futex: Mark the begin of futex exit explicitly

BugLink: https://bugs.launchpad.net/bugs/1855787
commit 18f694385c4fd77a09851fd301236746ca83f3cb upstream.

Instead of relying on PF_EXITING use an explicit state for the futex exit
and set it in the futex exit function. This moves the smp barrier and the
lock/unlock serialization into the futex code.

As with the DEAD state this is restricted to the exit path as exec
continues to use the same task struct.

This allows to simplify that logic in a next step.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20191106224556.539409004@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Kleber Sacilotto de Souza <kleber.souza@canonical.com>

diff --git a/include/linux/futex.h b/include/linux/futex.h
index fb698e25f210a7f729d277d0e975ab8e375ee653..ff143f766b46703e60f72f2e5d085d88c1ee10a3 100644 (file)
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -55,6 +55,7 @@ union futex_key {
 #ifdef CONFIG_FUTEX
 enum {
        FUTEX_STATE_OK,
+       FUTEX_STATE_EXITING,
        FUTEX_STATE_DEAD,
 };
 
@@ -69,33 +70,7 @@ static inline void futex_init_task(struct task_struct *tsk)
        tsk->futex_state = FUTEX_STATE_OK;
 }
 
-/**
- * futex_exit_done - Sets the tasks futex state to FUTEX_STATE_DEAD
- * @tsk:       task to set the state on
- *
- * Set the futex exit state of the task lockless. The futex waiter code
- * observes that state when a task is exiting and loops until the task has
- * actually finished the futex cleanup. The worst case for this is that the
- * waiter runs through the wait loop until the state becomes visible.
- *
- * This has two callers:
- *
- * - futex_mm_release() after the futex exit cleanup has been done
- *
- * - do_exit() from the recursive fault handling path.
- *
- * In case of a recursive fault this is best effort. Either the futex exit
- * code has run already or not. If the OWNER_DIED bit has been set on the
- * futex then the waiter can take it over. If not, the problem is pushed
- * back to user space. If the futex exit code did not run yet, then an
- * already queued waiter might block forever, but there is nothing which
- * can be done about that.
- */
-static inline void futex_exit_done(struct task_struct *tsk)
-{
-       tsk->futex_state = FUTEX_STATE_DEAD;
-}
-
+void futex_exit_recursive(struct task_struct *tsk);
 void futex_exit_release(struct task_struct *tsk);
 void futex_exec_release(struct task_struct *tsk);
 
@@ -103,7 +78,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
              u32 __user *uaddr2, u32 val2, u32 val3);
 #else
 static inline void futex_init_task(struct task_struct *tsk) { }
-static inline void futex_exit_done(struct task_struct *tsk) { }
+static inline void futex_exit_recursive(struct task_struct *tsk) { }
 static inline void futex_exit_release(struct task_struct *tsk) { }
 static inline void futex_exec_release(struct task_struct *tsk) { }
 #endif

diff --git a/kernel/exit.c b/kernel/exit.c
index fc633781a86e7fd9cd320b44ab5838f9b13d4d5e..de3fe9b0ec4e0fa535bc6086e0cbe940b3250f06 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -803,23 +803,12 @@ void __noreturn do_exit(long code)
         */
        if (unlikely(tsk->flags & PF_EXITING)) {
                pr_alert("Fixing recursive fault but reboot is needed!\n");
-               futex_exit_done(tsk);
+               futex_exit_recursive(tsk);
                set_current_state(TASK_UNINTERRUPTIBLE);
                schedule();
        }
 
        exit_signals(tsk);  /* sets PF_EXITING */
-       /*
-        * Ensure that all new tsk->pi_lock acquisitions must observe
-        * PF_EXITING. Serializes against futex.c:attach_to_pi_owner().
-        */
-       smp_mb();
-       /*
-        * Ensure that we must observe the pi_state in exit_mm() ->
-        * mm_release() -> exit_pi_state_list().
-        */
-       raw_spin_lock_irq(&tsk->pi_lock);
-       raw_spin_unlock_irq(&tsk->pi_lock);
 
        if (unlikely(in_atomic())) {
                pr_info("note: %s[%d] exited with preempt_count %d\n",

diff --git a/kernel/futex.c b/kernel/futex.c
index 01958a0eec30f4ea1d7eef625b0fe3d077614cda..8bfb4c0f3f5181d0ca587f6ff5692b313f0833cb 100644 (file)
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -3702,10 +3702,45 @@ void futex_exec_release(struct task_struct *tsk)
                exit_pi_state_list(tsk);
 }
 
+/**
+ * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD
+ * @tsk:       task to set the state on
+ *
+ * Set the futex exit state of the task lockless. The futex waiter code
+ * observes that state when a task is exiting and loops until the task has
+ * actually finished the futex cleanup. The worst case for this is that the
+ * waiter runs through the wait loop until the state becomes visible.
+ *
+ * This is called from the recursive fault handling path in do_exit().
+ *
+ * This is best effort. Either the futex exit code has run already or
+ * not. If the OWNER_DIED bit has been set on the futex then the waiter can
+ * take it over. If not, the problem is pushed back to user space. If the
+ * futex exit code did not run yet, then an already queued waiter might
+ * block forever, but there is nothing which can be done about that.
+ */
+void futex_exit_recursive(struct task_struct *tsk)
+{
+       tsk->futex_state = FUTEX_STATE_DEAD;
+}
+
 void futex_exit_release(struct task_struct *tsk)
 {
+       tsk->futex_state = FUTEX_STATE_EXITING;
+       /*
+        * Ensure that all new tsk->pi_lock acquisitions must observe
+        * FUTEX_STATE_EXITING. Serializes against attach_to_pi_owner().
+        */
+       smp_mb();
+       /*
+        * Ensure that we must observe the pi_state in exit_pi_state_list().
+        */
+       raw_spin_lock_irq(&tsk->pi_lock);
+       raw_spin_unlock_irq(&tsk->pi_lock);
+
        futex_exec_release(tsk);
-       futex_exit_done(tsk);
+
+       tsk->futex_state = FUTEX_STATE_DEAD;
 }
 
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,