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>

3 files changed, 46 insertions, 0 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5ea8baea938..7930131abc1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1400,6 +1400,8 @@ struct task_struct {
         int (*notifier)(void *priv);
         void *notifier_data;
         sigset_t *notifier_mask;
+        struct hlist_head task_works;
+
         struct audit_context *audit_context;
 #ifdef CONFIG_AUDITSYSCALL
         uid_t loginuid;
diff --git a/include/linux/task_work.h b/include/linux/task_work.h
new file mode 100644
index 00000000000..294d5d5e90b
--- /dev/null
+++ b/include/linux/task_work.h
@@ -0,0 +1,33 @@
+#ifndef _LINUX_TASK_WORK_H
+#define _LINUX_TASK_WORK_H
+
+#include <linux/list.h>
+#include <linux/sched.h>
+
+struct task_work;
+typedef void (*task_work_func_t)(struct task_work *);
+
+struct task_work {
+        struct hlist_node hlist;
+        task_work_func_t func;
+        void *data;
+};
+
+static inline void
+init_task_work(struct task_work *twork, task_work_func_t func, void *data)
+{
+        twork->func = func;
+        twork->data = data;
+}
+
+int task_work_add(struct task_struct *task, struct task_work *twork, bool);
+struct task_work *task_work_cancel(struct task_struct *, task_work_func_t);
+void task_work_run(void);
+
+static inline void exit_task_work(struct task_struct *task)
+{
+        if (unlikely(!hlist_empty(&task->task_works)))
+                task_work_run();
+}
+
+#endif  /* _LINUX_TASK_WORK_H */
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index b9ca903bb55..b2dd0917ca0 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -49,6 +49,7 @@
 #include <linux/sched.h>
 #include <linux/ptrace.h>
 #include <linux/security.h>
+#include <linux/task_work.h>
 struct linux_binprm;
 
 /*
@@ -164,8 +165,10 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info,
  */
 static inline void set_notify_resume(struct task_struct *task)
 {
+#ifdef TIF_NOTIFY_RESUME
         if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME))
                 kick_process(task);
+#endif
 }
 
 /**
@@ -185,6 +188,14 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 {
         if (current->replacement_session_keyring)
                 key_replace_session_keyring();
+        /*
+         * The caller just cleared TIF_NOTIFY_RESUME. This barrier
+         * pairs with task_work_add()->set_notify_resume() after
+         * hlist_add_head(task->task_works);
+         */
+        smp_mb__after_clear_bit();
+        if (unlikely(!hlist_empty(&current->task_works)))
+                task_work_run();
 }
 
 #endif  /* <linux/tracehook.h> */