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>

4 files changed, 203 insertions, 0 deletions

diff --git a/tools/dma/.gitignore b/tools/dma/.gitignore
new file mode 100644
index 000000000..94b68cf41
--- /dev/null
+++ b/tools/dma/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+dma_map_benchmark
+include/linux/map_benchmark.h
diff --git a/tools/dma/Makefile b/tools/dma/Makefile
new file mode 100644
index 000000000..e4abf37bf
--- /dev/null
+++ b/tools/dma/Makefile
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: GPL-2.0
+include ../scripts/Makefile.include
+
+bindir ?= /usr/bin
+
+# This will work when dma is built in tools env. where srctree
+# isn't set and when invoked from selftests build, where srctree
+# is set to ".". building_out_of_srctree is undefined for in srctree
+# builds
+ifndef building_out_of_srctree
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+# Do not use make's built-in rules
+# (this improves performance and avoids hard-to-debug behaviour);
+MAKEFLAGS += -r
+
+override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
+
+ALL_TARGETS := dma_map_benchmark
+ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
+
+all: $(ALL_PROGRAMS)
+
+export srctree OUTPUT CC LD CFLAGS
+include $(srctree)/tools/build/Makefile.include
+
+#
+# We need the following to be outside of kernel tree
+#
+$(OUTPUT)include/linux/map_benchmark.h: ../../include/uapi/linux/map_benchmark.h
+	mkdir -p $(OUTPUT)include/linux 2>&1 || true
+	ln -sf $(CURDIR)/../../include/uapi/linux/map_benchmark.h $@
+
+prepare: $(OUTPUT)include/linux/map_benchmark.h
+
+FORCE:
+
+DMA_MAP_BENCHMARK = dma_map_benchmark
+$(DMA_MAP_BENCHMARK): prepare FORCE
+	$(CC) $(CFLAGS) $(DMA_MAP_BENCHMARK).c -o $(DMA_MAP_BENCHMARK)
+
+clean:
+	rm -f $(ALL_PROGRAMS)
+	rm -rf $(OUTPUT)include
+	find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete
+
+install: $(ALL_PROGRAMS)
+	install -d -m 755 $(DESTDIR)$(bindir);		\
+	for program in $(ALL_PROGRAMS); do		\
+		install $$program $(DESTDIR)$(bindir);	\
+	done
+
+.PHONY: all install clean prepare FORCE
diff --git a/tools/dma/config b/tools/dma/config
new file mode 100644
index 000000000..6102ee3c4
--- /dev/null
+++ b/tools/dma/config
@@ -0,0 +1 @@
+CONFIG_DMA_MAP_BENCHMARK=y
diff --git a/tools/dma/dma_map_benchmark.c b/tools/dma/dma_map_benchmark.c
new file mode 100644
index 000000000..eab0ac611
--- /dev/null
+++ b/tools/dma/dma_map_benchmark.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 HiSilicon Limited.
+ */
+
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <linux/map_benchmark.h>
+
+#define NSEC_PER_MSEC	1000000L
+
+static char *directions[] = {
+	"BIDIRECTIONAL",
+	"TO_DEVICE",
+	"FROM_DEVICE",
+};
+
+static char *mode[] = {
+	"SINGLE_MODE",
+	"SG_MODE",
+};
+
+int main(int argc, char **argv)
+{
+	struct map_benchmark map;
+	int fd, opt;
+	/* default single thread, run 20 seconds on NUMA_NO_NODE */
+	int threads = 1, seconds = 20, node = -1;
+	/* default single map mode */
+	int map_mode = DMA_MAP_BENCH_SINGLE_MODE;
+	/* default dma mask 32bit, bidirectional DMA */
+	int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL;
+	/* default granule 1 PAGESIZE */
+	int granule = 1;
+
+	int cmd = DMA_MAP_BENCHMARK;
+
+	while ((opt = getopt(argc, argv, "t:s:n:b:d:x:g:m:")) != -1) {
+		switch (opt) {
+		case 't':
+			threads = atoi(optarg);
+			break;
+		case 's':
+			seconds = atoi(optarg);
+			break;
+		case 'n':
+			node = atoi(optarg);
+			break;
+		case 'b':
+			bits = atoi(optarg);
+			break;
+		case 'd':
+			dir = atoi(optarg);
+			break;
+		case 'x':
+			xdelay = atoi(optarg);
+			break;
+		case 'g':
+			granule = atoi(optarg);
+			break;
+		case 'm':
+			map_mode = atoi(optarg);
+			break;
+		default:
+			return -1;
+		}
+	}
+
+	if (map_mode < 0 || map_mode >= DMA_MAP_BENCH_MODE_MAX) {
+		fprintf(stderr, "invalid map mode, SINGLE_MODE:%d, SG_MODE: %d\n",
+			DMA_MAP_BENCH_SINGLE_MODE, DMA_MAP_BENCH_SG_MODE);
+		exit(1);
+	}
+
+	if (threads <= 0 || threads > DMA_MAP_MAX_THREADS) {
+		fprintf(stderr, "invalid number of threads, must be in 1-%d\n",
+			DMA_MAP_MAX_THREADS);
+		exit(1);
+	}
+
+	if (seconds <= 0 || seconds > DMA_MAP_MAX_SECONDS) {
+		fprintf(stderr, "invalid number of seconds, must be in 1-%d\n",
+			DMA_MAP_MAX_SECONDS);
+		exit(1);
+	}
+
+	if (xdelay < 0 || xdelay > DMA_MAP_MAX_TRANS_DELAY) {
+		fprintf(stderr, "invalid transmit delay, must be in 0-%ld\n",
+			DMA_MAP_MAX_TRANS_DELAY);
+		exit(1);
+	}
+
+	/* suppose the mininum DMA zone is 1MB in the world */
+	if (bits < 20 || bits > 64) {
+		fprintf(stderr, "invalid dma mask bit, must be in 20-64\n");
+		exit(1);
+	}
+
+	if (dir != DMA_MAP_BIDIRECTIONAL && dir != DMA_MAP_TO_DEVICE &&
+			dir != DMA_MAP_FROM_DEVICE) {
+		fprintf(stderr, "invalid dma direction\n");
+		exit(1);
+	}
+
+	if (granule < 1 || granule > 1024) {
+		fprintf(stderr, "invalid granule size\n");
+		exit(1);
+	}
+
+	fd = open("/sys/kernel/debug/dma_map_benchmark", O_RDWR);
+	if (fd == -1) {
+		perror("open");
+		exit(1);
+	}
+
+	memset(&map, 0, sizeof(map));
+	map.seconds = seconds;
+	map.threads = threads;
+	map.node = node;
+	map.dma_bits = bits;
+	map.dma_dir = dir;
+	map.dma_trans_ns = xdelay;
+	map.granule = granule;
+	map.map_mode = map_mode;
+
+	if (ioctl(fd, cmd, &map)) {
+		perror("ioctl");
+		exit(1);
+	}
+
+	printf("dma mapping benchmark(%s): threads:%d seconds:%d node:%d dir:%s granule:%d\n",
+			mode[map_mode], threads, seconds, node, directions[dir], granule);
+	printf("average map latency(us):%.1f standard deviation:%.1f\n",
+			map.avg_map_100ns/10.0, map.map_stddev/10.0);
+	printf("average unmap latency(us):%.1f standard deviation:%.1f\n",
+			map.avg_unmap_100ns/10.0, map.unmap_stddev/10.0);
+
+	return 0;
+}