drm/i915:bxt: implement WaProgramL3SqcReg1DefaultForPerf

This patch applies a performance enhancement workaround
based on analysis of DX and OCL S-Curve workloads. We
increase the General Priority Credits for L3SQ from the
hardware default of 56 to the max value 62, and decrease
the High Priority credits from 8 to 2.

v2: Only apply to B0 onwards

v3: Move w/a to per engine init, ie bxt_init_workarounds

Signed-off-by: Tim Gore <tim.gore@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1461314761-36854-1-git-send-email-tim.gore@intel.com
Reviewed-by: Michel Thierry <michel.thierry@intel.com>

drivers/gpu/drm/i915/i915_reg.h

@@ -6090,6 +6090,7 @@ enum skl_disp_power_wells {
 
 #define GEN8_L3SQCREG1				_MMIO(0xB100)
 #define  BDW_WA_L3SQCREG1_DEFAULT		0x784000
+#define  BXT_WA_L3SQCREG1_DEFAULT		0xF84000
 
 #define GEN7_L3CNTLREG1				_MMIO(0xB01C)
 #define  GEN7_WA_FOR_GEN7_L3_CONTROL			0x3C47FF8C

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -1180,6 +1180,10 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine)
 			return ret;
 	}
 
+	/* WaProgramL3SqcReg1DefaultForPerf:bxt */
+	if (IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER))
+		I915_WRITE(GEN8_L3SQCREG1, BXT_WA_L3SQCREG1_DEFAULT);
+
 	return 0;
 }