Merge tag 'for-5.3/block-20190708' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main block updates for 5.3. Nothing earth shattering or
  major in here, just fixes, additions, and improvements all over the
  map. This contains:

   - Series of documentation fixes (Bart)

   - Optimization of the blk-mq ctx get/put (Bart)

   - null_blk removal race condition fix (Bob)

   - req/bio_op() cleanups (Chaitanya)

   - Series cleaning up the segment accounting, and request/bio mapping
     (Christoph)

   - Series cleaning up the page getting/putting for bios (Christoph)

   - block cgroup cleanups and moving it to where it is used (Christoph)

   - block cgroup fixes (Tejun)

   - Series of fixes and improvements to bcache, most notably a write
     deadlock fix (Coly)

   - blk-iolatency STS_AGAIN and accounting fixes (Dennis)

   - Series of improvements and fixes to BFQ (Douglas, Paolo)

   - debugfs_create() return value check removal for drbd (Greg)

   - Use struct_size(), where appropriate (Gustavo)

   - Two lighnvm fixes (Heiner, Geert)

   - MD fixes, including a read balance and corruption fix (Guoqing,
     Marcos, Xiao, Yufen)

   - block opal shadow mbr additions (Jonas, Revanth)

   - sbitmap compare-and-exhange improvemnts (Pavel)

   - Fix for potential bio->bi_size overflow (Ming)

   - NVMe pull requests:
       - improved PCIe suspent support (Keith Busch)
       - error injection support for the admin queue (Akinobu Mita)
       - Fibre Channel discovery improvements (James Smart)
       - tracing improvements including nvmetc tracing support (Minwoo Im)
       - misc fixes and cleanups (Anton Eidelman, Minwoo Im, Chaitanya
         Kulkarni)"

   - Various little fixes and improvements to drivers and core"

* tag 'for-5.3/block-20190708' of git://git.kernel.dk/linux-block: (153 commits)
  blk-iolatency: fix STS_AGAIN handling
  block: nr_phys_segments needs to be zero for REQ_OP_WRITE_ZEROES
  blk-mq: simplify blk_mq_make_request()
  blk-mq: remove blk_mq_put_ctx()
  sbitmap: Replace cmpxchg with xchg
  block: fix .bi_size overflow
  block: sed-opal: check size of shadow mbr
  block: sed-opal: ioctl for writing to shadow mbr
  block: sed-opal: add ioctl for done-mark of shadow mbr
  block: never take page references for ITER_BVEC
  direct-io: use bio_release_pages in dio_bio_complete
  block_dev: use bio_release_pages in bio_unmap_user
  block_dev: use bio_release_pages in blkdev_bio_end_io
  iomap: use bio_release_pages in iomap_dio_bio_end_io
  block: use bio_release_pages in bio_map_user_iov
  block: use bio_release_pages in bio_unmap_user
  block: optionally mark pages dirty in bio_release_pages
  block: move the BIO_NO_PAGE_REF check into bio_release_pages
  block: skd_main.c: Remove call to memset after dma_alloc_coherent
  block: mtip32xx: Remove call to memset after dma_alloc_coherent
  ...

1 files changed, 38 insertions, 10 deletions

diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index c2faa77824f8..e80adf822bbe 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -357,6 +357,24 @@ struct bfq_queue {
 
 	/* max service rate measured so far */
 	u32 max_service_rate;
+
+	/*
+	 * Pointer to the waker queue for this queue, i.e., to the
+	 * queue Q such that this queue happens to get new I/O right
+	 * after some I/O request of Q is completed. For details, see
+	 * the comments on the choice of the queue for injection in
+	 * bfq_select_queue().
+	 */
+	struct bfq_queue *waker_bfqq;
+	/* node for woken_list, see below */
+	struct hlist_node woken_list_node;
+	/*
+	 * Head of the list of the woken queues for this queue, i.e.,
+	 * of the list of the queues for which this queue is a waker
+	 * queue. This list is used to reset the waker_bfqq pointer in
+	 * the woken queues when this queue exits.
+	 */
+	struct hlist_head woken_list;
 };
 
 /**
@@ -533,6 +551,9 @@ struct bfq_data {
 	/* time of last request completion (ns) */
 	u64 last_completion;
 
+	/* bfqq owning the last completed rq */
+	struct bfq_queue *last_completed_rq_bfqq;
+
 	/* time of last transition from empty to non-empty (ns) */
 	u64 last_empty_occupied_ns;
 
@@ -743,7 +764,8 @@ enum bfqq_state_flags {
 				 * update
 				 */
 	BFQQF_coop,		/* bfqq is shared */
-	BFQQF_split_coop	/* shared bfqq will be split */
+	BFQQF_split_coop,	/* shared bfqq will be split */
+	BFQQF_has_waker		/* bfqq has a waker queue */
 };
 
 #define BFQ_BFQQ_FNS(name)						\
@@ -763,6 +785,7 @@ BFQ_BFQQ_FNS(in_large_burst);
 BFQ_BFQQ_FNS(coop);
 BFQ_BFQQ_FNS(split_coop);
 BFQ_BFQQ_FNS(softrt_update);
+BFQ_BFQQ_FNS(has_waker);
 #undef BFQ_BFQQ_FNS
 
 /* Expiration reasons. */
@@ -777,8 +800,13 @@ enum bfqq_expiration {
 	BFQQE_PREEMPTED		/* preemption in progress */
 };
 
+struct bfq_stat {
+	struct percpu_counter		cpu_cnt;
+	atomic64_t			aux_cnt;
+};
+
 struct bfqg_stats {
-#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
 	/* number of ios merged */
 	struct blkg_rwstat		merged;
 	/* total time spent on device in ns, may not be accurate w/ queueing */
@@ -788,25 +816,25 @@ struct bfqg_stats {
 	/* number of IOs queued up */
 	struct blkg_rwstat		queued;
 	/* total disk time and nr sectors dispatched by this group */
-	struct blkg_stat		time;
+	struct bfq_stat		time;
 	/* sum of number of ios queued across all samples */
-	struct blkg_stat		avg_queue_size_sum;
+	struct bfq_stat		avg_queue_size_sum;
 	/* count of samples taken for average */
-	struct blkg_stat		avg_queue_size_samples;
+	struct bfq_stat		avg_queue_size_samples;
 	/* how many times this group has been removed from service tree */
-	struct blkg_stat		dequeue;
+	struct bfq_stat		dequeue;
 	/* total time spent waiting for it to be assigned a timeslice. */
-	struct blkg_stat		group_wait_time;
+	struct bfq_stat		group_wait_time;
 	/* time spent idling for this blkcg_gq */
-	struct blkg_stat		idle_time;
+	struct bfq_stat		idle_time;
 	/* total time with empty current active q with other requests queued */
-	struct blkg_stat		empty_time;
+	struct bfq_stat		empty_time;
 	/* fields after this shouldn't be cleared on stat reset */
 	u64				start_group_wait_time;
 	u64				start_idle_time;
 	u64				start_empty_time;
 	uint16_t			flags;
-#endif	/* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
+#endif /* CONFIG_BFQ_CGROUP_DEBUG */
 };
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED