ext4: fix ext4_get_group_number()

The function ext4_get_group_number() was introduced as an optimization
in commit bd86298e60b8.  Unfortunately, this commit incorrectly
calculate the group number for file systems with a 1k block size (when
s_first_data_block is 1 instead of zero).  This could cause the
following kernel BUG:

[  568.877799] ------------[ cut here ]------------
[  568.877833] kernel BUG at fs/ext4/mballoc.c:3728!
[  568.877840] Oops: Exception in kernel mode, sig: 5 [#1]
[  568.877845] SMP NR_CPUS=32 NUMA pSeries
[  568.877852] Modules linked in: binfmt_misc
[  568.877861] CPU: 1 PID: 3516 Comm: fs_mark Not tainted 3.10.0-03216-g7c6809f-dirty #1
[  568.877867] task: c0000001fb0b8000 ti: c0000001fa954000 task.ti: c0000001fa954000
[  568.877873] NIP: c0000000002f42a4 LR: c0000000002f4274 CTR: c000000000317ef8
[  568.877879] REGS: c0000001fa956ed0 TRAP: 0700   Not tainted  (3.10.0-03216-g7c6809f-dirty)
[  568.877884] MSR: 8000000000029032 <SF,EE,ME,IR,DR,RI>  CR: 24000428  XER: 00000000
[  568.877902] SOFTE: 1
[  568.877905] CFAR: c0000000002b5464
[  568.877908]
GPR00: 0000000000000001 c0000001fa957150 c000000000c6a408 c0000001fb588000
GPR04: 0000000000003fff c0000001fa9571c0 c0000001fa9571c4 000138098c50625f
GPR08: 1301200000000000 0000000000000002 0000000000000001 0000000000000000
GPR12: 0000000024000422 c00000000f33a300 0000000000008000 c0000001fa9577f0
GPR16: c0000001fb7d0100 c000000000c29190 c0000000007f46e8 c000000000a14672
GPR20: 0000000000000001 0000000000000008 ffffffffffffffff 0000000000000000
GPR24: 0000000000000100 c0000001fa957278 c0000001fdb2bc78 c0000001fa957288
GPR28: 0000000000100100 c0000001fa957288 c0000001fb588000 c0000001fdb2bd10
[  568.877993] NIP [c0000000002f42a4] .ext4_mb_release_group_pa+0xec/0x1c0
[  568.877999] LR [c0000000002f4274] .ext4_mb_release_group_pa+0xbc/0x1c0
[  568.878004] Call Trace:
[  568.878008] [c0000001fa957150] [c0000000002f4274] .ext4_mb_release_group_pa+0xbc/0x1c0 (unreliable)
[  568.878017] [c0000001fa957200] [c0000000002fb070] .ext4_mb_discard_lg_preallocations+0x394/0x444
[  568.878025] [c0000001fa957340] [c0000000002fb45c] .ext4_mb_release_context+0x33c/0x734
[  568.878032] [c0000001fa957440] [c0000000002fbcf8] .ext4_mb_new_blocks+0x4a4/0x5f4
[  568.878039] [c0000001fa957510] [c0000000002ef56c] .ext4_ext_map_blocks+0xc28/0x1178
[  568.878047] [c0000001fa957640] [c0000000002c1a94] .ext4_map_blocks+0x2c8/0x490
[  568.878054] [c0000001fa957730] [c0000000002c536c] .ext4_writepages+0x738/0xc60
[  568.878062] [c0000001fa957950] [c000000000168a78] .do_writepages+0x5c/0x80
[  568.878069] [c0000001fa9579d0] [c00000000015d1c4] .__filemap_fdatawrite_range+0x88/0xb0
[  568.878078] [c0000001fa957aa0] [c00000000015d23c] .filemap_write_and_wait_range+0x50/0xfc
[  568.878085] [c0000001fa957b30] [c0000000002b8edc] .ext4_sync_file+0x220/0x3c4
[  568.878092] [c0000001fa957be0] [c0000000001f849c] .vfs_fsync_range+0x64/0x80
[  568.878098] [c0000001fa957c70] [c0000000001f84f0] .vfs_fsync+0x38/0x4c
[  568.878105] [c0000001fa957d00] [c0000000001f87f4] .do_fsync+0x54/0x90
[  568.878111] [c0000001fa957db0] [c0000000001f8894] .SyS_fsync+0x28/0x3c
[  568.878120] [c0000001fa957e30] [c000000000009c88] syscall_exit+0x0/0x7c
[  568.878125] Instruction dump:
[  568.878130] 60000000 813d0034 81610070 38000000 7f8b4800 419e001c 813f007c 7d2bfe70
[  568.878144] 7d604a78 7c005850 54000ffe 7c0007b4 <0b000000> e8a10076 e87f0090 7fa4eb78
[  568.878160] ---[ end trace 594d911d9654770b ]---

In addition fix the STD_GROUP optimization so that it works for
bigalloc file systems as well.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Reported-by: Li Zhong <lizhongfs@gmail.com>
Reviewed-by: Lukas Czerner <lczerner@redhat.com>
Cc: stable@vger.kernel.org  # 3.10

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 58339393fa6e55c689adfa375b804a108a25c924..ddd715e42a5c516be8e576015e073846d872f578 100644 (file)
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -38,8 +38,8 @@ ext4_group_t ext4_get_group_number(struct super_block *sb,
        ext4_group_t group;
 
        if (test_opt2(sb, STD_GROUP_SIZE))
-               group = (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
-                        block) >>
+               group = (block -
+                        le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) >>
                        (EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3);
        else
                ext4_get_group_no_and_offset(sb, block, &group, NULL);

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 85b3dd60169beba2b2535ae4342a436387273e32..8862d4ddf71f78f96525f876349a596612d5011d 100644 (file)
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3624,10 +3624,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
        sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
        sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
 
-       /* Do we have standard group size of blocksize * 8 blocks ? */
-       if (sbi->s_blocks_per_group == blocksize << 3)
-               set_opt2(sb, STD_GROUP_SIZE);
-
        for (i = 0; i < 4; i++)
                sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
        sbi->s_def_hash_version = es->s_def_hash_version;
@@ -3697,6 +3693,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                goto failed_mount;
        }
 
+       /* Do we have standard group size of clustersize * 8 blocks ? */
+       if (sbi->s_blocks_per_group == clustersize << 3)
+               set_opt2(sb, STD_GROUP_SIZE);
+
        /*
         * Test whether we have more sectors than will fit in sector_t,
         * and whether the max offset is addressable by the page cache.