_print_stats(struct cache_set *c, char *buf)
 {
-	struct btree_op op;
 	struct bset_stats t;
 	int ret;
 
-	bch_btree_op_init_stack(&op);
 	memset(&t, 0, sizeof(struct bset_stats));
+	bch_btree_op_init(&t.op, -1);
 
-	ret = btree_root(bset_stats, c, &op, &t);
-	if (ret)
+	ret = bch_btree_map_nodes(&t.op, c, &ZERO_KEY, btree_bset_stats);
+	if (ret < 0)
 		return ret;
 
 	return snprintf(buf, PAGE_SIZE,

drivers/md/bcache/bset.h

@@ -148,6 +148,9 @@
 
 struct btree_iter {
 	size_t size, used;
+#ifdef CONFIG_BCACHE_DEBUG
+	struct btree *b;
+#endif
 	struct btree_iter_set {
 		struct bkey *k, *end;
 	} data[MAX_BSETS];
@@ -193,54 +196,26 @@ static __always_inline int64_t bkey_cmp(const struct bkey *l,
 		: (int64_t) KEY_OFFSET(l) - (int64_t) KEY_OFFSET(r);
 }
 
-static inline size_t bkey_u64s(const struct bkey *k)
-{
-	BUG_ON(KEY_CSUM(k) > 1);
-	return 2 + KEY_PTRS(k) + (KEY_CSUM(k) ? 1 : 0);
-}
-
-static inline size_t bkey_bytes(const struct bkey *k)
-{
-	return bkey_u64s(k) * sizeof(uint64_t);
-}
-
-static inline void bkey_copy(struct bkey *dest, const struct bkey *src)
-{
-	memcpy(dest, src, bkey_bytes(src));
-}
-
-static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src)
-{
-	if (!src)
-		src = &KEY(0, 0, 0);
-
-	SET_KEY_INODE(dest, KEY_INODE(src));
-	SET_KEY_OFFSET(dest, KEY_OFFSET(src));
-}
-
-static inline struct bkey *bkey_next(const struct bkey *k)
-{
-	uint64_t *d = (void *) k;
-	return (struct bkey *) (d + bkey_u64s(k));
-}
-
 /* Keylists */
 
 struct keylist {
-	struct bkey		*top;
 	union {
-		uint64_t		*list;
-		struct bkey		*bottom;
+		struct bkey		*keys;
+		uint64_t		*keys_p;
+	};
+	union {
+		struct bkey		*top;
+		uint64_t		*top_p;
 	};
 
 	/* Enough room for btree_split's keys without realloc */
 #define KEYLIST_INLINE		16
-	uint64_t		d[KEYLIST_INLINE];
+	uint64_t		inline_keys[KEYLIST_INLINE];
 };
 
 static inline void bch_keylist_init(struct keylist *l)
 {
-	l->top = (void *) (l->list = l->d);
+	l->top_p = l->keys_p = l->inline_keys;
 }
 
 static inline void bch_keylist_push(struct keylist *l)
@@ -256,17 +231,32 @@ static inline void bch_keylist_add(struct keylist *l, struct bkey *k)
 
 static inline bool bch_keylist_empty(struct keylist *l)
 {
-	return l->top == (void *) l->list;
+	return l->top == l->keys;
+}
+
+static inline void bch_keylist_reset(struct keylist *l)
+{
+	l->top = l->keys;
 }
 
 static inline void bch_keylist_free(struct keylist *l)
 {
-	if (l->list != l->d)
-		kfree(l->list);
+	if (l->keys_p != l->inline_keys)
+		kfree(l->keys_p);
+}
+
+static inline size_t bch_keylist_nkeys(struct keylist *l)
+{
+	return l->top_p - l->keys_p;
+}
+
+static inline size_t bch_keylist_bytes(struct keylist *l)
+{
+	return bch_keylist_nkeys(l) * sizeof(uint64_t);
 }
 
-void bch_keylist_copy(struct keylist *, struct keylist *);
 struct bkey *bch_keylist_pop(struct keylist *);
+void bch_keylist_pop_front(struct keylist *);
 int bch_keylist_realloc(struct keylist *, int, struct cache_set *);
 
 void bch_bkey_copy_single_ptr(struct bkey *, const struct bkey *,
@@ -287,7 +277,9 @@ static inline bool bch_cut_back(const struct bkey *where, struct bkey *k)
 }
 
 const char *bch_ptr_status(struct cache_set *, const struct bkey *);
-bool __bch_ptr_invalid(struct cache_set *, int level, const struct bkey *);
+bool bch_btree_ptr_invalid(struct cache_set *, const struct bkey *);
+bool bch_extent_ptr_invalid(struct cache_set *, const struct bkey *);
+
 bool bch_ptr_bad(struct btree *, const struct bkey *);
 
 static inline uint8_t gen_after(uint8_t a, uint8_t b)
@@ -311,7 +303,6 @@ static inline bool ptr_available(struct cache_set *c, const struct bkey *k,
 
 typedef bool (*ptr_filter_fn)(struct btree *, const struct bkey *);
 
-struct bkey *bch_next_recurse_key(struct btree *, struct bkey *);
 struct bkey *bch_btree_iter_next(struct btree_iter *);
 struct bkey *bch_btree_iter_next_filter(struct btree_iter *,
 					struct btree *, ptr_filter_fn);
@@ -361,12 +352,30 @@ void bch_bset_fix_lookup_table(struct btree *, struct bkey *);
 struct bkey *__bch_bset_search(struct btree *, struct bset_tree *,
 			   const struct bkey *);
 
+/*
+ * Returns the first key that is strictly greater than search
+ */
 static inline struct bkey *bch_bset_search(struct btree *b, struct bset_tree *t,
 					   const struct bkey *search)
 {
 	return search ? __bch_bset_search(b, t, search) : t->data->start;
 }
 
+#define PRECEDING_KEY(_k)					\
+({								\
+	struct bkey *_ret = NULL;				\
+								\
+	if (KEY_INODE(_k) || KEY_OFFSET(_k)) {			\
+		_ret = &KEY(KEY_INODE(_k), KEY_OFFSET(_k), 0);	\
+								\
+		if (!_ret->low)					\
+			_ret->high--;				\
+		_ret->low--;					\
+	}							\
+								\
+	_ret;							\
+})
+
 bool bch_bkey_try_merge(struct btree *, struct bkey *, struct bkey *);
 void bch_btree_sort_lazy(struct btree *);
 void bch_btree_sort_into(struct btree *, struct btree *);

drivers/md/bcache/btree.h

@@ -125,6 +125,7 @@ struct btree {
 	unsigned long		seq;
 	struct rw_semaphore	lock;
 	struct cache_set	*c;
+	struct btree		*parent;
 
 	unsigned long		flags;
 	uint16_t		written;	/* would be nice to kill */
@@ -200,12 +201,7 @@ static inline bool bkey_written(struct btree *b, struct bkey *k)
 
 static inline void set_gc_sectors(struct cache_set *c)
 {
-	atomic_set(&c->sectors_to_gc, c->sb.bucket_size * c->nbuckets / 8);
-}
-
-static inline bool bch_ptr_invalid(struct btree *b, const struct bkey *k)
-{
-	return __bch_ptr_invalid(b->c, b->level, k);
+	atomic_set(&c->sectors_to_gc, c->sb.bucket_size * c->nbuckets / 16);
 }
 
 static inline struct bkey *bch_btree_iter_init(struct btree *b,
@@ -215,6 +211,16 @@ static inline struct bkey *bch_btree_iter_init(struct btree *b,
 	return __bch_btree_iter_init(b, iter, search, b->sets);
 }
 
+static inline bool bch_ptr_invalid(struct btree *b, const struct bkey *k)
+{
+	if (b->level)
+		return bch_btree_ptr_invalid(b->c, k);
+	else
+		return bch_extent_ptr_invalid(b->c, k);
+}
+
+void bkey_put(struct cache_set *c, struct bkey *k);
+
 /* Looping macros */
 
 #define for_each_cached_btree(b, c, iter)				\
@@ -234,51 +240,17 @@ static inline struct bkey *bch_btree_iter_init(struct btree *b,
 /* Recursing down the btree */
 
 struct btree_op {
-	struct closure		cl;
-	struct cache_set	*c;
-
-	/* Journal entry we have a refcount on */
-	atomic_t		*journal;
-
-	/* Bio to be inserted into the cache */
-	struct bio		*cache_bio;
-
-	unsigned		inode;
-
-	uint16_t		write_prio;
-
 	/* Btree level at which we start taking write locks */
 	short			lock;
 
-	/* Btree insertion type */
-	enum {
-		BTREE_INSERT,
-		BTREE_REPLACE
-	} type:8;
-
-	unsigned		csum:1;
-	unsigned		skip:1;
-	unsigned		flush_journal:1;
-
-	unsigned		insert_data_done:1;
-	unsigned		lookup_done:1;
 	unsigned		insert_collision:1;
-
-	/* Anything after this point won't get zeroed in do_bio_hook() */
-
-	/* Keys to be inserted */
-	struct keylist		keys;
-	BKEY_PADDED(replace);
 };
 
-enum {
-	BTREE_INSERT_STATUS_INSERT,
-	BTREE_INSERT_STATUS_BACK_MERGE,
-	BTREE_INSERT_STATUS_OVERWROTE,
-	BTREE_INSERT_STATUS_FRONT_MERGE,
-};
-
-void bch_btree_op_init_stack(struct btree_op *);
+static inline void bch_btree_op_init(struct btree_op *op, int write_lock_level)
+{
+	memset(op, 0, sizeof(struct btree_op));
+	op->lock = write_lock_level;
+}
 
 static inline void rw_lock(bool w, struct btree *b, int level)
 {
@@ -290,108 +262,71 @@ static inline void rw_lock(bool w, struct btree *b, int level)
 
 static inline void rw_unlock(bool w, struct btree *b)
 {
-#ifdef CONFIG_BCACHE_EDEBUG
-	unsigned i;
-
-	if (w && b->key.ptr[0])
-		for (i = 0; i <= b->nsets; i++)
-			bch_check_key_order(b, b->sets[i].data);
-#endif
-
 	if (w)
 		b->seq++;
 	(w ? up_write : up_read)(&b->lock);
 }
 
-#define insert_lock(s, b)	((b)->level <= (s)->lock)
+void bch_btree_node_read(struct btree *);
+void bch_btree_node_write(struct btree *, struct closure *);
 
-/*
- * These macros are for recursing down the btree - they handle the details of
- * locking and looking up nodes in the cache for you. They're best treated as
- * mere syntax when reading code that uses them.
- *
- * op->lock determines whether we take a read or a write lock at a given depth.
- * If you've got a read lock and find that you need a write lock (i.e. you're
- * going to have to split), set op->lock and return -EINTR; btree_root() will
- * call you again and you'll have the correct lock.
- */
+void bch_btree_set_root(struct btree *);
+struct btree *bch_btree_node_alloc(struct cache_set *, int, bool);
+struct btree *bch_btree_node_get(struct cache_set *, struct bkey *, int, bool);
 
-/**
- * btree - recurse down the btree on a specified key
- * @fn:		function to call, which will be passed the child node
- * @key:	key to recurse on
- * @b:		parent btree node
- * @op:		pointer to struct btree_op
- */
-#define btree(fn, key, b, op, ...)					\
-({									\
-	int _r, l = (b)->level - 1;					\
-	bool _w = l <= (op)->lock;					\
-	struct btree *_b = bch_btree_node_get((b)->c, key, l, op);	\
-	if (!IS_ERR(_b)) {						\
-		_r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__);		\
-		rw_unlock(_w, _b);					\
-	} else								\
-		_r = PTR_ERR(_b);					\
-	_r;								\
-})
-
-/**
- * btree_root - call a function on the root of the btree
- * @fn:		function to call, which will be passed the child node
- * @c:		cache set
- * @op:		pointer to struct btree_op
- */
-#define btree_root(fn, c, op, ...)					\
-({									\
-	int _r = -EINTR;						\
-	do {								\
-		struct btree *_b = (c)->root;				\
-		bool _w = insert_lock(op, _b);				\
-		rw_lock(_w, _b, _b->level);				\
-		if (_b == (c)->root &&					\
-		    _w == insert_lock(op, _b))				\
-			_r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__);	\
-		rw_unlock(_w, _b);					\
-		bch_cannibalize_unlock(c, &(op)->cl);		\
-	} while (_r == -EINTR);						\
-									\
-	_r;								\
-})
+int bch_btree_insert_check_key(struct btree *, struct btree_op *,
+			       struct bkey *);
+int bch_btree_insert(struct cache_set *, struct keylist *,
+		     atomic_t *, struct bkey *);
+
+int bch_gc_thread_start(struct cache_set *);
+size_t bch_btree_gc_finish(struct cache_set *);
+void bch_moving_gc(struct cache_set *);
+int bch_btree_check(struct cache_set *);
+uint8_t __bch_btree_mark_key(struct cache_set *, int, struct bkey *);
 
-static inline bool should_split(struct btree *b)
+static inline void wake_up_gc(struct cache_set *c)
 {
-	struct bset *i = write_block(b);
-	return b->written >= btree_blocks(b) ||
-		(i->seq == b->sets[0].data->seq &&
-		 b->written + __set_blocks(i, i->keys + 15, b->c)
-		 > btree_blocks(b));
+	if (c->gc_thread)
+		wake_up_process(c->gc_thread);
 }
 
-void bch_btree_node_read(struct btree *);
-void bch_btree_node_write(struct btree *, struct closure *);
+#define MAP_DONE	0
+#define MAP_CONTINUE	1
 
-void bch_cannibalize_unlock(struct cache_set *, struct closure *);
-void bch_btree_set_root(struct btree *);
-struct btree *bch_btree_node_alloc(struct cache_set *, int, struct closure *);
-struct btree *bch_btree_node_get(struct cache_set *, struct bkey *,
-				int, struct btree_op *);
+#define MAP_ALL_NODES	0
+#define MAP_LEAF_NODES	1
 
-bool bch_btree_insert_check_key(struct btree *, struct btree_op *,
-				   struct bio *);
-int bch_btree_insert(struct btree_op *, struct cache_set *);
+#define MAP_END_KEY	1
 
-int bch_btree_search_recurse(struct btree *, struct btree_op *);
+typedef int (btree_map_nodes_fn)(struct btree_op *, struct btree *);
+int __bch_btree_map_nodes(struct btree_op *, struct cache_set *,
+			  struct bkey *, btree_map_nodes_fn *, int);
 
-void bch_queue_gc(struct cache_set *);
-size_t bch_btree_gc_finish(struct cache_set *);
-void bch_moving_gc(struct closure *);
-int bch_btree_check(struct cache_set *, struct btree_op *);
-uint8_t __bch_btree_mark_key(struct cache_set *, int, struct bkey *);
+static inline int bch_btree_map_nodes(struct btree_op *op, struct cache_set *c,
+				      struct bkey *from, btree_map_nodes_fn *fn)
+{
+	return __bch_btree_map_nodes(op, c, from, fn, MAP_ALL_NODES);
+}
+
+static inline int bch_btree_map_leaf_nodes(struct btree_op *op,
+					   struct cache_set *c,
+					   struct bkey *from,
+					   btree_map_nodes_fn *fn)
+{
+	return __bch_btree_map_nodes(op, c, from, fn, MAP_LEAF_NODES);
+}
+
+typedef int (btree_map_keys_fn)(struct btree_op *, struct btree *,
+				struct bkey *);
+int bch_btree_map_keys(struct btree_op *, struct cache_set *,
+		       struct bkey *, btree_map_keys_fn *, int);
+
+typedef bool (keybuf_pred_fn)(struct keybuf *, struct bkey *);
 
 void bch_keybuf_init(struct keybuf *);
-void bch_refill_keybuf(struct cache_set *, struct keybuf *, struct bkey *,
-		       keybuf_pred_fn *);
+void bch_refill_keybuf(struct cache_set *, struct keybuf *,
+		       struct bkey *, keybuf_pred_fn *);
 bool bch_keybuf_check_overlapping(struct keybuf *, struct bkey *,
 				  struct bkey *);
 void bch_keybuf_del(struct keybuf *, struct keybuf_key *);

drivers/md/bcache/closure.c

@@ -11,17 +11,6 @@
 
 #include "closure.h"
 
-void closure_queue(struct closure *cl)
-{
-	struct workqueue_struct *wq = cl->wq;
-	if (wq) {
-		INIT_WORK(&cl->work, cl->work.func);
-		BUG_ON(!queue_work(wq, &cl->work));
-	} else
-		cl->fn(cl);
-}
-EXPORT_SYMBOL_GPL(closure_queue);
-
 #define CL_FIELD(type, field)					\
 	case TYPE_ ## type:					\
 	return &container_of(cl, struct type, cl)->field
@@ -30,17 +19,6 @@ static struct closure_waitlist *closure_waitlist(struct closure *cl)
 {
 	switch (cl->type) {
 		CL_FIELD(closure_with_waitlist, wait);
-		CL_FIELD(closure_with_waitlist_and_timer, wait);
-	default:
-		return NULL;
-	}
-}
-
-static struct timer_list *closure_timer(struct closure *cl)
-{
-	switch (cl->type) {
-		CL_FIELD(closure_with_timer, timer);
-		CL_FIELD(closure_with_waitlist_and_timer, timer);
 	default:
 		return NULL;
 	}
@@ -51,7 +29,7 @@ static inline void closure_put_after_sub(struct closure *cl, int flags)
 	int r = flags & CLOSURE_REMAINING_MASK;
 
 	BUG_ON(flags & CLOSURE_GUARD_MASK);
-	BUG_ON(!r && (flags & ~(CLOSURE_DESTRUCTOR|CLOSURE_BLOCKING)));
+	BUG_ON(!r && (flags & ~CLOSURE_DESTRUCTOR));
 
 	/* Must deliver precisely one wakeup */
 	if (r == 1 && (flags & CLOSURE_SLEEPING))
@@ -59,7 +37,6 @@ static inline void closure_put_after_sub(struct closure *cl, int flags)
 
 	if (!r) {
 		if (cl->fn && !(flags & CLOSURE_DESTRUCTOR)) {
-			/* CLOSURE_BLOCKING might be set - clear it */
 			atomic_set(&cl->remaining,
 				   CLOSURE_REMAINING_INITIALIZER);
 			closure_queue(cl);
@@ -90,13 +67,13 @@ void closure_sub(struct closure *cl, int v)
 {
 	closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining));
 }
-EXPORT_SYMBOL_GPL(closure_sub);
+EXPORT_SYMBOL(closure_sub);
 
 void closure_put(struct closure *cl)
 {
 	closure_put_after_sub(cl, atomic_dec_return(&cl->remaining));
 }
-EXPORT_SYMBOL_GPL(closure_put);
+EXPORT_SYMBOL(closure_put);
 
 static void set_waiting(struct closure *cl, unsigned long f)
 {
@@ -133,7 +110,7 @@ void __closure_wake_up(struct closure_waitlist *wait_list)
 		closure_sub(cl, CLOSURE_WAITING + 1);
 	}
 }
-EXPORT_SYMBOL_GPL(__closure_wake_up);
+EXPORT_SYMBOL(__closure_wake_up);
 
 bool closure_wait(struct closure_waitlist *list, struct closure *cl)
 {
@@ -146,7 +123,7 @@ bool closure_wait(struct closure_waitlist *list, struct closure *cl)
 
 	return true;
 }
-EXPORT_SYMBOL_GPL(closure_wait);
+EXPORT_SYMBOL(closure_wait);
 
 /**
  * closure_sync() - sleep until a closure a closure has nothing left to wait on
@@ -169,7 +146,7 @@ void closure_sync(struct closure *cl)
 
 	__closure_end_sleep(cl);
 }
-EXPORT_SYMBOL_GPL(closure_sync);
+EXPORT_SYMBOL(closure_sync);
 
 /**
  * closure_trylock() - try to acquire the closure, without waiting
@@ -183,17 +160,17 @@ bool closure_trylock(struct closure *cl, struct closure *parent)
 			   CLOSURE_REMAINING_INITIALIZER) != -1)
 		return false;
 
-	closure_set_ret_ip(cl);
-
 	smp_mb();
+
 	cl->parent = parent;
 	if (parent)
 		closure_get(parent);
 
+	closure_set_ret_ip(cl);
 	closure_debug_create(cl);
 	return true;
 }
-EXPORT_SYMBOL_GPL(closure_trylock);
+EXPORT_SYMBOL(closure_trylock);
 
 void __closure_lock(struct closure *cl, struct closure *parent,
 		    struct closure_waitlist *wait_list)
@@ -205,57 +182,11 @@ void __closure_lock(struct closure *cl, struct closure *parent,
 		if (closure_trylock(cl, parent))
 			return;
 
-		closure_wait_event_sync(wait_list, &wait,
-					atomic_read(&cl->remaining) == -1);
+		closure_wait_event(wait_list, &wait,
+				   atomic_read(&cl->remaining) == -1);
 	}
 }
-EXPORT_SYMBOL_GPL(__closure_lock);
-
-static void closure_delay_timer_fn(unsigned long data)
-{
-	struct closure *cl = (struct closure *) data;
-	closure_sub(cl, CLOSURE_TIMER + 1);
-}
-
-void do_closure_timer_init(struct closure *cl)
-{
-	struct timer_list *timer = closure_timer(cl);
-
-	init_timer(timer);
-	timer->data	= (unsigned long) cl;
-	timer->function = closure_delay_timer_fn;
-}
-EXPORT_SYMBOL_GPL(do_closure_timer_init);
-
-bool __closure_delay(struct closure *cl, unsigned long delay,
-		     struct timer_list *timer)
-{
-	if (atomic_read(&cl->remaining) & CLOSURE_TIMER)
-		return false;
-
-	BUG_ON(timer_pending(timer));
-
-	timer->expires	= jiffies + delay;
-
-	atomic_add(CLOSURE_TIMER + 1, &cl->remaining);
-	add_timer(timer);
-	return true;
-}
-EXPORT_SYMBOL_GPL(__closure_delay);
-
-void __closure_flush(struct closure *cl, struct timer_list *timer)
-{
-	if (del_timer(timer))
-		closure_sub(cl, CLOSURE_TIMER + 1);
-}
-EXPORT_SYMBOL_GPL(__closure_flush);
-
-void __closure_flush_sync(struct closure *cl, struct timer_list *timer)
-{
-	if (del_timer_sync(timer))
-		closure_sub(cl, CLOSURE_TIMER + 1);
-}
-EXPORT_SYMBOL_GPL(__closure_flush_sync);
+EXPORT_SYMBOL(__closure_lock);
 
 #ifdef CONFIG_BCACHE_CLOSURES_DEBUG
 
@@ -273,7 +204,7 @@ void closure_debug_create(struct closure *cl)
 	list_add(&cl->all, &closure_list);
 	spin_unlock_irqrestore(&closure_list_lock, flags);
 }
-EXPORT_SYMBOL_GPL(closure_debug_create);
+EXPORT_SYMBOL(closure_debug_create);
 
 void closure_debug_destroy(struct closure *cl)
 {
@@ -286,7 +217,7 @@ void closure_debug_destroy(struct closure *cl)
 	list_del(&cl->all);
 	spin_unlock_irqrestore(&closure_list_lock, flags);
 }
-EXPORT_SYMBOL_GPL(closure_debug_destroy);
+EXPORT_SYMBOL(closure_debug_destroy);
 
 static struct dentry *debug;
 
@@ -304,14 +235,12 @@ static int debug_seq_show(struct seq_file *f, void *data)
 			   cl, (void *) cl->ip, cl->fn, cl->parent,
 			   r & CLOSURE_REMAINING_MASK);
 
-		seq_printf(f, "%s%s%s%s%s%s\n",
+		seq_printf(f, "%s%s%s%s\n",
 			   test_bit(WORK_STRUCT_PENDING,
 				    work_data_bits(&cl->work)) ? "Q" : "",
 			   r & CLOSURE_RUNNING	? "R" : "",
-			   r & CLOSURE_BLOCKING	? "B" : "",
 			   r & CLOSURE_STACK	? "S" : "",
-			   r & CLOSURE_SLEEPING	? "Sl" : "",
-			   r & CLOSURE_TIMER	? "T" : "");
+			   r & CLOSURE_SLEEPING	? "Sl" : "");
 
 		if (r & CLOSURE_WAITING)
 			seq_printf(f, " W %pF\n",

drivers/md/bcache/closure.h

@@ -155,21 +155,6 @@
  * delayed_work embeds a work item and a timer_list. The important thing is, use
  * it exactly like you would a regular closure and closure_put() will magically
  * handle everything for you.
- *
- * We've got closures that embed timers, too. They're called, appropriately
- * enough:
- * struct closure_with_timer;
- *
- * This gives you access to closure_delay(). It takes a refcount for a specified
- * number of jiffies - you could then call closure_sync() (for a slightly
- * convoluted version of msleep()) or continue_at() - which gives you the same
- * effect as using a delayed work item, except you can reuse the work_struct
- * already embedded in struct closure.
- *
- * Lastly, there's struct closure_with_waitlist_and_timer. It does what you
- * probably expect, if you happen to need the features of both. (You don't
- * really want to know how all this is implemented, but if I've done my job
- * right you shouldn't have to care).
  */
 
 struct closure;
@@ -182,16 +167,11 @@ struct closure_waitlist {
 enum closure_type {
 	TYPE_closure				= 0,
 	TYPE_closure_with_waitlist		= 1,
-	TYPE_closure_with_timer			= 2,
-	TYPE_closure_with_waitlist_and_timer	= 3,
-	MAX_CLOSURE_TYPE			= 3,
+	MAX_CLOSURE_TYPE			= 1,
 };
 
 enum closure_state {
 	/*
-	 * CLOSURE_BLOCKING: Causes closure_wait_event() to block, instead of
-	 * waiting asynchronously
-	 *
 	 * CLOSURE_WAITING: Set iff the closure is on a waitlist. Must be set by
 	 * the thread that owns the closure, and cleared by the thread that's
 	 * waking up the closure.
@@ -200,10 +180,6 @@ enum closure_state {
 	 * - indicates that cl->task is valid and closure_put() may wake it up.
 	 * Only set or cleared by the thread that owns the closure.
 	 *
-	 * CLOSURE_TIMER: Analagous to CLOSURE_WAITING, indicates that a closure
-	 * has an outstanding timer. Must be set by the thread that owns the
-	 * closure, and cleared by the timer function when the timer goes off.
-	 *
 	 * The rest are for debugging and don't affect behaviour:
 	 *
 	 * CLOSURE_RUNNING: Set when a closure is running (i.e. by
@@ -218,19 +194,17 @@ enum closure_state {
 	 * closure with this flag set
 	 */
 
-	CLOSURE_BITS_START	= (1 << 19),
-	CLOSURE_DESTRUCTOR	= (1 << 19),
-	CLOSURE_BLOCKING	= (1 << 21),
-	CLOSURE_WAITING		= (1 << 23),
-	CLOSURE_SLEEPING	= (1 << 25),
-	CLOSURE_TIMER		= (1 << 27),
+	CLOSURE_BITS_START	= (1 << 23),
+	CLOSURE_DESTRUCTOR	= (1 << 23),
+	CLOSURE_WAITING		= (1 << 25),
+	CLOSURE_SLEEPING	= (1 << 27),
 	CLOSURE_RUNNING		= (1 << 29),
 	CLOSURE_STACK		= (1 << 31),
 };
 
 #define CLOSURE_GUARD_MASK					\
-	((CLOSURE_DESTRUCTOR|CLOSURE_BLOCKING|CLOSURE_WAITING|	\
-	  CLOSURE_SLEEPING|CLOSURE_TIMER|CLOSURE_RUNNING|CLOSURE_STACK) << 1)
+	((CLOSURE_DESTRUCTOR|CLOSURE_WAITING|CLOSURE_SLEEPING|	\
+	  CLOSURE_RUNNING|CLOSURE_STACK) << 1)
 
 #define CLOSURE_REMAINING_MASK		(CLOSURE_BITS_START - 1)
 #define CLOSURE_REMAINING_INITIALIZER	(1|CLOSURE_RUNNING)
@@ -268,17 +242,6 @@ struct closure_with_waitlist {
 	struct closure_waitlist	wait;
 };
 
-struct closure_with_timer {
-	struct closure		cl;
-	struct timer_list	timer;
-};
-
-struct closure_with_waitlist_and_timer {
-	struct closure		cl;
-	struct closure_waitlist	wait;
-	struct timer_list	timer;
-};
-
 extern unsigned invalid_closure_type(void);
 
 #define __CLOSURE_TYPE(cl, _t)						\
@@ -289,14 +252,11 @@ extern unsigned invalid_closure_type(void);
 (									\
 	__CLOSURE_TYPE(cl, closure)					\
 	__CLOSURE_TYPE(cl, closure_with_waitlist)			\
-	__CLOSURE_TYPE(cl, closure_with_timer)				\
-	__CLOSURE_TYPE(cl, closure_with_waitlist_and_timer)		\
 	invalid_closure_type()						\
 )
 
 void closure_sub(struct closure *cl, int v);
 void closure_put(struct closure *cl);
-void closure_queue(struct closure *cl);
 void __closure_wake_up(struct closure_waitlist *list);
 bool closure_wait(struct closure_waitlist *list, struct closure *cl);
 void closure_sync(struct closure *cl);
@@ -305,12 +265,6 @@ bool closure_trylock(struct closure *cl, struct closure *parent);
 void __closure_lock(struct closure *cl, struct closure *parent,
 		    struct closure_waitlist *wait_list);
 
-void do_closure_timer_init(struct closure *cl);
-bool __closure_delay(struct closure *cl, unsigned long delay,
-		     struct timer_list *timer);
-void __closure_flush(struct closure *cl, struct timer_list *timer);
-void __closure_flush_sync(struct closure *cl, struct timer_list *timer);
-
 #ifdef CONFIG_BCACHE_CLOSURES_DEBUG
 
 void closure_debug_init(void);
@@ -354,11 +308,6 @@ static inline void closure_set_stopped(struct closure *cl)
 	atomic_sub(CLOSURE_RUNNING, &cl->remaining);
 }
 
-static inline bool closure_is_stopped(struct closure *cl)
-{
-	return !(atomic_read(&cl->remaining) & CLOSURE_RUNNING);
-}
-
 static inline bool closure_is_unlocked(struct closure *cl)
 {
 	return atomic_read(&cl->remaining) == -1;
@@ -367,14 +316,6 @@ static inline bool closure_is_unlocked(struct closure *cl)
 static inline void do_closure_init(struct closure *cl, struct closure *parent,
 				   bool running)
 {
-	switch (cl->type) {
-	case TYPE_closure_with_timer:
-	case TYPE_closure_with_waitlist_and_timer:
-		do_closure_timer_init(cl);
-	default:
-		break;
-	}
-
 	cl->parent = parent;
 	if (parent)
 		closure_get(parent);
@@ -429,8 +370,7 @@ do {								\
 static inline void closure_init_stack(struct closure *cl)
 {
 	memset(cl, 0, sizeof(struct closure));
-	atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER|
-		   CLOSURE_BLOCKING|CLOSURE_STACK);
+	atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER|CLOSURE_STACK);
 }
 
 /**
@@ -461,24 +401,6 @@ do {								\
 #define closure_lock(cl, parent)				\
 	__closure_lock(__to_internal_closure(cl), parent, &(cl)->wait)
 
-/**
- * closure_delay() - delay some number of jiffies
- * @cl:		the closure that will sleep
- * @delay:	the delay in jiffies
- *
- * Takes a refcount on @cl which will be released after @delay jiffies; this may
- * be used to have a function run after a delay with continue_at(), or
- * closure_sync() may be used for a convoluted version of msleep().
- */
-#define closure_delay(cl, delay)			\
-	__closure_delay(__to_internal_closure(cl), delay, &(cl)->timer)
-
-#define closure_flush(cl)				\
-	__closure_flush(__to_internal_closure(cl), &(cl)->timer)
-
-#define closure_flush_sync(cl)				\
-	__closure_flush_sync(__to_internal_closure(cl), &(cl)->timer)
-
 static inline void __closure_end_sleep(struct closure *cl)
 {
 	__set_current_state(TASK_RUNNING);
@@ -497,40 +419,6 @@ static inline void __closure_start_sleep(struct closure *cl)
 		atomic_add(CLOSURE_SLEEPING, &cl->remaining);
 }
 
-/**
- * closure_blocking() - returns true if the closure is in blocking mode.
- *
- * If a closure is in blocking mode, closure_wait_event() will sleep until the
- * condition is true instead of waiting asynchronously.
- */
-static inline bool closure_blocking(struct closure *cl)
-{
-	return atomic_read(&cl->remaining) & CLOSURE_BLOCKING;
-}
-
-/**
- * set_closure_blocking() - put a closure in blocking mode.
- *
- * If a closure is in blocking mode, closure_wait_event() will sleep until the
- * condition is true instead of waiting asynchronously.
- *
- * Not thread safe - can only be called by the thread running the closure.
- */
-static inline void set_closure_blocking(struct closure *cl)
-{
-	if (!closure_blocking(cl))
-		atomic_add(CLOSURE_BLOCKING, &cl->remaining);
-}
-
-/*
- * Not thread safe - can only be called by the thread running the closure.
- */
-static inline void clear_closure_blocking(struct closure *cl)
-{
-	if (closure_blocking(cl))
-		atomic_sub(CLOSURE_BLOCKING, &cl->remaining);
-}
-
 /**
  * closure_wake_up() - wake up all closures on a wait list.
  */
@@ -561,63 +449,36 @@ static inline void closure_wake_up(struct closure_waitlist *list)
  * refcount on our closure. If this was a stack allocated closure, that would be
  * bad.
  */
-#define __closure_wait_event(list, cl, condition, _block)		\
+#define closure_wait_event(list, cl, condition)				\
 ({									\
-	bool block = _block;						\
 	typeof(condition) ret;						\
 									\
 	while (1) {							\
 		ret = (condition);					\
 		if (ret) {						\
 			__closure_wake_up(list);			\
-			if (block)					\
-				closure_sync(cl);			\
-									\
+			closure_sync(cl);				\
 			break;						\
 		}							\
 									\
-		if (block)						\
-			__closure_start_sleep(cl);			\
-									\
-		if (!closure_wait(list, cl)) {				\
-			if (!block)					\
-				break;					\
+		__closure_start_sleep(cl);				\
 									\
+		if (!closure_wait(list, cl))				\
 			schedule();					\
-		}							\
 	}								\
 									\
 	ret;								\
 })
 
-/**
- * closure_wait_event() - wait on a condition, synchronously or asynchronously.
- * @list:	the wait list to wait on
- * @cl:		the closure that is doing the waiting
- * @condition:	a C expression for the event to wait for
- *
- * If the closure is in blocking mode, sleeps until the @condition evaluates to
- * true - exactly like wait_event().
- *
- * If the closure is not in blocking mode, waits asynchronously; if the
- * condition is currently false the @cl is put onto @list and returns. @list
- * owns a refcount on @cl; closure_sync() or continue_at() may be used later to
- * wait for another thread to wake up @list, which drops the refcount on @cl.
- *
- * Returns the value of @condition; @cl will be on @list iff @condition was
- * false.
- *
- * closure_wake_up(@list) must be called after changing any variable that could
- * cause @condition to become true.
- */
-#define closure_wait_event(list, cl, condition)				\
-	__closure_wait_event(list, cl, condition, closure_blocking(cl))
-
-#define closure_wait_event_async(list, cl, condition)			\
-	__closure_wait_event(list, cl, condition, false)
-
-#define closure_wait_event_sync(list, cl, condition)			\
-	__closure_wait_event(list, cl, condition, true)
+static inline void closure_queue(struct closure *cl)
+{
+	struct workqueue_struct *wq = cl->wq;
+	if (wq) {
+		INIT_WORK(&cl->work, cl->work.func);
+		BUG_ON(!queue_work(wq, &cl->work));
+	} else
+		cl->fn(cl);
+}
 
 static inline void set_closure_fn(struct closure *cl, closure_fn *fn,
 				  struct workqueue_struct *wq)
@@ -642,7 +503,7 @@ do {									\
 #define continue_at_nobarrier(_cl, _fn, _wq)				\
 do {									\
 	set_closure_fn(_cl, _fn, _wq);					\
-	closure_queue(cl);						\
+	closure_queue(_cl);						\
 	return;								\
 } while (0)