Skip to contentSkip to conversation

percpu_counter: add percpu_counter_sum_all interface

PATCH Applied Shakeel Butt 2 participants 3 messages Nov 9, 2022

Subsystems (6)
lore
Share & tools
lore
#0 lore raw

PATCH v2 1/1 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.

---
Changes since v1:
- Only call percpu_counter_sum_all() if percpu_counter_sum() gives non-zero value in check_mm().

 include/linux/percpu_counter.h |  6 ++++++
 kernel/fork.c                  |  5 +++++
 lib/percpu_counter.c           | 29 +++++++++++++++++++++++------
 3 files changed, 34 insertions(+), 6 deletions(-)
include/linux/percpu_counter.h +6 -0
index bde6c4c1f405..a3aae8d57a42 100644
@@ -45,6 +45,7 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
 void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount,
 			      s32 batch);
 s64 __percpu_counter_sum(struct percpu_counter *fbc);
+s64 percpu_counter_sum_all(struct percpu_counter *fbc);
 int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
 void percpu_counter_sync(struct percpu_counter *fbc);
 
@@ -193,6 +194,11 @@ static inline s64 percpu_counter_sum(struct percpu_counter *fbc)
 	return percpu_counter_read(fbc);
 }
 
+static inline s64 percpu_counter_sum_all(struct percpu_counter *fbc)
+{
+	return percpu_counter_read(fbc);
+}
+
 static inline bool percpu_counter_initialized(struct percpu_counter *fbc)
 {
 	return true;
kernel/fork.c +5 -0
index 9c32f593ef11..9f7fe3541897 100644
@@ -758,6 +758,11 @@ static void check_mm(struct mm_struct *mm)
 	for (i = 0; i < NR_MM_COUNTERS; i++) {
 		long x = percpu_counter_sum(&mm->rss_stat[i]);
 
+		if (likely(!x))
+			continue;
+
+		/* Making sure this is not due to race with CPU offlining. */
+		x = percpu_counter_sum_all(&mm->rss_stat[i]);
 		if (unlikely(x))
 			pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n",
 				 mm, resident_page_types[i], x);
lib/percpu_counter.c +23 -6
index ed610b75dc32..42f729c8e56c 100644
@@ -117,11 +117,8 @@ void percpu_counter_sync(struct percpu_counter *fbc)
 }
 EXPORT_SYMBOL(percpu_counter_sync);
 
-/*
- * Add up all the per-cpu counts, return the result.  This is a more accurate
- * but much slower version of percpu_counter_read_positive()
- */
-s64 __percpu_counter_sum(struct percpu_counter *fbc)
+static s64 __percpu_counter_sum_mask(struct percpu_counter *fbc,
+			      const struct cpumask *cpu_mask)
 {
 	s64 ret;
 	int cpu;
@@ -129,15 +126,35 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
 
 	raw_spin_lock_irqsave(&fbc->lock, flags);
 	ret = fbc->count;
-	for_each_online_cpu(cpu) {
+	for_each_cpu(cpu, cpu_mask) {
 		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
 		ret += *pcount;
 	}
 	raw_spin_unlock_irqrestore(&fbc->lock, flags);
 	return ret;
 }
+
+/*
+ * Add up all the per-cpu counts, return the result.  This is a more accurate
+ * but much slower version of percpu_counter_read_positive()
+ */
+s64 __percpu_counter_sum(struct percpu_counter *fbc)
+{
+	return __percpu_counter_sum_mask(fbc, cpu_online_mask);
+}
 EXPORT_SYMBOL(__percpu_counter_sum);
 
+/*
+ * This is slower version of percpu_counter_sum as it traverses all possible
+ * cpus. Use this only in the cases where accurate data is needed in the
+ * presense of CPUs getting offlined.
+ */
+s64 percpu_counter_sum_all(struct percpu_counter *fbc)
+{
+	return __percpu_counter_sum_mask(fbc, cpu_possible_mask);
+}
+EXPORT_SYMBOL(percpu_counter_sum_all);
+
 int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
 			  struct lock_class_key *key)
 {
Signature · 1 line
2.38.1.431.g37b22c650d-goog
maintainer
#1 lore raw
Quoted 10 lines · On Wed, 9 Nov 2022 01:20:11 +0000 Shakeel Butt <[email protected]> wrote:

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.

LGTM.

What are the user-visible effects of this bug? Should we cc:stable? If so, can you identify a suitable Fixes:?

Thanks.

#2 lore raw
Quoted 14 lines · Andrew Morton
Quoted 10 lines · On Wed, 9 Nov 2022 01:20:11 +0000 Shakeel Butt <[email protected]> wrote:

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.

Quoted 5 lines

LGTM.

What are the user-visible effects of this bug? Should we cc:stable? If so, can you identify a suitable Fixes:?

The patch which exposed this is still in mm-unstable (converting rss stats in mm_struct into percpu_counter) and other percpu_counter users don't really need this new interface. So, there is no need for a cc:stable.

thanks,
Shakeel