Merge tag 'locking-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Info Molnar:
 "Futex improvements:

   - Add the 'futex2' syscall ABI, which is an attempt to get away from
     the multiplex syscall and adds a little room for extentions, while
     lifting some limitations.

   - Fix futex PI recursive rt_mutex waiter state bug

   - Fix inter-process shared futexes on no-MMU systems

   - Use folios instead of pages

  Micro-optimizations of locking primitives:

   - Improve arch_spin_value_unlocked() on asm-generic ticket spinlock
     architectures, to improve lockref code generation

   - Improve the x86-32 lockref_get_not_zero() main loop by adding
     build-time CMPXCHG8B support detection for the relevant lockref
     code, and by better interfacing the CMPXCHG8B assembly code with
     the compiler

   - Introduce arch_sync_try_cmpxchg() on x86 to improve
     sync_try_cmpxchg() code generation. Convert some sync_cmpxchg()
     users to sync_try_cmpxchg().

   - Micro-optimize rcuref_put_slowpath()

  Locking debuggability improvements:

   - Improve CONFIG_DEBUG_RT_MUTEXES=y to have a fast-path as well

   - Enforce atomicity of sched_submit_work(), which is de-facto atomic
     but was un-enforced previously.

   - Extend <linux/cleanup.h>'s no_free_ptr() with __must_check
     semantics

   - Fix ww_mutex self-tests

   - Clean up const-propagation in <linux/seqlock.h> and simplify the
     API-instantiation macros a bit

  RT locking improvements:

   - Provide the rt_mutex_*_schedule() primitives/helpers and use them
     in the rtmutex code to avoid recursion vs. rtlock on the PI state.

   - Add nested blocking lockdep asserts to rt_mutex_lock(),
     rtlock_lock() and rwbase_read_lock()

  .. plus misc fixes & cleanups"

* tag 'locking-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (39 commits)
  futex: Don't include process MM in futex key on no-MMU
  locking/seqlock: Fix grammar in comment
  alpha: Fix up new futex syscall numbers
  locking/seqlock: Propagate 'const' pointers within read-only methods, remove forced type casts
  locking/lockdep: Fix string sizing bug that triggers a format-truncation compiler-warning
  locking/seqlock: Change __seqprop() to return the function pointer
  locking/seqlock: Simplify SEQCOUNT_LOCKNAME()
  locking/atomics: Use atomic_try_cmpxchg_release() to micro-optimize rcuref_put_slowpath()
  locking/atomic, xen: Use sync_try_cmpxchg() instead of sync_cmpxchg()
  locking/atomic/x86: Introduce arch_sync_try_cmpxchg()
  locking/atomic: Add generic support for sync_try_cmpxchg() and its fallback
  locking/seqlock: Fix typo in comment
  futex/requeue: Remove unnecessary ‘NULL’ initialization from futex_proxy_trylock_atomic()
  locking/local, arch: Rewrite local_add_unless() as a static inline function
  locking/debug: Fix debugfs API return value checks to use IS_ERR()
  locking/ww_mutex/test: Make sure we bail out instead of livelock
  locking/ww_mutex/test: Fix potential workqueue corruption
  locking/ww_mutex/test: Use prng instead of rng to avoid hangs at bootup
  futex: Add sys_futex_requeue()
  futex: Add flags2 argument to futex_requeue()
  ...

1 files changed, 50 insertions, 12 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 802551e0009b..9b075b541865 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6720,10 +6720,14 @@ void __noreturn do_task_dead(void)
 
 static inline void sched_submit_work(struct task_struct *tsk)
 {
+	static DEFINE_WAIT_OVERRIDE_MAP(sched_map, LD_WAIT_CONFIG);
 	unsigned int task_flags;
 
-	if (task_is_running(tsk))
-		return;
+	/*
+	 * Establish LD_WAIT_CONFIG context to ensure none of the code called
+	 * will use a blocking primitive -- which would lead to recursion.
+	 */
+	lock_map_acquire_try(&sched_map);
 
 	task_flags = tsk->flags;
 	/*
@@ -6749,6 +6753,8 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * make sure to submit it to avoid deadlocks.
 	 */
 	blk_flush_plug(tsk->plug, true);
+
+	lock_map_release(&sched_map);
 }
 
 static void sched_update_worker(struct task_struct *tsk)
@@ -6761,16 +6767,26 @@ static void sched_update_worker(struct task_struct *tsk)
 	}
 }
 
-asmlinkage __visible void __sched schedule(void)
+static __always_inline void __schedule_loop(unsigned int sched_mode)
 {
-	struct task_struct *tsk = current;
-
-	sched_submit_work(tsk);
 	do {
 		preempt_disable();
-		__schedule(SM_NONE);
+		__schedule(sched_mode);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
+}
+
+asmlinkage __visible void __sched schedule(void)
+{
+	struct task_struct *tsk = current;
+
+#ifdef CONFIG_RT_MUTEXES
+	lockdep_assert(!tsk->sched_rt_mutex);
+#endif
+
+	if (!task_is_running(tsk))
+		sched_submit_work(tsk);
+	__schedule_loop(SM_NONE);
 	sched_update_worker(tsk);
 }
 EXPORT_SYMBOL(schedule);
@@ -6834,11 +6850,7 @@ void __sched schedule_preempt_disabled(void)
 #ifdef CONFIG_PREEMPT_RT
 void __sched notrace schedule_rtlock(void)
 {
-	do {
-		preempt_disable();
-		__schedule(SM_RTLOCK_WAIT);
-		sched_preempt_enable_no_resched();
-	} while (need_resched());
+	__schedule_loop(SM_RTLOCK_WAIT);
 }
 NOKPROBE_SYMBOL(schedule_rtlock);
 #endif
@@ -7034,6 +7046,32 @@ static void __setscheduler_prio(struct task_struct *p, int prio)
 
 #ifdef CONFIG_RT_MUTEXES
 
+/*
+ * Would be more useful with typeof()/auto_type but they don't mix with
+ * bit-fields. Since it's a local thing, use int. Keep the generic sounding
+ * name such that if someone were to implement this function we get to compare
+ * notes.
+ */
+#define fetch_and_set(x, v) ({ int _x = (x); (x) = (v); _x; })
+
+void rt_mutex_pre_schedule(void)
+{
+	lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1));
+	sched_submit_work(current);
+}
+
+void rt_mutex_schedule(void)
+{
+	lockdep_assert(current->sched_rt_mutex);
+	__schedule_loop(SM_NONE);
+}
+
+void rt_mutex_post_schedule(void)
+{
+	sched_update_worker(current);
+	lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0));
+}
+
 static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
 {
 	if (pi_task)