[syzbot] [cgroups?] KASAN: slab-use-after-free Read in pressure_write

[syzbot] [cgroups?] KASAN: slab-use-after-free Read in pressure_write

[syzbot]

Hello,

syzbot found the following issue on:

HEAD commit:    591cd656a1bf Linux 7.0-rc7
git tree:       upstream
console output: https://syzkaller.appspot.com/x/log.txt?x=114a36ba580000
kernel config:  https://syzkaller.appspot.com/x/.config?x=45cb3c58fd963c27
dashboard link: https://syzkaller.appspot.com/bug?extid=33e571025d88efd1312c
compiler:       Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50), Debian LLD 21.1.8
syz repro:      https://syzkaller.appspot.com/x/repro.syz?x=16cb33da580000
C reproducer:   https://syzkaller.appspot.com/x/repro.c?x=12648bd6580000

Downloadable assets:
disk image: https://storage.googleapis.com/syzbot-assets/87739bfd4864/disk-591cd656.raw.xz
vmlinux: https://storage.googleapis.com/syzbot-assets/56be68f80e4e/vmlinux-591cd656.xz
kernel image: https://storage.googleapis.com/syzbot-assets/08638816d82a/bzImage-591cd656.xz

IMPORTANT: if you fix the issue, please add the following tag to the commit:
Reported-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com

==================================================================
BUG: KASAN: slab-use-after-free in pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
Read of size 8 at addr ffff88803160f208 by task syz.3.1283/9352

CPU: 0 UID: 0 PID: 9352 Comm: syz.3.1283 Not tainted syzkaller #0 PREEMPT_{RT,(full)} 
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/18/2026
Call Trace:
 <TASK>
 dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0xba/0x230 mm/kasan/report.c:482
 kasan_report+0x117/0x150 mm/kasan/report.c:595
 pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
 cgroup_file_write+0x36f/0x790 kernel/cgroup/cgroup.c:4311
 kernfs_fop_write_iter+0x3b0/0x540 fs/kernfs/file.c:352
 new_sync_write fs/read_write.c:595 [inline]
 vfs_write+0x629/0xba0 fs/read_write.c:688
 ksys_write+0x156/0x270 fs/read_write.c:740
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f73f541c819
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f73f4a76028 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007f73f5695fa0 RCX: 00007f73f541c819
RDX: 000000000000002f RSI: 0000200000000080 RDI: 0000000000000004
RBP: 00007f73f54b2c91 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f73f5696038 R14: 00007f73f5695fa0 R15: 00007ffe5707b838
 </TASK>

Allocated by task 9352:
 kasan_save_stack mm/kasan/common.c:57 [inline]
 kasan_save_track+0x3e/0x80 mm/kasan/common.c:78
 poison_kmalloc_redzone mm/kasan/common.c:398 [inline]
 __kasan_kmalloc+0x93/0xb0 mm/kasan/common.c:415
 kasan_kmalloc include/linux/kasan.h:263 [inline]
 __kmalloc_cache_noprof+0x3a6/0x690 mm/slub.c:5380
 kmalloc_noprof include/linux/slab.h:950 [inline]
 kzalloc_noprof include/linux/slab.h:1188 [inline]
 cgroup_file_open+0x90/0x3a0 kernel/cgroup/cgroup.c:4256
 kernfs_fop_open+0x9eb/0xcb0 fs/kernfs/file.c:724
 do_dentry_open+0x83d/0x13e0 fs/open.c:949
 vfs_open+0x3b/0x350 fs/open.c:1081
 do_open fs/namei.c:4677 [inline]
 path_openat+0x2e43/0x38a0 fs/namei.c:4836
 do_file_open+0x23e/0x4a0 fs/namei.c:4865
 do_sys_openat2+0x113/0x200 fs/open.c:1366
 do_sys_open fs/open.c:1372 [inline]
 __do_sys_openat fs/open.c:1388 [inline]
 __se_sys_openat fs/open.c:1383 [inline]
 __x64_sys_openat+0x138/0x170 fs/open.c:1383
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 9353:
 kasan_save_stack mm/kasan/common.c:57 [inline]
 kasan_save_track+0x3e/0x80 mm/kasan/common.c:78
 kasan_save_free_info+0x46/0x50 mm/kasan/generic.c:584
 poison_slab_object mm/kasan/common.c:253 [inline]
 __kasan_slab_free+0x5c/0x80 mm/kasan/common.c:285
 kasan_slab_free include/linux/kasan.h:235 [inline]
 slab_free_hook mm/slub.c:2685 [inline]
 slab_free mm/slub.c:6165 [inline]
 kfree+0x1c1/0x6c0 mm/slub.c:6483
 cgroup_file_release+0xd6/0x100 kernel/cgroup/cgroup.c:4283
 kernfs_release_file fs/kernfs/file.c:764 [inline]
 kernfs_drain_open_files+0x392/0x720 fs/kernfs/file.c:834
 kernfs_drain+0x470/0x600 fs/kernfs/dir.c:525
 __kernfs_remove+0x3cf/0x660 fs/kernfs/dir.c:1513
 kernfs_remove_by_name_ns+0xaf/0x130 fs/kernfs/dir.c:1722
 kernfs_remove_by_name include/linux/kernfs.h:633 [inline]
 cgroup_rm_file kernel/cgroup/cgroup.c:1758 [inline]
 cgroup_addrm_files+0x684/0xc30 kernel/cgroup/cgroup.c:4483
 cgroup_destroy_locked+0x321/0x630 kernel/cgroup/cgroup.c:6197
 cgroup_rmdir+0x3e8/0x710 kernel/cgroup/cgroup.c:6311
 kernfs_iop_rmdir+0x203/0x350 fs/kernfs/dir.c:1291
 vfs_rmdir+0x400/0x6f0 fs/namei.c:5344
 filename_rmdir+0x292/0x520 fs/namei.c:5399
 __do_sys_rmdir fs/namei.c:5422 [inline]
 __se_sys_rmdir+0x2e/0x140 fs/namei.c:5419
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

The buggy address belongs to the object at ffff88803160f200
 which belongs to the cache kmalloc-192 of size 192
The buggy address is located 8 bytes inside of
 freed 192-byte region [ffff88803160f200, ffff88803160f2c0)

The buggy address belongs to the physical page:
page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x3160f
flags: 0x80000000000000(node=0|zone=1)
page_type: f5(slab)
raw: 0080000000000000 ffff88813fe1a3c0 dead000000000100 dead000000000122
raw: 0000000000000000 0000000800100010 00000000f5000000 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 0, migratetype Unmovable, gfp_mask 0xd2cc0(GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 1, tgid 1 (swapper/0), ts 17504889254, free_ts 0
 set_page_owner include/linux/page_owner.h:32 [inline]
 post_alloc_hook+0x231/0x280 mm/page_alloc.c:1889
 prep_new_page mm/page_alloc.c:1897 [inline]
 get_page_from_freelist+0x28bb/0x2950 mm/page_alloc.c:3962
 __alloc_frozen_pages_noprof+0x18d/0x380 mm/page_alloc.c:5250
 alloc_slab_page mm/slub.c:3292 [inline]
 allocate_slab+0x77/0x660 mm/slub.c:3481
 new_slab mm/slub.c:3539 [inline]
 refill_objects+0x334/0x3c0 mm/slub.c:7175
 refill_sheaf mm/slub.c:2812 [inline]
 __pcs_replace_empty_main+0x35c/0x710 mm/slub.c:4615
 alloc_from_pcs mm/slub.c:4717 [inline]
 slab_alloc_node mm/slub.c:4851 [inline]
 __kmalloc_cache_noprof+0x44e/0x690 mm/slub.c:5375
 kmalloc_noprof include/linux/slab.h:950 [inline]
 kzalloc_noprof include/linux/slab.h:1188 [inline]
 call_usermodehelper_setup+0x8e/0x270 kernel/umh.c:362
 kobject_uevent_env+0x65b/0x9e0 lib/kobject_uevent.c:628
 device_add+0x557/0xb80 drivers/base/core.c:3672
 netdev_register_kobject+0x178/0x310 net/core/net-sysfs.c:2358
 register_netdevice+0x12d7/0x1d10 net/core/dev.c:11441
 register_netdev+0x40/0x60 net/core/dev.c:11557
 nr_proto_init+0x14a/0x720 net/netrom/af_netrom.c:1424
 do_one_initcall+0x250/0x8d0 init/main.c:1382
 do_initcall_level+0x104/0x190 init/main.c:1444
page_owner free stack trace missing

Memory state around the buggy address:
 ffff88803160f100: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff88803160f180: 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88803160f200: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                      ^
 ffff88803160f280: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
 ffff88803160f300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
==================================================================


---
This report is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.

syzbot will keep track of this issue. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot.

If the report is already addressed, let syzbot know by replying with:
#syz fix: exact-commit-title

If you want syzbot to run the reproducer, reply with:
#syz test: git://repo/address.git branch-or-commit-hash
If you attach or paste a git patch, syzbot will apply it before testing.

If you want to overwrite report's subsystems, reply with:
#syz set subsystems: new-subsystem
(See the list of subsystem names on the web dashboard)

If the report is a duplicate of another one, reply with:
#syz dup: exact-subject-of-another-report

If you want to undo deduplication, reply with:
#syz undup

[PATCH] sched/psi: fix race between file release and pressure write

[Edward Adam Davis]

A potential race condition exists between pressure write and cgroup file
release regarding the priv member of struct kernfs_open_file, which
triggers the uaf reported in [1].

The scope of the cgroup_mutex protection in pressure write has been
expanded to prevent the uaf described in [1].

[1]
BUG: KASAN: slab-use-after-free in pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
Call Trace:
 pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
 cgroup_file_write+0x36f/0x790 kernel/cgroup/cgroup.c:4311
 kernfs_fop_write_iter+0x3b0/0x540 fs/kernfs/file.c:352

Allocated by task 9352:
 cgroup_file_open+0x90/0x3a0 kernel/cgroup/cgroup.c:4256
 kernfs_fop_open+0x9eb/0xcb0 fs/kernfs/file.c:724
 do_dentry_open+0x83d/0x13e0 fs/open.c:949

Freed by task 9353:
 cgroup_file_release+0xd6/0x100 kernel/cgroup/cgroup.c:4283
 kernfs_release_file fs/kernfs/file.c:764 [inline]
 kernfs_drain_open_files+0x392/0x720 fs/kernfs/file.c:834
 kernfs_drain+0x470/0x600 fs/kernfs/dir.c:525

Fixes: 0e94682b73bf ("psi: introduce psi monitor")
Reported-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=33e571025d88efd1312c
Tested-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
---
 kernel/cgroup/cgroup.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4ca3cb993da2..c0cfe91c2991 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4005,11 +4005,11 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 		return -ENODEV;
 
 	cgroup_get(cgrp);
-	cgroup_kn_unlock(of->kn);
 
 	/* Allow only one trigger per file descriptor */
 	if (ctx->psi.trigger) {
 		cgroup_put(cgrp);
+		cgroup_kn_unlock(of->kn);
 		return -EBUSY;
 	}
 
@@ -4017,12 +4017,14 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 	new = psi_trigger_create(psi, buf, res, of->file, of);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
+		cgroup_kn_unlock(of->kn);
 		return PTR_ERR(new);
 	}
 
 	smp_store_release(&ctx->psi.trigger, new);
 	cgroup_put(cgrp);
 
+	cgroup_kn_unlock(of->kn);
 	return nbytes;
 }
 
-- 
2.43.0

Re: [PATCH] sched/psi: fix race between file release and pressure write

[Chen Ridong]

On 2026/4/10 12:00, Edward Adam Davis wrote:
> A potential race condition exists between pressure write and cgroup file
> release regarding the priv member of struct kernfs_open_file, which
> triggers the uaf reported in [1].
> 
> The scope of the cgroup_mutex protection in pressure write has been
> expanded to prevent the uaf described in [1].
> 
> [1]
> BUG: KASAN: slab-use-after-free in pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
> Call Trace:
>  pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
>  cgroup_file_write+0x36f/0x790 kernel/cgroup/cgroup.c:4311
>  kernfs_fop_write_iter+0x3b0/0x540 fs/kernfs/file.c:352
> 
> Allocated by task 9352:
>  cgroup_file_open+0x90/0x3a0 kernel/cgroup/cgroup.c:4256
>  kernfs_fop_open+0x9eb/0xcb0 fs/kernfs/file.c:724
>  do_dentry_open+0x83d/0x13e0 fs/open.c:949
> 
> Freed by task 9353:
>  cgroup_file_release+0xd6/0x100 kernel/cgroup/cgroup.c:4283
>  kernfs_release_file fs/kernfs/file.c:764 [inline]
>  kernfs_drain_open_files+0x392/0x720 fs/kernfs/file.c:834
>  kernfs_drain+0x470/0x600 fs/kernfs/dir.c:525
> 
> Fixes: 0e94682b73bf ("psi: introduce psi monitor")
> Reported-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com
> Closes: https://syzkaller.appspot.com/bug?extid=33e571025d88efd1312c
> Tested-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com
> Signed-off-by: Edward Adam Davis <eadavis@qq.com>
> ---
>  kernel/cgroup/cgroup.c | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
> 

Hi Edward,

Thank you for fixing this issue. The patch looks plausible, but the root cause
is not entirely clear from the diff alone. Could you please add more details to
the commit message explaining how the issue occurs and why this change resolves it?

Thanks.

> diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
> index 4ca3cb993da2..c0cfe91c2991 100644
> --- a/kernel/cgroup/cgroup.c
> +++ b/kernel/cgroup/cgroup.c
> @@ -4005,11 +4005,11 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
>  		return -ENODEV;
>  
>  	cgroup_get(cgrp);
> -	cgroup_kn_unlock(of->kn);
>  
>  	/* Allow only one trigger per file descriptor */
>  	if (ctx->psi.trigger) {
>  		cgroup_put(cgrp);
> +		cgroup_kn_unlock(of->kn);
>  		return -EBUSY;
>  	}
>  
> @@ -4017,12 +4017,14 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
>  	new = psi_trigger_create(psi, buf, res, of->file, of);
>  	if (IS_ERR(new)) {
>  		cgroup_put(cgrp);
> +		cgroup_kn_unlock(of->kn);
>  		return PTR_ERR(new);
>  	}
>  
>  	smp_store_release(&ctx->psi.trigger, new);
>  	cgroup_put(cgrp);
>  
> +	cgroup_kn_unlock(of->kn);
>  	return nbytes;
>  }
>  

-- 
Best regards,
Ridong

Re: [PATCH] sched/psi: fix race between file release and pressure write

[Edward Adam Davis]

On Fri, 10 Apr 2026 17:00:55 +0800, Chen Ridong wrote:
> > A potential race condition exists between pressure write and cgroup file
> > release regarding the priv member of struct kernfs_open_file, which
> > triggers the uaf reported in [1].
> > 
> > The scope of the cgroup_mutex protection in pressure write has been
> > expanded to prevent the uaf described in [1].
> > 
> > [1]
> > BUG: KASAN: slab-use-after-free in pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
> > Call Trace:
> >  pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
> >  cgroup_file_write+0x36f/0x790 kernel/cgroup/cgroup.c:4311
> >  kernfs_fop_write_iter+0x3b0/0x540 fs/kernfs/file.c:352
> > 
> > Allocated by task 9352:
> >  cgroup_file_open+0x90/0x3a0 kernel/cgroup/cgroup.c:4256
> >  kernfs_fop_open+0x9eb/0xcb0 fs/kernfs/file.c:724
> >  do_dentry_open+0x83d/0x13e0 fs/open.c:949
> > 
> > Freed by task 9353:
> >  cgroup_file_release+0xd6/0x100 kernel/cgroup/cgroup.c:4283
> >  kernfs_release_file fs/kernfs/file.c:764 [inline]
> >  kernfs_drain_open_files+0x392/0x720 fs/kernfs/file.c:834
> >  kernfs_drain+0x470/0x600 fs/kernfs/dir.c:525
> > 
> > Fixes: 0e94682b73bf ("psi: introduce psi monitor")
> > Reported-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com
> > Closes: https://syzkaller.appspot.com/bug?extid=33e571025d88efd1312c
> > Tested-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com
> > Signed-off-by: Edward Adam Davis <eadavis@qq.com>
> > ---
> >  kernel/cgroup/cgroup.c | 4 +++-
> >  1 file changed, 3 insertions(+), 1 deletion(-)
> > 
> 
> Hi Edward,
> 
> Thank you for fixing this issue. The patch looks plausible, but the root cause
> is not entirely clear from the diff alone. Could you please add more details to
> the commit message explaining how the issue occurs and why this change resolves it?
Consider the following scenario involving execution on two separate CPUs:

   CPU0					CPU1
   ====					====
					vfs_rmdir()
					kernfs_iop_rmdir()
					cgroup_rmdir()
					cgroup_kn_lock_live()
					cgroup_destroy_locked()
					cgroup_addrm_files()
					cgroup_rm_file()
					kernfs_remove_by_name()
					kernfs_remove_by_name_ns()
 vfs_write()				__kernfs_remove()
 new_sync_write()			kernfs_drain()
 kernfs_fop_write_iter()		kernfs_drain_open_files()
 cgroup_file_write()			kernfs_release_file()
 pressure_write()			cgroup_file_release()
 ctx = of->priv;
					kfree(ctx);
 					of->priv = NULL;
					cgroup_kn_unlock()
 cgroup_kn_lock_live()
 if (ctx->psi.trigger)  // here, trigger uaf for ctx, that is of->priv

The cgroup_rmdir() is protected by the cgroup_mutex, it also safeguards
the memory deallocation of of->priv performed within cgroup_file_release().
However, the operations involving of->priv executed within pressure_write()
are not entirely covered by the protection of cgroup_mutex. Consequently,
if the code in pressure_write(), specifically the section handling the
ctx variable executes after cgroup_file_release() has completed, a uaf
vulnerability involving of->priv is triggered.

Therefore, the issue can be resolved simply by extending the scope of
the cgroup_mutex lock within pressure_write() to encompass all code
paths involving of->priv, thereby properly synchronizing the race condition
occurring between cgroup_file_release() and pressure_write().

Edward
BR

[PATCH v2] sched/psi: fix race between file release and pressure write

[Edward Adam Davis]

A potential race condition exists between pressure write and cgroup file
release regarding the priv member of struct kernfs_open_file, which
triggers the uaf reported in [1].

Consider the following scenario involving execution on two separate CPUs:

   CPU0					CPU1
   ====					====
					vfs_rmdir()
					kernfs_iop_rmdir()
					cgroup_rmdir()
					cgroup_kn_lock_live()
					cgroup_destroy_locked()
					cgroup_addrm_files()
					cgroup_rm_file()
					kernfs_remove_by_name()
					kernfs_remove_by_name_ns()
 vfs_write()				__kernfs_remove()
 new_sync_write()			kernfs_drain()
 kernfs_fop_write_iter()		kernfs_drain_open_files()
 cgroup_file_write()			kernfs_release_file()
 pressure_write()			cgroup_file_release()
 ctx = of->priv;
					kfree(ctx);
 					of->priv = NULL;
					cgroup_kn_unlock()
 cgroup_kn_lock_live()
 cgroup_get(cgrp)
 cgroup_kn_unlock()
 if (ctx->psi.trigger)  // here, trigger uaf for ctx, that is of->priv

The cgroup_rmdir() is protected by the cgroup_mutex, it also safeguards
the memory deallocation of of->priv performed within cgroup_file_release().
However, the operations involving of->priv executed within pressure_write()
are not entirely covered by the protection of cgroup_mutex. Consequently,
if the code in pressure_write(), specifically the section handling the
ctx variable executes after cgroup_file_release() has completed, a uaf
vulnerability involving of->priv is triggered.

Therefore, the issue can be resolved by extending the scope of the
cgroup_mutex lock within pressure_write() to encompass all code paths
involving of->priv, thereby properly synchronizing the race condition
occurring between cgroup_file_release() and pressure_write().

[1]
BUG: KASAN: slab-use-after-free in pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
Call Trace:
 pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
 cgroup_file_write+0x36f/0x790 kernel/cgroup/cgroup.c:4311
 kernfs_fop_write_iter+0x3b0/0x540 fs/kernfs/file.c:352

Allocated by task 9352:
 cgroup_file_open+0x90/0x3a0 kernel/cgroup/cgroup.c:4256
 kernfs_fop_open+0x9eb/0xcb0 fs/kernfs/file.c:724
 do_dentry_open+0x83d/0x13e0 fs/open.c:949

Freed by task 9353:
 cgroup_file_release+0xd6/0x100 kernel/cgroup/cgroup.c:4283
 kernfs_release_file fs/kernfs/file.c:764 [inline]
 kernfs_drain_open_files+0x392/0x720 fs/kernfs/file.c:834
 kernfs_drain+0x470/0x600 fs/kernfs/dir.c:525

Fixes: 0e94682b73bf ("psi: introduce psi monitor")
Reported-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=33e571025d88efd1312c
Tested-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
---
v1 -> v2: refactor unlock and update comments

 kernel/cgroup/cgroup.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4ca3cb993da2..46db30de817b 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3995,34 +3995,47 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 			      size_t nbytes, enum psi_res res)
 {
-	struct cgroup_file_ctx *ctx = of->priv;
+	struct cgroup_file_ctx *ctx;
 	struct psi_trigger *new;
 	struct cgroup *cgrp;
 	struct psi_group *psi;
+	ssize_t ret = 0;
 
 	cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!cgrp)
 		return -ENODEV;
 
+	ctx = of->priv;
+	if (!ctx) {
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
 	cgroup_get(cgrp);
-	cgroup_kn_unlock(of->kn);
 
 	/* Allow only one trigger per file descriptor */
 	if (ctx->psi.trigger) {
 		cgroup_put(cgrp);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto out_unlock;
 	}
 
 	psi = cgroup_psi(cgrp);
 	new = psi_trigger_create(psi, buf, res, of->file, of);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
-		return PTR_ERR(new);
+		ret = PTR_ERR(new);
+		goto out_unlock;
 	}
 
 	smp_store_release(&ctx->psi.trigger, new);
 	cgroup_put(cgrp);
 
+out_unlock:
+	cgroup_kn_unlock(of->kn);
+	if (ret)
+		return ret;
+
 	return nbytes;
 }
 
-- 
2.43.0

Re: [PATCH v2] sched/psi: fix race between file release and pressure write

[Tejun Heo]

Hello,

On Fri, Apr 10, 2026 at 08:39:45PM +0800, Edward Adam Davis wrote:
>  static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
>  			      size_t nbytes, enum psi_res res)
>  {
> -	struct cgroup_file_ctx *ctx = of->priv;
> +	struct cgroup_file_ctx *ctx;
>  	struct psi_trigger *new;
>  	struct cgroup *cgrp;
>  	struct psi_group *psi;
> +	ssize_t ret = 0;
>  
>  	cgrp = cgroup_kn_lock_live(of->kn, false);
>  	if (!cgrp)
>  		return -ENODEV;
>  
> +	ctx = of->priv;
> +	if (!ctx) {

This test likely isn't necessary but that's pre-existing.

> +		ret = -ENODEV;
> +		goto out_unlock;
> +	}
> +
>  	cgroup_get(cgrp);

We don't need get/put if we don't drop the mutex, right?

Thanks.

-- 
tejun

Re: [PATCH v2] sched/psi: fix race between file release and pressure write

[Edward Adam Davis]

On Fri, 10 Apr 2026 09:14:05 -1000, Tejun Heo wrote:
> >  static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
> >  			      size_t nbytes, enum psi_res res)
> >  {
> > -	struct cgroup_file_ctx *ctx = of->priv;
> > +	struct cgroup_file_ctx *ctx;
> >  	struct psi_trigger *new;
> >  	struct cgroup *cgrp;
> >  	struct psi_group *psi;
> > +	ssize_t ret = 0;
> >
> >  	cgrp = cgroup_kn_lock_live(of->kn, false);
> >  	if (!cgrp)
> >  		return -ENODEV;
> >
> > +	ctx = of->priv;
> > +	if (!ctx) {
> 
> This test likely isn't necessary but that's pre-existing.
Where?
Are you referring to the check for of->released within:
'kernfs_fop_write_iter()->kernfs_get_active_of()'? This check is not
performed under the protection of the cgroup_mutex; consequently, it
is susceptible to race conditions, rendering the value unreliable, as
it could be updated at any moment.
> 
> > +		ret = -ENODEV;
> > +		goto out_unlock;
> > +	}
> > +
> >  	cgroup_get(cgrp);
> 
> We don't need get/put if we don't drop the mutex, right?
I believe that is indeed the case; the cgroup_get() call here is intended
to facilitate subsequent operations, such as executing an smp store.

Edward
BR

Re: [PATCH v2] sched/psi: fix race between file release and pressure write

[Tejun Heo]

Hello, Edward.

On Sat, Apr 11, 2026 at 12:25:47PM +0800, Edward Adam Davis wrote:
> > > +	ctx = of->priv;
> > > +	if (!ctx) {
> > 
> > This test likely isn't necessary but that's pre-existing.
> Where?
> Are you referring to the check for of->released within:

No, I'm talking about of->priv. I don't think it can be NULL while a live
cgroup kn is locked, can it?

Thanks.

-- 
tejun

Re: [PATCH v2] sched/psi: fix race between file release and pressure write

[Edward Adam Davis]

On Fri, 10 Apr 2026 21:39:49 -1000, Tejun Heo wrote:
> > > > +	ctx = of->priv;
> > > > +	if (!ctx) {
> > >
> > > This test likely isn't necessary but that's pre-existing.
> > Where?
> > Are you referring to the check for of->released within:
> 
> No, I'm talking about of->priv. I don't think it can be NULL while a live
> cgroup kn is locked, can it?
If the lock is acquired before the execution of cgroup_file_release()
completes, it will not be NULL; however, if acquired afterwards, it
will invariably be NULL.

Edward
BR

Re: [PATCH v2] sched/psi: fix race between file release and pressure write

[Tejun Heo]

Hello,

On Sat, Apr 11, 2026 at 04:29:22PM +0800, Edward Adam Davis wrote:
> On Fri, 10 Apr 2026 21:39:49 -1000, Tejun Heo wrote:
> > > > > +	ctx = of->priv;
> > > > > +	if (!ctx) {
> > > >
> > > > This test likely isn't necessary but that's pre-existing.
> > > Where?
> > > Are you referring to the check for of->released within:
> > 
> > No, I'm talking about of->priv. I don't think it can be NULL while a live
> > cgroup kn is locked, can it?
>
> If the lock is acquired before the execution of cgroup_file_release()
> completes, it will not be NULL; however, if acquired afterwards, it
> will invariably be NULL.

Hmmm? While the write is in flight the file can't be released and the cgroup
couldn't have been dead if lock_live succeeded. This part is tangential
anyway. Let's ignore for now.

Thanks.

-- 
tejun

Re: [PATCH v2] sched/psi: fix race between file release and pressure write

[Edward Adam Davis]

On Sat, 11 Apr 2026 10:40:13 -1000, Tejun Heo wrote:
> On Sat, Apr 11, 2026 at 04:29:22PM +0800, Edward Adam Davis wrote:
> > On Fri, 10 Apr 2026 21:39:49 -1000, Tejun Heo wrote:
> > > > > > +	ctx = of->priv;
> > > > > > +	if (!ctx) {
> > > > >
> > > > > This test likely isn't necessary but that's pre-existing.
> > > > Where?
> > > > Are you referring to the check for of->released within:
> > >
> > > No, I'm talking about of->priv. I don't think it can be NULL while a live
> > > cgroup kn is locked, can it?
> >
> > If the lock is acquired before the execution of cgroup_file_release()
> > completes, it will not be NULL; however, if acquired afterwards, it
> > will invariably be NULL.
> 
> Hmmm? While the write is in flight the file can't be released and the cgroup
> couldn't have been dead if lock_live succeeded. This part is tangential
> anyway. Let's ignore for now.
I have once again walked through the entire workflow for the cgroup
deletion operation. Indeed, if the active kn lock can be successfully
acquired while executing pressure write, it indicates that the cgroup
deletion process has not yet reached its final stage; therefore, the
`priv` pointer within open_file cannot possibly be NULL.

I will submit the third version of the patch shortly.

Edward
BR

[PATCH v3] sched/psi: fix race between file release and pressure write

[Edward Adam Davis]

A potential race condition exists between pressure write and cgroup file
release regarding the priv member of struct kernfs_open_file, which
triggers the uaf reported in [1].

Consider the following scenario involving execution on two separate CPUs:

   CPU0					CPU1
   ====					====
					vfs_rmdir()
					kernfs_iop_rmdir()
					cgroup_rmdir()
					cgroup_kn_lock_live()
					cgroup_destroy_locked()
					cgroup_addrm_files()
					cgroup_rm_file()
					kernfs_remove_by_name()
					kernfs_remove_by_name_ns()
 vfs_write()				__kernfs_remove()
 new_sync_write()			kernfs_drain()
 kernfs_fop_write_iter()		kernfs_drain_open_files()
 cgroup_file_write()			kernfs_release_file()
 pressure_write()			cgroup_file_release()
 ctx = of->priv;
					kfree(ctx);
 					of->priv = NULL;
					cgroup_kn_unlock()
 cgroup_kn_lock_live()
 cgroup_get(cgrp)
 cgroup_kn_unlock()
 if (ctx->psi.trigger)  // here, trigger uaf for ctx, that is of->priv

The cgroup_rmdir() is protected by the cgroup_mutex, it also safeguards
the memory deallocation of of->priv performed within cgroup_file_release().
However, the operations involving of->priv executed within pressure_write()
are not entirely covered by the protection of cgroup_mutex. Consequently,
if the code in pressure_write(), specifically the section handling the
ctx variable executes after cgroup_file_release() has completed, a uaf
vulnerability involving of->priv is triggered.

Therefore, the issue can be resolved by extending the scope of the
cgroup_mutex lock within pressure_write() to encompass all code paths
involving of->priv, thereby properly synchronizing the race condition
occurring between cgroup_file_release() and pressure_write().

And, if an active kn lock can be successfully acquired while executing
the pressure write operation, it indicates that the cgroup deletion
process has not yet reached its final stage; consequently, the priv
pointer within open_file cannot be NULL. Therefore, the operation to
retrieve the ctx value must be moved to a point *after* the active kn
lock has been successfully acquired.

[1]
BUG: KASAN: slab-use-after-free in pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
Call Trace:
 pressure_write+0xa4/0x210 kernel/cgroup/cgroup.c:4011
 cgroup_file_write+0x36f/0x790 kernel/cgroup/cgroup.c:4311
 kernfs_fop_write_iter+0x3b0/0x540 fs/kernfs/file.c:352

Allocated by task 9352:
 cgroup_file_open+0x90/0x3a0 kernel/cgroup/cgroup.c:4256
 kernfs_fop_open+0x9eb/0xcb0 fs/kernfs/file.c:724
 do_dentry_open+0x83d/0x13e0 fs/open.c:949

Freed by task 9353:
 cgroup_file_release+0xd6/0x100 kernel/cgroup/cgroup.c:4283
 kernfs_release_file fs/kernfs/file.c:764 [inline]
 kernfs_drain_open_files+0x392/0x720 fs/kernfs/file.c:834
 kernfs_drain+0x470/0x600 fs/kernfs/dir.c:525

Fixes: 0e94682b73bf ("psi: introduce psi monitor")
Reported-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=33e571025d88efd1312c
Tested-by: syzbot+33e571025d88efd1312c@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
---
v1 -> v2: refactor unlock and update comments
v2 -> v3: remove check for !ctx and update comments

 kernel/cgroup/cgroup.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4ca3cb993da2..1d89fab82850 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3995,34 +3995,43 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 			      size_t nbytes, enum psi_res res)
 {
-	struct cgroup_file_ctx *ctx = of->priv;
+	struct cgroup_file_ctx *ctx;
 	struct psi_trigger *new;
 	struct cgroup *cgrp;
 	struct psi_group *psi;
+	ssize_t ret = 0;
 
 	cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!cgrp)
 		return -ENODEV;
 
+	/* of->priv can not be NULL, because cgroup is CSS_ONLINE */
+	ctx = of->priv;
 	cgroup_get(cgrp);
-	cgroup_kn_unlock(of->kn);
 
 	/* Allow only one trigger per file descriptor */
 	if (ctx->psi.trigger) {
 		cgroup_put(cgrp);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto out_unlock;
 	}
 
 	psi = cgroup_psi(cgrp);
 	new = psi_trigger_create(psi, buf, res, of->file, of);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
-		return PTR_ERR(new);
+		ret = PTR_ERR(new);
+		goto out_unlock;
 	}
 
 	smp_store_release(&ctx->psi.trigger, new);
 	cgroup_put(cgrp);
 
+out_unlock:
+	cgroup_kn_unlock(of->kn);
+	if (ret)
+		return ret;
+
 	return nbytes;
 }
 
-- 
2.43.0