Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Minor overlapping changes for both merge conflicts.

Resolution work done by Stephen Rothwell was used
as a reference.

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 71 insertions, 56 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 0363cd731320..161491d0a879 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -88,19 +88,6 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
-config BLK_DEV_DAX
-	bool "Block device DAX support"
-	depends on FS_DAX
-	depends on BROKEN
-	help
-	  When DAX support is available (CONFIG_FS_DAX) raw block
-	  devices can also support direct userspace access to the
-	  storage capacity via MMAP(2) similar to a file on a
-	  DAX-enabled filesystem.  However, the DAX I/O-path disables
-	  some standard I/O-statistics, and the MMAP(2) path has some
-	  operational differences due to bypassing the page
-	  cache.  If in doubt, say N.
-
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index f70cc3bdfd01..63f72f00c72e 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -86,7 +86,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 
 	bip->bip_bio = bio;
 	bio->bi_integrity = bip;
-	bio->bi_rw |= REQ_INTEGRITY;
+	bio->bi_opf |= REQ_INTEGRITY;
 
 	return bip;
 err:
diff --git a/block/bio.c b/block/bio.c
index 54ee3846c3a5..f39477538fef 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -580,9 +580,11 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	 */
 	bio->bi_bdev = bio_src->bi_bdev;
 	bio_set_flag(bio, BIO_CLONED);
-	bio->bi_rw = bio_src->bi_rw;
+	bio->bi_opf = bio_src->bi_opf;
 	bio->bi_iter = bio_src->bi_iter;
 	bio->bi_io_vec = bio_src->bi_io_vec;
+
+	bio_clone_blkcg_association(bio, bio_src);
 }
 EXPORT_SYMBOL(__bio_clone_fast);
 
@@ -661,7 +663,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 	if (!bio)
 		return NULL;
 	bio->bi_bdev		= bio_src->bi_bdev;
-	bio->bi_rw		= bio_src->bi_rw;
+	bio->bi_opf		= bio_src->bi_opf;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
@@ -687,6 +689,8 @@ integrity_clone:
 		}
 	}
 
+	bio_clone_blkcg_association(bio, bio_src);
+
 	return bio;
 }
 EXPORT_SYMBOL(bio_clone_bioset);
@@ -869,7 +873,7 @@ int submit_bio_wait(struct bio *bio)
 	init_completion(&ret.event);
 	bio->bi_private = &ret;
 	bio->bi_end_io = submit_bio_wait_endio;
-	bio->bi_rw |= REQ_SYNC;
+	bio->bi_opf |= REQ_SYNC;
 	submit_bio(bio);
 	wait_for_completion_io(&ret.event);
 
@@ -2004,6 +2008,17 @@ void bio_disassociate_task(struct bio *bio)
 	}
 }
 
+/**
+ * bio_clone_blkcg_association - clone blkcg association from src to dst bio
+ * @dst: destination bio
+ * @src: source bio
+ */
+void bio_clone_blkcg_association(struct bio *dst, struct bio *src)
+{
+	if (src->bi_css)
+		WARN_ON(bio_associate_blkcg(dst, src->bi_css));
+}
+
 #endif /* CONFIG_BLK_CGROUP */
 
 static void __init biovec_init_slabs(void)
diff --git a/block/blk-core.c b/block/blk-core.c
index a687e9cc16c2..999442ec4601 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1029,7 +1029,7 @@ static bool blk_rq_should_init_elevator(struct bio *bio)
 	 * Flush requests do not use the elevator so skip initialization.
 	 * This allows a request to share the flush and elevator data.
 	 */
-	if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA))
+	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA))
 		return false;
 
 	return true;
@@ -1504,7 +1504,7 @@ EXPORT_SYMBOL_GPL(blk_add_request_payload);
 bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 			    struct bio *bio)
 {
-	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	const int ff = bio->bi_opf & REQ_FAILFAST_MASK;
 
 	if (!ll_back_merge_fn(q, req, bio))
 		return false;
@@ -1526,7 +1526,7 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 			     struct bio *bio)
 {
-	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	const int ff = bio->bi_opf & REQ_FAILFAST_MASK;
 
 	if (!ll_front_merge_fn(q, req, bio))
 		return false;
@@ -1648,8 +1648,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 {
 	req->cmd_type = REQ_TYPE_FS;
 
-	req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK;
-	if (bio->bi_rw & REQ_RAHEAD)
+	req->cmd_flags |= bio->bi_opf & REQ_COMMON_MASK;
+	if (bio->bi_opf & REQ_RAHEAD)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
 	req->errors = 0;
@@ -1660,7 +1660,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
-	const bool sync = !!(bio->bi_rw & REQ_SYNC);
+	const bool sync = !!(bio->bi_opf & REQ_SYNC);
 	struct blk_plug *plug;
 	int el_ret, rw_flags = 0, where = ELEVATOR_INSERT_SORT;
 	struct request *req;
@@ -1681,7 +1681,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) {
+	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) {
 		spin_lock_irq(q->queue_lock);
 		where = ELEVATOR_INSERT_FLUSH;
 		goto get_rq;
@@ -1728,7 +1728,7 @@ get_rq:
 	/*
 	 * Add in META/PRIO flags, if set, before we get to the IO scheduler
 	 */
-	rw_flags |= (bio->bi_rw & (REQ_META | REQ_PRIO));
+	rw_flags |= (bio->bi_opf & (REQ_META | REQ_PRIO));
 
 	/*
 	 * Grab a free request. This is might sleep but can not fail.
@@ -1805,7 +1805,7 @@ static void handle_bad_sector(struct bio *bio)
 	printk(KERN_INFO "attempt to access beyond end of device\n");
 	printk(KERN_INFO "%s: rw=%d, want=%Lu, limit=%Lu\n",
 			bdevname(bio->bi_bdev, b),
-			bio->bi_rw,
+			bio->bi_opf,
 			(unsigned long long)bio_end_sector(bio),
 			(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
 }
@@ -1918,9 +1918,9 @@ generic_make_request_checks(struct bio *bio)
 	 * drivers without flush support don't have to worry
 	 * about them.
 	 */
-	if ((bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) &&
+	if ((bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) &&
 	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
-		bio->bi_rw &= ~(REQ_PREFLUSH | REQ_FUA);
+		bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
 		if (!nr_sectors) {
 			err = 0;
 			goto end_io;
@@ -2219,7 +2219,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 	 * one.
 	 */
 	for (bio = rq->bio; bio; bio = bio->bi_next) {
-		if ((bio->bi_rw & ff) != ff)
+		if ((bio->bi_opf & ff) != ff)
 			break;
 		bytes += bio->bi_iter.bi_size;
 	}
@@ -2630,7 +2630,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	/* mixed attributes always follow the first bio */
 	if (req->cmd_flags & REQ_MIXED_MERGE) {
 		req->cmd_flags &= ~REQ_FAILFAST_MASK;
-		req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
+		req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK;
 	}
 
 	/*
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 41cbd4878958..3eec75a9e91d 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -186,7 +186,7 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 
 	if (split) {
 		/* there isn't chance to merge the splitted bio */
-		split->bi_rw |= REQ_NOMERGE;
+		split->bi_opf |= REQ_NOMERGE;
 
 		bio_chain(split, *bio);
 		trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
@@ -616,9 +616,9 @@ void blk_rq_set_mixed_merge(struct request *rq)
 	 * Distributes the attributs to each bio.
 	 */
 	for (bio = rq->bio; bio; bio = bio->bi_next) {
-		WARN_ON_ONCE((bio->bi_rw & REQ_FAILFAST_MASK) &&
-			     (bio->bi_rw & REQ_FAILFAST_MASK) != ff);
-		bio->bi_rw |= ff;
+		WARN_ON_ONCE((bio->bi_opf & REQ_FAILFAST_MASK) &&
+			     (bio->bi_opf & REQ_FAILFAST_MASK) != ff);
+		bio->bi_opf |= ff;
 	}
 	rq->cmd_flags |= REQ_MIXED_MERGE;
 }
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 4ea4dd8a1eed..fe822aa5b8e4 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -380,15 +380,13 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
 	return ret;
 }
 
-void blk_mq_unregister_disk(struct gendisk *disk)
+static void __blk_mq_unregister_disk(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	int i, j;
 
-	blk_mq_disable_hotplug();
-
 	queue_for_each_hw_ctx(q, hctx, i) {
 		blk_mq_unregister_hctx(hctx);
 
@@ -405,6 +403,12 @@ void blk_mq_unregister_disk(struct gendisk *disk)
 	kobject_put(&disk_to_dev(disk)->kobj);
 
 	q->mq_sysfs_init_done = false;
+}
+
+void blk_mq_unregister_disk(struct gendisk *disk)
+{
+	blk_mq_disable_hotplug();
+	__blk_mq_unregister_disk(disk);
 	blk_mq_enable_hotplug();
 }
 
@@ -450,7 +454,7 @@ int blk_mq_register_disk(struct gendisk *disk)
 	}
 
 	if (ret)
-		blk_mq_unregister_disk(disk);
+		__blk_mq_unregister_disk(disk);
 	else
 		q->mq_sysfs_init_done = true;
 out:
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 576e7112f807..e931a0e8e73d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -672,7 +672,20 @@ static void blk_mq_timeout_work(struct work_struct *work)
 	};
 	int i;
 
-	if (blk_queue_enter(q, true))
+	/* A deadlock might occur if a request is stuck requiring a
+	 * timeout at the same time a queue freeze is waiting
+	 * completion, since the timeout code would not be able to
+	 * acquire the queue reference here.
+	 *
+	 * That's why we don't use blk_queue_enter here; instead, we use
+	 * percpu_ref_tryget directly, because we need to be able to
+	 * obtain a reference even in the short window between the queue
+	 * starting to freeze, by dropping the first reference in
+	 * blk_mq_freeze_queue_start, and the moment the last request is
+	 * consumed, marked by the instant q_usage_counter reaches
+	 * zero.
+	 */
+	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return;
 
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);
@@ -1221,7 +1234,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	if (rw_is_sync(bio_op(bio), bio->bi_rw))
+	if (rw_is_sync(bio_op(bio), bio->bi_opf))
 		op_flags |= REQ_SYNC;
 
 	trace_block_getrq(q, bio, op);
@@ -1289,8 +1302,8 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
  */
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_rw);
-	const int is_flush_fua = bio->bi_rw & (REQ_PREFLUSH | REQ_FUA);
+	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf);
+	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_map_ctx data;
 	struct request *rq;
 	unsigned int request_count = 0;
@@ -1383,8 +1396,8 @@ done:
  */
 static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_rw);
-	const int is_flush_fua = bio->bi_rw & (REQ_PREFLUSH | REQ_FUA);
+	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf);
+	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_plug *plug;
 	unsigned int request_count = 0;
 	struct blk_map_ctx data;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 47a3e540631a..f1aba26f4719 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -145,11 +145,6 @@ struct throtl_data
 	/* Total Number of queued bios on READ and WRITE lists */
 	unsigned int nr_queued[2];
 
-	/*
-	 * number of total undestroyed groups
-	 */
-	unsigned int nr_undestroyed_grps;
-
 	/* Work for dispatching throttled bios */
 	struct work_struct dispatch_work;
 };
@@ -826,8 +821,8 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	 * second time when it eventually gets issued.  Set it when a bio
 	 * is being charged to a tg.
 	 */
-	if (!(bio->bi_rw & REQ_THROTTLED))
-		bio->bi_rw |= REQ_THROTTLED;
+	if (!(bio->bi_opf & REQ_THROTTLED))
+		bio->bi_opf |= REQ_THROTTLED;
 }
 
 /**
@@ -1404,7 +1399,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	/* see throtl_charge_bio() */
-	if ((bio->bi_rw & REQ_THROTTLED) || !tg->has_rules[rw])
+	if ((bio->bi_opf & REQ_THROTTLED) || !tg->has_rules[rw])
 		goto out;
 
 	spin_lock_irq(q->queue_lock);
@@ -1483,7 +1478,7 @@ out:
 	 * being issued.
 	 */
 	if (!throttled)
-		bio->bi_rw &= ~REQ_THROTTLED;
+		bio->bi_opf &= ~REQ_THROTTLED;
 	return throttled;
 }
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index acabba198de9..cc2f6dbd4303 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -918,7 +918,7 @@ static inline struct cfq_data *cic_to_cfqd(struct cfq_io_cq *cic)
  */
 static inline bool cfq_bio_sync(struct bio *bio)
 {
-	return bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC);
+	return bio_data_dir(bio) == READ || (bio->bi_opf & REQ_SYNC);
 }
 
 /*
@@ -2565,7 +2565,7 @@ static void cfq_merged_request(struct request_queue *q, struct request *req,
 static void cfq_bio_merged(struct request_queue *q, struct request *req,
 				struct bio *bio)
 {
-	cfqg_stats_update_io_merged(RQ_CFQG(req), bio_op(bio), bio->bi_rw);
+	cfqg_stats_update_io_merged(RQ_CFQG(req), bio_op(bio), bio->bi_opf);
 }
 
 static void
diff --git a/block/genhd.c b/block/genhd.c
index 3c9dede4e04f..fcd6d4fae657 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -614,7 +614,7 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
 
 	/* Register BDI before referencing it from bdev */
 	bdi = &disk->queue->backing_dev_info;
-	bdi_register_dev(bdi, disk_devt(disk));
+	bdi_register_owner(bdi, disk_to_dev(disk));
 
 	blk_register_region(disk_devt(disk), disk->minors, NULL,
 			    exact_match, exact_lock, disk);
@@ -856,6 +856,7 @@ static void disk_seqf_stop(struct seq_file *seqf, void *v)
 	if (iter) {
 		class_dev_iter_exit(iter);
 		kfree(iter);
+		seqf->private = NULL;
 	}
 }