Merge tag 'xfs-6.3-fixes-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs percpu counter fixes from Darrick Wong:
 "We discovered a filesystem summary counter corruption problem that was
  traced to cpu hot-remove racing with the call to percpu_counter_sum
  that sets the free block count in the superblock when writing it to
  disk. The root cause is that percpu_counter_sum doesn't cull from
  dying cpus and hence misses those counter values if the cpu shutdown
  hooks have not yet run to merge the values.

  I'm hoping this is a fairly painless fix to the problem, since the
  dying cpu mask should generally be empty. It's been in for-next for a
  week without any complaints from the bots.

   - Fix a race in the percpu counters summation code where the
     summation failed to add in the values for any CPUs that were dying
     but not yet dead. This fixes some minor discrepancies and incorrect
     assertions when running generic/650"

* tag 'xfs-6.3-fixes-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  pcpcntr: remove percpu_counter_sum_all()
  fork: remove use of percpu_counter_sum_all
  pcpcntrs: fix dying cpu summation race
  cpumask: introduce for_each_cpu_or

1 files changed, 14 insertions, 23 deletions

diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index dba56c5c1837..5004463c4f9f 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -122,8 +122,19 @@ void percpu_counter_sync(struct percpu_counter *fbc)
 }
 EXPORT_SYMBOL(percpu_counter_sync);
 
-static s64 __percpu_counter_sum_mask(struct percpu_counter *fbc,
-			      const struct cpumask *cpu_mask)
+/*
+ * Add up all the per-cpu counts, return the result.  This is a more accurate
+ * but much slower version of percpu_counter_read_positive().
+ *
+ * We use the cpu mask of (cpu_online_mask | cpu_dying_mask) to capture sums
+ * from CPUs that are in the process of being taken offline. Dying cpus have
+ * been removed from the online mask, but may not have had the hotplug dead
+ * notifier called to fold the percpu count back into the global counter sum.
+ * By including dying CPUs in the iteration mask, we avoid this race condition
+ * so __percpu_counter_sum() just does the right thing when CPUs are being taken
+ * offline.
+ */
+s64 __percpu_counter_sum(struct percpu_counter *fbc)
 {
 	s64 ret;
 	int cpu;
@@ -131,35 +142,15 @@ static s64 __percpu_counter_sum_mask(struct percpu_counter *fbc,
 
 	raw_spin_lock_irqsave(&fbc->lock, flags);
 	ret = fbc->count;
-	for_each_cpu(cpu, cpu_mask) {
+	for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_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)
 {