drm/i915: Use engine relative LRIs on context setup

Daniele pointed out that relative mmio works differently in
on context restore. Instead of adding the engine mmio base to offset,
it masks out the base and adds bits [12:2] to current engine base.

This should allow us to construct context register state to be
applicable to all instances, including virtual. And avoid the trouble
of updating the registers on virtual instances when submitting work.

v2: only enable for gen12 for now (Mika)
v3: make enabling readable (Chris)

Bspec: 20206
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190906134957.25909-1-mika.kuoppala@linux.intel.com

3 files changed, 32 insertions, 9 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 15e02cb58a67..943f0663837e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -481,6 +481,7 @@ struct intel_engine_cs {
 #define I915_ENGINE_HAS_SEMAPHORES   BIT(3)
 #define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4)
 #define I915_ENGINE_IS_VIRTUAL       BIT(5)
+#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6)
 	unsigned int flags;
 
 	/*
@@ -576,6 +577,12 @@ intel_engine_is_virtual(const struct intel_engine_cs *engine)
 	return engine->flags & I915_ENGINE_IS_VIRTUAL;
 }
 
+static inline bool
+intel_engine_has_relative_mmio(const struct intel_engine_cs * const engine)
+{
+	return engine->flags & I915_ENGINE_HAS_RELATIVE_MMIO;
+}
+
 #define instdone_has_slice(dev_priv___, sseu___, slice___) \
 	((IS_GEN(dev_priv___, 7) ? 1 : ((sseu___)->slice_mask)) & BIT(slice___))
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 86e00a2db8a4..fbad403ab7ac 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -132,6 +132,8 @@
  *   address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
  */
 #define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*(x)-1)
+/* Gen11+. addr = base + (ctx_restore ? offset & GENMASK(12,2) : offset) */
+#define   MI_LRI_CS_MMIO		(1<<19)
 #define   MI_LRI_FORCE_POSTED		(1<<12)
 #define MI_STORE_REGISTER_MEM        MI_INSTR(0x24, 1)
 #define MI_STORE_REGISTER_MEM_GEN8   MI_INSTR(0x24, 2)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 87b7473a6dfb..de86ca6add09 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1214,7 +1214,10 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				unsigned int n;
 
 				GEM_BUG_ON(READ_ONCE(ve->context.inflight));
-				virtual_update_register_offsets(regs, engine);
+
+				if (!intel_engine_has_relative_mmio(engine))
+					virtual_update_register_offsets(regs,
+									engine);
 
 				if (!list_empty(&ve->context.signals))
 					virtual_xfer_breadcrumbs(ve, engine);
@@ -2939,6 +2942,9 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 		if (HAS_LOGICAL_RING_PREEMPTION(engine->i915))
 			engine->flags |= I915_ENGINE_HAS_PREEMPTION;
 	}
+
+	if (engine->class != COPY_ENGINE_CLASS && INTEL_GEN(engine->i915) >= 12)
+		engine->flags |= I915_ENGINE_HAS_RELATIVE_MMIO;
 }
 
 static void execlists_destroy(struct intel_engine_cs *engine)
@@ -3130,8 +3136,10 @@ static void execlists_init_reg_state(u32 *regs,
 				     struct intel_ring *ring)
 {
 	struct i915_ppgtt *ppgtt = vm_alias(ce->vm);
-	bool rcs = engine->class == RENDER_CLASS;
-	u32 base = engine->mmio_base;
+	const bool rcs = engine->class == RENDER_CLASS;
+	const u32 base = engine->mmio_base;
+	const u32 lri_base =
+		intel_engine_has_relative_mmio(engine) ? MI_LRI_CS_MMIO : 0;
 
 	/*
 	 * A context is actually a big batch buffer with several
@@ -3143,8 +3151,10 @@ static void execlists_init_reg_state(u32 *regs,
 	 *
 	 * Must keep consistent with virtual_update_register_offsets().
 	 */
-	regs[CTX_LRI_HEADER_0] = MI_LOAD_REGISTER_IMM(rcs ? 14 : 11) |
-				 MI_LRI_FORCE_POSTED;
+	regs[CTX_LRI_HEADER_0] =
+		MI_LOAD_REGISTER_IMM(rcs ? 14 : 11) |
+		MI_LRI_FORCE_POSTED |
+		lri_base;
 
 	CTX_REG(regs, CTX_CONTEXT_CONTROL, RING_CONTEXT_CONTROL(base),
 		_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) |
@@ -3191,7 +3201,10 @@ static void execlists_init_reg_state(u32 *regs,
 		}
 	}
 
-	regs[CTX_LRI_HEADER_1] = MI_LOAD_REGISTER_IMM(9) | MI_LRI_FORCE_POSTED;
+	regs[CTX_LRI_HEADER_1] =
+		MI_LOAD_REGISTER_IMM(9) |
+		MI_LRI_FORCE_POSTED |
+		lri_base;
 
 	CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0);
 	/* PDP values well be assigned later if needed */
@@ -3218,7 +3231,7 @@ static void execlists_init_reg_state(u32 *regs,
 	}
 
 	if (rcs) {
-		regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
+		regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1) | lri_base;
 		CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0);
 	}
 
@@ -3411,8 +3424,9 @@ static void virtual_engine_initial_hint(struct virtual_engine *ve)
 		return;
 
 	swap(ve->siblings[swp], ve->siblings[0]);
-	virtual_update_register_offsets(ve->context.lrc_reg_state,
-					ve->siblings[0]);
+	if (!intel_engine_has_relative_mmio(ve->siblings[0]))
+		virtual_update_register_offsets(ve->context.lrc_reg_state,
+						ve->siblings[0]);
 }
 
 static int virtual_context_pin(struct intel_context *ce)