Merge branch 'for-4.13/block' of git://git.kernel.dk/linux-block

Pull core block/IO updates from Jens Axboe:
 "This is the main pull request for the block layer for 4.13. Not a huge
  round in terms of features, but there's a lot of churn related to some
  core cleanups.

  Note this depends on the UUID tree pull request, that Christoph
  already sent out.

  This pull request contains:

   - A series from Christoph, unifying the error/stats codes in the
     block layer. We now use blk_status_t everywhere, instead of using
     different schemes for different places.

   - Also from Christoph, some cleanups around request allocation and IO
     scheduler interactions in blk-mq.

   - And yet another series from Christoph, cleaning up how we handle
     and do bounce buffering in the block layer.

   - A blk-mq debugfs series from Bart, further improving on the support
     we have for exporting internal information to aid debugging IO
     hangs or stalls.

   - Also from Bart, a series that cleans up the request initialization
     differences across types of devices.

   - A series from Goldwyn Rodrigues, allowing the block layer to return
     failure if we will block and the user asked for non-blocking.

   - Patch from Hannes for supporting setting loop devices block size to
     that of the underlying device.

   - Two series of patches from Javier, fixing various issues with
     lightnvm, particular around pblk.

   - A series from me, adding support for write hints. This comes with
     NVMe support as well, so applications can help guide data placement
     on flash to improve performance, latencies, and write
     amplification.

   - A series from Ming, improving and hardening blk-mq support for
     stopping/starting and quiescing hardware queues.

   - Two pull requests for NVMe updates. Nothing major on the feature
     side, but lots of cleanups and bug fixes. From the usual crew.

   - A series from Neil Brown, greatly improving the bio rescue set
     support. Most notably, this kills the bio rescue work queues, if we
     don't really need them.

   - Lots of other little bug fixes that are all over the place"

* 'for-4.13/block' of git://git.kernel.dk/linux-block: (217 commits)
  lightnvm: pblk: set line bitmap check under debug
  lightnvm: pblk: verify that cache read is still valid
  lightnvm: pblk: add initialization check
  lightnvm: pblk: remove target using async. I/Os
  lightnvm: pblk: use vmalloc for GC data buffer
  lightnvm: pblk: use right metadata buffer for recovery
  lightnvm: pblk: schedule if data is not ready
  lightnvm: pblk: remove unused return variable
  lightnvm: pblk: fix double-free on pblk init
  lightnvm: pblk: fix bad le64 assignations
  nvme: Makefile: remove dead build rule
  blk-mq: map all HWQ also in hyperthreaded system
  nvmet-rdma: register ib_client to not deadlock in device removal
  nvme_fc: fix error recovery on link down.
  nvmet_fc: fix crashes on bad opcodes
  nvme_fc: Fix crash when nvme controller connection fails.
  nvme_fc: replace ioabort msleep loop with completion
  nvme_fc: fix double calls to nvme_cleanup_cmd()
  nvme-fabrics: verify that a controller returns the correct NQN
  nvme: simplify nvme_dev_attrs_are_visible
  ...

1 files changed, 51 insertions, 13 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index ebbd0c3fe0ed..0de11444e317 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -221,7 +221,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
 }
 
 static int
-figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
+figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit,
+		 loff_t logical_blocksize)
 {
 	loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
 	sector_t x = (sector_t)size;
@@ -233,6 +234,12 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
 		lo->lo_offset = offset;
 	if (lo->lo_sizelimit != sizelimit)
 		lo->lo_sizelimit = sizelimit;
+	if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) {
+		lo->lo_logical_blocksize = logical_blocksize;
+		blk_queue_physical_block_size(lo->lo_queue, lo->lo_blocksize);
+		blk_queue_logical_block_size(lo->lo_queue,
+					     lo->lo_logical_blocksize);
+	}
 	set_capacity(lo->lo_disk, x);
 	bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9);
 	/* let user-space know about the new size */
@@ -457,7 +464,7 @@ static void lo_complete_rq(struct request *rq)
 		zero_fill_bio(bio);
 	}
 
-	blk_mq_end_request(rq, cmd->ret < 0 ? -EIO : 0);
+	blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK);
 }
 
 static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
@@ -813,6 +820,7 @@ static void loop_config_discard(struct loop_device *lo)
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
 	struct request_queue *q = lo->lo_queue;
+	int lo_bits = 9;
 
 	/*
 	 * We use punch hole to reclaim the free space used by the
@@ -832,8 +840,11 @@ static void loop_config_discard(struct loop_device *lo)
 
 	q->limits.discard_granularity = inode->i_sb->s_blocksize;
 	q->limits.discard_alignment = 0;
-	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
+	if (lo->lo_flags & LO_FLAGS_BLOCKSIZE)
+		lo_bits = blksize_bits(lo->lo_logical_blocksize);
+
+	blk_queue_max_discard_sectors(q, UINT_MAX >> lo_bits);
+	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> lo_bits);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
 
@@ -843,10 +854,16 @@ static void loop_unprepare_queue(struct loop_device *lo)
 	kthread_stop(lo->worker_task);
 }
 
+static int loop_kthread_worker_fn(void *worker_ptr)
+{
+	current->flags |= PF_LESS_THROTTLE;
+	return kthread_worker_fn(worker_ptr);
+}
+
 static int loop_prepare_queue(struct loop_device *lo)
 {
 	kthread_init_worker(&lo->worker);
-	lo->worker_task = kthread_run(kthread_worker_fn,
+	lo->worker_task = kthread_run(loop_kthread_worker_fn,
 			&lo->worker, "loop%d", lo->lo_number);
 	if (IS_ERR(lo->worker_task))
 		return -ENOMEM;
@@ -921,6 +938,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 
 	lo->use_dio = false;
 	lo->lo_blocksize = lo_blocksize;
+	lo->lo_logical_blocksize = 512;
 	lo->lo_device = bdev;
 	lo->lo_flags = lo_flags;
 	lo->lo_backing_file = file;
@@ -1086,6 +1104,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	int err;
 	struct loop_func_table *xfer;
 	kuid_t uid = current_uid();
+	int lo_flags = lo->lo_flags;
 
 	if (lo->lo_encrypt_key_size &&
 	    !uid_eq(lo->lo_key_owner, uid) &&
@@ -1118,12 +1137,30 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (err)
 		goto exit;
 
+	if (info->lo_flags & LO_FLAGS_BLOCKSIZE) {
+		if (!(lo->lo_flags & LO_FLAGS_BLOCKSIZE))
+			lo->lo_logical_blocksize = 512;
+		lo->lo_flags |= LO_FLAGS_BLOCKSIZE;
+		if (LO_INFO_BLOCKSIZE(info) != 512 &&
+		    LO_INFO_BLOCKSIZE(info) != 1024 &&
+		    LO_INFO_BLOCKSIZE(info) != 2048 &&
+		    LO_INFO_BLOCKSIZE(info) != 4096)
+			return -EINVAL;
+		if (LO_INFO_BLOCKSIZE(info) > lo->lo_blocksize)
+			return -EINVAL;
+	}
+
 	if (lo->lo_offset != info->lo_offset ||
-	    lo->lo_sizelimit != info->lo_sizelimit)
-		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
+	    lo->lo_sizelimit != info->lo_sizelimit ||
+	    lo->lo_flags != lo_flags ||
+	    ((lo->lo_flags & LO_FLAGS_BLOCKSIZE) &&
+	     lo->lo_logical_blocksize != LO_INFO_BLOCKSIZE(info))) {
+		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit,
+				     LO_INFO_BLOCKSIZE(info))) {
 			err = -EFBIG;
 			goto exit;
 		}
+	}
 
 	loop_config_discard(lo);
 
@@ -1306,12 +1343,13 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
 	return err;
 }
 
-static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev)
+static int loop_set_capacity(struct loop_device *lo)
 {
 	if (unlikely(lo->lo_state != Lo_bound))
 		return -ENXIO;
 
-	return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
+	return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit,
+				lo->lo_logical_blocksize);
 }
 
 static int loop_set_dio(struct loop_device *lo, unsigned long arg)
@@ -1369,7 +1407,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_SET_CAPACITY:
 		err = -EPERM;
 		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
-			err = loop_set_capacity(lo, bdev);
+			err = loop_set_capacity(lo);
 		break;
 	case LOOP_SET_DIRECT_IO:
 		err = -EPERM;
@@ -1645,7 +1683,7 @@ int loop_unregister_transfer(int number)
 EXPORT_SYMBOL(loop_register_transfer);
 EXPORT_SYMBOL(loop_unregister_transfer);
 
-static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
@@ -1654,7 +1692,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_mq_start_request(bd->rq);
 
 	if (lo->lo_state != Lo_bound)
-		return BLK_MQ_RQ_QUEUE_ERROR;
+		return BLK_STS_IOERR;
 
 	switch (req_op(cmd->rq)) {
 	case REQ_OP_FLUSH:
@@ -1669,7 +1707,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	kthread_queue_work(&lo->worker, &cmd->work);
 
-	return BLK_MQ_RQ_QUEUE_OK;
+	return BLK_STS_OK;
 }
 
 static void loop_handle_cmd(struct loop_cmd *cmd)