aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/md/bcache
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/bcache')
-rw-r--r--drivers/md/bcache/bcache.h3
-rw-r--r--drivers/md/bcache/bset.c2
-rw-r--r--drivers/md/bcache/btree.c22
-rw-r--r--drivers/md/bcache/journal.c4
-rw-r--r--drivers/md/bcache/super.c19
-rw-r--r--drivers/md/bcache/writeback.c14
-rw-r--r--drivers/md/bcache/writeback.h19
7 files changed, 61 insertions, 22 deletions
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 2a2f189dd37c..6a380ed4919a 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -264,7 +264,7 @@ struct bcache_device {
#define BCACHE_DEV_UNLINK_DONE 2
#define BCACHE_DEV_WB_RUNNING 3
#define BCACHE_DEV_RATE_DW_RUNNING 4
- unsigned int nr_stripes;
+ int nr_stripes;
unsigned int stripe_size;
atomic_t *stripe_sectors_dirty;
unsigned long *full_dirty_stripes;
@@ -585,6 +585,7 @@ struct cache_set {
*/
wait_queue_head_t btree_cache_wait;
struct task_struct *btree_cache_alloc_lock;
+ spinlock_t btree_cannibalize_lock;
/*
* When we free a btree node, we increment the gen of the bucket the
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 268f1b685084..ec48cf86cab6 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -321,7 +321,7 @@ int bch_btree_keys_alloc(struct btree_keys *b,
b->page_order = page_order;
- t->data = (void *) __get_free_pages(gfp, b->page_order);
+ t->data = (void *) __get_free_pages(__GFP_COMP|gfp, b->page_order);
if (!t->data)
goto err;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index bb40bd66a10e..e388e7bb7b5d 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -830,7 +830,7 @@ int bch_btree_cache_alloc(struct cache_set *c)
mutex_init(&c->verify_lock);
c->verify_ondisk = (void *)
- __get_free_pages(GFP_KERNEL, ilog2(bucket_pages(c)));
+ __get_free_pages(GFP_KERNEL|__GFP_COMP, ilog2(bucket_pages(c)));
c->verify_data = mca_bucket_alloc(c, &ZERO_KEY, GFP_KERNEL);
@@ -876,15 +876,17 @@ out:
static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op)
{
- struct task_struct *old;
-
- old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current);
- if (old && old != current) {
+ spin_lock(&c->btree_cannibalize_lock);
+ if (likely(c->btree_cache_alloc_lock == NULL)) {
+ c->btree_cache_alloc_lock = current;
+ } else if (c->btree_cache_alloc_lock != current) {
if (op)
prepare_to_wait(&c->btree_cache_wait, &op->wait,
TASK_UNINTERRUPTIBLE);
+ spin_unlock(&c->btree_cannibalize_lock);
return -EINTR;
}
+ spin_unlock(&c->btree_cannibalize_lock);
return 0;
}
@@ -919,10 +921,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op,
*/
static void bch_cannibalize_unlock(struct cache_set *c)
{
+ spin_lock(&c->btree_cannibalize_lock);
if (c->btree_cache_alloc_lock == current) {
c->btree_cache_alloc_lock = NULL;
wake_up(&c->btree_cache_wait);
}
+ spin_unlock(&c->btree_cannibalize_lock);
}
static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op,
@@ -1432,7 +1436,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
if (__set_blocks(n1, n1->keys + n2->keys,
block_bytes(b->c)) >
btree_blocks(new_nodes[i]))
- goto out_nocoalesce;
+ goto out_unlock_nocoalesce;
keys = n2->keys;
/* Take the key of the node we're getting rid of */
@@ -1461,7 +1465,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
if (__bch_keylist_realloc(&keylist,
bkey_u64s(&new_nodes[i]->key)))
- goto out_nocoalesce;
+ goto out_unlock_nocoalesce;
bch_btree_node_write(new_nodes[i], &cl);
bch_keylist_add(&keylist, &new_nodes[i]->key);
@@ -1507,6 +1511,10 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
/* Invalidated our iterator */
return -EINTR;
+out_unlock_nocoalesce:
+ for (i = 0; i < nodes; i++)
+ mutex_unlock(&new_nodes[i]->write_lock);
+
out_nocoalesce:
closure_sync(&cl);
bch_keylist_free(&keylist);
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 7bb15cddca5e..182c2b7bd960 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -864,8 +864,8 @@ int bch_journal_alloc(struct cache_set *c)
j->w[1].c = c;
if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
- !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) ||
- !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)))
+ !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS)) ||
+ !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS)))
return -ENOMEM;
return 0;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 5b5cbfadd003..7787ec42f81e 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -775,7 +775,9 @@ static void bcache_device_free(struct bcache_device *d)
bcache_device_detach(d);
if (disk) {
- if (disk->flags & GENHD_FL_UP)
+ bool disk_added = (disk->flags & GENHD_FL_UP) != 0;
+
+ if (disk_added)
del_gendisk(disk);
if (disk->queue)
@@ -783,7 +785,8 @@ static void bcache_device_free(struct bcache_device *d)
ida_simple_remove(&bcache_device_idx,
first_minor_to_idx(disk->first_minor));
- put_disk(disk);
+ if (disk_added)
+ put_disk(disk);
}
bioset_exit(&d->bio_split);
@@ -1690,7 +1693,7 @@ void bch_cache_set_unregister(struct cache_set *c)
}
#define alloc_bucket_pages(gfp, c) \
- ((void *) __get_free_pages(__GFP_ZERO|gfp, ilog2(bucket_pages(c))))
+ ((void *) __get_free_pages(__GFP_ZERO|__GFP_COMP|gfp, ilog2(bucket_pages(c))))
struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
{
@@ -1734,6 +1737,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
sema_init(&c->sb_write_mutex, 1);
mutex_init(&c->bucket_lock);
init_waitqueue_head(&c->btree_cache_wait);
+ spin_lock_init(&c->btree_cannibalize_lock);
init_waitqueue_head(&c->bucket_wait);
init_waitqueue_head(&c->gc_wait);
sema_init(&c->uuid_write_mutex, 1);
@@ -2010,7 +2014,14 @@ found:
sysfs_create_link(&c->kobj, &ca->kobj, buf))
goto err;
- if (ca->sb.seq > c->sb.seq) {
+ /*
+ * A special case is both ca->sb.seq and c->sb.seq are 0,
+ * such condition happens on a new created cache device whose
+ * super block is never flushed yet. In this case c->sb.version
+ * and other members should be updated too, otherwise we will
+ * have a mistaken super block version in cache set.
+ */
+ if (ca->sb.seq > c->sb.seq || c->sb.seq == 0) {
c->sb.version = ca->sb.version;
memcpy(c->sb.set_uuid, ca->sb.set_uuid, 16);
c->sb.flags = ca->sb.flags;
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index b5fc3c6c7178..aa58833fb012 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -506,15 +506,19 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned int inode,
uint64_t offset, int nr_sectors)
{
struct bcache_device *d = c->devices[inode];
- unsigned int stripe_offset, stripe, sectors_dirty;
+ unsigned int stripe_offset, sectors_dirty;
+ int stripe;
if (!d)
return;
+ stripe = offset_to_stripe(d, offset);
+ if (stripe < 0)
+ return;
+
if (UUID_FLASH_ONLY(&c->uuids[inode]))
atomic_long_add(nr_sectors, &c->flash_dev_dirty_sectors);
- stripe = offset_to_stripe(d, offset);
stripe_offset = offset & (d->stripe_size - 1);
while (nr_sectors) {
@@ -554,12 +558,12 @@ static bool dirty_pred(struct keybuf *buf, struct bkey *k)
static void refill_full_stripes(struct cached_dev *dc)
{
struct keybuf *buf = &dc->writeback_keys;
- unsigned int start_stripe, stripe, next_stripe;
+ unsigned int start_stripe, next_stripe;
+ int stripe;
bool wrapped = false;
stripe = offset_to_stripe(&dc->disk, KEY_OFFSET(&buf->last_scanned));
-
- if (stripe >= dc->disk.nr_stripes)
+ if (stripe < 0)
stripe = 0;
start_stripe = stripe;
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index e75dc33339f6..b902e574c5c4 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -28,10 +28,22 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
return ret;
}
-static inline unsigned int offset_to_stripe(struct bcache_device *d,
+static inline int offset_to_stripe(struct bcache_device *d,
uint64_t offset)
{
do_div(offset, d->stripe_size);
+
+ /* d->nr_stripes is in range [1, INT_MAX] */
+ if (unlikely(offset >= d->nr_stripes)) {
+ pr_err("Invalid stripe %llu (>= nr_stripes %d).\n",
+ offset, d->nr_stripes);
+ return -EINVAL;
+ }
+
+ /*
+ * Here offset is definitly smaller than INT_MAX,
+ * return it as int will never overflow.
+ */
return offset;
}
@@ -39,7 +51,10 @@ static inline bool bcache_dev_stripe_dirty(struct cached_dev *dc,
uint64_t offset,
unsigned int nr_sectors)
{
- unsigned int stripe = offset_to_stripe(&dc->disk, offset);
+ int stripe = offset_to_stripe(&dc->disk, offset);
+
+ if (stripe < 0)
+ return false;
while (1) {
if (atomic_read(dc->disk.stripe_sectors_dirty + stripe))
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-19 08:31:24 +0000