Merge tag 'topic/kbl-4.7-fixes-2016-07-18' of...

Merge tag 'topic/kbl-4.7-fixes-2016-07-18' of git://anongit.freedesktop.org/drm-intel into drm-fixes

As promised here's the pile of kbl cherry-picks assembled by Mika&Rodrigo.
It's a bit much, but all well-contained to kbl code and been tested for a
while in drm-intel-next. Still separate in case too much, but in that case
I think we'd need to disable kbl by default again (which would be annoying
too) in 4.7.

* tag 'topic/kbl-4.7-fixes-2016-07-18' of git://anongit.freedesktop.org/drm-intel: (28 commits)
  drm/i915/kbl: Introduce the first official DMC for Kabylake.
  drm/i915: Introduce Kabypoint PCH for Kabylake H/DT.
  drm/i915/gen9: implement WaConextSwitchWithConcurrentTLBInvalidate
  drm/i915/gen9: Add WaFbcHighMemBwCorruptionAvoidance
  drm/i195/fbc: Add WaFbcNukeOnHostModify
  drm/i915/gen9: Add WaFbcWakeMemOn
  drm/i915/gen9: Add WaFbcTurnOffFbcWatermark
  drm/i915/kbl: Add WaClearSlmSpaceAtContextSwitch
  drm/i915/gen9: Add WaEnableChickenDCPR
  drm/i915/kbl: Add WaDisableSbeCacheDispatchPortSharing
  drm/i915/kbl: Add WaDisableGafsUnitClkGating
  drm/i915/kbl: Add WaForGAMHang
  drm/i915: Add WaInsertDummyPushConstP for bxt and kbl
  drm/i915/kbl: Add WaDisableDynamicCreditSharing
  drm/i915/kbl: Add WaDisableGamClockGating
  drm/i915/gen9: Enable must set chicken bits in config0 reg
  drm/i915/kbl: Add WaDisableLSQCROPERFforOCL
  drm/i915/kbl: Add WaDisableSDEUnitClockGating
  drm/i915/kbl: Add WaDisableFenceDestinationToSLM for A0
  drm/i915/kbl: Add WaEnableGapsTsvCreditFix
  ...

drivers/gpu/drm/i915/i915_drv.c

@@ -512,6 +512,10 @@ void intel_detect_pch(struct drm_device *dev)
 				DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n");
 				WARN_ON(!IS_SKYLAKE(dev) &&
 					!IS_KABYLAKE(dev));
+			} else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) {
+				dev_priv->pch_type = PCH_KBP;
+				DRM_DEBUG_KMS("Found KabyPoint PCH\n");
+				WARN_ON(!IS_KABYLAKE(dev));
 			} else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) ||
 				   (id == INTEL_PCH_P3X_DEVICE_ID_TYPE) ||
 				   ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) &&

drivers/gpu/drm/i915/i915_drv.h

@@ -990,6 +990,7 @@ enum intel_pch {
 	PCH_CPT,	/* Cougarpoint PCH */
 	PCH_LPT,	/* Lynxpoint PCH */
 	PCH_SPT,        /* Sunrisepoint PCH */
+	PCH_KBP,        /* Kabypoint PCH */
 	PCH_NOP,
 };
 
@@ -2600,6 +2601,15 @@ struct drm_i915_cmd_table {
 
 #define IS_BXT_REVID(p, since, until) (IS_BROXTON(p) && IS_REVID(p, since, until))
 
+#define KBL_REVID_A0		0x0
+#define KBL_REVID_B0		0x1
+#define KBL_REVID_C0		0x2
+#define KBL_REVID_D0		0x3
+#define KBL_REVID_E0		0x4
+
+#define IS_KBL_REVID(p, since, until) \
+	(IS_KABYLAKE(p) && IS_REVID(p, since, until))
+
 /*
  * The genX designation typically refers to the render engine, so render
  * capability related checks should use IS_GEN, while display and other checks
@@ -2708,11 +2718,13 @@ struct drm_i915_cmd_table {
 #define INTEL_PCH_LPT_LP_DEVICE_ID_TYPE		0x9c00
 #define INTEL_PCH_SPT_DEVICE_ID_TYPE		0xA100
 #define INTEL_PCH_SPT_LP_DEVICE_ID_TYPE		0x9D00
+#define INTEL_PCH_KBP_DEVICE_ID_TYPE		0xA200
 #define INTEL_PCH_P2X_DEVICE_ID_TYPE		0x7100
 #define INTEL_PCH_P3X_DEVICE_ID_TYPE		0x7000
 #define INTEL_PCH_QEMU_DEVICE_ID_TYPE		0x2900 /* qemu q35 has 2918 */
 
 #define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type)
+#define HAS_PCH_KBP(dev) (INTEL_PCH_TYPE(dev) == PCH_KBP)
 #define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT)
 #define HAS_PCH_LPT(dev) (INTEL_PCH_TYPE(dev) == PCH_LPT)
 #define HAS_PCH_LPT_LP(dev) (__I915__(dev)->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE)

drivers/gpu/drm/i915/i915_gem_stolen.c

@@ -55,8 +55,10 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
 		return -ENODEV;
 
 	/* See the comment at the drm_mm_init() call for more about this check.
-	 * WaSkipStolenMemoryFirstPage:bdw,chv (incomplete) */
-	if (INTEL_INFO(dev_priv)->gen == 8 && start < 4096)
+	 * WaSkipStolenMemoryFirstPage:bdw,chv,kbl (incomplete)
+	 */
+	if (start < 4096 && (IS_GEN8(dev_priv) ||
+			     IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)))
 		start = 4096;
 
 	mutex_lock(&dev_priv->mm.stolen_lock);

drivers/gpu/drm/i915/i915_irq.c

@@ -2471,7 +2471,7 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 			I915_WRITE(SDEIIR, iir);
 			ret = IRQ_HANDLED;
 
-			if (HAS_PCH_SPT(dev_priv))
+			if (HAS_PCH_SPT(dev_priv) || HAS_PCH_KBP(dev_priv))
 				spt_irq_handler(dev, iir);
 			else
 				cpt_irq_handler(dev, iir);
@@ -4661,7 +4661,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 		dev->driver->disable_vblank = gen8_disable_vblank;
 		if (IS_BROXTON(dev))
 			dev_priv->display.hpd_irq_setup = bxt_hpd_irq_setup;
-		else if (HAS_PCH_SPT(dev))
+		else if (HAS_PCH_SPT(dev) || HAS_PCH_KBP(dev))
 			dev_priv->display.hpd_irq_setup = spt_hpd_irq_setup;
 		else
 			dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup;

drivers/gpu/drm/i915/i915_reg.h

@@ -220,6 +220,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   ECOCHK_PPGTT_WT_HSW		(0x2<<3)
 #define   ECOCHK_PPGTT_WB_HSW		(0x3<<3)
 
+#define GEN8_CONFIG0			_MMIO(0xD00)
+#define  GEN9_DEFAULT_FIXES		(1 << 3 | 1 << 2 | 1 << 1)
+
 #define GAC_ECO_BITS			_MMIO(0x14090)
 #define   ECOBITS_SNB_BIT		(1<<13)
 #define   ECOBITS_PPGTT_CACHE64B	(3<<8)
@@ -1669,6 +1672,9 @@ enum skl_disp_power_wells {
 
 #define GEN7_TLB_RD_ADDR	_MMIO(0x4700)
 
+#define GAMT_CHKN_BIT_REG	_MMIO(0x4ab8)
+#define   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING	(1<<28)
+
 #if 0
 #define PRB0_TAIL	_MMIO(0x2030)
 #define PRB0_HEAD	_MMIO(0x2034)
@@ -1804,6 +1810,10 @@ enum skl_disp_power_wells {
 #define   GEN9_IZ_HASHING_MASK(slice)			(0x3 << ((slice) * 2))
 #define   GEN9_IZ_HASHING(slice, val)			((val) << ((slice) * 2))
 
+/* chicken reg for WaConextSwitchWithConcurrentTLBInvalidate */
+#define GEN9_CSFE_CHICKEN1_RCS _MMIO(0x20D4)
+#define   GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE (1 << 2)
+
 /* WaClearTdlStateAckDirtyBits */
 #define GEN8_STATE_ACK		_MMIO(0x20F0)
 #define GEN9_STATE_ACK_SLICE1	_MMIO(0x20F8)
@@ -2200,6 +2210,8 @@ enum skl_disp_power_wells {
 #define ILK_DPFC_STATUS		_MMIO(0x43210)
 #define ILK_DPFC_FENCE_YOFF	_MMIO(0x43218)
 #define ILK_DPFC_CHICKEN	_MMIO(0x43224)
+#define   ILK_DPFC_DISABLE_DUMMY0 (1<<8)
+#define   ILK_DPFC_NUKE_ON_ANY_MODIFICATION	(1<<23)
 #define ILK_FBC_RT_BASE		_MMIO(0x2128)
 #define   ILK_FBC_RT_VALID	(1<<0)
 #define   SNB_FBC_FRONT_BUFFER	(1<<1)
@@ -6031,6 +6043,7 @@ enum skl_disp_power_wells {
 #define CHICKEN_PAR1_1		_MMIO(0x42080)
 #define  DPA_MASK_VBLANK_SRD	(1 << 15)
 #define  FORCE_ARB_IDLE_PLANES	(1 << 14)
+#define  SKL_EDP_PSR_FIX_RDWRAP	(1 << 3)
 
 #define _CHICKEN_PIPESL_1_A	0x420b0
 #define _CHICKEN_PIPESL_1_B	0x420b4
@@ -6039,6 +6052,7 @@ enum skl_disp_power_wells {
 #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B)
 
 #define DISP_ARB_CTL	_MMIO(0x45000)
+#define  DISP_FBC_MEMORY_WAKE		(1<<31)
 #define  DISP_TILE_SURFACE_SWIZZLING	(1<<13)
 #define  DISP_FBC_WM_DIS		(1<<15)
 #define DISP_ARB_CTL2	_MMIO(0x45004)
@@ -6052,6 +6066,9 @@ enum skl_disp_power_wells {
 #define HSW_NDE_RSTWRN_OPT	_MMIO(0x46408)
 #define  RESET_PCH_HANDSHAKE_ENABLE	(1<<4)
 
+#define GEN8_CHICKEN_DCPR_1		_MMIO(0x46430)
+#define   MASK_WAKEMEM			(1<<13)
+
 #define SKL_DFSM			_MMIO(0x51000)
 #define SKL_DFSM_CDCLK_LIMIT_MASK	(3 << 23)
 #define SKL_DFSM_CDCLK_LIMIT_675	(0 << 23)
@@ -6069,6 +6086,7 @@ enum skl_disp_power_wells {
 #define  GEN9_TSG_BARRIER_ACK_DISABLE		(1<<8)
 
 #define GEN9_CS_DEBUG_MODE1		_MMIO(0x20ec)
+#define GEN9_CTX_PREEMPT_REG		_MMIO(0x2248)
 #define GEN8_CS_CHICKEN1		_MMIO(0x2580)
 
 /* GEN7 chicken */
@@ -6076,6 +6094,7 @@ enum skl_disp_power_wells {
 # define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1<<10) | (1<<26))
 # define GEN9_RHWO_OPTIMIZATION_DISABLE		(1<<14)
 #define COMMON_SLICE_CHICKEN2			_MMIO(0x7014)
+# define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION (1<<8)
 # define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE	(1<<0)
 
 #define HIZ_CHICKEN					_MMIO(0x7018)
@@ -6921,6 +6940,7 @@ enum skl_disp_power_wells {
 #define    EDRAM_SETS_IDX(cap)			(((cap) >> 8) & 0x3)
 
 #define GEN6_UCGCTL1				_MMIO(0x9400)
+# define GEN6_GAMUNIT_CLOCK_GATE_DISABLE		(1 << 22)
 # define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE		(1 << 16)
 # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE		(1 << 5)
 # define GEN6_CSUNIT_CLOCK_GATE_DISABLE			(1 << 7)
@@ -6937,6 +6957,7 @@ enum skl_disp_power_wells {
 
 #define GEN7_UCGCTL4				_MMIO(0x940c)
 #define  GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1<<25)
+#define  GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE	(1<<14)
 
 #define GEN6_RCGCTL1				_MMIO(0x9410)
 #define GEN6_RCGCTL2				_MMIO(0x9414)

drivers/gpu/drm/i915/intel_csr.c

@@ -41,16 +41,22 @@
  * be moved to FW_FAILED.
  */
 
+#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin"
+MODULE_FIRMWARE(I915_CSR_KBL);
+#define KBL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 1)
+
 #define I915_CSR_SKL "i915/skl_dmc_ver1.bin"
+MODULE_FIRMWARE(I915_CSR_SKL);
+#define SKL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 23)
+
 #define I915_CSR_BXT "i915/bxt_dmc_ver1.bin"
+MODULE_FIRMWARE(I915_CSR_BXT);
+#define BXT_CSR_VERSION_REQUIRED	CSR_VERSION(1, 7)
 
 #define FIRMWARE_URL  "https://01.org/linuxgraphics/intel-linux-graphics-firmwares"
 
-MODULE_FIRMWARE(I915_CSR_SKL);
-MODULE_FIRMWARE(I915_CSR_BXT);
 
-#define SKL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 23)
-#define BXT_CSR_VERSION_REQUIRED	CSR_VERSION(1, 7)
+
 
 #define CSR_MAX_FW_SIZE			0x2FFF
 #define CSR_DEFAULT_FW_OFFSET		0xFFFFFFFF
@@ -169,12 +175,10 @@ struct stepping_info {
 	char substepping;
 };
 
-/*
- * Kabylake derivated from Skylake H0, so SKL H0
- * is the right firmware for KBL A0 (revid 0).
- */
 static const struct stepping_info kbl_stepping_info[] = {
-	{'H', '0'}, {'I', '0'}
+	{'A', '0'}, {'B', '0'}, {'C', '0'},
+	{'D', '0'}, {'E', '0'}, {'F', '0'},
+	{'G', '0'}, {'H', '0'}, {'I', '0'},
 };
 
 static const struct stepping_info skl_stepping_info[] = {
@@ -298,7 +302,9 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv,
 
 	csr->version = css_header->version;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_KABYLAKE(dev_priv)) {
+		required_min_version = KBL_CSR_VERSION_REQUIRED;
+	} else if (IS_SKYLAKE(dev_priv)) {
 		required_min_version = SKL_CSR_VERSION_REQUIRED;
 	} else if (IS_BROXTON(dev_priv)) {
 		required_min_version = BXT_CSR_VERSION_REQUIRED;
@@ -446,7 +452,9 @@ void intel_csr_ucode_init(struct drm_i915_private *dev_priv)
 	if (!HAS_CSR(dev_priv))
 		return;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+	if (IS_KABYLAKE(dev_priv))
+		csr->fw_path = I915_CSR_KBL;
+	else if (IS_SKYLAKE(dev_priv))
 		csr->fw_path = I915_CSR_SKL;
 	else if (IS_BROXTON(dev_priv))
 		csr->fw_path = I915_CSR_BXT;

drivers/gpu/drm/i915/intel_lrc.c

@@ -1103,15 +1103,17 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
 						uint32_t *const batch,
 						uint32_t index)
 {
+	struct drm_i915_private *dev_priv = engine->dev->dev_private;
 	uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES);
 
 	/*
-	 * WaDisableLSQCROPERFforOCL:skl
+	 * WaDisableLSQCROPERFforOCL:skl,kbl
 	 * This WA is implemented in skl_init_clock_gating() but since
 	 * this batch updates GEN8_L3SQCREG4 with default value we need to
 	 * set this bit here to retain the WA during flush.
 	 */
-	if (IS_SKL_REVID(engine->dev, 0, SKL_REVID_E0))
+	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0) ||
+	    IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0))
 		l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS;
 
 	wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
@@ -1273,6 +1275,7 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine,
 {
 	int ret;
 	struct drm_device *dev = engine->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
 
 	/* WaDisableCtxRestoreArbitration:skl,bxt */
@@ -1286,6 +1289,22 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine,
 		return ret;
 	index = ret;
 
+	/* WaClearSlmSpaceAtContextSwitch:kbl */
+	/* Actual scratch location is at 128 bytes offset */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) {
+		uint32_t scratch_addr
+			= engine->scratch.gtt_offset + 2*CACHELINE_BYTES;
+
+		wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
+		wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
+					   PIPE_CONTROL_GLOBAL_GTT_IVB |
+					   PIPE_CONTROL_CS_STALL |
+					   PIPE_CONTROL_QW_WRITE));
+		wa_ctx_emit(batch, index, scratch_addr);
+		wa_ctx_emit(batch, index, 0);
+		wa_ctx_emit(batch, index, 0);
+		wa_ctx_emit(batch, index, 0);
+	}
 	/* Pad to end of cacheline */
 	while (index % CACHELINE_DWORDS)
 		wa_ctx_emit(batch, index, MI_NOOP);
@@ -1687,9 +1706,10 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
 	struct intel_engine_cs *engine = ringbuf->engine;
 	u32 scratch_addr = engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
-	bool vf_flush_wa = false;
+	bool vf_flush_wa = false, dc_flush_wa = false;
 	u32 flags = 0;
 	int ret;
+	int len;
 
 	flags |= PIPE_CONTROL_CS_STALL;
 
@@ -1716,9 +1736,21 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 		 */
 		if (IS_GEN9(engine->dev))
 			vf_flush_wa = true;
+
+		/* WaForGAMHang:kbl */
+		if (IS_KBL_REVID(request->i915, 0, KBL_REVID_B0))
+			dc_flush_wa = true;
 	}
 
-	ret = intel_ring_begin(request, vf_flush_wa ? 12 : 6);
+	len = 6;
+
+	if (vf_flush_wa)
+		len += 6;
+
+	if (dc_flush_wa)
+		len += 12;
+
+	ret = intel_ring_begin(request, len);
 	if (ret)
 		return ret;
 
@@ -1731,12 +1763,31 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 		intel_logical_ring_emit(ringbuf, 0);
 	}
 
+	if (dc_flush_wa) {
+		intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
+		intel_logical_ring_emit(ringbuf, PIPE_CONTROL_DC_FLUSH_ENABLE);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+	}
+
 	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);
+
+	if (dc_flush_wa) {
+		intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
+		intel_logical_ring_emit(ringbuf, PIPE_CONTROL_CS_STALL);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+	}
+
 	intel_logical_ring_advance(ringbuf);
 
 	return 0;

drivers/gpu/drm/i915/intel_panel.c

@@ -1731,7 +1731,8 @@ intel_panel_init_backlight_funcs(struct intel_panel *panel)
 		panel->backlight.set = bxt_set_backlight;
 		panel->backlight.get = bxt_get_backlight;
 		panel->backlight.hz_to_pwm = bxt_hz_to_pwm;
-	} else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_SPT(dev_priv)) {
+	} else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_SPT(dev_priv) ||
+		   HAS_PCH_KBP(dev_priv)) {
 		panel->backlight.setup = lpt_setup_backlight;
 		panel->backlight.enable = lpt_enable_backlight;
 		panel->backlight.disable = lpt_disable_backlight;

drivers/gpu/drm/i915/intel_pm.c

@@ -54,10 +54,38 @@
 #define INTEL_RC6p_ENABLE			(1<<1)
 #define INTEL_RC6pp_ENABLE			(1<<2)
 
+static void gen9_init_clock_gating(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl */
+	I915_WRITE(CHICKEN_PAR1_1,
+		   I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP);
+
+	I915_WRITE(GEN8_CONFIG0,
+		   I915_READ(GEN8_CONFIG0) | GEN9_DEFAULT_FIXES);
+
+	/* WaEnableChickenDCPR:skl,bxt,kbl */
+	I915_WRITE(GEN8_CHICKEN_DCPR_1,
+		   I915_READ(GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM);
+
+	/* WaFbcTurnOffFbcWatermark:skl,bxt,kbl */
+	/* WaFbcWakeMemOn:skl,bxt,kbl */
+	I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
+		   DISP_FBC_WM_DIS |
+		   DISP_FBC_MEMORY_WAKE);
+
+	/* WaFbcHighMemBwCorruptionAvoidance:skl,bxt,kbl */
+	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
+		   ILK_DPFC_DISABLE_DUMMY0);
+}
+
 static void bxt_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	gen9_init_clock_gating(dev);
+
 	/* WaDisableSDEUnitClockGating:bxt */
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
@@ -6698,6 +6726,38 @@ static void lpt_suspend_hw(struct drm_device *dev)
 	}
 }
 
+static void kabylake_init_clock_gating(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	gen9_init_clock_gating(dev);
+
+	/* WaDisableSDEUnitClockGating:kbl */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+		I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
+			   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaDisableGamClockGating:kbl */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+		I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
+			   GEN6_GAMUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaFbcNukeOnHostModify:kbl */
+	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
+		   ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
+}
+
+static void skylake_init_clock_gating(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	gen9_init_clock_gating(dev);
+
+	/* WaFbcNukeOnHostModify:skl */
+	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
+		   ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
+}
+
 static void broadwell_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -7163,9 +7223,9 @@ static void nop_init_clock_gating(struct drm_device *dev)
 void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
 {
 	if (IS_SKYLAKE(dev_priv))
-		dev_priv->display.init_clock_gating = nop_init_clock_gating;
+		dev_priv->display.init_clock_gating = skylake_init_clock_gating;
 	else if (IS_KABYLAKE(dev_priv))
-		dev_priv->display.init_clock_gating = nop_init_clock_gating;
+		dev_priv->display.init_clock_gating = kabylake_init_clock_gating;
 	else if (IS_BROXTON(dev_priv))
 		dev_priv->display.init_clock_gating = bxt_init_clock_gating;
 	else if (IS_BROADWELL(dev_priv))

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -913,24 +913,26 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine)
 {
 	struct drm_device *dev = engine->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t tmp;
 	int ret;
 
-	/* WaEnableLbsSlaRetryTimerDecrement:skl */
+	/* WaConextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl */
+	I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE));
+
+	/* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl */
 	I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
 		   GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
 
-	/* WaDisableKillLogic:bxt,skl */
+	/* WaDisableKillLogic:bxt,skl,kbl */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
 		   ECOCHK_DIS_TLB);
 
-	/* WaClearFlowControlGpgpuContextSave:skl,bxt */
-	/* WaDisablePartialInstShootdown:skl,bxt */
+	/* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl */
+	/* WaDisablePartialInstShootdown:skl,bxt,kbl */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
 			  FLOW_CONTROL_ENABLE |
 			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
 
-	/* Syncing dependencies between camera and graphics:skl,bxt */
+	/* Syncing dependencies between camera and graphics:skl,bxt,kbl */
 	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
 			  GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
 
@@ -952,18 +954,18 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine)
 		 */
 	}
 
-	/* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt */
-	/* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt */
+	/* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl */
+	/* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl */
 	WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
 			  GEN9_ENABLE_YV12_BUGFIX |
 			  GEN9_ENABLE_GPGPU_PREEMPTION);
 
-	/* Wa4x4STCOptimizationDisable:skl,bxt */
-	/* WaDisablePartialResolveInVc:skl,bxt */
+	/* Wa4x4STCOptimizationDisable:skl,bxt,kbl */
+	/* WaDisablePartialResolveInVc:skl,bxt,kbl */
 	WA_SET_BIT_MASKED(CACHE_MODE_1, (GEN8_4x4_STC_OPTIMIZATION_DISABLE |
 					 GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE));
 
-	/* WaCcsTlbPrefetchDisable:skl,bxt */
+	/* WaCcsTlbPrefetchDisable:skl,bxt,kbl */
 	WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
 			  GEN9_CCS_TLB_PREFETCH_ENABLE);
 
@@ -973,31 +975,57 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine)
 		WA_SET_BIT_MASKED(SLICE_ECO_CHICKEN0,
 				  PIXEL_MASK_CAMMING_DISABLE);
 
-	/* WaForceContextSaveRestoreNonCoherent:skl,bxt */
-	tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT;
-	if (IS_SKL_REVID(dev, SKL_REVID_F0, REVID_FOREVER) ||
-	    IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER))
-		tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE;
-	WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp);
+	/* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl */
+	WA_SET_BIT_MASKED(HDC_CHICKEN0,
+			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
+			  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE);
+
+	/* WaForceEnableNonCoherent and WaDisableHDCInvalidation are
+	 * both tied to WaForceContextSaveRestoreNonCoherent
+	 * in some hsds for skl. We keep the tie for all gen9. The
+	 * documentation is a bit hazy and so we want to get common behaviour,
+	 * even though there is no clear evidence we would need both on kbl/bxt.
+	 * This area has been source of system hangs so we play it safe
+	 * and mimic the skl regardless of what bspec says.
+	 *
+	 * Use Force Non-Coherent whenever executing a 3D context. This
+	 * is a workaround for a possible hang in the unlikely event
+	 * a TLB invalidation occurs during a PSD flush.
+	 */
+
+	/* WaForceEnableNonCoherent:skl,bxt,kbl */
+	WA_SET_BIT_MASKED(HDC_CHICKEN0,
+			  HDC_FORCE_NON_COHERENT);
+
+	/* WaDisableHDCInvalidation:skl,bxt,kbl */
+	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
+		   BDW_DISABLE_HDC_INVALIDATION);
 
-	/* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt */
-	if (IS_SKYLAKE(dev) || IS_BXT_REVID(dev, 0, BXT_REVID_B0))
+	/* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl */
+	if (IS_SKYLAKE(dev_priv) ||
+	    IS_KABYLAKE(dev_priv) ||
+	    IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0))
 		WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
 				  GEN8_SAMPLER_POWER_BYPASS_DIS);
 
-	/* WaDisableSTUnitPowerOptimization:skl,bxt */
+	/* WaDisableSTUnitPowerOptimization:skl,bxt,kbl */
 	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
 
-	/* WaOCLCoherentLineFlush:skl,bxt */
+	/* WaOCLCoherentLineFlush:skl,bxt,kbl */
 	I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) |
 				    GEN8_LQSC_FLUSH_COHERENT_LINES));
 
-	/* WaEnablePreemptionGranularityControlByUMD:skl,bxt */
+	/* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt */
+	ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG);
+	if (ret)
+		return ret;
+
+	/* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl */
 	ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1);
 	if (ret)
 		return ret;
 
-	/* WaAllowUMDToModifyHDCChicken1:skl,bxt */
+	/* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl */
 	ret = wa_ring_whitelist_reg(engine, GEN8_HDC_CHICKEN1);
 	if (ret)
 		return ret;
@@ -1092,22 +1120,6 @@ static int skl_init_workarounds(struct intel_engine_cs *engine)
 		WA_SET_BIT_MASKED(HIZ_CHICKEN,
 				  BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
 
-	/* This is tied to WaForceContextSaveRestoreNonCoherent */
-	if (IS_SKL_REVID(dev, 0, REVID_FOREVER)) {
-		/*
-		 *Use Force Non-Coherent whenever executing a 3D context. This
-		 * is a workaround for a possible hang in the unlikely event
-		 * a TLB invalidation occurs during a PSD flush.
-		 */
-		/* WaForceEnableNonCoherent:skl */
-		WA_SET_BIT_MASKED(HDC_CHICKEN0,
-				  HDC_FORCE_NON_COHERENT);
-
-		/* WaDisableHDCInvalidation:skl */
-		I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
-			   BDW_DISABLE_HDC_INVALIDATION);
-	}
-
 	/* WaBarrierPerformanceFixDisable:skl */
 	if (IS_SKL_REVID(dev, SKL_REVID_C0, SKL_REVID_D0))
 		WA_SET_BIT_MASKED(HDC_CHICKEN0,
@@ -1120,6 +1132,9 @@ static int skl_init_workarounds(struct intel_engine_cs *engine)
 			GEN7_HALF_SLICE_CHICKEN1,
 			GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
 
+	/* WaDisableGafsUnitClkGating:skl */
+	WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
+
 	/* WaDisableLSQCROPERFforOCL:skl */
 	ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4);
 	if (ret)
@@ -1174,6 +1189,63 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine)
 			return ret;
 	}
 
+	/* WaInsertDummyPushConstPs:bxt */
+	if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0))
+		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+				  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
+
+	return 0;
+}
+
+static int kbl_init_workarounds(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	int ret;
+
+	ret = gen9_init_workarounds(engine);
+	if (ret)
+		return ret;
+
+	/* WaEnableGapsTsvCreditFix:kbl */
+	I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
+				   GEN9_GAPS_TSV_CREDIT_DISABLE));
+
+	/* WaDisableDynamicCreditSharing:kbl */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+		WA_SET_BIT(GAMT_CHKN_BIT_REG,
+			   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING);
+
+	/* WaDisableFenceDestinationToSLM:kbl (pre-prod) */
+	if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0))
+		WA_SET_BIT_MASKED(HDC_CHICKEN0,
+				  HDC_FENCE_DEST_SLM_DISABLE);
+
+	/* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes
+	 * involving this register should also be added to WA batch as required.
+	 */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0))
+		/* WaDisableLSQCROPERFforOCL:kbl */
+		I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
+			   GEN8_LQSC_RO_PERF_DIS);
+
+	/* WaInsertDummyPushConstPs:kbl */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+				  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
+
+	/* WaDisableGafsUnitClkGating:kbl */
+	WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaDisableSbeCacheDispatchPortSharing:kbl */
+	WA_SET_BIT_MASKED(
+		GEN7_HALF_SLICE_CHICKEN1,
+		GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
+
+	/* WaDisableLSQCROPERFforOCL:kbl */
+	ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -1199,6 +1271,9 @@ int init_workarounds_ring(struct intel_engine_cs *engine)
 	if (IS_BROXTON(dev))
 		return bxt_init_workarounds(engine);
 
+	if (IS_KABYLAKE(dev_priv))
+		return kbl_init_workarounds(engine);
+
 	return 0;
 }