linux_dsm_epyc7002/drivers/gpu/drm/i915/selftests/i915_active.c
Chris Wilson c41166f9a1 drm/i915: Beware temporary wedging when determining -EIO
At a few points in our uABI, we check to see if the driver is wedged and
report -EIO back to the user in that case. However, as we perform the
check and reset asynchronously (where once before they were both
serialised by the struct_mutex), we may instead see the temporary wedging
used to cancel inflight rendering to avoid a deadlock during reset
(caused by either us timing out in our reset handler,
i915_wedge_on_timeout or with malice aforethought in intel_reset_prepare
for a stuck modeset). If we suspect this is the case, that is we see a
wedged driver *and* reset in progress, then wait until the reset is
resolved before reporting upon the wedged status.

v2: might_sleep() (Mika)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109580
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190220145637.23503-1-chris@chris-wilson.co.uk
2019-02-20 16:31:08 +00:00

158 lines
3.3 KiB
C

/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2018 Intel Corporation
*/
#include "../i915_selftest.h"
#include "igt_flush_test.h"
#include "lib_sw_fence.h"
struct live_active {
struct i915_active base;
bool retired;
};
static void __live_active_retire(struct i915_active *base)
{
struct live_active *active = container_of(base, typeof(*active), base);
active->retired = true;
}
static int __live_active_setup(struct drm_i915_private *i915,
struct live_active *active)
{
struct intel_engine_cs *engine;
struct i915_sw_fence *submit;
enum intel_engine_id id;
unsigned int count = 0;
int err = 0;
submit = heap_fence_create(GFP_KERNEL);
if (!submit)
return -ENOMEM;
i915_active_init(i915, &active->base, __live_active_retire);
active->retired = false;
if (!i915_active_acquire(&active->base)) {
pr_err("First i915_active_acquire should report being idle\n");
err = -EINVAL;
goto out;
}
for_each_engine(engine, i915, id) {
struct i915_request *rq;
rq = i915_request_alloc(engine, i915->kernel_context);
if (IS_ERR(rq)) {
err = PTR_ERR(rq);
break;
}
err = i915_sw_fence_await_sw_fence_gfp(&rq->submit,
submit,
GFP_KERNEL);
if (err >= 0)
err = i915_active_ref(&active->base,
rq->fence.context, rq);
i915_request_add(rq);
if (err) {
pr_err("Failed to track active ref!\n");
break;
}
count++;
}
i915_active_release(&active->base);
if (active->retired && count) {
pr_err("i915_active retired before submission!\n");
err = -EINVAL;
}
if (active->base.count != count) {
pr_err("i915_active not tracking all requests, found %d, expected %d\n",
active->base.count, count);
err = -EINVAL;
}
out:
i915_sw_fence_commit(submit);
heap_fence_put(submit);
return err;
}
static int live_active_wait(void *arg)
{
struct drm_i915_private *i915 = arg;
struct live_active active;
intel_wakeref_t wakeref;
int err;
/* Check that we get a callback when requests retire upon waiting */
mutex_lock(&i915->drm.struct_mutex);
wakeref = intel_runtime_pm_get(i915);
err = __live_active_setup(i915, &active);
i915_active_wait(&active.base);
if (!active.retired) {
pr_err("i915_active not retired after waiting!\n");
err = -EINVAL;
}
i915_active_fini(&active.base);
if (igt_flush_test(i915, I915_WAIT_LOCKED))
err = -EIO;
intel_runtime_pm_put(i915, wakeref);
mutex_unlock(&i915->drm.struct_mutex);
return err;
}
static int live_active_retire(void *arg)
{
struct drm_i915_private *i915 = arg;
struct live_active active;
intel_wakeref_t wakeref;
int err;
/* Check that we get a callback when requests are indirectly retired */
mutex_lock(&i915->drm.struct_mutex);
wakeref = intel_runtime_pm_get(i915);
err = __live_active_setup(i915, &active);
/* waits for & retires all requests */
if (igt_flush_test(i915, I915_WAIT_LOCKED))
err = -EIO;
if (!active.retired) {
pr_err("i915_active not retired after flushing!\n");
err = -EINVAL;
}
i915_active_fini(&active.base);
intel_runtime_pm_put(i915, wakeref);
mutex_unlock(&i915->drm.struct_mutex);
return err;
}
int i915_active_live_selftests(struct drm_i915_private *i915)
{
static const struct i915_subtest tests[] = {
SUBTEST(live_active_wait),
SUBTEST(live_active_retire),
};
if (i915_terminally_wedged(i915))
return 0;
return i915_subtests(tests, i915);
}