Merge commit 'v2.6.29-rc4' into perfcounters/core

Conflicts:
	arch/x86/kernel/setup_percpu.c
	arch/x86/mm/fault.c
	drivers/acpi/processor_idle.c
	kernel/irq/handle.c

7 files changed, 202 insertions, 102 deletions

diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 8eba4e43bb0c..f7dae57e6cab 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -302,7 +302,7 @@ static void bio_end_empty_barrier(struct bio *bio, int err)
  * Description:
  *    Issue a flush for the block device in question. Caller can supply
  *    room for storing the error offset in case of a flush error, if they
- *    wish to.  Caller must run wait_for_completion() on its own.
+ *    wish to.
  */
 int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 {
diff --git a/block/blk-core.c b/block/blk-core.c
index a824e49c0d0a..29bcfac6c688 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -64,11 +64,12 @@ static struct workqueue_struct *kblockd_workqueue;
 
 static void drive_stat_acct(struct request *rq, int new_io)
 {
+	struct gendisk *disk = rq->rq_disk;
 	struct hd_struct *part;
 	int rw = rq_data_dir(rq);
 	int cpu;
 
-	if (!blk_fs_request(rq) || !rq->rq_disk)
+	if (!blk_fs_request(rq) || !disk || !blk_do_io_stat(disk->queue))
 		return;
 
 	cpu = part_stat_lock();
@@ -599,8 +600,7 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unplug_fn		= generic_unplug_device;
-	q->queue_flags		= (1 << QUEUE_FLAG_CLUSTER |
-				   1 << QUEUE_FLAG_STACKABLE);
+	q->queue_flags		= QUEUE_FLAG_DEFAULT;
 	q->queue_lock		= lock;
 
 	blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
@@ -1125,6 +1125,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 
 	if (bio_sync(bio))
 		req->cmd_flags |= REQ_RW_SYNC;
+	if (bio_unplug(bio))
+		req->cmd_flags |= REQ_UNPLUG;
 	if (bio_rw_meta(bio))
 		req->cmd_flags |= REQ_RW_META;
 
@@ -1141,6 +1143,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	int el_ret, nr_sectors;
 	const unsigned short prio = bio_prio(bio);
 	const int sync = bio_sync(bio);
+	const int unplug = bio_unplug(bio);
 	int rw_flags;
 
 	nr_sectors = bio_sectors(bio);
@@ -1244,7 +1247,7 @@ get_rq:
 		blk_plug_device(q);
 	add_request(q, req);
 out:
-	if (sync || blk_queue_nonrot(q))
+	if (unplug || blk_queue_nonrot(q))
 		__generic_unplug_device(q);
 	spin_unlock_irq(q->queue_lock);
 	return 0;
@@ -1448,6 +1451,11 @@ static inline void __generic_make_request(struct bio *bio)
 			err = -EOPNOTSUPP;
 			goto end_io;
 		}
+		if (bio_barrier(bio) && bio_has_data(bio) &&
+		    (q->next_ordered == QUEUE_ORDERED_NONE)) {
+			err = -EOPNOTSUPP;
+			goto end_io;
+		}
 
 		ret = q->make_request_fn(q, bio);
 	} while (ret);
@@ -1655,6 +1663,55 @@ void blkdev_dequeue_request(struct request *req)
 }
 EXPORT_SYMBOL(blkdev_dequeue_request);
 
+static void blk_account_io_completion(struct request *req, unsigned int bytes)
+{
+	struct gendisk *disk = req->rq_disk;
+
+	if (!disk || !blk_do_io_stat(disk->queue))
+		return;
+
+	if (blk_fs_request(req)) {
+		const int rw = rq_data_dir(req);
+		struct hd_struct *part;
+		int cpu;
+
+		cpu = part_stat_lock();
+		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
+		part_stat_unlock();
+	}
+}
+
+static void blk_account_io_done(struct request *req)
+{
+	struct gendisk *disk = req->rq_disk;
+
+	if (!disk || !blk_do_io_stat(disk->queue))
+		return;
+
+	/*
+	 * Account IO completion.  bar_rq isn't accounted as a normal
+	 * IO on queueing nor completion.  Accounting the containing
+	 * request is enough.
+	 */
+	if (blk_fs_request(req) && req != &req->q->bar_rq) {
+		unsigned long duration = jiffies - req->start_time;
+		const int rw = rq_data_dir(req);
+		struct hd_struct *part;
+		int cpu;
+
+		cpu = part_stat_lock();
+		part = disk_map_sector_rcu(disk, req->sector);
+
+		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_stat_unlock();
+	}
+}
+
 /**
  * __end_that_request_first - end I/O on a request
  * @req:      the request being processed
@@ -1690,16 +1747,7 @@ static int __end_that_request_first(struct request *req, int error,
 				(unsigned long long)req->sector);
 	}
 
-	if (blk_fs_request(req) && req->rq_disk) {
-		const int rw = rq_data_dir(req);
-		struct hd_struct *part;
-		int cpu;
-
-		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
-		part_stat_add(cpu, part, sectors[rw], nr_bytes >> 9);
-		part_stat_unlock();
-	}
+	blk_account_io_completion(req, nr_bytes);
 
 	total_bytes = bio_nbytes = 0;
 	while ((bio = req->bio) != NULL) {
@@ -1779,8 +1827,6 @@ static int __end_that_request_first(struct request *req, int error,
  */
 static void end_that_request_last(struct request *req, int error)
 {
-	struct gendisk *disk = req->rq_disk;
-
 	if (blk_rq_tagged(req))
 		blk_queue_end_tag(req->q, req);
 
@@ -1792,27 +1838,7 @@ static void end_that_request_last(struct request *req, int error)
 
 	blk_delete_timer(req);
 
-	/*
-	 * Account IO completion.  bar_rq isn't accounted as a normal
-	 * IO on queueing nor completion.  Accounting the containing
-	 * request is enough.
-	 */
-	if (disk && blk_fs_request(req) && req != &req->q->bar_rq) {
-		unsigned long duration = jiffies - req->start_time;
-		const int rw = rq_data_dir(req);
-		struct hd_struct *part;
-		int cpu;
-
-		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(disk, req->sector);
-
-		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_stat_unlock();
-	}
+	blk_account_io_done(req);
 
 	if (req->end_io)
 		req->end_io(req, error);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 61a8e2f8fdd0..91fa8e06b6a5 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -309,24 +309,24 @@ static struct kobj_type integrity_ktype = {
 /**
  * blk_integrity_register - Register a gendisk as being integrity-capable
  * @disk:	struct gendisk pointer to make integrity-aware
- * @template:	integrity profile
+ * @template:	optional integrity profile to register
  *
  * Description: When a device needs to advertise itself as being able
  * to send/receive integrity metadata it must use this function to
  * register the capability with the block layer.  The template is a
  * blk_integrity struct with values appropriate for the underlying
- * hardware.  See Documentation/block/data-integrity.txt.
+ * hardware.  If template is NULL the new profile is allocated but
+ * not filled out. See Documentation/block/data-integrity.txt.
  */
 int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 {
 	struct blk_integrity *bi;
 
 	BUG_ON(disk == NULL);
-	BUG_ON(template == NULL);
 
 	if (disk->integrity == NULL) {
 		bi = kmem_cache_alloc(integrity_cachep,
-						GFP_KERNEL | __GFP_ZERO);
+				      GFP_KERNEL | __GFP_ZERO);
 		if (!bi)
 			return -1;
 
@@ -346,13 +346,16 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 		bi = disk->integrity;
 
 	/* Use the provided profile as template */
-	bi->name = template->name;
-	bi->generate_fn = template->generate_fn;
-	bi->verify_fn = template->verify_fn;
-	bi->tuple_size = template->tuple_size;
-	bi->set_tag_fn = template->set_tag_fn;
-	bi->get_tag_fn = template->get_tag_fn;
-	bi->tag_size = template->tag_size;
+	if (template != NULL) {
+		bi->name = template->name;
+		bi->generate_fn = template->generate_fn;
+		bi->verify_fn = template->verify_fn;
+		bi->tuple_size = template->tuple_size;
+		bi->set_tag_fn = template->set_tag_fn;
+		bi->get_tag_fn = template->get_tag_fn;
+		bi->tag_size = template->tag_size;
+	} else
+		bi->name = "unsupported";
 
 	return 0;
 }
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index a29cb788e408..e29ddfc73cf4 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -130,6 +130,27 @@ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_hw_sectors_kb, (page));
 }
 
+static ssize_t queue_nonrot_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(!blk_queue_nonrot(q), page);
+}
+
+static ssize_t queue_nonrot_store(struct request_queue *q, const char *page,
+				  size_t count)
+{
+	unsigned long nm;
+	ssize_t ret = queue_var_store(&nm, page, count);
+
+	spin_lock_irq(q->queue_lock);
+	if (nm)
+		queue_flag_clear(QUEUE_FLAG_NONROT, q);
+	else
+		queue_flag_set(QUEUE_FLAG_NONROT, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(blk_queue_nomerges(q), page);
@@ -146,8 +167,8 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
 		queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	else
 		queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
-
 	spin_unlock_irq(q->queue_lock);
+
 	return ret;
 }
 
@@ -176,6 +197,27 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 	return ret;
 }
 
+static ssize_t queue_iostats_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_io_stat(q), page);
+}
+
+static ssize_t queue_iostats_store(struct request_queue *q, const char *page,
+				   size_t count)
+{
+	unsigned long stats;
+	ssize_t ret = queue_var_store(&stats, page, count);
+
+	spin_lock_irq(q->queue_lock);
+	if (stats)
+		queue_flag_set(QUEUE_FLAG_IO_STAT, q);
+	else
+		queue_flag_clear(QUEUE_FLAG_IO_STAT, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -210,6 +252,12 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.show = queue_hw_sector_size_show,
 };
 
+static struct queue_sysfs_entry queue_nonrot_entry = {
+	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_nonrot_show,
+	.store = queue_nonrot_store,
+};
+
 static struct queue_sysfs_entry queue_nomerges_entry = {
 	.attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_nomerges_show,
@@ -222,6 +270,12 @@ static struct queue_sysfs_entry queue_rq_affinity_entry = {
 	.store = queue_rq_affinity_store,
 };
 
+static struct queue_sysfs_entry queue_iostats_entry = {
+	.attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_iostats_show,
+	.store = queue_iostats_store,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -229,8 +283,10 @@ static struct attribute *default_attrs[] = {
 	&queue_max_sectors_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
+	&queue_nonrot_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
+	&queue_iostats_entry.attr,
 	NULL,
 };
 
diff --git a/block/blk.h b/block/blk.h
index 6e1ed40534e9..0dce92c37496 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -108,4 +108,12 @@ static inline int blk_cpu_to_group(int cpu)
 #endif
 }
 
+static inline int blk_do_io_stat(struct request_queue *q)
+{
+	if (q)
+		return blk_queue_io_stat(q);
+
+	return 0;
+}
+
 #endif
diff --git a/block/blktrace.c b/block/blktrace.c
index b0a2cae886db..39cc3bfe56e4 100644
--- a/block/blktrace.c
+++ b/block/blktrace.c
@@ -187,59 +187,12 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 
 static struct dentry *blk_tree_root;
 static DEFINE_MUTEX(blk_tree_mutex);
-static unsigned int root_users;
-
-static inline void blk_remove_root(void)
-{
-	if (blk_tree_root) {
-		debugfs_remove(blk_tree_root);
-		blk_tree_root = NULL;
-	}
-}
-
-static void blk_remove_tree(struct dentry *dir)
-{
-	mutex_lock(&blk_tree_mutex);
-	debugfs_remove(dir);
-	if (--root_users == 0)
-		blk_remove_root();
-	mutex_unlock(&blk_tree_mutex);
-}
-
-static struct dentry *blk_create_tree(const char *blk_name)
-{
-	struct dentry *dir = NULL;
-	int created = 0;
-
-	mutex_lock(&blk_tree_mutex);
-
-	if (!blk_tree_root) {
-		blk_tree_root = debugfs_create_dir("block", NULL);
-		if (!blk_tree_root)
-			goto err;
-		created = 1;
-	}
-
-	dir = debugfs_create_dir(blk_name, blk_tree_root);
-	if (dir)
-		root_users++;
-	else {
-		/* Delete root only if we created it */
-		if (created)
-			blk_remove_root();
-	}
-
-err:
-	mutex_unlock(&blk_tree_mutex);
-	return dir;
-}
 
 static void blk_trace_cleanup(struct blk_trace *bt)
 {
-	relay_close(bt->rchan);
 	debugfs_remove(bt->msg_file);
 	debugfs_remove(bt->dropped_file);
-	blk_remove_tree(bt->dir);
+	relay_close(bt->rchan);
 	free_percpu(bt->sequence);
 	free_percpu(bt->msg_data);
 	kfree(bt);
@@ -346,7 +299,18 @@ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
 
 static int blk_remove_buf_file_callback(struct dentry *dentry)
 {
+	struct dentry *parent = dentry->d_parent;
 	debugfs_remove(dentry);
+
+	/*
+	* this will fail for all but the last file, but that is ok. what we
+	* care about is the top level buts->name directory going away, when
+	* the last trace file is gone. Then we don't have to rmdir() that
+	* manually on trace stop, so it nicely solves the issue with
+	* force killing of running traces.
+	*/
+
+	debugfs_remove(parent);
 	return 0;
 }
 
@@ -404,7 +368,15 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 		goto err;
 
 	ret = -ENOENT;
-	dir = blk_create_tree(buts->name);
+
+	if (!blk_tree_root) {
+		blk_tree_root = debugfs_create_dir("block", NULL);
+		if (!blk_tree_root)
+			return -ENOMEM;
+	}
+
+	dir = debugfs_create_dir(buts->name, blk_tree_root);
+
 	if (!dir)
 		goto err;
 
@@ -458,8 +430,6 @@ probe_err:
 	atomic_dec(&blk_probes_ref);
 	mutex_unlock(&blk_probe_mutex);
 err:
-	if (dir)
-		blk_remove_tree(dir);
 	if (bt) {
 		if (bt->msg_file)
 			debugfs_remove(bt->msg_file);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index e8525fa72823..664ebfd092ec 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -84,6 +84,11 @@ struct cfq_data {
 	 */
 	struct cfq_rb_root service_tree;
 	unsigned int busy_queues;
+	/*
+	 * Used to track any pending rt requests so we can pre-empt current
+	 * non-RT cfqq in service when this value is non-zero.
+	 */
+	unsigned int busy_rt_queues;
 
 	int rq_in_driver;
 	int sync_flight;
@@ -562,6 +567,8 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	cfq_mark_cfqq_on_rr(cfqq);
 	cfqd->busy_queues++;
+	if (cfq_class_rt(cfqq))
+		cfqd->busy_rt_queues++;
 
 	cfq_resort_rr_list(cfqd, cfqq);
 }
@@ -581,6 +588,8 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
 	BUG_ON(!cfqd->busy_queues);
 	cfqd->busy_queues--;
+	if (cfq_class_rt(cfqq))
+		cfqd->busy_rt_queues--;
 }
 
 /*
@@ -1005,6 +1014,20 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 		goto expire;
 
 	/*
+	 * If we have a RT cfqq waiting, then we pre-empt the current non-rt
+	 * cfqq.
+	 */
+	if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues) {
+		/*
+		 * We simulate this as cfqq timed out so that it gets to bank
+		 * the remaining of its time slice.
+		 */
+		cfq_log_cfqq(cfqd, cfqq, "preempt");
+		cfq_slice_expired(cfqd, 1);
+		goto new_queue;
+	}
+
+	/*
 	 * The active queue has requests and isn't expired, allow it to
 	 * dispatch.
 	 */
@@ -1067,6 +1090,13 @@ __cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		if (RB_EMPTY_ROOT(&cfqq->sort_list))
 			break;
 
+		/*
+		 * If there is a non-empty RT cfqq waiting for current
+		 * cfqq's timeslice to complete, pre-empt this cfqq
+		 */
+		if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues)
+			break;
+
 	} while (dispatched < max_dispatch);
 
 	/*
@@ -1801,6 +1831,12 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	if (rq_is_meta(rq) && !cfqq->meta_pending)
 		return 1;
 
+	/*
+	 * 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;
+
 	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
 		return 0;
 
@@ -1870,7 +1906,8 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		/*
 		 * not the active queue - expire current slice if it is
 		 * idle and has expired it's mean thinktime or this new queue
-		 * has some old slice time left and is of higher priority
+		 * has some old slice time left and is of higher priority or
+		 * this new queue is RT and the current one is BE
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
 		cfq_mark_cfqq_must_dispatch(cfqq);