[PATCH 3.16.y-ckt 026/170] ext4: move error report out of atomic context in ext4_init_block_bitmap()

From: Luis Henriques
Date: Tue Nov 11 2014 - 07:06:50 EST

3.16.7-ckt1 -stable review patch. If anyone has any objections, please let me know.

------------------

From: Dmitry Monakhov <dmonakhov@xxxxxxxxxx>

commit aef4885ae14f1df75b58395c5314d71f613d26d9 upstream.

Error report likely result in IO so it is bad idea to do it from
atomic context.

This patch should fix following issue:

BUG: sleeping function called from invalid context at include/linux/buffer_head.h:349
in_atomic(): 1, irqs_disabled(): 0, pid: 137, name: kworker/u128:1
5 locks held by kworker/u128:1/137:
#0: ("writeback"){......}, at: [<ffffffff81085618>] process_one_work+0x228/0x4d0
#1: ((&(&wb->dwork)->work)){......}, at: [<ffffffff81085618>] process_one_work+0x228/0x4d0
#2: (jbd2_handle){......}, at: [<ffffffff81242622>] start_this_handle+0x712/0x7b0
#3: (&ei->i_data_sem){......}, at: [<ffffffff811fa387>] ext4_map_blocks+0x297/0x430
#4: (&(&bgl->locks[i].lock)->rlock){......}, at: [<ffffffff811f3180>] ext4_read_block_bitmap_nowait+0x5d0/0x630
CPU: 3 PID: 137 Comm: kworker/u128:1 Not tainted 3.17.0-rc2-00184-g82752e4 #165
Hardware name: Intel Corporation W2600CR/W2600CR, BIOS SE5C600.86B.99.99.x028.061320111235 06/13/2011
Workqueue: writeback bdi_writeback_workfn (flush-1:0)
0000000000000411 ffff880813777288 ffffffff815c7fdc ffff880813777288
ffff880813a8bba0 ffff8808137772a8 ffffffff8108fb30 ffff880803e01e38
ffff880803e01e38 ffff8808137772c8 ffffffff811a8d53 ffff88080ecc6000
Call Trace:
[<ffffffff815c7fdc>] dump_stack+0x51/0x6d
[<ffffffff8108fb30>] __might_sleep+0xf0/0x100
[<ffffffff811a8d53>] __sync_dirty_buffer+0x43/0xe0
[<ffffffff811a8e03>] sync_dirty_buffer+0x13/0x20
[<ffffffff8120f581>] ext4_commit_super+0x1d1/0x230
[<ffffffff8120fa03>] save_error_info+0x23/0x30
[<ffffffff8120fd06>] __ext4_error+0xb6/0xd0
[<ffffffff8120f260>] ? ext4_group_desc_csum+0x140/0x190
[<ffffffff811f2d8c>] ext4_read_block_bitmap_nowait+0x1dc/0x630
[<ffffffff8122e23a>] ext4_mb_init_cache+0x21a/0x8f0
[<ffffffff8113ae95>] ? lru_cache_add+0x55/0x60
[<ffffffff8112e16c>] ? add_to_page_cache_lru+0x6c/0x80
[<ffffffff8122eaa0>] ext4_mb_init_group+0x190/0x280
[<ffffffff8122ec51>] ext4_mb_good_group+0xc1/0x190
[<ffffffff8123309a>] ext4_mb_regular_allocator+0x17a/0x410
[<ffffffff8122c821>] ? ext4_mb_use_preallocated+0x31/0x380
[<ffffffff81233535>] ? ext4_mb_new_blocks+0x205/0x8e0
[<ffffffff8116ed5c>] ? kmem_cache_alloc+0xfc/0x180
[<ffffffff812335b0>] ext4_mb_new_blocks+0x280/0x8e0
[<ffffffff8116f2c4>] ? __kmalloc+0x144/0x1c0
[<ffffffff81221797>] ? ext4_find_extent+0x97/0x320
[<ffffffff812257f4>] ext4_ext_map_blocks+0xbc4/0x1050
[<ffffffff811fa387>] ? ext4_map_blocks+0x297/0x430
[<ffffffff811fa3ab>] ext4_map_blocks+0x2bb/0x430
[<ffffffff81200e43>] ? ext4_init_io_end+0x23/0x50
[<ffffffff811feb44>] ext4_writepages+0x564/0xaf0
[<ffffffff815cde3b>] ? _raw_spin_unlock+0x2b/0x40
[<ffffffff810ac7bd>] ? lock_release_non_nested+0x2fd/0x3c0
[<ffffffff811a009e>] ? writeback_sb_inodes+0x10e/0x490
[<ffffffff811a009e>] ? writeback_sb_inodes+0x10e/0x490
[<ffffffff811377e3>] do_writepages+0x23/0x40
[<ffffffff8119c8ce>] __writeback_single_inode+0x9e/0x280
[<ffffffff811a026b>] writeback_sb_inodes+0x2db/0x490
[<ffffffff811a0664>] wb_writeback+0x174/0x2d0
[<ffffffff810ac359>] ? lock_release_holdtime+0x29/0x190
[<ffffffff811a0863>] wb_do_writeback+0xa3/0x200
[<ffffffff811a0a40>] bdi_writeback_workfn+0x80/0x230
[<ffffffff81085618>] ? process_one_work+0x228/0x4d0
[<ffffffff810856cd>] process_one_work+0x2dd/0x4d0
[<ffffffff81085618>] ? process_one_work+0x228/0x4d0
[<ffffffff81085c1d>] worker_thread+0x35d/0x460
[<ffffffff810858c0>] ? process_one_work+0x4d0/0x4d0
[<ffffffff810858c0>] ? process_one_work+0x4d0/0x4d0
[<ffffffff8108a885>] kthread+0xf5/0x100
[<ffffffff810990e5>] ? local_clock+0x25/0x30
[<ffffffff8108a790>] ? __init_kthread_worker+0x70/0x70
[<ffffffff815ce2ac>] ret_from_fork+0x7c/0xb0
[<ffffffff8108a790>] ? __init_kthread_work

Signed-off-by: Dmitry Monakhov <dmonakhov@xxxxxxxxxx>
Signed-off-by: Theodore Ts'o <tytso@xxxxxxx>
Signed-off-by: Luis Henriques <luis.henriques@xxxxxxxxxxxxx>
---
fs/ext4/balloc.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index fca382037ddd..06b65be20d48 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -176,7 +176,7 @@ static unsigned int num_clusters_in_group(struct super_block *sb,
}

/* Initializes an uninitialized block bitmap */
-static void ext4_init_block_bitmap(struct super_block *sb,
+static int ext4_init_block_bitmap(struct super_block *sb,
struct buffer_head *bh,
ext4_group_t block_group,
struct ext4_group_desc *gdp)
@@ -192,7 +192,6 @@ static void ext4_init_block_bitmap(struct super_block *sb,
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
- ext4_error(sb, "Checksum bad for group %u", block_group);
grp = ext4_get_group_info(sb, block_group);
if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -205,7 +204,7 @@ static void ext4_init_block_bitmap(struct super_block *sb,
count);
}
set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
- return;
+ return -EIO;
}
memset(bh->b_data, 0, sb->s_blocksize);

@@ -243,6 +242,7 @@ static void ext4_init_block_bitmap(struct super_block *sb,
sb->s_blocksize * 8, bh->b_data);
ext4_block_bitmap_csum_set(sb, block_group, gdp, bh);
ext4_group_desc_csum_set(sb, block_group, gdp);
+ return 0;
}

/* Return the number of free blocks in a block group. It is used when
@@ -438,11 +438,15 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
}
ext4_lock_group(sb, block_group);
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
- ext4_init_block_bitmap(sb, bh, block_group, desc);
+ int err;
+
+ err = ext4_init_block_bitmap(sb, bh, block_group, desc);
set_bitmap_uptodate(bh);
set_buffer_uptodate(bh);
ext4_unlock_group(sb, block_group);
unlock_buffer(bh);
+ if (err)
+ ext4_error(sb, "Checksum bad for grp %u", block_group);
return bh;
}
ext4_unlock_group(sb, block_group);
--
2.1.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/