Merge tag 'for-5.18/write-streams-2022-03-18' of git://git.kernel.dk/linux-block

Pull NVMe write streams removal from Jens Axboe:
 "This removes the write streams support in NVMe. No vendor ever really
  shipped working support for this, and they are not interested in
  supporting it.

  With the NVMe support gone, we have nothing in the tree that supports
  this. Remove passing around of the hints.

  The only discussion point in this patchset imho is the fact that the
  file specific write hint setting/getting fcntl helpers will now return
  -1/EINVAL like they did before we supported write hints. No known
  applications use these functions, I only know of one prototype that I
  help do for RocksDB, and that's not used. That said, with a change
  like this, it's always a bit controversial. Alternatively, we could
  just make them return 0 and pretend it worked. It's placement based
  hints after all"

* tag 'for-5.18/write-streams-2022-03-18' of git://git.kernel.dk/linux-block:
  fs: remove fs.f_write_hint
  fs: remove kiocb.ki_hint
  block: remove the per-bio/request write hint
  nvme: remove support or stream based temperature hint

Author: torvalds

block/bio.c

@@ -257,7 +257,6 @@ void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
 	bio->bi_opf = opf;
 	bio->bi_flags = 0;
 	bio->bi_ioprio = 0;
-	bio->bi_write_hint = 0;
 	bio->bi_status = 0;
 	bio->bi_iter.bi_sector = 0;
 	bio->bi_iter.bi_size = 0;
@@ -737,7 +736,6 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp)
 	    bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
 	bio->bi_ioprio = bio_src->bi_ioprio;
-	bio->bi_write_hint = bio_src->bi_write_hint;
 	bio->bi_iter = bio_src->bi_iter;
 
 	bio_clone_blkg_association(bio, bio_src);

block/blk-crypto-fallback.c

@@ -170,7 +170,6 @@ static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src)
 		bio_set_flag(bio, BIO_REMAPPED);
 	bio->bi_opf		= bio_src->bi_opf;
 	bio->bi_ioprio		= bio_src->bi_ioprio;
-	bio->bi_write_hint	= bio_src->bi_write_hint;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 

block/blk-merge.c

@@ -754,13 +754,6 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (rq_data_dir(req) != rq_data_dir(next))
 		return NULL;
 
-	/*
-	 * Don't allow merge of different write hints, or for a hint with
-	 * non-hint IO.
-	 */
-	if (req->write_hint != next->write_hint)
-		return NULL;
-
 	if (req->ioprio != next->ioprio)
 		return NULL;
 
@@ -886,13 +879,6 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (!bio_crypt_rq_ctx_compatible(rq, bio))
 		return false;
 
-	/*
-	 * Don't allow merge of different write hints, or for a hint with
-	 * non-hint IO.
-	 */
-	if (rq->write_hint != bio->bi_write_hint)
-		return false;
-
 	if (rq->ioprio != bio_prio(bio))
 		return false;
 

block/blk-mq-debugfs.c

@@ -183,35 +183,11 @@ static ssize_t queue_state_write(void *data, const char __user *buf,
 	return count;
 }
 
-static int queue_write_hint_show(void *data, struct seq_file *m)
-{
-	struct request_queue *q = data;
-	int i;
-
-	for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
-		seq_printf(m, "hint%d: %llu\n", i, q->write_hints[i]);
-
-	return 0;
-}
-
-static ssize_t queue_write_hint_store(void *data, const char __user *buf,
-				      size_t count, loff_t *ppos)
-{
-	struct request_queue *q = data;
-	int i;
-
-	for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
-		q->write_hints[i] = 0;
-
-	return count;
-}
-
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
 	{ "poll_stat", 0400, queue_poll_stat_show },
 	{ "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops },
 	{ "pm_only", 0600, queue_pm_only_show, NULL },
 	{ "state", 0600, queue_state_show, queue_state_write },
-	{ "write_hints", 0600, queue_write_hint_show, queue_write_hint_store },
 	{ "zone_wlock", 0400, queue_zone_wlock_show, NULL },
 	{ },
 };

block/blk-mq.c

@@ -2412,7 +2412,6 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 		rq->cmd_flags |= REQ_FAILFAST_MASK;
 
 	rq->__sector = bio->bi_iter.bi_sector;
-	rq->write_hint = bio->bi_write_hint;
 	blk_rq_bio_prep(rq, bio, nr_segs);
 
 	/* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */

block/bounce.c

@@ -169,7 +169,6 @@ static struct bio *bounce_clone_bio(struct bio *bio_src)
 	if (bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
 	bio->bi_ioprio		= bio_src->bi_ioprio;
-	bio->bi_write_hint	= bio_src->bi_write_hint;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 

block/fops.c

@@ -83,7 +83,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 		bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb));
 	}
 	bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
-	bio.bi_write_hint = iocb->ki_hint;
 	bio.bi_private = current;
 	bio.bi_end_io = blkdev_bio_end_io_simple;
 	bio.bi_ioprio = iocb->ki_ioprio;
@@ -225,7 +224,6 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 
 	for (;;) {
 		bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
-		bio->bi_write_hint = iocb->ki_hint;
 		bio->bi_private = dio;
 		bio->bi_end_io = blkdev_bio_end_io;
 		bio->bi_ioprio = iocb->ki_ioprio;
@@ -327,7 +325,6 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	dio->flags = 0;
 	dio->iocb = iocb;
 	bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
-	bio->bi_write_hint = iocb->ki_hint;
 	bio->bi_end_io = blkdev_bio_end_io_async;
 	bio->bi_ioprio = iocb->ki_ioprio;
 

drivers/md/raid1.c

@@ -1136,8 +1136,6 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
 		goto skip_copy;
 	}
 
-	behind_bio->bi_write_hint = bio->bi_write_hint;
-
 	while (i < vcnt && size) {
 		struct page *page;
 		int len = min_t(int, PAGE_SIZE, size);

drivers/md/raid5-ppl.c

@@ -466,7 +466,6 @@ static void ppl_submit_iounit(struct ppl_io_unit *io)
 	bio->bi_end_io = ppl_log_endio;
 	bio->bi_iter.bi_sector = log->next_io_sector;
 	bio_add_page(bio, io->header_page, PAGE_SIZE, 0);
-	bio->bi_write_hint = ppl_conf->write_hint;
 
 	pr_debug("%s: log->current_io_sector: %llu\n", __func__,
 	    (unsigned long long)log->next_io_sector);
@@ -496,7 +495,6 @@ static void ppl_submit_iounit(struct ppl_io_unit *io)
 			bio = bio_alloc_bioset(prev->bi_bdev, BIO_MAX_VECS,
 					       prev->bi_opf, GFP_NOIO,
 					       &ppl_conf->bs);
-			bio->bi_write_hint = prev->bi_write_hint;
 			bio->bi_iter.bi_sector = bio_end_sector(prev);
 			bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0);
 
@@ -1396,7 +1394,6 @@ int ppl_init_log(struct r5conf *conf)
 	atomic64_set(&ppl_conf->seq, 0);
 	INIT_LIST_HEAD(&ppl_conf->no_mem_stripes);
 	spin_lock_init(&ppl_conf->no_mem_stripes_lock);
-	ppl_conf->write_hint = RWH_WRITE_LIFE_NOT_SET;
 
 	if (!mddev->external) {
 		ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid));
@@ -1495,25 +1492,13 @@ int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add)
 static ssize_t
 ppl_write_hint_show(struct mddev *mddev, char *buf)
 {
-	size_t ret = 0;
-	struct r5conf *conf;
-	struct ppl_conf *ppl_conf = NULL;
-
-	spin_lock(&mddev->lock);
-	conf = mddev->private;
-	if (conf && raid5_has_ppl(conf))
-		ppl_conf = conf->log_private;
-	ret = sprintf(buf, "%d\n", ppl_conf ? ppl_conf->write_hint : 0);
-	spin_unlock(&mddev->lock);
-
-	return ret;
+	return sprintf(buf, "%d\n", 0);
 }
 
 static ssize_t
 ppl_write_hint_store(struct mddev *mddev, const char *page, size_t len)
 {
 	struct r5conf *conf;
-	struct ppl_conf *ppl_conf;
 	int err = 0;
 	unsigned short new;
 
@@ -1527,17 +1512,10 @@ ppl_write_hint_store(struct mddev *mddev, const char *page, size_t len)
 		return err;
 
 	conf = mddev->private;
-	if (!conf) {
+	if (!conf)
 		err = -ENODEV;
-	} else if (raid5_has_ppl(conf)) {
-		ppl_conf = conf->log_private;
-		if (!ppl_conf)
-			err = -EINVAL;
-		else
-			ppl_conf->write_hint = new;
-	} else {
+	else if (!raid5_has_ppl(conf) || !conf->log_private)
 		err = -EINVAL;
-	}
 
 	mddev_unlock(mddev);
 

drivers/md/raid5.c

@@ -1211,9 +1211,6 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			bi->bi_io_vec[0].bv_len = RAID5_STRIPE_SIZE(conf);
 			bi->bi_io_vec[0].bv_offset = sh->dev[i].offset;
 			bi->bi_iter.bi_size = RAID5_STRIPE_SIZE(conf);
-			bi->bi_write_hint = sh->dev[i].write_hint;
-			if (!rrdev)
-				sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -1264,8 +1261,6 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			rbi->bi_io_vec[0].bv_len = RAID5_STRIPE_SIZE(conf);
 			rbi->bi_io_vec[0].bv_offset = sh->dev[i].offset;
 			rbi->bi_iter.bi_size = RAID5_STRIPE_SIZE(conf);
-			rbi->bi_write_hint = sh->dev[i].write_hint;
-			sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -3407,7 +3402,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
 		(unsigned long long)sh->sector);
 
 	spin_lock_irq(&sh->stripe_lock);
-	sh->dev[dd_idx].write_hint = bi->bi_write_hint;
 	/* Don't allow new IO added to stripes in batch list */
 	if (sh->batch_head)
 		goto overlap;