Merge tag 'for-4.19/block-20180812' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "First pull request for this merge window, there will also be a
  followup request with some stragglers.

  This pull request contains:

   - Fix for a thundering heard issue in the wbt block code (Anchal
     Agarwal)

   - A few NVMe pull requests:
      * Improved tracepoints (Keith)
      * Larger inline data support for RDMA (Steve Wise)
      * RDMA setup/teardown fixes (Sagi)
      * Effects log suppor for NVMe target (Chaitanya Kulkarni)
      * Buffered IO suppor for NVMe target (Chaitanya Kulkarni)
      * TP4004 (ANA) support (Christoph)
      * Various NVMe fixes

   - Block io-latency controller support. Much needed support for
     properly containing block devices. (Josef)

   - Series improving how we handle sense information on the stack
     (Kees)

   - Lightnvm fixes and updates/improvements (Mathias/Javier et al)

   - Zoned device support for null_blk (Matias)

   - AIX partition fixes (Mauricio Faria de Oliveira)

   - DIF checksum code made generic (Max Gurtovoy)

   - Add support for discard in iostats (Michael Callahan / Tejun)

   - Set of updates for BFQ (Paolo)

   - Removal of async write support for bsg (Christoph)

   - Bio page dirtying and clone fixups (Christoph)

   - Set of bcache fix/changes (via Coly)

   - Series improving blk-mq queue setup/teardown speed (Ming)

   - Series improving merging performance on blk-mq (Ming)

   - Lots of other fixes and cleanups from a slew of folks"

* tag 'for-4.19/block-20180812' of git://git.kernel.dk/linux-block: (190 commits)
  blkcg: Make blkg_root_lookup() work for queues in bypass mode
  bcache: fix error setting writeback_rate through sysfs interface
  null_blk: add lock drop/acquire annotation
  Blk-throttle: reduce tail io latency when iops limit is enforced
  block: paride: pd: mark expected switch fall-throughs
  block: Ensure that a request queue is dissociated from the cgroup controller
  block: Introduce blk_exit_queue()
  blkcg: Introduce blkg_root_lookup()
  block: Remove two superfluous #include directives
  blk-mq: count the hctx as active before allocating tag
  block: bvec_nr_vecs() returns value for wrong slab
  bcache: trivial - remove tailing backslash in macro BTREE_FLAG
  bcache: make the pr_err statement used for ENOENT only in sysfs_attatch section
  bcache: set max writeback rate when I/O request is idle
  bcache: add code comments for bset.c
  bcache: fix mistaken comments in request.c
  bcache: fix mistaken code comments in bcache.h
  bcache: add a comment in super.c
  bcache: avoid unncessary cache prefetch bch_btree_node_get()
  bcache: display rate debug parameters to 0 when writeback is not running
  ...

1 files changed, 84 insertions, 124 deletions

diff --git a/block/bio.c b/block/bio.c
index 047c5dca6d90..b12966e415d3 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -28,9 +28,11 @@
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
+#include <linux/blk-cgroup.h>
 
 #include <trace/events/block.h>
 #include "blk.h"
+#include "blk-rq-qos.h"
 
 /*
  * Test patch to inline a certain number of bi_io_vec's inside the bio
@@ -156,7 +158,7 @@ out:
 
 unsigned int bvec_nr_vecs(unsigned short idx)
 {
-	return bvec_slabs[idx].nr_vecs;
+	return bvec_slabs[--idx].nr_vecs;
 }
 
 void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
@@ -645,83 +647,6 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 EXPORT_SYMBOL(bio_clone_fast);
 
 /**
- * 	bio_clone_bioset - clone a bio
- * 	@bio_src: bio to clone
- *	@gfp_mask: allocation priority
- *	@bs: bio_set to allocate from
- *
- *	Clone bio. Caller will own the returned bio, but not the actual data it
- *	points to. Reference count of returned bio will be one.
- */
-struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
-			     struct bio_set *bs)
-{
-	struct bvec_iter iter;
-	struct bio_vec bv;
-	struct bio *bio;
-
-	/*
-	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
-	 * bio_src->bi_io_vec to bio->bi_io_vec.
-	 *
-	 * We can't do that anymore, because:
-	 *
-	 *  - The point of cloning the biovec is to produce a bio with a biovec
-	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
-	 *
-	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
-	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
-	 *    But the clone should succeed as long as the number of biovecs we
-	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
-	 *
-	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
-	 *    that does not own the bio - reason being drivers don't use it for
-	 *    iterating over the biovec anymore, so expecting it to be kept up
-	 *    to date (i.e. for clones that share the parent biovec) is just
-	 *    asking for trouble and would force extra work on
-	 *    __bio_clone_fast() anyways.
-	 */
-
-	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
-	if (!bio)
-		return NULL;
-	bio->bi_disk		= bio_src->bi_disk;
-	bio->bi_opf		= bio_src->bi_opf;
-	bio->bi_write_hint	= bio_src->bi_write_hint;
-	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
-	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
-
-	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];
-		break;
-	default:
-		bio_for_each_segment(bv, bio_src, iter)
-			bio->bi_io_vec[bio->bi_vcnt++] = bv;
-		break;
-	}
-
-	if (bio_integrity(bio_src)) {
-		int ret;
-
-		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
-		if (ret < 0) {
-			bio_put(bio);
-			return NULL;
-		}
-	}
-
-	bio_clone_blkcg_association(bio, bio_src);
-
-	return bio;
-}
-EXPORT_SYMBOL(bio_clone_bioset);
-
-/**
  *	bio_add_pc_page	-	attempt to add page to bio
  *	@q: the target queue
  *	@bio: destination bio
@@ -1661,10 +1586,8 @@ void bio_set_pages_dirty(struct bio *bio)
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (page && !PageCompound(page))
-			set_page_dirty_lock(page);
+		if (!PageCompound(bvec->bv_page))
+			set_page_dirty_lock(bvec->bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
@@ -1674,19 +1597,15 @@ static void bio_release_pages(struct bio *bio)
 	struct bio_vec *bvec;
 	int i;
 
-	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (page)
-			put_page(page);
-	}
+	bio_for_each_segment_all(bvec, bio, i)
+		put_page(bvec->bv_page);
 }
 
 /*
  * bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
  * If they are, then fine.  If, however, some pages are clean then they must
  * have been written out during the direct-IO read.  So we take another ref on
- * the BIO and the offending pages and re-dirty the pages in process context.
+ * the BIO and re-dirty the pages in process context.
  *
  * It is expected that bio_check_pages_dirty() will wholly own the BIO from
  * here on.  It will run one put_page() against each page and will run one
@@ -1704,78 +1623,70 @@ static struct bio *bio_dirty_list;
  */
 static void bio_dirty_fn(struct work_struct *work)
 {
-	unsigned long flags;
-	struct bio *bio;
+	struct bio *bio, *next;
 
-	spin_lock_irqsave(&bio_dirty_lock, flags);
-	bio = bio_dirty_list;
+	spin_lock_irq(&bio_dirty_lock);
+	next = bio_dirty_list;
 	bio_dirty_list = NULL;
-	spin_unlock_irqrestore(&bio_dirty_lock, flags);
+	spin_unlock_irq(&bio_dirty_lock);
 
-	while (bio) {
-		struct bio *next = bio->bi_private;
+	while ((bio = next) != NULL) {
+		next = bio->bi_private;
 
 		bio_set_pages_dirty(bio);
 		bio_release_pages(bio);
 		bio_put(bio);
-		bio = next;
 	}
 }
 
 void bio_check_pages_dirty(struct bio *bio)
 {
 	struct bio_vec *bvec;
-	int nr_clean_pages = 0;
+	unsigned long flags;
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (PageDirty(page) || PageCompound(page)) {
-			put_page(page);
-			bvec->bv_page = NULL;
-		} else {
-			nr_clean_pages++;
-		}
+		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
+			goto defer;
 	}
 
-	if (nr_clean_pages) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&bio_dirty_lock, flags);
-		bio->bi_private = bio_dirty_list;
-		bio_dirty_list = bio;
-		spin_unlock_irqrestore(&bio_dirty_lock, flags);
-		schedule_work(&bio_dirty_work);
-	} else {
-		bio_put(bio);
-	}
+	bio_release_pages(bio);
+	bio_put(bio);
+	return;
+defer:
+	spin_lock_irqsave(&bio_dirty_lock, flags);
+	bio->bi_private = bio_dirty_list;
+	bio_dirty_list = bio;
+	spin_unlock_irqrestore(&bio_dirty_lock, flags);
+	schedule_work(&bio_dirty_work);
 }
 EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
 
-void generic_start_io_acct(struct request_queue *q, int rw,
+void generic_start_io_acct(struct request_queue *q, int op,
 			   unsigned long sectors, struct hd_struct *part)
 {
+	const int sgrp = op_stat_group(op);
 	int cpu = part_stat_lock();
 
 	part_round_stats(q, cpu, part);
-	part_stat_inc(cpu, part, ios[rw]);
-	part_stat_add(cpu, part, sectors[rw], sectors);
-	part_inc_in_flight(q, part, rw);
+	part_stat_inc(cpu, part, ios[sgrp]);
+	part_stat_add(cpu, part, sectors[sgrp], sectors);
+	part_inc_in_flight(q, part, op_is_write(op));
 
 	part_stat_unlock();
 }
 EXPORT_SYMBOL(generic_start_io_acct);
 
-void generic_end_io_acct(struct request_queue *q, int rw,
+void generic_end_io_acct(struct request_queue *q, int req_op,
 			 struct hd_struct *part, unsigned long start_time)
 {
 	unsigned long duration = jiffies - start_time;
+	const int sgrp = op_stat_group(req_op);
 	int cpu = part_stat_lock();
 
-	part_stat_add(cpu, part, ticks[rw], duration);
+	part_stat_add(cpu, part, ticks[sgrp], duration);
 	part_round_stats(q, cpu, part);
-	part_dec_in_flight(q, part, rw);
+	part_dec_in_flight(q, part, op_is_write(req_op));
 
 	part_stat_unlock();
 }
@@ -1834,6 +1745,9 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
+	if (bio->bi_disk)
+		rq_qos_done_bio(bio->bi_disk->queue, bio);
+
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
 	 * various corner cases will break (like stacking block devices that
@@ -2042,6 +1956,30 @@ EXPORT_SYMBOL(bioset_init_from_src);
 
 #ifdef CONFIG_BLK_CGROUP
 
+#ifdef CONFIG_MEMCG
+/**
+ * bio_associate_blkcg_from_page - associate a bio with the page's blkcg
+ * @bio: target bio
+ * @page: the page to lookup the blkcg from
+ *
+ * Associate @bio with the blkcg from @page's owning memcg.  This works like
+ * every other associate function wrt references.
+ */
+int bio_associate_blkcg_from_page(struct bio *bio, struct page *page)
+{
+	struct cgroup_subsys_state *blkcg_css;
+
+	if (unlikely(bio->bi_css))
+		return -EBUSY;
+	if (!page->mem_cgroup)
+		return 0;
+	blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup,
+				     &io_cgrp_subsys);
+	bio->bi_css = blkcg_css;
+	return 0;
+}
+#endif /* CONFIG_MEMCG */
+
 /**
  * bio_associate_blkcg - associate a bio with the specified blkcg
  * @bio: target bio
@@ -2065,6 +2003,24 @@ int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
 EXPORT_SYMBOL_GPL(bio_associate_blkcg);
 
 /**
+ * bio_associate_blkg - associate a bio with the specified blkg
+ * @bio: target bio
+ * @blkg: the blkg to associate
+ *
+ * Associate @bio with the blkg specified by @blkg.  This is the queue specific
+ * blkcg information associated with the @bio, a reference will be taken on the
+ * @blkg and will be freed when the bio is freed.
+ */
+int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
+{
+	if (unlikely(bio->bi_blkg))
+		return -EBUSY;
+	blkg_get(blkg);
+	bio->bi_blkg = blkg;
+	return 0;
+}
+
+/**
  * bio_disassociate_task - undo bio_associate_current()
  * @bio: target bio
  */
@@ -2078,6 +2034,10 @@ void bio_disassociate_task(struct bio *bio)
 		css_put(bio->bi_css);
 		bio->bi_css = NULL;
 	}
+	if (bio->bi_blkg) {
+		blkg_put(bio->bi_blkg);
+		bio->bi_blkg = NULL;
+	}
 }
 
 /**