Previously, we were storing the ring size in the ring pointer before it was actually allocated. We would then guard setting the ring size on checking for CONTEXT_ALLOC_BIT. This is error-prone at best and really only saves us a few bytes on something that already burns at least 4K. Instead, this patch adds a new ring_size field and makes everything use that.
v2 (Daniel Vetter): - Replace 512 * SZ_4K with SZ_2M
Signed-off-by: Jason Ekstrand jason@jlekstrand.net Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 3 +-- drivers/gpu/drm/i915/gt/intel_context.c | 3 ++- drivers/gpu/drm/i915/gt/intel_context.h | 5 ----- drivers/gpu/drm/i915/gt/intel_context_types.h | 1 + drivers/gpu/drm/i915/gt/intel_lrc.c | 2 +- drivers/gpu/drm/i915/gt/selftest_execlists.c | 2 +- drivers/gpu/drm/i915/gt/selftest_mocs.c | 2 +- drivers/gpu/drm/i915/gt/selftest_timeline.c | 2 +- drivers/gpu/drm/i915/gvt/scheduler.c | 7 ++----- 9 files changed, 10 insertions(+), 17 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 650364a0dae28..ec999b7ca50f4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -211,8 +211,7 @@ static void intel_context_set_gem(struct intel_context *ce, GEM_BUG_ON(rcu_access_pointer(ce->gem_context)); RCU_INIT_POINTER(ce->gem_context, ctx);
- if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) - ce->ring = __intel_context_ring_size(SZ_16K); + ce->ring_size = SZ_16K;
if (rcu_access_pointer(ctx->vm)) { struct i915_address_space *vm; diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 4033184f13b9f..bd63813c8a802 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -371,7 +371,8 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine) ce->engine = engine; ce->ops = engine->cops; ce->sseu = engine->sseu; - ce->ring = __intel_context_ring_size(SZ_4K); + ce->ring = NULL; + ce->ring_size = SZ_4K;
ewma_runtime_init(&ce->runtime.avg);
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index f83a73a2b39fc..b10cbe8fee992 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -175,11 +175,6 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
struct i915_request *intel_context_create_request(struct intel_context *ce);
-static inline struct intel_ring *__intel_context_ring_size(u64 sz) -{ - return u64_to_ptr(struct intel_ring, sz); -} - static inline bool intel_context_is_barrier(const struct intel_context *ce) { return test_bit(CONTEXT_BARRIER_BIT, &ce->flags); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index ed8c447a7346b..90026c1771055 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -82,6 +82,7 @@ struct intel_context { spinlock_t signal_lock; /* protects signals, the list of requests */
struct i915_vma *state; + u32 ring_size; struct intel_ring *ring; struct intel_timeline *timeline;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index aafe2a4df4960..890b43b296a90 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -845,7 +845,7 @@ int lrc_alloc(struct intel_context *ce, struct intel_engine_cs *engine) if (IS_ERR(vma)) return PTR_ERR(vma);
- ring = intel_engine_create_ring(engine, (unsigned long)ce->ring); + ring = intel_engine_create_ring(engine, ce->ring_size); if (IS_ERR(ring)) { err = PTR_ERR(ring); goto err_vma; diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 1081cd36a2bd3..01d9896dd4844 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -2793,7 +2793,7 @@ static int __live_preempt_ring(struct intel_engine_cs *engine, goto err_ce; }
- tmp->ring = __intel_context_ring_size(ring_sz); + tmp->ring_size = ring_sz;
err = intel_context_pin(tmp); if (err) { diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c index e55a887d11e2b..f343fa5fd986f 100644 --- a/drivers/gpu/drm/i915/gt/selftest_mocs.c +++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c @@ -28,7 +28,7 @@ static struct intel_context *mocs_context_create(struct intel_engine_cs *engine) return ce;
/* We build large requests to read the registers from the ring */ - ce->ring = __intel_context_ring_size(SZ_16K); + ce->ring_size = SZ_16K;
return ce; } diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c index 9adbd9d147bea..7eedecfb86e59 100644 --- a/drivers/gpu/drm/i915/gt/selftest_timeline.c +++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c @@ -874,7 +874,7 @@ static int create_watcher(struct hwsp_watcher *w, if (IS_ERR(ce)) return PTR_ERR(ce);
- ce->ring = __intel_context_ring_size(ringsz); + ce->ring_size = ringsz; w->rq = intel_context_create_request(ce); intel_context_put(ce); if (IS_ERR(w->rq)) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index fc735692f21fb..422cbe0d579d2 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -1409,11 +1409,8 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu) intel_context_set_single_submission(ce);
/* Max ring buffer size */ - if (!intel_uc_wants_guc_submission(&engine->gt->uc)) { - const unsigned int ring_size = 512 * SZ_4K; - - ce->ring = __intel_context_ring_size(ring_size); - } + if (!intel_uc_wants_guc_submission(&engine->gt->uc)) + ce->ring_size = SZ_2M;
s->shadow[i] = ce; }