drm/i915: implement WaClearTdlStateAckDirtyBits

This is to fix a GPU hang seen with mid thread pre-emption
and pooled EUs.

v2. Use IS_BXT_REVID instead of IS_BROXTON and INTEL_REVID

v3. And use correct type for register addresses

Signed-off-by: Tim Gore <tim.gore@intel.com>
Reviewed-by: Arun Siluvery <arun.siluvery@linux.intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1458571049-854-1-git-send-email-tim.gore@intel.com

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0744759..cea5a39 100644 (file)
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1790,6 +1790,18 @@ enum skl_disp_power_wells {
 #define   GEN9_IZ_HASHING_MASK(slice)                  (0x3 << ((slice) * 2))
 #define   GEN9_IZ_HASHING(slice, val)                  ((val) << ((slice) * 2))
 
+/* WaClearTdlStateAckDirtyBits */
+#define GEN8_STATE_ACK         _MMIO(0x20F0)
+#define GEN9_STATE_ACK_SLICE1  _MMIO(0x20F8)
+#define GEN9_STATE_ACK_SLICE2  _MMIO(0x2100)
+#define   GEN9_STATE_ACK_TDL0 (1 << 12)
+#define   GEN9_STATE_ACK_TDL1 (1 << 13)
+#define   GEN9_STATE_ACK_TDL2 (1 << 14)
+#define   GEN9_STATE_ACK_TDL3 (1 << 15)
+#define   GEN9_SUBSLICE_TDL_ACK_BITS \
+       (GEN9_STATE_ACK_TDL3 | GEN9_STATE_ACK_TDL2 | \
+        GEN9_STATE_ACK_TDL1 | GEN9_STATE_ACK_TDL0)
+
 #define GFX_MODE       _MMIO(0x2520)
 #define GFX_MODE_GEN7  _MMIO(0x229c)
 #define RING_MODE_GEN7(ring)   _MMIO((ring)->mmio_base+0x29c)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index f209ecf..0d6dc5e 100644 (file)
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1448,6 +1448,25 @@ static int gen9_init_perctx_bb(struct intel_engine_cs *engine,
                wa_ctx_emit(batch, index, MI_NOOP);
        }
 
+       /* WaClearTdlStateAckDirtyBits:bxt */
+       if (IS_BXT_REVID(dev, 0, BXT_REVID_B0)) {
+               wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(4));
+
+               wa_ctx_emit_reg(batch, index, GEN8_STATE_ACK);
+               wa_ctx_emit(batch, index, _MASKED_BIT_DISABLE(GEN9_SUBSLICE_TDL_ACK_BITS));
+
+               wa_ctx_emit_reg(batch, index, GEN9_STATE_ACK_SLICE1);
+               wa_ctx_emit(batch, index, _MASKED_BIT_DISABLE(GEN9_SUBSLICE_TDL_ACK_BITS));
+
+               wa_ctx_emit_reg(batch, index, GEN9_STATE_ACK_SLICE2);
+               wa_ctx_emit(batch, index, _MASKED_BIT_DISABLE(GEN9_SUBSLICE_TDL_ACK_BITS));
+
+               wa_ctx_emit_reg(batch, index, GEN7_ROW_CHICKEN2);
+               /* dummy write to CS, mask bits are 0 to ensure the register is not modified */
+               wa_ctx_emit(batch, index, 0x0);
+               wa_ctx_emit(batch, index, MI_NOOP);
+       }
+
        /* WaDisableCtxRestoreArbitration:skl,bxt */
        if (IS_SKL_REVID(dev, 0, SKL_REVID_D0) ||
            IS_BXT_REVID(dev, 0, BXT_REVID_A1))