linux-kernel - Re: [PATCH v3 15/17] ext4: convert free groups order lists to xarrays

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <ef789a81-f326-4af6-8e9b-a13b5b20412b@huawei.com>
Date: Thu, 24 Jul 2025 19:14:58 +0800
From: Zhang Yi <yi.zhang@...wei.com>
To: Theodore Ts'o <tytso@....edu>, Guenter Roeck <linux@...ck-us.net>
CC: Baokun Li <libaokun1@...wei.com>, <linux-ext4@...r.kernel.org>,
	<adilger.kernel@...ger.ca>, <jack@...e.cz>, <linux-kernel@...r.kernel.org>,
	<ojaswin@...ux.ibm.com>, <julia.lawall@...ia.fr>, <yangerkun@...wei.com>,
	<libaokun@...weicloud.com>
Subject: Re: [PATCH v3 15/17] ext4: convert free groups order lists to xarrays

On 2025/7/24 12:54, Theodore Ts'o wrote:
> On Wed, Jul 23, 2025 at 08:55:14PM -0700, Guenter Roeck wrote:
>> Hi,
>>
>> On Mon, Jul 14, 2025 at 09:03:25PM +0800, Baokun Li wrote:
>>> While traversing the list, holding a spin_lock prevents load_buddy, making
>>> direct use of ext4_try_lock_group impossible. This can lead to a bouncing
>>> scenario where spin_is_locked(grp_A) succeeds, but ext4_try_lock_group()
>>> fails, forcing the list traversal to repeatedly restart from grp_A.
>>>
>>
>> This patch causes crashes for pretty much every architecture when
>> running unit tests as part of booting.
> 
> I'm assuming that you're using a randconfig that happened to enable
> CONFIG_EXT4_KUNIT_TESTS=y.
> 
> A simpler reprducer is to have a .kunitconfig containing:
> 
> CONFIG_KUNIT=y
> CONFIG_KUNIT_TEST=y
> CONFIG_KUNIT_EXAMPLE_TEST=y
> CONFIG_EXT4_KUNIT_TESTS=y
> 
> ... and then run :./tools/testing/kunit/kunit.py run".
> 
> The first failure is actually with [11/17] ext4: fix largest free
> orders lists corruption on mb_optimize_scan switch, which triggers a
> failure of test_mb_mark_used.
> 
> Baokun, can you take a look please?   Many thanks!
> 

Hi Ted and Guenter,

I'm sorry for this regression, we didn't run these tests. Baokun is
currently on a business trip, so I help to look into this issue. The
reason for the failure is that the variable initialization in the
mb unit tests are insufficient, but this series relies on them.

Could you please try the following diff? I have tested it on my
machine, and the issue does not recur. If every thing looks fine, I
will send out the official patch.

Thanks,
Yi.


diff --git a/fs/ext4/mballoc-test.c b/fs/ext4/mballoc-test.c
index d634c12f1984..a9416b20ff64 100644
--- a/fs/ext4/mballoc-test.c
+++ b/fs/ext4/mballoc-test.c
@@ -155,6 +155,7 @@ static struct super_block *mbt_ext4_alloc_super_block(void)
 	bgl_lock_init(sbi->s_blockgroup_lock);

 	sbi->s_es = &fsb->es;
+	sbi->s_sb = sb;
 	sb->s_fs_info = sbi;

 	up_write(&sb->s_umount);
@@ -802,6 +803,8 @@ static void test_mb_mark_used(struct kunit *test)
 	KUNIT_ASSERT_EQ(test, ret, 0);

 	grp->bb_free = EXT4_CLUSTERS_PER_GROUP(sb);
+	grp->bb_largest_free_order = -1;
+	grp->bb_avg_fragment_size_order = -1;
 	mbt_generate_test_ranges(sb, ranges, TEST_RANGE_COUNT);
 	for (i = 0; i < TEST_RANGE_COUNT; i++)
 		test_mb_mark_used_range(test, &e4b, ranges[i].start,
@@ -875,6 +878,8 @@ static void test_mb_free_blocks(struct kunit *test)
 	ext4_unlock_group(sb, TEST_GOAL_GROUP);

 	grp->bb_free = 0;
+	grp->bb_largest_free_order = -1;
+	grp->bb_avg_fragment_size_order = -1;
 	memset(bitmap, 0xff, sb->s_blocksize);

 	mbt_generate_test_ranges(sb, ranges, TEST_RANGE_COUNT);