block: switch to per-cpu in-flight counters

Now when part_round_stats is gone, we can switch to per-cpu in-flight
counters.

We use the local-atomic type local_t, so that if part_inc_in_flight or
part_dec_in_flight is reentrantly called from an interrupt, the value will
be correct.

The other counters could be corrupted due to reentrant interrupt, but the
corruption only results in slight counter skew - the in_flight counter
must be exact, so it needs local_t.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 33 insertions, 10 deletions

diff --git a/block/genhd.c b/block/genhd.c
index cdf174d7d329..9827a2c05db7 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -50,9 +50,9 @@ void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
         if (queue_is_mq(q))
                 return;
 
-        atomic_inc(&part->in_flight[rw]);
+        part_stat_local_inc(part, in_flight[rw]);
         if (part->partno)
-                atomic_inc(&part_to_disk(part)->part0.in_flight[rw]);
+                part_stat_local_inc(&part_to_disk(part)->part0, in_flight[rw]);
 }
 
 void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
@@ -60,38 +60,61 @@ void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
         if (queue_is_mq(q))
                 return;
 
-        atomic_dec(&part->in_flight[rw]);
+        part_stat_local_dec(part, in_flight[rw]);
         if (part->partno)
-                atomic_dec(&part_to_disk(part)->part0.in_flight[rw]);
+                part_stat_local_dec(&part_to_disk(part)->part0, in_flight[rw]);
 }
 
 void part_in_flight(struct request_queue *q, struct hd_struct *part,
                     unsigned int inflight[2])
 {
+        int cpu;
+
         if (queue_is_mq(q)) {
                 blk_mq_in_flight(q, part, inflight);
                 return;
         }
 
-        inflight[0] = atomic_read(&part->in_flight[0]) +
-                        atomic_read(&part->in_flight[1]);
+        inflight[0] = 0;
+        for_each_possible_cpu(cpu) {
+                inflight[0] += part_stat_local_read_cpu(part, in_flight[0], cpu) +
+                               part_stat_local_read_cpu(part, in_flight[1], cpu);
+        }
+        if ((int)inflight[0] < 0)
+                inflight[0] = 0;
+
         if (part->partno) {
                 part = &part_to_disk(part)->part0;
-                inflight[1] = atomic_read(&part->in_flight[0]) +
-                                atomic_read(&part->in_flight[1]);
+                inflight[1] = 0;
+                for_each_possible_cpu(cpu) {
+                        inflight[1] += part_stat_local_read_cpu(part, in_flight[0], cpu) +
+                                       part_stat_local_read_cpu(part, in_flight[1], cpu);
+                }
+                if ((int)inflight[1] < 0)
+                        inflight[1] = 0;
         }
 }
 
 void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
                        unsigned int inflight[2])
 {
+        int cpu;
+
         if (queue_is_mq(q)) {
                 blk_mq_in_flight_rw(q, part, inflight);
                 return;
         }
 
-        inflight[0] = atomic_read(&part->in_flight[0]);
-        inflight[1] = atomic_read(&part->in_flight[1]);
+        inflight[0] = 0;
+        inflight[1] = 0;
+        for_each_possible_cpu(cpu) {
+                inflight[0] += part_stat_local_read_cpu(part, in_flight[0], cpu);
+                inflight[1] += part_stat_local_read_cpu(part, in_flight[1], cpu);
+        }
+        if ((int)inflight[0] < 0)
+                inflight[0] = 0;
+        if ((int)inflight[1] < 0)
+                inflight[1] = 0;
 }
 
 struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)