Merge branch 'for-3.14/drivers' of git://git.kernel.dk/linux-block

Pull block IO driver changes from Jens Axboe:

 - bcache update from Kent Overstreet.

 - two bcache fixes from Nicholas Swenson.

 - cciss pci init error fix from Andrew.

 - underflow fix in the parallel IDE pg_write code from Dan Carpenter.
   I'm sure the 1 (or 0) users of that are now happy.

 - two PCI related fixes for sx8 from Jingoo Han.

 - floppy init fix for first block read from Jiri Kosina.

 - pktcdvd error return miss fix from Julia Lawall.

 - removal of IRQF_SHARED from the SEGA Dreamcast CD-ROM code from
   Michael Opdenacker.

 - comment typo fix for the loop driver from Olaf Hering.

 - potential oops fix for null_blk from Raghavendra K T.

 - two fixes from Sam Bradshaw (Micron) for the mtip32xx driver, fixing
   an OOM problem and a problem with handling security locked conditions

* 'for-3.14/drivers' of git://git.kernel.dk/linux-block: (47 commits)
  mg_disk: Spelling s/finised/finished/
  null_blk: Null pointer deference problem in alloc_page_buffers
  mtip32xx: Correctly handle security locked condition
  mtip32xx: Make SGL container per-command to eliminate high order dma allocation
  drivers/block/loop.c: fix comment typo in loop_config_discard
  drivers/block/cciss.c:cciss_init_one(): use proper errnos
  drivers/block/paride/pg.c: underflow bug in pg_write()
  drivers/block/sx8.c: remove unnecessary pci_set_drvdata()
  drivers/block/sx8.c: use module_pci_driver()
  floppy: bail out in open() if drive is not responding to block0 read
  bcache: Fix auxiliary search trees for key size > cacheline size
  bcache: Don't return -EINTR when insert finished
  bcache: Improve bucket_prio() calculation
  bcache: Add bch_bkey_equal_header()
  bcache: update bch_bkey_try_merge
  bcache: Move insert_fixup() to btree_keys_ops
  bcache: Convert sorting to btree_keys
  bcache: Convert debug code to btree_keys
  bcache: Convert btree_iter to struct btree_keys
  bcache: Refactor bset_tree sysfs stats
  ...

1 files changed, 36 insertions, 46 deletions

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index dbdbca5a9591..0c707e4f4eaf 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -187,6 +187,7 @@
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
+#include "bset.h"
 #include "util.h"
 #include "closure.h"
 
@@ -309,7 +310,8 @@ struct cached_dev {
 	struct cache_sb		sb;
 	struct bio		sb_bio;
 	struct bio_vec		sb_bv[1];
-	struct closure_with_waitlist sb_write;
+	struct closure		sb_write;
+	struct semaphore	sb_write_mutex;
 
 	/* Refcount on the cache set. Always nonzero when we're caching. */
 	atomic_t		count;
@@ -382,12 +384,12 @@ struct cached_dev {
 	unsigned		writeback_rate_p_term_inverse;
 };
 
-enum alloc_watermarks {
-	WATERMARK_PRIO,
-	WATERMARK_METADATA,
-	WATERMARK_MOVINGGC,
-	WATERMARK_NONE,
-	WATERMARK_MAX
+enum alloc_reserve {
+	RESERVE_BTREE,
+	RESERVE_PRIO,
+	RESERVE_MOVINGGC,
+	RESERVE_NONE,
+	RESERVE_NR,
 };
 
 struct cache {
@@ -399,8 +401,6 @@ struct cache {
 	struct kobject		kobj;
 	struct block_device	*bdev;
 
-	unsigned		watermark[WATERMARK_MAX];
-
 	struct task_struct	*alloc_thread;
 
 	struct closure		prio;
@@ -429,7 +429,7 @@ struct cache {
 	 * because all the data they contained was overwritten), so we only
 	 * need to discard them before they can be moved to the free list.
 	 */
-	DECLARE_FIFO(long, free);
+	DECLARE_FIFO(long, free)[RESERVE_NR];
 	DECLARE_FIFO(long, free_inc);
 	DECLARE_FIFO(long, unused);
 
@@ -514,7 +514,8 @@ struct cache_set {
 	uint64_t		cached_dev_sectors;
 	struct closure		caching;
 
-	struct closure_with_waitlist sb_write;
+	struct closure		sb_write;
+	struct semaphore	sb_write_mutex;
 
 	mempool_t		*search;
 	mempool_t		*bio_meta;
@@ -629,13 +630,15 @@ struct cache_set {
 
 #ifdef CONFIG_BCACHE_DEBUG
 	struct btree		*verify_data;
+	struct bset		*verify_ondisk;
 	struct mutex		verify_lock;
 #endif
 
 	unsigned		nr_uuids;
 	struct uuid_entry	*uuids;
 	BKEY_PADDED(uuid_bucket);
-	struct closure_with_waitlist uuid_write;
+	struct closure		uuid_write;
+	struct semaphore	uuid_write_mutex;
 
 	/*
 	 * A btree node on disk could have too many bsets for an iterator to fit
@@ -643,13 +646,7 @@ struct cache_set {
 	 */
 	mempool_t		*fill_iter;
 
-	/*
-	 * btree_sort() is a merge sort and requires temporary space - single
-	 * element mempool
-	 */
-	struct mutex		sort_lock;
-	struct bset		*sort;
-	unsigned		sort_crit_factor;
+	struct bset_sort_state	sort;
 
 	/* List of buckets we're currently writing data to */
 	struct list_head	data_buckets;
@@ -665,7 +662,6 @@ struct cache_set {
 	unsigned		congested_read_threshold_us;
 	unsigned		congested_write_threshold_us;
 
-	struct time_stats	sort_time;
 	struct time_stats	btree_gc_time;
 	struct time_stats	btree_split_time;
 	struct time_stats	btree_read_time;
@@ -683,9 +679,9 @@ struct cache_set {
 	unsigned		error_decay;
 
 	unsigned short		journal_delay_ms;
+	bool			expensive_debug_checks;
 	unsigned		verify:1;
 	unsigned		key_merging_disabled:1;
-	unsigned		expensive_debug_checks:1;
 	unsigned		gc_always_rewrite:1;
 	unsigned		shrinker_disabled:1;
 	unsigned		copy_gc_enabled:1;
@@ -707,13 +703,8 @@ struct bbio {
 	struct bio		bio;
 };
 
-static inline unsigned local_clock_us(void)
-{
-	return local_clock() >> 10;
-}
-
 #define BTREE_PRIO		USHRT_MAX
-#define INITIAL_PRIO		32768
+#define INITIAL_PRIO		32768U
 
 #define btree_bytes(c)		((c)->btree_pages * PAGE_SIZE)
 #define btree_blocks(b)							\
@@ -726,21 +717,6 @@ static inline unsigned local_clock_us(void)
 #define bucket_bytes(c)		((c)->sb.bucket_size << 9)
 #define block_bytes(c)		((c)->sb.block_size << 9)
 
-#define __set_bytes(i, k)	(sizeof(*(i)) + (k) * sizeof(uint64_t))
-#define set_bytes(i)		__set_bytes(i, i->keys)
-
-#define __set_blocks(i, k, c)	DIV_ROUND_UP(__set_bytes(i, k), block_bytes(c))
-#define set_blocks(i, c)	__set_blocks(i, (i)->keys, c)
-
-#define node(i, j)		((struct bkey *) ((i)->d + (j)))
-#define end(i)			node(i, (i)->keys)
-
-#define index(i, b)							\
-	((size_t) (((void *) i - (void *) (b)->sets[0].data) /		\
-		   block_bytes(b->c)))
-
-#define btree_data_space(b)	(PAGE_SIZE << (b)->page_order)
-
 #define prios_per_bucket(c)				\
 	((bucket_bytes(c) - sizeof(struct prio_set)) /	\
 	 sizeof(struct bucket_disk))
@@ -783,20 +759,34 @@ static inline struct bucket *PTR_BUCKET(struct cache_set *c,
 	return PTR_CACHE(c, k, ptr)->buckets + PTR_BUCKET_NR(c, k, ptr);
 }
 
-/* Btree key macros */
+static inline uint8_t gen_after(uint8_t a, uint8_t b)
+{
+	uint8_t r = a - b;
+	return r > 128U ? 0 : r;
+}
 
-static inline void bkey_init(struct bkey *k)
+static inline uint8_t ptr_stale(struct cache_set *c, const struct bkey *k,
+				unsigned i)
 {
-	*k = ZERO_KEY;
+	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);
+}
+
+/* Btree key macros */
+
 /*
  * This is used for various on disk data structures - cache_sb, prio_set, bset,
  * jset: The checksum is _always_ the first 8 bytes of these structs
  */
 #define csum_set(i)							\
 	bch_crc64(((void *) (i)) + sizeof(uint64_t),			\
-	      ((void *) end(i)) - (((void *) (i)) + sizeof(uint64_t)))
+		  ((void *) bset_bkey_last(i)) -			\
+		  (((void *) (i)) + sizeof(uint64_t)))
 
 /* Error handling macros */