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".

Link: https://lkml.kernel.org/r/20221109012011.881058-1-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 34 insertions, 6 deletions

diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index bde6c4c1f405..a3aae8d57a42 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -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;
diff --git a/kernel/fork.c b/kernel/fork.c
index 0fef202434c3..1be4c4ab7f3e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -755,6 +755,11 @@ 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);
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index ed610b75dc32..42f729c8e56c 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -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)
 {