linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sarthak Kukreti <sarthakkukreti@chromium.org>
To: dm-devel@redhat.com, linux-block@vger.kernel.org,
	linux-ext4@vger.kernel.org, linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org
Cc: Jens Axboe <axboe@kernel.dk>,
	"Michael S . Tsirkin" <mst@redhat.com>,
	Jason Wang <jasowang@redhat.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	Alasdair Kergon <agk@redhat.com>,
	Mike Snitzer <snitzer@kernel.org>, Theodore Ts'o <tytso@mit.edu>,
	Andreas Dilger <adilger.kernel@dilger.ca>,
	Bart Van Assche <bvanassche@google.com>,
	Daniil Lunev <dlunev@google.com>, Evan Green <evgreen@google.com>,
	Gwendal Grignou <gwendal@google.com>,
	Sarthak Kukreti <sarthakkukreti@chromium.org>
Subject: [PATCH RFC 2/8] dm: Add support for block provisioning
Date: Thu, 15 Sep 2022 09:48:20 -0700	[thread overview]
Message-ID: <20220915164826.1396245-3-sarthakkukreti@google.com> (raw)
In-Reply-To: <20220915164826.1396245-1-sarthakkukreti@google.com>

From: Sarthak Kukreti <sarthakkukreti@chromium.org>

Add support to dm devices for REQ_OP_PROVISION. The default mode
is to pass through the request and dm-thin will utilize it to provision
blocks.

Signed-off-by: Sarthak Kukreti <sarthakkukreti@chromium.org>
---
 drivers/md/dm-crypt.c         |  4 +-
 drivers/md/dm-linear.c        |  1 +
 drivers/md/dm-table.c         | 17 +++++++
 drivers/md/dm-thin.c          | 86 +++++++++++++++++++++++++++++++++--
 drivers/md/dm.c               |  4 ++
 include/linux/device-mapper.h |  6 +++
 6 files changed, 113 insertions(+), 5 deletions(-)

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 159c6806c19b..357f0899cfb6 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -3081,6 +3081,8 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 	if (ret)
 		return ret;
 
+	ti->num_provision_bios = 1;
+
 	while (opt_params--) {
 		opt_string = dm_shift_arg(&as);
 		if (!opt_string) {
@@ -3384,7 +3386,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	 * - for REQ_OP_DISCARD caller must use flush if IO ordering matters
 	 */
 	if (unlikely(bio->bi_opf & REQ_PREFLUSH ||
-	    bio_op(bio) == REQ_OP_DISCARD)) {
+	    bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_PROVISION)) {
 		bio_set_dev(bio, cc->dev->bdev);
 		if (bio_sectors(bio))
 			bio->bi_iter.bi_sector = cc->start +
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 3212ef6aa81b..1aa782149428 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -61,6 +61,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ti->num_discard_bios = 1;
 	ti->num_secure_erase_bios = 1;
 	ti->num_write_zeroes_bios = 1;
+	ti->num_provision_bios = 1;
 	ti->private = lc;
 	return 0;
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 332f96b58252..b7f9cb66b7ba 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1853,6 +1853,18 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t)
 	return true;
 }
 
+static bool dm_table_supports_provision(struct dm_table *t)
+{
+	for (unsigned int i = 0; i < t->num_targets; i++) {
+		struct dm_target *ti = dm_table_get_target(t, i);
+
+		if (ti->num_provision_bios)
+			return true;
+	}
+
+	return false;
+}
+
 static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
 				     sector_t start, sector_t len, void *data)
 {
@@ -1989,6 +2001,11 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	if (!dm_table_supports_write_zeroes(t))
 		q->limits.max_write_zeroes_sectors = 0;
 
+	if (dm_table_supports_provision(t))
+		blk_queue_max_provision_sectors(q, UINT_MAX >> 9);
+	else
+		q->limits.max_provision_sectors = 0;
+
 	dm_table_verify_integrity(t);
 
 	/*
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index e76c96c760a9..fd3eb306c823 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -908,7 +908,8 @@ static void __inc_remap_and_issue_cell(void *context,
 	struct bio *bio;
 
 	while ((bio = bio_list_pop(&cell->bios))) {
-		if (op_is_flush(bio->bi_opf) || bio_op(bio) == REQ_OP_DISCARD)
+		if (op_is_flush(bio->bi_opf) || bio_op(bio) == REQ_OP_DISCARD ||
+		    bio_op(bio) == REQ_OP_PROVISION)
 			bio_list_add(&info->defer_bios, bio);
 		else {
 			inc_all_io_entry(info->tc->pool, bio);
@@ -1012,6 +1013,9 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 		goto out;
 	}
 
+	if (bio && bio_op(bio) == REQ_OP_PROVISION)
+		return;
+
 	/*
 	 * Release any bios held while the block was being provisioned.
 	 * If we are processing a write bio that completely covers the block,
@@ -1388,6 +1392,9 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 	m->data_block = data_block;
 	m->cell = cell;
 
+	if (bio && bio_op(bio) == REQ_OP_PROVISION)
+		m->bio = bio;
+
 	/*
 	 * If the whole block of data is being overwritten or we are not
 	 * zeroing pre-existing data, we can issue the bio immediately.
@@ -1897,7 +1904,7 @@ static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block
 	/*
 	 * Fill read bios with zeroes and complete them immediately.
 	 */
-	if (bio_data_dir(bio) == READ) {
+	if (bio_data_dir(bio) == READ && bio_op(bio) != REQ_OP_PROVISION) {
 		zero_fill_bio(bio);
 		cell_defer_no_holder(tc, cell);
 		bio_endio(bio);
@@ -1980,6 +1987,69 @@ static void process_cell(struct thin_c *tc, struct dm_bio_prison_cell *cell)
 	}
 }
 
+static void process_provision_cell(struct thin_c *tc, struct dm_bio_prison_cell *cell)
+{
+	int r;
+	struct pool *pool = tc->pool;
+	struct bio *bio = cell->holder;
+	dm_block_t begin, end;
+	struct dm_thin_lookup_result lookup_result;
+
+	if (tc->requeue_mode) {
+		cell_requeue(pool, cell);
+		return;
+	}
+
+	get_bio_block_range(tc, bio, &begin, &end);
+
+	while (begin != end) {
+		r = ensure_next_mapping(pool);
+		if (r)
+			/* we did our best */
+			return;
+
+		r = dm_thin_find_block(tc->td, begin, 1, &lookup_result);
+		switch (r) {
+		case 0:
+			begin++;
+			break;
+		case -ENODATA:
+			provision_block(tc, bio, begin, cell);
+			begin++;
+			break;
+		default:
+			DMERR_LIMIT(
+				"%s: dm_thin_find_block() failed: error = %d",
+				__func__, r);
+			cell_defer_no_holder(tc, cell);
+			bio_io_error(bio);
+			begin++;
+			break;
+		}
+	}
+	bio_endio(bio);
+	cell_defer_no_holder(tc, cell);
+}
+
+static void process_provision_bio(struct thin_c *tc, struct bio *bio)
+{
+	dm_block_t begin, end;
+	struct dm_cell_key virt_key;
+	struct dm_bio_prison_cell *virt_cell;
+
+	get_bio_block_range(tc, bio, &begin, &end);
+	if (begin == end) {
+		bio_endio(bio);
+		return;
+	}
+
+	build_key(tc->td, VIRTUAL, begin, end, &virt_key);
+	if (bio_detain(tc->pool, &virt_key, bio, &virt_cell))
+		return;
+
+	process_provision_cell(tc, virt_cell);
+}
+
 static void process_bio(struct thin_c *tc, struct bio *bio)
 {
 	struct pool *pool = tc->pool;
@@ -2024,7 +2094,7 @@ static void __process_bio_read_only(struct thin_c *tc, struct bio *bio,
 	case -ENODATA:
 		if (cell)
 			cell_defer_no_holder(tc, cell);
-		if (rw != READ) {
+		if (rw != READ || bio_op(bio) == REQ_OP_PROVISION) {
 			handle_unserviceable_bio(tc->pool, bio);
 			break;
 		}
@@ -2200,6 +2270,8 @@ static void process_thin_deferred_bios(struct thin_c *tc)
 
 		if (bio_op(bio) == REQ_OP_DISCARD)
 			pool->process_discard(tc, bio);
+		else if (bio_op(bio) == REQ_OP_PROVISION)
+			process_provision_bio(tc, bio);
 		else
 			pool->process_bio(tc, bio);
 
@@ -2716,7 +2788,8 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_SUBMITTED;
 	}
 
-	if (op_is_flush(bio->bi_opf) || bio_op(bio) == REQ_OP_DISCARD) {
+	if (op_is_flush(bio->bi_opf) || bio_op(bio) == REQ_OP_DISCARD ||
+	    bio_op(bio) == REQ_OP_PROVISION) {
 		thin_defer_bio_with_throttle(tc, bio);
 		return DM_MAPIO_SUBMITTED;
 	}
@@ -3353,6 +3426,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	pt->low_water_blocks = low_water_blocks;
 	pt->adjusted_pf = pt->requested_pf = pf;
 	ti->num_flush_bios = 1;
+	ti->num_provision_bios = 1;
 
 	/*
 	 * Only need to enable discards if the pool should pass
@@ -4043,6 +4117,7 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 		blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT);
 	}
 
+
 	/*
 	 * pt->adjusted_pf is a staging area for the actual features to use.
 	 * They get transferred to the live pool in bind_control_target()
@@ -4233,6 +4308,8 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		ti->num_discard_bios = 1;
 	}
 
+	ti->num_provision_bios = 1;
+
 	mutex_unlock(&dm_thin_pool_table.mutex);
 
 	spin_lock_irq(&tc->pool->lock);
@@ -4447,6 +4524,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 	limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
 	limits->max_discard_sectors = 2048 * 1024 * 16; /* 16G */
+	limits->max_provision_sectors = 2048 * 1024 * 16; /* 16G */
 }
 
 static struct target_type thin_target = {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 60549b65c799..3fe524800f5a 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1600,6 +1600,7 @@ static bool is_abnormal_io(struct bio *bio)
 		case REQ_OP_DISCARD:
 		case REQ_OP_SECURE_ERASE:
 		case REQ_OP_WRITE_ZEROES:
+		case REQ_OP_PROVISION:
 			return true;
 		default:
 			break;
@@ -1624,6 +1625,9 @@ static blk_status_t __process_abnormal_io(struct clone_info *ci,
 	case REQ_OP_WRITE_ZEROES:
 		num_bios = ti->num_write_zeroes_bios;
 		break;
+	case REQ_OP_PROVISION:
+		num_bios = ti->num_provision_bios;
+		break;
 	default:
 		break;
 	}
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 04c6acf7faaa..edeb47195b6f 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -333,6 +333,12 @@ struct dm_target {
 	 */
 	unsigned num_write_zeroes_bios;
 
+	/*
+	 * The number of PROVISION bios that will be submitted to the target.
+	 * The bio number can be accessed with dm_bio_get_target_bio_nr.
+	 */
+	unsigned num_provision_bios;
+
 	/*
 	 * The minimum number of extra bytes allocated in each io for the
 	 * target to use.
-- 
2.31.0


  parent reply	other threads:[~2022-09-15 16:49 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-15 16:48 [PATCH RFC 0/8] Introduce provisioning primitives for thinly provisioned storage Sarthak Kukreti
2022-09-15 16:48 ` [PATCH RFC 1/8] block: Introduce provisioning primitives Sarthak Kukreti
2022-09-23 15:15   ` Mike Snitzer
2022-12-29  8:17     ` Sarthak Kukreti
2022-09-15 16:48 ` Sarthak Kukreti [this message]
2022-09-23 14:23   ` [PATCH RFC 2/8] dm: Add support for block provisioning Mike Snitzer
2022-12-29  8:22     ` Sarthak Kukreti
2022-09-15 16:48 ` [PATCH RFC 3/8] virtio_blk: Add support for provision requests Sarthak Kukreti
2022-09-16  5:48   ` Stefan Hajnoczi
2022-09-20  2:33     ` Sarthak Kukreti
2022-09-27 21:37   ` Michael S. Tsirkin
2022-09-15 16:48 ` [PATCH RFC 4/8] fs: Introduce FALLOC_FL_PROVISION Sarthak Kukreti
2022-09-16 11:56   ` Brian Foster
2022-09-16 21:02     ` Sarthak Kukreti
2022-09-21 15:39       ` Brian Foster
2022-09-22  8:04         ` Sarthak Kukreti
2022-09-22 18:29           ` Brian Foster
2022-12-29  8:13             ` Sarthak Kukreti
2022-09-20  7:49   ` Christoph Hellwig
2022-09-21  5:54     ` Sarthak Kukreti
2022-09-21 15:21       ` Mike Snitzer
2022-09-22  8:08         ` Sarthak Kukreti
2022-09-23  8:45       ` Christoph Hellwig
2022-12-29  8:14         ` Sarthak Kukreti
2022-09-15 16:48 ` [PATCH RFC 5/8] loop: Add support for provision requests Sarthak Kukreti
2022-09-15 16:48 ` [PATCH RFC 6/8] ext4: Add support for FALLOC_FL_PROVISION Sarthak Kukreti
2022-09-15 16:48 ` [PATCH RFC 7/8] ext4: Add mount option for provisioning blocks during allocations Sarthak Kukreti
2022-09-15 16:48 ` [PATCH RFC 8/8] ext4: Add a per-file provision override xattr Sarthak Kukreti
2022-09-16  6:09 ` [PATCH RFC 0/8] Introduce provisioning primitives for thinly provisioned storage Stefan Hajnoczi
2022-09-16 18:48   ` Sarthak Kukreti
2022-09-16 20:01     ` Bart Van Assche
2022-09-16 21:59       ` Sarthak Kukreti
2022-09-20  7:46     ` Christoph Hellwig
     [not found]       ` <CAAKderPF5Z5QLxyEb80Y+90+eR0sfRmL-WfgXLp=eL=HxWSZ9g@mail.gmail.com>
2022-09-20 11:30         ` Christoph Hellwig
     [not found]           ` <CAAKderNcHpbBqWqqd5-WuKLRCQQUt7a_4D4ti4gy15+fKGK0vQ@mail.gmail.com>
2022-09-21 15:08             ` Mike Snitzer
2022-09-23  8:51             ` Christoph Hellwig
2022-09-23 14:08               ` Mike Snitzer
2022-12-29  8:17                 ` Sarthak Kukreti
2022-09-17  3:03 ` [dm-devel] " Darrick J. Wong
2022-09-17 19:46   ` Sarthak Kukreti
2022-09-19 16:36     ` Stefan Hajnoczi

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=20220915164826.1396245-3-sarthakkukreti@google.com \
    --to=sarthakkukreti@chromium.org \
    --cc=adilger.kernel@dilger.ca \
    --cc=agk@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=bvanassche@google.com \
    --cc=dlunev@google.com \
    --cc=dm-devel@redhat.com \
    --cc=evgreen@google.com \
    --cc=gwendal@google.com \
    --cc=jasowang@redhat.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=snitzer@kernel.org \
    --cc=stefanha@redhat.com \
    --cc=tytso@mit.edu \
    --cc=virtualization@lists.linux-foundation.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).