Merge branch 'for-4.10/block' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "This is the main block pull request this series. Contrary to previous
  release, I've kept the core and driver changes in the same branch. We
  always ended up having dependencies between the two for obvious
  reasons, so makes more sense to keep them together. That said, I'll
  probably try and keep more topical branches going forward, especially
  for cycles that end up being as busy as this one.

  The major parts of this pull request is:

   - Improved support for O_DIRECT on block devices, with a small
     private implementation instead of using the pig that is
     fs/direct-io.c. From Christoph.

   - Request completion tracking in a scalable fashion. This is utilized
     by two components in this pull, the new hybrid polling and the
     writeback queue throttling code.

   - Improved support for polling with O_DIRECT, adding a hybrid mode
     that combines pure polling with an initial sleep. From me.

   - Support for automatic throttling of writeback queues on the block
     side. This uses feedback from the device completion latencies to
     scale the queue on the block side up or down. From me.

   - Support from SMR drives in the block layer and for SD. From Hannes
     and Shaun.

   - Multi-connection support for nbd. From Josef.

   - Cleanup of request and bio flags, so we have a clear split between
     which are bio (or rq) private, and which ones are shared. From
     Christoph.

   - A set of patches from Bart, that improve how we handle queue
     stopping and starting in blk-mq.

   - Support for WRITE_ZEROES from Chaitanya.

   - Lightnvm updates from Javier/Matias.

   - Supoort for FC for the nvme-over-fabrics code. From James Smart.

   - A bunch of fixes from a whole slew of people, too many to name
     here"

* 'for-4.10/block' of git://git.kernel.dk/linux-block: (182 commits)
  blk-stat: fix a few cases of missing batch flushing
  blk-flush: run the queue when inserting blk-mq flush
  elevator: make the rqhash helpers exported
  blk-mq: abstract out blk_mq_dispatch_rq_list() helper
  blk-mq: add blk_mq_start_stopped_hw_queue()
  block: improve handling of the magic discard payload
  blk-wbt: don't throttle discard or write zeroes
  nbd: use dev_err_ratelimited in io path
  nbd: reset the setup task for NBD_CLEAR_SOCK
  nvme-fabrics: Add FC LLDD loopback driver to test FC-NVME
  nvme-fabrics: Add target support for FC transport
  nvme-fabrics: Add host support for FC transport
  nvme-fabrics: Add FC transport LLDD api definitions
  nvme-fabrics: Add FC transport FC-NVME definitions
  nvme-fabrics: Add FC transport error codes to nvme.h
  Add type 0x28 NVME type code to scsi fc headers
  nvme-fabrics: patch target code in prep for FC transport support
  nvme-fabrics: set sqe.command_id in core not transports
  parser: add u64 number parser
  nvme-rdma: align to generic ib_event logging helper
  ...

1 files changed, 348 insertions, 0 deletions

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
new file mode 100644
index 000000000000..472211fa183a
--- /dev/null
+++ b/block/blk-zoned.c
@@ -0,0 +1,348 @@
+/*
+ * Zoned block device handling
+ *
+ * Copyright (c) 2015, Hannes Reinecke
+ * Copyright (c) 2015, SUSE Linux GmbH
+ *
+ * Copyright (c) 2016, Damien Le Moal
+ * Copyright (c) 2016, Western Digital
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/rbtree.h>
+#include <linux/blkdev.h>
+
+static inline sector_t blk_zone_start(struct request_queue *q,
+				      sector_t sector)
+{
+	sector_t zone_mask = blk_queue_zone_size(q) - 1;
+
+	return sector & ~zone_mask;
+}
+
+/*
+ * Check that a zone report belongs to the partition.
+ * If yes, fix its start sector and write pointer, copy it in the
+ * zone information array and return true. Return false otherwise.
+ */
+static bool blkdev_report_zone(struct block_device *bdev,
+			       struct blk_zone *rep,
+			       struct blk_zone *zone)
+{
+	sector_t offset = get_start_sect(bdev);
+
+	if (rep->start < offset)
+		return false;
+
+	rep->start -= offset;
+	if (rep->start + rep->len > bdev->bd_part->nr_sects)
+		return false;
+
+	if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL)
+		rep->wp = rep->start + rep->len;
+	else
+		rep->wp -= offset;
+	memcpy(zone, rep, sizeof(struct blk_zone));
+
+	return true;
+}
+
+/**
+ * blkdev_report_zones - Get zones information
+ * @bdev:	Target block device
+ * @sector:	Sector from which to report zones
+ * @zones:	Array of zone structures where to return the zones information
+ * @nr_zones:	Number of zone structures in the zone array
+ * @gfp_mask:	Memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *    Get zone information starting from the zone containing @sector.
+ *    The number of zone information reported may be less than the number
+ *    requested by @nr_zones. The number of zones actually reported is
+ *    returned in @nr_zones.
+ */
+int blkdev_report_zones(struct block_device *bdev,
+			sector_t sector,
+			struct blk_zone *zones,
+			unsigned int *nr_zones,
+			gfp_t gfp_mask)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	struct blk_zone_report_hdr *hdr;
+	unsigned int nrz = *nr_zones;
+	struct page *page;
+	unsigned int nr_rep;
+	size_t rep_bytes;
+	unsigned int nr_pages;
+	struct bio *bio;
+	struct bio_vec *bv;
+	unsigned int i, n, nz;
+	unsigned int ofst;
+	void *addr;
+	int ret;
+
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -EOPNOTSUPP;
+
+	if (!nrz)
+		return 0;
+
+	if (sector > bdev->bd_part->nr_sects) {
+		*nr_zones = 0;
+		return 0;
+	}
+
+	/*
+	 * The zone report has a header. So make room for it in the
+	 * payload. Also make sure that the report fits in a single BIO
+	 * that will not be split down the stack.
+	 */
+	rep_bytes = sizeof(struct blk_zone_report_hdr) +
+		sizeof(struct blk_zone) * nrz;
+	rep_bytes = (rep_bytes + PAGE_SIZE - 1) & PAGE_MASK;
+	if (rep_bytes > (queue_max_sectors(q) << 9))
+		rep_bytes = queue_max_sectors(q) << 9;
+
+	nr_pages = min_t(unsigned int, BIO_MAX_PAGES,
+			 rep_bytes >> PAGE_SHIFT);
+	nr_pages = min_t(unsigned int, nr_pages,
+			 queue_max_segments(q));
+
+	bio = bio_alloc(gfp_mask, nr_pages);
+	if (!bio)
+		return -ENOMEM;
+
+	bio->bi_bdev = bdev;
+	bio->bi_iter.bi_sector = blk_zone_start(q, sector);
+	bio_set_op_attrs(bio, REQ_OP_ZONE_REPORT, 0);
+
+	for (i = 0; i < nr_pages; i++) {
+		page = alloc_page(gfp_mask);
+		if (!page) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		if (!bio_add_page(bio, page, PAGE_SIZE, 0)) {
+			__free_page(page);
+			break;
+		}
+	}
+
+	if (i == 0)
+		ret = -ENOMEM;
+	else
+		ret = submit_bio_wait(bio);
+	if (ret)
+		goto out;
+
+	/*
+	 * Process the report result: skip the header and go through the
+	 * reported zones to fixup and fixup the zone information for
+	 * partitions. At the same time, return the zone information into
+	 * the zone array.
+	 */
+	n = 0;
+	nz = 0;
+	nr_rep = 0;
+	bio_for_each_segment_all(bv, bio, i) {
+
+		if (!bv->bv_page)
+			break;
+
+		addr = kmap_atomic(bv->bv_page);
+
+		/* Get header in the first page */
+		ofst = 0;
+		if (!nr_rep) {
+			hdr = (struct blk_zone_report_hdr *) addr;
+			nr_rep = hdr->nr_zones;
+			ofst = sizeof(struct blk_zone_report_hdr);
+		}
+
+		/* Fixup and report zones */
+		while (ofst < bv->bv_len &&
+		       n < nr_rep && nz < nrz) {
+			if (blkdev_report_zone(bdev, addr + ofst, &zones[nz]))
+				nz++;
+			ofst += sizeof(struct blk_zone);
+			n++;
+		}
+
+		kunmap_atomic(addr);
+
+		if (n >= nr_rep || nz >= nrz)
+			break;
+
+	}
+
+	*nr_zones = nz;
+out:
+	bio_for_each_segment_all(bv, bio, i)
+		__free_page(bv->bv_page);
+	bio_put(bio);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_report_zones);
+
+/**
+ * blkdev_reset_zones - Reset zones write pointer
+ * @bdev:	Target block device
+ * @sector:	Start sector of the first zone to reset
+ * @nr_sectors:	Number of sectors, at least the length of one zone
+ * @gfp_mask:	Memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *    Reset the write pointer of the zones contained in the range
+ *    @sector..@sector+@nr_sectors. Specifying the entire disk sector range
+ *    is valid, but the specified range should not contain conventional zones.
+ */
+int blkdev_reset_zones(struct block_device *bdev,
+		       sector_t sector, sector_t nr_sectors,
+		       gfp_t gfp_mask)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	sector_t zone_sectors;
+	sector_t end_sector = sector + nr_sectors;
+	struct bio *bio;
+	int ret;
+
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -EOPNOTSUPP;
+
+	if (end_sector > bdev->bd_part->nr_sects)
+		/* Out of range */
+		return -EINVAL;
+
+	/* Check alignment (handle eventual smaller last zone) */
+	zone_sectors = blk_queue_zone_size(q);
+	if (sector & (zone_sectors - 1))
+		return -EINVAL;
+
+	if ((nr_sectors & (zone_sectors - 1)) &&
+	    end_sector != bdev->bd_part->nr_sects)
+		return -EINVAL;
+
+	while (sector < end_sector) {
+
+		bio = bio_alloc(gfp_mask, 0);
+		bio->bi_iter.bi_sector = sector;
+		bio->bi_bdev = bdev;
+		bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);
+
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+
+		if (ret)
+			return ret;
+
+		sector += zone_sectors;
+
+		/* This may take a while, so be nice to others */
+		cond_resched();
+
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blkdev_reset_zones);
+
+/**
+ * BLKREPORTZONE ioctl processing.
+ * Called from blkdev_ioctl.
+ */
+int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
+			      unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct request_queue *q;
+	struct blk_zone_report rep;
+	struct blk_zone *zones;
+	int ret;
+
+	if (!argp)
+		return -EINVAL;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -ENOTTY;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report)))
+		return -EFAULT;
+
+	if (!rep.nr_zones)
+		return -EINVAL;
+
+	zones = kcalloc(rep.nr_zones, sizeof(struct blk_zone), GFP_KERNEL);
+	if (!zones)
+		return -ENOMEM;
+
+	ret = blkdev_report_zones(bdev, rep.sector,
+				  zones, &rep.nr_zones,
+				  GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (rep.nr_zones) {
+		if (copy_to_user(argp + sizeof(struct blk_zone_report), zones,
+				 sizeof(struct blk_zone) * rep.nr_zones))
+			ret = -EFAULT;
+	}
+
+ out:
+	kfree(zones);
+
+	return ret;
+}
+
+/**
+ * BLKRESETZONE ioctl processing.
+ * Called from blkdev_ioctl.
+ */
+int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
+			     unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct request_queue *q;
+	struct blk_zone_range zrange;
+
+	if (!argp)
+		return -EINVAL;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_is_zoned(q))
+		return -ENOTTY;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (!(mode & FMODE_WRITE))
+		return -EBADF;
+
+	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
+		return -EFAULT;
+
+	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
+				  GFP_KERNEL);
+}