Merge tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block/storage for 4.21.

  Larger than usual, it was a busy round with lots of goodies queued up.
  Most notable is the removal of the old IO stack, which has been a long
  time coming. No new features for a while, everything coming in this
  week has all been fixes for things that were previously merged.

  This contains:

   - Use atomic counters instead of semaphores for mtip32xx (Arnd)

   - Cleanup of the mtip32xx request setup (Christoph)

   - Fix for circular locking dependency in loop (Jan, Tetsuo)

   - bcache (Coly, Guoju, Shenghui)
      * Optimizations for writeback caching
      * Various fixes and improvements

   - nvme (Chaitanya, Christoph, Sagi, Jay, me, Keith)
      * host and target support for NVMe over TCP
      * Error log page support
      * Support for separate read/write/poll queues
      * Much improved polling
      * discard OOM fallback
      * Tracepoint improvements

   - lightnvm (Hans, Hua, Igor, Matias, Javier)
      * Igor added packed metadata to pblk. Now drives without metadata
        per LBA can be used as well.
      * Fix from Geert on uninitialized value on chunk metadata reads.
      * Fixes from Hans and Javier to pblk recovery and write path.
      * Fix from Hua Su to fix a race condition in the pblk recovery
        code.
      * Scan optimization added to pblk recovery from Zhoujie.
      * Small geometry cleanup from me.

   - Conversion of the last few drivers that used the legacy path to
     blk-mq (me)

   - Removal of legacy IO path in SCSI (me, Christoph)

   - Removal of legacy IO stack and schedulers (me)

   - Support for much better polling, now without interrupts at all.
     blk-mq adds support for multiple queue maps, which enables us to
     have a map per type. This in turn enables nvme to have separate
     completion queues for polling, which can then be interrupt-less.
     Also means we're ready for async polled IO, which is hopefully
     coming in the next release.

   - Killing of (now) unused block exports (Christoph)

   - Unification of the blk-rq-qos and blk-wbt wait handling (Josef)

   - Support for zoned testing with null_blk (Masato)

   - sx8 conversion to per-host tag sets (Christoph)

   - IO priority improvements (Damien)

   - mq-deadline zoned fix (Damien)

   - Ref count blkcg series (Dennis)

   - Lots of blk-mq improvements and speedups (me)

   - sbitmap scalability improvements (me)

   - Make core inflight IO accounting per-cpu (Mikulas)

   - Export timeout setting in sysfs (Weiping)

   - Cleanup the direct issue path (Jianchao)

   - Export blk-wbt internals in block debugfs for easier debugging
     (Ming)

   - Lots of other fixes and improvements"

* tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block: (364 commits)
  kyber: use sbitmap add_wait_queue/list_del wait helpers
  sbitmap: add helpers for add/del wait queue handling
  block: save irq state in blkg_lookup_create()
  dm: don't reuse bio for flushes
  nvme-pci: trace SQ status on completions
  nvme-rdma: implement polling queue map
  nvme-fabrics: allow user to pass in nr_poll_queues
  nvme-fabrics: allow nvmf_connect_io_queue to poll
  nvme-core: optionally poll sync commands
  block: make request_to_qc_t public
  nvme-tcp: fix spelling mistake "attepmpt" -> "attempt"
  nvme-tcp: fix endianess annotations
  nvmet-tcp: fix endianess annotations
  nvme-pci: refactor nvme_poll_irqdisable to make sparse happy
  nvme-pci: only set nr_maps to 2 if poll queues are supported
  nvmet: use a macro for default error location
  nvmet: fix comparison of a u16 with -1
  blk-mq: enable IO poll if .nr_queues of type poll > 0
  blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()
  blk-mq: skip zero-queue maps in blk_mq_map_swqueue
  ...

1 files changed, 79 insertions, 10 deletions

diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 804a50983ec5..14d558146aea 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -30,14 +30,24 @@ struct seq_file;
  */
 struct sbitmap_word {
 	/**
-	 * @word: The bitmap word itself.
+	 * @depth: Number of bits being used in @word/@cleared
 	 */
-	unsigned long word;
+	unsigned long depth;
 
 	/**
-	 * @depth: Number of bits being used in @word.
+	 * @word: word holding free bits
 	 */
-	unsigned long depth;
+	unsigned long word ____cacheline_aligned_in_smp;
+
+	/**
+	 * @cleared: word holding cleared bits
+	 */
+	unsigned long cleared ____cacheline_aligned_in_smp;
+
+	/**
+	 * @swap_lock: Held while swapping word <-> cleared
+	 */
+	spinlock_t swap_lock;
 } ____cacheline_aligned_in_smp;
 
 /**
@@ -125,6 +135,11 @@ struct sbitmap_queue {
 	 */
 	struct sbq_wait_state *ws;
 
+	/*
+	 * @ws_active: count of currently active ws waitqueues
+	 */
+	atomic_t ws_active;
+
 	/**
 	 * @round_robin: Allocate bits in strict round-robin order.
 	 */
@@ -250,12 +265,14 @@ static inline void __sbitmap_for_each_set(struct sbitmap *sb,
 	nr = SB_NR_TO_BIT(sb, start);
 
 	while (scanned < sb->depth) {
-		struct sbitmap_word *word = &sb->map[index];
-		unsigned int depth = min_t(unsigned int, word->depth - nr,
+		unsigned long word;
+		unsigned int depth = min_t(unsigned int,
+					   sb->map[index].depth - nr,
 					   sb->depth - scanned);
 
 		scanned += depth;
-		if (!word->word)
+		word = sb->map[index].word & ~sb->map[index].cleared;
+		if (!word)
 			goto next;
 
 		/*
@@ -265,7 +282,7 @@ static inline void __sbitmap_for_each_set(struct sbitmap *sb,
 		 */
 		depth += nr;
 		while (1) {
-			nr = find_next_bit(&word->word, depth, nr);
+			nr = find_next_bit(&word, depth, nr);
 			if (nr >= depth)
 				break;
 			if (!fn(sb, (index << sb->shift) + nr, data))
@@ -310,6 +327,19 @@ static inline void sbitmap_clear_bit(struct sbitmap *sb, unsigned int bitnr)
 	clear_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
 }
 
+/*
+ * This one is special, since it doesn't actually clear the bit, rather it
+ * sets the corresponding bit in the ->cleared mask instead. Paired with
+ * the caller doing sbitmap_batch_clear() if a given index is full, which
+ * will clear the previously freed entries in the corresponding ->word.
+ */
+static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int bitnr)
+{
+	unsigned long *addr = &sb->map[SB_NR_TO_INDEX(sb, bitnr)].cleared;
+
+	set_bit(SB_NR_TO_BIT(sb, bitnr), addr);
+}
+
 static inline void sbitmap_clear_bit_unlock(struct sbitmap *sb,
 					    unsigned int bitnr)
 {
@@ -321,8 +351,6 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
 	return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
 }
 
-unsigned int sbitmap_weight(const struct sbitmap *sb);
-
 /**
  * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file.
  * @sb: Bitmap to show.
@@ -531,4 +559,45 @@ void sbitmap_queue_wake_up(struct sbitmap_queue *sbq);
  */
 void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m);
 
+struct sbq_wait {
+	struct sbitmap_queue *sbq;	/* if set, sbq_wait is accounted */
+	struct wait_queue_entry wait;
+};
+
+#define DEFINE_SBQ_WAIT(name)							\
+	struct sbq_wait name = {						\
+		.sbq = NULL,							\
+		.wait = {							\
+			.private	= current,				\
+			.func		= autoremove_wake_function,		\
+			.entry		= LIST_HEAD_INIT((name).wait.entry),	\
+		}								\
+	}
+
+/*
+ * Wrapper around prepare_to_wait_exclusive(), which maintains some extra
+ * internal state.
+ */
+void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq,
+				struct sbq_wait_state *ws,
+				struct sbq_wait *sbq_wait, int state);
+
+/*
+ * Must be paired with sbitmap_prepare_to_wait().
+ */
+void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws,
+				struct sbq_wait *sbq_wait);
+
+/*
+ * Wrapper around add_wait_queue(), which maintains some extra internal state
+ */
+void sbitmap_add_wait_queue(struct sbitmap_queue *sbq,
+			    struct sbq_wait_state *ws,
+			    struct sbq_wait *sbq_wait);
+
+/*
+ * Must be paired with sbitmap_add_wait_queue()
+ */
+void sbitmap_del_wait_queue(struct sbq_wait *sbq_wait);
+
 #endif /* __LINUX_SCALE_BITMAP_H */