Skip to main content

Browse the archive

Revision 082cd4ec240b8734a82a89ffb890216ac98fec68 authored by Ye Bin on 06 May 2021, 14:10:42 UTC, committed by Theodore Ts'o on 06 June 2021, 14:09:55 UTC 
ext4: fix bug on in ext4_es_cache_extent as ext4_split_extent_at failed
 
We got follow bug_on when run fsstress with injecting IO fault:
[130747.323114] kernel BUG at fs/ext4/extents_status.c:762!
[130747.323117] Internal error: Oops - BUG: 0 [#1] SMP
......
[130747.334329] Call trace:
[130747.334553]  ext4_es_cache_extent+0x150/0x168 [ext4]
[130747.334975]  ext4_cache_extents+0x64/0xe8 [ext4]
[130747.335368]  ext4_find_extent+0x300/0x330 [ext4]
[130747.335759]  ext4_ext_map_blocks+0x74/0x1178 [ext4]
[130747.336179]  ext4_map_blocks+0x2f4/0x5f0 [ext4]
[130747.336567]  ext4_mpage_readpages+0x4a8/0x7a8 [ext4]
[130747.336995]  ext4_readpage+0x54/0x100 [ext4]
[130747.337359]  generic_file_buffered_read+0x410/0xae8
[130747.337767]  generic_file_read_iter+0x114/0x190
[130747.338152]  ext4_file_read_iter+0x5c/0x140 [ext4]
[130747.338556]  __vfs_read+0x11c/0x188
[130747.338851]  vfs_read+0x94/0x150
[130747.339110]  ksys_read+0x74/0xf0

This patch's modification is according to Jan Kara's suggestion in:
https://patchwork.ozlabs.org/project/linux-ext4/patch/20210428085158.3728201-1-yebin10@huawei.com/
"I see. Now I understand your patch. Honestly, seeing how fragile is trying
to fix extent tree after split has failed in the middle, I would probably
go even further and make sure we fix the tree properly in case of ENOSPC
and EDQUOT (those are easily user triggerable).  Anything else indicates a
HW problem or fs corruption so I'd rather leave the extent tree as is and
don't try to fix it (which also means we will not create overlapping
extents)."

Cc: stable@kernel.org
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20210506141042.3298679-1-yebin10@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
1 parent b45f189
Raw File
failslab.c 
// SPDX-License-Identifier: GPL-2.0
#include <linux/fault-inject.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include "slab.h"

static struct {
	struct fault_attr attr;
	bool ignore_gfp_reclaim;
	bool cache_filter;
} failslab = {
	.attr = FAULT_ATTR_INITIALIZER,
	.ignore_gfp_reclaim = true,
	.cache_filter = false,
};

bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags)
{
	/* No fault-injection for bootstrap cache */
	if (unlikely(s == kmem_cache))
		return false;

	if (gfpflags & __GFP_NOFAIL)
		return false;

	if (failslab.ignore_gfp_reclaim &&
			(gfpflags & __GFP_DIRECT_RECLAIM))
		return false;

	if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB))
		return false;

	return should_fail(&failslab.attr, s->object_size);
}

static int __init setup_failslab(char *str)
{
	return setup_fault_attr(&failslab.attr, str);
}
__setup("failslab=", setup_failslab);

#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
static int __init failslab_debugfs_init(void)
{
	struct dentry *dir;
	umode_t mode = S_IFREG | 0600;

	dir = fault_create_debugfs_attr("failslab", NULL, &failslab.attr);
	if (IS_ERR(dir))
		return PTR_ERR(dir);

	debugfs_create_bool("ignore-gfp-wait", mode, dir,
			    &failslab.ignore_gfp_reclaim);
	debugfs_create_bool("cache-filter", mode, dir,
			    &failslab.cache_filter);

	return 0;
}

late_initcall(failslab_debugfs_init);

#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
back to top