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, 29 insertions, 1 deletions

diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 08c3a9f9676c..73f0efac2b9f 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -17,6 +17,15 @@
 #include <linux/sched/clock.h>
 #include <trace/events/bcache.h>
 
+static void update_gc_after_writeback(struct cache_set *c)
+{
+	if (c->gc_after_writeback != (BCH_ENABLE_AUTO_GC) ||
+	    c->gc_stats.in_use < BCH_AUTO_GC_DIRTY_THRESHOLD)
+		return;
+
+	c->gc_after_writeback |= BCH_DO_AUTO_GC;
+}
+
 /* Rate limiting */
 static uint64_t __calc_target_rate(struct cached_dev *dc)
 {
@@ -191,6 +200,7 @@ static void update_writeback_rate(struct work_struct *work)
 		if (!set_at_max_writeback_rate(c, dc)) {
 			down_read(&dc->writeback_lock);
 			__update_writeback_rate(dc);
+			update_gc_after_writeback(c);
 			up_read(&dc->writeback_lock);
 		}
 	}
@@ -689,6 +699,23 @@ static int bch_writeback_thread(void *arg)
 				up_write(&dc->writeback_lock);
 				break;
 			}
+
+			/*
+			 * When dirty data rate is high (e.g. 50%+), there might
+			 * be heavy buckets fragmentation after writeback
+			 * finished, which hurts following write performance.
+			 * If users really care about write performance they
+			 * may set BCH_ENABLE_AUTO_GC via sysfs, then when
+			 * BCH_DO_AUTO_GC is set, garbage collection thread
+			 * will be wake up here. After moving gc, the shrunk
+			 * btree and discarded free buckets SSD space may be
+			 * helpful for following write requests.
+			 */
+			if (c->gc_after_writeback ==
+			    (BCH_ENABLE_AUTO_GC|BCH_DO_AUTO_GC)) {
+				c->gc_after_writeback &= ~BCH_DO_AUTO_GC;
+				force_wake_up_gc(c);
+			}
 		}
 
 		up_write(&dc->writeback_lock);
@@ -777,7 +804,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 	bch_keybuf_init(&dc->writeback_keys);
 
 	dc->writeback_metadata		= true;
-	dc->writeback_running		= true;
+	dc->writeback_running		= false;
 	dc->writeback_percent		= 10;
 	dc->writeback_delay		= 30;
 	atomic_long_set(&dc->writeback_rate.rate, 1024);
@@ -805,6 +832,7 @@ int bch_cached_dev_writeback_start(struct cached_dev *dc)
 		cached_dev_put(dc);
 		return PTR_ERR(dc->writeback_thread);
 	}
+	dc->writeback_running = true;
 
 	WARN_ON(test_and_set_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags));
 	schedule_delayed_work(&dc->writeback_rate_update,