The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x d13f99632748462c32fc95d729f5e754bab06064
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023072120-vocalist-unfold-d697@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
d13f99632748 ("ext4: turn quotas off if mount failed after enabling quotas")
a5fc51193507 ("ext4: remove cantfind_ext4 error handler")
02f310fcf47f ("ext4: Speedup ext4 orphan inode handling")
25c6d98fc4c2 ("ext4: Move orphan inode handling into a separate file")
188c299e2a26 ("ext4: Support for checksumming from journal triggers")
bd2c38cf1726 ("ext4: Make sure quota files are not grabbed accidentally")
b9a037b7f3c4 ("ext4: cleanup in-core orphan list if ext4_truncate() failed to get a transaction handle")
72ffb49a7b62 ("ext4: do not set SB_ACTIVE in ext4_orphan_cleanup()")
c915fb80eaa6 ("ext4: fix bh ref count on error paths")
a3f5cf14ff91 ("ext4: drop ext4_handle_dirty_super()")
05c2c00f3769 ("ext4: protect superblock modifications with a buffer lock")
4392fbc4bab5 ("ext4: drop sync argument of ext4_commit_super()")
c92dc856848f ("ext4: defer saving error info from atomic context")
02a7780e4d2f ("ext4: simplify ext4 error translation")
4067662388f9 ("ext4: move functions in super.c")
014c9caa29d3 ("ext4: make ext4_abort() use __ext4_error()")
b08070eca9e2 ("ext4: don't remount read-only with errors=continue on reboot")
837c23fbc1b8 ("ext4: use ASSERT() to replace J_ASSERT()")
ca9b404ff137 ("ext4: print quota journalling mode on (re-)mount")
f177ee0882af ("ext4: add helpers for checking whether quota can be enabled/is journalled")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From d13f99632748462c32fc95d729f5e754bab06064 Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1(a)huawei.com>
Date: Mon, 27 Mar 2023 22:16:29 +0800
Subject: [PATCH] ext4: turn quotas off if mount failed after enabling quotas
Yi found during a review of the patch "ext4: don't BUG on inconsistent
journal feature" that when ext4_mark_recovery_complete() returns an error
value, the error handling path does not turn off the enabled quotas,
which triggers the following kmemleak:
================================================================
unreferenced object 0xffff8cf68678e7c0 (size 64):
comm "mount", pid 746, jiffies 4294871231 (age 11.540s)
hex dump (first 32 bytes):
00 90 ef 82 f6 8c ff ff 00 00 00 00 41 01 00 00 ............A...
c7 00 00 00 bd 00 00 00 0a 00 00 00 48 00 00 00 ............H...
backtrace:
[<00000000c561ef24>] __kmem_cache_alloc_node+0x4d4/0x880
[<00000000d4e621d7>] kmalloc_trace+0x39/0x140
[<00000000837eee74>] v2_read_file_info+0x18a/0x3a0
[<0000000088f6c877>] dquot_load_quota_sb+0x2ed/0x770
[<00000000340a4782>] dquot_load_quota_inode+0xc6/0x1c0
[<0000000089a18bd5>] ext4_enable_quotas+0x17e/0x3a0 [ext4]
[<000000003a0268fa>] __ext4_fill_super+0x3448/0x3910 [ext4]
[<00000000b0f2a8a8>] ext4_fill_super+0x13d/0x340 [ext4]
[<000000004a9489c4>] get_tree_bdev+0x1dc/0x370
[<000000006e723bf1>] ext4_get_tree+0x1d/0x30 [ext4]
[<00000000c7cb663d>] vfs_get_tree+0x31/0x160
[<00000000320e1bed>] do_new_mount+0x1d5/0x480
[<00000000c074654c>] path_mount+0x22e/0xbe0
[<0000000003e97a8e>] do_mount+0x95/0xc0
[<000000002f3d3736>] __x64_sys_mount+0xc4/0x160
[<0000000027d2140c>] do_syscall_64+0x3f/0x90
================================================================
To solve this problem, we add a "failed_mount10" tag, and call
ext4_quota_off_umount() in this tag to release the enabled qoutas.
Fixes: 11215630aada ("ext4: don't BUG on inconsistent journal feature")
Cc: stable(a)kernel.org
Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com>
Signed-off-by: Baokun Li <libaokun1(a)huawei.com>
Reviewed-by: Jan Kara <jack(a)suse.cz>
Link: https://lore.kernel.org/r/20230327141630.156875-2-libaokun1@huawei.com
Signed-off-by: Theodore Ts'o <tytso(a)mit.edu>
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 433550e93561..1cc60a7ae4aa 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5577,7 +5577,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
ext4_msg(sb, KERN_INFO, "recovery complete");
err = ext4_mark_recovery_complete(sb, es);
if (err)
- goto failed_mount9;
+ goto failed_mount10;
}
if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev))
@@ -5596,7 +5596,9 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
return 0;
-failed_mount9:
+failed_mount10:
+ ext4_quota_off_umount(sb);
+failed_mount9: __maybe_unused
ext4_release_orphan_info(sb);
failed_mount8:
ext4_unregister_sysfs(sb);
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 26fb5290240dc31cae99b8b4dd2af7f46dfcba6b
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023072109-anemia-unaltered-2936@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
26fb5290240d ("ext4: Fix reusing stale buffer heads from last failed mounting")
ee7ed3aa0f08 ("ext4: rename journal_dev to s_journal_dev inside ext4_sb_info")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 26fb5290240dc31cae99b8b4dd2af7f46dfcba6b Mon Sep 17 00:00:00 2001
From: Zhihao Cheng <chengzhihao1(a)huawei.com>
Date: Wed, 15 Mar 2023 09:31:23 +0800
Subject: [PATCH] ext4: Fix reusing stale buffer heads from last failed
mounting
Following process makes ext4 load stale buffer heads from last failed
mounting in a new mounting operation:
mount_bdev
ext4_fill_super
| ext4_load_and_init_journal
| ext4_load_journal
| jbd2_journal_load
| load_superblock
| journal_get_superblock
| set_buffer_verified(bh) // buffer head is verified
| jbd2_journal_recover // failed caused by EIO
| goto failed_mount3a // skip 'sb->s_root' initialization
deactivate_locked_super
kill_block_super
generic_shutdown_super
if (sb->s_root)
// false, skip ext4_put_super->invalidate_bdev->
// invalidate_mapping_pages->mapping_evict_folio->
// filemap_release_folio->try_to_free_buffers, which
// cannot drop buffer head.
blkdev_put
blkdev_put_whole
if (atomic_dec_and_test(&bdev->bd_openers))
// false, systemd-udev happens to open the device. Then
// blkdev_flush_mapping->kill_bdev->truncate_inode_pages->
// truncate_inode_folio->truncate_cleanup_folio->
// folio_invalidate->block_invalidate_folio->
// filemap_release_folio->try_to_free_buffers will be skipped,
// dropping buffer head is missed again.
Second mount:
ext4_fill_super
ext4_load_and_init_journal
ext4_load_journal
ext4_get_journal
jbd2_journal_init_inode
journal_init_common
bh = getblk_unmovable
bh = __find_get_block // Found stale bh in last failed mounting
journal->j_sb_buffer = bh
jbd2_journal_load
load_superblock
journal_get_superblock
if (buffer_verified(bh))
// true, skip journal->j_format_version = 2, value is 0
jbd2_journal_recover
do_one_pass
next_log_block += count_tags(journal, bh)
// According to journal_tag_bytes(), 'tag_bytes' calculating is
// affected by jbd2_has_feature_csum3(), jbd2_has_feature_csum3()
// returns false because 'j->j_format_version >= 2' is not true,
// then we get wrong next_log_block. The do_one_pass may exit
// early whenoccuring non JBD2_MAGIC_NUMBER in 'next_log_block'.
The filesystem is corrupted here, journal is partially replayed, and
new journal sequence number actually is already used by last mounting.
The invalidate_bdev() can drop all buffer heads even racing with bare
reading block device(eg. systemd-udev), so we can fix it by invalidating
bdev in error handling path in __ext4_fill_super().
Fetch a reproducer in [Link].
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217171
Fixes: 25ed6e8a54df ("jbd2: enable journal clients to enable v2 checksumming")
Cc: stable(a)vger.kernel.org # v3.5
Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com>
Reviewed-by: Jan Kara <jack(a)suse.cz>
Link: https://lore.kernel.org/r/20230315013128.3911115-2-chengzhihao1@huawei.com
Signed-off-by: Theodore Ts'o <tytso(a)mit.edu>
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7f9b087b9b20..6a8c5c3c9126 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1128,6 +1128,12 @@ static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
struct block_device *bdev;
bdev = sbi->s_journal_bdev;
if (bdev) {
+ /*
+ * Invalidate the journal device's buffers. We don't want them
+ * floating about in memory - the physical journal device may
+ * hotswapped, and it breaks the `ro-after' testing code.
+ */
+ invalidate_bdev(bdev);
ext4_blkdev_put(bdev);
sbi->s_journal_bdev = NULL;
}
@@ -1328,13 +1334,7 @@ static void ext4_put_super(struct super_block *sb)
sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
if (sbi->s_journal_bdev && sbi->s_journal_bdev != sb->s_bdev) {
- /*
- * Invalidate the journal device's buffers. We don't want them
- * floating about in memory - the physical journal device may
- * hotswapped, and it breaks the `ro-after' testing code.
- */
sync_blockdev(sbi->s_journal_bdev);
- invalidate_bdev(sbi->s_journal_bdev);
ext4_blkdev_remove(sbi);
}
@@ -5655,6 +5655,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
brelse(sbi->s_sbh);
ext4_blkdev_remove(sbi);
out_fail:
+ invalidate_bdev(sb->s_bdev);
sb->s_fs_info = NULL;
return err;
}
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 26fb5290240dc31cae99b8b4dd2af7f46dfcba6b
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023072107-action-steadily-cfc3@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
26fb5290240d ("ext4: Fix reusing stale buffer heads from last failed mounting")
ee7ed3aa0f08 ("ext4: rename journal_dev to s_journal_dev inside ext4_sb_info")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
4dc5794cf207 ("gpio: pca9570: Add DT bindings for NXP PCA9570")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 26fb5290240dc31cae99b8b4dd2af7f46dfcba6b Mon Sep 17 00:00:00 2001
From: Zhihao Cheng <chengzhihao1(a)huawei.com>
Date: Wed, 15 Mar 2023 09:31:23 +0800
Subject: [PATCH] ext4: Fix reusing stale buffer heads from last failed
mounting
Following process makes ext4 load stale buffer heads from last failed
mounting in a new mounting operation:
mount_bdev
ext4_fill_super
| ext4_load_and_init_journal
| ext4_load_journal
| jbd2_journal_load
| load_superblock
| journal_get_superblock
| set_buffer_verified(bh) // buffer head is verified
| jbd2_journal_recover // failed caused by EIO
| goto failed_mount3a // skip 'sb->s_root' initialization
deactivate_locked_super
kill_block_super
generic_shutdown_super
if (sb->s_root)
// false, skip ext4_put_super->invalidate_bdev->
// invalidate_mapping_pages->mapping_evict_folio->
// filemap_release_folio->try_to_free_buffers, which
// cannot drop buffer head.
blkdev_put
blkdev_put_whole
if (atomic_dec_and_test(&bdev->bd_openers))
// false, systemd-udev happens to open the device. Then
// blkdev_flush_mapping->kill_bdev->truncate_inode_pages->
// truncate_inode_folio->truncate_cleanup_folio->
// folio_invalidate->block_invalidate_folio->
// filemap_release_folio->try_to_free_buffers will be skipped,
// dropping buffer head is missed again.
Second mount:
ext4_fill_super
ext4_load_and_init_journal
ext4_load_journal
ext4_get_journal
jbd2_journal_init_inode
journal_init_common
bh = getblk_unmovable
bh = __find_get_block // Found stale bh in last failed mounting
journal->j_sb_buffer = bh
jbd2_journal_load
load_superblock
journal_get_superblock
if (buffer_verified(bh))
// true, skip journal->j_format_version = 2, value is 0
jbd2_journal_recover
do_one_pass
next_log_block += count_tags(journal, bh)
// According to journal_tag_bytes(), 'tag_bytes' calculating is
// affected by jbd2_has_feature_csum3(), jbd2_has_feature_csum3()
// returns false because 'j->j_format_version >= 2' is not true,
// then we get wrong next_log_block. The do_one_pass may exit
// early whenoccuring non JBD2_MAGIC_NUMBER in 'next_log_block'.
The filesystem is corrupted here, journal is partially replayed, and
new journal sequence number actually is already used by last mounting.
The invalidate_bdev() can drop all buffer heads even racing with bare
reading block device(eg. systemd-udev), so we can fix it by invalidating
bdev in error handling path in __ext4_fill_super().
Fetch a reproducer in [Link].
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217171
Fixes: 25ed6e8a54df ("jbd2: enable journal clients to enable v2 checksumming")
Cc: stable(a)vger.kernel.org # v3.5
Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com>
Reviewed-by: Jan Kara <jack(a)suse.cz>
Link: https://lore.kernel.org/r/20230315013128.3911115-2-chengzhihao1@huawei.com
Signed-off-by: Theodore Ts'o <tytso(a)mit.edu>
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7f9b087b9b20..6a8c5c3c9126 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1128,6 +1128,12 @@ static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
struct block_device *bdev;
bdev = sbi->s_journal_bdev;
if (bdev) {
+ /*
+ * Invalidate the journal device's buffers. We don't want them
+ * floating about in memory - the physical journal device may
+ * hotswapped, and it breaks the `ro-after' testing code.
+ */
+ invalidate_bdev(bdev);
ext4_blkdev_put(bdev);
sbi->s_journal_bdev = NULL;
}
@@ -1328,13 +1334,7 @@ static void ext4_put_super(struct super_block *sb)
sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
if (sbi->s_journal_bdev && sbi->s_journal_bdev != sb->s_bdev) {
- /*
- * Invalidate the journal device's buffers. We don't want them
- * floating about in memory - the physical journal device may
- * hotswapped, and it breaks the `ro-after' testing code.
- */
sync_blockdev(sbi->s_journal_bdev);
- invalidate_bdev(sbi->s_journal_bdev);
ext4_blkdev_remove(sbi);
}
@@ -5655,6 +5655,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
brelse(sbi->s_sbh);
ext4_blkdev_remove(sbi);
out_fail:
+ invalidate_bdev(sb->s_bdev);
sb->s_fs_info = NULL;
return err;
}
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 26fb5290240dc31cae99b8b4dd2af7f46dfcba6b
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023072106-retrial-nature-2689@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
26fb5290240d ("ext4: Fix reusing stale buffer heads from last failed mounting")
ee7ed3aa0f08 ("ext4: rename journal_dev to s_journal_dev inside ext4_sb_info")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 26fb5290240dc31cae99b8b4dd2af7f46dfcba6b Mon Sep 17 00:00:00 2001
From: Zhihao Cheng <chengzhihao1(a)huawei.com>
Date: Wed, 15 Mar 2023 09:31:23 +0800
Subject: [PATCH] ext4: Fix reusing stale buffer heads from last failed
mounting
Following process makes ext4 load stale buffer heads from last failed
mounting in a new mounting operation:
mount_bdev
ext4_fill_super
| ext4_load_and_init_journal
| ext4_load_journal
| jbd2_journal_load
| load_superblock
| journal_get_superblock
| set_buffer_verified(bh) // buffer head is verified
| jbd2_journal_recover // failed caused by EIO
| goto failed_mount3a // skip 'sb->s_root' initialization
deactivate_locked_super
kill_block_super
generic_shutdown_super
if (sb->s_root)
// false, skip ext4_put_super->invalidate_bdev->
// invalidate_mapping_pages->mapping_evict_folio->
// filemap_release_folio->try_to_free_buffers, which
// cannot drop buffer head.
blkdev_put
blkdev_put_whole
if (atomic_dec_and_test(&bdev->bd_openers))
// false, systemd-udev happens to open the device. Then
// blkdev_flush_mapping->kill_bdev->truncate_inode_pages->
// truncate_inode_folio->truncate_cleanup_folio->
// folio_invalidate->block_invalidate_folio->
// filemap_release_folio->try_to_free_buffers will be skipped,
// dropping buffer head is missed again.
Second mount:
ext4_fill_super
ext4_load_and_init_journal
ext4_load_journal
ext4_get_journal
jbd2_journal_init_inode
journal_init_common
bh = getblk_unmovable
bh = __find_get_block // Found stale bh in last failed mounting
journal->j_sb_buffer = bh
jbd2_journal_load
load_superblock
journal_get_superblock
if (buffer_verified(bh))
// true, skip journal->j_format_version = 2, value is 0
jbd2_journal_recover
do_one_pass
next_log_block += count_tags(journal, bh)
// According to journal_tag_bytes(), 'tag_bytes' calculating is
// affected by jbd2_has_feature_csum3(), jbd2_has_feature_csum3()
// returns false because 'j->j_format_version >= 2' is not true,
// then we get wrong next_log_block. The do_one_pass may exit
// early whenoccuring non JBD2_MAGIC_NUMBER in 'next_log_block'.
The filesystem is corrupted here, journal is partially replayed, and
new journal sequence number actually is already used by last mounting.
The invalidate_bdev() can drop all buffer heads even racing with bare
reading block device(eg. systemd-udev), so we can fix it by invalidating
bdev in error handling path in __ext4_fill_super().
Fetch a reproducer in [Link].
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217171
Fixes: 25ed6e8a54df ("jbd2: enable journal clients to enable v2 checksumming")
Cc: stable(a)vger.kernel.org # v3.5
Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com>
Reviewed-by: Jan Kara <jack(a)suse.cz>
Link: https://lore.kernel.org/r/20230315013128.3911115-2-chengzhihao1@huawei.com
Signed-off-by: Theodore Ts'o <tytso(a)mit.edu>
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7f9b087b9b20..6a8c5c3c9126 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1128,6 +1128,12 @@ static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
struct block_device *bdev;
bdev = sbi->s_journal_bdev;
if (bdev) {
+ /*
+ * Invalidate the journal device's buffers. We don't want them
+ * floating about in memory - the physical journal device may
+ * hotswapped, and it breaks the `ro-after' testing code.
+ */
+ invalidate_bdev(bdev);
ext4_blkdev_put(bdev);
sbi->s_journal_bdev = NULL;
}
@@ -1328,13 +1334,7 @@ static void ext4_put_super(struct super_block *sb)
sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
if (sbi->s_journal_bdev && sbi->s_journal_bdev != sb->s_bdev) {
- /*
- * Invalidate the journal device's buffers. We don't want them
- * floating about in memory - the physical journal device may
- * hotswapped, and it breaks the `ro-after' testing code.
- */
sync_blockdev(sbi->s_journal_bdev);
- invalidate_bdev(sbi->s_journal_bdev);
ext4_blkdev_remove(sbi);
}
@@ -5655,6 +5655,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
brelse(sbi->s_sbh);
ext4_blkdev_remove(sbi);
out_fail:
+ invalidate_bdev(sb->s_bdev);
sb->s_fs_info = NULL;
return err;
}
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 531b3d1195d096f14e030c4b01ec3a53b80276bf
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023072131-hydrant-clatter-4b9f@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
531b3d1195d0 ("MIPS: Loongson: Fix build error when make modules_install")
194a83521052 ("MIPS: Loongson: Move arch cflags to MIPS top level Makefile")
337ff6bb8960 ("MIPS: Prefer cc-option for additions to cflags")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 531b3d1195d096f14e030c4b01ec3a53b80276bf Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai(a)kernel.org>
Date: Wed, 28 Jun 2023 19:08:47 +0800
Subject: [PATCH] MIPS: Loongson: Fix build error when make modules_install
After commit 0e96ea5c3eb5904e5dc2f ("MIPS: Loongson64: Clean up use of
cc-ifversion") we get a build error when make modules_install:
cc1: error: '-mloongson-mmi' must be used with '-mhard-float'
The reason is when make modules_install, 'call cc-option' doesn't work
in $(KBUILD_CFLAGS) of 'CHECKFLAGS'. Then there is no -mno-loongson-mmi
applied and -march=loongson3a enable MMI instructions.
To be detail, the error message comes from the CHECKFLAGS invocation of
$(CC) but it has no impact on the final result of make modules_install,
it is purely a cosmetic issue. The error occurs because cc-option is
defined in scripts/Makefile.compiler, which is not included in Makefile
when running 'make modules_install', as install targets are not supposed
to require the compiler; see commit 805b2e1d427aab4b ("kbuild: include
Makefile.compiler only when compiler is needed"). As a result, the call
to check for '-mno-loongson-mmi' just never happens.
Fix this by partially reverting to the old logic, use 'call cc-option'
to conditionally apply -march=loongson3a and -march=mips64r2.
By the way, Loongson-2E/2F is also broken in commit 13ceb48bc19c563e05f4
("MIPS: Loongson2ef: Remove unnecessary {as,cc}-option calls") so fix it
together.
Fixes: 13ceb48bc19c563e05f4 ("MIPS: Loongson2ef: Remove unnecessary {as,cc}-option calls")
Fixes: 0e96ea5c3eb5904e5dc2 ("MIPS: Loongson64: Clean up use of cc-ifversion")
Cc: stable(a)vger.kernel.org
Cc: Feiyang Chen <chenfeiyang(a)loongson.cn>
Cc: Nathan Chancellor <nathan(a)kernel.org>
Cc: Nick Desaulniers <ndesaulniers(a)google.com>
Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn>
Reviewed-by: Nathan Chancellor <nathan(a)kernel.org>
Signed-off-by: Thomas Bogendoerfer <tsbogend(a)alpha.franken.de>
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index a7a4ee66a9d3..35a1b9b34734 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -181,16 +181,12 @@ endif
cflags-$(CONFIG_CAVIUM_CN63XXP1) += -Wa,-mfix-cn63xxp1
cflags-$(CONFIG_CPU_BMIPS) += -march=mips32 -Wa,-mips32 -Wa,--trap
-cflags-$(CONFIG_CPU_LOONGSON2E) += -march=loongson2e -Wa,--trap
-cflags-$(CONFIG_CPU_LOONGSON2F) += -march=loongson2f -Wa,--trap
+cflags-$(CONFIG_CPU_LOONGSON2E) += $(call cc-option,-march=loongson2e) -Wa,--trap
+cflags-$(CONFIG_CPU_LOONGSON2F) += $(call cc-option,-march=loongson2f) -Wa,--trap
+cflags-$(CONFIG_CPU_LOONGSON64) += $(call cc-option,-march=loongson3a,-march=mips64r2) -Wa,--trap
# Some -march= flags enable MMI instructions, and GCC complains about that
# support being enabled alongside -msoft-float. Thus explicitly disable MMI.
cflags-$(CONFIG_CPU_LOONGSON2EF) += $(call cc-option,-mno-loongson-mmi)
-ifdef CONFIG_CPU_LOONGSON64
-cflags-$(CONFIG_CPU_LOONGSON64) += -Wa,--trap
-cflags-$(CONFIG_CC_IS_GCC) += -march=loongson3a
-cflags-$(CONFIG_CC_IS_CLANG) += -march=mips64r2
-endif
cflags-$(CONFIG_CPU_LOONGSON64) += $(call cc-option,-mno-loongson-mmi)
cflags-$(CONFIG_CPU_R4000_WORKAROUNDS) += $(call cc-option,-mfix-r4000,)
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x fc80fc2d4e39137869da3150ee169b40bf879287
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023071115-freeway-undefined-38ac@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From fc80fc2d4e39137869da3150ee169b40bf879287 Mon Sep 17 00:00:00 2001
From: Ding Hui <dinghui(a)sangfor.com.cn>
Date: Mon, 15 May 2023 10:13:07 +0800
Subject: [PATCH] SUNRPC: Fix UAF in svc_tcp_listen_data_ready()
After the listener svc_sock is freed, and before invoking svc_tcp_accept()
for the established child sock, there is a window that the newsock
retaining a freed listener svc_sock in sk_user_data which cloning from
parent. In the race window, if data is received on the newsock, we will
observe use-after-free report in svc_tcp_listen_data_ready().
Reproduce by two tasks:
1. while :; do rpc.nfsd 0 ; rpc.nfsd; done
2. while :; do echo "" | ncat -4 127.0.0.1 2049 ; done
KASAN report:
==================================================================
BUG: KASAN: slab-use-after-free in svc_tcp_listen_data_ready+0x1cf/0x1f0 [sunrpc]
Read of size 8 at addr ffff888139d96228 by task nc/102553
CPU: 7 PID: 102553 Comm: nc Not tainted 6.3.0+ #18
Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 11/12/2020
Call Trace:
<IRQ>
dump_stack_lvl+0x33/0x50
print_address_description.constprop.0+0x27/0x310
print_report+0x3e/0x70
kasan_report+0xae/0xe0
svc_tcp_listen_data_ready+0x1cf/0x1f0 [sunrpc]
tcp_data_queue+0x9f4/0x20e0
tcp_rcv_established+0x666/0x1f60
tcp_v4_do_rcv+0x51c/0x850
tcp_v4_rcv+0x23fc/0x2e80
ip_protocol_deliver_rcu+0x62/0x300
ip_local_deliver_finish+0x267/0x350
ip_local_deliver+0x18b/0x2d0
ip_rcv+0x2fb/0x370
__netif_receive_skb_one_core+0x166/0x1b0
process_backlog+0x24c/0x5e0
__napi_poll+0xa2/0x500
net_rx_action+0x854/0xc90
__do_softirq+0x1bb/0x5de
do_softirq+0xcb/0x100
</IRQ>
<TASK>
...
</TASK>
Allocated by task 102371:
kasan_save_stack+0x1e/0x40
kasan_set_track+0x21/0x30
__kasan_kmalloc+0x7b/0x90
svc_setup_socket+0x52/0x4f0 [sunrpc]
svc_addsock+0x20d/0x400 [sunrpc]
__write_ports_addfd+0x209/0x390 [nfsd]
write_ports+0x239/0x2c0 [nfsd]
nfsctl_transaction_write+0xac/0x110 [nfsd]
vfs_write+0x1c3/0xae0
ksys_write+0xed/0x1c0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x72/0xdc
Freed by task 102551:
kasan_save_stack+0x1e/0x40
kasan_set_track+0x21/0x30
kasan_save_free_info+0x2a/0x50
__kasan_slab_free+0x106/0x190
__kmem_cache_free+0x133/0x270
svc_xprt_free+0x1e2/0x350 [sunrpc]
svc_xprt_destroy_all+0x25a/0x440 [sunrpc]
nfsd_put+0x125/0x240 [nfsd]
nfsd_svc+0x2cb/0x3c0 [nfsd]
write_threads+0x1ac/0x2a0 [nfsd]
nfsctl_transaction_write+0xac/0x110 [nfsd]
vfs_write+0x1c3/0xae0
ksys_write+0xed/0x1c0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x72/0xdc
Fix the UAF by simply doing nothing in svc_tcp_listen_data_ready()
if state != TCP_LISTEN, that will avoid dereferencing svsk for all
child socket.
Link: https://lore.kernel.org/lkml/20230507091131.23540-1-dinghui@sangfor.com.cn/
Fixes: fa9251afc33c ("SUNRPC: Call the default socket callbacks instead of open coding")
Signed-off-by: Ding Hui <dinghui(a)sangfor.com.cn>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com>
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index f77cebe2c071..15f4d0d40bdd 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -826,12 +826,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk)
trace_sk_data_ready(sk);
- if (svsk) {
- /* Refer to svc_setup_socket() for details. */
- rmb();
- svsk->sk_odata(sk);
- }
-
/*
* This callback may called twice when a new connection
* is established as a child socket inherits everything
@@ -840,13 +834,18 @@ static void svc_tcp_listen_data_ready(struct sock *sk)
* when one of child sockets become ESTABLISHED.
* 2) data_ready method of the child socket may be called
* when it receives data before the socket is accepted.
- * In case of 2, we should ignore it silently.
+ * In case of 2, we should ignore it silently and DO NOT
+ * dereference svsk.
*/
- if (sk->sk_state == TCP_LISTEN) {
- if (svsk) {
- set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
- svc_xprt_enqueue(&svsk->sk_xprt);
- }
+ if (sk->sk_state != TCP_LISTEN)
+ return;
+
+ if (svsk) {
+ /* Refer to svc_setup_socket() for details. */
+ rmb();
+ svsk->sk_odata(sk);
+ set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
+ svc_xprt_enqueue(&svsk->sk_xprt);
}
}
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x c11d34fa139e4b0fb4249a30f37b178353533fa1
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023071613-reminder-relapse-b922@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
c11d34fa139e ("mm/damon/ops-common: atomically test and clear young on ptes and pmds")
72c33ef4c02e ("mm/damon: replace pmd_huge() with pmd_trans_huge() for THP")
c8b9aff41930 ("mm/damon: validate if the pmd entry is present before accessing")
02e34fff195d ("mm: damon: use HPAGE_PMD_SIZE")
198f0f4c58b9 ("mm/damon/vaddr,paddr: support pageout prioritization")
57223ac29584 ("mm/damon/paddr: support the pageout scheme")
a28397beb55b ("mm/damon: implement primitives for physical address space monitoring")
46c3a0accdc4 ("mm/damon/vaddr: separate commonly usable functions")
6dea8add4d28 ("mm/damon/vaddr: support DAMON-based Operation Schemes")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From c11d34fa139e4b0fb4249a30f37b178353533fa1 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts(a)arm.com>
Date: Fri, 2 Jun 2023 10:29:47 +0100
Subject: [PATCH] mm/damon/ops-common: atomically test and clear young on ptes
and pmds
It is racy to non-atomically read a pte, then clear the young bit, then
write it back as this could discard dirty information. Further, it is bad
practice to directly set a pte entry within a table. Instead clearing
young must go through the arch-provided helper,
ptep_test_and_clear_young() to ensure it is modified atomically and to
give the arch code visibility and allow it to check (and potentially
modify) the operation.
Link: https://lkml.kernel.org/r/20230602092949.545577-3-ryan.roberts@arm.com
Fixes: 3f49584b262c ("mm/damon: implement primitives for the virtual memory address spaces").
Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com>
Reviewed-by: Zi Yan <ziy(a)nvidia.com>
Reviewed-by: SeongJae Park <sj(a)kernel.org>
Reviewed-by: Mike Rapoport (IBM) <rppt(a)kernel.org>
Cc: Christoph Hellwig <hch(a)lst.de>
Cc: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: Lorenzo Stoakes <lstoakes(a)gmail.com>
Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Cc: Uladzislau Rezki (Sony) <urezki(a)gmail.com>
Cc: Yu Zhao <yuzhao(a)google.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
index cc63cf953636..acc264b97903 100644
--- a/mm/damon/ops-common.c
+++ b/mm/damon/ops-common.c
@@ -37,7 +37,7 @@ struct folio *damon_get_folio(unsigned long pfn)
return folio;
}
-void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
+void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr)
{
bool referenced = false;
struct folio *folio = damon_get_folio(pte_pfn(*pte));
@@ -45,13 +45,11 @@ void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
if (!folio)
return;
- if (pte_young(*pte)) {
+ if (ptep_test_and_clear_young(vma, addr, pte))
referenced = true;
- *pte = pte_mkold(*pte);
- }
#ifdef CONFIG_MMU_NOTIFIER
- if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
+ if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE))
referenced = true;
#endif /* CONFIG_MMU_NOTIFIER */
@@ -62,7 +60,7 @@ void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
folio_put(folio);
}
-void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr)
+void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
bool referenced = false;
@@ -71,13 +69,11 @@ void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr)
if (!folio)
return;
- if (pmd_young(*pmd)) {
+ if (pmdp_test_and_clear_young(vma, addr, pmd))
referenced = true;
- *pmd = pmd_mkold(*pmd);
- }
#ifdef CONFIG_MMU_NOTIFIER
- if (mmu_notifier_clear_young(mm, addr, addr + HPAGE_PMD_SIZE))
+ if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + HPAGE_PMD_SIZE))
referenced = true;
#endif /* CONFIG_MMU_NOTIFIER */
diff --git a/mm/damon/ops-common.h b/mm/damon/ops-common.h
index 14f4bc69f29b..18d837d11bce 100644
--- a/mm/damon/ops-common.h
+++ b/mm/damon/ops-common.h
@@ -9,8 +9,8 @@
struct folio *damon_get_folio(unsigned long pfn);
-void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr);
-void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr);
+void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr);
+void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr);
int damon_cold_score(struct damon_ctx *c, struct damon_region *r,
struct damos *s);
diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index 467b99166b43..5b3a3463d078 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -24,9 +24,9 @@ static bool __damon_pa_mkold(struct folio *folio, struct vm_area_struct *vma,
while (page_vma_mapped_walk(&pvmw)) {
addr = pvmw.address;
if (pvmw.pte)
- damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr);
+ damon_ptep_mkold(pvmw.pte, vma, addr);
else
- damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr);
+ damon_pmdp_mkold(pvmw.pmd, vma, addr);
}
return true;
}
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 1fec16d7263e..37994fb6120c 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -311,7 +311,7 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
}
if (pmd_trans_huge(*pmd)) {
- damon_pmdp_mkold(pmd, walk->mm, addr);
+ damon_pmdp_mkold(pmd, walk->vma, addr);
spin_unlock(ptl);
return 0;
}
@@ -323,7 +323,7 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
if (!pte_present(*pte))
goto out;
- damon_ptep_mkold(pte, walk->mm, addr);
+ damon_ptep_mkold(pte, walk->vma, addr);
out:
pte_unmap_unlock(pte, ptl);
return 0;