Merge branch 'for-3.2/core' of git://git.kernel.dk/linux-block

* 'for-3.2/core' of git://git.kernel.dk/linux-block: (29 commits)
  block: don't call blk_drain_queue() if elevator is not up
  blk-throttle: use queue_is_locked() instead of lockdep_is_held()
  blk-throttle: Take blkcg->lock while traversing blkcg->policy_list
  blk-throttle: Free up policy node associated with deleted rule
  block: warn if tag is greater than real_max_depth.
  block: make gendisk hold a reference to its queue
  blk-flush: move the queue kick into
  blk-flush: fix invalid BUG_ON in blk_insert_flush
  block: Remove the control of complete cpu from bio.
  block: fix a typo in the blk-cgroup.h file
  block: initialize the bounce pool if high memory may be added later
  block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown
  block: drop @tsk from attempt_plug_merge() and explain sync rules
  block: make get_request[_wait]() fail if queue is dead
  block: reorganize throtl_get_tg() and blk_throtl_bio()
  block: reorganize queue draining
  block: drop unnecessary blk_get/put_queue() in scsi_cmd_ioctl() and blk_get_tg()
  block: pass around REQ_* flags instead of broken down booleans during request alloc/free
  block: move blk_throtl prototypes to block/blk.h
  block: fix genhd refcounting in blkio_policy_parse_and_set()
  ...

Fix up trivial conflicts due to "mddev_t" -> "struct mddev" conversion
and making the request functions be of type "void" instead of "int" in
 - drivers/md/{faulty.c,linear.c,md.c,md.h,multipath.c,raid0.c,raid1.c,raid10.c,raid5.c}
 - drivers/staging/zram/zram_drv.c

5 files changed, 27 insertions, 39 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index ce33e6868a2..a3c071c9e18 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -269,14 +269,6 @@ extern void bvec_free_bs(struct bio_set *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
 
 /*
- * Allow queuer to specify a completion CPU for this bio
- */
-static inline void bio_set_completion_cpu(struct bio *bio, unsigned int cpu)
-{
-	bio->bi_comp_cpu = cpu;
-}
-
-/*
  * bio_set is used to allow other portions of the IO system to
  * allocate their own private memory pools for bio and iovec structures.
  * These memory pools in turn all allocate from the bio_slab
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 71fc53bb8f1..4053cbd4490 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -59,8 +59,6 @@ struct bio {
 
 	unsigned int		bi_max_vecs;	/* max bvl_vecs we can hold */
 
-	unsigned int		bi_comp_cpu;	/* completion CPU */
-
 	atomic_t		bi_cnt;		/* pin count */
 
 	struct bio_vec		*bi_io_vec;	/* the actual vec list */
@@ -93,11 +91,10 @@ struct bio {
 #define BIO_BOUNCED	5	/* bio is a bounce bio */
 #define BIO_USER_MAPPED 6	/* contains user pages */
 #define BIO_EOPNOTSUPP	7	/* not supported */
-#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_MAPPED_INTEGRITY 12/* integrity metadata has been remapped */
+#define BIO_NULL_MAPPED 8	/* contains invalid user pages */
+#define BIO_FS_INTEGRITY 9	/* fs owns integrity data, not block layer */
+#define BIO_QUIET	10	/* Make BIO Quiet */
+#define BIO_MAPPED_INTEGRITY 11/* integrity metadata has been remapped */
 #define bio_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))
 
 /*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7fbaa910334..5267cd2f20d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -195,7 +195,7 @@ struct request_pm_state
 #include <linux/elevator.h>
 
 typedef void (request_fn_proc) (struct request_queue *q);
-typedef int (make_request_fn) (struct request_queue *q, struct bio *bio);
+typedef void (make_request_fn) (struct request_queue *q, struct bio *bio);
 typedef int (prep_rq_fn) (struct request_queue *, struct request *);
 typedef void (unprep_rq_fn) (struct request_queue *, struct request *);
 
@@ -680,6 +680,8 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 			 struct scsi_ioctl_command __user *);
 
+extern void blk_queue_bio(struct request_queue *q, struct bio *bio);
+
 /*
  * A queue has just exitted congestion.  Note this in the global counter of
  * congested queues, and wake up anyone who was waiting for requests to be
@@ -863,16 +865,22 @@ struct request_queue *blk_alloc_queue_node(gfp_t, int);
 extern void blk_put_queue(struct request_queue *);
 
 /*
- * Note: Code in between changing the blk_plug list/cb_list or element of such
- * lists is preemptable, but such code can't do sleep (or be very careful),
- * otherwise data is corrupted. For details, please check schedule() where
- * blk_schedule_flush_plug() is called.
+ * blk_plug permits building a queue of related requests by holding the I/O
+ * fragments for a short period. This allows merging of sequential requests
+ * into single larger request. As the requests are moved from a per-task list to
+ * the device's request_queue in a batch, this results in improved scalability
+ * as the lock contention for request_queue lock is reduced.
+ *
+ * It is ok not to disable preemption when adding the request to the plug list
+ * or when attempting a merge, because blk_schedule_flush_list() will only flush
+ * the plug list when the task sleeps by itself. For details, please see
+ * schedule() where blk_schedule_flush_plug() is called.
  */
 struct blk_plug {
-	unsigned long magic;
-	struct list_head list;
-	struct list_head cb_list;
-	unsigned int should_sort;
+	unsigned long magic; /* detect uninitialized use-cases */
+	struct list_head list; /* requests */
+	struct list_head cb_list; /* md requires an unplug callback */
+	unsigned int should_sort; /* list to be sorted before flushing? */
 };
 #define BLK_MAX_REQUEST_COUNT 16
 
@@ -1189,20 +1197,6 @@ static inline uint64_t rq_io_start_time_ns(struct request *req)
 }
 #endif
 
-#ifdef CONFIG_BLK_DEV_THROTTLING
-extern int blk_throtl_init(struct request_queue *q);
-extern void blk_throtl_exit(struct request_queue *q);
-extern int blk_throtl_bio(struct request_queue *q, struct bio **bio);
-#else /* CONFIG_BLK_DEV_THROTTLING */
-static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio)
-{
-	return 0;
-}
-
-static inline int blk_throtl_init(struct request_queue *q) { return 0; }
-static inline int blk_throtl_exit(struct request_queue *q) { return 0; }
-#endif /* CONFIG_BLK_DEV_THROTTLING */
-
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
 #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index d800d514218..1d0f7a2ff73 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -38,6 +38,12 @@ struct elevator_ops
 	elevator_merged_fn *elevator_merged_fn;
 	elevator_merge_req_fn *elevator_merge_req_fn;
 	elevator_allow_merge_fn *elevator_allow_merge_fn;
+
+	/*
+	 * Used for both plugged list and elevator merging and in the
+	 * former case called without queue_lock.  Read comment on top of
+	 * attempt_plug_merge() for details.
+	 */
 	elevator_bio_merged_fn *elevator_bio_merged_fn;
 
 	elevator_dispatch_fn *elevator_dispatch_fn;
diff --git a/include/linux/loop.h b/include/linux/loop.h
index 683d6989011..a0688068911 100644
--- a/include/linux/loop.h
+++ b/include/linux/loop.h
@@ -73,7 +73,6 @@ struct loop_device {
  */
 enum {
 	LO_FLAGS_READ_ONLY	= 1,
-	LO_FLAGS_USE_AOPS	= 2,
 	LO_FLAGS_AUTOCLEAR	= 4,
 };