From: Coly Li <colyli@suse.de>
To: axboe@kernel.dk
Cc: linux-bcache@vger.kernel.org, linux-block@vger.kernel.org,
jianpeng.ma@intel.com, qiaowei.ren@intel.com,
Coly Li <colyli@suse.de>
Subject: [PATCH 09/13] bcache: initialize bcache journal for NVDIMM meta device
Date: Wed, 14 Apr 2021 13:46:44 +0800 [thread overview]
Message-ID: <20210414054648.24098-10-colyli@suse.de> (raw)
In-Reply-To: <20210414054648.24098-1-colyli@suse.de>
The nvm-pages allocator may store and index the NVDIMM pages allocated
for bcache journal. This patch adds the initialization to store bcache
journal space on NVDIMM pages if BCH_FEATURE_INCOMPAT_NVDIMM_META bit is
set by bcache-tools.
If BCH_FEATURE_INCOMPAT_NVDIMM_META is set, get_nvdimm_journal_space()
will return the linear address of NVDIMM pages for bcache journal,
- If there is previously allocated space, find it from nvm-pages owner
list and return to bch_journal_init().
- If there is no previously allocated space, require a new NVDIMM range
from the nvm-pages allocator, and return it to bch_journal_init().
And in bch_journal_init(), keys in sb.d[] store the corresponding linear
address from NVDIMM into sb.d[i].ptr[0] where 'i' is the bucket index to
iterate all journal buckets.
Later when bcache journaling code stores the journaling jset, the target
NVDIMM linear address stored (and updated) in sb.d[i].ptr[0] can be used
directly in memory copy from DRAM pages into NVDIMM pages.
Signed-off-by: Coly Li <colyli@suse.de>
Cc: Jianpeng Ma <jianpeng.ma@intel.com>
Cc: Qiaowei Ren <qiaowei.ren@intel.com>
---
drivers/md/bcache/journal.c | 105 ++++++++++++++++++++++++++++++++++++
drivers/md/bcache/journal.h | 2 +-
drivers/md/bcache/super.c | 16 +++---
3 files changed, 115 insertions(+), 8 deletions(-)
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 61bd79babf7a..c26c6c568c65 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -9,6 +9,8 @@
#include "btree.h"
#include "debug.h"
#include "extents.h"
+#include "nvm-pages.h"
+#include "features.h"
#include <trace/events/bcache.h>
@@ -982,3 +984,106 @@ int bch_journal_alloc(struct cache_set *c)
return 0;
}
+
+#ifdef CONFIG_BCACHE_NVM_PAGES
+
+static void *find_journal_nvm_base(struct bch_nvm_pages_owner_head *owner_list,
+ struct cache *ca)
+{
+ unsigned long addr = 0;
+ struct bch_nvm_pgalloc_recs *recs_list = owner_list->recs[0];
+
+ while (recs_list) {
+ struct bch_pgalloc_rec *rec;
+ unsigned long jnl_pgoff;
+ int i;
+
+ jnl_pgoff = ((unsigned long)ca->sb.d[0]) >> PAGE_SHIFT;
+ rec = recs_list->recs;
+ for (i = 0; i < recs_list->used; i++) {
+ if (rec->pgoff == jnl_pgoff)
+ break;
+ rec++;
+ }
+ if (i < recs_list->used) {
+ addr = rec->pgoff << PAGE_SHIFT;
+ break;
+ }
+ recs_list = recs_list->next;
+ }
+ return (void *)addr;
+}
+
+static void *get_nvdimm_journal_space(struct cache *ca)
+{
+ struct bch_nvm_pages_owner_head *owner_list = NULL;
+ void *ret = NULL;
+ int order;
+
+ owner_list = bch_get_allocated_pages(ca->sb.set_uuid);
+ if (owner_list) {
+ ret = find_journal_nvm_base(owner_list, ca);
+ if (ret)
+ goto found;
+ }
+
+ order = ilog2(ca->sb.bucket_size *
+ ca->sb.njournal_buckets / PAGE_SECTORS);
+ ret = bch_nvm_alloc_pages(order, ca->sb.set_uuid);
+ if (ret)
+ memset(ret, 0, (1 << order) * PAGE_SIZE);
+
+found:
+ return ret;
+}
+
+static int __bch_journal_nvdimm_init(struct cache *ca)
+{
+ int i, ret = 0;
+ void *journal_nvm_base = NULL;
+
+ journal_nvm_base = get_nvdimm_journal_space(ca);
+ if (!journal_nvm_base) {
+ pr_err("Failed to get journal space from nvdimm\n");
+ ret = -1;
+ goto out;
+ }
+
+ /* Iniialized and reloaded from on-disk super block already */
+ if (ca->sb.d[0] != 0)
+ goto out;
+
+ for (i = 0; i < ca->sb.keys; i++)
+ ca->sb.d[i] =
+ (u64)(journal_nvm_base + (ca->sb.bucket_size * i));
+
+out:
+ return ret;
+}
+
+#else /* CONFIG_BCACHE_NVM_PAGES */
+
+static int __bch_journal_nvdimm_init(struct cache *ca)
+{
+ return -1;
+}
+
+#endif /* CONFIG_BCACHE_NVM_PAGES */
+
+int bch_journal_init(struct cache_set *c)
+{
+ int i, ret = 0;
+ struct cache *ca = c->cache;
+
+ ca->sb.keys = clamp_t(int, ca->sb.nbuckets >> 7,
+ 2, SB_JOURNAL_BUCKETS);
+
+ if (!bch_has_feature_nvdimm_meta(&ca->sb)) {
+ for (i = 0; i < ca->sb.keys; i++)
+ ca->sb.d[i] = ca->sb.first_bucket + i;
+ } else {
+ ret = __bch_journal_nvdimm_init(ca);
+ }
+
+ return ret;
+}
diff --git a/drivers/md/bcache/journal.h b/drivers/md/bcache/journal.h
index f2ea34d5f431..e3a7fa5a8fda 100644
--- a/drivers/md/bcache/journal.h
+++ b/drivers/md/bcache/journal.h
@@ -179,7 +179,7 @@ void bch_journal_mark(struct cache_set *c, struct list_head *list);
void bch_journal_meta(struct cache_set *c, struct closure *cl);
int bch_journal_read(struct cache_set *c, struct list_head *list);
int bch_journal_replay(struct cache_set *c, struct list_head *list);
-
+int bch_journal_init(struct cache_set *c);
void bch_journal_free(struct cache_set *c);
int bch_journal_alloc(struct cache_set *c);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 20f675731927..728a87af851f 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -146,10 +146,15 @@ static const char *read_super_common(struct cache_sb *sb, struct block_device *
goto err;
err = "Journal buckets not sequential";
+#ifdef CONFIG_BCACHE_NVM_PAGES
+ if (!bch_has_feature_nvdimm_meta(sb)) {
+#endif
for (i = 0; i < sb->keys; i++)
if (sb->d[i] != sb->first_bucket + i)
goto err;
-
+#ifdef CONFIG_BCACHE_NVM_PAGES
+ } /* bch_has_feature_nvdimm_meta */
+#endif
err = "Too many journal buckets";
if (sb->first_bucket + sb->keys > sb->nbuckets)
goto err;
@@ -2071,14 +2076,11 @@ static int run_cache_set(struct cache_set *c)
if (bch_journal_replay(c, &journal))
goto err;
} else {
- unsigned int j;
-
pr_notice("invalidating existing data\n");
- 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;
+ err = "error initializing journal";
+ if (bch_journal_init(c))
+ goto err;
bch_initial_gc_finish(c);
--
2.26.2
next prev parent reply other threads:[~2021-04-14 5:47 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-14 5:46 [PATCH 00/13] bcache patches for Linux v5.13 -- 2nd wave Coly Li
2021-04-14 5:46 ` [PATCH 01/13] bcache: add initial data structures for nvm pages Coly Li
2021-04-14 5:46 ` [PATCH 02/13] bcache: initialize the nvm pages allocator Coly Li
2021-04-14 5:46 ` [PATCH 03/13] bcache: initialization of the buddy Coly Li
2021-04-14 5:46 ` [PATCH 04/13] bcache: bch_nvm_alloc_pages() " Coly Li
2021-04-14 5:46 ` [PATCH 05/13] bcache: bch_nvm_free_pages() " Coly Li
2021-04-14 5:46 ` [PATCH 06/13] bcache: get allocated pages from specific owner Coly Li
2021-04-14 5:46 ` [PATCH 07/13] bcache: use bucket index to set GC_MARK_METADATA for journal buckets in bch_btree_gc_finish() Coly Li
2021-04-14 5:46 ` [PATCH 08/13] bcache: add BCH_FEATURE_INCOMPAT_NVDIMM_META into incompat feature set Coly Li
2021-04-14 5:46 ` Coly Li [this message]
2021-04-14 5:46 ` [PATCH 10/13] bcache: support storing bcache journal into NVDIMM meta device Coly Li
2021-04-14 5:46 ` [PATCH 11/13] bcache: read jset from NVDIMM pages for journal replay Coly Li
2021-04-14 5:46 ` [PATCH 12/13] bcache: add sysfs interface register_nvdimm_meta to register NVDIMM meta device Coly Li
2021-04-14 5:46 ` [PATCH 13/13] bcache: use div_u64() in init_owner_info() Coly Li
2021-04-16 12:01 ` Jens Axboe
2021-04-16 3:55 ` [PATCH 00/13] bcache patches for Linux v5.13 -- 2nd wave Coly Li
2021-04-16 12:02 ` Jens Axboe
2021-04-16 12:26 ` 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=20210414054648.24098-10-colyli@suse.de \
--to=colyli@suse.de \
--cc=axboe@kernel.dk \
--cc=jianpeng.ma@intel.com \
--cc=linux-bcache@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=qiaowei.ren@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).