scftorture: Count single_rpc offline failures in statistics outputgrafted

scf_torture_stats_print() aggregates each invoker thread's counters
into a local scf_statistics structure before printing, but the
n_single_rpc_ofl field is missing from the aggregation loop.  As a
result, the "single_rpc_ofl" value printed in the statistics line is
always zero, even when smp_call_function_single() invocations for the
RPC test have failed due to offline CPUs and been counted by the
invoker threads.

Add the missing accumulation so that the printed value reflects the
actual counts.

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Paul E. McKenney <paulmck@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