task_work_add: generic process-context callbacks

Provide a simple mechanism that allows running code in the (nonatomic)
context of the arbitrary task.

The caller does task_work_add(task, task_work) and this task executes
task_work->func() either from do_notify_resume() or from do_exit().  The
callback can rely on PF_EXITING to detect the latter case.

"struct task_work" can be embedded in another struct, still it has "void
*data" to handle the most common/simple case.

This allows us to kill the ->replacement_session_keyring hack, and
potentially this can have more users.

Performance-wise, this adds 2 "unlikely(!hlist_empty())" checks into
tracehook_notify_resume() and do_exit().  But at the same time we can
remove the "replacement_session_keyring != NULL" checks from
arch/*/signal.c and exit_creds().

Note: task_work_add/task_work_run abuses ->pi_lock.  This is only because
this lock is already used by lookup_pi_state() to synchronize with
do_exit() setting PF_EXITING.  Fortunately the scope of this lock in
task_work.c is really tiny, and the code is unlikely anyway.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: David Howells <dhowells@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Kuo <rkuo@codeaurora.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Alexander Gordeev <agordeev@redhat.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: David Smith <dsmith@redhat.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 84 insertions, 0 deletions

diff --git a/kernel/task_work.c b/kernel/task_work.c
new file mode 100644
index 0000000..82d1c79
--- /dev/null
+++ b/kernel/task_work.c
@@ -0,0 +1,84 @@
+#include <linux/spinlock.h>
+#include <linux/task_work.h>
+#include <linux/tracehook.h>
+
+int
+task_work_add(struct task_struct *task, struct task_work *twork, bool notify)
+{
+	unsigned long flags;
+	int err = -ESRCH;
+
+#ifndef TIF_NOTIFY_RESUME
+	if (notify)
+		return -ENOTSUPP;
+#endif
+	/*
+	 * We must not insert the new work if the task has already passed
+	 * exit_task_work(). We rely on do_exit()->raw_spin_unlock_wait()
+	 * and check PF_EXITING under pi_lock.
+	 */
+	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	if (likely(!(task->flags & PF_EXITING))) {
+		hlist_add_head(&twork->hlist, &task->task_works);
+		err = 0;
+	}
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+	/* test_and_set_bit() implies mb(), see tracehook_notify_resume(). */
+	if (likely(!err) && notify)
+		set_notify_resume(task);
+	return err;
+}
+
+struct task_work *
+task_work_cancel(struct task_struct *task, task_work_func_t func)
+{
+	unsigned long flags;
+	struct task_work *twork;
+	struct hlist_node *pos;
+
+	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	hlist_for_each_entry(twork, pos, &task->task_works, hlist) {
+		if (twork->func == func) {
+			hlist_del(&twork->hlist);
+			goto found;
+		}
+	}
+	twork = NULL;
+ found:
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+	return twork;
+}
+
+void task_work_run(void)
+{
+	struct task_struct *task = current;
+	struct hlist_head task_works;
+	struct hlist_node *pos;
+
+	raw_spin_lock_irq(&task->pi_lock);
+	hlist_move_list(&task->task_works, &task_works);
+	raw_spin_unlock_irq(&task->pi_lock);
+
+	if (unlikely(hlist_empty(&task_works)))
+		return;
+	/*
+	 * We use hlist to save the space in task_struct, but we want fifo.
+	 * Find the last entry, the list should be short, then process them
+	 * in reverse order.
+	 */
+	for (pos = task_works.first; pos->next; pos = pos->next)
+		;
+
+	for (;;) {
+		struct hlist_node **pprev = pos->pprev;
+		struct task_work *twork = container_of(pos, struct task_work,
+							hlist);
+		twork->func(twork);
+
+		if (pprev == &task_works.first)
+			break;
+		pos = container_of(pprev, struct hlist_node, next);
+	}
+}