Merge tag 'io_uring-5.12-2021-03-27' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:

 - Use thread info versions of flag testing, as discussed last week.

 - The series enabling PF_IO_WORKER to just take signals, instead of
   needing to special case that they do not in a bunch of places. Ends
   up being pretty trivial to do, and then we can revert all the special
   casing we're currently doing.

 - Kill dead pointer assignment

 - Fix hashed part of async work queue trace

 - Fix sign extension issue for IORING_OP_PROVIDE_BUFFERS

 - Fix a link completion ordering regression in this merge window

 - Cancellation fixes

* tag 'io_uring-5.12-2021-03-27' of git://git.kernel.dk/linux-block:
  io_uring: remove unsued assignment to pointer io
  io_uring: don't cancel extra on files match
  io_uring: don't cancel-track common timeouts
  io_uring: do post-completion chore on t-out cancel
  io_uring: fix timeout cancel return code
  Revert "signal: don't allow STOP on PF_IO_WORKER threads"
  Revert "kernel: freezer should treat PF_IO_WORKER like PF_KTHREAD for freezing"
  Revert "kernel: treat PF_IO_WORKER like PF_KTHREAD for ptrace/signals"
  Revert "signal: don't allow sending any signals to PF_IO_WORKER threads"
  kernel: stop masking signals in create_io_thread()
  io_uring: handle signals for IO threads like a normal thread
  kernel: don't call do_exit() for PF_IO_WORKER threads
  io_uring: maintain CQE order of a failed link
  io-wq: fix race around pending work on teardown
  io_uring: do ctx sqd ejection in a clear context
  io_uring: fix provide_buffers sign extension
  io_uring: don't skip file_end_write() on reissue
  io_uring: correct io_queue_async_work() traces
  io_uring: don't use {test,clear}_tsk_thread_flag() for current

4 files changed, 22 insertions, 18 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 54cc905e5fe0..426cd0c51f9e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1948,8 +1948,14 @@ static __latent_entropy struct task_struct *copy_process(
 	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
-	if (args->io_thread)
+	if (args->io_thread) {
+		/*
+		 * Mark us an IO worker, and block any signal that isn't
+		 * fatal or STOP
+		 */
 		p->flags |= PF_IO_WORKER;
+		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
+	}
 
 	/*
 	 * This _must_ happen before we call free_task(), i.e. before we jump
@@ -2438,14 +2444,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 		.stack_size	= (unsigned long)arg,
 		.io_thread	= 1,
 	};
-	struct task_struct *tsk;
 
-	tsk = copy_process(NULL, 0, node, &args);
-	if (!IS_ERR(tsk)) {
-		sigfillset(&tsk->blocked);
-		sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
-	}
-	return tsk;
+	return copy_process(NULL, 0, node, &args);
 }
 
 /*
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 1a2d57d1327c..dc520f01f99d 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -134,7 +134,7 @@ bool freeze_task(struct task_struct *p)
 		return false;
 	}
 
-	if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if (!(p->flags & PF_KTHREAD))
 		fake_signal_wake_up(p);
 	else
 		wake_up_state(p, TASK_INTERRUPTIBLE);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 821cf1723814..61db50f7ca86 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -375,7 +375,7 @@ static int ptrace_attach(struct task_struct *task, long request,
 	audit_ptrace(task);
 
 	retval = -EPERM;
-	if (unlikely(task->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if (unlikely(task->flags & PF_KTHREAD))
 		goto out;
 	if (same_thread_group(task, current))
 		goto out;
diff --git a/kernel/signal.c b/kernel/signal.c
index f2a1b898da29..f2718350bf4b 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -91,7 +91,7 @@ static bool sig_task_ignored(struct task_struct *t, int sig, bool force)
 		return true;
 
 	/* Only allow kernel generated signals to this kthread */
-	if (unlikely((t->flags & (PF_KTHREAD | PF_IO_WORKER)) &&
+	if (unlikely((t->flags & PF_KTHREAD) &&
 		     (handler == SIG_KTHREAD_KERNEL) && !force))
 		return true;
 
@@ -288,8 +288,7 @@ bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask)
 			JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING));
 	BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK));
 
-	if (unlikely(fatal_signal_pending(task) ||
-		     (task->flags & (PF_EXITING | PF_IO_WORKER))))
+	if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING)))
 		return false;
 
 	if (mask & JOBCTL_STOP_SIGMASK)
@@ -834,9 +833,6 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info,
 
 	if (!valid_signal(sig))
 		return -EINVAL;
-	/* PF_IO_WORKER threads don't take any signals */
-	if (t->flags & PF_IO_WORKER)
-		return -ESRCH;
 
 	if (!si_fromuser(info))
 		return 0;
@@ -1100,7 +1096,7 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc
 	/*
 	 * Skip useless siginfo allocation for SIGKILL and kernel threads.
 	 */
-	if ((sig == SIGKILL) || (t->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
 		goto out_set;
 
 	/*
@@ -2772,13 +2768,21 @@ relock:
 		}
 
 		/*
+		 * PF_IO_WORKER threads will catch and exit on fatal signals
+		 * themselves. They have cleanup that must be performed, so
+		 * we cannot call do_exit() on their behalf.
+		 */
+		if (current->flags & PF_IO_WORKER)
+			goto out;
+
+		/*
 		 * Death signals, no core dump.
 		 */
 		do_group_exit(ksig->info.si_signo);
 		/* NOTREACHED */
 	}
 	spin_unlock_irq(&sighand->siglock);
-
+out:
 	ksig->sig = signr;
 
 	if (!(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS))