[Intel-xe] [PATCH] drm/xe: Reinstate render / compute cache invalidation in ring ops

[Matthew Brost]

Render / compute engines have additional caches (not just TLBs) that
need to be invalidated each batch, reinstate these invalidations in ring
ops.

Suggested-by: Matt Roper <matthew.d.roper at intel.com>
Signed-off-by: Matthew Brost <matthew.brost at intel.com>
---
 drivers/gpu/drm/xe/regs/xe_gpu_commands.h |  5 ++++
 drivers/gpu/drm/xe/xe_ring_ops.c          | 30 +++++++++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/drivers/gpu/drm/xe/regs/xe_gpu_commands.h b/drivers/gpu/drm/xe/regs/xe_gpu_commands.h
index 288576035ce3..a1d7ab16a2c6 100644
--- a/drivers/gpu/drm/xe/regs/xe_gpu_commands.h
+++ b/drivers/gpu/drm/xe/regs/xe_gpu_commands.h
@@ -57,20 +57,25 @@
 #define   BLT_DEPTH_32			(3<<24)
 
 #define GFX_OP_PIPE_CONTROL(len)	((0x3<<29)|(0x3<<27)|(0x2<<24)|((len)-2))
+#define   PIPE_CONTROL_COMMAND_CACHE_INVALIDATE		(1<<29)
 #define   PIPE_CONTROL_TILE_CACHE_FLUSH			(1<<28)
 #define   PIPE_CONTROL_AMFS_FLUSH			(1<<25)
 #define   PIPE_CONTROL_GLOBAL_GTT_IVB			(1<<24)
+#define   PIPE_CONTROL_STORE_DATA_INDEX			(1<<21)
 #define   PIPE_CONTROL_CS_STALL				(1<<20)
 #define   PIPE_CONTROL_GLOBAL_SNAPSHOT_RESET		(1<<19)
 #define   PIPE_CONTROL_PSD_SYNC				(1<<17)
 #define   PIPE_CONTROL_QW_WRITE				(1<<14)
 #define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
 #define   PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH	(1<<12)
+#define   PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE	(1<<11)
 #define   PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE		(1<<10)
 #define   PIPE_CONTROL_INDIRECT_STATE_DISABLE		(1<<9)
 #define   PIPE_CONTROL_FLUSH_ENABLE			(1<<7)
 #define   PIPE_CONTROL_DC_FLUSH_ENABLE			(1<<5)
 #define   PIPE_CONTROL_VF_CACHE_INVALIDATE		(1<<4)
+#define   PIPE_CONTROL_CONST_CACHE_INVALIDATE		(1<<3)
+#define   PIPE_CONTROL_STATE_CACHE_INVALIDATE		(1<<2)
 #define   PIPE_CONTROL_STALL_AT_SCOREBOARD		(1<<1)
 #define   PIPE_CONTROL_DEPTH_CACHE_FLUSH		(1<<0)
 
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 4441fe60cd00..918e819e7c91 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -106,6 +106,30 @@ static int emit_flush_invalidate(u32 flag, u32 *dw, int i)
 	return i;
 }
 
+static int emit_pipe_invalidate(u32 mask_flags, u32 *dw, int i)
+{
+	u32 flags = PIPE_CONTROL_CS_STALL |
+		PIPE_CONTROL_COMMAND_CACHE_INVALIDATE |
+		PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE |
+		PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
+		PIPE_CONTROL_VF_CACHE_INVALIDATE |
+		PIPE_CONTROL_CONST_CACHE_INVALIDATE |
+		PIPE_CONTROL_STATE_CACHE_INVALIDATE |
+		PIPE_CONTROL_QW_WRITE |
+		PIPE_CONTROL_STORE_DATA_INDEX;
+
+	flags &= ~mask_flags;
+
+	dw[i++] = GFX_OP_PIPE_CONTROL(6);
+	dw[i++] = flags;
+	dw[i++] = LRC_PPHWSP_SCRATCH_ADDR;
+	dw[i++] = 0;
+	dw[i++] = 0;
+	dw[i++] = 0;
+
+	return i;
+}
+
 #define MI_STORE_QWORD_IMM_GEN8_POSTED (MI_INSTR(0x20, 3) | (1 << 21))
 
 static int emit_store_imm_ppgtt_posted(u64 addr, u64 value,
@@ -212,8 +236,14 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 	struct xe_gt *gt = job->engine->gt;
 	struct xe_device *xe = gt_to_xe(gt);
 	bool pvc = xe->info.platform == XE_PVC;
+	u32 mask_flags = 0;
 
 	dw[i++] = preparser_disable(true);
+	if (pvc)
+		mask_flags = PIPE_CONTROL_3D_ARCH_FLAGS;
+	else if (job->engine->class == XE_ENGINE_CLASS_COMPUTE)
+		mask_flags = PIPE_CONTROL_3D_ENGINE_FLAGS;
+	i = emit_pipe_invalidate(mask_flags, dw, i);
 	/* Wa_1809175790 */
 	if (!xe->info.has_flat_ccs)
 		i = emit_aux_table_inv(gt, GEN12_GFX_CCS_AUX_NV.reg, dw, i);
-- 
2.34.1