1 files changed, 230 insertions, 199 deletions

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index e4f7cf9d89c4..b25a27c86696 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -831,6 +831,8 @@ static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len)
 		return 0;
 	if (order == MB_NUM_ORDERS(sb))
 		order--;
+	if (WARN_ON_ONCE(order > MB_NUM_ORDERS(sb)))
+		order = MB_NUM_ORDERS(sb) - 1;
 	return order;
 }
 
@@ -1008,6 +1010,8 @@ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context
 	 * goal length.
 	 */
 	order = fls(ac->ac_g_ex.fe_len) - 1;
+	if (WARN_ON_ONCE(order - 1 > MB_NUM_ORDERS(ac->ac_sb)))
+		order = MB_NUM_ORDERS(ac->ac_sb);
 	min_order = order - sbi->s_mb_best_avail_max_trim_order;
 	if (min_order < 0)
 		min_order = 0;
@@ -1076,23 +1080,11 @@ static inline int should_optimize_scan(struct ext4_allocation_context *ac)
 }
 
 /*
- * Return next linear group for allocation. If linear traversal should not be
- * performed, this function just returns the same group
+ * Return next linear group for allocation.
  */
 static ext4_group_t
-next_linear_group(struct ext4_allocation_context *ac, ext4_group_t group,
-		  ext4_group_t ngroups)
+next_linear_group(ext4_group_t group, ext4_group_t ngroups)
 {
-	if (!should_optimize_scan(ac))
-		goto inc_and_return;
-
-	if (ac->ac_groups_linear_remaining) {
-		ac->ac_groups_linear_remaining--;
-		goto inc_and_return;
-	}
-
-	return group;
-inc_and_return:
 	/*
 	 * Artificially restricted ngroups for non-extent
 	 * files makes group > ngroups possible on first loop.
@@ -1118,8 +1110,19 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
 {
 	*new_cr = ac->ac_criteria;
 
-	if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) {
-		*group = next_linear_group(ac, *group, ngroups);
+	if (!should_optimize_scan(ac)) {
+		*group = next_linear_group(*group, ngroups);
+		return;
+	}
+
+	/*
+	 * Optimized scanning can return non adjacent groups which can cause
+	 * seek overhead for rotational disks. So try few linear groups before
+	 * trying optimized scan.
+	 */
+	if (ac->ac_groups_linear_remaining) {
+		*group = next_linear_group(*group, ngroups);
+		ac->ac_groups_linear_remaining--;
 		return;
 	}
 
@@ -1131,8 +1134,9 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
 		ext4_mb_choose_next_group_best_avail(ac, new_cr, group);
 	} else {
 		/*
-		 * TODO: For CR=2, we can arrange groups in an rb tree sorted by
-		 * bb_free. But until that happens, we should never come here.
+		 * TODO: For CR_GOAL_LEN_SLOW, we can arrange groups in an
+		 * rb tree sorted by bb_free. But until that happens, we should
+		 * never come here.
 		 */
 		WARN_ON(1);
 	}
@@ -1270,7 +1274,7 @@ static void mb_regenerate_buddy(struct ext4_buddy *e4b)
  * for this page; do not hold this lock when calling this routine!
  */
 
-static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
+static int ext4_mb_init_cache(struct folio *folio, char *incore, gfp_t gfp)
 {
 	ext4_group_t ngroups;
 	unsigned int blocksize;
@@ -1288,13 +1292,13 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 	char *bitmap;
 	struct ext4_group_info *grinfo;
 
-	inode = page->mapping->host;
+	inode = folio->mapping->host;
 	sb = inode->i_sb;
 	ngroups = ext4_get_groups_count(sb);
 	blocksize = i_blocksize(inode);
 	blocks_per_page = PAGE_SIZE / blocksize;
 
-	mb_debug(sb, "init page %lu\n", page->index);
+	mb_debug(sb, "init folio %lu\n", folio->index);
 
 	groups_per_page = blocks_per_page >> 1;
 	if (groups_per_page == 0)
@@ -1309,9 +1313,9 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 	} else
 		bh = &bhs;
 
-	first_group = page->index * blocks_per_page / 2;
+	first_group = folio->index * blocks_per_page / 2;
 
-	/* read all groups the page covers into the cache */
+	/* read all groups the folio covers into the cache */
 	for (i = 0, group = first_group; i < groups_per_page; i++, group++) {
 		if (group >= ngroups)
 			break;
@@ -1322,10 +1326,11 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 		/*
 		 * If page is uptodate then we came here after online resize
 		 * which added some new uninitialized group info structs, so
-		 * we must skip all initialized uptodate buddies on the page,
+		 * we must skip all initialized uptodate buddies on the folio,
 		 * which may be currently in use by an allocating task.
 		 */
-		if (PageUptodate(page) && !EXT4_MB_GRP_NEED_INIT(grinfo)) {
+		if (folio_test_uptodate(folio) &&
+				!EXT4_MB_GRP_NEED_INIT(grinfo)) {
 			bh[i] = NULL;
 			continue;
 		}
@@ -1349,7 +1354,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 			err = err2;
 	}
 
-	first_block = page->index * blocks_per_page;
+	first_block = folio->index * blocks_per_page;
 	for (i = 0; i < blocks_per_page; i++) {
 		group = (first_block + i) >> 1;
 		if (group >= ngroups)
@@ -1370,7 +1375,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 		 * above
 		 *
 		 */
-		data = page_address(page) + (i * blocksize);
+		data = folio_address(folio) + (i * blocksize);
 		bitmap = bh[group - first_group]->b_data;
 
 		/*
@@ -1385,8 +1390,8 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 		if ((first_block + i) & 1) {
 			/* this is block of buddy */
 			BUG_ON(incore == NULL);
-			mb_debug(sb, "put buddy for group %u in page %lu/%x\n",
-				group, page->index, i * blocksize);
+			mb_debug(sb, "put buddy for group %u in folio %lu/%x\n",
+				group, folio->index, i * blocksize);
 			trace_ext4_mb_buddy_bitmap_load(sb, group);
 			grinfo->bb_fragments = 0;
 			memset(grinfo->bb_counters, 0,
@@ -1404,8 +1409,8 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 		} else {
 			/* this is block of bitmap */
 			BUG_ON(incore != NULL);
-			mb_debug(sb, "put bitmap for group %u in page %lu/%x\n",
-				group, page->index, i * blocksize);
+			mb_debug(sb, "put bitmap for group %u in folio %lu/%x\n",
+				group, folio->index, i * blocksize);
 			trace_ext4_mb_bitmap_load(sb, group);
 
 			/* see comments in ext4_mb_put_pa() */
@@ -1423,7 +1428,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 			incore = data;
 		}
 	}
-	SetPageUptodate(page);
+	folio_mark_uptodate(folio);
 
 out:
 	if (bh) {
@@ -1439,7 +1444,7 @@ out:
  * Lock the buddy and bitmap pages. This make sure other parallel init_group
  * on the same buddy page doesn't happen whild holding the buddy page lock.
  * Return locked buddy and bitmap pages on e4b struct. If buddy and bitmap
- * are on the same page e4b->bd_buddy_page is NULL and return value is 0.
+ * are on the same page e4b->bd_buddy_folio is NULL and return value is 0.
  */
 static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 		ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp)
@@ -1447,10 +1452,10 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 	struct inode *inode = EXT4_SB(sb)->s_buddy_cache;
 	int block, pnum, poff;
 	int blocks_per_page;
-	struct page *page;
+	struct folio *folio;
 
-	e4b->bd_buddy_page = NULL;
-	e4b->bd_bitmap_page = NULL;
+	e4b->bd_buddy_folio = NULL;
+	e4b->bd_bitmap_folio = NULL;
 
 	blocks_per_page = PAGE_SIZE / sb->s_blocksize;
 	/*
@@ -1461,12 +1466,13 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 	block = group * 2;
 	pnum = block / blocks_per_page;
 	poff = block % blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, gfp);
-	if (!page)
-		return -ENOMEM;
-	BUG_ON(page->mapping != inode->i_mapping);
-	e4b->bd_bitmap_page = page;
-	e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
+	folio = __filemap_get_folio(inode->i_mapping, pnum,
+			FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
+	BUG_ON(folio->mapping != inode->i_mapping);
+	e4b->bd_bitmap_folio = folio;
+	e4b->bd_bitmap = folio_address(folio) + (poff * sb->s_blocksize);
 
 	if (blocks_per_page >= 2) {
 		/* buddy and bitmap are on the same page */
@@ -1474,23 +1480,24 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 	}
 
 	/* blocks_per_page == 1, hence we need another page for the buddy */
-	page = find_or_create_page(inode->i_mapping, block + 1, gfp);
-	if (!page)
-		return -ENOMEM;
-	BUG_ON(page->mapping != inode->i_mapping);
-	e4b->bd_buddy_page = page;
+	folio = __filemap_get_folio(inode->i_mapping, block + 1,
+			FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
+	BUG_ON(folio->mapping != inode->i_mapping);
+	e4b->bd_buddy_folio = folio;
 	return 0;
 }
 
 static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b)
 {
-	if (e4b->bd_bitmap_page) {
-		unlock_page(e4b->bd_bitmap_page);
-		put_page(e4b->bd_bitmap_page);
+	if (e4b->bd_bitmap_folio) {
+		folio_unlock(e4b->bd_bitmap_folio);
+		folio_put(e4b->bd_bitmap_folio);
 	}
-	if (e4b->bd_buddy_page) {
-		unlock_page(e4b->bd_buddy_page);
-		put_page(e4b->bd_buddy_page);
+	if (e4b->bd_buddy_folio) {
+		folio_unlock(e4b->bd_buddy_folio);
+		folio_put(e4b->bd_buddy_folio);
 	}
 }
 
@@ -1505,7 +1512,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp)
 
 	struct ext4_group_info *this_grp;
 	struct ext4_buddy e4b;
-	struct page *page;
+	struct folio *folio;
 	int ret = 0;
 
 	might_sleep();
@@ -1532,16 +1539,16 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp)
 		goto err;
 	}
 
-	page = e4b.bd_bitmap_page;
-	ret = ext4_mb_init_cache(page, NULL, gfp);
+	folio = e4b.bd_bitmap_folio;
+	ret = ext4_mb_init_cache(folio, NULL, gfp);
 	if (ret)
 		goto err;
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		ret = -EIO;
 		goto err;
 	}
 
-	if (e4b.bd_buddy_page == NULL) {
+	if (e4b.bd_buddy_folio == NULL) {
 		/*
 		 * If both the bitmap and buddy are in
 		 * the same page we don't need to force
@@ -1551,11 +1558,11 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp)
 		goto err;
 	}
 	/* init buddy cache */
-	page = e4b.bd_buddy_page;
-	ret = ext4_mb_init_cache(page, e4b.bd_bitmap, gfp);
+	folio = e4b.bd_buddy_folio;
+	ret = ext4_mb_init_cache(folio, e4b.bd_bitmap, gfp);
 	if (ret)
 		goto err;
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		ret = -EIO;
 		goto err;
 	}
@@ -1577,7 +1584,7 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
 	int block;
 	int pnum;
 	int poff;
-	struct page *page;
+	struct folio *folio;
 	int ret;
 	struct ext4_group_info *grp;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -1595,8 +1602,8 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
 	e4b->bd_info = grp;
 	e4b->bd_sb = sb;
 	e4b->bd_group = group;
-	e4b->bd_buddy_page = NULL;
-	e4b->bd_bitmap_page = NULL;
+	e4b->bd_buddy_folio = NULL;
+	e4b->bd_bitmap_folio = NULL;
 
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
 		/*
@@ -1617,102 +1624,103 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
 	pnum = block / blocks_per_page;
 	poff = block % blocks_per_page;
 
-	/* we could use find_or_create_page(), but it locks page
-	 * what we'd like to avoid in fast path ... */
-	page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
-	if (page == NULL || !PageUptodate(page)) {
-		if (page)
+	/* Avoid locking the folio in the fast path ... */
+	folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_ACCESSED, 0);
+	if (IS_ERR(folio) || !folio_test_uptodate(folio)) {
+		if (!IS_ERR(folio))
 			/*
-			 * drop the page reference and try
-			 * to get the page with lock. If we
+			 * drop the folio reference and try
+			 * to get the folio with lock. If we
 			 * are not uptodate that implies
-			 * somebody just created the page but
-			 * is yet to initialize the same. So
+			 * somebody just created the folio but
+			 * is yet to initialize it. So
 			 * wait for it to initialize.
 			 */
-			put_page(page);
-		page = find_or_create_page(inode->i_mapping, pnum, gfp);
-		if (page) {
-			if (WARN_RATELIMIT(page->mapping != inode->i_mapping,
-	"ext4: bitmap's paging->mapping != inode->i_mapping\n")) {
+			folio_put(folio);
+		folio = __filemap_get_folio(inode->i_mapping, pnum,
+				FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp);
+		if (!IS_ERR(folio)) {
+			if (WARN_RATELIMIT(folio->mapping != inode->i_mapping,
+	"ext4: bitmap's mapping != inode->i_mapping\n")) {
 				/* should never happen */
-				unlock_page(page);
+				folio_unlock(folio);
 				ret = -EINVAL;
 				goto err;
 			}
-			if (!PageUptodate(page)) {
-				ret = ext4_mb_init_cache(page, NULL, gfp);
+			if (!folio_test_uptodate(folio)) {
+				ret = ext4_mb_init_cache(folio, NULL, gfp);
 				if (ret) {
-					unlock_page(page);
+					folio_unlock(folio);
 					goto err;
 				}
-				mb_cmp_bitmaps(e4b, page_address(page) +
+				mb_cmp_bitmaps(e4b, folio_address(folio) +
 					       (poff * sb->s_blocksize));
 			}
-			unlock_page(page);
+			folio_unlock(folio);
 		}
 	}
-	if (page == NULL) {
-		ret = -ENOMEM;
+	if (IS_ERR(folio)) {
+		ret = PTR_ERR(folio);
 		goto err;
 	}
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		ret = -EIO;
 		goto err;
 	}
 
-	/* Pages marked accessed already */
-	e4b->bd_bitmap_page = page;
-	e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
+	/* Folios marked accessed already */
+	e4b->bd_bitmap_folio = folio;
+	e4b->bd_bitmap = folio_address(folio) + (poff * sb->s_blocksize);
 
 	block++;
 	pnum = block / blocks_per_page;
 	poff = block % blocks_per_page;
 
-	page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
-	if (page == NULL || !PageUptodate(page)) {
-		if (page)
-			put_page(page);
-		page = find_or_create_page(inode->i_mapping, pnum, gfp);
-		if (page) {
-			if (WARN_RATELIMIT(page->mapping != inode->i_mapping,
-	"ext4: buddy bitmap's page->mapping != inode->i_mapping\n")) {
+	folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_ACCESSED, 0);
+	if (IS_ERR(folio) || !folio_test_uptodate(folio)) {
+		if (!IS_ERR(folio))
+			folio_put(folio);
+		folio = __filemap_get_folio(inode->i_mapping, pnum,
+				FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp);
+		if (!IS_ERR(folio)) {
+			if (WARN_RATELIMIT(folio->mapping != inode->i_mapping,
+	"ext4: buddy bitmap's mapping != inode->i_mapping\n")) {
 				/* should never happen */
-				unlock_page(page);
+				folio_unlock(folio);
 				ret = -EINVAL;
 				goto err;
 			}
-			if (!PageUptodate(page)) {
-				ret = ext4_mb_init_cache(page, e4b->bd_bitmap,
+			if (!folio_test_uptodate(folio)) {
+				ret = ext4_mb_init_cache(folio, e4b->bd_bitmap,
 							 gfp);
 				if (ret) {
-					unlock_page(page);
+					folio_unlock(folio);
 					goto err;
 				}
 			}
-			unlock_page(page);
+			folio_unlock(folio);
 		}
 	}
-	if (page == NULL) {
-		ret = -ENOMEM;
+	if (IS_ERR(folio)) {
+		ret = PTR_ERR(folio);
 		goto err;
 	}
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		ret = -EIO;
 		goto err;
 	}
 
-	/* Pages marked accessed already */
-	e4b->bd_buddy_page = page;
-	e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize);
+	/* Folios marked accessed already */
+	e4b->bd_buddy_folio = folio;
+	e4b->bd_buddy = folio_address(folio) + (poff * sb->s_blocksize);
 
 	return 0;
 
 err:
-	if (page)
-		put_page(page);
-	if (e4b->bd_bitmap_page)
-		put_page(e4b->bd_bitmap_page);
+	if (!IS_ERR_OR_NULL(folio))
+		folio_put(folio);
+	if (e4b->bd_bitmap_folio)
+		folio_put(e4b->bd_bitmap_folio);
 
 	e4b->bd_buddy = NULL;
 	e4b->bd_bitmap = NULL;
@@ -1727,10 +1735,10 @@ static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 
 static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 {
-	if (e4b->bd_bitmap_page)
-		put_page(e4b->bd_bitmap_page);
-	if (e4b->bd_buddy_page)
-		put_page(e4b->bd_buddy_page);
+	if (e4b->bd_bitmap_folio)
+		folio_put(e4b->bd_bitmap_folio);
+	if (e4b->bd_buddy_folio)
+		folio_put(e4b->bd_buddy_folio);
 }
 
 
@@ -2040,13 +2048,12 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
 	int ord;
 	int mlen = 0;
 	int max = 0;
-	int cur;
 	int start = ex->fe_start;
 	int len = ex->fe_len;
 	unsigned ret = 0;
 	int len0 = len;
 	void *buddy;
-	bool split = false;
+	int ord_start, ord_end;
 
 	BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3));
 	BUG_ON(e4b->bd_group != ex->fe_group);
@@ -2071,16 +2078,12 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
 
 	/* let's maintain buddy itself */
 	while (len) {
-		if (!split)
-			ord = mb_find_order_for_block(e4b, start);
+		ord = mb_find_order_for_block(e4b, start);
 
 		if (((start >> ord) << ord) == start && len >= (1 << ord)) {
 			/* the whole chunk may be allocated at once! */
 			mlen = 1 << ord;
-			if (!split)
-				buddy = mb_find_buddy(e4b, ord, &max);
-			else
-				split = false;
+			buddy = mb_find_buddy(e4b, ord, &max);
 			BUG_ON((start >> ord) >= max);
 			mb_set_bit(start >> ord, buddy);
 			e4b->bd_info->bb_counters[ord]--;
@@ -2094,20 +2097,29 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
 		if (ret == 0)
 			ret = len | (ord << 16);
 
-		/* we have to split large buddy */
 		BUG_ON(ord <= 0);
 		buddy = mb_find_buddy(e4b, ord, &max);
 		mb_set_bit(start >> ord, buddy);
 		e4b->bd_info->bb_counters[ord]--;
 
-		ord--;
-		cur = (start >> ord) & ~1U;
-		buddy = mb_find_buddy(e4b, ord, &max);
-		mb_clear_bit(cur, buddy);
-		mb_clear_bit(cur + 1, buddy);
-		e4b->bd_info->bb_counters[ord]++;
-		e4b->bd_info->bb_counters[ord]++;
-		split = true;
+		ord_start = (start >> ord) << ord;
+		ord_end = ord_start + (1 << ord);
+		/* first chunk */
+		if (start > ord_start)
+			ext4_mb_mark_free_simple(e4b->bd_sb, e4b->bd_buddy,
+						 ord_start, start - ord_start,
+						 e4b->bd_info);
+
+		/* last chunk */
+		if (start + len < ord_end) {
+			ext4_mb_mark_free_simple(e4b->bd_sb, e4b->bd_buddy,
+						 start + len,
+						 ord_end - (start + len),
+						 e4b->bd_info);
+			break;
+		}
+		len = start + len - ord_end;
+		start = ord_end;
 	}
 	mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
 
@@ -2149,10 +2161,10 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac,
 	 * double allocate blocks. The reference is dropped
 	 * in ext4_mb_release_context
 	 */
-	ac->ac_bitmap_page = e4b->bd_bitmap_page;
-	get_page(ac->ac_bitmap_page);
-	ac->ac_buddy_page = e4b->bd_buddy_page;
-	get_page(ac->ac_buddy_page);
+	ac->ac_bitmap_folio = e4b->bd_bitmap_folio;
+	folio_get(ac->ac_bitmap_folio);
+	ac->ac_buddy_folio = e4b->bd_buddy_folio;
+	folio_get(ac->ac_buddy_folio);
 	/* store last allocated for subsequent stream allocation */
 	if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) {
 		spin_lock(&sbi->s_md_lock);
@@ -2344,7 +2356,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 	ex.fe_logical = 0xDEADFA11; /* debug value */
 
 	if (max >= ac->ac_g_ex.fe_len &&
-	    ac->ac_g_ex.fe_len == EXT4_B2C(sbi, sbi->s_stripe)) {
+	    ac->ac_g_ex.fe_len == EXT4_NUM_B2C(sbi, sbi->s_stripe)) {
 		ext4_fsblk_t start;
 
 		start = ext4_grp_offs_to_block(ac->ac_sb, &ex);
@@ -2541,7 +2553,7 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
 	do_div(a, sbi->s_stripe);
 	i = (a * sbi->s_stripe) - first_group_block;
 
-	stripe = EXT4_B2C(sbi, sbi->s_stripe);
+	stripe = EXT4_NUM_B2C(sbi, sbi->s_stripe);
 	i = EXT4_B2C(sbi, i);
 	while (i < EXT4_CLUSTERS_PER_GROUP(sb)) {
 		if (!mb_test_bit(i, bitmap)) {
@@ -2675,7 +2687,7 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac,
 		int ret;
 
 		/*
-		 * cr=CR_POWER2_ALIGNED/CR_GOAL_LEN_FAST is a very optimistic
+		 * CR_POWER2_ALIGNED/CR_GOAL_LEN_FAST is a very optimistic
 		 * search to find large good chunks almost for free. If buddy
 		 * data is not ready, then this optimization makes no sense. But
 		 * we never skip the first block group in a flex_bg, since this
@@ -2856,6 +2868,7 @@ repeat:
 		group = ac->ac_g_ex.fe_group;
 		ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups;
 		prefetch_grp = group;
+		nr = 0;
 
 		for (i = 0, new_cr = cr; i < ngroups; i++,
 		     ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) {
@@ -2915,9 +2928,11 @@ repeat:
 			if (cr == CR_POWER2_ALIGNED)
 				ext4_mb_simple_scan_group(ac, &e4b);
 			else {
-				bool is_stripe_aligned = sbi->s_stripe &&
+				bool is_stripe_aligned =
+					(sbi->s_stripe >=
+					 sbi->s_cluster_ratio) &&
 					!(ac->ac_g_ex.fe_len %
-					  EXT4_B2C(sbi, sbi->s_stripe));
+					  EXT4_NUM_B2C(sbi, sbi->s_stripe));
 
 				if ((cr == CR_GOAL_LEN_FAST ||
 				     cr == CR_BEST_AVAIL_LEN) &&
@@ -3015,8 +3030,8 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 {
 	struct super_block *sb = pde_data(file_inode(seq->file));
 	ext4_group_t group = (ext4_group_t) ((unsigned long) v);
-	int i;
-	int err, buddy_loaded = 0;
+	int i, err;
+	char nbuf[16];
 	struct ext4_buddy e4b;
 	struct ext4_group_info *grinfo;
 	unsigned char blocksize_bits = min_t(unsigned char,
@@ -3043,24 +3058,26 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) {
 		err = ext4_mb_load_buddy(sb, group, &e4b);
 		if (err) {
-			seq_printf(seq, "#%-5u: I/O error\n", group);
+			seq_printf(seq, "#%-5u: %s\n", group, ext4_decode_error(NULL, err, nbuf));
 			return 0;
 		}
-		buddy_loaded = 1;
+		ext4_mb_unload_buddy(&e4b);
 	}
 
+	/*
+	 * We care only about free space counters in the group info and
+	 * these are safe to access even after the buddy has been unloaded
+	 */
 	memcpy(&sg, grinfo, i);
-
-	if (buddy_loaded)
-		ext4_mb_unload_buddy(&e4b);
-
 	seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
 			sg.info.bb_fragments, sg.info.bb_first_free);
 	for (i = 0; i <= 13; i++)
 		seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ?
 				sg.info.bb_counters[i] : 0);
-	seq_puts(seq, " ]\n");
-
+	seq_puts(seq, " ]");
+	if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info))
+		seq_puts(seq, " Block bitmap corrupted!");
+	seq_putc(seq, '\n');
 	return 0;
 }
 
@@ -3183,7 +3200,6 @@ int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset)
 }
 
 static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos)
-__acquires(&EXT4_SB(sb)->s_mb_rb_lock)
 {
 	struct super_block *sb = pde_data(file_inode(seq->file));
 	unsigned long position;
@@ -3437,10 +3453,11 @@ static int ext4_mb_init_backend(struct super_block *sb)
 	}
 	if (sbi->s_mb_prefetch > ext4_get_groups_count(sb))
 		sbi->s_mb_prefetch = ext4_get_groups_count(sb);
-	/* now many real IOs to prefetch within a single allocation at cr=0
-	 * given cr=0 is an CPU-related optimization we shouldn't try to
-	 * load too many groups, at some point we should start to use what
-	 * we've got in memory.
+	/*
+	 * now many real IOs to prefetch within a single allocation at
+	 * CR_POWER2_ALIGNED. Given CR_POWER2_ALIGNED is an CPU-related
+	 * optimization we shouldn't try to load too many groups, at some point
+	 * we should start to use what we've got in memory.
 	 * with an average random access time 5ms, it'd take a second to get
 	 * 200 groups (* N with flex_bg), so let's make this limit 4
 	 */
@@ -3691,7 +3708,7 @@ int ext4_mb_init(struct super_block *sb)
 	 */
 	if (sbi->s_stripe > 1) {
 		sbi->s_mb_group_prealloc = roundup(
-			sbi->s_mb_group_prealloc, EXT4_B2C(sbi, sbi->s_stripe));
+			sbi->s_mb_group_prealloc, EXT4_NUM_B2C(sbi, sbi->s_stripe));
 	}
 
 	sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
@@ -3829,8 +3846,7 @@ void ext4_mb_release(struct super_block *sb)
 }
 
 static inline int ext4_issue_discard(struct super_block *sb,
-		ext4_group_t block_group, ext4_grpblk_t cluster, int count,
-		struct bio **biop)
+		ext4_group_t block_group, ext4_grpblk_t cluster, int count)
 {
 	ext4_fsblk_t discard_block;
 
@@ -3839,13 +3855,8 @@ static inline int ext4_issue_discard(struct super_block *sb,
 	count = EXT4_C2B(EXT4_SB(sb), count);
 	trace_ext4_discard_blocks(sb,
 			(unsigned long long) discard_block, count);
-	if (biop) {
-		return __blkdev_issue_discard(sb->s_bdev,
-			(sector_t)discard_block << (sb->s_blocksize_bits - 9),
-			(sector_t)count << (sb->s_blocksize_bits - 9),
-			GFP_NOFS, biop);
-	} else
-		return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
+
+	return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
 }
 
 static void ext4_free_data_in_buddy(struct super_block *sb,
@@ -3877,18 +3888,15 @@ static void ext4_free_data_in_buddy(struct super_block *sb,
 	/*
 	 * Clear the trimmed flag for the group so that the next
 	 * ext4_trim_fs can trim it.
-	 * If the volume is mounted with -o discard, online discard
-	 * is supported and the free blocks will be trimmed online.
 	 */
-	if (!test_opt(sb, DISCARD))
-		EXT4_MB_GRP_CLEAR_TRIMMED(db);
+	EXT4_MB_GRP_CLEAR_TRIMMED(db);
 
 	if (!db->bb_free_root.rb_node) {
 		/* No more items in the per group rb tree
 		 * balance refcounts from ext4_mb_free_metadata()
 		 */
-		put_page(e4b.bd_buddy_page);
-		put_page(e4b.bd_bitmap_page);
+		folio_put(e4b.bd_buddy_folio);
+		folio_put(e4b.bd_bitmap_folio);
 	}
 	ext4_unlock_group(sb, entry->efd_group);
 	ext4_mb_unload_buddy(&e4b);
@@ -5169,10 +5177,16 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 			.fe_len = ac->ac_orig_goal_len,
 		};
 		loff_t orig_goal_end = extent_logical_end(sbi, &ex);
+		loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex);
 
-		/* we can't allocate as much as normalizer wants.
-		 * so, found space must get proper lstart
-		 * to cover original request */
+		/*
+		 * We can't allocate as much as normalizer wants, so we try
+		 * to get proper lstart to cover the original request, except
+		 * when the goal doesn't cover the original request as below:
+		 *
+		 * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048
+		 * best_ex:0/200(200) -> adjusted: 1848/2048(200)
+		 */
 		BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical);
 		BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len);
 
@@ -5184,7 +5198,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 		 * 1. Check if best ex can be kept at end of goal (before
 		 *    cr_best_avail trimmed it) and still cover original start
 		 * 2. Else, check if best ex can be kept at start of goal and
-		 *    still cover original start
+		 *    still cover original end
 		 * 3. Else, keep the best ex at start of original request.
 		 */
 		ex.fe_len = ac->ac_b_ex.fe_len;
@@ -5194,7 +5208,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 			goto adjust_bex;
 
 		ex.fe_logical = ac->ac_g_ex.fe_logical;
-		if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex))
+		if (o_ex_end <= extent_logical_end(sbi, &ex))
 			goto adjust_bex;
 
 		ex.fe_logical = ac->ac_o_ex.fe_logical;
@@ -5202,7 +5216,6 @@ adjust_bex:
 		ac->ac_b_ex.fe_logical = ex.fe_logical;
 
 		BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
-		BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
 		BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end);
 	}
 
@@ -5698,7 +5711,7 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
 			(unsigned long)ac->ac_b_ex.fe_logical,
 			(int)ac->ac_criteria);
 	mb_debug(sb, "%u found", ac->ac_found);
-	mb_debug(sb, "used pa: %s, ", ac->ac_pa ? "yes" : "no");
+	mb_debug(sb, "used pa: %s, ", str_yes_no(ac->ac_pa));
 	if (ac->ac_pa)
 		mb_debug(sb, "pa_type %s\n", ac->ac_pa->pa_type == MB_GROUP_PA ?
 			 "group pa" : "inode pa");
@@ -5987,10 +6000,10 @@ static void ext4_mb_release_context(struct ext4_allocation_context *ac)
 
 		ext4_mb_put_pa(ac, ac->ac_sb, pa);
 	}
-	if (ac->ac_bitmap_page)
-		put_page(ac->ac_bitmap_page);
-	if (ac->ac_buddy_page)
-		put_page(ac->ac_buddy_page);
+	if (ac->ac_bitmap_folio)
+		folio_put(ac->ac_bitmap_folio);
+	if (ac->ac_buddy_folio)
+		folio_put(ac->ac_buddy_folio);
 	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
 		mutex_unlock(&ac->ac_lg->lg_mutex);
 	ext4_mb_collect_stats(ac);
@@ -6043,7 +6056,7 @@ static bool ext4_mb_discard_preallocations_should_retry(struct super_block *sb,
 	}
 
 out_dbg:
-	mb_debug(sb, "freed %d, retry ? %s\n", freed, ret ? "yes" : "no");
+	mb_debug(sb, "freed %d, retry ? %s\n", freed, str_yes_no(ret));
 	return ret;
 }
 
@@ -6111,6 +6124,7 @@ ext4_mb_new_blocks_simple(struct ext4_allocation_request *ar, int *errp)
 	ext4_mb_mark_bb(sb, block, 1, true);
 	ar->len = 1;
 
+	*errp = 0;
 	return block;
 }
 
@@ -6305,8 +6319,8 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	struct rb_node *parent = NULL, *new_node;
 
 	BUG_ON(!ext4_handle_valid(handle));
-	BUG_ON(e4b->bd_bitmap_page == NULL);
-	BUG_ON(e4b->bd_buddy_page == NULL);
+	BUG_ON(e4b->bd_bitmap_folio == NULL);
+	BUG_ON(e4b->bd_buddy_folio == NULL);
 
 	new_node = &new_entry->efd_node;
 	cluster = new_entry->efd_start_cluster;
@@ -6317,8 +6331,8 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 		 * otherwise we'll refresh it from
 		 * on-disk bitmap and lose not-yet-available
 		 * blocks */
-		get_page(e4b->bd_buddy_page);
-		get_page(e4b->bd_bitmap_page);
+		folio_get(e4b->bd_buddy_folio);
+		folio_get(e4b->bd_bitmap_folio);
 	}
 	while (*n) {
 		parent = *n;
@@ -6487,14 +6501,21 @@ do_more:
 	} else {
 		if (test_opt(sb, DISCARD)) {
 			err = ext4_issue_discard(sb, block_group, bit,
-						 count_clusters, NULL);
-			if (err && err != -EOPNOTSUPP)
+						 count_clusters);
+			/*
+			 * Ignore EOPNOTSUPP error. This is consistent with
+			 * what happens when using journal.
+			 */
+			if (err == -EOPNOTSUPP)
+				err = 0;
+			if (err)
 				ext4_msg(sb, KERN_WARNING, "discard request in"
 					 " group:%u block:%d count:%lu failed"
 					 " with %d", block_group, bit, count,
 					 err);
-		} else
-			EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
+		}
+
+		EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
 
 		ext4_lock_group(sb, block_group);
 		mb_free_blocks(inode, &e4b, bit, count_clusters);
@@ -6738,7 +6759,7 @@ __acquires(bitlock)
 	 */
 	mb_mark_used(e4b, &ex);
 	ext4_unlock_group(sb, group);
-	ret = ext4_issue_discard(sb, group, start, count, NULL);
+	ret = ext4_issue_discard(sb, group, start, count);
 	ext4_lock_group(sb, group);
 	mb_free_blocks(NULL, e4b, start, ex.fe_len);
 	return ret;
@@ -6978,13 +6999,14 @@ int
 ext4_mballoc_query_range(
 	struct super_block		*sb,
 	ext4_group_t			group,
-	ext4_grpblk_t			start,
+	ext4_grpblk_t			first,
 	ext4_grpblk_t			end,
+	ext4_mballoc_query_range_fn	meta_formatter,
 	ext4_mballoc_query_range_fn	formatter,
 	void				*priv)
 {
 	void				*bitmap;
-	ext4_grpblk_t			next;
+	ext4_grpblk_t			start, next;
 	struct ext4_buddy		e4b;
 	int				error;
 
@@ -6995,10 +7017,19 @@ ext4_mballoc_query_range(
 
 	ext4_lock_group(sb, group);
 
-	start = max(e4b.bd_info->bb_first_free, start);
+	start = max(e4b.bd_info->bb_first_free, first);
 	if (end >= EXT4_CLUSTERS_PER_GROUP(sb))
 		end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
-
+	if (meta_formatter && start != first) {
+		if (start > end)
+			start = end;
+		ext4_unlock_group(sb, group);
+		error = meta_formatter(sb, group, first, start - first,
+				       priv);
+		if (error)
+			goto out_unload;
+		ext4_lock_group(sb, group);
+	}
 	while (start <= end) {
 		start = mb_find_next_zero_bit(bitmap, end + 1, start);
 		if (start > end)