[PATCH v5 08/16] drm/xe/xelp: Wait for AuxCCS invalidation to complete

[Tvrtko Ursulin]

On AuxCCS platforms we need to wait for AuxCCS invalidations to complete.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at igalia.com>
---
 drivers/gpu/drm/xe/instructions/xe_mi_commands.h | 6 ++++++
 drivers/gpu/drm/xe/xe_ring_ops.c                 | 9 ++++++++-
 drivers/gpu/drm/xe/xe_ring_ops_types.h           | 2 +-
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
index eba582058d55..ae62a8b83265 100644
--- a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
+++ b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
@@ -76,4 +76,10 @@
 #define MI_SET_APPID_SESSION_ID_MASK	REG_GENMASK(6, 0)
 #define MI_SET_APPID_SESSION_ID(x)	REG_FIELD_PREP(MI_SET_APPID_SESSION_ID_MASK, x)
 
+#define MI_SEMAPHORE_WAIT_TOKEN		(__MI_INSTR(0x1c) | XE_INSTR_NUM_DW(3)) /* XeLP+ */
+#define   MI_SEMAPHORE_REGISTER_POLL	REG_BIT(16)
+#define   MI_SEMAPHORE_POLL		REG_BIT(15)
+#define   MI_SEMAPHORE_CMP_OP_MASK	REG_GENMASK(14, 12)
+#define   MI_SEMAPHORE_SAD_EQ_SDD	REG_FIELD_PREP(MI_SEMAPHORE_CMP_OP_MASK, 4)
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 7509c41dee97..62e62f0c6787 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -56,7 +56,14 @@ static int emit_aux_table_inv(struct xe_gt *gt, struct xe_reg reg,
 	dw[i++] = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1) | MI_LRI_MMIO_REMAP_EN;
 	dw[i++] = reg.addr + gt->mmio.adj_offset;
 	dw[i++] = AUX_INV;
-	dw[i++] = MI_NOOP;
+	dw[i++] = MI_SEMAPHORE_WAIT_TOKEN |
+		  MI_SEMAPHORE_REGISTER_POLL |
+		  MI_SEMAPHORE_POLL |
+		  MI_SEMAPHORE_SAD_EQ_SDD;
+	dw[i++] = 0;
+	dw[i++] = reg.addr + gt->mmio.adj_offset;
+	dw[i++] = 0;
+	dw[i++] = 0;
 
 	return i;
 }
diff --git a/drivers/gpu/drm/xe/xe_ring_ops_types.h b/drivers/gpu/drm/xe/xe_ring_ops_types.h
index 477dc7defd72..1197fc0bf2af 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops_types.h
+++ b/drivers/gpu/drm/xe/xe_ring_ops_types.h
@@ -8,7 +8,7 @@
 
 struct xe_sched_job;
 
-#define MAX_JOB_SIZE_DW 70
+#define MAX_JOB_SIZE_DW 74
 #define MAX_JOB_SIZE_BYTES (MAX_JOB_SIZE_DW * 4)
 
 /**
-- 
2.48.0