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, 36 insertions, 0 deletions

diff --git a/tools/perf/util/cacheline.h b/tools/perf/util/cacheline.h
new file mode 100644
index 000000000..fe6d5b60a
--- /dev/null
+++ b/tools/perf/util/cacheline.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef PERF_CACHELINE_H
+#define PERF_CACHELINE_H
+
+#include <linux/compiler.h>
+
+int __pure cacheline_size(void);
+
+
+/*
+ * Some architectures have 'Adjacent Cacheline Prefetch' feature,
+ * which performs like the cacheline size being doubled.
+ */
+static inline u64 cl_address(u64 address, bool double_cl)
+{
+	u64 size = cacheline_size();
+
+	if (double_cl)
+		size *= 2;
+
+	/* return the cacheline of the address */
+	return (address & ~(size - 1));
+}
+
+static inline u64 cl_offset(u64 address, bool double_cl)
+{
+	u64 size = cacheline_size();
+
+	if (double_cl)
+		size *= 2;
+
+	/* return the offset inside cacheline */
+	return (address & (size - 1));
+}
+
+#endif // PERF_CACHELINE_H