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, 143 insertions, 3 deletions

diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 6c666fd7de3c..34aec30e06c7 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -35,6 +35,7 @@ enum blkg_rwstat_type {
 	BLKG_RWSTAT_WRITE,
 	BLKG_RWSTAT_SYNC,
 	BLKG_RWSTAT_ASYNC,
+	BLKG_RWSTAT_DISCARD,
 
 	BLKG_RWSTAT_NR,
 	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
@@ -136,6 +137,12 @@ struct blkcg_gq {
 	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
 
 	struct rcu_head			rcu_head;
+
+	atomic_t			use_delay;
+	atomic64_t			delay_nsec;
+	atomic64_t			delay_start;
+	u64				last_delay;
+	int				last_use;
 };
 
 typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
@@ -148,6 +155,8 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
+typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf,
+				      size_t size);
 
 struct blkcg_policy {
 	int				plid;
@@ -167,6 +176,7 @@ struct blkcg_policy {
 	blkcg_pol_offline_pd_fn		*pd_offline_fn;
 	blkcg_pol_free_pd_fn		*pd_free_fn;
 	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;
+	blkcg_pol_stat_pd_fn		*pd_stat_fn;
 };
 
 extern struct blkcg blkcg_root;
@@ -238,6 +248,42 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
 	return css_to_blkcg(task_css(current, io_cgrp_id));
 }
 
+static inline bool blk_cgroup_congested(void)
+{
+	struct cgroup_subsys_state *css;
+	bool ret = false;
+
+	rcu_read_lock();
+	css = kthread_blkcg();
+	if (!css)
+		css = task_css(current, io_cgrp_id);
+	while (css) {
+		if (atomic_read(&css->cgroup->congestion_count)) {
+			ret = true;
+			break;
+		}
+		css = css->parent;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg
+ * @return: true if this bio needs to be submitted with the root blkg context.
+ *
+ * In order to avoid priority inversions we sometimes need to issue a bio as if
+ * it were attached to the root blkg, and then backcharge to the actual owning
+ * blkg.  The idea is we do bio_blkcg() to look up the actual context for the
+ * bio and attach the appropriate blkg to the bio.  Then we call this helper and
+ * if it is true run with the root blkg for that queue and then do any
+ * backcharging to the originating cgroup once the io is complete.
+ */
+static inline bool bio_issue_as_root_blkg(struct bio *bio)
+{
+	return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0;
+}
+
 /**
  * blkcg_parent - get the parent of a blkcg
  * @blkcg: blkcg of interest
@@ -296,6 +342,17 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 }
 
 /**
+ * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair
+ * @q: request_queue of interest
+ *
+ * Lookup blkg for @q at the root level. See also blkg_lookup().
+ */
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{
+	return q->root_blkg;
+}
+
+/**
  * blkg_to_pdata - get policy private data
  * @blkg: blkg of interest
  * @pol: policy of interest
@@ -355,6 +412,21 @@ static inline void blkg_get(struct blkcg_gq *blkg)
 	atomic_inc(&blkg->refcnt);
 }
 
+/**
+ * blkg_try_get - try and get a blkg reference
+ * @blkg: blkg to get
+ *
+ * This is for use when doing an RCU lookup of the blkg.  We may be in the midst
+ * of freeing this blkg, so we can only use it if the refcnt is not zero.
+ */
+static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg)
+{
+	if (atomic_inc_not_zero(&blkg->refcnt))
+		return blkg;
+	return NULL;
+}
+
+
 void __blkg_release_rcu(struct rcu_head *rcu);
 
 /**
@@ -589,7 +661,9 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
 {
 	struct percpu_counter *cnt;
 
-	if (op_is_write(op))
+	if (op_is_discard(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
+	else if (op_is_write(op))
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
@@ -706,8 +780,14 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 
 	if (!throtl) {
 		blkg = blkg ?: q->root_blkg;
-		blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
-				bio->bi_iter.bi_size);
+		/*
+		 * If the bio is flagged with BIO_QUEUE_ENTERED it means this
+		 * is a split bio and we would have already accounted for the
+		 * size of the bio.
+		 */
+		if (!bio_flagged(bio, BIO_QUEUE_ENTERED))
+			blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
+					bio->bi_iter.bi_size);
 		blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
 	}
 
@@ -715,6 +795,59 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 	return !throtl;
 }
 
+static inline void blkcg_use_delay(struct blkcg_gq *blkg)
+{
+	if (atomic_add_return(1, &blkg->use_delay) == 1)
+		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+}
+
+static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+
+	if (old == 0)
+		return 0;
+
+	/*
+	 * We do this song and dance because we can race with somebody else
+	 * adding or removing delay.  If we just did an atomic_dec we'd end up
+	 * negative and we'd already be in trouble.  We need to subtract 1 and
+	 * then check to see if we were the last delay so we can drop the
+	 * congestion count on the cgroup.
+	 */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1);
+		if (cur == old)
+			break;
+		old = cur;
+	}
+
+	if (old == 0)
+		return 0;
+	if (old == 1)
+		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+	return 1;
+}
+
+static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+	if (!old)
+		return;
+	/* We only want 1 person clearing the congestion count for this blkg. */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, 0);
+		if (cur == old) {
+			atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+			break;
+		}
+		old = cur;
+	}
+}
+
+void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
+void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
+void blkcg_maybe_throttle_current(void);
 #else	/* CONFIG_BLK_CGROUP */
 
 struct blkcg {
@@ -734,9 +867,16 @@ struct blkcg_policy {
 
 #define blkcg_root_css	((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
 
+static inline void blkcg_maybe_throttle_current(void) { }
+static inline bool blk_cgroup_congested(void) { return false; }
+
 #ifdef CONFIG_BLOCK
 
+static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
+
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{ return NULL; }
 static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
 static inline void blkcg_drain_queue(struct request_queue *q) { }
 static inline void blkcg_exit_queue(struct request_queue *q) { }