From 1ba1199ec5747f475538c0d25a32804e5ba1dfde Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Mon, 10 Apr 2023 21:08:26 +0800
Subject: [PATCH] writeback, cgroup: fix null-ptr-deref write in
bdi_split_work_to_wbs
Git-commit: 1ba1199ec5747f475538c0d25a32804e5ba1dfde
Patch-mainline: v6.3
References: bsc#1210769
KASAN report null-ptr-deref:
==================================================================
Bug: KASAN: null-ptr-deref in bdi_split_work_to_wbs+0x5c5/0x7b0
Write of size 8 at addr 0000000000000000 by task sync/943
Cpu: 5 PID: 943 Comm: sync Tainted: 6.3.0-rc5-next-20230406-dirty #461
Call Trace:
<TASK>
dump_stack_lvl+0x7f/0xc0
print_report+0x2ba/0x340
kasan_report+0xc4/0x120
kasan_check_range+0x1b7/0x2e0
__kasan_check_write+0x24/0x40
bdi_split_work_to_wbs+0x5c5/0x7b0
sync_inodes_sb+0x195/0x630
sync_inodes_one_sb+0x3a/0x50
iterate_supers+0x106/0x1b0
ksys_sync+0x98/0x160
[...]
==================================================================
The race that causes the above issue is as follows:
cpu1 cpu2
Acked-by: Jan Kara <jack@suse.cz>
-------------------------|-------------------------
inode_switch_wbs
INIT_WORK(&isw->work, inode_switch_wbs_work_fn)
queue_rcu_work(isw_wq, &isw->work)
// queue_work async
inode_switch_wbs_work_fn
wb_put_many(old_wb, nr_switched)
percpu_ref_put_many
ref->data->release(ref)
cgwb_release
queue_work(cgwb_release_wq, &wb->release_work)
// queue_work async
&wb->release_work
cgwb_release_workfn
ksys_sync
iterate_supers
sync_inodes_one_sb
sync_inodes_sb
bdi_split_work_to_wbs
kmalloc(sizeof(*work), GFP_ATOMIC)
// alloc memory failed
percpu_ref_exit
ref->data = NULL
kfree(data)
wb_get(wb)
percpu_ref_get(&wb->refcnt)
percpu_ref_get_many(ref, 1)
atomic_long_add(nr, &ref->data->count)
atomic64_add(i, v)
// trigger null-ptr-deref
bdi_split_work_to_wbs() traverses &bdi->wb_list to split work into all
wbs. If the allocation of new work fails, the on-stack fallback will be
used and the reference count of the current wb is increased afterwards.
If cgroup writeback membership switches occur before getting the reference
count and the current wb is released as old_wd, then calling wb_get() or
wb_put() will trigger the null pointer dereference above.
This issue was introduced in v4.3-rc7 (see fix tag1). Both
sync_inodes_sb() and __writeback_inodes_sb_nr() calls to
bdi_split_work_to_wbs() can trigger this issue. For scenarios called via
sync_inodes_sb(), originally commit 7fc5854f8c6e ("writeback: synchronize
sync(2) against cgroup writeback membership switches") reduced the
possibility of the issue by adding wb_switch_rwsem, but in v5.14-rc1 (see
fix tag2) removed the "inode_io_list_del_locked(inode, old_wb)" from
inode_switch_wbs_work_fn() so that wb->state contains WB_has_dirty_io,
thus old_wb is not skipped when traversing wbs in bdi_split_work_to_wbs(),
and the issue becomes easily reproducible again.
To solve this problem, percpu_ref_exit() is called under RCU protection to
avoid race between cgwb_release_workfn() and bdi_split_work_to_wbs().
Moreover, replace wb_get() with wb_tryget() in bdi_split_work_to_wbs(),
and skip the current wb if wb_tryget() fails because the wb has already
been shutdown.
Link: https://lkml.kernel.org/r/20230410130826.1492525-1-libaokun1@huawei.com
Fixes: b817525a4a80 ("writeback: bdi_writeback iteration must not skip dying ones")
Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Hou Tao <houtao1@huawei.com>
Cc: yangerkun <yangerkun@huawei.com>
Cc: Zhang Yi <yi.zhang@huawei.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/fs-writeback.c | 17 ++++++++++-------
mm/backing-dev.c | 12 ++++++++++--
2 files changed, 20 insertions(+), 9 deletions(-)
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1009,6 +1009,16 @@ restart:
continue;
}
+ /*
+ * If wb_tryget fails, the wb has been shutdown, skip it.
+ *
+ * Pin @wb so that it stays on @bdi->wb_list. This allows
+ * continuing iteration from @wb after dropping and
+ * regrabbing rcu read lock.
+ */
+ if (!wb_tryget(wb))
+ continue;
+
/* alloc failed, execute synchronously using on-stack fallback */
work = &fallback_work;
*work = *base_work;
@@ -1017,13 +1027,6 @@ restart:
work->done = &fallback_work_done;
wb_queue_work(wb, work);
-
- /*
- * Pin @wb so that it stays on @bdi->wb_list. This allows
- * continuing iteration from @wb after dropping and
- * regrabbing rcu read lock.
- */
- wb_get(wb);
last_wb = wb;
rcu_read_unlock();
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -385,6 +385,15 @@ static LIST_HEAD(offline_cgwbs);
static void cleanup_offline_cgwbs_workfn(struct work_struct *work);
static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn);
+static void cgwb_free_rcu(struct rcu_head *rcu_head)
+{
+ struct bdi_writeback *wb = container_of(rcu_head,
+ struct bdi_writeback, rcu);
+
+ percpu_ref_exit(&wb->refcnt);
+ kfree(wb);
+}
+
static void cgwb_release_workfn(struct work_struct *work)
{
struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
@@ -407,10 +416,9 @@ static void cgwb_release_workfn(struct w
list_del(&wb->offline_node);
spin_unlock_irq(&cgwb_lock);
- percpu_ref_exit(&wb->refcnt);
wb_exit(wb);
WARN_ON_ONCE(!list_empty(&wb->b_attached));
- kfree_rcu(wb, rcu);
+ call_rcu(&wb->rcu, cgwb_free_rcu);
}
static void cgwb_release(struct percpu_ref *refcnt)