linux/kernel/dma/map_benchmark.c

376 lines
9.3 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2020 Hisilicon Limited.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/debugfs.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/kernel.h>
#include <linux/kthread.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>
#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 */
__u8 expansion[80]; /* For future use */
};
struct map_benchmark_data {
struct map_benchmark bparam;
struct device *dev;
struct dentry *debugfs;
enum dma_data_direction dir;
atomic64_t sum_map_100ns;
atomic64_t sum_unmap_100ns;
atomic64_t sum_sq_map;
atomic64_t sum_sq_unmap;
atomic64_t loops;
};
static int map_benchmark_thread(void *data)
{
void *buf;
dma_addr_t dma_addr;
struct map_benchmark_data *map = data;
int ret = 0;
buf = (void *)__get_free_page(GFP_KERNEL);
if (!buf)
return -ENOMEM;
while (!kthread_should_stop()) {
u64 map_100ns, unmap_100ns, map_sq, unmap_sq;
ktime_t map_stime, map_etime, unmap_stime, unmap_etime;
ktime_t map_delta, unmap_delta;
/*
* for a non-coherent device, if we don't stain them in the
* cache, this will give an underestimate of the real-world
* overhead of BIDIRECTIONAL or TO_DEVICE mappings;
* 66 means evertything goes well! 66 is lucky.
*/
if (map->dir != DMA_FROM_DEVICE)
memset(buf, 0x66, PAGE_SIZE);
map_stime = ktime_get();
dma_addr = dma_map_single(map->dev, buf, PAGE_SIZE, map->dir);
if (unlikely(dma_mapping_error(map->dev, dma_addr))) {
pr_err("dma_map_single failed on %s\n",
dev_name(map->dev));
ret = -ENOMEM;
goto out;
}
map_etime = ktime_get();
map_delta = ktime_sub(map_etime, map_stime);
/* Pretend DMA is transmitting */
ndelay(map->bparam.dma_trans_ns);
unmap_stime = ktime_get();
dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir);
unmap_etime = ktime_get();
unmap_delta = ktime_sub(unmap_etime, unmap_stime);
/* calculate sum and sum of squares */
map_100ns = div64_ul(map_delta, 100);
unmap_100ns = div64_ul(unmap_delta, 100);
map_sq = map_100ns * map_100ns;
unmap_sq = unmap_100ns * unmap_100ns;
atomic64_add(map_100ns, &map->sum_map_100ns);
atomic64_add(unmap_100ns, &map->sum_unmap_100ns);
atomic64_add(map_sq, &map->sum_sq_map);
atomic64_add(unmap_sq, &map->sum_sq_unmap);
atomic64_inc(&map->loops);
}
out:
free_page((unsigned long)buf);
return ret;
}
static int do_map_benchmark(struct map_benchmark_data *map)
{
struct task_struct **tsk;
int threads = map->bparam.threads;
int node = map->bparam.node;
const cpumask_t *cpu_mask = cpumask_of_node(node);
u64 loops;
int ret = 0;
int i;
tsk = kmalloc_array(threads, sizeof(*tsk), GFP_KERNEL);
if (!tsk)
return -ENOMEM;
get_device(map->dev);
for (i = 0; i < threads; i++) {
tsk[i] = kthread_create_on_node(map_benchmark_thread, map,
map->bparam.node, "dma-map-benchmark/%d", i);
if (IS_ERR(tsk[i])) {
pr_err("create dma_map thread failed\n");
ret = PTR_ERR(tsk[i]);
goto out;
}
if (node != NUMA_NO_NODE)
kthread_bind_mask(tsk[i], cpu_mask);
}
/* clear the old value in the previous benchmark */
atomic64_set(&map->sum_map_100ns, 0);
atomic64_set(&map->sum_unmap_100ns, 0);
atomic64_set(&map->sum_sq_map, 0);
atomic64_set(&map->sum_sq_unmap, 0);
atomic64_set(&map->loops, 0);
dma-mapping: benchmark: fix kernel crash when dma_map_single fails if dma_map_single() fails, kernel will give the below oops since task_struct has been destroyed and we are running into the memory corruption due to use-after-free in kthread_stop(): [ 48.095310] Unable to handle kernel paging request at virtual address 000000c473548040 [ 48.095736] Mem abort info: [ 48.095864] ESR = 0x96000004 [ 48.096025] EC = 0x25: DABT (current EL), IL = 32 bits [ 48.096268] SET = 0, FnV = 0 [ 48.096401] EA = 0, S1PTW = 0 [ 48.096538] Data abort info: [ 48.096659] ISV = 0, ISS = 0x00000004 [ 48.096820] CM = 0, WnR = 0 [ 48.097079] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000104639000 [ 48.098099] [000000c473548040] pgd=0000000000000000, p4d=0000000000000000 [ 48.098832] Internal error: Oops: 96000004 [#1] PREEMPT SMP [ 48.099232] Modules linked in: [ 48.099387] CPU: 0 PID: 2 Comm: kthreadd Tainted: G W [ 48.099887] Hardware name: linux,dummy-virt (DT) [ 48.100078] pstate: 60000005 (nZCv daif -PAN -UAO -TCO BTYPE=--) [ 48.100516] pc : __kmalloc_node+0x214/0x368 [ 48.100944] lr : __kmalloc_node+0x1f4/0x368 [ 48.101458] sp : ffff800011f0bb80 [ 48.101843] x29: ffff800011f0bb80 x28: ffff0000c0098ec0 [ 48.102330] x27: 0000000000000000 x26: 00000000001d4600 [ 48.102648] x25: ffff0000c0098ec0 x24: ffff800011b6a000 [ 48.102988] x23: 00000000ffffffff x22: ffff0000c0098ec0 [ 48.103333] x21: ffff8000101d7a54 x20: 0000000000000dc0 [ 48.103657] x19: ffff0000c0001e00 x18: 0000000000000000 [ 48.104069] x17: 0000000000000000 x16: 0000000000000000 [ 48.105449] x15: 000001aa0304e7b9 x14: 00000000000003b1 [ 48.106401] x13: ffff8000122d5000 x12: ffff80001228d000 [ 48.107296] x11: ffff0000c0154340 x10: 0000000000000000 [ 48.107862] x9 : ffff80000fffffff x8 : ffff0000c473527f [ 48.108326] x7 : ffff800011e62f58 x6 : ffff0000c01c8ed8 [ 48.108778] x5 : ffff0000c0098ec0 x4 : 0000000000000000 [ 48.109223] x3 : 00000000001d4600 x2 : 0000000000000040 [ 48.109656] x1 : 0000000000000001 x0 : ff0000c473548000 [ 48.110104] Call trace: [ 48.110287] __kmalloc_node+0x214/0x368 [ 48.110493] __vmalloc_node_range+0xc4/0x298 [ 48.110805] copy_process+0x2c8/0x15c8 [ 48.111133] kernel_clone+0x5c/0x3c0 [ 48.111373] kernel_thread+0x64/0x90 [ 48.111604] kthreadd+0x158/0x368 [ 48.111810] ret_from_fork+0x10/0x30 [ 48.112336] Code: 17ffffe9 b9402a62 b94008a1 11000421 (f8626802) [ 48.112884] ---[ end trace d4890e21e75419d5 ]--- Signed-off-by: Barry Song <song.bao.hua@hisilicon.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2021-01-25 01:13:06 +00:00
for (i = 0; i < threads; i++) {
get_task_struct(tsk[i]);
wake_up_process(tsk[i]);
dma-mapping: benchmark: fix kernel crash when dma_map_single fails if dma_map_single() fails, kernel will give the below oops since task_struct has been destroyed and we are running into the memory corruption due to use-after-free in kthread_stop(): [ 48.095310] Unable to handle kernel paging request at virtual address 000000c473548040 [ 48.095736] Mem abort info: [ 48.095864] ESR = 0x96000004 [ 48.096025] EC = 0x25: DABT (current EL), IL = 32 bits [ 48.096268] SET = 0, FnV = 0 [ 48.096401] EA = 0, S1PTW = 0 [ 48.096538] Data abort info: [ 48.096659] ISV = 0, ISS = 0x00000004 [ 48.096820] CM = 0, WnR = 0 [ 48.097079] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000104639000 [ 48.098099] [000000c473548040] pgd=0000000000000000, p4d=0000000000000000 [ 48.098832] Internal error: Oops: 96000004 [#1] PREEMPT SMP [ 48.099232] Modules linked in: [ 48.099387] CPU: 0 PID: 2 Comm: kthreadd Tainted: G W [ 48.099887] Hardware name: linux,dummy-virt (DT) [ 48.100078] pstate: 60000005 (nZCv daif -PAN -UAO -TCO BTYPE=--) [ 48.100516] pc : __kmalloc_node+0x214/0x368 [ 48.100944] lr : __kmalloc_node+0x1f4/0x368 [ 48.101458] sp : ffff800011f0bb80 [ 48.101843] x29: ffff800011f0bb80 x28: ffff0000c0098ec0 [ 48.102330] x27: 0000000000000000 x26: 00000000001d4600 [ 48.102648] x25: ffff0000c0098ec0 x24: ffff800011b6a000 [ 48.102988] x23: 00000000ffffffff x22: ffff0000c0098ec0 [ 48.103333] x21: ffff8000101d7a54 x20: 0000000000000dc0 [ 48.103657] x19: ffff0000c0001e00 x18: 0000000000000000 [ 48.104069] x17: 0000000000000000 x16: 0000000000000000 [ 48.105449] x15: 000001aa0304e7b9 x14: 00000000000003b1 [ 48.106401] x13: ffff8000122d5000 x12: ffff80001228d000 [ 48.107296] x11: ffff0000c0154340 x10: 0000000000000000 [ 48.107862] x9 : ffff80000fffffff x8 : ffff0000c473527f [ 48.108326] x7 : ffff800011e62f58 x6 : ffff0000c01c8ed8 [ 48.108778] x5 : ffff0000c0098ec0 x4 : 0000000000000000 [ 48.109223] x3 : 00000000001d4600 x2 : 0000000000000040 [ 48.109656] x1 : 0000000000000001 x0 : ff0000c473548000 [ 48.110104] Call trace: [ 48.110287] __kmalloc_node+0x214/0x368 [ 48.110493] __vmalloc_node_range+0xc4/0x298 [ 48.110805] copy_process+0x2c8/0x15c8 [ 48.111133] kernel_clone+0x5c/0x3c0 [ 48.111373] kernel_thread+0x64/0x90 [ 48.111604] kthreadd+0x158/0x368 [ 48.111810] ret_from_fork+0x10/0x30 [ 48.112336] Code: 17ffffe9 b9402a62 b94008a1 11000421 (f8626802) [ 48.112884] ---[ end trace d4890e21e75419d5 ]--- Signed-off-by: Barry Song <song.bao.hua@hisilicon.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2021-01-25 01:13:06 +00:00
}
msleep_interruptible(map->bparam.seconds * 1000);
/* wait for the completion of benchmark threads */
for (i = 0; i < threads; i++) {
ret = kthread_stop(tsk[i]);
if (ret)
goto out;
}
loops = atomic64_read(&map->loops);
if (likely(loops > 0)) {
u64 map_variance, unmap_variance;
u64 sum_map = atomic64_read(&map->sum_map_100ns);
u64 sum_unmap = atomic64_read(&map->sum_unmap_100ns);
u64 sum_sq_map = atomic64_read(&map->sum_sq_map);
u64 sum_sq_unmap = atomic64_read(&map->sum_sq_unmap);
/* average latency */
map->bparam.avg_map_100ns = div64_u64(sum_map, loops);
map->bparam.avg_unmap_100ns = div64_u64(sum_unmap, loops);
/* standard deviation of latency */
map_variance = div64_u64(sum_sq_map, loops) -
map->bparam.avg_map_100ns *
map->bparam.avg_map_100ns;
unmap_variance = div64_u64(sum_sq_unmap, loops) -
map->bparam.avg_unmap_100ns *
map->bparam.avg_unmap_100ns;
map->bparam.map_stddev = int_sqrt64(map_variance);
map->bparam.unmap_stddev = int_sqrt64(unmap_variance);
}
out:
dma-mapping: benchmark: fix kernel crash when dma_map_single fails if dma_map_single() fails, kernel will give the below oops since task_struct has been destroyed and we are running into the memory corruption due to use-after-free in kthread_stop(): [ 48.095310] Unable to handle kernel paging request at virtual address 000000c473548040 [ 48.095736] Mem abort info: [ 48.095864] ESR = 0x96000004 [ 48.096025] EC = 0x25: DABT (current EL), IL = 32 bits [ 48.096268] SET = 0, FnV = 0 [ 48.096401] EA = 0, S1PTW = 0 [ 48.096538] Data abort info: [ 48.096659] ISV = 0, ISS = 0x00000004 [ 48.096820] CM = 0, WnR = 0 [ 48.097079] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000104639000 [ 48.098099] [000000c473548040] pgd=0000000000000000, p4d=0000000000000000 [ 48.098832] Internal error: Oops: 96000004 [#1] PREEMPT SMP [ 48.099232] Modules linked in: [ 48.099387] CPU: 0 PID: 2 Comm: kthreadd Tainted: G W [ 48.099887] Hardware name: linux,dummy-virt (DT) [ 48.100078] pstate: 60000005 (nZCv daif -PAN -UAO -TCO BTYPE=--) [ 48.100516] pc : __kmalloc_node+0x214/0x368 [ 48.100944] lr : __kmalloc_node+0x1f4/0x368 [ 48.101458] sp : ffff800011f0bb80 [ 48.101843] x29: ffff800011f0bb80 x28: ffff0000c0098ec0 [ 48.102330] x27: 0000000000000000 x26: 00000000001d4600 [ 48.102648] x25: ffff0000c0098ec0 x24: ffff800011b6a000 [ 48.102988] x23: 00000000ffffffff x22: ffff0000c0098ec0 [ 48.103333] x21: ffff8000101d7a54 x20: 0000000000000dc0 [ 48.103657] x19: ffff0000c0001e00 x18: 0000000000000000 [ 48.104069] x17: 0000000000000000 x16: 0000000000000000 [ 48.105449] x15: 000001aa0304e7b9 x14: 00000000000003b1 [ 48.106401] x13: ffff8000122d5000 x12: ffff80001228d000 [ 48.107296] x11: ffff0000c0154340 x10: 0000000000000000 [ 48.107862] x9 : ffff80000fffffff x8 : ffff0000c473527f [ 48.108326] x7 : ffff800011e62f58 x6 : ffff0000c01c8ed8 [ 48.108778] x5 : ffff0000c0098ec0 x4 : 0000000000000000 [ 48.109223] x3 : 00000000001d4600 x2 : 0000000000000040 [ 48.109656] x1 : 0000000000000001 x0 : ff0000c473548000 [ 48.110104] Call trace: [ 48.110287] __kmalloc_node+0x214/0x368 [ 48.110493] __vmalloc_node_range+0xc4/0x298 [ 48.110805] copy_process+0x2c8/0x15c8 [ 48.111133] kernel_clone+0x5c/0x3c0 [ 48.111373] kernel_thread+0x64/0x90 [ 48.111604] kthreadd+0x158/0x368 [ 48.111810] ret_from_fork+0x10/0x30 [ 48.112336] Code: 17ffffe9 b9402a62 b94008a1 11000421 (f8626802) [ 48.112884] ---[ end trace d4890e21e75419d5 ]--- Signed-off-by: Barry Song <song.bao.hua@hisilicon.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2021-01-25 01:13:06 +00:00
for (i = 0; i < threads; i++)
put_task_struct(tsk[i]);
put_device(map->dev);
kfree(tsk);
return ret;
}
static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct map_benchmark_data *map = file->private_data;
void __user *argp = (void __user *)arg;
u64 old_dma_mask;
int ret;
if (copy_from_user(&map->bparam, argp, sizeof(map->bparam)))
return -EFAULT;
switch (cmd) {
case DMA_MAP_BENCHMARK:
if (map->bparam.threads == 0 ||
map->bparam.threads > DMA_MAP_MAX_THREADS) {
pr_err("invalid thread number\n");
return -EINVAL;
}
if (map->bparam.seconds == 0 ||
map->bparam.seconds > DMA_MAP_MAX_SECONDS) {
pr_err("invalid duration seconds\n");
return -EINVAL;
}
if (map->bparam.dma_trans_ns > DMA_MAP_MAX_TRANS_DELAY) {
pr_err("invalid transmission delay\n");
return -EINVAL;
}
if (map->bparam.node != NUMA_NO_NODE &&
!node_possible(map->bparam.node)) {
pr_err("invalid numa node\n");
return -EINVAL;
}
switch (map->bparam.dma_dir) {
case DMA_MAP_BIDIRECTIONAL:
map->dir = DMA_BIDIRECTIONAL;
break;
case DMA_MAP_FROM_DEVICE:
map->dir = DMA_FROM_DEVICE;
break;
case DMA_MAP_TO_DEVICE:
map->dir = DMA_TO_DEVICE;
break;
default:
pr_err("invalid DMA direction\n");
return -EINVAL;
}
old_dma_mask = dma_get_mask(map->dev);
ret = dma_set_mask(map->dev,
DMA_BIT_MASK(map->bparam.dma_bits));
if (ret) {
pr_err("failed to set dma_mask on device %s\n",
dev_name(map->dev));
return -EINVAL;
}
ret = do_map_benchmark(map);
/*
* restore the original dma_mask as many devices' dma_mask are
* set by architectures, acpi, busses. When we bind them back
* to their original drivers, those drivers shouldn't see
* dma_mask changed by benchmark
*/
dma_set_mask(map->dev, old_dma_mask);
break;
default:
return -EINVAL;
}
if (copy_to_user(argp, &map->bparam, sizeof(map->bparam)))
return -EFAULT;
return ret;
}
static const struct file_operations map_benchmark_fops = {
.open = simple_open,
.unlocked_ioctl = map_benchmark_ioctl,
};
static void map_benchmark_remove_debugfs(void *data)
{
struct map_benchmark_data *map = (struct map_benchmark_data *)data;
debugfs_remove(map->debugfs);
}
static int __map_benchmark_probe(struct device *dev)
{
struct dentry *entry;
struct map_benchmark_data *map;
int ret;
map = devm_kzalloc(dev, sizeof(*map), GFP_KERNEL);
if (!map)
return -ENOMEM;
map->dev = dev;
ret = devm_add_action(dev, map_benchmark_remove_debugfs, map);
if (ret) {
pr_err("Can't add debugfs remove action\n");
return ret;
}
/*
* we only permit a device bound with this driver, 2nd probe
* will fail
*/
entry = debugfs_create_file("dma_map_benchmark", 0600, NULL, map,
&map_benchmark_fops);
if (IS_ERR(entry))
return PTR_ERR(entry);
map->debugfs = entry;
return 0;
}
static int map_benchmark_platform_probe(struct platform_device *pdev)
{
return __map_benchmark_probe(&pdev->dev);
}
static struct platform_driver map_benchmark_platform_driver = {
.driver = {
.name = "dma_map_benchmark",
},
.probe = map_benchmark_platform_probe,
};
static int
map_benchmark_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
return __map_benchmark_probe(&pdev->dev);
}
static struct pci_driver map_benchmark_pci_driver = {
.name = "dma_map_benchmark",
.probe = map_benchmark_pci_probe,
};
static int __init map_benchmark_init(void)
{
int ret;
ret = pci_register_driver(&map_benchmark_pci_driver);
if (ret)
return ret;
ret = platform_driver_register(&map_benchmark_platform_driver);
if (ret) {
pci_unregister_driver(&map_benchmark_pci_driver);
return ret;
}
return 0;
}
static void __exit map_benchmark_cleanup(void)
{
platform_driver_unregister(&map_benchmark_platform_driver);
pci_unregister_driver(&map_benchmark_pci_driver);
}
module_init(map_benchmark_init);
module_exit(map_benchmark_cleanup);
MODULE_AUTHOR("Barry Song <song.bao.hua@hisilicon.com>");
MODULE_DESCRIPTION("dma_map benchmark driver");
MODULE_LICENSE("GPL");