Merge branch 'for-3.10/core' of git://git.kernel.dk/linux-block

Pull block core updates from Jens Axboe:

 - Major bit is Kents prep work for immutable bio vecs.

 - Stable candidate fix for a scheduling-while-atomic in the queue
   bypass operation.

 - Fix for the hang on exceeded rq->datalen 32-bit unsigned when merging
   discard bios.

 - Tejuns changes to convert the writeback thread pool to the generic
   workqueue mechanism.

 - Runtime PM framework, SCSI patches exists on top of these in James'
   tree.

 - A few random fixes.

* 'for-3.10/core' of git://git.kernel.dk/linux-block: (40 commits)
  relay: move remove_buf_file inside relay_close_buf
  partitions/efi.c: replace useless kzalloc's by kmalloc's
  fs/block_dev.c: fix iov_shorten() criteria in blkdev_aio_read()
  block: fix max discard sectors limit
  blkcg: fix "scheduling while atomic" in blk_queue_bypass_start
  Documentation: cfq-iosched: update documentation help for cfq tunables
  writeback: expose the bdi_wq workqueue
  writeback: replace custom worker pool implementation with unbound workqueue
  writeback: remove unused bdi_pending_list
  aoe: Fix unitialized var usage
  bio-integrity: Add explicit field for owner of bip_buf
  block: Add an explicit bio flag for bios that own their bvec
  block: Add bio_alloc_pages()
  block: Convert some code to bio_for_each_segment_all()
  block: Add bio_for_each_segment_all()
  bounce: Refactor __blk_queue_bounce to not use bi_io_vec
  raid1: use bio_copy_data()
  pktcdvd: Use bio_reset() in disabled code to kill bi_idx usage
  pktcdvd: use bio_copy_data()
  block: Add bio_copy_data()
  ...

6 files changed, 229 insertions, 79 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index b2b9837f9dd..e8918ffaf96 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -972,10 +972,10 @@ int blkcg_activate_policy(struct request_queue *q,
 	if (!new_blkg)
 		return -ENOMEM;
 
-	preloaded = !radix_tree_preload(GFP_KERNEL);
-
 	blk_queue_bypass_start(q);
 
+	preloaded = !radix_tree_preload(GFP_KERNEL);
+
 	/*
 	 * Make sure the root blkg exists and count the existing blkgs.  As
 	 * @q is bypassing at this point, blkg_lookup_create() can't be
diff --git a/block/blk-core.c b/block/blk-core.c
index 7c288358a74..33c33bc99dd 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -30,6 +30,7 @@
 #include <linux/list_sort.h>
 #include <linux/delay.h>
 #include <linux/ratelimit.h>
+#include <linux/pm_runtime.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
@@ -159,20 +160,10 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 		error = -EIO;
 
-	if (unlikely(nbytes > bio->bi_size)) {
-		printk(KERN_ERR "%s: want %u bytes done, %u left\n",
-		       __func__, nbytes, bio->bi_size);
-		nbytes = bio->bi_size;
-	}
-
 	if (unlikely(rq->cmd_flags & REQ_QUIET))
 		set_bit(BIO_QUIET, &bio->bi_flags);
 
-	bio->bi_size -= nbytes;
-	bio->bi_sector += (nbytes >> 9);
-
-	if (bio_integrity(bio))
-		bio_integrity_advance(bio, nbytes);
+	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
 	if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
@@ -1264,6 +1255,16 @@ void part_round_stats(int cpu, struct hd_struct *part)
 }
 EXPORT_SYMBOL_GPL(part_round_stats);
 
+#ifdef CONFIG_PM_RUNTIME
+static void blk_pm_put_request(struct request *rq)
+{
+	if (rq->q->dev && !(rq->cmd_flags & REQ_PM) && !--rq->q->nr_pending)
+		pm_runtime_mark_last_busy(rq->q->dev);
+}
+#else
+static inline void blk_pm_put_request(struct request *rq) {}
+#endif
+
 /*
  * queue lock must be held
  */
@@ -1274,6 +1275,8 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	if (unlikely(--req->ref_count))
 		return;
 
+	blk_pm_put_request(req);
+
 	elv_completed_request(q, req);
 
 	/* this is a bio leak */
@@ -1597,7 +1600,7 @@ static void handle_bad_sector(struct bio *bio)
 	printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
 			bdevname(bio->bi_bdev, b),
 			bio->bi_rw,
-			(unsigned long long)bio->bi_sector + bio_sectors(bio),
+			(unsigned long long)bio_end_sector(bio),
 			(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
 
 	set_bit(BIO_EOF, &bio->bi_flags);
@@ -2053,6 +2056,28 @@ static void blk_account_io_done(struct request *req)
 	}
 }
 
+#ifdef CONFIG_PM_RUNTIME
+/*
+ * Don't process normal requests when queue is suspended
+ * or in the process of suspending/resuming
+ */
+static struct request *blk_pm_peek_request(struct request_queue *q,
+					   struct request *rq)
+{
+	if (q->dev && (q->rpm_status == RPM_SUSPENDED ||
+	    (q->rpm_status != RPM_ACTIVE && !(rq->cmd_flags & REQ_PM))))
+		return NULL;
+	else
+		return rq;
+}
+#else
+static inline struct request *blk_pm_peek_request(struct request_queue *q,
+						  struct request *rq)
+{
+	return rq;
+}
+#endif
+
 /**
  * blk_peek_request - peek at the top of a request queue
  * @q: request queue to peek at
@@ -2075,6 +2100,11 @@ struct request *blk_peek_request(struct request_queue *q)
 	int ret;
 
 	while ((rq = __elv_next_request(q)) != NULL) {
+
+		rq = blk_pm_peek_request(q, rq);
+		if (!rq)
+			break;
+
 		if (!(rq->cmd_flags & REQ_STARTED)) {
 			/*
 			 * This is the first time the device driver
@@ -2253,8 +2283,7 @@ EXPORT_SYMBOL(blk_fetch_request);
  **/
 bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 {
-	int total_bytes, bio_nbytes, next_idx = 0;
-	struct bio *bio;
+	int total_bytes;
 
 	if (!req->bio)
 		return false;
@@ -2300,56 +2329,21 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 
 	blk_account_io_completion(req, nr_bytes);
 
-	total_bytes = bio_nbytes = 0;
-	while ((bio = req->bio) != NULL) {
-		int nbytes;
+	total_bytes = 0;
+	while (req->bio) {
+		struct bio *bio = req->bio;
+		unsigned bio_bytes = min(bio->bi_size, nr_bytes);
 
-		if (nr_bytes >= bio->bi_size) {
+		if (bio_bytes == bio->bi_size)
 			req->bio = bio->bi_next;
-			nbytes = bio->bi_size;
-			req_bio_endio(req, bio, nbytes, error);
-			next_idx = 0;
-			bio_nbytes = 0;
-		} else {
-			int idx = bio->bi_idx + next_idx;
 
-			if (unlikely(idx >= bio->bi_vcnt)) {
-				blk_dump_rq_flags(req, "__end_that");
-				printk(KERN_ERR "%s: bio idx %d >= vcnt %d\n",
-				       __func__, idx, bio->bi_vcnt);
-				break;
-			}
+		req_bio_endio(req, bio, bio_bytes, error);
 
-			nbytes = bio_iovec_idx(bio, idx)->bv_len;
-			BIO_BUG_ON(nbytes > bio->bi_size);
+		total_bytes += bio_bytes;
+		nr_bytes -= bio_bytes;
 
-			/*
-			 * not a complete bvec done
-			 */
-			if (unlikely(nbytes > nr_bytes)) {
-				bio_nbytes += nr_bytes;
-				total_bytes += nr_bytes;
-				break;
-			}
-
-			/*
-			 * advance to the next vector
-			 */
-			next_idx++;
-			bio_nbytes += nbytes;
-		}
-
-		total_bytes += nbytes;
-		nr_bytes -= nbytes;
-
-		bio = req->bio;
-		if (bio) {
-			/*
-			 * end more in this run, or just return 'not-done'
-			 */
-			if (unlikely(nr_bytes <= 0))
-				break;
-		}
+		if (!nr_bytes)
+			break;
 	}
 
 	/*
@@ -2365,16 +2359,6 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 		return false;
 	}
 
-	/*
-	 * if the request wasn't completed, update state
-	 */
-	if (bio_nbytes) {
-		req_bio_endio(req, bio, bio_nbytes, error);
-		bio->bi_idx += next_idx;
-		bio_iovec(bio)->bv_offset += nr_bytes;
-		bio_iovec(bio)->bv_len -= nr_bytes;
-	}
-
 	req->__data_len -= total_bytes;
 	req->buffer = bio_data(req->bio);
 
@@ -3046,6 +3030,149 @@ void blk_finish_plug(struct blk_plug *plug)
 }
 EXPORT_SYMBOL(blk_finish_plug);
 
+#ifdef CONFIG_PM_RUNTIME
+/**
+ * blk_pm_runtime_init - Block layer runtime PM initialization routine
+ * @q: the queue of the device
+ * @dev: the device the queue belongs to
+ *
+ * Description:
+ *    Initialize runtime-PM-related fields for @q and start auto suspend for
+ *    @dev. Drivers that want to take advantage of request-based runtime PM
+ *    should call this function after @dev has been initialized, and its
+ *    request queue @q has been allocated, and runtime PM for it can not happen
+ *    yet(either due to disabled/forbidden or its usage_count > 0). In most
+ *    cases, driver should call this function before any I/O has taken place.
+ *
+ *    This function takes care of setting up using auto suspend for the device,
+ *    the autosuspend delay is set to -1 to make runtime suspend impossible
+ *    until an updated value is either set by user or by driver. Drivers do
+ *    not need to touch other autosuspend settings.
+ *
+ *    The block layer runtime PM is request based, so only works for drivers
+ *    that use request as their IO unit instead of those directly use bio's.
+ */
+void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
+{
+	q->dev = dev;
+	q->rpm_status = RPM_ACTIVE;
+	pm_runtime_set_autosuspend_delay(q->dev, -1);
+	pm_runtime_use_autosuspend(q->dev);
+}
+EXPORT_SYMBOL(blk_pm_runtime_init);
+
+/**
+ * blk_pre_runtime_suspend - Pre runtime suspend check
+ * @q: the queue of the device
+ *
+ * Description:
+ *    This function will check if runtime suspend is allowed for the device
+ *    by examining if there are any requests pending in the queue. If there
+ *    are requests pending, the device can not be runtime suspended; otherwise,
+ *    the queue's status will be updated to SUSPENDING and the driver can
+ *    proceed to suspend the device.
+ *
+ *    For the not allowed case, we mark last busy for the device so that
+ *    runtime PM core will try to autosuspend it some time later.
+ *
+ *    This function should be called near the start of the device's
+ *    runtime_suspend callback.
+ *
+ * Return:
+ *    0		- OK to runtime suspend the device
+ *    -EBUSY	- Device should not be runtime suspended
+ */
+int blk_pre_runtime_suspend(struct request_queue *q)
+{
+	int ret = 0;
+
+	spin_lock_irq(q->queue_lock);
+	if (q->nr_pending) {
+		ret = -EBUSY;
+		pm_runtime_mark_last_busy(q->dev);
+	} else {
+		q->rpm_status = RPM_SUSPENDING;
+	}
+	spin_unlock_irq(q->queue_lock);
+	return ret;
+}
+EXPORT_SYMBOL(blk_pre_runtime_suspend);
+
+/**
+ * blk_post_runtime_suspend - Post runtime suspend processing
+ * @q: the queue of the device
+ * @err: return value of the device's runtime_suspend function
+ *
+ * Description:
+ *    Update the queue's runtime status according to the return value of the
+ *    device's runtime suspend function and mark last busy for the device so
+ *    that PM core will try to auto suspend the device at a later time.
+ *
+ *    This function should be called near the end of the device's
+ *    runtime_suspend callback.
+ */
+void blk_post_runtime_suspend(struct request_queue *q, int err)
+{
+	spin_lock_irq(q->queue_lock);
+	if (!err) {
+		q->rpm_status = RPM_SUSPENDED;
+	} else {
+		q->rpm_status = RPM_ACTIVE;
+		pm_runtime_mark_last_busy(q->dev);
+	}
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_post_runtime_suspend);
+
+/**
+ * blk_pre_runtime_resume - Pre runtime resume processing
+ * @q: the queue of the device
+ *
+ * Description:
+ *    Update the queue's runtime status to RESUMING in preparation for the
+ *    runtime resume of the device.
+ *
+ *    This function should be called near the start of the device's
+ *    runtime_resume callback.
+ */
+void blk_pre_runtime_resume(struct request_queue *q)
+{
+	spin_lock_irq(q->queue_lock);
+	q->rpm_status = RPM_RESUMING;
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_pre_runtime_resume);
+
+/**
+ * blk_post_runtime_resume - Post runtime resume processing
+ * @q: the queue of the device
+ * @err: return value of the device's runtime_resume function
+ *
+ * Description:
+ *    Update the queue's runtime status according to the return value of the
+ *    device's runtime_resume function. If it is successfully resumed, process
+ *    the requests that are queued into the device's queue when it is resuming
+ *    and then mark last busy and initiate autosuspend for it.
+ *
+ *    This function should be called near the end of the device's
+ *    runtime_resume callback.
+ */
+void blk_post_runtime_resume(struct request_queue *q, int err)
+{
+	spin_lock_irq(q->queue_lock);
+	if (!err) {
+		q->rpm_status = RPM_ACTIVE;
+		__blk_run_queue(q);
+		pm_runtime_mark_last_busy(q->dev);
+		pm_runtime_autosuspend(q->dev);
+	} else {
+		q->rpm_status = RPM_SUSPENDED;
+	}
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_post_runtime_resume);
+#endif
+
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 4f0ade74cfd..d5cd3131c57 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -2270,11 +2270,8 @@ cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio)
 		return NULL;
 
 	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
-	if (cfqq) {
-		sector_t sector = bio->bi_sector + bio_sectors(bio);
-
-		return elv_rb_find(&cfqq->sort_list, sector);
-	}
+	if (cfqq)
+		return elv_rb_find(&cfqq->sort_list, bio_end_sector(bio));
 
 	return NULL;
 }
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index 90037b5eb17..ba19a3afab7 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -132,7 +132,7 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	 * check for front merge
 	 */
 	if (dd->front_merges) {
-		sector_t sector = bio->bi_sector + bio_sectors(bio);
+		sector_t sector = bio_end_sector(bio);
 
 		__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
 		if (__rq) {
diff --git a/block/elevator.c b/block/elevator.c
index a0ffdd943c9..eba5b04c29b 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -34,6 +34,7 @@
 #include <linux/blktrace_api.h>
 #include <linux/hash.h>
 #include <linux/uaccess.h>
+#include <linux/pm_runtime.h>
 
 #include <trace/events/block.h>
 
@@ -536,6 +537,27 @@ void elv_bio_merged(struct request_queue *q, struct request *rq,
 		e->type->ops.elevator_bio_merged_fn(q, rq, bio);
 }
 
+#ifdef CONFIG_PM_RUNTIME
+static void blk_pm_requeue_request(struct request *rq)
+{
+	if (rq->q->dev && !(rq->cmd_flags & REQ_PM))
+		rq->q->nr_pending--;
+}
+
+static void blk_pm_add_request(struct request_queue *q, struct request *rq)
+{
+	if (q->dev && !(rq->cmd_flags & REQ_PM) && q->nr_pending++ == 0 &&
+	    (q->rpm_status == RPM_SUSPENDED || q->rpm_status == RPM_SUSPENDING))
+		pm_request_resume(q->dev);
+}
+#else
+static inline void blk_pm_requeue_request(struct request *rq) {}
+static inline void blk_pm_add_request(struct request_queue *q,
+				      struct request *rq)
+{
+}
+#endif
+
 void elv_requeue_request(struct request_queue *q, struct request *rq)
 {
 	/*
@@ -550,6 +572,8 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
 
 	rq->cmd_flags &= ~REQ_STARTED;
 
+	blk_pm_requeue_request(rq);
+
 	__elv_add_request(q, rq, ELEVATOR_INSERT_REQUEUE);
 }
 
@@ -572,6 +596,8 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 {
 	trace_block_rq_insert(q, rq);
 
+	blk_pm_add_request(q, rq);
+
 	rq->q = q;
 
 	if (rq->cmd_flags & REQ_SOFTBARRIER) {
diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index ff5804e2f1d..c85fc895ecd 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -238,7 +238,7 @@ static gpt_entry *alloc_read_gpt_entries(struct parsed_partitions *state,
                 le32_to_cpu(gpt->sizeof_partition_entry);
 	if (!count)
 		return NULL;
-	pte = kzalloc(count, GFP_KERNEL);
+	pte = kmalloc(count, GFP_KERNEL);
 	if (!pte)
 		return NULL;
 
@@ -267,7 +267,7 @@ static gpt_header *alloc_read_gpt_header(struct parsed_partitions *state,
 	gpt_header *gpt;
 	unsigned ssz = bdev_logical_block_size(state->bdev);
 
-	gpt = kzalloc(ssz, GFP_KERNEL);
+	gpt = kmalloc(ssz, GFP_KERNEL);
 	if (!gpt)
 		return NULL;