summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bcache/bset.c16
-rw-r--r--drivers/md/bcache/bset.h34
-rw-r--r--drivers/md/bcache/sysfs.c7
-rw-r--r--drivers/md/dm-log-writes.c23
-rw-r--r--drivers/md/md.c36
-rw-r--r--drivers/md/raid0.c2
6 files changed, 84 insertions, 34 deletions
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 8f07fa6e1739..268f1b685084 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -887,12 +887,22 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
struct bset *i = bset_tree_last(b)->data;
struct bkey *m, *prev = NULL;
struct btree_iter iter;
+ struct bkey preceding_key_on_stack = ZERO_KEY;
+ struct bkey *preceding_key_p = &preceding_key_on_stack;
BUG_ON(b->ops->is_extents && !KEY_SIZE(k));
- m = bch_btree_iter_init(b, &iter, b->ops->is_extents
- ? PRECEDING_KEY(&START_KEY(k))
- : PRECEDING_KEY(k));
+ /*
+ * If k has preceding key, preceding_key_p will be set to address
+ * of k's preceding key; otherwise preceding_key_p will be set
+ * to NULL inside preceding_key().
+ */
+ if (b->ops->is_extents)
+ preceding_key(&START_KEY(k), &preceding_key_p);
+ else
+ preceding_key(k, &preceding_key_p);
+
+ m = bch_btree_iter_init(b, &iter, preceding_key_p);
if (b->ops->insert_fixup(b, k, &iter, replace_key))
return status;
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index bac76aabca6d..c71365e7c1fa 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -434,20 +434,26 @@ static inline bool bch_cut_back(const struct bkey *where, struct bkey *k)
return __bch_cut_back(where, k);
}
-#define PRECEDING_KEY(_k) \
-({ \
- struct bkey *_ret = NULL; \
- \
- if (KEY_INODE(_k) || KEY_OFFSET(_k)) { \
- _ret = &KEY(KEY_INODE(_k), KEY_OFFSET(_k), 0); \
- \
- if (!_ret->low) \
- _ret->high--; \
- _ret->low--; \
- } \
- \
- _ret; \
-})
+/*
+ * Pointer '*preceding_key_p' points to a memory object to store preceding
+ * key of k. If the preceding key does not exist, set '*preceding_key_p' to
+ * NULL. So the caller of preceding_key() needs to take care of memory
+ * which '*preceding_key_p' pointed to before calling preceding_key().
+ * Currently the only caller of preceding_key() is bch_btree_insert_key(),
+ * and it points to an on-stack variable, so the memory release is handled
+ * by stackframe itself.
+ */
+static inline void preceding_key(struct bkey *k, struct bkey **preceding_key_p)
+{
+ if (KEY_INODE(k) || KEY_OFFSET(k)) {
+ (**preceding_key_p) = KEY(KEY_INODE(k), KEY_OFFSET(k), 0);
+ if (!(*preceding_key_p)->low)
+ (*preceding_key_p)->high--;
+ (*preceding_key_p)->low--;
+ } else {
+ (*preceding_key_p) = NULL;
+ }
+}
static inline bool bch_ptr_invalid(struct btree_keys *b, const struct bkey *k)
{
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index d9481640b3e1..541454b4f479 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -393,8 +393,13 @@ STORE(bch_cached_dev)
if (attr == &sysfs_writeback_running)
bch_writeback_queue(dc);
+ /*
+ * Only set BCACHE_DEV_WB_RUNNING when cached device attached to
+ * a cache set, otherwise it doesn't make sense.
+ */
if (attr == &sysfs_writeback_percent)
- if (!test_and_set_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
+ if ((dc->disk.c != NULL) &&
+ (!test_and_set_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags)))
schedule_delayed_work(&dc->writeback_rate_update,
dc->writeback_rate_update_seconds * HZ);
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 9ea2b0291f20..e549392e0ea5 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -60,6 +60,7 @@
#define WRITE_LOG_VERSION 1ULL
#define WRITE_LOG_MAGIC 0x6a736677736872ULL
+#define WRITE_LOG_SUPER_SECTOR 0
/*
* The disk format for this is braindead simple.
@@ -115,6 +116,7 @@ struct log_writes_c {
struct list_head logging_blocks;
wait_queue_head_t wait;
struct task_struct *log_kthread;
+ struct completion super_done;
};
struct pending_block {
@@ -180,6 +182,14 @@ static void log_end_io(struct bio *bio)
bio_put(bio);
}
+static void log_end_super(struct bio *bio)
+{
+ struct log_writes_c *lc = bio->bi_private;
+
+ complete(&lc->super_done);
+ log_end_io(bio);
+}
+
/*
* Meant to be called if there is an error, it will free all the pages
* associated with the block.
@@ -215,7 +225,8 @@ static int write_metadata(struct log_writes_c *lc, void *entry,
bio->bi_iter.bi_size = 0;
bio->bi_iter.bi_sector = sector;
bio_set_dev(bio, lc->logdev->bdev);
- bio->bi_end_io = log_end_io;
+ bio->bi_end_io = (sector == WRITE_LOG_SUPER_SECTOR) ?
+ log_end_super : log_end_io;
bio->bi_private = lc;
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
@@ -418,11 +429,18 @@ static int log_super(struct log_writes_c *lc)
super.nr_entries = cpu_to_le64(lc->logged_entries);
super.sectorsize = cpu_to_le32(lc->sectorsize);
- if (write_metadata(lc, &super, sizeof(super), NULL, 0, 0)) {
+ if (write_metadata(lc, &super, sizeof(super), NULL, 0,
+ WRITE_LOG_SUPER_SECTOR)) {
DMERR("Couldn't write super");
return -1;
}
+ /*
+ * Super sector should be writen in-order, otherwise the
+ * nr_entries could be rewritten incorrectly by an old bio.
+ */
+ wait_for_completion_io(&lc->super_done);
+
return 0;
}
@@ -531,6 +549,7 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv)
INIT_LIST_HEAD(&lc->unflushed_blocks);
INIT_LIST_HEAD(&lc->logging_blocks);
init_waitqueue_head(&lc->wait);
+ init_completion(&lc->super_done);
atomic_set(&lc->io_blocks, 0);
atomic_set(&lc->pending_blocks, 0);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b924f62e2cd5..fb5d702e43b5 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -7625,9 +7625,9 @@ static void status_unused(struct seq_file *seq)
static int status_resync(struct seq_file *seq, struct mddev *mddev)
{
sector_t max_sectors, resync, res;
- unsigned long dt, db;
- sector_t rt;
- int scale;
+ unsigned long dt, db = 0;
+ sector_t rt, curr_mark_cnt, resync_mark_cnt;
+ int scale, recovery_active;
unsigned int per_milli;
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
@@ -7716,22 +7716,30 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
* db: blocks written from mark until now
* rt: remaining time
*
- * rt is a sector_t, so could be 32bit or 64bit.
- * So we divide before multiply in case it is 32bit and close
- * to the limit.
- * We scale the divisor (db) by 32 to avoid losing precision
- * near the end of resync when the number of remaining sectors
- * is close to 'db'.
- * We then divide rt by 32 after multiplying by db to compensate.
- * The '+1' avoids division by zero if db is very small.
+ * rt is a sector_t, which is always 64bit now. We are keeping
+ * the original algorithm, but it is not really necessary.
+ *
+ * Original algorithm:
+ * So we divide before multiply in case it is 32bit and close
+ * to the limit.
+ * We scale the divisor (db) by 32 to avoid losing precision
+ * near the end of resync when the number of remaining sectors
+ * is close to 'db'.
+ * We then divide rt by 32 after multiplying by db to compensate.
+ * The '+1' avoids division by zero if db is very small.
*/
dt = ((jiffies - mddev->resync_mark) / HZ);
if (!dt) dt++;
- db = (mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active))
- - mddev->resync_mark_cnt;
+
+ curr_mark_cnt = mddev->curr_mark_cnt;
+ recovery_active = atomic_read(&mddev->recovery_active);
+ resync_mark_cnt = mddev->resync_mark_cnt;
+
+ if (curr_mark_cnt >= (recovery_active + resync_mark_cnt))
+ db = curr_mark_cnt - (recovery_active + resync_mark_cnt);
rt = max_sectors - resync; /* number of remaining sectors */
- sector_div(rt, db/32+1);
+ rt = div64_u64(rt, db/32+1);
rt *= dt;
rt >>= 5;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index ac1cffd2a09b..f4daa56d204d 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -547,6 +547,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
trace_block_bio_remap(bdev_get_queue(rdev->bdev),
discard_bio, disk_devt(mddev->gendisk),
bio->bi_iter.bi_sector);
+ bio_clear_flag(bio, BIO_QUEUE_ENTERED);
generic_make_request(discard_bio);
}
bio_endio(bio);
@@ -602,6 +603,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
disk_devt(mddev->gendisk), bio_sector);
mddev_check_writesame(mddev, bio);
mddev_check_write_zeroes(mddev, bio);
+ bio_clear_flag(bio, BIO_QUEUE_ENTERED);
generic_make_request(bio);
return true;
}
generated by cgit v1.2.3 (git 2.0.4) at 2024-04-28 16:12:33 +0000