Merge tag 'for-5.1/block-20190302' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "Not a huge amount of changes in this round, the biggest one is that we
  finally have Mings multi-page bvec support merged. Apart from that,
  this pull request contains:

   - Small series that avoids quiescing the queue for sysfs changes that
     match what we currently have (Aleksei)

   - Series of bcache fixes (via Coly)

   - Series of lightnvm fixes (via Mathias)

   - NVMe pull request from Christoph. Nothing major, just SPDX/license
     cleanups, RR mp policy (Hannes), and little fixes (Bart,
     Chaitanya).

   - BFQ series (Paolo)

   - Save blk-mq cpu -> hw queue mapping, removing a pointer indirection
     for the fast path (Jianchao)

   - fops->iopoll() added for async IO polling, this is a feature that
     the upcoming io_uring interface will use (Christoph, me)

   - Partition scan loop fixes (Dongli)

   - mtip32xx conversion from managed resource API (Christoph)

   - cdrom registration race fix (Guenter)

   - MD pull from Song, two minor fixes.

   - Various documentation fixes (Marcos)

   - Multi-page bvec feature. This brings a lot of nice improvements
     with it, like more efficient splitting, larger IOs can be supported
     without growing the bvec table size, and so on. (Ming)

   - Various little fixes to core and drivers"

* tag 'for-5.1/block-20190302' of git://git.kernel.dk/linux-block: (117 commits)
  block: fix updating bio's front segment size
  block: Replace function name in string with __func__
  nbd: propagate genlmsg_reply return code
  floppy: remove set but not used variable 'q'
  null_blk: fix checking for REQ_FUA
  block: fix NULL pointer dereference in register_disk
  fs: fix guard_bio_eod to check for real EOD errors
  blk-mq: use HCTX_TYPE_DEFAULT but not 0 to index blk_mq_tag_set->map
  block: optimize bvec iteration in bvec_iter_advance
  block: introduce mp_bvec_for_each_page() for iterating over page
  block: optimize blk_bio_segment_split for single-page bvec
  block: optimize __blk_segment_map_sg() for single-page bvec
  block: introduce bvec_nth_page()
  iomap: wire up the iopoll method
  block: add bio_set_polled() helper
  block: wire up block device iopoll method
  fs: add an iopoll method to struct file_operations
  loop: set GENHD_FL_NO_PART_SCAN after blkdev_reread_part()
  loop: do not print warn message if partition scan is successful
  block: bounce: make sure that bvec table is updated
  ...

114 files changed, 1470 insertions, 1123 deletions

diff --git a/Documentation/block/biovecs.txt b/Documentation/block/biovecs.txt
index 25689584e6e0..ce6eccaf5df7 100644
--- a/Documentation/block/biovecs.txt
+++ b/Documentation/block/biovecs.txt
@@ -117,3 +117,28 @@ Other implications:
    size limitations and the limitations of the underlying devices. Thus
    there's no need to define ->merge_bvec_fn() callbacks for individual block
    drivers.
+
+Usage of helpers:
+=================
+
+* The following helpers whose names have the suffix of "_all" can only be used
+on non-BIO_CLONED bio. They are usually used by filesystem code. Drivers
+shouldn't use them because the bio may have been split before it reached the
+driver.
+
+	bio_for_each_segment_all()
+	bio_first_bvec_all()
+	bio_first_page_all()
+	bio_last_bvec_all()
+
+* The following helpers iterate over single-page segment. The passed 'struct
+bio_vec' will contain a single-page IO vector during the iteration
+
+	bio_for_each_segment()
+	bio_for_each_segment_all()
+
+* The following helpers iterate over multi-page bvec. The passed 'struct
+bio_vec' will contain a multi-page IO vector during the iteration
+
+	bio_for_each_bvec()
+	rq_for_each_bvec()
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 8dc8e9c2913f..761c6fd24a53 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -857,6 +857,7 @@ struct file_operations {
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
+	int (*iopoll)(struct kiocb *kiocb, bool spin);
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
@@ -902,6 +903,8 @@ otherwise noted.
 
   write_iter: possibly asynchronous write with iov_iter as source
 
+  iopoll: called when aio wants to poll for completions on HIPRI iocbs
+
   iterate: called when the VFS needs to read the directory contents
 
   iterate_shared: called when the VFS needs to read the directory contents
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index cd307767a134..4c592496a16a 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -230,11 +230,16 @@ static struct kmem_cache *bfq_pool;
 #define BFQ_MIN_TT		(2 * NSEC_PER_MSEC)
 
 /* hw_tag detection: parallel requests threshold and min samples needed. */
-#define BFQ_HW_QUEUE_THRESHOLD	4
+#define BFQ_HW_QUEUE_THRESHOLD	3
 #define BFQ_HW_QUEUE_SAMPLES	32
 
 #define BFQQ_SEEK_THR		(sector_t)(8 * 100)
 #define BFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
+#define BFQ_RQ_SEEKY(bfqd, last_pos, rq) \
+	(get_sdist(last_pos, rq) >			\
+	 BFQQ_SEEK_THR &&				\
+	 (!blk_queue_nonrot(bfqd->queue) ||		\
+	  blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT))
 #define BFQQ_CLOSE_THR		(sector_t)(8 * 1024)
 #define BFQQ_SEEKY(bfqq)	(hweight32(bfqq->seek_history) > 19)
 
@@ -624,26 +629,6 @@ void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 }
 
 /*
- * Tell whether there are active queues with different weights or
- * active groups.
- */
-static bool bfq_varied_queue_weights_or_active_groups(struct bfq_data *bfqd)
-{
-	/*
-	 * For queue weights to differ, queue_weights_tree must contain
-	 * at least two nodes.
-	 */
-	return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
-		(bfqd->queue_weights_tree.rb_node->rb_left ||
-		 bfqd->queue_weights_tree.rb_node->rb_right)
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-	       ) ||
-		(bfqd->num_groups_with_pending_reqs > 0
-#endif
-	       );
-}
-
-/*
  * The following function returns true if every queue must receive the
  * same share of the throughput (this condition is used when deciding
  * whether idling may be disabled, see the comments in the function
@@ -651,25 +636,48 @@ static bool bfq_varied_queue_weights_or_active_groups(struct bfq_data *bfqd)
  *
  * Such a scenario occurs when:
  * 1) all active queues have the same weight,
- * 2) all active groups at the same level in the groups tree have the same
- *    weight,
+ * 2) all active queues belong to the same I/O-priority class,
  * 3) all active groups at the same level in the groups tree have the same
+ *    weight,
+ * 4) all active groups at the same level in the groups tree have the same
  *    number of children.
  *
  * Unfortunately, keeping the necessary state for evaluating exactly
  * the last two symmetry sub-conditions above would be quite complex
- * and time consuming.  Therefore this function evaluates, instead,
- * only the following stronger two sub-conditions, for which it is
+ * and time consuming. Therefore this function evaluates, instead,
+ * only the following stronger three sub-conditions, for which it is
  * much easier to maintain the needed state:
  * 1) all active queues have the same weight,
- * 2) there are no active groups.
+ * 2) all active queues belong to the same I/O-priority class,
+ * 3) there are no active groups.
  * In particular, the last condition is always true if hierarchical
  * support or the cgroups interface are not enabled, thus no state
  * needs to be maintained in this case.
  */
 static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
 {
-	return !bfq_varied_queue_weights_or_active_groups(bfqd);
+	/*
+	 * For queue weights to differ, queue_weights_tree must contain
+	 * at least two nodes.
+	 */
+	bool varied_queue_weights = !RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
+		(bfqd->queue_weights_tree.rb_node->rb_left ||
+		 bfqd->queue_weights_tree.rb_node->rb_right);
+
+	bool multiple_classes_busy =
+		(bfqd->busy_queues[0] && bfqd->busy_queues[1]) ||
+		(bfqd->busy_queues[0] && bfqd->busy_queues[2]) ||
+		(bfqd->busy_queues[1] && bfqd->busy_queues[2]);