All of lore.kernel.org
 help / color / mirror / Atom feed
From: NeilBrown <neilb@suse.com>
To: Jens Axboe <axboe@kernel.dk>, Jack Wang <jinpu.wang@profitbricks.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Lars Ellenberg <lars.ellenberg@linbit.com>,
	Kent Overstreet <kent.overstreet@gmail.com>,
	Pavel Machek <pavel@ucw.cz>, Mike Snitzer <snitzer@redhat.com>,
	Mikulas Patocka <mpatocka@redhat.com>,
	linux-raid@vger.kernel.org,
	device-mapper development <dm-devel@redhat.com>,
	linux-block@vger.kernel.org
Subject: [PATCH 3/5] blk: make the bioset rescue_workqueue optional.
Date: Fri, 10 Mar 2017 15:35:40 +1100	[thread overview]
Message-ID: <874lz1hhpf.fsf@notabene.neil.brown.name> (raw)
In-Reply-To: <87d1dphhuy.fsf@notabene.neil.brown.name>

[-- Attachment #1: Type: text/plain, Size: 11485 bytes --]


This patch converts bioset_create() and bioset_create_nobvec()
to not create a workqueue so alloctions will never trigger
punt_bios_to_rescuer().
It also introduces bioset_create_rescued() and bioset_create_nobvec_rescued()
which preserve the old behaviour.

*All* callers of bioset_create() and bioset_create_nobvec() are
converted to the _rescued() version, so that not change in behaviour
is experienced.

It is hoped that most, if not all, bioset can end up being the
non-rescued version.

Signed-off-by: NeilBrown <neilb@suse.com>
---
 block/bio.c                         |   30 +++++++++++++++++++++++++-----
 block/blk-core.c                    |    2 +-
 drivers/block/drbd/drbd_main.c      |    2 +-
 drivers/md/bcache/super.c           |    4 ++--
 drivers/md/dm-crypt.c               |    2 +-
 drivers/md/dm-io.c                  |    2 +-
 drivers/md/dm.c                     |    5 +++--
 drivers/md/md.c                     |    2 +-
 drivers/md/raid5-cache.c            |    2 +-
 drivers/target/target_core_iblock.c |    2 +-
 fs/block_dev.c                      |    2 +-
 fs/btrfs/extent_io.c                |    4 ++--
 fs/xfs/xfs_super.c                  |    2 +-
 include/linux/bio.h                 |    2 ++
 14 files changed, 43 insertions(+), 20 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 84ae39f06f81..06587f1119f5 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -362,6 +362,8 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
 	struct bio_list punt, nopunt;
 	struct bio *bio;
 
+	if (!WARN_ON_ONCE(!bs->rescue_workqueue))
+		return;
 	/*
 	 * In order to guarantee forward progress we must punt only bios that
 	 * were allocated from this bio_set; otherwise, if there was a bio on
@@ -471,7 +473,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 
 		if (current->bio_list &&
 		    (!bio_list_empty(&current->bio_list[0]) ||
-		     !bio_list_empty(&current->bio_list[1])))
+		     !bio_list_empty(&current->bio_list[1])) &&
+		    bs->rescue_workqueue)
 			gfp_mask &= ~__GFP_DIRECT_RECLAIM;
 
 		p = mempool_alloc(bs->bio_pool, gfp_mask);
@@ -1940,7 +1943,8 @@ EXPORT_SYMBOL(bioset_free);
 
 static struct bio_set *__bioset_create(unsigned int pool_size,
 				       unsigned int front_pad,
-				       bool create_bvec_pool)
+				       bool create_bvec_pool,
+				       bool create_rescue_workqueue)
 {
 	unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
 	struct bio_set *bs;
@@ -1971,6 +1975,9 @@ static struct bio_set *__bioset_create(unsigned int pool_size,
 			goto bad;
 	}
 
+	if (!create_rescue_workqueue)
+		return bs;
+
 	bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
 	if (!bs->rescue_workqueue)
 		goto bad;
@@ -1996,10 +2003,16 @@ static struct bio_set *__bioset_create(unsigned int pool_size,
  */
 struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
 {
-	return __bioset_create(pool_size, front_pad, true);
+	return __bioset_create(pool_size, front_pad, true, false);
 }
 EXPORT_SYMBOL(bioset_create);
 
+struct bio_set *bioset_create_rescued(unsigned int pool_size, unsigned int front_pad)
+{
+	return __bioset_create(pool_size, front_pad, true, true);
+}
+EXPORT_SYMBOL(bioset_create_rescued);
+
 /**
  * bioset_create_nobvec  - Create a bio_set without bio_vec mempool
  * @pool_size:	Number of bio to cache in the mempool
@@ -2011,10 +2024,17 @@ EXPORT_SYMBOL(bioset_create);
  */
 struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_pad)
 {
-	return __bioset_create(pool_size, front_pad, false);
+	return __bioset_create(pool_size, front_pad, false, false);
 }
 EXPORT_SYMBOL(bioset_create_nobvec);
 
+struct bio_set *bioset_create_nobvec_rescued(unsigned int pool_size,
+					     unsigned int front_pad)
+{
+	return __bioset_create(pool_size, front_pad, false, true);
+}
+EXPORT_SYMBOL(bioset_create_nobvec_rescued);
+
 #ifdef CONFIG_BLK_CGROUP
 
 /**
@@ -2129,7 +2149,7 @@ static int __init init_bio(void)
 	bio_integrity_init();
 	biovec_init_slabs();
 
-	fs_bio_set = bioset_create(BIO_POOL_SIZE, 0);
+	fs_bio_set = bioset_create_rescued(BIO_POOL_SIZE, 0);
 	if (!fs_bio_set)
 		panic("bio: can't allocate bios\n");
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 375006c94c15..c3992d17dc2c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -714,7 +714,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (q->id < 0)
 		goto fail_q;
 
-	q->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+	q->bio_split = bioset_create_rescued(BIO_POOL_SIZE, 0);
 	if (!q->bio_split)
 		goto fail_id;
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 92c60cbd04ee..2c69c2ab0fff 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2166,7 +2166,7 @@ static int drbd_create_mempools(void)
 		goto Enomem;
 
 	/* mempools */
-	drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0);
+	drbd_md_io_bio_set = bioset_create_rescued(DRBD_MIN_POOL_PAGES, 0);
 	if (drbd_md_io_bio_set == NULL)
 		goto Enomem;
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 85e3f21c2514..6cb30792f0ed 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -786,7 +786,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 
 	minor *= BCACHE_MINORS;
 
-	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
+	if (!(d->bio_split = bioset_create_rescued(4, offsetof(struct bbio, bio))) ||
 	    !(d->disk = alloc_disk(BCACHE_MINORS))) {
 		ida_simple_remove(&bcache_minor, minor);
 		return -ENOMEM;
@@ -1520,7 +1520,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 				sizeof(struct bbio) + sizeof(struct bio_vec) *
 				bucket_pages(c))) ||
 	    !(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) ||
-	    !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
+	    !(c->bio_split = bioset_create_rescued(4, offsetof(struct bbio, bio))) ||
 	    !(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
 	    !(c->moving_gc_wq = alloc_workqueue("bcache_gc",
 						WQ_MEM_RECLAIM, 0)) ||
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 389a3637ffcc..91a2d637d44f 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1936,7 +1936,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
-	cc->bs = bioset_create(MIN_IOS, 0);
+	cc->bs = bioset_create_rescued(MIN_IOS, 0);
 	if (!cc->bs) {
 		ti->error = "Cannot allocate crypt bioset";
 		goto bad;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 03940bf36f6c..fe1241c196b1 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -58,7 +58,7 @@ struct dm_io_client *dm_io_client_create(void)
 	if (!client->pool)
 		goto bad;
 
-	client->bios = bioset_create(min_ios, 0);
+	client->bios = bioset_create_rescued(min_ios, 0);
 	if (!client->bios)
 		goto bad;
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index dfb75979e455..41b1f033841f 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1002,7 +1002,8 @@ static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
 
 		while ((bio = bio_list_pop(&list))) {
 			struct bio_set *bs = bio->bi_pool;
-			if (unlikely(!bs) || bs == fs_bio_set) {
+			if (unlikely(!bs) || bs == fs_bio_set ||
+			    !bs->rescue_workqueue) {
 				bio_list_add(&current->bio_list[i], bio);
 				continue;
 			}
@@ -2577,7 +2578,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 		BUG();
 	}
 
-	pools->bs = bioset_create_nobvec(pool_size, front_pad);
+	pools->bs = bioset_create_nobvec_rescued(pool_size, front_pad);
 	if (!pools->bs)
 		goto out;
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d7d2bb51a58d..e5f08a195837 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5220,7 +5220,7 @@ int md_run(struct mddev *mddev)
 	}
 
 	if (mddev->bio_set == NULL) {
-		mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0);
+		mddev->bio_set = bioset_create_rescued(BIO_POOL_SIZE, 0);
 		if (!mddev->bio_set)
 			return -ENOMEM;
 	}
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 3f307be01b10..c95c6c046395 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -2831,7 +2831,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 	if (!log->io_pool)
 		goto io_pool;
 
-	log->bs = bioset_create(R5L_POOL_SIZE, 0);
+	log->bs = bioset_create_rescued(R5L_POOL_SIZE, 0);
 	if (!log->bs)
 		goto io_bs;
 
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index d316ed537d59..5bf3392195c6 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -93,7 +93,7 @@ static int iblock_configure_device(struct se_device *dev)
 		return -EINVAL;
 	}
 
-	ib_dev->ibd_bio_set = bioset_create(IBLOCK_BIO_POOL_SIZE, 0);
+	ib_dev->ibd_bio_set = bioset_create_rescued(IBLOCK_BIO_POOL_SIZE, 0);
 	if (!ib_dev->ibd_bio_set) {
 		pr_err("IBLOCK: Unable to create bioset\n");
 		goto out;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2eca00ec4370..c0ca5f0d0369 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -436,7 +436,7 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 static __init int blkdev_init(void)
 {
-	blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio));
+	blkdev_dio_pool = bioset_create_rescued(4, offsetof(struct blkdev_dio, bio));
 	if (!blkdev_dio_pool)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 28e81922a21c..34aa8893790a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -173,8 +173,8 @@ int __init extent_io_init(void)
 	if (!extent_buffer_cache)
 		goto free_state_cache;
 
-	btrfs_bioset = bioset_create(BIO_POOL_SIZE,
-				     offsetof(struct btrfs_io_bio, bio));
+	btrfs_bioset = bioset_create_rescued(BIO_POOL_SIZE,
+					     offsetof(struct btrfs_io_bio, bio));
 	if (!btrfs_bioset)
 		goto free_buffer_cache;
 
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 890862f2447c..f4c4d6f41d91 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1756,7 +1756,7 @@ MODULE_ALIAS_FS("xfs");
 STATIC int __init
 xfs_init_zones(void)
 {
-	xfs_ioend_bioset = bioset_create(4 * MAX_BUF_PER_PAGE,
+	xfs_ioend_bioset = bioset_create_rescued(4 * MAX_BUF_PER_PAGE,
 			offsetof(struct xfs_ioend, io_inline_bio));
 	if (!xfs_ioend_bioset)
 		goto out;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 8e521194f6fc..05730603fcf1 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -379,7 +379,9 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors,
 }
 
 extern struct bio_set *bioset_create(unsigned int, unsigned int);
+extern struct bio_set *bioset_create_rescued(unsigned int, unsigned int);
 extern struct bio_set *bioset_create_nobvec(unsigned int, unsigned int);
+extern struct bio_set *bioset_create_nobvec_rescued(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
 extern mempool_t *biovec_create_pool(int pool_entries);
 



[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 832 bytes --]

  parent reply	other threads:[~2017-03-10  4:35 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-03  5:14 [PATCH] blk: improve order of bio handling in generic_make_request() NeilBrown
2017-03-03  9:28 ` Jack Wang
2017-03-06  4:40   ` NeilBrown
2017-03-06  9:43     ` Jack Wang
2017-03-07 15:46       ` Pavel Machek
2017-03-07 15:53         ` Jack Wang
2017-03-07 16:21         ` Jens Axboe
2017-03-06 20:18     ` Jens Axboe
2017-03-07  8:49       ` Jack Wang
2017-03-07 16:52         ` Mike Snitzer
2017-03-07 17:05           ` Jens Axboe
2017-03-07 17:14             ` Mike Snitzer
2017-03-07 20:29               ` NeilBrown
2017-03-07 23:01                 ` Mike Snitzer
2017-03-08 16:40                 ` Mikulas Patocka
2017-03-08 17:15                   ` Lars Ellenberg
2017-03-09  6:08                   ` NeilBrown
2017-03-08 11:46           ` Lars Ellenberg
2017-03-07 20:38       ` [PATCH v2] " NeilBrown
2017-03-07 20:38         ` NeilBrown
2017-03-10  4:32         ` NeilBrown
2017-03-10  4:33           ` [PATCH 1/5 v3] " NeilBrown
2017-03-10  4:34           ` [PATCH 2/5] blk: remove bio_set arg from blk_queue_split() NeilBrown
2017-03-10  4:35           ` NeilBrown [this message]
2017-03-10  4:36           ` [PATCH 4/5] blk: use non-rescuing bioset for q->bio_split NeilBrown
2017-03-10  4:37           ` [PATCH 5/5] block_dev: make blkdev_dio_pool a non-rescuing bioset NeilBrown
2017-03-10  4:38           ` [PATCH v2] blk: improve order of bio handling in generic_make_request() Jens Axboe
2017-03-10  4:40             ` Jens Axboe
2017-03-10  5:19             ` NeilBrown
2017-03-10 12:34               ` Lars Ellenberg
2017-03-10 14:38                 ` Mike Snitzer
2017-03-10 14:55                   ` Mikulas Patocka
2017-03-10 15:07                     ` Jack Wang
2017-03-10 15:35                       ` Mike Snitzer
2017-03-10 18:51                       ` Lars Ellenberg
2017-03-11  0:47                 ` NeilBrown
2017-03-11  0:47                   ` NeilBrown
2017-03-10  6:00 [PATCH 0/5] Updates following recent generic_make_request improvement NeilBrown
2017-03-10  6:00 ` [PATCH 3/5] blk: make the bioset rescue_workqueue optional NeilBrown

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=874lz1hhpf.fsf@notabene.neil.brown.name \
    --to=neilb@suse.com \
    --cc=axboe@kernel.dk \
    --cc=dm-devel@redhat.com \
    --cc=jinpu.wang@profitbricks.com \
    --cc=kent.overstreet@gmail.com \
    --cc=lars.ellenberg@linbit.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=mpatocka@redhat.com \
    --cc=pavel@ucw.cz \
    --cc=snitzer@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.