summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/Makefile3
-rw-r--r--drivers/md/bcache/btree.c4
-rw-r--r--drivers/md/bcache/closure.c2
-rw-r--r--drivers/md/bcache/closure.h3
-rw-r--r--drivers/md/bcache/debug.c6
-rw-r--r--drivers/md/bcache/io.c3
-rw-r--r--drivers/md/bcache/journal.c9
-rw-r--r--drivers/md/bcache/movinggc.c2
-rw-r--r--drivers/md/bcache/request.c34
-rw-r--r--drivers/md/bcache/super.c48
-rw-r--r--drivers/md/bcache/writeback.c4
-rw-r--r--drivers/md/bcache/writeback.h2
-rw-r--r--drivers/md/bitmap.c53
-rw-r--r--drivers/md/dm-bufio.c11
-rw-r--r--drivers/md/dm-builtin.c2
-rw-r--r--drivers/md/dm-cache-target.c18
-rw-r--r--drivers/md/dm-core.h149
-rw-r--r--drivers/md/dm-crypt.c17
-rw-r--r--drivers/md/dm-era-target.c4
-rw-r--r--drivers/md/dm-flakey.c6
-rw-r--r--drivers/md/dm-io.c65
-rw-r--r--drivers/md/dm-ioctl.c31
-rw-r--r--drivers/md/dm-kcopyd.c13
-rw-r--r--drivers/md/dm-linear.c21
-rw-r--r--drivers/md/dm-log-writes.c19
-rw-r--r--drivers/md/dm-log.c14
-rw-r--r--drivers/md/dm-mpath.c374
-rw-r--r--drivers/md/dm-raid.c3038
-rw-r--r--drivers/md/dm-raid1.c32
-rw-r--r--drivers/md/dm-region-hash.c6
-rw-r--r--drivers/md/dm-rq.c988
-rw-r--r--drivers/md/dm-rq.h64
-rw-r--r--drivers/md/dm-snap-persistent.c24
-rw-r--r--drivers/md/dm-snap.c27
-rw-r--r--drivers/md/dm-stats.c11
-rw-r--r--drivers/md/dm-stripe.c34
-rw-r--r--drivers/md/dm-sysfs.c3
-rw-r--r--drivers/md/dm-table.c114
-rw-r--r--drivers/md/dm-target.c11
-rw-r--r--drivers/md/dm-thin-metadata.c30
-rw-r--r--drivers/md/dm-thin-metadata.h3
-rw-r--r--drivers/md/dm-thin.c124
-rw-r--r--drivers/md/dm-zero.c15
-rw-r--r--drivers/md/dm.c1272
-rw-r--r--drivers/md/dm.h36
-rw-r--r--drivers/md/linear.c4
-rw-r--r--drivers/md/md-cluster.c12
-rw-r--r--drivers/md/md.c122
-rw-r--r--drivers/md/md.h15
-rw-r--r--drivers/md/multipath.c37
-rw-r--r--drivers/md/persistent-data/dm-btree.c9
-rw-r--r--drivers/md/raid0.c4
-rw-r--r--drivers/md/raid1.c173
-rw-r--r--drivers/md/raid10.c320
-rw-r--r--drivers/md/raid10.h3
-rw-r--r--drivers/md/raid5-cache.c79
-rw-r--r--drivers/md/raid5.c183
57 files changed, 5279 insertions, 2431 deletions
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 52ba8dd82..3cbda1af8 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -3,7 +3,8 @@
#
dm-mod-y += dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \
- dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o dm-stats.o
+ dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o dm-stats.o \
+ dm-rq.o
dm-multipath-y += dm-path-selector.o dm-mpath.o
dm-snapshot-y += dm-snap.o dm-exception-store.o dm-snap-transient.o \
dm-snap-persistent.o
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index eab505ee0..76f7534d1 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -294,10 +294,10 @@ static void bch_btree_node_read(struct btree *b)
closure_init_stack(&cl);
bio = bch_bbio_alloc(b->c);
- bio->bi_rw = REQ_META|READ_SYNC;
bio->bi_iter.bi_size = KEY_SIZE(&b->key) << 9;
bio->bi_end_io = btree_node_read_endio;
bio->bi_private = &cl;
+ bio_set_op_attrs(bio, REQ_OP_READ, REQ_META|READ_SYNC);
bch_bio_map(bio, b->keys.set[0].data);
@@ -396,8 +396,8 @@ static void do_btree_node_write(struct btree *b)
b->bio->bi_end_io = btree_node_write_endio;
b->bio->bi_private = cl;
- b->bio->bi_rw = REQ_META|WRITE_SYNC|REQ_FUA;
b->bio->bi_iter.bi_size = roundup(set_bytes(i), block_bytes(b->c));
+ bio_set_op_attrs(b->bio, REQ_OP_WRITE, REQ_META|WRITE_SYNC|REQ_FUA);
bch_bio_map(b->bio, i);
/*
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 9eaf1d6e8..864e673ae 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -112,7 +112,7 @@ bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl)
EXPORT_SYMBOL(closure_wait);
/**
- * closure_sync - sleep until a closure a closure has nothing left to wait on
+ * closure_sync - sleep until a closure has nothing left to wait on
*
* Sleeps until the refcount hits 1 - the thread that's running the closure owns
* the last refcount.
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 782cc2c8a..9b2fe2d3e 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -31,7 +31,8 @@
* passing it, as you might expect, the function to run when nothing is pending
* and the workqueue to run that function out of.
*
- * continue_at() also, critically, is a macro that returns the calling function.
+ * continue_at() also, critically, requires a 'return' immediately following the
+ * location where this macro is referenced, to return to the calling function.
* There's good reason for this.
*
* To use safely closures asynchronously, they must always have a refcount while
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 8b1f1d5c1..c28df1647 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -52,9 +52,10 @@ void bch_btree_verify(struct btree *b)
bio->bi_bdev = PTR_CACHE(b->c, &b->key, 0)->bdev;
bio->bi_iter.bi_sector = PTR_OFFSET(&b->key, 0);
bio->bi_iter.bi_size = KEY_SIZE(&v->key) << 9;
+ bio_set_op_attrs(bio, REQ_OP_READ, REQ_META|READ_SYNC);
bch_bio_map(bio, sorted);
- submit_bio_wait(REQ_META|READ_SYNC, bio);
+ submit_bio_wait(bio);
bch_bbio_free(bio, b->c);
memcpy(ondisk, sorted, KEY_SIZE(&v->key) << 9);
@@ -113,11 +114,12 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
check = bio_clone(bio, GFP_NOIO);
if (!check)
return;
+ bio_set_op_attrs(check, REQ_OP_READ, READ_SYNC);
if (bio_alloc_pages(check, GFP_NOIO))
goto out_put;
- submit_bio_wait(READ_SYNC, check);
+ submit_bio_wait(check);
bio_for_each_segment(bv, bio, iter) {
void *p1 = kmap_atomic(bv.bv_page);
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index 86a0bb871..e97b0acf7 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -25,7 +25,6 @@ struct bio *bch_bbio_alloc(struct cache_set *c)
struct bio *bio = &b->bio;
bio_init(bio);
- bio->bi_flags |= BIO_POOL_NONE << BIO_POOL_OFFSET;
bio->bi_max_vecs = bucket_pages(c);
bio->bi_io_vec = bio->bi_inline_vecs;
@@ -111,7 +110,7 @@ void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
struct bbio *b = container_of(bio, struct bbio, bio);
struct cache *ca = PTR_CACHE(c, &b->key, 0);
- unsigned threshold = bio->bi_rw & REQ_WRITE
+ unsigned threshold = op_is_write(bio_op(bio))
? c->congested_write_threshold_us
: c->congested_read_threshold_us;
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 29eba7219..6925023e1 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -54,11 +54,11 @@ reread: left = ca->sb.bucket_size - offset;
bio_reset(bio);
bio->bi_iter.bi_sector = bucket + offset;
bio->bi_bdev = ca->bdev;
- bio->bi_rw = READ;
bio->bi_iter.bi_size = len << 9;
bio->bi_end_io = journal_read_endio;
bio->bi_private = &cl;
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
bch_bio_map(bio, data);
closure_bio_submit(bio, &cl);
@@ -418,7 +418,7 @@ static void journal_discard_work(struct work_struct *work)
struct journal_device *ja =
container_of(work, struct journal_device, discard_work);
- submit_bio(0, &ja->discard_bio);
+ submit_bio(&ja->discard_bio);
}
static void do_journal_discard(struct cache *ca)
@@ -449,10 +449,10 @@ static void do_journal_discard(struct cache *ca)
atomic_set(&ja->discard_in_flight, DISCARD_IN_FLIGHT);
bio_init(bio);
+ bio_set_op_attrs(bio, REQ_OP_DISCARD, 0);
bio->bi_iter.bi_sector = bucket_to_sector(ca->set,
ca->sb.d[ja->discard_idx]);
bio->bi_bdev = ca->bdev;
- bio->bi_rw = REQ_WRITE|REQ_DISCARD;
bio->bi_max_vecs = 1;
bio->bi_io_vec = bio->bi_inline_vecs;
bio->bi_iter.bi_size = bucket_bytes(ca);
@@ -626,11 +626,12 @@ static void journal_write_unlocked(struct closure *cl)
bio_reset(bio);
bio->bi_iter.bi_sector = PTR_OFFSET(k, i);
bio->bi_bdev = ca->bdev;
- bio->bi_rw = REQ_WRITE|REQ_SYNC|REQ_META|REQ_FLUSH|REQ_FUA;
bio->bi_iter.bi_size = sectors << 9;
bio->bi_end_io = journal_write_endio;
bio->bi_private = w;
+ bio_set_op_attrs(bio, REQ_OP_WRITE,
+ REQ_SYNC|REQ_META|REQ_PREFLUSH|REQ_FUA);
bch_bio_map(bio, w->data);
trace_bcache_journal_write(bio);
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index b929fc944..1881319f2 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -163,7 +163,7 @@ static void read_moving(struct cache_set *c)
moving_init(io);
bio = &io->bio.bio;
- bio->bi_rw = READ;
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
bio->bi_end_io = read_moving_endio;
if (bio_alloc_pages(bio, GFP_KERNEL))
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 25fa8445b..4b177fe11 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -205,10 +205,10 @@ static void bch_data_insert_start(struct closure *cl)
return bch_data_invalidate(cl);
/*
- * Journal writes are marked REQ_FLUSH; if the original write was a
+ * Journal writes are marked REQ_PREFLUSH; if the original write was a
* flush, it'll wait on the journal write.
*/
- bio->bi_rw &= ~(REQ_FLUSH|REQ_FUA);
+ bio->bi_opf &= ~(REQ_PREFLUSH|REQ_FUA);
do {
unsigned i;
@@ -253,7 +253,7 @@ static void bch_data_insert_start(struct closure *cl)
trace_bcache_cache_insert(k);
bch_keylist_push(&op->insert_keys);
- n->bi_rw |= REQ_WRITE;
+ bio_set_op_attrs(n, REQ_OP_WRITE, 0);
bch_submit_bbio(n, op->c, k, 0);
} while (n != bio);
@@ -378,12 +378,12 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) ||
c->gc_stats.in_use > CUTOFF_CACHE_ADD ||
- (bio->bi_rw & REQ_DISCARD))
+ (bio_op(bio) == REQ_OP_DISCARD))
goto skip;
if (mode == CACHE_MODE_NONE ||
(mode == CACHE_MODE_WRITEAROUND &&
- (bio->bi_rw & REQ_WRITE)))
+ op_is_write(bio_op(bio))))
goto skip;
if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
@@ -404,8 +404,8 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
if (!congested &&
mode == CACHE_MODE_WRITEBACK &&
- (bio->bi_rw & REQ_WRITE) &&
- (bio->bi_rw & REQ_SYNC))
+ op_is_write(bio_op(bio)) &&
+ (bio->bi_opf & REQ_SYNC))
goto rescale;
spin_lock(&dc->io_lock);
@@ -657,7 +657,7 @@ static inline struct search *search_alloc(struct bio *bio,
s->cache_miss = NULL;
s->d = d;
s->recoverable = 1;
- s->write = (bio->bi_rw & REQ_WRITE) != 0;
+ s->write = op_is_write(bio_op(bio));
s->read_dirty_data = 0;
s->start_time = jiffies;
@@ -668,7 +668,7 @@ static inline struct search *search_alloc(struct bio *bio,
s->iop.write_prio = 0;
s->iop.error = 0;
s->iop.flags = 0;
- s->iop.flush_journal = (bio->bi_rw & (REQ_FLUSH|REQ_FUA)) != 0;
+ s->iop.flush_journal = (bio->bi_opf & (REQ_PREFLUSH|REQ_FUA)) != 0;
s->iop.wq = bcache_wq;
return s;
@@ -796,8 +796,8 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
goto out_submit;
}
- if (!(bio->bi_rw & REQ_RAHEAD) &&
- !(bio->bi_rw & REQ_META) &&
+ if (!(bio->bi_opf & REQ_RAHEAD) &&
+ !(bio->bi_opf & REQ_META) &&
s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA)
reada = min_t(sector_t, dc->readahead >> 9,
bdev_sectors(bio->bi_bdev) - bio_end_sector(bio));
@@ -899,7 +899,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
* But check_overlapping drops dirty keys for which io hasn't started,
* so we still want to call it.
*/
- if (bio->bi_rw & REQ_DISCARD)
+ if (bio_op(bio) == REQ_OP_DISCARD)
s->iop.bypass = true;
if (should_writeback(dc, s->orig_bio,
@@ -913,22 +913,22 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
s->iop.bio = s->orig_bio;
bio_get(s->iop.bio);
- if (!(bio->bi_rw & REQ_DISCARD) ||
+ if ((bio_op(bio) != REQ_OP_DISCARD) ||
blk_queue_discard(bdev_get_queue(dc->bdev)))
closure_bio_submit(bio, cl);
} else if (s->iop.writeback) {
bch_writeback_add(dc);
s->iop.bio = bio;
- if (bio->bi_rw & REQ_FLUSH) {
+ if (bio->bi_opf & REQ_PREFLUSH) {
/* Also need to send a flush to the backing device */
struct bio *flush = bio_alloc_bioset(GFP_NOIO, 0,
dc->disk.bio_split);
- flush->bi_rw = WRITE_FLUSH;
flush->bi_bdev = bio->bi_bdev;
flush->bi_end_io = request_endio;
flush->bi_private = cl;
+ bio_set_op_attrs(flush, REQ_OP_WRITE, WRITE_FLUSH);
closure_bio_submit(flush, cl);
}
@@ -992,7 +992,7 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
cached_dev_read(dc, s);
}
} else {
- if ((bio->bi_rw & REQ_DISCARD) &&
+ if ((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(dc->bdev)))
bio_endio(bio);
else
@@ -1103,7 +1103,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
&KEY(d->id, bio->bi_iter.bi_sector, 0),
&KEY(d->id, bio_end_sector(bio), 0));
- s->iop.bypass = (bio->bi_rw & REQ_DISCARD) != 0;
+ s->iop.bypass = (bio_op(bio) == REQ_OP_DISCARD) != 0;
s->iop.writeback = true;
s->iop.bio = bio;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 5d3b2318c..849ad441c 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -134,7 +134,6 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
case BCACHE_SB_VERSION_CDEV:
case BCACHE_SB_VERSION_CDEV_WITH_UUID:
sb->nbuckets = le64_to_cpu(s->nbuckets);
- sb->block_size = le16_to_cpu(s->block_size);
sb->bucket_size = le16_to_cpu(s->bucket_size);
sb->nr_in_set = le16_to_cpu(s->nr_in_set);
@@ -212,8 +211,8 @@ static void __write_super(struct cache_sb *sb, struct bio *bio)
unsigned i;
bio->bi_iter.bi_sector = SB_SECTOR;
- bio->bi_rw = REQ_SYNC|REQ_META;
bio->bi_iter.bi_size = SB_SIZE;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC|REQ_META);
bch_bio_map(bio, NULL);
out->offset = cpu_to_le64(sb->offset);
@@ -238,7 +237,7 @@ static void __write_super(struct cache_sb *sb, struct bio *bio)
pr_debug("ver %llu, flags %llu, seq %llu",
sb->version, sb->flags, sb->seq);
- submit_bio(REQ_WRITE, bio);
+ submit_bio(bio);
}
static void bch_write_bdev_super_unlock(struct closure *cl)
@@ -333,7 +332,7 @@ static void uuid_io_unlock(struct closure *cl)
up(&c->uuid_write_mutex);
}
-static void uuid_io(struct cache_set *c, unsigned long rw,
+static void uuid_io(struct cache_set *c, int op, unsigned long op_flags,
struct bkey *k, struct closure *parent)
{
struct closure *cl = &c->uuid_write;
@@ -348,21 +347,22 @@ static void uuid_io(struct cache_set *c, unsigned long rw,
for (i = 0; i < KEY_PTRS(k); i++) {
struct bio *bio = bch_bbio_alloc(c);
- bio->bi_rw = REQ_SYNC|REQ_META|rw;
+ bio->bi_opf = REQ_SYNC | REQ_META | op_flags;
bio->bi_iter.bi_size = KEY_SIZE(k) << 9;
bio->bi_end_io = uuid_endio;
bio->bi_private = cl;
+ bio_set_op_attrs(bio, op, REQ_SYNC|REQ_META|op_flags);
bch_bio_map(bio, c->uuids);
bch_submit_bbio(bio, c, k, i);
- if (!(rw & WRITE))
+ if (op != REQ_OP_WRITE)
break;
}
bch_extent_to_text(buf, sizeof(buf), k);
- pr_debug("%s UUIDs at %s", rw & REQ_WRITE ? "wrote" : "read", buf);
+ pr_debug("%s UUIDs at %s", op == REQ_OP_WRITE ? "wrote" : "read", buf);
for (u = c->uuids; u < c->uuids + c->nr_uuids; u++)
if (!bch_is_zero(u->uuid, 16))
@@ -381,7 +381,7 @@ static char *uuid_read(struct cache_set *c, struct jset *j, struct closure *cl)
return "bad uuid pointer";
bkey_copy(&c->uuid_bucket, k);
- uuid_io(c, READ_SYNC, k, cl);
+ uuid_io(c, REQ_OP_READ, READ_SYNC, k, cl);
if (j->version < BCACHE_JSET_VERSION_UUIDv1) {
struct uuid_entry_v0 *u0 = (void *) c->uuids;
@@ -426,7 +426,7 @@ static int __uuid_write(struct cache_set *c)
return 1;
SET_KEY_SIZE(&k.key, c->sb.bucket_size);
- uuid_io(c, REQ_WRITE, &k.key, &cl);
+ uuid_io(c, REQ_OP_WRITE, 0, &k.key, &cl);
closure_sync(&cl);
bkey_copy(&c->uuid_bucket, &k.key);
@@ -498,7 +498,8 @@ static void prio_endio(struct bio *bio)
closure_put(&ca->prio);
}
-static void prio_io(struct cache *ca, uint64_t bucket, unsigned long rw)
+static void prio_io(struct cache *ca, uint64_t bucket, int op,
+ unsigned long op_flags)
{
struct closure *cl = &ca->prio;
struct bio *bio = bch_bbio_alloc(ca->set);
@@ -507,11 +508,11 @@ static void prio_io(struct cache *ca, uint64_t bucket, unsigned long rw)
bio->bi_iter.bi_sector = bucket * ca->sb.bucket_size;
bio->bi_bdev = ca->bdev;
- bio->bi_rw = REQ_SYNC|REQ_META|rw;
bio->bi_iter.bi_size = bucket_bytes(ca);
bio->bi_end_io = prio_endio;
bio->bi_private = ca;
+ bio_set_op_attrs(bio, op, REQ_SYNC|REQ_META|op_flags);
bch_bio_map(bio, ca->disk_buckets);
closure_bio_submit(bio, &ca->prio);
@@ -557,7 +558,7 @@ void bch_prio_write(struct cache *ca)
BUG_ON(bucket == -1);
mutex_unlock(&ca->set->bucket_lock);
- prio_io(ca, bucket, REQ_WRITE);
+ prio_io(ca, bucket, REQ_OP_WRITE, 0);
mutex_lock(&ca->set->bucket_lock);
ca->prio_buckets[i] = bucket;
@@ -599,7 +600,7 @@ static void prio_read(struct cache *ca, uint64_t bucket)
ca->prio_last_buckets[bucket_nr] = bucket;
bucket_nr++;
- prio_io(ca, bucket, READ_SYNC);
+ prio_io(ca, bucket, REQ_OP_READ, READ_SYNC);
if (p->csum != bch_crc64(&p->magic, bucket_bytes(ca) - 8))
pr_warn("bad csum reading priorities");
@@ -759,7 +760,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
if (!d->nr_stripes ||
d->nr_stripes > INT_MAX ||
d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) {
- pr_err("nr_stripes too large");
+ pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)",
+ (unsigned)d->nr_stripes);
return -ENOMEM;
}
@@ -1518,7 +1520,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
!(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) ||
!(c->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
!(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
- !(c->moving_gc_wq = create_workqueue("bcache_gc")) ||
+ !(c->moving_gc_wq = alloc_workqueue("bcache_gc",
+ WQ_MEM_RECLAIM, 0)) ||
bch_journal_alloc(c) ||
bch_btree_cache_alloc(c) ||
bch_open_buckets_alloc(c) ||
@@ -1803,7 +1806,7 @@ void bch_cache_release(struct kobject *kobj)
module_put(THIS_MODULE);
}
-static int cache_alloc(struct cache_sb *sb, struct cache *ca)
+static int cache_alloc(struct cache *ca)
{
size_t free;
struct bucket *b;
@@ -1842,7 +1845,7 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
struct block_device *bdev, struct cache *ca)
{
char name[BDEVNAME_SIZE];
- const char *err = NULL;
+ const char *err = NULL; /* must be set for any error case */
int ret = 0;
memcpy(&ca->sb, sb, sizeof(struct cache_sb));
@@ -1858,9 +1861,14 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
if (blk_queue_discard(bdev_get_queue(ca->bdev)))
ca->discard = CACHE_DISCARD(&ca->sb);
- ret = cache_alloc(sb, ca);
- if (ret != 0)
+ ret = cache_alloc(ca);
+ if (ret != 0) {
+ if (ret == -ENOMEM)
+ err = "cache_alloc(): -ENOMEM";
+ else
+ err = "cache_alloc(): unknown error";
goto err;
+ }
if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) {
err = "error calling kobject_add";
@@ -2097,7 +2105,7 @@ static int __init bcache_init(void)
return bcache_major;
}
- if (!(bcache_wq = create_workqueue("bcache")) ||
+ if (!(bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0)) ||
!(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
sysfs_create_files(bcache_kobj, files) ||
bch_request_init() ||
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 60123677b..d9fd2a62e 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -182,7 +182,7 @@ static void write_dirty(struct closure *cl)
struct keybuf_key *w = io->bio.bi_private;
dirty_init(w);
- io->bio.bi_rw = WRITE;
+ bio_set_op_attrs(&io->bio, REQ_OP_WRITE, 0);
io->bio.bi_iter.bi_sector = KEY_START(&w->key);
io->bio.bi_bdev = io->dc->bdev;
io->bio.bi_end_io = dirty_endio;
@@ -251,10 +251,10 @@ static void read_dirty(struct cached_dev *dc)
io->dc = dc;
dirty_init(w);
+ bio_set_op_attrs(&io->bio, REQ_OP_READ, 0);
io->bio.bi_iter.bi_sector = PTR_OFFSET(&w->key, 0);
io->bio.bi_bdev = PTR_CACHE(dc->disk.c,
&w->key, 0)->bdev;
- io->bio.bi_rw = READ;
io->bio.bi_end_io = read_dirty_endio;
if (bio_alloc_pages(&io->bio, GFP_KERNEL))
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 073a042ae..301eaf565 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -57,7 +57,7 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
if (would_skip)
return false;
- return bio->bi_rw & REQ_SYNC ||
+ return bio->bi_opf & REQ_SYNC ||
in_use <= CUTOFF_WRITEBACK;
}
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index d8129ec93..13041ee37 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -162,7 +162,7 @@ static int read_sb_page(struct mddev *mddev, loff_t offset,
if (sync_page_io(rdev, target,
roundup(size, bdev_logical_block_size(rdev->bdev)),
- page, READ, true)) {
+ page, REQ_OP_READ, 0, true)) {
page->index = index;
return 0;
}
@@ -297,7 +297,7 @@ static void write_page(struct bitmap *bitmap, struct page *page, int wait)
atomic_inc(&bitmap->pending_writes);
set_buffer_locked(bh);
set_buffer_mapped(bh);
- submit_bh(WRITE | REQ_SYNC, bh);
+ submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
bh = bh->b_this_page;
}
@@ -392,7 +392,7 @@ static int read_page(struct file *file, unsigned long index,
atomic_inc(&bitmap->pending_writes);
set_buffer_locked(bh);
set_buffer_mapped(bh);
- submit_bh(READ, bh);
+ submit_bh(REQ_OP_READ, 0, bh);
}
block++;
bh = bh->b_this_page;
@@ -2183,19 +2183,29 @@ location_show(struct mddev *mddev, char *page)
static ssize_t
location_store(struct mddev *mddev, const char *buf, size_t len)
{
+ int rv;
+ rv = mddev_lock(mddev);
+ if (rv)
+ return rv;
if (mddev->pers) {
- if (!mddev->pers->quiesce)
- return -EBUSY;
- if (mddev->recovery || mddev->sync_thread)
- return -EBUSY;
+ if (!mddev->pers->quiesce) {
+ rv = -EBUSY;
+ goto out;
+ }
+ if (mddev->recovery || mddev->sync_thread) {
+ rv = -EBUSY;
+ goto out;
+ }
}
if (mddev->bitmap || mddev->bitmap_info.file ||
mddev->bitmap_info.offset) {
/* bitmap already configured. Only option is to clear it */
- if (strncmp(buf, "none", 4) != 0)
- return -EBUSY;
+ if (strncmp(buf, "none", 4) != 0) {
+ rv = -EBUSY;
+ goto out;
+ }
if (mddev->pers) {
mddev->pers->quiesce(mddev, 1);
bitmap_destroy(mddev);
@@ -2214,21 +2224,25 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
/* nothing to be done */;
else if (strncmp(buf, "file:", 5) == 0) {
/* Not supported yet */
- return -EINVAL;
+ rv = -EINVAL;
+ goto out;
} else {
- int rv;
if (buf[0] == '+')
rv = kstrtoll(buf+1, 10, &offset);
else
rv = kstrtoll(buf, 10, &offset);
if (rv)
- return rv;
- if (offset == 0)
- return -EINVAL;
+ goto out;
+ if (offset == 0) {
+ rv = -EINVAL;
+ goto out;
+ }
if (mddev->bitmap_info.external == 0 &&
mddev->major_version == 0 &&
- offset != mddev->bitmap_info.default_offset)
- return -EINVAL;
+ offset != mddev->bitmap_info.default_offset) {
+ rv = -EINVAL;
+ goto out;
+ }
mddev->bitmap_info.offset = offset;
if (mddev->pers) {
struct bitmap *bitmap;
@@ -2245,7 +2259,7 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
mddev->pers->quiesce(mddev, 0);
if (rv) {
bitmap_destroy(mddev);
- return rv;
+ goto out;
}
}
}
@@ -2257,6 +2271,11 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
set_bit(MD_CHANGE_DEVS, &mddev->flags);
md_wakeup_thread(mddev->thread);
}
+ rv = 0;
+out:
+ mddev_unlock(mddev);
+ if (rv)
+ return rv;
return len;
}
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index cd77216be..8625040ba 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -574,7 +574,8 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
{
int r;
struct dm_io_request io_req = {
- .bi_rw = rw,
+ .bi_op = rw,
+ .bi_op_flags = 0,
.notify.fn = dmio_complete,
.notify.context = b,
.client = b->c->dm_io,
@@ -634,6 +635,7 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
* the dm_buffer's inline bio is local to bufio.
*/
b->bio.bi_private = end_io;
+ bio_set_op_attrs(&b->bio, rw, 0);
/*
* We assume that if len >= PAGE_SIZE ptr is page-aligned.
@@ -660,7 +662,7 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
ptr += PAGE_SIZE;
} while (len > 0);
- submit_bio(rw, &b->bio);
+ submit_bio(&b->bio);
}
static void submit_io(struct dm_buffer *b, int rw, sector_t block,
@@ -1326,7 +1328,8 @@ EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers);
int dm_bufio_issue_flush(struct dm_bufio_client *c)
{
struct dm_io_request io_req = {
- .bi_rw = WRITE_FLUSH,
+ .bi_op = REQ_OP_WRITE,
+ .bi_op_flags = WRITE_FLUSH,
.mem.type = DM_IO_KMEM,
.mem.ptr.addr = NULL,
.client = c->dm_io,
@@ -1876,7 +1879,7 @@ static int __init dm_bufio_init(void)
__cache_size_refresh();
mutex_unlock(&dm_bufio_clients_lock);
- dm_bufio_wq = create_singlethread_workqueue("dm_bufio_cache");
+ dm_bufio_wq = alloc_workqueue("dm_bufio_cache", WQ_MEM_RECLAIM, 0);
if (!dm_bufio_wq)
return -ENOMEM;
diff --git a/drivers/md/dm-builtin.c b/drivers/md/dm-builtin.c
index 6c9049c51..f09277187 100644
--- a/drivers/md/dm-builtin.c
+++ b/drivers/md/dm-builtin.c
@@ -1,4 +1,4 @@
-#include "dm.h"
+#include "dm-core.h"
/*
* The kobject release method must not be placed in the module itself,
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index ee0510f9a..59b2c5056 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -788,7 +788,8 @@ static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio)
spin_lock_irqsave(&cache->lock, flags);
if (cache->need_tick_bio &&
- !(bio->bi_rw & (REQ_FUA | REQ_FLUSH | REQ_DISCARD))) {
+ !(bio->bi_opf & (REQ_FUA | REQ_PREFLUSH)) &&
+ bio_op(bio) != REQ_OP_DISCARD) {
pb->tick = true;
cache->need_tick_bio = false;
}
@@ -829,7 +830,7 @@ static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio)
static int bio_triggers_commit(struct cache *cache, struct bio *bio)
{
- return bio->bi_rw & (REQ_FLUSH | REQ_FUA);
+ return bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
}
/*
@@ -851,7 +852,7 @@ static void inc_ds(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->bi_rw & REQ_DISCARD));
+ bio_op(bio) != REQ_OP_DISCARD);
}
static void accounted_begin(struct cache *cache, struct bio *bio)
@@ -1067,7 +1068,8 @@ static void dec_io_migrations(struct cache *cache)
static bool discard_or_flush(struct bio *bio)
{
- return bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD);
+ return bio_op(bio) == REQ_OP_DISCARD ||
+ bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
}
static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell)
@@ -1612,8 +1614,8 @@ static void process_flush_bio(struct cache *cache, struct bio *bio)
remap_to_cache(cache, bio, 0);
/*
- * REQ_FLUSH is not directed at any particular block so we don't
- * need to inc_ds(). REQ_FUA's are split into a write + REQ_FLUSH
+ * REQ_PREFLUSH is not directed at any particular block so we don't
+ * need to inc_ds(). REQ_FUA's are split into a write + REQ_PREFLUSH
* by dm-core.
*/
issue(cache, bio);
@@ -1978,9 +1980,9 @@ static void process_deferred_bios(struct cache *cache)
bio = bio_list_pop(&bios);
- if (bio->bi_rw & REQ_FLUSH)
+ if (bio->bi_opf & REQ_PREFLUSH)
process_flush_bio(cache, bio);
- else if (bio->bi_rw & REQ_DISCARD)
+ else if (bio_op(bio) == REQ_OP_DISCARD)
process_discard_bio(cache, &structs, bio);
else
process_bio(cache, &structs, bio);
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
new file mode 100644
index 000000000..40ceba1fe
--- /dev/null
+++ b/drivers/md/dm-core.h
@@ -0,0 +1,149 @@
+/*
+ * Internal header file _only_ for device mapper core
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the LGPL.
+ */
+
+#ifndef DM_CORE_INTERNAL_H
+#define DM_CORE_INTERNAL_H
+
+#include <linux/kthread.h>
+#include <linux/ktime.h>
+#include <linux/blk-mq.h>
+
+#include <trace/events/block.h>
+
+#include "dm.h"
+
+#define DM_RESERVED_MAX_IOS 1024
+
+struct dm_kobject_holder {
+ struct kobject kobj;
+ struct completion completion;
+};
+
+/*
+ * DM core internal structure that used directly by dm.c and dm-rq.c
+ * DM targets must _not_ deference a mapped_device to directly access its members!
+ */
+struct mapped_device {
+ struct srcu_struct io_barrier;
+ struct mutex suspend_lock;
+
+ /*
+ * The current mapping (struct dm_table *).
+ * Use dm_get_live_table{_fast} or take suspend_lock for
+ * dereference.
+ */
+ void __rcu *map;
+
+ struct list_head table_devices;
+ struct mutex table_devices_lock;
+
+ unsigned long flags;
+
+ struct request_queue *queue;
+ int numa_node_id;
+
+ unsigned type;
+ /* Protect queue and type against concurrent access. */
+ struct mutex type_lock;
+
+ atomic_t holders;
+ atomic_t open_count;
+
+ struct dm_target *immutable_target;
+ struct target_type *immutable_target_type;
+
+ struct gendisk *disk;
+ char name[16];
+
+ void *interface_ptr;
+
+ /*
+ * A list of ios that arrived while we were suspended.
+ */
+ atomic_t pending[2];
+ wait_queue_head_t wait;
+ struct work_struct work;
+ spinlock_t deferred_lock;
+ struct bio_list deferred;
+
+ /*
+ * Event handling.
+ */
+ wait_queue_head_t eventq;
+ atomic_t event_nr;
+ atomic_t uevent_seq;
+ struct list_head uevent_list;
+ spinlock_t uevent_lock; /* Protect access to uevent_list */
+
+ /* the number of internal suspends */
+ unsigned internal_suspend_count;
+
+ /*
+ * Processing queue (flush)
+ */
+ struct workqueue_struct *wq;
+
+ /*
+ * io objects are allocated from here.
+ */
+ mempool_t *io_pool;
+ mempool_t *rq_pool;
+
+ struct bio_set *bs;
+
+ /*
+ * freeze/thaw support require holding onto a super block
+ */
+ struct super_block *frozen_sb;
+
+ /* forced geometry settings */
+ struct hd_geometry geometry;
+
+ struct block_device *bdev;
+
+ /* kobject and completion */
+ struct dm_kobject_holder kobj_holder;
+
+ /* zero-length flush that will be cloned and submitted to targets */
+ struct bio flush_bio;
+
+ struct dm_stats stats;
+
+ struct kthread_worker kworker;
+ struct task_struct *kworker_task;
+
+ /* for request-based merge heuristic in dm_request_fn() */
+ unsigned seq_rq_merge_deadline_usecs;
+ int last_rq_rw;
+ sector_t last_rq_pos;
+ ktime_t last_rq_start_time;
+
+ /* for blk-mq request-based DM support */
+ struct blk_mq_tag_set *tag_set;
+ bool use_blk_mq:1;
+ bool init_tio_pdu:1;
+};
+
+void dm_init_md_queue(struct mapped_device *md);
+void dm_init_normal_md_queue(struct mapped_device *md);
+int md_in_flight(struct mapped_device *md);
+void disable_write_same(struct mapped_device *md);
+
+static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
+{
+ return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
+}
+
+unsigned __dm_get_module_param(unsigned *module_param, unsigned def, unsigned max);
+
+static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen)
+{
+ return !maxlen || strlen(result) + 1 >= maxlen;
+}
+
+#endif
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index cfe28cf66..874295757 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -181,7 +181,7 @@ struct crypt_config {
u8 key[0];
};
-#define MIN_IOS 16
+#define MIN_IOS 64
static void clone_init(struct dm_crypt_io *, struct bio *);
static void kcryptd_queue_crypt(struct dm_crypt_io *io);
@@ -683,7 +683,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
u8 *data)
{
struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
- u64 sector = cpu_to_le64((u64)dmreq->iv_sector);
+ __le64 sector = cpu_to_le64(dmreq->iv_sector);
u8 buf[TCW_WHITENING_SIZE];
SHASH_DESC_ON_STACK(desc, tcw->crc32_tfm);
int i, r;
@@ -722,7 +722,7 @@ static int crypt_iv_tcw_gen(struct crypt_config *cc, u8 *iv,
struct dm_crypt_request *dmreq)
{
struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
- u64 sector = cpu_to_le64((u64)dmreq->iv_sector);
+ __le64 sector = cpu_to_le64(dmreq->iv_sector);
u8 *src;
int r = 0;
@@ -1136,7 +1136,7 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone)
clone->bi_private = io;
clone->bi_end_io = crypt_endio;
clone->bi_bdev = cc->dev->bdev;
- clone->bi_rw = io->base_bio->bi_rw;
+ bio_set_op_attrs(clone, bio_op(io->base_bio), io->base_bio->bi_opf);
}
static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
@@ -1911,11 +1911,12 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
struct crypt_config *cc = ti->private;
/*
- * If bio is REQ_FLUSH or REQ_DISCARD, just bypass crypt queues.
- * - for REQ_FLUSH device-mapper core ensures that no IO is in-flight
- * - for REQ_DISCARD caller must use flush if IO ordering matters
+ * If bio is REQ_PREFLUSH or REQ_OP_DISCARD, just bypass crypt queues.
+ * - for REQ_PREFLUSH device-mapper core ensures that no IO is in-flight
+ * - for REQ_OP_DISCARD caller must use flush if IO ordering matters
*/
- if (unlikely(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))) {
+ if (unlikely(bio->bi_opf & REQ_PREFLUSH ||
+ bio_op(bio) == REQ_OP_DISCARD)) {
bio->bi_bdev = cc->dev->bdev;
if (bio_sectors(bio))
bio->bi_iter.bi_sector = cc->start +
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index 665bf3285..bf2b2676c 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1540,9 +1540,9 @@ static int era_map(struct dm_target *ti, struct bio *bio)
remap_to_origin(era, bio);
/*
- * REQ_FLUSH bios carry no data, so we're not interested in them.
+ * REQ_PREFLUSH bios carry no data, so we're not interested in them.
*/
- if (!(bio->bi_rw & REQ_FLUSH) &&
+ if (!(bio->bi_opf & REQ_PREFLUSH) &&
(bio_data_dir(bio) == WRITE) &&
!metadata_current_marked(era->md, block)) {
defer_bio(era, bio);
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 4eb5c67b1..6a2e8dd44 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -16,7 +16,7 @@
#define DM_MSG_PREFIX "flakey"
#define all_corrupt_bio_flags_match(bio, fc) \
- (((bio)->bi_rw & (fc)->corrupt_bio_flags) == (fc)->corrupt_bio_flags)
+ (((bio)->bi_opf & (fc)->corrupt_bio_flags) == (fc)->corrupt_bio_flags)
/*
* Flakey: Used for testing only, simulates intermittent,
@@ -266,9 +266,9 @@ static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
data[fc->corrupt_bio_byte - 1] = fc->corrupt_bio_value;
DMDEBUG("Corrupting data bio=%p by writing %u to byte %u "
- "(rw=%c bi_rw=%lu bi_sector=%llu cur_bytes=%u)\n",
+ "(rw=%c bi_opf=%u bi_sector=%llu cur_bytes=%u)\n",
bio, fc->corrupt_bio_value, fc->corrupt_bio_byte,
- (bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_rw,
+ (bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_opf,
(unsigned long long)bio->bi_iter.bi_sector, bio_bytes);
}
}
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 06d426eb5..0bf1a12e3 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -5,7 +5,7 @@
* This file is released under the GPL.
*/
-#include "dm.h"
+#include "dm-core.h"
#include <linux/device-mapper.h>
@@ -278,8 +278,9 @@ static void km_dp_init(struct dpages *dp, void *data)
/*-----------------------------------------------------------------
* IO routines that accept a list of pages.
*---------------------------------------------------------------*/
-static void do_region(int rw, unsigned region, struct dm_io_region *where,
- struct dpages *dp, struct io *io)
+static void do_region(int op, int op_flags, unsigned region,
+ struct dm_io_region *where, struct dpages *dp,
+ struct io *io)
{
struct bio *bio;
struct page *page;
@@ -295,24 +296,25 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
/*
* Reject unsupported discard and write same requests.
*/
- if (rw & REQ_DISCARD)
+ if (op == REQ_OP_DISCARD)
special_cmd_max_sectors = q->limits.max_discard_sectors;
- else if (rw & REQ_WRITE_SAME)
+ else if (op == REQ_OP_WRITE_SAME)
special_cmd_max_sectors = q->limits.max_write_same_sectors;
- if ((rw & (REQ_DISCARD | REQ_WRITE_SAME)) && special_cmd_max_sectors == 0) {
+ if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_SAME) &&
+ special_cmd_max_sectors == 0) {
dec_count(io, region, -EOPNOTSUPP);
return;
}
/*
- * where->count may be zero if rw holds a flush and we need to
+ * where->count may be zero if op holds a flush and we need to
* send a zero-sized flush.
*/
do {
/*
* Allocate a suitably sized-bio.
*/
- if ((rw & REQ_DISCARD) || (rw & REQ_WRITE_SAME))
+ if ((op == REQ_OP_DISCARD) || (op == REQ_OP_WRITE_SAME))
num_bvecs = 1;
else
num_bvecs = min_t(int, BIO_MAX_PAGES,
@@ -322,13 +324,14 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
bio->bi_bdev = where->bdev;
bio->bi_end_io = endio;
+ bio_set_op_attrs(bio, op, op_flags);
store_io_and_region_in_bio(bio, io, region);
- if (rw & REQ_DISCARD) {
+ if (op == REQ_OP_DISCARD) {
num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
remaining -= num_sectors;
- } else if (rw & REQ_WRITE_SAME) {
+ } else if (op == REQ_OP_WRITE_SAME) {
/*
* WRITE SAME only uses a single page.
*/
@@ -355,11 +358,11 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
}
atomic_inc(&io->count);
- submit_bio(rw, bio);
+ submit_bio(bio);
} while (remaining);
}
-static void dispatch_io(int rw, unsigned int num_regions,
+static void dispatch_io(int op, int op_flags, unsigned int num_regions,
struct dm_io_region *where, struct dpages *dp,
struct io *io, int sync)
{
@@ -369,7 +372,7 @@ static void dispatch_io(int rw, unsigned int num_regions,
BUG_ON(num_regions > DM_IO_MAX_REGIONS);
if (sync)
- rw |= REQ_SYNC;
+ op_flags |= REQ_SYNC;
/*
* For multiple regions we need to be careful to rewind
@@ -377,8 +380,8 @@ static void dispatch_io(int rw, unsigned int num_regions,
*/
for (i = 0; i < num_regions; i++) {
*dp = old_pages;
- if (where[i].count || (rw & REQ_FLUSH))
- do_region(rw, i, where + i, dp, io);
+ if (where[i].count || (op_flags & REQ_PREFLUSH))
+ do_region(op, op_flags, i, where + i, dp, io);
}
/*
@@ -402,13 +405,13 @@ static void sync_io_complete(unsigned long error, void *context)
}
static int sync_io(struct dm_io_client *client, unsigned int num_regions,
- struct dm_io_region *where, int rw, struct dpages *dp,
- unsigned long *error_bits)
+ struct dm_io_region *where, int op, int op_flags,
+ struct dpages *dp, unsigned long *error_bits)
{
struct io *io;
struct sync_io sio;
- if (num_regions > 1 && (rw & RW_MASK) != WRITE) {
+ if (num_regions > 1 && !op_is_write(op)) {
WARN_ON(1);
return -EIO;
}
@@ -425,7 +428,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
io->vma_invalidate_address = dp->vma_invalidate_address;
io->vma_invalidate_size = dp->vma_invalidate_size;
- dispatch_io(rw, num_regions, where, dp, io, 1);
+ dispatch_io(op, op_flags, num_regions, where, dp, io, 1);
wait_for_completion_io(&sio.wait);
@@ -436,12 +439,12 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
}
static int async_io(struct dm_io_client *client, unsigned int num_regions,
- struct dm_io_region *where, int rw, struct dpages *dp,
- io_notify_fn fn, void *context)
+ struct dm_io_region *where, int op, int op_flags,
+ struct dpages *dp, io_notify_fn fn, void *context)
{
struct io *io;
- if (num_regions > 1 && (rw & RW_MASK) != WRITE) {
+ if (num_regions > 1 && !op_is_write(op)) {
WARN_ON(1);
fn(1, context);
return -EIO;
@@ -457,7 +460,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
io->vma_invalidate_address = dp->vma_invalidate_address;
io->vma_invalidate_size = dp->vma_invalidate_size;
- dispatch_io(rw, num_regions, where, dp, io, 0);
+ dispatch_io(op, op_flags, num_regions, where, dp, io, 0);
return 0;
}
@@ -480,7 +483,7 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp,
case DM_IO_VMA:
flush_kernel_vmap_range(io_req->mem.ptr.vma, size);
- if ((io_req->bi_rw & RW_MASK) == READ) {
+ if (io_req->bi_op == REQ_OP_READ) {
dp->vma_invalidate_address = io_req->mem.ptr.vma;
dp->vma_invalidate_size = size;
}
@@ -502,9 +505,9 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp,
* New collapsed (a)synchronous interface.
*
* If the IO is asynchronous (i.e. it has notify.fn), you must either unplug
- * the queue with blk_unplug() some time later or set REQ_SYNC in io_req->bi_rw.
- * If you fail to do one of these, the IO will be submitted to the disk after
- * q->unplug_delay, which defaults to 3ms in blk-settings.c.
+ * the queue with blk_unplug() some time later or set REQ_SYNC in
+ * io_req->bi_opf. If you fail to do one of these, the IO will be submitted to
+ * the disk after q->unplug_delay, which defaults to 3ms in blk-settings.c.
*/
int dm_io(struct dm_io_request *io_req, unsigned num_regions,
struct dm_io_region *where, unsigned long *sync_error_bits)
@@ -518,10 +521,12 @@ int dm_io(struct dm_io_request *io_req, unsigned num_regions,
if (!io_req->notify.fn)
return sync_io(io_req->client, num_regions, where,
- io_req->bi_rw, &dp, sync_error_bits);
+ io_req->bi_op, io_req->bi_op_flags, &dp,
+ sync_error_bits);
- return async_io(io_req->client, num_regions, where, io_req->bi_rw,
- &dp, io_req->notify.fn, io_req->notify.context);
+ return async_io(io_req->client, num_regions, where, io_req->bi_op,
+ io_req->bi_op_flags, &dp, io_req->notify.fn,
+ io_req->notify.context);
}
EXPORT_SYMBOL(dm_io);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 2c7ca258c..966eb4b61 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -5,7 +5,7 @@
* This file is released under the GPL.
*/
-#include "dm.h"
+#include "dm-core.h"
#include <linux/module.h>
#include <linux/vmalloc.h>
@@ -1267,6 +1267,15 @@ static int populate_table(struct dm_table *table,
return dm_table_complete(table);
}
+static bool is_valid_type(unsigned cur, unsigned new)
+{
+ if (cur == new ||
+ (cur == DM_TYPE_BIO_BASED && new == DM_TYPE_DAX_BIO_BASED))
+ return true;
+
+ return false;
+}
+
static int table_load(struct dm_ioctl *param, size_t param_size)
{
int r;
@@ -1309,7 +1318,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
DMWARN("unable to set up device queue for new table.");
goto err_unlock_md_type;
}
- } else if (dm_get_md_type(md) != dm_table_get_type(t)) {
+ } else if (!is_valid_type(dm_get_md_type(md), dm_table_get_type(t))) {
DMWARN("can't change device type after initial table load.");
r = -EINVAL;
goto err_unlock_md_type;
@@ -1670,8 +1679,7 @@ static int check_version(unsigned int cmd, struct dm_ioctl __user *user)
return r;
}
-#define DM_PARAMS_KMALLOC 0x0001 /* Params alloced with kmalloc */
-#define DM_PARAMS_VMALLOC 0x0002 /* Params alloced with vmalloc */
+#define DM_PARAMS_MALLOC 0x0001 /* Params allocated with kvmalloc() */
#define DM_WIPE_BUFFER 0x0010 /* Wipe input buffer before returning from ioctl */
static void free_params(struct dm_ioctl *param, size_t param_size, int param_flags)
@@ -1679,10 +1687,8 @@ static void free_params(struct dm_ioctl *param, size_t param_size, int param_fla
if (param_flags & DM_WIPE_BUFFER)
memset(param, 0, param_size);
- if (param_flags & DM_PARAMS_KMALLOC)
- kfree(param);
- if (param_flags & DM_PARAMS_VMALLOC)
- vfree(param);
+ if (param_flags & DM_PARAMS_MALLOC)
+ kvfree(param);
}
static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kernel,
@@ -1714,19 +1720,14 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
* Use kmalloc() rather than vmalloc() when we can.
*/
dmi = NULL;
- if (param_kernel->data_size <= KMALLOC_MAX_SIZE) {
+ if (param_kernel->data_size <= KMALLOC_MAX_SIZE)
dmi = kmalloc(param_kernel->data_size, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
- if (dmi)
- *param_flags |= DM_PARAMS_KMALLOC;
- }
if (!dmi) {
unsigned noio_flag;
noio_flag = memalloc_noio_save();
dmi = __vmalloc(param_kernel->data_size, GFP_NOIO | __GFP_HIGH | __GFP_HIGHMEM, PAGE_KERNEL);
memalloc_noio_restore(noio_flag);
- if (dmi)
- *param_flags |= DM_PARAMS_VMALLOC;
}
if (!dmi) {
@@ -1735,6 +1736,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
return -ENOMEM;
}
+ *param_flags |= DM_PARAMS_MALLOC;
+
if (copy_from_user(dmi, user, param_kernel->data_size))
goto bad;
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 1452ed9aa..9e9d04cb7 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -26,7 +26,7 @@
#include <linux/device-mapper.h>
#include <linux/dm-kcopyd.h>
-#include "dm.h"
+#include "dm-core.h"
#define SUB_JOB_SIZE 128
#define SPLIT_COUNT 8
@@ -465,7 +465,7 @@ static void complete_io(unsigned long error, void *context)
io_job_finish(kc->throttle);
if (error) {
- if (job->rw & WRITE)
+ if (op_is_write(job->rw))
job->write_err |= error;
else
job->read_err = 1;
@@ -477,7 +477,7 @@ static void complete_io(unsigned long error, void *context)
}
}
- if (job->rw & WRITE)
+ if (op_is_write(job->rw))
push(&kc->complete_jobs, job);
else {
@@ -496,7 +496,8 @@ static int run_io_job(struct kcopyd_job *job)
{
int r;
struct dm_io_request io_req = {
- .bi_rw = job->rw,
+ .bi_op = job->rw,
+ .bi_op_flags = 0,
.mem.type = DM_IO_PAGE_LIST,
.mem.ptr.pl = job->pages,
.mem.offset = 0,
@@ -550,7 +551,7 @@ static int process_jobs(struct list_head *jobs, struct dm_kcopyd_client *kc,
if (r < 0) {
/* error this rogue job */
- if (job->rw & WRITE)
+ if (op_is_write(job->rw))
job->write_err = (unsigned long) -1L;
else
job->read_err = 1;
@@ -734,7 +735,7 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
/*
* Use WRITE SAME to optimize zeroing if all dests support it.
*/
- job->rw = WRITE | REQ_WRITE_SAME;
+ job->rw = REQ_OP_WRITE_SAME;
for (i = 0; i < job->num_dests; i++)
if (!bdev_write_same(job->dests[i].bdev)) {
job->rw = WRITE;
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 05c35aacb..4788b0b98 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -141,9 +141,27 @@ static int linear_iterate_devices(struct dm_target *ti,
return fn(ti, lc->dev, lc->start, ti->len, data);
}
+static long linear_direct_access(struct dm_target *ti, sector_t sector,
+ void **kaddr, pfn_t *pfn, long size)
+{
+ struct linear_c *lc = ti->private;
+ struct block_device *bdev = lc->dev->bdev;
+ struct blk_dax_ctl dax = {
+ .sector = linear_map_sector(ti, sector),
+ .size = size,
+ };
+ long ret;
+
+ ret = bdev_direct_access(bdev, &dax);
+ *kaddr = dax.addr;
+ *pfn = dax.pfn;
+
+ return ret;
+}
+
static struct target_type linear_target = {
.name = "linear",
- .version = {1, 2, 1},
+ .version = {1, 3, 0},
.module = THIS_MODULE,
.ctr = linear_ctr,
.dtr = linear_dtr,
@@ -151,6 +169,7 @@ static struct target_type linear_target = {
.status = linear_status,
.prepare_ioctl = linear_prepare_ioctl,
.iterate_devices = linear_iterate_devices,
+ .direct_access = linear_direct_access,
};
int __init dm_linear_init(void)
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index d8f8cc85f..49e4d8d45 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -205,6 +205,7 @@ static int write_metadata(struct log_writes_c *lc, void *entry,
bio->bi_bdev = lc->logdev->bdev;
bio->bi_end_io = log_end_io;
bio->bi_private = lc;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
page = alloc_page(GFP_KERNEL);
if (!page) {
@@ -226,7 +227,7 @@ static int write_metadata(struct log_writes_c *lc, void *entry,
DMERR("Couldn't add page to the log block");
goto error_bio;
}
- submit_bio(WRITE, bio);
+ submit_bio(bio);
return 0;
error_bio:
bio_put(bio);
@@ -259,7 +260,7 @@ static int log_one_block(struct log_writes_c *lc,
sector++;
atomic_inc(&lc->io_blocks);
- bio = bio_alloc(GFP_KERNEL, block->vec_cnt);
+ bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt, BIO_MAX_PAGES));
if (!bio) {
DMERR("Couldn't alloc log bio");
goto error;
@@ -269,6 +270,7 @@ static int log_one_block(struct log_writes_c *lc,
bio->bi_bdev = lc->logdev->bdev;
bio->bi_end_io = log_end_io;
bio->bi_private = lc;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
for (i = 0; i < block->vec_cnt; i++) {
/*
@@ -279,8 +281,8 @@ static int log_one_block(struct log_writes_c *lc,
block->vecs[i].bv_len, 0);
if (ret != block->vecs[i].bv_len) {
atomic_inc(&lc->io_blocks);
- submit_bio(WRITE, bio);
- bio = bio_alloc(GFP_KERNEL, block->vec_cnt - i);
+ submit_bio(bio);
+ bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt - i, BIO_MAX_PAGES));
if (!bio) {
DMERR("Couldn't alloc log bio");
goto error;
@@ -290,6 +292,7 @@ static int log_one_block(struct log_writes_c *lc,
bio->bi_bdev = lc->logdev->bdev;
bio->bi_end_io = log_end_io;
bio->bi_private = lc;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
ret = bio_add_page(bio, block->vecs[i].bv_page,
block->vecs[i].bv_len, 0);
@@ -301,7 +304,7 @@ static int log_one_block(struct log_writes_c *lc,
}
sector += block->vecs[i].bv_len >> SECTOR_SHIFT;
}
- submit_bio(WRITE, bio);
+ submit_bio(bio);
out:
kfree(block->data);
kfree(block);
@@ -552,9 +555,9 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
struct bio_vec bv;
size_t alloc_size;
int i = 0;
- bool flush_bio = (bio->bi_rw & REQ_FLUSH);
- bool fua_bio = (bio->bi_rw & REQ_FUA);
- bool discard_bio = (bio->bi_rw & REQ_DISCARD);
+ bool flush_bio = (bio->bi_opf & REQ_PREFLUSH);
+ bool fua_bio = (bio->bi_opf & REQ_FUA);
+ bool discard_bio = (bio_op(bio) == REQ_OP_DISCARD);
pb->block = NULL;
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 627d19186..07fc1ad42 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -291,9 +291,10 @@ static void header_from_disk(struct log_header_core *core, struct log_header_dis
core->nr_regions = le64_to_cpu(disk->nr_regions);
}
-static int rw_header(struct log_c *lc, int rw)
+static int rw_header(struct log_c *lc, int op)
{
- lc->io_req.bi_rw = rw;
+ lc->io_req.bi_op = op;
+ lc->io_req.bi_op_flags = 0;
return dm_io(&lc->io_req, 1, &lc->header_location, NULL);
}
@@ -306,7 +307,8 @@ static int flush_header(struct log_c *lc)
.count = 0,
};
- lc->io_req.bi_rw = WRITE_FLUSH;
+ lc->io_req.bi_op = REQ_OP_WRITE;
+ lc->io_req.bi_op_flags = WRITE_FLUSH;
return dm_io(&lc->io_req, 1, &null_location, NULL);
}
@@ -315,7 +317,7 @@ static int read_header(struct log_c *log)
{
int r;
- r = rw_header(log, READ);
+ r = rw_header(log, REQ_OP_READ);
if (r)
return r;
@@ -629,7 +631,7 @@ static int disk_resume(struct dm_dirty_log *log)
header_to_disk(&lc->header, lc->disk_header);
/* write the new header */
- r = rw_header(lc, WRITE);
+ r = rw_header(lc, REQ_OP_WRITE);
if (!r) {
r = flush_header(lc);
if (r)
@@ -697,7 +699,7 @@ static int disk_flush(struct dm_dirty_log *log)
log_clear_bit(lc, lc->clean_bits, i);
}
- r = rw_header(lc, WRITE);
+ r = rw_header(lc, REQ_OP_WRITE);
if (r)
fail_log_device(lc);
else {
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 52baf8a5b..ac734e5bb 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -7,7 +7,8 @@
#include <linux/device-mapper.h>
-#include "dm.h"
+#include "dm-rq.h"
+#include "dm-bio-record.h"
#include "dm-path-selector.h"
#include "dm-uevent.h"
@@ -89,6 +90,8 @@ struct multipath {
atomic_t pg_init_in_progress; /* Only one pg_init allowed at once */
atomic_t pg_init_count; /* Number of times pg_init called */
+ unsigned queue_mode;
+
/*
* We must use a mempool of dm_mpath_io structs so that we
* can resubmit bios on error.
@@ -97,10 +100,13 @@ struct multipath {
struct mutex work_mutex;
struct work_struct trigger_event;
+
+ struct work_struct process_queued_bios;
+ struct bio_list queued_bios;
};
/*
- * Context information attached to each bio we process.
+ * Context information attached to each io we process.
*/
struct dm_mpath_io {
struct pgpath *pgpath;
@@ -114,6 +120,7 @@ static struct kmem_cache *_mpio_cache;
static struct workqueue_struct *kmultipathd, *kmpath_handlerd;
static void trigger_event(struct work_struct *work);
static void activate_path(struct work_struct *work);
+static void process_queued_bios(struct work_struct *work);
/*-----------------------------------------------
* Multipath state flags.
@@ -185,7 +192,7 @@ static void free_priority_group(struct priority_group *pg,
kfree(pg);
}
-static struct multipath *alloc_multipath(struct dm_target *ti, bool use_blk_mq)
+static struct multipath *alloc_multipath(struct dm_target *ti)
{
struct multipath *m;
@@ -203,15 +210,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti, bool use_blk_mq)
mutex_init(&m->work_mutex);
m->mpio_pool = NULL;
- if (!use_blk_mq) {
- unsigned min_ios = dm_get_reserved_rq_based_ios();
-
- m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
- if (!m->mpio_pool) {
- kfree(m);
- return NULL;
- }
- }
+ m->queue_mode = DM_TYPE_NONE;
m->ti = ti;
ti->private = m;
@@ -220,6 +219,39 @@ static struct multipath *alloc_multipath(struct dm_target *ti, bool use_blk_mq)
return m;
}
+static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m)
+{
+ if (m->queue_mode == DM_TYPE_NONE) {
+ /*
+ * Default to request-based.
+ */
+ if (dm_use_blk_mq(dm_table_get_md(ti->table)))
+ m->queue_mode = DM_TYPE_MQ_REQUEST_BASED;
+ else
+ m->queue_mode = DM_TYPE_REQUEST_BASED;
+ }
+
+ if (m->queue_mode == DM_TYPE_REQUEST_BASED) {
+ unsigned min_ios = dm_get_reserved_rq_based_ios();
+
+ m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
+ if (!m->mpio_pool)
+ return -ENOMEM;
+ }
+ else if (m->queue_mode == DM_TYPE_BIO_BASED) {
+ INIT_WORK(&m->process_queued_bios, process_queued_bios);
+ /*
+ * bio-based doesn't support any direct scsi_dh management;
+ * it just discovers if a scsi_dh is attached.
+ */
+ set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags);
+ }
+
+ dm_table_set_type(ti->table, m->queue_mode);
+
+ return 0;
+}
+
static void free_multipath(struct multipath *m)
{
struct priority_group *pg, *tmp;
@@ -272,6 +304,41 @@ static void clear_request_fn_mpio(struct multipath *m, union map_info *info)
}
}
+static size_t multipath_per_bio_data_size(void)
+{
+ return sizeof(struct dm_mpath_io) + sizeof(struct dm_bio_details);
+}
+
+static struct dm_mpath_io *get_mpio_from_bio(struct bio *bio)
+{
+ return dm_per_bio_data(bio, multipath_per_bio_data_size());
+}
+
+static struct dm_bio_details *get_bio_details_from_bio(struct bio *bio)
+{
+ /* dm_bio_details is immediately after the dm_mpath_io in bio's per-bio-data */
+ struct dm_mpath_io *mpio = get_mpio_from_bio(bio);
+ void *bio_details = mpio + 1;
+
+ return bio_details;
+}
+
+static void multipath_init_per_bio_data(struct bio *bio, struct dm_mpath_io **mpio_p,
+ struct dm_bio_details **bio_details_p)
+{
+ struct dm_mpath_io *mpio = get_mpio_from_bio(bio);
+ struct dm_bio_details *bio_details = get_bio_details_from_bio(bio);
+
+ memset(mpio, 0, sizeof(*mpio));
+ memset(bio_details, 0, sizeof(*bio_details));
+ dm_bio_record(bio_details, bio);
+
+ if (mpio_p)
+ *mpio_p = mpio;
+ if (bio_details_p)
+ *bio_details_p = bio_details;
+}
+
/*-----------------------------------------------
* Path selection
*-----------------------------------------------*/
@@ -431,16 +498,40 @@ failed:
* and multipath_resume() calls and we have no need to check
* for the DMF_NOFLUSH_SUSPENDING flag.
*/
-static int must_push_back(struct multipath *m)
+static bool __must_push_back(struct multipath *m)
{
- return (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) ||
- ((test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) !=
- test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags)) &&
- dm_noflush_suspending(m->ti)));
+ return ((test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) !=
+ test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags)) &&
+ dm_noflush_suspending(m->ti));
+}
+
+static bool must_push_back_rq(struct multipath *m)
+{
+ bool r;
+ unsigned long flags;
+
+ spin_lock_irqsave(&m->lock, flags);
+ r = (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) ||
+ __must_push_back(m));
+ spin_unlock_irqrestore(&m->lock, flags);
+
+ return r;
+}
+
+static bool must_push_back_bio(struct multipath *m)
+{
+ bool r;
+ unsigned long flags;
+
+ spin_lock_irqsave(&m->lock, flags);
+ r = __must_push_back(m);
+ spin_unlock_irqrestore(&m->lock, flags);
+
+ return r;
}
/*
- * Map cloned requests
+ * Map cloned requests (request-based multipath)
*/
static int __multipath_map(struct dm_target *ti, struct request *clone,
union map_info *map_context,
@@ -459,7 +550,7 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
pgpath = choose_pgpath(m, nr_bytes);
if (!pgpath) {
- if (!must_push_back(m))
+ if (!must_push_back_rq(m))
r = -EIO; /* Failed */
return r;
} else if (test_bit(MPATHF_QUEUE_IO, &m->flags) ||
@@ -530,6 +621,108 @@ static void multipath_release_clone(struct request *clone)
}
/*
+ * Map cloned bios (bio-based multipath)
+ */
+static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_mpath_io *mpio)
+{
+ size_t nr_bytes = bio->bi_iter.bi_size;
+ struct pgpath *pgpath;
+ unsigned long flags;
+ bool queue_io;
+
+ /* Do we need to select a new pgpath? */
+ pgpath = lockless_dereference(m->current_pgpath);
+ queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags);
+ if (!pgpath || !queue_io)
+ pgpath = choose_pgpath(m, nr_bytes);
+
+ if ((pgpath && queue_io) ||
+ (!pgpath && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))) {
+ /* Queue for the daemon to resubmit */
+ spin_lock_irqsave(&m->lock, flags);
+ bio_list_add(&m->queued_bios, bio);
+ spin_unlock_irqrestore(&m->lock, flags);
+ /* PG_INIT_REQUIRED cannot be set without QUEUE_IO */
+ if (queue_io || test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags))
+ pg_init_all_paths(m);
+ else if (!queue_io)
+ queue_work(kmultipathd, &m->process_queued_bios);
+ return DM_MAPIO_SUBMITTED;
+ }
+
+ if (!pgpath) {
+ if (!must_push_back_bio(m))
+ return -EIO;
+ return DM_MAPIO_REQUEUE;
+ }
+
+ mpio->pgpath = pgpath;
+ mpio->nr_bytes = nr_bytes;
+
+ bio->bi_error = 0;
+ bio->bi_bdev = pgpath->path.dev->bdev;
+ bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
+
+ if (pgpath->pg->ps.type->start_io)
+ pgpath->pg->ps.type->start_io(&pgpath->pg->ps,
+ &pgpath->path,
+ nr_bytes);
+ return DM_MAPIO_REMAPPED;
+}
+
+static int multipath_map_bio(struct dm_target *ti, struct bio *bio)
+{
+ struct multipath *m = ti->private;
+ struct dm_mpath_io *mpio = NULL;
+
+ multipath_init_per_bio_data(bio, &mpio, NULL);
+
+ return __multipath_map_bio(m, bio, mpio);
+}
+
+static void process_queued_bios_list(struct multipath *m)
+{
+ if (m->queue_mode == DM_TYPE_BIO_BASED)
+ queue_work(kmultipathd, &m->process_queued_bios);
+}
+
+static void process_queued_bios(struct work_struct *work)
+{
+ int r;
+ unsigned long flags;
+ struct bio *bio;
+ struct bio_list bios;
+ struct blk_plug plug;
+ struct multipath *m =
+ container_of(work, struct multipath, process_queued_bios);
+
+ bio_list_init(&bios);
+
+ spin_lock_irqsave(&m->lock, flags);
+
+ if (bio_list_empty(&m->queued_bios)) {
+ spin_unlock_irqrestore(&m->lock, flags);
+ return;
+ }
+
+ bio_list_merge(&bios, &m->queued_bios);
+ bio_list_init(&m->queued_bios);
+
+ spin_unlock_irqrestore(&m->lock, flags);
+
+ blk_start_plug(&plug);
+ while ((bio = bio_list_pop(&bios))) {
+ r = __multipath_map_bio(m, bio, get_mpio_from_bio(bio));
+ if (r < 0 || r == DM_MAPIO_REQUEUE) {
+ bio->bi_error = r;
+ bio_endio(bio);
+ } else if (r == DM_MAPIO_REMAPPED)
+ generic_make_request(bio);
+ }
+ blk_finish_plug(&plug);
+}
+
+/*
* If we run out of usable paths, should we queue I/O or error it?
*/
static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
@@ -557,8 +750,10 @@ static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
spin_unlock_irqrestore(&m->lock, flags);
- if (!queue_if_no_path)
+ if (!queue_if_no_path) {
dm_table_run_md_queue_async(m->ti->table);
+ process_queued_bios_list(m);
+ }
return 0;
}
@@ -798,6 +993,12 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m)
if (!hw_argc)
return 0;
+ if (m->queue_mode == DM_TYPE_BIO_BASED) {
+ dm_consume_args(as, hw_argc);
+ DMERR("bio-based multipath doesn't allow hardware handler args");
+ return 0;
+ }
+
m->hw_handler_name = kstrdup(dm_shift_arg(as), GFP_KERNEL);
if (hw_argc > 1) {
@@ -833,7 +1034,7 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m)
const char *arg_name;
static struct dm_arg _args[] = {
- {0, 6, "invalid number of feature args"},
+ {0, 8, "invalid number of feature args"},
{1, 50, "pg_init_retries must be between 1 and 50"},
{0, 60000, "pg_init_delay_msecs must be between 0 and 60000"},
};
@@ -873,6 +1074,24 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m)
continue;
}
+ if (!strcasecmp(arg_name, "queue_mode") &&
+ (argc >= 1)) {
+ const char *queue_mode_name = dm_shift_arg(as);
+
+ if (!strcasecmp(queue_mode_name, "bio"))
+ m->queue_mode = DM_TYPE_BIO_BASED;
+ else if (!strcasecmp(queue_mode_name, "rq"))
+ m->queue_mode = DM_TYPE_REQUEST_BASED;
+ else if (!strcasecmp(queue_mode_name, "mq"))
+ m->queue_mode = DM_TYPE_MQ_REQUEST_BASED;
+ else {
+ ti->error = "Unknown 'queue_mode' requested";
+ r = -EINVAL;
+ }
+ argc--;
+ continue;
+ }
+
ti->error = "Unrecognised multipath feature request";
r = -EINVAL;
} while (argc && !r);
@@ -880,8 +1099,7 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m)
return r;
}
-static int multipath_ctr(struct dm_target *ti, unsigned int argc,
- char **argv)
+static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
{
/* target arguments */
static struct dm_arg _args[] = {
@@ -894,12 +1112,11 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
struct dm_arg_set as;
unsigned pg_count = 0;
unsigned next_pg_num;
- bool use_blk_mq = dm_use_blk_mq(dm_table_get_md(ti->table));
as.argc = argc;
as.argv = argv;
- m = alloc_multipath(ti, use_blk_mq);
+ m = alloc_multipath(ti);
if (!m) {
ti->error = "can't allocate multipath";
return -EINVAL;
@@ -909,6 +1126,10 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
if (r)
goto bad;
+ r = alloc_multipath_stage2(ti, m);
+ if (r)
+ goto bad;
+
r = parse_hw_handler(&as, m);
if (r)
goto bad;
@@ -958,7 +1179,9 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->num_write_same_bios = 1;
- if (use_blk_mq)
+ if (m->queue_mode == DM_TYPE_BIO_BASED)
+ ti->per_io_data_size = multipath_per_bio_data_size();
+ else if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED)
ti->per_io_data_size = sizeof(struct dm_mpath_io);
return 0;
@@ -1083,8 +1306,10 @@ static int reinstate_path(struct pgpath *pgpath)
out:
spin_unlock_irqrestore(&m->lock, flags);
- if (run_queue)
+ if (run_queue) {
dm_table_run_md_queue_async(m->ti->table);
+ process_queued_bios_list(m);
+ }
return r;
}
@@ -1281,6 +1506,8 @@ static void pg_init_done(void *data, int errors)
}
clear_bit(MPATHF_QUEUE_IO, &m->flags);
+ process_queued_bios_list(m);
+
/*
* Wake up any thread waiting to suspend.
*/
@@ -1328,7 +1555,7 @@ static int do_end_io(struct multipath *m, struct request *clone,
* during end I/O handling, since those clone requests don't have
* bio clones. If we queue them inside the multipath target,
* we need to make bio clones, that requires memory allocation.
- * (See drivers/md/dm.c:end_clone_bio() about why the clone requests
+ * (See drivers/md/dm-rq.c:end_clone_bio() about why the clone requests
* don't have bio clones.)
* Instead of queueing the clone request here, we queue the original
* request into dm core, which will remake a clone request and
@@ -1347,7 +1574,7 @@ static int do_end_io(struct multipath *m, struct request *clone,
if (!atomic_read(&m->nr_valid_paths)) {
if (!test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
- if (!must_push_back(m))
+ if (!must_push_back_rq(m))
r = -EIO;
} else {
if (error == -EBADE)
@@ -1381,6 +1608,64 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
return r;
}
+static int do_end_io_bio(struct multipath *m, struct bio *clone,
+ int error, struct dm_mpath_io *mpio)
+{
+ unsigned long flags;
+
+ if (!error)
+ return 0; /* I/O complete */
+
+ if (noretry_error(error))
+ return error;
+
+ if (mpio->pgpath)
+ fail_path(mpio->pgpath);
+
+ if (!atomic_read(&m->nr_valid_paths)) {
+ if (!test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
+ if (!must_push_back_bio(m))
+ return -EIO;
+ return DM_ENDIO_REQUEUE;
+ } else {
+ if (error == -EBADE)
+ return error;
+ }
+ }
+
+ /* Queue for the daemon to resubmit */
+ dm_bio_restore(get_bio_details_from_bio(clone), clone);
+
+ spin_lock_irqsave(&m->lock, flags);
+ bio_list_add(&m->queued_bios, clone);
+ spin_unlock_irqrestore(&m->lock, flags);
+ if (!test_bit(MPATHF_QUEUE_IO, &m->flags))
+ queue_work(kmultipathd, &m->process_queued_bios);
+
+ return DM_ENDIO_INCOMPLETE;
+}
+
+static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone, int error)
+{
+ struct multipath *m = ti->private;
+ struct dm_mpath_io *mpio = get_mpio_from_bio(clone);
+ struct pgpath *pgpath;
+ struct path_selector *ps;
+ int r;
+
+ BUG_ON(!mpio);
+
+ r = do_end_io_bio(m, clone, error, mpio);
+ pgpath = mpio->pgpath;
+ if (pgpath) {
+ ps = &pgpath->pg->ps;
+ if (ps->type->end_io)
+ ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
+ }
+
+ return r;
+}
+
/*
* Suspend can't complete until all the I/O is processed so if
* the last path fails we must error any remaining I/O.
@@ -1409,12 +1694,14 @@ static void multipath_postsuspend(struct dm_target *ti)
static void multipath_resume(struct dm_target *ti)
{
struct multipath *m = ti->private;
+ unsigned long flags;
+ spin_lock_irqsave(&m->lock, flags);
if (test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags))
set_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags);
else
clear_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags);
- smp_mb__after_atomic();
+ spin_unlock_irqrestore(&m->lock, flags);
}
/*
@@ -1454,7 +1741,9 @@ static void multipath_status(struct dm_target *ti, status_type_t type,
DMEMIT("%u ", test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) +
(m->pg_init_retries > 0) * 2 +
(m->pg_init_delay_msecs != DM_PG_INIT_DELAY_DEFAULT) * 2 +
- test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags));
+ test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags) +
+ (m->queue_mode != DM_TYPE_REQUEST_BASED) * 2);
+
if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
DMEMIT("queue_if_no_path ");
if (m->pg_init_retries)
@@ -1463,6 +1752,16 @@ static void multipath_status(struct dm_target *ti, status_type_t type,
DMEMIT("pg_init_delay_msecs %u ", m->pg_init_delay_msecs);
if (test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags))
DMEMIT("retain_attached_hw_handler ");
+ if (m->queue_mode != DM_TYPE_REQUEST_BASED) {
+ switch(m->queue_mode) {
+ case DM_TYPE_BIO_BASED:
+ DMEMIT("queue_mode bio ");
+ break;
+ case DM_TYPE_MQ_REQUEST_BASED:
+ DMEMIT("queue_mode mq ");
+ break;
+ }
+ }
}
if (!m->hw_handler_name || type == STATUSTYPE_INFO)
@@ -1642,6 +1941,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
if (test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags))
pg_init_all_paths(m);
dm_table_run_md_queue_async(m->ti->table);
+ process_queued_bios_list(m);
}
/*
@@ -1748,7 +2048,7 @@ static int multipath_busy(struct dm_target *ti)
*---------------------------------------------------------------*/
static struct target_type multipath_target = {
.name = "multipath",
- .version = {1, 11, 0},
+ .version = {1, 12, 0},
.features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE,
.module = THIS_MODULE,
.ctr = multipath_ctr,
@@ -1757,6 +2057,8 @@ static struct target_type multipath_target = {
.clone_and_map_rq = multipath_clone_and_map,
.release_clone_rq = multipath_release_clone,
.rq_end_io = multipath_end_io,
+ .map = multipath_map_bio,
+ .end_io = multipath_end_io_bio,
.presuspend = multipath_presuspend,
.postsuspend = multipath_postsuspend,
.resume = multipath_resume,
@@ -1771,14 +2073,14 @@ static int __init dm_multipath_init(void)
{
int r;
- /* allocate a slab for the dm_ios */
+ /* allocate a slab for the dm_mpath_ios */
_mpio_cache = KMEM_CACHE(dm_mpath_io, 0);
if (!_mpio_cache)
return -ENOMEM;
r = dm_register_target(&multipath_target);
if (r < 0) {
- DMERR("register failed %d", r);
+ DMERR("request-based register failed %d", r);
r = -EINVAL;
goto bad_register_target;
}
@@ -1804,10 +2106,6 @@ static int __init dm_multipath_init(void)
goto bad_alloc_kmpath_handlerd;
}
- DMINFO("version %u.%u.%u loaded",
- multipath_target.version[0], multipath_target.version[1],
- multipath_target.version[2]);
-
return 0;
bad_alloc_kmpath_handlerd:
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 52532745a..8abde6b8c 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1,6 +1,6 @@
/*
* Copyright (C) 2010-2011 Neil Brown
- * Copyright (C) 2010-2015 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2010-2016 Red Hat, Inc. All rights reserved.
*
* This file is released under the GPL.
*/
@@ -17,7 +17,12 @@
#include <linux/device-mapper.h>
#define DM_MSG_PREFIX "raid"
-#define MAX_RAID_DEVICES 253 /* raid4/5/6 limit */
+#define MAX_RAID_DEVICES 253 /* md-raid kernel limit */
+
+/*
+ * Minimum sectors of free reshape space per raid device
+ */
+#define MIN_FREE_RESHAPE_SPACE to_sector(4*4096)
static bool devices_handle_discard_safely = false;
@@ -25,12 +30,12 @@ static bool devices_handle_discard_safely = false;
* The following flags are used by dm-raid.c to set up the array state.
* They must be cleared before md_run is called.
*/
-#define FirstUse 10 /* rdev flag */
+#define FirstUse 10 /* rdev flag */
struct raid_dev {
/*
* Two DM devices, one to hold metadata and one to hold the
- * actual data/parity. The reason for this is to not confuse
+ * actual data/parity. The reason for this is to not confuse
* ti->len and give more flexibility in altering size and
* characteristics.
*
@@ -46,25 +51,174 @@ struct raid_dev {
};
/*
+ * Bits for establishing rs->ctr_flags
+ *
+ * 1 = no flag value
+ * 2 = flag with value
+ */
+#define __CTR_FLAG_SYNC 0 /* 1 */ /* Not with raid0! */
+#define __CTR_FLAG_NOSYNC 1 /* 1 */ /* Not with raid0! */
+#define __CTR_FLAG_REBUILD 2 /* 2 */ /* Not with raid0! */
+#define __CTR_FLAG_DAEMON_SLEEP 3 /* 2 */ /* Not with raid0! */
+#define __CTR_FLAG_MIN_RECOVERY_RATE 4 /* 2 */ /* Not with raid0! */
+#define __CTR_FLAG_MAX_RECOVERY_RATE 5 /* 2 */ /* Not with raid0! */
+#define __CTR_FLAG_MAX_WRITE_BEHIND 6 /* 2 */ /* Only with raid1! */
+#define __CTR_FLAG_WRITE_MOSTLY 7 /* 2 */ /* Only with raid1! */
+#define __CTR_FLAG_STRIPE_CACHE 8 /* 2 */ /* Only with raid4/5/6! */
+#define __CTR_FLAG_REGION_SIZE 9 /* 2 */ /* Not with raid0! */
+#define __CTR_FLAG_RAID10_COPIES 10 /* 2 */ /* Only with raid10 */
+#define __CTR_FLAG_RAID10_FORMAT 11 /* 2 */ /* Only with raid10 */
+/* New for v1.9.0 */
+#define __CTR_FLAG_DELTA_DISKS 12 /* 2 */ /* Only with reshapable raid1/4/5/6/10! */
+#define __CTR_FLAG_DATA_OFFSET 13 /* 2 */ /* Only with reshapable raid4/5/6/10! */
+#define __CTR_FLAG_RAID10_USE_NEAR_SETS 14 /* 2 */ /* Only with raid10! */
+
+/*
* Flags for rs->ctr_flags field.
*/
-#define CTR_FLAG_SYNC 0x1
-#define CTR_FLAG_NOSYNC 0x2
-#define CTR_FLAG_REBUILD 0x4
-#define CTR_FLAG_DAEMON_SLEEP 0x8
-#define CTR_FLAG_MIN_RECOVERY_RATE 0x10
-#define CTR_FLAG_MAX_RECOVERY_RATE 0x20
-#define CTR_FLAG_MAX_WRITE_BEHIND 0x40
-#define CTR_FLAG_STRIPE_CACHE 0x80
-#define CTR_FLAG_REGION_SIZE 0x100
-#define CTR_FLAG_RAID10_COPIES 0x200
-#define CTR_FLAG_RAID10_FORMAT 0x400
+#define CTR_FLAG_SYNC (1 << __CTR_FLAG_SYNC)
+#define CTR_FLAG_NOSYNC (1 << __CTR_FLAG_NOSYNC)
+#define CTR_FLAG_REBUILD (1 << __CTR_FLAG_REBUILD)
+#define CTR_FLAG_DAEMON_SLEEP (1 << __CTR_FLAG_DAEMON_SLEEP)
+#define CTR_FLAG_MIN_RECOVERY_RATE (1 << __CTR_FLAG_MIN_RECOVERY_RATE)
+#define CTR_FLAG_MAX_RECOVERY_RATE (1 << __CTR_FLAG_MAX_RECOVERY_RATE)
+#define CTR_FLAG_MAX_WRITE_BEHIND (1 << __CTR_FLAG_MAX_WRITE_BEHIND)
+#define CTR_FLAG_WRITE_MOSTLY (1 << __CTR_FLAG_WRITE_MOSTLY)
+#define CTR_FLAG_STRIPE_CACHE (1 << __CTR_FLAG_STRIPE_CACHE)
+#define CTR_FLAG_REGION_SIZE (1 << __CTR_FLAG_REGION_SIZE)
+#define CTR_FLAG_RAID10_COPIES (1 << __CTR_FLAG_RAID10_COPIES)
+#define CTR_FLAG_RAID10_FORMAT (1 << __CTR_FLAG_RAID10_FORMAT)
+#define CTR_FLAG_DELTA_DISKS (1 << __CTR_FLAG_DELTA_DISKS)
+#define CTR_FLAG_DATA_OFFSET (1 << __CTR_FLAG_DATA_OFFSET)
+#define CTR_FLAG_RAID10_USE_NEAR_SETS (1 << __CTR_FLAG_RAID10_USE_NEAR_SETS)
+
+/*
+ * Definitions of various constructor flags to
+ * be used in checks of valid / invalid flags
+ * per raid level.
+ */
+/* Define all any sync flags */
+#define CTR_FLAGS_ANY_SYNC (CTR_FLAG_SYNC | CTR_FLAG_NOSYNC)
+
+/* Define flags for options without argument (e.g. 'nosync') */
+#define CTR_FLAG_OPTIONS_NO_ARGS (CTR_FLAGS_ANY_SYNC | \
+ CTR_FLAG_RAID10_USE_NEAR_SETS)
+
+/* Define flags for options with one argument (e.g. 'delta_disks +2') */
+#define CTR_FLAG_OPTIONS_ONE_ARG (CTR_FLAG_REBUILD | \
+ CTR_FLAG_WRITE_MOSTLY | \
+ CTR_FLAG_DAEMON_SLEEP | \
+ CTR_FLAG_MIN_RECOVERY_RATE | \
+ CTR_FLAG_MAX_RECOVERY_RATE | \
+ CTR_FLAG_MAX_WRITE_BEHIND | \
+ CTR_FLAG_STRIPE_CACHE | \
+ CTR_FLAG_REGION_SIZE | \
+ CTR_FLAG_RAID10_COPIES | \
+ CTR_FLAG_RAID10_FORMAT | \
+ CTR_FLAG_DELTA_DISKS | \
+ CTR_FLAG_DATA_OFFSET)
+
+/* Valid options definitions per raid level... */
+
+/* "raid0" does only accept data offset */
+#define RAID0_VALID_FLAGS (CTR_FLAG_DATA_OFFSET)
+
+/* "raid1" does not accept stripe cache, data offset, delta_disks or any raid10 options */
+#define RAID1_VALID_FLAGS (CTR_FLAGS_ANY_SYNC | \
+ CTR_FLAG_REBUILD | \
+ CTR_FLAG_WRITE_MOSTLY | \
+ CTR_FLAG_DAEMON_SLEEP | \
+ CTR_FLAG_MIN_RECOVERY_RATE | \
+ CTR_FLAG_MAX_RECOVERY_RATE | \
+ CTR_FLAG_MAX_WRITE_BEHIND | \
+ CTR_FLAG_REGION_SIZE | \
+ CTR_FLAG_DELTA_DISKS | \
+ CTR_FLAG_DATA_OFFSET)
+
+/* "raid10" does not accept any raid1 or stripe cache options */
+#define RAID10_VALID_FLAGS (CTR_FLAGS_ANY_SYNC | \
+ CTR_FLAG_REBUILD | \
+ CTR_FLAG_DAEMON_SLEEP | \
+ CTR_FLAG_MIN_RECOVERY_RATE | \
+ CTR_FLAG_MAX_RECOVERY_RATE | \
+ CTR_FLAG_REGION_SIZE | \
+ CTR_FLAG_RAID10_COPIES | \
+ CTR_FLAG_RAID10_FORMAT | \
+ CTR_FLAG_DELTA_DISKS | \
+ CTR_FLAG_DATA_OFFSET | \
+ CTR_FLAG_RAID10_USE_NEAR_SETS)
+
+/*
+ * "raid4/5/6" do not accept any raid1 or raid10 specific options
+ *
+ * "raid6" does not accept "nosync", because it is not guaranteed
+ * that both parity and q-syndrome are being written properly with
+ * any writes
+ */
+#define RAID45_VALID_FLAGS (CTR_FLAGS_ANY_SYNC | \
+ CTR_FLAG_REBUILD | \
+ CTR_FLAG_DAEMON_SLEEP | \
+ CTR_FLAG_MIN_RECOVERY_RATE | \
+ CTR_FLAG_MAX_RECOVERY_RATE | \
+ CTR_FLAG_MAX_WRITE_BEHIND | \
+ CTR_FLAG_STRIPE_CACHE | \
+ CTR_FLAG_REGION_SIZE | \
+ CTR_FLAG_DELTA_DISKS | \
+ CTR_FLAG_DATA_OFFSET)
+
+#define RAID6_VALID_FLAGS (CTR_FLAG_SYNC | \
+ CTR_FLAG_REBUILD | \
+ CTR_FLAG_DAEMON_SLEEP | \
+ CTR_FLAG_MIN_RECOVERY_RATE | \
+ CTR_FLAG_MAX_RECOVERY_RATE | \
+ CTR_FLAG_MAX_WRITE_BEHIND | \
+ CTR_FLAG_STRIPE_CACHE | \
+ CTR_FLAG_REGION_SIZE | \
+ CTR_FLAG_DELTA_DISKS | \
+ CTR_FLAG_DATA_OFFSET)
+/* ...valid options definitions per raid level */
+
+/*
+ * Flags for rs->runtime_flags field
+ * (RT_FLAG prefix meaning "runtime flag")
+ *
+ * These are all internal and used to define runtime state,
+ * e.g. to prevent another resume from preresume processing
+ * the raid set all over again.
+ */
+#define RT_FLAG_RS_PRERESUMED 0
+#define RT_FLAG_RS_RESUMED 1
+#define RT_FLAG_RS_BITMAP_LOADED 2
+#define RT_FLAG_UPDATE_SBS 3
+#define RT_FLAG_RESHAPE_RS 4
+
+/* Array elements of 64 bit needed for rebuild/failed disk bits */
+#define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
+
+/*
+ * raid set level, layout and chunk sectors backup/restore
+ */
+struct rs_layout {
+ int new_level;
+ int new_layout;
+ int new_chunk_sectors;
+};
struct raid_set {
struct dm_target *ti;
uint32_t bitmap_loaded;
- uint32_t ctr_flags;
+ uint32_t stripe_cache_entries;
+ unsigned long ctr_flags;
+ unsigned long runtime_flags;
+
+ uint64_t rebuild_disks[DISKS_ARRAY_ELEMS];
+
+ int raid_disks;
+ int delta_disks;
+ int data_offset;
+ int raid10_copies;
+ int requested_bitmap_chunk_sectors;
struct mddev md;
struct raid_type *raid_type;
@@ -73,82 +227,446 @@ struct raid_set {
struct raid_dev dev[0];
};
+static void rs_config_backup(struct raid_set *rs, struct rs_layout *l)
+{
+ struct mddev *mddev = &rs->md;
+
+ l->new_level = mddev->new_level;
+ l->new_layout = mddev->new_layout;
+ l->new_chunk_sectors = mddev->new_chunk_sectors;
+}
+
+static void rs_config_restore(struct raid_set *rs, struct rs_layout *l)
+{
+ struct mddev *mddev = &rs->md;
+
+ mddev->new_level = l->new_level;
+ mddev->new_layout = l->new_layout;
+ mddev->new_chunk_sectors = l->new_chunk_sectors;
+}
+
+/* raid10 algorithms (i.e. formats) */
+#define ALGORITHM_RAID10_DEFAULT 0
+#define ALGORITHM_RAID10_NEAR 1
+#define ALGORITHM_RAID10_OFFSET 2
+#define ALGORITHM_RAID10_FAR 3
+
/* Supported raid types and properties. */
static struct raid_type {
const char *name; /* RAID algorithm. */
const char *descr; /* Descriptor text for logging. */
- const unsigned parity_devs; /* # of parity devices. */
- const unsigned minimal_devs; /* minimal # of devices in set. */
- const unsigned level; /* RAID level. */
- const unsigned algorithm; /* RAID algorithm. */
+ const unsigned int parity_devs; /* # of parity devices. */
+ const unsigned int minimal_devs;/* minimal # of devices in set. */
+ const unsigned int level; /* RAID level. */
+ const unsigned int algorithm; /* RAID algorithm. */
} raid_types[] = {
- {"raid0", "RAID0 (striping)", 0, 2, 0, 0 /* NONE */},
- {"raid1", "RAID1 (mirroring)", 0, 2, 1, 0 /* NONE */},
- {"raid10", "RAID10 (striped mirrors)", 0, 2, 10, UINT_MAX /* Varies */},
- {"raid4", "RAID4 (dedicated parity disk)", 1, 2, 5, ALGORITHM_PARITY_0},
- {"raid5_la", "RAID5 (left asymmetric)", 1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC},
- {"raid5_ra", "RAID5 (right asymmetric)", 1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC},
- {"raid5_ls", "RAID5 (left symmetric)", 1, 2, 5, ALGORITHM_LEFT_SYMMETRIC},
- {"raid5_rs", "RAID5 (right symmetric)", 1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC},
- {"raid6_zr", "RAID6 (zero restart)", 2, 4, 6, ALGORITHM_ROTATING_ZERO_RESTART},
- {"raid6_nr", "RAID6 (N restart)", 2, 4, 6, ALGORITHM_ROTATING_N_RESTART},
- {"raid6_nc", "RAID6 (N continue)", 2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE}
+ {"raid0", "raid0 (striping)", 0, 2, 0, 0 /* NONE */},
+ {"raid1", "raid1 (mirroring)", 0, 2, 1, 0 /* NONE */},
+ {"raid10_far", "raid10 far (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_FAR},
+ {"raid10_offset", "raid10 offset (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_OFFSET},
+ {"raid10_near", "raid10 near (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_NEAR},
+ {"raid10", "raid10 (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_DEFAULT},
+ {"raid4", "raid4 (dedicated last parity disk)", 1, 2, 4, ALGORITHM_PARITY_N}, /* raid4 layout = raid5_n */
+ {"raid5_n", "raid5 (dedicated last parity disk)", 1, 2, 5, ALGORITHM_PARITY_N},
+ {"raid5_ls", "raid5 (left symmetric)", 1, 2, 5, ALGORITHM_LEFT_SYMMETRIC},
+ {"raid5_rs", "raid5 (right symmetric)", 1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC},
+ {"raid5_la", "raid5 (left asymmetric)", 1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC},
+ {"raid5_ra", "raid5 (right asymmetric)", 1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC},
+ {"raid6_zr", "raid6 (zero restart)", 2, 4, 6, ALGORITHM_ROTATING_ZERO_RESTART},
+ {"raid6_nr", "raid6 (N restart)", 2, 4, 6, ALGORITHM_ROTATING_N_RESTART},
+ {"raid6_nc", "raid6 (N continue)", 2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE},
+ {"raid6_n_6", "raid6 (dedicated parity/Q n/6)", 2, 4, 6, ALGORITHM_PARITY_N_6},
+ {"raid6_ls_6", "raid6 (left symmetric dedicated Q 6)", 2, 4, 6, ALGORITHM_LEFT_SYMMETRIC_6},
+ {"raid6_rs_6", "raid6 (right symmetric dedicated Q 6)", 2, 4, 6, ALGORITHM_RIGHT_SYMMETRIC_6},
+ {"raid6_la_6", "raid6 (left asymmetric dedicated Q 6)", 2, 4, 6, ALGORITHM_LEFT_ASYMMETRIC_6},
+ {"raid6_ra_6", "raid6 (right asymmetric dedicated Q 6)", 2, 4, 6, ALGORITHM_RIGHT_ASYMMETRIC_6}
+};
+
+/* True, if @v is in inclusive range [@min, @max] */
+static bool __within_range(long v, long min, long max)
+{
+ return v >= min && v <= max;
+}
+
+/* All table line arguments are defined here */
+static struct arg_name_flag {
+ const unsigned long flag;
+ const char *name;
+} __arg_name_flags[] = {
+ { CTR_FLAG_SYNC, "sync"},
+ { CTR_FLAG_NOSYNC, "nosync"},
+ { CTR_FLAG_REBUILD, "rebuild"},
+ { CTR_FLAG_DAEMON_SLEEP, "daemon_sleep"},
+ { CTR_FLAG_MIN_RECOVERY_RATE, "min_recovery_rate"},
+ { CTR_FLAG_MAX_RECOVERY_RATE, "max_recovery_rate"},
+ { CTR_FLAG_MAX_WRITE_BEHIND, "max_write_behind"},
+ { CTR_FLAG_WRITE_MOSTLY, "write_mostly"},
+ { CTR_FLAG_STRIPE_CACHE, "stripe_cache"},
+ { CTR_FLAG_REGION_SIZE, "region_size"},
+ { CTR_FLAG_RAID10_COPIES, "raid10_copies"},
+ { CTR_FLAG_RAID10_FORMAT, "raid10_format"},
+ { CTR_FLAG_DATA_OFFSET, "data_offset"},
+ { CTR_FLAG_DELTA_DISKS, "delta_disks"},
+ { CTR_FLAG_RAID10_USE_NEAR_SETS, "raid10_use_near_sets"},
};
-static char *raid10_md_layout_to_format(int layout)
+/* Return argument name string for given @flag */
+static const char *dm_raid_arg_name_by_flag(const uint32_t flag)
+{
+ if (hweight32(flag) == 1) {
+ struct arg_name_flag *anf = __arg_name_flags + ARRAY_SIZE(__arg_name_flags);
+
+ while (anf-- > __arg_name_flags)
+ if (flag & anf->flag)
+ return anf->name;
+
+ } else
+ DMERR("%s called with more than one flag!", __func__);
+
+ return NULL;
+}
+
+/*
+ * Bool helpers to test for various raid levels of a raid set.
+ * It's level as reported by the superblock rather than
+ * the requested raid_type passed to the constructor.
+ */
+/* Return true, if raid set in @rs is raid0 */
+static bool rs_is_raid0(struct raid_set *rs)
+{
+ return !rs->md.level;
+}
+
+/* Return true, if raid set in @rs is raid1 */
+static bool rs_is_raid1(struct raid_set *rs)
+{
+ return rs->md.level == 1;
+}
+
+/* Return true, if raid set in @rs is raid10 */
+static bool rs_is_raid10(struct raid_set *rs)
+{
+ return rs->md.level == 10;
+}
+
+/* Return true, if raid set in @rs is level 6 */
+static bool rs_is_raid6(struct raid_set *rs)
+{
+ return rs->md.level == 6;
+}
+
+/* Return true, if raid set in @rs is level 4, 5 or 6 */
+static bool rs_is_raid456(struct raid_set *rs)
+{
+ return __within_range(rs->md.level, 4, 6);
+}
+
+/* Return true, if raid set in @rs is reshapable */
+static bool __is_raid10_far(int layout);
+static bool rs_is_reshapable(struct raid_set *rs)
+{
+ return rs_is_raid456(rs) ||
+ (rs_is_raid10(rs) && !__is_raid10_far(rs->md.new_layout));
+}
+
+/* Return true, if raid set in @rs is recovering */
+static bool rs_is_recovering(struct raid_set *rs)
+{
+ return rs->md.recovery_cp < rs->dev[0].rdev.sectors;
+}
+
+/* Return true, if raid set in @rs is reshaping */
+static bool rs_is_reshaping(struct raid_set *rs)
+{
+ return rs->md.reshape_position != MaxSector;
+}
+
+/*
+ * bool helpers to test for various raid levels of a raid type @rt
+ */
+
+/* Return true, if raid type in @rt is raid0 */
+static bool rt_is_raid0(struct raid_type *rt)
+{
+ return !rt->level;
+}
+
+/* Return true, if raid type in @rt is raid1 */
+static bool rt_is_raid1(struct raid_type *rt)
+{
+ return rt->level == 1;
+}
+
+/* Return true, if raid type in @rt is raid10 */
+static bool rt_is_raid10(struct raid_type *rt)
+{
+ return rt->level == 10;
+}
+
+/* Return true, if raid type in @rt is raid4/5 */
+static bool rt_is_raid45(struct raid_type *rt)
+{
+ return __within_range(rt->level, 4, 5);
+}
+
+/* Return true, if raid type in @rt is raid6 */
+static bool rt_is_raid6(struct raid_type *rt)
+{
+ return rt->level == 6;
+}
+
+/* Return true, if raid type in @rt is raid4/5/6 */
+static bool rt_is_raid456(struct raid_type *rt)
+{
+ return __within_range(rt->level, 4, 6);
+}
+/* END: raid level bools */
+
+/* Return valid ctr flags for the raid level of @rs */
+static unsigned long __valid_flags(struct raid_set *rs)
+{
+ if (rt_is_raid0(rs->raid_type))
+ return RAID0_VALID_FLAGS;
+ else if (rt_is_raid1(rs->raid_type))
+ return RAID1_VALID_FLAGS;
+ else if (rt_is_raid10(rs->raid_type))
+ return RAID10_VALID_FLAGS;
+ else if (rt_is_raid45(rs->raid_type))
+ return RAID45_VALID_FLAGS;
+ else if (rt_is_raid6(rs->raid_type))
+ return RAID6_VALID_FLAGS;
+
+ return 0;
+}
+
+/*
+ * Check for valid flags set on @rs
+ *
+ * Has to be called after parsing of the ctr flags!
+ */
+static int rs_check_for_valid_flags(struct raid_set *rs)
+{
+ if (rs->ctr_flags & ~__valid_flags(rs)) {
+ rs->ti->error = "Invalid flags combination";
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/* MD raid10 bit definitions and helpers */
+#define RAID10_OFFSET (1 << 16) /* stripes with data copies area adjacent on devices */
+#define RAID10_BROCKEN_USE_FAR_SETS (1 << 17) /* Broken in raid10.c: use sets instead of whole stripe rotation */
+#define RAID10_USE_FAR_SETS (1 << 18) /* Use sets instead of whole stripe rotation */
+#define RAID10_FAR_COPIES_SHIFT 8 /* raid10 # far copies shift (2nd byte of layout) */
+
+/* Return md raid10 near copies for @layout */
+static unsigned int __raid10_near_copies(int layout)
+{
+ return layout & 0xFF;
+}
+
+/* Return md raid10 far copies for @layout */
+static unsigned int __raid10_far_copies(int layout)
+{
+ return __raid10_near_copies(layout >> RAID10_FAR_COPIES_SHIFT);
+}
+
+/* Return true if md raid10 offset for @layout */
+static bool __is_raid10_offset(int layout)
+{
+ return !!(layout & RAID10_OFFSET);
+}
+
+/* Return true if md raid10 near for @layout */
+static bool __is_raid10_near(int layout)
+{
+ return !__is_raid10_offset(layout) && __raid10_near_copies(layout) > 1;
+}
+
+/* Return true if md raid10 far for @layout */
+static bool __is_raid10_far(int layout)
+{
+ return !__is_raid10_offset(layout) && __raid10_far_copies(layout) > 1;
+}
+
+/* Return md raid10 layout string for @layout */
+static const char *raid10_md_layout_to_format(int layout)
{
/*
- * Bit 16 and 17 stand for "offset" and "use_far_sets"
+ * Bit 16 stands for "offset"
+ * (i.e. adjacent stripes hold copies)
+ *
* Refer to MD's raid10.c for details
*/
- if ((layout & 0x10000) && (layout & 0x20000))
+ if (__is_raid10_offset(layout))
return "offset";
- if ((layout & 0xFF) > 1)
+ if (__raid10_near_copies(layout) > 1)
return "near";
+ WARN_ON(__raid10_far_copies(layout) < 2);
+
return "far";
}
-static unsigned raid10_md_layout_to_copies(int layout)
+/* Return md raid10 algorithm for @name */
+static int raid10_name_to_format(const char *name)
+{
+ if (!strcasecmp(name, "near"))
+ return ALGORITHM_RAID10_NEAR;
+ else if (!strcasecmp(name, "offset"))
+ return ALGORITHM_RAID10_OFFSET;
+ else if (!strcasecmp(name, "far"))
+ return ALGORITHM_RAID10_FAR;
+
+ return -EINVAL;
+}
+
+/* Return md raid10 copies for @layout */
+static unsigned int raid10_md_layout_to_copies(int layout)
{
- if ((layout & 0xFF) > 1)
- return layout & 0xFF;
- return (layout >> 8) & 0xFF;
+ return max(__raid10_near_copies(layout), __raid10_far_copies(layout));
}
-static int raid10_format_to_md_layout(char *format, unsigned copies)
+/* Return md raid10 format id for @format string */
+static int raid10_format_to_md_layout(struct raid_set *rs,
+ unsigned int algorithm,
+ unsigned int copies)
{
- unsigned n = 1, f = 1;
+ unsigned int n = 1, f = 1, r = 0;
- if (!strcasecmp("near", format))
+ /*
+ * MD resilienece flaw:
+ *
+ * enabling use_far_sets for far/offset formats causes copies
+ * to be colocated on the same devs together with their origins!
+ *
+ * -> disable it for now in the definition above
+ */
+ if (algorithm == ALGORITHM_RAID10_DEFAULT ||
+ algorithm == ALGORITHM_RAID10_NEAR)
n = copies;
- else
+
+ else if (algorithm == ALGORITHM_RAID10_OFFSET) {
f = copies;
+ r = RAID10_OFFSET;
+ if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
+ r |= RAID10_USE_FAR_SETS;
- if (!strcasecmp("offset", format))
- return 0x30000 | (f << 8) | n;
+ } else if (algorithm == ALGORITHM_RAID10_FAR) {
+ f = copies;
+ r = !RAID10_OFFSET;
+ if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
+ r |= RAID10_USE_FAR_SETS;
- if (!strcasecmp("far", format))
- return 0x20000 | (f << 8) | n;
+ } else
+ return -EINVAL;
- return (f << 8) | n;
+ return r | (f << RAID10_FAR_COPIES_SHIFT) | n;
}
+/* END: MD raid10 bit definitions and helpers */
-static struct raid_type *get_raid_type(char *name)
+/* Check for any of the raid10 algorithms */
+static bool __got_raid10(struct raid_type *rtp, const int layout)
{
- int i;
+ if (rtp->level == 10) {
+ switch (rtp->algorithm) {
+ case ALGORITHM_RAID10_DEFAULT:
+ case ALGORITHM_RAID10_NEAR:
+ return __is_raid10_near(layout);
+ case ALGORITHM_RAID10_OFFSET:
+ return __is_raid10_offset(layout);
+ case ALGORITHM_RAID10_FAR:
+ return __is_raid10_far(layout);
+ default:
+ break;
+ }
+ }
- for (i = 0; i < ARRAY_SIZE(raid_types); i++)
- if (!strcmp(raid_types[i].name, name))
- return &raid_types[i];
+ return false;
+}
+
+/* Return raid_type for @name */
+static struct raid_type *get_raid_type(const char *name)
+{
+ struct raid_type *rtp = raid_types + ARRAY_SIZE(raid_types);
+
+ while (rtp-- > raid_types)
+ if (!strcasecmp(rtp->name, name))
+ return rtp;
return NULL;
}
-static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *raid_type, unsigned raid_devs)
+/* Return raid_type for @name based derived from @level and @layout */
+static struct raid_type *get_raid_type_by_ll(const int level, const int layout)
+{
+ struct raid_type *rtp = raid_types + ARRAY_SIZE(raid_types);
+
+ while (rtp-- > raid_types) {
+ /* RAID10 special checks based on @layout flags/properties */
+ if (rtp->level == level &&
+ (__got_raid10(rtp, layout) || rtp->algorithm == layout))
+ return rtp;
+ }
+
+ return NULL;
+}
+
+/*
+ * Conditionally change bdev capacity of @rs
+ * in case of a disk add/remove reshape
+ */
+static void rs_set_capacity(struct raid_set *rs)
+{
+ struct mddev *mddev = &rs->md;
+ struct md_rdev *rdev;
+ struct gendisk *gendisk = dm_disk(dm_table_get_md(rs->ti->table));
+
+ /*
+ * raid10 sets rdev->sector to the device size, which
+ * is unintended in case of out-of-place reshaping
+ */
+ rdev_for_each(rdev, mddev)
+ rdev->sectors = mddev->dev_sectors;
+
+ set_capacity(gendisk, mddev->array_sectors);
+ revalidate_disk(gendisk);
+}
+
+/*
+ * Set the mddev properties in @rs to the current
+ * ones retrieved from the freshest superblock
+ */
+static void rs_set_cur(struct raid_set *rs)
{
- unsigned i;
+ struct mddev *mddev = &rs->md;
+
+ mddev->new_level = mddev->level;
+ mddev->new_layout = mddev->layout;
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
+}
+
+/*
+ * Set the mddev properties in @rs to the new
+ * ones requested by the ctr
+ */
+static void rs_set_new(struct raid_set *rs)
+{
+ struct mddev *mddev = &rs->md;
+
+ mddev->level = mddev->new_level;
+ mddev->layout = mddev->new_layout;
+ mddev->chunk_sectors = mddev->new_chunk_sectors;
+ mddev->raid_disks = rs->raid_disks;
+ mddev->delta_disks = 0;
+}
+
+static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *raid_type,
+ unsigned int raid_devs)
+{
+ unsigned int i;
struct raid_set *rs;
if (raid_devs <= raid_type->parity_devs) {
@@ -164,15 +682,19 @@ static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *ra
mddev_init(&rs->md);
+ rs->raid_disks = raid_devs;
+ rs->delta_disks = 0;
+
rs->ti = ti;
rs->raid_type = raid_type;
+ rs->stripe_cache_entries = 256;
rs->md.raid_disks = raid_devs;
rs->md.level = raid_type->level;
rs->md.new_level = rs->md.level;
rs->md.layout = raid_type->algorithm;
rs->md.new_layout = rs->md.layout;
rs->md.delta_disks = 0;
- rs->md.recovery_cp = 0;
+ rs->md.recovery_cp = MaxSector;
for (i = 0; i < raid_devs; i++)
md_rdev_init(&rs->dev[i].rdev);
@@ -189,11 +711,11 @@ static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *ra
return rs;
}
-static void context_free(struct raid_set *rs)
+static void raid_set_free(struct raid_set *rs)
{
int i;
- for (i = 0; i < rs->md.raid_disks; i++) {
+ for (i = 0; i < rs->raid_disks; i++) {
if (rs->dev[i].meta_dev)
dm_put_device(rs->ti, rs->dev[i].meta_dev);
md_rdev_clear(&rs->dev[i].rdev);
@@ -218,16 +740,22 @@ static void context_free(struct raid_set *rs)
* <meta_dev> -
*
* This code parses those words. If there is a failure,
- * the caller must use context_free to unwind the operations.
+ * the caller must use raid_set_free() to unwind the operations.
*/
-static int dev_parms(struct raid_set *rs, char **argv)
+static int parse_dev_params(struct raid_set *rs, struct dm_arg_set *as)
{
int i;
int rebuild = 0;
int metadata_available = 0;
- int ret = 0;
+ int r = 0;
+ const char *arg;
+
+ /* Put off the number of raid devices argument to get to dev pairs */
+ arg = dm_shift_arg(as);
+ if (!arg)
+ return -EINVAL;
- for (i = 0; i < rs->md.raid_disks; i++, argv += 2) {
+ for (i = 0; i < rs->raid_disks; i++) {
rs->dev[i].rdev.raid_disk = i;
rs->dev[i].meta_dev = NULL;
@@ -240,39 +768,49 @@ static int dev_parms(struct raid_set *rs, char **argv)
rs->dev[i].rdev.data_offset = 0;
rs->dev[i].rdev.mddev = &rs->md;
- if (strcmp(argv[0], "-")) {
- ret = dm_get_device(rs->ti, argv[0],
- dm_table_get_mode(rs->ti->table),
- &rs->dev[i].meta_dev);
- rs->ti->error = "RAID metadata device lookup failure";
- if (ret)
- return ret;
+ arg = dm_shift_arg(as);
+ if (!arg)
+ return -EINVAL;
+
+ if (strcmp(arg, "-")) {
+ r = dm_get_device(rs->ti, arg, dm_table_get_mode(rs->ti->table),
+ &rs->dev[i].meta_dev);
+ if (r) {
+ rs->ti->error = "RAID metadata device lookup failure";
+ return r;
+ }
rs->dev[i].rdev.sb_page = alloc_page(GFP_KERNEL);
- if (!rs->dev[i].rdev.sb_page)
+ if (!rs->dev[i].rdev.sb_page) {
+ rs->ti->error = "Failed to allocate superblock page";
return -ENOMEM;
+ }
}
- if (!strcmp(argv[1], "-")) {
+ arg = dm_shift_arg(as);
+ if (!arg)
+ return -EINVAL;
+
+ if (!strcmp(arg, "-")) {
if (!test_bit(In_sync, &rs->dev[i].rdev.flags) &&
(!rs->dev[i].rdev.recovery_offset)) {
rs->ti->error = "Drive designated for rebuild not specified";
return -EINVAL;
}
- rs->ti->error = "No data device supplied with metadata device";
- if (rs->dev[i].meta_dev)
+ if (rs->dev[i].meta_dev) {
+ rs->ti->error = "No data device supplied with metadata device";
return -EINVAL;
+ }
continue;
}
- ret = dm_get_device(rs->ti, argv[1],
- dm_table_get_mode(rs->ti->table),
- &rs->dev[i].data_dev);
- if (ret) {
+ r = dm_get_device(rs->ti, arg, dm_table_get_mode(rs->ti->table),
+ &rs->dev[i].data_dev);
+ if (r) {
rs->ti->error = "RAID device lookup failure";
- return ret;
+ return r;
}
if (rs->dev[i].meta_dev) {
@@ -280,7 +818,7 @@ static int dev_parms(struct raid_set *rs, char **argv)
rs->dev[i].rdev.meta_bdev = rs->dev[i].meta_dev->bdev;
}
rs->dev[i].rdev.bdev = rs->dev[i].data_dev->bdev;
- list_add(&rs->dev[i].rdev.same_set, &rs->md.disks);
+ list_add_tail(&rs->dev[i].rdev.same_set, &rs->md.disks);
if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
rebuild++;
}
@@ -301,8 +839,7 @@ static int dev_parms(struct raid_set *rs, char **argv)
*
* User could specify 'nosync' option if desperate.
*/
- DMERR("Unable to rebuild drive while array is not in-sync");
- rs->ti->error = "RAID device lookup failure";
+ rs->ti->error = "Unable to rebuild drive while array is not in-sync";
return -EINVAL;
}
@@ -323,9 +860,12 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
{
unsigned long min_region_size = rs->ti->len / (1 << 21);
+ if (rs_is_raid0(rs))
+ return 0;
+
if (!region_size) {
/*
- * Choose a reasonable default. All figures in sectors.
+ * Choose a reasonable default. All figures in sectors.
*/
if (min_region_size > (1 << 13)) {
/* If not a power of 2, make it the next power of 2 */
@@ -366,7 +906,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
/*
* Convert sectors to bytes.
*/
- rs->md.bitmap_info.chunksize = (region_size << 9);
+ rs->md.bitmap_info.chunksize = to_bytes(region_size);
return 0;
}
@@ -382,9 +922,9 @@ 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 = 0, copies, d;
- unsigned group_size, last_group_start;
+ unsigned int i, rebuild_cnt = 0;
+ unsigned int rebuilds_per_group = 0, copies;
+ unsigned int group_size, last_group_start;
for (i = 0; i < rs->md.raid_disks; i++)
if (!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
@@ -392,6 +932,8 @@ static int validate_raid_redundancy(struct raid_set *rs)
rebuild_cnt++;
switch (rs->raid_type->level) {
+ case 0:
+ break;
case 1:
if (rebuild_cnt >= rs->md.raid_disks)
goto too_many;
@@ -403,7 +945,7 @@ static int validate_raid_redundancy(struct raid_set *rs)
goto too_many;
break;
case 10:
- copies = raid10_md_layout_to_copies(rs->md.layout);
+ copies = raid10_md_layout_to_copies(rs->md.new_layout);
if (rebuild_cnt < copies)
break;
@@ -417,17 +959,16 @@ static int validate_raid_redundancy(struct raid_set *rs)
* simple case where the number of devices is a multiple of the
* number of copies, we must also handle cases where the number
* of devices is not a multiple of the number of copies.
- * E.g. dev1 dev2 dev3 dev4 dev5
- * A A B B C
- * C D D E E
+ * E.g. dev1 dev2 dev3 dev4 dev5
+ * A A B B C
+ * C D D E E
*/
- if (!strcmp("near", raid10_md_layout_to_format(rs->md.layout))) {
- for (i = 0; i < rs->md.raid_disks * copies; i++) {
+ if (__is_raid10_near(rs->md.new_layout)) {
+ for (i = 0; i < rs->md.raid_disks; i++) {
if (!(i % copies))
rebuilds_per_group = 0;
- d = i % rs->md.raid_disks;
- if ((!rs->dev[d].rdev.sb_page ||
- !test_bit(In_sync, &rs->dev[d].rdev.flags)) &&
+ if ((!rs->dev[i].rdev.sb_page ||
+ !test_bit(In_sync, &rs->dev[i].rdev.flags)) &&
(++rebuilds_per_group >= copies))
goto too_many;
}
@@ -442,7 +983,7 @@ static int validate_raid_redundancy(struct raid_set *rs)
* use the 'use_far_sets' variant.)
*
* This check is somewhat complicated by the need to account
- * for arrays that are not a multiple of (far) copies. This
+ * for arrays that are not a multiple of (far) copies. This
* results in the need to treat the last (potentially larger)
* set differently.
*/
@@ -475,42 +1016,48 @@ too_many:
*
* Argument definitions
* <chunk_size> The number of sectors per disk that
- * will form the "stripe"
+ * will form the "stripe"
* [[no]sync] Force or prevent recovery of the
- * entire array
+ * entire array
* [rebuild <idx>] Rebuild the drive indicated by the index
* [daemon_sleep <ms>] Time between bitmap daemon work to
- * clear bits
+ * clear bits
* [min_recovery_rate <kB/sec/disk>] Throttle RAID initialization
* [max_recovery_rate <kB/sec/disk>] Throttle RAID initialization
* [write_mostly <idx>] Indicate a write mostly drive via index
* [max_write_behind <sectors>] See '-write-behind=' (man mdadm)
* [stripe_cache <sectors>] Stripe cache size for higher RAIDs
- * [region_size <sectors>] Defines granularity of bitmap
+ * [region_size <sectors>] Defines granularity of bitmap
*
* RAID10-only options:
- * [raid10_copies <# copies>] Number of copies. (Default: 2)
+ * [raid10_copies <# copies>] Number of copies. (Default: 2)
* [raid10_format <near|far|offset>] Layout algorithm. (Default: near)
*/
-static int parse_raid_params(struct raid_set *rs, char **argv,
- unsigned num_raid_params)
-{
- char *raid10_format = "near";
- unsigned raid10_copies = 2;
- unsigned i;
- unsigned long value, region_size = 0;
- sector_t sectors_per_dev = rs->ti->len;
+static int parse_raid_params(struct raid_set *rs, struct dm_arg_set *as,
+ unsigned int num_raid_params)
+{
+ int value, raid10_format = ALGORITHM_RAID10_DEFAULT;
+ unsigned int raid10_copies = 2;
+ unsigned int i, write_mostly = 0;
+ unsigned int region_size = 0;
sector_t max_io_len;
- char *key;
+ const char *arg, *key;
+ struct raid_dev *rd;
+ struct raid_type *rt = rs->raid_type;
+
+ arg = dm_shift_arg(as);
+ num_raid_params--; /* Account for chunk_size argument */
+
+ if (kstrtoint(arg, 10, &value) < 0) {
+ rs->ti->error = "Bad numerical argument given for chunk_size";
+ return -EINVAL;
+ }
/*
* First, parse the in-order required arguments
* "chunk_size" is the only argument of this type.
*/
- if ((kstrtoul(argv[0], 10, &value) < 0)) {
- rs->ti->error = "Bad chunk size";
- return -EINVAL;
- } else if (rs->raid_type->level == 1) {
+ if (rt_is_raid1(rt)) {
if (value)
DMERR("Ignoring chunk size parameter for RAID 1");
value = 0;
@@ -523,8 +1070,6 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
}
rs->md.new_chunk_sectors = rs->md.chunk_sectors = value;
- argv++;
- num_raid_params--;
/*
* We set each individual device as In_sync with a completed
@@ -532,18 +1077,18 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
* replacement then one of the following cases applies:
*
* 1) User specifies 'rebuild'.
- * - Device is reset when param is read.
+ * - Device is reset when param is read.
* 2) A new device is supplied.
- * - No matching superblock found, resets device.
+ * - No matching superblock found, resets device.
* 3) Device failure was transient and returns on reload.
- * - Failure noticed, resets device for bitmap replay.
+ * - Failure noticed, resets device for bitmap replay.
* 4) Device hadn't completed recovery after previous failure.
- * - Superblock is read and overrides recovery_offset.
+ * - Superblock is read and overrides recovery_offset.
*
* What is found in the superblocks of the devices is always
* authoritative, unless 'rebuild' or '[no]sync' was specified.
*/
- for (i = 0; i < rs->md.raid_disks; i++) {
+ for (i = 0; i < rs->raid_disks; i++) {
set_bit(In_sync, &rs->dev[i].rdev.flags);
rs->dev[i].rdev.recovery_offset = MaxSector;
}
@@ -552,72 +1097,112 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
* Second, parse the unordered optional arguments
*/
for (i = 0; i < num_raid_params; i++) {
- if (!strcasecmp(argv[i], "nosync")) {
- rs->md.recovery_cp = MaxSector;
- rs->ctr_flags |= CTR_FLAG_NOSYNC;
+ key = dm_shift_arg(as);
+ if (!key) {
+ rs->ti->error = "Not enough raid parameters given";
+ return -EINVAL;
+ }
+
+ if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_NOSYNC))) {
+ if (test_and_set_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)) {
+ rs->ti->error = "Only one 'nosync' argument allowed";
+ return -EINVAL;
+ }
+ continue;
+ }
+ if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_SYNC))) {
+ if (test_and_set_bit(__CTR_FLAG_SYNC, &rs->ctr_flags)) {
+ rs->ti->error = "Only one 'sync' argument allowed";
+ return -EINVAL;
+ }
continue;
}
- if (!strcasecmp(argv[i], "sync")) {
- rs->md.recovery_cp = 0;
- rs->ctr_flags |= CTR_FLAG_SYNC;
+ if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_USE_NEAR_SETS))) {
+ if (test_and_set_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags)) {
+ rs->ti->error = "Only one 'raid10_use_new_sets' argument allowed";
+ return -EINVAL;
+ }
continue;
}
- /* The rest of the optional arguments come in key/value pairs */
- if ((i + 1) >= num_raid_params) {
+ arg = dm_shift_arg(as);
+ i++; /* Account for the argument pairs */
+ if (!arg) {
rs->ti->error = "Wrong number of raid parameters given";
return -EINVAL;
}
- key = argv[i++];
+ /*
+ * Parameters that take a string value are checked here.
+ */
- /* Parameters that take a string value are checked here. */
- if (!strcasecmp(key, "raid10_format")) {
- if (rs->raid_type->level != 10) {
+ if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_FORMAT))) {
+ if (test_and_set_bit(__CTR_FLAG_RAID10_FORMAT, &rs->ctr_flags)) {
+ rs->ti->error = "Only one 'raid10_format' argument pair allowed";
+ return -EINVAL;
+ }
+ if (!rt_is_raid10(rt)) {
rs->ti->error = "'raid10_format' is an invalid parameter for this RAID type";
return -EINVAL;
}
- if (strcmp("near", argv[i]) &&
- strcmp("far", argv[i]) &&
- strcmp("offset", argv[i])) {
+ raid10_format = raid10_name_to_format(arg);
+ if (raid10_format < 0) {
rs->ti->error = "Invalid 'raid10_format' value given";
- return -EINVAL;
+ return raid10_format;
}
- raid10_format = argv[i];
- rs->ctr_flags |= CTR_FLAG_RAID10_FORMAT;
continue;
}
- if (kstrtoul(argv[i], 10, &value) < 0) {
+ if (kstrtoint(arg, 10, &value) < 0) {
rs->ti->error = "Bad numerical argument given in raid params";
return -EINVAL;
}
- /* Parameters that take a numeric value are checked here */
- if (!strcasecmp(key, "rebuild")) {
- if (value >= rs->md.raid_disks) {
+ if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_REBUILD))) {
+ /*
+ * "rebuild" is being passed in by userspace to provide
+ * indexes of replaced devices and to set up additional
+ * devices on raid level takeover.
+ */
+ if (!__within_range(value, 0, rs->raid_disks - 1)) {
rs->ti->error = "Invalid rebuild index given";
return -EINVAL;
}
- clear_bit(In_sync, &rs->dev[value].rdev.flags);
- rs->dev[value].rdev.recovery_offset = 0;
- rs->ctr_flags |= CTR_FLAG_REBUILD;
- } else if (!strcasecmp(key, "write_mostly")) {
- if (rs->raid_type->level != 1) {
+
+ if (test_and_set_bit(value, (void *) rs->rebuild_disks)) {
+ rs->ti->error = "rebuild for this index already given";
+ return -EINVAL;
+ }
+
+ rd = rs->dev + value;
+ clear_bit(In_sync, &rd->rdev.flags);
+ clear_bit(Faulty, &rd->rdev.flags);
+ rd->rdev.recovery_offset = 0;
+ set_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags);
+ } else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_WRITE_MOSTLY))) {
+ if (!rt_is_raid1(rt)) {
rs->ti->error = "write_mostly option is only valid for RAID1";
return -EINVAL;
}
- if (value >= rs->md.raid_disks) {
- rs->ti->error = "Invalid write_mostly drive index given";
+
+ if (!__within_range(value, 0, rs->md.raid_disks - 1)) {
+ rs->ti->error = "Invalid write_mostly index given";
return -EINVAL;
}
+
+ write_mostly++;
set_bit(WriteMostly, &rs->dev[value].rdev.flags);
- } else if (!strcasecmp(key, "max_write_behind")) {
- if (rs->raid_type->level != 1) {
+ set_bit(__CTR_FLAG_WRITE_MOSTLY, &rs->ctr_flags);
+ } else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MAX_WRITE_BEHIND))) {
+ if (!rt_is_raid1(rt)) {
rs->ti->error = "max_write_behind option is only valid for RAID1";
return -EINVAL;
}
- rs->ctr_flags |= CTR_FLAG_MAX_WRITE_BEHIND;
+
+ if (test_and_set_bit(__CTR_FLAG_MAX_WRITE_BEHIND, &rs->ctr_flags)) {
+ rs->ti->error = "Only one max_write_behind argument pair allowed";
+ return -EINVAL;
+ }
/*
* In device-mapper, we specify things in sectors, but
@@ -628,64 +1213,121 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
rs->ti->error = "Max write-behind limit out of range";
return -EINVAL;
}
+
rs->md.bitmap_info.max_write_behind = value;
- } else if (!strcasecmp(key, "daemon_sleep")) {
- rs->ctr_flags |= CTR_FLAG_DAEMON_SLEEP;
+ } else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DAEMON_SLEEP))) {
+ if (test_and_set_bit(__CTR_FLAG_DAEMON_SLEEP, &rs->ctr_flags)) {
+ rs->ti->error = "Only one daemon_sleep argument pair allowed";
+ return -EINVAL;
+ }
if (!value || (value > MAX_SCHEDULE_TIMEOUT)) {
rs->ti->error = "daemon sleep period out of range";
return -EINVAL;
}
rs->md.bitmap_info.daemon_sleep = value;
- } else if (!strcasecmp(key, "stripe_cache")) {
- rs->ctr_flags |= CTR_FLAG_STRIPE_CACHE;
+ } else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DATA_OFFSET))) {
+ /* Userspace passes new data_offset after having extended the the data image LV */
+ if (test_and_set_bit(__CTR_FLAG_DATA_OFFSET, &rs->ctr_flags)) {
+ rs->ti->error = "Only one data_offset argument pair allowed";
+ return -EINVAL;
+ }
+ /* Ensure sensible data offset */
+ if (value < 0 ||
+ (value && (value < MIN_FREE_RESHAPE_SPACE || value % to_sector(PAGE_SIZE)))) {
+ rs->ti->error = "Bogus data_offset value";
+ return -EINVAL;
+ }
+ rs->data_offset = value;
+ } else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DELTA_DISKS))) {
+ /* Define the +/-# of disks to add to/remove from the given raid set */
+ if (test_and_set_bit(__CTR_FLAG_DELTA_DISKS, &rs->ctr_flags)) {
+ rs->ti->error = "Only one delta_disks argument pair allowed";
+ return -EINVAL;
+ }
+ /* Ensure MAX_RAID_DEVICES and raid type minimal_devs! */
+ if (!__within_range(abs(value), 1, MAX_RAID_DEVICES - rt->minimal_devs)) {
+ rs->ti->error = "Too many delta_disk requested";
+ return -EINVAL;
+ }
- /*
- * In device-mapper, we specify things in sectors, but
- * MD records this value in kB
- */
- value /= 2;
+ rs->delta_disks = value;
+ } else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_STRIPE_CACHE))) {
+ if (test_and_set_bit(__CTR_FLAG_STRIPE_CACHE, &rs->ctr_flags)) {
+ rs->ti->error = "Only one stripe_cache argument pair allowed";
+ return -EINVAL;
+ }
- if ((rs->raid_type->level != 5) &&
- (rs->raid_type->level != 6)) {
+ if (!rt_is_raid456(rt)) {
rs->ti->error = "Inappropriate argument: stripe_cache";
return -EINVAL;
}
- if (raid5_set_cache_size(&rs->md, (int)value)) {
- rs->ti->error = "Bad stripe_cache size";
+
+ rs->stripe_cache_entries = value;
+ } else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MIN_RECOVERY_RATE))) {
+ if (test_and_set_bit(__CTR_FLAG_MIN_RECOVERY_RATE, &rs->ctr_flags)) {
+ rs->ti->error = "Only one min_recovery_rate argument pair allowed";
return -EINVAL;
}
- } else if (!strcasecmp(key, "min_recovery_rate")) {
- rs->ctr_flags |= CTR_FLAG_MIN_RECOVERY_RATE;
if (value > INT_MAX) {
rs->ti->error = "min_recovery_rate out of range";
return -EINVAL;
}
rs->md.sync_speed_min = (int)value;
- } else if (!strcasecmp(key, "max_recovery_rate")) {
- rs->ctr_flags |= CTR_FLAG_MAX_RECOVERY_RATE;
+ } else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MAX_RECOVERY_RATE))) {
+ if (test_and_set_bit(__CTR_FLAG_MAX_RECOVERY_RATE, &rs->ctr_flags)) {
+ rs->ti->error = "Only one max_recovery_rate argument pair allowed";
+ return -EINVAL;
+ }
if (value > INT_MAX) {
rs->ti->error = "max_recovery_rate out of range";
return -EINVAL;
}
rs->md.sync_speed_max = (int)value;
- } else if (!strcasecmp(key, "region_size")) {
- rs->ctr_flags |= CTR_FLAG_REGION_SIZE;
+ } else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_REGION_SIZE))) {
+ if (test_and_set_bit(__CTR_FLAG_REGION_SIZE, &rs->ctr_flags)) {
+ rs->ti->error = "Only one region_size argument pair allowed";
+ return -EINVAL;
+ }
+
region_size = value;
- } else if (!strcasecmp(key, "raid10_copies") &&
- (rs->raid_type->level == 10)) {
- if ((value < 2) || (value > 0xFF)) {
+ rs->requested_bitmap_chunk_sectors = value;
+ } else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_COPIES))) {
+ if (test_and_set_bit(__CTR_FLAG_RAID10_COPIES, &rs->ctr_flags)) {
+ rs->ti->error = "Only one raid10_copies argument pair allowed";
+ return -EINVAL;
+ }
+
+ if (!__within_range(value, 2, rs->md.raid_disks)) {
rs->ti->error = "Bad value for 'raid10_copies'";
return -EINVAL;
}
- rs->ctr_flags |= CTR_FLAG_RAID10_COPIES;
+
raid10_copies = value;
} else {
DMERR("Unable to parse RAID parameter: %s", key);
- rs->ti->error = "Unable to parse RAID parameters";
+ rs->ti->error = "Unable to parse RAID parameter";
return -EINVAL;
}
}
+ if (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) &&
+ test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)) {
+ rs->ti->error = "sync and nosync are mutually exclusive";
+ return -EINVAL;
+ }
+
+ if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags) &&
+ (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) ||
+ test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags))) {
+ rs->ti->error = "sync/nosync and rebuild are mutually exclusive";
+ return -EINVAL;
+ }
+
+ if (write_mostly >= rs->md.raid_disks) {
+ rs->ti->error = "Can't set all raid1 devices to write_mostly";
+ return -EINVAL;
+ }
+
if (validate_region_size(rs, region_size))
return -EINVAL;
@@ -697,47 +1339,193 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
if (dm_set_target_max_io_len(rs->ti, max_io_len))
return -EINVAL;
- if (rs->raid_type->level == 10) {
+ if (rt_is_raid10(rt)) {
if (raid10_copies > rs->md.raid_disks) {
rs->ti->error = "Not enough devices to satisfy specification";
return -EINVAL;
}
- /*
- * If the format is not "near", we only support
- * two copies at the moment.
- */
- if (strcmp("near", raid10_format) && (raid10_copies > 2)) {
- rs->ti->error = "Too many copies for given RAID10 format.";
+ rs->md.new_layout = raid10_format_to_md_layout(rs, raid10_format, raid10_copies);
+ if (rs->md.new_layout < 0) {
+ rs->ti->error = "Error getting raid10 format";
+ return rs->md.new_layout;
+ }
+
+ rt = get_raid_type_by_ll(10, rs->md.new_layout);
+ if (!rt) {
+ rs->ti->error = "Failed to recognize new raid10 layout";
return -EINVAL;
}
- /* (Len * #mirrors) / #devices */
- sectors_per_dev = rs->ti->len * raid10_copies;
- sector_div(sectors_per_dev, rs->md.raid_disks);
-
- rs->md.layout = raid10_format_to_md_layout(raid10_format,
- raid10_copies);
- rs->md.new_layout = rs->md.layout;
- } else if ((!rs->raid_type->level || rs->raid_type->level > 1) &&
- sector_div(sectors_per_dev,
- (rs->md.raid_disks - rs->raid_type->parity_devs))) {
- rs->ti->error = "Target length not divisible by number of data devices";
- return -EINVAL;
+ if ((rt->algorithm == ALGORITHM_RAID10_DEFAULT ||
+ rt->algorithm == ALGORITHM_RAID10_NEAR) &&
+ test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags)) {
+ rs->ti->error = "RAID10 format 'near' and 'raid10_use_near_sets' are incompatible";
+ return -EINVAL;
+ }
}
- rs->md.dev_sectors = sectors_per_dev;
+
+ rs->raid10_copies = raid10_copies;
/* Assume there are no metadata devices until the drives are parsed */
rs->md.persistent = 0;
rs->md.external = 1;
+ /* Check, if any invalid ctr arguments have been passed in for the raid level */
+ return rs_check_for_valid_flags(rs);
+}
+
+/* Set raid4/5/6 cache size */
+static int rs_set_raid456_stripe_cache(struct raid_set *rs)
+{
+ int r;
+ struct r5conf *conf;
+ struct mddev *mddev = &rs->md;
+ uint32_t min_stripes = max(mddev->chunk_sectors, mddev->new_chunk_sectors) / 2;
+ uint32_t nr_stripes = rs->stripe_cache_entries;
+
+ if (!rt_is_raid456(rs->raid_type)) {
+ rs->ti->error = "Inappropriate raid level; cannot change stripe_cache size";
+ return -EINVAL;
+ }
+
+ if (nr_stripes < min_stripes) {
+ DMINFO("Adjusting requested %u stripe cache entries to %u to suit stripe size",
+ nr_stripes, min_stripes);
+ nr_stripes = min_stripes;
+ }
+
+ conf = mddev->private;
+ if (!conf) {
+ rs->ti->error = "Cannot change stripe_cache size on inactive RAID set";
+ return -EINVAL;
+ }
+
+ /* Try setting number of stripes in raid456 stripe cache */
+ if (conf->min_nr_stripes != nr_stripes) {
+ r = raid5_set_cache_size(mddev, nr_stripes);
+ if (r) {
+ rs->ti->error = "Failed to set raid4/5/6 stripe cache size";
+ return r;
+ }
+
+ DMINFO("%u stripe cache entries", nr_stripes);
+ }
+
+ return 0;
+}
+
+/* Return # of data stripes as kept in mddev as of @rs (i.e. as of superblock) */
+static unsigned int mddev_data_stripes(struct raid_set *rs)
+{
+ return rs->md.raid_disks - rs->raid_type->parity_devs;
+}
+
+/* Return # of data stripes of @rs (i.e. as of ctr) */
+static unsigned int rs_data_stripes(struct raid_set *rs)
+{
+ return rs->raid_disks - rs->raid_type->parity_devs;
+}
+
+/* Calculate the sectors per device and per array used for @rs */
+static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev)
+{
+ int delta_disks;
+ unsigned int data_stripes;
+ struct mddev *mddev = &rs->md;
+ struct md_rdev *rdev;
+ sector_t array_sectors = rs->ti->len, dev_sectors = rs->ti->len;
+
+ if (use_mddev) {
+ delta_disks = mddev->delta_disks;
+ data_stripes = mddev_data_stripes(rs);
+ } else {
+ delta_disks = rs->delta_disks;
+ data_stripes = rs_data_stripes(rs);
+ }
+
+ /* Special raid1 case w/o delta_disks support (yet) */
+ if (rt_is_raid1(rs->raid_type))
+ ;
+ else if (rt_is_raid10(rs->raid_type)) {
+ if (rs->raid10_copies < 2 ||
+ delta_disks < 0) {
+ rs->ti->error = "Bogus raid10 data copies or delta disks";
+ return -EINVAL;
+ }
+
+ dev_sectors *= rs->raid10_copies;
+ if (sector_div(dev_sectors, data_stripes))
+ goto bad;
+
+ array_sectors = (data_stripes + delta_disks) * dev_sectors;
+ if (sector_div(array_sectors, rs->raid10_copies))
+ goto bad;
+
+ } else if (sector_div(dev_sectors, data_stripes))
+ goto bad;
+
+ else
+ /* Striped layouts */
+ array_sectors = (data_stripes + delta_disks) * dev_sectors;
+
+ rdev_for_each(rdev, mddev)
+ rdev->sectors = dev_sectors;
+
+ mddev->array_sectors = array_sectors;
+ mddev->dev_sectors = dev_sectors;
+
return 0;
+bad:
+ rs->ti->error = "Target length not divisible by number of data devices";
+ return -EINVAL;
+}
+
+/* Setup recovery on @rs */
+static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
+{
+ /* raid0 does not recover */
+ if (rs_is_raid0(rs))
+ rs->md.recovery_cp = MaxSector;
+ /*
+ * A raid6 set has to be recovered either
+ * completely or for the grown part to
+ * ensure proper parity and Q-Syndrome
+ */
+ else if (rs_is_raid6(rs))
+ rs->md.recovery_cp = dev_sectors;
+ /*
+ * Other raid set types may skip recovery
+ * depending on the 'nosync' flag.
+ */
+ else
+ rs->md.recovery_cp = test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)
+ ? MaxSector : dev_sectors;
+}
+
+/* Setup recovery on @rs based on raid type, device size and 'nosync' flag */
+static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
+{
+ if (!dev_sectors)
+ /* New raid set or 'sync' flag provided */
+ __rs_setup_recovery(rs, 0);
+ else if (dev_sectors == MaxSector)
+ /* Prevent recovery */
+ __rs_setup_recovery(rs, MaxSector);
+ else if (rs->dev[0].rdev.sectors < dev_sectors)
+ /* Grown raid set */
+ __rs_setup_recovery(rs, rs->dev[0].rdev.sectors);
+ else
+ __rs_setup_recovery(rs, MaxSector);
}
static void do_table_event(struct work_struct *ws)
{
struct raid_set *rs = container_of(ws, struct raid_set, md.event_work);
+ smp_rmb(); /* Make sure we access most actual mddev properties */
+ if (!rs_is_reshaping(rs))
+ rs_set_capacity(rs);
dm_table_event(rs->ti->table);
}
@@ -749,19 +1537,225 @@ static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
}
/*
+ * Make sure a valid takover (level switch) is being requested on @rs
+ *
+ * Conversions of raid sets from one MD personality to another
+ * have to conform to restrictions which are enforced here.
+ */
+static int rs_check_takeover(struct raid_set *rs)
+{
+ struct mddev *mddev = &rs->md;
+ unsigned int near_copies;
+
+ if (rs->md.degraded) {
+ rs->ti->error = "Can't takeover degraded raid set";
+ return -EPERM;
+ }
+
+ if (rs_is_reshaping(rs)) {
+ rs->ti->error = "Can't takeover reshaping raid set";
+ return -EPERM;
+ }
+
+ switch (mddev->level) {
+ case 0:
+ /* raid0 -> raid1/5 with one disk */
+ if ((mddev->new_level == 1 || mddev->new_level == 5) &&
+ mddev->raid_disks == 1)
+ return 0;
+
+ /* raid0 -> raid10 */
+ if (mddev->new_level == 10 &&
+ !(rs->raid_disks % mddev->raid_disks))
+ return 0;
+
+ /* raid0 with multiple disks -> raid4/5/6 */
+ if (__within_range(mddev->new_level, 4, 6) &&
+ mddev->new_layout == ALGORITHM_PARITY_N &&
+ mddev->raid_disks > 1)
+ return 0;
+
+ break;
+
+ case 10:
+ /* Can't takeover raid10_offset! */
+ if (__is_raid10_offset(mddev->layout))
+ break;
+
+ near_copies = __raid10_near_copies(mddev->layout);
+
+ /* raid10* -> raid0 */
+ if (mddev->new_level == 0) {
+ /* Can takeover raid10_near with raid disks divisable by data copies! */
+ if (near_copies > 1 &&
+ !(mddev->raid_disks % near_copies)) {
+ mddev->raid_disks /= near_copies;
+ mddev->delta_disks = mddev->raid_disks;
+ return 0;
+ }
+
+ /* Can takeover raid10_far */
+ if (near_copies == 1 &&
+ __raid10_far_copies(mddev->layout) > 1)
+ return 0;
+
+ break;
+ }
+
+ /* raid10_{near,far} -> raid1 */
+ if (mddev->new_level == 1 &&
+ max(near_copies, __raid10_far_copies(mddev->layout)) == mddev->raid_disks)
+ return 0;
+
+ /* raid10_{near,far} with 2 disks -> raid4/5 */
+ if (__within_range(mddev->new_level, 4, 5) &&
+ mddev->raid_disks == 2)
+ return 0;
+ break;
+
+ case 1:
+ /* raid1 with 2 disks -> raid4/5 */
+ if (__within_range(mddev->new_level, 4, 5) &&
+ mddev->raid_disks == 2) {
+ mddev->degraded = 1;
+ return 0;
+ }
+
+ /* raid1 -> raid0 */
+ if (mddev->new_level == 0 &&
+ mddev->raid_disks == 1)
+ return 0;
+
+ /* raid1 -> raid10 */
+ if (mddev->new_level == 10)
+ return 0;
+ break;
+
+ case 4:
+ /* raid4 -> raid0 */
+ if (mddev->new_level == 0)
+ return 0;
+
+ /* raid4 -> raid1/5 with 2 disks */
+ if ((mddev->new_level == 1 || mddev->new_level == 5) &&
+ mddev->raid_disks == 2)
+ return 0;
+
+ /* raid4 -> raid5/6 with parity N */
+ if (__within_range(mddev->new_level, 5, 6) &&
+ mddev->layout == ALGORITHM_PARITY_N)
+ return 0;
+ break;
+
+ case 5:
+ /* raid5 with parity N -> raid0 */
+ if (mddev->new_level == 0 &&
+ mddev->layout == ALGORITHM_PARITY_N)
+ return 0;
+
+ /* raid5 with parity N -> raid4 */
+ if (mddev->new_level == 4 &&
+ mddev->layout == ALGORITHM_PARITY_N)
+ return 0;
+
+ /* raid5 with 2 disks -> raid1/4/10 */
+ if ((mddev->new_level == 1 || mddev->new_level == 4 || mddev->new_level == 10) &&
+ mddev->raid_disks == 2)
+ return 0;
+
+ /* raid5_* -> raid6_*_6 with Q-Syndrome N (e.g. raid5_ra -> raid6_ra_6 */
+ if (mddev->new_level == 6 &&
+ ((mddev->layout == ALGORITHM_PARITY_N && mddev->new_layout == ALGORITHM_PARITY_N) ||
+ __within_range(mddev->new_layout, ALGORITHM_LEFT_ASYMMETRIC_6, ALGORITHM_RIGHT_SYMMETRIC_6)))
+ return 0;
+ break;
+
+ case 6:
+ /* raid6 with parity N -> raid0 */
+ if (mddev->new_level == 0 &&
+ mddev->layout == ALGORITHM_PARITY_N)
+ return 0;
+
+ /* raid6 with parity N -> raid4 */
+ if (mddev->new_level == 4 &&
+ mddev->layout == ALGORITHM_PARITY_N)
+ return 0;
+
+ /* raid6_*_n with Q-Syndrome N -> raid5_* */
+ if (mddev->new_level == 5 &&
+ ((mddev->layout == ALGORITHM_PARITY_N && mddev->new_layout == ALGORITHM_PARITY_N) ||
+ __within_range(mddev->new_layout, ALGORITHM_LEFT_ASYMMETRIC, ALGORITHM_RIGHT_SYMMETRIC)))
+ return 0;
+
+ default:
+ break;
+ }
+
+ rs->ti->error = "takeover not possible";
+ return -EINVAL;
+}
+
+/* True if @rs requested to be taken over */
+static bool rs_takeover_requested(struct raid_set *rs)
+{
+ return rs->md.new_level != rs->md.level;
+}
+
+/* True if @rs is requested to reshape by ctr */
+static bool rs_reshape_requested(struct raid_set *rs)
+{
+ bool change;
+ struct mddev *mddev = &rs->md;
+
+ if (rs_takeover_requested(rs))
+ return false;
+
+ if (!mddev->level)
+ return false;
+
+ change = mddev->new_layout != mddev->layout ||
+ mddev->new_chunk_sectors != mddev->chunk_sectors ||
+ rs->delta_disks;
+
+ /* Historical case to support raid1 reshape without delta disks */
+ if (mddev->level == 1) {
+ if (rs->delta_disks)
+ return !!rs->delta_disks;
+
+ return !change &&
+ mddev->raid_disks != rs->raid_disks;
+ }
+
+ if (mddev->level == 10)
+ return change &&
+ !__is_raid10_far(mddev->new_layout) &&
+ rs->delta_disks >= 0;
+
+ return change;
+}
+
+/* Features */
+#define FEATURE_FLAG_SUPPORTS_V190 0x1 /* Supports extended superblock */
+
+/* State flags for sb->flags */
+#define SB_FLAG_RESHAPE_ACTIVE 0x1
+#define SB_FLAG_RESHAPE_BACKWARDS 0x2
+
+/*
* This structure is never routinely used by userspace, unlike md superblocks.
* Devices with this superblock should only ever be accessed via device-mapper.
*/
#define DM_RAID_MAGIC 0x64526D44
struct dm_raid_superblock {
__le32 magic; /* "DmRd" */
- __le32 features; /* Used to indicate possible future changes */
+ __le32 compat_features; /* Used to indicate compatible features (like 1.9.0 ondisk metadata extension) */
- __le32 num_devices; /* Number of devices in this array. (Max 64) */
- __le32 array_position; /* The position of this drive in the array */
+ __le32 num_devices; /* Number of devices in this raid set. (Max 64) */
+ __le32 array_position; /* The position of this drive in the raid set */
__le64 events; /* Incremented by md when superblock updated */
- __le64 failed_devices; /* Bit field of devices to indicate failures */
+ __le64 failed_devices; /* Pre 1.9.0 part of bit field of devices to */
+ /* indicate failures (see extension below) */
/*
* This offset tracks the progress of the repair or replacement of
@@ -770,21 +1764,95 @@ struct dm_raid_superblock {
__le64 disk_recovery_offset;
/*
- * This offset tracks the progress of the initial array
+ * This offset tracks the progress of the initial raid set
* synchronisation/parity calculation.
*/
__le64 array_resync_offset;
/*
- * RAID characteristics
+ * raid characteristics
*/
__le32 level;
__le32 layout;
__le32 stripe_sectors;
- /* Remainder of a logical block is zero-filled when writing (see super_sync()). */
+ /********************************************************************
+ * BELOW FOLLOW V1.9.0 EXTENSIONS TO THE PRISTINE SUPERBLOCK FORMAT!!!
+ *
+ * FEATURE_FLAG_SUPPORTS_V190 in the features member indicates that those exist
+ */
+
+ __le32 flags; /* Flags defining array states for reshaping */
+
+ /*
+ * This offset tracks the progress of a raid
+ * set reshape in order to be able to restart it
+ */
+ __le64 reshape_position;
+
+ /*
+ * These define the properties of the array in case of an interrupted reshape
+ */
+ __le32 new_level;
+ __le32 new_layout;
+ __le32 new_stripe_sectors;
+ __le32 delta_disks;
+
+ __le64 array_sectors; /* Array size in sectors */
+
+ /*
+ * Sector offsets to data on devices (reshaping).
+ * Needed to support out of place reshaping, thus
+ * not writing over any stripes whilst converting
+ * them from old to new layout
+ */
+ __le64 data_offset;
+ __le64 new_data_offset;
+
+ __le64 sectors; /* Used device size in sectors */
+
+ /*
+ * Additonal Bit field of devices indicating failures to support
+ * up to 256 devices with the 1.9.0 on-disk metadata format
+ */
+ __le64 extended_failed_devices[DISKS_ARRAY_ELEMS - 1];
+
+ __le32 incompat_features; /* Used to indicate any incompatible features */
+
+ /* Always set rest up to logical block size to 0 when writing (see get_metadata_device() below). */
} __packed;
+/*
+ * Check for reshape constraints on raid set @rs:
+ *
+ * - reshape function non-existent
+ * - degraded set
+ * - ongoing recovery
+ * - ongoing reshape
+ *
+ * Returns 0 if none or -EPERM if given constraint
+ * and error message reference in @errmsg
+ */
+static int rs_check_reshape(struct raid_set *rs)
+{
+ struct mddev *mddev = &rs->md;
+
+ if (!mddev->pers || !mddev->pers->check_reshape)
+ rs->ti->error = "Reshape not supported";
+ else if (mddev->degraded)
+ rs->ti->error = "Can't reshape degraded raid set";
+ else if (rs_is_recovering(rs))
+ rs->ti->error = "Convert request on recovering raid set prohibited";
+ else if (rs_is_reshaping(rs))
+ rs->ti->error = "raid set already reshaping!";
+ else if (!(rs_is_raid1(rs) || rs_is_raid10(rs) || rs_is_raid456(rs)))
+ rs->ti->error = "Reshaping only supported for raid1/4/5/6/10";
+ else
+ return 0;
+
+ return -EPERM;
+}
+
static int read_disk_sb(struct md_rdev *rdev, int size)
{
BUG_ON(!rdev->sb_page);
@@ -792,7 +1860,7 @@ static int read_disk_sb(struct md_rdev *rdev, int size)
if (rdev->sb_loaded)
return 0;
- if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, 1)) {
+ if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, 0, true)) {
DMERR("Failed to read superblock of device at position %d",
rdev->raid_disk);
md_error(rdev->mddev, rdev);
@@ -804,31 +1872,67 @@ static int read_disk_sb(struct md_rdev *rdev, int size)
return 0;
}
+static void sb_retrieve_failed_devices(struct dm_raid_superblock *sb, uint64_t *failed_devices)
+{
+ failed_devices[0] = le64_to_cpu(sb->failed_devices);
+ memset(failed_devices + 1, 0, sizeof(sb->extended_failed_devices));
+
+ if (le32_to_cpu(sb->compat_features) & FEATURE_FLAG_SUPPORTS_V190) {
+ int i = ARRAY_SIZE(sb->extended_failed_devices);
+
+ while (i--)
+ failed_devices[i+1] = le64_to_cpu(sb->extended_failed_devices[i]);
+ }
+}
+
+static void sb_update_failed_devices(struct dm_raid_superblock *sb, uint64_t *failed_devices)
+{
+ int i = ARRAY_SIZE(sb->extended_failed_devices);
+
+ sb->failed_devices = cpu_to_le64(failed_devices[0]);
+ while (i--)
+ sb->extended_failed_devices[i] = cpu_to_le64(failed_devices[i+1]);
+}
+
+/*
+ * Synchronize the superblock members with the raid set properties
+ *
+ * All superblock data is little endian.
+ */
static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
{
- int i;
- uint64_t failed_devices;
+ bool update_failed_devices = false;
+ unsigned int i;
+ uint64_t failed_devices[DISKS_ARRAY_ELEMS];
struct dm_raid_superblock *sb;
struct raid_set *rs = container_of(mddev, struct raid_set, md);
+ /* No metadata device, no superblock */
+ if (!rdev->meta_bdev)
+ return;
+
+ BUG_ON(!rdev->sb_page);
+
sb = page_address(rdev->sb_page);
- failed_devices = le64_to_cpu(sb->failed_devices);
- for (i = 0; i < mddev->raid_disks; i++)
- if (!rs->dev[i].data_dev ||
- test_bit(Faulty, &(rs->dev[i].rdev.flags)))
- failed_devices |= (1ULL << i);
+ sb_retrieve_failed_devices(sb, failed_devices);
- memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));
+ for (i = 0; i < rs->raid_disks; i++)
+ if (!rs->dev[i].data_dev || test_bit(Faulty, &rs->dev[i].rdev.flags)) {
+ update_failed_devices = true;
+ set_bit(i, (void *) failed_devices);
+ }
+
+ if (update_failed_devices)
+ sb_update_failed_devices(sb, failed_devices);
sb->magic = cpu_to_le32(DM_RAID_MAGIC);
- sb->features = cpu_to_le32(0); /* No features yet */
+ sb->compat_features = cpu_to_le32(FEATURE_FLAG_SUPPORTS_V190);
sb->num_devices = cpu_to_le32(mddev->raid_disks);
sb->array_position = cpu_to_le32(rdev->raid_disk);
sb->events = cpu_to_le64(mddev->events);
- sb->failed_devices = cpu_to_le64(failed_devices);
sb->disk_recovery_offset = cpu_to_le64(rdev->recovery_offset);
sb->array_resync_offset = cpu_to_le64(mddev->recovery_cp);
@@ -836,6 +1940,34 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
sb->level = cpu_to_le32(mddev->level);
sb->layout = cpu_to_le32(mddev->layout);
sb->stripe_sectors = cpu_to_le32(mddev->chunk_sectors);
+
+ sb->new_level = cpu_to_le32(mddev->new_level);
+ sb->new_layout = cpu_to_le32(mddev->new_layout);
+ sb->new_stripe_sectors = cpu_to_le32(mddev->new_chunk_sectors);
+
+ sb->delta_disks = cpu_to_le32(mddev->delta_disks);
+
+ smp_rmb(); /* Make sure we access most recent reshape position */
+ sb->reshape_position = cpu_to_le64(mddev->reshape_position);
+ if (le64_to_cpu(sb->reshape_position) != MaxSector) {
+ /* Flag ongoing reshape */
+ sb->flags |= cpu_to_le32(SB_FLAG_RESHAPE_ACTIVE);
+
+ if (mddev->delta_disks < 0 || mddev->reshape_backwards)
+ sb->flags |= cpu_to_le32(SB_FLAG_RESHAPE_BACKWARDS);
+ } else {
+ /* Clear reshape flags */
+ sb->flags &= ~(cpu_to_le32(SB_FLAG_RESHAPE_ACTIVE|SB_FLAG_RESHAPE_BACKWARDS));
+ }
+
+ sb->array_sectors = cpu_to_le64(mddev->array_sectors);
+ sb->data_offset = cpu_to_le64(rdev->data_offset);
+ sb->new_data_offset = cpu_to_le64(rdev->new_data_offset);
+ sb->sectors = cpu_to_le64(rdev->sectors);
+ sb->incompat_features = cpu_to_le32(0);
+
+ /* Zero out the rest of the payload after the size of the superblock */
+ memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));
}
/*
@@ -848,7 +1980,7 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
*/
static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
{
- int ret;
+ int r;
struct dm_raid_superblock *sb;
struct dm_raid_superblock *refsb;
uint64_t events_sb, events_refsb;
@@ -860,9 +1992,9 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
return -EINVAL;
}
- ret = read_disk_sb(rdev, rdev->sb_size);
- if (ret)
- return ret;
+ r = read_disk_sb(rdev, rdev->sb_size);
+ if (r)
+ return r;
sb = page_address(rdev->sb_page);
@@ -876,6 +2008,7 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
super_sync(rdev->mddev, rdev);
set_bit(FirstUse, &rdev->flags);
+ sb->compat_features = cpu_to_le32(FEATURE_FLAG_SUPPORTS_V190);
/* Force writing of superblocks to disk */
set_bit(MD_CHANGE_DEVS, &rdev->mddev->flags);
@@ -895,129 +2028,212 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
return (events_sb > events_refsb) ? 1 : 0;
}
-static int super_init_validation(struct mddev *mddev, struct md_rdev *rdev)
+static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
{
int role;
- struct raid_set *rs = container_of(mddev, struct raid_set, md);
+ unsigned int d;
+ struct mddev *mddev = &rs->md;
uint64_t events_sb;
- uint64_t failed_devices;
+ uint64_t failed_devices[DISKS_ARRAY_ELEMS];
struct dm_raid_superblock *sb;
- uint32_t new_devs = 0;
- uint32_t rebuilds = 0;
+ uint32_t new_devs = 0, rebuild_and_new = 0, rebuilds = 0;
struct md_rdev *r;
struct dm_raid_superblock *sb2;
sb = page_address(rdev->sb_page);
events_sb = le64_to_cpu(sb->events);
- failed_devices = le64_to_cpu(sb->failed_devices);
/*
* Initialise to 1 if this is a new superblock.
*/
mddev->events = events_sb ? : 1;
+ mddev->reshape_position = MaxSector;
+
/*
- * Reshaping is not currently allowed
+ * Reshaping is supported, e.g. reshape_position is valid
+ * in superblock and superblock content is authoritative.
*/
- if (le32_to_cpu(sb->level) != mddev->level) {
- DMERR("Reshaping arrays not yet supported. (RAID level change)");
- return -EINVAL;
- }
- if (le32_to_cpu(sb->layout) != mddev->layout) {
- DMERR("Reshaping arrays not yet supported. (RAID layout change)");
- DMERR(" 0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout);
- DMERR(" Old layout: %s w/ %d copies",
- raid10_md_layout_to_format(le32_to_cpu(sb->layout)),
- raid10_md_layout_to_copies(le32_to_cpu(sb->layout)));
- DMERR(" New layout: %s w/ %d copies",
- raid10_md_layout_to_format(mddev->layout),
- raid10_md_layout_to_copies(mddev->layout));
- return -EINVAL;
- }
- if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) {
- DMERR("Reshaping arrays not yet supported. (stripe sectors change)");
- return -EINVAL;
- }
+ if (le32_to_cpu(sb->compat_features) & FEATURE_FLAG_SUPPORTS_V190) {
+ /* Superblock is authoritative wrt given raid set layout! */
+ mddev->raid_disks = le32_to_cpu(sb->num_devices);
+ mddev->level = le32_to_cpu(sb->level);
+ mddev->layout = le32_to_cpu(sb->layout);
+ mddev->chunk_sectors = le32_to_cpu(sb->stripe_sectors);
+ mddev->new_level = le32_to_cpu(sb->new_level);
+ mddev->new_layout = le32_to_cpu(sb->new_layout);
+ mddev->new_chunk_sectors = le32_to_cpu(sb->new_stripe_sectors);
+ mddev->delta_disks = le32_to_cpu(sb->delta_disks);
+ mddev->array_sectors = le64_to_cpu(sb->array_sectors);
+
+ /* raid was reshaping and got interrupted */
+ if (le32_to_cpu(sb->flags) & SB_FLAG_RESHAPE_ACTIVE) {
+ if (test_bit(__CTR_FLAG_DELTA_DISKS, &rs->ctr_flags)) {
+ DMERR("Reshape requested but raid set is still reshaping");
+ return -EINVAL;
+ }
- /* We can only change the number of devices in RAID1 right now */
- if ((rs->raid_type->level != 1) &&
- (le32_to_cpu(sb->num_devices) != mddev->raid_disks)) {
- DMERR("Reshaping arrays not yet supported. (device count change)");
- return -EINVAL;
+ if (mddev->delta_disks < 0 ||
+ (!mddev->delta_disks && (le32_to_cpu(sb->flags) & SB_FLAG_RESHAPE_BACKWARDS)))
+ mddev->reshape_backwards = 1;
+ else
+ mddev->reshape_backwards = 0;
+
+ mddev->reshape_position = le64_to_cpu(sb->reshape_position);
+ rs->raid_type = get_raid_type_by_ll(mddev->level, mddev->layout);
+ }
+
+ } else {
+ /*
+ * No takeover/reshaping, because we don't have the extended v1.9.0 metadata
+ */
+ if (le32_to_cpu(sb->level) != mddev->level) {
+ DMERR("Reshaping/takeover raid sets not yet supported. (raid level/stripes/size change)");
+ return -EINVAL;
+ }
+ if (le32_to_cpu(sb->layout) != mddev->layout) {
+ DMERR("Reshaping raid sets not yet supported. (raid layout change)");
+ DMERR(" 0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout);
+ DMERR(" Old layout: %s w/ %d copies",
+ raid10_md_layout_to_format(le32_to_cpu(sb->layout)),
+ raid10_md_layout_to_copies(le32_to_cpu(sb->layout)));
+ DMERR(" New layout: %s w/ %d copies",
+ raid10_md_layout_to_format(mddev->layout),
+ raid10_md_layout_to_copies(mddev->layout));
+ return -EINVAL;
+ }
+ if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) {
+ DMERR("Reshaping raid sets not yet supported. (stripe sectors change)");
+ return -EINVAL;
+ }
+
+ /* We can only change the number of devices in raid1 with old (i.e. pre 1.0.7) metadata */
+ if (!rt_is_raid1(rs->raid_type) &&
+ (le32_to_cpu(sb->num_devices) != mddev->raid_disks)) {
+ DMERR("Reshaping raid sets not yet supported. (device count change from %u to %u)",
+ sb->num_devices, mddev->raid_disks);
+ return -EINVAL;
+ }
+
+ /* Table line is checked vs. authoritative superblock */
+ rs_set_new(rs);
}
- if (!(rs->ctr_flags & (CTR_FLAG_SYNC | CTR_FLAG_NOSYNC)))
+ if (!test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags))
mddev->recovery_cp = le64_to_cpu(sb->array_resync_offset);
/*
* During load, we set FirstUse if a new superblock was written.
* There are two reasons we might not have a superblock:
- * 1) The array is brand new - in which case, all of the
- * devices must have their In_sync bit set. Also,
+ * 1) The raid set is brand new - in which case, all of the
+ * devices must have their In_sync bit set. Also,
* recovery_cp must be 0, unless forced.
- * 2) This is a new device being added to an old array
+ * 2) This is a new device being added to an old raid set
* and the new device needs to be rebuilt - in which
* case the In_sync bit will /not/ be set and
* recovery_cp must be MaxSector.
+ * 3) This is/are a new device(s) being added to an old
+ * raid set during takeover to a higher raid level
+ * to provide capacity for redundancy or during reshape
+ * to add capacity to grow the raid set.
*/
+ d = 0;
rdev_for_each(r, mddev) {
+ if (test_bit(FirstUse, &r->flags))
+ new_devs++;
+
if (!test_bit(In_sync, &r->flags)) {
- DMINFO("Device %d specified for rebuild: "
- "Clearing superblock", r->raid_disk);
+ DMINFO("Device %d specified for rebuild; clearing superblock",
+ r->raid_disk);
rebuilds++;
- } else if (test_bit(FirstUse, &r->flags))
- new_devs++;
+
+ if (test_bit(FirstUse, &r->flags))
+ rebuild_and_new++;
+ }
+
+ d++;
}
- if (!rebuilds) {
- if (new_devs == mddev->raid_disks) {
- DMINFO("Superblocks created for new array");
+ if (new_devs == rs->raid_disks || !rebuilds) {
+ /* Replace a broken device */
+ if (new_devs == 1 && !rs->delta_disks)
+ ;
+ if (new_devs == rs->raid_disks) {
+ DMINFO("Superblocks created for new raid set");
set_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
- } else if (new_devs) {
- DMERR("New device injected "
- "into existing array without 'rebuild' "
- "parameter specified");
+ } else if (new_devs != rebuilds &&
+ new_devs != rs->delta_disks) {
+ DMERR("New device injected into existing raid set without "
+ "'delta_disks' or 'rebuild' parameter specified");
return -EINVAL;
}
- } else if (new_devs) {
- DMERR("'rebuild' devices cannot be "
- "injected into an array with other first-time devices");
- return -EINVAL;
- } else if (mddev->recovery_cp != MaxSector) {
- DMERR("'rebuild' specified while array is not in-sync");
+ } else if (new_devs && new_devs != rebuilds) {
+ DMERR("%u 'rebuild' devices cannot be injected into"
+ " a raid set with %u other first-time devices",
+ rebuilds, new_devs);
return -EINVAL;
+ } else if (rebuilds) {
+ if (rebuild_and_new && rebuilds != rebuild_and_new) {
+ DMERR("new device%s provided without 'rebuild'",
+ new_devs > 1 ? "s" : "");
+ return -EINVAL;
+ } else if (rs_is_recovering(rs)) {
+ DMERR("'rebuild' specified while raid set is not in-sync (recovery_cp=%llu)",
+ (unsigned long long) mddev->recovery_cp);
+ return -EINVAL;
+ } else if (rs_is_reshaping(rs)) {
+ DMERR("'rebuild' specified while raid set is being reshaped (reshape_position=%llu)",
+ (unsigned long long) mddev->reshape_position);
+ return -EINVAL;
+ }
}
/*
* Now we set the Faulty bit for those devices that are
* recorded in the superblock as failed.
*/
+ sb_retrieve_failed_devices(sb, failed_devices);
rdev_for_each(r, mddev) {
if (!r->sb_page)
continue;
sb2 = page_address(r->sb_page);
sb2->failed_devices = 0;
+ memset(sb2->extended_failed_devices, 0, sizeof(sb2->extended_failed_devices));
/*
* Check for any device re-ordering.
*/
if (!test_bit(FirstUse, &r->flags) && (r->raid_disk >= 0)) {
role = le32_to_cpu(sb2->array_position);
+ if (role < 0)
+ continue;
+
if (role != r->raid_disk) {
- if (rs->raid_type->level != 1) {
- rs->ti->error = "Cannot change device "
- "positions in RAID array";
+ if (__is_raid10_near(mddev->layout)) {
+ if (mddev->raid_disks % __raid10_near_copies(mddev->layout) ||
+ rs->raid_disks % rs->raid10_copies) {
+ rs->ti->error =
+ "Cannot change raid10 near set to odd # of devices!";
+ return -EINVAL;
+ }
+
+ sb2->array_position = cpu_to_le32(r->raid_disk);
+
+ } else if (!(rs_is_raid10(rs) && rt_is_raid0(rs->raid_type)) &&
+ !(rs_is_raid0(rs) && rt_is_raid10(rs->raid_type)) &&
+ !rt_is_raid1(rs->raid_type)) {
+ rs->ti->error = "Cannot change device positions in raid set";
return -EINVAL;
}
- DMINFO("RAID1 device #%d now at position #%d",
- role, r->raid_disk);
+
+ DMINFO("raid device #%d now at position #%d", role, r->raid_disk);
}
/*
* Partial recovery is performed on
* returning failed devices.
*/
- if (failed_devices & (1 << role))
+ if (test_bit(role, (void *) failed_devices))
set_bit(Faulty, &r->flags);
}
}
@@ -1028,41 +2244,60 @@ static int super_init_validation(struct mddev *mddev, struct md_rdev *rdev)
static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
{
struct mddev *mddev = &rs->md;
- struct dm_raid_superblock *sb = page_address(rdev->sb_page);
+ struct dm_raid_superblock *sb;
+
+ if (rs_is_raid0(rs) || !rdev->sb_page)
+ return 0;
+
+ sb = page_address(rdev->sb_page);
/*
* If mddev->events is not set, we know we have not yet initialized
* the array.
*/
- if (!mddev->events && super_init_validation(mddev, rdev))
+ if (!mddev->events && super_init_validation(rs, rdev))
return -EINVAL;
- if (le32_to_cpu(sb->features)) {
- rs->ti->error = "Unable to assemble array: No feature flags supported yet";
+ if (le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) {
+ rs->ti->error = "Unable to assemble array: Unknown flag(s) in compatible feature flags";
+ return -EINVAL;
+ }
+
+ if (sb->incompat_features) {
+ rs->ti->error = "Unable to assemble array: No incompatible feature flags supported yet";
return -EINVAL;
}
/* Enable bitmap creation for RAID levels != 0 */
- mddev->bitmap_info.offset = (rs->raid_type->level) ? to_sector(4096) : 0;
+ mddev->bitmap_info.offset = rt_is_raid0(rs->raid_type) ? 0 : to_sector(4096);
rdev->mddev->bitmap_info.default_offset = mddev->bitmap_info.offset;
- if (!test_bit(FirstUse, &rdev->flags)) {
+ if (!test_and_clear_bit(FirstUse, &rdev->flags)) {
+ /* Retrieve device size stored in superblock to be prepared for shrink */
+ rdev->sectors = le64_to_cpu(sb->sectors);
rdev->recovery_offset = le64_to_cpu(sb->disk_recovery_offset);
- if (rdev->recovery_offset != MaxSector)
- clear_bit(In_sync, &rdev->flags);
+ if (rdev->recovery_offset == MaxSector)
+ set_bit(In_sync, &rdev->flags);
+ /*
+ * If no reshape in progress -> we're recovering single
+ * disk(s) and have to set the device(s) to out-of-sync
+ */
+ else if (!rs_is_reshaping(rs))
+ clear_bit(In_sync, &rdev->flags); /* Mandatory for recovery */
}
/*
* If a device comes back, set it as not In_sync and no longer faulty.
*/
- if (test_bit(Faulty, &rdev->flags)) {
- clear_bit(Faulty, &rdev->flags);
+ if (test_and_clear_bit(Faulty, &rdev->flags)) {
+ rdev->recovery_offset = 0;
clear_bit(In_sync, &rdev->flags);
rdev->saved_raid_disk = rdev->raid_disk;
- rdev->recovery_offset = 0;
}
- clear_bit(FirstUse, &rdev->flags);
+ /* Reshape support -> restore repective data offsets */
+ rdev->data_offset = le64_to_cpu(sb->data_offset);
+ rdev->new_data_offset = le64_to_cpu(sb->new_data_offset);
return 0;
}
@@ -1072,7 +2307,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
*/
static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
{
- int ret;
+ int r;
struct raid_dev *dev;
struct md_rdev *rdev, *tmp, *freshest;
struct mddev *mddev = &rs->md;
@@ -1082,30 +2317,35 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
/*
* Skipping super_load due to CTR_FLAG_SYNC will cause
* the array to undergo initialization again as
- * though it were new. This is the intended effect
+ * though it were new. This is the intended effect
* of the "sync" directive.
*
* When reshaping capability is added, we must ensure
* that the "sync" directive is disallowed during the
* reshape.
*/
- rdev->sectors = to_sector(i_size_read(rdev->bdev->bd_inode));
-
- if (rs->ctr_flags & CTR_FLAG_SYNC)
+ if (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags))
continue;
if (!rdev->meta_bdev)
continue;
- ret = super_load(rdev, freshest);
+ r = super_load(rdev, freshest);
- switch (ret) {
+ switch (r) {
case 1:
freshest = rdev;
break;
case 0:
break;
default:
+ /*
+ * We have to keep any raid0 data/metadata device pairs or
+ * the MD raid0 personality will fail to start the array.
+ */
+ if (rs_is_raid0(rs))
+ continue;
+
dev = container_of(rdev, struct raid_dev, rdev);
if (dev->meta_dev)
dm_put_device(ti, dev->meta_dev);
@@ -1148,25 +2388,334 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
* Validation of the freshest device provides the source of
* validation for the remaining devices.
*/
- ti->error = "Unable to assemble array: Invalid superblocks";
+ rs->ti->error = "Unable to assemble array: Invalid superblocks";
if (super_validate(rs, freshest))
return -EINVAL;
rdev_for_each(rdev, mddev)
if ((rdev != freshest) && super_validate(rs, rdev))
return -EINVAL;
+ return 0;
+}
+
+/*
+ * Adjust data_offset and new_data_offset on all disk members of @rs
+ * for out of place reshaping if requested by contructor
+ *
+ * We need free space at the beginning of each raid disk for forward
+ * and at the end for backward reshapes which userspace has to provide
+ * via remapping/reordering of space.
+ */
+static int rs_adjust_data_offsets(struct raid_set *rs)
+{
+ sector_t data_offset = 0, new_data_offset = 0;
+ struct md_rdev *rdev;
+
+ /* Constructor did not request data offset change */
+ if (!test_bit(__CTR_FLAG_DATA_OFFSET, &rs->ctr_flags)) {
+ if (!rs_is_reshapable(rs))
+ goto out;
+
+ return 0;
+ }
+
+ /* HM FIXME: get InSync raid_dev? */
+ rdev = &rs->dev[0].rdev;
+
+ if (rs->delta_disks < 0) {
+ /*
+ * Removing disks (reshaping backwards):
+ *
+ * - before reshape: data is at offset 0 and free space
+ * is at end of each component LV
+ *
+ * - after reshape: data is at offset rs->data_offset != 0 on each component LV
+ */
+ data_offset = 0;
+ new_data_offset = rs->data_offset;
+
+ } else if (rs->delta_disks > 0) {
+ /*
+ * Adding disks (reshaping forwards):
+ *
+ * - before reshape: data is at offset rs->data_offset != 0 and
+ * free space is at begin of each component LV
+ *
+ * - after reshape: data is at offset 0 on each component LV
+ */
+ data_offset = rs->data_offset;
+ new_data_offset = 0;
+
+ } else {
+ /*
+ * User space passes in 0 for data offset after having removed reshape space
+ *
+ * - or - (data offset != 0)
+ *
+ * Changing RAID layout or chunk size -> toggle offsets
+ *
+ * - before reshape: data is at offset rs->data_offset 0 and
+ * free space is at end of each component LV
+ * -or-
+ * data is at offset rs->data_offset != 0 and
+ * free space is at begin of each component LV
+ *
+ * - after reshape: data is at offset 0 if it was at offset != 0
+ * or at offset != 0 if it was at offset 0
+ * on each component LV
+ *
+ */
+ data_offset = rs->data_offset ? rdev->data_offset : 0;
+ new_data_offset = data_offset ? 0 : rs->data_offset;
+ set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+ }
+
+ /*
+ * Make sure we got a minimum amount of free sectors per device
+ */
+ if (rs->data_offset &&
+ to_sector(i_size_read(rdev->bdev->bd_inode)) - rdev->sectors < MIN_FREE_RESHAPE_SPACE) {
+ rs->ti->error = data_offset ? "No space for forward reshape" :
+ "No space for backward reshape";
+ return -ENOSPC;
+ }
+out:
+ /* Adjust data offsets on all rdevs */
+ rdev_for_each(rdev, &rs->md) {
+ rdev->data_offset = data_offset;
+ rdev->new_data_offset = new_data_offset;
+ }
+
+ return 0;
+}
+
+/* Userpace reordered disks -> adjust raid_disk indexes in @rs */
+static void __reorder_raid_disk_indexes(struct raid_set *rs)
+{
+ int i = 0;
+ struct md_rdev *rdev;
+
+ rdev_for_each(rdev, &rs->md) {
+ rdev->raid_disk = i++;
+ rdev->saved_raid_disk = rdev->new_raid_disk = -1;
+ }
+}
+
+/*
+ * Setup @rs for takeover by a different raid level
+ */
+static int rs_setup_takeover(struct raid_set *rs)
+{
+ struct mddev *mddev = &rs->md;
+ struct md_rdev *rdev;
+ unsigned int d = mddev->raid_disks = rs->raid_disks;
+ sector_t new_data_offset = rs->dev[0].rdev.data_offset ? 0 : rs->data_offset;
+
+ if (rt_is_raid10(rs->raid_type)) {
+ if (mddev->level == 0) {
+ /* Userpace reordered disks -> adjust raid_disk indexes */
+ __reorder_raid_disk_indexes(rs);
+
+ /* raid0 -> raid10_far layout */
+ mddev->layout = raid10_format_to_md_layout(rs, ALGORITHM_RAID10_FAR,
+ rs->raid10_copies);
+ } else if (mddev->level == 1)
+ /* raid1 -> raid10_near layout */
+ mddev->layout = raid10_format_to_md_layout(rs, ALGORITHM_RAID10_NEAR,
+ rs->raid_disks);
+ else
+ return -EINVAL;
+
+ }
+
+ clear_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
+ mddev->recovery_cp = MaxSector;
+
+ while (d--) {
+ rdev = &rs->dev[d].rdev;
+
+ if (test_bit(d, (void *) rs->rebuild_disks)) {
+ clear_bit(In_sync, &rdev->flags);
+ clear_bit(Faulty, &rdev->flags);
+ mddev->recovery_cp = rdev->recovery_offset = 0;
+ /* Bitmap has to be created when we do an "up" takeover */
+ set_bit(MD_ARRAY_FIRST_USE, &mddev->flags);
+ }
+
+ rdev->new_data_offset = new_data_offset;
+ }
+
+ return 0;
+}
+
+/* Prepare @rs for reshape */
+static int rs_prepare_reshape(struct raid_set *rs)
+{
+ bool reshape;
+ struct mddev *mddev = &rs->md;
+
+ if (rs_is_raid10(rs)) {
+ if (rs->raid_disks != mddev->raid_disks &&
+ __is_raid10_near(mddev->layout) &&
+ rs->raid10_copies &&
+ rs->raid10_copies != __raid10_near_copies(mddev->layout)) {
+ /*
+ * raid disk have to be multiple of data copies to allow this conversion,
+ *
+ * This is actually not a reshape it is a
+ * rebuild of any additional mirrors per group
+ */
+ if (rs->raid_disks % rs->raid10_copies) {
+ rs->ti->error = "Can't reshape raid10 mirror groups";
+ return -EINVAL;
+ }
+
+ /* Userpace reordered disks to add/remove mirrors -> adjust raid_disk indexes */
+ __reorder_raid_disk_indexes(rs);
+ mddev->layout = raid10_format_to_md_layout(rs, ALGORITHM_RAID10_NEAR,
+ rs->raid10_copies);
+ mddev->new_layout = mddev->layout;
+ reshape = false;
+ } else
+ reshape = true;
+
+ } else if (rs_is_raid456(rs))
+ reshape = true;
+
+ else if (rs_is_raid1(rs)) {
+ if (rs->delta_disks) {
+ /* Process raid1 via delta_disks */
+ mddev->degraded = rs->delta_disks < 0 ? -rs->delta_disks : rs->delta_disks;
+ reshape = true;
+ } else {
+ /* Process raid1 without delta_disks */
+ mddev->raid_disks = rs->raid_disks;
+ reshape = false;
+ }
+ } else {
+ rs->ti->error = "Called with bogus raid type";
+ return -EINVAL;
+ }
+
+ if (reshape) {
+ set_bit(RT_FLAG_RESHAPE_RS, &rs->runtime_flags);
+ set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+ } else if (mddev->raid_disks < rs->raid_disks)
+ /* Create new superblocks and bitmaps, if any new disks */
+ set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
return 0;
}
/*
+ *
+ * - change raid layout
+ * - change chunk size
+ * - add disks
+ * - remove disks
+ */
+static int rs_setup_reshape(struct raid_set *rs)
+{
+ int r = 0;
+ unsigned int cur_raid_devs, d;
+ struct mddev *mddev = &rs->md;
+ struct md_rdev *rdev;
+
+ mddev->delta_disks = rs->delta_disks;
+ cur_raid_devs = mddev->raid_disks;
+
+ /* Ignore impossible layout change whilst adding/removing disks */
+ if (mddev->delta_disks &&
+ mddev->layout != mddev->new_layout) {
+ DMINFO("Ignoring invalid layout change with delta_disks=%d", rs->delta_disks);
+ mddev->new_layout = mddev->layout;
+ }
+
+ /*
+ * Adjust array size:
+ *
+ * - in case of adding disks, array size has
+ * to grow after the disk adding reshape,
+ * which'll hapen in the event handler;
+ * reshape will happen forward, so space has to
+ * be available at the beginning of each disk
+ *
+ * - in case of removing disks, array size
+ * has to shrink before starting the reshape,
+ * which'll happen here;
+ * reshape will happen backward, so space has to
+ * be available at the end of each disk
+ *
+ * - data_offset and new_data_offset are
+ * adjusted for aforementioned out of place
+ * reshaping based on userspace passing in
+ * the "data_offset <sectors>" key/value
+ * pair via the constructor
+ */
+
+ /* Add disk(s) */
+ if (rs->delta_disks > 0) {
+ /* Prepare disks for check in raid4/5/6/10 {check|start}_reshape */
+ for (d = cur_raid_devs; d < rs->raid_disks; d++) {
+ rdev = &rs->dev[d].rdev;
+ clear_bit(In_sync, &rdev->flags);
+
+ /*
+ * save_raid_disk needs to be -1, or recovery_offset will be set to 0
+ * by md, which'll store that erroneously in the superblock on reshape
+ */
+ rdev->saved_raid_disk = -1;
+ rdev->raid_disk = d;
+
+ rdev->sectors = mddev->dev_sectors;
+ rdev->recovery_offset = rs_is_raid1(rs) ? 0 : MaxSector;
+ }
+
+ mddev->reshape_backwards = 0; /* adding disks -> forward reshape */
+
+ /* Remove disk(s) */
+ } else if (rs->delta_disks < 0) {
+ r = rs_set_dev_and_array_sectors(rs, true);
+ mddev->reshape_backwards = 1; /* removing disk(s) -> backward reshape */
+
+ /* Change layout and/or chunk size */
+ } else {
+ /*
+ * Reshape layout (e.g. raid5_ls -> raid5_n) and/or chunk size:
+ *
+ * keeping number of disks and do layout change ->
+ *
+ * toggle reshape_backward depending on data_offset:
+ *
+ * - free space upfront -> reshape forward
+ *
+ * - free space at the end -> reshape backward
+ *
+ *
+ * This utilizes free reshape space avoiding the need
+ * for userspace to move (parts of) LV segments in
+ * case of layout/chunksize change (for disk
+ * adding/removing reshape space has to be at
+ * the proper address (see above with delta_disks):
+ *
+ * add disk(s) -> begin
+ * remove disk(s)-> end
+ */
+ mddev->reshape_backwards = rs->dev[0].rdev.data_offset ? 0 : 1;
+ }
+
+ return r;
+}
+
+/*
* Enable/disable discard support on RAID set depending on
* RAID level and discard properties of underlying RAID members.
*/
-static void configure_discard_support(struct dm_target *ti, struct raid_set *rs)
+static void configure_discard_support(struct raid_set *rs)
{
int i;
bool raid456;
+ struct dm_target *ti = rs->ti;
/* Assume discards not supported until after checks below. */
ti->discards_supported = false;
@@ -1174,7 +2723,7 @@ static void configure_discard_support(struct dm_target *ti, struct raid_set *rs)
/* RAID level 4,5,6 require discard_zeroes_data for data integrity! */
raid456 = (rs->md.level == 4 || rs->md.level == 5 || rs->md.level == 6);
- for (i = 0; i < rs->md.raid_disks; i++) {
+ for (i = 0; i < rs->raid_disks; i++) {
struct request_queue *q;
if (!rs->dev[i].rdev.bdev)
@@ -1207,118 +2756,251 @@ static void configure_discard_support(struct dm_target *ti, struct raid_set *rs)
}
/*
- * Construct a RAID4/5/6 mapping:
+ * Construct a RAID0/1/10/4/5/6 mapping:
* Args:
- * <raid_type> <#raid_params> <raid_params> \
- * <#raid_devs> { <meta_dev1> <dev1> .. <meta_devN> <devN> }
+ * <raid_type> <#raid_params> <raid_params>{0,} \
+ * <#raid_devs> [<meta_dev1> <dev1>]{1,}
*
- * <raid_params> varies by <raid_type>. See 'parse_raid_params' for
+ * <raid_params> varies by <raid_type>. See 'parse_raid_params' for
* details on possible <raid_params>.
+ *
+ * Userspace is free to initialize the metadata devices, hence the superblocks to
+ * enforce recreation based on the passed in table parameters.
+ *
*/
-static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
+static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
- int ret;
+ int r;
+ bool resize;
struct raid_type *rt;
- unsigned long num_raid_params, num_raid_devs;
+ unsigned int num_raid_params, num_raid_devs;
+ sector_t calculated_dev_sectors;
struct raid_set *rs = NULL;
-
- /* Must have at least <raid_type> <#raid_params> */
- if (argc < 2) {
- ti->error = "Too few arguments";
+ const char *arg;
+ struct rs_layout rs_layout;
+ struct dm_arg_set as = { argc, argv }, as_nrd;
+ struct dm_arg _args[] = {
+ { 0, as.argc, "Cannot understand number of raid parameters" },
+ { 1, 254, "Cannot understand number of raid devices parameters" }
+ };
+
+ /* Must have <raid_type> */
+ arg = dm_shift_arg(&as);
+ if (!arg) {
+ ti->error = "No arguments";
return -EINVAL;
}
- /* raid type */
- rt = get_raid_type(argv[0]);
+ rt = get_raid_type(arg);
if (!rt) {
ti->error = "Unrecognised raid_type";
return -EINVAL;
}
- argc--;
- argv++;
-
- /* number of RAID parameters */
- if (kstrtoul(argv[0], 10, &num_raid_params) < 0) {
- ti->error = "Cannot understand number of RAID parameters";
- return -EINVAL;
- }
- argc--;
- argv++;
- /* Skip over RAID params for now and find out # of devices */
- if (num_raid_params >= argc) {
- ti->error = "Arguments do not agree with counts given";
+ /* Must have <#raid_params> */
+ if (dm_read_arg_group(_args, &as, &num_raid_params, &ti->error))
return -EINVAL;
- }
- if ((kstrtoul(argv[num_raid_params], 10, &num_raid_devs) < 0) ||
- (num_raid_devs > MAX_RAID_DEVICES)) {
- ti->error = "Cannot understand number of raid devices";
+ /* number of raid device tupples <meta_dev data_dev> */
+ as_nrd = as;
+ dm_consume_args(&as_nrd, num_raid_params);
+ _args[1].max = (as_nrd.argc - 1) / 2;
+ if (dm_read_arg(_args + 1, &as_nrd, &num_raid_devs, &ti->error))
return -EINVAL;
- }
- argc -= num_raid_params + 1; /* +1: we already have num_raid_devs */
- if (argc != (num_raid_devs * 2)) {
- ti->error = "Supplied RAID devices does not match the count given";
+ if (!__within_range(num_raid_devs, 1, MAX_RAID_DEVICES)) {
+ ti->error = "Invalid number of supplied raid devices";
return -EINVAL;
}
- rs = context_alloc(ti, rt, (unsigned)num_raid_devs);
+ rs = raid_set_alloc(ti, rt, num_raid_devs);
if (IS_ERR(rs))
return PTR_ERR(rs);
- ret = parse_raid_params(rs, argv, (unsigned)num_raid_params);
- if (ret)
+ r = parse_raid_params(rs, &as, num_raid_params);
+ if (r)
goto bad;
- argv += num_raid_params + 1;
-
- ret = dev_parms(rs, argv);
- if (ret)
+ r = parse_dev_params(rs, &as);
+ if (r)
goto bad;
rs->md.sync_super = super_sync;
- ret = analyse_superblocks(ti, rs);
- if (ret)
+
+ /*
+ * Calculate ctr requested array and device sizes to allow
+ * for superblock analysis needing device sizes defined.
+ *
+ * Any existing superblock will overwrite the array and device sizes
+ */
+ r = rs_set_dev_and_array_sectors(rs, false);
+ if (r)
+ goto bad;
+
+ calculated_dev_sectors = rs->dev[0].rdev.sectors;
+
+ /*
+ * Backup any new raid set level, layout, ...
+ * requested to be able to compare to superblock
+ * members for conversion decisions.
+ */
+ rs_config_backup(rs, &rs_layout);
+
+ r = analyse_superblocks(ti, rs);
+ if (r)
goto bad;
+ resize = calculated_dev_sectors != rs->dev[0].rdev.sectors;
+
INIT_WORK(&rs->md.event_work, do_table_event);
ti->private = rs;
ti->num_flush_bios = 1;
+ /* Restore any requested new layout for conversion decision */
+ rs_config_restore(rs, &rs_layout);
+
/*
- * Disable/enable discard support on RAID set.
+ * Now that we have any superblock metadata available,
+ * check for new, recovering, reshaping, to be taken over,
+ * to be reshaped or an existing, unchanged raid set to
+ * run in sequence.
*/
- configure_discard_support(ti, rs);
+ if (test_bit(MD_ARRAY_FIRST_USE, &rs->md.flags)) {
+ /* A new raid6 set has to be recovered to ensure proper parity and Q-Syndrome */
+ if (rs_is_raid6(rs) &&
+ test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)) {
+ ti->error = "'nosync' not allowed for new raid6 set";
+ r = -EINVAL;
+ goto bad;
+ }
+ rs_setup_recovery(rs, 0);
+ set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+ rs_set_new(rs);
+ } else if (rs_is_recovering(rs)) {
+ /* A recovering raid set may be resized */
+ ; /* skip setup rs */
+ } else if (rs_is_reshaping(rs)) {
+ /* Have to reject size change request during reshape */
+ if (resize) {
+ ti->error = "Can't resize a reshaping raid set";
+ r = -EPERM;
+ goto bad;
+ }
+ /* skip setup rs */
+ } else if (rs_takeover_requested(rs)) {
+ if (rs_is_reshaping(rs)) {
+ ti->error = "Can't takeover a reshaping raid set";
+ r = -EPERM;
+ goto bad;
+ }
+
+ /*
+ * If a takeover is needed, userspace sets any additional
+ * devices to rebuild and we can check for a valid request here.
+ *
+ * If acceptible, set the level to the new requested
+ * one, prohibit requesting recovery, allow the raid
+ * set to run and store superblocks during resume.
+ */
+ r = rs_check_takeover(rs);
+ if (r)
+ goto bad;
+
+ r = rs_setup_takeover(rs);
+ if (r)
+ goto bad;
+
+ set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+ /* Takeover ain't recovery, so disable recovery */
+ rs_setup_recovery(rs, MaxSector);
+ rs_set_new(rs);
+ } else if (rs_reshape_requested(rs)) {
+ /*
+ * We can only prepare for a reshape here, because the
+ * raid set needs to run to provide the repective reshape
+ * check functions via its MD personality instance.
+ *
+ * So do the reshape check after md_run() succeeded.
+ */
+ r = rs_prepare_reshape(rs);
+ if (r)
+ return r;
+
+ /* Reshaping ain't recovery, so disable recovery */
+ rs_setup_recovery(rs, MaxSector);
+ rs_set_cur(rs);
+ } else {
+ /* May not set recovery when a device rebuild is requested */
+ if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) {
+ rs_setup_recovery(rs, MaxSector);
+ set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
+ } else
+ rs_setup_recovery(rs, test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) ?
+ 0 : (resize ? calculated_dev_sectors : MaxSector));
+ rs_set_cur(rs);
+ }
+
+ /* If constructor requested it, change data and new_data offsets */
+ r = rs_adjust_data_offsets(rs);
+ if (r)
+ goto bad;
+
+ /* Start raid set read-only and assumed clean to change in raid_resume() */
+ rs->md.ro = 1;
+ rs->md.in_sync = 1;
+ set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
/* Has to be held on running the array */
mddev_lock_nointr(&rs->md);
- ret = md_run(&rs->md);
+ r = md_run(&rs->md);
rs->md.in_sync = 0; /* Assume already marked dirty */
- mddev_unlock(&rs->md);
- if (ret) {
- ti->error = "Fail to run raid array";
+ if (r) {
+ ti->error = "Failed to run raid array";
+ mddev_unlock(&rs->md);
goto bad;
}
- if (ti->len != rs->md.array_sectors) {
- ti->error = "Array size does not match requested target length";
- ret = -EINVAL;
- goto size_mismatch;
- }
rs->callbacks.congested_fn = raid_is_congested;
dm_table_add_target_callbacks(ti->table, &rs->callbacks);
mddev_suspend(&rs->md);
+
+ /* Try to adjust the raid4/5/6 stripe cache size to the stripe size */
+ if (rs_is_raid456(rs)) {
+ r = rs_set_raid456_stripe_cache(rs);
+ if (r)
+ goto bad_stripe_cache;
+ }
+
+ /* Now do an early reshape check */
+ if (test_bit(RT_FLAG_RESHAPE_RS, &rs->runtime_flags)) {
+ r = rs_check_reshape(rs);
+ if (r)
+ goto bad_check_reshape;
+
+ /* Restore new, ctr requested layout to perform check */
+ rs_config_restore(rs, &rs_layout);
+
+ if (rs->md.pers->start_reshape) {
+ r = rs->md.pers->check_reshape(&rs->md);
+ if (r) {
+ ti->error = "Reshape check failed";
+ goto bad_check_reshape;
+ }
+ }
+ }
+
+ mddev_unlock(&rs->md);
return 0;
-size_mismatch:
+bad_stripe_cache:
+bad_check_reshape:
md_stop(&rs->md);
bad:
- context_free(rs);
+ raid_set_free(rs);
- return ret;
+ return r;
}
static void raid_dtr(struct dm_target *ti)
@@ -1327,7 +3009,7 @@ static void raid_dtr(struct dm_target *ti)
list_del_init(&rs->callbacks.list);
md_stop(&rs->md);
- context_free(rs);
+ raid_set_free(rs);
}
static int raid_map(struct dm_target *ti, struct bio *bio)
@@ -1335,11 +3017,23 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
struct raid_set *rs = ti->private;
struct mddev *mddev = &rs->md;
+ /*
+ * If we're reshaping to add disk(s)), ti->len and
+ * mddev->array_sectors will differ during the process
+ * (ti->len > mddev->array_sectors), so we have to requeue
+ * bios with addresses > mddev->array_sectors here or
+ * there will occur accesses past EOD of the component
+ * data images thus erroring the raid set.
+ */
+ if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
+ return DM_MAPIO_REQUEUE;
+
mddev->pers->make_request(mddev, bio);
return DM_MAPIO_SUBMITTED;
}
+/* Return string describing the current sync action of @mddev */
static const char *decipher_sync_action(struct mddev *mddev)
{
if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
@@ -1365,195 +3059,260 @@ static const char *decipher_sync_action(struct mddev *mddev)
return "idle";
}
-static void raid_status(struct dm_target *ti, status_type_t type,
- unsigned status_flags, char *result, unsigned maxlen)
+/*
+ * Return status string @rdev
+ *
+ * Status characters:
+ *
+ * 'D' = Dead/Failed device
+ * 'a' = Alive but not in-sync
+ * 'A' = Alive and in-sync
+ */
+static const char *__raid_dev_status(struct md_rdev *rdev, bool array_in_sync)
{
- struct raid_set *rs = ti->private;
- unsigned raid_param_cnt = 1; /* at least 1 for chunksize */
- unsigned sz = 0;
- int i, array_in_sync = 0;
- sector_t sync;
+ if (test_bit(Faulty, &rdev->flags))
+ return "D";
+ else if (!array_in_sync || !test_bit(In_sync, &rdev->flags))
+ return "a";
+ else
+ return "A";
+}
- switch (type) {
- case STATUSTYPE_INFO:
- DMEMIT("%s %d ", rs->raid_type->name, rs->md.raid_disks);
+/* Helper to return resync/reshape progress for @rs and @array_in_sync */
+static sector_t rs_get_progress(struct raid_set *rs,
+ sector_t resync_max_sectors, bool *array_in_sync)
+{
+ sector_t r, recovery_cp, curr_resync_completed;
+ struct mddev *mddev = &rs->md;
- if (rs->raid_type->level) {
- if (test_bit(MD_RECOVERY_RUNNING, &rs->md.recovery))
- sync = rs->md.curr_resync_completed;
- else
- sync = rs->md.recovery_cp;
-
- if (sync >= rs->md.resync_max_sectors) {
- /*
- * Sync complete.
- */
- array_in_sync = 1;
- sync = rs->md.resync_max_sectors;
- } else if (test_bit(MD_RECOVERY_REQUESTED, &rs->md.recovery)) {
- /*
- * If "check" or "repair" is occurring, the array has
- * undergone and initial sync and the health characters
- * should not be 'a' anymore.
- */
- array_in_sync = 1;
+ curr_resync_completed = mddev->curr_resync_completed ?: mddev->recovery_cp;
+ recovery_cp = mddev->recovery_cp;
+ *array_in_sync = false;
+
+ if (rs_is_raid0(rs)) {
+ r = resync_max_sectors;
+ *array_in_sync = true;
+
+ } else {
+ r = mddev->reshape_position;
+
+ /* Reshape is relative to the array size */
+ if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ||
+ r != MaxSector) {
+ if (r == MaxSector) {
+ *array_in_sync = true;
+ r = resync_max_sectors;
} else {
- /*
- * The array may be doing an initial sync, or it may
- * be rebuilding individual components. If all the
- * devices are In_sync, then it is the array that is
- * being initialized.
- */
- for (i = 0; i < rs->md.raid_disks; i++)
- if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
- array_in_sync = 1;
+ /* Got to reverse on backward reshape */
+ if (mddev->reshape_backwards)
+ r = mddev->array_sectors - r;
+
+ /* Devide by # of data stripes */
+ sector_div(r, mddev_data_stripes(rs));
}
+
+ /* Sync is relative to the component device size */
+ } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+ r = curr_resync_completed;
+ else
+ r = recovery_cp;
+
+ if (r == MaxSector) {
+ /*
+ * Sync complete.
+ */
+ *array_in_sync = true;
+ r = resync_max_sectors;
+ } else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+ /*
+ * If "check" or "repair" is occurring, the raid set has
+ * undergone an initial sync and the health characters
+ * should not be 'a' anymore.
+ */
+ *array_in_sync = true;
} else {
- /* RAID0 */
- array_in_sync = 1;
- sync = rs->md.resync_max_sectors;
- }
+ struct md_rdev *rdev;
- /*
- * Status characters:
- * 'D' = Dead/Failed device
- * 'a' = Alive but not in-sync
- * 'A' = Alive and in-sync
- */
- for (i = 0; i < rs->md.raid_disks; i++) {
- if (test_bit(Faulty, &rs->dev[i].rdev.flags))
- DMEMIT("D");
- else if (!array_in_sync ||
- !test_bit(In_sync, &rs->dev[i].rdev.flags))
- DMEMIT("a");
- else
- DMEMIT("A");
+ /*
+ * The raid set may be doing an initial sync, or it may
+ * be rebuilding individual components. If all the
+ * devices are In_sync, then it is the raid set that is
+ * being initialized.
+ */
+ rdev_for_each(rdev, mddev)
+ if (!test_bit(In_sync, &rdev->flags))
+ *array_in_sync = true;
+#if 0
+ r = 0; /* HM FIXME: TESTME: https://bugzilla.redhat.com/show_bug.cgi?id=1210637 ? */
+#endif
}
+ }
+
+ return r;
+}
+
+/* Helper to return @dev name or "-" if !@dev */
+static const char *__get_dev_name(struct dm_dev *dev)
+{
+ return dev ? dev->name : "-";
+}
+
+static void raid_status(struct dm_target *ti, status_type_t type,
+ unsigned int status_flags, char *result, unsigned int maxlen)
+{
+ struct raid_set *rs = ti->private;
+ struct mddev *mddev = &rs->md;
+ struct r5conf *conf = mddev->private;
+ int i, max_nr_stripes = conf ? conf->max_nr_stripes : 0;
+ bool array_in_sync;
+ unsigned int raid_param_cnt = 1; /* at least 1 for chunksize */
+ unsigned int sz = 0;
+ unsigned int rebuild_disks;
+ unsigned int write_mostly_params = 0;
+ sector_t progress, resync_max_sectors, resync_mismatches;
+ const char *sync_action;
+ struct raid_type *rt;
+ struct md_rdev *rdev;
+
+ switch (type) {
+ case STATUSTYPE_INFO:
+ /* *Should* always succeed */
+ rt = get_raid_type_by_ll(mddev->new_level, mddev->new_layout);
+ if (!rt)
+ return;
+
+ DMEMIT("%s %d ", rt->name, mddev->raid_disks);
+
+ /* Access most recent mddev properties for status output */
+ smp_rmb();
+ /* Get sensible max sectors even if raid set not yet started */
+ resync_max_sectors = test_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags) ?
+ mddev->resync_max_sectors : mddev->dev_sectors;
+ progress = rs_get_progress(rs, resync_max_sectors, &array_in_sync);
+ resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ?
+ atomic64_read(&mddev->resync_mismatches) : 0;
+ sync_action = decipher_sync_action(&rs->md);
+
+ /* HM FIXME: do we want another state char for raid0? It shows 'D' or 'A' now */
+ rdev_for_each(rdev, mddev)
+ DMEMIT(__raid_dev_status(rdev, array_in_sync));
/*
- * In-sync ratio:
+ * In-sync/Reshape ratio:
* The in-sync ratio shows the progress of:
- * - Initializing the array
- * - Rebuilding a subset of devices of the array
+ * - Initializing the raid set
+ * - Rebuilding a subset of devices of the raid set
* The user can distinguish between the two by referring
* to the status characters.
+ *
+ * The reshape ratio shows the progress of
+ * changing the raid layout or the number of
+ * disks of a raid set
*/
- DMEMIT(" %llu/%llu",
- (unsigned long long) sync,
- (unsigned long long) rs->md.resync_max_sectors);
+ DMEMIT(" %llu/%llu", (unsigned long long) progress,
+ (unsigned long long) resync_max_sectors);
/*
+ * v1.5.0+:
+ *
* Sync action:
- * See Documentation/device-mapper/dm-raid.c for
+ * See Documentation/device-mapper/dm-raid.txt for
* information on each of these states.
*/
- DMEMIT(" %s", decipher_sync_action(&rs->md));
+ DMEMIT(" %s", sync_action);
/*
+ * v1.5.0+:
+ *
* resync_mismatches/mismatch_cnt
* This field shows the number of discrepancies found when
- * performing a "check" of the array.
+ * performing a "check" of the raid set.
*/
- DMEMIT(" %llu",
- (strcmp(rs->md.last_sync_action, "check")) ? 0 :
- (unsigned long long)
- atomic64_read(&rs->md.resync_mismatches));
- break;
- case STATUSTYPE_TABLE:
- /* The string you would use to construct this array */
- for (i = 0; i < rs->md.raid_disks; i++) {
- if ((rs->ctr_flags & CTR_FLAG_REBUILD) &&
- rs->dev[i].data_dev &&
- !test_bit(In_sync, &rs->dev[i].rdev.flags))
- raid_param_cnt += 2; /* for rebuilds */
- if (rs->dev[i].data_dev &&
- test_bit(WriteMostly, &rs->dev[i].rdev.flags))
- raid_param_cnt += 2;
- }
-
- raid_param_cnt += (hweight32(rs->ctr_flags & ~CTR_FLAG_REBUILD) * 2);
- if (rs->ctr_flags & (CTR_FLAG_SYNC | CTR_FLAG_NOSYNC))
- raid_param_cnt--;
-
- DMEMIT("%s %u %u", rs->raid_type->name,
- raid_param_cnt, rs->md.chunk_sectors);
-
- if ((rs->ctr_flags & CTR_FLAG_SYNC) &&
- (rs->md.recovery_cp == MaxSector))
- DMEMIT(" sync");
- if (rs->ctr_flags & CTR_FLAG_NOSYNC)
- DMEMIT(" nosync");
-
- for (i = 0; i < rs->md.raid_disks; i++)
- if ((rs->ctr_flags & CTR_FLAG_REBUILD) &&
- rs->dev[i].data_dev &&
- !test_bit(In_sync, &rs->dev[i].rdev.flags))
- DMEMIT(" rebuild %u", i);
-
- if (rs->ctr_flags & CTR_FLAG_DAEMON_SLEEP)
- DMEMIT(" daemon_sleep %lu",
- rs->md.bitmap_info.daemon_sleep);
-
- if (rs->ctr_flags & CTR_FLAG_MIN_RECOVERY_RATE)
- DMEMIT(" min_recovery_rate %d", rs->md.sync_speed_min);
-
- if (rs->ctr_flags & CTR_FLAG_MAX_RECOVERY_RATE)
- DMEMIT(" max_recovery_rate %d", rs->md.sync_speed_max);
-
- for (i = 0; i < rs->md.raid_disks; i++)
- if (rs->dev[i].data_dev &&
- test_bit(WriteMostly, &rs->dev[i].rdev.flags))
- DMEMIT(" write_mostly %u", i);
-
- if (rs->ctr_flags & CTR_FLAG_MAX_WRITE_BEHIND)
- DMEMIT(" max_write_behind %lu",
- rs->md.bitmap_info.max_write_behind);
-
- if (rs->ctr_flags & CTR_FLAG_STRIPE_CACHE) {
- struct r5conf *conf = rs->md.private;
-
- /* convert from kiB to sectors */
- DMEMIT(" stripe_cache %d",
- conf ? conf->max_nr_stripes * 2 : 0);
- }
-
- if (rs->ctr_flags & CTR_FLAG_REGION_SIZE)
- DMEMIT(" region_size %lu",
- rs->md.bitmap_info.chunksize >> 9);
+ DMEMIT(" %llu", (unsigned long long) resync_mismatches);
- if (rs->ctr_flags & CTR_FLAG_RAID10_COPIES)
- DMEMIT(" raid10_copies %u",
- raid10_md_layout_to_copies(rs->md.layout));
-
- if (rs->ctr_flags & CTR_FLAG_RAID10_FORMAT)
- DMEMIT(" raid10_format %s",
- raid10_md_layout_to_format(rs->md.layout));
-
- DMEMIT(" %d", rs->md.raid_disks);
- for (i = 0; i < rs->md.raid_disks; i++) {
- if (rs->dev[i].meta_dev)
- DMEMIT(" %s", rs->dev[i].meta_dev->name);
- else
- DMEMIT(" -");
+ /*
+ * v1.9.0+:
+ *
+ * data_offset (needed for out of space reshaping)
+ * This field shows the data offset into the data
+ * image LV where the first stripes data starts.
+ *
+ * We keep data_offset equal on all raid disks of the set,
+ * so retrieving it from the first raid disk is sufficient.
+ */
+ DMEMIT(" %llu", (unsigned long long) rs->dev[0].rdev.data_offset);
+ break;
- if (rs->dev[i].data_dev)
- DMEMIT(" %s", rs->dev[i].data_dev->name);
- else
- DMEMIT(" -");
- }
+ case STATUSTYPE_TABLE:
+ /* Report the table line string you would use to construct this raid set */
+
+ /* Calculate raid parameter count */
+ for (i = 0; i < rs->raid_disks; i++)
+ if (test_bit(WriteMostly, &rs->dev[i].rdev.flags))
+ write_mostly_params += 2;
+ rebuild_disks = memweight(rs->rebuild_disks, DISKS_ARRAY_ELEMS * sizeof(*rs->rebuild_disks));
+ raid_param_cnt += rebuild_disks * 2 +
+ write_mostly_params +
+ hweight32(rs->ctr_flags & CTR_FLAG_OPTIONS_NO_ARGS) +
+ hweight32(rs->ctr_flags & CTR_FLAG_OPTIONS_ONE_ARG) * 2;
+ /* Emit table line */
+ DMEMIT("%s %u %u", rs->raid_type->name, raid_param_cnt, mddev->new_chunk_sectors);
+ if (test_bit(__CTR_FLAG_RAID10_FORMAT, &rs->ctr_flags))
+ DMEMIT(" %s %s", dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_FORMAT),
+ raid10_md_layout_to_format(mddev->layout));
+ if (test_bit(__CTR_FLAG_RAID10_COPIES, &rs->ctr_flags))
+ DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_COPIES),
+ raid10_md_layout_to_copies(mddev->layout));
+ if (test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags))
+ DMEMIT(" %s", dm_raid_arg_name_by_flag(CTR_FLAG_NOSYNC));
+ if (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags))
+ DMEMIT(" %s", dm_raid_arg_name_by_flag(CTR_FLAG_SYNC));
+ if (test_bit(__CTR_FLAG_REGION_SIZE, &rs->ctr_flags))
+ DMEMIT(" %s %llu", dm_raid_arg_name_by_flag(CTR_FLAG_REGION_SIZE),
+ (unsigned long long) to_sector(mddev->bitmap_info.chunksize));
+ if (test_bit(__CTR_FLAG_DATA_OFFSET, &rs->ctr_flags))
+ DMEMIT(" %s %llu", dm_raid_arg_name_by_flag(CTR_FLAG_DATA_OFFSET),
+ (unsigned long long) rs->data_offset);
+ if (test_bit(__CTR_FLAG_DAEMON_SLEEP, &rs->ctr_flags))
+ DMEMIT(" %s %lu", dm_raid_arg_name_by_flag(CTR_FLAG_DAEMON_SLEEP),
+ mddev->bitmap_info.daemon_sleep);
+ if (test_bit(__CTR_FLAG_DELTA_DISKS, &rs->ctr_flags))
+ DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_DELTA_DISKS),
+ max(rs->delta_disks, mddev->delta_disks));
+ if (test_bit(__CTR_FLAG_STRIPE_CACHE, &rs->ctr_flags))
+ DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_STRIPE_CACHE),
+ max_nr_stripes);
+ if (rebuild_disks)
+ for (i = 0; i < rs->raid_disks; i++)
+ if (test_bit(rs->dev[i].rdev.raid_disk, (void *) rs->rebuild_disks))
+ DMEMIT(" %s %u", dm_raid_arg_name_by_flag(CTR_FLAG_REBUILD),
+ rs->dev[i].rdev.raid_disk);
+ if (write_mostly_params)
+ for (i = 0; i < rs->raid_disks; i++)
+ if (test_bit(WriteMostly, &rs->dev[i].rdev.flags))
+ DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_WRITE_MOSTLY),
+ rs->dev[i].rdev.raid_disk);
+ if (test_bit(__CTR_FLAG_MAX_WRITE_BEHIND, &rs->ctr_flags))
+ DMEMIT(" %s %lu", dm_raid_arg_name_by_flag(CTR_FLAG_MAX_WRITE_BEHIND),
+ mddev->bitmap_info.max_write_behind);
+ if (test_bit(__CTR_FLAG_MAX_RECOVERY_RATE, &rs->ctr_flags))
+ DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_MAX_RECOVERY_RATE),
+ mddev->sync_speed_max);
+ if (test_bit(__CTR_FLAG_MIN_RECOVERY_RATE, &rs->ctr_flags))
+ DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_MIN_RECOVERY_RATE),
+ mddev->sync_speed_min);
+ DMEMIT(" %d", rs->raid_disks);
+ for (i = 0; i < rs->raid_disks; i++)
+ DMEMIT(" %s %s", __get_dev_name(rs->dev[i].meta_dev),
+ __get_dev_name(rs->dev[i].data_dev));
}
}
-static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
+static int raid_message(struct dm_target *ti, unsigned int argc, char **argv)
{
struct raid_set *rs = ti->private;
struct mddev *mddev = &rs->md;
- if (!strcasecmp(argv[0], "reshape")) {
- DMERR("Reshape not supported.");
- return -EINVAL;
- }
-
if (!mddev->pers || !mddev->pers->sync_request)
return -EINVAL;
@@ -1571,11 +3330,10 @@ static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
return -EBUSY;
else if (!strcasecmp(argv[0], "resync"))
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- else if (!strcasecmp(argv[0], "recover")) {
+ ; /* MD_RECOVERY_NEEDED set below */
+ else if (!strcasecmp(argv[0], "recover"))
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- } else {
+ else {
if (!strcasecmp(argv[0], "check"))
set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
else if (!!strcasecmp(argv[0], "repair"))
@@ -1588,11 +3346,11 @@ static int raid_message(struct dm_target *ti, unsigned argc, char **argv)
* canceling read-auto mode
*/
mddev->ro = 0;
- if (!mddev->suspended)
+ if (!mddev->suspended && mddev->sync_thread)
md_wakeup_thread(mddev->sync_thread);
}
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- if (!mddev->suspended)
+ if (!mddev->suspended && mddev->thread)
md_wakeup_thread(mddev->thread);
return 0;
@@ -1602,28 +3360,27 @@ static int raid_iterate_devices(struct dm_target *ti,
iterate_devices_callout_fn fn, void *data)
{
struct raid_set *rs = ti->private;
- unsigned i;
- int ret = 0;
+ unsigned int i;
+ int r = 0;
- for (i = 0; !ret && i < rs->md.raid_disks; i++)
+ for (i = 0; !r && i < rs->md.raid_disks; i++)
if (rs->dev[i].data_dev)
- ret = fn(ti,
+ r = fn(ti,
rs->dev[i].data_dev,
0, /* No offset on data devs */
rs->md.dev_sectors,
data);
- return ret;
+ return r;
}
static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
struct raid_set *rs = ti->private;
- unsigned chunk_size = rs->md.chunk_sectors << 9;
- struct r5conf *conf = rs->md.private;
+ unsigned int chunk_size = to_bytes(rs->md.chunk_sectors);
blk_limits_io_min(limits, chunk_size);
- blk_limits_io_opt(limits, chunk_size * (conf->raid_disks - conf->max_degraded));
+ blk_limits_io_opt(limits, chunk_size * mddev_data_stripes(rs));
}
static void raid_presuspend(struct dm_target *ti)
@@ -1637,21 +3394,33 @@ static void raid_postsuspend(struct dm_target *ti)
{
struct raid_set *rs = ti->private;
- mddev_suspend(&rs->md);
+ if (!rs->md.suspended)
+ mddev_suspend(&rs->md);
+
+ rs->md.ro = 1;
}
static void attempt_restore_of_faulty_devices(struct raid_set *rs)
{
int i;
- uint64_t failed_devices, cleared_failed_devices = 0;
+ uint64_t cleared_failed_devices[DISKS_ARRAY_ELEMS];
unsigned long flags;
+ bool cleared = false;
struct dm_raid_superblock *sb;
+ struct mddev *mddev = &rs->md;
struct md_rdev *r;
+ /* RAID personalities have to provide hot add/remove methods or we need to bail out. */
+ if (!mddev->pers || !mddev->pers->hot_add_disk || !mddev->pers->hot_remove_disk)
+ return;
+
+ memset(cleared_failed_devices, 0, sizeof(cleared_failed_devices));
+
for (i = 0; i < rs->md.raid_disks; i++) {
r = &rs->dev[i].rdev;
if (test_bit(Faulty, &r->flags) && r->sb_page &&
- sync_page_io(r, 0, r->sb_size, r->sb_page, READ, 1)) {
+ sync_page_io(r, 0, r->sb_size, r->sb_page,
+ REQ_OP_READ, 0, true)) {
DMINFO("Faulty %s device #%d has readable super block."
" Attempting to revive it.",
rs->raid_type->name, i);
@@ -1660,13 +3429,13 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs)
* Faulty bit may be set, but sometimes the array can
* be suspended before the personalities can respond
* by removing the device from the array (i.e. calling
- * 'hot_remove_disk'). If they haven't yet removed
+ * 'hot_remove_disk'). If they haven't yet removed
* the failed device, its 'raid_disk' number will be
* '>= 0' - meaning we must call this function
* ourselves.
*/
if ((r->raid_disk >= 0) &&
- (r->mddev->pers->hot_remove_disk(r->mddev, r) != 0))
+ (mddev->pers->hot_remove_disk(mddev, r) != 0))
/* Failed to revive this device, try next */
continue;
@@ -1676,54 +3445,208 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs)
clear_bit(Faulty, &r->flags);
clear_bit(WriteErrorSeen, &r->flags);
clear_bit(In_sync, &r->flags);
- if (r->mddev->pers->hot_add_disk(r->mddev, r)) {
+ if (mddev->pers->hot_add_disk(mddev, r)) {
r->raid_disk = -1;
r->saved_raid_disk = -1;
r->flags = flags;
} else {
r->recovery_offset = 0;
- cleared_failed_devices |= 1 << i;
+ set_bit(i, (void *) cleared_failed_devices);
+ cleared = true;
}
}
}
- if (cleared_failed_devices) {
+
+ /* If any failed devices could be cleared, update all sbs failed_devices bits */
+ if (cleared) {
+ uint64_t failed_devices[DISKS_ARRAY_ELEMS];
+
rdev_for_each(r, &rs->md) {
sb = page_address(r->sb_page);
- failed_devices = le64_to_cpu(sb->failed_devices);
- failed_devices &= ~cleared_failed_devices;
- sb->failed_devices = cpu_to_le64(failed_devices);
+ sb_retrieve_failed_devices(sb, failed_devices);
+
+ for (i = 0; i < DISKS_ARRAY_ELEMS; i++)
+ failed_devices[i] &= ~cleared_failed_devices[i];
+
+ sb_update_failed_devices(sb, failed_devices);
}
}
}
-static void raid_resume(struct dm_target *ti)
+static int __load_dirty_region_bitmap(struct raid_set *rs)
{
- struct raid_set *rs = ti->private;
+ int r = 0;
+
+ /* Try loading the bitmap unless "raid0", which does not have one */
+ if (!rs_is_raid0(rs) &&
+ !test_and_set_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags)) {
+ r = bitmap_load(&rs->md);
+ if (r)
+ DMERR("Failed to load bitmap");
+ }
- if (rs->raid_type->level) {
- set_bit(MD_CHANGE_DEVS, &rs->md.flags);
+ return r;
+}
- if (!rs->bitmap_loaded) {
- bitmap_load(&rs->md);
- rs->bitmap_loaded = 1;
- } else {
- /*
- * A secondary resume while the device is active.
- * Take this opportunity to check whether any failed
- * devices are reachable again.
- */
- attempt_restore_of_faulty_devices(rs);
+/* Enforce updating all superblocks */
+static void rs_update_sbs(struct raid_set *rs)
+{
+ struct mddev *mddev = &rs->md;
+ int ro = mddev->ro;
+
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ mddev->ro = 0;
+ md_update_sb(mddev, 1);
+ mddev->ro = ro;
+}
+
+/*
+ * Reshape changes raid algorithm of @rs to new one within personality
+ * (e.g. raid6_zr -> raid6_nc), changes stripe size, adds/removes
+ * disks from a raid set thus growing/shrinking it or resizes the set
+ *
+ * Call mddev_lock_nointr() before!
+ */
+static int rs_start_reshape(struct raid_set *rs)
+{
+ int r;
+ struct mddev *mddev = &rs->md;
+ struct md_personality *pers = mddev->pers;
+
+ r = rs_setup_reshape(rs);
+ if (r)
+ return r;
+
+ /* Need to be resumed to be able to start reshape, recovery is frozen until raid_resume() though */
+ if (mddev->suspended)
+ mddev_resume(mddev);
+
+ /*
+ * Check any reshape constraints enforced by the personalility
+ *
+ * May as well already kick the reshape off so that * pers->start_reshape() becomes optional.
+ */
+ r = pers->check_reshape(mddev);
+ if (r) {
+ rs->ti->error = "pers->check_reshape() failed";
+ return r;
+ }
+
+ /*
+ * Personality may not provide start reshape method in which
+ * case check_reshape above has already covered everything
+ */
+ if (pers->start_reshape) {
+ r = pers->start_reshape(mddev);
+ if (r) {
+ rs->ti->error = "pers->start_reshape() failed";
+ return r;
}
+ }
+
+ /* Suspend because a resume will happen in raid_resume() */
+ if (!mddev->suspended)
+ mddev_suspend(mddev);
+
+ /*
+ * Now reshape got set up, update superblocks to
+ * reflect the fact so that a table reload will
+ * access proper superblock content in the ctr.
+ */
+ rs_update_sbs(rs);
+
+ return 0;
+}
+
+static int raid_preresume(struct dm_target *ti)
+{
+ int r;
+ struct raid_set *rs = ti->private;
+ struct mddev *mddev = &rs->md;
+
+ /* This is a resume after a suspend of the set -> it's already started */
+ if (test_and_set_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags))
+ return 0;
+
+ /*
+ * The superblocks need to be updated on disk if the
+ * array is new or new devices got added (thus zeroed
+ * out by userspace) or __load_dirty_region_bitmap
+ * will overwrite them in core with old data or fail.
+ */
+ if (test_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags))
+ rs_update_sbs(rs);
+
+ /*
+ * Disable/enable discard support on raid set after any
+ * conversion, because devices can have been added
+ */
+ configure_discard_support(rs);
+
+ /* Load the bitmap from disk unless raid0 */
+ r = __load_dirty_region_bitmap(rs);
+ if (r)
+ return r;
+
+ /* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */
+ if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) &&
+ mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) {
+ r = bitmap_resize(mddev->bitmap, mddev->dev_sectors,
+ to_bytes(rs->requested_bitmap_chunk_sectors), 0);
+ if (r)
+ DMERR("Failed to resize bitmap");
+ }
+
+ /* Check for any resize/reshape on @rs and adjust/initiate */
+ /* Be prepared for mddev_resume() in raid_resume() */
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) {
+ set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ mddev->resync_min = mddev->recovery_cp;
+ }
- clear_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
+ rs_set_capacity(rs);
+
+ /* Check for any reshape request unless new raid set */
+ if (test_and_clear_bit(RT_FLAG_RESHAPE_RS, &rs->runtime_flags)) {
+ /* Initiate a reshape. */
+ mddev_lock_nointr(mddev);
+ r = rs_start_reshape(rs);
+ mddev_unlock(mddev);
+ if (r)
+ DMWARN("Failed to check/start reshape, continuing without change");
+ r = 0;
}
- mddev_resume(&rs->md);
+ return r;
+}
+
+static void raid_resume(struct dm_target *ti)
+{
+ struct raid_set *rs = ti->private;
+ struct mddev *mddev = &rs->md;
+
+ if (test_and_set_bit(RT_FLAG_RS_RESUMED, &rs->runtime_flags)) {
+ /*
+ * A secondary resume while the device is active.
+ * Take this opportunity to check whether any failed
+ * devices are reachable again.
+ */
+ attempt_restore_of_faulty_devices(rs);
+ }
+
+ mddev->ro = 0;
+ mddev->in_sync = 0;
+
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+
+ if (mddev->suspended)
+ mddev_resume(mddev);
}
static struct target_type raid_target = {
.name = "raid",
- .version = {1, 8, 0},
+ .version = {1, 9, 0},
.module = THIS_MODULE,
.ctr = raid_ctr,
.dtr = raid_dtr,
@@ -1734,6 +3657,7 @@ static struct target_type raid_target = {
.io_hints = raid_io_hints,
.presuspend = raid_presuspend,
.postsuspend = raid_postsuspend,
+ .preresume = raid_preresume,
.resume = raid_resume,
};
@@ -1758,11 +3682,13 @@ module_param(devices_handle_discard_safely, bool, 0644);
MODULE_PARM_DESC(devices_handle_discard_safely,
"Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
-MODULE_DESCRIPTION(DM_NAME " raid4/5/6 target");
+MODULE_DESCRIPTION(DM_NAME " raid0/1/10/4/5/6 target");
+MODULE_ALIAS("dm-raid0");
MODULE_ALIAS("dm-raid1");
MODULE_ALIAS("dm-raid10");
MODULE_ALIAS("dm-raid4");
MODULE_ALIAS("dm-raid5");
MODULE_ALIAS("dm-raid6");
MODULE_AUTHOR("Neil Brown <dm-devel@redhat.com>");
+MODULE_AUTHOR("Heinz Mauelshagen <dm-devel@redhat.com>");
MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index b3ccf1e0d..bdf1606f6 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -260,7 +260,8 @@ static int mirror_flush(struct dm_target *ti)
struct dm_io_region io[ms->nr_mirrors];
struct mirror *m;
struct dm_io_request io_req = {
- .bi_rw = WRITE_FLUSH,
+ .bi_op = REQ_OP_WRITE,
+ .bi_op_flags = WRITE_FLUSH,
.mem.type = DM_IO_KMEM,
.mem.ptr.addr = NULL,
.client = ms->io_client,
@@ -527,7 +528,7 @@ static void read_callback(unsigned long error, void *context)
DMWARN_LIMIT("Read failure on mirror device %s. "
"Trying alternative device.",
m->dev->name);
- queue_bio(m->ms, bio, bio_rw(bio));
+ queue_bio(m->ms, bio, bio_data_dir(bio));
return;
}
@@ -541,7 +542,8 @@ static void read_async_bio(struct mirror *m, struct bio *bio)
{
struct dm_io_region io;
struct dm_io_request io_req = {
- .bi_rw = READ,
+ .bi_op = REQ_OP_READ,
+ .bi_op_flags = 0,
.mem.type = DM_IO_BIO,
.mem.ptr.bio = bio,
.notify.fn = read_callback,
@@ -624,7 +626,7 @@ static void write_callback(unsigned long error, void *context)
* If the bio is discard, return an error, but do not
* degrade the array.
*/
- if (bio->bi_rw & REQ_DISCARD) {
+ if (bio_op(bio) == REQ_OP_DISCARD) {
bio->bi_error = -EOPNOTSUPP;
bio_endio(bio);
return;
@@ -654,7 +656,8 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
struct dm_io_region io[ms->nr_mirrors], *dest = io;
struct mirror *m;
struct dm_io_request io_req = {
- .bi_rw = WRITE | (bio->bi_rw & WRITE_FLUSH_FUA),
+ .bi_op = REQ_OP_WRITE,
+ .bi_op_flags = bio->bi_opf & WRITE_FLUSH_FUA,
.mem.type = DM_IO_BIO,
.mem.ptr.bio = bio,
.notify.fn = write_callback,
@@ -662,8 +665,8 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
.client = ms->io_client,
};
- if (bio->bi_rw & REQ_DISCARD) {
- io_req.bi_rw |= REQ_DISCARD;
+ if (bio_op(bio) == REQ_OP_DISCARD) {
+ io_req.bi_op = REQ_OP_DISCARD;
io_req.mem.type = DM_IO_KMEM;
io_req.mem.ptr.addr = NULL;
}
@@ -701,8 +704,8 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
bio_list_init(&requeue);
while ((bio = bio_list_pop(writes))) {
- if ((bio->bi_rw & REQ_FLUSH) ||
- (bio->bi_rw & REQ_DISCARD)) {
+ if ((bio->bi_opf & REQ_PREFLUSH) ||
+ (bio_op(bio) == REQ_OP_DISCARD)) {
bio_list_add(&sync, bio);
continue;
}
@@ -1190,7 +1193,7 @@ static void mirror_dtr(struct dm_target *ti)
*/
static int mirror_map(struct dm_target *ti, struct bio *bio)
{
- int r, rw = bio_rw(bio);
+ int r, rw = bio_data_dir(bio);
struct mirror *m;
struct mirror_set *ms = ti->private;
struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
@@ -1214,7 +1217,7 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
* If region is not in-sync queue the bio.
*/
if (!r || (r == -EWOULDBLOCK)) {
- if (rw == READA)
+ if (bio->bi_opf & REQ_RAHEAD)
return -EWOULDBLOCK;
queue_bio(ms, bio, rw);
@@ -1239,7 +1242,7 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
{
- int rw = bio_rw(bio);
+ int rw = bio_data_dir(bio);
struct mirror_set *ms = (struct mirror_set *) ti->private;
struct mirror *m = NULL;
struct dm_bio_details *bd = NULL;
@@ -1250,7 +1253,8 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
* We need to dec pending if this was a write.
*/
if (rw == WRITE) {
- if (!(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD)))
+ if (!(bio->bi_opf & REQ_PREFLUSH) &&
+ bio_op(bio) != REQ_OP_DISCARD)
dm_rh_dec(ms->rh, bio_record->write_region);
return error;
}
@@ -1258,7 +1262,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
if (error == -EOPNOTSUPP)
goto out;
- if ((error == -EWOULDBLOCK) && (bio->bi_rw & REQ_RAHEAD))
+ if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD))
goto out;
if (unlikely(error)) {
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index 74cb7b991..85c32b22a 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -398,12 +398,12 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio)
region_t region = dm_rh_bio_to_region(rh, bio);
int recovering = 0;
- if (bio->bi_rw & REQ_FLUSH) {
+ if (bio->bi_opf & REQ_PREFLUSH) {
rh->flush_failure = 1;
return;
}
- if (bio->bi_rw & REQ_DISCARD)
+ if (bio_op(bio) == REQ_OP_DISCARD)
return;
/* We must inform the log that the sync count has changed. */
@@ -526,7 +526,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios)
struct bio *bio;
for (bio = bios->head; bio; bio = bio->bi_next) {
- if (bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))
+ if (bio->bi_opf & REQ_PREFLUSH || bio_op(bio) == REQ_OP_DISCARD)
continue;
rh_inc(rh, dm_rh_bio_to_region(rh, bio));
}
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
new file mode 100644
index 000000000..1ca7463e8
--- /dev/null
+++ b/drivers/md/dm-rq.c
@@ -0,0 +1,988 @@
+/*
+ * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-core.h"
+#include "dm-rq.h"
+
+#include <linux/elevator.h> /* for rq_end_sector() */
+#include <linux/blk-mq.h>
+
+#define DM_MSG_PREFIX "core-rq"
+
+#define DM_MQ_NR_HW_QUEUES 1
+#define DM_MQ_QUEUE_DEPTH 2048
+static unsigned dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES;
+static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH;
+
+/*
+ * Request-based DM's mempools' reserved IOs set by the user.
+ */
+#define RESERVED_REQUEST_BASED_IOS 256
+static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
+
+#ifdef CONFIG_DM_MQ_DEFAULT
+static bool use_blk_mq = true;
+#else
+static bool use_blk_mq = false;
+#endif
+
+bool dm_use_blk_mq_default(void)
+{
+ return use_blk_mq;
+}
+
+bool dm_use_blk_mq(struct mapped_device *md)
+{
+ return md->use_blk_mq;
+}
+EXPORT_SYMBOL_GPL(dm_use_blk_mq);
+
+unsigned dm_get_reserved_rq_based_ios(void)
+{
+ return __dm_get_module_param(&reserved_rq_based_ios,
+ RESERVED_REQUEST_BASED_IOS, DM_RESERVED_MAX_IOS);
+}
+EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);
+
+static unsigned dm_get_blk_mq_nr_hw_queues(void)
+{
+ return __dm_get_module_param(&dm_mq_nr_hw_queues, 1, 32);
+}
+
+static unsigned dm_get_blk_mq_queue_depth(void)
+{
+ return __dm_get_module_param(&dm_mq_queue_depth,
+ DM_MQ_QUEUE_DEPTH, BLK_MQ_MAX_DEPTH);
+}
+
+int dm_request_based(struct mapped_device *md)
+{
+ return blk_queue_stackable(md->queue);
+}
+
+static void dm_old_start_queue(struct request_queue *q)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ if (blk_queue_stopped(q))
+ blk_start_queue(q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+void dm_start_queue(struct request_queue *q)
+{
+ if (!q->mq_ops)
+ dm_old_start_queue(q);
+ else {
+ queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, q);
+ blk_mq_start_stopped_hw_queues(q, true);
+ blk_mq_kick_requeue_list(q);
+ }
+}
+
+static void dm_old_stop_queue(struct request_queue *q)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ if (blk_queue_stopped(q)) {
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ return;
+ }
+
+ blk_stop_queue(q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+void dm_stop_queue(struct request_queue *q)
+{
+ if (!q->mq_ops)
+ dm_old_stop_queue(q);
+ else {
+ spin_lock_irq(q->queue_lock);
+ queue_flag_set(QUEUE_FLAG_STOPPED, q);
+ spin_unlock_irq(q->queue_lock);
+
+ blk_mq_cancel_requeue_work(q);
+ blk_mq_stop_hw_queues(q);
+ }
+}
+
+static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
+ gfp_t gfp_mask)
+{
+ return mempool_alloc(md->io_pool, gfp_mask);
+}
+
+static void free_old_rq_tio(struct dm_rq_target_io *tio)
+{
+ mempool_free(tio, tio->md->io_pool);
+}
+
+static struct request *alloc_old_clone_request(struct mapped_device *md,
+ gfp_t gfp_mask)
+{
+ return mempool_alloc(md->rq_pool, gfp_mask);
+}
+
+static void free_old_clone_request(struct mapped_device *md, struct request *rq)
+{
+ mempool_free(rq, md->rq_pool);
+}
+
+/*
+ * Partial completion handling for request-based dm
+ */
+static void end_clone_bio(struct bio *clone)
+{
+ struct dm_rq_clone_bio_info *info =
+ container_of(clone, struct dm_rq_clone_bio_info, clone);
+ struct dm_rq_target_io *tio = info->tio;
+ struct bio *bio = info->orig;
+ unsigned int nr_bytes = info->orig->bi_iter.bi_size;
+ int error = clone->bi_error;
+
+ bio_put(clone);
+
+ if (tio->error)
+ /*
+ * An error has already been detected on the request.
+ * Once error occurred, just let clone->end_io() handle
+ * the remainder.
+ */
+ return;
+ else if (error) {
+ /*
+ * Don't notice the error to the upper layer yet.
+ * The error handling decision is made by the target driver,
+ * when the request is completed.
+ */
+ tio->error = error;
+ return;
+ }
+
+ /*
+ * I/O for the bio successfully completed.
+ * Notice the data completion to the upper layer.
+ */
+
+ /*
+ * bios are processed from the head of the list.
+ * So the completing bio should always be rq->bio.
+ * If it's not, something wrong is happening.
+ */
+ if (tio->orig->bio != bio)
+ DMERR("bio completion is going in the middle of the request");
+
+ /*
+ * Update the original request.
+ * Do not use blk_end_request() here, because it may complete
+ * the original request before the clone, and break the ordering.
+ */
+ blk_update_request(tio->orig, 0, nr_bytes);
+}
+
+static struct dm_rq_target_io *tio_from_request(struct request *rq)
+{
+ return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
+}
+
+static void rq_end_stats(struct mapped_device *md, struct request *orig)
+{
+ if (unlikely(dm_stats_used(&md->stats))) {
+ struct dm_rq_target_io *tio = tio_from_request(orig);
+ tio->duration_jiffies = jiffies - tio->duration_jiffies;
+ dm_stats_account_io(&md->stats, rq_data_dir(orig),
+ blk_rq_pos(orig), tio->n_sectors, true,
+ tio->duration_jiffies, &tio->stats_aux);
+ }
+}
+
+/*
+ * Don't touch any member of the md after calling this function because
+ * the md may be freed in dm_put() at the end of this function.
+ * Or do dm_get() before calling this function and dm_put() later.
+ */
+static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
+{
+ atomic_dec(&md->pending[rw]);
+
+ /* nudge anyone waiting on suspend queue */
+ if (!md_in_flight(md))
+ wake_up(&md->wait);
+
+ /*
+ * Run this off this callpath, as drivers could invoke end_io while
+ * inside their request_fn (and holding the queue lock). Calling
+ * back into ->request_fn() could deadlock attempting to grab the
+ * queue lock again.
+ */
+ if (!md->queue->mq_ops && run_queue)
+ blk_run_queue_async(md->queue);
+
+ /*
+ * dm_put() must be at the end of this function. See the comment above
+ */
+ dm_put(md);
+}
+
+static void free_rq_clone(struct request *clone)
+{
+ struct dm_rq_target_io *tio = clone->end_io_data;
+ struct mapped_device *md = tio->md;
+
+ blk_rq_unprep_clone(clone);
+
+ /*
+ * It is possible for a clone_old_rq() allocated clone to
+ * get passed in -- it may not yet have a request_queue.
+ * This is known to occur if the error target replaces
+ * a multipath target that has a request_fn queue stacked
+ * on blk-mq queue(s).
+ */
+ if (clone->q && clone->q->mq_ops)
+ /* stacked on blk-mq queue(s) */
+ tio->ti->type->release_clone_rq(clone);
+ else if (!md->queue->mq_ops)
+ /* request_fn queue stacked on request_fn queue(s) */
+ free_old_clone_request(md, clone);
+
+ if (!md->queue->mq_ops)
+ free_old_rq_tio(tio);
+}
+
+/*
+ * Complete the clone and the original request.
+ * Must be called without clone's queue lock held,
+ * see end_clone_request() for more details.
+ */
+static void dm_end_request(struct request *clone, int error)
+{
+ int rw = rq_data_dir(clone);
+ struct dm_rq_target_io *tio = clone->end_io_data;
+ struct mapped_device *md = tio->md;
+ struct request *rq = tio->orig;
+
+ if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
+ rq->errors = clone->errors;
+ rq->resid_len = clone->resid_len;
+
+ if (rq->sense)
+ /*
+ * We are using the sense buffer of the original
+ * request.
+ * So setting the length of the sense data is enough.
+ */
+ rq->sense_len = clone->sense_len;
+ }
+
+ free_rq_clone(clone);
+ rq_end_stats(md, rq);
+ if (!rq->q->mq_ops)
+ blk_end_request_all(rq, error);
+ else
+ blk_mq_end_request(rq, error);
+ rq_completed(md, rw, true);
+}
+
+static void dm_unprep_request(struct request *rq)
+{
+ struct dm_rq_target_io *tio = tio_from_request(rq);
+ struct request *clone = tio->clone;
+
+ if (!rq->q->mq_ops) {
+ rq->special = NULL;
+ rq->cmd_flags &= ~REQ_DONTPREP;
+ }
+
+ if (clone)
+ free_rq_clone(clone);
+ else if (!tio->md->queue->mq_ops)
+ free_old_rq_tio(tio);
+}
+
+/*
+ * Requeue the original request of a clone.
+ */
+static void dm_old_requeue_request(struct request *rq)
+{
+ struct request_queue *q = rq->q;
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ blk_requeue_request(q, rq);
+ blk_run_queue_async(q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static void dm_mq_requeue_request(struct request *rq)
+{
+ struct request_queue *q = rq->q;
+ unsigned long flags;
+
+ blk_mq_requeue_request(rq);
+ spin_lock_irqsave(q->queue_lock, flags);
+ if (!blk_queue_stopped(q))
+ blk_mq_kick_requeue_list(q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+static void dm_requeue_original_request(struct mapped_device *md,
+ struct request *rq)
+{
+ int rw = rq_data_dir(rq);
+
+ rq_end_stats(md, rq);
+ dm_unprep_request(rq);
+
+ if (!rq->q->mq_ops)
+ dm_old_requeue_request(rq);
+ else
+ dm_mq_requeue_request(rq);
+
+ rq_completed(md, rw, false);
+}
+
+static void dm_done(struct request *clone, int error, bool mapped)
+{
+ int r = error;
+ struct dm_rq_target_io *tio = clone->end_io_data;
+ dm_request_endio_fn rq_end_io = NULL;
+
+ if (tio->ti) {
+ rq_end_io = tio->ti->type->rq_end_io;
+
+ if (mapped && rq_end_io)
+ r = rq_end_io(tio->ti, clone, error, &tio->info);
+ }
+
+ if (unlikely(r == -EREMOTEIO && (req_op(clone) == REQ_OP_WRITE_SAME) &&
+ !clone->q->limits.max_write_same_sectors))
+ disable_write_same(tio->md);
+
+ if (r <= 0)
+ /* The target wants to complete the I/O */
+ dm_end_request(clone, r);
+ else if (r == DM_ENDIO_INCOMPLETE)
+ /* The target will handle the I/O */
+ return;
+ else if (r == DM_ENDIO_REQUEUE)
+ /* The target wants to requeue the I/O */
+ dm_requeue_original_request(tio->md, tio->orig);
+ else {
+ DMWARN("unimplemented target endio return value: %d", r);
+ BUG();
+ }
+}
+
+/*
+ * Request completion handler for request-based dm
+ */
+static void dm_softirq_done(struct request *rq)
+{
+ bool mapped = true;
+ struct dm_rq_target_io *tio = tio_from_request(rq);
+ struct request *clone = tio->clone;
+ int rw;
+
+ if (!clone) {
+ rq_end_stats(tio->md, rq);
+ rw = rq_data_dir(rq);
+ if (!rq->q->mq_ops) {
+ blk_end_request_all(rq, tio->error);
+ rq_completed(tio->md, rw, false);
+ free_old_rq_tio(tio);
+ } else {
+ blk_mq_end_request(rq, tio->error);
+ rq_completed(tio->md, rw, false);
+ }
+ return;
+ }
+
+ if (rq->cmd_flags & REQ_FAILED)
+ mapped = false;
+
+ dm_done(clone, tio->error, mapped);
+}
+
+/*
+ * Complete the clone and the original request with the error status
+ * through softirq context.
+ */
+static void dm_complete_request(struct request *rq, int error)
+{
+ struct dm_rq_target_io *tio = tio_from_request(rq);
+
+ tio->error = error;
+ if (!rq->q->mq_ops)
+ blk_complete_request(rq);
+ else
+ blk_mq_complete_request(rq, error);
+}
+
+/*
+ * Complete the not-mapped clone and the original request with the error status
+ * through softirq context.
+ * Target's rq_end_io() function isn't called.
+ * This may be used when the target's map_rq() or clone_and_map_rq() functions fail.
+ */
+static void dm_kill_unmapped_request(struct request *rq, int error)
+{
+ rq->cmd_flags |= REQ_FAILED;
+ dm_complete_request(rq, error);
+}
+
+/*
+ * Called with the clone's queue lock held (in the case of .request_fn)
+ */
+static void end_clone_request(struct request *clone, int error)
+{
+ struct dm_rq_target_io *tio = clone->end_io_data;
+
+ if (!clone->q->mq_ops) {
+ /*
+ * For just cleaning up the information of the queue in which
+ * the clone was dispatched.
+ * The clone is *NOT* freed actually here because it is alloced
+ * from dm own mempool (REQ_ALLOCED isn't set).
+ */
+ __blk_put_request(clone->q, clone);
+ }
+
+ /*
+ * Actual request completion is done in a softirq context which doesn't
+ * hold the clone's queue lock. Otherwise, deadlock could occur because:
+ * - another request may be submitted by the upper level driver
+ * of the stacking during the completion
+ * - the submission which requires queue lock may be done
+ * against this clone's queue
+ */
+ dm_complete_request(tio->orig, error);
+}
+
+static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
+{
+ int r;
+
+ if (blk_queue_io_stat(clone->q))
+ clone->cmd_flags |= REQ_IO_STAT;
+
+ clone->start_time = jiffies;
+ r = blk_insert_cloned_request(clone->q, clone);
+ if (r)
+ /* must complete clone in terms of original request */
+ dm_complete_request(rq, r);
+}
+
+static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
+ void *data)
+{
+ struct dm_rq_target_io *tio = data;
+ struct dm_rq_clone_bio_info *info =
+ container_of(bio, struct dm_rq_clone_bio_info, clone);
+
+ info->orig = bio_orig;
+ info->tio = tio;
+ bio->bi_end_io = end_clone_bio;
+
+ return 0;
+}
+
+static int setup_clone(struct request *clone, struct request *rq,
+ struct dm_rq_target_io *tio, gfp_t gfp_mask)
+{
+ int r;
+
+ r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
+ dm_rq_bio_constructor, tio);
+ if (r)
+ return r;
+
+ clone->cmd = rq->cmd;
+ clone->cmd_len = rq->cmd_len;
+ clone->sense = rq->sense;
+ clone->end_io = end_clone_request;
+ clone->end_io_data = tio;
+
+ tio->clone = clone;
+
+ return 0;
+}
+
+static struct request *clone_old_rq(struct request *rq, struct mapped_device *md,
+ struct dm_rq_target_io *tio, gfp_t gfp_mask)
+{
+ /*
+ * Create clone for use with .request_fn request_queue
+ */
+ struct request *clone;
+
+ clone = alloc_old_clone_request(md, gfp_mask);
+ if (!clone)
+ return NULL;
+
+ blk_rq_init(NULL, clone);
+ if (setup_clone(clone, rq, tio, gfp_mask)) {
+ /* -ENOMEM */
+ free_old_clone_request(md, clone);
+ return NULL;
+ }
+
+ return clone;
+}
+
+static void map_tio_request(struct kthread_work *work);
+
+static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
+ struct mapped_device *md)
+{
+ tio->md = md;
+ tio->ti = NULL;
+ tio->clone = NULL;
+ tio->orig = rq;
+ tio->error = 0;
+ /*
+ * Avoid initializing info for blk-mq; it passes
+ * target-specific data through info.ptr
+ * (see: dm_mq_init_request)
+ */
+ if (!md->init_tio_pdu)
+ memset(&tio->info, 0, sizeof(tio->info));
+ if (md->kworker_task)
+ init_kthread_work(&tio->work, map_tio_request);
+}
+
+static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq,
+ struct mapped_device *md,
+ gfp_t gfp_mask)
+{
+ struct dm_rq_target_io *tio;
+ int srcu_idx;
+ struct dm_table *table;
+
+ tio = alloc_old_rq_tio(md, gfp_mask);
+ if (!tio)
+ return NULL;
+
+ init_tio(tio, rq, md);
+
+ table = dm_get_live_table(md, &srcu_idx);
+ /*
+ * Must clone a request if this .request_fn DM device
+ * is stacked on .request_fn device(s).
+ */
+ if (!dm_table_all_blk_mq_devices(table)) {
+ if (!clone_old_rq(rq, md, tio, gfp_mask)) {
+ dm_put_live_table(md, srcu_idx);
+ free_old_rq_tio(tio);
+ return NULL;
+ }
+ }
+ dm_put_live_table(md, srcu_idx);
+
+ return tio;
+}
+
+/*
+ * Called with the queue lock held.
+ */
+static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
+{
+ struct mapped_device *md = q->queuedata;
+ struct dm_rq_target_io *tio;
+
+ if (unlikely(rq->special)) {
+ DMWARN("Already has something in rq->special.");
+ return BLKPREP_KILL;
+ }
+
+ tio = dm_old_prep_tio(rq, md, GFP_ATOMIC);
+ if (!tio)
+ return BLKPREP_DEFER;
+
+ rq->special = tio;
+ rq->cmd_flags |= REQ_DONTPREP;
+
+ return BLKPREP_OK;
+}
+
+/*
+ * Returns:
+ * 0 : the request has been processed
+ * DM_MAPIO_REQUEUE : the original request needs to be requeued
+ * < 0 : the request was completed due to failure
+ */
+static int map_request(struct dm_rq_target_io *tio, struct request *rq,
+ struct mapped_device *md)
+{
+ int r;
+ struct dm_target *ti = tio->ti;
+ struct request *clone = NULL;
+
+ if (tio->clone) {
+ clone = tio->clone;
+ r = ti->type->map_rq(ti, clone, &tio->info);
+ } else {
+ r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
+ if (r < 0) {
+ /* The target wants to complete the I/O */
+ dm_kill_unmapped_request(rq, r);
+ return r;
+ }
+ if (r != DM_MAPIO_REMAPPED)
+ return r;
+ if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
+ /* -ENOMEM */
+ ti->type->release_clone_rq(clone);
+ return DM_MAPIO_REQUEUE;
+ }
+ }
+
+ switch (r) {
+ case DM_MAPIO_SUBMITTED:
+ /* The target has taken the I/O to submit by itself later */
+ break;
+ case DM_MAPIO_REMAPPED:
+ /* The target has remapped the I/O so dispatch it */
+ trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
+ blk_rq_pos(rq));
+ dm_dispatch_clone_request(clone, rq);
+ break;
+ case DM_MAPIO_REQUEUE:
+ /* The target wants to requeue the I/O */
+ dm_requeue_original_request(md, tio->orig);
+ break;
+ default:
+ if (r > 0) {
+ DMWARN("unimplemented target map return value: %d", r);
+ BUG();
+ }
+
+ /* The target wants to complete the I/O */
+ dm_kill_unmapped_request(rq, r);
+ return r;
+ }
+
+ return 0;
+}
+
+static void dm_start_request(struct mapped_device *md, struct request *orig)
+{
+ if (!orig->q->mq_ops)
+ blk_start_request(orig);
+ else
+ blk_mq_start_request(orig);
+ atomic_inc(&md->pending[rq_data_dir(orig)]);
+
+ if (md->seq_rq_merge_deadline_usecs) {
+ md->last_rq_pos = rq_end_sector(orig);
+ md->last_rq_rw = rq_data_dir(orig);
+ md->last_rq_start_time = ktime_get();
+ }
+
+ if (unlikely(dm_stats_used(&md->stats))) {
+ struct dm_rq_target_io *tio = tio_from_request(orig);
+ tio->duration_jiffies = jiffies;
+ tio->n_sectors = blk_rq_sectors(orig);
+ dm_stats_account_io(&md->stats, rq_data_dir(orig),
+ blk_rq_pos(orig), tio->n_sectors, false, 0,
+ &tio->stats_aux);
+ }
+
+ /*
+ * Hold the md reference here for the in-flight I/O.
+ * We can't rely on the reference count by device opener,
+ * because the device may be closed during the request completion
+ * when all bios are completed.
+ * See the comment in rq_completed() too.
+ */
+ dm_get(md);
+}
+
+static void map_tio_request(struct kthread_work *work)
+{
+ struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
+ struct request *rq = tio->orig;
+ struct mapped_device *md = tio->md;
+
+ if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
+ dm_requeue_original_request(md, rq);
+}
+
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
+{
+ return sprintf(buf, "%u\n", md->seq_rq_merge_deadline_usecs);
+}
+
+#define MAX_SEQ_RQ_MERGE_DEADLINE_USECS 100000
+
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
+ const char *buf, size_t count)
+{
+ unsigned deadline;
+
+ if (dm_get_md_type(md) != DM_TYPE_REQUEST_BASED)
+ return count;
+
+ if (kstrtouint(buf, 10, &deadline))
+ return -EINVAL;
+
+ if (deadline > MAX_SEQ_RQ_MERGE_DEADLINE_USECS)
+ deadline = MAX_SEQ_RQ_MERGE_DEADLINE_USECS;
+
+ md->seq_rq_merge_deadline_usecs = deadline;
+
+ return count;
+}
+
+static bool dm_old_request_peeked_before_merge_deadline(struct mapped_device *md)
+{
+ ktime_t kt_deadline;
+
+ if (!md->seq_rq_merge_deadline_usecs)
+ return false;
+
+ kt_deadline = ns_to_ktime((u64)md->seq_rq_merge_deadline_usecs * NSEC_PER_USEC);
+ kt_deadline = ktime_add_safe(md->last_rq_start_time, kt_deadline);
+
+ return !ktime_after(ktime_get(), kt_deadline);
+}
+
+/*
+ * q->request_fn for old request-based dm.
+ * Called with the queue lock held.
+ */
+static void dm_old_request_fn(struct request_queue *q)
+{
+ struct mapped_device *md = q->queuedata;
+ struct dm_target *ti = md->immutable_target;
+ struct request *rq;
+ struct dm_rq_target_io *tio;
+ sector_t pos = 0;
+
+ if (unlikely(!ti)) {
+ int srcu_idx;
+ struct dm_table *map = dm_get_live_table(md, &srcu_idx);
+
+ ti = dm_table_find_target(map, pos);
+ dm_put_live_table(md, srcu_idx);
+ }
+
+ /*
+ * For suspend, check blk_queue_stopped() and increment
+ * ->pending within a single queue_lock not to increment the
+ * number of in-flight I/Os after the queue is stopped in
+ * dm_suspend().
+ */
+ while (!blk_queue_stopped(q)) {
+ rq = blk_peek_request(q);
+ if (!rq)
+ return;
+
+ /* always use block 0 to find the target for flushes for now */
+ pos = 0;
+ if (req_op(rq) != REQ_OP_FLUSH)
+ pos = blk_rq_pos(rq);
+
+ if ((dm_old_request_peeked_before_merge_deadline(md) &&
+ md_in_flight(md) && rq->bio && rq->bio->bi_vcnt == 1 &&
+ md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) ||
+ (ti->type->busy && ti->type->busy(ti))) {
+ blk_delay_queue(q, 10);
+ return;
+ }
+
+ dm_start_request(md, rq);
+
+ tio = tio_from_request(rq);
+ /* Establish tio->ti before queuing work (map_tio_request) */
+ tio->ti = ti;
+ queue_kthread_work(&md->kworker, &tio->work);
+ BUG_ON(!irqs_disabled());
+ }
+}
+
+/*
+ * Fully initialize a .request_fn request-based queue.
+ */
+int dm_old_init_request_queue(struct mapped_device *md)
+{
+ /* Fully initialize the queue */
+ if (!blk_init_allocated_queue(md->queue, dm_old_request_fn, NULL))
+ return -EINVAL;
+
+ /* disable dm_old_request_fn's merge heuristic by default */
+ md->seq_rq_merge_deadline_usecs = 0;
+
+ dm_init_normal_md_queue(md);
+ blk_queue_softirq_done(md->queue, dm_softirq_done);
+ blk_queue_prep_rq(md->queue, dm_old_prep_fn);
+
+ /* Initialize the request-based DM worker thread */
+ init_kthread_worker(&md->kworker);
+ md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
+ "kdmwork-%s", dm_device_name(md));
+ if (IS_ERR(md->kworker_task))
+ return PTR_ERR(md->kworker_task);
+
+ elv_register_queue(md->queue);
+
+ return 0;
+}
+
+static int dm_mq_init_request(void *data, struct request *rq,
+ unsigned int hctx_idx, unsigned int request_idx,
+ unsigned int numa_node)
+{
+ struct mapped_device *md = data;
+ struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
+
+ /*
+ * Must initialize md member of tio, otherwise it won't
+ * be available in dm_mq_queue_rq.
+ */
+ tio->md = md;
+
+ if (md->init_tio_pdu) {
+ /* target-specific per-io data is immediately after the tio */
+ tio->info.ptr = tio + 1;
+ }
+
+ return 0;
+}
+
+static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
+ const struct blk_mq_queue_data *bd)
+{
+ struct request *rq = bd->rq;
+ struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
+ struct mapped_device *md = tio->md;
+ struct dm_target *ti = md->immutable_target;
+
+ if (unlikely(!ti)) {
+ int srcu_idx;
+ struct dm_table *map = dm_get_live_table(md, &srcu_idx);
+
+ ti = dm_table_find_target(map, 0);
+ dm_put_live_table(md, srcu_idx);
+ }
+
+ /*
+ * On suspend dm_stop_queue() handles stopping the blk-mq
+ * request_queue BUT: even though the hw_queues are marked
+ * BLK_MQ_S_STOPPED at that point there is still a race that
+ * is allowing block/blk-mq.c to call ->queue_rq against a
+ * hctx that it really shouldn't. The following check guards
+ * against this rarity (albeit _not_ race-free).
+ */
+ if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
+ return BLK_MQ_RQ_QUEUE_BUSY;
+
+ if (ti->type->busy && ti->type->busy(ti))
+ return BLK_MQ_RQ_QUEUE_BUSY;
+
+ dm_start_request(md, rq);
+
+ /* Init tio using md established in .init_request */
+ init_tio(tio, rq, md);
+
+ /*
+ * Establish tio->ti before calling map_request().
+ */
+ tio->ti = ti;
+
+ /* Direct call is fine since .queue_rq allows allocations */
+ if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+ /* Undo dm_start_request() before requeuing */
+ rq_end_stats(md, rq);
+ rq_completed(md, rq_data_dir(rq), false);
+ return BLK_MQ_RQ_QUEUE_BUSY;
+ }
+
+ return BLK_MQ_RQ_QUEUE_OK;
+}
+
+static struct blk_mq_ops dm_mq_ops = {
+ .queue_rq = dm_mq_queue_rq,
+ .map_queue = blk_mq_map_queue,
+ .complete = dm_softirq_done,
+ .init_request = dm_mq_init_request,
+};
+
+int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
+{
+ struct request_queue *q;
+ struct dm_target *immutable_tgt;
+ int err;
+
+ if (!dm_table_all_blk_mq_devices(t)) {
+ DMERR("request-based dm-mq may only be stacked on blk-mq device(s)");
+ return -EINVAL;
+ }
+
+ md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id);
+ if (!md->tag_set)
+ return -ENOMEM;
+
+ md->tag_set->ops = &dm_mq_ops;
+ md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
+ md->tag_set->numa_node = md->numa_node_id;
+ md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+ md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
+ md->tag_set->driver_data = md;
+
+ md->tag_set->cmd_size = sizeof(struct dm_rq_target_io);
+ immutable_tgt = dm_table_get_immutable_target(t);
+ if (immutable_tgt && immutable_tgt->per_io_data_size) {
+ /* any target-specific per-io data is immediately after the tio */
+ md->tag_set->cmd_size += immutable_tgt->per_io_data_size;
+ md->init_tio_pdu = true;
+ }
+
+ err = blk_mq_alloc_tag_set(md->tag_set);
+ if (err)
+ goto out_kfree_tag_set;
+
+ q = blk_mq_init_allocated_queue(md->tag_set, md->queue);
+ if (IS_ERR(q)) {
+ err = PTR_ERR(q);
+ goto out_tag_set;
+ }
+ dm_init_md_queue(md);
+
+ /* backfill 'mq' sysfs registration normally done in blk_register_queue */
+ blk_mq_register_disk(md->disk);
+
+ return 0;
+
+out_tag_set:
+ blk_mq_free_tag_set(md->tag_set);
+out_kfree_tag_set:
+ kfree(md->tag_set);
+
+ return err;
+}
+
+void dm_mq_cleanup_mapped_device(struct mapped_device *md)
+{
+ if (md->tag_set) {
+ blk_mq_free_tag_set(md->tag_set);
+ kfree(md->tag_set);
+ }
+}
+
+module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");
+
+module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices");
+
+module_param(dm_mq_nr_hw_queues, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dm_mq_nr_hw_queues, "Number of hardware queues for request-based dm-mq devices");
+
+module_param(dm_mq_queue_depth, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dm_mq_queue_depth, "Queue depth for request-based dm-mq devices");
diff --git a/drivers/md/dm-rq.h b/drivers/md/dm-rq.h
new file mode 100644
index 000000000..9e6f0a377
--- /dev/null
+++ b/drivers/md/dm-rq.h
@@ -0,0 +1,64 @@
+/*
+ * Internal header file for device mapper
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the LGPL.
+ */
+
+#ifndef DM_RQ_INTERNAL_H
+#define DM_RQ_INTERNAL_H
+
+#include <linux/bio.h>
+#include <linux/kthread.h>
+
+#include "dm-stats.h"
+
+struct mapped_device;
+
+/*
+ * One of these is allocated per request.
+ */
+struct dm_rq_target_io {
+ struct mapped_device *md;
+ struct dm_target *ti;
+ struct request *orig, *clone;
+ struct kthread_work work;
+ int error;
+ union map_info info;
+ struct dm_stats_aux stats_aux;
+ unsigned long duration_jiffies;
+ unsigned n_sectors;
+};
+
+/*
+ * For request-based dm - the bio clones we allocate are embedded in these
+ * structs.
+ *
+ * We allocate these with bio_alloc_bioset, using the front_pad parameter when
+ * the bioset is created - this means the bio has to come at the end of the
+ * struct.
+ */
+struct dm_rq_clone_bio_info {
+ struct bio *orig;
+ struct dm_rq_target_io *tio;
+ struct bio clone;
+};
+
+bool dm_use_blk_mq_default(void);
+bool dm_use_blk_mq(struct mapped_device *md);
+
+int dm_old_init_request_queue(struct mapped_device *md);
+int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t);
+void dm_mq_cleanup_mapped_device(struct mapped_device *md);
+
+void dm_start_queue(struct request_queue *q);
+void dm_stop_queue(struct request_queue *q);
+
+unsigned dm_get_reserved_rq_based_ios(void);
+
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf);
+ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
+ const char *buf, size_t count);
+
+#endif
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 4d3909393..b8cf956b5 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -226,8 +226,8 @@ static void do_metadata(struct work_struct *work)
/*
* Read or write a chunk aligned and sized block of data from a device.
*/
-static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
- int metadata)
+static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int op,
+ int op_flags, int metadata)
{
struct dm_io_region where = {
.bdev = dm_snap_cow(ps->store->snap)->bdev,
@@ -235,7 +235,8 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
.count = ps->store->chunk_size,
};
struct dm_io_request io_req = {
- .bi_rw = rw,
+ .bi_op = op,
+ .bi_op_flags = op_flags,
.mem.type = DM_IO_VMA,
.mem.ptr.vma = area,
.client = ps->io_client,
@@ -281,14 +282,14 @@ static void skip_metadata(struct pstore *ps)
* Read or write a metadata area. Remembering to skip the first
* chunk which holds the header.
*/
-static int area_io(struct pstore *ps, int rw)
+static int area_io(struct pstore *ps, int op, int op_flags)
{
int r;
chunk_t chunk;
chunk = area_location(ps, ps->current_area);
- r = chunk_io(ps, ps->area, chunk, rw, 0);
+ r = chunk_io(ps, ps->area, chunk, op, op_flags, 0);
if (r)
return r;
@@ -302,7 +303,8 @@ static void zero_memory_area(struct pstore *ps)
static int zero_disk_area(struct pstore *ps, chunk_t area)
{
- return chunk_io(ps, ps->zero_area, area_location(ps, area), WRITE, 0);
+ return chunk_io(ps, ps->zero_area, area_location(ps, area),
+ REQ_OP_WRITE, 0, 0);
}
static int read_header(struct pstore *ps, int *new_snapshot)
@@ -334,7 +336,7 @@ static int read_header(struct pstore *ps, int *new_snapshot)
if (r)
return r;
- r = chunk_io(ps, ps->header_area, 0, READ, 1);
+ r = chunk_io(ps, ps->header_area, 0, REQ_OP_READ, 0, 1);
if (r)
goto bad;
@@ -395,7 +397,7 @@ static int write_header(struct pstore *ps)
dh->version = cpu_to_le32(ps->version);
dh->chunk_size = cpu_to_le32(ps->store->chunk_size);
- return chunk_io(ps, ps->header_area, 0, WRITE, 1);
+ return chunk_io(ps, ps->header_area, 0, REQ_OP_WRITE, 0, 1);
}
/*
@@ -739,7 +741,7 @@ static void persistent_commit_exception(struct dm_exception_store *store,
/*
* Commit exceptions to disk.
*/
- if (ps->valid && area_io(ps, WRITE_FLUSH_FUA))
+ if (ps->valid && area_io(ps, REQ_OP_WRITE, WRITE_FLUSH_FUA))
ps->valid = 0;
/*
@@ -779,7 +781,7 @@ static int persistent_prepare_merge(struct dm_exception_store *store,
return 0;
ps->current_area--;
- r = area_io(ps, READ);
+ r = area_io(ps, REQ_OP_READ, 0);
if (r < 0)
return r;
ps->current_committed = ps->exceptions_per_area;
@@ -816,7 +818,7 @@ static int persistent_commit_merge(struct dm_exception_store *store,
for (i = 0; i < nr_merged; i++)
clear_exception(ps, ps->current_committed - 1 - i);
- r = area_io(ps, WRITE_FLUSH_FUA);
+ r = area_io(ps, REQ_OP_WRITE, WRITE_FLUSH_FUA);
if (r < 0)
return r;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 70bb0e8b6..c65feeada 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1680,7 +1680,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
init_tracked_chunk(bio);
- if (bio->bi_rw & REQ_FLUSH) {
+ if (bio->bi_opf & REQ_PREFLUSH) {
bio->bi_bdev = s->cow->bdev;
return DM_MAPIO_REMAPPED;
}
@@ -1696,7 +1696,8 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
* to copy an exception */
down_write(&s->lock);
- if (!s->valid || (unlikely(s->snapshot_overflowed) && bio_rw(bio) == WRITE)) {
+ if (!s->valid || (unlikely(s->snapshot_overflowed) &&
+ bio_data_dir(bio) == WRITE)) {
r = -EIO;
goto out_unlock;
}
@@ -1713,7 +1714,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
* flags so we should only get this if we are
* writeable.
*/
- if (bio_rw(bio) == WRITE) {
+ if (bio_data_dir(bio) == WRITE) {
pe = __lookup_pending_exception(s, chunk);
if (!pe) {
up_write(&s->lock);
@@ -1799,7 +1800,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio)
init_tracked_chunk(bio);
- if (bio->bi_rw & REQ_FLUSH) {
+ if (bio->bi_opf & REQ_PREFLUSH) {
if (!dm_bio_get_target_bio_nr(bio))
bio->bi_bdev = s->origin->bdev;
else
@@ -1819,7 +1820,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio)
e = dm_lookup_exception(&s->complete, chunk);
if (e) {
/* Queue writes overlapping with chunks being merged */
- if (bio_rw(bio) == WRITE &&
+ if (bio_data_dir(bio) == WRITE &&
chunk >= s->first_merging_chunk &&
chunk < (s->first_merging_chunk +
s->num_merging_chunks)) {
@@ -1831,7 +1832,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio)
remap_exception(s, e, bio, chunk);
- if (bio_rw(bio) == WRITE)
+ if (bio_data_dir(bio) == WRITE)
track_chunk(s, bio, chunk);
goto out_unlock;
}
@@ -1839,7 +1840,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio)
redirect_to_origin:
bio->bi_bdev = s->origin->bdev;
- if (bio_rw(bio) == WRITE) {
+ if (bio_data_dir(bio) == WRITE) {
up_write(&s->lock);
return do_origin(s->origin, bio);
}
@@ -2285,10 +2286,10 @@ static int origin_map(struct dm_target *ti, struct bio *bio)
bio->bi_bdev = o->dev->bdev;
- if (unlikely(bio->bi_rw & REQ_FLUSH))
+ if (unlikely(bio->bi_opf & REQ_PREFLUSH))
return DM_MAPIO_REMAPPED;
- if (bio_rw(bio) != WRITE)
+ if (bio_data_dir(bio) != WRITE)
return DM_MAPIO_REMAPPED;
available_sectors = o->split_boundary -
@@ -2301,6 +2302,13 @@ static int origin_map(struct dm_target *ti, struct bio *bio)
return do_origin(o->dev, bio);
}
+static long origin_direct_access(struct dm_target *ti, sector_t sector,
+ void **kaddr, pfn_t *pfn, long size)
+{
+ DMWARN("device does not support dax.");
+ return -EIO;
+}
+
/*
* Set the target "max_io_len" field to the minimum of all the snapshots'
* chunk sizes.
@@ -2360,6 +2368,7 @@ static struct target_type origin_target = {
.postsuspend = origin_postsuspend,
.status = origin_status,
.iterate_devices = origin_iterate_devices,
+ .direct_access = origin_direct_access,
};
static struct target_type snapshot_target = {
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 8289804cc..38b05f23b 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -10,7 +10,7 @@
#include <linux/module.h>
#include <linux/device-mapper.h>
-#include "dm.h"
+#include "dm-core.h"
#include "dm-stats.h"
#define DM_MSG_PREFIX "stats"
@@ -514,11 +514,10 @@ static void dm_stat_round(struct dm_stat *s, struct dm_stat_shared *shared,
}
static void dm_stat_for_entry(struct dm_stat *s, size_t entry,
- unsigned long bi_rw, sector_t len,
+ int idx, sector_t len,
struct dm_stats_aux *stats_aux, bool end,
unsigned long duration_jiffies)
{
- unsigned long idx = bi_rw & REQ_WRITE;
struct dm_stat_shared *shared = &s->stat_shared[entry];
struct dm_stat_percpu *p;
@@ -584,7 +583,7 @@ static void dm_stat_for_entry(struct dm_stat *s, size_t entry,
#endif
}
-static void __dm_stat_bio(struct dm_stat *s, unsigned long bi_rw,
+static void __dm_stat_bio(struct dm_stat *s, int bi_rw,
sector_t bi_sector, sector_t end_sector,
bool end, unsigned long duration_jiffies,
struct dm_stats_aux *stats_aux)
@@ -645,8 +644,8 @@ void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw,
last = raw_cpu_ptr(stats->last);
stats_aux->merged =
(bi_sector == (ACCESS_ONCE(last->last_sector) &&
- ((bi_rw & (REQ_WRITE | REQ_DISCARD)) ==
- (ACCESS_ONCE(last->last_rw) & (REQ_WRITE | REQ_DISCARD)))
+ ((bi_rw == WRITE) ==
+ (ACCESS_ONCE(last->last_rw) == WRITE))
));
ACCESS_ONCE(last->last_sector) = end_sector;
ACCESS_ONCE(last->last_rw) = bi_rw;
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 797ddb900..28193a57b 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -286,14 +286,14 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
uint32_t stripe;
unsigned target_bio_nr;
- if (bio->bi_rw & REQ_FLUSH) {
+ if (bio->bi_opf & REQ_PREFLUSH) {
target_bio_nr = dm_bio_get_target_bio_nr(bio);
BUG_ON(target_bio_nr >= sc->stripes);
bio->bi_bdev = sc->stripe[target_bio_nr].dev->bdev;
return DM_MAPIO_REMAPPED;
}
- if (unlikely(bio->bi_rw & REQ_DISCARD) ||
- unlikely(bio->bi_rw & REQ_WRITE_SAME)) {
+ if (unlikely(bio_op(bio) == REQ_OP_DISCARD) ||
+ unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) {
target_bio_nr = dm_bio_get_target_bio_nr(bio);
BUG_ON(target_bio_nr >= sc->stripes);
return stripe_map_range(sc, bio, target_bio_nr);
@@ -308,6 +308,29 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
return DM_MAPIO_REMAPPED;
}
+static long stripe_direct_access(struct dm_target *ti, sector_t sector,
+ void **kaddr, pfn_t *pfn, long size)
+{
+ struct stripe_c *sc = ti->private;
+ uint32_t stripe;
+ struct block_device *bdev;
+ struct blk_dax_ctl dax = {
+ .size = size,
+ };
+ long ret;
+
+ stripe_map_sector(sc, sector, &stripe, &dax.sector);
+
+ dax.sector += sc->stripe[stripe].physical_start;
+ bdev = sc->stripe[stripe].dev->bdev;
+
+ ret = bdev_direct_access(bdev, &dax);
+ *kaddr = dax.addr;
+ *pfn = dax.pfn;
+
+ return ret;
+}
+
/*
* Stripe status:
*
@@ -360,7 +383,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio, int error)
if (!error)
return 0; /* I/O complete */
- if ((error == -EWOULDBLOCK) && (bio->bi_rw & REQ_RAHEAD))
+ if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD))
return error;
if (error == -EOPNOTSUPP)
@@ -416,7 +439,7 @@ static void stripe_io_hints(struct dm_target *ti,
static struct target_type stripe_target = {
.name = "striped",
- .version = {1, 5, 1},
+ .version = {1, 6, 0},
.module = THIS_MODULE,
.ctr = stripe_ctr,
.dtr = stripe_dtr,
@@ -425,6 +448,7 @@ static struct target_type stripe_target = {
.status = stripe_status,
.iterate_devices = stripe_iterate_devices,
.io_hints = stripe_io_hints,
+ .direct_access = stripe_direct_access,
};
int __init dm_stripe_init(void)
diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c
index 7e818f5f1..c209b8a19 100644
--- a/drivers/md/dm-sysfs.c
+++ b/drivers/md/dm-sysfs.c
@@ -6,7 +6,8 @@
#include <linux/sysfs.h>
#include <linux/dm-ioctl.h>
-#include "dm.h"
+#include "dm-core.h"
+#include "dm-rq.h"
struct dm_sysfs_attr {
struct attribute attr;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 626a5ec04..3e407a9cd 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -5,7 +5,7 @@
* This file is released under the GPL.
*/
-#include "dm.h"
+#include "dm-core.h"
#include <linux/module.h>
#include <linux/vmalloc.h>
@@ -43,8 +43,10 @@ struct dm_table {
struct dm_target *targets;
struct target_type *immutable_target_type;
- unsigned integrity_supported:1;
- unsigned singleton:1;
+
+ bool integrity_supported:1;
+ bool singleton:1;
+ bool all_blk_mq:1;
/*
* Indicates the rw permissions for the new logical
@@ -206,6 +208,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
return -ENOMEM;
}
+ t->type = DM_TYPE_NONE;
t->mode = mode;
t->md = md;
*result = t;
@@ -703,7 +706,7 @@ int dm_table_add_target(struct dm_table *t, const char *type,
dm_device_name(t->md), type);
return -EINVAL;
}
- t->singleton = 1;
+ t->singleton = true;
}
if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) {
@@ -824,22 +827,70 @@ void dm_consume_args(struct dm_arg_set *as, unsigned num_args)
}
EXPORT_SYMBOL(dm_consume_args);
+static bool __table_type_bio_based(unsigned table_type)
+{
+ return (table_type == DM_TYPE_BIO_BASED ||
+ table_type == DM_TYPE_DAX_BIO_BASED);
+}
+
static bool __table_type_request_based(unsigned table_type)
{
return (table_type == DM_TYPE_REQUEST_BASED ||
table_type == DM_TYPE_MQ_REQUEST_BASED);
}
-static int dm_table_set_type(struct dm_table *t)
+void dm_table_set_type(struct dm_table *t, unsigned type)
+{
+ t->type = type;
+}
+EXPORT_SYMBOL_GPL(dm_table_set_type);
+
+static int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ struct request_queue *q = bdev_get_queue(dev->bdev);
+
+ return q && blk_queue_dax(q);
+}
+
+static bool dm_table_supports_dax(struct dm_table *t)
+{
+ struct dm_target *ti;
+ unsigned i = 0;
+
+ /* Ensure that all targets support DAX. */
+ while (i < dm_table_get_num_targets(t)) {
+ ti = dm_table_get_target(t, i++);
+
+ if (!ti->type->direct_access)
+ return false;
+
+ if (!ti->type->iterate_devices ||
+ !ti->type->iterate_devices(ti, device_supports_dax, NULL))
+ return false;
+ }
+
+ return true;
+}
+
+static int dm_table_determine_type(struct dm_table *t)
{
unsigned i;
unsigned bio_based = 0, request_based = 0, hybrid = 0;
- bool use_blk_mq = false;
+ bool verify_blk_mq = false;
struct dm_target *tgt;
struct dm_dev_internal *dd;
- struct list_head *devices;
+ struct list_head *devices = dm_table_get_devices(t);
unsigned live_md_type = dm_get_md_type(t->md);
+ if (t->type != DM_TYPE_NONE) {
+ /* target already set the table's type */
+ if (t->type == DM_TYPE_BIO_BASED)
+ return 0;
+ BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED);
+ goto verify_rq_based;
+ }
+
for (i = 0; i < t->num_targets; i++) {
tgt = t->targets + i;
if (dm_target_hybrid(tgt))
@@ -871,11 +922,27 @@ static int dm_table_set_type(struct dm_table *t)
if (bio_based) {
/* We must use this table as bio-based */
t->type = DM_TYPE_BIO_BASED;
+ if (dm_table_supports_dax(t) ||
+ (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED))
+ t->type = DM_TYPE_DAX_BIO_BASED;
return 0;
}
BUG_ON(!request_based); /* No targets in this table */
+ if (list_empty(devices) && __table_type_request_based(live_md_type)) {
+ /* inherit live MD type */
+ t->type = live_md_type;
+ return 0;
+ }
+
+ /*
+ * The only way to establish DM_TYPE_MQ_REQUEST_BASED is by
+ * having a compatible target use dm_table_set_type.
+ */
+ t->type = DM_TYPE_REQUEST_BASED;
+
+verify_rq_based:
/*
* Request-based dm supports only tables that have a single target now.
* To support multiple targets, request splitting support is needed,
@@ -888,7 +955,6 @@ static int dm_table_set_type(struct dm_table *t)
}
/* Non-request-stackable devices can't be used for request-based dm */
- devices = dm_table_get_devices(t);
list_for_each_entry(dd, devices, list) {
struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
@@ -899,10 +965,10 @@ static int dm_table_set_type(struct dm_table *t)
}
if (q->mq_ops)
- use_blk_mq = true;
+ verify_blk_mq = true;
}
- if (use_blk_mq) {
+ if (verify_blk_mq) {
/* verify _all_ devices in the table are blk-mq devices */
list_for_each_entry(dd, devices, list)
if (!bdev_get_queue(dd->dm_dev->bdev)->mq_ops) {
@@ -910,14 +976,9 @@ static int dm_table_set_type(struct dm_table *t)
" are blk-mq request-stackable");
return -EINVAL;
}
- t->type = DM_TYPE_MQ_REQUEST_BASED;
- } else if (list_empty(devices) && __table_type_request_based(live_md_type)) {
- /* inherit live MD type */
- t->type = live_md_type;
-
- } else
- t->type = DM_TYPE_REQUEST_BASED;
+ t->all_blk_mq = true;
+ }
return 0;
}
@@ -956,14 +1017,19 @@ struct dm_target *dm_table_get_wildcard_target(struct dm_table *t)
return NULL;
}
+bool dm_table_bio_based(struct dm_table *t)
+{
+ return __table_type_bio_based(dm_table_get_type(t));
+}
+
bool dm_table_request_based(struct dm_table *t)
{
return __table_type_request_based(dm_table_get_type(t));
}
-bool dm_table_mq_request_based(struct dm_table *t)
+bool dm_table_all_blk_mq_devices(struct dm_table *t)
{
- return dm_table_get_type(t) == DM_TYPE_MQ_REQUEST_BASED;
+ return t->all_blk_mq;
}
static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md)
@@ -978,7 +1044,7 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
return -EINVAL;
}
- if (type == DM_TYPE_BIO_BASED)
+ if (__table_type_bio_based(type))
for (i = 0; i < t->num_targets; i++) {
tgt = t->targets + i;
per_io_data_size = max(per_io_data_size, tgt->per_io_data_size);
@@ -1106,7 +1172,7 @@ static int dm_table_register_integrity(struct dm_table *t)
return 0;
if (!integrity_profile_exists(dm_disk(md))) {
- t->integrity_supported = 1;
+ t->integrity_supported = true;
/*
* Register integrity profile during table load; we can do
* this because the final profile must match during resume.
@@ -1129,7 +1195,7 @@ static int dm_table_register_integrity(struct dm_table *t)
}
/* Preserve existing integrity profile */
- t->integrity_supported = 1;
+ t->integrity_supported = true;
return 0;
}
@@ -1141,9 +1207,9 @@ int dm_table_complete(struct dm_table *t)
{
int r;
- r = dm_table_set_type(t);
+ r = dm_table_determine_type(t);
if (r) {
- DMERR("unable to set table type");
+ DMERR("unable to determine table type");
return r;
}
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index a317dd884..710ae28fd 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -4,7 +4,7 @@
* This file is released under the GPL.
*/
-#include "dm.h"
+#include "dm-core.h"
#include <linux/module.h>
#include <linux/init.h>
@@ -148,9 +148,15 @@ static void io_err_release_clone_rq(struct request *clone)
{
}
+static long io_err_direct_access(struct dm_target *ti, sector_t sector,
+ void **kaddr, pfn_t *pfn, long size)
+{
+ return -EIO;
+}
+
static struct target_type error_target = {
.name = "error",
- .version = {1, 4, 0},
+ .version = {1, 5, 0},
.features = DM_TARGET_WILDCARD,
.ctr = io_err_ctr,
.dtr = io_err_dtr,
@@ -158,6 +164,7 @@ static struct target_type error_target = {
.map_rq = io_err_map_rq,
.clone_and_map_rq = io_err_clone_and_map_rq,
.release_clone_rq = io_err_release_clone_rq,
+ .direct_access = io_err_direct_access,
};
int __init dm_target_init(void)
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 43824d733..a15091a0d 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1677,6 +1677,36 @@ int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *resu
return r;
}
+int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e)
+{
+ int r = 0;
+
+ down_write(&pmd->root_lock);
+ for (; b != e; b++) {
+ r = dm_sm_inc_block(pmd->data_sm, b);
+ if (r)
+ break;
+ }
+ up_write(&pmd->root_lock);
+
+ return r;
+}
+
+int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e)
+{
+ int r = 0;
+
+ down_write(&pmd->root_lock);
+ for (; b != e; b++) {
+ r = dm_sm_dec_block(pmd->data_sm, b);
+ if (r)
+ break;
+ }
+ up_write(&pmd->root_lock);
+
+ return r;
+}
+
bool dm_thin_changed_this_transaction(struct dm_thin_device *td)
{
int r;
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index a938babe4..35e954ea2 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -197,6 +197,9 @@ int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result);
int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result);
+int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e);
+int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e);
+
/*
* Returns -ENOSPC if the new size is too small and already allocated
* blocks would be lost.
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index fc803d50f..d1c05c12a 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -253,6 +253,7 @@ struct pool {
struct bio_list deferred_flush_bios;
struct list_head prepared_mappings;
struct list_head prepared_discards;
+ struct list_head prepared_discards_pt2;
struct list_head active_thins;
struct dm_deferred_set *shared_read_ds;
@@ -269,6 +270,7 @@ struct pool {
process_mapping_fn process_prepared_mapping;
process_mapping_fn process_prepared_discard;
+ process_mapping_fn process_prepared_discard_pt2;
struct dm_bio_prison_cell **cell_sort_array;
};
@@ -360,7 +362,7 @@ static int issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t da
sector_t len = block_to_sectors(tc->pool, data_e - data_b);
return __blkdev_issue_discard(tc->pool_dev->bdev, s, len,
- GFP_NOWAIT, REQ_WRITE | REQ_DISCARD, &op->bio);
+ GFP_NOWAIT, 0, &op->bio);
}
static void end_discard(struct discard_op *op, int r)
@@ -371,7 +373,8 @@ static void end_discard(struct discard_op *op, int r)
* need to wait for the chain to complete.
*/
bio_chain(op->bio, op->parent_bio);
- submit_bio(REQ_WRITE | REQ_DISCARD, op->bio);
+ bio_set_op_attrs(op->bio, REQ_OP_DISCARD, 0);
+ submit_bio(op->bio);
}
blk_finish_plug(&op->plug);
@@ -696,7 +699,7 @@ static void remap_to_origin(struct thin_c *tc, struct bio *bio)
static int bio_triggers_commit(struct thin_c *tc, struct bio *bio)
{
- return (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) &&
+ return (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) &&
dm_thin_changed_this_transaction(tc->td);
}
@@ -704,7 +707,7 @@ static void inc_all_io_entry(struct pool *pool, struct bio *bio)
{
struct dm_thin_endio_hook *h;
- if (bio->bi_rw & REQ_DISCARD)
+ if (bio_op(bio) == REQ_OP_DISCARD)
return;
h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
@@ -867,7 +870,8 @@ static void __inc_remap_and_issue_cell(void *context,
struct bio *bio;
while ((bio = bio_list_pop(&cell->bios))) {
- if (bio->bi_rw & (REQ_DISCARD | REQ_FLUSH | REQ_FUA))
+ if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) ||
+ bio_op(bio) == REQ_OP_DISCARD)
bio_list_add(&info->defer_bios, bio);
else {
inc_all_io_entry(info->tc->pool, bio);
@@ -999,7 +1003,8 @@ static void process_prepared_discard_no_passdown(struct dm_thin_new_mapping *m)
/*----------------------------------------------------------------*/
-static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m)
+static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m,
+ struct bio *discard_parent)
{
/*
* We've already unmapped this range of blocks, but before we
@@ -1012,7 +1017,7 @@ static void passdown_double_checking_shared_status(struct dm_thin_new_mapping *m
dm_block_t b = m->data_block, e, end = m->data_block + m->virt_end - m->virt_begin;
struct discard_op op;
- begin_discard(&op, tc, m->bio);
+ begin_discard(&op, tc, discard_parent);
while (b != end) {
/* find start of unmapped run */
for (; b < end; b++) {
@@ -1047,28 +1052,101 @@ out:
end_discard(&op, r);
}
-static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
+static void queue_passdown_pt2(struct dm_thin_new_mapping *m)
+{
+ unsigned long flags;
+ struct pool *pool = m->tc->pool;
+
+ spin_lock_irqsave(&pool->lock, flags);
+ list_add_tail(&m->list, &pool->prepared_discards_pt2);
+ spin_unlock_irqrestore(&pool->lock, flags);
+ wake_worker(pool);
+}
+
+static void passdown_endio(struct bio *bio)
+{
+ /*
+ * It doesn't matter if the passdown discard failed, we still want
+ * to unmap (we ignore err).
+ */
+ queue_passdown_pt2(bio->bi_private);
+}
+
+static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m)
{
int r;
struct thin_c *tc = m->tc;
struct pool *pool = tc->pool;
+ struct bio *discard_parent;
+ dm_block_t data_end = m->data_block + (m->virt_end - m->virt_begin);
+ /*
+ * Only this thread allocates blocks, so we can be sure that the
+ * newly unmapped blocks will not be allocated before the end of
+ * the function.
+ */
r = dm_thin_remove_range(tc->td, m->virt_begin, m->virt_end);
if (r) {
metadata_operation_failed(pool, "dm_thin_remove_range", r);
bio_io_error(m->bio);
+ cell_defer_no_holder(tc, m->cell);
+ mempool_free(m, pool->mapping_pool);
+ return;
+ }
- } else if (m->maybe_shared) {
- passdown_double_checking_shared_status(m);
+ discard_parent = bio_alloc(GFP_NOIO, 1);
+ if (!discard_parent) {
+ DMWARN("%s: unable to allocate top level discard bio for passdown. Skipping passdown.",
+ dm_device_name(tc->pool->pool_md));
+ queue_passdown_pt2(m);
} else {
- struct discard_op op;
- begin_discard(&op, tc, m->bio);
- r = issue_discard(&op, m->data_block,
- m->data_block + (m->virt_end - m->virt_begin));
- end_discard(&op, r);
+ discard_parent->bi_end_io = passdown_endio;
+ discard_parent->bi_private = m;
+
+ if (m->maybe_shared)
+ passdown_double_checking_shared_status(m, discard_parent);
+ else {
+ struct discard_op op;
+
+ begin_discard(&op, tc, discard_parent);
+ r = issue_discard(&op, m->data_block, data_end);
+ end_discard(&op, r);
+ }
}
+ /*
+ * Increment the unmapped blocks. This prevents a race between the
+ * passdown io and reallocation of freed blocks.
+ */
+ r = dm_pool_inc_data_range(pool->pmd, m->data_block, data_end);
+ if (r) {
+ metadata_operation_failed(pool, "dm_pool_inc_data_range", r);
+ bio_io_error(m->bio);
+ cell_defer_no_holder(tc, m->cell);
+ mempool_free(m, pool->mapping_pool);
+ return;
+ }
+}
+
+static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m)
+{
+ int r;
+ struct thin_c *tc = m->tc;
+ struct pool *pool = tc->pool;
+
+ /*
+ * The passdown has completed, so now we can decrement all those
+ * unmapped blocks.
+ */
+ r = dm_pool_dec_data_range(pool->pmd, m->data_block,
+ m->data_block + (m->virt_end - m->virt_begin));
+ if (r) {
+ metadata_operation_failed(pool, "dm_pool_dec_data_range", r);
+ bio_io_error(m->bio);
+ } else
+ bio_endio(m->bio);
+
cell_defer_no_holder(tc, m->cell);
mempool_free(m, pool->mapping_pool);
}
@@ -1639,7 +1717,8 @@ static void __remap_and_issue_shared_cell(void *context,
while ((bio = bio_list_pop(&cell->bios))) {
if ((bio_data_dir(bio) == WRITE) ||
- (bio->bi_rw & (REQ_DISCARD | REQ_FLUSH | REQ_FUA)))
+ (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) ||
+ bio_op(bio) == REQ_OP_DISCARD))
bio_list_add(&info->defer_bios, bio);
else {
struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));;
@@ -2028,7 +2107,7 @@ static void process_thin_deferred_bios(struct thin_c *tc)
break;
}
- if (bio->bi_rw & REQ_DISCARD)
+ if (bio_op(bio) == REQ_OP_DISCARD)
pool->process_discard(tc, bio);
else
pool->process_bio(tc, bio);
@@ -2115,7 +2194,7 @@ static void process_thin_deferred_cells(struct thin_c *tc)
return;
}
- if (cell->holder->bi_rw & REQ_DISCARD)
+ if (bio_op(cell->holder) == REQ_OP_DISCARD)
pool->process_discard_cell(tc, cell);
else
pool->process_cell(tc, cell);
@@ -2212,6 +2291,8 @@ static void do_worker(struct work_struct *ws)
throttle_work_update(&pool->throttle);
process_prepared(pool, &pool->prepared_discards, &pool->process_prepared_discard);
throttle_work_update(&pool->throttle);
+ process_prepared(pool, &pool->prepared_discards_pt2, &pool->process_prepared_discard_pt2);
+ throttle_work_update(&pool->throttle);
process_deferred_bios(pool);
throttle_work_complete(&pool->throttle);
}
@@ -2340,7 +2421,8 @@ static void set_discard_callbacks(struct pool *pool)
if (passdown_enabled(pt)) {
pool->process_discard_cell = process_discard_cell_passdown;
- pool->process_prepared_discard = process_prepared_discard_passdown;
+ pool->process_prepared_discard = process_prepared_discard_passdown_pt1;
+ pool->process_prepared_discard_pt2 = process_prepared_discard_passdown_pt2;
} else {
pool->process_discard_cell = process_discard_cell_no_passdown;
pool->process_prepared_discard = process_prepared_discard_no_passdown;
@@ -2553,7 +2635,8 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
return DM_MAPIO_SUBMITTED;
}
- if (bio->bi_rw & (REQ_DISCARD | REQ_FLUSH | REQ_FUA)) {
+ if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) ||
+ bio_op(bio) == REQ_OP_DISCARD) {
thin_defer_bio_with_throttle(tc, bio);
return DM_MAPIO_SUBMITTED;
}
@@ -2826,6 +2909,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
bio_list_init(&pool->deferred_flush_bios);
INIT_LIST_HEAD(&pool->prepared_mappings);
INIT_LIST_HEAD(&pool->prepared_discards);
+ INIT_LIST_HEAD(&pool->prepared_discards_pt2);
INIT_LIST_HEAD(&pool->active_thins);
pool->low_water_triggered = false;
pool->suspended = true;
diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c
index 766bc9300..b616f11d8 100644
--- a/drivers/md/dm-zero.c
+++ b/drivers/md/dm-zero.c
@@ -35,16 +35,19 @@ static int zero_ctr(struct dm_target *ti, unsigned int argc, char **argv)
*/
static int zero_map(struct dm_target *ti, struct bio *bio)
{
- switch(bio_rw(bio)) {
- case READ:
+ switch (bio_op(bio)) {
+ case REQ_OP_READ:
+ if (bio->bi_opf & REQ_RAHEAD) {
+ /* readahead of null bytes only wastes buffer cache */
+ return -EIO;
+ }
zero_fill_bio(bio);
break;
- case READA:
- /* readahead of null bytes only wastes buffer cache */
- return -EIO;
- case WRITE:
+ case REQ_OP_WRITE:
/* writes get silently dropped */
break;
+ default:
+ return -EIO;
}
bio_endio(bio);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index fd40bcb39..fa9b1cb44 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -5,13 +5,13 @@
* This file is released under the GPL.
*/
-#include "dm.h"
+#include "dm-core.h"
+#include "dm-rq.h"
#include "dm-uevent.h"
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mutex.h>
-#include <linux/moduleparam.h>
#include <linux/blkpg.h>
#include <linux/bio.h>
#include <linux/mempool.h>
@@ -20,14 +20,8 @@
#include <linux/hdreg.h>
#include <linux/delay.h>
#include <linux/wait.h>
-#include <linux/kthread.h>
-#include <linux/ktime.h>
-#include <linux/elevator.h> /* for rq_end_sector() */
-#include <linux/blk-mq.h>
#include <linux/pr.h>
-#include <trace/events/block.h>
-
#define DM_MSG_PREFIX "core"
#ifdef CONFIG_PRINTK
@@ -63,7 +57,6 @@ static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
static struct workqueue_struct *deferred_remove_workqueue;
/*
- * For bio-based dm.
* One of these is allocated per bio.
*/
struct dm_io {
@@ -76,36 +69,6 @@ struct dm_io {
struct dm_stats_aux stats_aux;
};
-/*
- * For request-based dm.
- * One of these is allocated per request.
- */
-struct dm_rq_target_io {
- struct mapped_device *md;
- struct dm_target *ti;
- struct request *orig, *clone;
- struct kthread_work work;
- int error;
- union map_info info;
- struct dm_stats_aux stats_aux;
- unsigned long duration_jiffies;
- unsigned n_sectors;
-};
-
-/*
- * For request-based dm - the bio clones we allocate are embedded in these
- * structs.
- *
- * We allocate these with bio_alloc_bioset, using the front_pad parameter when
- * the bioset is created - this means the bio has to come at the end of the
- * struct.
- */
-struct dm_rq_clone_bio_info {
- struct bio *orig;
- struct dm_rq_target_io *tio;
- struct bio clone;
-};
-
#define MINOR_ALLOCED ((void *)-1)
/*
@@ -120,130 +83,9 @@ struct dm_rq_clone_bio_info {
#define DMF_DEFERRED_REMOVE 6
#define DMF_SUSPENDED_INTERNALLY 7
-/*
- * Work processed by per-device workqueue.
- */
-struct mapped_device {
- struct srcu_struct io_barrier;
- struct mutex suspend_lock;
-
- /*
- * The current mapping (struct dm_table *).
- * Use dm_get_live_table{_fast} or take suspend_lock for
- * dereference.
- */
- void __rcu *map;
-
- struct list_head table_devices;
- struct mutex table_devices_lock;
-
- unsigned long flags;
-
- struct request_queue *queue;
- int numa_node_id;
-
- unsigned type;
- /* Protect queue and type against concurrent access. */
- struct mutex type_lock;
-
- atomic_t holders;
- atomic_t open_count;
-
- struct dm_target *immutable_target;
- struct target_type *immutable_target_type;
-
- struct gendisk *disk;
- char name[16];
-
- void *interface_ptr;
-
- /*
- * A list of ios that arrived while we were suspended.
- */
- atomic_t pending[2];
- wait_queue_head_t wait;
- struct work_struct work;
- spinlock_t deferred_lock;
- struct bio_list deferred;
-
- /*
- * Event handling.
- */
- wait_queue_head_t eventq;
- atomic_t event_nr;
- atomic_t uevent_seq;
- struct list_head uevent_list;
- spinlock_t uevent_lock; /* Protect access to uevent_list */
-
- /* the number of internal suspends */
- unsigned internal_suspend_count;
-
- /*
- * Processing queue (flush)
- */
- struct workqueue_struct *wq;
-
- /*
- * io objects are allocated from here.
- */
- mempool_t *io_pool;
- mempool_t *rq_pool;
-
- struct bio_set *bs;
-
- /*
- * freeze/thaw support require holding onto a super block
- */
- struct super_block *frozen_sb;
-
- /* forced geometry settings */
- struct hd_geometry geometry;
-
- struct block_device *bdev;
-
- /* kobject and completion */
- struct dm_kobject_holder kobj_holder;
-
- /* zero-length flush that will be cloned and submitted to targets */
- struct bio flush_bio;
-
- struct dm_stats stats;
-
- struct kthread_worker kworker;
- struct task_struct *kworker_task;
-
- /* for request-based merge heuristic in dm_request_fn() */
- unsigned seq_rq_merge_deadline_usecs;
- int last_rq_rw;
- sector_t last_rq_pos;
- ktime_t last_rq_start_time;
-
- /* for blk-mq request-based DM support */
- struct blk_mq_tag_set *tag_set;
- bool use_blk_mq:1;
- bool init_tio_pdu:1;
-};
-
-#ifdef CONFIG_DM_MQ_DEFAULT
-static bool use_blk_mq = true;
-#else
-static bool use_blk_mq = false;
-#endif
-
-#define DM_MQ_NR_HW_QUEUES 1
-#define DM_MQ_QUEUE_DEPTH 2048
#define DM_NUMA_NODE NUMA_NO_NODE
-
-static unsigned dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES;
-static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH;
static int dm_numa_node = DM_NUMA_NODE;
-bool dm_use_blk_mq(struct mapped_device *md)
-{
- return md->use_blk_mq;
-}
-EXPORT_SYMBOL_GPL(dm_use_blk_mq);
-
/*
* For mempools pre-allocation at the table loading time.
*/
@@ -259,9 +101,6 @@ struct table_device {
struct dm_dev dm_dev;
};
-#define RESERVED_BIO_BASED_IOS 16
-#define RESERVED_REQUEST_BASED_IOS 256
-#define RESERVED_MAX_IOS 1024
static struct kmem_cache *_io_cache;
static struct kmem_cache *_rq_tio_cache;
static struct kmem_cache *_rq_cache;
@@ -269,13 +108,9 @@ static struct kmem_cache *_rq_cache;
/*
* Bio-based DM's mempools' reserved IOs set by the user.
*/
+#define RESERVED_BIO_BASED_IOS 16
static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS;
-/*
- * Request-based DM's mempools' reserved IOs set by the user.
- */
-static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
-
static int __dm_get_module_param_int(int *module_param, int min, int max)
{
int param = ACCESS_ONCE(*module_param);
@@ -297,8 +132,8 @@ static int __dm_get_module_param_int(int *module_param, int min, int max)
return param;
}
-static unsigned __dm_get_module_param(unsigned *module_param,
- unsigned def, unsigned max)
+unsigned __dm_get_module_param(unsigned *module_param,
+ unsigned def, unsigned max)
{
unsigned param = ACCESS_ONCE(*module_param);
unsigned modified_param = 0;
@@ -319,28 +154,10 @@ static unsigned __dm_get_module_param(unsigned *module_param,
unsigned dm_get_reserved_bio_based_ios(void)
{
return __dm_get_module_param(&reserved_bio_based_ios,
- RESERVED_BIO_BASED_IOS, RESERVED_MAX_IOS);
+ RESERVED_BIO_BASED_IOS, DM_RESERVED_MAX_IOS);
}
EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios);
-unsigned dm_get_reserved_rq_based_ios(void)
-{
- return __dm_get_module_param(&reserved_rq_based_ios,
- RESERVED_REQUEST_BASED_IOS, RESERVED_MAX_IOS);
-}
-EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);
-
-static unsigned dm_get_blk_mq_nr_hw_queues(void)
-{
- return __dm_get_module_param(&dm_mq_nr_hw_queues, 1, 32);
-}
-
-static unsigned dm_get_blk_mq_queue_depth(void)
-{
- return __dm_get_module_param(&dm_mq_queue_depth,
- DM_MQ_QUEUE_DEPTH, BLK_MQ_MAX_DEPTH);
-}
-
static unsigned dm_get_numa_node(void)
{
return __dm_get_module_param_int(&dm_numa_node,
@@ -679,29 +496,7 @@ static void free_tio(struct dm_target_io *tio)
bio_put(&tio->clone);
}
-static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
- gfp_t gfp_mask)
-{
- return mempool_alloc(md->io_pool, gfp_mask);
-}
-
-static void free_old_rq_tio(struct dm_rq_target_io *tio)
-{
- mempool_free(tio, tio->md->io_pool);
-}
-
-static struct request *alloc_old_clone_request(struct mapped_device *md,
- gfp_t gfp_mask)
-{
- return mempool_alloc(md->rq_pool, gfp_mask);
-}
-
-static void free_old_clone_request(struct mapped_device *md, struct request *rq)
-{
- mempool_free(rq, md->rq_pool);
-}
-
-static int md_in_flight(struct mapped_device *md)
+int md_in_flight(struct mapped_device *md)
{
return atomic_read(&md->pending[READ]) +
atomic_read(&md->pending[WRITE]);
@@ -723,8 +518,9 @@ static void start_io_acct(struct dm_io *io)
atomic_inc_return(&md->pending[rw]));
if (unlikely(dm_stats_used(&md->stats)))
- dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector,
- bio_sectors(bio), false, 0, &io->stats_aux);
+ dm_stats_account_io(&md->stats, bio_data_dir(bio),
+ bio->bi_iter.bi_sector, bio_sectors(bio),
+ false, 0, &io->stats_aux);
}
static void end_io_acct(struct dm_io *io)
@@ -738,8 +534,9 @@ static void end_io_acct(struct dm_io *io)
generic_end_io_acct(rw, &dm_disk(md)->part0, io->start_time);
if (unlikely(dm_stats_used(&md->stats)))
- dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector,
- bio_sectors(bio), true, duration, &io->stats_aux);
+ dm_stats_account_io(&md->stats, bio_data_dir(bio),
+ bio->bi_iter.bi_sector, bio_sectors(bio),
+ true, duration, &io->stats_aux);
/*
* After this is decremented the bio must not be touched if it is
@@ -1001,12 +798,12 @@ static void dec_pending(struct dm_io *io, int error)
if (io_error == DM_ENDIO_REQUEUE)
return;
- if ((bio->bi_rw & REQ_FLUSH) && bio->bi_iter.bi_size) {
+ if ((bio->bi_opf & REQ_PREFLUSH) && bio->bi_iter.bi_size) {
/*
* Preflush done for flush with data, reissue
- * without REQ_FLUSH.
+ * without REQ_PREFLUSH.
*/
- bio->bi_rw &= ~REQ_FLUSH;
+ bio->bi_opf &= ~REQ_PREFLUSH;
queue_io(md, bio);
} else {
/* done with normal IO or empty flush */
@@ -1017,7 +814,7 @@ static void dec_pending(struct dm_io *io, int error)
}
}
-static void disable_write_same(struct mapped_device *md)
+void disable_write_same(struct mapped_device *md)
{
struct queue_limits *limits = dm_get_queue_limits(md);
@@ -1051,7 +848,7 @@ static void clone_endio(struct bio *bio)
}
}
- if (unlikely(r == -EREMOTEIO && (bio->bi_rw & REQ_WRITE_SAME) &&
+ if (unlikely(r == -EREMOTEIO && (bio_op(bio) == REQ_OP_WRITE_SAME) &&
!bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors))
disable_write_same(md);
@@ -1060,371 +857,6 @@ static void clone_endio(struct bio *bio)
}
/*
- * Partial completion handling for request-based dm
- */
-static void end_clone_bio(struct bio *clone)
-{
- struct dm_rq_clone_bio_info *info =
- container_of(clone, struct dm_rq_clone_bio_info, clone);
- struct dm_rq_target_io *tio = info->tio;
- struct bio *bio = info->orig;
- unsigned int nr_bytes = info->orig->bi_iter.bi_size;
- int error = clone->bi_error;
-
- bio_put(clone);
-
- if (tio->error)
- /*
- * An error has already been detected on the request.
- * Once error occurred, just let clone->end_io() handle
- * the remainder.
- */
- return;
- else if (error) {
- /*
- * Don't notice the error to the upper layer yet.
- * The error handling decision is made by the target driver,
- * when the request is completed.
- */
- tio->error = error;
- return;
- }
-
- /*
- * I/O for the bio successfully completed.
- * Notice the data completion to the upper layer.
- */
-
- /*
- * bios are processed from the head of the list.
- * So the completing bio should always be rq->bio.
- * If it's not, something wrong is happening.
- */
- if (tio->orig->bio != bio)
- DMERR("bio completion is going in the middle of the request");
-
- /*
- * Update the original request.
- * Do not use blk_end_request() here, because it may complete
- * the original request before the clone, and break the ordering.
- */
- blk_update_request(tio->orig, 0, nr_bytes);
-}
-
-static struct dm_rq_target_io *tio_from_request(struct request *rq)
-{
- return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
-}
-
-static void rq_end_stats(struct mapped_device *md, struct request *orig)
-{
- if (unlikely(dm_stats_used(&md->stats))) {
- struct dm_rq_target_io *tio = tio_from_request(orig);
- tio->duration_jiffies = jiffies - tio->duration_jiffies;
- dm_stats_account_io(&md->stats, orig->cmd_flags, blk_rq_pos(orig),
- tio->n_sectors, true, tio->duration_jiffies,
- &tio->stats_aux);
- }
-}
-
-/*
- * Don't touch any member of the md after calling this function because
- * the md may be freed in dm_put() at the end of this function.
- * Or do dm_get() before calling this function and dm_put() later.
- */
-static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
-{
- atomic_dec(&md->pending[rw]);
-
- /* nudge anyone waiting on suspend queue */
- if (!md_in_flight(md))
- wake_up(&md->wait);
-
- /*
- * Run this off this callpath, as drivers could invoke end_io while
- * inside their request_fn (and holding the queue lock). Calling
- * back into ->request_fn() could deadlock attempting to grab the
- * queue lock again.
- */
- if (!md->queue->mq_ops && run_queue)
- blk_run_queue_async(md->queue);
-
- /*
- * dm_put() must be at the end of this function. See the comment above
- */
- dm_put(md);
-}
-
-static void free_rq_clone(struct request *clone)
-{
- struct dm_rq_target_io *tio = clone->end_io_data;
- struct mapped_device *md = tio->md;
-
- blk_rq_unprep_clone(clone);
-
- if (md->type == DM_TYPE_MQ_REQUEST_BASED)
- /* stacked on blk-mq queue(s) */
- tio->ti->type->release_clone_rq(clone);
- else if (!md->queue->mq_ops)
- /* request_fn queue stacked on request_fn queue(s) */
- free_old_clone_request(md, clone);
-
- if (!md->queue->mq_ops)
- free_old_rq_tio(tio);
-}
-
-/*
- * Complete the clone and the original request.
- * Must be called without clone's queue lock held,
- * see end_clone_request() for more details.
- */
-static void dm_end_request(struct request *clone, int error)
-{
- int rw = rq_data_dir(clone);
- struct dm_rq_target_io *tio = clone->end_io_data;
- struct mapped_device *md = tio->md;
- struct request *rq = tio->orig;
-
- if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
- rq->errors = clone->errors;
- rq->resid_len = clone->resid_len;
-
- if (rq->sense)
- /*
- * We are using the sense buffer of the original
- * request.
- * So setting the length of the sense data is enough.
- */
- rq->sense_len = clone->sense_len;
- }
-
- free_rq_clone(clone);
- rq_end_stats(md, rq);
- if (!rq->q->mq_ops)
- blk_end_request_all(rq, error);
- else
- blk_mq_end_request(rq, error);
- rq_completed(md, rw, true);
-}
-
-static void dm_unprep_request(struct request *rq)
-{
- struct dm_rq_target_io *tio = tio_from_request(rq);
- struct request *clone = tio->clone;
-
- if (!rq->q->mq_ops) {
- rq->special = NULL;
- rq->cmd_flags &= ~REQ_DONTPREP;
- }
-
- if (clone)
- free_rq_clone(clone);
- else if (!tio->md->queue->mq_ops)
- free_old_rq_tio(tio);
-}
-
-/*
- * Requeue the original request of a clone.
- */
-static void dm_old_requeue_request(struct request *rq)
-{
- struct request_queue *q = rq->q;
- unsigned long flags;
-
- spin_lock_irqsave(q->queue_lock, flags);
- blk_requeue_request(q, rq);
- blk_run_queue_async(q);
- spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_mq_requeue_request(struct request *rq)
-{
- struct request_queue *q = rq->q;
- unsigned long flags;
-
- blk_mq_requeue_request(rq);
- spin_lock_irqsave(q->queue_lock, flags);
- if (!blk_queue_stopped(q))
- blk_mq_kick_requeue_list(q);
- spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_requeue_original_request(struct mapped_device *md,
- struct request *rq)
-{
- int rw = rq_data_dir(rq);
-
- rq_end_stats(md, rq);
- dm_unprep_request(rq);
-
- if (!rq->q->mq_ops)
- dm_old_requeue_request(rq);
- else
- dm_mq_requeue_request(rq);
-
- rq_completed(md, rw, false);
-}
-
-static void dm_old_stop_queue(struct request_queue *q)
-{
- unsigned long flags;
-
- spin_lock_irqsave(q->queue_lock, flags);
- if (blk_queue_stopped(q)) {
- spin_unlock_irqrestore(q->queue_lock, flags);
- return;
- }
-
- blk_stop_queue(q);
- spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_stop_queue(struct request_queue *q)
-{
- if (!q->mq_ops)
- dm_old_stop_queue(q);
- else
- blk_mq_stop_hw_queues(q);
-}
-
-static void dm_old_start_queue(struct request_queue *q)
-{
- unsigned long flags;
-
- spin_lock_irqsave(q->queue_lock, flags);
- if (blk_queue_stopped(q))
- blk_start_queue(q);
- spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-static void dm_start_queue(struct request_queue *q)
-{
- if (!q->mq_ops)
- dm_old_start_queue(q);
- else {
- blk_mq_start_stopped_hw_queues(q, true);
- blk_mq_kick_requeue_list(q);
- }
-}
-
-static void dm_done(struct request *clone, int error, bool mapped)
-{
- int r = error;
- struct dm_rq_target_io *tio = clone->end_io_data;
- dm_request_endio_fn rq_end_io = NULL;
-
- if (tio->ti) {
- rq_end_io = tio->ti->type->rq_end_io;
-
- if (mapped && rq_end_io)
- r = rq_end_io(tio->ti, clone, error, &tio->info);
- }
-
- if (unlikely(r == -EREMOTEIO && (clone->cmd_flags & REQ_WRITE_SAME) &&
- !clone->q->limits.max_write_same_sectors))
- disable_write_same(tio->md);
-
- if (r <= 0)
- /* The target wants to complete the I/O */
- dm_end_request(clone, r);
- else if (r == DM_ENDIO_INCOMPLETE)
- /* The target will handle the I/O */
- return;
- else if (r == DM_ENDIO_REQUEUE)
- /* The target wants to requeue the I/O */
- dm_requeue_original_request(tio->md, tio->orig);
- else {
- DMWARN("unimplemented target endio return value: %d", r);
- BUG();
- }
-}
-
-/*
- * Request completion handler for request-based dm
- */
-static void dm_softirq_done(struct request *rq)
-{
- bool mapped = true;
- struct dm_rq_target_io *tio = tio_from_request(rq);
- struct request *clone = tio->clone;
- int rw;
-
- if (!clone) {
- rq_end_stats(tio->md, rq);
- rw = rq_data_dir(rq);
- if (!rq->q->mq_ops) {
- blk_end_request_all(rq, tio->error);
- rq_completed(tio->md, rw, false);
- free_old_rq_tio(tio);
- } else {
- blk_mq_end_request(rq, tio->error);
- rq_completed(tio->md, rw, false);
- }
- return;
- }
-
- if (rq->cmd_flags & REQ_FAILED)
- mapped = false;
-
- dm_done(clone, tio->error, mapped);
-}
-
-/*
- * Complete the clone and the original request with the error status
- * through softirq context.
- */
-static void dm_complete_request(struct request *rq, int error)
-{
- struct dm_rq_target_io *tio = tio_from_request(rq);
-
- tio->error = error;
- if (!rq->q->mq_ops)
- blk_complete_request(rq);
- else
- blk_mq_complete_request(rq, error);
-}
-
-/*
- * Complete the not-mapped clone and the original request with the error status
- * through softirq context.
- * Target's rq_end_io() function isn't called.
- * This may be used when the target's map_rq() or clone_and_map_rq() functions fail.
- */
-static void dm_kill_unmapped_request(struct request *rq, int error)
-{
- rq->cmd_flags |= REQ_FAILED;
- dm_complete_request(rq, error);
-}
-
-/*
- * Called with the clone's queue lock held (in the case of .request_fn)
- */
-static void end_clone_request(struct request *clone, int error)
-{
- struct dm_rq_target_io *tio = clone->end_io_data;
-
- if (!clone->q->mq_ops) {
- /*
- * For just cleaning up the information of the queue in which
- * the clone was dispatched.
- * The clone is *NOT* freed actually here because it is alloced
- * from dm own mempool (REQ_ALLOCED isn't set).
- */
- __blk_put_request(clone->q, clone);
- }
-
- /*
- * Actual request completion is done in a softirq context which doesn't
- * hold the clone's queue lock. Otherwise, deadlock could occur because:
- * - another request may be submitted by the upper level driver
- * of the stacking during the completion
- * - the submission which requires queue lock may be done
- * against this clone's queue
- */
- dm_complete_request(tio->orig, error);
-}
-
-/*
* Return maximum size of I/O possible at the supplied sector up to the current
* target boundary.
*/
@@ -1473,9 +905,36 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
}
EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
+static long dm_blk_direct_access(struct block_device *bdev, sector_t sector,
+ void **kaddr, pfn_t *pfn, long size)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ struct dm_table *map;
+ struct dm_target *ti;
+ int srcu_idx;
+ long len, ret = -EIO;
+
+ map = dm_get_live_table(md, &srcu_idx);
+ if (!map)
+ goto out;
+
+ ti = dm_table_find_target(map, sector);
+ if (!dm_target_is_valid(ti))
+ goto out;
+
+ len = max_io_len(sector, ti) << SECTOR_SHIFT;
+ size = min(len, size);
+
+ if (ti->type->direct_access)
+ ret = ti->type->direct_access(ti, sector, kaddr, pfn, size);
+out:
+ dm_put_live_table(md, srcu_idx);
+ return min(ret, size);
+}
+
/*
* A target may call dm_accept_partial_bio only from the map routine. It is
- * allowed for all bio types except REQ_FLUSH.
+ * allowed for all bio types except REQ_PREFLUSH.
*
* dm_accept_partial_bio informs the dm that the target only wants to process
* additional n_sectors sectors of the bio and the rest of the data should be
@@ -1505,7 +964,7 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
{
struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
unsigned bi_size = bio->bi_iter.bi_size >> SECTOR_SHIFT;
- BUG_ON(bio->bi_rw & REQ_FLUSH);
+ BUG_ON(bio->bi_opf & REQ_PREFLUSH);
BUG_ON(bi_size > *tio->len_ptr);
BUG_ON(n_sectors > bi_size);
*tio->len_ptr -= bi_size - n_sectors;
@@ -1746,9 +1205,9 @@ static int __split_and_process_non_flush(struct clone_info *ci)
unsigned len;
int r;
- if (unlikely(bio->bi_rw & REQ_DISCARD))
+ if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
return __send_discard(ci);
- else if (unlikely(bio->bi_rw & REQ_WRITE_SAME))
+ else if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
return __send_write_same(ci);
ti = dm_table_find_target(ci->map, ci->sector);
@@ -1793,7 +1252,7 @@ static void __split_and_process_bio(struct mapped_device *md,
start_io_acct(ci.io);
- if (bio->bi_rw & REQ_FLUSH) {
+ if (bio->bi_opf & REQ_PREFLUSH) {
ci.bio = &ci.md->flush_bio;
ci.sector_count = 0;
error = __send_empty_flush(&ci);
@@ -1831,7 +1290,7 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
dm_put_live_table(md, srcu_idx);
- if (bio_rw(bio) != READA)
+ if (!(bio->bi_opf & REQ_RAHEAD))
queue_io(md, bio);
else
bio_io_error(bio);
@@ -1843,352 +1302,6 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
return BLK_QC_T_NONE;
}
-int dm_request_based(struct mapped_device *md)
-{
- return blk_queue_stackable(md->queue);
-}
-
-static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
-{
- int r;
-
- if (blk_queue_io_stat(clone->q))
- clone->cmd_flags |= REQ_IO_STAT;
-
- clone->start_time = jiffies;
- r = blk_insert_cloned_request(clone->q, clone);
- if (r)
- /* must complete clone in terms of original request */
- dm_complete_request(rq, r);
-}
-
-static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
- void *data)
-{
- struct dm_rq_target_io *tio = data;
- struct dm_rq_clone_bio_info *info =
- container_of(bio, struct dm_rq_clone_bio_info, clone);
-
- info->orig = bio_orig;
- info->tio = tio;
- bio->bi_end_io = end_clone_bio;
-
- return 0;
-}
-
-static int setup_clone(struct request *clone, struct request *rq,
- struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
- int r;
-
- r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
- dm_rq_bio_constructor, tio);
- if (r)
- return r;
-
- clone->cmd = rq->cmd;
- clone->cmd_len = rq->cmd_len;
- clone->sense = rq->sense;
- clone->end_io = end_clone_request;
- clone->end_io_data = tio;
-
- tio->clone = clone;
-
- return 0;
-}
-
-static struct request *clone_old_rq(struct request *rq, struct mapped_device *md,
- struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
- /*
- * Create clone for use with .request_fn request_queue
- */
- struct request *clone;
-
- clone = alloc_old_clone_request(md, gfp_mask);
- if (!clone)
- return NULL;
-
- blk_rq_init(NULL, clone);
- if (setup_clone(clone, rq, tio, gfp_mask)) {
- /* -ENOMEM */
- free_old_clone_request(md, clone);
- return NULL;
- }
-
- return clone;
-}
-
-static void map_tio_request(struct kthread_work *work);
-
-static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
- struct mapped_device *md)
-{
- tio->md = md;
- tio->ti = NULL;
- tio->clone = NULL;
- tio->orig = rq;
- tio->error = 0;
- /*
- * Avoid initializing info for blk-mq; it passes
- * target-specific data through info.ptr
- * (see: dm_mq_init_request)
- */
- if (!md->init_tio_pdu)
- memset(&tio->info, 0, sizeof(tio->info));
- if (md->kworker_task)
- init_kthread_work(&tio->work, map_tio_request);
-}
-
-static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq,
- struct mapped_device *md,
- gfp_t gfp_mask)
-{
- struct dm_rq_target_io *tio;
- int srcu_idx;
- struct dm_table *table;
-
- tio = alloc_old_rq_tio(md, gfp_mask);
- if (!tio)
- return NULL;
-
- init_tio(tio, rq, md);
-
- table = dm_get_live_table(md, &srcu_idx);
- /*
- * Must clone a request if this .request_fn DM device
- * is stacked on .request_fn device(s).
- */
- if (!dm_table_mq_request_based(table)) {
- if (!clone_old_rq(rq, md, tio, gfp_mask)) {
- dm_put_live_table(md, srcu_idx);
- free_old_rq_tio(tio);
- return NULL;
- }
- }
- dm_put_live_table(md, srcu_idx);
-
- return tio;
-}
-
-/*
- * Called with the queue lock held.
- */
-static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
-{
- struct mapped_device *md = q->queuedata;
- struct dm_rq_target_io *tio;
-
- if (unlikely(rq->special)) {
- DMWARN("Already has something in rq->special.");
- return BLKPREP_KILL;
- }
-
- tio = dm_old_prep_tio(rq, md, GFP_ATOMIC);
- if (!tio)
- return BLKPREP_DEFER;
-
- rq->special = tio;
- rq->cmd_flags |= REQ_DONTPREP;
-
- return BLKPREP_OK;
-}
-
-/*
- * Returns:
- * 0 : the request has been processed
- * DM_MAPIO_REQUEUE : the original request needs to be requeued
- * < 0 : the request was completed due to failure
- */
-static int map_request(struct dm_rq_target_io *tio, struct request *rq,
- struct mapped_device *md)
-{
- int r;
- struct dm_target *ti = tio->ti;
- struct request *clone = NULL;
-
- if (tio->clone) {
- clone = tio->clone;
- r = ti->type->map_rq(ti, clone, &tio->info);
- } else {
- r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
- if (r < 0) {
- /* The target wants to complete the I/O */
- dm_kill_unmapped_request(rq, r);
- return r;
- }
- if (r != DM_MAPIO_REMAPPED)
- return r;
- if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
- /* -ENOMEM */
- ti->type->release_clone_rq(clone);
- return DM_MAPIO_REQUEUE;
- }
- }
-
- switch (r) {
- case DM_MAPIO_SUBMITTED:
- /* The target has taken the I/O to submit by itself later */
- break;
- case DM_MAPIO_REMAPPED:
- /* The target has remapped the I/O so dispatch it */
- trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
- blk_rq_pos(rq));
- dm_dispatch_clone_request(clone, rq);
- break;
- case DM_MAPIO_REQUEUE:
- /* The target wants to requeue the I/O */
- dm_requeue_original_request(md, tio->orig);
- break;
- default:
- if (r > 0) {
- DMWARN("unimplemented target map return value: %d", r);
- BUG();
- }
-
- /* The target wants to complete the I/O */
- dm_kill_unmapped_request(rq, r);
- return r;
- }
-
- return 0;
-}
-
-static void map_tio_request(struct kthread_work *work)
-{
- struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
- struct request *rq = tio->orig;
- struct mapped_device *md = tio->md;
-
- if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
- dm_requeue_original_request(md, rq);
-}
-
-static void dm_start_request(struct mapped_device *md, struct request *orig)
-{
- if (!orig->q->mq_ops)
- blk_start_request(orig);
- else
- blk_mq_start_request(orig);
- atomic_inc(&md->pending[rq_data_dir(orig)]);
-
- if (md->seq_rq_merge_deadline_usecs) {
- md->last_rq_pos = rq_end_sector(orig);
- md->last_rq_rw = rq_data_dir(orig);
- md->last_rq_start_time = ktime_get();
- }
-
- if (unlikely(dm_stats_used(&md->stats))) {
- struct dm_rq_target_io *tio = tio_from_request(orig);
- tio->duration_jiffies = jiffies;
- tio->n_sectors = blk_rq_sectors(orig);
- dm_stats_account_io(&md->stats, orig->cmd_flags, blk_rq_pos(orig),
- tio->n_sectors, false, 0, &tio->stats_aux);
- }
-
- /*
- * Hold the md reference here for the in-flight I/O.
- * We can't rely on the reference count by device opener,
- * because the device may be closed during the request completion
- * when all bios are completed.
- * See the comment in rq_completed() too.
- */
- dm_get(md);
-}
-
-#define MAX_SEQ_RQ_MERGE_DEADLINE_USECS 100000
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
-{
- return sprintf(buf, "%u\n", md->seq_rq_merge_deadline_usecs);
-}
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
- const char *buf, size_t count)
-{
- unsigned deadline;
-
- if (!dm_request_based(md) || md->use_blk_mq)
- return count;
-
- if (kstrtouint(buf, 10, &deadline))
- return -EINVAL;
-
- if (deadline > MAX_SEQ_RQ_MERGE_DEADLINE_USECS)
- deadline = MAX_SEQ_RQ_MERGE_DEADLINE_USECS;
-
- md->seq_rq_merge_deadline_usecs = deadline;
-
- return count;
-}
-
-static bool dm_request_peeked_before_merge_deadline(struct mapped_device *md)
-{
- ktime_t kt_deadline;
-
- if (!md->seq_rq_merge_deadline_usecs)
- return false;
-
- kt_deadline = ns_to_ktime((u64)md->seq_rq_merge_deadline_usecs * NSEC_PER_USEC);
- kt_deadline = ktime_add_safe(md->last_rq_start_time, kt_deadline);
-
- return !ktime_after(ktime_get(), kt_deadline);
-}
-
-/*
- * q->request_fn for request-based dm.
- * Called with the queue lock held.
- */
-static void dm_request_fn(struct request_queue *q)
-{
- struct mapped_device *md = q->queuedata;
- struct dm_target *ti = md->immutable_target;
- struct request *rq;
- struct dm_rq_target_io *tio;
- sector_t pos = 0;
-
- if (unlikely(!ti)) {
- int srcu_idx;
- struct dm_table *map = dm_get_live_table(md, &srcu_idx);
-
- ti = dm_table_find_target(map, pos);
- dm_put_live_table(md, srcu_idx);
- }
-
- /*
- * For suspend, check blk_queue_stopped() and increment
- * ->pending within a single queue_lock not to increment the
- * number of in-flight I/Os after the queue is stopped in
- * dm_suspend().
- */
- while (!blk_queue_stopped(q)) {
- rq = blk_peek_request(q);
- if (!rq)
- return;
-
- /* always use block 0 to find the target for flushes for now */
- pos = 0;
- if (!(rq->cmd_flags & REQ_FLUSH))
- pos = blk_rq_pos(rq);
-
- if ((dm_request_peeked_before_merge_deadline(md) &&
- md_in_flight(md) && rq->bio && rq->bio->bi_vcnt == 1 &&
- md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) ||
- (ti->type->busy && ti->type->busy(ti))) {
- blk_delay_queue(q, 10);
- return;
- }
-
- dm_start_request(md, rq);
-
- tio = tio_from_request(rq);
- /* Establish tio->ti before queuing work (map_tio_request) */
- tio->ti = ti;
- queue_kthread_work(&md->kworker, &tio->work);
- BUG_ON(!irqs_disabled());
- }
-}
-
static int dm_any_congested(void *congested_data, int bdi_bits)
{
int r = bdi_bits;
@@ -2266,7 +1379,7 @@ static const struct block_device_operations dm_blk_dops;
static void dm_wq_work(struct work_struct *work);
-static void dm_init_md_queue(struct mapped_device *md)
+void dm_init_md_queue(struct mapped_device *md)
{
/*
* Request-based dm devices cannot be stacked on top of bio-based dm
@@ -2287,7 +1400,7 @@ static void dm_init_md_queue(struct mapped_device *md)
md->queue->backing_dev_info.congested_data = md;
}
-static void dm_init_normal_md_queue(struct mapped_device *md)
+void dm_init_normal_md_queue(struct mapped_device *md)
{
md->use_blk_mq = false;
dm_init_md_queue(md);
@@ -2327,6 +1440,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
bdput(md->bdev);
md->bdev = NULL;
}
+
+ dm_mq_cleanup_mapped_device(md);
}
/*
@@ -2360,7 +1475,7 @@ static struct mapped_device *alloc_dev(int minor)
goto bad_io_barrier;
md->numa_node_id = numa_node_id;
- md->use_blk_mq = use_blk_mq;
+ md->use_blk_mq = dm_use_blk_mq_default();
md->init_tio_pdu = false;
md->type = DM_TYPE_NONE;
mutex_init(&md->suspend_lock);
@@ -2412,7 +1527,7 @@ static struct mapped_device *alloc_dev(int minor)
bio_init(&md->flush_bio);
md->flush_bio.bi_bdev = md->bdev;
- md->flush_bio.bi_rw = WRITE_FLUSH;
+ bio_set_op_attrs(&md->flush_bio, REQ_OP_WRITE, WRITE_FLUSH);
dm_stats_init(&md->stats);
@@ -2445,10 +1560,6 @@ static void free_dev(struct mapped_device *md)
unlock_fs(md);
cleanup_mapped_device(md);
- if (md->tag_set) {
- blk_mq_free_tag_set(md->tag_set);
- kfree(md->tag_set);
- }
free_table_devices(&md->table_devices);
dm_stats_cleanup(&md->stats);
@@ -2464,7 +1575,7 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
if (md->bs) {
/* The md already has necessary mempools. */
- if (dm_table_get_type(t) == DM_TYPE_BIO_BASED) {
+ if (dm_table_bio_based(t)) {
/*
* Reload bioset because front_pad may have changed
* because a different table was loaded.
@@ -2654,176 +1765,15 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
}
EXPORT_SYMBOL_GPL(dm_get_queue_limits);
-static void dm_old_init_rq_based_worker_thread(struct mapped_device *md)
-{
- /* Initialize the request-based DM worker thread */
- init_kthread_worker(&md->kworker);
- md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
- "kdmwork-%s", dm_device_name(md));
-}
-
-/*
- * Fully initialize a .request_fn request-based queue.
- */
-static int dm_old_init_request_queue(struct mapped_device *md)
-{
- /* Fully initialize the queue */
- if (!blk_init_allocated_queue(md->queue, dm_request_fn, NULL))
- return -EINVAL;
-
- /* disable dm_request_fn's merge heuristic by default */
- md->seq_rq_merge_deadline_usecs = 0;
-
- dm_init_normal_md_queue(md);
- blk_queue_softirq_done(md->queue, dm_softirq_done);
- blk_queue_prep_rq(md->queue, dm_old_prep_fn);
-
- dm_old_init_rq_based_worker_thread(md);
-
- elv_register_queue(md->queue);
-
- return 0;
-}
-
-static int dm_mq_init_request(void *data, struct request *rq,
- unsigned int hctx_idx, unsigned int request_idx,
- unsigned int numa_node)
-{
- struct mapped_device *md = data;
- struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
-
- /*
- * Must initialize md member of tio, otherwise it won't
- * be available in dm_mq_queue_rq.
- */
- tio->md = md;
-
- if (md->init_tio_pdu) {
- /* target-specific per-io data is immediately after the tio */
- tio->info.ptr = tio + 1;
- }
-
- return 0;
-}
-
-static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
- const struct blk_mq_queue_data *bd)
-{
- struct request *rq = bd->rq;
- struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
- struct mapped_device *md = tio->md;
- struct dm_target *ti = md->immutable_target;
-
- if (unlikely(!ti)) {
- int srcu_idx;
- struct dm_table *map = dm_get_live_table(md, &srcu_idx);
-
- ti = dm_table_find_target(map, 0);
- dm_put_live_table(md, srcu_idx);
- }
-
- if (ti->type->busy && ti->type->busy(ti))
- return BLK_MQ_RQ_QUEUE_BUSY;
-
- dm_start_request(md, rq);
-
- /* Init tio using md established in .init_request */
- init_tio(tio, rq, md);
-
- /*
- * Establish tio->ti before queuing work (map_tio_request)
- * or making direct call to map_request().
- */
- tio->ti = ti;
-
- /* Direct call is fine since .queue_rq allows allocations */
- if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
- /* Undo dm_start_request() before requeuing */
- rq_end_stats(md, rq);
- rq_completed(md, rq_data_dir(rq), false);
- return BLK_MQ_RQ_QUEUE_BUSY;
- }
-
- return BLK_MQ_RQ_QUEUE_OK;
-}
-
-static struct blk_mq_ops dm_mq_ops = {
- .queue_rq = dm_mq_queue_rq,
- .map_queue = blk_mq_map_queue,
- .complete = dm_softirq_done,
- .init_request = dm_mq_init_request,
-};
-
-static int dm_mq_init_request_queue(struct mapped_device *md,
- struct dm_target *immutable_tgt)
-{
- struct request_queue *q;
- int err;
-
- if (dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) {
- DMERR("request-based dm-mq may only be stacked on blk-mq device(s)");
- return -EINVAL;
- }
-
- md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id);
- if (!md->tag_set)
- return -ENOMEM;
-
- md->tag_set->ops = &dm_mq_ops;
- md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
- md->tag_set->numa_node = md->numa_node_id;
- md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
- md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
- md->tag_set->driver_data = md;
-
- md->tag_set->cmd_size = sizeof(struct dm_rq_target_io);
- if (immutable_tgt && immutable_tgt->per_io_data_size) {
- /* any target-specific per-io data is immediately after the tio */
- md->tag_set->cmd_size += immutable_tgt->per_io_data_size;
- md->init_tio_pdu = true;
- }
-
- err = blk_mq_alloc_tag_set(md->tag_set);
- if (err)
- goto out_kfree_tag_set;
-
- q = blk_mq_init_allocated_queue(md->tag_set, md->queue);
- if (IS_ERR(q)) {
- err = PTR_ERR(q);
- goto out_tag_set;
- }
- dm_init_md_queue(md);
-
- /* backfill 'mq' sysfs registration normally done in blk_register_queue */
- blk_mq_register_disk(md->disk);
-
- return 0;
-
-out_tag_set:
- blk_mq_free_tag_set(md->tag_set);
-out_kfree_tag_set:
- kfree(md->tag_set);
-
- return err;
-}
-
-static unsigned filter_md_type(unsigned type, struct mapped_device *md)
-{
- if (type == DM_TYPE_BIO_BASED)
- return type;
-
- return !md->use_blk_mq ? DM_TYPE_REQUEST_BASED : DM_TYPE_MQ_REQUEST_BASED;
-}
-
/*
* Setup the DM device's queue based on md's type
*/
int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
{
int r;
- unsigned md_type = filter_md_type(dm_get_md_type(md), md);
+ unsigned type = dm_get_md_type(md);
- switch (md_type) {
+ switch (type) {
case DM_TYPE_REQUEST_BASED:
r = dm_old_init_request_queue(md);
if (r) {
@@ -2832,13 +1782,14 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
}
break;
case DM_TYPE_MQ_REQUEST_BASED:
- r = dm_mq_init_request_queue(md, dm_table_get_immutable_target(t));
+ r = dm_mq_init_request_queue(md, t);
if (r) {
DMERR("Cannot initialize queue for request-based dm-mq mapped device");
return r;
}
break;
case DM_TYPE_BIO_BASED:
+ case DM_TYPE_DAX_BIO_BASED:
dm_init_normal_md_queue(md);
blk_queue_make_request(md->queue, dm_make_request);
/*
@@ -2847,6 +1798,9 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
*/
bioset_free(md->queue->bio_split);
md->queue->bio_split = NULL;
+
+ if (type == DM_TYPE_DAX_BIO_BASED)
+ queue_flag_set_unlocked(QUEUE_FLAG_DAX, md->queue);
break;
}
@@ -3541,10 +2495,9 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
if (!pools)
return NULL;
- type = filter_md_type(type, md);
-
switch (type) {
case DM_TYPE_BIO_BASED:
+ case DM_TYPE_DAX_BIO_BASED:
cachep = _io_cache;
pool_size = dm_get_reserved_bio_based_ios();
front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
@@ -3601,26 +2554,76 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
kfree(pools);
}
-static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
- u32 flags)
+struct dm_pr {
+ u64 old_key;
+ u64 new_key;
+ u32 flags;
+ bool fail_early;
+};
+
+static int dm_call_pr(struct block_device *bdev, iterate_devices_callout_fn fn,
+ void *data)
{
struct mapped_device *md = bdev->bd_disk->private_data;
- const struct pr_ops *ops;
- fmode_t mode;
- int r;
+ struct dm_table *table;
+ struct dm_target *ti;
+ int ret = -ENOTTY, srcu_idx;
- r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
- if (r < 0)
- return r;
+ table = dm_get_live_table(md, &srcu_idx);
+ if (!table || !dm_table_get_size(table))
+ goto out;
- ops = bdev->bd_disk->fops->pr_ops;
- if (ops && ops->pr_register)
- r = ops->pr_register(bdev, old_key, new_key, flags);
- else
- r = -EOPNOTSUPP;
+ /* We only support devices that have a single target */
+ if (dm_table_get_num_targets(table) != 1)
+ goto out;
+ ti = dm_table_get_target(table, 0);
- bdput(bdev);
- return r;
+ ret = -EINVAL;
+ if (!ti->type->iterate_devices)
+ goto out;
+
+ ret = ti->type->iterate_devices(ti, fn, data);
+out:
+ dm_put_live_table(md, srcu_idx);
+ return ret;
+}
+
+/*
+ * For register / unregister we need to manually call out to every path.
+ */
+static int __dm_pr_register(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ struct dm_pr *pr = data;
+ const struct pr_ops *ops = dev->bdev->bd_disk->fops->pr_ops;
+
+ if (!ops || !ops->pr_register)
+ return -EOPNOTSUPP;
+ return ops->pr_register(dev->bdev, pr->old_key, pr->new_key, pr->flags);
+}
+
+static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
+ u32 flags)
+{
+ struct dm_pr pr = {
+ .old_key = old_key,
+ .new_key = new_key,
+ .flags = flags,
+ .fail_early = true,
+ };
+ int ret;
+
+ ret = dm_call_pr(bdev, __dm_pr_register, &pr);
+ if (ret && new_key) {
+ /* unregister all paths if we failed to register any path */
+ pr.old_key = new_key;
+ pr.new_key = 0;
+ pr.flags = 0;
+ pr.fail_early = false;
+ dm_call_pr(bdev, __dm_pr_register, &pr);
+ }
+
+ return ret;
}
static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
@@ -3721,6 +2724,7 @@ static const struct block_device_operations dm_blk_dops = {
.open = dm_blk_open,
.release = dm_blk_close,
.ioctl = dm_blk_ioctl,
+ .direct_access = dm_blk_direct_access,
.getgeo = dm_blk_getgeo,
.pr_ops = &dm_pr_ops,
.owner = THIS_MODULE
@@ -3738,18 +2742,6 @@ MODULE_PARM_DESC(major, "The major number of the device mapper");
module_param(reserved_bio_based_ios, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools");
-module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");
-
-module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices");
-
-module_param(dm_mq_nr_hw_queues, uint, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(dm_mq_nr_hw_queues, "Number of hardware queues for request-based dm-mq devices");
-
-module_param(dm_mq_queue_depth, uint, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(dm_mq_queue_depth, "Queue depth for request-based dm-mq devices");
-
module_param(dm_numa_node, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(dm_numa_node, "NUMA node for DM device memory allocations");
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 13a758ec0..f0aad08b9 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -13,6 +13,7 @@
#include <linux/fs.h>
#include <linux/device-mapper.h>
#include <linux/list.h>
+#include <linux/moduleparam.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/hdreg.h>
@@ -33,14 +34,6 @@
#define DM_STATUS_NOFLUSH_FLAG (1 << 0)
/*
- * Type of table and mapped_device's mempool
- */
-#define DM_TYPE_NONE 0
-#define DM_TYPE_BIO_BASED 1
-#define DM_TYPE_REQUEST_BASED 2
-#define DM_TYPE_MQ_REQUEST_BASED 3
-
-/*
* List of devices that a metadevice uses and should open/close.
*/
struct dm_dev_internal {
@@ -75,8 +68,9 @@ unsigned dm_table_get_type(struct dm_table *t);
struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
struct dm_target *dm_table_get_wildcard_target(struct dm_table *t);
+bool dm_table_bio_based(struct dm_table *t);
bool dm_table_request_based(struct dm_table *t);
-bool dm_table_mq_request_based(struct dm_table *t);
+bool dm_table_all_blk_mq_devices(struct dm_table *t);
void dm_table_free_md_mempools(struct dm_table *t);
struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
@@ -161,16 +155,6 @@ void dm_interface_exit(void);
/*
* sysfs interface
*/
-struct dm_kobject_holder {
- struct kobject kobj;
- struct completion completion;
-};
-
-static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
-{
- return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
-}
-
int dm_sysfs_init(struct mapped_device *md);
void dm_sysfs_exit(struct mapped_device *md);
struct kobject *dm_kobject(struct mapped_device *md);
@@ -212,8 +196,6 @@ int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
void dm_internal_suspend(struct mapped_device *md);
void dm_internal_resume(struct mapped_device *md);
-bool dm_use_blk_mq(struct mapped_device *md);
-
int dm_io_init(void);
void dm_io_exit(void);
@@ -228,18 +210,8 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
void dm_free_md_mempools(struct dm_md_mempools *pools);
/*
- * Helpers that are used by DM core
+ * Various helpers
*/
unsigned dm_get_reserved_bio_based_ios(void);
-unsigned dm_get_reserved_rq_based_ios(void);
-
-static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen)
-{
- return !maxlen || strlen(result) + 1 >= maxlen;
-}
-
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf);
-ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
- const char *buf, size_t count);
#endif
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index b7fe7e9fc..86f5d4359 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -221,7 +221,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
struct bio *split;
sector_t start_sector, end_sector, data_offset;
- if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+ if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
md_flush_request(mddev, bio);
return;
}
@@ -252,7 +252,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
split->bi_iter.bi_sector = split->bi_iter.bi_sector -
start_sector + data_offset;
- if (unlikely((split->bi_rw & REQ_DISCARD) &&
+ if (unlikely((bio_op(split) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
/* Just ignore it */
bio_endio(split);
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 41573f1f6..34a840d9d 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -834,8 +834,10 @@ static int join(struct mddev *mddev, int nodes)
goto err;
}
cinfo->ack_lockres = lockres_init(mddev, "ack", ack_bast, 0);
- if (!cinfo->ack_lockres)
+ if (!cinfo->ack_lockres) {
+ ret = -ENOMEM;
goto err;
+ }
/* get sync CR lock on ACK. */
if (dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR))
pr_err("md-cluster: failed to get a sync CR lock on ACK!(%d)\n",
@@ -849,8 +851,10 @@ static int join(struct mddev *mddev, int nodes)
pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number);
snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1);
cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1);
- if (!cinfo->bitmap_lockres)
+ if (!cinfo->bitmap_lockres) {
+ ret = -ENOMEM;
goto err;
+ }
if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) {
pr_err("Failed to get bitmap lock\n");
ret = -EINVAL;
@@ -858,8 +862,10 @@ static int join(struct mddev *mddev, int nodes)
}
cinfo->resync_lockres = lockres_init(mddev, "resync", NULL, 0);
- if (!cinfo->resync_lockres)
+ if (!cinfo->resync_lockres) {
+ ret = -ENOMEM;
goto err;
+ }
return 0;
err:
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0678a0a95..915e84d63 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -285,7 +285,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
*/
sectors = bio_sectors(bio);
/* bio could be mergeable after passing to underlayer */
- bio->bi_rw &= ~REQ_NOMERGE;
+ bio->bi_opf &= ~REQ_NOMERGE;
mddev->pers->make_request(mddev, bio);
cpu = part_stat_lock();
@@ -394,8 +394,9 @@ static void submit_flushes(struct work_struct *ws)
bi->bi_end_io = md_end_flush;
bi->bi_private = rdev;
bi->bi_bdev = rdev->bdev;
+ bio_set_op_attrs(bi, REQ_OP_WRITE, WRITE_FLUSH);
atomic_inc(&mddev->flush_pending);
- submit_bio(WRITE_FLUSH, bi);
+ submit_bio(bi);
rcu_read_lock();
rdev_dec_pending(rdev, mddev);
}
@@ -413,7 +414,7 @@ static void md_submit_flush_data(struct work_struct *ws)
/* an empty barrier - all done */
bio_endio(bio);
else {
- bio->bi_rw &= ~REQ_FLUSH;
+ bio->bi_opf &= ~REQ_PREFLUSH;
mddev->pers->make_request(mddev, bio);
}
@@ -742,9 +743,10 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
bio_add_page(bio, page, size, 0);
bio->bi_private = rdev;
bio->bi_end_io = super_written;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH_FUA);
atomic_inc(&mddev->pending_writes);
- submit_bio(WRITE_FLUSH_FUA, bio);
+ submit_bio(bio);
}
void md_super_wait(struct mddev *mddev)
@@ -754,13 +756,14 @@ void md_super_wait(struct mddev *mddev)
}
int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
- struct page *page, int rw, bool metadata_op)
+ struct page *page, int op, int op_flags, bool metadata_op)
{
struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, rdev->mddev);
int ret;
bio->bi_bdev = (metadata_op && rdev->meta_bdev) ?
rdev->meta_bdev : rdev->bdev;
+ bio_set_op_attrs(bio, op, op_flags);
if (metadata_op)
bio->bi_iter.bi_sector = sector + rdev->sb_start;
else if (rdev->mddev->reshape_position != MaxSector &&
@@ -770,7 +773,8 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
else
bio->bi_iter.bi_sector = sector + rdev->data_offset;
bio_add_page(bio, page, size, 0);
- submit_bio_wait(rw, bio);
+
+ submit_bio_wait(bio);
ret = !bio->bi_error;
bio_put(bio);
@@ -785,7 +789,7 @@ static int read_disk_sb(struct md_rdev *rdev, int size)
if (rdev->sb_loaded)
return 0;
- if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, true))
+ if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, 0, true))
goto fail;
rdev->sb_loaded = 1;
return 0;
@@ -1471,7 +1475,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
return -EINVAL;
bb_sector = (long long)offset;
if (!sync_page_io(rdev, bb_sector, sectors << 9,
- rdev->bb_page, READ, true))
+ rdev->bb_page, REQ_OP_READ, 0, true))
return -EIO;
bbp = (u64 *)page_address(rdev->bb_page);
rdev->badblocks.shift = sb->bblog_shift;
@@ -1600,11 +1604,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
mddev->new_chunk_sectors = mddev->chunk_sectors;
}
- if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) {
+ if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
set_bit(MD_HAS_JOURNAL, &mddev->flags);
- if (mddev->recovery_cp == MaxSector)
- set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
- }
} else if (mddev->pers == NULL) {
/* Insist of good event counter while assembling, except for
* spares (which don't need an event count) */
@@ -2478,8 +2479,7 @@ static int add_bound_rdev(struct md_rdev *rdev)
if (add_journal)
mddev_resume(mddev);
if (err) {
- unbind_rdev_from_array(rdev);
- export_rdev(rdev);
+ md_kick_rdev_from_array(rdev);
return err;
}
}
@@ -2596,6 +2596,10 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
else
err = -EBUSY;
} else if (cmd_match(buf, "remove")) {
+ if (rdev->mddev->pers) {
+ clear_bit(Blocked, &rdev->flags);
+ remove_and_add_spares(rdev->mddev, rdev);
+ }
if (rdev->raid_disk >= 0)
err = -EBUSY;
else {
@@ -3172,8 +3176,7 @@ int md_rdev_init(struct md_rdev *rdev)
rdev->data_offset = 0;
rdev->new_data_offset = 0;
rdev->sb_events = 0;
- rdev->last_read_error.tv_sec = 0;
- rdev->last_read_error.tv_nsec = 0;
+ rdev->last_read_error = 0;
rdev->sb_loaded = 0;
rdev->bb_page = NULL;
atomic_set(&rdev->nr_pending, 0);
@@ -3579,6 +3582,8 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
mddev->to_remove = &md_redundancy_group;
}
+ module_put(oldpers->owner);
+
rdev_for_each(rdev, mddev) {
if (rdev->raid_disk < 0)
continue;
@@ -3936,6 +3941,8 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
} else
err = -EBUSY;
}
+ if (!err)
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
spin_unlock(&mddev->lock);
return err ?: len;
}
@@ -4187,7 +4194,8 @@ size_store(struct mddev *mddev, const char *buf, size_t len)
return err;
if (mddev->pers) {
err = update_size(mddev, sectors);
- md_update_sb(mddev, 1);
+ if (err == 0)
+ md_update_sb(mddev, 1);
} else {
if (mddev->dev_sectors == 0 ||
mddev->dev_sectors > sectors)
@@ -5840,6 +5848,9 @@ static int get_array_info(struct mddev *mddev, void __user *arg)
working++;
if (test_bit(In_sync, &rdev->flags))
insync++;
+ else if (test_bit(Journal, &rdev->flags))
+ /* TODO: add journal count to md_u.h */
+ ;
else
spare++;
}
@@ -7805,6 +7816,7 @@ void md_do_sync(struct md_thread *thread)
if (ret)
goto skip;
+ set_bit(MD_CLUSTER_RESYNC_LOCKED, &mddev->flags);
if (!(test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ||
test_bit(MD_RECOVERY_RECOVER, &mddev->recovery))
@@ -7846,6 +7858,7 @@ void md_do_sync(struct md_thread *thread)
*/
do {
+ int mddev2_minor = -1;
mddev->curr_resync = 2;
try_again:
@@ -7875,10 +7888,14 @@ void md_do_sync(struct md_thread *thread)
prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE);
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
mddev2->curr_resync >= mddev->curr_resync) {
- printk(KERN_INFO "md: delaying %s of %s"
- " until %s has finished (they"
- " share one or more physical units)\n",
- desc, mdname(mddev), mdname(mddev2));
+ if (mddev2_minor != mddev2->md_minor) {
+ mddev2_minor = mddev2->md_minor;
+ printk(KERN_INFO "md: delaying %s of %s"
+ " until %s has finished (they"
+ " share one or more physical units)\n",
+ desc, mdname(mddev),
+ mdname(mddev2));
+ }
mddev_put(mddev2);
if (signal_pending(current))
flush_signals(current);
@@ -8143,18 +8160,11 @@ void md_do_sync(struct md_thread *thread)
}
}
skip:
- if (mddev_is_clustered(mddev) &&
- ret == 0) {
- /* set CHANGE_PENDING here since maybe another
- * update is needed, so other nodes are informed */
- set_mask_bits(&mddev->flags, 0,
- BIT(MD_CHANGE_PENDING) | BIT(MD_CHANGE_DEVS));
- md_wakeup_thread(mddev->thread);
- wait_event(mddev->sb_wait,
- !test_bit(MD_CHANGE_PENDING, &mddev->flags));
- md_cluster_ops->resync_finish(mddev);
- } else
- set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ /* set CHANGE_PENDING here since maybe another update is needed,
+ * so other nodes are informed. It should be harmless for normal
+ * raid */
+ set_mask_bits(&mddev->flags, 0,
+ BIT(MD_CHANGE_PENDING) | BIT(MD_CHANGE_DEVS));
spin_lock(&mddev->lock);
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
@@ -8180,15 +8190,34 @@ static int remove_and_add_spares(struct mddev *mddev,
struct md_rdev *rdev;
int spares = 0;
int removed = 0;
+ bool remove_some = false;
- rdev_for_each(rdev, mddev)
+ rdev_for_each(rdev, mddev) {
if ((this == NULL || rdev == this) &&
rdev->raid_disk >= 0 &&
!test_bit(Blocked, &rdev->flags) &&
- (test_bit(Faulty, &rdev->flags) ||
+ test_bit(Faulty, &rdev->flags) &&
+ atomic_read(&rdev->nr_pending)==0) {
+ /* Faulty non-Blocked devices with nr_pending == 0
+ * never get nr_pending incremented,
+ * never get Faulty cleared, and never get Blocked set.
+ * So we can synchronize_rcu now rather than once per device
+ */
+ remove_some = true;
+ set_bit(RemoveSynchronized, &rdev->flags);
+ }
+ }
+
+ if (remove_some)
+ synchronize_rcu();
+ rdev_for_each(rdev, mddev) {
+ if ((this == NULL || rdev == this) &&
+ rdev->raid_disk >= 0 &&
+ !test_bit(Blocked, &rdev->flags) &&
+ ((test_bit(RemoveSynchronized, &rdev->flags) ||
(!test_bit(In_sync, &rdev->flags) &&
!test_bit(Journal, &rdev->flags))) &&
- atomic_read(&rdev->nr_pending)==0) {
+ atomic_read(&rdev->nr_pending)==0)) {
if (mddev->pers->hot_remove_disk(
mddev, rdev) == 0) {
sysfs_unlink_rdev(mddev, rdev);
@@ -8196,6 +8225,10 @@ static int remove_and_add_spares(struct mddev *mddev,
removed++;
}
}
+ if (remove_some && test_bit(RemoveSynchronized, &rdev->flags))
+ clear_bit(RemoveSynchronized, &rdev->flags);
+ }
+
if (removed && mddev->kobj.sd)
sysfs_notify(&mddev->kobj, NULL, "degraded");
@@ -8243,16 +8276,13 @@ no_add:
static void md_start_sync(struct work_struct *ws)
{
struct mddev *mddev = container_of(ws, struct mddev, del_work);
- int ret = 0;
mddev->sync_thread = md_register_thread(md_do_sync,
mddev,
"resync");
if (!mddev->sync_thread) {
- if (!(mddev_is_clustered(mddev) && ret == -EAGAIN))
- printk(KERN_ERR "%s: could not start resync"
- " thread...\n",
- mdname(mddev));
+ printk(KERN_ERR "%s: could not start resync thread...\n",
+ mdname(mddev));
/* leave the spares where they are, it shouldn't hurt */
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
@@ -8498,6 +8528,11 @@ void md_reap_sync_thread(struct mddev *mddev)
rdev->saved_raid_disk = -1;
md_update_sb(mddev, 1);
+ /* MD_CHANGE_PENDING should be cleared by md_update_sb, so we can
+ * call resync_finish here if MD_CLUSTER_RESYNC_LOCKED is set by
+ * clustered raid */
+ if (test_and_clear_bit(MD_CLUSTER_RESYNC_LOCKED, &mddev->flags))
+ md_cluster_ops->resync_finish(mddev);
clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
@@ -8795,6 +8830,7 @@ EXPORT_SYMBOL(md_reload_sb);
* at boot time.
*/
+static DEFINE_MUTEX(detected_devices_mutex);
static LIST_HEAD(all_detected_devices);
struct detected_devices_node {
struct list_head list;
@@ -8808,7 +8844,9 @@ void md_autodetect_dev(dev_t dev)
node_detected_dev = kzalloc(sizeof(*node_detected_dev), GFP_KERNEL);
if (node_detected_dev) {
node_detected_dev->dev = dev;
+ mutex_lock(&detected_devices_mutex);
list_add_tail(&node_detected_dev->list, &all_detected_devices);
+ mutex_unlock(&detected_devices_mutex);
} else {
printk(KERN_CRIT "md: md_autodetect_dev: kzalloc failed"
", skipping dev(%d,%d)\n", MAJOR(dev), MINOR(dev));
@@ -8827,6 +8865,7 @@ static void autostart_arrays(int part)
printk(KERN_INFO "md: Autodetecting RAID arrays.\n");
+ mutex_lock(&detected_devices_mutex);
while (!list_empty(&all_detected_devices) && i_scanned < INT_MAX) {
i_scanned++;
node_detected_dev = list_entry(all_detected_devices.next,
@@ -8845,6 +8884,7 @@ static void autostart_arrays(int part)
list_add(&rdev->same_set, &pending_raid_disks);
i_passed++;
}
+ mutex_unlock(&detected_devices_mutex);
printk(KERN_INFO "md: Scanned %d and added %d devices.\n",
i_scanned, i_passed);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index b5c4be73e..20c667579 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -99,7 +99,7 @@ struct md_rdev {
atomic_t read_errors; /* number of consecutive read errors that
* we have tried to ignore.
*/
- struct timespec last_read_error; /* monotonic time since our
+ time64_t last_read_error; /* monotonic time since our
* last read error
*/
atomic_t corrected_errors; /* number of corrected read errors,
@@ -163,6 +163,11 @@ enum flag_bits {
* than other devices in the array
*/
ClusterRemove,
+ RemoveSynchronized, /* synchronize_rcu() was called after
+ * this device was known to be faulty,
+ * so it is safe to remove without
+ * another synchronize_rcu() call.
+ */
};
static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
@@ -204,6 +209,9 @@ struct mddev {
#define MD_RELOAD_SB 7 /* Reload the superblock because another node
* updated it.
*/
+#define MD_CLUSTER_RESYNC_LOCKED 8 /* cluster raid only, which means node
+ * already took resync lock, need to
+ * release the lock */
int suspended;
atomic_t active_io;
@@ -424,7 +432,7 @@ struct mddev {
/* Generic flush handling.
* The last to finish preflush schedules a worker to submit
- * the rest of the request (without the REQ_FLUSH flag).
+ * the rest of the request (without the REQ_PREFLUSH flag).
*/
struct bio *flush_bio;
atomic_t flush_pending;
@@ -618,7 +626,8 @@ extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
sector_t sector, int size, struct page *page);
extern void md_super_wait(struct mddev *mddev);
extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
- struct page *page, int rw, bool metadata_op);
+ struct page *page, int op, int op_flags,
+ 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);
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index dd483bb2e..673efbd6f 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -43,7 +43,8 @@ static int multipath_map (struct mpconf *conf)
rcu_read_lock();
for (i = 0; i < disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
- if (rdev && test_bit(In_sync, &rdev->flags)) {
+ if (rdev && test_bit(In_sync, &rdev->flags) &&
+ !test_bit(Faulty, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
return i;
@@ -90,7 +91,7 @@ static void multipath_end_request(struct bio *bio)
if (!bio->bi_error)
multipath_end_bh_io(mp_bh, 0);
- else if (!(bio->bi_rw & REQ_RAHEAD)) {
+ else if (!(bio->bi_opf & REQ_RAHEAD)) {
/*
* oops, IO error:
*/
@@ -111,7 +112,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
struct multipath_bh * mp_bh;
struct multipath_info *multipath;
- if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+ if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
md_flush_request(mddev, bio);
return;
}
@@ -134,24 +135,26 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
mp_bh->bio.bi_bdev = multipath->rdev->bdev;
- mp_bh->bio.bi_rw |= REQ_FAILFAST_TRANSPORT;
+ mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT;
mp_bh->bio.bi_end_io = multipath_end_request;
mp_bh->bio.bi_private = mp_bh;
generic_make_request(&mp_bh->bio);
return;
}
-static void multipath_status (struct seq_file *seq, struct mddev *mddev)
+static void multipath_status(struct seq_file *seq, struct mddev *mddev)
{
struct mpconf *conf = mddev->private;
int i;
seq_printf (seq, " [%d/%d] [", conf->raid_disks,
conf->raid_disks - mddev->degraded);
- for (i = 0; i < conf->raid_disks; i++)
- seq_printf (seq, "%s",
- conf->multipaths[i].rdev &&
- test_bit(In_sync, &conf->multipaths[i].rdev->flags) ? "U" : "_");
+ rcu_read_lock();
+ for (i = 0; i < conf->raid_disks; i++) {
+ struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
+ seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
+ }
+ rcu_read_unlock();
seq_printf (seq, "]");
}
@@ -295,12 +298,14 @@ static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
goto abort;
}
p->rdev = NULL;
- synchronize_rcu();
- if (atomic_read(&rdev->nr_pending)) {
- /* lost the race, try later */
- err = -EBUSY;
- p->rdev = rdev;
- goto abort;
+ if (!test_bit(RemoveSynchronized, &rdev->flags)) {
+ synchronize_rcu();
+ if (atomic_read(&rdev->nr_pending)) {
+ /* lost the race, try later */
+ err = -EBUSY;
+ p->rdev = rdev;
+ goto abort;
+ }
}
err = md_integrity_register(mddev);
}
@@ -355,7 +360,7 @@ static void multipathd(struct md_thread *thread)
bio->bi_iter.bi_sector +=
conf->multipaths[mp_bh->path].rdev->data_offset;
bio->bi_bdev = conf->multipaths[mp_bh->path].rdev->bdev;
- bio->bi_rw |= REQ_FAILFAST_TRANSPORT;
+ bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
bio->bi_end_io = multipath_end_request;
bio->bi_private = mp_bh;
generic_make_request(bio);
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index ea3d3b656..2cc187780 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -429,7 +429,14 @@ static int dm_btree_lookup_next_single(struct dm_btree_info *info, dm_block_t ro
if (flags & INTERNAL_NODE) {
i = lower_bound(n, key);
- if (i < 0 || i >= nr_entries) {
+ if (i < 0) {
+ /*
+ * avoid early -ENODATA return when all entries are
+ * higher than the search @key.
+ */
+ i = 0;
+ }
+ if (i >= nr_entries) {
r = -ENODATA;
goto out;
}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 34783a3c8..258986a26 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -458,7 +458,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
struct md_rdev *tmp_dev;
struct bio *split;
- if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+ if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
md_flush_request(mddev, bio);
return;
}
@@ -488,7 +488,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
split->bi_iter.bi_sector = sector + zone->dev_start +
tmp_dev->data_offset;
- if (unlikely((split->bi_rw & REQ_DISCARD) &&
+ if (unlikely((bio_op(split) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
/* Just ignore it */
bio_endio(split);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index c7c8cde0a..21dc00eb1 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -319,14 +319,13 @@ static void raid1_end_read_request(struct bio *bio)
{
int uptodate = !bio->bi_error;
struct r1bio *r1_bio = bio->bi_private;
- int mirror;
struct r1conf *conf = r1_bio->mddev->private;
+ struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev;
- mirror = r1_bio->read_disk;
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
- update_head_pos(mirror, r1_bio);
+ update_head_pos(r1_bio->read_disk, r1_bio);
if (uptodate)
set_bit(R1BIO_Uptodate, &r1_bio->state);
@@ -339,14 +338,14 @@ static void raid1_end_read_request(struct bio *bio)
spin_lock_irqsave(&conf->device_lock, flags);
if (r1_bio->mddev->degraded == conf->raid_disks ||
(r1_bio->mddev->degraded == conf->raid_disks-1 &&
- test_bit(In_sync, &conf->mirrors[mirror].rdev->flags)))
+ test_bit(In_sync, &rdev->flags)))
uptodate = 1;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
if (uptodate) {
raid_end_bio_io(r1_bio);
- rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
+ rdev_dec_pending(rdev, conf->mddev);
} else {
/*
* oops, read error:
@@ -356,7 +355,7 @@ static void raid1_end_read_request(struct bio *bio)
KERN_ERR "md/raid1:%s: %s: "
"rescheduling sector %llu\n",
mdname(conf->mddev),
- bdevname(conf->mirrors[mirror].rdev->bdev,
+ bdevname(rdev->bdev,
b),
(unsigned long long)r1_bio->sector);
set_bit(R1BIO_ReadError, &r1_bio->state);
@@ -403,20 +402,18 @@ static void r1_bio_write_done(struct r1bio *r1_bio)
static void raid1_end_write_request(struct bio *bio)
{
struct r1bio *r1_bio = bio->bi_private;
- int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
+ int behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
struct r1conf *conf = r1_bio->mddev->private;
struct bio *to_put = NULL;
-
- mirror = find_bio_disk(r1_bio, bio);
+ int mirror = find_bio_disk(r1_bio, bio);
+ struct md_rdev *rdev = conf->mirrors[mirror].rdev;
/*
* 'one mirror IO has finished' event handler:
*/
if (bio->bi_error) {
- set_bit(WriteErrorSeen,
- &conf->mirrors[mirror].rdev->flags);
- if (!test_and_set_bit(WantReplacement,
- &conf->mirrors[mirror].rdev->flags))
+ set_bit(WriteErrorSeen, &rdev->flags);
+ if (!test_and_set_bit(WantReplacement, &rdev->flags))
set_bit(MD_RECOVERY_NEEDED, &
conf->mddev->recovery);
@@ -445,13 +442,12 @@ static void raid1_end_write_request(struct bio *bio)
* before rdev->recovery_offset, but for simplicity we don't
* check this here.
*/
- if (test_bit(In_sync, &conf->mirrors[mirror].rdev->flags) &&
- !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags))
+ if (test_bit(In_sync, &rdev->flags) &&
+ !test_bit(Faulty, &rdev->flags))
set_bit(R1BIO_Uptodate, &r1_bio->state);
/* Maybe we can clear some bad blocks. */
- if (is_badblock(conf->mirrors[mirror].rdev,
- r1_bio->sector, r1_bio->sectors,
+ if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
&first_bad, &bad_sectors)) {
r1_bio->bios[mirror] = IO_MADE_GOOD;
set_bit(R1BIO_MadeGood, &r1_bio->state);
@@ -459,7 +455,7 @@ static void raid1_end_write_request(struct bio *bio)
}
if (behind) {
- if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
+ if (test_bit(WriteMostly, &rdev->flags))
atomic_dec(&r1_bio->behind_remaining);
/*
@@ -483,8 +479,7 @@ static void raid1_end_write_request(struct bio *bio)
}
}
if (r1_bio->bios[mirror] == NULL)
- rdev_dec_pending(conf->mirrors[mirror].rdev,
- conf->mddev);
+ rdev_dec_pending(rdev, conf->mddev);
/*
* Let's see if all mirrored write operations have finished
@@ -689,13 +684,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
if (!rdev)
goto retry;
atomic_inc(&rdev->nr_pending);
- if (test_bit(Faulty, &rdev->flags)) {
- /* cannot risk returning a device that failed
- * before we inc'ed nr_pending
- */
- rdev_dec_pending(rdev, conf->mddev);
- goto retry;
- }
sectors = best_good_sectors;
if (conf->mirrors[best_disk].next_seq_sect != this_sector)
@@ -759,7 +747,7 @@ static void flush_pending_writes(struct r1conf *conf)
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
bio->bi_next = NULL;
- if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+ if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
bio_endio(bio);
@@ -1033,7 +1021,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
bio->bi_next = NULL;
- if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+ if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
bio_endio(bio);
@@ -1053,12 +1041,11 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio)
int i, disks;
struct bitmap *bitmap;
unsigned long flags;
+ const int op = bio_op(bio);
const int rw = bio_data_dir(bio);
- const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
- const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA));
- const unsigned long do_discard = (bio->bi_rw
- & (REQ_DISCARD | REQ_SECURE));
- const unsigned long do_same = (bio->bi_rw & REQ_WRITE_SAME);
+ const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
+ const unsigned long do_flush_fua = (bio->bi_opf &
+ (REQ_PREFLUSH | REQ_FUA));
struct md_rdev *blocked_rdev;
struct blk_plug_cb *cb;
struct raid1_plug_cb *plug = NULL;
@@ -1106,7 +1093,7 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio)
bitmap = mddev->bitmap;
/*
- * make_request() can abort the operation when READA is being
+ * make_request() can abort the operation when read-ahead is being
* used and no empty request is available.
*
*/
@@ -1166,7 +1153,7 @@ read_again:
mirror->rdev->data_offset;
read_bio->bi_bdev = mirror->rdev->bdev;
read_bio->bi_end_io = raid1_end_read_request;
- read_bio->bi_rw = READ | do_sync;
+ bio_set_op_attrs(read_bio, op, do_sync);
read_bio->bi_private = r1_bio;
if (max_sectors < r1_bio->sectors) {
@@ -1376,8 +1363,7 @@ read_again:
conf->mirrors[i].rdev->data_offset);
mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
mbio->bi_end_io = raid1_end_write_request;
- mbio->bi_rw =
- WRITE | do_flush_fua | do_sync | do_discard | do_same;
+ bio_set_op_attrs(mbio, op, do_flush_fua | do_sync);
mbio->bi_private = r1_bio;
atomic_inc(&r1_bio->remaining);
@@ -1668,13 +1654,16 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
goto abort;
}
p->rdev = NULL;
- synchronize_rcu();
- if (atomic_read(&rdev->nr_pending)) {
- /* lost the race, try later */
- err = -EBUSY;
- p->rdev = rdev;
- goto abort;
- } else if (conf->mirrors[conf->raid_disks + number].rdev) {
+ if (!test_bit(RemoveSynchronized, &rdev->flags)) {
+ synchronize_rcu();
+ if (atomic_read(&rdev->nr_pending)) {
+ /* lost the race, try later */
+ err = -EBUSY;
+ p->rdev = rdev;
+ goto abort;
+ }
+ }
+ if (conf->mirrors[conf->raid_disks + number].rdev) {
/* We just removed a device that is being replaced.
* Move down the replacement. We drain all IO before
* doing this to avoid confusion.
@@ -1721,11 +1710,9 @@ static void end_sync_write(struct bio *bio)
struct r1bio *r1_bio = bio->bi_private;
struct mddev *mddev = r1_bio->mddev;
struct r1conf *conf = mddev->private;
- int mirror=0;
sector_t first_bad;
int bad_sectors;
-
- mirror = find_bio_disk(r1_bio, bio);
+ struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev;
if (!uptodate) {
sector_t sync_blocks = 0;
@@ -1738,16 +1725,12 @@ static void end_sync_write(struct bio *bio)
s += sync_blocks;
sectors_to_go -= sync_blocks;
} while (sectors_to_go > 0);
- set_bit(WriteErrorSeen,
- &conf->mirrors[mirror].rdev->flags);
- if (!test_and_set_bit(WantReplacement,
- &conf->mirrors[mirror].rdev->flags))
+ set_bit(WriteErrorSeen, &rdev->flags);
+ if (!test_and_set_bit(WantReplacement, &rdev->flags))
set_bit(MD_RECOVERY_NEEDED, &
mddev->recovery);
set_bit(R1BIO_WriteError, &r1_bio->state);
- } else if (is_badblock(conf->mirrors[mirror].rdev,
- r1_bio->sector,
- r1_bio->sectors,
+ } else if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
&first_bad, &bad_sectors) &&
!is_badblock(conf->mirrors[r1_bio->read_disk].rdev,
r1_bio->sector,
@@ -1771,7 +1754,7 @@ static void end_sync_write(struct bio *bio)
static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
int sectors, struct page *page, int rw)
{
- if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
+ if (sync_page_io(rdev, sector, sectors << 9, page, rw, 0, false))
/* success */
return 1;
if (rw == WRITE) {
@@ -1825,7 +1808,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
rdev = conf->mirrors[d].rdev;
if (sync_page_io(rdev, sect, s<<9,
bio->bi_io_vec[idx].bv_page,
- READ, false)) {
+ REQ_OP_READ, 0, false)) {
success = 1;
break;
}
@@ -2030,7 +2013,7 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
!test_bit(MD_RECOVERY_SYNC, &mddev->recovery))))
continue;
- wbio->bi_rw = WRITE;
+ bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
wbio->bi_end_io = end_sync_write;
atomic_inc(&r1_bio->remaining);
md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio));
@@ -2074,29 +2057,30 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
s = PAGE_SIZE >> 9;
do {
- /* Note: no rcu protection needed here
- * as this is synchronous in the raid1d thread
- * which is the thread that might remove
- * a device. If raid1d ever becomes multi-threaded....
- */
sector_t first_bad;
int bad_sectors;
- rdev = conf->mirrors[d].rdev;
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev &&
(test_bit(In_sync, &rdev->flags) ||
(!test_bit(Faulty, &rdev->flags) &&
rdev->recovery_offset >= sect + s)) &&
is_badblock(rdev, sect, s,
- &first_bad, &bad_sectors) == 0 &&
- sync_page_io(rdev, sect, s<<9,
- conf->tmppage, READ, false))
- success = 1;
- else {
- d++;
- if (d == conf->raid_disks * 2)
- d = 0;
- }
+ &first_bad, &bad_sectors) == 0) {
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
+ if (sync_page_io(rdev, sect, s<<9,
+ conf->tmppage, REQ_OP_READ, 0, false))
+ success = 1;
+ rdev_dec_pending(rdev, mddev);
+ if (success)
+ break;
+ } else
+ rcu_read_unlock();
+ d++;
+ if (d == conf->raid_disks * 2)
+ d = 0;
} while (!success && d != read_disk);
if (!success) {
@@ -2112,11 +2096,17 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
if (d==0)
d = conf->raid_disks * 2;
d--;
- rdev = conf->mirrors[d].rdev;
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev &&
- !test_bit(Faulty, &rdev->flags))
+ !test_bit(Faulty, &rdev->flags)) {
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
r1_sync_page_io(rdev, sect, s,
conf->tmppage, WRITE);
+ rdev_dec_pending(rdev, mddev);
+ } else
+ rcu_read_unlock();
}
d = start;
while (d != read_disk) {
@@ -2124,9 +2114,12 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
if (d==0)
d = conf->raid_disks * 2;
d--;
- rdev = conf->mirrors[d].rdev;
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev &&
!test_bit(Faulty, &rdev->flags)) {
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
if (r1_sync_page_io(rdev, sect, s,
conf->tmppage, READ)) {
atomic_add(s, &rdev->corrected_errors);
@@ -2135,10 +2128,12 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
"(%d sectors at %llu on %s)\n",
mdname(mddev), s,
(unsigned long long)(sect +
- rdev->data_offset),
+ rdev->data_offset),
bdevname(rdev->bdev, b));
}
- }
+ rdev_dec_pending(rdev, mddev);
+ } else
+ rcu_read_unlock();
}
sectors -= s;
sect += s;
@@ -2201,14 +2196,15 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
wbio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev);
}
- wbio->bi_rw = WRITE;
+ bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
wbio->bi_iter.bi_sector = r1_bio->sector;
wbio->bi_iter.bi_size = r1_bio->sectors << 9;
bio_trim(wbio, sector - r1_bio->sector, sectors);
wbio->bi_iter.bi_sector += rdev->data_offset;
wbio->bi_bdev = rdev->bdev;
- if (submit_bio_wait(WRITE, wbio) < 0)
+
+ if (submit_bio_wait(wbio) < 0)
/* failure! */
ok = rdev_set_badblocks(rdev, sector,
sectors, 0)
@@ -2322,7 +2318,7 @@ read_more:
raid_end_bio_io(r1_bio);
} else {
const unsigned long do_sync
- = r1_bio->master_bio->bi_rw & REQ_SYNC;
+ = r1_bio->master_bio->bi_opf & REQ_SYNC;
if (bio) {
r1_bio->bios[r1_bio->read_disk] =
mddev->ro ? IO_BLOCKED : NULL;
@@ -2343,7 +2339,7 @@ read_more:
bio->bi_iter.bi_sector = r1_bio->sector + rdev->data_offset;
bio->bi_bdev = rdev->bdev;
bio->bi_end_io = raid1_end_read_request;
- bio->bi_rw = READ | do_sync;
+ bio_set_op_attrs(bio, REQ_OP_READ, do_sync);
bio->bi_private = r1_bio;
if (max_sectors < r1_bio->sectors) {
/* Drat - have to split this up more */
@@ -2535,6 +2531,13 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
return sync_blocks;
}
+ /*
+ * If there is non-resync activity waiting for a turn, then let it
+ * though before starting on this new sync request.
+ */
+ if (conf->nr_waiting)
+ schedule_timeout_uninterruptible(1);
+
/* we are incrementing sector_nr below. To be safe, we check against
* sector_nr + two times RESYNC_SECTORS
*/
@@ -2571,7 +2574,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
if (i < conf->raid_disks)
still_degraded = 1;
} else if (!test_bit(In_sync, &rdev->flags)) {
- bio->bi_rw = WRITE;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_end_io = end_sync_write;
write_targets ++;
} else {
@@ -2598,7 +2601,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
if (disk < 0)
disk = i;
}
- bio->bi_rw = READ;
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
bio->bi_end_io = end_sync_read;
read_targets++;
} else if (!test_bit(WriteErrorSeen, &rdev->flags) &&
@@ -2610,7 +2613,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
* if we are doing resync or repair. Otherwise, leave
* this device alone for this sync request.
*/
- bio->bi_rw = WRITE;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_end_io = end_sync_write;
write_targets++;
}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index c7de2a53e..be1a9fca3 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -707,7 +707,6 @@ static struct md_rdev *read_balance(struct r10conf *conf,
raid10_find_phys(conf, r10_bio);
rcu_read_lock();
-retry:
sectors = r10_bio->sectors;
best_slot = -1;
best_rdev = NULL;
@@ -804,13 +803,6 @@ retry:
if (slot >= 0) {
atomic_inc(&rdev->nr_pending);
- if (test_bit(Faulty, &rdev->flags)) {
- /* Cannot risk returning a device that failed
- * before we inc'ed nr_pending
- */
- rdev_dec_pending(rdev, conf->mddev);
- goto retry;
- }
r10_bio->read_slot = slot;
} else
rdev = NULL;
@@ -865,7 +857,7 @@ static void flush_pending_writes(struct r10conf *conf)
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
bio->bi_next = NULL;
- if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+ if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
bio_endio(bio);
@@ -913,7 +905,7 @@ static void raise_barrier(struct r10conf *conf, int force)
/* Now wait for all pending IO to complete */
wait_event_lock_irq(conf->wait_barrier,
- !conf->nr_pending && conf->barrier < RESYNC_DEPTH,
+ !atomic_read(&conf->nr_pending) && conf->barrier < RESYNC_DEPTH,
conf->resync_lock);
spin_unlock_irq(&conf->resync_lock);
@@ -944,23 +936,23 @@ static void wait_barrier(struct r10conf *conf)
*/
wait_event_lock_irq(conf->wait_barrier,
!conf->barrier ||
- (conf->nr_pending &&
+ (atomic_read(&conf->nr_pending) &&
current->bio_list &&
!bio_list_empty(current->bio_list)),
conf->resync_lock);
conf->nr_waiting--;
+ if (!conf->nr_waiting)
+ wake_up(&conf->wait_barrier);
}
- conf->nr_pending++;
+ atomic_inc(&conf->nr_pending);
spin_unlock_irq(&conf->resync_lock);
}
static void allow_barrier(struct r10conf *conf)
{
- unsigned long flags;
- spin_lock_irqsave(&conf->resync_lock, flags);
- conf->nr_pending--;
- spin_unlock_irqrestore(&conf->resync_lock, flags);
- wake_up(&conf->wait_barrier);
+ if ((atomic_dec_and_test(&conf->nr_pending)) ||
+ (conf->array_freeze_pending))
+ wake_up(&conf->wait_barrier);
}
static void freeze_array(struct r10conf *conf, int extra)
@@ -978,13 +970,15 @@ static void freeze_array(struct r10conf *conf, int extra)
* we continue.
*/
spin_lock_irq(&conf->resync_lock);
+ conf->array_freeze_pending++;
conf->barrier++;
conf->nr_waiting++;
wait_event_lock_irq_cmd(conf->wait_barrier,
- conf->nr_pending == conf->nr_queued+extra,
+ atomic_read(&conf->nr_pending) == conf->nr_queued+extra,
conf->resync_lock,
flush_pending_writes(conf));
+ conf->array_freeze_pending--;
spin_unlock_irq(&conf->resync_lock);
}
@@ -1041,7 +1035,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
bio->bi_next = NULL;
- if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+ if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
bio_endio(bio);
@@ -1058,12 +1052,10 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
struct r10bio *r10_bio;
struct bio *read_bio;
int i;
+ const int op = bio_op(bio);
const int rw = bio_data_dir(bio);
- const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
- const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
- const unsigned long do_discard = (bio->bi_rw
- & (REQ_DISCARD | REQ_SECURE));
- const unsigned long do_same = (bio->bi_rw & REQ_WRITE_SAME);
+ const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
+ const unsigned long do_fua = (bio->bi_opf & REQ_FUA);
unsigned long flags;
struct md_rdev *blocked_rdev;
struct blk_plug_cb *cb;
@@ -1072,6 +1064,8 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
int max_sectors;
int sectors;
+ md_write_start(mddev, bio);
+
/*
* Register the new request and wait if the reconstruction
* thread has put up a bar for new requests.
@@ -1156,7 +1150,7 @@ read_again:
choose_data_offset(r10_bio, rdev);
read_bio->bi_bdev = rdev->bdev;
read_bio->bi_end_io = raid10_end_read_request;
- read_bio->bi_rw = READ | do_sync;
+ bio_set_op_attrs(read_bio, op, do_sync);
read_bio->bi_private = r10_bio;
if (max_sectors < r10_bio->sectors) {
@@ -1363,8 +1357,7 @@ retry_write:
rdev));
mbio->bi_bdev = rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw =
- WRITE | do_sync | do_fua | do_discard | do_same;
+ bio_set_op_attrs(mbio, op, do_sync | do_fua);
mbio->bi_private = r10_bio;
atomic_inc(&r10_bio->remaining);
@@ -1406,8 +1399,7 @@ retry_write:
r10_bio, rdev));
mbio->bi_bdev = rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw =
- WRITE | do_sync | do_fua | do_discard | do_same;
+ bio_set_op_attrs(mbio, op, do_sync | do_fua);
mbio->bi_private = r10_bio;
atomic_inc(&r10_bio->remaining);
@@ -1450,13 +1442,11 @@ static void raid10_make_request(struct mddev *mddev, struct bio *bio)
struct bio *split;
- if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+ if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
md_flush_request(mddev, bio);
return;
}
- md_write_start(mddev, bio);
-
do {
/*
@@ -1503,10 +1493,12 @@ static void raid10_status(struct seq_file *seq, struct mddev *mddev)
}
seq_printf(seq, " [%d/%d] [", conf->geo.raid_disks,
conf->geo.raid_disks - mddev->degraded);
- for (i = 0; i < conf->geo.raid_disks; i++)
- seq_printf(seq, "%s",
- conf->mirrors[i].rdev &&
- test_bit(In_sync, &conf->mirrors[i].rdev->flags) ? "U" : "_");
+ rcu_read_lock();
+ for (i = 0; i < conf->geo.raid_disks; i++) {
+ struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+ seq_printf(seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
+ }
+ rcu_read_unlock();
seq_printf(seq, "]");
}
@@ -1604,7 +1596,7 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
static void print_conf(struct r10conf *conf)
{
int i;
- struct raid10_info *tmp;
+ struct md_rdev *rdev;
printk(KERN_DEBUG "RAID10 conf printout:\n");
if (!conf) {
@@ -1614,14 +1606,16 @@ static void print_conf(struct r10conf *conf)
printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->geo.raid_disks - conf->mddev->degraded,
conf->geo.raid_disks);
+ /* This is only called with ->reconfix_mutex held, so
+ * rcu protection of rdev is not needed */
for (i = 0; i < conf->geo.raid_disks; i++) {
char b[BDEVNAME_SIZE];
- tmp = conf->mirrors + i;
- if (tmp->rdev)
+ rdev = conf->mirrors[i].rdev;
+ if (rdev)
printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n",
- i, !test_bit(In_sync, &tmp->rdev->flags),
- !test_bit(Faulty, &tmp->rdev->flags),
- bdevname(tmp->rdev->bdev,b));
+ i, !test_bit(In_sync, &rdev->flags),
+ !test_bit(Faulty, &rdev->flags),
+ bdevname(rdev->bdev,b));
}
}
@@ -1770,7 +1764,7 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
err = -EBUSY;
goto abort;
}
- /* Only remove faulty devices if recovery
+ /* Only remove non-faulty devices if recovery
* is not possible.
*/
if (!test_bit(Faulty, &rdev->flags) &&
@@ -1782,13 +1776,16 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
goto abort;
}
*rdevp = NULL;
- synchronize_rcu();
- if (atomic_read(&rdev->nr_pending)) {
- /* lost the race, try later */
- err = -EBUSY;
- *rdevp = rdev;
- goto abort;
- } else if (p->replacement) {
+ if (!test_bit(RemoveSynchronized, &rdev->flags)) {
+ synchronize_rcu();
+ if (atomic_read(&rdev->nr_pending)) {
+ /* lost the race, try later */
+ err = -EBUSY;
+ *rdevp = rdev;
+ goto abort;
+ }
+ }
+ if (p->replacement) {
/* We must have just cleared 'rdev' */
p->rdev = p->replacement;
clear_bit(Replacement, &p->replacement->flags);
@@ -1992,10 +1989,10 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
tbio->bi_vcnt = vcnt;
tbio->bi_iter.bi_size = fbio->bi_iter.bi_size;
- tbio->bi_rw = WRITE;
tbio->bi_private = r10_bio;
tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
tbio->bi_end_io = end_sync_write;
+ bio_set_op_attrs(tbio, REQ_OP_WRITE, 0);
bio_copy_data(tbio, fbio);
@@ -2078,7 +2075,7 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
addr,
s << 9,
bio->bi_io_vec[idx].bv_page,
- READ, false);
+ REQ_OP_READ, 0, false);
if (ok) {
rdev = conf->mirrors[dw].rdev;
addr = r10_bio->devs[1].addr + sect;
@@ -2086,7 +2083,7 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
addr,
s << 9,
bio->bi_io_vec[idx].bv_page,
- WRITE, false);
+ REQ_OP_WRITE, 0, false);
if (!ok) {
set_bit(WriteErrorSeen, &rdev->flags);
if (!test_and_set_bit(WantReplacement,
@@ -2175,21 +2172,20 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
*/
static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev)
{
- struct timespec cur_time_mon;
+ long cur_time_mon;
unsigned long hours_since_last;
unsigned int read_errors = atomic_read(&rdev->read_errors);
- ktime_get_ts(&cur_time_mon);
+ cur_time_mon = ktime_get_seconds();
- if (rdev->last_read_error.tv_sec == 0 &&
- rdev->last_read_error.tv_nsec == 0) {
+ if (rdev->last_read_error == 0) {
/* first time we've seen a read error */
rdev->last_read_error = cur_time_mon;
return;
}
- hours_since_last = (cur_time_mon.tv_sec -
- rdev->last_read_error.tv_sec) / 3600;
+ hours_since_last = (long)(cur_time_mon -
+ rdev->last_read_error) / 3600;
rdev->last_read_error = cur_time_mon;
@@ -2213,7 +2209,7 @@ static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors)
&& (rw == READ || test_bit(WriteErrorSeen, &rdev->flags)))
return -1;
- if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
+ if (sync_page_io(rdev, sector, sectors << 9, page, rw, 0, false))
/* success */
return 1;
if (rw == WRITE) {
@@ -2268,7 +2264,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
printk(KERN_NOTICE
"md/raid10:%s: %s: Failing raid device\n",
mdname(mddev), b);
- md_error(mddev, conf->mirrors[d].rdev);
+ md_error(mddev, rdev);
r10_bio->devs[r10_bio->read_slot].bio = IO_BLOCKED;
return;
}
@@ -2291,6 +2287,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev &&
test_bit(In_sync, &rdev->flags) &&
+ !test_bit(Faulty, &rdev->flags) &&
is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
&first_bad, &bad_sectors) == 0) {
atomic_inc(&rdev->nr_pending);
@@ -2299,7 +2296,8 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
r10_bio->devs[sl].addr +
sect,
s<<9,
- conf->tmppage, READ, false);
+ conf->tmppage,
+ REQ_OP_READ, 0, false);
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
if (success)
@@ -2343,6 +2341,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
d = r10_bio->devs[sl].devnum;
rdev = rcu_dereference(conf->mirrors[d].rdev);
if (!rdev ||
+ test_bit(Faulty, &rdev->flags) ||
!test_bit(In_sync, &rdev->flags))
continue;
@@ -2382,6 +2381,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
d = r10_bio->devs[sl].devnum;
rdev = rcu_dereference(conf->mirrors[d].rdev);
if (!rdev ||
+ test_bit(Faulty, &rdev->flags) ||
!test_bit(In_sync, &rdev->flags))
continue;
@@ -2465,18 +2465,21 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
while (sect_to_write) {
struct bio *wbio;
+ sector_t wsector;
if (sectors > sect_to_write)
sectors = sect_to_write;
/* Write at 'sector' for 'sectors' */
wbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors);
- wbio->bi_iter.bi_sector = (r10_bio->devs[i].addr+
- choose_data_offset(r10_bio, rdev) +
- (sector - r10_bio->sector));
+ wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
+ wbio->bi_iter.bi_sector = wsector +
+ choose_data_offset(r10_bio, rdev);
wbio->bi_bdev = rdev->bdev;
- if (submit_bio_wait(WRITE, wbio) < 0)
+ bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
+
+ if (submit_bio_wait(wbio) < 0)
/* Failure! */
- ok = rdev_set_badblocks(rdev, sector,
+ ok = rdev_set_badblocks(rdev, wsector,
sectors, 0)
&& ok;
@@ -2531,7 +2534,7 @@ read_more:
return;
}
- do_sync = (r10_bio->master_bio->bi_rw & REQ_SYNC);
+ do_sync = (r10_bio->master_bio->bi_opf & REQ_SYNC);
slot = r10_bio->read_slot;
printk_ratelimited(
KERN_ERR
@@ -2548,7 +2551,7 @@ read_more:
bio->bi_iter.bi_sector = r10_bio->devs[slot].addr
+ choose_data_offset(r10_bio, rdev);
bio->bi_bdev = rdev->bdev;
- bio->bi_rw = READ | do_sync;
+ bio_set_op_attrs(bio, REQ_OP_READ, do_sync);
bio->bi_private = r10_bio;
bio->bi_end_io = raid10_end_read_request;
if (max_sectors < r10_bio->sectors) {
@@ -2877,11 +2880,14 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
/* Completed a full sync so the replacements
* are now fully recovered.
*/
- for (i = 0; i < conf->geo.raid_disks; i++)
- if (conf->mirrors[i].replacement)
- conf->mirrors[i].replacement
- ->recovery_offset
- = MaxSector;
+ rcu_read_lock();
+ for (i = 0; i < conf->geo.raid_disks; i++) {
+ struct md_rdev *rdev =
+ rcu_dereference(conf->mirrors[i].replacement);
+ if (rdev)
+ rdev->recovery_offset = MaxSector;
+ }
+ rcu_read_unlock();
}
conf->fullsync = 0;
}
@@ -2912,6 +2918,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
max_sector > (sector_nr | chunk_mask))
max_sector = (sector_nr | chunk_mask) + 1;
+ /*
+ * If there is non-resync activity waiting for a turn, then let it
+ * though before starting on this new sync request.
+ */
+ if (conf->nr_waiting)
+ schedule_timeout_uninterruptible(1);
+
/* Again, very different code for resync and recovery.
* Both must result in an r10bio with a list of bios that
* have bi_end_io, bi_sector, bi_bdev set,
@@ -2940,14 +2953,20 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
int must_sync;
int any_working;
struct raid10_info *mirror = &conf->mirrors[i];
+ struct md_rdev *mrdev, *mreplace;
- if ((mirror->rdev == NULL ||
- test_bit(In_sync, &mirror->rdev->flags))
- &&
- (mirror->replacement == NULL ||
- test_bit(Faulty,
- &mirror->replacement->flags)))
+ rcu_read_lock();
+ mrdev = rcu_dereference(mirror->rdev);
+ mreplace = rcu_dereference(mirror->replacement);
+
+ if ((mrdev == NULL ||
+ test_bit(Faulty, &mrdev->flags) ||
+ test_bit(In_sync, &mrdev->flags)) &&
+ (mreplace == NULL ||
+ test_bit(Faulty, &mreplace->flags))) {
+ rcu_read_unlock();
continue;
+ }
still_degraded = 0;
/* want to reconstruct this device */
@@ -2957,8 +2976,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
/* last stripe is not complete - don't
* try to recover this sector.
*/
+ rcu_read_unlock();
continue;
}
+ if (mreplace && test_bit(Faulty, &mreplace->flags))
+ mreplace = NULL;
/* Unless we are doing a full sync, or a replacement
* we only need to recover the block if it is set in
* the bitmap
@@ -2968,14 +2990,19 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
if (sync_blocks < max_sync)
max_sync = sync_blocks;
if (!must_sync &&
- mirror->replacement == NULL &&
+ mreplace == NULL &&
!conf->fullsync) {
/* yep, skip the sync_blocks here, but don't assume
* that there will never be anything to do here
*/
chunks_skipped = -1;
+ rcu_read_unlock();
continue;
}
+ atomic_inc(&mrdev->nr_pending);
+ if (mreplace)
+ atomic_inc(&mreplace->nr_pending);
+ rcu_read_unlock();
r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
r10_bio->state = 0;
@@ -2994,12 +3021,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
/* Need to check if the array will still be
* degraded
*/
- for (j = 0; j < conf->geo.raid_disks; j++)
- if (conf->mirrors[j].rdev == NULL ||
- test_bit(Faulty, &conf->mirrors[j].rdev->flags)) {
+ rcu_read_lock();
+ for (j = 0; j < conf->geo.raid_disks; j++) {
+ struct md_rdev *rdev = rcu_dereference(
+ conf->mirrors[j].rdev);
+ if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
still_degraded = 1;
break;
}
+ }
must_sync = bitmap_start_sync(mddev->bitmap, sect,
&sync_blocks, still_degraded);
@@ -3009,15 +3039,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
int k;
int d = r10_bio->devs[j].devnum;
sector_t from_addr, to_addr;
- struct md_rdev *rdev;
+ struct md_rdev *rdev =
+ rcu_dereference(conf->mirrors[d].rdev);
sector_t sector, first_bad;
int bad_sectors;
- if (!conf->mirrors[d].rdev ||
- !test_bit(In_sync, &conf->mirrors[d].rdev->flags))
+ if (!rdev ||
+ !test_bit(In_sync, &rdev->flags))
continue;
/* This is where we read from */
any_working = 1;
- rdev = conf->mirrors[d].rdev;
sector = r10_bio->devs[j].addr;
if (is_badblock(rdev, sector, max_sync,
@@ -3038,7 +3068,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
biolist = bio;
bio->bi_private = r10_bio;
bio->bi_end_io = end_sync_read;
- bio->bi_rw = READ;
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
from_addr = r10_bio->devs[j].addr;
bio->bi_iter.bi_sector = from_addr +
rdev->data_offset;
@@ -3056,18 +3086,17 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
r10_bio->devs[1].devnum = i;
r10_bio->devs[1].addr = to_addr;
- rdev = mirror->rdev;
- if (!test_bit(In_sync, &rdev->flags)) {
+ if (!test_bit(In_sync, &mrdev->flags)) {
bio = r10_bio->devs[1].bio;
bio_reset(bio);
bio->bi_next = biolist;
biolist = bio;
bio->bi_private = r10_bio;
bio->bi_end_io = end_sync_write;
- bio->bi_rw = WRITE;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_iter.bi_sector = to_addr
- + rdev->data_offset;
- bio->bi_bdev = rdev->bdev;
+ + mrdev->data_offset;
+ bio->bi_bdev = mrdev->bdev;
atomic_inc(&r10_bio->remaining);
} else
r10_bio->devs[1].bio->bi_end_io = NULL;
@@ -3076,8 +3105,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
bio = r10_bio->devs[1].repl_bio;
if (bio)
bio->bi_end_io = NULL;
- rdev = mirror->replacement;
- /* Note: if rdev != NULL, then bio
+ /* Note: if mreplace != NULL, then bio
* cannot be NULL as r10buf_pool_alloc will
* have allocated it.
* So the second test here is pointless.
@@ -3085,21 +3113,22 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
* this comment keeps human reviewers
* happy.
*/
- if (rdev == NULL || bio == NULL ||
- test_bit(Faulty, &rdev->flags))
+ if (mreplace == NULL || bio == NULL ||
+ test_bit(Faulty, &mreplace->flags))
break;
bio_reset(bio);
bio->bi_next = biolist;
biolist = bio;
bio->bi_private = r10_bio;
bio->bi_end_io = end_sync_write;
- bio->bi_rw = WRITE;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_iter.bi_sector = to_addr +
- rdev->data_offset;
- bio->bi_bdev = rdev->bdev;
+ mreplace->data_offset;
+ bio->bi_bdev = mreplace->bdev;
atomic_inc(&r10_bio->remaining);
break;
}
+ rcu_read_unlock();
if (j == conf->copies) {
/* Cannot recover, so abort the recovery or
* record a bad block */
@@ -3112,15 +3141,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
if (r10_bio->devs[k].devnum == i)
break;
if (!test_bit(In_sync,
- &mirror->rdev->flags)
+ &mrdev->flags)
&& !rdev_set_badblocks(
- mirror->rdev,
+ mrdev,
r10_bio->devs[k].addr,
max_sync, 0))
any_working = 0;
- if (mirror->replacement &&
+ if (mreplace &&
!rdev_set_badblocks(
- mirror->replacement,
+ mreplace,
r10_bio->devs[k].addr,
max_sync, 0))
any_working = 0;
@@ -3138,8 +3167,14 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
if (rb2)
atomic_dec(&rb2->remaining);
r10_bio = rb2;
+ rdev_dec_pending(mrdev, mddev);
+ if (mreplace)
+ rdev_dec_pending(mreplace, mddev);
break;
}
+ rdev_dec_pending(mrdev, mddev);
+ if (mreplace)
+ rdev_dec_pending(mreplace, mddev);
}
if (biolist == NULL) {
while (r10_bio) {
@@ -3184,6 +3219,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
int d = r10_bio->devs[i].devnum;
sector_t first_bad, sector;
int bad_sectors;
+ struct md_rdev *rdev;
if (r10_bio->devs[i].repl_bio)
r10_bio->devs[i].repl_bio->bi_end_io = NULL;
@@ -3191,12 +3227,14 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
bio = r10_bio->devs[i].bio;
bio_reset(bio);
bio->bi_error = -EIO;
- if (conf->mirrors[d].rdev == NULL ||
- test_bit(Faulty, &conf->mirrors[d].rdev->flags))
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->mirrors[d].rdev);
+ if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
+ rcu_read_unlock();
continue;
+ }
sector = r10_bio->devs[i].addr;
- if (is_badblock(conf->mirrors[d].rdev,
- sector, max_sync,
+ if (is_badblock(rdev, sector, max_sync,
&first_bad, &bad_sectors)) {
if (first_bad > sector)
max_sync = first_bad - sector;
@@ -3204,25 +3242,28 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
bad_sectors -= (sector - first_bad);
if (max_sync > bad_sectors)
max_sync = bad_sectors;
+ rcu_read_unlock();
continue;
}
}
- atomic_inc(&conf->mirrors[d].rdev->nr_pending);
+ atomic_inc(&rdev->nr_pending);
atomic_inc(&r10_bio->remaining);
bio->bi_next = biolist;
biolist = bio;
bio->bi_private = r10_bio;
bio->bi_end_io = end_sync_read;
- bio->bi_rw = READ;
- bio->bi_iter.bi_sector = sector +
- conf->mirrors[d].rdev->data_offset;
- bio->bi_bdev = conf->mirrors[d].rdev->bdev;
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+ bio->bi_iter.bi_sector = sector + rdev->data_offset;
+ bio->bi_bdev = rdev->bdev;
count++;
- if (conf->mirrors[d].replacement == NULL ||
- test_bit(Faulty,
- &conf->mirrors[d].replacement->flags))
+ rdev = rcu_dereference(conf->mirrors[d].replacement);
+ if (rdev == NULL || test_bit(Faulty, &rdev->flags)) {
+ rcu_read_unlock();
continue;
+ }
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
/* Need to set up for writing to the replacement */
bio = r10_bio->devs[i].repl_bio;
@@ -3230,15 +3271,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
bio->bi_error = -EIO;
sector = r10_bio->devs[i].addr;
- atomic_inc(&conf->mirrors[d].rdev->nr_pending);
bio->bi_next = biolist;
biolist = bio;
bio->bi_private = r10_bio;
bio->bi_end_io = end_sync_write;
- bio->bi_rw = WRITE;
- bio->bi_iter.bi_sector = sector +
- conf->mirrors[d].replacement->data_offset;
- bio->bi_bdev = conf->mirrors[d].replacement->bdev;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ bio->bi_iter.bi_sector = sector + rdev->data_offset;
+ bio->bi_bdev = rdev->bdev;
count++;
}
@@ -3505,6 +3544,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
spin_lock_init(&conf->resync_lock);
init_waitqueue_head(&conf->wait_barrier);
+ atomic_set(&conf->nr_pending, 0);
conf->thread = md_register_thread(raid10d, mddev, "raid10");
if (!conf->thread)
@@ -4320,7 +4360,7 @@ read_more:
+ rdev->data_offset);
read_bio->bi_private = r10_bio;
read_bio->bi_end_io = end_sync_read;
- read_bio->bi_rw = READ;
+ bio_set_op_attrs(read_bio, REQ_OP_READ, 0);
read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
read_bio->bi_error = 0;
read_bio->bi_vcnt = 0;
@@ -4334,15 +4374,16 @@ read_more:
blist = read_bio;
read_bio->bi_next = NULL;
+ rcu_read_lock();
for (s = 0; s < conf->copies*2; s++) {
struct bio *b;
int d = r10_bio->devs[s/2].devnum;
struct md_rdev *rdev2;
if (s&1) {
- rdev2 = conf->mirrors[d].replacement;
+ rdev2 = rcu_dereference(conf->mirrors[d].replacement);
b = r10_bio->devs[s/2].repl_bio;
} else {
- rdev2 = conf->mirrors[d].rdev;
+ rdev2 = rcu_dereference(conf->mirrors[d].rdev);
b = r10_bio->devs[s/2].bio;
}
if (!rdev2 || test_bit(Faulty, &rdev2->flags))
@@ -4354,7 +4395,7 @@ read_more:
rdev2->new_data_offset;
b->bi_private = r10_bio;
b->bi_end_io = end_reshape_write;
- b->bi_rw = WRITE;
+ bio_set_op_attrs(b, REQ_OP_WRITE, 0);
b->bi_next = blist;
blist = b;
}
@@ -4387,6 +4428,7 @@ read_more:
nr_sectors += len >> 9;
}
bio_full:
+ rcu_read_unlock();
r10_bio->sectors = nr_sectors;
/* Now submit the read */
@@ -4438,16 +4480,20 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio)
struct bio *b;
int d = r10_bio->devs[s/2].devnum;
struct md_rdev *rdev;
+ rcu_read_lock();
if (s&1) {
- rdev = conf->mirrors[d].replacement;
+ rdev = rcu_dereference(conf->mirrors[d].replacement);
b = r10_bio->devs[s/2].repl_bio;
} else {
- rdev = conf->mirrors[d].rdev;
+ rdev = rcu_dereference(conf->mirrors[d].rdev);
b = r10_bio->devs[s/2].bio;
}
- if (!rdev || test_bit(Faulty, &rdev->flags))
+ if (!rdev || test_bit(Faulty, &rdev->flags)) {
+ rcu_read_unlock();
continue;
+ }
atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
md_sync_acct(b->bi_bdev, r10_bio->sectors);
atomic_inc(&r10_bio->remaining);
b->bi_next = NULL;
@@ -4508,9 +4554,10 @@ static int handle_reshape_read_error(struct mddev *mddev,
if (s > (PAGE_SIZE >> 9))
s = PAGE_SIZE >> 9;
+ rcu_read_lock();
while (!success) {
int d = r10b->devs[slot].devnum;
- struct md_rdev *rdev = conf->mirrors[d].rdev;
+ struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
sector_t addr;
if (rdev == NULL ||
test_bit(Faulty, &rdev->flags) ||
@@ -4518,11 +4565,15 @@ static int handle_reshape_read_error(struct mddev *mddev,
goto failed;
addr = r10b->devs[slot].addr + idx * PAGE_SIZE;
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
success = sync_page_io(rdev,
addr,
s << 9,
bvec[idx].bv_page,
- READ, false);
+ REQ_OP_READ, 0, false);
+ rdev_dec_pending(rdev, mddev);
+ rcu_read_lock();
if (success)
break;
failed:
@@ -4532,6 +4583,7 @@ static int handle_reshape_read_error(struct mddev *mddev,
if (slot == first_slot)
break;
}
+ rcu_read_unlock();
if (!success) {
/* couldn't read this block, must give up */
set_bit(MD_RECOVERY_INTR,
@@ -4601,16 +4653,18 @@ static void raid10_finish_reshape(struct mddev *mddev)
}
} else {
int d;
+ rcu_read_lock();
for (d = conf->geo.raid_disks ;
d < conf->geo.raid_disks - mddev->delta_disks;
d++) {
- struct md_rdev *rdev = conf->mirrors[d].rdev;
+ struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev)
clear_bit(In_sync, &rdev->flags);
- rdev = conf->mirrors[d].replacement;
+ rdev = rcu_dereference(conf->mirrors[d].replacement);
if (rdev)
clear_bit(In_sync, &rdev->flags);
}
+ rcu_read_unlock();
}
mddev->layout = mddev->new_layout;
mddev->chunk_sectors = 1 << conf->geo.chunk_shift;
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index 6fc2c7575..18ec1f7a9 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -64,10 +64,11 @@ struct r10conf {
int pending_count;
spinlock_t resync_lock;
- int nr_pending;
+ atomic_t nr_pending;
int nr_waiting;
int nr_queued;
int barrier;
+ int array_freeze_pending;
sector_t next_resync;
int fullsync; /* set to 1 if a full sync is needed,
* (fresh device added).
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index e889e2deb..1b1ab4a1d 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -96,7 +96,6 @@ struct r5l_log {
spinlock_t no_space_stripes_lock;
bool need_cache_flush;
- bool in_teardown;
};
/*
@@ -254,14 +253,14 @@ static void r5l_submit_current_io(struct r5l_log *log)
__r5l_set_io_unit_state(io, IO_UNIT_IO_START);
spin_unlock_irqrestore(&log->io_list_lock, flags);
- submit_bio(WRITE, io->current_bio);
+ submit_bio(io->current_bio);
}
static struct bio *r5l_bio_alloc(struct r5l_log *log)
{
struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, log->bs);
- bio->bi_rw = WRITE;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_bdev = log->rdev->bdev;
bio->bi_iter.bi_sector = log->rdev->data_offset + log->log_start;
@@ -373,7 +372,7 @@ static void r5l_append_payload_page(struct r5l_log *log, struct page *page)
io->current_bio = r5l_bio_alloc(log);
bio_chain(io->current_bio, prev);
- submit_bio(WRITE, prev);
+ submit_bio(prev);
}
if (!bio_add_page(io->current_bio, page, PAGE_SIZE, 0))
@@ -536,7 +535,7 @@ int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio)
bio_endio(bio);
return 0;
}
- bio->bi_rw &= ~REQ_FLUSH;
+ bio->bi_opf &= ~REQ_PREFLUSH;
return -EAGAIN;
}
@@ -686,7 +685,8 @@ void r5l_flush_stripe_to_raid(struct r5l_log *log)
bio_reset(&log->flush_bio);
log->flush_bio.bi_bdev = log->rdev->bdev;
log->flush_bio.bi_end_io = r5l_log_flush_endio;
- submit_bio(WRITE_FLUSH, &log->flush_bio);
+ bio_set_op_attrs(&log->flush_bio, REQ_OP_WRITE, WRITE_FLUSH);
+ submit_bio(&log->flush_bio);
}
static void r5l_write_super(struct r5l_log *log, sector_t cp);
@@ -703,31 +703,22 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log,
mddev = log->rdev->mddev;
/*
- * This is to avoid a deadlock. r5l_quiesce holds reconfig_mutex and
- * wait for this thread to finish. This thread waits for
- * MD_CHANGE_PENDING clear, which is supposed to be done in
- * md_check_recovery(). md_check_recovery() tries to get
- * reconfig_mutex. Since r5l_quiesce already holds the mutex,
- * md_check_recovery() fails, so the PENDING never get cleared. The
- * in_teardown check workaround this issue.
+ * Discard could zero data, so before discard we must make sure
+ * superblock is updated to new log tail. Updating superblock (either
+ * directly call md_update_sb() or depend on md thread) must hold
+ * reconfig mutex. On the other hand, raid5_quiesce is called with
+ * reconfig_mutex hold. The first step of raid5_quiesce() is waitting
+ * for all IO finish, hence waitting for reclaim thread, while reclaim
+ * thread is calling this function and waitting for reconfig mutex. So
+ * there is a deadlock. We workaround this issue with a trylock.
+ * FIXME: we could miss discard if we can't take reconfig mutex
*/
- if (!log->in_teardown) {
- set_mask_bits(&mddev->flags, 0,
- BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
- md_wakeup_thread(mddev->thread);
- wait_event(mddev->sb_wait,
- !test_bit(MD_CHANGE_PENDING, &mddev->flags) ||
- log->in_teardown);
- /*
- * r5l_quiesce could run after in_teardown check and hold
- * mutex first. Superblock might get updated twice.
- */
- if (log->in_teardown)
- md_update_sb(mddev, 1);
- } else {
- WARN_ON(!mddev_is_locked(mddev));
- md_update_sb(mddev, 1);
- }
+ set_mask_bits(&mddev->flags, 0,
+ BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
+ if (!mddev_trylock(mddev))
+ return;
+ md_update_sb(mddev, 1);
+ mddev_unlock(mddev);
/* discard IO error really doesn't matter, ignore it */
if (log->last_checkpoint < end) {
@@ -826,7 +817,6 @@ void r5l_quiesce(struct r5l_log *log, int state)
if (!log || state == 2)
return;
if (state == 0) {
- log->in_teardown = 0;
/*
* This is a special case for hotadd. In suspend, the array has
* no journal. In resume, journal is initialized as well as the
@@ -837,11 +827,6 @@ void r5l_quiesce(struct r5l_log *log, int state)
log->reclaim_thread = md_register_thread(r5l_reclaim_thread,
log->rdev->mddev, "reclaim");
} else if (state == 1) {
- /*
- * at this point all stripes are finished, so io_unit is at
- * least in STRIPE_END state
- */
- log->in_teardown = 1;
/* make sure r5l_write_super_and_discard_space exits */
mddev = log->rdev->mddev;
wake_up(&mddev->sb_wait);
@@ -881,7 +866,8 @@ static int r5l_read_meta_block(struct r5l_log *log,
struct r5l_meta_block *mb;
u32 crc, stored_crc;
- if (!sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page, READ, false))
+ if (!sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page, REQ_OP_READ, 0,
+ false))
return -EIO;
mb = page_address(page);
@@ -926,7 +912,8 @@ static int r5l_recovery_flush_one_stripe(struct r5l_log *log,
&disk_index, sh);
sync_page_io(log->rdev, *log_offset, PAGE_SIZE,
- sh->dev[disk_index].page, READ, false);
+ sh->dev[disk_index].page, REQ_OP_READ, 0,
+ false);
sh->dev[disk_index].log_checksum =
le32_to_cpu(payload->checksum[0]);
set_bit(R5_Wantwrite, &sh->dev[disk_index].flags);
@@ -934,7 +921,8 @@ static int r5l_recovery_flush_one_stripe(struct r5l_log *log,
} else {
disk_index = sh->pd_idx;
sync_page_io(log->rdev, *log_offset, PAGE_SIZE,
- sh->dev[disk_index].page, READ, false);
+ sh->dev[disk_index].page, REQ_OP_READ, 0,
+ false);
sh->dev[disk_index].log_checksum =
le32_to_cpu(payload->checksum[0]);
set_bit(R5_Wantwrite, &sh->dev[disk_index].flags);
@@ -944,7 +932,7 @@ static int r5l_recovery_flush_one_stripe(struct r5l_log *log,
sync_page_io(log->rdev,
r5l_ring_add(log, *log_offset, BLOCK_SECTORS),
PAGE_SIZE, sh->dev[disk_index].page,
- READ, false);
+ REQ_OP_READ, 0, false);
sh->dev[disk_index].log_checksum =
le32_to_cpu(payload->checksum[1]);
set_bit(R5_Wantwrite,
@@ -986,11 +974,13 @@ static int r5l_recovery_flush_one_stripe(struct r5l_log *log,
rdev = rcu_dereference(conf->disks[disk_index].rdev);
if (rdev)
sync_page_io(rdev, stripe_sect, PAGE_SIZE,
- sh->dev[disk_index].page, WRITE, false);
+ sh->dev[disk_index].page, REQ_OP_WRITE, 0,
+ false);
rrdev = rcu_dereference(conf->disks[disk_index].replacement);
if (rrdev)
sync_page_io(rrdev, stripe_sect, PAGE_SIZE,
- sh->dev[disk_index].page, WRITE, false);
+ sh->dev[disk_index].page, REQ_OP_WRITE, 0,
+ false);
}
raid5_release_stripe(sh);
return 0;
@@ -1062,7 +1052,8 @@ static int r5l_log_write_empty_meta_block(struct r5l_log *log, sector_t pos,
crc = crc32c_le(log->uuid_checksum, mb, PAGE_SIZE);
mb->checksum = cpu_to_le32(crc);
- if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, WRITE_FUA, false)) {
+ if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, REQ_OP_WRITE,
+ WRITE_FUA, false)) {
__free_page(page);
return -EIO;
}
@@ -1137,7 +1128,7 @@ static int r5l_load_log(struct r5l_log *log)
if (!page)
return -ENOMEM;
- if (!sync_page_io(rdev, cp, PAGE_SIZE, page, READ, false)) {
+ if (!sync_page_io(rdev, cp, PAGE_SIZE, page, REQ_OP_READ, 0, false)) {
ret = -EIO;
goto ioerr;
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8959e6dd3..ee7fc3701 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -659,6 +659,7 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
{
struct stripe_head *sh;
int hash = stripe_hash_locks_hash(sector);
+ int inc_empty_inactive_list_flag;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
@@ -703,7 +704,12 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&sh->lru) &&
!test_bit(STRIPE_EXPANDING, &sh->state));
+ inc_empty_inactive_list_flag = 0;
+ if (!list_empty(conf->inactive_list + hash))
+ inc_empty_inactive_list_flag = 1;
list_del_init(&sh->lru);
+ if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+ atomic_inc(&conf->empty_inactive_list_nr);
if (sh->group) {
sh->group->stripes_cnt--;
sh->group = NULL;
@@ -762,6 +768,7 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
sector_t head_sector, tmp_sec;
int hash;
int dd_idx;
+ int inc_empty_inactive_list_flag;
/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
tmp_sec = sh->sector;
@@ -779,7 +786,12 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&head->lru) &&
!test_bit(STRIPE_EXPANDING, &head->state));
+ inc_empty_inactive_list_flag = 0;
+ if (!list_empty(conf->inactive_list + hash))
+ inc_empty_inactive_list_flag = 1;
list_del_init(&head->lru);
+ if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+ atomic_inc(&conf->empty_inactive_list_nr);
if (head->group) {
head->group->stripes_cnt--;
head->group = NULL;
@@ -806,7 +818,8 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
dd_idx = 0;
while (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
dd_idx++;
- if (head->dev[dd_idx].towrite->bi_rw != sh->dev[dd_idx].towrite->bi_rw)
+ if (head->dev[dd_idx].towrite->bi_opf != sh->dev[dd_idx].towrite->bi_opf ||
+ bio_op(head->dev[dd_idx].towrite) != bio_op(sh->dev[dd_idx].towrite))
goto unlock_out;
if (head->batch_head) {
@@ -891,29 +904,28 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
if (r5l_write_stripe(conf->log, sh) == 0)
return;
for (i = disks; i--; ) {
- int rw;
+ int op, op_flags = 0;
int replace_only = 0;
struct bio *bi, *rbi;
struct md_rdev *rdev, *rrdev = NULL;
sh = head_sh;
if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
+ op = REQ_OP_WRITE;
if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
- rw = WRITE_FUA;
- else
- rw = WRITE;
+ op_flags = WRITE_FUA;
if (test_bit(R5_Discard, &sh->dev[i].flags))
- rw |= REQ_DISCARD;
+ op = REQ_OP_DISCARD;
} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
- rw = READ;
+ op = REQ_OP_READ;
else if (test_and_clear_bit(R5_WantReplace,
&sh->dev[i].flags)) {
- rw = WRITE;
+ op = REQ_OP_WRITE;
replace_only = 1;
} else
continue;
if (test_and_clear_bit(R5_SyncIO, &sh->dev[i].flags))
- rw |= REQ_SYNC;
+ op_flags |= REQ_SYNC;
again:
bi = &sh->dev[i].req;
@@ -927,7 +939,7 @@ again:
rdev = rrdev;
rrdev = NULL;
}
- if (rw & WRITE) {
+ if (op_is_write(op)) {
if (replace_only)
rdev = NULL;
if (rdev == rrdev)
@@ -953,7 +965,7 @@ again:
* need to check for writes. We never accept write errors
* on the replacement, so we don't to check rrdev.
*/
- while ((rw & WRITE) && rdev &&
+ while (op_is_write(op) && rdev &&
test_bit(WriteErrorSeen, &rdev->flags)) {
sector_t first_bad;
int bad_sectors;
@@ -993,17 +1005,16 @@ again:
set_bit(STRIPE_IO_STARTED, &sh->state);
- bio_reset(bi);
bi->bi_bdev = rdev->bdev;
- bi->bi_rw = rw;
- bi->bi_end_io = (rw & WRITE)
+ bio_set_op_attrs(bi, op, op_flags);
+ bi->bi_end_io = op_is_write(op)
? raid5_end_write_request
: raid5_end_read_request;
bi->bi_private = sh;
- pr_debug("%s: for %llu schedule op %ld on disc %d\n",
+ pr_debug("%s: for %llu schedule op %d on disc %d\n",
__func__, (unsigned long long)sh->sector,
- bi->bi_rw, i);
+ bi->bi_opf, i);
atomic_inc(&sh->count);
if (sh != head_sh)
atomic_inc(&head_sh->count);
@@ -1014,7 +1025,7 @@ again:
bi->bi_iter.bi_sector = (sh->sector
+ rdev->data_offset);
if (test_bit(R5_ReadNoMerge, &head_sh->dev[i].flags))
- bi->bi_rw |= REQ_NOMERGE;
+ bi->bi_opf |= REQ_NOMERGE;
if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
@@ -1027,7 +1038,7 @@ again:
* If this is discard request, set bi_vcnt 0. We don't
* want to confuse SCSI because SCSI will replace payload
*/
- if (rw & REQ_DISCARD)
+ if (op == REQ_OP_DISCARD)
bi->bi_vcnt = 0;
if (rrdev)
set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
@@ -1045,17 +1056,16 @@ again:
set_bit(STRIPE_IO_STARTED, &sh->state);
- bio_reset(rbi);
rbi->bi_bdev = rrdev->bdev;
- rbi->bi_rw = rw;
- BUG_ON(!(rw & WRITE));
+ bio_set_op_attrs(rbi, op, op_flags);
+ BUG_ON(!op_is_write(op));
rbi->bi_end_io = raid5_end_write_request;
rbi->bi_private = sh;
- pr_debug("%s: for %llu schedule op %ld on "
+ pr_debug("%s: for %llu schedule op %d on "
"replacement disc %d\n",
__func__, (unsigned long long)sh->sector,
- rbi->bi_rw, i);
+ rbi->bi_opf, i);
atomic_inc(&sh->count);
if (sh != head_sh)
atomic_inc(&head_sh->count);
@@ -1076,7 +1086,7 @@ again:
* If this is discard request, set bi_vcnt 0. We don't
* want to confuse SCSI because SCSI will replace payload
*/
- if (rw & REQ_DISCARD)
+ if (op == REQ_OP_DISCARD)
rbi->bi_vcnt = 0;
if (conf->mddev->gendisk)
trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
@@ -1085,10 +1095,10 @@ again:
generic_make_request(rbi);
}
if (!rdev && !rrdev) {
- if (rw & WRITE)
+ if (op_is_write(op))
set_bit(STRIPE_DEGRADED, &sh->state);
- pr_debug("skip op %ld on disc %d for sector %llu\n",
- bi->bi_rw, i, (unsigned long long)sh->sector);
+ pr_debug("skip op %d on disc %d for sector %llu\n",
+ bi->bi_opf, i, (unsigned long long)sh->sector);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
}
@@ -1619,11 +1629,11 @@ again:
while (wbi && wbi->bi_iter.bi_sector <
dev->sector + STRIPE_SECTORS) {
- if (wbi->bi_rw & REQ_FUA)
+ if (wbi->bi_opf & REQ_FUA)
set_bit(R5_WantFUA, &dev->flags);
- if (wbi->bi_rw & REQ_SYNC)
+ if (wbi->bi_opf & REQ_SYNC)
set_bit(R5_SyncIO, &dev->flags);
- if (wbi->bi_rw & REQ_DISCARD)
+ if (bio_op(wbi) == REQ_OP_DISCARD)
set_bit(R5_Discard, &dev->flags);
else {
tx = async_copy_data(1, wbi, &dev->page,
@@ -1978,9 +1988,11 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
put_cpu();
}
-static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
+static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
+ int disks)
{
struct stripe_head *sh;
+ int i;
sh = kmem_cache_zalloc(sc, gfp);
if (sh) {
@@ -1989,6 +2001,17 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
INIT_LIST_HEAD(&sh->batch_list);
INIT_LIST_HEAD(&sh->lru);
atomic_set(&sh->count, 1);
+ for (i = 0; i < disks; i++) {
+ struct r5dev *dev = &sh->dev[i];
+
+ bio_init(&dev->req);
+ dev->req.bi_io_vec = &dev->vec;
+ dev->req.bi_max_vecs = 1;
+
+ bio_init(&dev->rreq);
+ dev->rreq.bi_io_vec = &dev->rvec;
+ dev->rreq.bi_max_vecs = 1;
+ }
}
return sh;
}
@@ -1996,7 +2019,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
{
struct stripe_head *sh;
- sh = alloc_stripe(conf->slab_cache, gfp);
+ sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size);
if (!sh)
return 0;
@@ -2167,7 +2190,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
mutex_lock(&conf->cache_size_mutex);
for (i = conf->max_nr_stripes; i; i--) {
- nsh = alloc_stripe(sc, GFP_KERNEL);
+ nsh = alloc_stripe(sc, GFP_KERNEL, newsize);
if (!nsh)
break;
@@ -2299,6 +2322,7 @@ static void raid5_end_read_request(struct bio * bi)
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_error);
if (i == disks) {
+ bio_reset(bi);
BUG();
return;
}
@@ -2399,6 +2423,7 @@ static void raid5_end_read_request(struct bio * bi)
}
}
rdev_dec_pending(rdev, conf->mddev);
+ bio_reset(bi);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
@@ -2436,6 +2461,7 @@ static void raid5_end_write_request(struct bio *bi)
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_error);
if (i == disks) {
+ bio_reset(bi);
BUG();
return;
}
@@ -2472,6 +2498,7 @@ static void raid5_end_write_request(struct bio *bi)
if (sh->batch_head && bi->bi_error && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
+ bio_reset(bi);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
@@ -2485,16 +2512,6 @@ static void raid5_build_block(struct stripe_head *sh, int i, int previous)
{
struct r5dev *dev = &sh->dev[i];
- bio_init(&dev->req);
- dev->req.bi_io_vec = &dev->vec;
- dev->req.bi_max_vecs = 1;
- dev->req.bi_private = sh;
-
- bio_init(&dev->rreq);
- dev->rreq.bi_io_vec = &dev->rvec;
- dev->rreq.bi_max_vecs = 1;
- dev->rreq.bi_private = sh;
-
dev->flags = 0;
dev->sector = raid5_compute_blocknr(sh, i, previous);
}
@@ -3080,7 +3097,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
struct md_rdev *rdev;
rcu_read_lock();
rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && test_bit(In_sync, &rdev->flags))
+ if (rdev && test_bit(In_sync, &rdev->flags) &&
+ !test_bit(Faulty, &rdev->flags))
atomic_inc(&rdev->nr_pending);
else
rdev = NULL;
@@ -3210,15 +3228,16 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
/* During recovery devices cannot be removed, so
* locking and refcounting of rdevs is not needed
*/
+ rcu_read_lock();
for (i = 0; i < conf->raid_disks; i++) {
- struct md_rdev *rdev = conf->disks[i].rdev;
+ struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev
&& !test_bit(Faulty, &rdev->flags)
&& !test_bit(In_sync, &rdev->flags)
&& !rdev_set_badblocks(rdev, sh->sector,
STRIPE_SECTORS, 0))
abort = 1;
- rdev = conf->disks[i].replacement;
+ rdev = rcu_dereference(conf->disks[i].replacement);
if (rdev
&& !test_bit(Faulty, &rdev->flags)
&& !test_bit(In_sync, &rdev->flags)
@@ -3226,6 +3245,7 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
STRIPE_SECTORS, 0))
abort = 1;
}
+ rcu_read_unlock();
if (abort)
conf->recovery_disabled =
conf->mddev->recovery_disabled;
@@ -3237,15 +3257,16 @@ static int want_replace(struct stripe_head *sh, int disk_idx)
{
struct md_rdev *rdev;
int rv = 0;
- /* Doing recovery so rcu locking not required */
- rdev = sh->raid_conf->disks[disk_idx].replacement;
+
+ rcu_read_lock();
+ rdev = rcu_dereference(sh->raid_conf->disks[disk_idx].replacement);
if (rdev
&& !test_bit(Faulty, &rdev->flags)
&& !test_bit(In_sync, &rdev->flags)
&& (rdev->recovery_offset <= sh->sector
|| rdev->mddev->recovery_cp <= sh->sector))
rv = 1;
-
+ rcu_read_unlock();
return rv;
}
@@ -3600,7 +3621,7 @@ static void handle_stripe_dirtying(struct r5conf *conf,
pr_debug("for sector %llu, rmw=%d rcw=%d\n",
(unsigned long long)sh->sector, rmw, rcw);
set_bit(STRIPE_HANDLE, &sh->state);
- if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_ENABLE_RMW)) && rmw > 0) {
+ 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,
@@ -3627,7 +3648,7 @@ static void handle_stripe_dirtying(struct r5conf *conf,
}
}
}
- if ((rcw < rmw || (rcw == rmw && conf->rmw_level != PARITY_ENABLE_RMW)) && rcw > 0) {
+ if ((rcw < rmw || (rcw == rmw && conf->rmw_level != PARITY_PREFER_RMW)) && rcw > 0) {
/* want reconstruct write, but need to get some data */
int qread =0;
rcw = 0;
@@ -4624,7 +4645,9 @@ finish:
}
if (!bio_list_empty(&s.return_bi)) {
- if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) {
+ if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags) &&
+ (s.failed <= conf->max_degraded ||
+ conf->mddev->external == 0)) {
spin_lock_irq(&conf->device_lock);
bio_list_merge(&conf->return_bi, &s.return_bi);
spin_unlock_irq(&conf->device_lock);
@@ -5150,7 +5173,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
DEFINE_WAIT(w);
bool do_prepare;
- if (unlikely(bi->bi_rw & REQ_FLUSH)) {
+ if (unlikely(bi->bi_opf & REQ_PREFLUSH)) {
int ret = r5l_handle_flush_request(conf->log, bi);
if (ret == 0)
@@ -5176,7 +5199,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
return;
}
- if (unlikely(bi->bi_rw & REQ_DISCARD)) {
+ if (unlikely(bio_op(bi) == REQ_OP_DISCARD)) {
make_discard_request(mddev, bi);
return;
}
@@ -5233,7 +5256,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
(unsigned long long)logical_sector);
sh = raid5_get_active_stripe(conf, new_sector, previous,
- (bi->bi_rw&RWA_MASK), 0);
+ (bi->bi_opf & REQ_RAHEAD), 0);
if (sh) {
if (unlikely(previous)) {
/* expansion might have moved on while waiting for a
@@ -5301,7 +5324,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
set_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
if ((!sh->batch_head || sh == sh->batch_head) &&
- (bi->bi_rw & REQ_SYNC) &&
+ (bi->bi_opf & REQ_SYNC) &&
!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
atomic_inc(&conf->preread_active_stripes);
release_stripe_plug(mddev, sh);
@@ -6616,6 +6639,16 @@ static struct r5conf *setup_conf(struct mddev *mddev)
}
conf->min_nr_stripes = NR_STRIPES;
+ if (mddev->reshape_position != MaxSector) {
+ int stripes = max_t(int,
+ ((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4,
+ ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4);
+ conf->min_nr_stripes = max(NR_STRIPES, stripes);
+ if (conf->min_nr_stripes != NR_STRIPES)
+ printk(KERN_INFO
+ "md/raid:%s: force stripe size %d for reshape\n",
+ mdname(mddev), conf->min_nr_stripes);
+ }
memory = conf->min_nr_stripes * (sizeof(struct stripe_head) +
max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS);
@@ -6822,11 +6855,14 @@ static int raid5_run(struct mddev *mddev)
if (IS_ERR(conf))
return PTR_ERR(conf);
- if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !journal_dev) {
- printk(KERN_ERR "md/raid:%s: journal disk is missing, force array readonly\n",
- mdname(mddev));
- mddev->ro = 1;
- set_disk_ro(mddev->gendisk, 1);
+ if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+ if (!journal_dev) {
+ pr_err("md/raid:%s: journal disk is missing, force array readonly\n",
+ mdname(mddev));
+ mddev->ro = 1;
+ set_disk_ro(mddev->gendisk, 1);
+ } else if (mddev->recovery_cp == MaxSector)
+ set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
}
conf->min_offset_diff = min_offset_diff;
@@ -7066,10 +7102,12 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev)
seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
conf->chunk_sectors / 2, mddev->layout);
seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded);
- for (i = 0; i < conf->raid_disks; i++)
- seq_printf (seq, "%s",
- conf->disks[i].rdev &&
- test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_");
+ rcu_read_lock();
+ for (i = 0; i < conf->raid_disks; i++) {
+ struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+ seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
+ }
+ rcu_read_unlock();
seq_printf (seq, "]");
}
@@ -7191,12 +7229,15 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
goto abort;
}
*rdevp = NULL;
- synchronize_rcu();
- if (atomic_read(&rdev->nr_pending)) {
- /* lost the race, try later */
- err = -EBUSY;
- *rdevp = rdev;
- } else if (p->replacement) {
+ if (!test_bit(RemoveSynchronized, &rdev->flags)) {
+ synchronize_rcu();
+ if (atomic_read(&rdev->nr_pending)) {
+ /* lost the race, try later */
+ err = -EBUSY;
+ *rdevp = rdev;
+ }
+ }
+ if (p->replacement) {
/* We must have just cleared 'rdev' */
p->rdev = p->replacement;
clear_bit(Replacement, &p->replacement->flags);