Merge branch 'for-linus' into for-2.6.33

15 files changed, 228 insertions, 201 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 81f3431..ac0fa10 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -70,7 +70,7 @@ static void drive_stat_acct(struct request *rq, int new_io)
 		part_stat_inc(cpu, part, merges[rw]);
 	else {
 		part_round_stats(cpu, part);
-		part_inc_in_flight(part);
+		part_inc_in_flight(part, rw);
 	}
 
 	part_stat_unlock();
@@ -1030,9 +1030,9 @@ static void part_round_stats_single(int cpu, struct hd_struct *part,
 	if (now == part->stamp)
 		return;
 
-	if (part->in_flight) {
+	if (part_in_flight(part)) {
 		__part_stat_add(cpu, part, time_in_queue,
-				part->in_flight * (now - part->stamp));
+				part_in_flight(part) * (now - part->stamp));
 		__part_stat_add(cpu, part, io_ticks, (now - part->stamp));
 	}
 	part->stamp = now;
@@ -1739,7 +1739,7 @@ static void blk_account_io_done(struct request *req)
 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);
 		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
+		part_dec_in_flight(part, rw);
 
 		part_stat_unlock();
 	}
@@ -2492,14 +2492,6 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
 }
 EXPORT_SYMBOL(kblockd_schedule_work);
 
-int kblockd_schedule_delayed_work(struct request_queue *q,
-				  struct delayed_work *work,
-				  unsigned long delay)
-{
-	return queue_delayed_work(kblockd_workqueue, work, delay);
-}
-EXPORT_SYMBOL(kblockd_schedule_delayed_work);
-
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
diff --git a/block/blk-merge.c b/block/blk-merge.c
index b0de857..99cb5cf 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -351,7 +351,7 @@ static void blk_account_io_merge(struct request *req)
 		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
 
 		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
+		part_dec_in_flight(part, rq_data_dir(req));
 
 		part_stat_unlock();
 	}
diff --git a/block/blk-settings.c b/block/blk-settings.c
index e0695bc..66d4aa8 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -242,7 +242,7 @@ EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 /**
  * blk_queue_max_discard_sectors - set max sectors for a single discard
  * @q:  the request queue for the device
- * @max_discard: maximum number of sectors to discard
+ * @max_discard_sectors: maximum number of sectors to discard
  **/
 void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors)
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 2e5cfeb..6b0f52c 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -359,7 +359,7 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 		max_depth -= 2;
 		if (!max_depth)
 			max_depth = 1;
-		if (q->in_flight[0] > max_depth)
+		if (q->in_flight[BLK_RW_ASYNC] > max_depth)
 			return 1;
 	}
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 9c4b679..069a610 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -150,7 +150,7 @@ struct cfq_data {
 	 * idle window management
 	 */
 	struct timer_list idle_slice_timer;
-	struct delayed_work unplug_work;
+	struct work_struct unplug_work;
 
 	struct cfq_queue *active_queue;
 	struct cfq_io_context *active_cic;
@@ -230,7 +230,7 @@ CFQ_CFQQ_FNS(coop);
 	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
 
 static void cfq_dispatch_insert(struct request_queue *, struct request *);
-static struct cfq_queue *cfq_get_queue(struct cfq_data *, int,
+static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,
 				       struct io_context *, gfp_t);
 static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
 						struct io_context *);
@@ -241,40 +241,35 @@ static inline int rq_in_driver(struct cfq_data *cfqd)
 }
 
 static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
-					    int is_sync)
+					    bool is_sync)
 {
-	return cic->cfqq[!!is_sync];
+	return cic->cfqq[is_sync];
 }
 
 static inline void cic_set_cfqq(struct cfq_io_context *cic,
-				struct cfq_queue *cfqq, int is_sync)
+				struct cfq_queue *cfqq, bool is_sync)
 {
-	cic->cfqq[!!is_sync] = cfqq;
+	cic->cfqq[is_sync] = cfqq;
 }
 
 /*
  * We regard a request as SYNC, if it's either a read or has the SYNC bit
  * set (in which case it could also be direct WRITE).
  */
-static inline int cfq_bio_sync(struct bio *bio)
+static inline bool cfq_bio_sync(struct bio *bio)
 {
-	if (bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO))
-		return 1;
-
-	return 0;
+	return bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO);
 }
 
 /*
  * scheduler run of queue, if there are requests pending and no one in the
  * driver that will restart queueing
  */
-static inline void cfq_schedule_dispatch(struct cfq_data *cfqd,
-					 unsigned long delay)
+static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
 {
 	if (cfqd->busy_queues) {
 		cfq_log(cfqd, "schedule dispatch");
-		kblockd_schedule_delayed_work(cfqd->queue, &cfqd->unplug_work,
-						delay);
+		kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work);
 	}
 }
 
@@ -290,7 +285,7 @@ static int cfq_queue_empty(struct request_queue *q)
  * if a queue is marked sync and has sync io queued. A sync queue with async
  * io only, should not get full sync slice length.
  */
-static inline int cfq_prio_slice(struct cfq_data *cfqd, int sync,
+static inline int cfq_prio_slice(struct cfq_data *cfqd, bool sync,
 				 unsigned short prio)
 {
 	const int base_slice = cfqd->cfq_slice[sync];
@@ -318,7 +313,7 @@ cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  * isn't valid until the first request from the dispatch is activated
  * and the slice time set.
  */
-static inline int cfq_slice_used(struct cfq_queue *cfqq)
+static inline bool cfq_slice_used(struct cfq_queue *cfqq)
 {
 	if (cfq_cfqq_slice_new(cfqq))
 		return 0;
@@ -493,7 +488,7 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
  * we will service the queues.
  */
 static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-				 int add_front)
+				 bool add_front)
 {
 	struct rb_node **p, *parent;
 	struct cfq_queue *__cfqq;
@@ -509,11 +504,20 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		} else
 			rb_key += jiffies;
 	} else if (!add_front) {
+		/*
+		 * Get our rb key offset. Subtract any residual slice
+		 * value carried from last service. A negative resid
+		 * count indicates slice overrun, and this should position
+		 * the next service time further away in the tree.
+		 */
 		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
-		rb_key += cfqq->slice_resid;
+		rb_key -= cfqq->slice_resid;
 		cfqq->slice_resid = 0;
-	} else
-		rb_key = 0;
+	} else {
+		rb_key = -HZ;
+		__cfqq = cfq_rb_first(&cfqd->service_tree);
+		rb_key += __cfqq ? __cfqq->rb_key : jiffies;
+	}
 
 	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
 		/*
@@ -547,7 +551,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			n = &(*p)->rb_left;
 		else if (cfq_class_idle(cfqq) > cfq_class_idle(__cfqq))
 			n = &(*p)->rb_right;
-		else if (rb_key < __cfqq->rb_key)
+		else if (time_before(rb_key, __cfqq->rb_key))
 			n = &(*p)->rb_left;
 		else
 			n = &(*p)->rb_right;
@@ -827,8 +831,10 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	 * reposition in fifo if next is older than rq
 	 */
 	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
-	    time_before(next->start_time, rq->start_time))
+	    time_before(rq_fifo_time(next), rq_fifo_time(rq))) {
 		list_move(&rq->queuelist, &next->queuelist);
+		rq_set_fifo_time(rq, rq_fifo_time(next));
+	}
 
 	cfq_remove_request(next);
 }
@@ -844,7 +850,7 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	 * Disallow merge of a sync bio into an async request.
 	 */
 	if (cfq_bio_sync(bio) && !rq_is_sync(rq))
-		return 0;
+		return false;
 
 	/*
 	 * Lookup the cfqq that this bio will be queued with. Allow
@@ -852,13 +858,10 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	 */
 	cic = cfq_cic_lookup(cfqd, current->io_context);
 	if (!cic)
-		return 0;
+		return false;
 
 	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
-	if (cfqq == RQ_CFQQ(rq))
-		return 1;
-
-	return 0;
+	return cfqq == RQ_CFQQ(rq);
 }
 
 static void __cfq_set_active_queue(struct cfq_data *cfqd,
@@ -886,7 +889,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
  */
 static void
 __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-		    int timed_out)
+		    bool timed_out)
 {
 	cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
 
@@ -914,7 +917,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	}
 }
 
-static inline void cfq_slice_expired(struct cfq_data *cfqd, int timed_out)
+static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 
@@ -1026,7 +1029,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
  */
 static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 					      struct cfq_queue *cur_cfqq,
-					      int probe)
+					      bool probe)
 {
 	struct cfq_queue *cfqq;
 
@@ -1090,6 +1093,15 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	if (!cic || !atomic_read(&cic->ioc->nr_tasks))
 		return;
 
+	/*
+	 * If our average think time is larger than the remaining time
+	 * slice, then don't idle. This avoids overrunning the allotted
+	 * time slice.
+	 */
+	if (sample_valid(cic->ttime_samples) &&
+	    (cfqq->slice_end - jiffies < cic->ttime_mean))
+		return;
+
 	cfq_mark_cfqq_wait_request(cfqq);
 
 	/*
@@ -1129,9 +1141,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
  */
 static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 {
-	struct cfq_data *cfqd = cfqq->cfqd;
-	struct request *rq;
-	int fifo;
+	struct request *rq = NULL;
 
 	if (cfq_cfqq_fifo_expire(cfqq))
 		return NULL;
@@ -1141,13 +1151,11 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 	if (list_empty(&cfqq->fifo))
 		return NULL;
 
-	fifo = cfq_cfqq_sync(cfqq);
 	rq = rq_entry_fifo(cfqq->fifo.next);
-
-	if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo]))
+	if (time_before(jiffies, rq_fifo_time(rq)))
 		rq = NULL;
 
-	cfq_log_cfqq(cfqd, cfqq, "fifo=%p", rq);
+	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
 	return rq;
 }
 
@@ -1248,67 +1256,21 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 	return dispatched;
 }
 
-/*
- * Dispatch a request from cfqq, moving them to the request queue
- * dispatch list.
- */
-static void cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	struct request *rq;
-
-	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
-
-	/*
-	 * follow expired path, else get first next available
-	 */
-	rq = cfq_check_fifo(cfqq);
-	if (!rq)
-		rq = cfqq->next_rq;
-
-	/*
-	 * insert request into driver dispatch list
-	 */
-	cfq_dispatch_insert(cfqd->queue, rq);
-
-	if (!cfqd->active_cic) {
-		struct cfq_io_context *cic = RQ_CIC(rq);
-
-		atomic_long_inc(&cic->ioc->refcount);
-		cfqd->active_cic = cic;
-	}
-}
-
-/*
- * Find the cfqq that we need to service and move a request from that to the
- * dispatch list
- */
-static int cfq_dispatch_requests(struct request_queue *q, int force)
-{
-	struct cfq_data *cfqd = q->elevator->elevator_data;
-	struct cfq_queue *cfqq;
 	unsigned int max_dispatch;
 
-	if (!cfqd->busy_queues)
-		return 0;
-
-	if (unlikely(force))
-		return cfq_forced_dispatch(cfqd);
-
-	cfqq = cfq_select_queue(cfqd);
-	if (!cfqq)
-		return 0;
-
 	/*
 	 * Drain async requests before we start sync IO
 	 */
 	if (cfq_cfqq_idle_window(cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC])
-		return 0;
+		return false;
 
 	/*
 	 * If this is an async queue and we have sync IO in flight, let it wait
 	 */
 	if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
-		return 0;
+		return false;
 
 	max_dispatch = cfqd->cfq_quantum;
 	if (cfq_class_idle(cfqq))
@@ -1322,13 +1284,13 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 		 * idle queue must always only have a single IO in flight
 		 */
 		if (cfq_class_idle(cfqq))
-			return 0;
+			return false;
 
 		/*
 		 * We have other queues, don't allow more IO from this one
 		 */
 		if (cfqd->busy_queues > 1)
-			return 0;
+			return false;
 
 		/*
 		 * Sole queue user, allow bigger slice
@@ -1352,13 +1314,72 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 			max_dispatch = depth;
 	}
 
-	if (cfqq->dispatched >= max_dispatch)
+	/*
+	 * If we're below the current max, allow a dispatch
+	 */
+	return cfqq->dispatched < max_dispatch;
+}
+
+/*
+ * Dispatch a request from cfqq, moving them to the request queue
+ * dispatch list.
+ */
+static bool cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	struct request *rq;
+
+	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
+
+	if (!cfq_may_dispatch(cfqd, cfqq))
+		return false;
+
+	/*
+	 * follow expired path, else get first next available
+	 */
+	rq = cfq_check_fifo(cfqq);
+	if (!rq)
+		rq = cfqq->next_rq;
+
+	/*
+	 * insert request into driver dispatch list
+	 */
+	cfq_dispatch_insert(cfqd->queue, rq);
+
+	if (!cfqd->active_cic) {
+		struct cfq_io_context *cic = RQ_CIC(rq);
+
+		atomic_long_inc(&cic->ioc->refcount);
+		cfqd->active_cic = cic;
+	}
+
+	return true;
+}
+
+/*
+ * Find the cfqq that we need to service and move a request from that to the
+ * dispatch list
+ */
+static int cfq_dispatch_requests(struct request_queue *q, int force)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+	struct cfq_queue *cfqq;
+
+	if (!cfqd->busy_queues)
+		return 0;
+
+	if (unlikely(force))
+		return cfq_forced_dispatch(cfqd);
+
+	cfqq = cfq_select_queue(cfqd);
+	if (!cfqq)
 		return 0;
 
 	/*
-	 * Dispatch a request from this cfqq
+	 * Dispatch a request from this cfqq, if it is allowed
 	 */
-	cfq_dispatch_request(cfqd, cfqq);
+	if (!cfq_dispatch_request(cfqd, cfqq))
+		return 0;
+
 	cfqq->slice_dispatch++;
 	cfq_clear_cfqq_must_dispatch(cfqq);
 
@@ -1399,7 +1420,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 
 	if (unlikely(cfqd->active_queue == cfqq)) {
 		__cfq_slice_expired(cfqd, cfqq, 0);
-		cfq_schedule_dispatch(cfqd, 0);
+		cfq_schedule_dispatch(cfqd);
 	}
 
 	kmem_cache_free(cfq_pool, cfqq);
@@ -1494,7 +1515,7 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	if (unlikely(cfqq == cfqd->active_queue)) {
 		__cfq_slice_expired(cfqd, cfqq, 0);
-		cfq_schedule_dispatch(cfqd, 0);
+		cfq_schedule_dispatch(cfqd);
 	}
 
 	cfq_put_queue(cfqq);
@@ -1658,7 +1679,7 @@ static void cfq_ioc_set_ioprio(struct io_context *ioc)
 }
 
 static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-			  pid_t pid, int is_sync)
+			  pid_t pid, bool is_sync)
 {
 	RB_CLEAR_NODE(&cfqq->rb_node);
 	RB_CLEAR_NODE(&cfqq->p_node);
@@ -1678,7 +1699,7 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 }
 
 static struct cfq_queue *
-cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync,
+cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
 		     struct io_context *ioc, gfp_t gfp_mask)
 {
 	struct cfq_queue *cfqq, *new_cfqq = NULL;
@@ -1742,7 +1763,7 @@ cfq_async_queue_prio(struct cfq_data *cfqd, int ioprio_class, int ioprio)
 }
 
 static struct cfq_queue *
-cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc,
+cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct io_context *ioc,
 	      gfp_t gfp_mask)
 {
 	const int ioprio = task_ioprio(ioc);
@@ -1977,7 +1998,10 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	    (!cfqd->cfq_latency && cfqd->hw_tag && CIC_SEEKY(cic)))
 		enable_idle = 0;
 	else if (sample_valid(cic->ttime_samples)) {
-		if (cic->ttime_mean > cfqd->cfq_slice_idle)
+		unsigned int slice_idle = cfqd->cfq_slice_idle;
+		if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic))
+			slice_idle = msecs_to_jiffies(CFQ_MIN_TT);
+		if (cic->ttime_mean > slice_idle)
 			enable_idle = 0;
 		else
 			enable_idle = 1;
@@ -1996,7 +2020,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
  * Check if new_cfqq should preempt the currently active queue. Return 0 for
  * no or if we aren't sure, a 1 will cause a preempt.
  */
-static int
+static bool
 cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 		   struct request *rq)
 {
@@ -2004,48 +2028,48 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 
 	cfqq = cfqd->active_queue;
 	if (!cfqq)
-		return 0;
+		return false;
 
 	if (cfq_slice_used(cfqq))
-		return 1;
+		return true;
 
 	if (cfq_class_idle(new_cfqq))
-		return 0;
+		return false;
 
 	if (cfq_class_idle(cfqq))
-		return 1;
+		return true;
 
 	/*
 	 * if the new request is sync, but the currently running queue is
 	 * not, let the sync request have priority.
 	 */
 	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
-		return 1;
+		return true;
 
 	/*
 	 * So both queues are sync. Let the new request get disk time if
 	 * it's a metadata request and the current queue is doing regular IO.
 	 */
 	if (rq_is_meta(rq) && !cfqq->meta_pending)
-		return 1;
+		return false;
 
 	/*
 	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
 	 */
 	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
-		return 1;
+		return true;
 
 	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
-		return 0;
+		return false;
 
 	/*
 	 * if this request is as-good as one we would expect from the
 	 * current cfqq, let it preempt
 	 */
 	if (cfq_rq_close(cfqd, rq))
-		return 1;
+		return true;
 
-	return 0;
+	return false;
 }
 
 /*
@@ -2130,6 +2154,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 
 	cfq_add_rq_rb(rq);
 
+	rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]);
 	list_add_tail(&rq->queuelist, &cfqq->fifo);
 
 	cfq_rq_enqueued(cfqd, cfqq, rq);
@@ -2211,7 +2236,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	}
 
 	if (!rq_in_driver(cfqd))
-		cfq_schedule_dispatch(cfqd, 0);
+		cfq_schedule_dispatch(cfqd);
 }
 
 /*
@@ -2309,7 +2334,7 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_io_context *cic;
 	const int rw = rq_data_dir(rq);
-	const int is_sync = rq_is_sync(rq);
+	const bool is_sync = rq_is_sync(rq);
 	struct cfq_queue *cfqq;
 	unsigned long flags;
 
@@ -2341,7 +2366,7 @@ queue_fail:
 	if (cic)
 		put_io_context(cic->ioc);
 
-	cfq_schedule_dispatch(cfqd, 0);
+	cfq_schedule_dispatch(cfqd);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 	cfq_log(cfqd, "set_request fail");
 	return 1;
@@ -2350,7 +2375,7 @@ queue_fail:
 static void cfq_kick_queue(struct work_struct *work)
 {
 	struct cfq_data *cfqd =
-		container_of(work, struct cfq_data, unplug_work.work);
+		container_of(work, struct cfq_data, unplug_work);
 	struct request_queue *q = cfqd->queue;
 
 	spin_lock_irq(q->queue_lock);
@@ -2404,7 +2429,7 @@ static void cfq_idle_slice_timer(unsigned long data)
 expire:
 	cfq_slice_expired(cfqd, timed_out);
 out_kick:
-	cfq_schedule_dispatch(cfqd, 0);
+	cfq_schedule_dispatch(cfqd);
 out_cont:
 	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
 }
@@ -2412,7 +2437,7 @@ out_cont:
 static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
 {
 	del_timer_sync(&cfqd->idle_slice_timer);
-	cancel_delayed_work_sync(&cfqd->unplug_work);
+	cancel_work_sync(&cfqd->unplug_work);
 }
 
 static void cfq_put_async_queues(struct cfq_data *cfqd)
@@ -2494,7 +2519,7 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
 	cfqd->idle_slice_timer.data = (unsigned long) cfqd;
 
-	INIT_DELAYED_WORK(&cfqd->unplug_work, cfq_kick_queue);
+	INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);
 
 	cfqd->cfq_quantum = cfq_quantum;
 	cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0];
diff --git a/block/elevator.c b/block/elevator.c
index bb30f0e..9ad5ccc 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -1053,9 +1053,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 		return count;
 
 	strlcpy(elevator_name, name, sizeof(elevator_name));
-	strstrip(elevator_name);
-
-	e = elevator_get(elevator_name);
+	e = elevator_get(strstrip(elevator_name));
 	if (!e) {
 		printk(KERN_ERR "elevator: type %s not found\n", elevator_name);
 		return -EINVAL;
diff --git a/block/genhd.c b/block/genhd.c
index 5a0861d..517e433 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -869,6 +869,7 @@ static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
 static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL);
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
@@ -888,6 +889,7 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_alignment_offset.attr,
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
+	&dev_attr_inflight.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif
@@ -1053,7 +1055,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   part_stat_read(hd, merges[1]),
 			   (unsigned long long)part_stat_read(hd, sectors[1]),
 			   jiffies_to_msecs(part_stat_read(hd, ticks[1])),
-			   hd->in_flight,
+			   part_in_flight(hd),
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
 			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
 			);
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index fb5be2d..6399e50 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -68,6 +68,12 @@ MODULE_SUPPORTED_DEVICE("HP SA5i SA5i+ SA532 SA5300 SA5312 SA641 SA642 SA6400"
 MODULE_VERSION("3.6.20");
 MODULE_LICENSE("GPL");
 
+static int cciss_allow_hpsa;
+module_param(cciss_allow_hpsa, int, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(cciss_allow_hpsa,
+	"Prevent cciss driver from accessing hardware known to be "
+	" supported by the hpsa driver");
+
 #include "cciss_cmd.h"
 #include "cciss.h"
 #include <linux/cciss_ioctl.h>
@@ -101,8 +107,6 @@ static const struct pci_device_id cciss_pci_device_id[] = {
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x3249},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x324A},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x324B},
-	{PCI_VENDOR_ID_HP,     PCI_ANY_ID,	PCI_ANY_ID, PCI_ANY_ID,
-		PCI_CLASS_STORAGE_RAID << 8, 0xffff << 8, 0},
 	{0,}
 };
 
@@ -123,8 +127,6 @@ static struct board_type products[] = {
 	{0x409D0E11, "Smart Array 6400 EM", &SA5_access},
 	{0x40910E11, "Smart Array 6i", &SA5_access},
 	{0x3225103C, "Smart Array P600", &SA5_access},
-	{0x3223103C, "Smart Array P800", &SA5_access},
-	{0x3234103C, "Smart Array P400", &SA5_access},
 	{0x3235103C, "Smart Array P400i", &SA5_access},
 	{0x3211103C, "Smart Array E200i", &SA5_access},
 	{0x3212103C, "Smart Array E200", &SA5_access},
@@ -132,6 +134,10 @@ static struct board_type products[] = {
 	{0x3214103C, "Smart Array E200i", &SA5_access},
 	{0x3215103C, "Smart Array E200i", &SA5_access},
 	{0x3237103C, "Smart Array E500", &SA5_access},
+/* controllers below this line are also supported by the hpsa driver. */
+#define HPSA_BOUNDARY 0x3223103C
+	{0x3223103C, "Smart Array P800", &SA5_access},
+	{0x3234103C, "Smart Array P400", &SA5_access},
 	{0x323D103C, "Smart Array P700m", &SA5_access},
 	{0x3241103C, "Smart Array P212", &SA5_access},
 	{0x3243103C, "Smart Array P410", &SA5_access},
@@ -140,7 +146,6 @@ static struct board_type products[] = {
 	{0x3249103C, "Smart Array P812", &SA5_access},
 	{0x324A103C, "Smart Array P712m", &SA5_access},
 	{0x324B103C, "Smart Array P711m", &SA5_access},
-	{0xFFFF103C, "Unknown Smart Array", &SA5_access},
 };
 
 /* How long to wait (in milliseconds) for board to go into simple mode */
@@ -3754,7 +3759,27 @@ static int __devinit cciss_pci_init(ctlr_info_t *c, struct pci_dev *pdev)
 	__u64 cfg_offset;
 	__u32 cfg_base_addr;
 	__u64 cfg_base_addr_index;
-	int i, err;
+	int i, prod_index, err;
+
+	subsystem_vendor_id = pdev->subsystem_vendor;
+	subsystem_device_id = pdev->subsystem_device;
+	board_id = (((__u32) (subsystem_device_id << 16) & 0xffff0000) |
+		    subsystem_vendor_id);
+
+	for (i = 0; i < ARRAY_SIZE(products); i++) {
+		/* Stand aside for hpsa driver on request */
+		if (cciss_allow_hpsa && products[i].board_id == HPSA_BOUNDARY)
+			return -ENODEV;
+		if (board_id == products[i].board_id)
+			break;
+	}
+	prod_index = i;
+	if (prod_index == ARRAY_SIZE(products)) {
+		dev_warn(&pdev->dev,
+			"unrecognized board ID: 0x%08lx, ignoring.\n",
+			(unsigned long) board_id);
+		return -ENODEV;
+	}
 
 	/* check to see if controller has been disabled */
 	/* BEFORE trying to enable it */
@@ -3778,11 +3803,6 @@ static int __devinit cciss_pci_init(ctlr_info_t *c, struct pci_dev *pdev)
 		return err;
 	}
 
-	subsystem_vendor_id = pdev->subsystem_vendor;
-	subsystem_device_id = pdev->subsystem_device;
-	board_id = (((__u32) (subsystem_device_id << 16) & 0xffff0000) |
-		    subsystem_vendor_id);
-
 #ifdef CCISS_DEBUG
 	printk("command = %x\n", command);
 	printk("irq = %x\n", pdev->irq);
@@ -3868,14 +3888,9 @@ static int __devinit cciss_pci_init(ctlr_info_t *c, struct pci_dev *pdev)
 	 * leave a little room for ioctl calls.
 	 */
 	c->max_commands = readl(&(c->cfgtable->CmdsOutMax));
-	for (i = 0; i < ARRAY_SIZE(products); i++) {
-		if (board_id == products[i].board_id) {
-			c->product_name = products[i].product_name;
-			c->access = *(products[i].access);
-			c->nr_cmds = c->max_commands - 4;
-			break;
-		}
-	}
+	c->product_name = products[prod_index].product_name;
+	c->access = *(products[prod_index].access);
+	c->nr_cmds = c->max_commands - 4;
 	if ((readb(&c->cfgtable->Signature[0]) != 'C') ||
 	    (readb(&c->cfgtable->Signature[1]) != 'I') ||
 	    (readb(&c->cfgtable->Signature[2]) != 'S') ||
@@ -3884,27 +3899,6 @@ static int __devinit cciss_pci_init(ctlr_info_t *c, struct pci_dev *pdev)
 		err = -ENODEV;
 		goto err_out_free_res;
 	}
-	/* We didn't find the controller in our list. We know the
-	 * signature is valid. If it's an HP device let's try to
-	 * bind to the device and fire it up. Otherwise we bail.
-	 */
-	if (i == ARRAY_SIZE(products)) {
-		if (subsystem_vendor_id == PCI_VENDOR_ID_HP) {
-			c->product_name = products[i-1].product_name;
-			c->access = *(products[i-1].access);
-			c->nr_cmds = c->max_commands - 4;
-			printk(KERN_WARNING "cciss: This is an unknown "
-				"Smart Array controller.\n"
-				"cciss: Please update to the latest driver "
-				"available from www.hp.com.\n");
-		} else {
-			printk(KERN_WARNING "cciss: Sorry, I don't know how"
-				" to access the Smart Array controller %08lx\n"
-					, (unsigned long)board_id);
-			err = -ENODEV;
-			goto err_out_free_res;
-		}
-	}
 #ifdef CONFIG_X86
 	{
 		/* Need to enable prefetch in the SCSI core for 6400 in x86 */
@@ -4254,7 +4248,7 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 	mutex_init(&hba[i]->busy_shutting_down);
 
 	if (cciss_pci_init(hba[i], pdev) != 0)
-		goto clean0;
+		goto clean_no_release_regions;
 
 	sprintf(hba[i]->devname, "cciss%d", i);
 	hba[i]->ctlr = i;
@@ -4391,13 +4385,14 @@ clean2:
 clean1:
 	cciss_destroy_hba_sysfs_entry(hba[i]);
 clean0:
+	pci_release_regions(pdev);
+clean_no_release_regions:
 	hba[i]->busy_initializing = 0;
 
 	/*
 	 * Deliberately omit pci_disable_device(): it does something nasty to
 	 * Smart Array controllers that pci_enable_device does not undo
 	 */
-	pci_release_regions(pdev);
 	pci_set_drvdata(pdev, NULL);
 	free_hba(i);
 	return -1;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 23e76fe..376f1ab 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -130,7 +130,7 @@ struct mapped_device {
 	/*
 	 * A list of ios that arrived while we were suspended.
 	 */
-	atomic_t pending;
+	atomic_t pending[2];
 	wait_queue_head_t wait;
 	struct work_struct work;
 	struct bio_list deferred;
@@ -453,13 +453,14 @@ static void start_io_acct(struct dm_io *io)
 {
 	struct mapped_device *md = io->md;
 	int cpu;
+	int rw = bio_data_dir(io->bio);
 
 	io->start_time = jiffies;
 
 	cpu = part_stat_lock();
 	part_round_stats(cpu, &dm_disk(md)->part0);
 	part_stat_unlock();
-	dm_disk(md)->part0.in_flight = atomic_inc_return(&md->pending);
+	dm_disk(md)->part0.in_flight[rw] = atomic_inc_return(&md->pending[rw]);
 }
 
 static void end_io_acct(struct dm_io *io)
@@ -479,8 +480,9 @@ static void end_io_acct(struct dm_io *io)
 	 * After this is decremented the bio must not be touched if it is
 	 * a barrier.
 	 */
-	dm_disk(md)->part0.in_flight = pending =
-		atomic_dec_return(&md->pending);
+	dm_disk(md)->part0.in_flight[rw] = pending =
+		atomic_dec_return(&md->pending[rw]);
+	pending += atomic_read(&md->pending[rw^0x1]);
 
 	/* nudge anyone waiting on suspend queue */
 	if (!pending)
@@ -1785,7 +1787,8 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->disk)
 		goto bad_disk;
 
-	atomic_set(&md->pending, 0);
+	atomic_set(&md->pending[0], 0);
+	atomic_set(&md->pending[1], 0);
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
@@ -2088,7 +2091,8 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible)
 				break;
 			}
 			spin_unlock_irqrestore(q->queue_lock, flags);
-		} else if (!atomic_read(&md->pending))
+		} else if (!atomic_read(&md->pending[0]) &&
+					!atomic_read(&md->pending[1]))
 			break;
 
 		if (interruptible == TASK_INTERRUPTIBLE &&
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index f38fee0..7b685e1 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -248,11 +248,19 @@ ssize_t part_stat_show(struct device *dev,
 		part_stat_read(p, merges[WRITE]),
 		(unsigned long long)part_stat_read(p, sectors[WRITE]),
 		jiffies_to_msecs(part_stat_read(p, ticks[WRITE])),
-		p->in_flight,
+		part_in_flight(p),
 		jiffies_to_msecs(part_stat_read(p, io_ticks)),
 		jiffies_to_msecs(part_stat_read(p, time_in_queue)));
 }
 
+ssize_t part_inflight_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+
+	return sprintf(buf, "%8u %8u\n", p->in_flight[0], p->in_flight[1]);
+}
+
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 ssize_t part_fail_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
@@ -281,6 +289,7 @@ static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
 static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
@@ -292,6 +301,7 @@ static struct attribute *part_attrs[] = {
 	&dev_attr_size.attr,
 	&dev_attr_alignment_offset.attr,
 	&dev_attr_stat.attr,
+	&dev_attr_inflight.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2511904..221cecd 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1172,11 +1172,7 @@ static inline void put_dev_sector(Sector p)
 }
 
 struct work_struct;
-struct delayed_work;
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
-int kblockd_schedule_delayed_work(struct request_queue *q,
-					struct delayed_work *work,
-				 	unsigned long delay);
 
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 7beaa21..297df45 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -98,7 +98,7 @@ struct hd_struct {
 	int make_it_fail;
 #endif
 	unsigned long stamp;
-	int in_flight;
+	int in_flight[2];
 #ifdef	CONFIG_SMP
 	struct disk_stats *dkstats;
 #else
@@ -322,18 +322,23 @@ static inline void free_part_stats(struct hd_struct *part)
 #define part_stat_sub(cpu, gendiskp, field, subnd)			\
 	part_stat_add(cpu, gendiskp, field, -subnd)
 
-static inline void part_inc_in_flight(struct hd_struct *part)
+static inline void part_inc_in_flight(struct hd_struct *part, int rw)
 {
-	part->in_flight++;
+	part->in_flight[rw]++;
 	if (part->partno)
-		part_to_disk(part)->part0.in_flight++;
+		part_to_disk(part)->part0.in_flight[rw]++;
 }
 
-static inline void part_dec_in_flight(struct hd_struct *part)
+static inline void part_dec_in_flight(struct hd_struct *part, int rw)
 {
-	part->in_flight--;
+	part->in_flight[rw]--;
 	if (part->partno)
-		part_to_disk(part)->part0.in_flight--;
+		part_to_disk(part)->part0.in_flight[rw]--;
+}
+
+static inline int part_in_flight(struct hd_struct *part)
+{
+	return part->in_flight[0] + part->in_flight[1];
 }
 
 /* block/blk-core.c */
@@ -546,6 +551,8 @@ extern ssize_t part_size_show(struct device *dev,
 			      struct device_attribute *attr, char *buf);
 extern ssize_t part_stat_show(struct device *dev,
 			      struct device_attribute *attr, char *buf);
+extern ssize_t part_inflight_show(struct device *dev,
+			      struct device_attribute *attr, char *buf);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 extern ssize_t part_fail_show(struct device *dev,
 			      struct device_attribute *attr, char *buf);
diff --git a/kernel/sched.c b/kernel/sched.c
index 1535f38..074f753 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6720,9 +6720,6 @@ EXPORT_SYMBOL(yield);
 /*
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
- *
- * But don't do that if it is a deliberate, throttling IO wait (this task
- * has set its backing_dev_info: the queue against which it should throttle)
  */
 void __sched io_schedule(void)
 {
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 3d3accb..5a37e20 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -92,7 +92,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   "BdiDirtyThresh:   %8lu kB\n"
 		   "DirtyThresh:      %8lu kB\n"
 		   "BackgroundThresh: %8lu kB\n"
-		   "WriteBack threads:%8lu\n"
+		   "WritebackThreads: %8lu\n"
 		   "b_dirty:          %8lu\n"
 		   "b_io:             %8lu\n"
 		   "b_more_io:        %8lu\n"
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a3b1409..2c5d792 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -566,7 +566,8 @@ static void balance_dirty_pages(struct address_space *mapping,
 		if (pages_written >= write_chunk)
 			break;		/* We've done our duty */
 
-		schedule_timeout_interruptible(pause);
+		__set_current_state(TASK_INTERRUPTIBLE);
+		io_schedule_timeout(pause);
 
 		/*
 		 * Increase the delay for each loop, up to our previous