[Intel-gfx] [PATCH 03/21] drm/i915/gem: Set the watchdog timeout directly in intel_context_set_gem

[Tvrtko Ursulin]

On 28/04/2021 18:24, Jason Ekstrand wrote:
> On Wed, Apr 28, 2021 at 10:55 AM Tvrtko Ursulin
> <tvrtko.ursulin at linux.intel.com> wrote:
>> On 23/04/2021 23:31, Jason Ekstrand wrote:
>>> Instead of handling it like a context param, unconditionally set it when
>>> intel_contexts are created.  This doesn't fix anything but does simplify
>>> the code a bit.
>>>
>>> Signed-off-by: Jason Ekstrand <jason at jlekstrand.net>
>>> ---
>>>    drivers/gpu/drm/i915/gem/i915_gem_context.c   | 43 +++----------------
>>>    .../gpu/drm/i915/gem/i915_gem_context_types.h |  4 --
>>>    drivers/gpu/drm/i915/gt/intel_context_param.h |  3 +-
>>>    3 files changed, 6 insertions(+), 44 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
>>> index 35bcdeddfbf3f..1091cc04a242a 100644
>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
>>> @@ -233,7 +233,11 @@ static void intel_context_set_gem(struct intel_context *ce,
>>>            intel_engine_has_timeslices(ce->engine))
>>>                __set_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
>>>
>>> -     intel_context_set_watchdog_us(ce, ctx->watchdog.timeout_us);
>>> +     if (IS_ACTIVE(CONFIG_DRM_I915_REQUEST_TIMEOUT) &&
>>> +         ctx->i915->params.request_timeout_ms) {
>>> +             unsigned int timeout_ms = ctx->i915->params.request_timeout_ms;
>>> +             intel_context_set_watchdog_us(ce, (u64)timeout_ms * 1000);
>>
>> Blank line between declarations and code please, or just lose the local.
>>
>> Otherwise looks okay. Slight change that same GEM context can now have a
>> mix of different request expirations isn't interesting I think. At least
>> the change goes away by the end of the series.
> 
> In order for that to happen, I think you'd have to have a race between
> CREATE_CONTEXT and someone smashing the request_timeout_ms param via
> sysfs.  Or am I missing something?  Given that timeouts are really
> per-engine anyway, I don't think we need to care too much about that.

We don't care, no.

For completeness only - by the end of the series it is what you say. But 
at _this_ point in the series though it is if modparam changes at any 
point between context create and replacing engines. Which is a change 
compared to before this patch, since modparam was cached in the GEM 
context so far. So one GEM context was a single request_timeout_ms.

Regards,

Tvrtko

> --Jason
> 
>> Regards,
>>
>> Tvrtko
>>
>>> +     }
>>>    }
>>>
>>>    static void __free_engines(struct i915_gem_engines *e, unsigned int count)
>>> @@ -792,41 +796,6 @@ static void __assign_timeline(struct i915_gem_context *ctx,
>>>        context_apply_all(ctx, __apply_timeline, timeline);
>>>    }
>>>
>>> -static int __apply_watchdog(struct intel_context *ce, void *timeout_us)
>>> -{
>>> -     return intel_context_set_watchdog_us(ce, (uintptr_t)timeout_us);
>>> -}
>>> -
>>> -static int
>>> -__set_watchdog(struct i915_gem_context *ctx, unsigned long timeout_us)
>>> -{
>>> -     int ret;
>>> -
>>> -     ret = context_apply_all(ctx, __apply_watchdog,
>>> -                             (void *)(uintptr_t)timeout_us);
>>> -     if (!ret)
>>> -             ctx->watchdog.timeout_us = timeout_us;
>>> -
>>> -     return ret;
>>> -}
>>> -
>>> -static void __set_default_fence_expiry(struct i915_gem_context *ctx)
>>> -{
>>> -     struct drm_i915_private *i915 = ctx->i915;
>>> -     int ret;
>>> -
>>> -     if (!IS_ACTIVE(CONFIG_DRM_I915_REQUEST_TIMEOUT) ||
>>> -         !i915->params.request_timeout_ms)
>>> -             return;
>>> -
>>> -     /* Default expiry for user fences. */
>>> -     ret = __set_watchdog(ctx, i915->params.request_timeout_ms * 1000);
>>> -     if (ret)
>>> -             drm_notice(&i915->drm,
>>> -                        "Failed to configure default fence expiry! (%d)",
>>> -                        ret);
>>> -}
>>> -
>>>    static struct i915_gem_context *
>>>    i915_gem_create_context(struct drm_i915_private *i915, unsigned int flags)
>>>    {
>>> @@ -871,8 +840,6 @@ i915_gem_create_context(struct drm_i915_private *i915, unsigned int flags)
>>>                intel_timeline_put(timeline);
>>>        }
>>>
>>> -     __set_default_fence_expiry(ctx);
>>> -
>>>        trace_i915_context_create(ctx);
>>>
>>>        return ctx;
>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
>>> index 5ae71ec936f7c..676592e27e7d2 100644
>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
>>> @@ -153,10 +153,6 @@ struct i915_gem_context {
>>>         */
>>>        atomic_t active_count;
>>>
>>> -     struct {
>>> -             u64 timeout_us;
>>> -     } watchdog;
>>> -
>>>        /**
>>>         * @hang_timestamp: The last time(s) this context caused a GPU hang
>>>         */
>>> diff --git a/drivers/gpu/drm/i915/gt/intel_context_param.h b/drivers/gpu/drm/i915/gt/intel_context_param.h
>>> index dffedd983693d..0c69cb42d075c 100644
>>> --- a/drivers/gpu/drm/i915/gt/intel_context_param.h
>>> +++ b/drivers/gpu/drm/i915/gt/intel_context_param.h
>>> @@ -10,11 +10,10 @@
>>>
>>>    #include "intel_context.h"
>>>
>>> -static inline int
>>> +static inline void
>>>    intel_context_set_watchdog_us(struct intel_context *ce, u64 timeout_us)
>>>    {
>>>        ce->watchdog.timeout_us = timeout_us;
>>> -     return 0;
>>>    }
>>>
>>>    #endif /* INTEL_CONTEXT_PARAM_H */
>>>