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, 41 insertions, 20 deletions

diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 26f035a0c5b9..557a8a3270a1 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -16,7 +16,7 @@
 #include <linux/sort.h>
 #include <linux/sched/clock.h>
 
-/* Default is -1; we skip past it for struct cached_dev's cache mode */
+/* Default is 0 ("writethrough") */
 static const char * const bch_cache_modes[] = {
 	"writethrough",
 	"writeback",
@@ -25,7 +25,7 @@ static const char * const bch_cache_modes[] = {
 	NULL
 };
 
-/* Default is -1; we skip past it for stop_when_cache_set_failed */
+/* Default is 0 ("auto") */
 static const char * const bch_stop_on_failure_modes[] = {
 	"auto",
 	"always",
@@ -88,6 +88,8 @@ read_attribute(writeback_keys_done);
 read_attribute(writeback_keys_failed);
 read_attribute(io_errors);
 read_attribute(congested);
+read_attribute(cutoff_writeback);
+read_attribute(cutoff_writeback_sync);
 rw_attribute(congested_read_threshold_us);
 rw_attribute(congested_write_threshold_us);
 
@@ -128,6 +130,7 @@ rw_attribute(expensive_debug_checks);
 rw_attribute(cache_replacement_policy);
 rw_attribute(btree_shrinker_disabled);
 rw_attribute(copy_gc_enabled);
+rw_attribute(gc_after_writeback);
 rw_attribute(size);
 
 static ssize_t bch_snprint_string_list(char *buf,
@@ -264,7 +267,8 @@ STORE(__cached_dev)
 	d_strtoul(writeback_running);
 	d_strtoul(writeback_delay);
 
-	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40);
+	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent,
+			    0, bch_cutoff_writeback);
 
 	if (attr == &sysfs_writeback_rate) {
 		ssize_t ret;
@@ -384,8 +388,25 @@ STORE(bch_cached_dev)
 	mutex_lock(&bch_register_lock);
 	size = __cached_dev_store(kobj, attr, buf, size);
 
-	if (attr == &sysfs_writeback_running)
-		bch_writeback_queue(dc);
+	if (attr == &sysfs_writeback_running) {
+		/* dc->writeback_running changed in __cached_dev_store() */
+		if (IS_ERR_OR_NULL(dc->writeback_thread)) {
+			/*
+			 * reject setting it to 1 via sysfs if writeback
+			 * kthread is not created yet.
+			 */
+			if (dc->writeback_running) {
+				dc->writeback_running = false;
+				pr_err("%s: failed to run non-existent writeback thread",
+						dc->disk.disk->disk_name);
+			}
+		} else
+			/*
+			 * writeback kthread will check if dc->writeback_running
+			 * is true or false.
+			 */
+			bch_writeback_queue(dc);
+	}
 
 	if (attr == &sysfs_writeback_percent)
 		if (!test_and_set_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
@@ -668,6 +689,9 @@ SHOW(__bch_cache_set)
 	sysfs_print(congested_write_threshold_us,
 		    c->congested_write_threshold_us);
 
+	sysfs_print(cutoff_writeback, bch_cutoff_writeback);
+	sysfs_print(cutoff_writeback_sync, bch_cutoff_writeback_sync);
+
 	sysfs_print(active_journal_entries,	fifo_used(&c->journal.pin));
 	sysfs_printf(verify,			"%i", c->verify);
 	sysfs_printf(key_merging_disabled,	"%i", c->key_merging_disabled);
@@ -676,6 +700,7 @@ SHOW(__bch_cache_set)
 	sysfs_printf(gc_always_rewrite,		"%i", c->gc_always_rewrite);
 	sysfs_printf(btree_shrinker_disabled,	"%i", c->shrinker_disabled);
 	sysfs_printf(copy_gc_enabled,		"%i", c->copy_gc_enabled);
+	sysfs_printf(gc_after_writeback,	"%i", c->gc_after_writeback);
 	sysfs_printf(io_disable,		"%i",
 		     test_bit(CACHE_SET_IO_DISABLE, &c->flags));
 
@@ -725,21 +750,8 @@ STORE(__bch_cache_set)
 		bch_cache_accounting_clear(&c->accounting);
 	}
 
-	if (attr == &sysfs_trigger_gc) {
-		/*
-		 * Garbage collection thread only works when sectors_to_gc < 0,
-		 * when users write to sysfs entry trigger_gc, most of time
-		 * they want to forcibly triger gargage collection. Here -1 is
-		 * set to c->sectors_to_gc, to make gc_should_run() give a
-		 * chance to permit gc thread to run. "give a chance" means
-		 * before going into gc_should_run(), there is still chance
-		 * that c->sectors_to_gc being set to other positive value. So
-		 * writing sysfs entry trigger_gc won't always make sure gc
-		 * thread takes effect.
-		 */
-		atomic_set(&c->sectors_to_gc, -1);
-		wake_up_gc(c);
-	}
+	if (attr == &sysfs_trigger_gc)
+		force_wake_up_gc(c);
 
 	if (attr == &sysfs_prune_cache) {
 		struct shrink_control sc;
@@ -789,6 +801,12 @@ STORE(__bch_cache_set)
 	sysfs_strtoul(gc_always_rewrite,	c->gc_always_rewrite);
 	sysfs_strtoul(btree_shrinker_disabled,	c->shrinker_disabled);
 	sysfs_strtoul(copy_gc_enabled,		c->copy_gc_enabled);
+	/*
+	 * write gc_after_writeback here may overwrite an already set
+	 * BCH_DO_AUTO_GC, it doesn't matter because this flag will be
+	 * set in next chance.
+	 */
+	sysfs_strtoul_clamp(gc_after_writeback, c->gc_after_writeback, 0, 1);
 
 	return size;
 }
@@ -869,7 +887,10 @@ static struct attribute *bch_cache_set_internal_files[] = {
 	&sysfs_gc_always_rewrite,
 	&sysfs_btree_shrinker_disabled,
 	&sysfs_copy_gc_enabled,
+	&sysfs_gc_after_writeback,
 	&sysfs_io_disable,
+	&sysfs_cutoff_writeback,
+	&sysfs_cutoff_writeback_sync,
 	NULL
 };
 KTYPE(bch_cache_set_internal);