From 5fdee2127faa77c9c91862ad5e001dfab7013e92 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 5 Oct 2017 21:22:52 +0200
Subject: block: remove QUEUE_FLAG_STACKABLE

We already have a queue_is_rq_based helper to check if a request_queue
is request based, so we can remove the flag for it.

Acked-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 02fa42d24b52..9fb71fc7d0e8 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -609,7 +609,6 @@ struct request_queue {
 #define QUEUE_FLAG_NOMERGES     5	/* disable merge attempts */
 #define QUEUE_FLAG_SAME_COMP	6	/* complete on same CPU-group */
 #define QUEUE_FLAG_FAIL_IO	7	/* fake timeout */
-#define QUEUE_FLAG_STACKABLE	8	/* supports request stacking */
 #define QUEUE_FLAG_NONROT	9	/* non-rotational device (SSD) */
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
 #define QUEUE_FLAG_IO_STAT     10	/* do IO stats */
@@ -633,12 +632,10 @@ struct request_queue {
 #define QUEUE_FLAG_QUIESCED    28	/* queue has been quiesced */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
-				 (1 << QUEUE_FLAG_STACKABLE)	|	\
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
 				 (1 << QUEUE_FLAG_ADD_RANDOM))
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
-				 (1 << QUEUE_FLAG_STACKABLE)	|	\
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
 				 (1 << QUEUE_FLAG_POLL))
 
@@ -722,8 +719,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
-#define blk_queue_stackable(q)	\
-	test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
 #define blk_queue_secure_erase(q) \
 	(test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags))
-- 
cgit v1.2.3-70-g09d2


From 7f66721a7d5bf6251f9c49aada9200c61ddcecc5 Mon Sep 17 00:00:00 2001
From: Rakesh Pandit <rakesh@tuxera.com>
Date: Thu, 12 Oct 2017 19:58:10 +0300
Subject: fs/block_dev: remove vfs_msg() interface

Replaced by pr_err usage in commit ef51042472f5 ("block, dax: move
"select DAX" from BLOCK to FS_DAX")

Signed-off-by: Rakesh Pandit <rakesh@tuxera.com>
Acked-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c         | 12 ------------
 include/linux/blkdev.h | 11 -----------
 2 files changed, 23 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 93d088ffc05c..07ddccd17801 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -54,18 +54,6 @@ struct block_device *I_BDEV(struct inode *inode)
 }
 EXPORT_SYMBOL(I_BDEV);
 
-void __vfs_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-
-	va_start(args, fmt);
-	vaf.fmt = fmt;
-	vaf.va = &args;
-	printk_ratelimited("%sVFS (%s): %pV\n", prefix, sb->s_id, &vaf);
-	va_end(args);
-}
-
 static void bdev_write_inode(struct block_device *bdev)
 {
 	struct inode *inode = bdev->bd_inode;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9fb71fc7d0e8..72637028f3c9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -917,17 +917,6 @@ static inline void rq_flush_dcache_pages(struct request *rq)
 }
 #endif
 
-#ifdef CONFIG_PRINTK
-#define vfs_msg(sb, level, fmt, ...)				\
-	__vfs_msg(sb, level, fmt, ##__VA_ARGS__)
-#else
-#define vfs_msg(sb, level, fmt, ...)				\
-do {								\
-	no_printk(fmt, ##__VA_ARGS__);				\
-	__vfs_msg(sb, "", " ");					\
-} while (0)
-#endif
-
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
 extern blk_qc_t generic_make_request(struct bio *bio);
-- 
cgit v1.2.3-70-g09d2


From f421e1d9ade4e1b88183e54425cf50e390d16a7f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 2 Nov 2017 21:29:50 +0300
Subject: block: provide a direct_make_request helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This helper allows reinserting a bio into a new queue without much
overhead, but requires all queue limits to be the same for the upper
and lower queues, and it does not provide any recursion preventions.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 34 ++++++++++++++++++++++++++++++++++
 include/linux/blkdev.h |  1 +
 2 files changed, 35 insertions(+)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index bb4fce694a60..96aaa3a419a3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2243,6 +2243,40 @@ out:
 }
 EXPORT_SYMBOL(generic_make_request);
 
+/**
+ * direct_make_request - hand a buffer directly to its device driver for I/O
+ * @bio:  The bio describing the location in memory and on the device.
+ *
+ * This function behaves like generic_make_request(), but does not protect
+ * against recursion.  Must only be used if the called driver is known
+ * to not call generic_make_request (or direct_make_request) again from
+ * its make_request function.  (Calling direct_make_request again from
+ * a workqueue is perfectly fine as that doesn't recurse).
+ */
+blk_qc_t direct_make_request(struct bio *bio)
+{
+	struct request_queue *q = bio->bi_disk->queue;
+	bool nowait = bio->bi_opf & REQ_NOWAIT;
+	blk_qc_t ret;
+
+	if (!generic_make_request_checks(bio))
+		return BLK_QC_T_NONE;
+
+	if (unlikely(blk_queue_enter(q, nowait))) {
+		if (nowait && !blk_queue_dying(q))
+			bio->bi_status = BLK_STS_AGAIN;
+		else
+			bio->bi_status = BLK_STS_IOERR;
+		bio_endio(bio);
+		return BLK_QC_T_NONE;
+	}
+
+	ret = q->make_request_fn(q, bio);
+	blk_queue_exit(q);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(direct_make_request);
+
 /**
  * submit_bio - submit a bio to the block device layer for I/O
  * @bio: The &struct bio which describes the I/O
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 72637028f3c9..eda3d25c0f68 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -920,6 +920,7 @@ static inline void rq_flush_dcache_pages(struct request *rq)
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
 extern blk_qc_t generic_make_request(struct bio *bio);
+extern blk_qc_t direct_make_request(struct bio *bio);
 extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_init_request_from_bio(struct request *req, struct bio *bio);
 extern void blk_put_request(struct request *);
-- 
cgit v1.2.3-70-g09d2


From ef71de8b15d891b27b8c983a9a8972b11cb4576a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 2 Nov 2017 21:29:51 +0300
Subject: block: add a blk_steal_bios helper

This helpers allows to bounce steal the uncompleted bios from a request so
that they can be reissued on another path.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 21 +++++++++++++++++++++
 include/linux/blkdev.h |  2 ++
 2 files changed, 23 insertions(+)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index 96aaa3a419a3..68cfe6780a9b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2769,6 +2769,27 @@ struct request *blk_fetch_request(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_fetch_request);
 
+/*
+ * Steal bios from a request and add them to a bio list.
+ * The request must not have been partially completed before.
+ */
+void blk_steal_bios(struct bio_list *list, struct request *rq)
+{
+	if (rq->bio) {
+		if (list->tail)
+			list->tail->bi_next = rq->bio;
+		else
+			list->head = rq->bio;
+		list->tail = rq->biotail;
+
+		rq->bio = NULL;
+		rq->biotail = NULL;
+	}
+
+	rq->__data_len = 0;
+}
+EXPORT_SYMBOL_GPL(blk_steal_bios);
+
 /**
  * blk_update_request - Special helper function for request stacking drivers
  * @req:      the request being processed
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index eda3d25c0f68..fddda6a1f9b5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1094,6 +1094,8 @@ extern struct request *blk_peek_request(struct request_queue *q);
 extern void blk_start_request(struct request *rq);
 extern struct request *blk_fetch_request(struct request_queue *q);
 
+void blk_steal_bios(struct bio_list *list, struct request *rq);
+
 /*
  * Request completion related functions.
  *
-- 
cgit v1.2.3-70-g09d2


From ea435e1b9392a33deceaea2a16ebaa3397bead93 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 2 Nov 2017 21:29:54 +0300
Subject: block: add a poll_fn callback to struct request_queue

That we we can also poll non blk-mq queues.  Mostly needed for
the NVMe multipath code, but could also be useful elsewhere.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c             | 11 +++++++++++
 block/blk-mq.c               | 14 +++++---------
 drivers/nvme/target/io-cmd.c |  2 +-
 fs/block_dev.c               |  4 ++--
 fs/direct-io.c               |  2 +-
 fs/iomap.c                   |  2 +-
 include/linux/blkdev.h       |  4 +++-
 mm/page_io.c                 |  2 +-
 8 files changed, 25 insertions(+), 16 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index 68cfe6780a9b..395bfb10d658 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2321,6 +2321,17 @@ blk_qc_t submit_bio(struct bio *bio)
 }
 EXPORT_SYMBOL(submit_bio);
 
+bool blk_poll(struct request_queue *q, blk_qc_t cookie)
+{
+	if (!q->poll_fn || !blk_qc_t_valid(cookie))
+		return false;
+
+	if (current->plug)
+		blk_flush_plug_list(current->plug, false);
+	return q->poll_fn(q, cookie);
+}
+EXPORT_SYMBOL_GPL(blk_poll);
+
 /**
  * blk_cloned_rq_check_limits - Helper function to check a cloned request
  *                              for new the queue limits
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e4d2490f4e7e..95ea5889b825 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -37,6 +37,7 @@
 #include "blk-wbt.h"
 #include "blk-mq-sched.h"
 
+static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie);
 static void blk_mq_poll_stats_start(struct request_queue *q);
 static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
 
@@ -2499,6 +2500,8 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	spin_lock_init(&q->requeue_lock);
 
 	blk_queue_make_request(q, blk_mq_make_request);
+	if (q->mq_ops->poll)
+		q->poll_fn = blk_mq_poll;
 
 	/*
 	 * Do this after blk_queue_make_request() overrides it...
@@ -2961,20 +2964,14 @@ static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq)
 	return false;
 }
 
-bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
+static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
 {
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_plug *plug;
 	struct request *rq;
 
-	if (!q->mq_ops || !q->mq_ops->poll || !blk_qc_t_valid(cookie) ||
-	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+	if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return false;
 
-	plug = current->plug;
-	if (plug)
-		blk_flush_plug_list(plug, false);
-
 	hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
 	if (!blk_qc_t_is_internal(cookie))
 		rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
@@ -2992,7 +2989,6 @@ bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
 
 	return __blk_mq_poll(hctx, rq);
 }
-EXPORT_SYMBOL_GPL(blk_mq_poll);
 
 static int __init blk_mq_init(void)
 {
diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c
index 0d4c23dc4532..db632818777d 100644
--- a/drivers/nvme/target/io-cmd.c
+++ b/drivers/nvme/target/io-cmd.c
@@ -94,7 +94,7 @@ static void nvmet_execute_rw(struct nvmet_req *req)
 
 	cookie = submit_bio(bio);
 
-	blk_mq_poll(bdev_get_queue(req->ns->bdev), cookie);
+	blk_poll(bdev_get_queue(req->ns->bdev), cookie);
 }
 
 static void nvmet_execute_flush(struct nvmet_req *req)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 07ddccd17801..4afa4d5ff969 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -237,7 +237,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 		if (!READ_ONCE(bio.bi_private))
 			break;
 		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_mq_poll(bdev_get_queue(bdev), qc))
+		    !blk_poll(bdev_get_queue(bdev), qc))
 			io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -402,7 +402,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 			break;
 
 		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_mq_poll(bdev_get_queue(bdev), qc))
+		    !blk_poll(bdev_get_queue(bdev), qc))
 			io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 62cf812ed0e5..d2bc339cb1e9 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -486,7 +486,7 @@ static struct bio *dio_await_one(struct dio *dio)
 		dio->waiter = current;
 		spin_unlock_irqrestore(&dio->bio_lock, flags);
 		if (!(dio->iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_mq_poll(dio->bio_disk->queue, dio->bio_cookie))
+		    !blk_poll(dio->bio_disk->queue, dio->bio_cookie))
 			io_schedule();
 		/* wake up sets us TASK_RUNNING */
 		spin_lock_irqsave(&dio->bio_lock, flags);
diff --git a/fs/iomap.c b/fs/iomap.c
index 8194d30bdca0..4241bac905b1 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1049,7 +1049,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 
 			if (!(iocb->ki_flags & IOCB_HIPRI) ||
 			    !dio->submit.last_queue ||
-			    !blk_mq_poll(dio->submit.last_queue,
+			    !blk_poll(dio->submit.last_queue,
 					 dio->submit.cookie))
 				io_schedule();
 		}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index fddda6a1f9b5..225617dd0a3f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -266,6 +266,7 @@ struct blk_queue_ctx;
 
 typedef void (request_fn_proc) (struct request_queue *q);
 typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio);
+typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t);
 typedef int (prep_rq_fn) (struct request_queue *, struct request *);
 typedef void (unprep_rq_fn) (struct request_queue *, struct request *);
 
@@ -408,6 +409,7 @@ struct request_queue {
 
 	request_fn_proc		*request_fn;
 	make_request_fn		*make_request_fn;
+	poll_q_fn		*poll_fn;
 	prep_rq_fn		*prep_rq_fn;
 	unprep_rq_fn		*unprep_rq_fn;
 	softirq_done_fn		*softirq_done_fn;
@@ -975,7 +977,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
 int blk_status_to_errno(blk_status_t status);
 blk_status_t errno_to_blk_status(int errno);
 
-bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie);
+bool blk_poll(struct request_queue *q, blk_qc_t cookie);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 {
diff --git a/mm/page_io.c b/mm/page_io.c
index 21502d341a67..ff04de630c46 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -407,7 +407,7 @@ int swap_readpage(struct page *page, bool do_poll)
 		if (!READ_ONCE(bio->bi_private))
 			break;
 
-		if (!blk_mq_poll(disk->queue, qc))
+		if (!blk_poll(disk->queue, qc))
 			break;
 	}
 	__set_current_state(TASK_RUNNING);
-- 
cgit v1.2.3-70-g09d2


From f00c4d80ffdac9e3a64947ebd57489f3232d5a74 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 5 Nov 2017 10:36:31 +0300
Subject: block: pass full fmode_t to blk_verify_command

Use the obvious calling convention.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bsg.c            | 18 ++++++++----------
 block/scsi_ioctl.c     |  8 ++++----
 drivers/scsi/sg.c      |  2 +-
 include/linux/blkdev.h |  2 +-
 4 files changed, 14 insertions(+), 16 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/bsg.c b/block/bsg.c
index ee1335c68de7..452f94f1c5d4 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -137,7 +137,7 @@ static inline struct hlist_head *bsg_dev_idx_hash(int index)
 
 static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 				struct sg_io_v4 *hdr, struct bsg_device *bd,
-				fmode_t has_write_perm)
+				fmode_t mode)
 {
 	struct scsi_request *req = scsi_req(rq);
 
@@ -152,7 +152,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 		return -EFAULT;
 
 	if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) {
-		if (blk_verify_command(req->cmd, has_write_perm))
+		if (blk_verify_command(req->cmd, mode))
 			return -EPERM;
 	} else if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
@@ -206,7 +206,7 @@ bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *op)
  * map sg_io_v4 to a request.
  */
 static struct request *
-bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
+bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t mode)
 {
 	struct request_queue *q = bd->queue;
 	struct request *rq, *next_rq = NULL;
@@ -237,7 +237,7 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
 	if (IS_ERR(rq))
 		return rq;
 
-	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
+	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, mode);
 	if (ret)
 		goto out;
 
@@ -587,8 +587,7 @@ bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 }
 
 static int __bsg_write(struct bsg_device *bd, const char __user *buf,
-		       size_t count, ssize_t *bytes_written,
-		       fmode_t has_write_perm)
+		       size_t count, ssize_t *bytes_written, fmode_t mode)
 {
 	struct bsg_command *bc;
 	struct request *rq;
@@ -619,7 +618,7 @@ static int __bsg_write(struct bsg_device *bd, const char __user *buf,
 		/*
 		 * get a request, fill in the blanks, and add to request queue
 		 */
-		rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm);
+		rq = bsg_map_hdr(bd, &bc->hdr, mode);
 		if (IS_ERR(rq)) {
 			ret = PTR_ERR(rq);
 			rq = NULL;
@@ -655,8 +654,7 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 	bsg_set_block(bd, file);
 
 	bytes_written = 0;
-	ret = __bsg_write(bd, buf, count, &bytes_written,
-			  file->f_mode & FMODE_WRITE);
+	ret = __bsg_write(bd, buf, count, &bytes_written, file->f_mode);
 
 	*ppos = bytes_written;
 
@@ -915,7 +913,7 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (copy_from_user(&hdr, uarg, sizeof(hdr)))
 			return -EFAULT;
 
-		rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE);
+		rq = bsg_map_hdr(bd, &hdr, file->f_mode);
 		if (IS_ERR(rq))
 			return PTR_ERR(rq);
 
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 7440de44dd85..edcfff974527 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -207,7 +207,7 @@ static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
 	__set_bit(GPCMD_SET_READ_AHEAD, filter->write_ok);
 }
 
-int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm)
+int blk_verify_command(unsigned char *cmd, fmode_t mode)
 {
 	struct blk_cmd_filter *filter = &blk_default_cmd_filter;
 
@@ -220,7 +220,7 @@ int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm)
 		return 0;
 
 	/* Write-safe commands require a writable open */
-	if (test_bit(cmd[0], filter->write_ok) && has_write_perm)
+	if (test_bit(cmd[0], filter->write_ok) && (mode & FMODE_WRITE))
 		return 0;
 
 	return -EPERM;
@@ -234,7 +234,7 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 
 	if (copy_from_user(req->cmd, hdr->cmdp, hdr->cmd_len))
 		return -EFAULT;
-	if (blk_verify_command(req->cmd, mode & FMODE_WRITE))
+	if (blk_verify_command(req->cmd, mode))
 		return -EPERM;
 
 	/*
@@ -469,7 +469,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 	if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
 		goto error;
 
-	err = blk_verify_command(req->cmd, mode & FMODE_WRITE);
+	err = blk_verify_command(req->cmd, mode);
 	if (err)
 		goto error;
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 0419c2298eab..92fd870e1315 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -217,7 +217,7 @@ static int sg_allow_access(struct file *filp, unsigned char *cmd)
 	if (sfp->parentdp->device->type == TYPE_SCANNER)
 		return 0;
 
-	return blk_verify_command(cmd, filp->f_mode & FMODE_WRITE);
+	return blk_verify_command(cmd, filp->f_mode);
 }
 
 static int
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 225617dd0a3f..1437ef4d8037 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1360,7 +1360,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 				    gfp_mask, 0);
 }
 
-extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
+extern int blk_verify_command(unsigned char *cmd, fmode_t mode);
 
 enum blk_default_limits {
 	BLK_MAX_SEGMENTS	= 128,
-- 
cgit v1.2.3-70-g09d2


From 6a15674d1e90917f1723a814e2e8c949000440f7 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 9 Nov 2017 10:49:54 -0800
Subject: block: Introduce blk_get_request_flags()

A side effect of this patch is that the GFP mask that is passed to
several allocation functions in the legacy block layer is changed
from GFP_KERNEL into __GFP_DIRECT_RECLAIM.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Martin Steigerwald <martin@lichtvoll.de>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 50 +++++++++++++++++++++++++++++++++++---------------
 include/linux/blkdev.h |  3 +++
 2 files changed, 38 insertions(+), 15 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index a4362849059a..0f7093dfc010 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1160,7 +1160,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
  * @rl: request list to allocate from
  * @op: operation and flags
  * @bio: bio to allocate request for (can be %NULL)
- * @gfp_mask: allocation mask
+ * @flags: BLQ_MQ_REQ_* flags
  *
  * Get a free request from @q.  This function may fail under memory
  * pressure or if @q is dead.
@@ -1170,7 +1170,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
 static struct request *__get_request(struct request_list *rl, unsigned int op,
-		struct bio *bio, gfp_t gfp_mask)
+				     struct bio *bio, unsigned int flags)
 {
 	struct request_queue *q = rl->q;
 	struct request *rq;
@@ -1179,6 +1179,8 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 	struct io_cq *icq = NULL;
 	const bool is_sync = op_is_sync(op);
 	int may_queue;
+	gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC :
+			 __GFP_DIRECT_RECLAIM;
 	req_flags_t rq_flags = RQF_ALLOCED;
 
 	lockdep_assert_held(q->queue_lock);
@@ -1339,7 +1341,7 @@ rq_starved:
  * @q: request_queue to allocate request from
  * @op: operation and flags
  * @bio: bio to allocate request for (can be %NULL)
- * @gfp_mask: allocation mask
+ * @flags: BLK_MQ_REQ_* flags.
  *
  * Get a free request from @q.  If %__GFP_DIRECT_RECLAIM is set in @gfp_mask,
  * this function keeps retrying under memory pressure and fails iff @q is dead.
@@ -1349,7 +1351,7 @@ rq_starved:
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
 static struct request *get_request(struct request_queue *q, unsigned int op,
-		struct bio *bio, gfp_t gfp_mask)
+				   struct bio *bio, unsigned int flags)
 {
 	const bool is_sync = op_is_sync(op);
 	DEFINE_WAIT(wait);
@@ -1361,7 +1363,7 @@ static struct request *get_request(struct request_queue *q, unsigned int op,
 
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
-	rq = __get_request(rl, op, bio, gfp_mask);
+	rq = __get_request(rl, op, bio, flags);
 	if (!IS_ERR(rq))
 		return rq;
 
@@ -1370,7 +1372,7 @@ retry:
 		return ERR_PTR(-EAGAIN);
 	}
 
-	if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) {
+	if ((flags & BLK_MQ_REQ_NOWAIT) || unlikely(blk_queue_dying(q))) {
 		blk_put_rl(rl);
 		return rq;
 	}
@@ -1397,10 +1399,13 @@ retry:
 	goto retry;
 }
 
+/* flags: BLK_MQ_REQ_PREEMPT and/or BLK_MQ_REQ_NOWAIT. */
 static struct request *blk_old_get_request(struct request_queue *q,
-					   unsigned int op, gfp_t gfp_mask)
+					   unsigned int op, unsigned int flags)
 {
 	struct request *rq;
+	gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC :
+			 __GFP_DIRECT_RECLAIM;
 	int ret = 0;
 
 	WARN_ON_ONCE(q->mq_ops);
@@ -1413,7 +1418,7 @@ static struct request *blk_old_get_request(struct request_queue *q,
 	if (ret)
 		return ERR_PTR(ret);
 	spin_lock_irq(q->queue_lock);
-	rq = get_request(q, op, NULL, gfp_mask);
+	rq = get_request(q, op, NULL, flags);
 	if (IS_ERR(rq)) {
 		spin_unlock_irq(q->queue_lock);
 		blk_queue_exit(q);
@@ -1427,25 +1432,40 @@ static struct request *blk_old_get_request(struct request_queue *q,
 	return rq;
 }
 
-struct request *blk_get_request(struct request_queue *q, unsigned int op,
-				gfp_t gfp_mask)
+/**
+ * blk_get_request_flags - allocate a request
+ * @q: request queue to allocate a request for
+ * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC.
+ * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT.
+ */
+struct request *blk_get_request_flags(struct request_queue *q, unsigned int op,
+				      unsigned int flags)
 {
 	struct request *req;
 
+	WARN_ON_ONCE(op & REQ_NOWAIT);
+	WARN_ON_ONCE(flags & ~BLK_MQ_REQ_NOWAIT);
+
 	if (q->mq_ops) {
-		req = blk_mq_alloc_request(q, op,
-			(gfp_mask & __GFP_DIRECT_RECLAIM) ?
-				0 : BLK_MQ_REQ_NOWAIT);
+		req = blk_mq_alloc_request(q, op, flags);
 		if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
 			q->mq_ops->initialize_rq_fn(req);
 	} else {
-		req = blk_old_get_request(q, op, gfp_mask);
+		req = blk_old_get_request(q, op, flags);
 		if (!IS_ERR(req) && q->initialize_rq_fn)
 			q->initialize_rq_fn(req);
 	}
 
 	return req;
 }
+EXPORT_SYMBOL(blk_get_request_flags);
+
+struct request *blk_get_request(struct request_queue *q, unsigned int op,
+				gfp_t gfp_mask)
+{
+	return blk_get_request_flags(q, op, gfp_mask & __GFP_DIRECT_RECLAIM ?
+				     0 : BLK_MQ_REQ_NOWAIT);
+}
 EXPORT_SYMBOL(blk_get_request);
 
 /**
@@ -1871,7 +1891,7 @@ get_rq:
 	 * Returns with the queue unlocked.
 	 */
 	blk_queue_enter_live(q);
-	req = get_request(q, bio->bi_opf, bio, GFP_NOIO);
+	req = get_request(q, bio->bi_opf, bio, 0);
 	if (IS_ERR(req)) {
 		blk_queue_exit(q);
 		__wbt_done(q->rq_wb, wb_acct);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1437ef4d8037..1af5ddd0f631 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -927,6 +927,9 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_init_request_from_bio(struct request *req, struct bio *bio);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
+extern struct request *blk_get_request_flags(struct request_queue *,
+					     unsigned int op,
+					     unsigned int flags);
 extern struct request *blk_get_request(struct request_queue *, unsigned int op,
 				       gfp_t gfp_mask);
 extern void blk_requeue_request(struct request_queue *, struct request *);
-- 
cgit v1.2.3-70-g09d2


From c9254f2ddb19387ea9714a57ea48463c20333b92 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 9 Nov 2017 10:49:57 -0800
Subject: block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag

This flag will be used in the next patch to let the block layer
core know whether or not a SCSI request queue has been quiesced.
A quiesced SCSI queue namely only processes RQF_PREEMPT requests.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Martin Steigerwald <martin@lichtvoll.de>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 30 ++++++++++++++++++++++++++++++
 block/blk-mq-debugfs.c |  1 +
 include/linux/blkdev.h |  6 ++++++
 3 files changed, 37 insertions(+)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index 17eed16a6e04..edc276899116 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -348,6 +348,36 @@ void blk_sync_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
+/**
+ * blk_set_preempt_only - set QUEUE_FLAG_PREEMPT_ONLY
+ * @q: request queue pointer
+ *
+ * Returns the previous value of the PREEMPT_ONLY flag - 0 if the flag was not
+ * set and 1 if the flag was already set.
+ */
+int blk_set_preempt_only(struct request_queue *q)
+{
+	unsigned long flags;
+	int res;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	res = queue_flag_test_and_set(QUEUE_FLAG_PREEMPT_ONLY, q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return res;
+}
+EXPORT_SYMBOL_GPL(blk_set_preempt_only);
+
+void blk_clear_preempt_only(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	queue_flag_clear(QUEUE_FLAG_PREEMPT_ONLY, q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blk_clear_preempt_only);
+
 /**
  * __blk_run_queue_uncond - run a queue whether or not it has been stopped
  * @q:	The queue to run
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index bb7f08415203..e4f2bb936e66 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -74,6 +74,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(REGISTERED),
 	QUEUE_FLAG_NAME(SCSI_PASSTHROUGH),
 	QUEUE_FLAG_NAME(QUIESCED),
+	QUEUE_FLAG_NAME(PREEMPT_ONLY),
 };
 #undef QUEUE_FLAG_NAME
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1af5ddd0f631..2147e2381a22 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -632,6 +632,7 @@ struct request_queue {
 #define QUEUE_FLAG_REGISTERED  26	/* queue has been registered to a disk */
 #define QUEUE_FLAG_SCSI_PASSTHROUGH 27	/* queue supports SCSI commands */
 #define QUEUE_FLAG_QUIESCED    28	/* queue has been quiesced */
+#define QUEUE_FLAG_PREEMPT_ONLY	29	/* only process REQ_PREEMPT requests */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
@@ -732,6 +733,11 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
 			     REQ_FAILFAST_DRIVER))
 #define blk_queue_quiesced(q)	test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
+#define blk_queue_preempt_only(q)				\
+	test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags)
+
+extern int blk_set_preempt_only(struct request_queue *q);
+extern void blk_clear_preempt_only(struct request_queue *q);
 
 static inline bool blk_account_rq(struct request *rq)
 {
-- 
cgit v1.2.3-70-g09d2


From 3a0a529971ec4e2d933e9c7798db101dfb6b1aec Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 9 Nov 2017 10:49:58 -0800
Subject: block, scsi: Make SCSI quiesce and resume work reliably

The contexts from which a SCSI device can be quiesced or resumed are:
* Writing into /sys/class/scsi_device/*/device/state.
* SCSI parallel (SPI) domain validation.
* The SCSI device power management methods. See also scsi_bus_pm_ops.

It is essential during suspend and resume that neither the filesystem
state nor the filesystem metadata in RAM changes. This is why while
the hibernation image is being written or restored that SCSI devices
are quiesced. The SCSI core quiesces devices through scsi_device_quiesce()
and scsi_device_resume(). In the SDEV_QUIESCE state execution of
non-preempt requests is deferred. This is realized by returning
BLKPREP_DEFER from inside scsi_prep_state_check() for quiesced SCSI
devices. Avoid that a full queue prevents power management requests
to be submitted by deferring allocation of non-preempt requests for
devices in the quiesced state. This patch has been tested by running
the following commands and by verifying that after each resume the
fio job was still running:

for ((i=0; i<10; i++)); do
  (
    cd /sys/block/md0/md &&
    while true; do
      [ "$(<sync_action)" = "idle" ] && echo check > sync_action
      sleep 1
    done
  ) &
  pids=($!)
  for d in /sys/class/block/sd*[a-z]; do
    bdev=${d#/sys/class/block/}
    hcil=$(readlink "$d/device")
    hcil=${hcil#../../../}
    echo 4 > "$d/queue/nr_requests"
    echo 1 > "/sys/class/scsi_device/$hcil/device/queue_depth"
    fio --name="$bdev" --filename="/dev/$bdev" --buffered=0 --bs=512 \
      --rw=randread --ioengine=libaio --numjobs=4 --iodepth=16       \
      --iodepth_batch=1 --thread --loops=$((2**31)) &
    pids+=($!)
  done
  sleep 1
  echo "$(date) Hibernating ..." >>hibernate-test-log.txt
  systemctl hibernate
  sleep 10
  kill "${pids[@]}"
  echo idle > /sys/block/md0/md/sync_action
  wait
  echo "$(date) Done." >>hibernate-test-log.txt
done

Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
References: "I/O hangs after resuming from suspend-to-ram" (https://marc.info/?l=linux-block&m=150340235201348).
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Martin Steigerwald <martin@lichtvoll.de>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c           | 42 ++++++++++++++++++++++++++++++++++--------
 block/blk-mq.c             |  4 ++--
 drivers/scsi/scsi_lib.c    | 42 ++++++++++++++++++++++++++++++------------
 fs/block_dev.c             |  4 ++--
 include/linux/blkdev.h     |  2 +-
 include/scsi/scsi_device.h |  1 +
 6 files changed, 70 insertions(+), 25 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index edc276899116..29b08428ae45 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -374,6 +374,7 @@ void blk_clear_preempt_only(struct request_queue *q)
 
 	spin_lock_irqsave(q->queue_lock, flags);
 	queue_flag_clear(QUEUE_FLAG_PREEMPT_ONLY, q);
+	wake_up_all(&q->mq_freeze_wq);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL_GPL(blk_clear_preempt_only);
@@ -795,15 +796,38 @@ struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(blk_alloc_queue);
 
-int blk_queue_enter(struct request_queue *q, bool nowait)
+/**
+ * blk_queue_enter() - try to increase q->q_usage_counter
+ * @q: request queue pointer
+ * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PREEMPT
+ */
+int blk_queue_enter(struct request_queue *q, unsigned int flags)
 {
+	const bool preempt = flags & BLK_MQ_REQ_PREEMPT;
+
 	while (true) {
+		bool success = false;
 		int ret;
 
-		if (percpu_ref_tryget_live(&q->q_usage_counter))
+		rcu_read_lock_sched();
+		if (percpu_ref_tryget_live(&q->q_usage_counter)) {
+			/*
+			 * The code that sets the PREEMPT_ONLY flag is
+			 * responsible for ensuring that that flag is globally
+			 * visible before the queue is unfrozen.
+			 */
+			if (preempt || !blk_queue_preempt_only(q)) {
+				success = true;
+			} else {
+				percpu_ref_put(&q->q_usage_counter);
+			}
+		}
+		rcu_read_unlock_sched();
+
+		if (success)
 			return 0;
 
-		if (nowait)
+		if (flags & BLK_MQ_REQ_NOWAIT)
 			return -EBUSY;
 
 		/*
@@ -816,7 +840,8 @@ int blk_queue_enter(struct request_queue *q, bool nowait)
 		smp_rmb();
 
 		ret = wait_event_interruptible(q->mq_freeze_wq,
-				!atomic_read(&q->mq_freeze_depth) ||
+				(atomic_read(&q->mq_freeze_depth) == 0 &&
+				 (preempt || !blk_queue_preempt_only(q))) ||
 				blk_queue_dying(q));
 		if (blk_queue_dying(q))
 			return -ENODEV;
@@ -1445,8 +1470,7 @@ static struct request *blk_old_get_request(struct request_queue *q,
 	/* create ioc upfront */
 	create_io_context(gfp_mask, q->node);
 
-	ret = blk_queue_enter(q, !(gfp_mask & __GFP_DIRECT_RECLAIM) ||
-			      (op & REQ_NOWAIT));
+	ret = blk_queue_enter(q, flags);
 	if (ret)
 		return ERR_PTR(ret);
 	spin_lock_irq(q->queue_lock);
@@ -2267,8 +2291,10 @@ blk_qc_t generic_make_request(struct bio *bio)
 	current->bio_list = bio_list_on_stack;
 	do {
 		struct request_queue *q = bio->bi_disk->queue;
+		unsigned int flags = bio->bi_opf & REQ_NOWAIT ?
+			BLK_MQ_REQ_NOWAIT : 0;
 
-		if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) {
+		if (likely(blk_queue_enter(q, flags) == 0)) {
 			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
@@ -2327,7 +2353,7 @@ blk_qc_t direct_make_request(struct bio *bio)
 	if (!generic_make_request_checks(bio))
 		return BLK_QC_T_NONE;
 
-	if (unlikely(blk_queue_enter(q, nowait))) {
+	if (unlikely(blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0))) {
 		if (nowait && !blk_queue_dying(q))
 			bio->bi_status = BLK_STS_AGAIN;
 		else
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e21876778cec..211bc8a3e2cc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -389,7 +389,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 	struct request *rq;
 	int ret;
 
-	ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT);
+	ret = blk_queue_enter(q, flags);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -428,7 +428,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	if (hctx_idx >= q->nr_hw_queues)
 		return ERR_PTR(-EIO);
 
-	ret = blk_queue_enter(q, true);
+	ret = blk_queue_enter(q, flags);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index eb129dfc2ebe..f907e2f8c1dd 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2947,21 +2947,37 @@ static void scsi_wait_for_queuecommand(struct scsi_device *sdev)
 int
 scsi_device_quiesce(struct scsi_device *sdev)
 {
+	struct request_queue *q = sdev->request_queue;
 	int err;
 
+	/*
+	 * It is allowed to call scsi_device_quiesce() multiple times from
+	 * the same context but concurrent scsi_device_quiesce() calls are
+	 * not allowed.
+	 */
+	WARN_ON_ONCE(sdev->quiesced_by && sdev->quiesced_by != current);
+
+	blk_set_preempt_only(q);
+
+	blk_mq_freeze_queue(q);
+	/*
+	 * Ensure that the effect of blk_set_preempt_only() will be visible
+	 * for percpu_ref_tryget() callers that occur after the queue
+	 * unfreeze even if the queue was already frozen before this function
+	 * was called. See also https://lwn.net/Articles/573497/.
+	 */
+	synchronize_rcu();
+	blk_mq_unfreeze_queue(q);
+
 	mutex_lock(&sdev->state_mutex);
 	err = scsi_device_set_state(sdev, SDEV_QUIESCE);
+	if (err == 0)
+		sdev->quiesced_by = current;
+	else
+		blk_clear_preempt_only(q);
 	mutex_unlock(&sdev->state_mutex);
 
-	if (err)
-		return err;
-
-	scsi_run_queue(sdev->request_queue);
-	while (atomic_read(&sdev->device_busy)) {
-		msleep_interruptible(200);
-		scsi_run_queue(sdev->request_queue);
-	}
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL(scsi_device_quiesce);
 
@@ -2981,9 +2997,11 @@ void scsi_device_resume(struct scsi_device *sdev)
 	 * device deleted during suspend)
 	 */
 	mutex_lock(&sdev->state_mutex);
-	if (sdev->sdev_state == SDEV_QUIESCE &&
-	    scsi_device_set_state(sdev, SDEV_RUNNING) == 0)
-		scsi_run_queue(sdev->request_queue);
+	WARN_ON_ONCE(!sdev->quiesced_by);
+	sdev->quiesced_by = NULL;
+	blk_clear_preempt_only(sdev->request_queue);
+	if (sdev->sdev_state == SDEV_QUIESCE)
+		scsi_device_set_state(sdev, SDEV_RUNNING);
 	mutex_unlock(&sdev->state_mutex);
 }
 EXPORT_SYMBOL(scsi_device_resume);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 4afa4d5ff969..04973f484422 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -662,7 +662,7 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return result;
 
-	result = blk_queue_enter(bdev->bd_queue, false);
+	result = blk_queue_enter(bdev->bd_queue, 0);
 	if (result)
 		return result;
 	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false);
@@ -698,7 +698,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 
 	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return -EOPNOTSUPP;
-	result = blk_queue_enter(bdev->bd_queue, false);
+	result = blk_queue_enter(bdev->bd_queue, 0);
 	if (result)
 		return result;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2147e2381a22..402c9d536ae1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -959,7 +959,7 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 			 struct scsi_ioctl_command __user *);
 
-extern int blk_queue_enter(struct request_queue *q, bool nowait);
+extern int blk_queue_enter(struct request_queue *q, unsigned int flags);
 extern void blk_queue_exit(struct request_queue *q);
 extern void blk_start_queue(struct request_queue *q);
 extern void blk_start_queue_async(struct request_queue *q);
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 82e93ee94708..6f0f1e242e23 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -219,6 +219,7 @@ struct scsi_device {
 	unsigned char		access_state;
 	struct mutex		state_mutex;
 	enum scsi_device_state sdev_state;
+	struct task_struct	*quiesced_by;
 	unsigned long		sdev_data[0];
 } __attribute__((aligned(sizeof(unsigned long))));
 
-- 
cgit v1.2.3-70-g09d2


From 9a95e4ef709533efac4aafcb8bddf73f96db50ed Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 9 Nov 2017 10:49:59 -0800
Subject: block, nvme: Introduce blk_mq_req_flags_t

Several block layer and NVMe core functions accept a combination
of BLK_MQ_REQ_* flags through the 'flags' argument but there is
no verification at compile time whether the right type of block
layer flags is passed. Make it possible for sparse to verify this.
This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: linux-nvme@lists.infradead.org
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c          | 12 ++++++------
 block/blk-mq.c            |  4 ++--
 block/blk-mq.h            |  2 +-
 drivers/nvme/host/core.c  |  5 +++--
 drivers/nvme/host/nvme.h  |  5 +++--
 include/linux/blk-mq.h    | 17 +++++++++++------
 include/linux/blk_types.h |  2 ++
 include/linux/blkdev.h    |  4 ++--
 8 files changed, 30 insertions(+), 21 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index 29b08428ae45..7c54c195e79e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -801,7 +801,7 @@ EXPORT_SYMBOL(blk_alloc_queue);
  * @q: request queue pointer
  * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PREEMPT
  */
-int blk_queue_enter(struct request_queue *q, unsigned int flags)
+int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 {
 	const bool preempt = flags & BLK_MQ_REQ_PREEMPT;
 
@@ -1225,7 +1225,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
 static struct request *__get_request(struct request_list *rl, unsigned int op,
-				     struct bio *bio, unsigned int flags)
+				     struct bio *bio, blk_mq_req_flags_t flags)
 {
 	struct request_queue *q = rl->q;
 	struct request *rq;
@@ -1408,7 +1408,7 @@ rq_starved:
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
 static struct request *get_request(struct request_queue *q, unsigned int op,
-				   struct bio *bio, unsigned int flags)
+				   struct bio *bio, blk_mq_req_flags_t flags)
 {
 	const bool is_sync = op_is_sync(op);
 	DEFINE_WAIT(wait);
@@ -1458,7 +1458,7 @@ retry:
 
 /* flags: BLK_MQ_REQ_PREEMPT and/or BLK_MQ_REQ_NOWAIT. */
 static struct request *blk_old_get_request(struct request_queue *q,
-					   unsigned int op, unsigned int flags)
+				unsigned int op, blk_mq_req_flags_t flags)
 {
 	struct request *rq;
 	gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC :
@@ -1495,7 +1495,7 @@ static struct request *blk_old_get_request(struct request_queue *q,
  * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT.
  */
 struct request *blk_get_request_flags(struct request_queue *q, unsigned int op,
-				      unsigned int flags)
+				      blk_mq_req_flags_t flags)
 {
 	struct request *req;
 
@@ -2291,7 +2291,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	current->bio_list = bio_list_on_stack;
 	do {
 		struct request_queue *q = bio->bi_disk->queue;
-		unsigned int flags = bio->bi_opf & REQ_NOWAIT ?
+		blk_mq_req_flags_t flags = bio->bi_opf & REQ_NOWAIT ?
 			BLK_MQ_REQ_NOWAIT : 0;
 
 		if (likely(blk_queue_enter(q, flags) == 0)) {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 211bc8a3e2cc..bfe24a5b62a3 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -383,7 +383,7 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 }
 
 struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
-		unsigned int flags)
+		blk_mq_req_flags_t flags)
 {
 	struct blk_mq_alloc_data alloc_data = { .flags = flags };
 	struct request *rq;
@@ -409,7 +409,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 EXPORT_SYMBOL(blk_mq_alloc_request);
 
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
-		unsigned int op, unsigned int flags, unsigned int hctx_idx)
+	unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
 {
 	struct blk_mq_alloc_data alloc_data = { .flags = flags };
 	struct request *rq;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 2502f40ccdc0..99a19c5523e2 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -111,7 +111,7 @@ static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
 struct blk_mq_alloc_data {
 	/* input parameter */
 	struct request_queue *q;
-	unsigned int flags;
+	blk_mq_req_flags_t flags;
 	unsigned int shallow_depth;
 
 	/* input & output parameter */
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 683d890d73fa..878d5c09d15b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -305,7 +305,7 @@ static void nvme_put_ns(struct nvme_ns *ns)
 }
 
 struct request *nvme_alloc_request(struct request_queue *q,
-		struct nvme_command *cmd, unsigned int flags, int qid)
+		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
 {
 	unsigned op = nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
 	struct request *req;
@@ -573,7 +573,8 @@ EXPORT_SYMBOL_GPL(nvme_setup_cmd);
  */
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
-		unsigned timeout, int qid, int at_head, int flags)
+		unsigned timeout, int qid, int at_head,
+		blk_mq_req_flags_t flags)
 {
 	struct request *req;
 	int ret;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 7b9cc7d616b7..23b8504ace7f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -327,14 +327,15 @@ int nvme_reinit_tagset(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set);
 
 #define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,
-		struct nvme_command *cmd, unsigned int flags, int qid);
+		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid);
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd);
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buf, unsigned bufflen);
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
-		unsigned timeout, int qid, int at_head, int flags);
+		unsigned timeout, int qid, int at_head,
+		blk_mq_req_flags_t flags);
 int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
 void nvme_start_keep_alive(struct nvme_ctrl *ctrl);
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 82b56609736a..b326208277ee 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -209,16 +209,21 @@ void blk_mq_free_request(struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
 
 enum {
-	BLK_MQ_REQ_NOWAIT	= (1 << 0), /* return when out of requests */
-	BLK_MQ_REQ_RESERVED	= (1 << 1), /* allocate from reserved pool */
-	BLK_MQ_REQ_INTERNAL	= (1 << 2), /* allocate internal/sched tag */
-	BLK_MQ_REQ_PREEMPT	= (1 << 3), /* set RQF_PREEMPT */
+	/* return when out of requests */
+	BLK_MQ_REQ_NOWAIT	= (__force blk_mq_req_flags_t)(1 << 0),
+	/* allocate from reserved pool */
+	BLK_MQ_REQ_RESERVED	= (__force blk_mq_req_flags_t)(1 << 1),
+	/* allocate internal/sched tag */
+	BLK_MQ_REQ_INTERNAL	= (__force blk_mq_req_flags_t)(1 << 2),
+	/* set RQF_PREEMPT */
+	BLK_MQ_REQ_PREEMPT	= (__force blk_mq_req_flags_t)(1 << 3),
 };
 
 struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
-		unsigned int flags);
+		blk_mq_req_flags_t flags);
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
-		unsigned int op, unsigned int flags, unsigned int hctx_idx);
+		unsigned int op, blk_mq_req_flags_t flags,
+		unsigned int hctx_idx);
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
 
 enum {
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 1b04085255fb..13ccfc9b210a 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -162,6 +162,8 @@ struct bio {
  */
 #define BIO_RESET_BITS	BVEC_POOL_OFFSET
 
+typedef __u32 __bitwise blk_mq_req_flags_t;
+
 /*
  * Operations and flags common to the bio and request structures.
  * We use 8 bits for encoding the operation, and the remaining 24 for flags.
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 402c9d536ae1..e80ea1d31343 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -935,7 +935,7 @@ extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request_flags(struct request_queue *,
 					     unsigned int op,
-					     unsigned int flags);
+					     blk_mq_req_flags_t flags);
 extern struct request *blk_get_request(struct request_queue *, unsigned int op,
 				       gfp_t gfp_mask);
 extern void blk_requeue_request(struct request_queue *, struct request *);
@@ -959,7 +959,7 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 			 struct scsi_ioctl_command __user *);
 
-extern int blk_queue_enter(struct request_queue *q, unsigned int flags);
+extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags);
 extern void blk_queue_exit(struct request_queue *q);
 extern void blk_start_queue(struct request_queue *q);
 extern void blk_start_queue_async(struct request_queue *q);
-- 
cgit v1.2.3-70-g09d2