+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2022 HiSilicon Limited.
- */
-
-#ifndef _KERNEL_DMA_BENCHMARK_H
-#define _KERNEL_DMA_BENCHMARK_H
-
-#define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark)
-#define DMA_MAP_MAX_THREADS 1024
-#define DMA_MAP_MAX_SECONDS 300
-#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC)
-
-#define DMA_MAP_BIDIRECTIONAL 0
-#define DMA_MAP_TO_DEVICE 1
-#define DMA_MAP_FROM_DEVICE 2
-
-struct map_benchmark {
- __u64 avg_map_100ns; /* average map latency in 100ns */
- __u64 map_stddev; /* standard deviation of map latency */
- __u64 avg_unmap_100ns; /* as above */
- __u64 unmap_stddev;
- __u32 threads; /* how many threads will do map/unmap in parallel */
- __u32 seconds; /* how long the test will last */
- __s32 node; /* which numa node this benchmark will run on */
- __u32 dma_bits; /* DMA addressing capability */
- __u32 dma_dir; /* DMA data direction */
- __u32 dma_trans_ns; /* time for DMA transmission in ns */
- __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */
- __u8 expansion[76]; /* For future use */
-};
-#endif /* _KERNEL_DMA_BENCHMARK_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2022-2025 HiSilicon Limited.
+ */
+
+#ifndef _UAPI_DMA_BENCHMARK_H
+#define _UAPI_DMA_BENCHMARK_H
+
+#include <linux/types.h>
+
+#define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark)
+#define DMA_MAP_MAX_THREADS 1024
+#define DMA_MAP_MAX_SECONDS 300
+#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC)
+
+#define DMA_MAP_BIDIRECTIONAL 0
+#define DMA_MAP_TO_DEVICE 1
+#define DMA_MAP_FROM_DEVICE 2
+
+struct map_benchmark {
+ __u64 avg_map_100ns; /* average map latency in 100ns */
+ __u64 map_stddev; /* standard deviation of map latency */
+ __u64 avg_unmap_100ns; /* as above */
+ __u64 unmap_stddev;
+ __u32 threads; /* how many threads will do map/unmap in parallel */
+ __u32 seconds; /* how long the test will last */
+ __s32 node; /* which numa node this benchmark will run on */
+ __u32 dma_bits; /* DMA addressing capability */
+ __u32 dma_dir; /* DMA data direction */
+ __u32 dma_trans_ns; /* time for DMA transmission in ns */
+ __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */
+ __u8 expansion[76]; /* For future use */
+};
+
+#endif /* _UAPI_DMA_BENCHMARK_H */
#include <linux/dma-mapping.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
-#include <linux/map_benchmark.h>
#include <linux/math64.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/timekeeping.h>
+#include <uapi/linux/map_benchmark.h>
struct map_benchmark_data {
struct map_benchmark bparam;
@echo ' counter - counter tools'
@echo ' cpupower - a tool for all things x86 CPU power'
@echo ' debugging - tools for debugging'
+ @echo ' dma - tools for DMA mapping'
@echo ' firewire - the userspace part of nosy, an IEEE-1394 traffic sniffer'
@echo ' firmware - Firmware tools'
@echo ' freefall - laptop accelerometer program for disk protection'
cpupower: FORCE
$(call descend,power/$@)
-counter firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi firmware debugging tracing: FORCE
+counter dma firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi firmware debugging tracing: FORCE
$(call descend,$@)
bpf/%: FORCE
ynl: FORCE
$(call descend,net/ynl)
-all: acpi counter cpupower gpio hv firewire \
+all: acpi counter cpupower dma gpio hv firewire \
perf selftests bootconfig spi turbostat usb \
virtio mm bpf x86_energy_perf_policy \
tmon freefall iio objtool kvm_stat wmi \
cpupower_install:
$(call descend,power/$(@:_install=),install)
-counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install debugging_install tracing_install:
+counter_install dma_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install debugging_install tracing_install:
$(call descend,$(@:_install=),install)
selftests_install:
ynl_install:
$(call descend,net/$(@:_install=),install)
-install: acpi_install counter_install cpupower_install gpio_install \
+install: acpi_install counter_install cpupower_install dma_install gpio_install \
hv_install firewire_install iio_install \
perf_install selftests_install turbostat_install usb_install \
virtio_install mm_install bpf_install x86_energy_perf_policy_install \
cpupower_clean:
$(call descend,power/cpupower,clean)
-counter_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean mm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean firmware_clean debugging_clean tracing_clean:
+counter_clean dma_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean mm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean firmware_clean debugging_clean tracing_clean:
$(call descend,$(@:_clean=),clean)
libapi_clean:
ynl_clean:
$(call descend,net/$(@:_clean=),clean)
-clean: acpi_clean counter_clean cpupower_clean hv_clean firewire_clean \
+clean: acpi_clean counter_clean cpupower_clean dma_clean hv_clean firewire_clean \
perf_clean selftests_clean turbostat_clean bootconfig_clean spi_clean usb_clean virtio_clean \
mm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
freefall_clean build_clean libbpf_clean libsubcmd_clean \
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0-only
+dma_map_benchmark
+include/linux/map_benchmark.h
--- /dev/null
+# 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
--- /dev/null
+CONFIG_DMA_MAP_BENCHMARK=y
--- /dev/null
+// 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",
+};
+
+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 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:")) != -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;
+ default:
+ return -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;
+
+ if (ioctl(fd, cmd, &map)) {
+ perror("ioctl");
+ exit(1);
+ }
+
+ printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule: %d\n",
+ threads, seconds, node, dir[directions], 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;
+}
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -I../../../../usr/include/
-CFLAGS += -I../../../../include/
-
-TEST_GEN_PROGS := dma_map_benchmark
-
-include ../lib.mk
+++ /dev/null
-CONFIG_DMA_MAP_BENCHMARK=y
+++ /dev/null
-// 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/types.h>
-#include <linux/map_benchmark.h>
-
-#define NSEC_PER_MSEC 1000000L
-
-static char *directions[] = {
- "BIDIRECTIONAL",
- "TO_DEVICE",
- "FROM_DEVICE",
-};
-
-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 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:")) != -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;
- default:
- return -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;
-
- if (ioctl(fd, cmd, &map)) {
- perror("ioctl");
- exit(1);
- }
-
- printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule: %d\n",
- threads, seconds, node, dir[directions], 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;
-}
projects / linux-2.6-microblaze.git / commitdiff