Merge branch 'for-4.14/block-postmerge' of git://git.kernel.dk/linux-block

Pull followup block layer updates from Jens Axboe:
 "I ended up splitting the main pull request for this series into two,
  mainly because of clashes between NVMe fixes that went into 4.13 after
  the for-4.14 branches were split off. This pull request is mostly
  NVMe, but not exclusively. In detail, it contains:

   - Two pull request for NVMe changes from Christoph. Nothing new on
     the feature front, basically just fixes all over the map for the
     core bits, transport, rdma, etc.

   - Series from Bart, cleaning up various bits in the BFQ scheduler.

   - Series of bcache fixes, which has been lingering for a release or
     two. Coly sent this in, but patches from various people in this
     area.

   - Set of patches for BFQ from Paolo himself, updating both
     documentation and fixing some corner cases in performance.

   - Series from Omar, attempting to now get the 4k loop support
     correct. Our confidence level is higher this time.

   - Series from Shaohua for loop as well, improving O_DIRECT
     performance and fixing a use-after-free"

* 'for-4.14/block-postmerge' of git://git.kernel.dk/linux-block: (74 commits)
  bcache: initialize dirty stripes in flash_dev_run()
  loop: set physical block size to logical block size
  bcache: fix bch_hprint crash and improve output
  bcache: Update continue_at() documentation
  bcache: silence static checker warning
  bcache: fix for gc and write-back race
  bcache: increase the number of open buckets
  bcache: Correct return value for sysfs attach errors
  bcache: correct cache_dirty_target in __update_writeback_rate()
  bcache: gc does not work when triggering by manual command
  bcache: Don't reinvent the wheel but use existing llist API
  bcache: do not subtract sectors_to_gc for bypassed IO
  bcache: fix sequential large write IO bypass
  bcache: Fix leak of bdev reference
  block/loop: remove unused field
  block/loop: fix use after free
  bfq: Use icq_to_bic() consistently
  bfq: Suppress compiler warnings about comparisons
  bfq: Check kstrtoul() return value
  bfq: Declare local functions static
  ...

2 files changed, 109 insertions, 92 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 407cb172d6e3..85de67334695 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -213,10 +213,13 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
 	 */
 	blk_mq_freeze_queue(lo->lo_queue);
 	lo->use_dio = use_dio;
-	if (use_dio)
+	if (use_dio) {
+		queue_flag_clear_unlocked(QUEUE_FLAG_NOMERGES, lo->lo_queue);
 		lo->lo_flags |= LO_FLAGS_DIRECT_IO;
-	else
+	} else {
+		queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, lo->lo_queue);
 		lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
+	}
 	blk_mq_unfreeze_queue(lo->lo_queue);
 }
 
@@ -460,12 +463,21 @@ static void lo_complete_rq(struct request *rq)
 	blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK);
 }
 
+static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
+{
+	if (!atomic_dec_and_test(&cmd->ref))
+		return;
+	kfree(cmd->bvec);
+	cmd->bvec = NULL;
+	blk_mq_complete_request(cmd->rq);
+}
+
 static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
 {
 	struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);
 
 	cmd->ret = ret;
-	blk_mq_complete_request(cmd->rq);
+	lo_rw_aio_do_completion(cmd);
 }
 
 static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
@@ -473,22 +485,51 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 {
 	struct iov_iter iter;
 	struct bio_vec *bvec;
-	struct bio *bio = cmd->rq->bio;
+	struct request *rq = cmd->rq;
+	struct bio *bio = rq->bio;
 	struct file *file = lo->lo_backing_file;
+	unsigned int offset;
+	int segments = 0;
 	int ret;
 
-	/* nomerge for loop request queue */
-	WARN_ON(cmd->rq->bio != cmd->rq->biotail);
+	if (rq->bio != rq->biotail) {
+		struct req_iterator iter;
+		struct bio_vec tmp;
+
+		__rq_for_each_bio(bio, rq)
+			segments += bio_segments(bio);
+		bvec = kmalloc(sizeof(struct bio_vec) * segments, GFP_NOIO);
+		if (!bvec)
+			return -EIO;
+		cmd->bvec = bvec;
+
+		/*
+		 * The bios of the request may be started from the middle of
+		 * the 'bvec' because of bio splitting, so we can't directly
+		 * copy bio->bi_iov_vec to new bvec. The rq_for_each_segment
+		 * API will take care of all details for us.
+		 */
+		rq_for_each_segment(tmp, rq, iter) {
+			*bvec = tmp;
+			bvec++;
+		}
+		bvec = cmd->bvec;
+		offset = 0;
+	} else {
+		/*
+		 * Same here, this bio may be started from the middle of the
+		 * 'bvec' because of bio splitting, so offset from the bvec
+		 * must be passed to iov iterator
+		 */
+		offset = bio->bi_iter.bi_bvec_done;
+		bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
+		segments = bio_segments(bio);
+	}
+	atomic_set(&cmd->ref, 2);
 
-	bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
 	iov_iter_bvec(&iter, ITER_BVEC | rw, bvec,
-		      bio_segments(bio), blk_rq_bytes(cmd->rq));
-	/*
-	 * This bio may be started from the middle of the 'bvec'
-	 * because of bio splitting, so offset from the bvec must
-	 * be passed to iov iterator
-	 */
-	iter.iov_offset = bio->bi_iter.bi_bvec_done;
+		      segments, blk_rq_bytes(rq));
+	iter.iov_offset = offset;
 
 	cmd->iocb.ki_pos = pos;
 	cmd->iocb.ki_filp = file;
@@ -500,6 +541,8 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 	else
 		ret = call_read_iter(file, &cmd->iocb, &iter);
 
+	lo_rw_aio_do_completion(cmd);
+
 	if (ret != -EIOCBQUEUED)
 		cmd->iocb.ki_complete(&cmd->iocb, ret, 0);
 	return 0;
@@ -546,74 +589,12 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	}
 }
 
-struct switch_request {
-	struct file *file;
-	struct completion wait;
-};
-
 static inline void loop_update_dio(struct loop_device *lo)
 {
 	__loop_update_dio(lo, io_is_direct(lo->lo_backing_file) |
 			lo->use_dio);
 }
 
-/*
- * Do the actual switch; called from the BIO completion routine
- */
-static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
-{
-	struct file *file = p->file;
-	struct file *old_file = lo->lo_backing_file;
-	struct address_space *mapping;
-
-	/* if no new file, only flush of queued bios requested */
-	if (!file)
-		return;
-
-	mapping = file->f_mapping;
-	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
-	lo->lo_backing_file = file;
-	lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
-		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
-	lo->old_gfp_mask = mapping_gfp_mask(mapping);
-	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
-	loop_update_dio(lo);
-}
-
-/*
- * loop_switch performs the hard work of switching a backing store.
- * First it needs to flush existing IO, it does this by sending a magic
- * BIO down the pipe. The completion of this BIO does the actual switch.
- */
-static int loop_switch(struct loop_device *lo, struct file *file)
-{
-	struct switch_request w;
-
-	w.file = file;
-
-	/* freeze queue and wait for completion of scheduled requests */
-	blk_mq_freeze_queue(lo->lo_queue);
-
-	/* do the switch action */
-	do_loop_switch(lo, &w);
-
-	/* unfreeze */
-	blk_mq_unfreeze_queue(lo->lo_queue);
-
-	return 0;
-}
-
-/*
- * Helper to flush the IOs in loop, but keeping loop thread running
- */
-static int loop_flush(struct loop_device *lo)
-{
-	/* loop not yet configured, no running thread, nothing to flush */
-	if (lo->lo_state != Lo_bound)
-		return 0;
-	return loop_switch(lo, NULL);
-}
-
 static void loop_reread_partitions(struct loop_device *lo,
 				   struct block_device *bdev)
 {
@@ -678,9 +659,14 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 		goto out_putf;
 
 	/* and ... switch */
-	error = loop_switch(lo, file);
-	if (error)
-		goto out_putf;
+	blk_mq_freeze_queue(lo->lo_queue);
+	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
+	lo->lo_backing_file = file;
+	lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping);
+	mapping_set_gfp_mask(file->f_mapping,
+			     lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
+	loop_update_dio(lo);
+	blk_mq_unfreeze_queue(lo->lo_queue);
 
 	fput(old_file);
 	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
@@ -867,7 +853,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	struct file	*file, *f;
 	struct inode	*inode;
 	struct address_space *mapping;
-	unsigned lo_blocksize;
 	int		lo_flags = 0;
 	int		error;
 	loff_t		size;
@@ -911,9 +896,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	    !file->f_op->write_iter)
 		lo_flags |= LO_FLAGS_READ_ONLY;
 
-	lo_blocksize = S_ISBLK(inode->i_mode) ?
-		inode->i_bdev->bd_block_size : PAGE_SIZE;
-
 	error = -EFBIG;
 	size = get_loop_size(lo, file);
 	if ((loff_t)(sector_t)size != size)
@@ -927,7 +909,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);
 
 	lo->use_dio = false;
-	lo->lo_blocksize = lo_blocksize;
 	lo->lo_device = bdev;
 	lo->lo_flags = lo_flags;
 	lo->lo_backing_file = file;
@@ -947,7 +928,8 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	/* let user-space know about the new size */
 	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
 
-	set_blocksize(bdev, lo_blocksize);
+	set_blocksize(bdev, S_ISBLK(inode->i_mode) ?
+		      block_size(inode->i_bdev) : PAGE_SIZE);
 
 	lo->lo_state = Lo_bound;
 	if (part_shift)
@@ -1053,6 +1035,9 @@ static int loop_clr_fd(struct loop_device *lo)
 	memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
 	memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
 	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
+	blk_queue_logical_block_size(lo->lo_queue, 512);
+	blk_queue_physical_block_size(lo->lo_queue, 512);
+	blk_queue_io_min(lo->lo_queue, 512);
 	if (bdev) {
 		bdput(bdev);
 		invalidate_bdev(bdev);
@@ -1336,6 +1321,26 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg)
 	return error;
 }
 
+static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
+{
+	if (lo->lo_state != Lo_bound)
+		return -ENXIO;
+
+	if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg))
+		return -EINVAL;
+
+	blk_mq_freeze_queue(lo->lo_queue);
+
+	blk_queue_logical_block_size(lo->lo_queue, arg);
+	blk_queue_physical_block_size(lo->lo_queue, arg);
+	blk_queue_io_min(lo->lo_queue, arg);
+	loop_update_dio(lo);
+
+	blk_mq_unfreeze_queue(lo->lo_queue);
+
+	return 0;
+}
+
 static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	unsigned int cmd, unsigned long arg)
 {
@@ -1384,6 +1389,11 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
 			err = loop_set_dio(lo, arg);
 		break;
+	case LOOP_SET_BLOCK_SIZE:
+		err = -EPERM;
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+			err = loop_set_block_size(lo, arg);
+		break;
 	default:
 		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
 	}
@@ -1583,12 +1593,13 @@ static void lo_release(struct gendisk *disk, fmode_t mode)
 		err = loop_clr_fd(lo);
 		if (!err)
 			return;
-	} else {
+	} else if (lo->lo_state == Lo_bound) {
 		/*
 		 * Otherwise keep thread (if running) and config,
 		 * but flush possible ongoing bios in thread.
 		 */
-		loop_flush(lo);
+		blk_mq_freeze_queue(lo->lo_queue);
+		blk_mq_unfreeze_queue(lo->lo_queue);
 	}
 
 	mutex_unlock(&lo->lo_ctl_mutex);
@@ -1770,9 +1781,13 @@ static int loop_add(struct loop_device **l, int i)
 	}
 	lo->lo_queue->queuedata = lo;
 
+	blk_queue_max_hw_sectors(lo->lo_queue, BLK_DEF_MAX_SECTORS);
+
 	/*
-	 * It doesn't make sense to enable merge because the I/O
-	 * submitted to backing file is handled page by page.
+	 * By default, we do buffer IO, so it doesn't make sense to enable
+	 * merge because the I/O submitted to backing file is handled page by
+	 * page. For directio mode, merge does help to dispatch bigger request
+	 * to underlayer disk. We will enable merge once directio is enabled.
 	 */
 	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, lo->lo_queue);
 
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index fecd3f97ef8c..f68c1d50802f 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -48,7 +48,6 @@ struct loop_device {
 
 	struct file *	lo_backing_file;
 	struct block_device *lo_device;
-	unsigned	lo_blocksize;
 	void		*key_data; 
 
 	gfp_t		old_gfp_mask;
@@ -68,10 +67,13 @@ struct loop_device {
 struct loop_cmd {
 	struct kthread_work work;
 	struct request *rq;
-	struct list_head list;
-	bool use_aio;           /* use AIO interface to handle I/O */
+	union {
+		bool use_aio; /* use AIO interface to handle I/O */
+		atomic_t ref; /* only for aio */
+	};
 	long ret;
 	struct kiocb iocb;
+	struct bio_vec *bvec;
 };
 
 /* Support for loadable transfer modules */