[Intel-gfx] [PATCH v2 6/7] 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 | 24 ++++++++++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5203c79..33b0ff1 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 24a7dcd..c49f2ce 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1121,8 +1121,15 @@ create_wa_bb(struct intel_engine_cs *ring, uint32_t bb_size)
 static int gen8_init_indirectctx_bb(struct intel_engine_cs *ring,
 				    struct intel_context *ctx)
 {
+	u32 scratch_addr;
+	unsigned long flags = 0;
 	struct intel_ringbuffer *ringbuf = NULL;
 
+	if (ring->scratch.obj == NULL) {
+		DRM_ERROR("scratch page not allocated for %s\n", ring->name);
+		return -EINVAL;
+	}
+
 	ringbuf = create_wa_bb(ring, PAGE_SIZE);
 	if (!ringbuf)
 		return -ENOMEM;
@@ -1140,6 +1147,23 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *ring,
 	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, 0);
 
+	/* 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;
+
+	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
+	intel_logical_ring_emit(ringbuf, flags);
+	intel_logical_ring_emit(ringbuf, scratch_addr);
+	intel_logical_ring_emit(ringbuf, 0);
+	intel_logical_ring_emit(ringbuf, 0);
+	intel_logical_ring_emit(ringbuf, 0);
+
 	/* padding */
 	while (((unsigned long) ringbuf->tail % CACHELINE_BYTES) != 0)
 		intel_logical_ring_emit(ringbuf, MI_NOOP);
-- 
2.3.0