[Intel-gfx] [PATCH v4 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 | 19 +++++++++++++++++++
 2 files changed, 20 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 92556b9..27e6692 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1085,6 +1085,8 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *ring,
 	uint32_t index;
 	struct page *page;
 	uint32_t *cmd;
+	u32 scratch_addr;
+	unsigned long flags = 0;
 
 	page = i915_gem_object_get_page(ring->wa_ctx.obj, 0);
 	cmd = kmap_atomic(page);
@@ -1117,6 +1119,23 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *ring,
 			~GEN8_LQSC_FLUSH_COHERENT_LINES;
 	}
 
+	/* WaClearSlmSpaceAtContextSwitch:bdw,chv */
+	flags = PIPE_CONTROL_FLUSH_L3 |
+		PIPE_CONTROL_GLOBAL_GTT_IVB |
+		PIPE_CONTROL_CS_STALL |
+		PIPE_CONTROL_QW_WRITE;
+
+	/* Actual scratch location is at 128 bytes offset */
+	scratch_addr = ring->scratch.gtt_offset + 2*CACHELINE_BYTES;
+	scratch_addr |= PIPE_CONTROL_GLOBAL_GTT;
+
+	cmd[index++] = GFX_OP_PIPE_CONTROL(6);
+	cmd[index++] = flags;
+	cmd[index++] = scratch_addr;
+	cmd[index++] = 0;
+	cmd[index++] = 0;
+	cmd[index++] = 0;
+
 	/* padding */
         while (((unsigned long) (cmd + index) % CACHELINE_BYTES) != 0)
 		cmd[index++] = MI_NOOP;
-- 
2.3.0