[igt-dev] [RFC, i-g-t, v2] tests/device_reset: Test device sysfs reset

[Janusz Krzysztofik]

Hi Marcin,

On Mon, 2020-06-29 at 11:23 +0200, Marcin Bernatowicz wrote:
> Device reset is initiated by writing "1" to reset sysfs file,
> which should initiate device FLR if supported by device.
> 
> Test scenarios:
> 1. unbind driver from device, initiate sysfs reset, rebind driver to
> device
> 2. device reset with bound driver
> 
> v2: removed unbind-rebind (duplicates core_hotunplug at unbind-rebind)
>     added healthcheck to each test (Janusz)
> 
> Signed-off-by: Marcin Bernatowicz <marcin.bernatowicz at intel.com>
> ---
>  tests/device_reset.c | 263 +++++++++++++++++++++++++++++++++++++++++++
>  tests/meson.build    |   1 +
>  2 files changed, 264 insertions(+)
>  create mode 100644 tests/device_reset.c
> 
> diff --git a/tests/device_reset.c b/tests/device_reset.c
> new file mode 100644
> index 000000000..0e1e9e3aa
> --- /dev/null
> +++ b/tests/device_reset.c
> @@ -0,0 +1,263 @@
> +// SPDX-License-Identifier: MIT
> +/*
> + * Copyright(c) 2020 Intel Corporation. All rights reserved.
> + */
> +
> +#include <fcntl.h>
> +#include <sys/stat.h>
> +#include "igt.h"
> +#include "igt_device_scan.h"
> +#include "igt_sysfs.h"
> +
> +IGT_TEST_DESCRIPTION("Examine behavior of a driver on device sysfs reset");
> +
> +
> +#define DEV_PATH_LEN 80
> +#define DEV_BUS_ADDR_LEN 13 /* addr has form 0000:00:00.0 */
> +
> +/**
> + * Helper structure containing sysfs file descriptors
> + * and path related to tested device
> + */
> +struct sysfs_fds {
> +	struct {
> +		int dev;

NIT: In your code, sysfs.fds.dev doesn't correspond to a sysfs node,
only to a device special file under /dev.  Then, 'sysfs_fds' as the
name of the structure type and 'sysfs' as the name of its instance may
be misleading in regard to the fds.dev member.

> +		int dev_dir;
> +		int drv_dir;
> +	} fds;
> +	char dev_bus_addr[DEV_BUS_ADDR_LEN];
> +};
> +
> +static int __open_sysfs_dir(int fd, const char* path)
> +{
> +	int sysfs;
> +
> +	sysfs = igt_sysfs_open(fd);
> +	if (sysfs < 0) {
> +		return -1;
> +	}
> +
> +	return openat(sysfs, path, O_DIRECTORY);

Can we take care of closing the 'sysfs' fd before returning?

> +}
> +
> +static int open_device_sysfs_dir(int fd)
> +{
> +	return __open_sysfs_dir(fd, "device");
> +}
> +
> +static int open_driver_sysfs_dir(int fd)
> +{
> +	return __open_sysfs_dir(fd, "device/driver");
> +}
> +
> +/**
> + * device_sysfs_path:
> + * @fd: opened device file descriptor
> + * @path: buffer to store sysfs path to device directory
> + *
> + * Returns:
> + * On successfull path resolution sysfs path to device directory,
> + * NULL otherwise
> + */
> +static char *device_sysfs_path(int fd, char *path)
> +{
> +	char sysfs[DEV_PATH_LEN];
> +
> +	if (!igt_sysfs_path(fd, sysfs, sizeof(sysfs)))
> +		return NULL;
> +
> +	if (DEV_PATH_LEN <= (strlen(sysfs) + strlen("/device")))
> +		return NULL;
> +
> +	strcat(sysfs, "/device");
> +
> +	return realpath(sysfs, path);
> +}
> +
> +static void init_sysfs_fds(struct sysfs_fds *sysfs)
> +{
> +	char dev_path[PATH_MAX];
> +	char *addr_pos;
> +
> +	igt_debug("open device\n");
> +	/**
> +	 * As subtests must be able to close examined devices
> +	 * completely, don't use drm_open_driver() as it keeps
> +	 * a device file descriptor open for exit handler use.
> +	 */
> +	sysfs->fds.dev = __drm_open_driver(DRIVER_ANY);
> +	igt_assert_fd(sysfs->fds.dev);
> +
> +	igt_assert(device_sysfs_path(sysfs->fds.dev, dev_path));
> +	addr_pos = strrchr(dev_path, '/');
> +	snprintf(sysfs->dev_bus_addr, sizeof(sysfs->dev_bus_addr),
> +		 "%s", (addr_pos ? addr_pos + 1 : ""));

NIT: Couldn't we assert non-NULL addr_pos before using it instead of
using this conditional expression?

> +	igt_assert(sysfs->dev_bus_addr[0]);

NIT: Couldn't we assert correctness of return value of snprintf()
instead?

> +
> +	sysfs->fds.dev_dir = open_device_sysfs_dir(sysfs->fds.dev);
> +	igt_assert_fd(sysfs->fds.dev_dir);
> +
> +	sysfs->fds.drv_dir = open_driver_sysfs_dir(sysfs->fds.dev);
> +	igt_assert_fd(sysfs->fds.drv_dir);
> +}
> +
> +static int close_if_opened(int *fd)
> +{
> +	int rc = 0;

Could we have declarations separated here from the code with a blank
line?

> +	if (fd && *fd != -1) {
> +		rc = close(*fd);
> +		*fd = -1;
> +	}
> +	return rc;
> +}
> +
> +static void cleanup_sysfs_fds(struct sysfs_fds *sysfs)
> +{
> +	close_if_opened(&sysfs->fds.dev);
> +	close_if_opened(&sysfs->fds.dev_dir);
> +	close_if_opened(&sysfs->fds.drv_dir);

NIT: There is an igt_ignore_warn() helper which you may want to use for
preventively suppressing potential compiler warnings on ignored return
values of non-void functions.

> +	sysfs->dev_bus_addr[0] = '\0';

Is cleanup of dev_bus_addr content really needed?

> +}
> +
> +/**
> + * is_sysfs_reset_supported:
> + * @fd: opened device file descriptor
> + *
> + * Check if device supports reset based on sysfs file presence.
> + *
> + * Returns:
> + * True if device supports reset, false otherwise.
> + */
> +static bool is_sysfs_reset_supported(int fd)
> +{
> +	struct stat st;
> +	int rc;
> +	int sysfs;
> +	int reset_fd = -1;
> +
> +	sysfs = igt_sysfs_open(fd);
> +
> +	if (sysfs >= 0) {
> +		reset_fd = openat(sysfs, "device/reset", O_WRONLY);
> +		close(sysfs);
> +	}
> +
> +	if (reset_fd < 0)
> +		return false;
> +
> +	rc = fstat(reset_fd, &st);
> +	close(reset_fd);
> +
> +	if (rc || !S_ISREG(st.st_mode))
> +		return false;
> +
> +	return true;
> +}
> +
> +/* Unbind the driver from the device */
> +static void driver_unbind(struct sysfs_fds *sysfs)
> +{
> +	igt_debug("unbind the driver from the device\n");
> +	igt_assert(igt_sysfs_set(sysfs->fds.drv_dir, "unbind",
> +		   sysfs->dev_bus_addr));
> +}
> +
> +/* Re-bind the driver to the device */
> +static void driver_bind(struct sysfs_fds *sysfs)
> +{
> +	igt_debug("rebind the driver to the device\n");
> +	igt_abort_on_f(!igt_sysfs_set(sysfs->fds.drv_dir, "bind",
> +		       sysfs->dev_bus_addr), "driver rebind failed");
> +}
> +
> +/* Initiate device reset */
> +static void initiate_device_reset(struct sysfs_fds *sysfs)
> +{
> +	igt_debug("reset device\n");
> +	igt_assert(igt_sysfs_set(sysfs->fds.dev_dir, "reset", "1"));
> +}
> +
> +/**
> + * healthcheck:
> + * @sysfs: structure with device descriptor, if descriptor equals -1
> + * 	   the device is reopened
> + */
> +static void healthcheck(struct sysfs_fds *sysfs)
> +{
> +	if (sysfs->fds.dev == -1) {
> +		/* refresh device list */
> +		igt_devices_scan(true);
> +		igt_debug("reopen the device\n");
> +		sysfs->fds.dev = __drm_open_driver(DRIVER_ANY);
> +	}
> +	igt_assert_fd(sysfs->fds.dev);
> +
> +	if (is_i915_device(sysfs->fds.dev))
> +		gem_test_engine(sysfs->fds.dev, ALL_ENGINES);
> +}
> +
> +/**
> + * set_device_filter:
> + *
> + * Sets device filter to ensure subtests always reopen the same device
> + *
> + * @dev_path: path to device under tests
> + */
> +static void set_device_filter(const char* dev_path)
> +{
> +	char filter[strlen("sys:") + strlen(dev_path) + 1];

Can we avoiding variable-length arrays?

Other than that, LGTM.

Thanks,
Janusz


> +
> +	snprintf(filter, sizeof(filter), "sys:%s", dev_path);
> +	igt_device_filter_free_all();
> +	igt_assert_eq(igt_device_filter_add(filter), 1);
> +}
> +
> +static void unbind_reset_rebind(struct sysfs_fds *sysfs)
> +{
> +	igt_debug("close the device\n");
> +	close_if_opened(&sysfs->fds.dev);
> +
> +	driver_unbind(sysfs);
> +
> +	initiate_device_reset(sysfs);
> +
> +	driver_bind(sysfs);
> +}
> +
> +igt_main
> +{
> +	struct sysfs_fds sysfs;
> +
> +	igt_fixture {
> +		char dev_path[PATH_MAX];
> +
> +		igt_debug("opening device\n");
> +		init_sysfs_fds(&sysfs);
> +
> +		/* Make sure subtests always reopen the same device */
> +		igt_assert(device_sysfs_path(sysfs.fds.dev, dev_path));
> +		set_device_filter(dev_path);
> +
> +		igt_skip_on(!is_sysfs_reset_supported(sysfs.fds.dev));
> +
> +		igt_set_timeout(60, "device reset tests timed out after 60s");
> +	}
> +
> +	igt_describe("Unbinds driver from device, initiates reset"
> +		     " then rebinds driver to device");
> +	igt_subtest("unbind-reset-rebind") {
> +		unbind_reset_rebind(&sysfs);
> +		healthcheck(&sysfs);
> +	}
> +
> +	igt_describe("Resets device with bound driver");
> +	igt_subtest("reset-bound") {
> +		initiate_device_reset(&sysfs);
> +		healthcheck(&sysfs);
> +	}
> +
> +	igt_fixture {
> +		igt_reset_timeout();
> +		cleanup_sysfs_fds(&sysfs);
> +	}
> +}
> diff --git a/tests/meson.build b/tests/meson.build
> index 28091794f..b0acdf7c0 100644
> --- a/tests/meson.build
> +++ b/tests/meson.build
> @@ -8,6 +8,7 @@ test_progs = [
>  	'core_setmaster_vs_auth',
>  	'debugfs_test',
>  	'dmabuf',
> +	'device_reset',
>  	'drm_import_export',
>  	'drm_mm',
>  	'drm_read',