From c396b90e502691fc6ff7b43984cfd9d1b15aaa80 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Mar 2024 07:01:40 -0700
Subject: md: add a mddev_trace_remap helper

Add a helper to trace bio remapping that hides some argument
dereferences and the check for a DM-mapped MD device.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-2-hch@lst.de
---
 drivers/md/md.c     |  6 +-----
 drivers/md/md.h     |  8 ++++++++
 drivers/md/raid0.c  |  5 +----
 drivers/md/raid1.c  | 11 ++---------
 drivers/md/raid10.c | 10 ++--------
 drivers/md/raid5.c  | 14 +++-----------
 6 files changed, 17 insertions(+), 37 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 64d544f09295..a52642ecd394 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -65,7 +65,6 @@
 #include <linux/percpu-refcount.h>
 #include <linux/part_stat.h>
 
-#include <trace/events/block.h>
 #include "md.h"
 #include "md-bitmap.h"
 #include "md-cluster.h"
@@ -8686,10 +8685,7 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 
 	bio_chain(discard_bio, bio);
 	bio_clone_blkg_association(discard_bio, bio);
-	if (mddev->gendisk)
-		trace_block_bio_remap(discard_bio,
-				disk_devt(mddev->gendisk),
-				bio->bi_iter.bi_sector);
+	mddev_trace_remap(mddev, discard_bio, bio->bi_iter.bi_sector);
 	submit_bio_noacct(discard_bio);
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 556db28a49aa..928086b638a3 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -18,6 +18,7 @@
 #include <linux/timer.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <trace/events/block.h>
 #include "md-cluster.h"
 
 #define MaxSector (~(sector_t)0)
@@ -910,4 +911,11 @@ int do_md_run(struct mddev *mddev);
 
 extern const struct block_device_operations md_fops;
 
+static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio,
+		sector_t sector)
+{
+	if (mddev->gendisk)
+		trace_block_bio_remap(bio, disk_devt(mddev->gendisk), sector);
+}
+
 #endif /* _MD_MD_H */
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index c50a7abda744..aff094de9743 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -578,10 +578,7 @@ static void raid0_map_submit_bio(struct mddev *mddev, struct bio *bio)
 	bio_set_dev(bio, tmp_dev->bdev);
 	bio->bi_iter.bi_sector = sector + zone->dev_start +
 		tmp_dev->data_offset;
-
-	if (mddev->gendisk)
-		trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
-				      bio_sector);
+	mddev_trace_remap(mddev, bio, bio_sector);
 	mddev_check_write_zeroes(mddev, bio);
 	submit_bio_noacct(bio);
 }
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index afca975ec7f3..421154430f24 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1418,11 +1418,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	    test_bit(R1BIO_FailFast, &r1_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
 	read_bio->bi_private = r1_bio;
-
-	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
-				      r1_bio->sector);
-
+	mddev_trace_remap(mddev, read_bio, r1_bio->sector);
 	submit_bio_noacct(read_bio);
 }
 
@@ -1655,10 +1651,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		mbio->bi_private = r1_bio;
 
 		atomic_inc(&r1_bio->remaining);
-
-		if (mddev->gendisk)
-			trace_block_bio_remap(mbio, disk_devt(mddev->gendisk),
-					      r1_bio->sector);
+		mddev_trace_remap(mddev, mbio, r1_bio->sector);
 		/* flush_pending_writes() needs access to the rdev so...*/
 		mbio->bi_bdev = (void *)rdev;
 		if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug, disks)) {
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 8aecdb1ccc16..9335a1620e6c 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1235,10 +1235,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	    test_bit(R10BIO_FailFast, &r10_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
 	read_bio->bi_private = r10_bio;
-
-	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
-	                              r10_bio->sector);
+	mddev_trace_remap(mddev, read_bio, r10_bio->sector);
 	submit_bio_noacct(read_bio);
 	return;
 }
@@ -1274,10 +1271,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 			 && enough(conf, devnum))
 		mbio->bi_opf |= MD_FAILFAST;
 	mbio->bi_private = r10_bio;
-
-	if (conf->mddev->gendisk)
-		trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk),
-				      r10_bio->sector);
+	mddev_trace_remap(mddev, mbio, r10_bio->sector);
 	/* flush_pending_writes() needs access to the rdev so...*/
 	mbio->bi_bdev = (void *)rdev;
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 58f8395b56d6..f0bc96f68665 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1295,10 +1295,7 @@ again:
 			if (rrdev)
 				set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
 
-			if (conf->mddev->gendisk)
-				trace_block_bio_remap(bi,
-						disk_devt(conf->mddev->gendisk),
-						sh->dev[i].sector);
+			mddev_trace_remap(conf->mddev, bi, sh->dev[i].sector);
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, bi);
 			else
@@ -1342,10 +1339,7 @@ again:
 			 */
 			if (op == REQ_OP_DISCARD)
 				rbi->bi_vcnt = 0;
-			if (conf->mddev->gendisk)
-				trace_block_bio_remap(rbi,
-						disk_devt(conf->mddev->gendisk),
-						sh->dev[i].sector);
+			mddev_trace_remap(conf->mddev, rbi, sh->dev[i].sector);
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, rbi);
 			else
@@ -5523,9 +5517,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 		spin_unlock_irq(&conf->device_lock);
 	}
 
-	if (mddev->gendisk)
-		trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk),
-				      raid_bio->bi_iter.bi_sector);
+	mddev_trace_remap(mddev, align_bio, raid_bio->bi_iter.bi_sector);
 	submit_bio_noacct(align_bio);
 	return 1;
 }
-- 
cgit 


From 28be4fd310d146e9a43d7b1bb55cb7e9f5e06e88 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Mar 2024 07:01:41 -0700
Subject: md: add a mddev_add_trace_msg helper

Add a small wrapper around blk_add_trace_msg that hides some argument
dereferences and the check for a DM-mapped MD device.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-3-hch@lst.de
---
 drivers/md/md-bitmap.c |  9 +++------
 drivers/md/md.c        |  3 +--
 drivers/md/md.h        |  6 ++++++
 drivers/md/raid1.c     | 10 ++++------
 drivers/md/raid10.c    | 15 +++++++--------
 drivers/md/raid5.c     | 14 +++++++-------
 6 files changed, 28 insertions(+), 29 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index a4976ceae868..059afc24c08b 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -1046,9 +1046,8 @@ void md_bitmap_unplug(struct bitmap *bitmap)
 		if (dirty || need_write) {
 			if (!writing) {
 				md_bitmap_wait_writes(bitmap);
-				if (bitmap->mddev->queue)
-					blk_add_trace_msg(bitmap->mddev->queue,
-							  "md bitmap_unplug");
+				mddev_add_trace_msg(bitmap->mddev,
+					"md bitmap_unplug");
 			}
 			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
 			filemap_write_page(bitmap, i, false);
@@ -1319,9 +1318,7 @@ void md_bitmap_daemon_work(struct mddev *mddev)
 	}
 	bitmap->allclean = 1;
 
-	if (bitmap->mddev->queue)
-		blk_add_trace_msg(bitmap->mddev->queue,
-				  "md bitmap_daemon_work");
+	mddev_add_trace_msg(bitmap->mddev, "md bitmap_daemon_work");
 
 	/* Any file-page which is PENDING now needs to be written.
 	 * So set NEEDWRITE now, then after we make any last-minute changes
diff --git a/drivers/md/md.c b/drivers/md/md.c
index a52642ecd394..ab231537c476 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2856,8 +2856,7 @@ repeat:
 	pr_debug("md: updating %s RAID superblock on device (in sync %d)\n",
 		 mdname(mddev), mddev->in_sync);
 
-	if (mddev->queue)
-		blk_add_trace_msg(mddev->queue, "md md_update_sb");
+	mddev_add_trace_msg(mddev, "md md_update_sb");
 rewrite:
 	md_bitmap_update_sb(mddev->bitmap);
 	rdev_for_each(rdev, mddev) {
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 928086b638a3..e2e1ddd397ea 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -918,4 +918,10 @@ static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio,
 		trace_block_bio_remap(bio, disk_devt(mddev->gendisk), sector);
 }
 
+#define mddev_add_trace_msg(mddev, fmt, args...)			\
+do {									\
+	if ((mddev)->gendisk)						\
+		blk_add_trace_msg((mddev)->queue, fmt, ##args);		\
+} while (0)
+
 #endif /* _MD_MD_H */
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 421154430f24..05870a4565fc 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -46,9 +46,6 @@
 static void allow_barrier(struct r1conf *conf, sector_t sector_nr);
 static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
 
-#define raid1_log(md, fmt, args...)				\
-	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
-
 #define RAID_1_10_NAME "raid1"
 #include "raid1-10.c"
 
@@ -1196,7 +1193,7 @@ static void freeze_array(struct r1conf *conf, int extra)
 	 */
 	spin_lock_irq(&conf->resync_lock);
 	conf->array_frozen = 1;
-	raid1_log(conf->mddev, "wait freeze");
+	mddev_add_trace_msg(conf->mddev, "raid1 wait freeze");
 	wait_event_lock_irq_cmd(
 		conf->wait_barrier,
 		get_unqueued_pending(conf) == extra,
@@ -1385,7 +1382,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 		 * Reading from a write-mostly device must take care not to
 		 * over-take any writes that are 'behind'
 		 */
-		raid1_log(mddev, "wait behind writes");
+		mddev_add_trace_msg(mddev, "raid1 wait behind writes");
 		wait_event(bitmap->behind_wait,
 			   atomic_read(&bitmap->behind_writes) == 0);
 	}
@@ -1568,7 +1565,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			bio_wouldblock_error(bio);
 			return;
 		}
-		raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
+		mddev_add_trace_msg(mddev, "raid1 wait rdev %d blocked",
+				blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		wait_barrier(conf, bio->bi_iter.bi_sector, false);
 		goto retry_write;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 9335a1620e6c..1447cb1e4414 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -76,9 +76,6 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
 static void end_reshape_write(struct bio *bio);
 static void end_reshape(struct r10conf *conf);
 
-#define raid10_log(md, fmt, args...)				\
-	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0)
-
 #include "raid1-10.c"
 
 #define NULL_CMD
@@ -1019,7 +1016,7 @@ static bool wait_barrier(struct r10conf *conf, bool nowait)
 			ret = false;
 		} else {
 			conf->nr_waiting++;
-			raid10_log(conf->mddev, "wait barrier");
+			mddev_add_trace_msg(conf->mddev, "raid10 wait barrier");
 			wait_event_barrier(conf, stop_waiting_barrier(conf));
 			conf->nr_waiting--;
 		}
@@ -1138,7 +1135,7 @@ static bool regular_request_wait(struct mddev *mddev, struct r10conf *conf,
 			bio_wouldblock_error(bio);
 			return false;
 		}
-		raid10_log(conf->mddev, "wait reshape");
+		mddev_add_trace_msg(conf->mddev, "raid10 wait reshape");
 		wait_event(conf->wait_barrier,
 			   conf->reshape_progress <= bio->bi_iter.bi_sector ||
 			   conf->reshape_progress >= bio->bi_iter.bi_sector +
@@ -1336,8 +1333,9 @@ retry_wait:
 	if (unlikely(blocked_rdev)) {
 		/* Have to wait for this device to get unblocked, then retry */
 		allow_barrier(conf);
-		raid10_log(conf->mddev, "%s wait rdev %d blocked",
-				__func__, blocked_rdev->raid_disk);
+		mddev_add_trace_msg(conf->mddev,
+			"raid10 %s wait rdev %d blocked",
+			__func__, blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		wait_barrier(conf, false);
 		goto retry_wait;
@@ -1392,7 +1390,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 			bio_wouldblock_error(bio);
 			return;
 		}
-		raid10_log(conf->mddev, "wait reshape metadata");
+		mddev_add_trace_msg(conf->mddev,
+			"raid10 wait reshape metadata");
 		wait_event(mddev->sb_wait,
 			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f0bc96f68665..c082b07d3f63 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4195,10 +4195,9 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 	set_bit(STRIPE_HANDLE, &sh->state);
 	if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_PREFER_RMW)) && rmw > 0) {
 		/* prefer read-modify-write, but need to get some data */
-		if (conf->mddev->queue)
-			blk_add_trace_msg(conf->mddev->queue,
-					  "raid5 rmw %llu %d",
-					  (unsigned long long)sh->sector, rmw);
+		mddev_add_trace_msg(conf->mddev, "raid5 rmw %llu %d",
+				sh->sector, rmw);
+
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if (test_bit(R5_InJournal, &dev->flags) &&
@@ -4276,9 +4275,10 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 			}
 		}
 		if (rcw && conf->mddev->queue)
-			blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
-					  (unsigned long long)sh->sector,
-					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
+			mddev_add_trace_msg(conf->mddev,
+				"raid5 rcw %llu %d %d %d",
+				sh->sector, rcw, qread,
+				test_bit(STRIPE_DELAYED, &sh->state));
 	}
 
 	if (rcw > disks && rmw > disks &&
-- 
cgit 


From 176df894d7974166c65d0cce3b3b019678f9e698 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Mar 2024 07:01:42 -0700
Subject: md: add a mddev_is_dm helper

Add a helper to check for a DM-mapped MD device instead of using
the obfuscated ->gendisk or ->queue NULL checks.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-4-hch@lst.de
---
 drivers/md/md.c     | 15 +++++++--------
 drivers/md/md.h     | 12 ++++++++++--
 drivers/md/raid0.c  |  2 +-
 drivers/md/raid1.c  | 13 +++++--------
 drivers/md/raid10.c | 10 +++++-----
 drivers/md/raid5.c  | 21 ++++++++++-----------
 6 files changed, 38 insertions(+), 35 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/md.c b/drivers/md/md.c
index ab231537c476..2d93ea127b82 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2410,7 +2410,7 @@ int md_integrity_register(struct mddev *mddev)
 
 	if (list_empty(&mddev->disks))
 		return 0; /* nothing to do */
-	if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
+	if (mddev_is_dm(mddev) || blk_get_integrity(mddev->gendisk))
 		return 0; /* shouldn't register, or already is */
 	rdev_for_each(rdev, mddev) {
 		/* skip spares and non-functional disks */
@@ -2463,7 +2463,7 @@ int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
 {
 	struct blk_integrity *bi_mddev;
 
-	if (!mddev->gendisk)
+	if (mddev_is_dm(mddev))
 		return 0;
 
 	bi_mddev = blk_get_integrity(mddev->gendisk);
@@ -5977,7 +5977,7 @@ int md_run(struct mddev *mddev)
 		invalidate_bdev(rdev->bdev);
 		if (mddev->ro != MD_RDONLY && rdev_read_only(rdev)) {
 			mddev->ro = MD_RDONLY;
-			if (mddev->gendisk)
+			if (!mddev_is_dm(mddev))
 				set_disk_ro(mddev->gendisk, 1);
 		}
 
@@ -6139,7 +6139,7 @@ int md_run(struct mddev *mddev)
 		}
 	}
 
-	if (mddev->queue) {
+	if (!mddev_is_dm(mddev)) {
 		bool nonrot = true;
 
 		rdev_for_each(rdev, mddev) {
@@ -6404,7 +6404,7 @@ static void mddev_detach(struct mddev *mddev)
 		mddev->pers->quiesce(mddev, 0);
 	}
 	md_unregister_thread(mddev, &mddev->thread);
-	if (mddev->queue)
+	if (!mddev_is_dm(mddev))
 		blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 }
 
@@ -7360,10 +7360,9 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	if (!rv) {
 		if (mddev_is_clustered(mddev))
 			md_cluster_ops->update_size(mddev, old_dev_sectors);
-		else if (mddev->queue) {
+		else if (!mddev_is_dm(mddev))
 			set_capacity_and_notify(mddev->gendisk,
 						mddev->array_sectors);
-		}
 	}
 	return rv;
 }
@@ -9177,7 +9176,7 @@ void md_do_sync(struct md_thread *thread)
 			mddev->delta_disks > 0 &&
 			mddev->pers->finish_reshape &&
 			mddev->pers->size &&
-			mddev->queue) {
+			!mddev_is_dm(mddev)) {
 		mddev_lock_nointr(mddev);
 		md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0));
 		mddev_unlock(mddev);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index e2e1ddd397ea..d5e99653c690 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -911,16 +911,24 @@ int do_md_run(struct mddev *mddev);
 
 extern const struct block_device_operations md_fops;
 
+/*
+ * MD devices can be used undeneath by DM, in which case ->gendisk is NULL.
+ */
+static inline bool mddev_is_dm(struct mddev *mddev)
+{
+	return !mddev->gendisk;
+}
+
 static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio,
 		sector_t sector)
 {
-	if (mddev->gendisk)
+	if (!mddev_is_dm(mddev))
 		trace_block_bio_remap(bio, disk_devt(mddev->gendisk), sector);
 }
 
 #define mddev_add_trace_msg(mddev, fmt, args...)			\
 do {									\
-	if ((mddev)->gendisk)						\
+	if (!mddev_is_dm(mddev))					\
 		blk_add_trace_msg((mddev)->queue, fmt, ##args);		\
 } while (0)
 
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index aff094de9743..9f787ae77ede 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -399,7 +399,7 @@ static int raid0_run(struct mddev *mddev)
 		mddev->private = conf;
 	}
 	conf = mddev->private;
-	if (mddev->queue) {
+	if (!mddev_is_dm(mddev)) {
 		struct md_rdev *rdev;
 
 		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 05870a4565fc..dd1393d0f084 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1926,7 +1926,7 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors + mirror;
 		if (!p->rdev) {
-			if (mddev->gendisk)
+			if (!mddev_is_dm(mddev))
 				disk_stack_limits(mddev->gendisk, rdev->bdev,
 						  rdev->data_offset << 9);
 
@@ -3227,14 +3227,11 @@ static int raid1_run(struct mddev *mddev)
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
-	if (mddev->queue)
+	if (!mddev_is_dm(mddev)) {
 		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-
-	rdev_for_each(rdev, mddev) {
-		if (!mddev->gendisk)
-			continue;
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
+		rdev_for_each(rdev, mddev)
+			disk_stack_limits(mddev->gendisk, rdev->bdev,
+					  rdev->data_offset << 9);
 	}
 
 	mddev->degraded = 0;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 1447cb1e4414..4021cf06b3a6 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2106,7 +2106,7 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			continue;
 		}
 
-		if (mddev->gendisk)
+		if (!mddev_is_dm(mddev))
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
 
@@ -2126,7 +2126,7 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		set_bit(Replacement, &rdev->flags);
 		rdev->raid_disk = repl_slot;
 		err = 0;
-		if (mddev->gendisk)
+		if (!mddev_is_dm(mddev))
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
 		conf->fullsync = 1;
@@ -4014,7 +4014,7 @@ static int raid10_run(struct mddev *mddev)
 		}
 	}
 
-	if (mddev->queue) {
+	if (!mddev_is_dm(conf->mddev)) {
 		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
 		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
 		raid10_set_io_opt(conf);
@@ -4048,7 +4048,7 @@ static int raid10_run(struct mddev *mddev)
 		if (first || diff < min_offset_diff)
 			min_offset_diff = diff;
 
-		if (mddev->gendisk)
+		if (!mddev_is_dm(mddev))
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
 
@@ -4933,7 +4933,7 @@ static void end_reshape(struct r10conf *conf)
 	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
-	if (conf->mddev->queue)
+	if (!mddev_is_dm(conf->mddev))
 		raid10_set_io_opt(conf);
 	conf->fullsync = 0;
 }
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c082b07d3f63..f8a81176eff8 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2416,12 +2416,12 @@ static int grow_stripes(struct r5conf *conf, int num)
 	size_t namelen = sizeof(conf->cache_name[0]);
 	int devs = max(conf->raid_disks, conf->previous_raid_disks);
 
-	if (conf->mddev->gendisk)
+	if (mddev_is_dm(conf->mddev))
 		snprintf(conf->cache_name[0], namelen,
-			"raid%d-%s", conf->level, mdname(conf->mddev));
+			"raid%d-%p", conf->level, conf->mddev);
 	else
 		snprintf(conf->cache_name[0], namelen,
-			"raid%d-%p", conf->level, conf->mddev);
+			"raid%d-%s", conf->level, mdname(conf->mddev));
 	snprintf(conf->cache_name[1], namelen, "%.27s-alt", conf->cache_name[0]);
 
 	conf->active_name = 0;
@@ -4274,11 +4274,10 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 					set_bit(STRIPE_DELAYED, &sh->state);
 			}
 		}
-		if (rcw && conf->mddev->queue)
-			mddev_add_trace_msg(conf->mddev,
-				"raid5 rcw %llu %d %d %d",
-				sh->sector, rcw, qread,
-				test_bit(STRIPE_DELAYED, &sh->state));
+		if (rcw && !mddev_is_dm(conf->mddev))
+			blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
+					  (unsigned long long)sh->sector,
+					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
 	}
 
 	if (rcw > disks && rmw > disks &&
@@ -5686,7 +5685,7 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
 	}
 	release_inactive_stripe_list(conf, cb->temp_inactive_list,
 				     NR_STRIPE_HASH_LOCKS);
-	if (mddev->queue)
+	if (!mddev_is_dm(mddev))
 		trace_block_unplug(mddev->queue, cnt, !from_schedule);
 	kfree(cb);
 }
@@ -7960,7 +7959,7 @@ static int raid5_run(struct mddev *mddev)
 			mdname(mddev));
 	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 
-	if (mddev->queue) {
+	if (!mddev_is_dm(mddev)) {
 		int chunk_size;
 		/* read-ahead size must cover two whole stripes, which
 		 * is 2 * (datadisks) * chunksize where 'n' is the
@@ -8564,7 +8563,7 @@ static void end_reshape(struct r5conf *conf)
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 
-		if (conf->mddev->queue)
+		if (!mddev_is_dm(conf->mddev))
 			raid5_set_io_opt(conf);
 	}
 }
-- 
cgit 


From e305fce1883128a9468efe1876a057df48a261d6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Mar 2024 07:01:43 -0700
Subject: md: add queue limit helpers

Add a few helpers that wrap the block queue limits API for use in MD.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-5-hch@lst.de
---
 drivers/md/md.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
 drivers/md/md.h |  3 +++
 2 files changed, 48 insertions(+)

(limited to 'drivers/md')

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 2d93ea127b82..7c9fb7dcf0d4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5751,6 +5751,51 @@ static const struct kobj_type md_ktype = {
 
 int mdp_major = 0;
 
+/* stack the limit for all rdevs into lim */
+void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim)
+{
+	struct md_rdev *rdev;
+
+	rdev_for_each(rdev, mddev) {
+		queue_limits_stack_bdev(lim, rdev->bdev, rdev->data_offset,
+					mddev->gendisk->disk_name);
+	}
+}
+EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits);
+
+/* apply the extra stacking limits from a new rdev into mddev */
+int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev)
+{
+	struct queue_limits lim;
+
+	if (mddev_is_dm(mddev))
+		return 0;
+
+	lim = queue_limits_start_update(mddev->queue);
+	queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset,
+				mddev->gendisk->disk_name);
+	return queue_limits_commit_update(mddev->queue, &lim);
+}
+EXPORT_SYMBOL_GPL(mddev_stack_new_rdev);
+
+/* update the optimal I/O size after a reshape */
+void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes)
+{
+	struct queue_limits lim;
+
+	if (mddev_is_dm(mddev))
+		return;
+
+	/* don't bother updating io_opt if we can't suspend the array */
+	if (mddev_suspend(mddev, false) < 0)
+		return;
+	lim = queue_limits_start_update(mddev->gendisk->queue);
+	lim.io_opt = lim.io_min * nr_stripes;
+	queue_limits_commit_update(mddev->gendisk->queue, &lim);
+	mddev_resume(mddev);
+}
+EXPORT_SYMBOL_GPL(mddev_update_io_opt);
+
 static void mddev_delayed_delete(struct work_struct *ws)
 {
 	struct mddev *mddev = container_of(ws, struct mddev, del_work);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index d5e99653c690..0d1119be0b50 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -908,6 +908,9 @@ void md_autostart_arrays(int part);
 int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info);
 int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info);
 int do_md_run(struct mddev *mddev);
+void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim);
+int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev);
+void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes);
 
 extern const struct block_device_operations md_fops;
 
-- 
cgit 


From 56cf22d6f672453f8d3392776c9317f217e68dca Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Mar 2024 07:01:44 -0700
Subject: md/raid0: use the atomic queue limit update APIs

Build the queue limits outside the queue and apply them using
queue_limits_set.  To make the code more obvious also split the queue
limits handling into a separate helper function.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-6-hch@lst.de
---
 drivers/md/raid0.c | 35 ++++++++++++++++++++---------------
 1 file changed, 20 insertions(+), 15 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 9f787ae77ede..f65aa6ecec04 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -379,6 +379,19 @@ static void raid0_free(struct mddev *mddev, void *priv)
 	free_conf(mddev, conf);
 }
 
+static int raid0_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+
+	blk_set_stacking_limits(&lim);
+	lim.max_hw_sectors = mddev->chunk_sectors;
+	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
+	lim.io_min = mddev->chunk_sectors << 9;
+	lim.io_opt = lim.io_min * mddev->raid_disks;
+	mddev_stack_rdev_limits(mddev, &lim);
+	return queue_limits_set(mddev->queue, &lim);
+}
+
 static int raid0_run(struct mddev *mddev)
 {
 	struct r0conf *conf;
@@ -400,19 +413,9 @@ static int raid0_run(struct mddev *mddev)
 	}
 	conf = mddev->private;
 	if (!mddev_is_dm(mddev)) {
-		struct md_rdev *rdev;
-
-		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
-
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		blk_queue_io_opt(mddev->queue,
-				 (mddev->chunk_sectors << 9) * mddev->raid_disks);
-
-		rdev_for_each(rdev, mddev) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-		}
+		ret = raid0_set_limits(mddev);
+		if (ret)
+			goto out_free_conf;
 	}
 
 	/* calculate array device size */
@@ -426,8 +429,10 @@ static int raid0_run(struct mddev *mddev)
 
 	ret = md_integrity_register(mddev);
 	if (ret)
-		free_conf(mddev, conf);
-
+		goto out_free_conf;
+	return 0;
+out_free_conf:
+	free_conf(mddev, conf);
 	return ret;
 }
 
-- 
cgit 


From 97894f7d3c2966164516a8a5109674763d3a55e1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Mar 2024 07:01:45 -0700
Subject: md/raid1: use the atomic queue limit update APIs

Build the queue limits outside the queue and apply them using
queue_limits_set.  To make the code more obvious also split the queue
limits handling into a separate helper function.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-7-hch@lst.de
---
 drivers/md/raid1.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index dd1393d0f084..c34968378377 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1926,12 +1926,11 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors + mirror;
 		if (!p->rdev) {
-			if (!mddev_is_dm(mddev))
-				disk_stack_limits(mddev->gendisk, rdev->bdev,
-						  rdev->data_offset << 9);
+			err = mddev_stack_new_rdev(mddev, rdev);
+			if (err)
+				return err;
 
 			raid1_add_conf(conf, rdev, mirror, false);
-			err = 0;
 			/* As all devices are equivalent, we don't need a full recovery
 			 * if this was recently any drive of the array
 			 */
@@ -3195,12 +3194,21 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
+static int raid1_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+
+	blk_set_stacking_limits(&lim);
+	lim.max_write_zeroes_sectors = 0;
+	mddev_stack_rdev_limits(mddev, &lim);
+	return queue_limits_set(mddev->queue, &lim);
+}
+
 static void raid1_free(struct mddev *mddev, void *priv);
 static int raid1_run(struct mddev *mddev)
 {
 	struct r1conf *conf;
 	int i;
-	struct md_rdev *rdev;
 	int ret;
 
 	if (mddev->level != 1) {
@@ -3228,10 +3236,9 @@ static int raid1_run(struct mddev *mddev)
 		return PTR_ERR(conf);
 
 	if (!mddev_is_dm(mddev)) {
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-		rdev_for_each(rdev, mddev)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
+		ret = raid1_set_limits(mddev);
+		if (ret)
+			goto abort;
 	}
 
 	mddev->degraded = 0;
-- 
cgit 


From f63f17350e537300312e9e19b51f69b61fa44291 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Mar 2024 07:01:46 -0700
Subject: md/raid5: use the atomic queue limit update APIs

Build the queue limits outside the queue and apply them using
queue_limits_set.  To make the code more obvious also split the queue
limits handling into separate helpers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-8-hch@lst.de
---
 drivers/md/raid5.c | 130 ++++++++++++++++++++++++++---------------------------
 1 file changed, 65 insertions(+), 65 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f8a81176eff8..5012069782ba 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7691,10 +7691,65 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
 	return 0;
 }
 
-static void raid5_set_io_opt(struct r5conf *conf)
+static int raid5_set_limits(struct mddev *mddev)
 {
-	blk_queue_io_opt(conf->mddev->queue, (conf->chunk_sectors << 9) *
-			 (conf->raid_disks - conf->max_degraded));
+	struct r5conf *conf = mddev->private;
+	struct queue_limits lim;
+	int data_disks, stripe;
+	struct md_rdev *rdev;
+
+	/*
+	 * The read-ahead size must cover two whole stripes, which is
+	 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices.
+	 */
+	data_disks = conf->previous_raid_disks - conf->max_degraded;
+
+	/*
+	 * We can only discard a whole stripe. It doesn't make sense to
+	 * discard data disk but write parity disk
+	 */
+	stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9));
+
+	blk_set_stacking_limits(&lim);
+	lim.io_min = mddev->chunk_sectors << 9;
+	lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded);
+	lim.raid_partial_stripes_expensive = 1;
+	lim.discard_granularity = stripe;
+	lim.max_write_zeroes_sectors = 0;
+	mddev_stack_rdev_limits(mddev, &lim);
+	rdev_for_each(rdev, mddev)
+		queue_limits_stack_bdev(&lim, rdev->bdev, rdev->new_data_offset,
+				mddev->gendisk->disk_name);
+
+	/*
+	 * Zeroing is required for discard, otherwise data could be lost.
+	 *
+	 * Consider a scenario: discard a stripe (the stripe could be
+	 * inconsistent if discard_zeroes_data is 0); write one disk of the
+	 * stripe (the stripe could be inconsistent again depending on which
+	 * disks are used to calculate parity); the disk is broken; The stripe
+	 * data of this disk is lost.
+	 *
+	 * We only allow DISCARD if the sysadmin has confirmed that only safe
+	 * devices are in use by setting a module parameter.  A better idea
+	 * might be to turn DISCARD into WRITE_ZEROES requests, as that is
+	 * required to be safe.
+	 */
+	if (!devices_handle_discard_safely ||
+	    lim.max_discard_sectors < (stripe >> 9) ||
+	    lim.discard_granularity < stripe)
+		lim.max_hw_discard_sectors = 0;
+
+	/*
+	 * Requests require having a bitmap for each stripe.
+	 * Limit the max sectors based on this.
+	 */
+	lim.max_hw_sectors = RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf);
+
+	/* No restrictions on the number of segments in the request */
+	lim.max_segments = USHRT_MAX;
+
+	return queue_limits_set(mddev->queue, &lim);
 }
 
 static int raid5_run(struct mddev *mddev)
@@ -7707,6 +7762,7 @@ static int raid5_run(struct mddev *mddev)
 	int i;
 	long long min_offset_diff = 0;
 	int first = 1;
+	int ret = -EIO;
 
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
@@ -7960,65 +8016,9 @@ static int raid5_run(struct mddev *mddev)
 	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 
 	if (!mddev_is_dm(mddev)) {
-		int chunk_size;
-		/* read-ahead size must cover two whole stripes, which
-		 * is 2 * (datadisks) * chunksize where 'n' is the
-		 * number of raid devices
-		 */
-		int data_disks = conf->previous_raid_disks - conf->max_degraded;
-		int stripe = data_disks *
-			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-
-		chunk_size = mddev->chunk_sectors << 9;
-		blk_queue_io_min(mddev->queue, chunk_size);
-		raid5_set_io_opt(conf);
-		mddev->queue->limits.raid_partial_stripes_expensive = 1;
-		/*
-		 * We can only discard a whole stripe. It doesn't make sense to
-		 * discard data disk but write parity disk
-		 */
-		stripe = stripe * PAGE_SIZE;
-		stripe = roundup_pow_of_two(stripe);
-		mddev->queue->limits.discard_granularity = stripe;
-
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-
-		rdev_for_each(rdev, mddev) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->new_data_offset << 9);
-		}
-
-		/*
-		 * zeroing is required, otherwise data
-		 * could be lost. Consider a scenario: discard a stripe
-		 * (the stripe could be inconsistent if
-		 * discard_zeroes_data is 0); write one disk of the
-		 * stripe (the stripe could be inconsistent again
-		 * depending on which disks are used to calculate
-		 * parity); the disk is broken; The stripe data of this
-		 * disk is lost.
-		 *
-		 * We only allow DISCARD if the sysadmin has confirmed that
-		 * only safe devices are in use by setting a module parameter.
-		 * A better idea might be to turn DISCARD into WRITE_ZEROES
-		 * requests, as that is required to be safe.
-		 */
-		if (!devices_handle_discard_safely ||
-		    mddev->queue->limits.max_discard_sectors < (stripe >> 9) ||
-		    mddev->queue->limits.discard_granularity < stripe)
-			blk_queue_max_discard_sectors(mddev->queue, 0);
-
-		/*
-		 * Requests require having a bitmap for each stripe.
-		 * Limit the max sectors based on this.
-		 */
-		blk_queue_max_hw_sectors(mddev->queue,
-			RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf));
-
-		/* No restrictions on the number of segments in the request */
-		blk_queue_max_segments(mddev->queue, USHRT_MAX);
+		ret = raid5_set_limits(mddev);
+		if (ret)
+			goto abort;
 	}
 
 	if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
@@ -8031,7 +8031,7 @@ abort:
 	free_conf(conf);
 	mddev->private = NULL;
 	pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev));
-	return -EIO;
+	return ret;
 }
 
 static void raid5_free(struct mddev *mddev, void *priv)
@@ -8563,8 +8563,8 @@ static void end_reshape(struct r5conf *conf)
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 
-		if (!mddev_is_dm(conf->mddev))
-			raid5_set_io_opt(conf);
+		mddev_update_io_opt(conf->mddev,
+			conf->raid_disks - conf->max_degraded);
 	}
 }
 
-- 
cgit 


From 3d8466ba68d444f5528dcbff106e8bf5c7d51aa0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Mar 2024 07:01:47 -0700
Subject: md/raid10: use the atomic queue limit update APIs

Build the queue limits outside the queue and apply them using
queue_limits_set.   To make the code more obvious also split the queue
limits handling into separate helpers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-9-hch@lst.de
---
 drivers/md/raid10.c | 60 +++++++++++++++++++++++++++++------------------------
 1 file changed, 33 insertions(+), 27 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 4021cf06b3a6..e96fdf47319f 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2106,10 +2106,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			continue;
 		}
 
-		if (!mddev_is_dm(mddev))
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
+		err = mddev_stack_new_rdev(mddev, rdev);
+		if (err)
+			return err;
 		p->head_position = 0;
 		p->recovery_disabled = mddev->recovery_disabled - 1;
 		rdev->raid_disk = mirror;
@@ -2125,10 +2124,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		clear_bit(In_sync, &rdev->flags);
 		set_bit(Replacement, &rdev->flags);
 		rdev->raid_disk = repl_slot;
-		err = 0;
-		if (!mddev_is_dm(mddev))
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
+		err = mddev_stack_new_rdev(mddev, rdev);
+		if (err)
+			return err;
 		conf->fullsync = 1;
 		WRITE_ONCE(p->replacement, rdev);
 	}
@@ -3969,14 +3967,26 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
-static void raid10_set_io_opt(struct r10conf *conf)
+static unsigned int raid10_nr_stripes(struct r10conf *conf)
 {
-	int raid_disks = conf->geo.raid_disks;
+	unsigned int raid_disks = conf->geo.raid_disks;
+
+	if (conf->geo.raid_disks % conf->geo.near_copies)
+		return raid_disks;
+	return raid_disks / conf->geo.near_copies;
+}
 
-	if (!(conf->geo.raid_disks % conf->geo.near_copies))
-		raid_disks /= conf->geo.near_copies;
-	blk_queue_io_opt(conf->mddev->queue, (conf->mddev->chunk_sectors << 9) *
-			 raid_disks);
+static int raid10_set_queue_limits(struct mddev *mddev)
+{
+	struct r10conf *conf = mddev->private;
+	struct queue_limits lim;
+
+	blk_set_stacking_limits(&lim);
+	lim.max_write_zeroes_sectors = 0;
+	lim.io_min = mddev->chunk_sectors << 9;
+	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
+	mddev_stack_rdev_limits(mddev, &lim);
+	return queue_limits_set(mddev->queue, &lim);
 }
 
 static int raid10_run(struct mddev *mddev)
@@ -3988,6 +3998,7 @@ static int raid10_run(struct mddev *mddev)
 	sector_t size;
 	sector_t min_offset_diff = 0;
 	int first = 1;
+	int ret = -EIO;
 
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
@@ -4014,12 +4025,6 @@ static int raid10_run(struct mddev *mddev)
 		}
 	}
 
-	if (!mddev_is_dm(conf->mddev)) {
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		raid10_set_io_opt(conf);
-	}
-
 	rdev_for_each(rdev, mddev) {
 		long long diff;
 
@@ -4048,14 +4053,16 @@ static int raid10_run(struct mddev *mddev)
 		if (first || diff < min_offset_diff)
 			min_offset_diff = diff;
 
-		if (!mddev_is_dm(mddev))
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
 		disk->head_position = 0;
 		first = 0;
 	}
 
+	if (!mddev_is_dm(conf->mddev)) {
+		ret = raid10_set_queue_limits(mddev);
+		if (ret)
+			goto out_free_conf;
+	}
+
 	/* need to check that every block has at least one working mirror */
 	if (!enough(conf, -1)) {
 		pr_err("md/raid10:%s: not enough operational mirrors.\n",
@@ -4156,7 +4163,7 @@ out_free_conf:
 	raid10_free_conf(conf);
 	mddev->private = NULL;
 out:
-	return -EIO;
+	return ret;
 }
 
 static void raid10_free(struct mddev *mddev, void *priv)
@@ -4933,8 +4940,7 @@ static void end_reshape(struct r10conf *conf)
 	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
-	if (!mddev_is_dm(conf->mddev))
-		raid10_set_io_opt(conf);
+	mddev_update_io_opt(conf->mddev, raid10_nr_stripes(conf));
 	conf->fullsync = 0;
 }
 
-- 
cgit 


From 81a16e19d545fd244ad176f7222d92b67215a33b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Mar 2024 07:01:48 -0700
Subject: md: don't initialize queue limits

Initial queue limits are now set from ->run.  Remove the superfluous
initialization in md_alloc and level_store.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-10-hch@lst.de
---
 drivers/md/md.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 7c9fb7dcf0d4..4bc47ed2d7a8 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4164,7 +4164,6 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->in_sync = 1;
 		del_timer_sync(&mddev->safemode_timer);
 	}
-	blk_set_stacking_limits(&mddev->queue->limits);
 	pers->run(mddev);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 	if (!mddev->thread)
@@ -5879,7 +5878,6 @@ struct mddev *md_alloc(dev_t dev, char *name)
 	disk->private_data = mddev;
 
 	mddev->queue = disk->queue;
-	blk_set_stacking_limits(&mddev->queue->limits);
 	blk_queue_write_cache(mddev->queue, true, true);
 	disk->events |= DISK_EVENT_MEDIA_CHANGE;
 	mddev->gendisk = disk;
-- 
cgit 


From 396799eb5b6f87ec2d759e1a90e179f7058ab9e6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 3 Mar 2024 07:01:49 -0700
Subject: md: remove mddev->queue

Just use the request_queue from the gendisk pointer in the relatively
few places that sill need it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed--by: Song Liu <song@kernel.org>
Tested-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240303140150.5435-11-hch@lst.de
---
 drivers/md/md.c        | 22 ++++++++++++----------
 drivers/md/md.h        |  5 ++---
 drivers/md/raid0.c     |  2 +-
 drivers/md/raid1.c     |  2 +-
 drivers/md/raid10.c    |  2 +-
 drivers/md/raid5-ppl.c |  3 ++-
 drivers/md/raid5.c     | 13 +++++++------
 7 files changed, 26 insertions(+), 23 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4bc47ed2d7a8..7d7b982e369c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5770,10 +5770,10 @@ int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev)
 	if (mddev_is_dm(mddev))
 		return 0;
 
-	lim = queue_limits_start_update(mddev->queue);
+	lim = queue_limits_start_update(mddev->gendisk->queue);
 	queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset,
 				mddev->gendisk->disk_name);
-	return queue_limits_commit_update(mddev->queue, &lim);
+	return queue_limits_commit_update(mddev->gendisk->queue, &lim);
 }
 EXPORT_SYMBOL_GPL(mddev_stack_new_rdev);
 
@@ -5877,8 +5877,7 @@ struct mddev *md_alloc(dev_t dev, char *name)
 	disk->fops = &md_fops;
 	disk->private_data = mddev;
 
-	mddev->queue = disk->queue;
-	blk_queue_write_cache(mddev->queue, true, true);
+	blk_queue_write_cache(disk->queue, true, true);
 	disk->events |= DISK_EVENT_MEDIA_CHANGE;
 	mddev->gendisk = disk;
 	error = add_disk(disk);
@@ -6183,6 +6182,7 @@ int md_run(struct mddev *mddev)
 	}
 
 	if (!mddev_is_dm(mddev)) {
+		struct request_queue *q = mddev->gendisk->queue;
 		bool nonrot = true;
 
 		rdev_for_each(rdev, mddev) {
@@ -6194,14 +6194,14 @@ int md_run(struct mddev *mddev)
 		if (mddev->degraded)
 			nonrot = false;
 		if (nonrot)
-			blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
+			blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 		else
-			blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
-		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue);
+			blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
+		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, q);
 
 		/* Set the NOWAIT flags if all underlying devices support it */
 		if (nowait)
-			blk_queue_flag_set(QUEUE_FLAG_NOWAIT, mddev->queue);
+			blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -6447,8 +6447,10 @@ static void mddev_detach(struct mddev *mddev)
 		mddev->pers->quiesce(mddev, 0);
 	}
 	md_unregister_thread(mddev, &mddev->thread);
+
+	/* the unplug fn references 'conf' */
 	if (!mddev_is_dm(mddev))
-		blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+		blk_sync_queue(mddev->gendisk->queue);
 }
 
 static void __md_stop(struct mddev *mddev)
@@ -7166,7 +7168,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
 	if (!bdev_nowait(rdev->bdev)) {
 		pr_info("%s: Disabling nowait because %pg does not support nowait\n",
 			mdname(mddev), rdev->bdev);
-		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->queue);
+		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->gendisk->queue);
 	}
 	/*
 	 * Kick recovery, maybe this spare has to be added to the
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 0d1119be0b50..67e50c44f4b5 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -480,7 +480,6 @@ struct mddev {
 	struct timer_list		safemode_timer;
 	struct percpu_ref		writes_pending;
 	int				sync_checkers;	/* # of threads checking writes_pending */
-	struct request_queue		*queue;	/* for plugging ... */
 
 	struct bitmap			*bitmap; /* the bitmap for the device */
 	struct {
@@ -869,7 +868,7 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio
 {
 	if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
 	    !bio->bi_bdev->bd_disk->queue->limits.max_write_zeroes_sectors)
-		mddev->queue->limits.max_write_zeroes_sectors = 0;
+		mddev->gendisk->queue->limits.max_write_zeroes_sectors = 0;
 }
 
 static inline int mddev_suspend_and_lock(struct mddev *mddev)
@@ -932,7 +931,7 @@ static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio,
 #define mddev_add_trace_msg(mddev, fmt, args...)			\
 do {									\
 	if (!mddev_is_dm(mddev))					\
-		blk_add_trace_msg((mddev)->queue, fmt, ##args);		\
+		blk_add_trace_msg((mddev)->gendisk->queue, fmt, ##args); \
 } while (0)
 
 #endif /* _MD_MD_H */
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index f65aa6ecec04..c5d4aeb68404 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -389,7 +389,7 @@ static int raid0_set_limits(struct mddev *mddev)
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * mddev->raid_disks;
 	mddev_stack_rdev_limits(mddev, &lim);
-	return queue_limits_set(mddev->queue, &lim);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
 static int raid0_run(struct mddev *mddev)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index c34968378377..be8ac24f50b6 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3201,7 +3201,7 @@ static int raid1_set_limits(struct mddev *mddev)
 	blk_set_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	mddev_stack_rdev_limits(mddev, &lim);
-	return queue_limits_set(mddev->queue, &lim);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
 static void raid1_free(struct mddev *mddev, void *priv);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index e96fdf47319f..b0fd3005f5c1 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3986,7 +3986,7 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
 	mddev_stack_rdev_limits(mddev, &lim);
-	return queue_limits_set(mddev->queue, &lim);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
 static int raid10_run(struct mddev *mddev)
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index da4ba736c4f0..a70cbec12ed0 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -1393,7 +1393,8 @@ int ppl_init_log(struct r5conf *conf)
 		ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid));
 		ppl_conf->block_size = 512;
 	} else {
-		ppl_conf->block_size = queue_logical_block_size(mddev->queue);
+		ppl_conf->block_size =
+			queue_logical_block_size(mddev->gendisk->queue);
 	}
 
 	for (i = 0; i < ppl_conf->count; i++) {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 5012069782ba..f2e3c3e2d879 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4275,9 +4275,10 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 			}
 		}
 		if (rcw && !mddev_is_dm(conf->mddev))
-			blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
-					  (unsigned long long)sh->sector,
-					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
+			blk_add_trace_msg(conf->mddev->gendisk->queue,
+				"raid5 rcw %llu %d %d %d",
+				(unsigned long long)sh->sector, rcw, qread,
+				test_bit(STRIPE_DELAYED, &sh->state));
 	}
 
 	if (rcw > disks && rmw > disks &&
@@ -5686,7 +5687,7 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
 	release_inactive_stripe_list(conf, cb->temp_inactive_list,
 				     NR_STRIPE_HASH_LOCKS);
 	if (!mddev_is_dm(mddev))
-		trace_block_unplug(mddev->queue, cnt, !from_schedule);
+		trace_block_unplug(mddev->gendisk->queue, cnt, !from_schedule);
 	kfree(cb);
 }
 
@@ -7089,7 +7090,7 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 	if (!conf)
 		err = -ENODEV;
 	else if (new != conf->skip_copy) {
-		struct request_queue *q = mddev->queue;
+		struct request_queue *q = mddev->gendisk->queue;
 
 		conf->skip_copy = new;
 		if (new)
@@ -7749,7 +7750,7 @@ static int raid5_set_limits(struct mddev *mddev)
 	/* No restrictions on the number of segments in the request */
 	lim.max_segments = USHRT_MAX;
 
-	return queue_limits_set(mddev->queue, &lim);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
 static int raid5_run(struct mddev *mddev)
-- 
cgit