futex: Fix might_sleep() warning in futex_pivot_pending()

A younger me put a WARN in might_sleep() to warn about nested sleep loops. This
younger me also build a wait-loop variant that can deal with it. This wait-loop
variant doesn't have all the fancy wrappers, since it isn't used much. It also
lacks wait-bit support.

Add the wait-bit support and use it to fix the nested wait issue.

Fixes: 8e7ff73 ("futex: Fix race in futex_pivot_pending() during private hash resize")
Reported-by: syzbot+350a93852ac854927f45@syzkaller.appspotmail.com
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260820074927.GH1246887@noisy.programming.kicks-ass.net
Closes: https://syzkaller.appspot.com/bug?extid=350a93852ac854927f45

Author: Peter Zijlstra

include/linux/wait.h

@@ -1228,6 +1228,7 @@ long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_en
 void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout);
 int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
+int woken_wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
 int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
 
 #define DEFINE_WAIT_FUNC(name, function)					\

include/linux/wait_bit.h

@@ -32,6 +32,7 @@ int out_of_line_wait_on_bit_timeout(unsigned long *word, int, wait_bit_action_f
 int out_of_line_wait_on_bit_lock(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode);
 struct wait_queue_head *bit_waitqueue(unsigned long *word, int bit);
 extern void __init wait_bit_init(void);
+extern struct wait_bit_key *__var_wake_key(struct wait_queue_entry *wq_entry, void *arg);
 
 int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
 

kernel/futex/core.c

@@ -45,6 +45,7 @@
 #include <linux/rseq.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/wait_bit.h>
 
 #include <vdso/futex.h>
 
@@ -1884,11 +1885,35 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags)
 		futex_hash_bucket_init(&fph->queues[i]);
 
 	if (custom) {
+		struct wait_bit_queue_entry __wbq_entry;
+		struct wait_queue_head *__wq_head;
+
 		/*
 		 * Only let prctl() wait / retry; don't unduly delay clone().
 		 */
 again:
-		wait_var_event(mm, futex_pivot_pending(mm));
+		__wq_head = __var_waitqueue(mm);
+		init_wait_var_entry(&__wbq_entry, mm, 0);
+		__wbq_entry.wq_entry.func = woken_wake_bit_function;
+		add_wait_queue(__wq_head, &__wbq_entry.wq_entry);
+
+		/*
+		 * add_wait_queue()		futex_ref_put()
+		 * MB (this)			MB (implied)
+		 * futex_pivot_pending()	wake_up_var()
+		 *                                waitqueue_active()
+		 *
+		 * Notably, it must not be possible to see
+		 * !futex_pivot_pending() && !waitqueue_active().
+		 */
+		smp_mb();
+
+		while (!futex_pivot_pending(mm) &&
+		       wait_woken(&__wbq_entry.wq_entry, TASK_UNINTERRUPTIBLE,
+				  MAX_SCHEDULE_TIMEOUT))
+			/* empty */;
+
+		remove_wait_queue(__wq_head, &__wbq_entry.wq_entry);
 	}
 
 	scoped_guard(mutex, &mm->futex.phash.lock) {

kernel/sched/wait.c

@@ -5,6 +5,7 @@
  * (C) 2004 Nadia Yvette Chambers, Oracle
  */
 #include "sched.h"
+#include <linux/wait_bit.h>
 
 void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key)
 {
@@ -463,3 +464,17 @@ int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sy
 	return default_wake_function(wq_entry, mode, sync, key);
 }
 EXPORT_SYMBOL(woken_wake_function);
+
+int woken_wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *arg)
+{
+	struct wait_bit_key *key = __var_wake_key(wq_entry, arg);
+	if (!key)
+		return 0;
+
+	/* Pairs with the smp_store_mb() in wait_woken(). */
+	smp_mb(); /* C */
+	wq_entry->flags |= WQ_FLAG_WOKEN;
+
+	return default_wake_function(wq_entry, mode, sync, key);
+}
+EXPORT_SYMBOL(woken_wake_bit_function);

kernel/sched/wait_bit.c

@@ -167,16 +167,24 @@ wait_queue_head_t *__var_waitqueue(void *p)
 }
 EXPORT_SYMBOL(__var_waitqueue);
 
-static int
-var_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode,
-		  int sync, void *arg)
+struct wait_bit_key *__var_wake_key(struct wait_queue_entry *wq_entry, void *arg)
 {
 	struct wait_bit_key *key = arg;
 	struct wait_bit_queue_entry *wbq_entry =
 		container_of(wq_entry, struct wait_bit_queue_entry, wq_entry);
 
 	if (wbq_entry->key.flags != key->flags ||
 	    wbq_entry->key.bit_nr != key->bit_nr)
+		return NULL;
+
+	return key;
+}
+
+static int var_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode,
+			     int sync, void *arg)
+{
+	struct wait_bit_key *key = __var_wake_key(wq_entry, arg);
+	if (!key)
 		return 0;
 
 	return autoremove_wake_function(wq_entry, mode, sync, key);