drm/i915/selftests: Add tests for GT and engine workaround verification

Two simple selftests which test that both GT and engine workarounds are
not lost after either a full GPU reset, or after the per-engine ones.

(Including checks that one engine reset is not affecting workarounds not
belonging to itself.)

v2:
 * Rebase for series refactoring.
 * Add spinner for actual engine reset!
 * Add idle reset test as well. (Chris Wilson)
 * Share existing global_reset_lock. (Chris Wilson)

v3:
 * intel_engine_verify_workarounds can be static.
 * API rename. (Chris Wilson)
 * Move global reset lock out of the loop. (Chris Wilson)

v4:
 * Add missing rpm puts. (Chris Wilson)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20181203125014.3219-5-tvrtko.ursulin@linux.intel.com
This commit is contained in:
Tvrtko Ursulin 2018-12-03 12:50:11 +00:00
parent 094304beb4
commit 28d6ccce73
6 changed files with 214 additions and 47 deletions

View File

@ -166,6 +166,7 @@ i915-$(CONFIG_DRM_I915_SELFTEST) += \
selftests/i915_random.o \
selftests/i915_selftest.o \
selftests/igt_flush_test.o \
selftests/igt_reset.o \
selftests/igt_spinner.o
# virtual gpu code

View File

@ -1303,5 +1303,11 @@ void intel_engine_apply_workarounds(struct intel_engine_cs *engine)
}
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
static bool intel_engine_verify_workarounds(struct intel_engine_cs *engine,
const char *from)
{
return wa_list_verify(engine->i915, &engine->wa_list, from);
}
#include "selftests/intel_workarounds.c"
#endif

View File

@ -0,0 +1,44 @@
/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2018 Intel Corporation
*/
#include "igt_reset.h"
#include "../i915_drv.h"
#include "../intel_ringbuffer.h"
void igt_global_reset_lock(struct drm_i915_private *i915)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
pr_debug("%s: current gpu_error=%08lx\n",
__func__, i915->gpu_error.flags);
while (test_and_set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags))
wait_event(i915->gpu_error.reset_queue,
!test_bit(I915_RESET_BACKOFF,
&i915->gpu_error.flags));
for_each_engine(engine, i915, id) {
while (test_and_set_bit(I915_RESET_ENGINE + id,
&i915->gpu_error.flags))
wait_on_bit(&i915->gpu_error.flags,
I915_RESET_ENGINE + id,
TASK_UNINTERRUPTIBLE);
}
}
void igt_global_reset_unlock(struct drm_i915_private *i915)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
for_each_engine(engine, i915, id)
clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
wake_up_all(&i915->gpu_error.reset_queue);
}

View File

@ -0,0 +1,15 @@
/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2018 Intel Corporation
*/
#ifndef __I915_SELFTESTS_IGT_RESET_H__
#define __I915_SELFTESTS_IGT_RESET_H__
#include "../i915_drv.h"
void igt_global_reset_lock(struct drm_i915_private *i915);
void igt_global_reset_unlock(struct drm_i915_private *i915);
#endif

View File

@ -27,6 +27,7 @@
#include "../i915_selftest.h"
#include "i915_random.h"
#include "igt_flush_test.h"
#include "igt_reset.h"
#include "igt_wedge_me.h"
#include "mock_context.h"
@ -354,40 +355,6 @@ static int igt_hang_sanitycheck(void *arg)
return err;
}
static void global_reset_lock(struct drm_i915_private *i915)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
pr_debug("%s: current gpu_error=%08lx\n",
__func__, i915->gpu_error.flags);
while (test_and_set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags))
wait_event(i915->gpu_error.reset_queue,
!test_bit(I915_RESET_BACKOFF,
&i915->gpu_error.flags));
for_each_engine(engine, i915, id) {
while (test_and_set_bit(I915_RESET_ENGINE + id,
&i915->gpu_error.flags))
wait_on_bit(&i915->gpu_error.flags,
I915_RESET_ENGINE + id,
TASK_UNINTERRUPTIBLE);
}
}
static void global_reset_unlock(struct drm_i915_private *i915)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
for_each_engine(engine, i915, id)
clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
wake_up_all(&i915->gpu_error.reset_queue);
}
static int igt_global_reset(void *arg)
{
struct drm_i915_private *i915 = arg;
@ -396,7 +363,7 @@ static int igt_global_reset(void *arg)
/* Check that we can issue a global GPU reset */
global_reset_lock(i915);
igt_global_reset_lock(i915);
set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags);
mutex_lock(&i915->drm.struct_mutex);
@ -411,7 +378,7 @@ static int igt_global_reset(void *arg)
mutex_unlock(&i915->drm.struct_mutex);
GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags));
global_reset_unlock(i915);
igt_global_reset_unlock(i915);
if (i915_terminally_wedged(&i915->gpu_error))
err = -EIO;
@ -942,7 +909,7 @@ static int igt_reset_wait(void *arg)
/* Check that we detect a stuck waiter and issue a reset */
global_reset_lock(i915);
igt_global_reset_lock(i915);
mutex_lock(&i915->drm.struct_mutex);
err = hang_init(&h, i915);
@ -994,7 +961,7 @@ static int igt_reset_wait(void *arg)
hang_fini(&h);
unlock:
mutex_unlock(&i915->drm.struct_mutex);
global_reset_unlock(i915);
igt_global_reset_unlock(i915);
if (i915_terminally_wedged(&i915->gpu_error))
return -EIO;
@ -1072,7 +1039,7 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915,
/* Check that we can recover an unbind stuck on a hanging request */
global_reset_lock(i915);
igt_global_reset_lock(i915);
mutex_lock(&i915->drm.struct_mutex);
err = hang_init(&h, i915);
@ -1192,7 +1159,7 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915,
hang_fini(&h);
unlock:
mutex_unlock(&i915->drm.struct_mutex);
global_reset_unlock(i915);
igt_global_reset_unlock(i915);
if (i915_terminally_wedged(&i915->gpu_error))
return -EIO;
@ -1272,7 +1239,7 @@ static int igt_reset_queue(void *arg)
/* Check that we replay pending requests following a hang */
global_reset_lock(i915);
igt_global_reset_lock(i915);
mutex_lock(&i915->drm.struct_mutex);
err = hang_init(&h, i915);
@ -1403,7 +1370,7 @@ static int igt_reset_queue(void *arg)
hang_fini(&h);
unlock:
mutex_unlock(&i915->drm.struct_mutex);
global_reset_unlock(i915);
igt_global_reset_unlock(i915);
if (i915_terminally_wedged(&i915->gpu_error))
return -EIO;

View File

@ -6,6 +6,8 @@
#include "../i915_selftest.h"
#include "igt_flush_test.h"
#include "igt_reset.h"
#include "igt_spinner.h"
#include "igt_wedge_me.h"
#include "mock_context.h"
@ -290,7 +292,6 @@ static int live_reset_whitelist(void *arg)
{
struct drm_i915_private *i915 = arg;
struct intel_engine_cs *engine = i915->engine[RCS];
struct i915_gpu_error *error = &i915->gpu_error;
struct whitelist w;
int err = 0;
@ -302,8 +303,7 @@ static int live_reset_whitelist(void *arg)
if (!whitelist_build(engine, &w))
return 0;
set_bit(I915_RESET_BACKOFF, &error->flags);
set_bit(I915_RESET_ENGINE + engine->id, &error->flags);
igt_global_reset_lock(i915);
if (intel_has_reset_engine(i915)) {
err = check_whitelist_across_reset(engine,
@ -322,15 +322,149 @@ static int live_reset_whitelist(void *arg)
}
out:
clear_bit(I915_RESET_ENGINE + engine->id, &error->flags);
clear_bit(I915_RESET_BACKOFF, &error->flags);
igt_global_reset_unlock(i915);
return err;
}
static bool verify_gt_engine_wa(struct drm_i915_private *i915, const char *str)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
bool ok = true;
ok &= intel_gt_verify_workarounds(i915, str);
for_each_engine(engine, i915, id)
ok &= intel_engine_verify_workarounds(engine, str);
return ok;
}
static int
live_gpu_reset_gt_engine_workarounds(void *arg)
{
struct drm_i915_private *i915 = arg;
struct i915_gpu_error *error = &i915->gpu_error;
bool ok;
if (!intel_has_gpu_reset(i915))
return 0;
pr_info("Verifying after GPU reset...\n");
igt_global_reset_lock(i915);
ok = verify_gt_engine_wa(i915, "before reset");
if (!ok)
goto out;
intel_runtime_pm_get(i915);
set_bit(I915_RESET_HANDOFF, &error->flags);
i915_reset(i915, ALL_ENGINES, "live_workarounds");
intel_runtime_pm_put(i915);
ok = verify_gt_engine_wa(i915, "after reset");
out:
igt_global_reset_unlock(i915);
return ok ? 0 : -ESRCH;
}
static int
live_engine_reset_gt_engine_workarounds(void *arg)
{
struct drm_i915_private *i915 = arg;
struct intel_engine_cs *engine;
struct i915_gem_context *ctx;
struct igt_spinner spin;
enum intel_engine_id id;
struct i915_request *rq;
int ret = 0;
if (!intel_has_reset_engine(i915))
return 0;
ctx = kernel_context(i915);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
igt_global_reset_lock(i915);
for_each_engine(engine, i915, id) {
bool ok;
pr_info("Verifying after %s reset...\n", engine->name);
ok = verify_gt_engine_wa(i915, "before reset");
if (!ok) {
ret = -ESRCH;
goto err;
}
intel_runtime_pm_get(i915);
i915_reset_engine(engine, "live_workarounds");
intel_runtime_pm_put(i915);
ok = verify_gt_engine_wa(i915, "after idle reset");
if (!ok) {
ret = -ESRCH;
goto err;
}
ret = igt_spinner_init(&spin, i915);
if (ret)
goto err;
intel_runtime_pm_get(i915);
rq = igt_spinner_create_request(&spin, ctx, engine, MI_NOOP);
if (IS_ERR(rq)) {
ret = PTR_ERR(rq);
igt_spinner_fini(&spin);
intel_runtime_pm_put(i915);
goto err;
}
i915_request_add(rq);
if (!igt_wait_for_spinner(&spin, rq)) {
pr_err("Spinner failed to start\n");
igt_spinner_fini(&spin);
intel_runtime_pm_put(i915);
ret = -ETIMEDOUT;
goto err;
}
i915_reset_engine(engine, "live_workarounds");
intel_runtime_pm_put(i915);
igt_spinner_end(&spin);
igt_spinner_fini(&spin);
ok = verify_gt_engine_wa(i915, "after busy reset");
if (!ok) {
ret = -ESRCH;
goto err;
}
}
err:
igt_global_reset_unlock(i915);
kernel_context_close(ctx);
igt_flush_test(i915, I915_WAIT_LOCKED);
return ret;
}
int intel_workarounds_live_selftests(struct drm_i915_private *i915)
{
static const struct i915_subtest tests[] = {
SUBTEST(live_reset_whitelist),
SUBTEST(live_gpu_reset_gt_engine_workarounds),
SUBTEST(live_engine_reset_gt_engine_workarounds),
};
int err;