The compute engine handles the same commands the render engine can
(except 3D pipeline), so it makes sense that CCS is more similar to RCS
than non-render engines.
The CCS context state (lrc) is also similar to the render one, so reuse
it. Note that the compute engine has its own CTX_R_PWR_CLK_STATE
register.
In order to avoid having multiple RCS && CCS checks, add the following
engine flag:
- I915_ENGINE_HAS_RCS_REG_STATE - use the render (larger) reg state ctx.
BSpec: 46260
Original-author: Michel Thierry
Cc: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxxxxxxxx>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@xxxxxxxxx>
Signed-off-by: Aravind Iddamsetty <aravind.iddamsetty@xxxxxxxxx>
Signed-off-by: Matt Roper <matthew.d.roper@xxxxxxxxx>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
---
drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c | 8 +++++---
drivers/gpu/drm/i915/gt/intel_engine_cs.c | 6 ++++++
drivers/gpu/drm/i915/gt/intel_engine_types.h | 1 +
drivers/gpu/drm/i915/gt/intel_execlists_submission.c | 2 +-
drivers/gpu/drm/i915/gt/intel_lrc.c | 4 ++--
drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 2 +-
6 files changed, 16 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index bd60d42238fb..7609db87df05 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -885,7 +885,9 @@ static int igt_shared_ctx_exec(void *arg)
return err;
}
-static int rpcs_query_batch(struct drm_i915_gem_object *rpcs, struct i915_vma *vma)
+static int rpcs_query_batch(struct drm_i915_gem_object *rpcs,
+ struct i915_vma *vma,
+ struct intel_engine_cs *engine)
{
u32 *cmd;
@@ -896,7 +898,7 @@ static int rpcs_query_batch(struct drm_i915_gem_object *rpcs, struct i915_vma *v
return PTR_ERR(cmd);
*cmd++ = MI_STORE_REGISTER_MEM_GEN8;
- *cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE(RENDER_RING_BASE));
+ *cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE(engine->mmio_base));
*cmd++ = lower_32_bits(vma->node.start);
*cmd++ = upper_32_bits(vma->node.start);
*cmd = MI_BATCH_BUFFER_END;
@@ -957,7 +959,7 @@ emit_rpcs_query(struct drm_i915_gem_object *obj,
if (err)
goto err_vma;
- err = rpcs_query_batch(rpcs, vma);
+ err = rpcs_query_batch(rpcs, vma, ce->engine);
if (err)
goto err_batch;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 3150c0847f65..edba18c942cf 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -208,6 +208,8 @@ u32 intel_engine_context_size(struct intel_gt *gt, u8 class)
BUILD_BUG_ON(I915_GTT_PAGE_SIZE != PAGE_SIZE);
switch (class) {
+ case COMPUTE_CLASS:
+ fallthrough;
case RENDER_CLASS:
switch (GRAPHICS_VER(gt->i915)) {
default:
@@ -431,6 +433,10 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id,
if (GRAPHICS_VER(i915) == 12 && engine->class == RENDER_CLASS)
engine->props.preempt_timeout_ms = 0;
+ /* features common between engines sharing EUs */
+ if (engine->class == RENDER_CLASS || engine->class == COMPUTE_CLASS)
+ engine->flags |= I915_ENGINE_HAS_RCS_REG_STATE;
+
engine->defaults = engine->props; /* never to change again */
engine->context_size = intel_engine_context_size(gt, engine->class);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index f4533ccafbaf..5fa5f21bbf2d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -524,6 +524,7 @@ struct intel_engine_cs {
#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6)
#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7)
#define I915_ENGINE_WANT_FORCED_PREEMPTION BIT(8)
+#define I915_ENGINE_HAS_RCS_REG_STATE BIT(9)
unsigned int flags;
/*
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 961d795220a3..47fca5ebfa76 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3480,7 +3480,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
logical_ring_default_vfuncs(engine);
logical_ring_default_irqs(engine);
- if (engine->class == RENDER_CLASS)
+ if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE)
rcs_submission_override(engine);
lrc_init_wa_ctx(engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 004e1216e654..d333400d29fe 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -623,7 +623,7 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
GEM_BUG_ON(GRAPHICS_VER(engine->i915) >= 12 &&
!intel_engine_has_relative_mmio(engine));
- if (engine->class == RENDER_CLASS) {
+ if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) {
if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
return dg2_rcs_offsets;
else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
@@ -1619,7 +1619,7 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine)
unsigned int i;
int err;
- if (engine->class != RENDER_CLASS)
+ if (!(engine->flags & I915_ENGINE_HAS_RCS_REG_STATE))
return;
switch (GRAPHICS_VER(engine->i915)) {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index b0de9110884a..891b98236155 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -3776,7 +3776,7 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine)
guc_default_irqs(engine);
guc_init_breadcrumbs(engine);
- if (engine->class == RENDER_CLASS)
+ if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE)
rcs_submission_override(engine);
lrc_init_wa_ctx(engine);
--
2.34.1
