sched/mmcid: Convert mm CID mask to a bitmap

This is truly a bitmap and just conveniently uses a cpumask because the
maximum size of the bitmap is nr_cpu_ids.

But that prevents to do searches for a zero bit in a limited range, which
is helpful to provide an efficient mechanism to consolidate the CID space
when the number of users decreases.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
Link: https://patch.msgid.link/20251119172549.642866767@linutronix.de

Author: KAGA-KOKO

include/linux/mm_types.h

@@ -1342,13 +1342,13 @@ static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm)
 }
 
 /* Accessor for struct mm_struct's cidmask. */
-static inline cpumask_t *mm_cidmask(struct mm_struct *mm)
+static inline unsigned long *mm_cidmask(struct mm_struct *mm)
 {
 	unsigned long cid_bitmap = (unsigned long)mm_cpus_allowed(mm);
 
 	/* Skip mm_cpus_allowed */
 	cid_bitmap += cpumask_size();
-	return (struct cpumask *)cid_bitmap;
+	return (unsigned long *)cid_bitmap;
 }
 
 static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
@@ -1363,7 +1363,7 @@ static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
 	mm->mm_cid.nr_cpus_allowed = p->nr_cpus_allowed;
 	raw_spin_lock_init(&mm->mm_cid.lock);
 	cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask);
-	cpumask_clear(mm_cidmask(mm));
+	bitmap_zero(mm_cidmask(mm), num_possible_cpus());
 }
 
 static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct *p)
@@ -1384,7 +1384,8 @@ static inline void mm_destroy_cid(struct mm_struct *mm)
 
 static inline unsigned int mm_cid_size(void)
 {
-	return 2 * cpumask_size();	/* mm_cpus_allowed(), mm_cidmask(). */
+	/* mm_cpus_allowed(), mm_cidmask(). */
+	return cpumask_size() + bitmap_size(num_possible_cpus());
 }
 
 #else /* CONFIG_SCHED_MM_CID */

kernel/sched/core.c

@@ -10402,7 +10402,7 @@ void sched_mm_cid_exit_signals(struct task_struct *t)
 	guard(preempt)();
 	t->mm_cid.active = 0;
 	if (t->mm_cid.cid != MM_CID_UNSET) {
-		cpumask_clear_cpu(t->mm_cid.cid, mm_cidmask(mm));
+		clear_bit(t->mm_cid.cid, mm_cidmask(mm));
 		t->mm_cid.cid = MM_CID_UNSET;
 	}
 }

kernel/sched/sched.h

@@ -3559,7 +3559,7 @@ static inline bool __mm_cid_get(struct task_struct *t, unsigned int cid, unsigne
 
 	if (cid >= max_cids)
 		return false;
-	if (cpumask_test_and_set_cpu(cid, mm_cidmask(mm)))
+	if (test_and_set_bit(cid, mm_cidmask(mm)))
 		return false;
 	t->mm_cid.cid = t->mm_cid.last_cid = cid;
 	__this_cpu_write(mm->mm_cid.pcpu->cid, cid);
@@ -3582,7 +3582,7 @@ static inline bool mm_cid_get(struct task_struct *t)
 		return true;
 
 	/* Try the first zero bit in the cidmask. */
-	return __mm_cid_get(t, cpumask_first_zero(mm_cidmask(mm)), max_cids);
+	return __mm_cid_get(t, find_first_zero_bit(mm_cidmask(mm), num_possible_cpus()), max_cids);
 }
 
 static inline void mm_cid_select(struct task_struct *t)
@@ -3603,7 +3603,7 @@ static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *n
 {
 	if (prev->mm_cid.active) {
 		if (prev->mm_cid.cid != MM_CID_UNSET)
-			cpumask_clear_cpu(prev->mm_cid.cid, mm_cidmask(prev->mm));
+			clear_bit(prev->mm_cid.cid, mm_cidmask(prev->mm));
 		prev->mm_cid.cid = MM_CID_UNSET;
 	}