[Intel-gfx] [PATCH] drm/i915: Use locked access to ctx->engines in set_priority

[Jason Ekstrand]

On Tue, Aug 10, 2021 at 8:05 AM Daniel Vetter <daniel.vetter at ffwll.ch> wrote:
>
> This essentially reverts
>
> commit 89ff76bf9b3b0b86e6bbe344bd6378d8661303fc
> Author: Chris Wilson <chris at chris-wilson.co.uk>
> Date:   Thu Apr 2 13:42:18 2020 +0100
>
>     drm/i915/gem: Utilize rcu iteration of context engines
>
> Note that the other use of __context_engines_await have disappeard in
> the following commits:
>
> ccbc1b97948a ("drm/i915/gem: Don't allow changing the VM on running contexts (v4)")
> c7a71fc8ee04 ("drm/i915: Drop getparam support for I915_CONTEXT_PARAM_ENGINES")
> 4a766ae40ec8 ("drm/i915: Drop the CONTEXT_CLONE API (v2)")
>
> None of these have any business to optimize their engine lookup with
> rcu, unless extremely convincing benchmark data and a solid analysis
> why we can't make that workload (whatever it is that does) faster with
> a proper design fix.
>
> Also since there's only one caller of context_apply_all left and it's
> really just a loop, inline it and then inline the lopp body too. This
> is how all other callers that take the engine lock loop over engines,
> it's much simpler.
>
> Signed-off-by: Daniel Vetter <daniel.vetter at intel.com>
> Cc: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
> Cc: Daniel Vetter <daniel.vetter at ffwll.ch>
> Cc: Jason Ekstrand <jason at jlekstrand.net>
> Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
> Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
> Cc: Matthew Brost <matthew.brost at intel.com>
> ---
>  drivers/gpu/drm/i915/gem/i915_gem_context.c | 72 ++++-----------------
>  1 file changed, 14 insertions(+), 58 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> index dbaeb924a437..fd169cf2f75a 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> @@ -1284,49 +1284,6 @@ static int __context_set_persistence(struct i915_gem_context *ctx, bool state)
>         return 0;
>  }
>
> -static inline struct i915_gem_engines *
> -__context_engines_await(const struct i915_gem_context *ctx,
> -                       bool *user_engines)
> -{
> -       struct i915_gem_engines *engines;
> -
> -       rcu_read_lock();
> -       do {
> -               engines = rcu_dereference(ctx->engines);
> -               GEM_BUG_ON(!engines);
> -
> -               if (user_engines)
> -                       *user_engines = i915_gem_context_user_engines(ctx);
> -
> -               /* successful await => strong mb */
> -               if (unlikely(!i915_sw_fence_await(&engines->fence)))

Ugh... The first time I looked at this I thought the SW fence meant it
was actually waiting on something.  But, no, it's just making sure the
engines object still exists.  *sigh*  Burn it!

Reviewed-by: Jason Ekstrand <jason at jlekstrand.net>

> -                       continue;
> -
> -               if (likely(engines == rcu_access_pointer(ctx->engines)))
> -                       break;
> -
> -               i915_sw_fence_complete(&engines->fence);
> -       } while (1);
> -       rcu_read_unlock();
> -
> -       return engines;
> -}
> -
> -static void
> -context_apply_all(struct i915_gem_context *ctx,
> -                 void (*fn)(struct intel_context *ce, void *data),
> -                 void *data)
> -{
> -       struct i915_gem_engines_iter it;
> -       struct i915_gem_engines *e;
> -       struct intel_context *ce;
> -
> -       e = __context_engines_await(ctx, NULL);
> -       for_each_gem_engine(ce, e, it)
> -               fn(ce, data);
> -       i915_sw_fence_complete(&e->fence);
> -}
> -
>  static struct i915_gem_context *
>  i915_gem_create_context(struct drm_i915_private *i915,
>                         const struct i915_gem_proto_context *pc)
> @@ -1776,23 +1733,11 @@ set_persistence(struct i915_gem_context *ctx,
>         return __context_set_persistence(ctx, args->value);
>  }
>
> -static void __apply_priority(struct intel_context *ce, void *arg)
> -{
> -       struct i915_gem_context *ctx = arg;
> -
> -       if (!intel_engine_has_timeslices(ce->engine))
> -               return;
> -
> -       if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
> -           intel_engine_has_semaphores(ce->engine))
> -               intel_context_set_use_semaphores(ce);
> -       else
> -               intel_context_clear_use_semaphores(ce);
> -}
> -
>  static int set_priority(struct i915_gem_context *ctx,
>                         const struct drm_i915_gem_context_param *args)
>  {
> +       struct i915_gem_engines_iter it;
> +       struct intel_context *ce;
>         int err;
>
>         err = validate_priority(ctx->i915, args);
> @@ -1800,7 +1745,18 @@ static int set_priority(struct i915_gem_context *ctx,
>                 return err;
>
>         ctx->sched.priority = args->value;
> -       context_apply_all(ctx, __apply_priority, ctx);
> +
> +       for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
> +               if (!intel_engine_has_timeslices(ce->engine))
> +                       continue;
> +
> +               if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
> +                   intel_engine_has_semaphores(ce->engine))
> +                       intel_context_set_use_semaphores(ce);
> +               else
> +                       intel_context_clear_use_semaphores(ce);
> +       }
> +       i915_gem_context_unlock_engines(ctx);
>
>         return 0;
>  }
> --
> 2.32.0
>