Merge branch 'for-2.6.29' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.29' of git://git.kernel.dk/linux-2.6-block: (43 commits)
  bio: get rid of bio_vec clearing
  bounce: don't rely on a zeroed bio_vec list
  cciss: simplify parameters to deregister_disk function
  cfq-iosched: fix race between exiting queue and exiting task
  loop: Do not call loop_unplug for not configured loop device.
  loop: Flush possible running bios when loop device is released.
  alpha: remove dead BIO_VMERGE_BOUNDARY
  Get rid of CONFIG_LSF
  block: make blk_softirq_init() static
  block: use min_not_zero in blk_queue_stack_limits
  block: add one-hit cache for disk partition lookup
  cfq-iosched: remove limit of dispatch depth of max 4 times quantum
  nbd: tell the block layer that it is not a rotational device
  block: get rid of elevator_t typedef
  aio: make the lookup_ioctx() lockless
  bio: add support for inlining a number of bio_vecs inside the bio
  bio: allow individual slabs in the bio_set
  bio: move the slab pointer inside the bio_set
  bio: only mempool back the largest bio_vec slab cache
  block: don't use plugging on SSD devices
  ...

8 files changed, 69 insertions, 40 deletions

diff --git a/include/linux/aio.h b/include/linux/aio.h
index f6b8cf99b59..b16a957030f 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -5,6 +5,7 @@
 #include <linux/workqueue.h>
 #include <linux/aio_abi.h>
 #include <linux/uio.h>
+#include <linux/rcupdate.h>
 
 #include <asm/atomic.h>
 
@@ -183,7 +184,7 @@ struct kioctx {
 
 	/* This needs improving */
 	unsigned long		user_id;
-	struct kioctx		*next;
+	struct hlist_node	list;
 
 	wait_queue_head_t	wait;
 
@@ -199,6 +200,8 @@ struct kioctx {
 	struct aio_ring_info	ring_info;
 
 	struct delayed_work	wq;
+
+	struct rcu_head		rcu_head;
 };
 
 /* prototypes */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 6a642098e5c..18462c5b8ff 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -90,10 +90,11 @@ struct bio {
 
 	unsigned int		bi_comp_cpu;	/* completion CPU */
 
+	atomic_t		bi_cnt;		/* pin count */
+
 	struct bio_vec		*bi_io_vec;	/* the actual vec list */
 
 	bio_end_io_t		*bi_end_io;
-	atomic_t		bi_cnt;		/* pin count */
 
 	void			*bi_private;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
@@ -101,6 +102,13 @@ struct bio {
 #endif
 
 	bio_destructor_t	*bi_destructor;	/* destructor */
+
+	/*
+	 * We can inline a number of vecs at the end of the bio, to avoid
+	 * double allocations for a small number of bio_vecs. This member
+	 * MUST obviously be kept at the very end of the bio.
+	 */
+	struct bio_vec		bi_inline_vecs[0];
 };
 
 /*
@@ -117,6 +125,7 @@ struct bio {
 #define BIO_CPU_AFFINE	8	/* complete bio on same CPU as submitted */
 #define BIO_NULL_MAPPED 9	/* contains invalid user pages */
 #define BIO_FS_INTEGRITY 10	/* fs owns integrity data, not block layer */
+#define BIO_QUIET	11	/* Make BIO Quiet */
 #define bio_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))
 
 /*
@@ -211,6 +220,11 @@ static inline void *bio_data(struct bio *bio)
 	return NULL;
 }
 
+static inline int bio_has_allocated_vec(struct bio *bio)
+{
+	return bio->bi_io_vec && bio->bi_io_vec != bio->bi_inline_vecs;
+}
+
 /*
  * will die
  */
@@ -332,7 +346,7 @@ struct bio_pair {
 extern struct bio_pair *bio_split(struct bio *bi, int first_sectors);
 extern void bio_pair_release(struct bio_pair *dbio);
 
-extern struct bio_set *bioset_create(int, int);
+extern struct bio_set *bioset_create(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
 
 extern struct bio *bio_alloc(gfp_t, int);
@@ -377,6 +391,7 @@ extern struct bio *bio_copy_user_iov(struct request_queue *,
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
 extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *);
+extern void bvec_free_bs(struct bio_set *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
 
 /*
@@ -395,13 +410,17 @@ static inline void bio_set_completion_cpu(struct bio *bio, unsigned int cpu)
  */
 #define BIO_POOL_SIZE 2
 #define BIOVEC_NR_POOLS 6
+#define BIOVEC_MAX_IDX	(BIOVEC_NR_POOLS - 1)
 
 struct bio_set {
+	struct kmem_cache *bio_slab;
+	unsigned int front_pad;
+
 	mempool_t *bio_pool;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	mempool_t *bio_integrity_pool;
 #endif
-	mempool_t *bvec_pools[BIOVEC_NR_POOLS];
+	mempool_t *bvec_pool;
 };
 
 struct biovec_slab {
@@ -411,6 +430,7 @@ struct biovec_slab {
 };
 
 extern struct bio_set *fs_bio_set;
+extern struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly;
 
 /*
  * a small number of entries is fine, not going to be performance critical.
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 031a315c050..7035cec583b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -26,7 +26,6 @@ struct scsi_ioctl_command;
 
 struct request_queue;
 struct elevator_queue;
-typedef struct elevator_queue elevator_t;
 struct request_pm_state;
 struct blk_trace;
 struct request;
@@ -313,7 +312,7 @@ struct request_queue
 	 */
 	struct list_head	queue_head;
 	struct request		*last_merge;
-	elevator_t		*elevator;
+	struct elevator_queue	*elevator;
 
 	/*
 	 * the queue request freelist, one for reads and one for writes
@@ -449,6 +448,7 @@ struct request_queue
 #define QUEUE_FLAG_FAIL_IO     12	/* fake timeout */
 #define QUEUE_FLAG_STACKABLE   13	/* supports request stacking */
 #define QUEUE_FLAG_NONROT      14	/* non-rotational device (SSD) */
+#define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
 
 static inline int queue_is_locked(struct request_queue *q)
 {
@@ -522,22 +522,32 @@ enum {
 	 * TAG_FLUSH	: ordering by tag w/ pre and post flushes
 	 * TAG_FUA	: ordering by tag w/ pre flush and FUA write
 	 */
-	QUEUE_ORDERED_NONE	= 0x00,
-	QUEUE_ORDERED_DRAIN	= 0x01,
-	QUEUE_ORDERED_TAG	= 0x02,
-
-	QUEUE_ORDERED_PREFLUSH	= 0x10,
-	QUEUE_ORDERED_POSTFLUSH	= 0x20,
-	QUEUE_ORDERED_FUA	= 0x40,
-
-	QUEUE_ORDERED_DRAIN_FLUSH = QUEUE_ORDERED_DRAIN |
-			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH,
-	QUEUE_ORDERED_DRAIN_FUA	= QUEUE_ORDERED_DRAIN |
-			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_FUA,
-	QUEUE_ORDERED_TAG_FLUSH	= QUEUE_ORDERED_TAG |
-			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH,
-	QUEUE_ORDERED_TAG_FUA	= QUEUE_ORDERED_TAG |
-			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_FUA,
+	QUEUE_ORDERED_BY_DRAIN		= 0x01,
+	QUEUE_ORDERED_BY_TAG		= 0x02,
+	QUEUE_ORDERED_DO_PREFLUSH	= 0x10,
+	QUEUE_ORDERED_DO_BAR		= 0x20,
+	QUEUE_ORDERED_DO_POSTFLUSH	= 0x40,
+	QUEUE_ORDERED_DO_FUA		= 0x80,
+
+	QUEUE_ORDERED_NONE		= 0x00,
+
+	QUEUE_ORDERED_DRAIN		= QUEUE_ORDERED_BY_DRAIN |
+					  QUEUE_ORDERED_DO_BAR,
+	QUEUE_ORDERED_DRAIN_FLUSH	= QUEUE_ORDERED_DRAIN |
+					  QUEUE_ORDERED_DO_PREFLUSH |
+					  QUEUE_ORDERED_DO_POSTFLUSH,
+	QUEUE_ORDERED_DRAIN_FUA		= QUEUE_ORDERED_DRAIN |
+					  QUEUE_ORDERED_DO_PREFLUSH |
+					  QUEUE_ORDERED_DO_FUA,
+
+	QUEUE_ORDERED_TAG		= QUEUE_ORDERED_BY_TAG |
+					  QUEUE_ORDERED_DO_BAR,
+	QUEUE_ORDERED_TAG_FLUSH		= QUEUE_ORDERED_TAG |
+					  QUEUE_ORDERED_DO_PREFLUSH |
+					  QUEUE_ORDERED_DO_POSTFLUSH,
+	QUEUE_ORDERED_TAG_FUA		= QUEUE_ORDERED_TAG |
+					  QUEUE_ORDERED_DO_PREFLUSH |
+					  QUEUE_ORDERED_DO_FUA,
 
 	/*
 	 * Ordered operation sequence
@@ -585,7 +595,6 @@ enum {
 #define blk_fua_rq(rq)		((rq)->cmd_flags & REQ_FUA)
 #define blk_discard_rq(rq)	((rq)->cmd_flags & REQ_DISCARD)
 #define blk_bidi_rq(rq)		((rq)->next_rq != NULL)
-#define blk_empty_barrier(rq)	(blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors)
 /* rq->queuelist of dequeued request must be list_empty() */
 #define blk_queued_rq(rq)	(!list_empty(&(rq)->queuelist))
 
@@ -855,10 +864,10 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 extern int blk_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *);
-extern int blk_do_ordered(struct request_queue *, struct request **);
+extern bool blk_do_ordered(struct request_queue *, struct request **);
 extern unsigned blk_ordered_cur_seq(struct request_queue *);
 extern unsigned blk_ordered_req_seq(struct request *);
-extern void blk_ordered_complete_seq(struct request_queue *, unsigned, int);
+extern bool blk_ordered_complete_seq(struct request_queue *, unsigned, int);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
@@ -977,7 +986,6 @@ static inline void put_dev_sector(Sector p)
 
 struct work_struct;
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
-void kblockd_flush_work(struct work_struct *work);
 
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 3ce64b90118..8605f8a74df 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -35,6 +35,7 @@ enum bh_state_bits {
 	BH_Ordered,	/* ordered write */
 	BH_Eopnotsupp,	/* operation not supported (barrier) */
 	BH_Unwritten,	/* Buffer is allocated on disk but not written */
+	BH_Quiet,	/* Buffer Error Prinks to be quiet */
 
 	BH_PrivateStart,/* not a state bit, but the first bit available
 			 * for private allocation by other entities
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 92f6f634e3e..7a204256b15 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -28,7 +28,7 @@ typedef void (elevator_activate_req_fn) (struct request_queue *, struct request
 typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct request *);
 
 typedef void *(elevator_init_fn) (struct request_queue *);
-typedef void (elevator_exit_fn) (elevator_t *);
+typedef void (elevator_exit_fn) (struct elevator_queue *);
 
 struct elevator_ops
 {
@@ -62,8 +62,8 @@ struct elevator_ops
 
 struct elv_fs_entry {
 	struct attribute attr;
-	ssize_t (*show)(elevator_t *, char *);
-	ssize_t (*store)(elevator_t *, const char *, size_t);
+	ssize_t (*show)(struct elevator_queue *, char *);
+	ssize_t (*store)(struct elevator_queue *, const char *, size_t);
 };
 
 /*
@@ -130,7 +130,7 @@ extern ssize_t elv_iosched_show(struct request_queue *, char *);
 extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
 
 extern int elevator_init(struct request_queue *, char *);
-extern void elevator_exit(elevator_t *);
+extern void elevator_exit(struct elevator_queue *);
 extern int elv_rq_merge_ok(struct request *, struct bio *);
 
 /*
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 3df7742ce24..16948eaecae 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -126,6 +126,7 @@ struct blk_scsi_cmd_filter {
 struct disk_part_tbl {
 	struct rcu_head rcu_head;
 	int len;
+	struct hd_struct *last_lookup;
 	struct hd_struct *part[];
 };
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index fe825471d5a..9cfc9b627fd 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -232,8 +232,9 @@ struct mm_struct {
 	struct core_state *core_state; /* coredumping support */
 
 	/* aio bits */
-	rwlock_t		ioctx_list_lock;	/* aio lock */
-	struct kioctx		*ioctx_list;
+	spinlock_t		ioctx_lock;
+	struct hlist_head	ioctx_list;
+
 #ifdef CONFIG_MM_OWNER
 	/*
 	 * "owner" points to a task that is regarded as the canonical
diff --git a/include/linux/types.h b/include/linux/types.h
index 1d98330b1f2..121f349cb7e 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -135,19 +135,14 @@ typedef		__s64		int64_t;
  *
  * Linux always considers sectors to be 512 bytes long independently
  * of the devices real block size.
+ *
+ * blkcnt_t is the type of the inode's block count.
  */
 #ifdef CONFIG_LBD
 typedef u64 sector_t;
-#else
-typedef unsigned long sector_t;
-#endif
-
-/*
- * The type of the inode's block count.
- */
-#ifdef CONFIG_LSF
 typedef u64 blkcnt_t;
 #else
+typedef unsigned long sector_t;
 typedef unsigned long blkcnt_t;
 #endif