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: Kent 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.

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/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
+
+/* */