Linux-bcache Archive on lore.kernel.org
 help / color / Atom feed
From: Coly Li <colyli@suse.de>
To: axboe@kernel.dk
Cc: linux-bcache@vger.kernel.org, linux-block@vger.kernel.org,
	Coly Li <colyli@suse.de>, Jianpeng Ma <jianpeng.ma@intel.com>,
	Qiaowei Ren <qiaowei.ren@intel.com>
Subject: [PATCH 16/20] bcache: initialize bcache journal for NVDIMM meta device
Date: Wed, 10 Feb 2021 13:07:38 +0800
Message-ID: <20210210050742.31237-17-colyli@suse.de> (raw)
In-Reply-To: <20210210050742.31237-1-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 | 97 +++++++++++++++++++++++++++++++++++++
 drivers/md/bcache/journal.h |  2 +-
 drivers/md/bcache/super.c   | 16 +++---
 3 files changed, 107 insertions(+), 8 deletions(-)

diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index c6613e817333..1f16d8e497cf 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 +984,98 @@ int bch_journal_alloc(struct cache_set *c)
 
 	return 0;
 }
+
+static void *find_journal_nvm_base(struct bch_extent *list, struct cache *ca)
+{
+	void *ret = NULL;
+	struct bch_extent *cur, *next;
+
+	next = list;
+	do {
+		cur = next;
+		/* Match journal area's nvdimm address */
+		if (cur->kaddr == (void *)ca->sb.d[0]) {
+			ret = cur->kaddr;
+			break;
+		}
+		next = list_entry(cur->list.next, struct bch_extent, list);
+	} while (next != list);
+
+	return ret;
+}
+
+static void bch_release_nvm_extent_list(struct bch_extent *list)
+{
+	struct bch_extent *ext;
+	struct list_head *cur, *next;
+
+	list_for_each_safe(cur, next, &list->list) {
+		ext = list_entry(cur, struct bch_extent, list);
+		kfree(ext);
+	}
+}
+
+static void *get_nvdimm_journal_space(struct cache *ca)
+{
+	struct bch_extent *allocated_list = NULL;
+	void *ret = NULL;
+
+	allocated_list = bch_get_allocated_pages(ca->sb.set_uuid);
+	if (allocated_list) {
+		ret = find_journal_nvm_base(allocated_list, ca);
+		bch_release_nvm_extent_list(allocated_list);
+	}
+
+	if (!ret) {
+		int 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);
+	}
+
+	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;
+}
+
+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 915f1ea4dfd9..57c96c16ee16 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;
@@ -2072,14 +2077,11 @@ 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


  parent reply index

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-10  5:07 [PATCH 00/20] bcache patches for Linux v5.12 Coly Li
2021-02-10  5:07 ` [PATCH 01/20] bcache: consider the fragmentation when update the writeback rate Coly Li
2021-02-10  5:07 ` [PATCH 02/20] bcache: Fix register_device_aync typo Coly Li
2021-02-10  5:07 ` [PATCH 03/20] Revert "bcache: Kill btree_io_wq" Coly Li
2021-02-10  5:07 ` [PATCH 04/20] bcache: Give btree_io_wq correct semantics again Coly Li
2021-02-10  5:07 ` [PATCH 05/20] bcache: Move journal work to new flush wq Coly Li
2021-02-10  5:07 ` [PATCH 06/20] bcache: Avoid comma separated statements Coly Li
2021-02-10  5:07 ` [PATCH 07/20] bcache: add initial data structures for nvm pages Coly Li
2021-02-10 15:09   ` Jens Axboe
2021-02-11  3:58     ` Coly Li
2021-02-10  5:07 ` [PATCH 08/20] bcache: initialize the nvm pages allocator Coly Li
2021-02-10  5:07 ` [PATCH 09/20] bcache: initialization of the buddy Coly Li
2021-02-10  5:07 ` [PATCH 10/20] bcache: bch_nvm_alloc_pages() " Coly Li
2021-02-10  5:07 ` [PATCH 11/20] bcache: bch_nvm_free_pages() " Coly Li
2021-02-10  5:07 ` [PATCH 12/20] bcache: get allocated pages from specific owner Coly Li
2021-02-10  5:07 ` [PATCH 13/20] bcache: persist owner info when alloc/free pages Coly Li
2021-02-10  5:07 ` [PATCH 14/20] bcache: use bucket index for SET_GC_MARK() in bch_btree_gc_finish() Coly Li
2021-02-10  5:07 ` [PATCH 15/20] bcache: add BCH_FEATURE_INCOMPAT_NVDIMM_META into incompat feature set Coly Li
2021-02-10  5:07 ` Coly Li [this message]
2021-02-10  5:07 ` [PATCH 17/20] bcache: support storing bcache journal into NVDIMM meta device Coly Li
2021-02-18 21:21   ` Nix
2021-02-10  5:07 ` [PATCH 18/20] bcache: read jset from NVDIMM pages for journal replay Coly Li
2021-02-10  5:07 ` [PATCH 19/20] bcache: add sysfs interface register_nvdimm_meta to register NVDIMM meta device Coly Li
2021-02-10  5:07 ` [PATCH 20/20] bcache: only initialize nvm-pages allocator when CONFIG_BCACHE_NVM_PAGES configured Coly Li
2021-02-10 15:11 ` [PATCH 00/20] bcache patches for Linux v5.12 Jens Axboe
2021-02-12 16:09   ` 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=20210210050742.31237-17-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

Linux-bcache Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-bcache/0 linux-bcache/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-bcache linux-bcache/ https://lore.kernel.org/linux-bcache \
		linux-bcache@vger.kernel.org
	public-inbox-index linux-bcache

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-bcache


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git