X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=kernel%2Fkernel%2Fsched%2Ffair.c;fp=kernel%2Fkernel%2Fsched%2Ffair.c;h=cf0a1adba6c6be79f2b005ac1bdd3f6a061ba07b;hb=52f993b8e89487ec9ee15a7fb4979e0f09a45b27;hp=8c71e627b5f29c82900d0200b1d513860789dd96;hpb=c189ccac5702322ed843fe17057035b7222a59b6;p=kvmfornfv.git

diff --git a/kernel/kernel/sched/fair.c b/kernel/kernel/sched/fair.c
index 8c71e627b..cf0a1adba 100644
--- a/kernel/kernel/sched/fair.c
+++ b/kernel/kernel/sched/fair.c
@@ -687,8 +687,6 @@ void init_entity_runnable_average(struct sched_entity *se)
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
 
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
-static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
 #else
 void init_entity_runnable_average(struct sched_entity *se)
 {
@@ -1193,8 +1191,6 @@ static void task_numa_assign(struct task_numa_env *env,
 {
 	if (env->best_task)
 		put_task_struct(env->best_task);
-	if (p)
-		get_task_struct(p);
 
 	env->best_task = p;
 	env->best_imp = imp;
@@ -1262,20 +1258,30 @@ static void task_numa_compare(struct task_numa_env *env,
 	long imp = env->p->numa_group ? groupimp : taskimp;
 	long moveimp = imp;
 	int dist = env->dist;
+	bool assigned = false;
 
 	rcu_read_lock();
 
 	raw_spin_lock_irq(&dst_rq->lock);
 	cur = dst_rq->curr;
 	/*
-	 * No need to move the exiting task, and this ensures that ->curr
-	 * wasn't reaped and thus get_task_struct() in task_numa_assign()
-	 * is safe under RCU read lock.
-	 * Note that rcu_read_lock() itself can't protect from the final
-	 * put_task_struct() after the last schedule().
+	 * No need to move the exiting task or idle task.
 	 */
 	if ((cur->flags & PF_EXITING) || is_idle_task(cur))
 		cur = NULL;
+	else {
+		/*
+		 * The task_struct must be protected here to protect the
+		 * p->numa_faults access in the task_weight since the
+		 * numa_faults could already be freed in the following path:
+		 * finish_task_switch()
+		 *     --> put_task_struct()
+		 *         --> __put_task_struct()
+		 *             --> task_numa_free()
+		 */
+		get_task_struct(cur);
+	}
+
 	raw_spin_unlock_irq(&dst_rq->lock);
 
 	/*
@@ -1359,6 +1365,7 @@ balance:
 		 */
 		if (!load_too_imbalanced(src_load, dst_load, env)) {
 			imp = moveimp - 1;
+			put_task_struct(cur);
 			cur = NULL;
 			goto assign;
 		}
@@ -1384,9 +1391,16 @@ balance:
 		env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
 
 assign:
+	assigned = true;
 	task_numa_assign(env, cur, imp);
 unlock:
 	rcu_read_unlock();
+	/*
+	 * The dst_rq->curr isn't assigned. The protection for task_struct is
+	 * finished.
+	 */
+	if (cur && !assigned)
+		put_task_struct(cur);
 }
 
 static void task_numa_find_cpu(struct task_numa_env *env,
@@ -2682,6 +2696,23 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 
 static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
 
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do {				\
+	typeof(_ptr) ptr = (_ptr);				\
+	typeof(*ptr) val = (_val);				\
+	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
+	res = var - val;					\
+	if (res > var)						\
+		res = 0;					\
+	WRITE_ONCE(*ptr, res);					\
+} while (0)
+
 /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
 static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 {
@@ -2690,15 +2721,15 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 
 	if (atomic_long_read(&cfs_rq->removed_load_avg)) {
 		s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
-		sa->load_avg = max_t(long, sa->load_avg - r, 0);
-		sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+		sub_positive(&sa->load_avg, r);
+		sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
 		removed = 1;
 	}
 
 	if (atomic_long_read(&cfs_rq->removed_util_avg)) {
 		long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
-		sa->util_avg = max_t(long, sa->util_avg - r, 0);
-		sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+		sub_positive(&sa->util_avg, r);
+		sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
 	}
 
 	decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -2764,10 +2795,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 			  &se->avg, se->on_rq * scale_load_down(se->load.weight),
 			  cfs_rq->curr == se, NULL);
 
-	cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
-	cfs_rq->avg.load_sum = max_t(s64,  cfs_rq->avg.load_sum - se->avg.load_sum, 0);
-	cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
-	cfs_rq->avg.util_sum = max_t(s32,  cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+	sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
+	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
 }
 
 /* Add the load generated by se into cfs_rq's load average */
@@ -4577,19 +4608,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 		return wl;
 
 	for_each_sched_entity(se) {
-		long w, W;
+		struct cfs_rq *cfs_rq = se->my_q;
+		long W, w = cfs_rq_load_avg(cfs_rq);
 
-		tg = se->my_q->tg;
+		tg = cfs_rq->tg;
 
 		/*
 		 * W = @wg + \Sum rw_j
 		 */
-		W = wg + calc_tg_weight(tg, se->my_q);
+		W = wg + atomic_long_read(&tg->load_avg);
+
+		/* Ensure \Sum rw_j >= rw_i */
+		W -= cfs_rq->tg_load_avg_contrib;
+		W += w;
 
 		/*
 		 * w = rw_i + @wl
 		 */
-		w = cfs_rq_load_avg(se->my_q) + wl;
+		w += wl;
 
 		/*
 		 * wl = S * s'_i; see (2)