[Devel] [PATCH RHEL7 COMMIT] ms ext4: fix online resize with very large inode tables

[Konstantin Khorenko]

The commit is pushed to "branch-rh7-3.10.0-123.1.2-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-123.1.2.vz7.5.15
------>
commit e50caa544a93a639be31060d95ceb462afcec726
Author: Theodore Ts'o <tytso at mit.edu>
Date:   Mon Jun 22 14:39:04 2015 +0400

    ms ext4: fix online resize with very large inode tables
    
    https://jira.sw.ru/browse/PSBM-24924
    
    Original commit: b93c95353413041a8cebad915a8109619f66bcc6
    [PATCH] ext4: fix online resize with very large inode tables
    
    If a file system has a large number of inodes per block group, all of
    the metadata blocks in a flex_bg may be larger than what can fit in a
    single block group.  Unfortunately, ext4_alloc_group_tables() in
    resize.c was never tested to see if it would handle this case
    correctly, and there were a large number of bugs which caused the
    following sequence to result in a BUG_ON:
    
    kernel bug at fs/ext4/resize.c:409!
       ...
    call trace:
     [<ffffffff81256768>] ext4_flex_group_add+0x1448/0x1830
     [<ffffffff81257de2>] ext4_resize_fs+0x7b2/0xe80
     [<ffffffff8123ac50>] ext4_ioctl+0xbf0/0xf00
     [<ffffffff811c111d>] do_vfs_ioctl+0x2dd/0x4b0
     [<ffffffff811b9df2>] ? final_putname+0x22/0x50
     [<ffffffff811c1371>] sys_ioctl+0x81/0xa0
     [<ffffffff81676aa9>] system_call_fastpath+0x16/0x1b
    code: c8 4c 89 df e8 41 96 f8 ff 44 89 e8 49 01 c4 44 29 6d d4 0
    rip  [<ffffffff81254fa1>] set_flexbg_block_bitmap+0x171/0x180
    
    This can be reproduced with the following command sequence:
    
       mke2fs -t ext4 -i 4096 /dev/vdd 1G
       mount -t ext4 /dev/vdd /vdd
       resize2fs /dev/vdd 8G
    
    To fix this, we need to make sure the right thing happens when a block
    group's inode table straddles two block groups, which means the
    following bugs had to be fixed:
    
    1) Not clearing the BLOCK_UNINIT flag in the second block group in
       ext4_alloc_group_tables --- the was proximate cause of the BUG_ON.
    
    2) Incorrectly determining how many block groups contained contiguous
       free blocks in ext4_alloc_group_tables().
    
    3) Incorrectly setting the start of the next block range to be marked
       in use after a discontinuity in setup_new_flex_group_blocks().
    
    Signed-off-by: Dmitry Monakhov <dmonakhov at openvz.org>
---
 fs/ext4/resize.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index c1568ec..6dae8ee 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -243,6 +243,7 @@ static int ext4_alloc_group_tables(struct super_block *sb,
 	ext4_group_t group;
 	ext4_group_t last_group;
 	unsigned overhead;
+	__u16 uninit_mask = (flexbg_size > 1) ? ~EXT4_BG_BLOCK_UNINIT : ~0;
 
 	BUG_ON(flex_gd->count == 0 || group_data == NULL);
 
@@ -280,8 +281,7 @@ next_group:
 		group = ext4_get_group_number(sb, start_blk - 1);
 		group -= group_data[0].group;
 		group_data[group].free_blocks_count--;
-		if (flexbg_size > 1)
-			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+		flex_gd->bg_flags[group] &= uninit_mask;
 	}
 
 	/* Allocate inode bitmaps */
@@ -292,21 +292,30 @@ next_group:
 		group = ext4_get_group_number(sb, start_blk - 1);
 		group -= group_data[0].group;
 		group_data[group].free_blocks_count--;
-		if (flexbg_size > 1)
-			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+		flex_gd->bg_flags[group] &= uninit_mask;
 	}
 
 	/* Allocate inode tables */
 	for (; it_index < flex_gd->count; it_index++) {
+		unsigned int itb = EXT4_SB(sb)->s_itb_per_group;
+		ext4_fsblk_t next_group_start;
+
 		if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk)
 			goto next_group;
+
 		group_data[it_index].inode_table = start_blk;
 		group = ext4_get_group_number(sb, start_blk - 1);
+		next_group_start = ext4_group_first_block_no(sb, group + 1);
 		group -= group_data[0].group;
-		group_data[group].free_blocks_count -=
-					EXT4_SB(sb)->s_itb_per_group;
-		if (flexbg_size > 1)
-			flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+		if (start_blk + itb > next_group_start) {
+			flex_gd->bg_flags[group + 1] &= uninit_mask;
+			overhead = start_blk + itb - next_group_start;
+			group_data[group + 1].free_blocks_count -= overhead;
+			itb -= overhead;
+		}
+
+		group_data[group].free_blocks_count -= itb;
+		flex_gd->bg_flags[group] &= uninit_mask;
 
 		start_blk += EXT4_SB(sb)->s_itb_per_group;
 	}
@@ -620,7 +629,7 @@ handle_ib:
 			if (err)
 				goto out;
 			count = group_table_count[j];
-			start = group_data[i].block_bitmap;
+			start = (&group_data[i].block_bitmap)[j];
 			block = start;
 		}