Merge commit 'origin/master' into for-linus/xen/master

* commit 'origin/master': (4825 commits)
  Fix build errors due to CONFIG_BRANCH_TRACER=y
  parport: Use the PCI IRQ if offered
  tty: jsm cleanups
  Adjust path to gpio headers
  KGDB_SERIAL_CONSOLE check for module
  Change KCONFIG name
  tty: Blackin CTS/RTS
  Change hardware flow control from poll to interrupt driven
  Add support for the MAX3100 SPI UART.
  lanana: assign a device name and numbering for MAX3100
  serqt: initial clean up pass for tty side
  tty: Use the generic RS485 ioctl on CRIS
  tty: Correct inline types for tty_driver_kref_get()
  splice: fix deadlock in splicing to file
  nilfs2: support nanosecond timestamp
  nilfs2: introduce secondary super block
  nilfs2: simplify handling of active state of segments
  nilfs2: mark minor flag for checkpoint created by internal operation
  nilfs2: clean up sketch file
  nilfs2: super block operations fix endian bug
  ...

Conflicts:
	arch/x86/include/asm/thread_info.h
	arch/x86/lguest/boot.c
	drivers/xen/manage.c

11 files changed, 244 insertions, 1076 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 0cbb3b88b59..e7d12782bcf 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -44,22 +44,6 @@ config LBD
 
 	  If unsure, say N.
 
-config BLK_DEV_IO_TRACE
-	bool "Support for tracing block io actions"
-	depends on SYSFS
-	select RELAY
-	select DEBUG_FS
-	select TRACEPOINTS
-	help
-	  Say Y here if you want to be able to trace the block layer actions
-	  on a given queue. Tracing allows you to see any traffic happening
-	  on a block device queue. For more information (and the userspace
-	  support tools needed), fetch the blktrace tools from:
-
-	  git://git.kernel.dk/blktrace.git
-
-	  If unsure, say N.
-
 config BLK_DEV_BSG
 	bool "Block layer SG support v4 (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
diff --git a/block/Makefile b/block/Makefile
index bfe73049f93..e9fa4dd690f 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -13,6 +13,5 @@ obj-$(CONFIG_IOSCHED_AS)	+= as-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 
-obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY)	+= blk-integrity.o
diff --git a/block/blk-core.c b/block/blk-core.c
index 996ed906d8c..43fdedc524e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -64,12 +64,11 @@ 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) || !disk || !blk_do_io_stat(disk->queue))
+	if (!blk_fs_request(rq) || !blk_do_io_stat(rq))
 		return;
 
 	cpu = part_stat_lock();
@@ -484,11 +483,11 @@ static int blk_init_free_list(struct request_queue *q)
 {
 	struct request_list *rl = &q->rq;
 
-	rl->count[READ] = rl->count[WRITE] = 0;
-	rl->starved[READ] = rl->starved[WRITE] = 0;
+	rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
+	rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
 	rl->elvpriv = 0;
-	init_waitqueue_head(&rl->wait[READ]);
-	init_waitqueue_head(&rl->wait[WRITE]);
+	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
+	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
 
 	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
 				mempool_free_slab, request_cachep, q->node);
@@ -699,18 +698,18 @@ static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)
 	ioc->last_waited = jiffies;
 }
 
-static void __freed_request(struct request_queue *q, int rw)
+static void __freed_request(struct request_queue *q, int sync)
 {
 	struct request_list *rl = &q->rq;
 
-	if (rl->count[rw] < queue_congestion_off_threshold(q))
-		blk_clear_queue_congested(q, rw);
+	if (rl->count[sync] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, sync);
 
-	if (rl->count[rw] + 1 <= q->nr_requests) {
-		if (waitqueue_active(&rl->wait[rw]))
-			wake_up(&rl->wait[rw]);
+	if (rl->count[sync] + 1 <= q->nr_requests) {
+		if (waitqueue_active(&rl->wait[sync]))
+			wake_up(&rl->wait[sync]);
 
-		blk_clear_queue_full(q, rw);
+		blk_clear_queue_full(q, sync);
 	}
 }
 
@@ -718,18 +717,18 @@ static void __freed_request(struct request_queue *q, int rw)
  * A request has just been released.  Account for it, update the full and
  * congestion status, wake up any waiters.   Called under q->queue_lock.
  */
-static void freed_request(struct request_queue *q, int rw, int priv)
+static void freed_request(struct request_queue *q, int sync, int priv)
 {
 	struct request_list *rl = &q->rq;
 
-	rl->count[rw]--;
+	rl->count[sync]--;
 	if (priv)
 		rl->elvpriv--;
 
-	__freed_request(q, rw);
+	__freed_request(q, sync);
 
-	if (unlikely(rl->starved[rw ^ 1]))
-		__freed_request(q, rw ^ 1);
+	if (unlikely(rl->starved[sync ^ 1]))
+		__freed_request(q, sync ^ 1);
 }
 
 /*
@@ -743,15 +742,15 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	struct request *rq = NULL;
 	struct request_list *rl = &q->rq;
 	struct io_context *ioc = NULL;
-	const int rw = rw_flags & 0x01;
+	const bool is_sync = rw_is_sync(rw_flags) != 0;
 	int may_queue, priv;
 
 	may_queue = elv_may_queue(q, rw_flags);
 	if (may_queue == ELV_MQUEUE_NO)
 		goto rq_starved;
 
-	if (rl->count[rw]+1 >= queue_congestion_on_threshold(q)) {
-		if (rl->count[rw]+1 >= q->nr_requests) {
+	if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) {
+		if (rl->count[is_sync]+1 >= q->nr_requests) {
 			ioc = current_io_context(GFP_ATOMIC, q->node);
 			/*
 			 * The queue will fill after this allocation, so set
@@ -759,9 +758,9 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 			 * This process will be allowed to complete a batch of
 			 * requests, others will be blocked.
 			 */
-			if (!blk_queue_full(q, rw)) {
+			if (!blk_queue_full(q, is_sync)) {
 				ioc_set_batching(q, ioc);
-				blk_set_queue_full(q, rw);
+				blk_set_queue_full(q, is_sync);
 			} else {
 				if (may_queue != ELV_MQUEUE_MUST
 						&& !ioc_batching(q, ioc)) {
@@ -774,7 +773,7 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 				}
 			}
 		}
-		blk_set_queue_congested(q, rw);
+		blk_set_queue_congested(q, is_sync);
 	}
 
 	/*
@@ -782,11 +781,11 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	 * limit of requests, otherwise we could have thousands of requests
 	 * allocated with any setting of ->nr_requests
 	 */
-	if (rl->count[rw] >= (3 * q->nr_requests / 2))
+	if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
 		goto out;
 
-	rl->count[rw]++;
-	rl->starved[rw] = 0;
+	rl->count[is_sync]++;
+	rl->starved[is_sync] = 0;
 
 	priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
 	if (priv)
@@ -804,7 +803,7 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 		 * wait queue, but this is pretty rare.
 		 */
 		spin_lock_irq(q->queue_lock);
-		freed_request(q, rw, priv);
+		freed_request(q, is_sync, priv);
 
 		/*
 		 * in the very unlikely event that allocation failed and no
@@ -814,8 +813,8 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 		 * rq mempool into READ and WRITE
 		 */
 rq_starved:
-		if (unlikely(rl->count[rw] == 0))
-			rl->starved[rw] = 1;
+		if (unlikely(rl->count[is_sync] == 0))
+			rl->starved[is_sync] = 1;
 
 		goto out;
 	}
@@ -829,7 +828,7 @@ rq_starved:
 	if (ioc_batching(q, ioc))
 		ioc->nr_batch_requests--;
 
-	trace_block_getrq(q, bio, rw);
+	trace_block_getrq(q, bio, rw_flags & 1);
 out:
 	return rq;
 }
@@ -843,7 +842,7 @@ out:
 static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 					struct bio *bio)
 {
-	const int rw = rw_flags & 0x01;
+	const bool is_sync = rw_is_sync(rw_flags) != 0;
 	struct request *rq;
 
 	rq = get_request(q, rw_flags, bio, GFP_NOIO);
@@ -852,10 +851,10 @@ static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 		struct io_context *ioc;
 		struct request_list *rl = &q->rq;
 
-		prepare_to_wait_exclusive(&rl->wait[rw], &wait,
+		prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
 				TASK_UNINTERRUPTIBLE);
 
-		trace_block_sleeprq(q, bio, rw);
+		trace_block_sleeprq(q, bio, rw_flags & 1);
 
 		__generic_unplug_device(q);
 		spin_unlock_irq(q->queue_lock);
@@ -871,7 +870,7 @@ static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 		ioc_set_batching(q, ioc);
 
 		spin_lock_irq(q->queue_lock);
-		finish_wait(&rl->wait[rw], &wait);
+		finish_wait(&rl->wait[is_sync], &wait);
 
 		rq = get_request(q, rw_flags, bio, GFP_NOIO);
 	};
@@ -1070,14 +1069,14 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	 * it didn't come out of our reserved rq pools
 	 */
 	if (req->cmd_flags & REQ_ALLOCED) {
-		int rw = rq_data_dir(req);
+		int is_sync = rq_is_sync(req) != 0;
 		int priv = req->cmd_flags & REQ_ELVPRIV;
 
 		BUG_ON(!list_empty(&req->queuelist));
 		BUG_ON(!hlist_unhashed(&req->hash));
 
 		blk_free_request(q, req);
-		freed_request(q, rw, priv);
+		freed_request(q, is_sync, priv);
 	}
 }
 EXPORT_SYMBOL_GPL(__blk_put_request);
@@ -1124,10 +1123,10 @@ 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;
+	if (bio_noidle(bio))
+		req->cmd_flags |= REQ_NOIDLE;
 
 	req->errors = 0;
 	req->hard_sector = req->sector = bio->bi_sector;
@@ -1136,6 +1135,15 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	blk_rq_bio_prep(req->q, req, bio);
 }
 
+/*
+ * Only disabling plugging for non-rotational devices if it does tagging
+ * as well, otherwise we do need the proper merging
+ */
+static inline bool queue_should_plug(struct request_queue *q)
+{
+	return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
+}
+
 static int __make_request(struct request_queue *q, struct bio *bio)
 {
 	struct request *req;
@@ -1242,11 +1250,11 @@ get_rq:
 	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) ||
 	    bio_flagged(bio, BIO_CPU_AFFINE))
 		req->cpu = blk_cpu_to_group(smp_processor_id());
-	if (!blk_queue_nonrot(q) && elv_queue_empty(q))
+	if (queue_should_plug(q) && elv_queue_empty(q))
 		blk_plug_device(q);
 	add_request(q, req);
 out:
-	if (unplug || blk_queue_nonrot(q))
+	if (unplug || !queue_should_plug(q))
 		__generic_unplug_device(q);
 	spin_unlock_irq(q->queue_lock);
 	return 0;
@@ -1664,9 +1672,7 @@ 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))
+	if (!blk_do_io_stat(req))
 		return;
 
 	if (blk_fs_request(req)) {
@@ -1683,9 +1689,7 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 
 static void blk_account_io_done(struct request *req)
 {
-	struct gendisk *disk = req->rq_disk;
-
-	if (!disk || !blk_do_io_stat(disk->queue))
+	if (!blk_do_io_stat(req))
 		return;
 
 	/*
@@ -1700,7 +1704,7 @@ static void blk_account_io_done(struct request *req)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(disk, req->sector);
+		part = disk_map_sector_rcu(req->rq_disk, req->sector);
 
 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index e39cb24b767..63760ca3da0 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -338,6 +338,22 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	return 1;
 }
 
+static void blk_account_io_merge(struct request *req)
+{
+	if (blk_do_io_stat(req)) {
+		struct hd_struct *part;
+		int cpu;
+
+		cpu = part_stat_lock();
+		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+
+		part_round_stats(cpu, part);
+		part_dec_in_flight(part);
+
+		part_stat_unlock();
+	}
+}
+
 /*
  * Has to be called with the request spinlock acquired
  */
@@ -386,18 +402,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 
 	elv_merge_requests(q, req, next);
 
-	if (req->rq_disk) {
-		struct hd_struct *part;
-		int cpu;
-
-		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
-
-		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
-
-		part_stat_unlock();
-	}
+	blk_account_io_merge(req);
 
 	req->ioprio = ioprio_best(req->ioprio, next->ioprio);
 	if (blk_rq_cpu_valid(next))
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 59fd05d9f1d..69c42adde52 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -431,7 +431,7 @@ EXPORT_SYMBOL(blk_queue_segment_boundary);
  *
  * description:
  *    set required memory and length alignment for direct dma transactions.
- *    this is used when buiding direct io requests for the queue.
+ *    this is used when building direct io requests for the queue.
  *
  **/
 void blk_queue_dma_alignment(struct request_queue *q, int mask)
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index ce0efc6b26d..ee9c2160222 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -64,7 +64,7 @@ static int raise_blk_irq(int cpu, struct request *rq)
 		data->info = rq;
 		data->flags = 0;
 
-		__smp_call_function_single(cpu, data);
+		__smp_call_function_single(cpu, data, 0);
 		return 0;
 	}
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index e29ddfc73cf..73f36beff5c 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -48,28 +48,28 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 	q->nr_requests = nr;
 	blk_queue_congestion_threshold(q);
 
-	if (rl->count[READ] >= queue_congestion_on_threshold(q))
-		blk_set_queue_congested(q, READ);
-	else if (rl->count[READ] < queue_congestion_off_threshold(q))
-		blk_clear_queue_congested(q, READ);
-
-	if (rl->count[WRITE] >= queue_congestion_on_threshold(q))
-		blk_set_queue_congested(q, WRITE);
-	else if (rl->count[WRITE] < queue_congestion_off_threshold(q))
-		blk_clear_queue_congested(q, WRITE);
-
-	if (rl->count[READ] >= q->nr_requests) {
-		blk_set_queue_full(q, READ);
-	} else if (rl->count[READ]+1 <= q->nr_requests) {
-		blk_clear_queue_full(q, READ);
-		wake_up(&rl->wait[READ]);
+	if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, BLK_RW_SYNC);
+	else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, BLK_RW_SYNC);
+
+	if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, BLK_RW_ASYNC);
+	else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, BLK_RW_ASYNC);
+
+	if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
+		blk_set_queue_full(q, BLK_RW_SYNC);
+	} else if (rl->count[BLK_RW_SYNC]+1 <= q->nr_requests) {
+		blk_clear_queue_full(q, BLK_RW_SYNC);
+		wake_up(&rl->wait[BLK_RW_SYNC]);
 	}
 
-	if (rl->count[WRITE] >= q->nr_requests) {
-		blk_set_queue_full(q, WRITE);
-	} else if (rl->count[WRITE]+1 <= q->nr_requests) {
-		blk_clear_queue_full(q, WRITE);
-		wake_up(&rl->wait[WRITE]);
+	if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
+		blk_set_queue_full(q, BLK_RW_ASYNC);
+	} else if (rl->count[BLK_RW_ASYNC]+1 <= q->nr_requests) {
+		blk_clear_queue_full(q, BLK_RW_ASYNC);
+		wake_up(&rl->wait[BLK_RW_ASYNC]);
 	}
 	spin_unlock_irq(q->queue_lock);
 	return ret;
@@ -209,10 +209,14 @@ static ssize_t queue_iostats_store(struct request_queue *q, const char *page,
 	ssize_t ret = queue_var_store(&stats, page, count);
 
 	spin_lock_irq(q->queue_lock);
+	elv_quisce_start(q);
+
 	if (stats)
 		queue_flag_set(QUEUE_FLAG_IO_STAT, q);
 	else
 		queue_flag_clear(QUEUE_FLAG_IO_STAT, q);
+
+	elv_quisce_end(q);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
diff --git a/block/blk.h b/block/blk.h
index 0dce92c3749..24fcaeeaf62 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -70,6 +70,10 @@ void blk_queue_congestion_threshold(struct request_queue *q);
 
 int blk_dev_init(void);
 
+void elv_quisce_start(struct request_queue *q);
+void elv_quisce_end(struct request_queue *q);
+
+
 /*
  * Return the threshold (number of used requests) at which the queue is
  * considered to be congested.  It include a little hysteresis to keep the
@@ -102,18 +106,20 @@ static inline int blk_cpu_to_group(int cpu)
 	const struct cpumask *mask = cpu_coregroup_mask(cpu);
 	return cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	return first_cpu(per_cpu(cpu_sibling_map, cpu));
+	return cpumask_first(topology_thread_cpumask(cpu));
 #else
 	return cpu;
 #endif
 }
 
-static inline int blk_do_io_stat(struct request_queue *q)
+static inline int blk_do_io_stat(struct request *rq)
 {
-	if (q)
-		return blk_queue_io_stat(q);
+	struct gendisk *disk = rq->rq_disk;
 
-	return 0;
+	if (!disk || !disk->queue)
+		return 0;
+
+	return blk_queue_io_stat(disk->queue) && (rq->cmd_flags & REQ_ELVPRIV);
 }
 
 #endif
diff --git a/block/blktrace.c b/block/blktrace.c
deleted file mode 100644
index 028120a0965..00000000000
--- a/block/blktrace.c
+++ /dev/null
@@ -1,860 +0,0 @@
-/*
- * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
- */
-#include <linux/kernel.h>
-#include <linux/blkdev.h>
-#include <linux/blktrace_api.h>
-#include <linux/percpu.h>
-#include <linux/init.h>
-#include <linux/mutex.h>
-#include <linux/debugfs.h>
-#include <linux/time.h>
-#include <trace/block.h>
-#include <asm/uaccess.h>
-
-static unsigned int blktrace_seq __read_mostly = 1;
-
-/* Global reference count of probes */
-static DEFINE_MUTEX(blk_probe_mutex);
-static atomic_t blk_probes_ref = ATOMIC_INIT(0);
-
-static int blk_register_tracepoints(void);
-static void blk_unregister_tracepoints(void);
-
-/*
- * Send out a notify message.
- */
-static void trace_note(struct blk_trace *bt, pid_t pid, int action,
-		       const void *data, size_t len)
-{
-	struct blk_io_trace *t;
-
-	t = relay_reserve(bt->rchan, sizeof(*t) + len);
-	if (t) {
-		const int cpu = smp_processor_id();
-
-		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
-		t->time = ktime_to_ns(ktime_get());
-		t->device = bt->dev;
-		t->action = action;
-		t->pid = pid;
-		t->cpu = cpu;
-		t->pdu_len = len;
-		memcpy((void *) t + sizeof(*t), data, len);
-	}
-}
-
-/*
- * Send out a notify for this process, if we haven't done so since a trace
- * started
- */
-static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk)
-{
-	tsk->btrace_seq = blktrace_seq;
-	trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm));
-}
-
-static void trace_note_time(struct blk_trace *bt)
-{
-	struct timespec now;
-	unsigned long flags;
-	u32 words[2];
-
-	getnstimeofday(&now);
-	words[0] = now.tv_sec;
-	words[1] = now.tv_nsec;
-
-	local_irq_save(flags);
-	trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words));
-	local_irq_restore(flags);
-}
-
-void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
-{
-	int n;
-	va_list args;
-	unsigned long flags;
-	char *buf;
-
-	local_irq_save(flags);
-	buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
-	va_start(args, fmt);
-	n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
-	va_end(args);
-
-	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(__trace_note_message);
-
-static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
-			 pid_t pid)
-{
-	if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
-		return 1;
-	if (sector < bt->start_lba || sector > bt->end_lba)
-		return 1;
-	if (bt->pid && pid != bt->pid)
-		return 1;
-
-	return 0;
-}
-
-/*
- * Data direction bit lookup
- */
-static u32 ddir_act[2] __read_mostly = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) };
-
-/* The ilog2() calls fall out because they're constant */
-#define MASK_TC_BIT(rw, __name) ( (rw & (1 << BIO_RW_ ## __name)) << \
-	  (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - BIO_RW_ ## __name) )
-
-/*
- * The worker for the various blk_add_trace*() types. Fills out a
- * blk_io_trace structure and places it in a per-cpu subbuffer.
- */
-static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
-		     int rw, u32 what, int error, int pdu_len, void *pdu_data)
-{
-	struct task_struct *tsk = current;
-	struct blk_io_trace *t;
-	unsigned long flags;
-	unsigned long *sequence;
-	pid_t pid;
-	int cpu;
-
-	if (unlikely(bt->trace_state != Blktrace_running))
-		return;
-
-	what |= ddir_act[rw & WRITE];
-	what |= MASK_TC_BIT(rw, BARRIER);
-	what |= MASK_TC_BIT(rw, SYNCIO);
-	what |= MASK_TC_BIT(rw, AHEAD);
-	what |= MASK_TC_BIT(rw, META);
-	what |= MASK_TC_BIT(rw, DISCARD);
-
-	pid = tsk->pid;
-	if (unlikely(act_log_check(bt, what, sector, pid)))
-		return;
-
-	/*
-	 * A word about the locking here - we disable interrupts to reserve
-	 * some space in the relay per-cpu buffer, to prevent an irq
-	 * from coming in and stepping on our toes.
-	 */
-	local_irq_save(flags);
-
-	if (unlikely(tsk->btrace_seq != blktrace_seq))
-		trace_note_tsk(bt, tsk);
-
-	t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len);
-	if (t) {
-		cpu = smp_processor_id();
-		sequence = per_cpu_ptr(bt->sequence, cpu);
-
-		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
-		t->sequence = ++(*sequence);
-		t->time = ktime_to_ns(ktime_get());
-		t->sector = sector;
-		t->bytes = bytes;
-		t->action = what;
-		t->pid = pid;
-		t->device = bt->dev;
-		t->cpu = cpu;
-		t->error = error;
-		t->pdu_len = pdu_len;
-
-		if (pdu_len)
-			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
-	}
-
-	local_irq_restore(flags);
-}
-
-static struct dentry *blk_tree_root;
-static DEFINE_MUTEX(blk_tree_mutex);
-
-static void blk_trace_cleanup(struct blk_trace *bt)
-{
-	debugfs_remove(bt->msg_file);
-	debugfs_remove(bt->dropped_file);
-	relay_close(bt->rchan);
-	free_percpu(bt->sequence);
-	free_percpu(bt->msg_data);
-	kfree(bt);
-	mutex_lock(&blk_probe_mutex);
-	if (atomic_dec_and_test(&blk_probes_ref))
-		blk_unregister_tracepoints();
-	mutex_unlock(&blk_probe_mutex);
-}
-
-int blk_trace_remove(struct request_queue *q)
-{
-	struct blk_trace *bt;
-
-	bt = xchg(&q->blk_trace, NULL);
-	if (!bt)
-		return -EINVAL;
-
-	if (bt->trace_state == Blktrace_setup ||
-	    bt->trace_state == Blktrace_stopped)
-		blk_trace_cleanup(bt);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blk_trace_remove);
-
-static int blk_dropped_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-
-	return 0;
-}
-
-static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	struct blk_trace *bt = filp->private_data;
-	char buf[16];
-
-	snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped));
-
-	return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
-}
-
-static const struct file_operations blk_dropped_fops = {
-	.owner =	THIS_MODULE,
-	.open =		blk_dropped_open,
-	.read =		blk_dropped_read,
-};
-
-static int blk_msg_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-
-	return 0;
-}
-
-static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
-				size_t count, loff_t *ppos)
-{
-	char *msg;
-	struct blk_trace *bt;
-
-	if (count > BLK_TN_MAX_MSG)
-		return -EINVAL;
-
-	msg = kmalloc(count, GFP_KERNEL);
-	if (msg == NULL)
-		return -ENOMEM;
-
-	if (copy_from_user(msg, buffer, count)) {
-		kfree(msg);
-		return -EFAULT;
-	}
-
-	bt = filp->private_data;
-	__trace_note_message(bt, "%s", msg);
-	kfree(msg);
-
-	return count;
-}
-
-static const struct file_operations blk_msg_fops = {
-	.owner =	THIS_MODULE,
-	.open =		blk_msg_open,
-	.write =	blk_msg_write,
-};
-
-/*
- * Keep track of how many times we encountered a full subbuffer, to aid
- * the user space app in telling how many lost events there were.
- */
-static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
-				     void *prev_subbuf, size_t prev_padding)
-{
-	struct blk_trace *bt;
-
-	if (!relay_buf_full(buf))
-		return 1;
-
-	bt = buf->chan->private_data;
-	atomic_inc(&bt->dropped);
-	return 0;
-}
-
-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;
-}
-
-static struct dentry *blk_create_buf_file_callback(const char *filename,
-						   struct dentry *parent,
-						   int mode,
-						   struct rchan_buf *buf,
-						   int *is_global)
-{
-	return debugfs_create_file(filename, mode, parent, buf,
-					&relay_file_operations);
-}
-
-static struct rchan_callbacks blk_relay_callbacks = {
-	.subbuf_start		= blk_subbuf_start_callback,
-	.create_buf_file	= blk_create_buf_file_callback,
-	.remove_buf_file	= blk_remove_buf_file_callback,
-};
-
-/*
- * Setup everything required to start tracing
- */
-int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
-			struct blk_user_trace_setup *buts)
-{
-	struct blk_trace *old_bt, *bt = NULL;
-	struct dentry *dir = NULL;
-	int ret, i;
-
-	if (!buts->buf_size || !buts->buf_nr)
-		return -EINVAL;
-
-	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
-	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
-
-	/*
-	 * some device names have larger paths - convert the slashes
-	 * to underscores for this to work as expected
-	 */
-	for (i = 0; i < strlen(buts->name); i++)
-		if (buts->name[i] == '/')
-			buts->name[i] = '_';
-
-	ret = -ENOMEM;
-	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
-	if (!bt)
-		goto err;
-
-	bt->sequence = alloc_percpu(unsigned long);
-	if (!bt->sequence)
-		goto err;
-
-	bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
-	if (!bt->msg_data)
-		goto err;
-
-	ret = -ENOENT;
-
-	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;
-
-	bt->dir = dir;
-	bt->dev = dev;
-	atomic_set(&bt->dropped, 0);
-
-	ret = -EIO;
-	bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops);
-	if (!bt->dropped_file)
-		goto err;
-
-	bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
-	if (!bt->msg_file)
-		goto err;
-
-	bt->rchan = relay_open("trace", dir, buts->buf_size,
-				buts->buf_nr, &blk_relay_callbacks, bt);
-	if (!bt->rchan)
-		goto err;
-
-	bt->act_mask = buts->act_mask;
-	if (!bt->act_mask)
-		bt->act_mask = (u16) -1;
-
-	bt->start_lba = buts->start_lba;
-	bt->end_lba = buts->end_lba;
-	if (!bt->end_lba)
-		bt->end_lba = -1ULL;
-
-	bt->pid = buts->pid;
-	bt->trace_state = Blktrace_setup;
-
-	mutex_lock(&blk_probe_mutex);
-	if (atomic_add_return(1, &blk_probes_ref) == 1) {
-		ret = blk_register_tracepoints();
-		if (ret)
-			goto probe_err;
-	}
-	mutex_unlock(&blk_probe_mutex);
-
-	ret = -EBUSY;
-	old_bt = xchg(&q->blk_trace, bt);
-	if (old_bt) {
-		(void) xchg(&q->blk_trace, old_bt);
-		goto err;
-	}
-
-	return 0;
-probe_err:
-	atomic_dec(&blk_probes_ref);
-	mutex_unlock(&blk_probe_mutex);
-err:
-	if (bt) {
-		if (bt->msg_file)
-			debugfs_remove(bt->msg_file);
-		if (bt->dropped_file)
-			debugfs_remove(bt->dropped_file);
-		free_percpu(bt->sequence);
-		free_percpu(bt->msg_data);
-		if (bt->rchan)
-			relay_close(bt->rchan);
-		kfree(bt);
-	}
-	return ret;
-}
-
-int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
-		    char __user *arg)
-{
-	struct blk_user_trace_setup buts;
-	int ret;
-
-	ret = copy_from_user(&buts, arg, sizeof(buts));
-	if (ret)
-		return -EFAULT;
-
-	ret = do_blk_trace_setup(q, name, dev, &buts);
-	if (ret)
-		return ret;
-
-	if (copy_to_user(arg, &buts, sizeof(buts)))
-		return -EFAULT;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blk_trace_setup);
-
-int blk_trace_startstop(struct request_queue *q, int start)
-{
-	struct blk_trace *bt;
-	int ret;
-
-	if ((bt = q->blk_trace) == NULL)
-		return -EINVAL;
-
-	/*
-	 * For starting a trace, we can transition from a setup or stopped
-	 * trace. For stopping a trace, the state must be running
-	 */
-	ret = -EINVAL;
-	if (start) {
-		if (bt->trace_state == Blktrace_setup ||
-		    bt->trace_state == Blktrace_stopped) {
-			blktrace_seq++;
-			smp_mb();
-			bt->trace_state = Blktrace_running;
-
-			trace_note_time(bt);
-			ret = 0;
-		}
-	} else {
-		if (bt->trace_state == Blktrace_running) {
-			bt->trace_state = Blktrace_stopped;
-			relay_flush(bt->rchan);
-			ret = 0;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(blk_trace_startstop);
-
-/**
- * blk_trace_ioctl: - handle the ioctls associated with tracing
- * @bdev:	the block device
- * @cmd: 	the ioctl cmd
- * @arg:	the argument data, if any
- *
- **/
-int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
-{
-	struct request_queue *q;
-	int ret, start = 0;
-	char b[BD