1 files changed, 258 insertions, 201 deletions

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index d8a16eecf1d5..859f2ae8864e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -787,6 +787,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	struct inode *inode;
 	char *data;
 	char *bitmap;
+	struct ext4_group_info *grinfo;
 
 	mb_debug(1, "init page %lu\n", page->index);
 
@@ -819,6 +820,18 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 		if (first_group + i >= ngroups)
 			break;
 
+		grinfo = ext4_get_group_info(sb, first_group + i);
+		/*
+		 * 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,
+		 * which may be currently in use by an allocating task.
+		 */
+		if (PageUptodate(page) && !EXT4_MB_GRP_NEED_INIT(grinfo)) {
+			bh[i] = NULL;
+			continue;
+		}
+
 		err = -EIO;
 		desc = ext4_get_group_desc(sb, first_group + i, NULL);
 		if (desc == NULL)
@@ -871,26 +884,28 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	}
 
 	/* wait for I/O completion */
-	for (i = 0; i < groups_per_page && bh[i]; i++)
-		wait_on_buffer(bh[i]);
+	for (i = 0; i < groups_per_page; i++)
+		if (bh[i])
+			wait_on_buffer(bh[i]);
 
 	err = -EIO;
-	for (i = 0; i < groups_per_page && bh[i]; i++)
-		if (!buffer_uptodate(bh[i]))
+	for (i = 0; i < groups_per_page; i++)
+		if (bh[i] && !buffer_uptodate(bh[i]))
 			goto out;
 
 	err = 0;
 	first_block = page->index * blocks_per_page;
-	/* init the page  */
-	memset(page_address(page), 0xff, PAGE_CACHE_SIZE);
 	for (i = 0; i < blocks_per_page; i++) {
 		int group;
-		struct ext4_group_info *grinfo;
 
 		group = (first_block + i) >> 1;
 		if (group >= ngroups)
 			break;
 
+		if (!bh[group - first_group])
+			/* skip initialized uptodate buddy */
+			continue;
+
 		/*
 		 * data carry information regarding this
 		 * particular group in the format specified
@@ -919,6 +934,8 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 			 * incore got set to the group block bitmap below
 			 */
 			ext4_lock_group(sb, group);
+			/* init the buddy */
+			memset(data, 0xff, blocksize);
 			ext4_mb_generate_buddy(sb, data, incore, group);
 			ext4_unlock_group(sb, group);
 			incore = NULL;
@@ -948,7 +965,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 
 out:
 	if (bh) {
-		for (i = 0; i < groups_per_page && bh[i]; i++)
+		for (i = 0; i < groups_per_page; i++)
 			brelse(bh[i]);
 		if (bh != &bhs)
 			kfree(bh);
@@ -957,22 +974,21 @@ out:
 }
 
 /*
- * lock the group_info alloc_sem of all the groups
- * belonging to the same buddy cache page. This
- * make sure other parallel operation on the buddy
- * cache doesn't happen  whild holding the buddy cache
- * lock
+ * 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.
  */
-static int ext4_mb_get_buddy_cache_lock(struct super_block *sb,
-					ext4_group_t group)
+static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
+		ext4_group_t group, struct ext4_buddy *e4b)
 {
-	int i;
-	int block, pnum;
+	struct inode *inode = EXT4_SB(sb)->s_buddy_cache;
+	int block, pnum, poff;
 	int blocks_per_page;
-	int groups_per_page;
-	ext4_group_t ngroups = ext4_get_groups_count(sb);
-	ext4_group_t first_group;
-	struct ext4_group_info *grp;
+	struct page *page;
+
+	e4b->bd_buddy_page = NULL;
+	e4b->bd_bitmap_page = NULL;
 
 	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
 	/*
@@ -982,57 +998,40 @@ static int ext4_mb_get_buddy_cache_lock(struct super_block *sb,
 	 */
 	block = group * 2;
 	pnum = block / blocks_per_page;
-	first_group = pnum * blocks_per_page / 2;
-
-	groups_per_page = blocks_per_page >> 1;
-	if (groups_per_page == 0)
-		groups_per_page = 1;
-	/* read all groups the page covers into the cache */
-	for (i = 0; i < groups_per_page; i++) {
+	poff = block % blocks_per_page;
+	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	if (!page)
+		return -EIO;
+	BUG_ON(page->mapping != inode->i_mapping);
+	e4b->bd_bitmap_page = page;
+	e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
 
-		if ((first_group + i) >= ngroups)
-			break;
-		grp = ext4_get_group_info(sb, first_group + i);
-		/* take all groups write allocation
-		 * semaphore. This make sure there is
-		 * no block allocation going on in any
-		 * of that groups
-		 */
-		down_write_nested(&grp->alloc_sem, i);
+	if (blocks_per_page >= 2) {
+		/* buddy and bitmap are on the same page */
+		return 0;
 	}
-	return i;
+
+	block++;
+	pnum = block / blocks_per_page;
+	poff = block % blocks_per_page;
+	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	if (!page)
+		return -EIO;
+	BUG_ON(page->mapping != inode->i_mapping);
+	e4b->bd_buddy_page = page;
+	return 0;
 }
 
-static void ext4_mb_put_buddy_cache_lock(struct super_block *sb,
-					 ext4_group_t group, int locked_group)
+static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b)
 {
-	int i;
-	int block, pnum;
-	int blocks_per_page;
-	ext4_group_t first_group;
-	struct ext4_group_info *grp;
-
-	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
-	/*
-	 * the buddy cache inode stores the block bitmap
-	 * and buddy information in consecutive blocks.
-	 * So for each group we need two blocks.
-	 */
-	block = group * 2;
-	pnum = block / blocks_per_page;
-	first_group = pnum * blocks_per_page / 2;
-	/* release locks on all the groups */
-	for (i = 0; i < locked_group; i++) {
-
-		grp = ext4_get_group_info(sb, first_group + i);
-		/* take all groups write allocation
-		 * semaphore. This make sure there is
-		 * no block allocation going on in any
-		 * of that groups
-		 */
-		up_write(&grp->alloc_sem);
+	if (e4b->bd_bitmap_page) {
+		unlock_page(e4b->bd_bitmap_page);
+		page_cache_release(e4b->bd_bitmap_page);
+	}
+	if (e4b->bd_buddy_page) {
+		unlock_page(e4b->bd_buddy_page);
+		page_cache_release(e4b->bd_buddy_page);
 	}
-
 }
 
 /*
@@ -1044,93 +1043,60 @@ static noinline_for_stack
 int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 {
 
-	int ret = 0;
-	void *bitmap;
-	int blocks_per_page;
-	int block, pnum, poff;
-	int num_grp_locked = 0;
 	struct ext4_group_info *this_grp;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct inode *inode = sbi->s_buddy_cache;
-	struct page *page = NULL, *bitmap_page = NULL;
+	struct ext4_buddy e4b;
+	struct page *page;
+	int ret = 0;
 
 	mb_debug(1, "init group %u\n", group);
-	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
 	this_grp = ext4_get_group_info(sb, group);
 	/*
 	 * This ensures that we don't reinit the buddy cache
 	 * page which map to the group from which we are already
 	 * allocating. If we are looking at the buddy cache we would
 	 * have taken a reference using ext4_mb_load_buddy and that
-	 * would have taken the alloc_sem lock.
+	 * would have pinned buddy page to page cache.
 	 */
-	num_grp_locked =  ext4_mb_get_buddy_cache_lock(sb, group);
-	if (!EXT4_MB_GRP_NEED_INIT(this_grp)) {
+	ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
+	if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
 		/*
 		 * somebody initialized the group
 		 * return without doing anything
 		 */
-		ret = 0;
 		goto err;
 	}
-	/*
-	 * the buddy cache inode stores the block bitmap
-	 * and buddy information in consecutive blocks.
-	 * So for each group we need two blocks.
-	 */
-	block = group * 2;
-	pnum = block / blocks_per_page;
-	poff = block % blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
-	if (page) {
-		BUG_ON(page->mapping != inode->i_mapping);
-		ret = ext4_mb_init_cache(page, NULL);
-		if (ret) {
-			unlock_page(page);
-			goto err;
-		}
-		unlock_page(page);
-	}
-	if (page == NULL || !PageUptodate(page)) {
+
+	page = e4b.bd_bitmap_page;
+	ret = ext4_mb_init_cache(page, NULL);
+	if (ret)
+		goto err;
+	if (!PageUptodate(page)) {
 		ret = -EIO;
 		goto err;
 	}
 	mark_page_accessed(page);
-	bitmap_page = page;
-	bitmap = page_address(page) + (poff * sb->s_blocksize);
 
-	/* init buddy cache */
-	block++;
-	pnum = block / blocks_per_page;
-	poff = block % blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
-	if (page == bitmap_page) {
+	if (e4b.bd_buddy_page == NULL) {
 		/*
 		 * If both the bitmap and buddy are in
 		 * the same page we don't need to force
 		 * init the buddy
 		 */
-		unlock_page(page);
-	} else if (page) {
-		BUG_ON(page->mapping != inode->i_mapping);
-		ret = ext4_mb_init_cache(page, bitmap);
-		if (ret) {
-			unlock_page(page);
-			goto err;
-		}
-		unlock_page(page);
+		ret = 0;
+		goto err;
 	}
-	if (page == NULL || !PageUptodate(page)) {
+	/* init buddy cache */
+	page = e4b.bd_buddy_page;
+	ret = ext4_mb_init_cache(page, e4b.bd_bitmap);
+	if (ret)
+		goto err;
+	if (!PageUptodate(page)) {
 		ret = -EIO;
 		goto err;
 	}
 	mark_page_accessed(page);
 err:
-	ext4_mb_put_buddy_cache_lock(sb, group, num_grp_locked);
-	if (bitmap_page)
-		page_cache_release(bitmap_page);
-	if (page)
-		page_cache_release(page);
+	ext4_mb_put_buddy_page_lock(&e4b);
 	return ret;
 }
 
@@ -1164,24 +1130,8 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 	e4b->bd_group = group;
 	e4b->bd_buddy_page = NULL;
 	e4b->bd_bitmap_page = NULL;
-	e4b->alloc_semp = &grp->alloc_sem;
-
-	/* Take the read lock on the group alloc
-	 * sem. This would make sure a parallel
-	 * ext4_mb_init_group happening on other
-	 * groups mapped by the page is blocked
-	 * till we are done with allocation
-	 */
-repeat_load_buddy:
-	down_read(e4b->alloc_semp);
 
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-		/* we need to check for group need init flag
-		 * with alloc_semp held so that we can be sure
-		 * that new blocks didn't get added to the group
-		 * when we are loading the buddy cache
-		 */
-		up_read(e4b->alloc_semp);
 		/*
 		 * we need full data about the group
 		 * to make a good selection
@@ -1189,7 +1139,6 @@ repeat_load_buddy:
 		ret = ext4_mb_init_group(sb, group);
 		if (ret)
 			return ret;
-		goto repeat_load_buddy;
 	}
 
 	/*
@@ -1273,15 +1222,14 @@ repeat_load_buddy:
 	return 0;
 
 err:
+	if (page)
+		page_cache_release(page);
 	if (e4b->bd_bitmap_page)
 		page_cache_release(e4b->bd_bitmap_page);
 	if (e4b->bd_buddy_page)
 		page_cache_release(e4b->bd_buddy_page);
 	e4b->bd_buddy = NULL;
 	e4b->bd_bitmap = NULL;
-
-	/* Done with the buddy cache */
-	up_read(e4b->alloc_semp);
 	return ret;
 }
 
@@ -1291,9 +1239,6 @@ static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 		page_cache_release(e4b->bd_bitmap_page);
 	if (e4b->bd_buddy_page)
 		page_cache_release(e4b->bd_buddy_page);
-	/* Done with the buddy cache */
-	if (e4b->alloc_semp)
-		up_read(e4b->alloc_semp);
 }
 
 
@@ -1606,9 +1551,6 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac,
 	get_page(ac->ac_bitmap_page);
 	ac->ac_buddy_page = e4b->bd_buddy_page;
 	get_page(ac->ac_buddy_page);
-	/* on allocation we use ac to track the held semaphore */
-	ac->alloc_semp =  e4b->alloc_semp;
-	e4b->alloc_semp = NULL;
 	/* store last allocated for subsequent stream allocation */
 	if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) {
 		spin_lock(&sbi->s_md_lock);
@@ -2659,7 +2601,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 	struct super_block *sb = journal->j_private;
 	struct ext4_buddy e4b;
 	struct ext4_group_info *db;
-	int err, ret, count = 0, count2 = 0;
+	int err, count = 0, count2 = 0;
 	struct ext4_free_data *entry;
 	struct list_head *l, *ltmp;
 
@@ -2669,15 +2611,9 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 		mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
 			 entry->count, entry->group, entry);
 
-		if (test_opt(sb, DISCARD)) {
-			ret = ext4_issue_discard(sb, entry->group,
-					entry->start_blk, entry->count);
-			if (unlikely(ret == -EOPNOTSUPP)) {
-				ext4_warning(sb, "discard not supported, "
-						 "disabling");
-				clear_opt(sb, DISCARD);
-			}
-		}
+		if (test_opt(sb, DISCARD))
+			ext4_issue_discard(sb, entry->group,
+					   entry->start_blk, entry->count);
 
 		err = ext4_mb_load_buddy(sb, entry->group, &e4b);
 		/* we expect to find existing buddy because it's pinned */
@@ -4226,15 +4162,12 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 			spin_unlock(&pa->pa_lock);
 		}
 	}
-	if (ac->alloc_semp)
-		up_read(ac->alloc_semp);
 	if (pa) {
 		/*
 		 * We want to add the pa to the right bucket.
 		 * Remove it from the list and while adding
 		 * make sure the list to which we are adding
-		 * doesn't grow big.  We need to release
-		 * alloc_semp before calling ext4_mb_add_n_trim()
+		 * doesn't grow big.
 		 */
 		if ((pa->pa_type == MB_GROUP_PA) && likely(pa->pa_free)) {
 			spin_lock(pa->pa_obj_lock);
@@ -4303,7 +4236,9 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 		 * there is enough free blocks to do block allocation
 		 * and verify allocation doesn't exceed the quota limits.
 		 */
-		while (ar->len && ext4_claim_free_blocks(sbi, ar->len)) {
+		while (ar->len &&
+			ext4_claim_free_blocks(sbi, ar->len, ar->flags)) {
+
 			/* let others to free the space */
 			yield();
 			ar->len = ar->len >> 1;
@@ -4313,9 +4248,15 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 			return 0;
 		}
 		reserv_blks = ar->len;
-		while (ar->len && dquot_alloc_block(ar->inode, ar->len)) {
-			ar->flags |= EXT4_MB_HINT_NOPREALLOC;
-			ar->len--;
+		if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) {
+			dquot_alloc_block_nofail(ar->inode, ar->len);
+		} else {
+			while (ar->len &&
+				dquot_alloc_block(ar->inode, ar->len)) {
+
+				ar->flags |= EXT4_MB_HINT_NOPREALLOC;
+				ar->len--;
+			}
 		}
 		inquota = ar->len;
 		if (ar->len == 0) {
@@ -4704,6 +4645,127 @@ error_return:
 }
 
 /**
+ * ext4_add_groupblocks() -- Add given blocks to an existing group
+ * @handle:			handle to this transaction
+ * @sb:				super block
+ * @block:			start physcial block to add to the block group
+ * @count:			number of blocks to free
+ *
+ * This marks the blocks as free in the bitmap and buddy.
+ */
+void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+			 ext4_fsblk_t block, unsigned long count)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *gd_bh;
+	ext4_group_t block_group;
+	ext4_grpblk_t bit;
+	unsigned int i;
+	struct ext4_group_desc *desc;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_buddy e4b;
+	int err = 0, ret, blk_free_count;
+	ext4_grpblk_t blocks_freed;
+	struct ext4_group_info *grp;
+
+	ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
+
+	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+	grp = ext4_get_group_info(sb, block_group);
+	/*
+	 * Check to see if we are freeing blocks across a group
+	 * boundary.
+	 */
+	if (bit + count > EXT4_BLOCKS_PER_GROUP(sb))
+		goto error_return;
+
+	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
+	if (!bitmap_bh)
+		goto error_return;
+	desc = ext4_get_group_desc(sb, block_group, &gd_bh);
+	if (!desc)
+		goto error_return;
+
+	if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
+	    in_range(ext4_inode_bitmap(sb, desc), block, count) ||
+	    in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
+	    in_range(block + count - 1, ext4_inode_table(sb, desc),
+		     sbi->s_itb_per_group)) {
+		ext4_error(sb, "Adding blocks in system zones - "
+			   "Block = %llu, count = %lu",
+			   block, count);
+		goto error_return;
+	}
+
+	BUFFER_TRACE(bitmap_bh, "getting write access");
+	err = ext4_journal_get_write_access(handle, bitmap_bh);
+	if (err)
+		goto error_return;
+
+	/*
+	 * We are about to modify some metadata.  Call the journal APIs
+	 * to unshare ->b_data if a currently-committing transaction is
+	 * using it
+	 */
+	BUFFER_TRACE(gd_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, gd_bh);
+	if (err)
+		goto error_return;
+
+	for (i = 0, blocks_freed = 0; i < count; i++) {
+		BUFFER_TRACE(bitmap_bh, "clear bit");
+		if (!mb_test_bit(bit + i, bitmap_bh->b_data)) {
+			ext4_error(sb, "bit already cleared for block %llu",
+				   (ext4_fsblk_t)(block + i));
+			BUFFER_TRACE(bitmap_bh, "bit already cleared");
+		} else {
+			blocks_freed++;
+		}
+	}
+
+	err = ext4_mb_load_buddy(sb, block_group, &e4b);
+	if (err)
+		goto error_return;
+
+	/*
+	 * need to update group_info->bb_free and bitmap
+	 * with group lock held. generate_buddy look at
+	 * them with group lock_held
+	 */
+	ext4_lock_group(sb, block_group);
+	mb_clear_bits(bitmap_bh->b_data, bit, count);
+	mb_free_blocks(NULL, &e4b, bit, count);
+	blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
+	ext4_free_blks_set(sb, desc, blk_free_count);
+	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
+	ext4_unlock_group(sb, block_group);
+	percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
+
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
+		atomic_add(blocks_freed,
+			   &sbi->s_flex_groups[flex_group].free_blocks);
+	}
+
+	ext4_mb_unload_buddy(&e4b);
+
+	/* We dirtied the bitmap block */
+	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+
+	/* And the group descriptor block */
+	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
+	ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
+	if (!err)
+		err = ret;
+
+error_return:
+	brelse(bitmap_bh);
+	ext4_std_error(sb, err);
+	return;
+}
+
+/**
  * ext4_trim_extent -- function to TRIM one single free extent in the group
  * @sb:		super block for the file system
  * @start:	starting block of the free extent in the alloc. group
@@ -4715,11 +4777,10 @@ error_return:
  * one will allocate those blocks, mark it as used in buddy bitmap. This must
  * be called with under the group lock.
  */
-static int ext4_trim_extent(struct super_block *sb, int start, int count,
-		ext4_group_t group, struct ext4_buddy *e4b)
+static void ext4_trim_extent(struct super_block *sb, int start, int count,
+			     ext4_group_t group, struct ext4_buddy *e4b)
 {
 	struct ext4_free_extent ex;
-	int ret = 0;
 
 	assert_spin_locked(ext4_group_lock_ptr(sb, group));
 
@@ -4733,12 +4794,9 @@ static int ext4_trim_extent(struct super_block *sb, int start, int count,
 	 */
 	mb_mark_used(e4b, &ex);
 	ext4_unlock_group(sb, group);
-
-	ret = ext4_issue_discard(sb, group, start, count);
-
+	ext4_issue_discard(sb, group, start, count);
 	ext4_lock_group(sb, group);
 	mb_free_blocks(NULL, e4b, start, ex.fe_len);
-	return ret;
 }
 
 /**
@@ -4760,21 +4818,26 @@ static int ext4_trim_extent(struct super_block *sb, int start, int count,
  * the group buddy bitmap. This is done until whole group is scanned.
  */
 static ext4_grpblk_t
-ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
-		ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks)
+ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
+		   ext4_grpblk_t start, ext4_grpblk_t max,
+		   ext4_grpblk_t minblocks)
 {
 	void *bitmap;
 	ext4_grpblk_t next, count = 0;
-	ext4_group_t group;
-	int ret = 0;
+	struct ext4_buddy e4b;
+	int ret;
 
-	BUG_ON(e4b == NULL);
+	ret = ext4_mb_load_buddy(sb, group, &e4b);
+	if (ret) {
+		ext4_error(sb, "Error in loading buddy "
+				"information for %u", group);
+		return ret;
+	}
+	bitmap = e4b.bd_bitmap;
 
-	bitmap = e4b->bd_bitmap;
-	group = e4b->bd_group;
-	start = (e4b->bd_info->bb_first_free > start) ?
-		e4b->bd_info->bb_first_free : start;
 	ext4_lock_group(sb, group);
+	start = (e4b.bd_info->bb_first_free > start) ?
+		e4b.bd_info->bb_first_free : start;
 
 	while (start < max) {
 		start = mb_find_next_zero_bit(bitmap, max, start);
@@ -4783,10 +4846,8 @@ ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
 		next = mb_find_next_bit(bitmap, max, start);
 
 		if ((next - start) >= minblocks) {
-			ret = ext4_trim_extent(sb, start,
-				next - start, group, e4b);
-			if (ret < 0)
-				break;
+			ext4_trim_extent(sb, start,
+					 next - start, group, &e4b);
 			count += next - start;
 		}
 		start = next + 1;
@@ -4802,17 +4863,15 @@ ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
 			ext4_lock_group(sb, group);
 		}
 
-		if ((e4b->bd_info->bb_free - count) < minblocks)
+		if ((e4b.bd_info->bb_free - count) < minblocks)
 			break;
 	}
 	ext4_unlock_group(sb, group);
+	ext4_mb_unload_buddy(&e4b);
 
 	ext4_debug("trimmed %d blocks in the group %d\n",
 		count, group);
 
-	if (ret < 0)
-		count = ret;
-
 	return count;
 }
 
@@ -4830,11 +4889,11 @@ ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
  */
 int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 {
-	struct ext4_buddy e4b;
+	struct ext4_group_info *grp;
 	ext4_group_t first_group, last_group;
 	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
 	ext4_grpblk_t cnt = 0, first_block, last_block;
-	uint64_t start, len, minlen, trimmed;
+	uint64_t start, len, minlen, trimmed = 0;
 	ext4_fsblk_t first_data_blk =
 			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
 	int ret = 0;
@@ -4842,7 +4901,6 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	start = range->start >> sb->s_blocksize_bits;
 	len = range->len >> sb->s_blocksize_bits;
 	minlen = range->minlen >> sb->s_blocksize_bits;
-	trimmed = 0;
 
 	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
 		return -EINVAL;
@@ -4863,11 +4921,12 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		return -EINVAL;
 
 	for (group = first_group; group <= last_group; group++) {
-		ret = ext4_mb_load_buddy(sb, group, &e4b);
-		if (ret) {
-			ext4_error(sb, "Error in loading buddy "
-					"information for %u", group);
-			break;
+		grp = ext4_get_group_info(sb, group);
+		/* We only do this if the grp has never been initialized */
+		if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
+			ret = ext4_mb_init_group(sb, group);
+			if (ret)
+				break;
 		}
 
 		/*
@@ -4880,16 +4939,14 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 			last_block = first_block + len;
 		len -= last_block - first_block;
 
-		if (e4b.bd_info->bb_free >= minlen) {
-			cnt = ext4_trim_all_free(sb, &e4b, first_block,
+		if (grp->bb_free >= minlen) {
+			cnt = ext4_trim_all_free(sb, group, first_block,
 						last_block, minlen);
 			if (cnt < 0) {
 				ret = cnt;
-				ext4_mb_unload_buddy(&e4b);
 				break;
 			}
 		}
-		ext4_mb_unload_buddy(&e4b);
 		trimmed += cnt;
 		first_block = 0;
 	}