2013-03-23 17:11:31 -06:00
|
|
|
/*
|
|
|
|
* bcache setup/teardown code, and some metadata io - read a superblock and
|
|
|
|
* figure out what to do with it.
|
|
|
|
*
|
|
|
|
* Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
|
|
|
|
* Copyright 2012 Google, Inc.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "bcache.h"
|
|
|
|
#include "btree.h"
|
|
|
|
#include "debug.h"
|
2013-12-20 18:22:05 -07:00
|
|
|
#include "extents.h"
|
2013-03-23 17:11:31 -06:00
|
|
|
#include "request.h"
|
2013-06-05 07:21:07 -06:00
|
|
|
#include "writeback.h"
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-26 16:39:55 -06:00
|
|
|
#include <linux/blkdev.h>
|
2013-03-23 17:11:31 -06:00
|
|
|
#include <linux/buffer_head.h>
|
|
|
|
#include <linux/debugfs.h>
|
|
|
|
#include <linux/genhd.h>
|
2013-07-31 02:12:02 -06:00
|
|
|
#include <linux/idr.h>
|
2013-07-10 19:31:58 -06:00
|
|
|
#include <linux/kthread.h>
|
2013-03-23 17:11:31 -06:00
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/random.h>
|
|
|
|
#include <linux/reboot.h>
|
|
|
|
#include <linux/sysfs.h>
|
|
|
|
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
MODULE_AUTHOR("Kent Overstreet <kent.overstreet@gmail.com>");
|
|
|
|
|
|
|
|
static const char bcache_magic[] = {
|
|
|
|
0xc6, 0x85, 0x73, 0xf6, 0x4e, 0x1a, 0x45, 0xca,
|
|
|
|
0x82, 0x65, 0xf5, 0x7f, 0x48, 0xba, 0x6d, 0x81
|
|
|
|
};
|
|
|
|
|
|
|
|
static const char invalid_uuid[] = {
|
|
|
|
0xa0, 0x3e, 0xf8, 0xed, 0x3e, 0xe1, 0xb8, 0x78,
|
|
|
|
0xc8, 0x50, 0xfc, 0x5e, 0xcb, 0x16, 0xcd, 0x99
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Default is -1; we skip past it for struct cached_dev's cache mode */
|
|
|
|
const char * const bch_cache_modes[] = {
|
|
|
|
"default",
|
|
|
|
"writethrough",
|
|
|
|
"writeback",
|
|
|
|
"writearound",
|
|
|
|
"none",
|
|
|
|
NULL
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct kobject *bcache_kobj;
|
|
|
|
struct mutex bch_register_lock;
|
|
|
|
LIST_HEAD(bch_cache_sets);
|
|
|
|
static LIST_HEAD(uncached_devices);
|
|
|
|
|
2013-07-31 02:12:02 -06:00
|
|
|
static int bcache_major;
|
|
|
|
static DEFINE_IDA(bcache_minor);
|
2013-03-23 17:11:31 -06:00
|
|
|
static wait_queue_head_t unregister_wait;
|
|
|
|
struct workqueue_struct *bcache_wq;
|
|
|
|
|
|
|
|
#define BTREE_MAX_PAGES (256 * 1024 / PAGE_SIZE)
|
|
|
|
|
|
|
|
/* Superblock */
|
|
|
|
|
|
|
|
static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
|
|
|
|
struct page **res)
|
|
|
|
{
|
|
|
|
const char *err;
|
|
|
|
struct cache_sb *s;
|
|
|
|
struct buffer_head *bh = __bread(bdev, 1, SB_SIZE);
|
|
|
|
unsigned i;
|
|
|
|
|
|
|
|
if (!bh)
|
|
|
|
return "IO error";
|
|
|
|
|
|
|
|
s = (struct cache_sb *) bh->b_data;
|
|
|
|
|
|
|
|
sb->offset = le64_to_cpu(s->offset);
|
|
|
|
sb->version = le64_to_cpu(s->version);
|
|
|
|
|
|
|
|
memcpy(sb->magic, s->magic, 16);
|
|
|
|
memcpy(sb->uuid, s->uuid, 16);
|
|
|
|
memcpy(sb->set_uuid, s->set_uuid, 16);
|
|
|
|
memcpy(sb->label, s->label, SB_LABEL_SIZE);
|
|
|
|
|
|
|
|
sb->flags = le64_to_cpu(s->flags);
|
|
|
|
sb->seq = le64_to_cpu(s->seq);
|
|
|
|
sb->last_mount = le32_to_cpu(s->last_mount);
|
|
|
|
sb->first_bucket = le16_to_cpu(s->first_bucket);
|
|
|
|
sb->keys = le16_to_cpu(s->keys);
|
|
|
|
|
|
|
|
for (i = 0; i < SB_JOURNAL_BUCKETS; i++)
|
|
|
|
sb->d[i] = le64_to_cpu(s->d[i]);
|
|
|
|
|
|
|
|
pr_debug("read sb version %llu, flags %llu, seq %llu, journal size %u",
|
|
|
|
sb->version, sb->flags, sb->seq, sb->keys);
|
|
|
|
|
|
|
|
err = "Not a bcache superblock";
|
|
|
|
if (sb->offset != SB_SECTOR)
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
if (memcmp(sb->magic, bcache_magic, 16))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
err = "Too many journal buckets";
|
|
|
|
if (sb->keys > SB_JOURNAL_BUCKETS)
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
err = "Bad checksum";
|
|
|
|
if (s->csum != csum_set(s))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
err = "Bad UUID";
|
2013-03-28 12:50:55 -06:00
|
|
|
if (bch_is_zero(sb->uuid, 16))
|
2013-03-23 17:11:31 -06:00
|
|
|
goto err;
|
|
|
|
|
2013-04-23 22:51:48 -06:00
|
|
|
sb->block_size = le16_to_cpu(s->block_size);
|
|
|
|
|
|
|
|
err = "Superblock block size smaller than device block size";
|
|
|
|
if (sb->block_size << 9 < bdev_logical_block_size(bdev))
|
|
|
|
goto err;
|
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
switch (sb->version) {
|
|
|
|
case BCACHE_SB_VERSION_BDEV:
|
|
|
|
sb->data_offset = BDEV_DATA_START_DEFAULT;
|
|
|
|
break;
|
|
|
|
case BCACHE_SB_VERSION_BDEV_WITH_OFFSET:
|
|
|
|
sb->data_offset = le64_to_cpu(s->data_offset);
|
|
|
|
|
|
|
|
err = "Bad data offset";
|
|
|
|
if (sb->data_offset < BDEV_DATA_START_DEFAULT)
|
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
break;
|
|
|
|
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);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
sb->nr_in_set = le16_to_cpu(s->nr_in_set);
|
|
|
|
sb->nr_this_dev = le16_to_cpu(s->nr_this_dev);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
err = "Too many buckets";
|
|
|
|
if (sb->nbuckets > LONG_MAX)
|
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
err = "Not enough buckets";
|
|
|
|
if (sb->nbuckets < 1 << 7)
|
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
err = "Bad block/bucket size";
|
|
|
|
if (!is_power_of_2(sb->block_size) ||
|
|
|
|
sb->block_size > PAGE_SECTORS ||
|
|
|
|
!is_power_of_2(sb->bucket_size) ||
|
|
|
|
sb->bucket_size < PAGE_SECTORS)
|
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
err = "Invalid superblock: device too small";
|
|
|
|
if (get_capacity(bdev->bd_disk) < sb->bucket_size * sb->nbuckets)
|
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
err = "Bad UUID";
|
|
|
|
if (bch_is_zero(sb->set_uuid, 16))
|
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
err = "Bad cache device number in set";
|
|
|
|
if (!sb->nr_in_set ||
|
|
|
|
sb->nr_in_set <= sb->nr_this_dev ||
|
|
|
|
sb->nr_in_set > MAX_CACHES_PER_SET)
|
2013-03-23 17:11:31 -06:00
|
|
|
goto err;
|
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
err = "Journal buckets not sequential";
|
|
|
|
for (i = 0; i < sb->keys; i++)
|
|
|
|
if (sb->d[i] != sb->first_bucket + i)
|
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
err = "Too many journal buckets";
|
|
|
|
if (sb->first_bucket + sb->keys > sb->nbuckets)
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
err = "Invalid superblock: first bucket comes before end of super";
|
|
|
|
if (sb->first_bucket * sb->bucket_size < 16)
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
err = "Unsupported superblock version";
|
2013-03-23 17:11:31 -06:00
|
|
|
goto err;
|
2013-04-11 16:14:35 -06:00
|
|
|
}
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
sb->last_mount = get_seconds();
|
|
|
|
err = NULL;
|
|
|
|
|
|
|
|
get_page(bh->b_page);
|
|
|
|
*res = bh->b_page;
|
|
|
|
err:
|
|
|
|
put_bh(bh);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2015-07-20 07:29:37 -06:00
|
|
|
static void write_bdev_super_endio(struct bio *bio)
|
2013-03-23 17:11:31 -06:00
|
|
|
{
|
|
|
|
struct cached_dev *dc = bio->bi_private;
|
|
|
|
/* XXX: error checking */
|
|
|
|
|
2013-12-16 16:27:25 -07:00
|
|
|
closure_put(&dc->sb_write);
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
static void __write_super(struct cache_sb *sb, struct bio *bio)
|
|
|
|
{
|
|
|
|
struct cache_sb *out = page_address(bio->bi_io_vec[0].bv_page);
|
|
|
|
unsigned i;
|
|
|
|
|
2013-10-11 16:44:27 -06:00
|
|
|
bio->bi_iter.bi_sector = SB_SECTOR;
|
|
|
|
bio->bi_rw = REQ_SYNC|REQ_META;
|
|
|
|
bio->bi_iter.bi_size = SB_SIZE;
|
2013-03-28 12:50:55 -06:00
|
|
|
bch_bio_map(bio, NULL);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
out->offset = cpu_to_le64(sb->offset);
|
|
|
|
out->version = cpu_to_le64(sb->version);
|
|
|
|
|
|
|
|
memcpy(out->uuid, sb->uuid, 16);
|
|
|
|
memcpy(out->set_uuid, sb->set_uuid, 16);
|
|
|
|
memcpy(out->label, sb->label, SB_LABEL_SIZE);
|
|
|
|
|
|
|
|
out->flags = cpu_to_le64(sb->flags);
|
|
|
|
out->seq = cpu_to_le64(sb->seq);
|
|
|
|
|
|
|
|
out->last_mount = cpu_to_le32(sb->last_mount);
|
|
|
|
out->first_bucket = cpu_to_le16(sb->first_bucket);
|
|
|
|
out->keys = cpu_to_le16(sb->keys);
|
|
|
|
|
|
|
|
for (i = 0; i < sb->keys; i++)
|
|
|
|
out->d[i] = cpu_to_le64(sb->d[i]);
|
|
|
|
|
|
|
|
out->csum = csum_set(out);
|
|
|
|
|
|
|
|
pr_debug("ver %llu, flags %llu, seq %llu",
|
|
|
|
sb->version, sb->flags, sb->seq);
|
|
|
|
|
|
|
|
submit_bio(REQ_WRITE, bio);
|
|
|
|
}
|
|
|
|
|
2013-12-16 16:27:25 -07:00
|
|
|
static void bch_write_bdev_super_unlock(struct closure *cl)
|
|
|
|
{
|
|
|
|
struct cached_dev *dc = container_of(cl, struct cached_dev, sb_write);
|
|
|
|
|
|
|
|
up(&dc->sb_write_mutex);
|
|
|
|
}
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent)
|
|
|
|
{
|
2013-12-16 16:27:25 -07:00
|
|
|
struct closure *cl = &dc->sb_write;
|
2013-03-23 17:11:31 -06:00
|
|
|
struct bio *bio = &dc->sb_bio;
|
|
|
|
|
2013-12-16 16:27:25 -07:00
|
|
|
down(&dc->sb_write_mutex);
|
|
|
|
closure_init(cl, parent);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
bio_reset(bio);
|
|
|
|
bio->bi_bdev = dc->bdev;
|
|
|
|
bio->bi_end_io = write_bdev_super_endio;
|
|
|
|
bio->bi_private = dc;
|
|
|
|
|
|
|
|
closure_get(cl);
|
|
|
|
__write_super(&dc->sb, bio);
|
|
|
|
|
2013-12-16 16:27:25 -07:00
|
|
|
closure_return_with_destructor(cl, bch_write_bdev_super_unlock);
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
2015-07-20 07:29:37 -06:00
|
|
|
static void write_super_endio(struct bio *bio)
|
2013-03-23 17:11:31 -06:00
|
|
|
{
|
|
|
|
struct cache *ca = bio->bi_private;
|
|
|
|
|
2015-07-20 07:29:37 -06:00
|
|
|
bch_count_io_errors(ca, bio->bi_error, "writing superblock");
|
2013-12-16 16:27:25 -07:00
|
|
|
closure_put(&ca->set->sb_write);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void bcache_write_super_unlock(struct closure *cl)
|
|
|
|
{
|
|
|
|
struct cache_set *c = container_of(cl, struct cache_set, sb_write);
|
|
|
|
|
|
|
|
up(&c->sb_write_mutex);
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
void bcache_write_super(struct cache_set *c)
|
|
|
|
{
|
2013-12-16 16:27:25 -07:00
|
|
|
struct closure *cl = &c->sb_write;
|
2013-03-23 17:11:31 -06:00
|
|
|
struct cache *ca;
|
|
|
|
unsigned i;
|
|
|
|
|
2013-12-16 16:27:25 -07:00
|
|
|
down(&c->sb_write_mutex);
|
|
|
|
closure_init(cl, &c->cl);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
c->sb.seq++;
|
|
|
|
|
|
|
|
for_each_cache(ca, c, i) {
|
|
|
|
struct bio *bio = &ca->sb_bio;
|
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
ca->sb.version = BCACHE_SB_VERSION_CDEV_WITH_UUID;
|
2013-03-23 17:11:31 -06:00
|
|
|
ca->sb.seq = c->sb.seq;
|
|
|
|
ca->sb.last_mount = c->sb.last_mount;
|
|
|
|
|
|
|
|
SET_CACHE_SYNC(&ca->sb, CACHE_SYNC(&c->sb));
|
|
|
|
|
|
|
|
bio_reset(bio);
|
|
|
|
bio->bi_bdev = ca->bdev;
|
|
|
|
bio->bi_end_io = write_super_endio;
|
|
|
|
bio->bi_private = ca;
|
|
|
|
|
|
|
|
closure_get(cl);
|
|
|
|
__write_super(&ca->sb, bio);
|
|
|
|
}
|
|
|
|
|
2013-12-16 16:27:25 -07:00
|
|
|
closure_return_with_destructor(cl, bcache_write_super_unlock);
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
/* UUID io */
|
|
|
|
|
2015-07-20 07:29:37 -06:00
|
|
|
static void uuid_endio(struct bio *bio)
|
2013-03-23 17:11:31 -06:00
|
|
|
{
|
|
|
|
struct closure *cl = bio->bi_private;
|
2013-12-16 16:27:25 -07:00
|
|
|
struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2015-07-20 07:29:37 -06:00
|
|
|
cache_set_err_on(bio->bi_error, c, "accessing uuids");
|
2013-03-23 17:11:31 -06:00
|
|
|
bch_bbio_free(bio, c);
|
|
|
|
closure_put(cl);
|
|
|
|
}
|
|
|
|
|
2013-12-16 16:27:25 -07:00
|
|
|
static void uuid_io_unlock(struct closure *cl)
|
|
|
|
{
|
|
|
|
struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
|
|
|
|
|
|
|
|
up(&c->uuid_write_mutex);
|
|
|
|
}
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
static void uuid_io(struct cache_set *c, unsigned long rw,
|
|
|
|
struct bkey *k, struct closure *parent)
|
|
|
|
{
|
2013-12-16 16:27:25 -07:00
|
|
|
struct closure *cl = &c->uuid_write;
|
2013-03-23 17:11:31 -06:00
|
|
|
struct uuid_entry *u;
|
|
|
|
unsigned i;
|
2013-05-14 21:33:16 -06:00
|
|
|
char buf[80];
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
BUG_ON(!parent);
|
2013-12-16 16:27:25 -07:00
|
|
|
down(&c->uuid_write_mutex);
|
|
|
|
closure_init(cl, parent);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
for (i = 0; i < KEY_PTRS(k); i++) {
|
|
|
|
struct bio *bio = bch_bbio_alloc(c);
|
|
|
|
|
|
|
|
bio->bi_rw = REQ_SYNC|REQ_META|rw;
|
2013-10-11 16:44:27 -06:00
|
|
|
bio->bi_iter.bi_size = KEY_SIZE(k) << 9;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
bio->bi_end_io = uuid_endio;
|
|
|
|
bio->bi_private = cl;
|
2013-03-28 12:50:55 -06:00
|
|
|
bch_bio_map(bio, c->uuids);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
bch_submit_bbio(bio, c, k, i);
|
|
|
|
|
|
|
|
if (!(rw & WRITE))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2013-12-18 00:47:33 -07:00
|
|
|
bch_extent_to_text(buf, sizeof(buf), k);
|
2013-05-14 21:33:16 -06:00
|
|
|
pr_debug("%s UUIDs at %s", rw & REQ_WRITE ? "wrote" : "read", buf);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
for (u = c->uuids; u < c->uuids + c->nr_uuids; u++)
|
2013-03-28 12:50:55 -06:00
|
|
|
if (!bch_is_zero(u->uuid, 16))
|
2013-03-23 17:11:31 -06:00
|
|
|
pr_debug("Slot %zi: %pU: %s: 1st: %u last: %u inv: %u",
|
|
|
|
u - c->uuids, u->uuid, u->label,
|
|
|
|
u->first_reg, u->last_reg, u->invalidated);
|
|
|
|
|
2013-12-16 16:27:25 -07:00
|
|
|
closure_return_with_destructor(cl, uuid_io_unlock);
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
static char *uuid_read(struct cache_set *c, struct jset *j, struct closure *cl)
|
|
|
|
{
|
|
|
|
struct bkey *k = &j->uuid_bucket;
|
|
|
|
|
2013-12-20 18:22:05 -07:00
|
|
|
if (__bch_btree_ptr_invalid(c, k))
|
2013-03-23 17:11:31 -06:00
|
|
|
return "bad uuid pointer";
|
|
|
|
|
|
|
|
bkey_copy(&c->uuid_bucket, k);
|
|
|
|
uuid_io(c, READ_SYNC, k, cl);
|
|
|
|
|
|
|
|
if (j->version < BCACHE_JSET_VERSION_UUIDv1) {
|
|
|
|
struct uuid_entry_v0 *u0 = (void *) c->uuids;
|
|
|
|
struct uuid_entry *u1 = (void *) c->uuids;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
closure_sync(cl);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Since the new uuid entry is bigger than the old, we have to
|
|
|
|
* convert starting at the highest memory address and work down
|
|
|
|
* in order to do it in place
|
|
|
|
*/
|
|
|
|
|
|
|
|
for (i = c->nr_uuids - 1;
|
|
|
|
i >= 0;
|
|
|
|
--i) {
|
|
|
|
memcpy(u1[i].uuid, u0[i].uuid, 16);
|
|
|
|
memcpy(u1[i].label, u0[i].label, 32);
|
|
|
|
|
|
|
|
u1[i].first_reg = u0[i].first_reg;
|
|
|
|
u1[i].last_reg = u0[i].last_reg;
|
|
|
|
u1[i].invalidated = u0[i].invalidated;
|
|
|
|
|
|
|
|
u1[i].flags = 0;
|
|
|
|
u1[i].sectors = 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __uuid_write(struct cache_set *c)
|
|
|
|
{
|
|
|
|
BKEY_PADDED(key) k;
|
|
|
|
struct closure cl;
|
|
|
|
closure_init_stack(&cl);
|
|
|
|
|
|
|
|
lockdep_assert_held(&bch_register_lock);
|
|
|
|
|
2013-12-17 02:29:34 -07:00
|
|
|
if (bch_bucket_alloc_set(c, RESERVE_BTREE, &k.key, 1, true))
|
2013-03-23 17:11:31 -06:00
|
|
|
return 1;
|
|
|
|
|
|
|
|
SET_KEY_SIZE(&k.key, c->sb.bucket_size);
|
|
|
|
uuid_io(c, REQ_WRITE, &k.key, &cl);
|
|
|
|
closure_sync(&cl);
|
|
|
|
|
|
|
|
bkey_copy(&c->uuid_bucket, &k.key);
|
2013-07-24 17:46:42 -06:00
|
|
|
bkey_put(c, &k.key);
|
2013-03-23 17:11:31 -06:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int bch_uuid_write(struct cache_set *c)
|
|
|
|
{
|
|
|
|
int ret = __uuid_write(c);
|
|
|
|
|
|
|
|
if (!ret)
|
|
|
|
bch_journal_meta(c, NULL);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct uuid_entry *uuid_find(struct cache_set *c, const char *uuid)
|
|
|
|
{
|
|
|
|
struct uuid_entry *u;
|
|
|
|
|
|
|
|
for (u = c->uuids;
|
|
|
|
u < c->uuids + c->nr_uuids; u++)
|
|
|
|
if (!memcmp(u->uuid, uuid, 16))
|
|
|
|
return u;
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Bucket priorities/gens:
|
|
|
|
*
|
|
|
|
* For each bucket, we store on disk its
|
|
|
|
* 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
|
|
|
|
* it's just an opaque integer.
|
|
|
|
*
|
|
|
|
* The gens and the priorities don't have a whole lot to do with each other, and
|
|
|
|
* it's actually the gens that must be written out at specific times - it's no
|
|
|
|
* big deal if the priorities don't get written, if we lose them we just reuse
|
|
|
|
* buckets in suboptimal order.
|
|
|
|
*
|
|
|
|
* On disk they're stored in a packed array, and in as many buckets are required
|
|
|
|
* to fit them all. The buckets we use to store them form a list; the journal
|
|
|
|
* header points to the first bucket, the first bucket points to the second
|
|
|
|
* bucket, et cetera.
|
|
|
|
*
|
|
|
|
* This code is used by the allocation code; periodically (whenever it runs out
|
|
|
|
* of buckets to allocate from) the allocation code will invalidate some
|
|
|
|
* buckets, but it can't use those buckets until their new gens are safely on
|
|
|
|
* disk.
|
|
|
|
*/
|
|
|
|
|
2015-07-20 07:29:37 -06:00
|
|
|
static void prio_endio(struct bio *bio)
|
2013-03-23 17:11:31 -06:00
|
|
|
{
|
|
|
|
struct cache *ca = bio->bi_private;
|
|
|
|
|
2015-07-20 07:29:37 -06:00
|
|
|
cache_set_err_on(bio->bi_error, ca->set, "accessing priorities");
|
2013-03-23 17:11:31 -06:00
|
|
|
bch_bbio_free(bio, ca->set);
|
|
|
|
closure_put(&ca->prio);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void prio_io(struct cache *ca, uint64_t bucket, unsigned long rw)
|
|
|
|
{
|
|
|
|
struct closure *cl = &ca->prio;
|
|
|
|
struct bio *bio = bch_bbio_alloc(ca->set);
|
|
|
|
|
|
|
|
closure_init_stack(cl);
|
|
|
|
|
2013-10-11 16:44:27 -06:00
|
|
|
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);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
bio->bi_end_io = prio_endio;
|
|
|
|
bio->bi_private = ca;
|
2013-03-28 12:50:55 -06:00
|
|
|
bch_bio_map(bio, ca->disk_buckets);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-11-24 00:11:25 -07:00
|
|
|
closure_bio_submit(bio, &ca->prio);
|
2013-03-23 17:11:31 -06:00
|
|
|
closure_sync(cl);
|
|
|
|
}
|
|
|
|
|
|
|
|
void bch_prio_write(struct cache *ca)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
struct bucket *b;
|
|
|
|
struct closure cl;
|
|
|
|
|
|
|
|
closure_init_stack(&cl);
|
|
|
|
|
|
|
|
lockdep_assert_held(&ca->set->bucket_lock);
|
|
|
|
|
|
|
|
ca->disk_buckets->seq++;
|
|
|
|
|
|
|
|
atomic_long_add(ca->sb.bucket_size * prio_buckets(ca),
|
|
|
|
&ca->meta_sectors_written);
|
|
|
|
|
2013-12-17 02:29:34 -07:00
|
|
|
//pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free),
|
|
|
|
// fifo_used(&ca->free_inc), fifo_used(&ca->unused));
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
for (i = prio_buckets(ca) - 1; i >= 0; --i) {
|
|
|
|
long bucket;
|
|
|
|
struct prio_set *p = ca->disk_buckets;
|
2013-03-25 12:46:44 -06:00
|
|
|
struct bucket_disk *d = p->data;
|
|
|
|
struct bucket_disk *end = d + prios_per_bucket(ca);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
for (b = ca->buckets + i * prios_per_bucket(ca);
|
|
|
|
b < ca->buckets + ca->sb.nbuckets && d < end;
|
|
|
|
b++, d++) {
|
|
|
|
d->prio = cpu_to_le16(b->prio);
|
|
|
|
d->gen = b->gen;
|
|
|
|
}
|
|
|
|
|
|
|
|
p->next_bucket = ca->prio_buckets[i + 1];
|
2013-10-31 16:46:42 -06:00
|
|
|
p->magic = pset_magic(&ca->sb);
|
2013-03-28 12:50:55 -06:00
|
|
|
p->csum = bch_crc64(&p->magic, bucket_bytes(ca) - 8);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-12-17 02:29:34 -07:00
|
|
|
bucket = bch_bucket_alloc(ca, RESERVE_PRIO, true);
|
2013-03-23 17:11:31 -06:00
|
|
|
BUG_ON(bucket == -1);
|
|
|
|
|
|
|
|
mutex_unlock(&ca->set->bucket_lock);
|
|
|
|
prio_io(ca, bucket, REQ_WRITE);
|
|
|
|
mutex_lock(&ca->set->bucket_lock);
|
|
|
|
|
|
|
|
ca->prio_buckets[i] = bucket;
|
|
|
|
atomic_dec_bug(&ca->buckets[bucket].pin);
|
|
|
|
}
|
|
|
|
|
|
|
|
mutex_unlock(&ca->set->bucket_lock);
|
|
|
|
|
|
|
|
bch_journal_meta(ca->set, &cl);
|
|
|
|
closure_sync(&cl);
|
|
|
|
|
|
|
|
mutex_lock(&ca->set->bucket_lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Don't want the old priorities to get garbage collected until after we
|
|
|
|
* finish writing the new ones, and they're journalled
|
|
|
|
*/
|
2014-03-17 17:55:55 -06:00
|
|
|
for (i = 0; i < prio_buckets(ca); i++) {
|
|
|
|
if (ca->prio_last_buckets[i])
|
|
|
|
__bch_bucket_free(ca,
|
|
|
|
&ca->buckets[ca->prio_last_buckets[i]]);
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
ca->prio_last_buckets[i] = ca->prio_buckets[i];
|
2014-03-17 17:55:55 -06:00
|
|
|
}
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
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;
|
|
|
|
|
|
|
|
for (b = ca->buckets;
|
|
|
|
b < ca->buckets + ca->sb.nbuckets;
|
|
|
|
b++, d++) {
|
|
|
|
if (d == end) {
|
|
|
|
ca->prio_buckets[bucket_nr] = bucket;
|
|
|
|
ca->prio_last_buckets[bucket_nr] = bucket;
|
|
|
|
bucket_nr++;
|
|
|
|
|
|
|
|
prio_io(ca, bucket, READ_SYNC);
|
|
|
|
|
2013-03-28 12:50:55 -06:00
|
|
|
if (p->csum != bch_crc64(&p->magic, bucket_bytes(ca) - 8))
|
2013-03-23 17:11:31 -06:00
|
|
|
pr_warn("bad csum reading priorities");
|
|
|
|
|
2013-10-31 16:46:42 -06:00
|
|
|
if (p->magic != pset_magic(&ca->sb))
|
2013-03-23 17:11:31 -06:00
|
|
|
pr_warn("bad magic reading priorities");
|
|
|
|
|
|
|
|
bucket = p->next_bucket;
|
|
|
|
d = p->data;
|
|
|
|
}
|
|
|
|
|
|
|
|
b->prio = le16_to_cpu(d->prio);
|
2014-02-27 18:51:12 -07:00
|
|
|
b->gen = b->last_gc = d->gen;
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Bcache device */
|
|
|
|
|
|
|
|
static int open_dev(struct block_device *b, fmode_t mode)
|
|
|
|
{
|
|
|
|
struct bcache_device *d = b->bd_disk->private_data;
|
2013-08-21 18:49:09 -06:00
|
|
|
if (test_bit(BCACHE_DEV_CLOSING, &d->flags))
|
2013-03-23 17:11:31 -06:00
|
|
|
return -ENXIO;
|
|
|
|
|
|
|
|
closure_get(&d->cl);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-05-09 14:39:26 -06:00
|
|
|
static void release_dev(struct gendisk *b, fmode_t mode)
|
2013-03-23 17:11:31 -06:00
|
|
|
{
|
|
|
|
struct bcache_device *d = b->private_data;
|
|
|
|
closure_put(&d->cl);
|
|
|
|
}
|
|
|
|
|
|
|
|
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;
|
|
|
|
return d->ioctl(d, mode, cmd, arg);
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct block_device_operations bcache_ops = {
|
|
|
|
.open = open_dev,
|
|
|
|
.release = release_dev,
|
|
|
|
.ioctl = ioctl_dev,
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
};
|
|
|
|
|
|
|
|
void bcache_device_stop(struct bcache_device *d)
|
|
|
|
{
|
2013-08-21 18:49:09 -06:00
|
|
|
if (!test_and_set_bit(BCACHE_DEV_CLOSING, &d->flags))
|
2013-03-23 17:11:31 -06:00
|
|
|
closure_queue(&d->cl);
|
|
|
|
}
|
|
|
|
|
2013-02-01 08:29:41 -07:00
|
|
|
static void bcache_device_unlink(struct bcache_device *d)
|
|
|
|
{
|
2013-08-21 18:49:09 -06:00
|
|
|
lockdep_assert_held(&bch_register_lock);
|
2013-02-01 08:29:41 -07:00
|
|
|
|
2013-08-21 18:49:09 -06:00
|
|
|
if (d->c && !test_and_set_bit(BCACHE_DEV_UNLINK_DONE, &d->flags)) {
|
|
|
|
unsigned i;
|
|
|
|
struct cache *ca;
|
2013-02-01 08:29:41 -07:00
|
|
|
|
2013-08-21 18:49:09 -06:00
|
|
|
sysfs_remove_link(&d->c->kobj, d->name);
|
|
|
|
sysfs_remove_link(&d->kobj, "cache");
|
|
|
|
|
|
|
|
for_each_cache(ca, d->c, i)
|
|
|
|
bd_unlink_disk_holder(ca->bdev, d->disk);
|
|
|
|
}
|
2013-02-01 08:29:41 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
static void bcache_device_link(struct bcache_device *d, struct cache_set *c,
|
|
|
|
const char *name)
|
|
|
|
{
|
|
|
|
unsigned i;
|
|
|
|
struct cache *ca;
|
|
|
|
|
|
|
|
for_each_cache(ca, d->c, i)
|
|
|
|
bd_link_disk_holder(ca->bdev, d->disk);
|
|
|
|
|
|
|
|
snprintf(d->name, BCACHEDEVNAME_SIZE,
|
|
|
|
"%s%u", name, d->id);
|
|
|
|
|
|
|
|
WARN(sysfs_create_link(&d->kobj, &c->kobj, "cache") ||
|
|
|
|
sysfs_create_link(&c->kobj, &d->kobj, d->name),
|
|
|
|
"Couldn't create device <-> cache set symlinks");
|
|
|
|
}
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
static void bcache_device_detach(struct bcache_device *d)
|
|
|
|
{
|
|
|
|
lockdep_assert_held(&bch_register_lock);
|
|
|
|
|
2013-08-21 18:49:09 -06:00
|
|
|
if (test_bit(BCACHE_DEV_DETACHING, &d->flags)) {
|
2013-03-23 17:11:31 -06:00
|
|
|
struct uuid_entry *u = d->c->uuids + d->id;
|
|
|
|
|
|
|
|
SET_UUID_FLASH_ONLY(u, 0);
|
|
|
|
memcpy(u->uuid, invalid_uuid, 16);
|
|
|
|
u->invalidated = cpu_to_le32(get_seconds());
|
|
|
|
bch_uuid_write(d->c);
|
|
|
|
}
|
|
|
|
|
2013-08-21 18:49:09 -06:00
|
|
|
bcache_device_unlink(d);
|
2013-02-01 08:29:41 -07:00
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
d->c->devices[d->id] = NULL;
|
|
|
|
closure_put(&d->c->caching);
|
|
|
|
d->c = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void bcache_device_attach(struct bcache_device *d, struct cache_set *c,
|
|
|
|
unsigned id)
|
|
|
|
{
|
|
|
|
d->id = id;
|
|
|
|
d->c = c;
|
|
|
|
c->devices[id] = d;
|
|
|
|
|
|
|
|
closure_get(&c->caching);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void bcache_device_free(struct bcache_device *d)
|
|
|
|
{
|
|
|
|
lockdep_assert_held(&bch_register_lock);
|
|
|
|
|
|
|
|
pr_info("%s stopped", d->disk->disk_name);
|
|
|
|
|
|
|
|
if (d->c)
|
|
|
|
bcache_device_detach(d);
|
2013-05-15 01:11:26 -06:00
|
|
|
if (d->disk && d->disk->flags & GENHD_FL_UP)
|
2013-03-23 17:11:31 -06:00
|
|
|
del_gendisk(d->disk);
|
|
|
|
if (d->disk && d->disk->queue)
|
|
|
|
blk_cleanup_queue(d->disk->queue);
|
2013-07-31 02:12:02 -06:00
|
|
|
if (d->disk) {
|
|
|
|
ida_simple_remove(&bcache_minor, d->disk->first_minor);
|
2013-03-23 17:11:31 -06:00
|
|
|
put_disk(d->disk);
|
2013-07-31 02:12:02 -06:00
|
|
|
}
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
if (d->bio_split)
|
|
|
|
bioset_free(d->bio_split);
|
2015-06-30 15:59:30 -06:00
|
|
|
kvfree(d->full_dirty_stripes);
|
|
|
|
kvfree(d->stripe_sectors_dirty);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
closure_debug_destroy(&d->cl);
|
|
|
|
}
|
|
|
|
|
2013-06-05 07:21:07 -06:00
|
|
|
static int bcache_device_init(struct bcache_device *d, unsigned block_size,
|
|
|
|
sector_t sectors)
|
2013-03-23 17:11:31 -06:00
|
|
|
{
|
|
|
|
struct request_queue *q;
|
2013-06-05 07:21:07 -06:00
|
|
|
size_t n;
|
2013-07-31 02:12:02 -06:00
|
|
|
int minor;
|
2013-06-05 07:21:07 -06:00
|
|
|
|
2013-08-17 03:13:15 -06:00
|
|
|
if (!d->stripe_size)
|
|
|
|
d->stripe_size = 1 << 31;
|
2013-06-05 07:21:07 -06:00
|
|
|
|
2013-08-17 03:13:15 -06:00
|
|
|
d->nr_stripes = DIV_ROUND_UP_ULL(sectors, d->stripe_size);
|
2013-06-05 07:21:07 -06:00
|
|
|
|
2013-10-31 16:43:22 -06:00
|
|
|
if (!d->nr_stripes ||
|
|
|
|
d->nr_stripes > INT_MAX ||
|
|
|
|
d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) {
|
|
|
|
pr_err("nr_stripes too large");
|
2013-06-05 07:21:07 -06:00
|
|
|
return -ENOMEM;
|
2013-10-31 16:43:22 -06:00
|
|
|
}
|
2013-06-05 07:21:07 -06:00
|
|
|
|
|
|
|
n = d->nr_stripes * sizeof(atomic_t);
|
|
|
|
d->stripe_sectors_dirty = n < PAGE_SIZE << 6
|
|
|
|
? kzalloc(n, GFP_KERNEL)
|
|
|
|
: vzalloc(n);
|
|
|
|
if (!d->stripe_sectors_dirty)
|
|
|
|
return -ENOMEM;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-10-31 16:43:22 -06:00
|
|
|
n = BITS_TO_LONGS(d->nr_stripes) * sizeof(unsigned long);
|
|
|
|
d->full_dirty_stripes = n < PAGE_SIZE << 6
|
|
|
|
? kzalloc(n, GFP_KERNEL)
|
|
|
|
: vzalloc(n);
|
|
|
|
if (!d->full_dirty_stripes)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2013-07-31 02:12:02 -06:00
|
|
|
minor = ida_simple_get(&bcache_minor, 0, MINORMASK + 1, GFP_KERNEL);
|
|
|
|
if (minor < 0)
|
|
|
|
return minor;
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
|
2013-07-31 02:12:02 -06:00
|
|
|
!(d->disk = alloc_disk(1))) {
|
|
|
|
ida_simple_remove(&bcache_minor, minor);
|
2013-03-23 17:11:31 -06:00
|
|
|
return -ENOMEM;
|
2013-07-31 02:12:02 -06:00
|
|
|
}
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-06-05 07:21:07 -06:00
|
|
|
set_capacity(d->disk, sectors);
|
2013-07-31 02:12:02 -06:00
|
|
|
snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", minor);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
d->disk->major = bcache_major;
|
2013-07-31 02:12:02 -06:00
|
|
|
d->disk->first_minor = minor;
|
2013-03-23 17:11:31 -06:00
|
|
|
d->disk->fops = &bcache_ops;
|
|
|
|
d->disk->private_data = d;
|
|
|
|
|
2013-07-31 02:12:02 -06:00
|
|
|
q = blk_alloc_queue(GFP_KERNEL);
|
|
|
|
if (!q)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
blk_queue_make_request(q, NULL);
|
|
|
|
d->disk->queue = q;
|
|
|
|
q->queuedata = d;
|
|
|
|
q->backing_dev_info.congested_data = d;
|
|
|
|
q->limits.max_hw_sectors = UINT_MAX;
|
|
|
|
q->limits.max_sectors = UINT_MAX;
|
|
|
|
q->limits.max_segment_size = UINT_MAX;
|
|
|
|
q->limits.max_segments = BIO_MAX_PAGES;
|
2015-07-14 08:15:12 -06:00
|
|
|
blk_queue_max_discard_sectors(q, UINT_MAX);
|
2014-02-10 18:26:40 -07:00
|
|
|
q->limits.discard_granularity = 512;
|
2013-03-23 17:11:31 -06:00
|
|
|
q->limits.io_min = block_size;
|
|
|
|
q->limits.logical_block_size = block_size;
|
|
|
|
q->limits.physical_block_size = block_size;
|
|
|
|
set_bit(QUEUE_FLAG_NONROT, &d->disk->queue->queue_flags);
|
2014-10-04 10:55:32 -06:00
|
|
|
clear_bit(QUEUE_FLAG_ADD_RANDOM, &d->disk->queue->queue_flags);
|
2013-03-23 17:11:31 -06:00
|
|
|
set_bit(QUEUE_FLAG_DISCARD, &d->disk->queue->queue_flags);
|
|
|
|
|
2013-07-10 19:44:40 -06:00
|
|
|
blk_queue_flush(q, REQ_FLUSH|REQ_FUA);
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Cached device */
|
|
|
|
|
|
|
|
static void calc_cached_dev_sectors(struct cache_set *c)
|
|
|
|
{
|
|
|
|
uint64_t sectors = 0;
|
|
|
|
struct cached_dev *dc;
|
|
|
|
|
|
|
|
list_for_each_entry(dc, &c->cached_devs, list)
|
|
|
|
sectors += bdev_sectors(dc->bdev);
|
|
|
|
|
|
|
|
c->cached_dev_sectors = sectors;
|
|
|
|
}
|
|
|
|
|
|
|
|
void bch_cached_dev_run(struct cached_dev *dc)
|
|
|
|
{
|
|
|
|
struct bcache_device *d = &dc->disk;
|
2013-06-08 16:54:48 -06:00
|
|
|
char buf[SB_LABEL_SIZE + 1];
|
2013-06-07 15:27:01 -06:00
|
|
|
char *env[] = {
|
|
|
|
"DRIVER=bcache",
|
|
|
|
kasprintf(GFP_KERNEL, "CACHED_UUID=%pU", dc->sb.uuid),
|
2013-06-08 16:54:48 -06:00
|
|
|
NULL,
|
|
|
|
NULL,
|
2013-06-07 15:27:01 -06:00
|
|
|
};
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-06-08 16:54:48 -06:00
|
|
|
memcpy(buf, dc->sb.label, SB_LABEL_SIZE);
|
|
|
|
buf[SB_LABEL_SIZE] = '\0';
|
|
|
|
env[2] = kasprintf(GFP_KERNEL, "CACHED_LABEL=%s", buf);
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
if (atomic_xchg(&dc->running, 1))
|
|
|
|
return;
|
|
|
|
|
|
|
|
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);
|
|
|
|
bch_write_bdev_super(dc, &cl);
|
|
|
|
closure_sync(&cl);
|
|
|
|
}
|
|
|
|
|
|
|
|
add_disk(d->disk);
|
2013-02-01 08:29:41 -07:00
|
|
|
bd_link_disk_holder(dc->bdev, dc->disk.disk);
|
2013-06-07 15:27:01 -06:00
|
|
|
/* won't show up in the uevent file, use udevadm monitor -e instead
|
|
|
|
* only class / kset properties are persistent */
|
2013-03-23 17:11:31 -06:00
|
|
|
kobject_uevent_env(&disk_to_dev(d->disk)->kobj, KOBJ_CHANGE, env);
|
2013-06-07 15:27:01 -06:00
|
|
|
kfree(env[1]);
|
2013-06-08 16:54:48 -06:00
|
|
|
kfree(env[2]);
|
2013-06-07 15:27:01 -06:00
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
if (sysfs_create_link(&d->kobj, &disk_to_dev(d->disk)->kobj, "dev") ||
|
|
|
|
sysfs_create_link(&disk_to_dev(d->disk)->kobj, &d->kobj, "bcache"))
|
|
|
|
pr_debug("error creating sysfs link");
|
|
|
|
}
|
|
|
|
|
|
|
|
static void cached_dev_detach_finish(struct work_struct *w)
|
|
|
|
{
|
|
|
|
struct cached_dev *dc = container_of(w, struct cached_dev, detach);
|
|
|
|
char buf[BDEVNAME_SIZE];
|
|
|
|
struct closure cl;
|
|
|
|
closure_init_stack(&cl);
|
|
|
|
|
2013-08-21 18:49:09 -06:00
|
|
|
BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags));
|
2013-03-23 17:11:31 -06:00
|
|
|
BUG_ON(atomic_read(&dc->count));
|
|
|
|
|
|
|
|
mutex_lock(&bch_register_lock);
|
|
|
|
|
|
|
|
memset(&dc->sb.set_uuid, 0, 16);
|
|
|
|
SET_BDEV_STATE(&dc->sb, BDEV_STATE_NONE);
|
|
|
|
|
|
|
|
bch_write_bdev_super(dc, &cl);
|
|
|
|
closure_sync(&cl);
|
|
|
|
|
|
|
|
bcache_device_detach(&dc->disk);
|
|
|
|
list_move(&dc->list, &uncached_devices);
|
|
|
|
|
2013-08-21 18:49:09 -06:00
|
|
|
clear_bit(BCACHE_DEV_DETACHING, &dc->disk.flags);
|
2014-03-19 18:49:37 -06:00
|
|
|
clear_bit(BCACHE_DEV_UNLINK_DONE, &dc->disk.flags);
|
2013-08-21 18:49:09 -06:00
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
mutex_unlock(&bch_register_lock);
|
|
|
|
|
|
|
|
pr_info("Caching disabled for %s", bdevname(dc->bdev, buf));
|
|
|
|
|
|
|
|
/* Drop ref we took in cached_dev_detach() */
|
|
|
|
closure_put(&dc->disk.cl);
|
|
|
|
}
|
|
|
|
|
|
|
|
void bch_cached_dev_detach(struct cached_dev *dc)
|
|
|
|
{
|
|
|
|
lockdep_assert_held(&bch_register_lock);
|
|
|
|
|
2013-08-21 18:49:09 -06:00
|
|
|
if (test_bit(BCACHE_DEV_CLOSING, &dc->disk.flags))
|
2013-03-23 17:11:31 -06:00
|
|
|
return;
|
|
|
|
|
2013-08-21 18:49:09 -06:00
|
|
|
if (test_and_set_bit(BCACHE_DEV_DETACHING, &dc->disk.flags))
|
2013-03-23 17:11:31 -06:00
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Block the device from being closed and freed until we're finished
|
|
|
|
* detaching
|
|
|
|
*/
|
|
|
|
closure_get(&dc->disk.cl);
|
|
|
|
|
|
|
|
bch_writeback_queue(dc);
|
|
|
|
cached_dev_put(dc);
|
|
|
|
}
|
|
|
|
|
|
|
|
int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
|
|
|
|
{
|
|
|
|
uint32_t rtime = cpu_to_le32(get_seconds());
|
|
|
|
struct uuid_entry *u;
|
|
|
|
char buf[BDEVNAME_SIZE];
|
|
|
|
|
|
|
|
bdevname(dc->bdev, buf);
|
|
|
|
|
|
|
|
if (memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16))
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
if (dc->disk.c) {
|
|
|
|
pr_err("Can't attach %s: already attached", buf);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (test_bit(CACHE_SET_STOPPING, &c->flags)) {
|
|
|
|
pr_err("Can't attach %s: shutting down", buf);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (dc->sb.block_size < c->sb.block_size) {
|
|
|
|
/* Will die */
|
2013-03-25 12:46:44 -06:00
|
|
|
pr_err("Couldn't attach %s: block size less than set's block size",
|
|
|
|
buf);
|
2013-03-23 17:11:31 -06:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
u = uuid_find(c, dc->sb.uuid);
|
|
|
|
|
|
|
|
if (u &&
|
|
|
|
(BDEV_STATE(&dc->sb) == BDEV_STATE_STALE ||
|
|
|
|
BDEV_STATE(&dc->sb) == BDEV_STATE_NONE)) {
|
|
|
|
memcpy(u->uuid, invalid_uuid, 16);
|
|
|
|
u->invalidated = cpu_to_le32(get_seconds());
|
|
|
|
u = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!u) {
|
|
|
|
if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
|
|
|
|
pr_err("Couldn't find uuid for %s in set", buf);
|
|
|
|
return -ENOENT;
|
|
|
|
}
|
|
|
|
|
|
|
|
u = uuid_find_empty(c);
|
|
|
|
if (!u) {
|
|
|
|
pr_err("Not caching %s, no room for UUID", buf);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Deadlocks since we're called via sysfs...
|
|
|
|
sysfs_remove_file(&dc->kobj, &sysfs_attach);
|
|
|
|
*/
|
|
|
|
|
2013-03-28 12:50:55 -06:00
|
|
|
if (bch_is_zero(u->uuid, 16)) {
|
2013-03-23 17:11:31 -06:00
|
|
|
struct closure cl;
|
|
|
|
closure_init_stack(&cl);
|
|
|
|
|
|
|
|
memcpy(u->uuid, dc->sb.uuid, 16);
|
|
|
|
memcpy(u->label, dc->sb.label, SB_LABEL_SIZE);
|
|
|
|
u->first_reg = u->last_reg = rtime;
|
|
|
|
bch_uuid_write(c);
|
|
|
|
|
|
|
|
memcpy(dc->sb.set_uuid, c->sb.set_uuid, 16);
|
|
|
|
SET_BDEV_STATE(&dc->sb, BDEV_STATE_CLEAN);
|
|
|
|
|
|
|
|
bch_write_bdev_super(dc, &cl);
|
|
|
|
closure_sync(&cl);
|
|
|
|
} else {
|
|
|
|
u->last_reg = rtime;
|
|
|
|
bch_uuid_write(c);
|
|
|
|
}
|
|
|
|
|
|
|
|
bcache_device_attach(&dc->disk, c, u - c->uuids);
|
|
|
|
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()
|
|
|
|
*/
|
|
|
|
atomic_set(&dc->count, 1);
|
|
|
|
|
2014-05-01 14:48:57 -06:00
|
|
|
if (bch_cached_dev_writeback_start(dc))
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
|
2013-05-11 18:07:26 -06:00
|
|
|
bch_sectors_dirty_init(dc);
|
2013-03-23 17:11:31 -06:00
|
|
|
atomic_set(&dc->has_dirty, 1);
|
|
|
|
atomic_inc(&dc->count);
|
|
|
|
bch_writeback_queue(dc);
|
|
|
|
}
|
|
|
|
|
|
|
|
bch_cached_dev_run(dc);
|
2013-02-01 08:29:41 -07:00
|
|
|
bcache_device_link(&dc->disk, c, "bdev");
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
pr_info("Caching %s as %s on set %pU",
|
|
|
|
bdevname(dc->bdev, buf), dc->disk.disk->disk_name,
|
|
|
|
dc->disk.c->sb.set_uuid);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void bch_cached_dev_release(struct kobject *kobj)
|
|
|
|
{
|
|
|
|
struct cached_dev *dc = container_of(kobj, struct cached_dev,
|
|
|
|
disk.kobj);
|
|
|
|
kfree(dc);
|
|
|
|
module_put(THIS_MODULE);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void cached_dev_free(struct closure *cl)
|
|
|
|
{
|
|
|
|
struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
|
|
|
|
|
|
|
|
cancel_delayed_work_sync(&dc->writeback_rate_update);
|
2014-05-20 13:20:28 -06:00
|
|
|
if (!IS_ERR_OR_NULL(dc->writeback_thread))
|
|
|
|
kthread_stop(dc->writeback_thread);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
mutex_lock(&bch_register_lock);
|
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
if (atomic_read(&dc->running))
|
|
|
|
bd_unlink_disk_holder(dc->bdev, dc->disk.disk);
|
2013-03-23 17:11:31 -06:00
|
|
|
bcache_device_free(&dc->disk);
|
|
|
|
list_del(&dc->list);
|
|
|
|
|
|
|
|
mutex_unlock(&bch_register_lock);
|
|
|
|
|
2014-07-07 14:03:36 -06:00
|
|
|
if (!IS_ERR_OR_NULL(dc->bdev))
|
2013-03-23 17:11:31 -06:00
|
|
|
blkdev_put(dc->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
|
|
|
|
|
|
|
|
wake_up(&unregister_wait);
|
|
|
|
|
|
|
|
kobject_put(&dc->disk.kobj);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void cached_dev_flush(struct closure *cl)
|
|
|
|
{
|
|
|
|
struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
|
|
|
|
struct bcache_device *d = &dc->disk;
|
|
|
|
|
2013-07-10 22:25:02 -06:00
|
|
|
mutex_lock(&bch_register_lock);
|
2013-08-21 18:49:09 -06:00
|
|
|
bcache_device_unlink(d);
|
2013-07-10 22:25:02 -06:00
|
|
|
mutex_unlock(&bch_register_lock);
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
bch_cache_accounting_destroy(&dc->accounting);
|
|
|
|
kobject_del(&d->kobj);
|
|
|
|
|
|
|
|
continue_at(cl, cached_dev_free, system_wq);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int cached_dev_init(struct cached_dev *dc, unsigned block_size)
|
|
|
|
{
|
2013-05-15 01:11:26 -06:00
|
|
|
int ret;
|
2013-03-23 17:11:31 -06:00
|
|
|
struct io *io;
|
2013-05-15 01:11:26 -06:00
|
|
|
struct request_queue *q = bdev_get_queue(dc->bdev);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
__module_get(THIS_MODULE);
|
|
|
|
INIT_LIST_HEAD(&dc->list);
|
2013-05-15 01:11:26 -06:00
|
|
|
closure_init(&dc->disk.cl, NULL);
|
|
|
|
set_closure_fn(&dc->disk.cl, cached_dev_flush, system_wq);
|
2013-03-23 17:11:31 -06:00
|
|
|
kobject_init(&dc->disk.kobj, &bch_cached_dev_ktype);
|
|
|
|
INIT_WORK(&dc->detach, cached_dev_detach_finish);
|
2013-12-16 16:27:25 -07:00
|
|
|
sema_init(&dc->sb_write_mutex, 1);
|
2013-05-15 01:11:26 -06:00
|
|
|
INIT_LIST_HEAD(&dc->io_lru);
|
|
|
|
spin_lock_init(&dc->io_lock);
|
|
|
|
bch_cache_accounting_init(&dc->accounting, &dc->disk.cl);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
dc->sequential_cutoff = 4 << 20;
|
|
|
|
|
|
|
|
for (io = dc->io; io < dc->io + RECENT_IO; io++) {
|
|
|
|
list_add(&io->lru, &dc->io_lru);
|
|
|
|
hlist_add_head(&io->hash, dc->io_hash + RECENT_IO);
|
|
|
|
}
|
|
|
|
|
2013-07-11 23:39:53 -06:00
|
|
|
dc->disk.stripe_size = q->limits.io_opt >> 9;
|
|
|
|
|
|
|
|
if (dc->disk.stripe_size)
|
|
|
|
dc->partial_stripes_expensive =
|
|
|
|
q->limits.raid_partial_stripes_expensive;
|
|
|
|
|
2013-06-05 07:21:07 -06:00
|
|
|
ret = bcache_device_init(&dc->disk, block_size,
|
|
|
|
dc->bdev->bd_part->nr_sects - dc->sb.data_offset);
|
2013-05-15 01:11:26 -06:00
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
set_capacity(dc->disk.disk,
|
|
|
|
dc->bdev->bd_part->nr_sects - dc->sb.data_offset);
|
|
|
|
|
|
|
|
dc->disk.disk->queue->backing_dev_info.ra_pages =
|
|
|
|
max(dc->disk.disk->queue->backing_dev_info.ra_pages,
|
|
|
|
q->backing_dev_info.ra_pages);
|
|
|
|
|
|
|
|
bch_cached_dev_request_init(dc);
|
|
|
|
bch_cached_dev_writeback_init(dc);
|
2013-03-23 17:11:31 -06:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Cached device - bcache superblock */
|
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
static void register_bdev(struct cache_sb *sb, struct page *sb_page,
|
2013-03-23 17:11:31 -06:00
|
|
|
struct block_device *bdev,
|
|
|
|
struct cached_dev *dc)
|
|
|
|
{
|
|
|
|
char name[BDEVNAME_SIZE];
|
|
|
|
const char *err = "cannot allocate memory";
|
|
|
|
struct cache_set *c;
|
|
|
|
|
|
|
|
memcpy(&dc->sb, sb, sizeof(struct cache_sb));
|
|
|
|
dc->bdev = bdev;
|
|
|
|
dc->bdev->bd_holder = dc;
|
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
bio_init(&dc->sb_bio);
|
|
|
|
dc->sb_bio.bi_max_vecs = 1;
|
|
|
|
dc->sb_bio.bi_io_vec = dc->sb_bio.bi_inline_vecs;
|
|
|
|
dc->sb_bio.bi_io_vec[0].bv_page = sb_page;
|
|
|
|
get_page(sb_page);
|
2013-03-27 12:09:23 -06:00
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
if (cached_dev_init(dc, sb->block_size << 9))
|
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
err = "error creating kobject";
|
|
|
|
if (kobject_add(&dc->disk.kobj, &part_to_dev(bdev->bd_part)->kobj,
|
|
|
|
"bcache"))
|
|
|
|
goto err;
|
|
|
|
if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
|
|
|
|
goto err;
|
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
pr_info("registered backing device %s", bdevname(bdev, name));
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
list_add(&dc->list, &uncached_devices);
|
|
|
|
list_for_each_entry(c, &bch_cache_sets, list)
|
|
|
|
bch_cached_dev_attach(dc, c);
|
|
|
|
|
|
|
|
if (BDEV_STATE(&dc->sb) == BDEV_STATE_NONE ||
|
|
|
|
BDEV_STATE(&dc->sb) == BDEV_STATE_STALE)
|
|
|
|
bch_cached_dev_run(dc);
|
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
return;
|
2013-03-23 17:11:31 -06:00
|
|
|
err:
|
|
|
|
pr_notice("error opening %s: %s", bdevname(bdev, name), err);
|
2013-05-15 01:11:26 -06:00
|
|
|
bcache_device_stop(&dc->disk);
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Flash only volumes */
|
|
|
|
|
|
|
|
void bch_flash_dev_release(struct kobject *kobj)
|
|
|
|
{
|
|
|
|
struct bcache_device *d = container_of(kobj, struct bcache_device,
|
|
|
|
kobj);
|
|
|
|
kfree(d);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void flash_dev_free(struct closure *cl)
|
|
|
|
{
|
|
|
|
struct bcache_device *d = container_of(cl, struct bcache_device, cl);
|
2014-04-29 16:39:27 -06:00
|
|
|
mutex_lock(&bch_register_lock);
|
2013-03-23 17:11:31 -06:00
|
|
|
bcache_device_free(d);
|
2014-04-29 16:39:27 -06:00
|
|
|
mutex_unlock(&bch_register_lock);
|
2013-03-23 17:11:31 -06:00
|
|
|
kobject_put(&d->kobj);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void flash_dev_flush(struct closure *cl)
|
|
|
|
{
|
|
|
|
struct bcache_device *d = container_of(cl, struct bcache_device, cl);
|
|
|
|
|
2014-04-29 16:39:27 -06:00
|
|
|
mutex_lock(&bch_register_lock);
|
2013-02-01 08:29:41 -07:00
|
|
|
bcache_device_unlink(d);
|
2014-04-29 16:39:27 -06:00
|
|
|
mutex_unlock(&bch_register_lock);
|
2013-03-23 17:11:31 -06:00
|
|
|
kobject_del(&d->kobj);
|
|
|
|
continue_at(cl, flash_dev_free, system_wq);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
|
|
|
|
{
|
|
|
|
struct bcache_device *d = kzalloc(sizeof(struct bcache_device),
|
|
|
|
GFP_KERNEL);
|
|
|
|
if (!d)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
closure_init(&d->cl, NULL);
|
|
|
|
set_closure_fn(&d->cl, flash_dev_flush, system_wq);
|
|
|
|
|
|
|
|
kobject_init(&d->kobj, &bch_flash_dev_ktype);
|
|
|
|
|
2013-06-05 07:21:07 -06:00
|
|
|
if (bcache_device_init(d, block_bytes(c), u->sectors))
|
2013-03-23 17:11:31 -06:00
|
|
|
goto err;
|
|
|
|
|
|
|
|
bcache_device_attach(d, c, u - c->uuids);
|
|
|
|
bch_flash_dev_request_init(d);
|
|
|
|
add_disk(d->disk);
|
|
|
|
|
|
|
|
if (kobject_add(&d->kobj, &disk_to_dev(d->disk)->kobj, "bcache"))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
bcache_device_link(d, c, "volume");
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
err:
|
|
|
|
kobject_put(&d->kobj);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int flash_devs_run(struct cache_set *c)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
struct uuid_entry *u;
|
|
|
|
|
|
|
|
for (u = c->uuids;
|
|
|
|
u < c->uuids + c->nr_uuids && !ret;
|
|
|
|
u++)
|
|
|
|
if (UUID_FLASH_ONLY(u))
|
|
|
|
ret = flash_dev_run(c, u);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
int bch_flash_dev_create(struct cache_set *c, uint64_t size)
|
|
|
|
{
|
|
|
|
struct uuid_entry *u;
|
|
|
|
|
|
|
|
if (test_bit(CACHE_SET_STOPPING, &c->flags))
|
|
|
|
return -EINTR;
|
|
|
|
|
2014-07-11 13:17:41 -06:00
|
|
|
if (!test_bit(CACHE_SET_RUNNING, &c->flags))
|
|
|
|
return -EPERM;
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
u = uuid_find_empty(c);
|
|
|
|
if (!u) {
|
|
|
|
pr_err("Can't create volume, no room for UUID");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
get_random_bytes(u->uuid, 16);
|
|
|
|
memset(u->label, 0, 32);
|
|
|
|
u->first_reg = u->last_reg = cpu_to_le32(get_seconds());
|
|
|
|
|
|
|
|
SET_UUID_FLASH_ONLY(u, 1);
|
|
|
|
u->sectors = size >> 9;
|
|
|
|
|
|
|
|
bch_uuid_write(c);
|
|
|
|
|
|
|
|
return flash_dev_run(c, u);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Cache set */
|
|
|
|
|
|
|
|
__printf(2, 3)
|
|
|
|
bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...)
|
|
|
|
{
|
|
|
|
va_list args;
|
|
|
|
|
2013-07-11 20:42:51 -06:00
|
|
|
if (c->on_error != ON_ERROR_PANIC &&
|
|
|
|
test_bit(CACHE_SET_STOPPING, &c->flags))
|
2013-03-23 17:11:31 -06:00
|
|
|
return false;
|
|
|
|
|
|
|
|
/* XXX: we can be called from atomic context
|
|
|
|
acquire_console_sem();
|
|
|
|
*/
|
|
|
|
|
|
|
|
printk(KERN_ERR "bcache: error on %pU: ", c->sb.set_uuid);
|
|
|
|
|
|
|
|
va_start(args, fmt);
|
|
|
|
vprintk(fmt, args);
|
|
|
|
va_end(args);
|
|
|
|
|
|
|
|
printk(", disabling caching\n");
|
|
|
|
|
2013-07-11 20:42:51 -06:00
|
|
|
if (c->on_error == ON_ERROR_PANIC)
|
|
|
|
panic("panic forced after error\n");
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
bch_cache_set_unregister(c);
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void cache_set_free(struct closure *cl)
|
|
|
|
{
|
|
|
|
struct cache_set *c = container_of(cl, struct cache_set, cl);
|
|
|
|
struct cache *ca;
|
|
|
|
unsigned i;
|
|
|
|
|
|
|
|
if (!IS_ERR_OR_NULL(c->debug))
|
|
|
|
debugfs_remove(c->debug);
|
|
|
|
|
|
|
|
bch_open_buckets_free(c);
|
|
|
|
bch_btree_cache_free(c);
|
|
|
|
bch_journal_free(c);
|
|
|
|
|
|
|
|
for_each_cache(ca, c, i)
|
2014-06-19 16:05:59 -06:00
|
|
|
if (ca) {
|
|
|
|
ca->set = NULL;
|
|
|
|
c->cache[ca->sb.nr_this_dev] = NULL;
|
2013-03-23 17:11:31 -06:00
|
|
|
kobject_put(&ca->kobj);
|
2014-06-19 16:05:59 -06:00
|
|
|
}
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-09-10 23:53:34 -06:00
|
|
|
bch_bset_sort_state_free(&c->sort);
|
2013-03-23 17:11:31 -06:00
|
|
|
free_pages((unsigned long) c->uuids, ilog2(bucket_pages(c)));
|
|
|
|
|
2014-01-09 17:03:04 -07:00
|
|
|
if (c->moving_gc_wq)
|
|
|
|
destroy_workqueue(c->moving_gc_wq);
|
2013-03-23 17:11:31 -06:00
|
|
|
if (c->bio_split)
|
|
|
|
bioset_free(c->bio_split);
|
2013-04-25 14:58:35 -06:00
|
|
|
if (c->fill_iter)
|
|
|
|
mempool_destroy(c->fill_iter);
|
2013-03-23 17:11:31 -06:00
|
|
|
if (c->bio_meta)
|
|
|
|
mempool_destroy(c->bio_meta);
|
|
|
|
if (c->search)
|
|
|
|
mempool_destroy(c->search);
|
|
|
|
kfree(c->devices);
|
|
|
|
|
|
|
|
mutex_lock(&bch_register_lock);
|
|
|
|
list_del(&c->list);
|
|
|
|
mutex_unlock(&bch_register_lock);
|
|
|
|
|
|
|
|
pr_info("Cache set %pU unregistered", c->sb.set_uuid);
|
|
|
|
wake_up(&unregister_wait);
|
|
|
|
|
|
|
|
closure_debug_destroy(&c->cl);
|
|
|
|
kobject_put(&c->kobj);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void cache_set_flush(struct closure *cl)
|
|
|
|
{
|
|
|
|
struct cache_set *c = container_of(cl, struct cache_set, caching);
|
2013-07-10 19:31:58 -06:00
|
|
|
struct cache *ca;
|
2013-03-23 17:11:31 -06:00
|
|
|
struct btree *b;
|
2013-07-10 19:31:58 -06:00
|
|
|
unsigned i;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
bch_cache_accounting_destroy(&c->accounting);
|
|
|
|
|
|
|
|
kobject_put(&c->internal);
|
|
|
|
kobject_del(&c->kobj);
|
|
|
|
|
2013-10-24 18:19:26 -06:00
|
|
|
if (c->gc_thread)
|
|
|
|
kthread_stop(c->gc_thread);
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
if (!IS_ERR_OR_NULL(c->root))
|
|
|
|
list_add(&c->root->list, &c->btree_cache);
|
|
|
|
|
|
|
|
/* Should skip this if we're unregistering because of an error */
|
2014-03-04 17:42:42 -07:00
|
|
|
list_for_each_entry(b, &c->btree_cache, list) {
|
|
|
|
mutex_lock(&b->write_lock);
|
2013-03-23 17:11:31 -06:00
|
|
|
if (btree_node_dirty(b))
|
2014-03-04 17:42:42 -07:00
|
|
|
__bch_btree_node_write(b, NULL);
|
|
|
|
mutex_unlock(&b->write_lock);
|
|
|
|
}
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-07-10 19:31:58 -06:00
|
|
|
for_each_cache(ca, c, i)
|
|
|
|
if (ca->alloc_thread)
|
|
|
|
kthread_stop(ca->alloc_thread);
|
|
|
|
|
2014-03-19 18:49:37 -06:00
|
|
|
if (c->journal.cur) {
|
|
|
|
cancel_delayed_work_sync(&c->journal.work);
|
|
|
|
/* flush last journal entry if needed */
|
|
|
|
c->journal.work.work.func(&c->journal.work.work);
|
|
|
|
}
|
2014-02-19 20:48:26 -07:00
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
closure_return(cl);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __cache_set_unregister(struct closure *cl)
|
|
|
|
{
|
|
|
|
struct cache_set *c = container_of(cl, struct cache_set, caching);
|
2013-07-10 22:03:25 -06:00
|
|
|
struct cached_dev *dc;
|
2013-03-23 17:11:31 -06:00
|
|
|
size_t i;
|
|
|
|
|
|
|
|
mutex_lock(&bch_register_lock);
|
|
|
|
|
|
|
|
for (i = 0; i < c->nr_uuids; i++)
|
2013-07-10 22:03:25 -06:00
|
|
|
if (c->devices[i]) {
|
|
|
|
if (!UUID_FLASH_ONLY(&c->uuids[i]) &&
|
|
|
|
test_bit(CACHE_SET_UNREGISTERING, &c->flags)) {
|
|
|
|
dc = container_of(c->devices[i],
|
|
|
|
struct cached_dev, disk);
|
|
|
|
bch_cached_dev_detach(dc);
|
|
|
|
} else {
|
|
|
|
bcache_device_stop(c->devices[i]);
|
|
|
|
}
|
|
|
|
}
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
mutex_unlock(&bch_register_lock);
|
|
|
|
|
|
|
|
continue_at(cl, cache_set_flush, system_wq);
|
|
|
|
}
|
|
|
|
|
|
|
|
void bch_cache_set_stop(struct cache_set *c)
|
|
|
|
{
|
|
|
|
if (!test_and_set_bit(CACHE_SET_STOPPING, &c->flags))
|
|
|
|
closure_queue(&c->caching);
|
|
|
|
}
|
|
|
|
|
|
|
|
void bch_cache_set_unregister(struct cache_set *c)
|
|
|
|
{
|
|
|
|
set_bit(CACHE_SET_UNREGISTERING, &c->flags);
|
|
|
|
bch_cache_set_stop(c);
|
|
|
|
}
|
|
|
|
|
|
|
|
#define alloc_bucket_pages(gfp, c) \
|
|
|
|
((void *) __get_free_pages(__GFP_ZERO|gfp, ilog2(bucket_pages(c))))
|
|
|
|
|
|
|
|
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;
|
|
|
|
|
|
|
|
__module_get(THIS_MODULE);
|
|
|
|
closure_init(&c->cl, NULL);
|
|
|
|
set_closure_fn(&c->cl, cache_set_free, system_wq);
|
|
|
|
|
|
|
|
closure_init(&c->caching, &c->cl);
|
|
|
|
set_closure_fn(&c->caching, __cache_set_unregister, system_wq);
|
|
|
|
|
|
|
|
/* Maybe create continue_at_noreturn() and use it here? */
|
|
|
|
closure_set_stopped(&c->cl);
|
|
|
|
closure_put(&c->cl);
|
|
|
|
|
|
|
|
kobject_init(&c->kobj, &bch_cache_set_ktype);
|
|
|
|
kobject_init(&c->internal, &bch_cache_set_internal_ktype);
|
|
|
|
|
|
|
|
bch_cache_accounting_init(&c->accounting, &c->cl);
|
|
|
|
|
|
|
|
memcpy(c->sb.set_uuid, sb->set_uuid, 16);
|
|
|
|
c->sb.block_size = sb->block_size;
|
|
|
|
c->sb.bucket_size = sb->bucket_size;
|
|
|
|
c->sb.nr_in_set = sb->nr_in_set;
|
|
|
|
c->sb.last_mount = sb->last_mount;
|
|
|
|
c->bucket_bits = ilog2(sb->bucket_size);
|
|
|
|
c->block_bits = ilog2(sb->block_size);
|
|
|
|
c->nr_uuids = bucket_bytes(c) / sizeof(struct uuid_entry);
|
|
|
|
|
2013-12-18 00:49:49 -07:00
|
|
|
c->btree_pages = bucket_pages(c);
|
2013-03-23 17:11:31 -06:00
|
|
|
if (c->btree_pages > BTREE_MAX_PAGES)
|
|
|
|
c->btree_pages = max_t(int, c->btree_pages / 4,
|
|
|
|
BTREE_MAX_PAGES);
|
|
|
|
|
2013-12-16 16:27:25 -07:00
|
|
|
sema_init(&c->sb_write_mutex, 1);
|
2013-07-24 18:27:07 -06:00
|
|
|
mutex_init(&c->bucket_lock);
|
2014-03-17 18:15:53 -06:00
|
|
|
init_waitqueue_head(&c->btree_cache_wait);
|
2013-07-24 18:29:09 -06:00
|
|
|
init_waitqueue_head(&c->bucket_wait);
|
2013-12-16 16:27:25 -07:00
|
|
|
sema_init(&c->uuid_write_mutex, 1);
|
2013-07-31 01:03:54 -06:00
|
|
|
|
|
|
|
spin_lock_init(&c->btree_gc_time.lock);
|
|
|
|
spin_lock_init(&c->btree_split_time.lock);
|
|
|
|
spin_lock_init(&c->btree_read_time.lock);
|
2013-07-24 18:27:07 -06:00
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
bch_moving_init_cache_set(c);
|
|
|
|
|
|
|
|
INIT_LIST_HEAD(&c->list);
|
|
|
|
INIT_LIST_HEAD(&c->cached_devs);
|
|
|
|
INIT_LIST_HEAD(&c->btree_cache);
|
|
|
|
INIT_LIST_HEAD(&c->btree_cache_freeable);
|
|
|
|
INIT_LIST_HEAD(&c->btree_cache_freed);
|
|
|
|
INIT_LIST_HEAD(&c->data_buckets);
|
|
|
|
|
|
|
|
c->search = mempool_create_slab_pool(32, bch_search_cache);
|
|
|
|
if (!c->search)
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
iter_size = (sb->bucket_size / sb->block_size + 1) *
|
|
|
|
sizeof(struct btree_iter_set);
|
|
|
|
|
|
|
|
if (!(c->devices = kzalloc(c->nr_uuids * sizeof(void *), GFP_KERNEL)) ||
|
|
|
|
!(c->bio_meta = mempool_create_kmalloc_pool(2,
|
|
|
|
sizeof(struct bbio) + sizeof(struct bio_vec) *
|
|
|
|
bucket_pages(c))) ||
|
2013-04-25 14:58:35 -06:00
|
|
|
!(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) ||
|
2013-03-23 17:11:31 -06:00
|
|
|
!(c->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
|
|
|
|
!(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
|
2014-01-09 17:03:04 -07:00
|
|
|
!(c->moving_gc_wq = create_workqueue("bcache_gc")) ||
|
2013-03-23 17:11:31 -06:00
|
|
|
bch_journal_alloc(c) ||
|
|
|
|
bch_btree_cache_alloc(c) ||
|
2013-09-10 23:53:34 -06:00
|
|
|
bch_open_buckets_alloc(c) ||
|
|
|
|
bch_bset_sort_state_init(&c->sort, ilog2(c->btree_pages)))
|
2013-03-23 17:11:31 -06:00
|
|
|
goto err;
|
|
|
|
|
|
|
|
c->congested_read_threshold_us = 2000;
|
|
|
|
c->congested_write_threshold_us = 20000;
|
|
|
|
c->error_limit = 8 << IO_ERROR_SHIFT;
|
|
|
|
|
|
|
|
return c;
|
|
|
|
err:
|
|
|
|
bch_cache_set_unregister(c);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void run_cache_set(struct cache_set *c)
|
|
|
|
{
|
|
|
|
const char *err = "cannot allocate memory";
|
|
|
|
struct cached_dev *dc, *t;
|
|
|
|
struct cache *ca;
|
2013-07-24 18:44:17 -06:00
|
|
|
struct closure cl;
|
2013-03-23 17:11:31 -06:00
|
|
|
unsigned i;
|
|
|
|
|
2013-07-24 18:44:17 -06:00
|
|
|
closure_init_stack(&cl);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
for_each_cache(ca, c, i)
|
|
|
|
c->nbuckets += ca->sb.nbuckets;
|
|
|
|
|
|
|
|
if (CACHE_SYNC(&c->sb)) {
|
|
|
|
LIST_HEAD(journal);
|
|
|
|
struct bkey *k;
|
|
|
|
struct jset *j;
|
|
|
|
|
|
|
|
err = "cannot allocate memory for journal";
|
2013-07-24 18:44:17 -06:00
|
|
|
if (bch_journal_read(c, &journal))
|
2013-03-23 17:11:31 -06:00
|
|
|
goto err;
|
|
|
|
|
|
|
|
pr_debug("btree_journal_read() done");
|
|
|
|
|
|
|
|
err = "no journal entries found";
|
|
|
|
if (list_empty(&journal))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
j = &list_entry(journal.prev, struct journal_replay, list)->j;
|
|
|
|
|
|
|
|
err = "IO error reading priorities";
|
|
|
|
for_each_cache(ca, c, i)
|
|
|
|
prio_read(ca, j->prio_bucket[ca->sb.nr_this_dev]);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If prio_read() fails it'll call cache_set_error and we'll
|
|
|
|
* tear everything down right away, but if we perhaps checked
|
|
|
|
* sooner we could avoid journal replay.
|
|
|
|
*/
|
|
|
|
|
|
|
|
k = &j->btree_root;
|
|
|
|
|
|
|
|
err = "bad btree root";
|
2013-12-20 18:22:05 -07:00
|
|
|
if (__bch_btree_ptr_invalid(c, k))
|
2013-03-23 17:11:31 -06:00
|
|
|
goto err;
|
|
|
|
|
|
|
|
err = "error reading btree root";
|
2014-07-12 01:22:53 -06:00
|
|
|
c->root = bch_btree_node_get(c, NULL, k, j->btree_level, true, NULL);
|
2013-03-23 17:11:31 -06:00
|
|
|
if (IS_ERR_OR_NULL(c->root))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
list_del_init(&c->root->list);
|
|
|
|
rw_unlock(true, c->root);
|
|
|
|
|
2013-07-24 18:44:17 -06:00
|
|
|
err = uuid_read(c, j, &cl);
|
2013-03-23 17:11:31 -06:00
|
|
|
if (err)
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
err = "error in recovery";
|
2013-07-24 18:44:17 -06:00
|
|
|
if (bch_btree_check(c))
|
2013-03-23 17:11:31 -06:00
|
|
|
goto err;
|
|
|
|
|
|
|
|
bch_journal_mark(c, &journal);
|
2014-03-17 17:55:55 -06:00
|
|
|
bch_initial_gc_finish(c);
|
2013-03-23 17:11:31 -06:00
|
|
|
pr_debug("btree_check() done");
|
|
|
|
|
|
|
|
/*
|
|
|
|
* bcache_journal_next() can't happen sooner, or
|
|
|
|
* btree_gc_finish() will give spurious errors about last_gc >
|
|
|
|
* gc_gen - this is a hack but oh well.
|
|
|
|
*/
|
|
|
|
bch_journal_next(&c->journal);
|
|
|
|
|
2013-04-24 20:01:12 -06:00
|
|
|
err = "error starting allocator thread";
|
2013-03-23 17:11:31 -06:00
|
|
|
for_each_cache(ca, c, i)
|
2013-04-24 20:01:12 -06:00
|
|
|
if (bch_cache_allocator_start(ca))
|
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* First place it's safe to allocate: btree_check() and
|
|
|
|
* btree_gc_finish() have to run before we have buckets to
|
|
|
|
* allocate, and bch_bucket_alloc_set() might cause a journal
|
|
|
|
* entry to be written so bcache_journal_next() has to be called
|
|
|
|
* first.
|
|
|
|
*
|
|
|
|
* If the uuids were in the old format we have to rewrite them
|
|
|
|
* before the next journal entry is written:
|
|
|
|
*/
|
|
|
|
if (j->version < BCACHE_JSET_VERSION_UUID)
|
|
|
|
__uuid_write(c);
|
|
|
|
|
2013-07-24 18:44:17 -06:00
|
|
|
bch_journal_replay(c, &journal);
|
2013-03-23 17:11:31 -06:00
|
|
|
} else {
|
|
|
|
pr_notice("invalidating existing data");
|
|
|
|
|
|
|
|
for_each_cache(ca, c, i) {
|
|
|
|
unsigned j;
|
|
|
|
|
|
|
|
ca->sb.keys = clamp_t(int, ca->sb.nbuckets >> 7,
|
|
|
|
2, SB_JOURNAL_BUCKETS);
|
|
|
|
|
|
|
|
for (j = 0; j < ca->sb.keys; j++)
|
|
|
|
ca->sb.d[j] = ca->sb.first_bucket + j;
|
|
|
|
}
|
|
|
|
|
2014-03-17 17:55:55 -06:00
|
|
|
bch_initial_gc_finish(c);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-04-24 20:01:12 -06:00
|
|
|
err = "error starting allocator thread";
|
2013-03-23 17:11:31 -06:00
|
|
|
for_each_cache(ca, c, i)
|
2013-04-24 20:01:12 -06:00
|
|
|
if (bch_cache_allocator_start(ca))
|
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
mutex_lock(&c->bucket_lock);
|
|
|
|
for_each_cache(ca, c, i)
|
|
|
|
bch_prio_write(ca);
|
|
|
|
mutex_unlock(&c->bucket_lock);
|
|
|
|
|
|
|
|
err = "cannot allocate new UUID bucket";
|
|
|
|
if (__uuid_write(c))
|
2013-10-24 18:19:26 -06:00
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
err = "cannot allocate new btree root";
|
2014-07-12 01:22:53 -06:00
|
|
|
c->root = __bch_btree_node_alloc(c, NULL, 0, true, NULL);
|
2013-03-23 17:11:31 -06:00
|
|
|
if (IS_ERR_OR_NULL(c->root))
|
2013-10-24 18:19:26 -06:00
|
|
|
goto err;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2014-03-04 17:42:42 -07:00
|
|
|
mutex_lock(&c->root->write_lock);
|
2013-03-23 17:11:31 -06:00
|
|
|
bkey_copy_key(&c->root->key, &MAX_KEY);
|
2013-07-24 18:44:17 -06:00
|
|
|
bch_btree_node_write(c->root, &cl);
|
2014-03-04 17:42:42 -07:00
|
|
|
mutex_unlock(&c->root->write_lock);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
bch_btree_set_root(c->root);
|
|
|
|
rw_unlock(true, c->root);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We don't want to write the first journal entry until
|
|
|
|
* everything is set up - fortunately journal entries won't be
|
|
|
|
* written until the SET_CACHE_SYNC() here:
|
|
|
|
*/
|
|
|
|
SET_CACHE_SYNC(&c->sb, true);
|
|
|
|
|
|
|
|
bch_journal_next(&c->journal);
|
2013-07-24 18:44:17 -06:00
|
|
|
bch_journal_meta(c, &cl);
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
2013-10-24 18:19:26 -06:00
|
|
|
err = "error starting gc thread";
|
|
|
|
if (bch_gc_thread_start(c))
|
|
|
|
goto err;
|
|
|
|
|
2013-07-24 18:44:17 -06:00
|
|
|
closure_sync(&cl);
|
2013-03-23 17:11:31 -06:00
|
|
|
c->sb.last_mount = get_seconds();
|
|
|
|
bcache_write_super(c);
|
|
|
|
|
|
|
|
list_for_each_entry_safe(dc, t, &uncached_devices, list)
|
|
|
|
bch_cached_dev_attach(dc, c);
|
|
|
|
|
|
|
|
flash_devs_run(c);
|
|
|
|
|
2014-07-11 13:17:41 -06:00
|
|
|
set_bit(CACHE_SET_RUNNING, &c->flags);
|
2013-03-23 17:11:31 -06:00
|
|
|
return;
|
|
|
|
err:
|
2013-07-24 18:44:17 -06:00
|
|
|
closure_sync(&cl);
|
2013-03-23 17:11:31 -06:00
|
|
|
/* XXX: test this, it's broken */
|
2013-09-10 22:41:34 -06:00
|
|
|
bch_cache_set_error(c, "%s", err);
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
static bool can_attach_cache(struct cache *ca, struct cache_set *c)
|
|
|
|
{
|
|
|
|
return ca->sb.block_size == c->sb.block_size &&
|
2013-10-22 14:19:23 -06:00
|
|
|
ca->sb.bucket_size == c->sb.bucket_size &&
|
2013-03-23 17:11:31 -06:00
|
|
|
ca->sb.nr_in_set == c->sb.nr_in_set;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const char *register_cache_set(struct cache *ca)
|
|
|
|
{
|
|
|
|
char buf[12];
|
|
|
|
const char *err = "cannot allocate memory";
|
|
|
|
struct cache_set *c;
|
|
|
|
|
|
|
|
list_for_each_entry(c, &bch_cache_sets, list)
|
|
|
|
if (!memcmp(c->sb.set_uuid, ca->sb.set_uuid, 16)) {
|
|
|
|
if (c->cache[ca->sb.nr_this_dev])
|
|
|
|
return "duplicate cache set member";
|
|
|
|
|
|
|
|
if (!can_attach_cache(ca, c))
|
|
|
|
return "cache sb does not match set";
|
|
|
|
|
|
|
|
if (!CACHE_SYNC(&ca->sb))
|
|
|
|
SET_CACHE_SYNC(&c->sb, false);
|
|
|
|
|
|
|
|
goto found;
|
|
|
|
}
|
|
|
|
|
|
|
|
c = bch_cache_set_alloc(&ca->sb);
|
|
|
|
if (!c)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
err = "error creating kobject";
|
|
|
|
if (kobject_add(&c->kobj, bcache_kobj, "%pU", c->sb.set_uuid) ||
|
|
|
|
kobject_add(&c->internal, &c->kobj, "internal"))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
if (bch_cache_accounting_add_kobjs(&c->accounting, &c->kobj))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
bch_debug_init_cache_set(c);
|
|
|
|
|
|
|
|
list_add(&c->list, &bch_cache_sets);
|
|
|
|
found:
|
|
|
|
sprintf(buf, "cache%i", ca->sb.nr_this_dev);
|
|
|
|
if (sysfs_create_link(&ca->kobj, &c->kobj, "set") ||
|
|
|
|
sysfs_create_link(&c->kobj, &ca->kobj, buf))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
if (ca->sb.seq > c->sb.seq) {
|
|
|
|
c->sb.version = ca->sb.version;
|
|
|
|
memcpy(c->sb.set_uuid, ca->sb.set_uuid, 16);
|
|
|
|
c->sb.flags = ca->sb.flags;
|
|
|
|
c->sb.seq = ca->sb.seq;
|
|
|
|
pr_debug("set version = %llu", c->sb.version);
|
|
|
|
}
|
|
|
|
|
2014-06-11 20:44:49 -06:00
|
|
|
kobject_get(&ca->kobj);
|
2013-03-23 17:11:31 -06:00
|
|
|
ca->set = c;
|
|
|
|
ca->set->cache[ca->sb.nr_this_dev] = ca;
|
|
|
|
c->cache_by_alloc[c->caches_loaded++] = ca;
|
|
|
|
|
|
|
|
if (c->caches_loaded == c->sb.nr_in_set)
|
|
|
|
run_cache_set(c);
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
err:
|
|
|
|
bch_cache_set_unregister(c);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Cache device */
|
|
|
|
|
|
|
|
void bch_cache_release(struct kobject *kobj)
|
|
|
|
{
|
|
|
|
struct cache *ca = container_of(kobj, struct cache, kobj);
|
2013-12-17 02:29:34 -07:00
|
|
|
unsigned i;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2014-06-19 16:05:59 -06:00
|
|
|
if (ca->set) {
|
|
|
|
BUG_ON(ca->set->cache[ca->sb.nr_this_dev] != ca);
|
2013-03-23 17:11:31 -06:00
|
|
|
ca->set->cache[ca->sb.nr_this_dev] = NULL;
|
2014-06-19 16:05:59 -06:00
|
|
|
}
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
free_pages((unsigned long) ca->disk_buckets, ilog2(bucket_pages(ca)));
|
|
|
|
kfree(ca->prio_buckets);
|
|
|
|
vfree(ca->buckets);
|
|
|
|
|
|
|
|
free_heap(&ca->heap);
|
|
|
|
free_fifo(&ca->free_inc);
|
2013-12-17 02:29:34 -07:00
|
|
|
|
|
|
|
for (i = 0; i < RESERVE_NR; i++)
|
|
|
|
free_fifo(&ca->free[i]);
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
if (ca->sb_bio.bi_inline_vecs[0].bv_page)
|
|
|
|
put_page(ca->sb_bio.bi_io_vec[0].bv_page);
|
|
|
|
|
2014-07-07 14:03:36 -06:00
|
|
|
if (!IS_ERR_OR_NULL(ca->bdev))
|
2013-03-23 17:11:31 -06:00
|
|
|
blkdev_put(ca->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
|
|
|
|
|
|
|
|
kfree(ca);
|
|
|
|
module_put(THIS_MODULE);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int cache_alloc(struct cache_sb *sb, struct cache *ca)
|
|
|
|
{
|
|
|
|
size_t free;
|
|
|
|
struct bucket *b;
|
|
|
|
|
|
|
|
__module_get(THIS_MODULE);
|
|
|
|
kobject_init(&ca->kobj, &bch_cache_ktype);
|
|
|
|
|
|
|
|
bio_init(&ca->journal.bio);
|
|
|
|
ca->journal.bio.bi_max_vecs = 8;
|
|
|
|
ca->journal.bio.bi_io_vec = ca->journal.bio.bi_inline_vecs;
|
|
|
|
|
2013-12-17 02:29:34 -07:00
|
|
|
free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-12-17 02:29:34 -07:00
|
|
|
if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
|
|
|
|
!init_fifo(&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) ||
|
2013-03-23 17:11:31 -06:00
|
|
|
!init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) ||
|
|
|
|
!init_heap(&ca->heap, free << 3, GFP_KERNEL) ||
|
2013-05-15 01:11:26 -06:00
|
|
|
!(ca->buckets = vzalloc(sizeof(struct bucket) *
|
2013-03-23 17:11:31 -06:00
|
|
|
ca->sb.nbuckets)) ||
|
|
|
|
!(ca->prio_buckets = kzalloc(sizeof(uint64_t) * prio_buckets(ca) *
|
|
|
|
2, GFP_KERNEL)) ||
|
2013-11-24 00:11:25 -07:00
|
|
|
!(ca->disk_buckets = alloc_bucket_pages(GFP_KERNEL, ca)))
|
2013-05-15 01:11:26 -06:00
|
|
|
return -ENOMEM;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
ca->prio_last_buckets = ca->prio_buckets + prio_buckets(ca);
|
|
|
|
|
|
|
|
for_each_bucket(b, ca)
|
|
|
|
atomic_set(&b->pin, 0);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
static void register_cache(struct cache_sb *sb, struct page *sb_page,
|
2014-06-19 16:05:59 -06:00
|
|
|
struct block_device *bdev, struct cache *ca)
|
2013-03-23 17:11:31 -06:00
|
|
|
{
|
|
|
|
char name[BDEVNAME_SIZE];
|
|
|
|
const char *err = "cannot allocate memory";
|
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
memcpy(&ca->sb, sb, sizeof(struct cache_sb));
|
2013-03-23 17:11:31 -06:00
|
|
|
ca->bdev = bdev;
|
|
|
|
ca->bdev->bd_holder = ca;
|
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
bio_init(&ca->sb_bio);
|
|
|
|
ca->sb_bio.bi_max_vecs = 1;
|
|
|
|
ca->sb_bio.bi_io_vec = ca->sb_bio.bi_inline_vecs;
|
|
|
|
ca->sb_bio.bi_io_vec[0].bv_page = sb_page;
|
|
|
|
get_page(sb_page);
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
if (blk_queue_discard(bdev_get_queue(ca->bdev)))
|
|
|
|
ca->discard = CACHE_DISCARD(&ca->sb);
|
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
if (cache_alloc(sb, ca) != 0)
|
|
|
|
goto err;
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
err = "error creating kobject";
|
|
|
|
if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache"))
|
|
|
|
goto err;
|
|
|
|
|
2014-03-17 19:58:55 -06:00
|
|
|
mutex_lock(&bch_register_lock);
|
2013-03-23 17:11:31 -06:00
|
|
|
err = register_cache_set(ca);
|
2014-03-17 19:58:55 -06:00
|
|
|
mutex_unlock(&bch_register_lock);
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
if (err)
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
pr_info("registered cache device %s", bdevname(bdev, name));
|
2014-06-11 20:44:49 -06:00
|
|
|
out:
|
|
|
|
kobject_put(&ca->kobj);
|
2013-05-15 01:11:26 -06:00
|
|
|
return;
|
2013-03-23 17:11:31 -06:00
|
|
|
err:
|
2013-05-15 01:11:26 -06:00
|
|
|
pr_notice("error opening %s: %s", bdevname(bdev, name), err);
|
2014-06-11 20:44:49 -06:00
|
|
|
goto out;
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Global interfaces/init */
|
|
|
|
|
|
|
|
static ssize_t register_bcache(struct kobject *, struct kobj_attribute *,
|
|
|
|
const char *, size_t);
|
|
|
|
|
|
|
|
kobj_attribute_write(register, register_bcache);
|
|
|
|
kobj_attribute_write(register_quiet, register_bcache);
|
|
|
|
|
2013-05-04 04:19:41 -06:00
|
|
|
static bool bch_is_open_backing(struct block_device *bdev) {
|
|
|
|
struct cache_set *c, *tc;
|
|
|
|
struct cached_dev *dc, *t;
|
|
|
|
|
|
|
|
list_for_each_entry_safe(c, tc, &bch_cache_sets, list)
|
|
|
|
list_for_each_entry_safe(dc, t, &c->cached_devs, list)
|
|
|
|
if (dc->bdev == bdev)
|
|
|
|
return true;
|
|
|
|
list_for_each_entry_safe(dc, t, &uncached_devices, list)
|
|
|
|
if (dc->bdev == bdev)
|
|
|
|
return true;
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool bch_is_open_cache(struct block_device *bdev) {
|
|
|
|
struct cache_set *c, *tc;
|
|
|
|
struct cache *ca;
|
|
|
|
unsigned i;
|
|
|
|
|
|
|
|
list_for_each_entry_safe(c, tc, &bch_cache_sets, list)
|
|
|
|
for_each_cache(ca, c, i)
|
|
|
|
if (ca->bdev == bdev)
|
|
|
|
return true;
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool bch_is_open(struct block_device *bdev) {
|
|
|
|
return bch_is_open_cache(bdev) || bch_is_open_backing(bdev);
|
|
|
|
}
|
|
|
|
|
2013-03-23 17:11:31 -06:00
|
|
|
static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
|
|
|
|
const char *buffer, size_t size)
|
|
|
|
{
|
|
|
|
ssize_t ret = size;
|
|
|
|
const char *err = "cannot allocate memory";
|
|
|
|
char *path = NULL;
|
|
|
|
struct cache_sb *sb = NULL;
|
|
|
|
struct block_device *bdev = NULL;
|
|
|
|
struct page *sb_page = NULL;
|
|
|
|
|
|
|
|
if (!try_module_get(THIS_MODULE))
|
|
|
|
return -EBUSY;
|
|
|
|
|
|
|
|
if (!(path = kstrndup(buffer, size, GFP_KERNEL)) ||
|
|
|
|
!(sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL)))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
err = "failed to open device";
|
|
|
|
bdev = blkdev_get_by_path(strim(path),
|
|
|
|
FMODE_READ|FMODE_WRITE|FMODE_EXCL,
|
|
|
|
sb);
|
2013-05-15 01:11:26 -06:00
|
|
|
if (IS_ERR(bdev)) {
|
2013-05-04 04:19:41 -06:00
|
|
|
if (bdev == ERR_PTR(-EBUSY)) {
|
|
|
|
bdev = lookup_bdev(strim(path));
|
2014-07-13 10:08:59 -06:00
|
|
|
mutex_lock(&bch_register_lock);
|
2013-05-04 04:19:41 -06:00
|
|
|
if (!IS_ERR(bdev) && bch_is_open(bdev))
|
|
|
|
err = "device already registered";
|
|
|
|
else
|
|
|
|
err = "device busy";
|
2014-07-13 10:08:59 -06:00
|
|
|
mutex_unlock(&bch_register_lock);
|
2013-05-04 04:19:41 -06:00
|
|
|
}
|
2013-03-23 17:11:31 -06:00
|
|
|
goto err;
|
2013-05-15 01:11:26 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
err = "failed to set blocksize";
|
|
|
|
if (set_blocksize(bdev, 4096))
|
|
|
|
goto err_close;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
err = read_super(sb, bdev, &sb_page);
|
|
|
|
if (err)
|
|
|
|
goto err_close;
|
|
|
|
|
2013-04-11 16:14:35 -06:00
|
|
|
if (SB_IS_BDEV(sb)) {
|
2013-03-23 17:11:31 -06:00
|
|
|
struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
|
2013-05-15 01:11:26 -06:00
|
|
|
if (!dc)
|
|
|
|
goto err_close;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2014-03-17 19:58:55 -06:00
|
|
|
mutex_lock(&bch_register_lock);
|
2013-05-15 01:11:26 -06:00
|
|
|
register_bdev(sb, sb_page, bdev, dc);
|
2014-03-17 19:58:55 -06:00
|
|
|
mutex_unlock(&bch_register_lock);
|
2013-03-23 17:11:31 -06:00
|
|
|
} else {
|
|
|
|
struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
|
2013-05-15 01:11:26 -06:00
|
|
|
if (!ca)
|
|
|
|
goto err_close;
|
2013-03-23 17:11:31 -06:00
|
|
|
|
2013-05-15 01:11:26 -06:00
|
|
|
register_cache(sb, sb_page, bdev, ca);
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
2013-05-15 01:11:26 -06:00
|
|
|
out:
|
|
|
|
if (sb_page)
|
2013-03-23 17:11:31 -06:00
|
|
|
put_page(sb_page);
|
|
|
|
kfree(sb);
|
|
|
|
kfree(path);
|
|
|
|
module_put(THIS_MODULE);
|
|
|
|
return ret;
|
2013-05-15 01:11:26 -06:00
|
|
|
|
|
|
|
err_close:
|
|
|
|
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
|
|
|
|
err:
|
|
|
|
if (attr != &ksysfs_register_quiet)
|
|
|
|
pr_info("error opening %s: %s", path, err);
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto out;
|
2013-03-23 17:11:31 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x)
|
|
|
|
{
|
|
|
|
if (code == SYS_DOWN ||
|
|
|
|
code == SYS_HALT ||
|
|
|
|
code == SYS_POWER_OFF) {
|
|
|
|
DEFINE_WAIT(wait);
|
|
|
|
unsigned long start = jiffies;
|
|
|
|
bool stopped = false;
|
|
|
|
|
|
|
|
struct cache_set *c, *tc;
|
|
|
|
struct cached_dev *dc, *tdc;
|
|
|
|
|
|
|
|
mutex_lock(&bch_register_lock);
|
|
|
|
|
|
|
|
if (list_empty(&bch_cache_sets) &&
|
|
|
|
list_empty(&uncached_devices))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
pr_info("Stopping all devices:");
|
|
|
|
|
|
|
|
list_for_each_entry_safe(c, tc, &bch_cache_sets, list)
|
|
|
|
bch_cache_set_stop(c);
|
|
|
|
|
|
|
|
list_for_each_entry_safe(dc, tdc, &uncached_devices, list)
|
|
|
|
bcache_device_stop(&dc->disk);
|
|
|
|
|
|
|
|
/* What's a condition variable? */
|
|
|
|
while (1) {
|
|
|
|
long timeout = start + 2 * HZ - jiffies;
|
|
|
|
|
|
|
|
stopped = list_empty(&bch_cache_sets) &&
|
|
|
|
list_empty(&uncached_devices);
|
|
|
|
|
|
|
|
if (timeout < 0 || stopped)
|
|
|
|
break;
|
|
|
|
|
|
|
|
prepare_to_wait(&unregister_wait, &wait,
|
|
|
|
TASK_UNINTERRUPTIBLE);
|
|
|
|
|
|
|
|
mutex_unlock(&bch_register_lock);
|
|
|
|
schedule_timeout(timeout);
|
|
|
|
mutex_lock(&bch_register_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
finish_wait(&unregister_wait, &wait);
|
|
|
|
|
|
|
|
if (stopped)
|
|
|
|
pr_info("All devices stopped");
|
|
|
|
else
|
|
|
|
pr_notice("Timeout waiting for devices to be closed");
|
|
|
|
out:
|
|
|
|
mutex_unlock(&bch_register_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
return NOTIFY_DONE;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct notifier_block reboot = {
|
|
|
|
.notifier_call = bcache_reboot,
|
|
|
|
.priority = INT_MAX, /* before any real devices */
|
|
|
|
};
|
|
|
|
|
|
|
|
static void bcache_exit(void)
|
|
|
|
{
|
|
|
|
bch_debug_exit();
|
|
|
|
bch_request_exit();
|
|
|
|
if (bcache_kobj)
|
|
|
|
kobject_put(bcache_kobj);
|
|
|
|
if (bcache_wq)
|
|
|
|
destroy_workqueue(bcache_wq);
|
2013-07-08 18:53:26 -06:00
|
|
|
if (bcache_major)
|
|
|
|
unregister_blkdev(bcache_major, "bcache");
|
2013-03-23 17:11:31 -06:00
|
|
|
unregister_reboot_notifier(&reboot);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __init bcache_init(void)
|
|
|
|
{
|
|
|
|
static const struct attribute *files[] = {
|
|
|
|
&ksysfs_register.attr,
|
|
|
|
&ksysfs_register_quiet.attr,
|
|
|
|
NULL
|
|
|
|
};
|
|
|
|
|
|
|
|
mutex_init(&bch_register_lock);
|
|
|
|
init_waitqueue_head(&unregister_wait);
|
|
|
|
register_reboot_notifier(&reboot);
|
2013-03-25 12:46:43 -06:00
|
|
|
closure_debug_init();
|
2013-03-23 17:11:31 -06:00
|
|
|
|
|
|
|
bcache_major = register_blkdev(0, "bcache");
|
|
|
|
if (bcache_major < 0)
|
|
|
|
return bcache_major;
|
|
|
|
|
|
|
|
if (!(bcache_wq = create_workqueue("bcache")) ||
|
|
|
|
!(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
|
|
|
|
sysfs_create_files(bcache_kobj, files) ||
|
|
|
|
bch_request_init() ||
|
|
|
|
bch_debug_init(bcache_kobj))
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
err:
|
|
|
|
bcache_exit();
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
module_exit(bcache_exit);
|
|
|
|
module_init(bcache_init);
|