drm/i915/gen8: Add WaClearSlmSpaceAtContextSwitch workaround

In Indirect context w/a batch buffer,
WaClearSlmSpaceAtContextSwitch

This WA performs writes to scratch page so it must be valid, this check
is performed before initializing the batch with this WA.

v2: s/PIPE_CONTROL_FLUSH_RO_CACHES/PIPE_CONTROL_FLUSH_L3 (Ville)

v3: GTT bit in scratch address should be mbz (Chris)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Dave Gordon <david.s.gordon@intel.com>
Signed-off-by: NRafael Barbalho <rafael.barbalho@intel.com>
Signed-off-by: NArun Siluvery <arun.siluvery@linux.intel.com>
Acked-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_reg.h

@@ -415,6 +415,7 @@
 #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)

drivers/gpu/drm/i915/intel_lrc.c

@@ -1147,6 +1147,7 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *ring,
 				    uint32_t *const batch,
 				    uint32_t *offset)
 {
+	uint32_t scratch_addr;
 	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
 
 	/* WaDisableCtxRestoreArbitration:bdw,chv */
@@ -1175,6 +1176,20 @@ 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;
+
+	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);
+
 	/* Pad to end of cacheline */
 	while (index % CACHELINE_DWORDS)
 		wa_ctx_emit(batch, MI_NOOP);