Merge branch 'linus' into tracing/core

Merge reason: update to upstream tracing facilities

Signed-off-by: Ingo Molnar <mingo@elte.hu>

10 files changed, 94 insertions, 90 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 29bcfac6c68..25572802dac 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -484,11 +484,11 @@ 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);
@@ -603,13 +603,10 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 	q->queue_flags		= QUEUE_FLAG_DEFAULT;
 	q->queue_lock		= lock;
 
-	blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
-
+	/*
+	 * This also sets hw/phys segments, boundary and size
+	 */
 	blk_queue_make_request(q, __make_request);
-	blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
-
-	blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
-	blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
 
 	q->sg_reserved_size = INT_MAX;
 
@@ -702,18 +699,18 @@ 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);
 	}
 }
 
@@ -721,21 +718,20 @@ 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);
 }
 
-#define blkdev_free_rq(list) list_entry((list)->next, struct request, queuelist)
 /*
  * Get a free request, queue_lock must be held.
  * Returns NULL on failure, with queue_lock held.
@@ -747,15 +743,15 @@ 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
@@ -763,9 +759,9 @@ 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)) {
@@ -778,7 +774,7 @@ 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);
 	}
 
 	/*
@@ -786,11 +782,11 @@ 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)
@@ -808,7 +804,7 @@ 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
@@ -818,8 +814,8 @@ 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;
 	}
@@ -833,7 +829,7 @@ 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;
 }
@@ -847,7 +843,7 @@ 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);
@@ -856,10 +852,10 @@ 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);
@@ -875,7 +871,7 @@ 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);
 	};
@@ -1066,19 +1062,22 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 
 	elv_completed_request(q, req);
 
+	/* this is a bio leak */
+	WARN_ON(req->bio != NULL);
+
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
 	 * 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);
@@ -1129,6 +1128,8 @@ void init_request_from_bio(struct request *req, struct bio *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;
@@ -1137,6 +1138,15 @@ 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;
@@ -1243,11 +1253,11 @@ 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;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 5a244f05360..e39cb24b767 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -403,6 +403,8 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (blk_rq_cpu_valid(next))
 		req->cpu = next->cpu;
 
+	/* owner-ship of bio passed from next to req */
+	next->bio = NULL;
 	__blk_put_request(q, next);
 	return 1;
 }
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..3ff9bba3379 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;
diff --git a/block/blk.h b/block/blk.h
index 0dce92c3749..3ee94358b43 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -102,7 +102,7 @@ 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
diff --git a/block/bsg.c b/block/bsg.c
index 0ce8806dd0c..206060e795d 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -218,9 +218,6 @@ bsg_validate_sgv4_hdr(struct request_queue *q, struct sg_io_v4 *hdr, int *rw)
 
 	if (hdr->guard != 'Q')
 		return -EINVAL;
-	if (hdr->dout_xfer_len > (q->max_sectors << 9) ||
-	    hdr->din_xfer_len > (q->max_sectors << 9))
-		return -EIO;
 
 	switch (hdr->protocol) {
 	case BSG_PROTOCOL_SCSI:
@@ -353,6 +350,8 @@ static void bsg_rq_end_io(struct request *rq, int uptodate)
 static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
 			    struct bsg_command *bc, struct request *rq)
 {
+	int at_head = (0 == (bc->hdr.flags & BSG_FLAG_Q_AT_TAIL));
+
 	/*
 	 * add bc command to busy queue and submit rq for io
 	 */
@@ -368,7 +367,7 @@ static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
 	dprintk("%s: queueing rq %p, bc %p\n", bd->name, rq, bc);
 
 	rq->end_io_data = bc;
-	blk_execute_rq_nowait(q, NULL, rq, 1, bsg_rq_end_io);
+	blk_execute_rq_nowait(q, NULL, rq, at_head, bsg_rq_end_io);
 }
 
 static struct bsg_command *bsg_next_done_cmd(struct bsg_device *bd)
@@ -924,6 +923,7 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		struct request *rq;
 		struct bio *bio, *bidi_bio = NULL;
 		struct sg_io_v4 hdr;
+		int at_head;
 		u8 sense[SCSI_SENSE_BUFFERSIZE];
 
 		if (copy_from_user(&hdr, uarg, sizeof(hdr)))
@@ -936,7 +936,9 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		bio = rq->bio;
 		if (rq->next_rq)
 			bidi_bio = rq->next_rq->bio;
-		blk_execute_rq(bd->queue, NULL, rq, 0);
+
+		at_head = (0 == (hdr.flags & BSG_FLAG_Q_AT_TAIL));
+		blk_execute_rq(bd->queue, NULL, rq, at_head);
 		ret = blk_complete_sgv4_hdr_rq(rq, &hdr, bio, bidi_bio);
 
 		if (copy_to_user(uarg, &hdr, sizeof(hdr)))
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 664ebfd092e..9e809345f71 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1992,8 +1992,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		}
 		if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
 			cfq_slice_expired(cfqd, 1);
-		else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list))
+		else if (sync && !rq_noidle(rq) &&
+			 RB_EMPTY_ROOT(&cfqq->sort_list)) {
 			cfq_arm_slice_timer(cfqd);
+		}
 	}
 
 	if (!cfqd->rq_in_driver)
diff --git a/block/cmd-filter.c b/block/cmd-filter.c
index 504b275e1b9..572bbc2f900 100644
--- a/block/cmd-filter.c
+++ b/block/cmd-filter.c
@@ -22,6 +22,7 @@
 #include <linux/spinlock.h>
 #include <linux/capability.h>
 #include <linux/bitops.h>
+#include <linux/blkdev.h>
 
 #include <scsi/scsi.h>
 #include <linux/cdrom.h>
diff --git a/block/elevator.c b/block/elevator.c
index 98259eda0ef..ca6788a0195 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -677,7 +677,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 	}
 
 	if (unplug_it && blk_queue_plugged(q)) {
-		int nrq = q->rq.count[READ] + q->rq.count[WRITE]
+		int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC]
 			- q->in_flight;
 
 		if (nrq >= q->unplug_thresh)
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index ee9c67d7e1b..626ee274c5c 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -214,21 +214,10 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 	return 0;
 }
 
-/*
- * unmap a request that was previously mapped to this sg_io_hdr. handles
- * both sg and non-sg sg_io_hdr.
- */
-static int blk_unmap_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr)
-{
-	blk_rq_unmap_user(rq->bio);
-	blk_put_request(rq);
-	return 0;
-}
-
 static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 				 struct bio *bio)
 {
-	int r, ret = 0;
+	int ret = 0;
 
 	/*
 	 * fill in all the output members
@@ -253,12 +242,10 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 			ret = -EFAULT;
 	}
 
-	rq->bio = bio;
-	r = blk_unmap_sghdr_rq(rq, hdr);
-	if (ret)
-		r = ret;
+	blk_rq_unmap_user(bio);
+	blk_put_request(rq);
 
-	return r;
+	return ret;
 }
 
 static int sg_io(struct request_queue *q, struct gendisk *bd_disk,