locking/semaphore: Use wake_q to wake up processes outside lock critical section

[ Upstream commit 85b2b9c ]

A circular lock dependency splat has been seen involving down_trylock():

  ======================================================
  WARNING: possible circular locking dependency detected
  6.12.0-41.el10.s390x+debug
  ------------------------------------------------------
  dd/32479 is trying to acquire lock:
  0015a20accd0d4f8 ((console_sem).lock){-.-.}-{2:2}, at: down_trylock+0x26/0x90

  but task is already holding lock:
  000000017e461698 (&zone->lock){-.-.}-{2:2}, at: rmqueue_bulk+0xac/0x8f0

  the existing dependency chain (in reverse order) is:
  -> #4 (&zone->lock){-.-.}-{2:2}:
  -> #3 (hrtimer_bases.lock){-.-.}-{2:2}:
  -> #2 (&rq->__lock){-.-.}-{2:2}:
  -> #1 (&p->pi_lock){-.-.}-{2:2}:
  -> #0 ((console_sem).lock){-.-.}-{2:2}:

The console_sem -> pi_lock dependency is due to calling try_to_wake_up()
while holding the console_sem raw_spinlock. This dependency can be broken
by using wake_q to do the wakeup instead of calling try_to_wake_up()
under the console_sem lock. This will also make the semaphore's
raw_spinlock become a terminal lock without taking any further locks
underneath it.

The hrtimer_bases.lock is a raw_spinlock while zone->lock is a
spinlock. The hrtimer_bases.lock -> zone->lock dependency happens via
the debug_objects_fill_pool() helper function in the debugobjects code.

  -> #4 (&zone->lock){-.-.}-{2:2}:
         __lock_acquire+0xe86/0x1cc0
         lock_acquire.part.0+0x258/0x630
         lock_acquire+0xb8/0xe0
         _raw_spin_lock_irqsave+0xb4/0x120
         rmqueue_bulk+0xac/0x8f0
         __rmqueue_pcplist+0x580/0x830
         rmqueue_pcplist+0xfc/0x470
         rmqueue.isra.0+0xdec/0x11b0
         get_page_from_freelist+0x2ee/0xeb0
         __alloc_pages_noprof+0x2c2/0x520
         alloc_pages_mpol_noprof+0x1fc/0x4d0
         alloc_pages_noprof+0x8c/0xe0
         allocate_slab+0x320/0x460
         ___slab_alloc+0xa58/0x12b0
         __slab_alloc.isra.0+0x42/0x60
         kmem_cache_alloc_noprof+0x304/0x350
         fill_pool+0xf6/0x450
         debug_object_activate+0xfe/0x360
         enqueue_hrtimer+0x34/0x190
         __run_hrtimer+0x3c8/0x4c0
         __hrtimer_run_queues+0x1b2/0x260
         hrtimer_interrupt+0x316/0x760
         do_IRQ+0x9a/0xe0
         do_irq_async+0xf6/0x160

Normally a raw_spinlock to spinlock dependency is not legitimate
and will be warned if CONFIG_PROVE_RAW_LOCK_NESTING is enabled,
but debug_objects_fill_pool() is an exception as it explicitly
allows this dependency for non-PREEMPT_RT kernel without causing
PROVE_RAW_LOCK_NESTING lockdep splat. As a result, this dependency is
legitimate and not a bug.

Anyway, semaphore is the only locking primitive left that is still
using try_to_wake_up() to do wakeup inside critical section, all the
other locking primitives had been migrated to use wake_q to do wakeup
outside of the critical section. It is also possible that there are
other circular locking dependencies involving printk/console_sem or
other existing/new semaphores lurking somewhere which may show up in
the future. Let just do the migration now to wake_q to avoid headache
like this.

Reported-by: [email protected]
Signed-off-by: Waiman Long <[email protected]>
Signed-off-by: Boqun Feng <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Cc: Linus Torvalds <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>

Author: Waiman-Long

kernel/locking/semaphore.c

@@ -29,6 +29,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/wake_q.h>
 #include <linux/semaphore.h>
 #include <linux/spinlock.h>
 #include <linux/ftrace.h>
@@ -38,7 +39,7 @@ static noinline void __down(struct semaphore *sem);
 static noinline int __down_interruptible(struct semaphore *sem);
 static noinline int __down_killable(struct semaphore *sem);
 static noinline int __down_timeout(struct semaphore *sem, long timeout);
-static noinline void __up(struct semaphore *sem);
+static noinline void __up(struct semaphore *sem, struct wake_q_head *wake_q);
 
 /**
  * down - acquire the semaphore
@@ -183,13 +184,16 @@ EXPORT_SYMBOL(down_timeout);
 void __sched up(struct semaphore *sem)
 {
 	unsigned long flags;
+	DEFINE_WAKE_Q(wake_q);
 
 	raw_spin_lock_irqsave(&sem->lock, flags);
 	if (likely(list_empty(&sem->wait_list)))
 		sem->count++;
 	else
-		__up(sem);
+		__up(sem, &wake_q);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
+	if (!wake_q_empty(&wake_q))
+		wake_up_q(&wake_q);
 }
 EXPORT_SYMBOL(up);
 
@@ -269,11 +273,12 @@ static noinline int __sched __down_timeout(struct semaphore *sem, long timeout)
 	return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout);
 }
 
-static noinline void __sched __up(struct semaphore *sem)
+static noinline void __sched __up(struct semaphore *sem,
+				  struct wake_q_head *wake_q)
 {
 	struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
 						struct semaphore_waiter, list);
 	list_del(&waiter->list);
 	waiter->up = true;
-	wake_up_process(waiter->task);
+	wake_q_add(wake_q, waiter->task);
 }