aboutsummaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bcache/bcache.h7
-rw-r--r--drivers/md/bcache/bset.c39
-rw-r--r--drivers/md/bcache/btree.c2
-rw-r--r--drivers/md/bcache/journal.c33
-rw-r--r--drivers/md/bcache/request.c15
-rw-r--r--drivers/md/bcache/sysfs.c8
-rw-r--r--drivers/md/bcache/util.c11
-rw-r--r--drivers/md/bcache/util.h12
-rw-r--r--drivers/md/bcache/writeback.c42
-rw-r--r--drivers/md/dm-mpath.c11
-rw-r--r--drivers/md/dm-raid.c2
-rw-r--r--drivers/md/dm-snap-persistent.c2
-rw-r--r--drivers/md/dm-snap.c5
-rw-r--r--drivers/md/dm.c11
14 files changed, 132 insertions, 68 deletions
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index c42b14b2304..6bc016eabdc 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -499,7 +499,7 @@ struct cached_dev {
*/
atomic_t has_dirty;
- struct ratelimit writeback_rate;
+ struct bch_ratelimit writeback_rate;
struct delayed_work writeback_rate_update;
/*
@@ -508,10 +508,9 @@ struct cached_dev {
*/
sector_t last_read;
- /* Number of writeback bios in flight */
- atomic_t in_flight;
+ /* Limit number of writeback bios in flight */
+ struct semaphore in_flight;
struct closure_with_timer writeback;
- struct closure_waitlist writeback_wait;
struct keybuf writeback_keys;
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index cb4578a327b..14032e8c773 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -918,28 +918,45 @@ struct bkey *bch_next_recurse_key(struct btree *b, struct bkey *search)
/* Mergesort */
+static void sort_key_next(struct btree_iter *iter,
+ struct btree_iter_set *i)
+{
+ i->k = bkey_next(i->k);
+
+ if (i->k == i->end)
+ *i = iter->data[--iter->used];
+}
+
static void btree_sort_fixup(struct btree_iter *iter)
{
while (iter->used > 1) {
struct btree_iter_set *top = iter->data, *i = top + 1;
- struct bkey *k;
if (iter->used > 2 &&
btree_iter_cmp(i[0], i[1]))
i++;
- for (k = i->k;
- k != i->end && bkey_cmp(top->k, &START_KEY(k)) > 0;
- k = bkey_next(k))
- if (top->k > i->k)
- __bch_cut_front(top->k, k);
- else if (KEY_SIZE(k))
- bch_cut_back(&START_KEY(k), top->k);
-
- if (top->k < i->k || k == i->k)
+ if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0)
break;
- heap_sift(iter, i - top, btree_iter_cmp);
+ if (!KEY_SIZE(i->k)) {
+ sort_key_next(iter, i);
+ heap_sift(iter, i - top, btree_iter_cmp);
+ continue;
+ }
+
+ if (top->k > i->k) {
+ if (bkey_cmp(top->k, i->k) >= 0)
+ sort_key_next(iter, i);
+ else
+ bch_cut_front(top->k, i->k);
+
+ heap_sift(iter, i - top, btree_iter_cmp);
+ } else {
+ /* can't happen because of comparison func */
+ BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k)));
+ bch_cut_back(&START_KEY(i->k), top->k);
+ }
}
}
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 833c590806b..7d3deab11fc 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -633,7 +633,7 @@ static int bch_mca_shrink(struct shrinker *shrink, struct shrink_control *sc)
return mca_can_free(c) * c->btree_pages;
/* Return -1 if we can't do anything right now */
- if (sc->gfp_mask & __GFP_WAIT)
+ if (sc->gfp_mask & __GFP_IO)
mutex_lock(&c->bucket_lock);
else if (!mutex_trylock(&c->bucket_lock))
return -1;
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index b49abb246bb..151a4ab90dd 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -151,7 +151,8 @@ int bch_journal_read(struct cache_set *c, struct list_head *list,
bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
pr_debug("%u journal buckets", ca->sb.njournal_buckets);
- /* Read journal buckets ordered by golden ratio hash to quickly
+ /*
+ * Read journal buckets ordered by golden ratio hash to quickly
* find a sequence of buckets with valid journal entries
*/
for (i = 0; i < ca->sb.njournal_buckets; i++) {
@@ -164,18 +165,20 @@ int bch_journal_read(struct cache_set *c, struct list_head *list,
goto bsearch;
}
- /* If that fails, check all the buckets we haven't checked
+ /*
+ * If that fails, check all the buckets we haven't checked
* already
*/
pr_debug("falling back to linear search");
- for (l = 0; l < ca->sb.njournal_buckets; l++) {
- if (test_bit(l, bitmap))
- continue;
-
+ for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets);
+ l < ca->sb.njournal_buckets;
+ l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets, l + 1))
if (read_bucket(l))
goto bsearch;
- }
+
+ if (list_empty(list))
+ continue;
bsearch:
/* Binary search */
m = r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
@@ -195,10 +198,12 @@ bsearch:
r = m;
}
- /* Read buckets in reverse order until we stop finding more
+ /*
+ * Read buckets in reverse order until we stop finding more
* journal entries
*/
- pr_debug("finishing up");
+ pr_debug("finishing up: m %u njournal_buckets %u",
+ m, ca->sb.njournal_buckets);
l = m;
while (1) {
@@ -226,9 +231,10 @@ bsearch:
}
}
- c->journal.seq = list_entry(list->prev,
- struct journal_replay,
- list)->j.seq;
+ if (!list_empty(list))
+ c->journal.seq = list_entry(list->prev,
+ struct journal_replay,
+ list)->j.seq;
return 0;
#undef read_bucket
@@ -425,7 +431,7 @@ static void do_journal_discard(struct cache *ca)
return;
}
- switch (atomic_read(&ja->discard_in_flight) == DISCARD_IN_FLIGHT) {
+ switch (atomic_read(&ja->discard_in_flight)) {
case DISCARD_IN_FLIGHT:
return;
@@ -686,6 +692,7 @@ void bch_journal_meta(struct cache_set *c, struct closure *cl)
if (cl)
BUG_ON(!closure_wait(&w->wait, cl));
+ closure_flush(&c->journal.io);
__journal_try_write(c, true);
}
}
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index afb9a998a73..2fe37fac1ca 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1056,14 +1056,17 @@ static void request_write(struct cached_dev *dc, struct search *s)
trace_bcache_writeback(s->orig_bio);
bch_writeback_add(dc, bio_sectors(bio));
- if (s->op.flush_journal) {
+ if (bio->bi_rw & REQ_FLUSH) {
/* Also need to send a flush to the backing device */
- s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO,
- dc->disk.bio_split);
+ struct bio *flush = bio_alloc_bioset(0, GFP_NOIO,
+ dc->disk.bio_split);
- bio->bi_size = 0;
- bio->bi_vcnt = 0;
- closure_bio_submit(bio, cl, s->d);
+ flush->bi_rw = WRITE_FLUSH;
+ flush->bi_bdev = bio->bi_bdev;
+ flush->bi_end_io = request_endio;
+ flush->bi_private = cl;
+
+ closure_bio_submit(flush, cl, s->d);
} else {
s->op.cache_bio = bio;
}
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 4d9cca47e4c..e9bd6c0cca5 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -214,7 +214,13 @@ STORE(__cached_dev)
}
if (attr == &sysfs_label) {
- memcpy(dc->sb.label, buf, SB_LABEL_SIZE);
+ if (size > SB_LABEL_SIZE)
+ return -EINVAL;
+ memcpy(dc->sb.label, buf, size);
+ if (size < SB_LABEL_SIZE)
+ dc->sb.label[size] = '\0';
+ if (size && dc->sb.label[size - 1] == '\n')
+ dc->sb.label[size - 1] = '\0';
bch_write_bdev_super(dc, NULL);
if (dc->disk.c) {
memcpy(dc->disk.c->uuids[dc->disk.id].label,
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index da3a99e85b1..38a43f8d36e 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -190,7 +190,16 @@ void bch_time_stats_update(struct time_stats *stats, uint64_t start_time)
stats->last = now ?: 1;
}
-unsigned bch_next_delay(struct ratelimit *d, uint64_t done)
+/**
+ * bch_next_delay() - increment @d by the amount of work done, and return how
+ * long to delay until the next time to do some work.
+ *
+ * @d - the struct bch_ratelimit to update
+ * @done - the amount of work done, in arbitrary units
+ *
+ * Returns the amount of time to delay by, in jiffies
+ */
+uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
{
uint64_t now = local_clock();
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 577393e38c3..43fd78affce 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -452,17 +452,23 @@ read_attribute(name ## _last_ ## frequency_units)
(ewma) >> factor; \
})
-struct ratelimit {
+struct bch_ratelimit {
+ /* Next time we want to do some work, in nanoseconds */
uint64_t next;
+
+ /*
+ * Rate at which we want to do work, in units per nanosecond
+ * The units here correspond to the units passed to bch_next_delay()
+ */
unsigned rate;
};
-static inline void ratelimit_reset(struct ratelimit *d)
+static inline void bch_ratelimit_reset(struct bch_ratelimit *d)
{
d->next = local_clock();
}
-unsigned bch_next_delay(struct ratelimit *d, uint64_t done);
+uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done);
#define __DIV_SAFE(n, d, zero) \
({ \
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 2714ed3991d..841f0490d4e 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -91,11 +91,15 @@ static void update_writeback_rate(struct work_struct *work)
static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
{
+ uint64_t ret;
+
if (atomic_read(&dc->disk.detaching) ||
!dc->writeback_percent)
return 0;
- return bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+ ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+
+ return min_t(uint64_t, ret, HZ);
}
/* Background writeback */
@@ -165,7 +169,7 @@ static void refill_dirty(struct closure *cl)
up_write(&dc->writeback_lock);
- ratelimit_reset(&dc->writeback_rate);
+ bch_ratelimit_reset(&dc->writeback_rate);
/* Punt to workqueue only so we don't recurse and blow the stack */
continue_at(cl, read_dirty, dirty_wq);
@@ -246,9 +250,7 @@ static void write_dirty_finish(struct closure *cl)
}
bch_keybuf_del(&dc->writeback_keys, w);
- atomic_dec_bug(&dc->in_flight);
-
- closure_wake_up(&dc->writeback_wait);
+ up(&dc->in_flight);
closure_return_with_destructor(cl, dirty_io_destructor);
}
@@ -278,7 +280,7 @@ static void write_dirty(struct closure *cl)
trace_bcache_write_dirty(&io->bio);
closure_bio_submit(&io->bio, cl, &io->dc->disk);
- continue_at(cl, write_dirty_finish, dirty_wq);
+ continue_at(cl, write_dirty_finish, system_wq);
}
static void read_dirty_endio(struct bio *bio, int error)
@@ -299,7 +301,7 @@ static void read_dirty_submit(struct closure *cl)
trace_bcache_read_dirty(&io->bio);
closure_bio_submit(&io->bio, cl, &io->dc->disk);
- continue_at(cl, write_dirty, dirty_wq);
+ continue_at(cl, write_dirty, system_wq);
}
static void read_dirty(struct closure *cl)
@@ -324,12 +326,8 @@ static void read_dirty(struct closure *cl)
if (delay > 0 &&
(KEY_START(&w->key) != dc->last_read ||
- jiffies_to_msecs(delay) > 50)) {
- w->private = NULL;
-
- closure_delay(&dc->writeback, delay);
- continue_at(cl, read_dirty, dirty_wq);
- }
+ jiffies_to_msecs(delay) > 50))
+ delay = schedule_timeout_uninterruptible(delay);
dc->last_read = KEY_OFFSET(&w->key);
@@ -354,15 +352,10 @@ static void read_dirty(struct closure *cl)
pr_debug("%s", pkey(&w->key));
- closure_call(&io->cl, read_dirty_submit, NULL, &dc->disk.cl);
+ down(&dc->in_flight);
+ closure_call(&io->cl, read_dirty_submit, NULL, cl);
delay = writeback_delay(dc, KEY_SIZE(&w->key));
-
- atomic_inc(&dc->in_flight);
-
- if (!closure_wait_event(&dc->writeback_wait, cl,
- atomic_read(&dc->in_flight) < 64))
- continue_at(cl, read_dirty, dirty_wq);
}
if (0) {
@@ -372,11 +365,16 @@ err:
bch_keybuf_del(&dc->writeback_keys, w);
}
- refill_dirty(cl);
+ /*
+ * Wait for outstanding writeback IOs to finish (and keybuf slots to be
+ * freed) before refilling again
+ */
+ continue_at(cl, refill_dirty, dirty_wq);
}
void bch_cached_dev_writeback_init(struct cached_dev *dc)
{
+ sema_init(&dc->in_flight, 64);
closure_init_unlocked(&dc->writeback);
init_rwsem(&dc->writeback_lock);
@@ -406,7 +404,7 @@ void bch_writeback_exit(void)
int __init bch_writeback_init(void)
{
- dirty_wq = create_singlethread_workqueue("bcache_writeback");
+ dirty_wq = create_workqueue("bcache_writeback");
if (!dirty_wq)
return -ENOMEM;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 5adede17ddf..c5b7b3dd91c 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1284,8 +1284,17 @@ static int do_end_io(struct multipath *m, struct request *clone,
if (!error && !clone->errors)
return 0; /* I/O complete */
- if (error == -EOPNOTSUPP || error == -EREMOTEIO || error == -EILSEQ)
+ if (error == -EOPNOTSUPP || error == -EREMOTEIO || error == -EILSEQ) {
+ if ((clone->cmd_flags & REQ_WRITE_SAME) &&
+ !clone->q->limits.max_write_same_sectors) {
+ struct queue_limits *limits;
+
+ /* device doesn't really support WRITE SAME, disable it */
+ limits = dm_get_queue_limits(dm_table_get_md(m->ti->table));
+ limits->max_write_same_sectors = 0;
+ }
return error;
+ }
if (mpio->pgpath)
fail_path(mpio->pgpath);
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1d3fe1a40a9..2dea49c4279 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -380,7 +380,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
static int validate_raid_redundancy(struct raid_set *rs)
{
unsigned i, rebuild_cnt = 0;
- unsigned rebuilds_per_group, copies, d;
+ unsigned rebuilds_per_group = 0, copies, d;
unsigned group_size, last_group_start;
for (i = 0; i < rs->md.raid_disks; i++)
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 3ac415675b6..4caa8e6d59d 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -256,7 +256,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
*/
INIT_WORK_ONSTACK(&req.work, do_metadata);
queue_work(ps->metadata_wq, &req.work);
- flush_work(&req.work);
+ flush_workqueue(ps->metadata_wq);
return req.result;
}
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index c434e5aab2d..aec57d76db5 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -725,17 +725,16 @@ static int calc_max_buckets(void)
*/
static int init_hash_tables(struct dm_snapshot *s)
{
- sector_t hash_size, cow_dev_size, origin_dev_size, max_buckets;
+ sector_t hash_size, cow_dev_size, max_buckets;
/*
* Calculate based on the size of the original volume or
* the COW volume...
*/
cow_dev_size = get_dev_size(s->cow->bdev);
- origin_dev_size = get_dev_size(s->origin->bdev);
max_buckets = calc_max_buckets();
- hash_size = min(origin_dev_size, cow_dev_size) >> s->store->chunk_shift;
+ hash_size = cow_dev_size >> s->store->chunk_shift;
hash_size = min(hash_size, max_buckets);
if (hash_size < 64)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 33f20103d8d..1c13071a81b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2219,6 +2219,17 @@ struct target_type *dm_get_immutable_target_type(struct mapped_device *md)
}
/*
+ * The queue_limits are only valid as long as you have a reference
+ * count on 'md'.
+ */
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
+{
+ BUG_ON(!atomic_read(&md->holders));
+ return &md->queue->limits;
+}
+EXPORT_SYMBOL_GPL(dm_get_queue_limits);
+
+/*
* Fully initialize a request-based queue (->elevator, ->request_fn, etc).
*/
static int dm_init_request_based_queue(struct mapped_device *md)
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-27 22:49:17 +0000