summaryrefslogtreecommitdiffstats
path: root/drivers/md/bcache/super.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/bcache/super.c')
-rw-r--r--drivers/md/bcache/super.c228
1 files changed, 167 insertions, 61 deletions
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 55a37641aa95..7bbd670a5a84 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* bcache setup/teardown code, and some metadata io - read a superblock and
* figure out what to do with it.
@@ -46,6 +47,7 @@ static int bcache_major;
static DEFINE_IDA(bcache_device_idx);
static wait_queue_head_t unregister_wait;
struct workqueue_struct *bcache_wq;
+struct workqueue_struct *bch_journal_wq;
#define BTREE_MAX_PAGES (256 * 1024 / PAGE_SIZE)
/* limitation of partitions number on single bcache device */
@@ -61,7 +63,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
const char *err;
struct cache_sb *s;
struct buffer_head *bh = __bread(bdev, 1, SB_SIZE);
- unsigned i;
+ unsigned int i;
if (!bh)
return "IO error";
@@ -149,7 +151,8 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
goto err;
err = "Invalid superblock: device too small";
- if (get_capacity(bdev->bd_disk) < sb->bucket_size * sb->nbuckets)
+ if (get_capacity(bdev->bd_disk) <
+ sb->bucket_size * sb->nbuckets)
goto err;
err = "Bad UUID";
@@ -202,7 +205,7 @@ static void write_bdev_super_endio(struct bio *bio)
static void __write_super(struct cache_sb *sb, struct bio *bio)
{
struct cache_sb *out = page_address(bio_first_page_all(bio));
- unsigned i;
+ unsigned int i;
bio->bi_iter.bi_sector = SB_SECTOR;
bio->bi_iter.bi_size = SB_SIZE;
@@ -282,7 +285,7 @@ void bcache_write_super(struct cache_set *c)
{
struct closure *cl = &c->sb_write;
struct cache *ca;
- unsigned i;
+ unsigned int i;
down(&c->sb_write_mutex);
closure_init(cl, &c->cl);
@@ -334,7 +337,7 @@ static void uuid_io(struct cache_set *c, int op, unsigned long op_flags,
{
struct closure *cl = &c->uuid_write;
struct uuid_entry *u;
- unsigned i;
+ unsigned int i;
char buf[80];
BUG_ON(!parent);
@@ -415,8 +418,9 @@ static int __uuid_write(struct cache_set *c)
{
BKEY_PADDED(key) k;
struct closure cl;
- closure_init_stack(&cl);
+ struct cache *ca;
+ closure_init_stack(&cl);
lockdep_assert_held(&bch_register_lock);
if (bch_bucket_alloc_set(c, RESERVE_BTREE, &k.key, 1, true))
@@ -426,6 +430,10 @@ static int __uuid_write(struct cache_set *c)
uuid_io(c, REQ_OP_WRITE, 0, &k.key, &cl);
closure_sync(&cl);
+ /* Only one bucket used for uuid write */
+ ca = PTR_CACHE(c, &k.key, 0);
+ atomic_long_add(ca->sb.bucket_size, &ca->meta_sectors_written);
+
bkey_copy(&c->uuid_bucket, &k.key);
bkey_put(c, &k.key);
return 0;
@@ -456,6 +464,7 @@ static struct uuid_entry *uuid_find(struct cache_set *c, const char *uuid)
static struct uuid_entry *uuid_find_empty(struct cache_set *c)
{
static const char zero_uuid[16] = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
+
return uuid_find(c, zero_uuid);
}
@@ -463,8 +472,8 @@ static struct uuid_entry *uuid_find_empty(struct cache_set *c)
* Bucket priorities/gens:
*
* For each bucket, we store on disk its
- * 8 bit gen
- * 16 bit priority
+ * 8 bit gen
+ * 16 bit priority
*
* See alloc.c for an explanation of the gen. The priority is used to implement
* lru (and in the future other) cache replacement policies; for most purposes
@@ -587,7 +596,7 @@ static void prio_read(struct cache *ca, uint64_t bucket)
struct prio_set *p = ca->disk_buckets;
struct bucket_disk *d = p->data + prios_per_bucket(ca), *end = d;
struct bucket *b;
- unsigned bucket_nr = 0;
+ unsigned int bucket_nr = 0;
for (b = ca->buckets;
b < ca->buckets + ca->sb.nbuckets;
@@ -599,7 +608,8 @@ static void prio_read(struct cache *ca, uint64_t bucket)
prio_io(ca, bucket, REQ_OP_READ, 0);
- if (p->csum != bch_crc64(&p->magic, bucket_bytes(ca) - 8))
+ if (p->csum !=
+ bch_crc64(&p->magic, bucket_bytes(ca) - 8))
pr_warn("bad csum reading priorities");
if (p->magic != pset_magic(&ca->sb))
@@ -619,6 +629,7 @@ static void prio_read(struct cache *ca, uint64_t bucket)
static int open_dev(struct block_device *b, fmode_t mode)
{
struct bcache_device *d = b->bd_disk->private_data;
+
if (test_bit(BCACHE_DEV_CLOSING, &d->flags))
return -ENXIO;
@@ -629,6 +640,7 @@ static int open_dev(struct block_device *b, fmode_t mode)
static void release_dev(struct gendisk *b, fmode_t mode)
{
struct bcache_device *d = b->private_data;
+
closure_put(&d->cl);
}
@@ -636,10 +648,6 @@ static int ioctl_dev(struct block_device *b, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct bcache_device *d = b->bd_disk->private_data;
- struct cached_dev *dc = container_of(d, struct cached_dev, disk);
-
- if (dc->io_disable)
- return -EIO;
return d->ioctl(d, mode, cmd, arg);
}
@@ -662,7 +670,7 @@ static void bcache_device_unlink(struct bcache_device *d)
lockdep_assert_held(&bch_register_lock);
if (d->c && !test_and_set_bit(BCACHE_DEV_UNLINK_DONE, &d->flags)) {
- unsigned i;
+ unsigned int i;
struct cache *ca;
sysfs_remove_link(&d->c->kobj, d->name);
@@ -676,7 +684,7 @@ static void bcache_device_unlink(struct bcache_device *d)
static void bcache_device_link(struct bcache_device *d, struct cache_set *c,
const char *name)
{
- unsigned i;
+ unsigned int i;
struct cache *ca;
for_each_cache(ca, d->c, i)
@@ -715,7 +723,7 @@ static void bcache_device_detach(struct bcache_device *d)
}
static void bcache_device_attach(struct bcache_device *d, struct cache_set *c,
- unsigned id)
+ unsigned int id)
{
d->id = id;
d->c = c;
@@ -762,7 +770,7 @@ static void bcache_device_free(struct bcache_device *d)
closure_debug_destroy(&d->cl);
}
-static int bcache_device_init(struct bcache_device *d, unsigned block_size,
+static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
sector_t sectors)
{
struct request_queue *q;
@@ -778,7 +786,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
if (!d->nr_stripes || d->nr_stripes > max_stripes) {
pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)",
- (unsigned)d->nr_stripes);
+ (unsigned int)d->nr_stripes);
return -ENOMEM;
}
@@ -919,6 +927,7 @@ void bch_cached_dev_run(struct cached_dev *dc)
if (!d->c &&
BDEV_STATE(&dc->sb) != BDEV_STATE_NONE) {
struct closure cl;
+
closure_init_stack(&cl);
SET_BDEV_STATE(&dc->sb, BDEV_STATE_STALE);
@@ -928,8 +937,10 @@ void bch_cached_dev_run(struct cached_dev *dc)
add_disk(d->disk);
bd_link_disk_holder(dc->bdev, dc->disk.disk);
- /* won't show up in the uevent file, use udevadm monitor -e instead
- * only class / kset properties are persistent */
+ /*
+ * won't show up in the uevent file, use udevadm monitor -e instead
+ * only class / kset properties are persistent
+ */
kobject_uevent_env(&disk_to_dev(d->disk)->kobj, KOBJ_CHANGE, env);
kfree(env[1]);
kfree(env[2]);
@@ -976,6 +987,7 @@ static void cached_dev_detach_finish(struct work_struct *w)
{
struct cached_dev *dc = container_of(w, struct cached_dev, detach);
struct closure cl;
+
closure_init_stack(&cl);
BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags));
@@ -997,6 +1009,7 @@ static void cached_dev_detach_finish(struct work_struct *w)
bch_write_bdev_super(dc, &cl);
closure_sync(&cl);
+ calc_cached_dev_sectors(dc->disk.c);
bcache_device_detach(&dc->disk);
list_move(&dc->list, &uncached_devices);
@@ -1097,12 +1110,14 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
}
}
- /* Deadlocks since we're called via sysfs...
- sysfs_remove_file(&dc->kobj, &sysfs_attach);
+ /*
+ * Deadlocks since we're called via sysfs...
+ * sysfs_remove_file(&dc->kobj, &sysfs_attach);
*/
if (bch_is_zero(u->uuid, 16)) {
struct closure cl;
+
closure_init_stack(&cl);
memcpy(u->uuid, dc->sb.uuid, 16);
@@ -1124,11 +1139,11 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
list_move(&dc->list, &c->cached_devs);
calc_cached_dev_sectors(c);
- smp_wmb();
/*
* dc->c must be set before dc->count != 0 - paired with the mb in
* cached_dev_get()
*/
+ smp_wmb();
refcount_set(&dc->count, 1);
/* Block writeback thread, but spawn it */
@@ -1139,11 +1154,12 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
}
if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
- bch_sectors_dirty_init(&dc->disk);
atomic_set(&dc->has_dirty, 1);
bch_writeback_queue(dc);
}
+ bch_sectors_dirty_init(&dc->disk);
+
bch_cached_dev_run(dc);
bcache_device_link(&dc->disk, c, "bdev");
atomic_inc(&c->attached_dev_nr);
@@ -1212,7 +1228,7 @@ static void cached_dev_flush(struct closure *cl)
continue_at(cl, cached_dev_free, system_wq);
}
-static int cached_dev_init(struct cached_dev *dc, unsigned block_size)
+static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
{
int ret;
struct io *io;
@@ -1320,6 +1336,7 @@ void bch_flash_dev_release(struct kobject *kobj)
static void flash_dev_free(struct closure *cl)
{
struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+
mutex_lock(&bch_register_lock);
atomic_long_sub(bcache_dev_sectors_dirty(d),
&d->c->flash_dev_dirty_sectors);
@@ -1459,17 +1476,18 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...)
if (test_and_set_bit(CACHE_SET_IO_DISABLE, &c->flags))
pr_info("CACHE_SET_IO_DISABLE already set");
- /* XXX: we can be called from atomic context
- acquire_console_sem();
- */
+ /*
+ * XXX: we can be called from atomic context
+ * acquire_console_sem();
+ */
- printk(KERN_ERR "bcache: error on %pU: ", c->sb.set_uuid);
+ pr_err("bcache: error on %pU: ", c->sb.set_uuid);
va_start(args, fmt);
vprintk(fmt, args);
va_end(args);
- printk(", disabling caching\n");
+ pr_err(", disabling caching\n");
if (c->on_error == ON_ERROR_PANIC)
panic("panic forced after error\n");
@@ -1481,6 +1499,7 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...)
void bch_cache_set_release(struct kobject *kobj)
{
struct cache_set *c = container_of(kobj, struct cache_set, kobj);
+
kfree(c);
module_put(THIS_MODULE);
}
@@ -1489,7 +1508,7 @@ static void cache_set_free(struct closure *cl)
{
struct cache_set *c = container_of(cl, struct cache_set, cl);
struct cache *ca;
- unsigned i;
+ unsigned int i;
if (!IS_ERR_OR_NULL(c->debug))
debugfs_remove(c->debug);
@@ -1532,7 +1551,7 @@ static void cache_set_flush(struct closure *cl)
struct cache_set *c = container_of(cl, struct cache_set, caching);
struct cache *ca;
struct btree *b;
- unsigned i;
+ unsigned int i;
bch_cache_accounting_destroy(&c->accounting);
@@ -1671,6 +1690,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
{
int iter_size;
struct cache_set *c = kzalloc(sizeof(struct cache_set), GFP_KERNEL);
+
if (!c)
return NULL;
@@ -1731,8 +1751,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
if (!(c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL)) ||
mempool_init_slab_pool(&c->search, 32, bch_search_cache) ||
mempool_init_kmalloc_pool(&c->bio_meta, 2,
- sizeof(struct bbio) + sizeof(struct bio_vec) *
- bucket_pages(c)) ||
+ sizeof(struct bbio) + sizeof(struct bio_vec) *
+ bucket_pages(c)) ||
mempool_init_kmalloc_pool(&c->fill_iter, 1, iter_size) ||
bioset_init(&c->bio_split, 4, offsetof(struct bbio, bio),
BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
@@ -1762,7 +1782,7 @@ static void run_cache_set(struct cache_set *c)
struct cached_dev *dc, *t;
struct cache *ca;
struct closure cl;
- unsigned i;
+ unsigned int i;
closure_init_stack(&cl);
@@ -1804,7 +1824,9 @@ static void run_cache_set(struct cache_set *c)
goto err;
err = "error reading btree root";
- c->root = bch_btree_node_get(c, NULL, k, j->btree_level, true, NULL);
+ c->root = bch_btree_node_get(c, NULL, k,
+ j->btree_level,
+ true, NULL);
if (IS_ERR_OR_NULL(c->root))
goto err;
@@ -1853,7 +1875,7 @@ static void run_cache_set(struct cache_set *c)
pr_notice("invalidating existing data");
for_each_cache(ca, c, i) {
- unsigned j;
+ unsigned int j;
ca->sb.keys = clamp_t(int, ca->sb.nbuckets >> 7,
2, SB_JOURNAL_BUCKETS);
@@ -1998,7 +2020,7 @@ err:
void bch_cache_release(struct kobject *kobj)
{
struct cache *ca = container_of(kobj, struct cache, kobj);
- unsigned i;
+ unsigned int i;
if (ca->set) {
BUG_ON(ca->set->cache[ca->sb.nr_this_dev] != ca);
@@ -2030,6 +2052,8 @@ static int cache_alloc(struct cache *ca)
size_t free;
size_t btree_buckets;
struct bucket *b;
+ int ret = -ENOMEM;
+ const char *err = NULL;
__module_get(THIS_MODULE);
kobject_init(&ca->kobj, &bch_cache_ktype);
@@ -2047,27 +2071,93 @@ static int cache_alloc(struct cache *ca)
*/
btree_buckets = ca->sb.njournal_buckets ?: 8;
free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
+ if (!free) {
+ ret = -EPERM;
+ err = "ca->sb.nbuckets is too small";
+ goto err_free;
+ }
- if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets, GFP_KERNEL) ||
- !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
- !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
- !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
- !init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) ||
- !init_heap(&ca->heap, free << 3, GFP_KERNEL) ||
- !(ca->buckets = vzalloc(array_size(sizeof(struct bucket),
- ca->sb.nbuckets))) ||
- !(ca->prio_buckets = kzalloc(array3_size(sizeof(uint64_t),
- prio_buckets(ca), 2),
- GFP_KERNEL)) ||
- !(ca->disk_buckets = alloc_bucket_pages(GFP_KERNEL, ca)))
- return -ENOMEM;
+ if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets,
+ GFP_KERNEL)) {
+ err = "ca->free[RESERVE_BTREE] alloc failed";
+ goto err_btree_alloc;
+ }
+
+ if (!init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca),
+ GFP_KERNEL)) {
+ err = "ca->free[RESERVE_PRIO] alloc failed";
+ goto err_prio_alloc;
+ }
+
+ if (!init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL)) {
+ err = "ca->free[RESERVE_MOVINGGC] alloc failed";
+ goto err_movinggc_alloc;
+ }
+
+ if (!init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL)) {
+ err = "ca->free[RESERVE_NONE] alloc failed";
+ goto err_none_alloc;
+ }
+
+ if (!init_fifo(&ca->free_inc, free << 2, GFP_KERNEL)) {
+ err = "ca->free_inc alloc failed";
+ goto err_free_inc_alloc;
+ }
+
+ if (!init_heap(&ca->heap, free << 3, GFP_KERNEL)) {
+ err = "ca->heap alloc failed";
+ goto err_heap_alloc;
+ }
+
+ ca->buckets = vzalloc(array_size(sizeof(struct bucket),
+ ca->sb.nbuckets));
+ if (!ca->buckets) {
+ err = "ca->buckets alloc failed";
+ goto err_buckets_alloc;
+ }
+
+ ca->prio_buckets = kzalloc(array3_size(sizeof(uint64_t),
+ prio_buckets(ca), 2),
+ GFP_KERNEL);
+ if (!ca->prio_buckets) {
+ err = "ca->prio_buckets alloc failed";
+ goto err_prio_buckets_alloc;
+ }
+
+ ca->disk_buckets = alloc_bucket_pages(GFP_KERNEL, ca);
+ if (!ca->disk_buckets) {
+ err = "ca->disk_buckets alloc failed";
+ goto err_disk_buckets_alloc;
+ }
ca->prio_last_buckets = ca->prio_buckets + prio_buckets(ca);
for_each_bucket(b, ca)
atomic_set(&b->pin, 0);
-
return 0;
+
+err_disk_buckets_alloc:
+ kfree(ca->prio_buckets);
+err_prio_buckets_alloc:
+ vfree(ca->buckets);
+err_buckets_alloc:
+ free_heap(&ca->heap);
+err_heap_alloc:
+ free_fifo(&ca->free_inc);
+err_free_inc_alloc:
+ free_fifo(&ca->free[RESERVE_NONE]);
+err_none_alloc:
+ free_fifo(&ca->free[RESERVE_MOVINGGC]);
+err_movinggc_alloc:
+ free_fifo(&ca->free[RESERVE_PRIO]);
+err_prio_alloc:
+ free_fifo(&ca->free[RESERVE_BTREE]);
+err_btree_alloc:
+err_free:
+ module_put(THIS_MODULE);
+ if (err)
+ pr_notice("error %s: %s", ca->cache_dev_name, err);
+ return ret;
}
static int register_cache(struct cache_sb *sb, struct page *sb_page,
@@ -2093,12 +2183,16 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
if (ret == -ENOMEM)
err = "cache_alloc(): -ENOMEM";
+ else if (ret == -EPERM)
+ err = "cache_alloc(): cache device is too small";
else
err = "cache_alloc(): unknown error";
goto err;
}
- if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) {
+ if (kobject_add(&ca->kobj,
+ &part_to_dev(bdev->bd_part)->kobj,
+ "bcache")) {
err = "error calling kobject_add";
ret = -ENOMEM;
goto out;
@@ -2127,13 +2221,14 @@ err:
/* Global interfaces/init */
-static ssize_t register_bcache(struct kobject *, struct kobj_attribute *,
- const char *, size_t);
+static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
+ const char *buffer, size_t size);
kobj_attribute_write(register, register_bcache);
kobj_attribute_write(register_quiet, register_bcache);
-static bool bch_is_open_backing(struct block_device *bdev) {
+static bool bch_is_open_backing(struct block_device *bdev)
+{
struct cache_set *c, *tc;
struct cached_dev *dc, *t;
@@ -2147,10 +2242,11 @@ static bool bch_is_open_backing(struct block_device *bdev) {
return false;
}
-static bool bch_is_open_cache(struct block_device *bdev) {
+static bool bch_is_open_cache(struct block_device *bdev)
+{
struct cache_set *c, *tc;
struct cache *ca;
- unsigned i;
+ unsigned int i;
list_for_each_entry_safe(c, tc, &bch_cache_sets, list)
for_each_cache(ca, c, i)
@@ -2159,7 +2255,8 @@ static bool bch_is_open_cache(struct block_device *bdev) {
return false;
}
-static bool bch_is_open(struct block_device *bdev) {
+static bool bch_is_open(struct block_device *bdev)
+{
return bch_is_open_cache(bdev) || bch_is_open_backing(bdev);
}
@@ -2216,6 +2313,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
err = "failed to register device";
if (SB_IS_BDEV(sb)) {
struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
+
if (!dc)
goto err_close;
@@ -2224,6 +2322,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
mutex_unlock(&bch_register_lock);
} else {
struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+
if (!ca)
goto err_close;
@@ -2316,6 +2415,9 @@ static void bcache_exit(void)
kobject_put(bcache_kobj);
if (bcache_wq)
destroy_workqueue(bcache_wq);
+ if (bch_journal_wq)
+ destroy_workqueue(bch_journal_wq);
+
if (bcache_major)
unregister_blkdev(bcache_major, "bcache");
unregister_reboot_notifier(&reboot);
@@ -2345,6 +2447,10 @@ static int __init bcache_init(void)
if (!bcache_wq)
goto err;
+ bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0);
+ if (!bch_journal_wq)
+ goto err;
+
bcache_kobj = kobject_create_and_add("bcache", fs_kobj);
if (!bcache_kobj)
goto err;
@@ -2353,7 +2459,7 @@ static int __init bcache_init(void)
sysfs_create_files(bcache_kobj, files))
goto err;
- bch_debug_init(bcache_kobj);
+ bch_debug_init();
closure_debug_init();
return 0;
OpenPOWER on IntegriCloud