Merge tag 'io_uring-5.12-2021-03-19' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:
 "Quieter week this time, which was both expected and desired. About
  half of the below is fixes for this release, the other half are just
  fixes in general. In detail:

   - Fix the freezing of IO threads, by making the freezer not send them
     fake signals. Make them freezable by default.

   - Like we did for personalities, move the buffer IDR to xarray. Kills
     some code and avoids a use-after-free on teardown.

   - SQPOLL cleanups and fixes (Pavel)

   - Fix linked timeout race (Pavel)

   - Fix potential completion post use-after-free (Pavel)

   - Cleanup and move internal structures outside of general kernel view
     (Stefan)

   - Use MSG_SIGNAL for send/recv from io_uring (Stefan)"

* tag 'io_uring-5.12-2021-03-19' of git://git.kernel.dk/linux-block:
  io_uring: don't leak creds on SQO attach error
  io_uring: use typesafe pointers in io_uring_task
  io_uring: remove structures from include/linux/io_uring.h
  io_uring: imply MSG_NOSIGNAL for send[msg]()/recv[msg]() calls
  io_uring: fix sqpoll cancellation via task_work
  io_uring: add generic callback_head helpers
  io_uring: fix concurrent parking
  io_uring: halt SQO submission on ctx exit
  io_uring: replace sqd rw_semaphore with mutex
  io_uring: fix complete_post use ctx after free
  io_uring: fix ->flags races by linked timeouts
  io_uring: convert io_buffer_idr to XArray
  io_uring: allow IO worker threads to be frozen
  kernel: freezer should treat PF_IO_WORKER like PF_KTHREAD for freezing

fs/io-wq.c

@@ -488,6 +488,8 @@ static int io_wqe_worker(void *data)
 	set_task_comm(current, buf);
 
 	while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
+		long ret;
+
 		set_current_state(TASK_INTERRUPTIBLE);
 loop:
 		raw_spin_lock_irq(&wqe->lock);
@@ -498,7 +500,8 @@ static int io_wqe_worker(void *data)
 		__io_worker_idle(wqe, worker);
 		raw_spin_unlock_irq(&wqe->lock);
 		io_flush_signals();
-		if (schedule_timeout(WORKER_IDLE_TIMEOUT))
+		ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
+		if (try_to_freeze() || ret)
 			continue;
 		if (fatal_signal_pending(current))
 			break;
@@ -709,6 +712,7 @@ 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));

fs/io-wq.h

@@ -2,7 +2,6 @@
 #define INTERNAL_IO_WQ_H
 
 #include <linux/refcount.h>
-#include <linux/io_uring.h>
 
 struct io_wq;
 
@@ -21,6 +20,15 @@ enum io_wq_cancel {
 	IO_WQ_CANCEL_NOTFOUND,	/* work not found */
 };
 
+struct io_wq_work_node {
+	struct io_wq_work_node *next;
+};
+
+struct io_wq_work_list {
+	struct io_wq_work_node *first;
+	struct io_wq_work_node *last;
+};
+
 static inline void wq_list_add_after(struct io_wq_work_node *node,
 				     struct io_wq_work_node *pos,
 				     struct io_wq_work_list *list)

include/linux/io_uring.h

@@ -5,31 +5,6 @@
 #include <linux/sched.h>
 #include <linux/xarray.h>
 
-struct io_wq_work_node {
-	struct io_wq_work_node *next;
-};
-
-struct io_wq_work_list {
-	struct io_wq_work_node *first;
-	struct io_wq_work_node *last;
-};
-
-struct io_uring_task {
-	/* submission side */
-	struct xarray		xa;
-	struct wait_queue_head	wait;
-	void			*last;
-	void			*io_wq;
-	struct percpu_counter	inflight;
-	atomic_t		in_idle;
-	bool			sqpoll;
-
-	spinlock_t		task_lock;
-	struct io_wq_work_list	task_list;
-	unsigned long		task_state;
-	struct callback_head	task_work;
-};
-
 #if defined(CONFIG_IO_URING)
 struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_task_cancel(void);

kernel/fork.c

@@ -2444,7 +2444,6 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 	if (!IS_ERR(tsk)) {
 		sigfillset(&tsk->blocked);
 		sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
-		tsk->flags |= PF_NOFREEZE;
 	}
 	return tsk;
 }

kernel/freezer.c

@@ -134,7 +134,7 @@ bool freeze_task(struct task_struct *p)
 		return false;
 	}
 
-	if (!(p->flags & PF_KTHREAD))
+	if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))
 		fake_signal_wake_up(p);
 	else
 		wake_up_state(p, TASK_INTERRUPTIBLE);