[PATCH] md/md-llbitmap: allocate page controls independently

From: Yu Kuai <[email protected]>

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.

Signed-off-by: Yu Kuai <[email protected]>
---
 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 ecf3ed712315..2f2896fe4d6f 100644
--- a/drivers/md/md-llbitmap.c
+++ b/drivers/md/md-llbitmap.c
@@ -510,24 +510,32 @@ static void llbitmap_write(struct llbitmap *llbitmap, enum llbitmap_state state,
 		llbitmap_set_page_dirty(llbitmap, idx, bit, true);
 	else if (state == BitNeedSyncUnwritten)
 		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;
 
 	page = alloc_page(GFP_KERNEL | __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;
 
 		if (rdev->raid_disk < 0 || test_bit(Faulty, &rdev->flags) ||
@@ -594,65 +602,82 @@ static void llbitmap_free_pages(struct llbitmap *llbitmap)
 		return;
 
 	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_KERNEL | __GFP_ZERO);
-	if (!llbitmap->pctl)
-		return -ENOMEM;
 
 	size = round_up(size, cache_line_size());
-	pctl = kmalloc_array(nr_pages, size, GFP_KERNEL | __GFP_ZERO);
-	if (!pctl) {
-		kfree(llbitmap->pctl);
-		return -ENOMEM;
+	pctl = kzalloc(size, GFP_KERNEL);
+	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_KERNEL)) {
+		__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_KERNEL);
+	if (!llbitmap->pctl)
+		return -ENOMEM;
 
-		if (percpu_ref_init(&pctl->active, active_release,
-				    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
-			__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;
 }
 
@@ -921,11 +946,11 @@ static int llbitmap_init(struct llbitmap *llbitmap)
 	llbitmap->chunksize = chunksize;
 	llbitmap->chunks = chunks;
 	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;
 
 	llbitmap_state_machine(llbitmap, 0, llbitmap->chunks - 1,
 			       BitmapActionInit);
@@ -1030,11 +1055,11 @@ static int llbitmap_read_sb(struct llbitmap *llbitmap)
 	llbitmap->barrier_idle = DEFAULT_BARRIER_IDLE;
 	llbitmap->chunksize = chunksize;
 	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);
 	kunmap_local(sb);
 	return ret;
-- 
2.51.0