From: Yu Kuai <yukuai@kernel.org>
To: Song Liu <song@kernel.org>, Li Nan <magiclinan@didiglobal.com>,
Xiao Ni <xiao@kernel.org>
Cc: Yu Kuai <yukuai@fygo.io>,
linux-raid@vger.kernel.org, linux-kernel@vger.kernel.org,
Mykola Marzhan <mykola@meshstor.io>, Su Yue <glass.su@suse.com>
Subject: [PATCH v5 14/29] md/md-llbitmap: allocate page controls independently
Date: Mon, 3 Aug 2026 03:50:23 +0800 [thread overview]
Message-ID: <20260802195038.164272-15-yukuai@kernel.org> (raw)
In-Reply-To: <20260802195038.164272-1-yukuai@kernel.org>
From: Yu Kuai <yukuai@fygo.io>
Allocate one llbitmap page-control object at a time and free each
object through the same model.
Let llbitmap_read_page() return a zeroed page without reading disk when
the page index is beyond the current bitmap size, so page-control
allocation no longer needs a separate read_existing flag.
This keeps the llbitmap page-control lifetime self-consistent and
prepares the page-cache code for later in-place growth.
Reviewed-by: Su Yue <glass.su@suse.com>
Tested-by: Mykola Marzhan <mykola@meshstor.io>
Signed-off-by: Yu Kuai <yukuai@fygo.io>
---
drivers/md/md-llbitmap.c | 99 +++++++++++++++++++++++++---------------
1 file changed, 62 insertions(+), 37 deletions(-)
diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c
index 0813cebfbdeb..300dd8b93b01 100644
--- a/drivers/md/md-llbitmap.c
+++ b/drivers/md/md-llbitmap.c
@@ -512,13 +512,19 @@ static void llbitmap_write(struct llbitmap *llbitmap, enum llbitmap_state state,
llbitmap_set_page_dirty(llbitmap, idx, bit, false);
}
+static unsigned int llbitmap_used_pages(struct llbitmap *llbitmap,
+ unsigned long chunks)
+{
+ return DIV_ROUND_UP(chunks + BITMAP_DATA_OFFSET, PAGE_SIZE);
+}
+
static struct page *llbitmap_read_page(struct llbitmap *llbitmap, int idx)
{
struct mddev *mddev = llbitmap->mddev;
struct page *page = NULL;
struct md_rdev *rdev;
- if (llbitmap->pctl && llbitmap->pctl[idx])
+ if (llbitmap->pctl && idx < llbitmap->nr_pages && llbitmap->pctl[idx])
page = llbitmap->pctl[idx]->page;
if (page)
return page;
@@ -526,6 +532,8 @@ static struct page *llbitmap_read_page(struct llbitmap *llbitmap, int idx)
page = alloc_page(GFP_NOIO | __GFP_ZERO);
if (!page)
return ERR_PTR(-ENOMEM);
+ if (idx >= llbitmap_used_pages(llbitmap, llbitmap->chunks))
+ return page;
rdev_for_each(rdev, mddev) {
sector_t sector;
@@ -596,61 +604,78 @@ static void llbitmap_free_pages(struct llbitmap *llbitmap)
for (i = 0; i < llbitmap->nr_pages; i++) {
struct llbitmap_page_ctl *pctl = llbitmap->pctl[i];
- if (!pctl || !pctl->page)
- break;
-
- __free_page(pctl->page);
+ if (!pctl)
+ continue;
+ if (pctl->page)
+ __free_page(pctl->page);
percpu_ref_exit(&pctl->active);
+ kfree(pctl);
}
- kfree(llbitmap->pctl[0]);
kfree(llbitmap->pctl);
llbitmap->pctl = NULL;
}
-static int llbitmap_cache_pages(struct llbitmap *llbitmap)
+static struct llbitmap_page_ctl *
+llbitmap_alloc_page_ctl(struct llbitmap *llbitmap, int idx)
{
struct llbitmap_page_ctl *pctl;
- unsigned int nr_pages = DIV_ROUND_UP(llbitmap->chunks +
- BITMAP_DATA_OFFSET, PAGE_SIZE);
+ struct page *page;
unsigned int size = struct_size(pctl, dirty, BITS_TO_LONGS(
llbitmap->blocks_per_page));
- int i;
-
- llbitmap->pctl = kmalloc_array(nr_pages, sizeof(void *),
- GFP_NOIO | __GFP_ZERO);
- if (!llbitmap->pctl)
- return -ENOMEM;
size = round_up(size, cache_line_size());
- pctl = kmalloc_array(nr_pages, size, GFP_NOIO | __GFP_ZERO);
- if (!pctl) {
- kfree(llbitmap->pctl);
- return -ENOMEM;
+ pctl = kzalloc(size, GFP_NOIO);
+ if (!pctl)
+ return ERR_PTR(-ENOMEM);
+
+ page = llbitmap_read_page(llbitmap, idx);
+
+ if (IS_ERR(page)) {
+ kfree(pctl);
+ return ERR_CAST(page);
}
- llbitmap->nr_pages = nr_pages;
+ if (percpu_ref_init(&pctl->active, active_release,
+ PERCPU_REF_ALLOW_REINIT, GFP_NOIO)) {
+ __free_page(page);
+ kfree(pctl);
+ return ERR_PTR(-ENOMEM);
+ }
- for (i = 0; i < nr_pages; i++, pctl = (void *)pctl + size) {
- struct page *page = llbitmap_read_page(llbitmap, i);
+ pctl->page = page;
+ pctl->state = page_address(page);
+ init_waitqueue_head(&pctl->wait);
+ return pctl;
+}
- llbitmap->pctl[i] = pctl;
+static unsigned int llbitmap_reserved_pages(struct llbitmap *llbitmap)
+{
+ return DIV_ROUND_UP(llbitmap->mddev->bitmap_info.space << SECTOR_SHIFT,
+ PAGE_SIZE);
+}
- if (IS_ERR(page)) {
- llbitmap_free_pages(llbitmap);
- return PTR_ERR(page);
- }
+static int llbitmap_alloc_pages(struct llbitmap *llbitmap)
+{
+ unsigned int used_pages = llbitmap_used_pages(llbitmap, llbitmap->chunks);
+ unsigned int nr_pages = max(used_pages, llbitmap_reserved_pages(llbitmap));
+ int i;
+
+ llbitmap->pctl = kcalloc(nr_pages, sizeof(*llbitmap->pctl), GFP_NOIO);
+ if (!llbitmap->pctl)
+ return -ENOMEM;
- if (percpu_ref_init(&pctl->active, active_release,
- PERCPU_REF_ALLOW_REINIT, GFP_NOIO)) {
- __free_page(page);
+ llbitmap->nr_pages = nr_pages;
+
+ for (i = 0; i < nr_pages; i++) {
+ llbitmap->pctl[i] = llbitmap_alloc_page_ctl(llbitmap, i);
+ if (IS_ERR(llbitmap->pctl[i])) {
+ int ret = PTR_ERR(llbitmap->pctl[i]);
+
+ llbitmap->pctl[i] = NULL;
llbitmap_free_pages(llbitmap);
- return -ENOMEM;
+ return ret;
}
-
- pctl->page = page;
- pctl->state = page_address(page);
- init_waitqueue_head(&pctl->wait);
}
return 0;
@@ -924,7 +949,7 @@ static int llbitmap_init(struct llbitmap *llbitmap)
llbitmap->sync_size = blocks;
mddev->bitmap_info.daemon_sleep = DEFAULT_DAEMON_SLEEP;
- ret = llbitmap_cache_pages(llbitmap);
+ ret = llbitmap_alloc_pages(llbitmap);
if (ret)
return ret;
@@ -1038,7 +1063,7 @@ static int llbitmap_read_sb(struct llbitmap *llbitmap)
llbitmap->chunks = DIV_ROUND_UP_SECTOR_T(sync_size, chunksize);
llbitmap->chunkshift = ffz(~chunksize);
llbitmap->sync_size = sync_size;
- ret = llbitmap_cache_pages(llbitmap);
+ ret = llbitmap_alloc_pages(llbitmap);
out_put_page:
__free_page(sb_page);
--
2.51.0
next prev parent reply other threads:[~2026-08-02 19:51 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-02 19:50 [PATCH v5 00/29] md: improve lockless bitmap reshape support Yu Kuai
2026-08-02 19:50 ` [PATCH v5 01/29] md/md-llbitmap: clear flush state after daemon flush Yu Kuai
2026-08-02 20:28 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 02/29] md/md-llbitmap: use GFP_NOIO for cache allocations Yu Kuai
2026-08-02 20:44 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 03/29] md/md-llbitmap: only end fully synced chunks Yu Kuai
2026-08-02 19:50 ` [PATCH v5 04/29] md/raid5: reject zero-sector reshape chunks Yu Kuai
2026-08-02 20:31 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 05/29] md/raid5: round bitmap stripes with sector division Yu Kuai
2026-08-02 20:19 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 06/29] md: wait for behind writes before destroying bitmap Yu Kuai
2026-08-02 20:40 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 07/29] md: avoid stale clone I/O accounting timestamps Yu Kuai
2026-08-02 20:45 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 08/29] md/md-llbitmap: prevent create failure bitmap UAF Yu Kuai
2026-08-02 20:39 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 09/29] md/md-llbitmap: stop daemon timer rearm on destroy Yu Kuai
2026-08-02 20:19 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 10/29] md: skip bitmap accounting for empty write ranges Yu Kuai
2026-08-02 19:50 ` [PATCH v5 11/29] md: add helper to split bios at reshape offset Yu Kuai
2026-08-02 20:19 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 12/29] md: add exact bitmap mapping and reshape hooks Yu Kuai
2026-08-02 19:50 ` [PATCH v5 13/29] md/md-llbitmap: track bitmap sync_size explicitly Yu Kuai
2026-08-02 20:24 ` sashiko-bot
2026-08-02 19:50 ` Yu Kuai [this message]
2026-08-02 20:27 ` [PATCH v5 14/29] md/md-llbitmap: allocate page controls independently sashiko-bot
2026-08-02 19:50 ` [PATCH v5 15/29] md/md-llbitmap: grow the page cache in place for reshape Yu Kuai
2026-08-02 20:37 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 16/29] md/md-llbitmap: track target reshape geometry fields Yu Kuai
2026-08-02 20:25 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 17/29] md/md-llbitmap: finish reshape geometry Yu Kuai
2026-08-02 20:39 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 18/29] md/md-llbitmap: refuse reshape while llbitmap still needs sync Yu Kuai
2026-08-02 20:44 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 19/29] md/md-llbitmap: add reshape range mapping helpers Yu Kuai
2026-08-02 20:31 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 20/29] md/md-llbitmap: don't skip reshape ranges from bitmap state Yu Kuai
2026-08-02 20:31 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 21/29] md/md-llbitmap: remap checkpointed bits as reshape progresses Yu Kuai
2026-08-02 20:43 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 22/29] md/md-llbitmap: clamp state-machine walks to tracked bits Yu Kuai
2026-08-02 19:50 ` [PATCH v5 23/29] md/raid10: reject llbitmap reshape when md chunk shrinks Yu Kuai
2026-08-02 20:40 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 24/29] md/raid10: wire llbitmap reshape lifecycle Yu Kuai
2026-08-02 20:49 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 25/29] md/raid10: split reshape bios before bitmap accounting Yu Kuai
2026-08-02 20:46 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 26/29] md/raid5: add exact old and new llbitmap mapping helpers Yu Kuai
2026-08-02 19:50 ` [PATCH v5 27/29] md/raid5: reject llbitmap reshape when md chunk shrinks Yu Kuai
2026-08-02 20:42 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 28/29] md/raid5: wire llbitmap reshape lifecycle Yu Kuai
2026-08-02 20:46 ` sashiko-bot
2026-08-02 19:50 ` [PATCH v5 29/29] md/raid5: split reshape bios before bitmap accounting Yu Kuai
2026-08-03 12:11 ` [PATCH v5 00/29] md: improve lockless bitmap reshape support Mykola Marzhan
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=20260802195038.164272-15-yukuai@kernel.org \
--to=yukuai@kernel.org \
--cc=glass.su@suse.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=magiclinan@didiglobal.com \
--cc=mykola@meshstor.io \
--cc=song@kernel.org \
--cc=xiao@kernel.org \
--cc=yukuai@fygo.io \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.