[PATCH 1/1] Engine relative MMIO for trybot

[Matthew Brost]

Signed-off-by: Matthew Brost <matthew.brost at intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c  |  7 ++---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c    | 27 ++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  3 +++
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h |  6 +++++
 drivers/gpu/drm/i915/gt/intel_lrc.c          |  4 +--
 5 files changed, 41 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 188dee13e017..a8a195bfcb57 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1211,7 +1211,7 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)
 {
 	struct i915_address_space *vm = rq->context->vm;
 	struct intel_engine_cs *engine = rq->engine;
-	u32 base = engine->mmio_base;
+	u32 base = engine->lri_mmio_base;
 	u32 *cs;
 	int i;
 
@@ -1223,7 +1223,7 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		*cs++ = MI_LOAD_REGISTER_IMM(2);
+		*cs++ = MI_LOAD_REGISTER_IMM_REL(engine, 2);
 
 		*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 0));
 		*cs++ = upper_32_bits(pd_daddr);
@@ -1245,7 +1245,8 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		*cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES) | MI_LRI_FORCE_POSTED;
+		*cs++ = MI_LOAD_REGISTER_IMM_REL(engine, 2 * GEN8_3LVL_PDPES) |
+			MI_LRI_FORCE_POSTED;
 		for (i = GEN8_3LVL_PDPES; i--; ) {
 			const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 3f9a811eb02b..cd7ceb9f6c95 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -15,6 +15,7 @@
 #include "intel_engine_pm.h"
 #include "intel_engine_user.h"
 #include "intel_execlists_submission.h"
+#include "intel_gpu_commands.h"
 #include "intel_gt.h"
 #include "intel_gt_requests.h"
 #include "intel_gt_pm.h"
@@ -222,6 +223,30 @@ static u32 __engine_mmio_base(struct drm_i915_private *i915,
 	return bases[i].base;
 }
 
+static bool i915_engine_has_relative_lri(const struct intel_engine_cs *engine)
+{
+	if (INTEL_GEN(engine->i915) < 11)
+		return false;
+
+	/* Gen 12+ supports relative addressing on BCS engine */
+	if (engine->class == COPY_ENGINE_CLASS &&
+	    INTEL_GEN(engine->i915) == 11)
+		return false;
+
+	return true;
+}
+
+static void lri_init(struct intel_engine_cs *engine)
+{
+	if (i915_engine_has_relative_lri(engine)) {
+		engine->lri_cmd_mode = MI_LRI_LRM_CS_MMIO;
+		engine->lri_mmio_base = 0;
+	} else {
+		engine->lri_cmd_mode = 0;
+		engine->lri_mmio_base = engine->mmio_base;
+	}
+}
+
 static void __sprint_engine_name(struct intel_engine_cs *engine)
 {
 	/*
@@ -329,6 +354,8 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
 
+	lri_init(engine);
+
 	ewma__engine_latency_init(&engine->latency);
 	seqcount_init(&engine->stats.lock);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 9ef349cd5cea..e48da23c9b0f 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -310,6 +310,9 @@ struct intel_engine_cs {
 	u32 context_size;
 	u32 mmio_base;
 
+	u32 lri_mmio_base;
+	u32 lri_cmd_mode;
+
 	/*
 	 * Some w/a require forcewake to be held (which prevents RC6) while
 	 * a particular engine is active. If so, we set fw_domain to which
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 2694dbb9967e..f0f101134fd8 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -134,8 +134,14 @@
  *   simply ignores the register load under certain conditions.
  * - One can actually load arbitrary many arbitrary registers: Simply issue x
  *   address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
+ * - Newer hardware supports engine relative addressing but older hardware does
+ *   not. This is required for hw engine load balancing. The
+ *   MI_LOAD_REGISTER_IMM_REL macro can be used on both newer and older
+ *   hardware.
  */
 #define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*(x)-1)
+#define MI_LOAD_REGISTER_IMM_REL(egine, x)	\
+	(MI_LOAD_REGISTER_IMM(x) | engine->lri_cmd_mode)
 /* Gen11+. addr = base + (ctx_restore ? offset & GENMASK(12,2) : offset) */
 #define   MI_LRI_LRM_CS_MMIO		REG_BIT(19)
 #define   MI_LRI_FORCE_POSTED		(1<<12)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index aafe2a4df496..390628666564 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -44,11 +44,9 @@ static void set_offsets(u32 *regs,
 		flags = *data >> 6;
 		data++;
 
-		*regs = MI_LOAD_REGISTER_IMM(count);
+		*regs = MI_LOAD_REGISTER_IMM_REL(engine, count);
 		if (flags & POSTED)
 			*regs |= MI_LRI_FORCE_POSTED;
-		if (INTEL_GEN(engine->i915) >= 11)
-			*regs |= MI_LRI_LRM_CS_MMIO;
 		regs++;
 
 		GEM_BUG_ON(!count);
-- 
2.28.0