percpu_counter: add a cmpxchg-based _add_batch variant

Interrupt disable/enable trips are quite expensive on x86-64 compared to a
mere cmpxchg (note: no lock prefix!) and percpu counters are used quite
often.

With this change I get a bump of 1% ops/s for negative path lookups,
plugged into will-it-scale:

void testcase(unsigned long long *iterations, unsigned long nr)
{
        while (1) {
                int fd = open("/tmp/nonexistent", O_RDONLY);
                assert(fd == -1);

                (*iterations)++;
        }
}

The win would be higher if it was not for other slowdowns, but one has
to start somewhere.

Link: https://lkml.kernel.org/r/20240528204257.434817-1-mjguzik@gmail.com
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Dennis Zhou <dennis@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 44dd133594d4d6a005321d27acbf76f9aa1d4c95..51bc5246986d089bcbafac7e4fe4184c4e16dcea 100644 (file)
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -73,17 +73,50 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
 EXPORT_SYMBOL(percpu_counter_set);
 
 /*
- * local_irq_save() is needed to make the function irq safe:
- * - The slow path would be ok as protected by an irq-safe spinlock.
- * - this_cpu_add would be ok as it is irq-safe by definition.
- * But:
- * The decision slow path/fast path and the actual update must be atomic, too.
+ * Add to a counter while respecting batch size.
+ *
+ * There are 2 implementations, both dealing with the following problem:
+ *
+ * The decision slow path/fast path and the actual update must be atomic.
  * Otherwise a call in process context could check the current values and
  * decide that the fast path can be used. If now an interrupt occurs before
  * the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters),
  * then the this_cpu_add() that is executed after the interrupt has completed
  * can produce values larger than "batch" or even overflows.
  */
+#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
+/*
+ * Safety against interrupts is achieved in 2 ways:
+ * 1. the fast path uses local cmpxchg (note: no lock prefix)
+ * 2. the slow path operates with interrupts disabled
+ */
+void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
+{
+       s64 count;
+       unsigned long flags;
+
+       count = this_cpu_read(*fbc->counters);
+       do {
+               if (unlikely(abs(count + amount) >= batch)) {
+                       raw_spin_lock_irqsave(&fbc->lock, flags);
+                       /*
+                        * Note: by now we might have migrated to another CPU
+                        * or the value might have changed.
+                        */
+                       count = __this_cpu_read(*fbc->counters);
+                       fbc->count += count + amount;
+                       __this_cpu_sub(*fbc->counters, count);
+                       raw_spin_unlock_irqrestore(&fbc->lock, flags);
+                       return;
+               }
+       } while (!this_cpu_try_cmpxchg(*fbc->counters, &count, count + amount));
+}
+#else
+/*
+ * local_irq_save() is used to make the function irq safe:
+ * - The slow path would be ok as protected by an irq-safe spinlock.
+ * - this_cpu_add would be ok as it is irq-safe by definition.
+ */
 void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 {
        s64 count;
@@ -101,6 +134,7 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
        }
        local_irq_restore(flags);
 }
+#endif
 EXPORT_SYMBOL(percpu_counter_add_batch);
 
 /*