1 files changed, 36 insertions, 81 deletions
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 5877974ece92..4bb587d5d34f 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -299,40 +299,6 @@ static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop)
 	spin_unlock_irq(&cgroup_rstat_lock);
 }
 
-/* see cgroup_rstat_flush() */
-static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
-	__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
-{
-	int cpu;
-
-	lockdep_assert_held(&cgroup_rstat_lock);
-
-	for_each_possible_cpu(cpu) {
-		struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
-
-		for (; pos; pos = pos->rstat_flush_next) {
-			struct cgroup_subsys_state *css;
-
-			cgroup_base_stat_flush(pos, cpu);
-			bpf_rstat_flush(pos, cgroup_parent(pos), cpu);
-
-			rcu_read_lock();
-			list_for_each_entry_rcu(css, &pos->rstat_css_list,
-						rstat_css_node)
-				css->ss->css_rstat_flush(css, cpu);
-			rcu_read_unlock();
-		}
-
-		/* play nice and yield if necessary */
-		if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) {
-			__cgroup_rstat_unlock(cgrp, cpu);
-			if (!cond_resched())
-				cpu_relax();
-			__cgroup_rstat_lock(cgrp, cpu);
-		}
-	}
-}
-
 /**
  * cgroup_rstat_flush - flush stats in @cgrp's subtree
  * @cgrp: target cgroup
@@ -348,38 +314,30 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
  */
 __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp)
 {
+	int cpu;
+
 	might_sleep();
+	for_each_possible_cpu(cpu) {
+		struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
 
-	__cgroup_rstat_lock(cgrp, -1);
-	cgroup_rstat_flush_locked(cgrp);
-	__cgroup_rstat_unlock(cgrp, -1);
-}
+		/* Reacquire for each CPU to avoid disabling IRQs too long */
+		__cgroup_rstat_lock(cgrp, cpu);
+		for (; pos; pos = pos->rstat_flush_next) {
+			struct cgroup_subsys_state *css;
 
-/**
- * cgroup_rstat_flush_hold - flush stats in @cgrp's subtree and hold
- * @cgrp: target cgroup
- *
- * Flush stats in @cgrp's subtree and prevent further flushes.  Must be
- * paired with cgroup_rstat_flush_release().
- *
- * This function may block.
- */
-void cgroup_rstat_flush_hold(struct cgroup *cgrp)
-	__acquires(&cgroup_rstat_lock)
-{
-	might_sleep();
-	__cgroup_rstat_lock(cgrp, -1);
-	cgroup_rstat_flush_locked(cgrp);
-}
+			cgroup_base_stat_flush(pos, cpu);
+			bpf_rstat_flush(pos, cgroup_parent(pos), cpu);
 
-/**
- * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold()
- * @cgrp: cgroup used by tracepoint
- */
-void cgroup_rstat_flush_release(struct cgroup *cgrp)
-	__releases(&cgroup_rstat_lock)
-{
-	__cgroup_rstat_unlock(cgrp, -1);
+			rcu_read_lock();
+			list_for_each_entry_rcu(css, &pos->rstat_css_list,
+						rstat_css_node)
+				css->ss->css_rstat_flush(css, cpu);
+			rcu_read_unlock();
+		}
+		__cgroup_rstat_unlock(cgrp, cpu);
+		if (!cond_resched())
+			cpu_relax();
+	}
 }
 
 int cgroup_rstat_init(struct cgroup *cgrp)
@@ -590,7 +548,6 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat)
 
 		cputime->sum_exec_runtime += user;
 		cputime->sum_exec_runtime += sys;
-		cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL];
 
 #ifdef CONFIG_SCHED_CORE
 		bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE];
@@ -613,36 +570,34 @@ static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat
 void cgroup_base_stat_cputime_show(struct seq_file *seq)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	u64 usage, utime, stime, ntime;
+	struct cgroup_base_stat bstat;
 
 	if (cgroup_parent(cgrp)) {
-		cgroup_rstat_flush_hold(cgrp);
-		usage = cgrp->bstat.cputime.sum_exec_runtime;
+		cgroup_rstat_flush(cgrp);
+		__cgroup_rstat_lock(cgrp, -1);
+		bstat = cgrp->bstat;
 		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
-			       &utime, &stime);
-		ntime = cgrp->bstat.ntime;
-		cgroup_rstat_flush_release(cgrp);
+			       &bstat.cputime.utime, &bstat.cputime.stime);
+		__cgroup_rstat_unlock(cgrp, -1);
 	} else {
-		/* cgrp->bstat of root is not actually used, reuse it */
-		root_cgroup_cputime(&cgrp->bstat);
-		usage = cgrp->bstat.cputime.sum_exec_runtime;
-		utime = cgrp->bstat.cputime.utime;
-		stime = cgrp->bstat.cputime.stime;
-		ntime = cgrp->bstat.ntime;
+		root_cgroup_cputime(&bstat);
 	}
 
-	do_div(usage, NSEC_PER_USEC);
-	do_div(utime, NSEC_PER_USEC);
-	do_div(stime, NSEC_PER_USEC);
-	do_div(ntime, NSEC_PER_USEC);
+	do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC);
+	do_div(bstat.cputime.utime, NSEC_PER_USEC);
+	do_div(bstat.cputime.stime, NSEC_PER_USEC);
+	do_div(bstat.ntime, NSEC_PER_USEC);
 
 	seq_printf(seq, "usage_usec %llu\n"
 			"user_usec %llu\n"
 			"system_usec %llu\n"
 			"nice_usec %llu\n",
-			usage, utime, stime, ntime);
+			bstat.cputime.sum_exec_runtime,
+			bstat.cputime.utime,
+			bstat.cputime.stime,
+			bstat.ntime);
 
-	cgroup_force_idle_show(seq, &cgrp->bstat);
+	cgroup_force_idle_show(seq, &bstat);
 }
 
 /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */