In kfree_rcu_monitor(), new free business at krcp is attached to any free
channel at krwp. kfree_rcu_monitor() is responsible to make sure new free
business is handled after the rcu grace period. But if there is any none-free
channel at krwp already, that means there is an on-going rcu work,
which will cause the kvfree_call_rcu()-triggered free business is done
before the wanted rcu grace period ends.
This commit ignore krwp which has non-free channel at kfree_rcu_monitor(),
to fix the issue that kvfree_call_rcu() loses effectiveness.
Below is the css_set obj "from_cset" use-after-free case caused by
kvfree_call_rcu() losing effectiveness.
CPU 0 calls rcu_read_lock(), then use "from_cset", then hard irq comes,
the task is schedule out.
CPU 1 calls kfree_rcu(cset, rcu_head), willing to free "from_cset" after new gp.
But "from_cset" is freed right after current gp end. "from_cset" is reallocated.
CPU 0 's task arrives back, references "from_cset"'s member, which causes crash.
CPU 0 CPU 1
count_memcg_event_mm()
|rcu_read_lock() <---
|mem_cgroup_from_task()
|// css_set_ptr is the "from_cset" mentioned on CPU 1
|css_set_ptr = rcu_dereference((task)->cgroups)
|// Hard irq comes, current task is scheduled out.
cgroup_attach_task()
|cgroup_migrate()
|cgroup_migrate_execute()
|css_set_move_task(task, from_cset, to_cset, true)
|cgroup_move_task(task, to_cset)
|rcu_assign_pointer(.., to_cset)
|...
|cgroup_migrate_finish()
|put_css_set_locked(from_cset)
|from_cset->refcount return 0
|kfree_rcu(cset, rcu_head) // means to free from_cset after new gp
|add_ptr_to_bulk_krc_lock()
|schedule_delayed_work(&krcp->monitor_work, ..)
kfree_rcu_monitor()
|krcp->bulk_head[0]'s work attached to krwp->bulk_head_free[]
|queue_rcu_work(system_wq, &krwp->rcu_work)
|if rwork->rcu.work is not in WORK_STRUCT_PENDING_BIT state,
|call_rcu(&rwork->rcu, rcu_work_rcufn) <--- request a new gp
// There is a perious call_rcu(.., rcu_work_rcufn)
// gp end, rcu_work_rcufn() is called.
rcu_work_rcufn()
|__queue_work(.., rwork->wq, &rwork->work);
|kfree_rcu_work()
|krwp->bulk_head_free[0] bulk is freed before new gp end!!!
|The "from_cset" is freed before new gp end.
// the task is scheduled in after many ms.
|css_set_ptr->subsys[(subsys_id) <--- Caused kernel crash, because css_set_ptr is freed.
v2: Use helper function instead of inserted code block at kfree_rcu_monitor().
Fixes: c014efeef76a ("rcu: Add multiple in-flight batches of kfree_rcu() work")
Signed-off-by: Ziwei Dai <ziwei.dai@xxxxxxxxxx>
---
kernel/rcu/tree.c | 27 +++++++++++++++++++--------
1 file changed, 19 insertions(+), 8 deletions(-)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8e880c0..7b95ee9 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3024,6 +3024,18 @@ static void kfree_rcu_work(struct work_struct *work)
return !!READ_ONCE(krcp->head);
}
+static bool
+need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp)
+{
+ int i;
+
+ for (i = 0; i < FREE_N_CHANNELS; i++)
+ if (!list_empty(&krwp->bulk_head_free[i]))
+ return true;
+
+ return !!krwp->head_free;
+}
+
static int krc_count(struct kfree_rcu_cpu *krcp)
{
int sum = atomic_read(&krcp->head_count);
@@ -3107,15 +3119,14 @@ static void kfree_rcu_monitor(struct work_struct *work)
for (i = 0; i < KFREE_N_BATCHES; i++) {
struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]);
- // Try to detach bulk_head or head and attach it over any
- // available corresponding free channel. It can be that
- // a previous RCU batch is in progress, it means that
- // immediately to queue another one is not possible so
- // in that case the monitor work is rearmed.
- if ((!list_empty(&krcp->bulk_head[0]) && list_empty(&krwp->bulk_head_free[0])) ||
- (!list_empty(&krcp->bulk_head[1]) && list_empty(&krwp->bulk_head_free[1])) ||
- (READ_ONCE(krcp->head) && !krwp->head_free)) {
+ // Try to detach bulk_head or head and attach it, only when
+ // all channels are free. Any channel is not free means at krwp
+ // there is on-going rcu work to handle krwp's free business.
+ if (need_wait_for_krwp_work(krwp))
+ continue;
+ // kvfree_rcu_drain_ready() might handle this krcp, if so give up.
+ if (need_offload_krc(krcp)) {
// Channel 1 corresponds to the SLAB-pointer bulk path.
// Channel 2 corresponds to vmalloc-pointer bulk path.
for (j = 0; j < FREE_N_CHANNELS; j++) {
--
1.9.1
