io_uring: ensure that threads freeze on suspend

Alex reports that his system fails to suspend using 5.12-rc1, with the
following dump:

[  240.650300] PM: suspend entry (deep)
[  240.650748] Filesystems sync: 0.000 seconds
[  240.725605] Freezing user space processes ...
[  260.739483] Freezing of tasks failed after 20.013 seconds (3 tasks refusing to freeze, wq_busy=0):
[  260.739497] task:iou-mgr-446     state:S stack:    0 pid:  516 ppid:   439 flags:0x00004224
[  260.739504] Call Trace:
[  260.739507]  ? sysvec_apic_timer_interrupt+0xb/0x81
[  260.739515]  ? pick_next_task_fair+0x197/0x1cde
[  260.739519]  ? sysvec_reschedule_ipi+0x2f/0x6a
[  260.739522]  ? asm_sysvec_reschedule_ipi+0x12/0x20
[  260.739525]  ? __schedule+0x57/0x6d6
[  260.739529]  ? del_timer_sync+0xb9/0x115
[  260.739533]  ? schedule+0x63/0xd5
[  260.739536]  ? schedule_timeout+0x219/0x356
[  260.739540]  ? __next_timer_interrupt+0xf1/0xf1
[  260.739544]  ? io_wq_manager+0x73/0xb1
[  260.739549]  ? io_wq_create+0x262/0x262
[  260.739553]  ? ret_from_fork+0x22/0x30
[  260.739557] task:iou-mgr-517     state:S stack:    0 pid:  522 ppid:   439 flags:0x00004224
[  260.739561] Call Trace:
[  260.739563]  ? sysvec_apic_timer_interrupt+0xb/0x81
[  260.739566]  ? pick_next_task_fair+0x16f/0x1cde
[  260.739569]  ? sysvec_apic_timer_interrupt+0xb/0x81
[  260.739571]  ? asm_sysvec_apic_timer_interrupt+0x12/0x20
[  260.739574]  ? __schedule+0x5b7/0x6d6
[  260.739578]  ? del_timer_sync+0x70/0x115
[  260.739581]  ? schedule_timeout+0x211/0x356
[  260.739585]  ? __next_timer_interrupt+0xf1/0xf1
[  260.739588]  ? io_wq_check_workers+0x15/0x11f
[  260.739592]  ? io_wq_manager+0x69/0xb1
[  260.739596]  ? io_wq_create+0x262/0x262
[  260.739600]  ? ret_from_fork+0x22/0x30
[  260.739603] task:iou-wrk-517     state:S stack:    0 pid:  523 ppid:   439 flags:0x00004224
[  260.739607] Call Trace:
[  260.739609]  ? __schedule+0x5b7/0x6d6
[  260.739614]  ? schedule+0x63/0xd5
[  260.739617]  ? schedule_timeout+0x219/0x356
[  260.739621]  ? __next_timer_interrupt+0xf1/0xf1
[  260.739624]  ? task_thread.isra.0+0x148/0x3af
[  260.739628]  ? task_thread_unbound+0xa/0xa
[  260.739632]  ? task_thread_bound+0x7/0x7
[  260.739636]  ? ret_from_fork+0x22/0x30
[  260.739647] OOM killer enabled.
[  260.739648] Restarting tasks ... done.
[  260.740077] PM: suspend exit

Play nice and ensure that any thread we create will call try_to_freeze()
at an opportune time so that memory suspend can proceed. For the io-wq
worker threads, mark them as PF_NOFREEZE. They could potentially be
blocked for a long time.

Reported-by: Alex Xu (Hello71) <alex_y_xu@yahoo.ca>
Tested-by: Alex Xu (Hello71) <alex_y_xu@yahoo.ca>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 5 insertions, 3 deletions

diff --git a/fs/io-wq.c b/fs/io-wq.c
index dc430381b69413..acffc85d1a932c 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -16,6 +16,7 @@
 #include <linux/rculist_nulls.h>
 #include <linux/cpu.h>
 #include <linux/tracehook.h>
+#include <linux/freezer.h>
 
 #include "../kernel/sched/sched.h"
 #include "io-wq.h"
@@ -263,6 +264,7 @@ static void io_wqe_dec_running(struct io_worker *worker)
 
 static void io_worker_start(struct io_worker *worker)
 {
+	current->flags |= PF_NOFREEZE;
 	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
 	io_wqe_inc_running(worker);
 	complete(&worker->started);
@@ -731,6 +733,7 @@ static int io_wq_manager(void *data)
 		set_current_state(TASK_INTERRUPTIBLE);
 		io_wq_check_workers(wq);
 		schedule_timeout(HZ);
+		try_to_freeze();
 		if (fatal_signal_pending(current))
 			set_bit(IO_WQ_BIT_EXIT, &wq->state);
 	} while (!test_bit(IO_WQ_BIT_EXIT, &wq->state));
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 26e83cabf3bf04..b1734efdc7e875 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -74,13 +74,11 @@
 #include <linux/fsnotify.h>
 #include <linux/fadvise.h>
 #include <linux/eventpoll.h>
-#include <linux/fs_struct.h>
 #include <linux/splice.h>
 #include <linux/task_work.h>
 #include <linux/pagemap.h>
 #include <linux/io_uring.h>
-#include <linux/blk-cgroup.h>
-#include <linux/audit.h>
+#include <linux/freezer.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -6736,6 +6734,7 @@ static int io_sq_thread(void *data)
 				io_ring_set_wakeup_flag(ctx);
 
 			schedule();
+			try_to_freeze();
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_clear_wakeup_flag(ctx);
 		}