Automatically size the local hash based on the number of threads. The
logic tries to allocate between 16 and futex_hashsize (the default for
the system wide hash bucket) and uses 4 * number-of-threads.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/futex.h | 12 ------------
 kernel/fork.c         |  4 +---
 kernel/futex/core.c   | 25 ++++++++++++++++++++++---
 3 files changed, 23 insertions(+), 18 deletions(-)

diff --git a/include/linux/futex.h b/include/linux/futex.h
index 3ced01a9c5218..403b54526a081 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -87,13 +87,6 @@ static inline void futex_mm_init(struct mm_struct *mm)
 	mutex_init(&mm->futex_hash_lock);
 }
 
-static inline bool futex_hash_requires_allocation(void)
-{
-	if (current->mm->futex_hash_bucket)
-		return false;
-	return true;
-}
-
 #else
 static inline void futex_init_task(struct task_struct *tsk) { }
 static inline void futex_exit_recursive(struct task_struct *tsk) { }
@@ -116,11 +109,6 @@ static inline int futex_hash_allocate_default(void)
 static inline void futex_hash_free(struct mm_struct *mm) { }
 static inline void futex_mm_init(struct mm_struct *mm) { }
 
-static inline bool futex_hash_requires_allocation(void)
-{
-	return false;
-}
-
 #endif
 
 #endif
diff --git a/kernel/fork.c b/kernel/fork.c
index 95d38709fde10..7364fa5f2872a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2134,9 +2134,7 @@ static bool need_futex_hash_allocate_default(u64 clone_flags)
 {
 	if ((clone_flags & (CLONE_THREAD | CLONE_VM)) != (CLONE_THREAD | CLONE_VM))
 		return false;
-	if (!thread_group_empty(current))
-		return false;
-	return futex_hash_requires_allocation();
+	return true;
 }
 
 /*
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 44e16f033a4dd..95a177f0c5d68 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -1370,8 +1370,8 @@ static int futex_hash_allocate(unsigned int hash_slots)
 		hash_slots = 16;
 	if (hash_slots < 2)
 		hash_slots = 2;
-	if (hash_slots > 131072)
-		hash_slots = 131072;
+	if (hash_slots > futex_hashsize)
+		hash_slots = futex_hashsize;
 	if (!is_power_of_2(hash_slots))
 		hash_slots = rounddown_pow_of_two(hash_slots);
 
@@ -1412,7 +1412,26 @@ static int futex_hash_allocate(unsigned int hash_slots)
 
 int futex_hash_allocate_default(void)
 {
-	return futex_hash_allocate(0);
+	unsigned int threads, buckets, current_buckets = 0;
+	struct futex_hash_bucket_private *hb_p;
+
+	if (!current->mm)
+		return 0;
+
+	scoped_guard(rcu) {
+		threads = get_nr_threads(current);
+		hb_p = rcu_dereference(current->mm->futex_hash_bucket);
+		if (hb_p)
+			current_buckets = hb_p->hash_mask + 1;
+	}
+
+	buckets = roundup_pow_of_two(4 * threads);
+	buckets = max(buckets, 16);
+	buckets = min(buckets, futex_hashsize);
+	if (current_buckets >= buckets)
+		return 0;
+
+	return futex_hash_allocate(buckets);
 }
 
 static int futex_hash_get_slots(void)
-- 
2.45.2