workqueue: skip the node_nr_active update for non-unbound workqueuesgrafted

apply_wqattrs_commit() updates node_nr_active->max unconditionally.
wq->node_nr_active[] is only allocated for unbound workqueues, so guard
the call before per-cpu workqueues start using this path.

No functional change: only unbound workqueues reach apply_wqattrs_*()
today.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 42 insertions, 0 deletions

diff --git a/arch/loongarch/lib/delay.c b/arch/loongarch/lib/delay.c
new file mode 100644
index 000000000..831d4761f
--- /dev/null
+++ b/arch/loongarch/lib/delay.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/smp.h>
+#include <linux/timex.h>
+
+#include <asm/processor.h>
+
+void __delay(unsigned long cycles)
+{
+	u64 t0 = get_cycles();
+
+	while ((unsigned long)(get_cycles() - t0) < cycles)
+		cpu_relax();
+}
+EXPORT_SYMBOL(__delay);
+
+/*
+ * Division by multiplication: you don't have to worry about
+ * loss of precision.
+ *
+ * Use only for very small delays ( < 1 msec).	Should probably use a
+ * lookup table, really, as the multiplications take much too long with
+ * short delays.  This is a "reasonable" implementation, though (and the
+ * first constant multiplications gets optimized away if the delay is
+ * a constant)
+ */
+
+void __udelay(unsigned long us)
+{
+	__delay((us * 0x000010c7ull * HZ * lpj_fine) >> 32);
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long ns)
+{
+	__delay((ns * 0x00000005ull * HZ * lpj_fine) >> 32);
+}
+EXPORT_SYMBOL(__ndelay);