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, 57 insertions, 11 deletions

diff --git a/block/bio.c b/block/bio.c
index db85c57..2b37502 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -270,11 +270,15 @@ static void bio_free(struct bio *bio)
 	}
 }
 
-void bio_init(struct bio *bio)
+void bio_init(struct bio *bio, struct bio_vec *table,
+	      unsigned short max_vecs)
 {
 	memset(bio, 0, sizeof(*bio));
 	atomic_set(&bio->__bi_remaining, 1);
 	atomic_set(&bio->__bi_cnt, 1);
+
+	bio->bi_io_vec = table;
+	bio->bi_max_vecs = max_vecs;
 }
 EXPORT_SYMBOL(bio_init);
 
@@ -480,7 +484,7 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		return NULL;
 
 	bio = p + front_pad;
-	bio_init(bio);
+	bio_init(bio, NULL, 0);
 
 	if (nr_iovecs > inline_vecs) {
 		unsigned long idx = 0;
@@ -670,6 +674,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
+	case REQ_OP_WRITE_ZEROES:
 		break;
 	case REQ_OP_WRITE_SAME:
 		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
@@ -847,6 +852,55 @@ done:
 }
 EXPORT_SYMBOL(bio_add_page);
 
+/**
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * @bio: bio to add pages to
+ * @iter: iov iterator describing the region to be mapped
+ *
+ * Pins as many pages from *iter and appends them to @bio's bvec array. The
+ * pages will have to be released using put_page() when done.
+ */
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
+	struct page **pages = (struct page **)bv;
+	size_t offset, diff;
+	ssize_t size;
+
+	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
+	if (unlikely(size <= 0))
+		return size ? size : -EFAULT;
+	nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
+
+	/*
+	 * Deep magic below:  We need to walk the pinned pages backwards
+	 * because we are abusing the space allocated for the bio_vecs
+	 * for the page array.  Because the bio_vecs are larger than the
+	 * page pointers by definition this will always work.  But it also
+	 * means we can't use bio_add_page, so any changes to it's semantics
+	 * need to be reflected here as well.
+	 */
+	bio->bi_iter.bi_size += size;
+	bio->bi_vcnt += nr_pages;
+
+	diff = (nr_pages * PAGE_SIZE - offset) - size;
+	while (nr_pages--) {
+		bv[nr_pages].bv_page = pages[nr_pages];
+		bv[nr_pages].bv_len = PAGE_SIZE;
+		bv[nr_pages].bv_offset = 0;
+	}
+
+	bv[0].bv_offset += offset;
+	bv[0].bv_len -= offset;
+	if (diff)
+		bv[bio->bi_vcnt - 1].bv_len -= diff;
+
+	iov_iter_advance(iter, size);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
+
 struct submit_bio_ret {
 	struct completion event;
 	int error;
@@ -1786,15 +1840,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	BUG_ON(sectors <= 0);
 	BUG_ON(sectors >= bio_sectors(bio));
 
-	/*
-	 * Discards need a mutable bio_vec to accommodate the payload
-	 * required by the DSM TRIM and UNMAP commands.
-	 */
-	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
-		split = bio_clone_bioset(bio, gfp, bs);
-	else
-		split = bio_clone_fast(bio, gfp, bs);
-
+	split = bio_clone_fast(bio, gfp, bs);
 	if (!split)
 		return NULL;