Robert noticed that the FF_SLICE_CS_CHICKEN2 offset was wrong. Ooops.
Ville noticed that the write was wrong since FF_SLICE_CS_CHICKEN2 is a
masked register. Re-oops.
A wonder if went through 2 people while having roughly a bug per line...
The problem was introduced in the original patch:
  commit 
2caa3b260aa6a3d015352c07d1bce1461825fa6c
  Author: Damien Lespiau <damien.lespiau@intel.com>
  Date:   Mon Feb 9 19:33:20 2015 +0000
      drm/i915/skl: Implement WaDisableChickenBitTSGBarrierAckForFFSliceCS
v2: Also fix the register write (Ville)
Reported-by: Robert Beckett <robert.beckett@intel.com>
Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Robert Beckett <robert.beckett@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Nick Hoath <nicholas.hoath@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
 #define HSW_NDE_RSTWRN_OPT     0x46408
 #define  RESET_PCH_HANDSHAKE_ENABLE    (1<<4)
 
-#define FF_SLICE_CS_CHICKEN2                   0x02e4
+#define FF_SLICE_CS_CHICKEN2                   0x20e4
 #define  GEN9_TSG_BARRIER_ACK_DISABLE          (1<<8)
 
 /* GEN7 chicken */
 
 
                /* WaDisableChickenBitTSGBarrierAckForFFSliceCS:skl */
                I915_WRITE(FF_SLICE_CS_CHICKEN2,
-                          I915_READ(FF_SLICE_CS_CHICKEN2) |
-                          GEN9_TSG_BARRIER_ACK_DISABLE);
+                          _MASKED_BIT_ENABLE(GEN9_TSG_BARRIER_ACK_DISABLE));
        }
 
        if (INTEL_REVID(dev) <= SKL_REVID_E0)