This patch implements two methods to read jset from media for journal
replay,
- __jnl_rd_bkt() for block device
This is the legacy method to read jset via block device interface.
- __jnl_rd_nvm_bkt() for NVDIMM
This is the method to read jset from NVDIMM memory interface, a.k.a
memcopy() from NVDIMM pages to DRAM pages.
If BCH_FEATURE_INCOMPAT_NVDIMM_META is set in incompat feature set,
during running cache set, journal_read_bucket() will read the journal
content from NVDIMM by __jnl_rd_nvm_bkt(). The linear addresses of
NVDIMM pages to read jset are stored in sb.d[SB_JOURNAL_BUCKETS], which
were initialized and maintained in previous runs of the cache set.
A thing should be noticed is, when bch_journal_read() is called, the
linear address of NVDIMM pages is not loaded and initialized yet, it
is necessary to call __bch_journal_nvdimm_init() before reading the jset
from NVDIMM pages.
The code comments added in journal_read_bucket() is noticed by kernel
test robot and Dan Carpenter, it explains why it is safe to only check
!bch_has_feature_nvdimm_meta() condition in the if() statement when
CONFIG_BCACHE_NVM_PAGES is not configured. To avoid confusion from the
bogus warning message from static checking tool.
Signed-off-by: Coly Li <colyli@xxxxxxx>
Reported-by: kernel test robot <lkp@xxxxxxxxx>
Reported-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Hannes Reinecke <hare@xxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Jianpeng Ma <jianpeng.ma@xxxxxxxxx>
Cc: Qiaowei Ren <qiaowei.ren@xxxxxxxxx>
---
drivers/md/bcache/journal.c | 88 ++++++++++++++++++++++++++++++-------
1 file changed, 71 insertions(+), 17 deletions(-)
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 8cd0c4dc9137..987306b4db20 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -34,18 +34,60 @@ static void journal_read_endio(struct bio *bio)
closure_put(cl);
}
+static struct jset *__jnl_rd_bkt(struct cache *ca, unsigned int bkt_idx,
+ unsigned int len, unsigned int offset,
+ struct closure *cl)
+{
+ sector_t bucket = bucket_to_sector(ca->set, ca->sb.d[bkt_idx]);
+ struct bio *bio = &ca->journal.bio;
+ struct jset *data = ca->set->journal.w[0].data;
+
+ bio_reset(bio);
+ bio->bi_iter.bi_sector = bucket + offset;
+ bio_set_dev(bio, ca->bdev);
+ bio->bi_iter.bi_size = len << 9;
+
+ bio->bi_end_io = journal_read_endio;
+ bio->bi_private = cl;
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+ bch_bio_map(bio, data);
+
+ closure_bio_submit(ca->set, bio, cl);
+ closure_sync(cl);
+
+ /* Indeed journal.w[0].data */
+ return data;
+}
+
+#if defined(CONFIG_BCACHE_NVM_PAGES)
+
+static struct jset *__jnl_rd_nvm_bkt(struct cache *ca, unsigned int bkt_idx,
+ unsigned int len, unsigned int offset)
+{
+ void *jset_addr;
+ struct jset *data;
+
+ jset_addr = bch_nvmpg_offset_to_ptr(ca->sb.d[bkt_idx]) + (offset << 9);
+ data = ca->set->journal.w[0].data;
+
+ memcpy(data, jset_addr, len << 9);
+
+ /* Indeed journal.w[0].data */
+ return data;
+}
+
+#endif /* CONFIG_BCACHE_NVM_PAGES */
+
static int journal_read_bucket(struct cache *ca, struct list_head *list,
unsigned int bucket_index)
{
struct journal_device *ja = &ca->journal;
- struct bio *bio = &ja->bio;
struct journal_replay *i;
- struct jset *j, *data = ca->set->journal.w[0].data;
+ struct jset *j;
struct closure cl;
unsigned int len, left, offset = 0;
int ret = 0;
- sector_t bucket = bucket_to_sector(ca->set, ca->sb.d[bucket_index]);
closure_init_stack(&cl);
@@ -55,26 +97,27 @@ static int journal_read_bucket(struct cache *ca, struct list_head *list,
reread: left = ca->sb.bucket_size - offset;
len = min_t(unsigned int, left, PAGE_SECTORS << JSET_BITS);
- bio_reset(bio);
- bio->bi_iter.bi_sector = bucket + offset;
- bio_set_dev(bio, ca->bdev);
- bio->bi_iter.bi_size = len << 9;
-
- bio->bi_end_io = journal_read_endio;
- bio->bi_private = &cl;
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
- bch_bio_map(bio, data);
-
- closure_bio_submit(ca->set, bio, &cl);
- closure_sync(&cl);
+ if (!bch_has_feature_nvdimm_meta(&ca->sb))
+ j = __jnl_rd_bkt(ca, bucket_index, len, offset, &cl);
+ /*
+ * If CONFIG_BCACHE_NVM_PAGES is not defined, the feature bit
+ * BCH_FEATURE_INCOMPAT_NVDIMM_META won't in incompatible
+ * support feature set, a cache device format with feature bit
+ * BCH_FEATURE_INCOMPAT_NVDIMM_META will fail much earlier in
+ * read_super() by bch_has_unknown_incompat_features().
+ * Therefore when CONFIG_BCACHE_NVM_PAGES is not define, it is
+ * safe to ignore the bch_has_feature_nvdimm_meta() condition.
+ */
+#if defined(CONFIG_BCACHE_NVM_PAGES)
+ else
+ j = __jnl_rd_nvm_bkt(ca, bucket_index, len, offset);
+#endif
/* This function could be simpler now since we no longer write
* journal entries that overlap bucket boundaries; this means
* the start of a bucket will always have a valid journal entry
* if it has any journal entries at all.
*/
-
- j = data;
while (len) {
struct list_head *where;
size_t blocks, bytes = set_bytes(j);
@@ -170,6 +213,8 @@ reread: left = ca->sb.bucket_size - offset;
return ret;
}
+static int __bch_journal_nvdimm_init(struct cache *ca);
+
int bch_journal_read(struct cache_set *c, struct list_head *list)
{
#define read_bucket(b) \
@@ -188,6 +233,15 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
unsigned int i, l, r, m;
uint64_t seq;
+ /*
+ * Linear addresses of NVDIMM pages for journaling is not
+ * initialized yet, do it before read jset from NVDIMM pages.
+ */
+ if (bch_has_feature_nvdimm_meta(&ca->sb)) {
+ if (__bch_journal_nvdimm_init(ca) < 0)
+ return -ENXIO;
+ }
+
bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
pr_debug("%u journal buckets\n", ca->sb.njournal_buckets);
--
2.26.2
