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,
	Jianpeng Ma <jianpeng.ma@intel.com>,
	Qiaowei Ren <qiaowei.ren@intel.com>, Coly Li <colyli@suse.de>
Subject: [PATCH 11/20] bcache: bch_nvm_free_pages() of the buddy
Date: Wed, 10 Feb 2021 13:07:33 +0800
Message-ID: <20210210050742.31237-12-colyli@suse.de> (raw)
In-Reply-To: <20210210050742.31237-1-colyli@suse.de>

From: Jianpeng Ma <jianpeng.ma@intel.com>

This patch implements the bch_nvm_free_pages() of the buddy.

Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
Co-authored-by: Qiaowei Ren <qiaowei.ren@intel.com>
Signed-off-by: Coly Li <colyli@suse.de>
---
 drivers/md/bcache/nvm-pages.c | 143 ++++++++++++++++++++++++++++++++--
 drivers/md/bcache/nvm-pages.h |   3 +
 2 files changed, 138 insertions(+), 8 deletions(-)

diff --git a/drivers/md/bcache/nvm-pages.c b/drivers/md/bcache/nvm-pages.c
index 0b992c17ce47..b40bdbac873f 100644
--- a/drivers/md/bcache/nvm-pages.c
+++ b/drivers/md/bcache/nvm-pages.c
@@ -168,8 +168,7 @@ static inline void *extent_end_addr(struct bch_extent *extent)
 static void add_extent(struct bch_nvm_alloced_recs *alloced_recs, void *addr, int order)
 {
 	struct list_head *list = alloced_recs->extent_head.next;
-	struct bch_extent *extent, *tmp;
-	void *end_addr = addr + (((u64)1 << order) << PAGE_SHIFT);
+	struct bch_extent *extent;
 
 	while (list != &alloced_recs->extent_head) {
 		extent = container_of(list, struct bch_extent, list);
@@ -187,6 +186,136 @@ static void add_extent(struct bch_nvm_alloced_recs *alloced_recs, void *addr, in
 	alloced_recs->nr++;
 }
 
+static inline void *nvm_end_addr(struct bch_nvm_namespace *ns)
+{
+	return ns->kaddr + (ns->pages_total << PAGE_SHIFT);
+}
+
+static inline bool in_nvm_range(struct bch_nvm_namespace *ns,
+		void *start_addr, void *end_addr)
+{
+	return (start_addr >= ns->kaddr) && (end_addr <= nvm_end_addr(ns));
+}
+
+static struct bch_nvm_namespace *find_nvm_by_addr(void *addr, int order)
+{
+	int i;
+	struct bch_nvm_namespace *ns;
+
+	for (i = 0; i < only_set->total_namespaces_nr; i++) {
+		ns = only_set->nss[i];
+		if (ns && in_nvm_range(ns, addr, addr + (1 << order)))
+			return ns;
+	}
+	return NULL;
+}
+
+static int remove_extent(struct bch_nvm_alloced_recs *alloced_recs, void *addr, int order)
+{
+	struct list_head *list = alloced_recs->extent_head.next;
+	struct bch_extent *extent;
+
+	while (list != &alloced_recs->extent_head) {
+		extent = container_of(list, struct bch_extent, list);
+
+		if (addr < extent->kaddr)
+			return -ENOENT;
+		if (addr > extent->kaddr) {
+			list = list->next;
+			continue;
+		}
+
+		WARN_ON(extent->nr != (1 << order));
+		list_del(list);
+		kfree(extent);
+		alloced_recs->nr--;
+		break;
+	}
+	return (list == &alloced_recs->extent_head) ? -ENOENT : 0;
+}
+
+static void __free_space(struct bch_nvm_namespace *ns, void *addr, int order)
+{
+	unsigned int add_pages = (1 << order);
+	pgoff_t pgoff;
+	struct page *page;
+
+	page = nvm_vaddr_to_page(ns, addr);
+	WARN_ON((!page) || (page->private != order));
+	pgoff = page->index;
+
+	while (order < BCH_MAX_ORDER - 1) {
+		struct page *buddy_page;
+
+		pgoff_t buddy_pgoff = pgoff ^ (1 << order);
+		pgoff_t parent_pgoff = pgoff & ~(1 << order);
+
+		if ((parent_pgoff + (1 << (order + 1)) > ns->pages_total))
+			break;
+
+		buddy_page = nvm_vaddr_to_page(ns, nvm_pgoff_to_vaddr(ns, buddy_pgoff));
+		WARN_ON(!buddy_page);
+
+		if (PageBuddy(buddy_page) && (buddy_page->private == order)) {
+			list_del((struct list_head *)&buddy_page->zone_device_data);
+			__ClearPageBuddy(buddy_page);
+			pgoff = parent_pgoff;
+			order++;
+			continue;
+		}
+		break;
+	}
+
+	page = nvm_vaddr_to_page(ns, nvm_pgoff_to_vaddr(ns, pgoff));
+	WARN_ON(!page);
+	list_add((struct list_head *)&page->zone_device_data, &ns->free_area[order]);
+	page->index = pgoff;
+	set_page_private(page, order);
+	__SetPageBuddy(page);
+	ns->free += add_pages;
+}
+
+void bch_nvm_free_pages(void *addr, int order, const char *owner_uuid)
+{
+	struct bch_nvm_namespace *ns;
+	struct bch_owner_list *owner_list;
+	struct bch_nvm_alloced_recs *alloced_recs;
+	int r;
+
+	mutex_lock(&only_set->lock);
+
+	ns = find_nvm_by_addr(addr, order);
+	if (!ns) {
+		pr_info("can't find nvm_dev by kaddr %p\n", addr);
+		goto unlock;
+	}
+
+	owner_list = find_owner_list(owner_uuid, false);
+	if (!owner_list) {
+		pr_info("can't found owner(uuid=%s)\n", owner_uuid);
+		goto unlock;
+	}
+
+	alloced_recs = find_nvm_alloced_recs(owner_list, ns, false);
+	if (!alloced_recs) {
+		pr_info("can't find alloced_recs(uuid=%s)\n", ns->uuid);
+		goto unlock;
+	}
+
+	r = remove_extent(alloced_recs, addr, order);
+	if (r < 0) {
+		pr_info("can't find extent\n");
+		goto unlock;
+	}
+
+	__free_space(ns, addr, order);
+
+unlock:
+	mutex_unlock(&only_set->lock);
+}
+EXPORT_SYMBOL_GPL(bch_nvm_free_pages);
+
+
 void *bch_nvm_alloc_pages(int order, const char *owner_uuid)
 {
 	void *kaddr = NULL;
@@ -276,7 +405,6 @@ static int init_owner_info(struct bch_nvm_namespace *ns)
 		for (j = 0; j < only_set->total_namespaces_nr; j++) {
 			if (!only_set->nss[j] || !owner_head->recs[j])
 				continue;
-
 			nvm_pgalloc_recs = (struct bch_nvm_pgalloc_recs *)
 					((long)owner_head->recs[j] + ns->kaddr);
 			if (memcmp(nvm_pgalloc_recs->magic, bch_nvm_pages_pgalloc_magic, 16)) {
@@ -348,7 +476,7 @@ static void init_nvm_free_space(struct bch_nvm_namespace *ns)
 {
 	unsigned int start, end, i;
 	struct page *page;
-	long long pages;
+	u64 pages;
 	pgoff_t pgoff_start;
 
 	bitmap_for_each_clear_region(ns->pages_bitmap, start, end, 0, ns->pages_total) {
@@ -364,9 +492,8 @@ static void init_nvm_free_space(struct bch_nvm_namespace *ns)
 			page = nvm_vaddr_to_page(ns, nvm_pgoff_to_vaddr(ns, pgoff_start));
 			page->index = pgoff_start;
 			set_page_private(page, i);
-			__SetPageBuddy(page);
-			list_add((struct list_head *)&page->zone_device_data, &ns->free_area[i]);
-
+			/* in order to update ns->free */
+			__free_space(ns, nvm_pgoff_to_vaddr(ns, pgoff_start), i);
 			pgoff_start += 1 << i;
 			pages -= 1 << i;
 		}
@@ -530,7 +657,7 @@ struct bch_nvm_namespace *bch_register_namespace(const char *dev_path)
 	ns->page_size = ns->sb.page_size;
 	ns->pages_offset = ns->sb.pages_offset;
 	ns->pages_total = ns->sb.pages_total;
-	ns->free = 0;
+	ns->free = 0; /* increased by __free_space() */
 	ns->bdev = bdev;
 	ns->nvm_set = only_set;
 
diff --git a/drivers/md/bcache/nvm-pages.h b/drivers/md/bcache/nvm-pages.h
index 10157d993126..1bc3129f2482 100644
--- a/drivers/md/bcache/nvm-pages.h
+++ b/drivers/md/bcache/nvm-pages.h
@@ -80,6 +80,7 @@ struct bch_nvm_namespace *bch_register_namespace(const char *dev_path);
 int bch_nvm_init(void);
 void bch_nvm_exit(void);
 void *bch_nvm_alloc_pages(int order, const char *owner_uuid);
+void bch_nvm_free_pages(void *addr, int order, const char *owner_uuid);
 
 #else
 
@@ -98,6 +99,8 @@ static inline void *bch_nvm_alloc_pages(int order, const char *owner_uuid)
 	return NULL;
 }
 
+static inline void bch_nvm_free_pages(void *addr, int order, const char *owner_uuid) { }
+
 #endif /* CONFIG_BCACHE_NVM_PAGES */
 
 #endif /* _BCACHE_NVM_PAGES_H */
-- 
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 ` Coly Li [this message]
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 ` [PATCH 16/20] bcache: initialize bcache journal for NVDIMM meta device Coly Li
2021-02-10  5:07 ` [PATCH 17/20] bcache: support storing bcache journal into " 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=20210210050742.31237-12-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