percpu_counter: add percpu_counter_sum_all interface

The percpu_counter is used for scenarios where performance is more important than the accuracy. For percpu_counter users, who want more accurate information in their slowpath, percpu_counter_sum is provided which traverses all the online CPUs to accumulate the data. The reason it only needs to traverse online CPUs is because percpu_counter does implement CPU offline callback which syncs the local data of the offlined CPU. However there is a small race window between the online CPUs traversal of percpu_counter_sum and the CPU offline callback. The offline callback has to traverse all the percpu_counters on the system to flush the CPU local data which can be a lot. During that time, the CPU which is going offline has already been published as offline to all the readers. So, as the offline callback is running, percpu_counter_sum can be called for one counter which has some state on the CPU going offline. Since percpu_counter_sum only traverses online CPUs, it will skip that specific CPU and the offline callback might not have flushed the state for that specific percpu_counter on that offlined CPU. Normally this is not an issue because percpu_counter users can deal with some inaccuracy for small time window. However a new user i.e. mm_struct on the cleanup path wants to check the exact state of the percpu_counter through check_mm(). For such users, this patch introduces percpu_counter_sum_all() which traverses all possible CPUs and it is used in fork.c:check_mm() to avoid the potential race. This issue is exposed by the later patch "mm: convert mm's rss stats into percpu_counter".

Shakeel Butt committed 4 years ago

Commit f6890541 parent f1a79413 files · +34 −6Browse files

Unified · Split

3 files

include/linux/percpu_counter.h +6 −0
kernel/fork.c +5 −0
lib/percpu_counter.c +23 −6

include/linux/percpu_counter.h+6−0

@@ -45,6 +45,7 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount); · 44 unmodified lines
45	45	void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount,
46	46	s32 batch);
47	47	s64 __percpu_counter_sum(struct percpu_counter *fbc);
	48	+s64 percpu_counter_sum_all(struct percpu_counter *fbc);
48	49	int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
49	50	void percpu_counter_sync(struct percpu_counter *fbc);
50	51
@@ -193,6 +194,11 @@ static inline s64 percpu_counter_sum(struct percpu_counter *fbc) · 142 unmodified lines
193	194	return percpu_counter_read(fbc);
194	195	}
195	196
	197	+static inline s64 percpu_counter_sum_all(struct percpu_counter *fbc)
	198	+{
	199	+ return percpu_counter_read(fbc);
	200	+}
	201	+
196	202	static inline bool percpu_counter_initialized(struct percpu_counter *fbc)
197	203	{
198	204	return true;

kernel/fork.c+5−0

@@ -755,6 +755,11 @@ static void check_mm(struct mm_struct *mm) · 754 unmodified lines
755	755	for (i = 0; i < NR_MM_COUNTERS; i++) {
756	756	long x = percpu_counter_sum(&mm->rss_stat[i]);
757	757
	758	+ if (likely(!x))
	759	+ continue;
	760	+
	761	+ /* Making sure this is not due to race with CPU offlining. */
	762	+ x = percpu_counter_sum_all(&mm->rss_stat[i]);
758	763	if (unlikely(x))
759	764	pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n",
760	765	mm, resident_page_types[i], x);

lib/percpu_counter.c+23−6

@@ -117,11 +117,8 @@ void percpu_counter_sync(struct percpu_counter *fbc) · 116 unmodified lines
117	117	}
118	118	EXPORT_SYMBOL(percpu_counter_sync);
119	119
120		−/*
121		− * Add up all the per-cpu counts, return the result. This is a more accurate
122		− * but much slower version of percpu_counter_read_positive()
123		− */
124		−s64 __percpu_counter_sum(struct percpu_counter *fbc)
	120	+static s64 __percpu_counter_sum_mask(struct percpu_counter *fbc,
	121	+ const struct cpumask *cpu_mask)
125	122	{
126	123	s64 ret;
127	124	int cpu;
@@ -129,15 +126,35 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc) · 1 unmodified line
129	126
130	127	raw_spin_lock_irqsave(&fbc->lock, flags);
131	128	ret = fbc->count;
132		− for_each_online_cpu(cpu) {
	129	+ for_each_cpu(cpu, cpu_mask) {
133	130	s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
134	131	ret += *pcount;
135	132	}
136	133	raw_spin_unlock_irqrestore(&fbc->lock, flags);
137	134	return ret;
138	135	}
	136	+
	137	+/*
	138	+ * Add up all the per-cpu counts, return the result. This is a more accurate
	139	+ * but much slower version of percpu_counter_read_positive()
	140	+ */
	141	+s64 __percpu_counter_sum(struct percpu_counter *fbc)
	142	+{
	143	+ return __percpu_counter_sum_mask(fbc, cpu_online_mask);
	144	+}
139	145	EXPORT_SYMBOL(__percpu_counter_sum);
140	146
	147	+/*
	148	+ * This is slower version of percpu_counter_sum as it traverses all possible
	149	+ * cpus. Use this only in the cases where accurate data is needed in the
	150	+ * presense of CPUs getting offlined.
	151	+ */
	152	+s64 percpu_counter_sum_all(struct percpu_counter *fbc)
	153	+{
	154	+ return __percpu_counter_sum_mask(fbc, cpu_possible_mask);
	155	+}
	156	+EXPORT_SYMBOL(percpu_counter_sum_all);
	157	+
141	158	int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
142	159	struct lock_class_key *key)
143	160	{