futex: Replace PF_EXITPIDONE with a state

commit 3d4775df0a89240f671861c6ab6e8d59af8e9e41 upstream.

The futex exit handling relies on PF_ flags. That's suboptimal as it
requires a smp_mb() and an ugly lock/unlock of the exiting tasks pi_lock in
the middle of do_exit() to enforce the observability of PF_EXITING in the
futex code.

Add a futex_state member to task_struct and convert the PF_EXITPIDONE logic
over to the new state. The PF_EXITING dependency will be cleaned up in a
later step.

This prepares for handling various futex exit issues later.

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/20191106224556.149449274@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 34 insertions, 1 deletions

diff --git a/include/linux/futex.h b/include/linux/futex.h
index bc4138b87035..35703ec3a255 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -53,6 +53,10 @@ union futex_key {
 #define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } }
 
 #ifdef CONFIG_FUTEX
+enum {
+	FUTEX_STATE_OK,
+	FUTEX_STATE_DEAD,
+};
 
 static inline void futex_init_task(struct task_struct *tsk)
 {
@@ -62,6 +66,34 @@ static inline void futex_init_task(struct task_struct *tsk)
 #endif
 	INIT_LIST_HEAD(&tsk->pi_state_list);
 	tsk->pi_state_cache = NULL;
+	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_mm_release(struct task_struct *tsk);
@@ -71,6 +103,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 #else
 static inline void futex_init_task(struct task_struct *tsk) { }
 static inline void futex_mm_release(struct task_struct *tsk) { }
+static inline void futex_exit_done(struct task_struct *tsk) { }
 #endif
 
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 866439c361a9..6a3e0053791a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -959,6 +959,7 @@ struct task_struct {
 #endif
 	struct list_head		pi_state_list;
 	struct futex_pi_state		*pi_state_cache;
+	unsigned int			futex_state;
 #endif
 #ifdef CONFIG_PERF_EVENTS
 	struct perf_event_context	*perf_event_ctxp[perf_nr_task_contexts];
@@ -1334,7 +1335,6 @@ extern struct pid *cad_pid;
  */
 #define PF_IDLE			0x00000002	/* I am an IDLE thread */
 #define PF_EXITING		0x00000004	/* Getting shut down */
-#define PF_EXITPIDONE		0x00000008	/* PI exit done on shut down */
 #define PF_VCPU			0x00000010	/* I'm a virtual CPU */
 #define PF_WQ_WORKER		0x00000020	/* I'm a workqueue worker */
 #define PF_FORKNOEXEC		0x00000040	/* Forked but didn't exec */