bcache: A block layer cache

Does writethrough and writeback caching, handles unclean shutdown, and
has a bunch of other nifty features motivated by real world usage.

See the wiki at http://bcache.evilpiepirate.org for more.
Signed-off-by: NKent Overstreet <koverstreet@google.com>

Documentation/ABI/testing/sysfs-block-bcache

+What:		/sys/block/<disk>/bcache/unregister
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		A write to this file causes the backing device or cache to be
+		unregistered. If a backing device had dirty data in the cache,
+		writeback mode is automatically disabled and all dirty data is
+		flushed before the device is unregistered. Caches unregister
+		all associated backing devices before unregistering themselves.
+
+What:		/sys/block/<disk>/bcache/clear_stats
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		Writing to this file resets all the statistics for the device.
+
+What:		/sys/block/<disk>/bcache/cache
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a backing device that has cache, a symlink to
+		the bcache/ dir of that cache.
+
+What:		/sys/block/<disk>/bcache/cache_hits
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: integer number of full cache hits,
+		counted per bio. A partial cache hit counts as a miss.
+
+What:		/sys/block/<disk>/bcache/cache_misses
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: integer number of cache misses.
+
+What:		/sys/block/<disk>/bcache/cache_hit_ratio
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: cache hits as a percentage.
+
+What:		/sys/block/<disk>/bcache/sequential_cutoff
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: Threshold past which sequential IO will
+		skip the cache. Read and written as bytes in human readable
+		units (i.e. echo 10M > sequntial_cutoff).
+
+What:		/sys/block/<disk>/bcache/bypassed
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		Sum of all reads and writes that have bypassed the cache (due
+		to the sequential cutoff).  Expressed as bytes in human
+		readable units.
+
+What:		/sys/block/<disk>/bcache/writeback
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: When on, writeback caching is enabled and
+		writes will be buffered in the cache. When off, caching is in
+		writethrough mode; reads and writes will be added to the
+		cache but no write buffering will take place.
+
+What:		/sys/block/<disk>/bcache/writeback_running
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: when off, dirty data will not be written
+		from the cache to the backing device. The cache will still be
+		used to buffer writes until it is mostly full, at which point
+		writes transparently revert to writethrough mode. Intended only
+		for benchmarking/testing.
+
+What:		/sys/block/<disk>/bcache/writeback_delay
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: In writeback mode, when dirty data is
+		written to the cache and the cache held no dirty data for that
+		backing device, writeback from cache to backing device starts
+		after this delay, expressed as an integer number of seconds.
+
+What:		/sys/block/<disk>/bcache/writeback_percent
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: If nonzero, writeback from cache to
+		backing device only takes place when more than this percentage
+		of the cache is used, allowing more write coalescing to take
+		place and reducing total number of writes sent to the backing
+		device. Integer between 0 and 40.
+
+What:		/sys/block/<disk>/bcache/synchronous
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, a boolean that allows synchronous mode to be
+		switched on and off. In synchronous mode all writes are ordered
+		such that the cache can reliably recover from unclean shutdown;
+		if disabled bcache will not generally wait for writes to
+		complete but if the cache is not shut down cleanly all data
+		will be discarded from the cache. Should not be turned off with
+		writeback caching enabled.
+
+What:		/sys/block/<disk>/bcache/discard
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, a boolean allowing discard/TRIM to be turned off
+		or back on if the device supports it.
+
+What:		/sys/block/<disk>/bcache/bucket_size
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, bucket size in human readable units, as set at
+		cache creation time; should match the erase block size of the
+		SSD for optimal performance.
+
+What:		/sys/block/<disk>/bcache/nbuckets
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, the number of usable buckets.
+
+What:		/sys/block/<disk>/bcache/tree_depth
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, height of the btree excluding leaf nodes (i.e. a
+		one node tree will have a depth of 0).
+
+What:		/sys/block/<disk>/bcache/btree_cache_size
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		Number of btree buckets/nodes that are currently cached in
+		memory; cache dynamically grows and shrinks in response to
+		memory pressure from the rest of the system.
+
+What:		/sys/block/<disk>/bcache/written
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, total amount of data in human readable units
+		written to the cache, excluding all metadata.
+
+What:		/sys/block/<disk>/bcache/btree_written
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, sum of all btree writes in human readable units.

Documentation/bcache.txt

+Say you've got a big slow raid 6, and an X-25E or three. Wouldn't it be
+nice if you could use them as cache... Hence bcache.
+
+Wiki and git repositories are at:
+  http://bcache.evilpiepirate.org
+  http://evilpiepirate.org/git/linux-bcache.git
+  http://evilpiepirate.org/git/bcache-tools.git
+
+It's designed around the performance characteristics of SSDs - it only allocates
+in erase block sized buckets, and it uses a hybrid btree/log to track cached
+extants (which can be anywhere from a single sector to the bucket size). It's
+designed to avoid random writes at all costs; it fills up an erase block
+sequentially, then issues a discard before reusing it.
+
+Both writethrough and writeback caching are supported. Writeback defaults to
+off, but can be switched on and off arbitrarily at runtime. Bcache goes to
+great lengths to protect your data - it reliably handles unclean shutdown. (It
+doesn't even have a notion of a clean shutdown; bcache simply doesn't return
+writes as completed until they're on stable storage).
+
+Writeback caching can use most of the cache for buffering writes - writing
+dirty data to the backing device is always done sequentially, scanning from the
+start to the end of the index.
+
+Since random IO is what SSDs excel at, there generally won't be much benefit
+to caching large sequential IO. Bcache detects sequential IO and skips it;
+it also keeps a rolling average of the IO sizes per task, and as long as the
+average is above the cutoff it will skip all IO from that task - instead of
+caching the first 512k after every seek. Backups and large file copies should
+thus entirely bypass the cache.
+
+In the event of a data IO error on the flash it will try to recover by reading
+from disk or invalidating cache entries.  For unrecoverable errors (meta data
+or dirty data), caching is automatically disabled; if dirty data was present
+in the cache it first disables writeback caching and waits for all dirty data
+to be flushed.
+
+Getting started:
+You'll need make-bcache from the bcache-tools repository. Both the cache device
+and backing device must be formatted before use.
+  make-bcache -B /dev/sdb
+  make-bcache -C /dev/sdc
+
+make-bcache has the ability to format multiple devices at the same time - if
+you format your backing devices and cache device at the same time, you won't
+have to manually attach:
+  make-bcache -B /dev/sda /dev/sdb -C /dev/sdc
+
+To make bcache devices known to the kernel, echo them to /sys/fs/bcache/register:
+
+  echo /dev/sdb > /sys/fs/bcache/register
+  echo /dev/sdc > /sys/fs/bcache/register
+
+To register your bcache devices automatically, you could add something like
+this to an init script:
+
+  echo /dev/sd* > /sys/fs/bcache/register_quiet
+
+It'll look for bcache superblocks and ignore everything that doesn't have one.
+
+Registering the backing device makes the bcache show up in /dev; you can now
+format it and use it as normal. But the first time using a new bcache device,
+it'll be running in passthrough mode until you attach it to a cache. See the
+section on attaching.
+
+The devices show up at /dev/bcacheN, and can be controlled via sysfs from
+/sys/block/bcacheN/bcache:
+
+  mkfs.ext4 /dev/bcache0
+  mount /dev/bcache0 /mnt
+
+Cache devices are managed as sets; multiple caches per set isn't supported yet
+but will allow for mirroring of metadata and dirty data in the future. Your new
+cache set shows up as /sys/fs/bcache/<UUID>
+
+ATTACHING:
+
+After your cache device and backing device are registered, the backing device
+must be attached to your cache set to enable caching. Attaching a backing
+device to a cache set is done thusly, with the UUID of the cache set in
+/sys/fs/bcache:
+
+  echo <UUID> > /sys/block/bcache0/bcache/attach
+
+This only has to be done once. The next time you reboot, just reregister all
+your bcache devices. If a backing device has data in a cache somewhere, the
+/dev/bcache# device won't be created until the cache shows up - particularly
+important if you have writeback caching turned on.
+
+If you're booting up and your cache device is gone and never coming back, you
+can force run the backing device:
+
+  echo 1 > /sys/block/sdb/bcache/running
+
+(You need to use /sys/block/sdb (or whatever your backing device is called), not
+/sys/block/bcache0, because bcache0 doesn't exist yet. If you're using a
+partition, the bcache directory would be at /sys/block/sdb/sdb2/bcache)
+
+The backing device will still use that cache set if it shows up in the future,
+but all the cached data will be invalidated. If there was dirty data in the
+cache, don't expect the filesystem to be recoverable - you will have massive
+filesystem corruption, though ext4's fsck does work miracles.
+
+SYSFS - BACKING DEVICE:
+
+attach
+  Echo the UUID of a cache set to this file to enable caching.
+
+cache_mode
+  Can be one of either writethrough, writeback, writearound or none.
+
+clear_stats
+  Writing to this file resets the running total stats (not the day/hour/5 minute
+  decaying versions).
+
+detach
+  Write to this file to detach from a cache set. If there is dirty data in the
+  cache, it will be flushed first.
+
+dirty_data
+  Amount of dirty data for this backing device in the cache. Continuously
+  updated unlike the cache set's version, but may be slightly off.
+
+label
+  Name of underlying device.
+
+readahead
+  Size of readahead that should be performed.  Defaults to 0.  If set to e.g.
+  1M, it will round cache miss reads up to that size, but without overlapping
+  existing cache entries.
+
+running
+  1 if bcache is running (i.e. whether the /dev/bcache device exists, whether
+  it's in passthrough mode or caching).
+
+sequential_cutoff
+  A sequential IO will bypass the cache once it passes this threshhold; the
+  most recent 128 IOs are tracked so sequential IO can be detected even when
+  it isn't all done at once.
+
+sequential_merge
+  If non zero, bcache keeps a list of the last 128 requests submitted to compare
+  against all new requests to determine which new requests are sequential
+  continuations of previous requests for the purpose of determining sequential
+  cutoff. This is necessary if the sequential cutoff value is greater than the
+  maximum acceptable sequential size for any single request. 
+
+state
+  The backing device can be in one of four different states:
+
+  no cache: Has never been attached to a cache set.
+
+  clean: Part of a cache set, and there is no cached dirty data.
+
+  dirty: Part of a cache set, and there is cached dirty data.
+
+  inconsistent: The backing device was forcibly run by the user when there was
+  dirty data cached but the cache set was unavailable; whatever data was on the
+  backing device has likely been corrupted.
+
+stop
+  Write to this file to shut down the bcache device and close the backing
+  device.
+
+writeback_delay
+  When dirty data is written to the cache and it previously did not contain
+  any, waits some number of seconds before initiating writeback. Defaults to
+  30.
+
+writeback_percent
+  If nonzero, bcache tries to keep around this percentage of the cache dirty by
+  throttling background writeback and using a PD controller to smoothly adjust
+  the rate.
+
+writeback_rate
+  Rate in sectors per second - if writeback_percent is nonzero, background
+  writeback is throttled to this rate. Continuously adjusted by bcache but may
+  also be set by the user.
+
+writeback_running
+  If off, writeback of dirty data will not take place at all. Dirty data will
+  still be added to the cache until it is mostly full; only meant for
+  benchmarking. Defaults to on.
+
+SYSFS - BACKING DEVICE STATS:
+
+There are directories with these numbers for a running total, as well as
+versions that decay over the past day, hour and 5 minutes; they're also
+aggregated in the cache set directory as well.
+
+bypassed
+  Amount of IO (both reads and writes) that has bypassed the cache
+
+cache_hits
+cache_misses
+cache_hit_ratio
+  Hits and misses are counted per individual IO as bcache sees them; a
+  partial hit is counted as a miss.
+
+cache_bypass_hits
+cache_bypass_misses
+  Hits and misses for IO that is intended to skip the cache are still counted,
+  but broken out here.
+
+cache_miss_collisions
+  Counts instances where data was going to be inserted into the cache from a
+  cache miss, but raced with a write and data was already present (usually 0
+  since the synchronization for cache misses was rewritten)
+
+cache_readaheads
+  Count of times readahead occured.
+
+SYSFS - CACHE SET:
+
+average_key_size
+  Average data per key in the btree.
+
+bdev<0..n>
+  Symlink to each of the attached backing devices.
+
+block_size
+  Block size of the cache devices.
+
+btree_cache_size
+  Amount of memory currently used by the btree cache
+
+bucket_size
+  Size of buckets
+
+cache<0..n>
+  Symlink to each of the cache devices comprising this cache set. 
+
+cache_available_percent
+  Percentage of cache device free.
+
+clear_stats
+  Clears the statistics associated with this cache
+
+dirty_data
+  Amount of dirty data is in the cache (updated when garbage collection runs).
+
+flash_vol_create
+  Echoing a size to this file (in human readable units, k/M/G) creates a thinly
+  provisioned volume backed by the cache set.
+
+io_error_halflife
+io_error_limit
+  These determines how many errors we accept before disabling the cache.
+  Each error is decayed by the half life (in # ios).  If the decaying count
+  reaches io_error_limit dirty data is written out and the cache is disabled.
+
+journal_delay_ms
+  Journal writes will delay for up to this many milliseconds, unless a cache
+  flush happens sooner. Defaults to 100.
+
+root_usage_percent
+  Percentage of the root btree node in use.  If this gets too high the node
+  will split, increasing the tree depth.
+
+stop
+  Write to this file to shut down the cache set - waits until all attached
+  backing devices have been shut down.
+
+tree_depth
+  Depth of the btree (A single node btree has depth 0).
+
+unregister
+  Detaches all backing devices and closes the cache devices; if dirty data is
+  present it will disable writeback caching and wait for it to be flushed.
+
+SYSFS - CACHE SET INTERNAL:
+
+This directory also exposes timings for a number of internal operations, with
+separate files for average duration, average frequency, last occurence and max
+duration: garbage collection, btree read, btree node sorts and btree splits.
+
+active_journal_entries
+  Number of journal entries that are newer than the index.
+
+btree_nodes
+  Total nodes in the btree.
+
+btree_used_percent
+  Average fraction of btree in use.
+
+bset_tree_stats
+  Statistics about the auxiliary search trees
+
+btree_cache_max_chain
+  Longest chain in the btree node cache's hash table
+
+cache_read_races
+  Counts instances where while data was being read from the cache, the bucket
+  was reused and invalidated - i.e. where the pointer was stale after the read
+  completed. When this occurs the data is reread from the backing device.
+
+trigger_gc
+  Writing to this file forces garbage collection to run.
+
+SYSFS - CACHE DEVICE:
+
+block_size
+  Minimum granularity of writes - should match hardware sector size.
+
+btree_written
+  Sum of all btree writes, in (kilo/mega/giga) bytes
+
+bucket_size
+  Size of buckets
+
+cache_replacement_policy
+  One of either lru, fifo or random.
+
+discard
+  Boolean; if on a discard/TRIM will be issued to each bucket before it is
+  reused. Defaults to off, since SATA TRIM is an unqueued command (and thus
+  slow).
+
+freelist_percent
+  Size of the freelist as a percentage of nbuckets. Can be written to to
+  increase the number of buckets kept on the freelist, which lets you
+  artificially reduce the size of the cache at runtime. Mostly for testing
+  purposes (i.e. testing how different size caches affect your hit rate), but
+  since buckets are discarded when they move on to the freelist will also make
+  the SSD's garbage collection easier by effectively giving it more reserved
+  space.
+
+io_errors
+  Number of errors that have occured, decayed by io_error_halflife.
+
+metadata_written
+  Sum of all non data writes (btree writes and all other metadata).
+
+nbuckets
+  Total buckets in this cache
+
+priority_stats
+  Statistics about how recently data in the cache has been accessed.  This can
+  reveal your working set size.
+
+written
+  Sum of all data that has been written to the cache; comparison with
+  btree_written gives the amount of write inflation in bcache.

MAINTAINERS

@@ -1616,6 +1616,13 @@ W:	http://www.baycom.org/~tom/ham/ham.html
 S:	Maintained
 F:	drivers/net/hamradio/baycom*
 
+BCACHE (BLOCK LAYER CACHE)
+M:	Kent Overstreet <koverstreet@google.com>
+L:	linux-bcache@vger.kernel.org
+W:	http://bcache.evilpiepirate.org
+S:	Maintained:
+F:	drivers/md/bcache/
+
 BEFS FILE SYSTEM
 S:	Orphan
 F:	Documentation/filesystems/befs.txt

drivers/md/Kconfig

@@ -174,6 +174,8 @@ config MD_FAULTY
 
 	  In unsure, say N.
 
+source "drivers/md/bcache/Kconfig"
+
 config BLK_DEV_DM
 	tristate "Device mapper support"
 	---help---

drivers/md/Makefile

@@ -29,6 +29,7 @@ obj-$(CONFIG_MD_RAID10)		+= raid10.o
 obj-$(CONFIG_MD_RAID456)	+= raid456.o
 obj-$(CONFIG_MD_MULTIPATH)	+= multipath.o
 obj-$(CONFIG_MD_FAULTY)		+= faulty.o
+obj-$(CONFIG_BCACHE)		+= bcache/
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
 obj-$(CONFIG_BLK_DEV_DM)	+= dm-mod.o
 obj-$(CONFIG_DM_BUFIO)		+= dm-bufio.o

drivers/md/bcache/Kconfig

+
+config BCACHE
+	tristate "Block device as cache"
+	select CLOSURES
+	---help---
+	Allows a block device to be used as cache for other devices; uses
+	a btree for indexing and the layout is optimized for SSDs.
+
+	See Documentation/bcache.txt for details.
+
+config BCACHE_DEBUG
+	bool "Bcache debugging"
+	depends on BCACHE
+	---help---
+	Don't select this option unless you're a developer
+
+	Enables extra debugging tools (primarily a fuzz tester)
+
+config BCACHE_EDEBUG
+	bool "Extended runtime checks"
+	depends on BCACHE
+	---help---
+	Don't select this option unless you're a developer
+
+	Enables extra runtime checks which significantly affect performance
+
+config BCACHE_CLOSURES_DEBUG
+	bool "Debug closures"
+	depends on BCACHE
+	select DEBUG_FS
+	---help---
+	Keeps all active closures in a linked list and provides a debugfs
+	interface to list them, which makes it possible to see asynchronous
+	operations that get stuck.
+
+# cgroup code needs to be updated:
+#
+#config CGROUP_BCACHE
+#	bool "Cgroup controls for bcache"
+#	depends on BCACHE && BLK_CGROUP
+#	---help---
+#	TODO

drivers/md/bcache/Makefile

+
+obj-$(CONFIG_BCACHE)	+= bcache.o
+
+bcache-y		:= alloc.o btree.o bset.o io.o journal.o writeback.o\
+	movinggc.o request.o super.o sysfs.o debug.o util.o trace.o stats.o closure.o
+
+CFLAGS_request.o	+= -Iblock

drivers/md/bcache/alloc.c

+/*
+ * Primary bucket allocation code
+ *
+ * Copyright 2012 Google, Inc.
+ *
+ * Allocation in bcache is done in terms of buckets:
+ *
+ * Each bucket has associated an 8 bit gen; this gen corresponds to the gen in
+ * btree pointers - they must match for the pointer to be considered valid.
+ *
+ * Thus (assuming a bucket has no dirty data or metadata in it) we can reuse a
+ * bucket simply by incrementing its gen.
+ *
+ * The gens (along with the priorities; it's really the gens are important but
+ * the code is named as if it's the priorities) are written in an arbitrary list
+ * of buckets on disk, with a pointer to them in the journal header.
+ *
+ * When we invalidate a bucket, we have to write its new gen to disk and wait
+ * for that write to complete before we use it - otherwise after a crash we
+ * could have pointers that appeared to be good but pointed to data that had
+ * been overwritten.
+ *
+ * Since the gens and priorities are all stored contiguously on disk, we can
+ * batch this up: We fill up the free_inc list with freshly invalidated buckets,
+ * call prio_write(), and when prio_write() finishes we pull buckets off the
+ * free_inc list and optionally discard them.
+ *
+ * free_inc isn't the only freelist - if it was, we'd often to sleep while
+ * priorities and gens were being written before we could allocate. c->free is a
+ * smaller freelist, and buckets on that list are always ready to be used.
+ *
+ * If we've got discards enabled, that happens when a bucket moves from the
+ * free_inc list to the free list.
+ *
+ * There is another freelist, because sometimes we have buckets that we know
+ * have nothing pointing into them - these we can reuse without waiting for
+ * priorities to be rewritten. These come from freed btree nodes and buckets
+ * that garbage collection discovered no longer had valid keys pointing into
+ * them (because they were overwritten). That's the unused list - buckets on the
+ * unused list move to the free list, optionally being discarded in the process.
+ *
+ * It's also important to ensure that gens don't wrap around - with respect to
+ * either the oldest gen in the btree or the gen on disk. This is quite
+ * difficult to do in practice, but we explicitly guard against it anyways - if
+ * a bucket is in danger of wrapping around we simply skip invalidating it that
+ * time around, and we garbage collect or rewrite the priorities sooner than we
+ * would have otherwise.
+ *
+ * bch_bucket_alloc() allocates a single bucket from a specific cache.
+ *
+ * bch_bucket_alloc_set() allocates one or more buckets from different caches
+ * out of a cache set.
+ *
+ * free_some_buckets() drives all the processes described above. It's called
+ * from bch_bucket_alloc() and a few other places that need to make sure free
+ * buckets are ready.
+ *
+ * invalidate_buckets_(lru|fifo)() find buckets that are available to be
+ * invalidated, and then invalidate them and stick them on the free_inc list -
+ * in either lru or fifo order.
+ */
+
+#include "bcache.h"
+#include "btree.h"
+
+#include <linux/random.h>
+
+#define MAX_IN_FLIGHT_DISCARDS		8U
+
+/* Bucket heap / gen */
+
+uint8_t bch_inc_gen(struct cache *ca, struct bucket *b)
+{
+	uint8_t ret = ++b->gen;
+
+	ca->set->need_gc = max(ca->set->need_gc, bucket_gc_gen(b));
+	WARN_ON_ONCE(ca->set->need_gc > BUCKET_GC_GEN_MAX);
+
+	if (CACHE_SYNC(&ca->set->sb)) {
+		ca->need_save_prio = max(ca->need_save_prio,
+					 bucket_disk_gen(b));
+		WARN_ON_ONCE(ca->need_save_prio > BUCKET_DISK_GEN_MAX);
+	}
+
+	return ret;
+}
+
+void bch_rescale_priorities(struct cache_set *c, int sectors)
+{
+	struct cache *ca;
+	struct bucket *b;
+	unsigned next = c->nbuckets * c->sb.bucket_size / 1024;
+	unsigned i;
+	int r;
+
+	atomic_sub(sectors, &c->rescale);
+
+	do {
+		r = atomic_read(&c->rescale);
+
+		if (r >= 0)
+			return;
+	} while (atomic_cmpxchg(&c->rescale, r, r + next) != r);
+
+	mutex_lock(&c->bucket_lock);
+
+	c->min_prio = USHRT_MAX;
+
+	for_each_cache(ca, c, i)
+		for_each_bucket(b, ca)
+			if (b->prio &&
+			    b->prio != BTREE_PRIO &&
+			    !atomic_read(&b->pin)) {
+				b->prio--;
+				c->min_prio = min(c->min_prio, b->prio);
+			}
+
+	mutex_unlock(&c->bucket_lock);
+}
+
+/* Discard/TRIM */
+
+struct discard {
+	struct list_head	list;
+	struct work_struct	work;
+	struct cache		*ca;
+	long			bucket;
+
+	struct bio		bio;
+	struct bio_vec		bv;
+};
+
+static void discard_finish(struct work_struct *w)
+{
+	struct discard *d = container_of(w, struct discard, work);
+	struct cache *ca = d->ca;
+	char buf[BDEVNAME_SIZE];
+
+	if (!test_bit(BIO_UPTODATE, &d->bio.bi_flags)) {
+		pr_notice("discard error on %s, disabling",
+			 bdevname(ca->bdev, buf));
+		d->ca->discard = 0;
+	}
+
+	mutex_lock(&ca->set->bucket_lock);
+
+	fifo_push(&ca->free, d->bucket);
+	list_add(&d->list, &ca->discards);
+	atomic_dec(&ca->discards_in_flight);
+
+	mutex_unlock(&ca->set->bucket_lock);
+
+	closure_wake_up(&ca->set->bucket_wait);
+	wake_up(&ca->set->alloc_wait);
+
+	closure_put(&ca->set->cl);
+}
+
+static void discard_endio(struct bio *bio, int error)
+{
+	struct discard *d = container_of(bio, struct discard, bio);
+	schedule_work(&d->work);
+}
+
+static void do_discard(struct cache *ca, long bucket)
+{
+	struct discard *d = list_first_entry(&ca->discards,
+					     struct discard, list);
+
+	list_del(&d->list);
+	d->bucket = bucket;
+
+	atomic_inc(&ca->discards_in_flight);
+	closure_get(&ca->set->cl);
+
+	bio_init(&d->bio);
+
+	d->bio.bi_sector	= bucket_to_sector(ca->set, d->bucket);
+	d->bio.bi_bdev		= ca->bdev;
+	d->bio.bi_rw		= REQ_WRITE|REQ_DISCARD;
+	d->bio.bi_max_vecs	= 1;
+	d->bio.bi_io_vec	= d->bio.bi_inline_vecs;
+	d->bio.bi_size		= bucket_bytes(ca);
+	d->bio.bi_end_io	= discard_endio;
+	bio_set_prio(&d->bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
+
+	submit_bio(0, &d->bio);
+}
+
+/* Allocation */
+
+static inline bool can_inc_bucket_gen(struct bucket *b)
+{
+	return bucket_gc_gen(b) < BUCKET_GC_GEN_MAX &&
+		bucket_disk_gen(b) < BUCKET_DISK_GEN_MAX;
+}
+
+bool bch_bucket_add_unused(struct cache *ca, struct bucket *b)
+{
+	BUG_ON(GC_MARK(b) || GC_SECTORS_USED(b));
+
+	if (fifo_used(&ca->free) > ca->watermark[WATERMARK_MOVINGGC] &&
+	    CACHE_REPLACEMENT(&ca->sb) == CACHE_REPLACEMENT_FIFO)
+		return false;
+
+	b->prio = 0;
+
+	if (can_inc_bucket_gen(b) &&
+	    fifo_push(&ca->unused, b - ca->buckets)) {
+		atomic_inc(&b->pin);
+		return true;
+	}
+
+	return false;
+}
+
+static bool can_invalidate_bucket(struct cache *ca, struct bucket *b)
+{
+	return GC_MARK(b) == GC_MARK_RECLAIMABLE &&
+		!atomic_read(&b->pin) &&
+		can_inc_bucket_gen(b);
+}
+
+static void invalidate_one_bucket(struct cache *ca, struct bucket *b)
+{
+	bch_inc_gen(ca, b);
+	b->prio = INITIAL_PRIO;
+	atomic_inc(&b->pin);
+	fifo_push(&ca->free_inc, b - ca->buckets);
+}
+
+static void invalidate_buckets_lru(struct cache *ca)
+{
+	unsigned bucket_prio(struct bucket *b)
+	{
+		return ((unsigned) (b->prio - ca->set->min_prio)) *
+			GC_SECTORS_USED(b);
+	}
+
+	bool bucket_max_cmp(struct bucket *l, struct bucket *r)
+	{
+		return bucket_prio(l) < bucket_prio(r);
+	}
+
+	bool bucket_min_cmp(struct bucket *l, struct bucket *r)
+	{
+		return bucket_prio(l) > bucket_prio(r);
+	}
+
+	struct bucket *b;
+	ssize_t i;
+
+	ca->heap.used = 0;
+
+	for_each_bucket(b, ca) {
+		if (!can_invalidate_bucket(ca, b))
+			continue;
+
+		if (!GC_SECTORS_USED(b)) {
+			if (!bch_bucket_add_unused(ca, b))
+				return;
+		} else {
+			if (!heap_full(&ca->heap))
+				heap_add(&ca->heap, b, bucket_max_cmp);
+			else if (bucket_max_cmp(b, heap_peek(&ca->heap))) {
+				ca->heap.data[0] = b;
+				heap_sift(&ca->heap, 0, bucket_max_cmp);
+			}
+		}
+	}
+
+	if (ca->heap.used * 2 < ca->heap.size)
+		bch_queue_gc(ca->set);
+
+	for (i = ca->heap.used / 2 - 1; i >= 0; --i)
+		heap_sift(&ca->heap, i, bucket_min_cmp);
+
+	while (!fifo_full(&ca->free_inc)) {
+		if (!heap_pop(&ca->heap, b, bucket_min_cmp)) {
+			/* We don't want to be calling invalidate_buckets()
+			 * multiple times when it can't do anything
+			 */
+			ca->invalidate_needs_gc = 1;
+			bch_queue_gc(ca->set);
+			return;
+		}
+
+		invalidate_one_bucket(ca, b);
+	}
+}
+
+static void invalidate_buckets_fifo(struct cache *ca)
+{
+	struct bucket *b;
+	size_t checked = 0;
+
+	while (!fifo_full(&ca->free_inc)) {
+		if (ca->fifo_last_bucket <  ca->sb.first_bucket ||
+		    ca->fifo_last_bucket >= ca->sb.nbuckets)
+			ca->fifo_last_bucket = ca->sb.first_bucket;
+
+		b = ca->buckets + ca->fifo_last_bucket++;
+
+		if (can_invalidate_bucket(ca, b))
+			invalidate_one_bucket(ca, b);
+
+		if (++checked >= ca->sb.nbuckets) {
+			ca->invalidate_needs_gc = 1;
+			bch_queue_gc(ca->set);
+			return;
+		}
+	}
+}
+
+static void invalidate_buckets_random(struct cache *ca)
+{
+	struct bucket *b;
+	size_t checked = 0;
+
+	while (!fifo_full(&ca->free_inc)) {
+		size_t n;
+		get_random_bytes(&n, sizeof(n));
+
+		n %= (size_t) (ca->sb.nbuckets - ca->sb.first_bucket);
+		n += ca->sb.first_bucket;
+
+		b = ca->buckets + n;
+
+		if (can_invalidate_bucket(ca, b))
+			invalidate_one_bucket(ca, b);
+
+		if (++checked >= ca->sb.nbuckets / 2) {
+			ca->invalidate_needs_gc = 1;
+			bch_queue_gc(ca->set);
+			return;
+		}
+	}
+}
+
+static void invalidate_buckets(struct cache *ca)
+{
+	if (ca->invalidate_needs_gc)
+		return;
+
+	switch (CACHE_REPLACEMENT(&ca->sb)) {
+	case CACHE_REPLACEMENT_LRU:
+		invalidate_buckets_lru(ca);
+		break;
+	case CACHE_REPLACEMENT_FIFO:
+		invalidate_buckets_fifo(ca);
+		break;
+	case CACHE_REPLACEMENT_RANDOM:
+		invalidate_buckets_random(ca);
+		break;
+	}
+}
+
+#define allocator_wait(ca, cond)					\
+do {									\
+	DEFINE_WAIT(__wait);						\
+									\
+	while (!(cond)) {						\
+		prepare_to_wait(&ca->set->alloc_wait,			\
+				&__wait, TASK_INTERRUPTIBLE);		\
+									\
+		mutex_unlock(&(ca)->set->bucket_lock);			\
+		if (test_bit(CACHE_SET_STOPPING_2, &ca->set->flags)) {	\
+			finish_wait(&ca->set->alloc_wait, &__wait);	\
+			closure_return(cl);				\
+		}							\
+									\
+		schedule();						\
+		__set_current_state(TASK_RUNNING);			\
+		mutex_lock(&(ca)->set->bucket_lock);			\
+	}								\
+									\
+	finish_wait(&ca->set->alloc_wait, &__wait);			\
+} while (0)
+
+void bch_allocator_thread(struct closure *cl)
+{
+	struct cache *ca = container_of(cl, struct cache, alloc);
+
+	mutex_lock(&ca->set->bucket_lock);
+
+	while (1) {
+		while (1) {
+			long bucket;
+
+			if ((!atomic_read(&ca->set->prio_blocked) ||
+			     !CACHE_SYNC(&ca->set->sb)) &&
+			    !fifo_empty(&ca->unused))
+				fifo_pop(&ca->unused, bucket);
+			else if (!fifo_empty(&ca->free_inc))
+				fifo_pop(&ca->free_inc, bucket);
+			else
+				break;
+
+			allocator_wait(ca, (int) fifo_free(&ca->free) >
+				       atomic_read(&ca->discards_in_flight));
+
+			if (ca->discard) {
+				allocator_wait(ca, !list_empty(&ca->discards));
+				do_discard(ca, bucket);
+			} else {
+				fifo_push(&ca->free, bucket);
+				closure_wake_up(&ca->set->bucket_wait);
+			}
+		}
+
+		allocator_wait(ca, ca->set->gc_mark_valid);
+		invalidate_buckets(ca);
+
+		allocator_wait(ca, !atomic_read(&ca->set->prio_blocked) ||
+			       !CACHE_SYNC(&ca->set->sb));
+
+		if (CACHE_SYNC(&ca->set->sb) &&
+		    (!fifo_empty(&ca->free_inc) ||
+		     ca->need_save_prio > 64)) {
+			bch_prio_write(ca);
+		}
+	}
+}
+
+long bch_bucket_alloc(struct cache *ca, unsigned watermark, struct closure *cl)
+{
+	long r = -1;
+again:
+	wake_up(&ca->set->alloc_wait);
+
+	if (fifo_used(&ca->free) > ca->watermark[watermark] &&
+	    fifo_pop(&ca->free, r)) {
+		struct bucket *b = ca->buckets + r;
+#ifdef CONFIG_BCACHE_EDEBUG
+		size_t iter;
+		long i;
+
+		for (iter = 0; iter < prio_buckets(ca) * 2; iter++)
+			BUG_ON(ca->prio_buckets[iter] == (uint64_t) r);
+
+		fifo_for_each(i, &ca->free, iter)
+			BUG_ON(i == r);
+		fifo_for_each(i, &ca->free_inc, iter)
+			BUG_ON(i == r);
+		fifo_for_each(i, &ca->unused, iter)
+			BUG_ON(i == r);
+#endif
+		BUG_ON(atomic_read(&b->pin) != 1);
+
+		SET_GC_SECTORS_USED(b, ca->sb.bucket_size);
+
+		if (watermark <= WATERMARK_METADATA) {
+			SET_GC_MARK(b, GC_MARK_METADATA);
+			b->prio = BTREE_PRIO;
+		} else {
+			SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
+			b->prio = INITIAL_PRIO;
+		}
+
+		return r;
+	}
+
+	pr_debug("alloc failure: blocked %i free %zu free_inc %zu unused %zu",
+		 atomic_read(&ca->set->prio_blocked), fifo_used(&ca->free),
+		 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
+
+	if (cl) {
+		closure_wait(&ca->set->bucket_wait, cl);
+
+		if (closure_blocking(cl)) {
+			mutex_unlock(&ca->set->bucket_lock);
+			closure_sync(cl);
+			mutex_lock(&ca->set->bucket_lock);
+			goto again;
+		}
+	}
+
+	return -1;
+}
+
+void bch_bucket_free(struct cache_set *c, struct bkey *k)
+{
+	unsigned i;
+
+	for (i = 0; i < KEY_PTRS(k); i++) {
+		struct bucket *b = PTR_BUCKET(c, k, i);
+
+		SET_GC_MARK(b, 0);
+		SET_GC_SECTORS_USED(b, 0);
+		bch_bucket_add_unused(PTR_CACHE(c, k, i), b);
+	}
+}
+
+int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
+			   struct bkey *k, int n, struct closure *cl)
+{
+	int i;
+
+	lockdep_assert_held(&c->bucket_lock);
+	BUG_ON(!n || n > c->caches_loaded || n > 8);
+
+	bkey_init(k);
+
+	/* sort by free space/prio of oldest data in caches */
+
+	for (i = 0; i < n; i++) {
+		struct cache *ca = c->cache_by_alloc[i];
+		long b = bch_bucket_alloc(ca, watermark, cl);
+
+		if (b == -1)
+			goto err;
+
+		k->ptr[i] = PTR(ca->buckets[b].gen,
+				bucket_to_sector(c, b),
+				ca->sb.nr_this_dev);
+
+		SET_KEY_PTRS(k, i + 1);
+	}
+
+	return 0;
+err:
+	bch_bucket_free(c, k);
+	__bkey_put(c, k);
+	return -1;
+}
+
+int bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
+			 struct bkey *k, int n, struct closure *cl)
+{
+	int ret;
+	mutex_lock(&c->bucket_lock);
+	ret = __bch_bucket_alloc_set(c, watermark, k, n, cl);
+	mutex_unlock(&c->bucket_lock);
+	return ret;
+}
+
+/* Init */
+
+void bch_cache_allocator_exit(struct cache *ca)
+{
+	struct discard *d;
+
+	while (!list_empty(&ca->discards)) {
+		d = list_first_entry(&ca->discards, struct discard, list);
+		cancel_work_sync(&d->work);
+		list_del(&d->list);
+		kfree(d);
+	}
+}
+
+int bch_cache_allocator_init(struct cache *ca)
+{
+	unsigned i;
+
+	/*
+	 * Reserve:
+	 * Prio/gen writes first
+	 * Then 8 for btree allocations
+	 * Then half for the moving garbage collector
+	 */
+
+	ca->watermark[WATERMARK_PRIO] = 0;
+
+	ca->watermark[WATERMARK_METADATA] = prio_buckets(ca);
+
+	ca->watermark[WATERMARK_MOVINGGC] = 8 +
+		ca->watermark[WATERMARK_METADATA];
+
+	ca->watermark[WATERMARK_NONE] = ca->free.size / 2 +
+		ca->watermark[WATERMARK_MOVINGGC];
+
+	for (i = 0; i < MAX_IN_FLIGHT_DISCARDS; i++) {
+		struct discard *d = kzalloc(sizeof(*d), GFP_KERNEL);
+		if (!d)
+			return -ENOMEM;
+
+		d->ca = ca;
+		INIT_WORK(&d->work, discard_finish);
+		list_add(&d->list, &ca->discards);
+	}
+
+	return 0;
+}

drivers/md/bcache/bset.h

+#ifndef _BCACHE_BSET_H
+#define _BCACHE_BSET_H
+
+/*
+ * BKEYS:
+ *
+ * A bkey contains a key, a size field, a variable number of pointers, and some
+ * ancillary flag bits.
+ *
+ * We use two different functions for validating bkeys, bch_ptr_invalid and
+ * bch_ptr_bad().
+ *
+ * bch_ptr_invalid() primarily filters out keys and pointers that would be
+ * invalid due to some sort of bug, whereas bch_ptr_bad() filters out keys and
+ * pointer that occur in normal practice but don't point to real data.
+ *
+ * The one exception to the rule that ptr_invalid() filters out invalid keys is
+ * that it also filters out keys of size 0 - these are keys that have been
+ * completely overwritten. It'd be safe to delete these in memory while leaving
+ * them on disk, just unnecessary work - so we filter them out when resorting
+ * instead.
+ *
+ * We can't filter out stale keys when we're resorting, because garbage
+ * collection needs to find them to ensure bucket gens don't wrap around -
+ * unless we're rewriting the btree node those stale keys still exist on disk.
+ *
+ * We also implement functions here for removing some number of sectors from the
+ * front or the back of a bkey - this is mainly used for fixing overlapping
+ * extents, by removing the overlapping sectors from the older key.
+ *
+ * BSETS:
+ *
+ * A bset is an array of bkeys laid out contiguously in memory in sorted order,
+ * along with a header. A btree node is made up of a number of these, written at
+ * different times.
+ *
+ * There could be many of them on disk, but we never allow there to be more than
+ * 4 in memory - we lazily resort as needed.
+ *
+ * We implement code here for creating and maintaining auxiliary search trees
+ * (described below) for searching an individial bset, and on top of that we
+ * implement a btree iterator.
+ *
+ * BTREE ITERATOR:
+ *
+ * Most of the code in bcache doesn't care about an individual bset - it needs
+ * to search entire btree nodes and iterate over them in sorted order.
+ *
+ * The btree iterator code serves both functions; it iterates through the keys
+ * in a btree node in sorted order, starting from either keys after a specific
+ * point (if you pass it a search key) or the start of the btree node.
+ *
+ * AUXILIARY SEARCH TREES:
+ *
+ * Since keys are variable length, we can't use a binary search on a bset - we
+ * wouldn't be able to find the start of the next key. But binary searches are
+ * slow anyways, due to terrible cache behaviour; bcache originally used binary
+ * searches and that code topped out at under 50k lookups/second.
+ *
+ * So we need to construct some sort of lookup table. Since we only insert keys
+ * into the last (unwritten) set, most of the keys within a given btree node are
+ * usually in sets that are mostly constant. We use two different types of
+ * lookup tables to take advantage of this.
+ *
+ * Both lookup tables share in common that they don't index every key in the
+ * set; they index one key every BSET_CACHELINE bytes, and then a linear search
+ * is used for the rest.
+ *
+ * For sets that have been written to disk and are no longer being inserted
+ * into, we construct a binary search tree in an array - traversing a binary
+ * search tree in an array gives excellent locality of reference and is very
+ * fast, since both children of any node are adjacent to each other in memory
+ * (and their grandchildren, and great grandchildren...) - this means
+ * prefetching can be used to great effect.
+ *
+ * It's quite useful performance wise to keep these nodes small - not just
+ * because they're more likely to be in L2, but also because we can prefetch
+ * more nodes on a single cacheline and thus prefetch more iterations in advance
+ * when traversing this tree.
+ *
+ * Nodes in the auxiliary search tree must contain both a key to compare against
+ * (we don't want to fetch the key from the set, that would defeat the purpose),
+ * and a pointer to the key. We use a few tricks to compress both of these.
+ *
+ * To compress the pointer, we take advantage of the fact that one node in the
+ * search tree corresponds to precisely BSET_CACHELINE bytes in the set. We have
+ * a function (to_inorder()) that takes the index of a node in a binary tree and
+ * returns what its index would be in an inorder traversal, so we only have to
+ * store the low bits of the offset.
+ *
+ * The key is 84 bits (KEY_DEV + key->key, the offset on the device). To
+ * compress that,  we take advantage of the fact that when we're traversing the
+ * search tree at every iteration we know that both our search key and the key
+ * we're looking for lie within some range - bounded by our previous
+ * comparisons. (We special case the start of a search so that this is true even
+ * at the root of the tree).
+ *
+ * So we know the key we're looking for is between a and b, and a and b don't
+ * differ higher than bit 50, we don't need to check anything higher than bit
+ * 50.
+ *
+ * We don't usually need the rest of the bits, either; we only need enough bits
+ * to partition the key range we're currently checking.  Consider key n - the
+ * key our auxiliary search tree node corresponds to, and key p, the key
+ * immediately preceding n.  The lowest bit we need to store in the auxiliary
+ * search tree is the highest bit that differs between n and p.
+ *
+ * Note that this could be bit 0 - we might sometimes need all 80 bits to do the
+ * comparison. But we'd really like our nodes in the auxiliary search tree to be
+ * of fixed size.
+ *
+ * The solution is to make them fixed size, and when we're constructing a node
+ * check if p and n differed in the bits we needed them to. If they don't we
+ * flag that node, and when doing lookups we fallback to comparing against the
+ * real key. As long as this doesn't happen to often (and it seems to reliably
+ * happen a bit less than 1% of the time), we win - even on failures, that key
+ * is then more likely to be in cache than if we were doing binary searches all
+ * the way, since we're touching so much less memory.
+ *
+ * The keys in the auxiliary search tree are stored in (software) floating
+ * point, with an exponent and a mantissa. The exponent needs to be big enough
+ * to address all the bits in the original key, but the number of bits in the
+ * mantissa is somewhat arbitrary; more bits just gets us fewer failures.
+ *
+ * We need 7 bits for the exponent and 3 bits for the key's offset (since keys
+ * are 8 byte aligned); using 22 bits for the mantissa means a node is 4 bytes.
+ * We need one node per 128 bytes in the btree node, which means the auxiliary
+ * search trees take up 3% as much memory as the btree itself.
+ *
+ * Constructing these auxiliary search trees is moderately expensive, and we
+ * don't want to be constantly rebuilding the search tree for the last set
+ * whenever we insert another key into it. For the unwritten set, we use a much
+ * simpler lookup table - it's just a flat array, so index i in the lookup table
+ * corresponds to the i range of BSET_CACHELINE bytes in the set. Indexing
+ * within each byte range works the same as with the auxiliary search trees.
+ *
+ * These are much easier to keep up to date when we insert a key - we do it
+ * somewhat lazily; when we shift a key up we usually just increment the pointer
+ * to it, only when it would overflow do we go to the trouble of finding the
+ * first key in that range of bytes again.
+ */
+
+/* Btree key comparison/iteration */
+
+struct btree_iter {
+	size_t size, used;
+	struct btree_iter_set {
+		struct bkey *k, *end;
+	} data[MAX_BSETS];
+};
+
+struct bset_tree {
+	/*
+	 * We construct a binary tree in an array as if the array
+	 * started at 1, so that things line up on the same cachelines
+	 * better: see comments in bset.c at cacheline_to_bkey() for
+	 * details
+	 */
+
+	/* size of the binary tree and prev array */
+	unsigned	size;
+
+	/* function of size - precalculated for to_inorder() */
+	unsigned	extra;
+
+	/* copy of the last key in the set */
+	struct bkey	end;
+	struct bkey_float *tree;
+
+	/*
+	 * The nodes in the bset tree point to specific keys - this
+	 * array holds the sizes of the previous key.
+	 *
+	 * Conceptually it's a member of struct bkey_float, but we want
+	 * to keep bkey_float to 4 bytes and prev isn't used in the fast
+	 * path.
+	 */
+	uint8_t		*prev;
+
+	/* The actual btree node, with pointers to each sorted set */
+	struct bset	*data;
+};
+
+static __always_inline int64_t bkey_cmp(const struct bkey *l,
+					const struct bkey *r)
+{
+	return unlikely(KEY_INODE(l) != KEY_INODE(r))
+		? (int64_t) KEY_INODE(l) - (int64_t) KEY_INODE(r)
+		: (int64_t) KEY_OFFSET(l) - (int64_t) KEY_OFFSET(r);
+}
+
+static inline size_t bkey_u64s(const struct bkey *k)
+{
+	BUG_ON(KEY_CSUM(k) > 1);
+	return 2 + KEY_PTRS(k) + (KEY_CSUM(k) ? 1 : 0);
+}
+
+static inline size_t bkey_bytes(const struct bkey *k)
+{
+	return bkey_u64s(k) * sizeof(uint64_t);
+}
+
+static inline void bkey_copy(struct bkey *dest, const struct bkey *src)
+{
+	memcpy(dest, src, bkey_bytes(src));
+}
+
+static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src)
+{
+	if (!src)
+		src = &KEY(0, 0, 0);
+
+	SET_KEY_INODE(dest, KEY_INODE(src));
+	SET_KEY_OFFSET(dest, KEY_OFFSET(src));
+}
+
+static inline struct bkey *bkey_next(const struct bkey *k)
+{
+	uint64_t *d = (void *) k;
+	return (struct bkey *) (d + bkey_u64s(k));
+}
+
+/* Keylists */
+
+struct keylist {
+	struct bkey		*top;
+	union {
+		uint64_t		*list;
+		struct bkey		*bottom;
+	};
+
+	/* Enough room for btree_split's keys without realloc */
+#define KEYLIST_INLINE		16
+	uint64_t		d[KEYLIST_INLINE];
+};
+
+static inline void bch_keylist_init(struct keylist *l)
+{
+	l->top = (void *) (l->list = l->d);
+}
+
+static inline void bch_keylist_push(struct keylist *l)
+{
+	l->top = bkey_next(l->top);
+}
+
+static inline void bch_keylist_add(struct keylist *l, struct bkey *k)
+{
+	bkey_copy(l->top, k);
+	bch_keylist_push(l);
+}
+
+static inline bool bch_keylist_empty(struct keylist *l)
+{
+	return l->top == (void *) l->list;
+}
+
+static inline void bch_keylist_free(struct keylist *l)
+{
+	if (l->list != l->d)
+		kfree(l->list);
+}
+
+void bch_keylist_copy(struct keylist *, struct keylist *);
+struct bkey *bch_keylist_pop(struct keylist *);
+int bch_keylist_realloc(struct keylist *, int, struct cache_set *);
+
+void bch_bkey_copy_single_ptr(struct bkey *, const struct bkey *,
+			      unsigned);
+bool __bch_cut_front(const struct bkey *, struct bkey *);
+bool __bch_cut_back(const struct bkey *, struct bkey *);
+
+static inline bool bch_cut_front(const struct bkey *where, struct bkey *k)
+{
+	BUG_ON(bkey_cmp(where, k) > 0);
+	return __bch_cut_front(where, k);
+}
+
+static inline bool bch_cut_back(const struct bkey *where, struct bkey *k)
+{
+	BUG_ON(bkey_cmp(where, &START_KEY(k)) < 0);
+	return __bch_cut_back(where, k);
+}
+
+const char *bch_ptr_status(struct cache_set *, const struct bkey *);
+bool __bch_ptr_invalid(struct cache_set *, int level, const struct bkey *);
+bool bch_ptr_bad(struct btree *, const struct bkey *);
+
+static inline uint8_t gen_after(uint8_t a, uint8_t b)
+{
+	uint8_t r = a - b;
+	return r > 128U ? 0 : r;
+}
+
+static inline uint8_t ptr_stale(struct cache_set *c, const struct bkey *k,
+				unsigned i)
+{
+	return gen_after(PTR_BUCKET(c, k, i)->gen, PTR_GEN(k, i));
+}
+
+static inline bool ptr_available(struct cache_set *c, const struct bkey *k,
+				 unsigned i)
+{
+	return (PTR_DEV(k, i) < MAX_CACHES_PER_SET) && PTR_CACHE(c, k, i);
+}
+
+
+typedef bool (*ptr_filter_fn)(struct btree *, const struct bkey *);
+
+struct bkey *bch_next_recurse_key(struct btree *, struct bkey *);
+struct bkey *bch_btree_iter_next(struct btree_iter *);
+struct bkey *bch_btree_iter_next_filter(struct btree_iter *,
+					struct btree *, ptr_filter_fn);
+
+void bch_btree_iter_push(struct btree_iter *, struct bkey *, struct bkey *);
+struct bkey *__bch_btree_iter_init(struct btree *, struct btree_iter *,
+				   struct bkey *, struct bset_tree *);
+
+/* 32 bits total: */
+#define BKEY_MID_BITS		3
+#define BKEY_EXPONENT_BITS	7
+#define BKEY_MANTISSA_BITS	22
+#define BKEY_MANTISSA_MASK	((1 << BKEY_MANTISSA_BITS) - 1)
+
+struct bkey_float {
+	unsigned	exponent:BKEY_EXPONENT_BITS;
+	unsigned	m:BKEY_MID_BITS;
+	unsigned	mantissa:BKEY_MANTISSA_BITS;
+} __packed;
+
+/*
+ * BSET_CACHELINE was originally intended to match the hardware cacheline size -
+ * it used to be 64, but I realized the lookup code would touch slightly less
+ * memory if it was 128.
+ *
+ * It definites the number of bytes (in struct bset) per struct bkey_float in
+ * the auxiliar search tree - when we're done searching the bset_float tree we
+ * have this many bytes left that we do a linear search over.
+ *
+ * Since (after level 5) every level of the bset_tree is on a new cacheline,
+ * we're touching one fewer cacheline in the bset tree in exchange for one more
+ * cacheline in the linear search - but the linear search might stop before it
+ * gets to the second cacheline.
+ */
+
+#define BSET_CACHELINE		128
+#define bset_tree_space(b)	(btree_data_space(b) / BSET_CACHELINE)
+
+#define bset_tree_bytes(b)	(bset_tree_space(b) * sizeof(struct bkey_float))
+#define bset_prev_bytes(b)	(bset_tree_space(b) * sizeof(uint8_t))
+
+void bch_bset_init_next(struct btree *);
+
+void bch_bset_fix_invalidated_key(struct btree *, struct bkey *);
+void bch_bset_fix_lookup_table(struct btree *, struct bkey *);
+
+struct bkey *__bch_bset_search(struct btree *, struct bset_tree *,
+			   const struct bkey *);
+
+static inline struct bkey *bch_bset_search(struct btree *b, struct bset_tree *t,
+					   const struct bkey *search)
+{
+	return search ? __bch_bset_search(b, t, search) : t->data->start;
+}
+
+bool bch_bkey_try_merge(struct btree *, struct bkey *, struct bkey *);
+void bch_btree_sort_lazy(struct btree *);
+void bch_btree_sort_into(struct btree *, struct btree *);
+void bch_btree_sort_and_fix_extents(struct btree *, struct btree_iter *);
+void bch_btree_sort_partial(struct btree *, unsigned);
+
+static inline void bch_btree_sort(struct btree *b)
+{
+	bch_btree_sort_partial(b, 0);
+}
+
+int bch_bset_print_stats(struct cache_set *, char *);
+
+#endif

drivers/md/bcache/btree.h

+#ifndef _BCACHE_BTREE_H
+#define _BCACHE_BTREE_H
+
+/*
+ * THE BTREE:
+ *
+ * At a high level, bcache's btree is relatively standard b+ tree. All keys and
+ * pointers are in the leaves; interior nodes only have pointers to the child
+ * nodes.
+ *
+ * In the interior nodes, a struct bkey always points to a child btree node, and
+ * the key is the highest key in the child node - except that the highest key in
+ * an interior node is always MAX_KEY. The size field refers to the size on disk
+ * of the child node - this would allow us to have variable sized btree nodes
+ * (handy for keeping the depth of the btree 1 by expanding just the root).
+ *
+ * Btree nodes are themselves log structured, but this is hidden fairly
+ * thoroughly. Btree nodes on disk will in practice have extents that overlap
+ * (because they were written at different times), but in memory we never have
+ * overlapping extents - when we read in a btree node from disk, the first thing
+ * we do is resort all the sets of keys with a mergesort, and in the same pass
+ * we check for overlapping extents and adjust them appropriately.
+ *
+ * struct btree_op is a central interface to the btree code. It's used for
+ * specifying read vs. write locking, and the embedded closure is used for
+ * waiting on IO or reserve memory.
+ *
+ * BTREE CACHE:
+ *
+ * Btree nodes are cached in memory; traversing the btree might require reading
+ * in btree nodes which is handled mostly transparently.
+ *
+ * bch_btree_node_get() looks up a btree node in the cache and reads it in from
+ * disk if necessary. This function is almost never called directly though - the
+ * btree() macro is used to get a btree node, call some function on it, and
+ * unlock the node after the function returns.
+ *
+ * The root is special cased - it's taken out of the cache's lru (thus pinning
+ * it in memory), so we can find the root of the btree by just dereferencing a
+ * pointer instead of looking it up in the cache. This makes locking a bit
+ * tricky, since the root pointer is protected by the lock in the btree node it
+ * points to - the btree_root() macro handles this.
+ *
+ * In various places we must be able to allocate memory for multiple btree nodes
+ * in order to make forward progress. To do this we use the btree cache itself
+ * as a reserve; if __get_free_pages() fails, we'll find a node in the btree
+ * cache we can reuse. We can't allow more than one thread to be doing this at a
+ * time, so there's a lock, implemented by a pointer to the btree_op closure -
+ * this allows the btree_root() macro to implicitly release this lock.
+ *
+ * BTREE IO:
+ *
+ * Btree nodes never have to be explicitly read in; bch_btree_node_get() handles
+ * this.
+ *
+ * For writing, we have two btree_write structs embeddded in struct btree - one
+ * write in flight, and one being set up, and we toggle between them.
+ *
+ * Writing is done with a single function -  bch_btree_write() really serves two
+ * different purposes and should be broken up into two different functions. When
+ * passing now = false, it merely indicates that the node is now dirty - calling
+ * it ensures that the dirty keys will be written at some point in the future.
+ *
+ * When passing now = true, bch_btree_write() causes a write to happen
+ * "immediately" (if there was already a write in flight, it'll cause the write
+ * to happen as soon as the previous write completes). It returns immediately
+ * though - but it takes a refcount on the closure in struct btree_op you passed
+ * to it, so a closure_sync() later can be used to wait for the write to
+ * complete.
+ *
+ * This is handy because btree_split() and garbage collection can issue writes
+ * in parallel, reducing the amount of time they have to hold write locks.
+ *
+ * LOCKING:
+ *
+ * When traversing the btree, we may need write locks starting at some level -
+ * inserting a key into the btree will typically only require a write lock on
+ * the leaf node.
+ *
+ * This is specified with the lock field in struct btree_op; lock = 0 means we
+ * take write locks at level <= 0, i.e. only leaf nodes. bch_btree_node_get()
+ * checks this field and returns the node with the appropriate lock held.
+ *
+ * If, after traversing the btree, the insertion code discovers it has to split
+ * then it must restart from the root and take new locks - to do this it changes
+ * the lock field and returns -EINTR, which causes the btree_root() macro to
+ * loop.
+ *
+ * Handling cache misses require a different mechanism for upgrading to a write
+ * lock. We do cache lookups with only a read lock held, but if we get a cache
+ * miss and we wish to insert this data into the cache, we have to insert a
+ * placeholder key to detect races - otherwise, we could race with a write and
+ * overwrite the data that was just written to the cache with stale data from
+ * the backing device.
+ *
+ * For this we use a sequence number that write locks and unlocks increment - to
+ * insert the check key it unlocks the btree node and then takes a write lock,
+ * and fails if the sequence number doesn't match.
+ */
+
+#include "bset.h"
+#include "debug.h"
+
+struct btree_write {
+	struct closure		*owner;
+	atomic_t		*journal;
+
+	/* If btree_split() frees a btree node, it writes a new pointer to that
+	 * btree node indicating it was freed; it takes a refcount on
+	 * c->prio_blocked because we can't write the gens until the new
+	 * pointer is on disk. This allows btree_write_endio() to release the
+	 * refcount that btree_split() took.
+	 */
+	int			prio_blocked;
+};
+
+struct btree {
+	/* Hottest entries first */
+	struct hlist_node	hash;
+
+	/* Key/pointer for this btree node */
+	BKEY_PADDED(key);
+
+	/* Single bit - set when accessed, cleared by shrinker */
+	unsigned long		accessed;
+	unsigned long		seq;
+	struct rw_semaphore	lock;
+	struct cache_set	*c;
+
+	unsigned long		flags;
+	uint16_t		written;	/* would be nice to kill */
+	uint8_t			level;
+	uint8_t			nsets;
+	uint8_t			page_order;
+
+	/*
+	 * Set of sorted keys - the real btree node - plus a binary search tree
+	 *
+	 * sets[0] is special; set[0]->tree, set[0]->prev and set[0]->data point
+	 * to the memory we have allocated for this btree node. Additionally,
+	 * set[0]->data points to the entire btree node as it exists on disk.
+	 */
+	struct bset_tree	sets[MAX_BSETS];
+
+	/* Used to refcount bio splits, also protects b->bio */
+	struct closure_with_waitlist	io;
+
+	/* Gets transferred to w->prio_blocked - see the comment there */
+	int			prio_blocked;
+
+	struct list_head	list;
+	struct delayed_work	work;
+
+	uint64_t		io_start_time;
+	struct btree_write	writes[2];
+	struct bio		*bio;
+};
+
+#define BTREE_FLAG(flag)						\
+static inline bool btree_node_ ## flag(struct btree *b)			\
+{	return test_bit(BTREE_NODE_ ## flag, &b->flags); }		\
+									\
+static inline void set_btree_node_ ## flag(struct btree *b)		\
+{	set_bit(BTREE_NODE_ ## flag, &b->flags); }			\
+
+enum btree_flags {
+	BTREE_NODE_read_done,
+	BTREE_NODE_io_error,
+	BTREE_NODE_dirty,
+	BTREE_NODE_write_idx,
+};
+
+BTREE_FLAG(read_done);
+BTREE_FLAG(io_error);
+BTREE_FLAG(dirty);
+BTREE_FLAG(write_idx);
+
+static inline struct btree_write *btree_current_write(struct btree *b)
+{
+	return b->writes + btree_node_write_idx(b);
+}
+
+static inline struct btree_write *btree_prev_write(struct btree *b)
+{
+	return b->writes + (btree_node_write_idx(b) ^ 1);
+}
+
+static inline unsigned bset_offset(struct btree *b, struct bset *i)
+{
+	return (((size_t) i) - ((size_t) b->sets->data)) >> 9;
+}
+
+static inline struct bset *write_block(struct btree *b)
+{
+	return ((void *) b->sets[0].data) + b->written * block_bytes(b->c);
+}
+
+static inline bool bset_written(struct btree *b, struct bset_tree *t)
+{
+	return t->data < write_block(b);
+}
+
+static inline bool bkey_written(struct btree *b, struct bkey *k)
+{
+	return k < write_block(b)->start;
+}
+
+static inline void set_gc_sectors(struct cache_set *c)
+{
+	atomic_set(&c->sectors_to_gc, c->sb.bucket_size * c->nbuckets / 8);
+}
+
+static inline bool bch_ptr_invalid(struct btree *b, const struct bkey *k)
+{
+	return __bch_ptr_invalid(b->c, b->level, k);
+}
+
+static inline struct bkey *bch_btree_iter_init(struct btree *b,
+					       struct btree_iter *iter,
+					       struct bkey *search)
+{
+	return __bch_btree_iter_init(b, iter, search, b->sets);
+}
+
+/* Looping macros */
+
+#define for_each_cached_btree(b, c, iter)				\
+	for (iter = 0;							\
+	     iter < ARRAY_SIZE((c)->bucket_hash);			\
+	     iter++)							\
+		hlist_for_each_entry_rcu((b), (c)->bucket_hash + iter, hash)
+
+#define for_each_key_filter(b, k, iter, filter)				\
+	for (bch_btree_iter_init((b), (iter), NULL);			\
+	     ((k) = bch_btree_iter_next_filter((iter), b, filter));)
+
+#define for_each_key(b, k, iter)					\
+	for (bch_btree_iter_init((b), (iter), NULL);			\
+	     ((k) = bch_btree_iter_next(iter));)
+
+/* Recursing down the btree */
+
+struct btree_op {
+	struct closure		cl;
+	struct cache_set	*c;
+
+	/* Journal entry we have a refcount on */
+	atomic_t		*journal;
+
+	/* Bio to be inserted into the cache */
+	struct bio		*cache_bio;
+
+	unsigned		inode;
+
+	uint16_t		write_prio;
+
+	/* Btree level at which we start taking write locks */
+	short			lock;
+
+	/* Btree insertion type */
+	enum {
+		BTREE_INSERT,
+		BTREE_REPLACE
+	} type:8;
+
+	unsigned		csum:1;
+	unsigned		skip:1;
+	unsigned		flush_journal:1;
+
+	unsigned		insert_data_done:1;
+	unsigned		lookup_done:1;
+	unsigned		insert_collision:1;
+
+	/* Anything after this point won't get zeroed in do_bio_hook() */
+
+	/* Keys to be inserted */
+	struct keylist		keys;
+	BKEY_PADDED(replace);
+};
+
+void bch_btree_op_init_stack(struct btree_op *);
+
+static inline void rw_lock(bool w, struct btree *b, int level)
+{
+	w ? down_write_nested(&b->lock, level + 1)
+	  : down_read_nested(&b->lock, level + 1);
+	if (w)
+		b->seq++;
+}
+
+static inline void rw_unlock(bool w, struct btree *b)
+{
+#ifdef CONFIG_BCACHE_EDEBUG
+	unsigned i;
+
+	if (w &&
+	    b->key.ptr[0] &&
+	    btree_node_read_done(b))
+		for (i = 0; i <= b->nsets; i++)
+			bch_check_key_order(b, b->sets[i].data);
+#endif
+
+	if (w)
+		b->seq++;
+	(w ? up_write : up_read)(&b->lock);
+}
+
+#define insert_lock(s, b)	((b)->level <= (s)->lock)
+
+/*
+ * These macros are for recursing down the btree - they handle the details of
+ * locking and looking up nodes in the cache for you. They're best treated as
+ * mere syntax when reading code that uses them.
+ *
+ * op->lock determines whether we take a read or a write lock at a given depth.
+ * If you've got a read lock and find that you need a write lock (i.e. you're
+ * going to have to split), set op->lock and return -EINTR; btree_root() will
+ * call you again and you'll have the correct lock.
+ */
+
+/**
+ * btree - recurse down the btree on a specified key
+ * @fn:		function to call, which will be passed the child node
+ * @key:	key to recurse on
+ * @b:		parent btree node
+ * @op:		pointer to struct btree_op
+ */
+#define btree(fn, key, b, op, ...)					\
+({									\
+	int _r, l = (b)->level - 1;					\
+	bool _w = l <= (op)->lock;					\
+	struct btree *_b = bch_btree_node_get((b)->c, key, l, op);	\
+	if (!IS_ERR(_b)) {						\
+		_r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__);		\
+		rw_unlock(_w, _b);					\
+	} else								\
+		_r = PTR_ERR(_b);					\
+	_r;								\
+})
+
+/**
+ * btree_root - call a function on the root of the btree
+ * @fn:		function to call, which will be passed the child node
+ * @c:		cache set
+ * @op:		pointer to struct btree_op
+ */
+#define btree_root(fn, c, op, ...)					\
+({									\
+	int _r = -EINTR;						\
+	do {								\
+		struct btree *_b = (c)->root;				\
+		bool _w = insert_lock(op, _b);				\
+		rw_lock(_w, _b, _b->level);				\
+		if (_b == (c)->root &&					\
+		    _w == insert_lock(op, _b))				\
+			_r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__);	\
+		rw_unlock(_w, _b);					\
+		bch_cannibalize_unlock(c, &(op)->cl);		\
+	} while (_r == -EINTR);						\
+									\
+	_r;								\
+})
+
+static inline bool should_split(struct btree *b)
+{
+	struct bset *i = write_block(b);
+	return b->written >= btree_blocks(b) ||
+		(i->seq == b->sets[0].data->seq &&
+		 b->written + __set_blocks(i, i->keys + 15, b->c)
+		 > btree_blocks(b));
+}
+
+void bch_btree_read_done(struct closure *);
+void bch_btree_read(struct btree *);
+void bch_btree_write(struct btree *b, bool now, struct btree_op *op);
+
+void bch_cannibalize_unlock(struct cache_set *, struct closure *);
+void bch_btree_set_root(struct btree *);
+struct btree *bch_btree_node_alloc(struct cache_set *, int, struct closure *);
+struct btree *bch_btree_node_get(struct cache_set *, struct bkey *,
+				int, struct btree_op *);
+
+bool bch_btree_insert_keys(struct btree *, struct btree_op *);
+bool bch_btree_insert_check_key(struct btree *, struct btree_op *,
+				   struct bio *);
+int bch_btree_insert(struct btree_op *, struct cache_set *);
+
+int bch_btree_search_recurse(struct btree *, struct btree_op *);
+
+void bch_queue_gc(struct cache_set *);
+size_t bch_btree_gc_finish(struct cache_set *);
+void bch_moving_gc(struct closure *);
+int bch_btree_check(struct cache_set *, struct btree_op *);
+uint8_t __bch_btree_mark_key(struct cache_set *, int, struct bkey *);
+
+void bch_keybuf_init(struct keybuf *, keybuf_pred_fn *);
+void bch_refill_keybuf(struct cache_set *, struct keybuf *, struct bkey *);
+bool bch_keybuf_check_overlapping(struct keybuf *, struct bkey *,
+				  struct bkey *);
+void bch_keybuf_del(struct keybuf *, struct keybuf_key *);
+struct keybuf_key *bch_keybuf_next(struct keybuf *);
+struct keybuf_key *bch_keybuf_next_rescan(struct cache_set *,
+					  struct keybuf *, struct bkey *);
+
+#endif

drivers/md/bcache/closure.c

+/*
+ * Asynchronous refcounty things
+ *
+ * Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
+ * Copyright 2012 Google, Inc.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+
+#include "closure.h"
+
+void closure_queue(struct closure *cl)
+{
+	struct workqueue_struct *wq = cl->wq;
+	if (wq) {
+		INIT_WORK(&cl->work, cl->work.func);
+		BUG_ON(!queue_work(wq, &cl->work));
+	} else
+		cl->fn(cl);
+}
+EXPORT_SYMBOL_GPL(closure_queue);
+
+#define CL_FIELD(type, field)					\
+	case TYPE_ ## type:					\
+	return &container_of(cl, struct type, cl)->field
+
+static struct closure_waitlist *closure_waitlist(struct closure *cl)
+{
+	switch (cl->type) {
+		CL_FIELD(closure_with_waitlist, wait);
+		CL_FIELD(closure_with_waitlist_and_timer, wait);
+	default:
+		return NULL;
+	}
+}
+
+static struct timer_list *closure_timer(struct closure *cl)
+{
+	switch (cl->type) {
+		CL_FIELD(closure_with_timer, timer);
+		CL_FIELD(closure_with_waitlist_and_timer, timer);
+	default:
+		return NULL;
+	}
+}
+
+static inline void closure_put_after_sub(struct closure *cl, int flags)
+{
+	int r = flags & CLOSURE_REMAINING_MASK;
+
+	BUG_ON(flags & CLOSURE_GUARD_MASK);
+	BUG_ON(!r && (flags & ~(CLOSURE_DESTRUCTOR|CLOSURE_BLOCKING)));
+
+	/* Must deliver precisely one wakeup */
+	if (r == 1 && (flags & CLOSURE_SLEEPING))
+		wake_up_process(cl->task);
+
+	if (!r) {
+		if (cl->fn && !(flags & CLOSURE_DESTRUCTOR)) {
+			/* CLOSURE_BLOCKING might be set - clear it */
+			atomic_set(&cl->remaining,
+				   CLOSURE_REMAINING_INITIALIZER);
+			closure_queue(cl);
+		} else {
+			struct closure *parent = cl->parent;
+			struct closure_waitlist *wait = closure_waitlist(cl);
+
+			closure_debug_destroy(cl);
+
+			atomic_set(&cl->remaining, -1);
+
+			if (wait)
+				closure_wake_up(wait);
+
+			if (cl->fn)
+				cl->fn(cl);
+
+			if (parent)
+				closure_put(parent);
+		}
+	}
+}
+
+/* For clearing flags with the same atomic op as a put */
+void closure_sub(struct closure *cl, int v)
+{
+	closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining));
+}
+EXPORT_SYMBOL_GPL(closure_sub);
+
+void closure_put(struct closure *cl)
+{
+	closure_put_after_sub(cl, atomic_dec_return(&cl->remaining));
+}
+EXPORT_SYMBOL_GPL(closure_put);
+
+static void set_waiting(struct closure *cl, unsigned long f)
+{
+#ifdef CONFIG_BCACHE_CLOSURES_DEBUG
+	cl->waiting_on = f;
+#endif
+}
+
+void __closure_wake_up(struct closure_waitlist *wait_list)
+{
+	struct llist_node *list;
+	struct closure *cl;
+	struct llist_node *reverse = NULL;
+
+	list = llist_del_all(&wait_list->list);
+
+	/* We first reverse the list to preserve FIFO ordering and fairness */
+
+	while (list) {
+		struct llist_node *t = list;
+		list = llist_next(list);
+
+		t->next = reverse;
+		reverse = t;
+	}
+
+	/* Then do the wakeups */
+
+	while (reverse) {
+		cl = container_of(reverse, struct closure, list);
+		reverse = llist_next(reverse);
+
+		set_waiting(cl, 0);
+		closure_sub(cl, CLOSURE_WAITING + 1);
+	}
+}
+EXPORT_SYMBOL_GPL(__closure_wake_up);
+
+bool closure_wait(struct closure_waitlist *list, struct closure *cl)
+{
+	if (atomic_read(&cl->remaining) & CLOSURE_WAITING)
+		return false;
+
+	set_waiting(cl, _RET_IP_);
+	atomic_add(CLOSURE_WAITING + 1, &cl->remaining);
+	llist_add(&cl->list, &list->list);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(closure_wait);
+
+/**
+ * closure_sync() - sleep until a closure a closure has nothing left to wait on
+ *
+ * Sleeps until the refcount hits 1 - the thread that's running the closure owns
+ * the last refcount.
+ */
+void closure_sync(struct closure *cl)
+{
+	while (1) {
+		__closure_start_sleep(cl);
+		closure_set_ret_ip(cl);
+
+		if ((atomic_read(&cl->remaining) &
+		     CLOSURE_REMAINING_MASK) == 1)
+			break;
+
+		schedule();
+	}
+
+	__closure_end_sleep(cl);
+}
+EXPORT_SYMBOL_GPL(closure_sync);
+
+/**
+ * closure_trylock() - try to acquire the closure, without waiting
+ * @cl:		closure to lock
+ *
+ * Returns true if the closure was succesfully locked.
+ */
+bool closure_trylock(struct closure *cl, struct closure *parent)
+{
+	if (atomic_cmpxchg(&cl->remaining, -1,
+			   CLOSURE_REMAINING_INITIALIZER) != -1)
+		return false;
+
+	closure_set_ret_ip(cl);
+
+	smp_mb();
+	cl->parent = parent;
+	if (parent)
+		closure_get(parent);
+
+	closure_debug_create(cl);
+	return true;
+}
+EXPORT_SYMBOL_GPL(closure_trylock);
+
+void __closure_lock(struct closure *cl, struct closure *parent,
+		    struct closure_waitlist *wait_list)
+{
+	struct closure wait;
+	closure_init_stack(&wait);
+
+	while (1) {
+		if (closure_trylock(cl, parent))
+			return;
+
+		closure_wait_event_sync(wait_list, &wait,
+					atomic_read(&cl->remaining) == -1);
+	}
+}
+EXPORT_SYMBOL_GPL(__closure_lock);
+
+static void closure_delay_timer_fn(unsigned long data)
+{
+	struct closure *cl = (struct closure *) data;
+	closure_sub(cl, CLOSURE_TIMER + 1);
+}
+
+void do_closure_timer_init(struct closure *cl)
+{
+	struct timer_list *timer = closure_timer(cl);
+
+	init_timer(timer);
+	timer->data	= (unsigned long) cl;
+	timer->function = closure_delay_timer_fn;
+}
+EXPORT_SYMBOL_GPL(do_closure_timer_init);
+
+bool __closure_delay(struct closure *cl, unsigned long delay,
+		     struct timer_list *timer)
+{
+	if (atomic_read(&cl->remaining) & CLOSURE_TIMER)
+		return false;
+
+	BUG_ON(timer_pending(timer));
+
+	timer->expires	= jiffies + delay;
+
+	atomic_add(CLOSURE_TIMER + 1, &cl->remaining);
+	add_timer(timer);
+	return true;
+}
+EXPORT_SYMBOL_GPL(__closure_delay);
+
+void __closure_flush(struct closure *cl, struct timer_list *timer)
+{
+	if (del_timer(timer))
+		closure_sub(cl, CLOSURE_TIMER + 1);
+}
+EXPORT_SYMBOL_GPL(__closure_flush);
+
+void __closure_flush_sync(struct closure *cl, struct timer_list *timer)
+{
+	if (del_timer_sync(timer))
+		closure_sub(cl, CLOSURE_TIMER + 1);
+}
+EXPORT_SYMBOL_GPL(__closure_flush_sync);
+
+#ifdef CONFIG_BCACHE_CLOSURES_DEBUG
+
+static LIST_HEAD(closure_list);
+static DEFINE_SPINLOCK(closure_list_lock);
+
+void closure_debug_create(struct closure *cl)
+{
+	unsigned long flags;
+
+	BUG_ON(cl->magic == CLOSURE_MAGIC_ALIVE);
+	cl->magic = CLOSURE_MAGIC_ALIVE;
+
+	spin_lock_irqsave(&closure_list_lock, flags);
+	list_add(&cl->all, &closure_list);
+	spin_unlock_irqrestore(&closure_list_lock, flags);
+}
+EXPORT_SYMBOL_GPL(closure_debug_create);
+
+void closure_debug_destroy(struct closure *cl)
+{
+	unsigned long flags;
+
+	BUG_ON(cl->magic != CLOSURE_MAGIC_ALIVE);
+	cl->magic = CLOSURE_MAGIC_DEAD;
+
+	spin_lock_irqsave(&closure_list_lock, flags);
+	list_del(&cl->all);
+	spin_unlock_irqrestore(&closure_list_lock, flags);
+}
+EXPORT_SYMBOL_GPL(closure_debug_destroy);
+
+static struct dentry *debug;
+
+#define work_data_bits(work) ((unsigned long *)(&(work)->data))
+
+static int debug_seq_show(struct seq_file *f, void *data)
+{
+	struct closure *cl;
+	spin_lock_irq(&closure_list_lock);
+
+	list_for_each_entry(cl, &closure_list, all) {
+		int r = atomic_read(&cl->remaining);
+
+		seq_printf(f, "%p: %pF -> %pf p %p r %i ",
+			   cl, (void *) cl->ip, cl->fn, cl->parent,
+			   r & CLOSURE_REMAINING_MASK);
+
+		seq_printf(f, "%s%s%s%s%s%s\n",
+			   test_bit(WORK_STRUCT_PENDING,
+				    work_data_bits(&cl->work)) ? "Q" : "",
+			   r & CLOSURE_RUNNING	? "R" : "",
+			   r & CLOSURE_BLOCKING	? "B" : "",
+			   r & CLOSURE_STACK	? "S" : "",
+			   r & CLOSURE_SLEEPING	? "Sl" : "",
+			   r & CLOSURE_TIMER	? "T" : "");
+
+		if (r & CLOSURE_WAITING)
+			seq_printf(f, " W %pF\n",
+				   (void *) cl->waiting_on);
+
+		seq_printf(f, "\n");
+	}
+
+	spin_unlock_irq(&closure_list_lock);
+	return 0;
+}
+
+static int debug_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, debug_seq_show, NULL);
+}
+
+static const struct file_operations debug_ops = {
+	.owner		= THIS_MODULE,
+	.open		= debug_seq_open,
+	.read		= seq_read,
+	.release	= single_release
+};
+
+int __init closure_debug_init(void)
+{
+	debug = debugfs_create_file("closures", 0400, NULL, NULL, &debug_ops);
+	return 0;
+}
+
+module_init(closure_debug_init);
+
+#endif
+
+MODULE_AUTHOR("Kent Overstreet <koverstreet@google.com>");
+MODULE_LICENSE("GPL");

drivers/md/bcache/debug.h

+#ifndef _BCACHE_DEBUG_H
+#define _BCACHE_DEBUG_H
+
+/* Btree/bkey debug printing */
+
+#define KEYHACK_SIZE 80
+struct keyprint_hack {
+	char s[KEYHACK_SIZE];
+};
+
+struct keyprint_hack bch_pkey(const struct bkey *k);
+struct keyprint_hack bch_pbtree(const struct btree *b);
+#define pkey(k)		(&bch_pkey(k).s[0])
+#define pbtree(b)	(&bch_pbtree(b).s[0])
+
+#ifdef CONFIG_BCACHE_EDEBUG
+
+unsigned bch_count_data(struct btree *);
+void bch_check_key_order_msg(struct btree *, struct bset *, const char *, ...);
+void bch_check_keys(struct btree *, const char *, ...);
+
+#define bch_check_key_order(b, i)			\
+	bch_check_key_order_msg(b, i, "keys out of order")
+#define EBUG_ON(cond)		BUG_ON(cond)
+
+#else /* EDEBUG */
+
+#define bch_count_data(b)				0
+#define bch_check_key_order(b, i)			do {} while (0)
+#define bch_check_key_order_msg(b, i, ...)		do {} while (0)
+#define bch_check_keys(b, ...)				do {} while (0)
+#define EBUG_ON(cond)					do {} while (0)
+
+#endif
+
+#ifdef CONFIG_BCACHE_DEBUG
+
+void bch_btree_verify(struct btree *, struct bset *);
+void bch_data_verify(struct search *);
+
+#else /* DEBUG */
+
+static inline void bch_btree_verify(struct btree *b, struct bset *i) {}
+static inline void bch_data_verify(struct search *s) {};
+
+#endif
+
+#ifdef CONFIG_DEBUG_FS
+void bch_debug_init_cache_set(struct cache_set *);
+#else
+static inline void bch_debug_init_cache_set(struct cache_set *c) {}
+#endif
+
+#endif

drivers/md/bcache/journal.h

+#ifndef _BCACHE_JOURNAL_H
+#define _BCACHE_JOURNAL_H
+
+/*
+ * THE JOURNAL:
+ *
+ * The journal is treated as a circular buffer of buckets - a journal entry
+ * never spans two buckets. This means (not implemented yet) we can resize the
+ * journal at runtime, and will be needed for bcache on raw flash support.
+ *
+ * Journal entries contain a list of keys, ordered by the time they were
+ * inserted; thus journal replay just has to reinsert the keys.
+ *
+ * We also keep some things in the journal header that are logically part of the
+ * superblock - all the things that are frequently updated. This is for future
+ * bcache on raw flash support; the superblock (which will become another
+ * journal) can't be moved or wear leveled, so it contains just enough
+ * information to find the main journal, and the superblock only has to be
+ * rewritten when we want to move/wear level the main journal.
+ *
+ * Currently, we don't journal BTREE_REPLACE operations - this will hopefully be
+ * fixed eventually. This isn't a bug - BTREE_REPLACE is used for insertions
+ * from cache misses, which don't have to be journaled, and for writeback and
+ * moving gc we work around it by flushing the btree to disk before updating the
+ * gc information. But it is a potential issue with incremental garbage
+ * collection, and it's fragile.
+ *
+ * OPEN JOURNAL ENTRIES:
+ *
+ * Each journal entry contains, in the header, the sequence number of the last
+ * journal entry still open - i.e. that has keys that haven't been flushed to
+ * disk in the btree.
+ *
+ * We track this by maintaining a refcount for every open journal entry, in a
+ * fifo; each entry in the fifo corresponds to a particular journal
+ * entry/sequence number. When the refcount at the tail of the fifo goes to
+ * zero, we pop it off - thus, the size of the fifo tells us the number of open
+ * journal entries
+ *
+ * We take a refcount on a journal entry when we add some keys to a journal
+ * entry that we're going to insert (held by struct btree_op), and then when we
+ * insert those keys into the btree the btree write we're setting up takes a
+ * copy of that refcount (held by struct btree_write). That refcount is dropped
+ * when the btree write completes.
+ *
+ * A struct btree_write can only hold a refcount on a single journal entry, but
+ * might contain keys for many journal entries - we handle this by making sure
+ * it always has a refcount on the _oldest_ journal entry of all the journal
+ * entries it has keys for.
+ *
+ * JOURNAL RECLAIM:
+ *
+ * As mentioned previously, our fifo of refcounts tells us the number of open
+ * journal entries; from that and the current journal sequence number we compute
+ * last_seq - the oldest journal entry we still need. We write last_seq in each
+ * journal entry, and we also have to keep track of where it exists on disk so
+ * we don't overwrite it when we loop around the journal.
+ *
+ * To do that we track, for each journal bucket, the sequence number of the
+ * newest journal entry it contains - if we don't need that journal entry we
+ * don't need anything in that bucket anymore. From that we track the last
+ * journal bucket we still need; all this is tracked in struct journal_device
+ * and updated by journal_reclaim().
+ *
+ * JOURNAL FILLING UP:
+ *
+ * There are two ways the journal could fill up; either we could run out of
+ * space to write to, or we could have too many open journal entries and run out
+ * of room in the fifo of refcounts. Since those refcounts are decremented
+ * without any locking we can't safely resize that fifo, so we handle it the
+ * same way.
+ *
+ * If the journal fills up, we start flushing dirty btree nodes until we can
+ * allocate space for a journal write again - preferentially flushing btree
+ * nodes that are pinning the oldest journal entries first.
+ */
+
+#define BCACHE_JSET_VERSION_UUIDv1	1
+/* Always latest UUID format */
+#define BCACHE_JSET_VERSION_UUID	1
+#define BCACHE_JSET_VERSION		1
+
+/*
+ * On disk format for a journal entry:
+ * seq is monotonically increasing; every journal entry has its own unique
+ * sequence number.
+ *
+ * last_seq is the oldest journal entry that still has keys the btree hasn't
+ * flushed to disk yet.
+ *
+ * version is for on disk format changes.
+ */
+struct jset {
+	uint64_t		csum;
+	uint64_t		magic;
+	uint64_t		seq;
+	uint32_t		version;
+	uint32_t		keys;
+
+	uint64_t		last_seq;
+
+	BKEY_PADDED(uuid_bucket);
+	BKEY_PADDED(btree_root);
+	uint16_t		btree_level;
+	uint16_t		pad[3];
+
+	uint64_t		prio_bucket[MAX_CACHES_PER_SET];
+
+	union {
+		struct bkey	start[0];
+		uint64_t	d[0];
+	};
+};
+
+/*
+ * Only used for holding the journal entries we read in btree_journal_read()
+ * during cache_registration
+ */
+struct journal_replay {
+	struct list_head	list;
+	atomic_t		*pin;
+	struct jset		j;
+};
+
+/*
+ * We put two of these in struct journal; we used them for writes to the
+ * journal that are being staged or in flight.
+ */
+struct journal_write {
+	struct jset		*data;
+#define JSET_BITS		3
+
+	struct cache_set	*c;
+	struct closure_waitlist	wait;
+	bool			need_write;
+};
+
+/* Embedded in struct cache_set */
+struct journal {
+	spinlock_t		lock;
+	/* used when waiting because the journal was full */
+	struct closure_waitlist	wait;
+	struct closure_with_timer io;
+
+	/* Number of blocks free in the bucket(s) we're currently writing to */
+	unsigned		blocks_free;
+	uint64_t		seq;
+	DECLARE_FIFO(atomic_t, pin);
+
+	BKEY_PADDED(key);
+
+	struct journal_write	w[2], *cur;
+};
+
+/*
+ * Embedded in struct cache. First three fields refer to the array of journal
+ * buckets, in cache_sb.
+ */
+struct journal_device {
+	/*
+	 * For each journal bucket, contains the max sequence number of the
+	 * journal writes it contains - so we know when a bucket can be reused.
+	 */
+	uint64_t		seq[SB_JOURNAL_BUCKETS];
+
+	/* Journal bucket we're currently writing to */
+	unsigned		cur_idx;
+
+	/* Last journal bucket that still contains an open journal entry */
+	unsigned		last_idx;
+
+	/* Next journal bucket to be discarded */
+	unsigned		discard_idx;
+
+#define DISCARD_READY		0
+#define DISCARD_IN_FLIGHT	1
+#define DISCARD_DONE		2
+	/* 1 - discard in flight, -1 - discard completed */
+	atomic_t		discard_in_flight;
+
+	struct work_struct	discard_work;
+	struct bio		discard_bio;
+	struct bio_vec		discard_bv;
+
+	/* Bio for journal reads/writes to this device */
+	struct bio		bio;
+	struct bio_vec		bv[8];
+};
+
+#define journal_pin_cmp(c, l, r)				\
+	(fifo_idx(&(c)->journal.pin, (l)->journal) >		\
+	 fifo_idx(&(c)->journal.pin, (r)->journal))
+
+#define JOURNAL_PIN	20000
+
+#define journal_full(j)						\
+	(!(j)->blocks_free || fifo_free(&(j)->pin) <= 1)
+
+struct closure;
+struct cache_set;
+struct btree_op;
+
+void bch_journal(struct closure *);
+void bch_journal_next(struct journal *);
+void bch_journal_mark(struct cache_set *, struct list_head *);
+void bch_journal_meta(struct cache_set *, struct closure *);
+int bch_journal_read(struct cache_set *, struct list_head *,
+			struct btree_op *);
+int bch_journal_replay(struct cache_set *, struct list_head *,
+			  struct btree_op *);
+
+void bch_journal_free(struct cache_set *);
+int bch_journal_alloc(struct cache_set *);
+
+#endif /* _BCACHE_JOURNAL_H */

include/linux/cgroup_subsys.h

@@ -78,3 +78,9 @@ SUBSYS(hugetlb)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_BCACHE
+SUBSYS(bcache)
+#endif
+
+/* */