Linux RAID subsystem development
 help / color / mirror / Atom feed
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 15/29] md/md-llbitmap: grow the page cache in place for reshape
Date: Mon,  3 Aug 2026 03:50:24 +0800	[thread overview]
Message-ID: <20260802195038.164272-16-yukuai@kernel.org> (raw)
In-Reply-To: <20260802195038.164272-1-yukuai@kernel.org>

From: Yu Kuai <yukuai@fygo.io>

Use the page-control helpers to grow llbitmap's cached pages in place
for resize and later reshape preparation, instead of rebuilding the
whole cache.

Tested-by: Mykola Marzhan <mykola@meshstor.io>
Signed-off-by: Yu Kuai <yukuai@fygo.io>
---
 drivers/md/md-llbitmap.c | 145 +++++++++++++++++++++++++++++++++++----
 1 file changed, 133 insertions(+), 12 deletions(-)

diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c
index 300dd8b93b01..ddeea2098987 100644
--- a/drivers/md/md-llbitmap.c
+++ b/drivers/md/md-llbitmap.c
@@ -416,6 +416,19 @@ static char state_machine[BitStateCount][BitmapActionCount] = {
 };
 
 static void __llbitmap_flush(struct mddev *mddev);
+static void llbitmap_flush(struct mddev *mddev);
+static void llbitmap_update_sb(void *data);
+
+static void llbitmap_calculate_chunks(struct mddev *mddev, sector_t blocks,
+				      unsigned long *chunksize,
+				      unsigned long *chunks)
+{
+	*chunks = DIV_ROUND_UP_SECTOR_T(blocks, *chunksize);
+	while (*chunks > mddev->bitmap_info.space << SECTOR_SHIFT) {
+		*chunksize = *chunksize << 1;
+		*chunks = DIV_ROUND_UP_SECTOR_T(blocks, *chunksize);
+	}
+}
 
 static enum llbitmap_state llbitmap_read(struct llbitmap *llbitmap, loff_t pos)
 {
@@ -655,6 +668,48 @@ static unsigned int llbitmap_reserved_pages(struct llbitmap *llbitmap)
 			    PAGE_SIZE);
 }
 
+static int llbitmap_expand_pages(struct llbitmap *llbitmap,
+				 unsigned long chunks)
+{
+	struct llbitmap_page_ctl **pctl;
+	unsigned int old_nr_pages = llbitmap->nr_pages;
+	unsigned int nr_pages = llbitmap_used_pages(llbitmap, chunks);
+	unsigned int i;
+	int ret;
+
+	if (nr_pages <= old_nr_pages)
+		return 0;
+
+	pctl = kcalloc(nr_pages, sizeof(*pctl), GFP_NOIO);
+	if (!pctl)
+		return -ENOMEM;
+
+	if (llbitmap->pctl)
+		memcpy(pctl, llbitmap->pctl,
+		       array_size(old_nr_pages, sizeof(*pctl)));
+
+	for (i = old_nr_pages; i < nr_pages; i++) {
+		pctl[i] = llbitmap_alloc_page_ctl(llbitmap, i);
+		if (IS_ERR(pctl[i]))
+			goto err_alloc_ptr;
+	}
+
+	kfree(llbitmap->pctl);
+	llbitmap->pctl = pctl;
+	llbitmap->nr_pages = nr_pages;
+	return 0;
+
+err_alloc_ptr:
+	ret = PTR_ERR(pctl[i]);
+	while (i-- > old_nr_pages) {
+		__free_page(pctl[i]->page);
+		percpu_ref_exit(&pctl[i]->active);
+		kfree(pctl[i]);
+	}
+	kfree(pctl);
+	return ret;
+}
+
 static int llbitmap_alloc_pages(struct llbitmap *llbitmap)
 {
 	unsigned int used_pages = llbitmap_used_pages(llbitmap, llbitmap->chunks);
@@ -730,6 +785,34 @@ static bool llbitmap_zero_all_disks(struct llbitmap *llbitmap)
 	return true;
 }
 
+static void llbitmap_mark_range(struct llbitmap *llbitmap,
+				unsigned long start,
+				unsigned long end,
+				enum llbitmap_state state)
+{
+	while (start <= end) {
+		llbitmap_write(llbitmap, state, start);
+		start++;
+	}
+}
+
+static int llbitmap_prepare_resize(struct llbitmap *llbitmap,
+				   unsigned long old_chunks,
+				   unsigned long new_chunks,
+				   unsigned long cache_chunks)
+{
+	int ret;
+
+	llbitmap_flush(llbitmap->mddev);
+	ret = llbitmap_expand_pages(llbitmap, cache_chunks);
+	if (ret)
+		return ret;
+	if (new_chunks > old_chunks)
+		llbitmap_mark_range(llbitmap, old_chunks, new_chunks - 1,
+				    BitUnwritten);
+	return 0;
+}
+
 static void llbitmap_init_state(struct llbitmap *llbitmap)
 {
 	struct mddev *mddev = llbitmap->mddev;
@@ -1032,10 +1115,10 @@ static int llbitmap_read_sb(struct llbitmap *llbitmap)
 		goto out_put_page;
 	}
 
-	if (chunksize < DIV_ROUND_UP_SECTOR_T(mddev->resync_max_sectors,
+	if (chunksize < DIV_ROUND_UP_SECTOR_T(sync_size,
 					      mddev->bitmap_info.space << SECTOR_SHIFT)) {
 		pr_err("md/llbitmap: %s: chunksize too small %lu < %llu / %lu",
-		       mdname(mddev), chunksize, mddev->resync_max_sectors,
+		       mdname(mddev), chunksize, sync_size,
 		       mddev->bitmap_info.space);
 		goto out_put_page;
 	}
@@ -1184,24 +1267,62 @@ static int llbitmap_create(struct mddev *mddev)
 static int llbitmap_resize(struct mddev *mddev, sector_t blocks, int chunksize)
 {
 	struct llbitmap *llbitmap = mddev->bitmap;
+	sector_t old_blocks = llbitmap->sync_size;
+	unsigned long old_chunks = llbitmap->chunks;
 	unsigned long chunks;
+	unsigned long cache_chunks;
+	int ret = 0;
+	unsigned long bitmap_chunksize;
+	bool reshape;
+	bool quiesced = false;
 
 	if (chunksize == 0)
 		chunksize = llbitmap->chunksize;
 
-	/* If there is enough space, leave the chunksize unchanged. */
-	chunks = DIV_ROUND_UP_SECTOR_T(blocks, chunksize);
-	while (chunks > mddev->bitmap_info.space << SECTOR_SHIFT) {
-		chunksize = chunksize << 1;
-		chunks = DIV_ROUND_UP_SECTOR_T(blocks, chunksize);
-	}
+	bitmap_chunksize = chunksize;
+	llbitmap_calculate_chunks(mddev, blocks, &bitmap_chunksize, &chunks);
 
-	llbitmap->chunkshift = ffz(~chunksize);
-	llbitmap->chunksize = chunksize;
-	llbitmap->chunks = chunks;
-	llbitmap->sync_size = blocks;
+	reshape = mddev->delta_disks || mddev->new_level != mddev->level ||
+		mddev->new_layout != mddev->layout ||
+		mddev->new_chunk_sectors != mddev->chunk_sectors;
+	if (!reshape && bitmap_chunksize != llbitmap->chunksize)
+		return -EOPNOTSUPP;
+	if (blocks == old_blocks && chunks == llbitmap->chunks)
+		return 0;
 
+	if (mddev->pers->quiesce) {
+		mddev->pers->quiesce(mddev, 1);
+		quiesced = true;
+	}
+
+	mutex_lock(&mddev->bitmap_info.mutex);
+	cache_chunks = reshape ? max(old_chunks, chunks) : chunks;
+	ret = llbitmap_prepare_resize(llbitmap, old_chunks, chunks, cache_chunks);
+	if (ret)
+		goto out;
+
+	if (reshape) {
+		llbitmap->chunks = max(old_chunks, chunks);
+	} else {
+		if (blocks < old_blocks && chunks < old_chunks)
+			llbitmap_mark_range(llbitmap, chunks, old_chunks - 1,
+					    BitUnwritten);
+		mddev->bitmap_info.chunksize = bitmap_chunksize;
+		llbitmap->chunks = chunks;
+		llbitmap->sync_size = blocks;
+		llbitmap_update_sb(llbitmap);
+	}
+	__llbitmap_flush(mddev);
+	mutex_unlock(&mddev->bitmap_info.mutex);
+	if (quiesced)
+		mddev->pers->quiesce(mddev, 0);
 	return 0;
+
+out:
+	mutex_unlock(&mddev->bitmap_info.mutex);
+	if (quiesced)
+		mddev->pers->quiesce(mddev, 0);
+	return ret;
 }
 
 static int llbitmap_load(struct mddev *mddev)
-- 
2.51.0


  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 ` [PATCH v5 14/29] md/md-llbitmap: allocate page controls independently Yu Kuai
2026-08-02 20:27   ` sashiko-bot
2026-08-02 19:50 ` Yu Kuai [this message]
2026-08-02 20:37   ` [PATCH v5 15/29] md/md-llbitmap: grow the page cache in place for reshape 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=20260802195038.164272-16-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox