From: Hannes Reinecke <hare@suse.de>
To: Coly Li <colyli@suse.de>, 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>
Subject: Re: [PATCH 07/14] bcache: bch_nvm_free_pages() of the buddy
Date: Tue, 22 Jun 2021 12:53:31 +0200 [thread overview]
Message-ID: <327edd3d-c239-9099-5e2a-448dcc7a972f@suse.de> (raw)
In-Reply-To: <20210615054921.101421-8-colyli@suse.de>
On 6/15/21 7:49 AM, Coly Li wrote:
> From: Jianpeng Ma <jianpeng.ma@intel.com>
>
> This patch implements the bch_nvm_free_pages() of the buddy.
>
> The difference between this and page-buddy-free:
> it need owner_uuid to free owner allocated pages.And must
> persistent after free.
>
> Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
> Co-developed-by: Qiaowei Ren <qiaowei.ren@intel.com>
> Signed-off-by: Qiaowei Ren <qiaowei.ren@intel.com>
> Signed-off-by: Coly Li <colyli@suse.de>
> ---
> drivers/md/bcache/nvm-pages.c | 164 ++++++++++++++++++++++++++++++++--
> drivers/md/bcache/nvm-pages.h | 3 +-
> 2 files changed, 159 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/md/bcache/nvm-pages.c b/drivers/md/bcache/nvm-pages.c
> index 5d095d241483..74d08950c67c 100644
> --- a/drivers/md/bcache/nvm-pages.c
> +++ b/drivers/md/bcache/nvm-pages.c
> @@ -52,7 +52,7 @@ static void release_nvm_set(struct bch_nvm_set *nvm_set)
> kfree(nvm_set);
> }
>
> -static struct page *nvm_vaddr_to_page(struct bch_nvm_namespace *ns, void *addr)
> +static struct page *nvm_vaddr_to_page(void *addr)
> {
> return virt_to_page(addr);
> }
If you don't need this argument please modify the patch adding the
nvm_vaddr_to_page() function.
> @@ -183,6 +183,155 @@ static void add_pgalloc_rec(struct bch_nvm_pgalloc_recs *recs, void *kaddr, int
> BUG_ON(i == recs->size);
> }
>
> +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 + (1L << order)))
> + return ns;
> + }
> + return NULL;
> +}
> +
> +static int remove_pgalloc_rec(struct bch_nvm_pgalloc_recs *pgalloc_recs, int ns_nr,
> + void *kaddr, int order)
> +{
> + struct bch_nvm_pages_owner_head *owner_head = pgalloc_recs->owner;
> + struct bch_nvm_pgalloc_recs *prev_recs, *sys_recs;
> + u64 pgoff = (unsigned long)kaddr >> PAGE_SHIFT;
> + struct bch_nvm_namespace *ns = only_set->nss[0];
> + int i;
> +
> + prev_recs = pgalloc_recs;
> + sys_recs = ns->kaddr + BCH_NVM_PAGES_SYS_RECS_HEAD_OFFSET;
> + while (pgalloc_recs) {
> + for (i = 0; i < pgalloc_recs->size; i++) {
> + struct bch_pgalloc_rec *rec = &(pgalloc_recs->recs[i]);
> +
> + if (rec->pgoff == pgoff) {
> + WARN_ON(rec->order != order);
> + rec->pgoff = 0;
> + rec->order = 0;
> + pgalloc_recs->used--;
> +
> + if (pgalloc_recs->used == 0) {
> + int recs_pos = pgalloc_recs - sys_recs;
> +
> + if (pgalloc_recs == prev_recs)
> + owner_head->recs[ns_nr] = pgalloc_recs->next;
> + else
> + prev_recs->next = pgalloc_recs->next;
> +
> + pgalloc_recs->next = NULL;
> + pgalloc_recs->owner = NULL;
> +
> + bitmap_clear(ns->pgalloc_recs_bitmap, recs_pos, 1);
> + }
> + goto exit;
> + }
> + }
> + prev_recs = pgalloc_recs;
> + pgalloc_recs = pgalloc_recs->next;
> + }
> +exit:
> + return pgalloc_recs ? 0 : -ENOENT;
> +}
> +
> +static void __free_space(struct bch_nvm_namespace *ns, void *addr, int order)
> +{
> + unsigned long add_pages = (1L << order);
> + pgoff_t pgoff;
> + struct page *page;
> +
> + page = nvm_vaddr_to_page(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 ^ (1L << order);
> + pgoff_t parent_pgoff = pgoff & ~(1L << order);
> +
> + if ((parent_pgoff + (1L << (order + 1)) > ns->pages_total))
> + break;
> +
> + buddy_page = nvm_vaddr_to_page(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(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_nvm_pages_owner_head *owner_head;
> + struct bch_nvm_pgalloc_recs *pgalloc_recs;
> + int r;
> +
> + mutex_lock(&only_set->lock);
> +
> + ns = find_nvm_by_addr(addr, order);
> + if (!ns) {
> + pr_err("can't find nvm_dev by kaddr %p\n", addr);
> + goto unlock;
> + }
> +
> + owner_head = find_owner_head(owner_uuid, false);
> + if (!owner_head) {
> + pr_err("can't found bch_nvm_pages_owner_head by(uuid=%s)\n", owner_uuid);
> + goto unlock;
> + }
> +
> + pgalloc_recs = find_nvm_pgalloc_recs(ns, owner_head, false);
> + if (!pgalloc_recs) {
> + pr_err("can't find bch_nvm_pgalloc_recs by(uuid=%s)\n", owner_uuid);
> + goto unlock;
> + }
> +
> + r = remove_pgalloc_rec(pgalloc_recs, ns->sb->this_namespace_nr, addr, order);
> + if (r < 0) {
> + pr_err("can't find bch_pgalloc_rec\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;
> @@ -217,7 +366,7 @@ void *bch_nvm_alloc_pages(int order, const char *owner_uuid)
> list_del(list);
>
> while (i != order) {
> - buddy_page = nvm_vaddr_to_page(ns,
> + buddy_page = nvm_vaddr_to_page(
> nvm_pgoff_to_vaddr(ns, page->index + (1L << (i - 1))));
> set_page_private(buddy_page, i - 1);
> buddy_page->index = page->index + (1L << (i - 1));
> @@ -301,7 +450,7 @@ static int init_owner_info(struct bch_nvm_namespace *ns)
> BUG_ON(rec->pgoff <= offset);
>
> /* init struct page: index/private */
> - page = nvm_vaddr_to_page(ns,
> + page = nvm_vaddr_to_page(
> BCH_PGOFF_TO_KVADDR(rec->pgoff));
>
> set_page_private(page, rec->order);
> @@ -340,11 +489,12 @@ static void init_nvm_free_space(struct bch_nvm_namespace *ns)
> break;
> }
>
> - page = nvm_vaddr_to_page(ns, nvm_pgoff_to_vaddr(ns, pgoff_start));
> + page = nvm_vaddr_to_page(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 += 1L << i;
> pages -= 1L << i;
> @@ -535,7 +685,7 @@ 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; /* increase by __free_space() */
> ns->bdev = bdev;
> ns->nvm_set = only_set;
> mutex_init(&ns->lock);
> diff --git a/drivers/md/bcache/nvm-pages.h b/drivers/md/bcache/nvm-pages.h
> index f2583723aca6..0ca699166855 100644
> --- a/drivers/md/bcache/nvm-pages.h
> +++ b/drivers/md/bcache/nvm-pages.h
> @@ -63,6 +63,7 @@ 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
>
> @@ -79,7 +80,7 @@ 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 */
>
>
Cheers,
Hannes
--
Dr. Hannes Reinecke Kernel Storage Architect
hare@suse.de +49 911 74053 688
SUSE Software Solutions Germany GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), GF: Felix Imendörffer
next prev parent reply other threads:[~2021-06-22 10:53 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-15 5:49 [PATCH 00/14] bcache patches for Linux v5.14 Coly Li
2021-06-15 5:49 ` [PATCH 01/14] bcache: fix error info in register_bcache() Coly Li
2021-06-22 9:47 ` Hannes Reinecke
2021-06-15 5:49 ` [PATCH 02/14] md: bcache: Fix spelling of 'acquire' Coly Li
2021-06-22 10:03 ` Hannes Reinecke
2021-06-15 5:49 ` [PATCH 03/14] bcache: add initial data structures for nvm pages Coly Li
2021-06-21 16:17 ` Ask help for code review (was Re: [PATCH 03/14] bcache: add initial data structures for nvm pages) Coly Li
2021-06-22 8:41 ` Huang, Ying
2021-06-23 4:32 ` Coly Li
2021-06-23 6:53 ` Huang, Ying
2021-06-23 7:04 ` Christoph Hellwig
2021-06-23 7:19 ` Coly Li
2021-06-23 7:21 ` Christoph Hellwig
2021-06-23 10:05 ` Coly Li
2021-06-23 11:16 ` Coly Li
2021-06-23 11:49 ` Christoph Hellwig
2021-06-23 12:09 ` Coly Li
2021-06-22 10:19 ` [PATCH 03/14] bcache: add initial data structures for nvm pages Hannes Reinecke
2021-06-23 7:09 ` Coly Li
2021-06-15 5:49 ` [PATCH 04/14] bcache: initialize the nvm pages allocator Coly Li
2021-06-22 10:39 ` Hannes Reinecke
2021-06-23 5:26 ` Coly Li
2021-06-23 9:16 ` Hannes Reinecke
2021-06-23 9:34 ` Coly Li
2021-06-15 5:49 ` [PATCH 05/14] bcache: initialization of the buddy Coly Li
2021-06-22 10:45 ` Hannes Reinecke
2021-06-23 5:35 ` Coly Li
2021-06-23 5:46 ` Re[2]: " Pavel Goran
2021-06-23 6:03 ` Coly Li
2021-06-15 5:49 ` [PATCH 06/14] bcache: bch_nvm_alloc_pages() " Coly Li
2021-06-22 10:51 ` Hannes Reinecke
2021-06-23 6:02 ` Coly Li
2021-06-15 5:49 ` [PATCH 07/14] bcache: bch_nvm_free_pages() " Coly Li
2021-06-22 10:53 ` Hannes Reinecke [this message]
2021-06-23 6:06 ` Coly Li
2021-06-15 5:49 ` [PATCH 08/14] bcache: get allocated pages from specific owner Coly Li
2021-06-22 10:54 ` Hannes Reinecke
2021-06-23 6:08 ` Coly Li
2021-06-15 5:49 ` [PATCH 09/14] bcache: use bucket index to set GC_MARK_METADATA for journal buckets in bch_btree_gc_finish() Coly Li
2021-06-22 10:55 ` Hannes Reinecke
2021-06-23 6:09 ` Coly Li
2021-06-15 5:49 ` [PATCH 10/14] bcache: add BCH_FEATURE_INCOMPAT_NVDIMM_META into incompat feature set Coly Li
2021-06-22 10:59 ` Hannes Reinecke
2021-06-23 6:09 ` Coly Li
2021-06-15 5:49 ` [PATCH 11/14] bcache: initialize bcache journal for NVDIMM meta device Coly Li
2021-06-22 11:01 ` Hannes Reinecke
2021-06-23 6:17 ` Coly Li
2021-06-23 9:20 ` Hannes Reinecke
2021-06-23 10:14 ` Coly Li
2021-06-15 5:49 ` [PATCH 12/14] bcache: support storing bcache journal into " Coly Li
2021-06-22 11:03 ` Hannes Reinecke
2021-06-23 6:19 ` Coly Li
2021-06-15 5:49 ` [PATCH 13/14] bcache: read jset from NVDIMM pages for journal replay Coly Li
2021-06-22 11:04 ` Hannes Reinecke
2021-06-23 6:21 ` Coly Li
2021-06-15 5:49 ` [PATCH 14/14] bcache: add sysfs interface register_nvdimm_meta to register NVDIMM meta device Coly Li
2021-06-22 11:04 ` Hannes Reinecke
2021-06-21 15:14 ` [PATCH 00/14] bcache patches for Linux v5.14 Jens Axboe
2021-06-21 15:25 ` Coly Li
2021-06-21 15:27 ` Jens Axboe
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=327edd3d-c239-9099-5e2a-448dcc7a972f@suse.de \
--to=hare@suse.de \
--cc=axboe@kernel.dk \
--cc=colyli@suse.de \
--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).