[Intel-gfx] [PATCH v5 5/6] drm/i915/gen8: Add WaClearSlmSpaceAtContextSwitch workaround

[Arun Siluvery]

In Indirect context w/a batch buffer,
WaClearSlmSpaceAtContextSwitch

v2: s/PIPE_CONTROL_FLUSH_RO_CACHES/PIPE_CONTROL_FLUSH_L3 (Ville)

Signed-off-by: Rafael Barbalho <rafael.barbalho at intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_reg.h  |  1 +
 drivers/gpu/drm/i915/intel_lrc.c | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index d14ad20..7637e64 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -410,6 +410,7 @@
 #define   DISPLAY_PLANE_A           (0<<20)
 #define   DISPLAY_PLANE_B           (1<<20)
 #define GFX_OP_PIPE_CONTROL(len)	((0x3<<29)|(0x3<<27)|(0x2<<24)|(len-2))
+#define   PIPE_CONTROL_FLUSH_L3				(1<<27)
 #define   PIPE_CONTROL_GLOBAL_GTT_IVB			(1<<24) /* gen7+ */
 #define   PIPE_CONTROL_MMIO_WRITE			(1<<23)
 #define   PIPE_CONTROL_STORE_DATA_INDEX			(1<<21)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index dff8303..792d559 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1106,6 +1106,7 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *ring,
 				    uint32_t *num_dwords)
 {
 	uint32_t index;
+	uint32_t scratch_addr;
 	uint32_t *batch = *wa_ctx_batch;
 
 	index = offset;
@@ -1136,6 +1137,21 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *ring,
 		wa_ctx_emit(batch, l3sqc4_flush & ~GEN8_LQSC_FLUSH_COHERENT_LINES);
 	}
 
+	/* WaClearSlmSpaceAtContextSwitch:bdw,chv */
+	/* Actual scratch location is at 128 bytes offset */
+	scratch_addr = ring->scratch.gtt_offset + 2*CACHELINE_BYTES;
+	scratch_addr |= PIPE_CONTROL_GLOBAL_GTT;
+
+	wa_ctx_emit(batch, GFX_OP_PIPE_CONTROL(6));
+	wa_ctx_emit(batch, (PIPE_CONTROL_FLUSH_L3 |
+			    PIPE_CONTROL_GLOBAL_GTT_IVB |
+			    PIPE_CONTROL_CS_STALL |
+			    PIPE_CONTROL_QW_WRITE));
+	wa_ctx_emit(batch, scratch_addr);
+	wa_ctx_emit(batch, 0);
+	wa_ctx_emit(batch, 0);
+	wa_ctx_emit(batch, 0);
+
 	/* padding */
         while (((unsigned long) (batch + index) % CACHELINE_BYTES) != 0)
 		wa_ctx_emit(batch, MI_NOOP);
-- 
2.3.0