From 3d05f3aed5d721c2c77d20288c29ab26c6193ed5 Mon Sep 17 00:00:00 2001
From: Julia Cartwright <julia@ni.com>
Date: Fri, 28 Apr 2017 12:41:02 -0500
Subject: md/raid5: make use of spin_lock_irq over local_irq_disable +
 spin_lock

On mainline, there is no functional difference, just less code, and
symmetric lock/unlock paths.

On PREEMPT_RT builds, this fixes the following warning, seen by
Alexander GQ Gerasiov, due to the sleeping nature of spinlocks.

   BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:993
   in_atomic(): 0, irqs_disabled(): 1, pid: 58, name: kworker/u12:1
   CPU: 5 PID: 58 Comm: kworker/u12:1 Tainted: G        W       4.9.20-rt16-stand6-686 #1
   Hardware name: Supermicro SYS-5027R-WRF/X9SRW-F, BIOS 3.2a 10/28/2015
   Workqueue: writeback wb_workfn (flush-253:0)
   Call Trace:
    dump_stack+0x47/0x68
    ? migrate_enable+0x4a/0xf0
    ___might_sleep+0x101/0x180
    rt_spin_lock+0x17/0x40
    add_stripe_bio+0x4e3/0x6c0 [raid456]
    ? preempt_count_add+0x42/0xb0
    raid5_make_request+0x737/0xdd0 [raid456]

Reported-by: Alexander GQ Gerasiov <gq@redlab-i.ru>
Tested-by: Alexander GQ Gerasiov <gq@redlab-i.ru>
Signed-off-by: Julia Cartwright <julia@ni.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid5.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2e38cfac5b1d..3809a2192132 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -103,8 +103,7 @@ static inline void unlock_device_hash_lock(struct r5conf *conf, int hash)
 static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
 {
 	int i;
-	local_irq_disable();
-	spin_lock(conf->hash_locks);
+	spin_lock_irq(conf->hash_locks);
 	for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++)
 		spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks);
 	spin_lock(&conf->device_lock);
@@ -114,9 +113,9 @@ static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
 {
 	int i;
 	spin_unlock(&conf->device_lock);
-	for (i = NR_STRIPE_HASH_LOCKS; i; i--)
-		spin_unlock(conf->hash_locks + i - 1);
-	local_irq_enable();
+	for (i = NR_STRIPE_HASH_LOCKS - 1; i; i--)
+		spin_unlock(conf->hash_locks + i);
+	spin_unlock_irq(conf->hash_locks);
 }
 
 /* Find first data disk in a raid6 stripe */
@@ -714,12 +713,11 @@ static bool is_full_stripe_write(struct stripe_head *sh)
 
 static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 {
-	local_irq_disable();
 	if (sh1 > sh2) {
-		spin_lock(&sh2->stripe_lock);
+		spin_lock_irq(&sh2->stripe_lock);
 		spin_lock_nested(&sh1->stripe_lock, 1);
 	} else {
-		spin_lock(&sh1->stripe_lock);
+		spin_lock_irq(&sh1->stripe_lock);
 		spin_lock_nested(&sh2->stripe_lock, 1);
 	}
 }
@@ -727,8 +725,7 @@ static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 {
 	spin_unlock(&sh1->stripe_lock);
-	spin_unlock(&sh2->stripe_lock);
-	local_irq_enable();
+	spin_unlock_irq(&sh2->stripe_lock);
 }
 
 /* Only freshly new full stripe normal write stripe can be added to a batch list */
-- 
cgit v1.2.3


From 2214c260c72b0bd94e6c1c19bf451686212025d3 Mon Sep 17 00:00:00 2001
From: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Date: Mon, 8 May 2017 11:56:55 +0200
Subject: md: don't return -EAGAIN in md_allow_write for external metadata
 arrays

This essentially reverts commit b5470dc5fc18 ("md: resolve external
metadata handling deadlock in md_allow_write") with some adjustments.

Since commit 6791875e2e53 ("md: make reconfig_mutex optional for writes
to md sysfs files.") changing array_state to 'active' does not use
mddev_lock() and will not cause a deadlock with md_allow_write(). This
revert simplifies userspace tools that write to sysfs attributes like
"stripe_cache_size" or "consistency_policy" because it removes the need
for special handling for external metadata arrays, checking for EAGAIN
and retrying the write.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/md.c    | 20 ++++++++------------
 drivers/md/md.h    |  2 +-
 drivers/md/raid1.c |  9 +++------
 drivers/md/raid5.c | 12 +++---------
 4 files changed, 15 insertions(+), 28 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 82f798be964f..10367ffe92e3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8022,18 +8022,15 @@ EXPORT_SYMBOL(md_write_end);
  * may proceed without blocking.  It is important to call this before
  * attempting a GFP_KERNEL allocation while holding the mddev lock.
  * Must be called with mddev_lock held.
- *
- * In the ->external case MD_SB_CHANGE_PENDING can not be cleared until mddev->lock
- * is dropped, so return -EAGAIN after notifying userspace.
  */
-int md_allow_write(struct mddev *mddev)
+void md_allow_write(struct mddev *mddev)
 {
 	if (!mddev->pers)
-		return 0;
+		return;
 	if (mddev->ro)
-		return 0;
+		return;
 	if (!mddev->pers->sync_request)
-		return 0;
+		return;
 
 	spin_lock(&mddev->lock);
 	if (mddev->in_sync) {
@@ -8046,13 +8043,12 @@ int md_allow_write(struct mddev *mddev)
 		spin_unlock(&mddev->lock);
 		md_update_sb(mddev, 0);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
+		/* wait for the dirty state to be recorded in the metadata */
+		wait_event(mddev->sb_wait,
+			   !test_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags) &&
+			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	} else
 		spin_unlock(&mddev->lock);
-
-	if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
-		return -EAGAIN;
-	else
-		return 0;
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 4e75d121bfcc..11f15146ce51 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -665,7 +665,7 @@ extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
 			bool metadata_op);
 extern void md_do_sync(struct md_thread *thread);
 extern void md_new_event(struct mddev *mddev);
-extern int md_allow_write(struct mddev *mddev);
+extern void md_allow_write(struct mddev *mddev);
 extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
 extern int md_check_no_bitmap(struct mddev *mddev);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 7ed59351fe97..7c1f73398800 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3197,7 +3197,7 @@ static int raid1_reshape(struct mddev *mddev)
 	struct r1conf *conf = mddev->private;
 	int cnt, raid_disks;
 	unsigned long flags;
-	int d, d2, err;
+	int d, d2;
 
 	/* Cannot change chunk_size, layout, or level */
 	if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
@@ -3209,11 +3209,8 @@ static int raid1_reshape(struct mddev *mddev)
 		return -EINVAL;
 	}
 
-	if (!mddev_is_clustered(mddev)) {
-		err = md_allow_write(mddev);
-		if (err)
-			return err;
-	}
+	if (!mddev_is_clustered(mddev))
+		md_allow_write(mddev);
 
 	raid_disks = mddev->raid_disks + mddev->delta_disks;
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 3809a2192132..f8055a7abb4b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2309,14 +2309,12 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	struct stripe_head *osh, *nsh;
 	LIST_HEAD(newstripes);
 	struct disk_info *ndisks;
-	int err;
+	int err = 0;
 	struct kmem_cache *sc;
 	int i;
 	int hash, cnt;
 
-	err = md_allow_write(conf->mddev);
-	if (err)
-		return err;
+	md_allow_write(conf->mddev);
 
 	/* Step 1 */
 	sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
@@ -6310,7 +6308,6 @@ int
 raid5_set_cache_size(struct mddev *mddev, int size)
 {
 	struct r5conf *conf = mddev->private;
-	int err;
 
 	if (size <= 16 || size > 32768)
 		return -EINVAL;
@@ -6322,10 +6319,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 		;
 	mutex_unlock(&conf->cache_size_mutex);
 
-
-	err = md_allow_write(mddev);
-	if (err)
-		return err;
+	md_allow_write(mddev);
 
 	mutex_lock(&conf->cache_size_mutex);
 	while (size > conf->max_nr_stripes)
-- 
cgit v1.2.3


From 29efc390b9462582ae95eb9a0b8cd17ab956afc0 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Sun, 7 May 2017 17:36:24 -0700
Subject: md/md0: optimize raid0 discard handling

There are complaints that raid0 discard handling is slow. Currently we
divide discard request into chunks and dispatch to underlayer disks. The
block layer will do merge to form big requests. This causes a lot of
request split/merge and uses significant CPU time.

A simple idea is to calculate the range for each raid disk for an IO
request and send a discard request to raid disks, which will avoid the
split/merge completely. Previously Coly tried the approach, but the
implementation was too complex because of raid0 zones. This patch always
split bio in zone boundary and handle bio within one zone. It simplifies
the implementation a lot.

Reviewed-by: NeilBrown <neilb@suse.com>
Acked-by: Coly Li <colyli@suse.de>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid0.c | 116 ++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 102 insertions(+), 14 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 84e58596594d..d6c0bc76e837 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -385,7 +385,7 @@ static int raid0_run(struct mddev *mddev)
 		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
+		blk_queue_max_discard_sectors(mddev->queue, UINT_MAX);
 
 		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
 		blk_queue_io_opt(mddev->queue,
@@ -459,6 +459,95 @@ static inline int is_io_in_chunk_boundary(struct mddev *mddev,
 	}
 }
 
+static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
+{
+	struct r0conf *conf = mddev->private;
+	struct strip_zone *zone;
+	sector_t start = bio->bi_iter.bi_sector;
+	sector_t end;
+	unsigned int stripe_size;
+	sector_t first_stripe_index, last_stripe_index;
+	sector_t start_disk_offset;
+	unsigned int start_disk_index;
+	sector_t end_disk_offset;
+	unsigned int end_disk_index;
+	unsigned int disk;
+
+	zone = find_zone(conf, &start);
+
+	if (bio_end_sector(bio) > zone->zone_end) {
+		struct bio *split = bio_split(bio,
+			zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO,
+			mddev->bio_set);
+		bio_chain(split, bio);
+		generic_make_request(bio);
+		bio = split;
+		end = zone->zone_end;
+	} else
+		end = bio_end_sector(bio);
+
+	if (zone != conf->strip_zone)
+		end = end - zone[-1].zone_end;
+
+	/* Now start and end is the offset in zone */
+	stripe_size = zone->nb_dev * mddev->chunk_sectors;
+
+	first_stripe_index = start;
+	sector_div(first_stripe_index, stripe_size);
+	last_stripe_index = end;
+	sector_div(last_stripe_index, stripe_size);
+
+	start_disk_index = (int)(start - first_stripe_index * stripe_size) /
+		mddev->chunk_sectors;
+	start_disk_offset = ((int)(start - first_stripe_index * stripe_size) %
+		mddev->chunk_sectors) +
+		first_stripe_index * mddev->chunk_sectors;
+	end_disk_index = (int)(end - last_stripe_index * stripe_size) /
+		mddev->chunk_sectors;
+	end_disk_offset = ((int)(end - last_stripe_index * stripe_size) %
+		mddev->chunk_sectors) +
+		last_stripe_index * mddev->chunk_sectors;
+
+	for (disk = 0; disk < zone->nb_dev; disk++) {
+		sector_t dev_start, dev_end;
+		struct bio *discard_bio = NULL;
+		struct md_rdev *rdev;
+
+		if (disk < start_disk_index)
+			dev_start = (first_stripe_index + 1) *
+				mddev->chunk_sectors;
+		else if (disk > start_disk_index)
+			dev_start = first_stripe_index * mddev->chunk_sectors;
+		else
+			dev_start = start_disk_offset;
+
+		if (disk < end_disk_index)
+			dev_end = (last_stripe_index + 1) * mddev->chunk_sectors;
+		else if (disk > end_disk_index)
+			dev_end = last_stripe_index * mddev->chunk_sectors;
+		else
+			dev_end = end_disk_offset;
+
+		if (dev_end <= dev_start)
+			continue;
+
+		rdev = conf->devlist[(zone - conf->strip_zone) *
+			conf->strip_zone[0].nb_dev + disk];
+		if (__blkdev_issue_discard(rdev->bdev,
+			dev_start + zone->dev_start + rdev->data_offset,
+			dev_end - dev_start, GFP_NOIO, 0, &discard_bio) ||
+		    !discard_bio)
+			continue;
+		bio_chain(discard_bio, bio);
+		if (mddev->gendisk)
+			trace_block_bio_remap(bdev_get_queue(rdev->bdev),
+				discard_bio, disk_devt(mddev->gendisk),
+				bio->bi_iter.bi_sector);
+		generic_make_request(discard_bio);
+	}
+	bio_endio(bio);
+}
+
 static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 {
 	struct strip_zone *zone;
@@ -473,6 +562,11 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 		return;
 	}
 
+	if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) {
+		raid0_handle_discard(mddev, bio);
+		return;
+	}
+
 	bio_sector = bio->bi_iter.bi_sector;
 	sector = bio_sector;
 	chunk_sects = mddev->chunk_sectors;
@@ -498,19 +592,13 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 	bio->bi_iter.bi_sector = sector + zone->dev_start +
 		tmp_dev->data_offset;
 
-	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-		     !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) {
-		/* Just ignore it */
-		bio_endio(bio);
-	} else {
-		if (mddev->gendisk)
-			trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
-					      bio, disk_devt(mddev->gendisk),
-					      bio_sector);
-		mddev_check_writesame(mddev, bio);
-		mddev_check_write_zeroes(mddev, bio);
-		generic_make_request(bio);
-	}
+	if (mddev->gendisk)
+		trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
+				      bio, disk_devt(mddev->gendisk),
+				      bio_sector);
+	mddev_check_writesame(mddev, bio);
+	mddev_check_write_zeroes(mddev, bio);
+	generic_make_request(bio);
 }
 
 static void raid0_status(struct seq_file *seq, struct mddev *mddev)
-- 
cgit v1.2.3


From bb3338d3474e0329918fda9dae2c52751731eb58 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Mon, 8 May 2017 17:39:24 -0700
Subject: md/raid5-cache: in r5l_do_submit_io(), submit io->split_bio first

In r5l_do_submit_io(), it is necessary to check io->split_bio before
submit io->current_bio. This is because, endio of current_bio may
free the whole IO unit, and thus change io->split_bio.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid5-cache.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 26ba09282e7c..a6a62e212cd3 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -622,20 +622,30 @@ static void r5l_do_submit_io(struct r5l_log *log, struct r5l_io_unit *io)
 	__r5l_set_io_unit_state(io, IO_UNIT_IO_START);
 	spin_unlock_irqrestore(&log->io_list_lock, flags);
 
+	/*
+	 * In case of journal device failures, submit_bio will get error
+	 * and calls endio, then active stripes will continue write
+	 * process. Therefore, it is not necessary to check Faulty bit
+	 * of journal device here.
+	 *
+	 * We can't check split_bio after current_bio is submitted. If
+	 * io->split_bio is null, after current_bio is submitted, current_bio
+	 * might already be completed and the io_unit is freed. We submit
+	 * split_bio first to avoid the issue.
+	 */
+	if (io->split_bio) {
+		if (io->has_flush)
+			io->split_bio->bi_opf |= REQ_PREFLUSH;
+		if (io->has_fua)
+			io->split_bio->bi_opf |= REQ_FUA;
+		submit_bio(io->split_bio);
+	}
+
 	if (io->has_flush)
 		io->current_bio->bi_opf |= REQ_PREFLUSH;
 	if (io->has_fua)
 		io->current_bio->bi_opf |= REQ_FUA;
 	submit_bio(io->current_bio);
-
-	if (!io->split_bio)
-		return;
-
-	if (io->has_flush)
-		io->split_bio->bi_opf |= REQ_PREFLUSH;
-	if (io->has_fua)
-		io->split_bio->bi_opf |= REQ_FUA;
-	submit_bio(io->split_bio);
 }
 
 /* deferred io_unit will be dispatched here */
-- 
cgit v1.2.3


From 23b245c04d0ef408087430dd4d1b214a5da1eb78 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Wed, 10 May 2017 08:47:11 -0700
Subject: md/raid1/10: avoid unnecessary locking

If we add bios to block plugging list, locking is unnecessry, since the block
unplug is guaranteed not to run at that time.

Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid1.c  | 7 +++----
 drivers/md/raid10.c | 7 +++----
 2 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 7c1f73398800..a17ed6218d51 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1529,17 +1529,16 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			plug = container_of(cb, struct raid1_plug_cb, cb);
 		else
 			plug = NULL;
-		spin_lock_irqsave(&conf->device_lock, flags);
 		if (plug) {
 			bio_list_add(&plug->pending, mbio);
 			plug->pending_cnt++;
 		} else {
+			spin_lock_irqsave(&conf->device_lock, flags);
 			bio_list_add(&conf->pending_bio_list, mbio);
 			conf->pending_count++;
-		}
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		if (!plug)
+			spin_unlock_irqrestore(&conf->device_lock, flags);
 			md_wakeup_thread(mddev->thread);
+		}
 	}
 
 	r1_bio_write_done(r1_bio);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 6b86a0032cf8..4343d7ff9916 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1282,17 +1282,16 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 		plug = container_of(cb, struct raid10_plug_cb, cb);
 	else
 		plug = NULL;
-	spin_lock_irqsave(&conf->device_lock, flags);
 	if (plug) {
 		bio_list_add(&plug->pending, mbio);
 		plug->pending_cnt++;
 	} else {
+		spin_lock_irqsave(&conf->device_lock, flags);
 		bio_list_add(&conf->pending_bio_list, mbio);
 		conf->pending_count++;
-	}
-	spin_unlock_irqrestore(&conf->device_lock, flags);
-	if (!plug)
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 		md_wakeup_thread(mddev->thread);
+	}
 }
 
 static void raid10_write_request(struct mddev *mddev, struct bio *bio,
-- 
cgit v1.2.3


From 70d466f760b351fe30b5f8c956354ddf29aa676b Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Thu, 11 May 2017 15:28:28 -0700
Subject: md/r5cache: gracefully handle journal device errors for writeback
 mode

For the raid456 with writeback cache, when journal device failed during
normal operation, it is still possible to persist all data, as all
pending data is still in stripe cache. However, it is necessary to handle
journal failure gracefully.

During journal failures, the following logic handles the graceful shutdown
of journal:
1. raid5_error() marks the device as Faulty and schedules async work
   log->disable_writeback_work;
2. In disable_writeback_work (r5c_disable_writeback_async), the mddev is
   suspended, set to write through, and then resumed. mddev_suspend()
   flushes all cached stripes;
3. All cached stripes need to be flushed carefully to the RAID array.

This patch fixes issues within the process above:
1. In r5c_update_on_rdev_error() schedule disable_writeback_work for
   journal failures;
2. In r5c_disable_writeback_async(), wait for MD_SB_CHANGE_PENDING,
   since raid5_error() updates superblock.
3. In handle_stripe(), allow stripes with data in journal (s.injournal > 0)
   to make progress during log_failed;
4. In delay_towrite(), if log failed only process data in the cache (skip
   new writes in dev->towrite);
5. In __get_priority_stripe(), process loprio_list during journal device
   failures.
6. In raid5_remove_disk(), wait for all cached stripes are flushed before
   calling log_exit().

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid5-cache.c | 11 +++++++++--
 drivers/md/raid5-log.h   |  3 ++-
 drivers/md/raid5.c       | 29 +++++++++++++++++++++++------
 3 files changed, 34 insertions(+), 9 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index a6a62e212cd3..cc3f8442f11f 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -24,6 +24,7 @@
 #include "md.h"
 #include "raid5.h"
 #include "bitmap.h"
+#include "raid5-log.h"
 
 /*
  * metadata/data stored in disk with 4k size unit (a block) regardless
@@ -680,6 +681,11 @@ static void r5c_disable_writeback_async(struct work_struct *work)
 		return;
 	pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n",
 		mdname(mddev));
+
+	/* wait superblock change before suspend */
+	wait_event(mddev->sb_wait,
+		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
+
 	mddev_suspend(mddev);
 	log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
 	mddev_resume(mddev);
@@ -2983,7 +2989,7 @@ ioerr:
 	return ret;
 }
 
-void r5c_update_on_rdev_error(struct mddev *mddev)
+void r5c_update_on_rdev_error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r5conf *conf = mddev->private;
 	struct r5l_log *log = conf->log;
@@ -2991,7 +2997,8 @@ void r5c_update_on_rdev_error(struct mddev *mddev)
 	if (!log)
 		return;
 
-	if (raid5_calc_degraded(conf) > 0 &&
+	if ((raid5_calc_degraded(conf) > 0 ||
+	     test_bit(Journal, &rdev->flags)) &&
 	    conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK)
 		schedule_work(&log->disable_writeback_work);
 }
diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h
index 27097101ccca..328d67aedda4 100644
--- a/drivers/md/raid5-log.h
+++ b/drivers/md/raid5-log.h
@@ -28,7 +28,8 @@ extern void r5c_flush_cache(struct r5conf *conf, int num);
 extern void r5c_check_stripe_cache_usage(struct r5conf *conf);
 extern void r5c_check_cached_full_stripe(struct r5conf *conf);
 extern struct md_sysfs_entry r5c_journal_mode;
-extern void r5c_update_on_rdev_error(struct mddev *mddev);
+extern void r5c_update_on_rdev_error(struct mddev *mddev,
+				     struct md_rdev *rdev);
 extern bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect);
 
 extern struct dma_async_tx_descriptor *
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f8055a7abb4b..0ac57a925606 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2689,7 +2689,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
 		bdevname(rdev->bdev, b),
 		mdname(mddev),
 		conf->raid_disks - mddev->degraded);
-	r5c_update_on_rdev_error(mddev);
+	r5c_update_on_rdev_error(mddev, rdev);
 }
 
 /*
@@ -3050,6 +3050,11 @@ sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous)
  *      When LOG_CRITICAL, stripes with injournal == 0 will be sent to
  *      no_space_stripes list.
  *
+ *   3. during journal failure
+ *      In journal failure, we try to flush all cached data to raid disks
+ *      based on data in stripe cache. The array is read-only to upper
+ *      layers, so we would skip all pending writes.
+ *
  */
 static inline bool delay_towrite(struct r5conf *conf,
 				 struct r5dev *dev,
@@ -3063,6 +3068,9 @@ static inline bool delay_towrite(struct r5conf *conf,
 	if (test_bit(R5C_LOG_CRITICAL, &conf->cache_state) &&
 	    s->injournal > 0)
 		return true;
+	/* case 3 above */
+	if (s->log_failed && s->injournal)
+		return true;
 	return false;
 }
 
@@ -4696,10 +4704,15 @@ static void handle_stripe(struct stripe_head *sh)
 	       " to_write=%d failed=%d failed_num=%d,%d\n",
 	       s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
 	       s.failed_num[0], s.failed_num[1]);
-	/* check if the array has lost more than max_degraded devices and,
+	/*
+	 * check if the array has lost more than max_degraded devices and,
 	 * if so, some requests might need to be failed.
+	 *
+	 * When journal device failed (log_failed), we will only process
+	 * the stripe if there is data need write to raid disks
 	 */
-	if (s.failed > conf->max_degraded || s.log_failed) {
+	if (s.failed > conf->max_degraded ||
+	    (s.log_failed && s.injournal == 0)) {
 		sh->check_state = 0;
 		sh->reconstruct_state = 0;
 		break_stripe_batch_list(sh, 0);
@@ -5272,8 +5285,10 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
 	struct stripe_head *sh, *tmp;
 	struct list_head *handle_list = NULL;
 	struct r5worker_group *wg;
-	bool second_try = !r5c_is_writeback(conf->log);
-	bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state);
+	bool second_try = !r5c_is_writeback(conf->log) &&
+		!r5l_log_disk_error(conf);
+	bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state) ||
+		r5l_log_disk_error(conf);
 
 again:
 	wg = NULL;
@@ -7521,7 +7536,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 		 * neilb: there is no locking about new writes here,
 		 * so this cannot be safe.
 		 */
-		if (atomic_read(&conf->active_stripes)) {
+		if (atomic_read(&conf->active_stripes) ||
+		    atomic_read(&conf->r5c_cached_full_stripes) ||
+		    atomic_read(&conf->r5c_cached_partial_stripes)) {
 			return -EBUSY;
 		}
 		log_exit(conf);
-- 
cgit v1.2.3


From 5ddf0440a1a28f00f69ed2e093476bab3b60c2c3 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Thu, 11 May 2017 17:03:44 -0700
Subject: md/r5cache: handle sync with data in write back cache

Currently, sync of raid456 array cannot make progress when hitting
data in writeback r5cache.

This patch fixes this issue by flushing cached data of the stripe
before processing the sync request. This is achived by:

1. In handle_stripe(), do not set STRIPE_SYNCING if the stripe is
   in write back cache;
2. In r5c_try_caching_write(), handle the stripe in sync with write
   through;
3. In do_release_stripe(), make stripe in sync write out and send
   it to the state machine.

Shaohua: explictly set STRIPE_HANDLE after write out completed

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid5-cache.c |  8 +++++++-
 drivers/md/raid5.c       | 21 +++++++++++++++------
 2 files changed, 22 insertions(+), 7 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index cc3f8442f11f..4c00bc248287 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -2637,8 +2637,11 @@ int r5c_try_caching_write(struct r5conf *conf,
 	 * When run in degraded mode, array is set to write-through mode.
 	 * This check helps drain pending write safely in the transition to
 	 * write-through mode.
+	 *
+	 * When a stripe is syncing, the write is also handled in write
+	 * through mode.
 	 */
-	if (s->failed) {
+	if (s->failed || test_bit(STRIPE_SYNCING, &sh->state)) {
 		r5c_make_stripe_write_out(sh);
 		return -EAGAIN;
 	}
@@ -2841,6 +2844,9 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,
 	}
 
 	r5l_append_flush_payload(log, sh->sector);
+	/* stripe is flused to raid disks, we can do resync now */
+	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
+		set_bit(STRIPE_HANDLE, &sh->state);
 }
 
 int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 0ac57a925606..9c4f7659f8b1 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -233,11 +233,15 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
 			if (test_bit(R5_InJournal, &sh->dev[i].flags))
 				injournal++;
 	/*
-	 * When quiesce in r5c write back, set STRIPE_HANDLE for stripes with
-	 * data in journal, so they are not released to cached lists
+	 * In the following cases, the stripe cannot be released to cached
+	 * lists. Therefore, we make the stripe write out and set
+	 * STRIPE_HANDLE:
+	 *   1. when quiesce in r5c write back;
+	 *   2. when resync is requested fot the stripe.
 	 */
-	if (conf->quiesce && r5c_is_writeback(conf->log) &&
-	    !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0) {
+	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) ||
+	    (conf->quiesce && r5c_is_writeback(conf->log) &&
+	     !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0)) {
 		if (test_bit(STRIPE_R5C_CACHING, &sh->state))
 			r5c_make_stripe_write_out(sh);
 		set_bit(STRIPE_HANDLE, &sh->state);
@@ -4656,8 +4660,13 @@ static void handle_stripe(struct stripe_head *sh)
 
 	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
 		spin_lock(&sh->stripe_lock);
-		/* Cannot process 'sync' concurrently with 'discard' */
-		if (!test_bit(STRIPE_DISCARD, &sh->state) &&
+		/*
+		 * Cannot process 'sync' concurrently with 'discard'.
+		 * Flush data in r5cache before 'sync'.
+		 */
+		if (!test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state) &&
+		    !test_bit(STRIPE_R5C_FULL_STRIPE, &sh->state) &&
+		    !test_bit(STRIPE_DISCARD, &sh->state) &&
 		    test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
 			set_bit(STRIPE_SYNCING, &sh->state);
 			clear_bit(STRIPE_INSYNC, &sh->state);
-- 
cgit v1.2.3


From d82dd0e34d0347be201fd274dc84cd645dccc064 Mon Sep 17 00:00:00 2001
From: Tomasz Majchrzak <tomasz.majchrzak@intel.com>
Date: Fri, 12 May 2017 14:26:10 +0200
Subject: raid1: prefer disk without bad blocks

If an array consists of two drives and the first drive has the bad
block, the read request to the region overlapping the bad block chooses
the same disk (with bad block) as device to read from over and over and
the request gets stuck. If the first disk only partially overlaps with
bad block, it becomes a candidate ("best disk") for shorter range of
sectors. The second disk is capable of reading the entire requested
range and it is updated accordingly, however it is not recorded as a
best device for the request. In the end the request is sent to the first
disk to read entire range of sectors. It fails and is re-tried in a
moment but with the same outcome.

Actually it is quite likely scenario but it had little exposure in my
test until commit 715d40b93b10 ("md/raid1: add failfast handling for
reads.") removed preference for idle disk. Such scenario had been
passing as second disk was always chosen when idle.

Reset a candidate ("best disk") to read from if disk can read entire
range. Do it only if other disk has already been chosen as a candidate
for a smaller range. The head position / disk type logic will select
the best disk to read from - it is fine as disk with bad block won't be
considered for it.

Signed-off-by: Tomasz Majchrzak <tomasz.majchrzak@intel.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid1.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/md')

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index a17ed6218d51..af5056d56878 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -666,8 +666,11 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 					break;
 			}
 			continue;
-		} else
+		} else {
+			if ((sectors > best_good_sectors) && (best_disk >= 0))
+				best_disk = -1;
 			best_good_sectors = sectors;
+		}
 
 		if (best_disk >= 0)
 			/* At least two disks to choose from so failfast is OK */
-- 
cgit v1.2.3


From 072792dcdfc8d5f91a26050e5665285f50afebf5 Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt@redhat.com>
Date: Thu, 11 May 2017 06:14:16 -0400
Subject: dm cache: fix incorrect 'idle_time' reset in IO tracker

Some bios have no payload (eg, a FLUSH), don't reset the idle_time when
these come in.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-cache-target.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 1db375f50a13..0760ba409c21 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -94,6 +94,9 @@ static void iot_io_begin(struct io_tracker *iot, sector_t len)
 
 static void __iot_io_end(struct io_tracker *iot, sector_t len)
 {
+	if (!len)
+		return;
+
 	iot->in_flight -= len;
 	if (!iot->in_flight)
 		iot->idle_time = jiffies;
-- 
cgit v1.2.3


From a8cd1eba6135e086109e2b94bf96deb17456ede8 Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt@redhat.com>
Date: Thu, 11 May 2017 05:07:34 -0400
Subject: dm cache policy smq: only demote entries in bottom half of the clean
 multiqueue

Heavy IO load may mean there are very few clean blocks in the cache, and
we risk demoting entries that get hit a lot.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-cache-policy-smq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index 72479bd61e11..a177559f2049 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1190,7 +1190,7 @@ static void queue_demotion(struct smq_policy *mq)
 	if (unlikely(WARN_ON_ONCE(!mq->migrations_allowed)))
 		return;
 
-	e = q_peek(&mq->clean, mq->clean.nr_levels, true);
+	e = q_peek(&mq->clean, mq->clean.nr_levels / 2, true);
 	if (!e) {
 		if (!clean_target_met(mq, false))
 			queue_writeback(mq);
-- 
cgit v1.2.3


From 78c45607b909fb384c47c134d89b39285a6a8b45 Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt@redhat.com>
Date: Thu, 11 May 2017 05:09:38 -0400
Subject: dm cache policy smq: be more aggressive about triggering a writeback

If there are no clean entries to demote we really want to writeback
immediately.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-cache-policy-smq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index a177559f2049..5aa8f43856c5 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1192,7 +1192,7 @@ static void queue_demotion(struct smq_policy *mq)
 
 	e = q_peek(&mq->clean, mq->clean.nr_levels / 2, true);
 	if (!e) {
-		if (!clean_target_met(mq, false))
+		if (!clean_target_met(mq, true))
 			queue_writeback(mq);
 		return;
 	}
-- 
cgit v1.2.3


From 4d44ec5ab751be63c5d348f13294304d87baa8c3 Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt@redhat.com>
Date: Thu, 11 May 2017 05:11:06 -0400
Subject: dm cache policy smq: put newly promoted entries at the top of the
 multiqueue

This stops entries bouncing in and out of the cache quickly.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-cache-policy-smq.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index 5aa8f43856c5..54421a846a0c 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1452,6 +1452,7 @@ static void __complete_background_work(struct smq_policy *mq,
 		clear_pending(mq, e);
 		if (success) {
 			e->oblock = work->oblock;
+			e->level = NR_CACHE_LEVELS - 1;
 			push(mq, e);
 			// h, q, a
 		} else {
-- 
cgit v1.2.3


From 6cf4cc8f8b3b7bc9e3c04a7eab44b985d50029fc Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt@redhat.com>
Date: Thu, 11 May 2017 07:48:18 -0400
Subject: dm cache policy smq: stop preemptively demoting blocks

It causes a lot of churn if the working set's size is close to the fast
device's size.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-cache-policy-smq.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index 54421a846a0c..758480a1893d 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1134,13 +1134,10 @@ static bool clean_target_met(struct smq_policy *mq, bool idle)
 		percent_to_target(mq, CLEAN_TARGET);
 }
 
-static bool free_target_met(struct smq_policy *mq, bool idle)
+static bool free_target_met(struct smq_policy *mq)
 {
 	unsigned nr_free;
 
-	if (!idle)
-		return true;
-
 	nr_free = from_cblock(mq->cache_size) - mq->cache_alloc.nr_allocated;
 	return (nr_free + btracker_nr_demotions_queued(mq->bg_work)) >=
 		percent_to_target(mq, FREE_TARGET);
@@ -1220,7 +1217,7 @@ static void queue_promotion(struct smq_policy *mq, dm_oblock_t oblock,
 		 * We always claim to be 'idle' to ensure some demotions happen
 		 * with continuous loads.
 		 */
-		if (!free_target_met(mq, true))
+		if (!free_target_met(mq))
 			queue_demotion(mq);
 		return;
 	}
@@ -1421,14 +1418,10 @@ static int smq_get_background_work(struct dm_cache_policy *p, bool idle,
 	spin_lock_irqsave(&mq->lock, flags);
 	r = btracker_issue(mq->bg_work, result);
 	if (r == -ENODATA) {
-		/* find some writeback work to do */
-		if (mq->migrations_allowed && !free_target_met(mq, idle))
-			queue_demotion(mq);
-
-		else if (!clean_target_met(mq, idle))
+		if (!clean_target_met(mq, idle)) {
 			queue_writeback(mq);
-
-		r = btracker_issue(mq->bg_work, result);
+			r = btracker_issue(mq->bg_work, result);
+		}
 	}
 	spin_unlock_irqrestore(&mq->lock, flags);
 
-- 
cgit v1.2.3


From 701e03e4e180f0cd97d4139a32e2b2d879d12da2 Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt@redhat.com>
Date: Thu, 11 May 2017 08:22:31 -0400
Subject: dm cache: track all IO to the cache rather than just the origin
 device's IO

IO tracking used to throttle writebacks when the origin device is busy.

Even if all the IO is going to the fast device, writebacks can
significantly degrade performance.  So track all IO to gauge whether the
cache is busy or not.

Otherwise, synthetic IO tests (e.g. fio) that might send all IO to the
fast device wouldn't cause writebacks to get throttled.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-cache-target.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 0760ba409c21..232078e48167 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -477,7 +477,7 @@ struct cache {
 	spinlock_t invalidation_lock;
 	struct list_head invalidation_requests;
 
-	struct io_tracker origin_tracker;
+	struct io_tracker tracker;
 
 	struct work_struct commit_ws;
 	struct batcher committer;
@@ -904,8 +904,7 @@ static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio)
 
 static bool accountable_bio(struct cache *cache, struct bio *bio)
 {
-	return ((bio->bi_bdev == cache->origin_dev->bdev) &&
-		bio_op(bio) != REQ_OP_DISCARD);
+	return bio_op(bio) != REQ_OP_DISCARD;
 }
 
 static void accounted_begin(struct cache *cache, struct bio *bio)
@@ -915,7 +914,7 @@ static void accounted_begin(struct cache *cache, struct bio *bio)
 
 	if (accountable_bio(cache, bio)) {
 		pb->len = bio_sectors(bio);
-		iot_io_begin(&cache->origin_tracker, pb->len);
+		iot_io_begin(&cache->tracker, pb->len);
 	}
 }
 
@@ -924,7 +923,7 @@ static void accounted_complete(struct cache *cache, struct bio *bio)
 	size_t pb_data_size = get_per_bio_data_size(cache);
 	struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);
 
-	iot_io_end(&cache->origin_tracker, pb->len);
+	iot_io_end(&cache->tracker, pb->len);
 }
 
 static void accounted_request(struct cache *cache, struct bio *bio)
@@ -1725,7 +1724,7 @@ enum busy {
 
 static enum busy spare_migration_bandwidth(struct cache *cache)
 {
-	bool idle = iot_idle_for(&cache->origin_tracker, HZ);
+	bool idle = iot_idle_for(&cache->tracker, HZ);
 	sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) *
 		cache->sectors_per_block;
 
@@ -2720,7 +2719,7 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 
 	batcher_init(&cache->committer, commit_op, cache,
 		     issue_op, cache, cache->wq);
-	iot_init(&cache->origin_tracker);
+	iot_init(&cache->tracker);
 
 	init_rwsem(&cache->background_work_lock);
 	prevent_background_work(cache);
@@ -2944,7 +2943,7 @@ static void cache_postsuspend(struct dm_target *ti)
 
 	cancel_delayed_work(&cache->waker);
 	flush_workqueue(cache->wq);
-	WARN_ON(cache->origin_tracker.in_flight);
+	WARN_ON(cache->tracker.in_flight);
 
 	/*
 	 * If it's a flush suspend there won't be any deferred bios, so this
-- 
cgit v1.2.3


From 49b7f768900f4084a65c3689d955b2fceac39e53 Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt@redhat.com>
Date: Thu, 11 May 2017 09:07:16 -0400
Subject: dm cache: simplify the IDLE vs BUSY state calculation

Drop the MODERATE state since it wasn't buying us much.

Also, in check_migrations(), prepare for the next commit ("dm cache
policy smq: don't do any writebacks unless IDLE") by deferring to the
policy to make the final decision on whether writebacks can be
serviced.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-cache-target.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 232078e48167..d682a0511381 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -1718,7 +1718,6 @@ static int invalidate_start(struct cache *cache, dm_cblock_t cblock,
 
 enum busy {
 	IDLE,
-	MODERATE,
 	BUSY
 };
 
@@ -1728,10 +1727,10 @@ static enum busy spare_migration_bandwidth(struct cache *cache)
 	sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) *
 		cache->sectors_per_block;
 
-	if (current_volume <= cache->migration_threshold)
-		return idle ? IDLE : MODERATE;
+	if (idle && current_volume <= cache->migration_threshold)
+		return IDLE;
 	else
-		return idle ? MODERATE : BUSY;
+		return BUSY;
 }
 
 static void inc_hit_counter(struct cache *cache, struct bio *bio)
@@ -2047,8 +2046,6 @@ static void check_migrations(struct work_struct *ws)
 
 	for (;;) {
 		b = spare_migration_bandwidth(cache);
-		if (b == BUSY)
-			break;
 
 		r = policy_get_background_work(cache->policy, b == IDLE, &op);
 		if (r == -ENODATA)
-- 
cgit v1.2.3


From 2e63309507c818e8b631a03f02c363031c007fb7 Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt@redhat.com>
Date: Thu, 11 May 2017 09:09:04 -0400
Subject: dm cache policy smq: don't do any writebacks unless IDLE

If there are no clean blocks to be demoted the writeback will be
triggered at that point.  Preemptively writing back can hurt high IO
load scenarios.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-cache-policy-smq.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index 758480a1893d..e5eb9c9b4bc8 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1120,8 +1120,6 @@ static bool clean_target_met(struct smq_policy *mq, bool idle)
 	 * Cache entries may not be populated.  So we cannot rely on the
 	 * size of the clean queue.
 	 */
-	unsigned nr_clean;
-
 	if (idle) {
 		/*
 		 * We'd like to clean everything.
@@ -1129,9 +1127,10 @@ static bool clean_target_met(struct smq_policy *mq, bool idle)
 		return q_size(&mq->dirty) == 0u;
 	}
 
-	nr_clean = from_cblock(mq->cache_size) - q_size(&mq->dirty);
-	return (nr_clean + btracker_nr_writebacks_queued(mq->bg_work)) >=
-		percent_to_target(mq, CLEAN_TARGET);
+	/*
+	 * If we're busy we don't worry about cleaning at all.
+	 */
+	return true;
 }
 
 static bool free_target_met(struct smq_policy *mq)
-- 
cgit v1.2.3


From 91bcdb92d39711d1adb40c26b653b7978d93eb98 Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt@redhat.com>
Date: Mon, 15 May 2017 09:43:05 -0400
Subject: dm thin metadata: call precommit before saving the roots

These calls were the wrong way round in __write_initial_superblock.

Cc: stable@vger.kernel.org
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-thin-metadata.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 0f0251d0d337..d31d18d9727c 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -484,11 +484,11 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 	if (r < 0)
 		return r;
 
-	r = save_sm_roots(pmd);
+	r = dm_tm_pre_commit(pmd->tm);
 	if (r < 0)
 		return r;
 
-	r = dm_tm_pre_commit(pmd->tm);
+	r = save_sm_roots(pmd);
 	if (r < 0)
 		return r;
 
-- 
cgit v1.2.3


From 0377a07c7a035e0d033cd8b29f0cb15244c0916a Mon Sep 17 00:00:00 2001
From: Joe Thornber <ejt@redhat.com>
Date: Mon, 15 May 2017 09:45:40 -0400
Subject: dm space map disk: fix some book keeping in the disk space map

When decrementing the reference count for a block, the free count wasn't
being updated if the reference count went to zero.

Cc: stable@vger.kernel.org
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/persistent-data/dm-space-map-disk.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

(limited to 'drivers/md')

diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c
index ebb280a14325..32adf6b4a9c7 100644
--- a/drivers/md/persistent-data/dm-space-map-disk.c
+++ b/drivers/md/persistent-data/dm-space-map-disk.c
@@ -142,10 +142,23 @@ static int sm_disk_inc_block(struct dm_space_map *sm, dm_block_t b)
 
 static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b)
 {
+	int r;
+	uint32_t old_count;
 	enum allocation_event ev;
 	struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
 
-	return sm_ll_dec(&smd->ll, b, &ev);
+	r = sm_ll_dec(&smd->ll, b, &ev);
+	if (!r && (ev == SM_FREE)) {
+		/*
+		 * It's only free if it's also free in the last
+		 * transaction.
+		 */
+		r = sm_ll_lookup(&smd->old_ll, b, &old_count);
+		if (!r && !old_count)
+			smd->nr_allocated_this_transaction--;
+	}
+
+	return r;
 }
 
 static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b)
-- 
cgit v1.2.3


From ece0728037b15f4d31198f12b359104bcb5db4c8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 15 May 2017 17:28:36 +0200
Subject: dm rq: add a missing break to map_request

We don't want to bug when receiving a DM_MAPIO_KILL value..

Fixes: 412445ac ("dm: introduce a new DM_MAPIO_KILL return value")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-rq.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 2af27026aa2e..b639fa7246ee 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -507,6 +507,7 @@ static int map_request(struct dm_rq_target_io *tio)
 	case DM_MAPIO_KILL:
 		/* The target wants to complete the I/O */
 		dm_kill_unmapped_request(rq, -EIO);
+		break;
 	default:
 		DMWARN("unimplemented target map return value: %d", r);
 		BUG();
-- 
cgit v1.2.3


From 18a482f5245cc875755090853e84283512b3e6bd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 15 May 2017 17:28:37 +0200
Subject: dm mpath: don't return -EIO from dm_report_EIO

Instead just turn the macro into a helper for the warning message.
This removes an unnecessary assignment and will allow the next commit to
fix a place where -EIO is the wrong return value.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-mpath.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 926a6bcb32c8..d55454f98b59 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -447,7 +447,7 @@ failed:
  * it has been invoked.
  */
 #define dm_report_EIO(m)						\
-({									\
+do {									\
 	struct mapped_device *md = dm_table_get_md((m)->ti->table);	\
 									\
 	pr_debug("%s: returning EIO; QIFNP = %d; SQIFNP = %d; DNFS = %d\n", \
@@ -455,8 +455,7 @@ failed:
 		 test_bit(MPATHF_QUEUE_IF_NO_PATH, &(m)->flags),	\
 		 test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &(m)->flags),	\
 		 dm_noflush_suspending((m)->ti));			\
-	-EIO;								\
-})
+} while (0)
 
 /*
  * Map cloned requests (request-based multipath)
@@ -481,7 +480,8 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 	if (!pgpath) {
 		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
 			return DM_MAPIO_DELAY_REQUEUE;
-		return dm_report_EIO(m);	/* Failed */
+		dm_report_EIO(m);	/* Failed */
+		return -EIO;
 	} else if (test_bit(MPATHF_QUEUE_IO, &m->flags) ||
 		   test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags)) {
 		if (pg_init_all_paths(m))
@@ -558,7 +558,8 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
 	if (!pgpath) {
 		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
 			return DM_MAPIO_REQUEUE;
-		return dm_report_EIO(m);
+		dm_report_EIO(m);
+		return -EIO;
 	}
 
 	mpio->pgpath = pgpath;
@@ -1493,7 +1494,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 		if (atomic_read(&m->nr_valid_paths) == 0 &&
 		    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
 			if (error == -EIO)
-				error = dm_report_EIO(m);
+				dm_report_EIO(m);
 			/* complete with the original error */
 			r = DM_ENDIO_DONE;
 		}
@@ -1524,8 +1525,10 @@ static int do_end_io_bio(struct multipath *m, struct bio *clone,
 		fail_path(mpio->pgpath);
 
 	if (atomic_read(&m->nr_valid_paths) == 0 &&
-	    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
-		return dm_report_EIO(m);
+	    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
+		dm_report_EIO(m);
+		return -EIO;
+	}
 
 	/* Queue for the daemon to resubmit */
 	dm_bio_restore(get_bio_details_from_bio(clone), clone);
-- 
cgit v1.2.3


From f98e0eb68008aff9824d1c4dad7276c8bab83ca5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 15 May 2017 17:28:38 +0200
Subject: dm mpath: multipath_clone_and_map must not return -EIO

Since 412445ac ("dm: introduce a new DM_MAPIO_KILL return value"), the
clone_and_map_rq methods must not return errno values, so fix it up
to properly return DM_MAPIO_KILL, instead of the -EIO value that snuck
in due to a conflict between two patches.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-mpath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index d55454f98b59..3df056b73b66 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -481,7 +481,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
 			return DM_MAPIO_DELAY_REQUEUE;
 		dm_report_EIO(m);	/* Failed */
-		return -EIO;
+		return DM_MAPIO_KILL;
 	} else if (test_bit(MPATHF_QUEUE_IO, &m->flags) ||
 		   test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags)) {
 		if (pg_init_all_paths(m))
-- 
cgit v1.2.3


From 13840d38016203f0095cd547b90352812d24b787 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Sun, 30 Apr 2017 17:32:28 -0400
Subject: dm bufio: make the parameter "retain_bytes" unsigned long

Change the type of the parameter "retain_bytes" from unsigned to
unsigned long, so that on 64-bit machines the user can set more than
4GiB of data to be retained.

Also, change the type of the variable "count" in the function
"__evict_old_buffers" to unsigned long.  The assignment
"count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];"
could result in unsigned long to unsigned overflow and that could result
in buffers not being freed when they should.

While at it, avoid division in get_retain_buffers().  Division is slow,
we can change it to shift because we have precalculated the log2 of
block size.

Cc: stable@vger.kernel.org
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-bufio.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 5db11a405129..cd8139593ccd 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -218,7 +218,7 @@ static DEFINE_SPINLOCK(param_spinlock);
  * Buffers are freed after this timeout
  */
 static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS;
-static unsigned dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
+static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
 
 static unsigned long dm_bufio_peak_allocated;
 static unsigned long dm_bufio_allocated_kmem_cache;
@@ -1558,10 +1558,10 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp)
 	return true;
 }
 
-static unsigned get_retain_buffers(struct dm_bufio_client *c)
+static unsigned long get_retain_buffers(struct dm_bufio_client *c)
 {
-        unsigned retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes);
-        return retain_bytes / c->block_size;
+        unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes);
+        return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT);
 }
 
 static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
@@ -1571,7 +1571,7 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
 	struct dm_buffer *b, *tmp;
 	unsigned long freed = 0;
 	unsigned long count = nr_to_scan;
-	unsigned retain_target = get_retain_buffers(c);
+	unsigned long retain_target = get_retain_buffers(c);
 
 	for (l = 0; l < LIST_SIZE; l++) {
 		list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
@@ -1794,8 +1794,8 @@ static bool older_than(struct dm_buffer *b, unsigned long age_hz)
 static void __evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz)
 {
 	struct dm_buffer *b, *tmp;
-	unsigned retain_target = get_retain_buffers(c);
-	unsigned count;
+	unsigned long retain_target = get_retain_buffers(c);
+	unsigned long count;
 	LIST_HEAD(write_list);
 
 	dm_bufio_lock(c);
@@ -1955,7 +1955,7 @@ MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache");
 module_param_named(max_age_seconds, dm_bufio_max_age, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds");
 
-module_param_named(retain_bytes, dm_bufio_retain_bytes, uint, S_IRUGO | S_IWUSR);
+module_param_named(retain_bytes, dm_bufio_retain_bytes, ulong, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(retain_bytes, "Try to keep at least this many bytes cached in memory");
 
 module_param_named(peak_allocated_bytes, dm_bufio_peak_allocated, ulong, S_IRUGO | S_IWUSR);
-- 
cgit v1.2.3


From 7e1b9521f5a8356553f5e58b07952bf346632ea4 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 11 Mar 2017 19:09:45 +0000
Subject: dm cache: handle kmalloc failure allocating background_tracker struct

Currently there is no kmalloc failure check on the allocation of
the background_tracker struct in btracker_create(), and so a NULL return
will lead to a NULL pointer dereference.  Add a NULL check.

Detected by CoverityScan, CID#1416587 ("Dereference null return value")

Fixes: b29d4986d ("dm cache: significant rework to leverage dm-bio-prison-v2")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-cache-background-tracker.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'drivers/md')

diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c
index 9b1afdfb13f0..707233891291 100644
--- a/drivers/md/dm-cache-background-tracker.c
+++ b/drivers/md/dm-cache-background-tracker.c
@@ -33,6 +33,11 @@ struct background_tracker *btracker_create(unsigned max_work)
 {
 	struct background_tracker *b = kmalloc(sizeof(*b), GFP_KERNEL);
 
+	if (!b) {
+		DMERR("couldn't create background_tracker");
+		return NULL;
+	}
+
 	b->max_work = max_work;
 	atomic_set(&b->pending_promotes, 0);
 	atomic_set(&b->pending_writebacks, 0);
-- 
cgit v1.2.3