Merge tag 'v4.5-rc5' into devel

Linux 4.5-rc5

10 files changed, 61 insertions, 63 deletions

diff --git a/block/bio.c b/block/bio.c
index dbabd48b1934..cf7591551b17 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -874,7 +874,7 @@ int submit_bio_wait(int rw, struct bio *bio)
 	bio->bi_private = &ret;
 	bio->bi_end_io = submit_bio_wait_endio;
 	submit_bio(rw, bio);
-	wait_for_completion(&ret.event);
+	wait_for_completion_io(&ret.event);
 
 	return ret.error;
 }
@@ -1090,9 +1090,12 @@ int bio_uncopy_user(struct bio *bio)
 	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
-		 * don't copy into a random user address space, just free.
+		 * don't copy into a random user address space, just free
+		 * and return -EINTR so user space doesn't expect any data.
 		 */
-		if (current->mm && bio_data_dir(bio) == READ)
+		if (!current->mm)
+			ret = -EINTR;
+		else if (bio_data_dir(bio) == READ)
 			ret = bio_copy_to_iter(bio, bmd->iter);
 		if (bmd->is_our_pages)
 			bio_free_pages(bio);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5a37188b559f..66e6f1aae02e 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -788,6 +788,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 {
 	struct gendisk *disk;
 	struct blkcg_gq *blkg;
+	struct module *owner;
 	unsigned int major, minor;
 	int key_len, part, ret;
 	char *body;
@@ -804,7 +805,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	if (!disk)
 		return -ENODEV;
 	if (part) {
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		return -ENODEV;
 	}
 
@@ -820,7 +823,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		ret = PTR_ERR(blkg);
 		rcu_read_unlock();
 		spin_unlock_irq(disk->queue->queue_lock);
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		/*
 		 * If queue was bypassing, we should retry.  Do so after a
 		 * short msleep().  It isn't strictly necessary but queue
@@ -851,9 +856,13 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
 {
+	struct module *owner;
+
 	spin_unlock_irq(ctx->disk->queue->queue_lock);
 	rcu_read_unlock();
+	owner = ctx->disk->fops->owner;
 	put_disk(ctx->disk);
+	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index ab51685988c2..b83d29755b5a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2455,14 +2455,16 @@ struct request *blk_peek_request(struct request_queue *q)
 
 			rq = NULL;
 			break;
-		} else if (ret == BLKPREP_KILL) {
+		} else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) {
+			int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO;
+
 			rq->cmd_flags |= REQ_QUIET;
 			/*
 			 * Mark this request as started so we don't trigger
 			 * any debug logic in the end I/O path.
 			 */
 			blk_start_request(rq);
-			__blk_end_request_all(rq, -EIO);
+			__blk_end_request_all(rq, err);
 		} else {
 			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
 			break;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 1699df5b0493..888a7fec81f7 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -70,6 +70,18 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q,
 	return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
 }
 
+static inline unsigned get_max_io_size(struct request_queue *q,
+				       struct bio *bio)
+{
+	unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
+	unsigned mask = queue_logical_block_size(q) - 1;
+
+	/* aligned to logical block size */
+	sectors &= ~(mask >> 9);
+
+	return sectors;
+}
+
 static struct bio *blk_bio_segment_split(struct request_queue *q,
 					 struct bio *bio,
 					 struct bio_set *bs,
@@ -81,6 +93,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	unsigned front_seg_size = bio->bi_seg_front_size;
 	bool do_split = true;
 	struct bio *new = NULL;
+	const unsigned max_sectors = get_max_io_size(q, bio);
 
 	bio_for_each_segment(bv, bio, iter) {
 		/*
@@ -90,20 +103,19 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 		if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset))
 			goto split;
 
-		if (sectors + (bv.bv_len >> 9) >
-				blk_max_size_offset(q, bio->bi_iter.bi_sector)) {
+		if (sectors + (bv.bv_len >> 9) > max_sectors) {
 			/*
 			 * Consider this a new segment if we're splitting in
 			 * the middle of this vector.
 			 */
 			if (nsegs < queue_max_segments(q) &&
-			    sectors < blk_max_size_offset(q,
-						bio->bi_iter.bi_sector)) {
+			    sectors < max_sectors) {
 				nsegs++;
-				sectors = blk_max_size_offset(q,
-						bio->bi_iter.bi_sector);
+				sectors = max_sectors;
 			}
-			goto split;
+			if (sectors)
+				goto split;
+			/* Make this single bvec as the 1st segment */
 		}
 
 		if (bvprvp && blk_queue_cluster(q)) {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4c0622fae413..56c0a726b619 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -599,8 +599,10 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		 * If a request wasn't started before the queue was
 		 * marked dying, kill it here or it'll go unnoticed.
 		 */
-		if (unlikely(blk_queue_dying(rq->q)))
-			blk_mq_complete_request(rq, -EIO);
+		if (unlikely(blk_queue_dying(rq->q))) {
+			rq->errors = -EIO;
+			blk_mq_end_request(rq, rq->errors);
+		}
 		return;
 	}
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index dd4973583978..c7bb666aafd1 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -91,8 +91,8 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->virt_boundary_mask = 0;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-	lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors =
-		BLK_SAFE_MAX_SECTORS;
+	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	lim->max_dev_sectors = 0;
 	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index e140cc487ce1..dd93763057ce 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -147,10 +147,9 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
 
 static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
 {
-	unsigned long long val;
 
-	val = q->limits.max_hw_discard_sectors << 9;
-	return sprintf(page, "%llu\n", val);
+	return sprintf(page, "%llu\n",
+		(unsigned long long)q->limits.max_hw_discard_sectors << 9);
 }
 
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index a753df2b3fc2..d0dd7882d8c7 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -39,7 +39,6 @@ struct deadline_data {
 	 */
 	struct request *next_rq[2];
 	unsigned int batching;		/* number of sequential requests made */
-	sector_t last_sector;		/* head position */
 	unsigned int starved;		/* times reads have starved writes */
 
 	/*
@@ -210,8 +209,6 @@ deadline_move_request(struct deadline_data *dd, struct request *rq)
 	dd->next_rq[WRITE] = NULL;
 	dd->next_rq[data_dir] = deadline_latter_request(rq);
 
-	dd->last_sector = rq_end_sector(rq);
-
 	/*
 	 * take it off the sort and fifo list, move
 	 * to dispatch queue
diff --git a/block/ioctl.c b/block/ioctl.c
index 77f5d17779d6..d8996bbd7f12 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -434,42 +434,6 @@ bool blkdev_dax_capable(struct block_device *bdev)
 
 	return true;
 }
-
-static int blkdev_daxset(struct block_device *bdev, unsigned long argp)
-{
-	unsigned long arg;
-	int rc = 0;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EACCES;
-
-	if (get_user(arg, (int __user *)(argp)))
-		return -EFAULT;
-	arg = !!arg;
-	if (arg == !!(bdev->bd_inode->i_flags & S_DAX))
-		return 0;
-
-	if (arg)
-		arg = S_DAX;
-
-	if (arg && !blkdev_dax_capable(bdev))
-		return -ENOTTY;
-
-	inode_lock(bdev->bd_inode);
-	if (bdev->bd_map_count == 0)
-		inode_set_flags(bdev->bd_inode, arg, S_DAX);
-	else
-		rc = -EBUSY;
-	inode_unlock(bdev->bd_inode);
-	return rc;
-}
-#else
-static int blkdev_daxset(struct block_device *bdev, int arg)
-{
-	if (arg)
-		return -ENOTTY;
-	return 0;
-}
 #endif
 
 static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
@@ -634,8 +598,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKTRACESETUP:
 	case BLKTRACETEARDOWN:
 		return blk_trace_ioctl(bdev, cmd, argp);
-	case BLKDAXSET:
-		return blkdev_daxset(bdev, arg);
 	case BLKDAXGET:
 		return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX));
 		break;
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 746935a5973c..fefd01b496a0 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -16,6 +16,7 @@
 #include <linux/kmod.h>
 #include <linux/ctype.h>
 #include <linux/genhd.h>
+#include <linux/dax.h>
 #include <linux/blktrace_api.h>
 
 #include "partitions/check.h"
@@ -550,13 +551,24 @@ int invalidate_partitions(struct gendisk *disk, struct block_device *bdev)
 	return 0;
 }
 
-unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
+static struct page *read_pagecache_sector(struct block_device *bdev, sector_t n)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
+
+	return read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)),
+			NULL);
+}
+
+unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
+{
 	struct page *page;
 
-	page = read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)),
-				 NULL);
+	/* don't populate page cache for dax capable devices */
+	if (IS_DAX(bdev->bd_inode))
+		page = read_dax_sector(bdev, n);
+	else
+		page = read_pagecache_sector(bdev, n);
+
 	if (!IS_ERR(page)) {
 		if (PageError(page))
 			goto fail;