From: Coly Li <colyli@suse.de>
To: linux-bcache@vger.kernel.org
Cc: linux-block@vger.kernel.org, linux-nvdimm@lists.linux.dev,
axboe@kernel.dk, hare@suse.com, jack@suse.cz,
dan.j.williams@intel.com, hch@lst.de, ying.huang@intel.com,
Coly Li <colyli@suse.de>, Hannes Reinecke <hare@suse.de>,
Jianpeng Ma <jianpeng.ma@intel.com>,
Qiaowei Ren <qiaowei.ren@intel.com>
Subject: [PATCH v12 10/12] bcache: support storing bcache journal into NVDIMM meta device
Date: Thu, 12 Aug 2021 01:02:22 +0800 [thread overview]
Message-ID: <20210811170224.42837-11-colyli@suse.de> (raw)
In-Reply-To: <20210811170224.42837-1-colyli@suse.de>
This patch implements two methods to store bcache journal to,
1) __journal_write_unlocked() for block interface device
The latency method to compose bio and issue the jset bio to cache
device (e.g. SSD). c->journal.key.ptr[0] indicates the LBA on cache
device to store the journal jset.
2) __journal_nvdimm_write_unlocked() for memory interface NVDIMM
Use memory interface to access NVDIMM pages and store the jset by
memcpy_flushcache(). c->journal.key.ptr[0] indicates the linear
address from the NVDIMM pages to store the journal jset.
For legacy configuration without NVDIMM meta device, journal I/O is
handled by __journal_write_unlocked() with existing code logic. If the
NVDIMM meta device is used (by bcache-tools), the journal I/O will
be handled by __journal_nvdimm_write_unlocked() and go into the NVDIMM
pages.
And when NVDIMM meta device is used, sb.d[] stores the linear addresses
from NVDIMM pages (no more bucket index), in journal_reclaim() the
journaling location in c->journal.key.ptr[0] should also be updated by
linear address from NVDIMM pages (no more LBA combined by sectors offset
and bucket index).
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jianpeng Ma <jianpeng.ma@intel.com>
Cc: Qiaowei Ren <qiaowei.ren@intel.com>
---
drivers/md/bcache/journal.c | 120 +++++++++++++++++++++++++-----------
drivers/md/bcache/super.c | 3 +-
2 files changed, 85 insertions(+), 38 deletions(-)
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 9fe6c1abfd84..8cd0c4dc9137 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -596,6 +596,8 @@ static void do_journal_discard(struct cache *ca)
return;
}
+ BUG_ON(bch_has_feature_nvdimm_meta(&ca->sb));
+
switch (atomic_read(&ja->discard_in_flight)) {
case DISCARD_IN_FLIGHT:
return;
@@ -661,9 +663,16 @@ static void journal_reclaim(struct cache_set *c)
goto out;
ja->cur_idx = next;
- k->ptr[0] = MAKE_PTR(0,
- bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
- ca->sb.nr_this_dev);
+ if (!bch_has_feature_nvdimm_meta(&ca->sb))
+ k->ptr[0] = MAKE_PTR(0,
+ bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
+ ca->sb.nr_this_dev);
+#if defined(CONFIG_BCACHE_NVM_PAGES)
+ else
+ k->ptr[0] = (unsigned long)bch_nvmpg_offset_to_ptr(
+ ca->sb.d[ja->cur_idx]);
+#endif
+
atomic_long_inc(&c->reclaimed_journal_buckets);
bkey_init(k);
@@ -729,46 +738,21 @@ static void journal_write_unlock(struct closure *cl)
spin_unlock(&c->journal.lock);
}
-static void journal_write_unlocked(struct closure *cl)
+
+static void __journal_write_unlocked(struct cache_set *c)
__releases(c->journal.lock)
{
- struct cache_set *c = container_of(cl, struct cache_set, journal.io);
- struct cache *ca = c->cache;
- struct journal_write *w = c->journal.cur;
struct bkey *k = &c->journal.key;
- unsigned int i, sectors = set_blocks(w->data, block_bytes(ca)) *
- ca->sb.block_size;
-
+ struct journal_write *w = c->journal.cur;
+ struct closure *cl = &c->journal.io;
+ struct cache *ca = c->cache;
struct bio *bio;
struct bio_list list;
+ unsigned int i, sectors = set_blocks(w->data, block_bytes(ca)) *
+ ca->sb.block_size;
bio_list_init(&list);
- if (!w->need_write) {
- closure_return_with_destructor(cl, journal_write_unlock);
- return;
- } else if (journal_full(&c->journal)) {
- journal_reclaim(c);
- spin_unlock(&c->journal.lock);
-
- btree_flush_write(c);
- continue_at(cl, journal_write, bch_journal_wq);
- return;
- }
-
- c->journal.blocks_free -= set_blocks(w->data, block_bytes(ca));
-
- w->data->btree_level = c->root->level;
-
- bkey_copy(&w->data->btree_root, &c->root->key);
- bkey_copy(&w->data->uuid_bucket, &c->uuid_bucket);
-
- w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
- w->data->magic = jset_magic(&ca->sb);
- w->data->version = BCACHE_JSET_VERSION;
- w->data->last_seq = last_seq(&c->journal);
- w->data->csum = csum_set(w->data);
-
for (i = 0; i < KEY_PTRS(k); i++) {
ca = c->cache;
bio = &ca->journal.bio;
@@ -793,7 +777,6 @@ static void journal_write_unlocked(struct closure *cl)
ca->journal.seq[ca->journal.cur_idx] = w->data->seq;
}
-
/* If KEY_PTRS(k) == 0, this jset gets lost in air */
BUG_ON(i == 0);
@@ -805,6 +788,71 @@ static void journal_write_unlocked(struct closure *cl)
while ((bio = bio_list_pop(&list)))
closure_bio_submit(c, bio, cl);
+}
+
+#if defined(CONFIG_BCACHE_NVM_PAGES)
+
+static void __journal_nvdimm_write_unlocked(struct cache_set *c)
+ __releases(c->journal.lock)
+{
+ struct journal_write *w = c->journal.cur;
+ struct cache *ca = c->cache;
+ unsigned int sectors;
+
+ sectors = set_blocks(w->data, block_bytes(ca)) * ca->sb.block_size;
+ atomic_long_add(sectors, &ca->meta_sectors_written);
+
+ memcpy_flushcache((void *)c->journal.key.ptr[0], w->data, sectors << 9);
+
+ c->journal.key.ptr[0] += sectors << 9;
+ ca->journal.seq[ca->journal.cur_idx] = w->data->seq;
+
+ atomic_dec_bug(&fifo_back(&c->journal.pin));
+ bch_journal_next(&c->journal);
+ journal_reclaim(c);
+
+ spin_unlock(&c->journal.lock);
+}
+
+#endif /* CONFIG_BCACHE_NVM_PAGES */
+
+static void journal_write_unlocked(struct closure *cl)
+{
+ struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+ struct cache *ca = c->cache;
+ struct journal_write *w = c->journal.cur;
+
+ if (!w->need_write) {
+ closure_return_with_destructor(cl, journal_write_unlock);
+ return;
+ } else if (journal_full(&c->journal)) {
+ journal_reclaim(c);
+ spin_unlock(&c->journal.lock);
+
+ btree_flush_write(c);
+ continue_at(cl, journal_write, bch_journal_wq);
+ return;
+ }
+
+ c->journal.blocks_free -= set_blocks(w->data, block_bytes(ca));
+
+ w->data->btree_level = c->root->level;
+
+ bkey_copy(&w->data->btree_root, &c->root->key);
+ bkey_copy(&w->data->uuid_bucket, &c->uuid_bucket);
+
+ w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
+ w->data->magic = jset_magic(&ca->sb);
+ w->data->version = BCACHE_JSET_VERSION;
+ w->data->last_seq = last_seq(&c->journal);
+ w->data->csum = csum_set(w->data);
+
+ if (!bch_has_feature_nvdimm_meta(&ca->sb))
+ __journal_write_unlocked(c);
+#if defined(CONFIG_BCACHE_NVM_PAGES)
+ else
+ __journal_nvdimm_write_unlocked(c);
+#endif
continue_at(cl, journal_write_done, NULL);
}
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index e66e1d6ef260..24734250d005 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1676,7 +1676,7 @@ void bch_cache_set_release(struct kobject *kobj)
static void cache_set_free(struct closure *cl)
{
struct cache_set *c = container_of(cl, struct cache_set, cl);
- struct cache *ca;
+ struct cache *ca = c->cache;
debugfs_remove(c->debug);
@@ -1688,7 +1688,6 @@ static void cache_set_free(struct closure *cl)
bch_bset_sort_state_free(&c->sort);
free_pages((unsigned long) c->uuids, ilog2(meta_bucket_pages(&c->cache->sb)));
- ca = c->cache;
if (ca) {
ca->set = NULL;
c->cache = NULL;
--
2.26.2
next prev parent reply other threads:[~2021-08-11 17:05 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-11 17:02 [PATCH v12 00/12] bcache: support NVDIMM for journaling Coly Li
2021-08-11 17:02 ` [PATCH v12 01/12] bcache: add initial data structures for nvm pages Coly Li
2021-08-11 17:02 ` [PATCH v12 02/12] bcache: initialize the nvm pages allocator Coly Li
2021-08-12 5:43 ` Dan Williams
2021-08-12 8:26 ` Coly Li
2021-08-11 17:02 ` [PATCH v12 03/12] bcache: initialization of the buddy Coly Li
2021-08-11 17:02 ` [PATCH v12 04/12] bcache: bch_nvmpg_alloc_pages() " Coly Li
2021-08-11 17:02 ` [PATCH v12 05/12] bcache: bch_nvmpg_free_pages() of the buddy allocator Coly Li
2021-08-11 17:02 ` [PATCH v12 06/12] bcache: get recs list head for allocated pages by specific uuid Coly Li
2021-08-11 17:02 ` [PATCH v12 07/12] bcache: use bucket index to set GC_MARK_METADATA for journal buckets in bch_btree_gc_finish() Coly Li
2021-08-11 17:02 ` [PATCH v12 08/12] bcache: add BCH_FEATURE_INCOMPAT_NVDIMM_META into incompat feature set Coly Li
2021-08-11 17:02 ` [PATCH v12 09/12] bcache: initialize bcache journal for NVDIMM meta device Coly Li
2021-08-11 17:02 ` Coly Li [this message]
2021-08-11 17:02 ` [PATCH v12 11/12] bcache: read jset from NVDIMM pages for journal replay Coly Li
2021-08-11 17:02 ` [PATCH v12 12/12] bcache: add sysfs interface register_nvdimm_meta to register NVDIMM meta device Coly Li
2021-08-15 16:21 ` [PATCH v12 00/12] bcache: support NVDIMM for journaling Coly Li
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210811170224.42837-11-colyli@suse.de \
--to=colyli@suse.de \
--cc=axboe@kernel.dk \
--cc=dan.j.williams@intel.com \
--cc=hare@suse.com \
--cc=hare@suse.de \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=jianpeng.ma@intel.com \
--cc=linux-bcache@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-nvdimm@lists.linux.dev \
--cc=qiaowei.ren@intel.com \
--cc=ying.huang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).