Merge tag 'drm-intel-next-2015-11-20-merged' of...

Merge tag 'drm-intel-next-2015-11-20-merged' of git://anongit.freedesktop.org/drm-intel into drm-next

drm-intel-next-2015-11-20-rebased:
4 weeks because of my vacation, so a bit more:
- final bits of the typesafe register mmio functions (Ville)
- power domain fix for hdmi detection (Imre)
- tons of fixes and improvements to the psr code (Rodrigo)
- refactoring of the dp detection code (Ander)
- complete rework of the dmc loader and dc5/dc6 handling (Imre, Patrik and
  others)
- dp compliance improvements from Shubhangi Shrivastava
- stop_machine hack from Chris to fix corruptions when updating GTT ptes on bsw
- lots of fifo underrun fixes from Ville
- big pile of fbc fixes and improvements from Paulo
- fix fbdev failures paths (Tvrtko and Lukas Wunner)
- dp link training refactoring (Ander)
- interruptible prepare_plane for atomic (Maarten)
- basic kabylake support (Deepak&Rodrigo)
- don't leak ringspace on resets (Chris)
drm-intel-next-2015-10-23:
- 2nd attempt at atomic watermarks from Matt, but just prep for now
- fixes all over

* tag 'drm-intel-next-2015-11-20-merged' of git://anongit.freedesktop.org/drm-intel: (209 commits)
  drm/i915: Update DRIVER_DATE to 20151120
  drm/i915: take a power domain reference while checking the HDMI live status
  drm/i915: take a power domain ref only when needed during HDMI detect
  drm/i915: Tear down fbdev if initialization fails
  async: export current_is_async()
  Revert "drm/i915: Initialize HWS page address after GPU reset"
  drm/i915: Fix oops caused by fbdev initialization failure
  drm/i915: Fix i915_ggtt_view_equal to handle rotation correctly
  drm/i915: Stuff rotation params into view union
  drm/i915: Drop return value from intel_fill_fb_ggtt_view
  drm/i915 : Fix to remove unnecsessary checks in postclose function.
  drm/i915: add MISSING_CASE to a few port/aux power domain helpers
  drm/i915/ddi: fix intel_display_port_aux_power_domain() after HDMI detect
  drm/i915: Remove platform specific *_dp_detect() functions
  drm/i915: Don't do edp panel detection in g4x_dp_detect()
  drm/i915: Send TP1 TP2/3 even when panel claims no NO_TRAIN_ON_EXIT.
  drm/i915: PSR: Don't Skip aux handshake on DP_PSR_NO_TRAIN_ON_EXIT.
  drm/i915: Reduce PSR re-activation time for VLV/CHV.
  drm/i915: Delay first PSR activation.
  drm/i915: Type safe register read/write
  ...

Documentation/DocBook/gpu.tmpl

@@ -4177,17 +4177,21 @@ int num_ioctls;</synopsis>
       </sect2>
     </sect1>
     <sect1>
-      <title>GuC-based Command Submission</title>
+      <title>GuC</title>
       <sect2>
-        <title>GuC</title>
+        <title>GuC-specific firmware loader</title>
 !Pdrivers/gpu/drm/i915/intel_guc_loader.c GuC-specific firmware loader
 !Idrivers/gpu/drm/i915/intel_guc_loader.c
       </sect2>
       <sect2>
-        <title>GuC Client</title>
-!Pdrivers/gpu/drm/i915/i915_guc_submission.c GuC-based command submissison
+        <title>GuC-based command submission</title>
+!Pdrivers/gpu/drm/i915/i915_guc_submission.c GuC-based command submission
 !Idrivers/gpu/drm/i915/i915_guc_submission.c
       </sect2>
+      <sect2>
+        <title>GuC Firmware Layout</title>
+!Pdrivers/gpu/drm/i915/intel_guc_fwif.h GuC Firmware Layout
+      </sect2>
     </sect1>
 
     <sect1>

arch/x86/kernel/early-quirks.c

@@ -547,6 +547,7 @@ static const struct pci_device_id intel_stolen_ids[] __initconst = {
 	INTEL_CHV_IDS(&chv_stolen_funcs),
 	INTEL_SKL_IDS(&gen9_stolen_funcs),
 	INTEL_BXT_IDS(&gen9_stolen_funcs),
+	INTEL_KBL_IDS(&gen9_stolen_funcs),
 };
 
 static void __init intel_graphics_stolen(int num, int slot, int func)

drivers/gpu/drm/i915/Kconfig

@@ -10,6 +10,7 @@ config DRM_I915
 	# the shmem_readpage() which depends upon tmpfs
 	select SHMEM
 	select TMPFS
+	select STOP_MACHINE
 	select DRM_KMS_HELPER
 	select DRM_PANEL
 	select DRM_MIPI_DSI

drivers/gpu/drm/i915/Makefile

@@ -77,6 +77,7 @@ i915-y += dvo_ch7017.o \
 	  dvo_tfp410.o \
 	  intel_crt.o \
 	  intel_ddi.o \
+	  intel_dp_link_training.o \
 	  intel_dp_mst.o \
 	  intel_dp.o \
 	  intel_dsi.o \

drivers/gpu/drm/i915/dvo.h

@@ -32,7 +32,8 @@ struct intel_dvo_device {
 	const char *name;
 	int type;
 	/* DVOA/B/C output register */
-	u32 dvo_reg;
+	i915_reg_t dvo_reg;
+	i915_reg_t dvo_srcdim_reg;
 	/* GPIO register used for i2c bus to control this device */
 	u32 gpio;
 	int slave_addr;

drivers/gpu/drm/i915/i915_cmd_parser.c

@@ -407,14 +407,14 @@ static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = {
  * LRI.
  */
 struct drm_i915_reg_descriptor {
-	u32 addr;
+	i915_reg_t addr;
 	u32 mask;
 	u32 value;
 };
 
 /* Convenience macro for adding 32-bit registers. */
-#define REG32(address, ...)                             \
-	{ .addr = address, __VA_ARGS__ }
+#define REG32(_reg, ...) \
+	{ .addr = (_reg), __VA_ARGS__ }
 
 /*
  * Convenience macro for adding 64-bit registers.
@@ -423,8 +423,13 @@ struct drm_i915_reg_descriptor {
  * access commands only allow 32-bit accesses. Hence, we have to include
  * entries for both halves of the 64-bit registers.
  */
-#define REG64(addr)                                     \
-	REG32(addr), REG32(addr + sizeof(u32))
+#define REG64(_reg) \
+	{ .addr = _reg }, \
+	{ .addr = _reg ## _UDW }
+
+#define REG64_IDX(_reg, idx) \
+	{ .addr = _reg(idx) }, \
+	{ .addr = _reg ## _UDW(idx) }
 
 static const struct drm_i915_reg_descriptor gen7_render_regs[] = {
 	REG64(GPGPU_THREADS_DISPATCHED),
@@ -451,14 +456,14 @@ static const struct drm_i915_reg_descriptor gen7_render_regs[] = {
 	REG32(GEN7_GPGPU_DISPATCHDIMX),
 	REG32(GEN7_GPGPU_DISPATCHDIMY),
 	REG32(GEN7_GPGPU_DISPATCHDIMZ),
-	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(0)),
-	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(1)),
-	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(2)),
-	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(3)),
-	REG64(GEN7_SO_PRIM_STORAGE_NEEDED(0)),
-	REG64(GEN7_SO_PRIM_STORAGE_NEEDED(1)),
-	REG64(GEN7_SO_PRIM_STORAGE_NEEDED(2)),
-	REG64(GEN7_SO_PRIM_STORAGE_NEEDED(3)),
+	REG64_IDX(GEN7_SO_NUM_PRIMS_WRITTEN, 0),
+	REG64_IDX(GEN7_SO_NUM_PRIMS_WRITTEN, 1),
+	REG64_IDX(GEN7_SO_NUM_PRIMS_WRITTEN, 2),
+	REG64_IDX(GEN7_SO_NUM_PRIMS_WRITTEN, 3),
+	REG64_IDX(GEN7_SO_PRIM_STORAGE_NEEDED, 0),
+	REG64_IDX(GEN7_SO_PRIM_STORAGE_NEEDED, 1),
+	REG64_IDX(GEN7_SO_PRIM_STORAGE_NEEDED, 2),
+	REG64_IDX(GEN7_SO_PRIM_STORAGE_NEEDED, 3),
 	REG32(GEN7_SO_WRITE_OFFSET(0)),
 	REG32(GEN7_SO_WRITE_OFFSET(1)),
 	REG32(GEN7_SO_WRITE_OFFSET(2)),
@@ -592,7 +597,7 @@ static bool check_sorted(int ring_id,
 	bool ret = true;
 
 	for (i = 0; i < reg_count; i++) {
-		u32 curr = reg_table[i].addr;
+		u32 curr = i915_mmio_reg_offset(reg_table[i].addr);
 
 		if (curr < previous) {
 			DRM_ERROR("CMD: table not sorted ring=%d entry=%d reg=0x%08X prev=0x%08X\n",
@@ -847,7 +852,7 @@ find_reg(const struct drm_i915_reg_descriptor *table,
 		int i;
 
 		for (i = 0; i < count; i++) {
-			if (table[i].addr == addr)
+			if (i915_mmio_reg_offset(table[i].addr) == addr)
 				return &table[i];
 		}
 	}
@@ -1023,7 +1028,7 @@ static bool check_cmd(const struct intel_engine_cs *ring,
 			 * to the register. Hence, limit OACONTROL writes to
 			 * only MI_LOAD_REGISTER_IMM commands.
 			 */
-			if (reg_addr == OACONTROL) {
+			if (reg_addr == i915_mmio_reg_offset(OACONTROL)) {
 				if (desc->cmd.value == MI_LOAD_REGISTER_MEM) {
 					DRM_DEBUG_DRIVER("CMD: Rejected LRM to OACONTROL\n");
 					return false;

drivers/gpu/drm/i915/i915_dma.c

@@ -28,7 +28,6 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/async.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
@@ -338,7 +337,7 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_
 		i915_resume_switcheroo(dev);
 		dev->switch_power_state = DRM_SWITCH_POWER_ON;
 	} else {
-		pr_err("switched off\n");
+		pr_info("switched off\n");
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 		i915_suspend_switcheroo(dev, pmm);
 		dev->switch_power_state = DRM_SWITCH_POWER_OFF;
@@ -396,7 +395,9 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	if (ret)
 		goto cleanup_vga_switcheroo;
 
-	intel_power_domains_init_hw(dev_priv);
+	intel_power_domains_init_hw(dev_priv, false);
+
+	intel_csr_ucode_init(dev_priv);
 
 	ret = intel_irq_install(dev_priv);
 	if (ret)
@@ -437,7 +438,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	 * scanning against hotplug events. Hence do this first and ignore the
 	 * tiny window where we will loose hotplug notifactions.
 	 */
-	async_schedule(intel_fbdev_initial_config, dev_priv);
+	intel_fbdev_initial_config_async(dev);
 
 	drm_kms_helper_poll_init(dev);
 
@@ -663,7 +664,8 @@ static void gen9_sseu_info_init(struct drm_device *dev)
 	 * supports EU power gating on devices with more than one EU
 	 * pair per subslice.
 	*/
-	info->has_slice_pg = (IS_SKYLAKE(dev) && (info->slice_total > 1));
+	info->has_slice_pg = ((IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) &&
+			       (info->slice_total > 1));
 	info->has_subslice_pg = (IS_BROXTON(dev) && (info->subslice_total > 1));
 	info->has_eu_pg = (info->eu_per_subslice > 2);
 }
@@ -890,7 +892,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	spin_lock_init(&dev_priv->mmio_flip_lock);
 	mutex_init(&dev_priv->sb_lock);
 	mutex_init(&dev_priv->modeset_restore_lock);
-	mutex_init(&dev_priv->csr_lock);
 	mutex_init(&dev_priv->av_mutex);
 
 	intel_pm_setup(dev);
@@ -937,9 +938,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	intel_uncore_init(dev);
 
-	/* Load CSR Firmware for SKL */
-	intel_csr_ucode_init(dev);
-
 	ret = i915_gem_gtt_init(dev);
 	if (ret)
 		goto out_freecsr;
@@ -1113,7 +1111,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 out_gtt:
 	i915_global_gtt_cleanup(dev);
 out_freecsr:
-	intel_csr_ucode_fini(dev);
+	intel_csr_ucode_fini(dev_priv);
 	intel_uncore_fini(dev);
 	pci_iounmap(dev->pdev, dev_priv->regs);
 put_bridge:
@@ -1131,6 +1129,8 @@ int i915_driver_unload(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
+	intel_fbdev_fini(dev);
+
 	i915_audio_component_cleanup(dev_priv);
 
 	ret = i915_gem_suspend(dev);
@@ -1153,8 +1153,6 @@ int i915_driver_unload(struct drm_device *dev)
 
 	acpi_video_unregister();
 
-	intel_fbdev_fini(dev);
-
 	drm_vblank_cleanup(dev);
 
 	intel_modeset_cleanup(dev);
@@ -1196,7 +1194,7 @@ int i915_driver_unload(struct drm_device *dev)
 	intel_fbc_cleanup_cfb(dev_priv);
 	i915_gem_cleanup_stolen(dev);
 
-	intel_csr_ucode_fini(dev);
+	intel_csr_ucode_fini(dev_priv);
 
 	intel_teardown_gmbus(dev);
 	intel_teardown_mchbar(dev);
@@ -1264,8 +1262,6 @@ void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 
-	if (file_priv && file_priv->bsd_ring)
-		file_priv->bsd_ring = NULL;
 	kfree(file_priv);
 }
 

drivers/gpu/drm/i915/i915_drv.c

@@ -383,6 +383,7 @@ static const struct intel_device_info intel_skylake_gt3_info = {
 
 static const struct intel_device_info intel_broxton_info = {
 	.is_preliminary = 1,
+	.is_broxton = 1,
 	.gen = 9,
 	.need_gfx_hws = 1, .has_hotplug = 1,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
@@ -394,50 +395,81 @@ static const struct intel_device_info intel_broxton_info = {
 	IVB_CURSOR_OFFSETS,
 };
 
+static const struct intel_device_info intel_kabylake_info = {
+	.is_preliminary = 1,
+	.is_kabylake = 1,
+	.gen = 9,
+	.num_pipes = 3,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
+	.has_llc = 1,
+	.has_ddi = 1,
+	.has_fpga_dbg = 1,
+	.has_fbc = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_kabylake_gt3_info = {
+	.is_preliminary = 1,
+	.is_kabylake = 1,
+	.gen = 9,
+	.num_pipes = 3,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
+	.has_llc = 1,
+	.has_ddi = 1,
+	.has_fpga_dbg = 1,
+	.has_fbc = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
+};
+
 /*
  * Make sure any device matches here are from most specific to most
  * general.  For example, since the Quanta match is based on the subsystem
  * and subvendor IDs, we need it to come before the more general IVB
  * PCI ID matches, otherwise we'll use the wrong info struct above.
  */
-#define INTEL_PCI_IDS \
-	INTEL_I830_IDS(&intel_i830_info),	\
-	INTEL_I845G_IDS(&intel_845g_info),	\
-	INTEL_I85X_IDS(&intel_i85x_info),	\
-	INTEL_I865G_IDS(&intel_i865g_info),	\
-	INTEL_I915G_IDS(&intel_i915g_info),	\
-	INTEL_I915GM_IDS(&intel_i915gm_info),	\
-	INTEL_I945G_IDS(&intel_i945g_info),	\
-	INTEL_I945GM_IDS(&intel_i945gm_info),	\
-	INTEL_I965G_IDS(&intel_i965g_info),	\
-	INTEL_G33_IDS(&intel_g33_info),		\
-	INTEL_I965GM_IDS(&intel_i965gm_info),	\
-	INTEL_GM45_IDS(&intel_gm45_info), 	\
-	INTEL_G45_IDS(&intel_g45_info), 	\
-	INTEL_PINEVIEW_IDS(&intel_pineview_info),	\
-	INTEL_IRONLAKE_D_IDS(&intel_ironlake_d_info),	\
-	INTEL_IRONLAKE_M_IDS(&intel_ironlake_m_info),	\
-	INTEL_SNB_D_IDS(&intel_sandybridge_d_info),	\
-	INTEL_SNB_M_IDS(&intel_sandybridge_m_info),	\
-	INTEL_IVB_Q_IDS(&intel_ivybridge_q_info), /* must be first IVB */ \
-	INTEL_IVB_M_IDS(&intel_ivybridge_m_info),	\
-	INTEL_IVB_D_IDS(&intel_ivybridge_d_info),	\
-	INTEL_HSW_D_IDS(&intel_haswell_d_info), \
-	INTEL_HSW_M_IDS(&intel_haswell_m_info), \
-	INTEL_VLV_M_IDS(&intel_valleyview_m_info),	\
-	INTEL_VLV_D_IDS(&intel_valleyview_d_info),	\
-	INTEL_BDW_GT12M_IDS(&intel_broadwell_m_info),	\
-	INTEL_BDW_GT12D_IDS(&intel_broadwell_d_info),	\
-	INTEL_BDW_GT3M_IDS(&intel_broadwell_gt3m_info),	\
-	INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info), \
-	INTEL_CHV_IDS(&intel_cherryview_info),	\
-	INTEL_SKL_GT1_IDS(&intel_skylake_info),	\
-	INTEL_SKL_GT2_IDS(&intel_skylake_info),	\
-	INTEL_SKL_GT3_IDS(&intel_skylake_gt3_info),	\
-	INTEL_BXT_IDS(&intel_broxton_info)
-
-static const struct pci_device_id pciidlist[] = {		/* aka */
-	INTEL_PCI_IDS,
+static const struct pci_device_id pciidlist[] = {
+	INTEL_I830_IDS(&intel_i830_info),
+	INTEL_I845G_IDS(&intel_845g_info),
+	INTEL_I85X_IDS(&intel_i85x_info),
+	INTEL_I865G_IDS(&intel_i865g_info),
+	INTEL_I915G_IDS(&intel_i915g_info),
+	INTEL_I915GM_IDS(&intel_i915gm_info),
+	INTEL_I945G_IDS(&intel_i945g_info),
+	INTEL_I945GM_IDS(&intel_i945gm_info),
+	INTEL_I965G_IDS(&intel_i965g_info),
+	INTEL_G33_IDS(&intel_g33_info),
+	INTEL_I965GM_IDS(&intel_i965gm_info),
+	INTEL_GM45_IDS(&intel_gm45_info),
+	INTEL_G45_IDS(&intel_g45_info),
+	INTEL_PINEVIEW_IDS(&intel_pineview_info),
+	INTEL_IRONLAKE_D_IDS(&intel_ironlake_d_info),
+	INTEL_IRONLAKE_M_IDS(&intel_ironlake_m_info),
+	INTEL_SNB_D_IDS(&intel_sandybridge_d_info),
+	INTEL_SNB_M_IDS(&intel_sandybridge_m_info),
+	INTEL_IVB_Q_IDS(&intel_ivybridge_q_info), /* must be first IVB */
+	INTEL_IVB_M_IDS(&intel_ivybridge_m_info),
+	INTEL_IVB_D_IDS(&intel_ivybridge_d_info),
+	INTEL_HSW_D_IDS(&intel_haswell_d_info),
+	INTEL_HSW_M_IDS(&intel_haswell_m_info),
+	INTEL_VLV_M_IDS(&intel_valleyview_m_info),
+	INTEL_VLV_D_IDS(&intel_valleyview_d_info),
+	INTEL_BDW_GT12M_IDS(&intel_broadwell_m_info),
+	INTEL_BDW_GT12D_IDS(&intel_broadwell_d_info),
+	INTEL_BDW_GT3M_IDS(&intel_broadwell_gt3m_info),
+	INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info),
+	INTEL_CHV_IDS(&intel_cherryview_info),
+	INTEL_SKL_GT1_IDS(&intel_skylake_info),
+	INTEL_SKL_GT2_IDS(&intel_skylake_info),
+	INTEL_SKL_GT3_IDS(&intel_skylake_gt3_info),
+	INTEL_BXT_IDS(&intel_broxton_info),
+	INTEL_KBL_GT1_IDS(&intel_kabylake_info),
+	INTEL_KBL_GT2_IDS(&intel_kabylake_info),
+	INTEL_KBL_GT3_IDS(&intel_kabylake_gt3_info),
+	INTEL_KBL_GT4_IDS(&intel_kabylake_gt3_info),
 	{0, 0, 0}
 };
 
@@ -463,7 +495,7 @@ static enum intel_pch intel_virt_detect_pch(struct drm_device *dev)
 	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		ret = PCH_LPT;
 		DRM_DEBUG_KMS("Assuming LynxPoint PCH\n");
-	} else if (IS_SKYLAKE(dev)) {
+	} else if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) {
 		ret = PCH_SPT;
 		DRM_DEBUG_KMS("Assuming SunrisePoint PCH\n");
 	}
@@ -526,11 +558,13 @@ void intel_detect_pch(struct drm_device *dev)
 			} else if (id == INTEL_PCH_SPT_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_SPT;
 				DRM_DEBUG_KMS("Found SunrisePoint PCH\n");
-				WARN_ON(!IS_SKYLAKE(dev));
+				WARN_ON(!IS_SKYLAKE(dev) &&
+					!IS_KABYLAKE(dev));
 			} else if (id == INTEL_PCH_SPT_LP_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_SPT;
 				DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n");
-				WARN_ON(!IS_SKYLAKE(dev));
+				WARN_ON(!IS_SKYLAKE(dev) &&
+					!IS_KABYLAKE(dev));
 			} else if (id == INTEL_PCH_P2X_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = intel_virt_detect_pch(dev);
 			} else
@@ -570,26 +604,6 @@ bool i915_semaphore_is_enabled(struct drm_device *dev)
 	return true;
 }
 
-void i915_firmware_load_error_print(const char *fw_path, int err)
-{
-	DRM_ERROR("failed to load firmware %s (%d)\n", fw_path, err);
-
-	/*
-	 * If the reason is not known assume -ENOENT since that's the most
-	 * usual failure mode.
-	 */
-	if (!err)
-		err = -ENOENT;
-
-	if (!(IS_BUILTIN(CONFIG_DRM_I915) && err == -ENOENT))
-		return;
-
-	DRM_ERROR(
-	  "The driver is built-in, so to load the firmware you need to\n"
-	  "include it either in the kernel (see CONFIG_EXTRA_FIRMWARE) or\n"
-	  "in your initrd/initramfs image.\n");
-}
-
 static void intel_suspend_encoders(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
@@ -608,7 +622,6 @@ static void intel_suspend_encoders(struct drm_i915_private *dev_priv)
 static int intel_suspend_complete(struct drm_i915_private *dev_priv);
 static int vlv_resume_prepare(struct drm_i915_private *dev_priv,
 			      bool rpm_resume);
-static int skl_resume_prepare(struct drm_i915_private *dev_priv);
 static int bxt_resume_prepare(struct drm_i915_private *dev_priv);
 
 
@@ -679,6 +692,9 @@ static int i915_drm_suspend(struct drm_device *dev)
 
 	intel_display_set_init_power(dev_priv, false);
 
+	if (HAS_CSR(dev_priv))
+		flush_work(&dev_priv->csr.work);
+
 	return 0;
 }
 
@@ -687,10 +703,13 @@ static int i915_drm_suspend_late(struct drm_device *drm_dev, bool hibernation)
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	int ret;
 
+	intel_power_domains_suspend(dev_priv);
+
 	ret = intel_suspend_complete(dev_priv);
 
 	if (ret) {
 		DRM_ERROR("Suspend complete failed: %d\n", ret);
+		intel_power_domains_init_hw(dev_priv, true);
 
 		return ret;
 	}
@@ -838,13 +857,11 @@ static int i915_drm_resume_early(struct drm_device *dev)
 
 	if (IS_BROXTON(dev))
 		ret = bxt_resume_prepare(dev_priv);
-	else if (IS_SKYLAKE(dev_priv))
-		ret = skl_resume_prepare(dev_priv);
 	else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		hsw_disable_pc8(dev_priv);
 
 	intel_uncore_sanitize(dev);
-	intel_power_domains_init_hw(dev_priv);
+	intel_power_domains_init_hw(dev_priv, true);
 
 	return ret;
 }
@@ -1051,15 +1068,6 @@ static int i915_pm_resume(struct device *dev)
 	return i915_drm_resume(drm_dev);
 }
 
-static int skl_suspend_complete(struct drm_i915_private *dev_priv)
-{
-	/* Enabling DC6 is not a hard requirement to enter runtime D3 */
-
-	skl_uninit_cdclk(dev_priv);
-
-	return 0;
-}
-
 static int hsw_suspend_complete(struct drm_i915_private *dev_priv)
 {
 	hsw_enable_pc8(dev_priv);
@@ -1099,16 +1107,6 @@ static int bxt_resume_prepare(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-static int skl_resume_prepare(struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = dev_priv->dev;
-
-	skl_init_cdclk(dev_priv);
-	intel_csr_load_program(dev);
-
-	return 0;
-}
-
 /*
  * Save all Gunit registers that may be lost after a D3 and a subsequent
  * S0i[R123] transition. The list of registers needing a save/restore is
@@ -1572,8 +1570,6 @@ static int intel_runtime_resume(struct device *device)
 
 	if (IS_BROXTON(dev))
 		ret = bxt_resume_prepare(dev_priv);
-	else if (IS_SKYLAKE(dev))
-		ret = skl_resume_prepare(dev_priv);
 	else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		hsw_disable_pc8(dev_priv);
 	else if (IS_VALLEYVIEW(dev_priv))
@@ -1616,8 +1612,6 @@ static int intel_suspend_complete(struct drm_i915_private *dev_priv)
 
 	if (IS_BROXTON(dev_priv))
 		ret = bxt_suspend_complete(dev_priv);
-	else if (IS_SKYLAKE(dev_priv))
-		ret = skl_suspend_complete(dev_priv);
 	else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		ret = hsw_suspend_complete(dev_priv);
 	else if (IS_VALLEYVIEW(dev_priv))

drivers/gpu/drm/i915/i915_gem.c

@@ -2737,6 +2737,8 @@ static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv,
 static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 					struct intel_engine_cs *ring)
 {
+	struct intel_ringbuffer *buffer;
+
 	while (!list_empty(&ring->active_list)) {
 		struct drm_i915_gem_object *obj;
 
@@ -2752,18 +2754,23 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 	 * are the ones that keep the context and ringbuffer backing objects
 	 * pinned in place.
 	 */
-	while (!list_empty(&ring->execlist_queue)) {
-		struct drm_i915_gem_request *submit_req;
 
-		submit_req = list_first_entry(&ring->execlist_queue,
-				struct drm_i915_gem_request,
-				execlist_link);
-		list_del(&submit_req->execlist_link);
+	if (i915.enable_execlists) {
+		spin_lock_irq(&ring->execlist_lock);
+		while (!list_empty(&ring->execlist_queue)) {
+			struct drm_i915_gem_request *submit_req;
+
+			submit_req = list_first_entry(&ring->execlist_queue,
+					struct drm_i915_gem_request,
+					execlist_link);
+			list_del(&submit_req->execlist_link);
 
-		if (submit_req->ctx != ring->default_context)
-			intel_lr_context_unpin(submit_req);
+			if (submit_req->ctx != ring->default_context)
+				intel_lr_context_unpin(submit_req);
 
-		i915_gem_request_unreference(submit_req);
+			i915_gem_request_unreference(submit_req);
+		}
+		spin_unlock_irq(&ring->execlist_lock);
 	}
 
 	/*
@@ -2782,6 +2789,18 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 
 		i915_gem_request_retire(request);
 	}
+
+	/* Having flushed all requests from all queues, we know that all
+	 * ringbuffers must now be empty. However, since we do not reclaim
+	 * all space when retiring the request (to prevent HEADs colliding
+	 * with rapid ringbuffer wraparound) the amount of available space
+	 * upon reset is less than when we start. Do one more pass over
+	 * all the ringbuffers to reset last_retired_head.
+	 */
+	list_for_each_entry(buffer, &ring->buffers, link) {
+		buffer->last_retired_head = buffer->tail;
+		intel_ring_update_space(buffer);
+	}
 }
 
 void i915_gem_reset(struct drm_device *dev)
@@ -3826,7 +3845,7 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 		 * cacheline, whereas normally such cachelines would get
 		 * invalidated.
 		 */
-		if (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0)
+		if (IS_BXT_REVID(dev, 0, BXT_REVID_A1))
 			return -ENODEV;
 
 		level = I915_CACHE_LLC;
@@ -3869,17 +3888,11 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 int
 i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     u32 alignment,
-				     struct intel_engine_cs *pipelined,
-				     struct drm_i915_gem_request **pipelined_request,
 				     const struct i915_ggtt_view *view)
 {
 	u32 old_read_domains, old_write_domain;
 	int ret;
 
-	ret = i915_gem_object_sync(obj, pipelined, pipelined_request);
-	if (ret)
-		return ret;
-
 	/* Mark the pin_display early so that we account for the
 	 * display coherency whilst setting up the cache domains.
 	 */
@@ -4476,10 +4489,8 @@ struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
 {
 	struct i915_vma *vma;
 	list_for_each_entry(vma, &obj->vma_list, vma_link) {
-		if (i915_is_ggtt(vma->vm) &&
-		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
-			continue;
-		if (vma->vm == vm)
+		if (vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL &&
+		    vma->vm == vm)
 			return vma;
 	}
 	return NULL;
@@ -4568,7 +4579,6 @@ int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
 	struct intel_engine_cs *ring = req->ring;
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
 	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	int i, ret;
 
@@ -4584,10 +4594,10 @@ int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
 	 * here because no other code should access these registers other than
 	 * at initialization time.
 	 */
-	for (i = 0; i < GEN7_L3LOG_SIZE; i += 4) {
+	for (i = 0; i < GEN7_L3LOG_SIZE / 4; i++) {
 		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-		intel_ring_emit(ring, reg_base + i);
-		intel_ring_emit(ring, remap_info[i/4]);
+		intel_ring_emit_reg(ring, GEN7_L3LOG(slice, i));
+		intel_ring_emit(ring, remap_info[i]);
 	}
 
 	intel_ring_advance(ring);
@@ -4755,18 +4765,9 @@ i915_gem_init_hw(struct drm_device *dev)
 	if (HAS_GUC_UCODE(dev)) {
 		ret = intel_guc_ucode_load(dev);
 		if (ret) {
-			/*
-			 * If we got an error and GuC submission is enabled, map
-			 * the error to -EIO so the GPU will be declared wedged.
-			 * OTOH, if we didn't intend to use the GuC anyway, just
-			 * discard the error and carry on.
-			 */
-			DRM_ERROR("Failed to initialize GuC, error %d%s\n", ret,
-				  i915.enable_guc_submission ? "" :
-				  " (ignored)");
-			ret = i915.enable_guc_submission ? -EIO : 0;
-			if (ret)
-				goto out;
+			DRM_ERROR("Failed to initialize GuC, error %d\n", ret);
+			ret = -EIO;
+			goto out;
 		}
 	}
 

drivers/gpu/drm/i915/i915_gem_context.c

@@ -556,7 +556,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 				if (signaller == ring)
 					continue;
 
-				intel_ring_emit(ring, RING_PSMI_CTL(signaller->mmio_base));
+				intel_ring_emit_reg(ring, RING_PSMI_CTL(signaller->mmio_base));
 				intel_ring_emit(ring, _MASKED_BIT_ENABLE(GEN6_PSMI_SLEEP_MSG_DISABLE));
 			}
 		}
@@ -581,7 +581,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 				if (signaller == ring)
 					continue;
 
-				intel_ring_emit(ring, RING_PSMI_CTL(signaller->mmio_base));
+				intel_ring_emit_reg(ring, RING_PSMI_CTL(signaller->mmio_base));
 				intel_ring_emit(ring, _MASKED_BIT_DISABLE(GEN6_PSMI_SLEEP_MSG_DISABLE));
 			}
 		}
@@ -925,6 +925,14 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_CONTEXT_PARAM_NO_ZEROMAP:
 		args->value = ctx->flags & CONTEXT_NO_ZEROMAP;
 		break;
+	case I915_CONTEXT_PARAM_GTT_SIZE:
+		if (ctx->ppgtt)
+			args->value = ctx->ppgtt->base.total;
+		else if (to_i915(dev)->mm.aliasing_ppgtt)
+			args->value = to_i915(dev)->mm.aliasing_ppgtt->base.total;
+		else
+			args->value = to_i915(dev)->gtt.base.total;
+		break;
 	default:
 		ret = -EINVAL;
 		break;

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -1114,7 +1114,7 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
 
 	for (i = 0; i < 4; i++) {
 		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-		intel_ring_emit(ring, GEN7_SO_WRITE_OFFSET(i));
+		intel_ring_emit_reg(ring, GEN7_SO_WRITE_OFFSET(i));
 		intel_ring_emit(ring, 0);
 	}
 
@@ -1241,7 +1241,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
 
 		intel_ring_emit(ring, MI_NOOP);
 		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-		intel_ring_emit(ring, INSTPM);
+		intel_ring_emit_reg(ring, INSTPM);
 		intel_ring_emit(ring, instp_mask << 16 | instp_mode);
 		intel_ring_advance(ring);
 

drivers/gpu/drm/i915/i915_gem_fence.c

@@ -59,7 +59,7 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 				 struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int fence_reg_lo, fence_reg_hi;
+	i915_reg_t fence_reg_lo, fence_reg_hi;
 	int fence_pitch_shift;
 
 	if (INTEL_INFO(dev)->gen >= 6) {

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -24,6 +24,7 @@
  */
 
 #include <linux/seq_file.h>
+#include <linux/stop_machine.h>
 #include <drm/drmP.h>
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
@@ -104,9 +105,11 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
 {
 	bool has_aliasing_ppgtt;
 	bool has_full_ppgtt;
+	bool has_full_48bit_ppgtt;
 
 	has_aliasing_ppgtt = INTEL_INFO(dev)->gen >= 6;
 	has_full_ppgtt = INTEL_INFO(dev)->gen >= 7;
+	has_full_48bit_ppgtt = IS_BROADWELL(dev) || INTEL_INFO(dev)->gen >= 9;
 
 	if (intel_vgpu_active(dev))
 		has_full_ppgtt = false; /* emulation is too hard */
@@ -125,6 +128,9 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
 	if (enable_ppgtt == 2 && has_full_ppgtt)
 		return 2;
 
+	if (enable_ppgtt == 3 && has_full_48bit_ppgtt)
+		return 3;
+
 #ifdef CONFIG_INTEL_IOMMU
 	/* Disable ppgtt on SNB if VT-d is on. */
 	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped) {
@@ -141,7 +147,7 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
 	}
 
 	if (INTEL_INFO(dev)->gen >= 8 && i915.enable_execlists)
-		return 2;
+		return has_full_48bit_ppgtt ? 3 : 2;
 	else
 		return has_aliasing_ppgtt ? 1 : 0;
 }
@@ -661,10 +667,10 @@ static int gen8_write_pdp(struct drm_i915_gem_request *req,
 		return ret;
 
 	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-	intel_ring_emit(ring, GEN8_RING_PDP_UDW(ring, entry));
+	intel_ring_emit_reg(ring, GEN8_RING_PDP_UDW(ring, entry));
 	intel_ring_emit(ring, upper_32_bits(addr));
 	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-	intel_ring_emit(ring, GEN8_RING_PDP_LDW(ring, entry));
+	intel_ring_emit_reg(ring, GEN8_RING_PDP_LDW(ring, entry));
 	intel_ring_emit(ring, lower_32_bits(addr));
 	intel_ring_advance(ring);
 
@@ -904,14 +910,13 @@ static int gen8_ppgtt_notify_vgt(struct i915_hw_ppgtt *ppgtt, bool create)
 	enum vgt_g2v_type msg;
 	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned int offset = vgtif_reg(pdp0_lo);
 	int i;
 
 	if (USES_FULL_48BIT_PPGTT(dev)) {
 		u64 daddr = px_dma(&ppgtt->pml4);
 
-		I915_WRITE(offset, lower_32_bits(daddr));
-		I915_WRITE(offset + 4, upper_32_bits(daddr));
+		I915_WRITE(vgtif_reg(pdp[0].lo), lower_32_bits(daddr));
+		I915_WRITE(vgtif_reg(pdp[0].hi), upper_32_bits(daddr));
 
 		msg = (create ? VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE :
 				VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY);
@@ -919,10 +924,8 @@ static int gen8_ppgtt_notify_vgt(struct i915_hw_ppgtt *ppgtt, bool create)
 		for (i = 0; i < GEN8_LEGACY_PDPES; i++) {
 			u64 daddr = i915_page_dir_dma_addr(ppgtt, i);
 
-			I915_WRITE(offset, lower_32_bits(daddr));
-			I915_WRITE(offset + 4, upper_32_bits(daddr));
-
-			offset += 8;
+			I915_WRITE(vgtif_reg(pdp[i].lo), lower_32_bits(daddr));
+			I915_WRITE(vgtif_reg(pdp[i].hi), upper_32_bits(daddr));
 		}
 
 		msg = (create ? VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE :
@@ -1662,9 +1665,9 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
 		return ret;
 
 	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(2));
-	intel_ring_emit(ring, RING_PP_DIR_DCLV(ring));
+	intel_ring_emit_reg(ring, RING_PP_DIR_DCLV(ring));
 	intel_ring_emit(ring, PP_DIR_DCLV_2G);
-	intel_ring_emit(ring, RING_PP_DIR_BASE(ring));
+	intel_ring_emit_reg(ring, RING_PP_DIR_BASE(ring));
 	intel_ring_emit(ring, get_pd_offset(ppgtt));
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
@@ -1699,9 +1702,9 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
 		return ret;
 
 	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(2));
-	intel_ring_emit(ring, RING_PP_DIR_DCLV(ring));
+	intel_ring_emit_reg(ring, RING_PP_DIR_DCLV(ring));
 	intel_ring_emit(ring, PP_DIR_DCLV_2G);
-	intel_ring_emit(ring, RING_PP_DIR_BASE(ring));
+	intel_ring_emit_reg(ring, RING_PP_DIR_BASE(ring));
 	intel_ring_emit(ring, get_pd_offset(ppgtt));
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
@@ -2528,6 +2531,26 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 	return 0;
 }
 
+struct ggtt_bind_vma__cb {
+	struct i915_vma *vma;
+	enum i915_cache_level cache_level;
+	u32 flags;
+};
+
+static int ggtt_bind_vma__cb(void *_arg)
+{
+	struct ggtt_bind_vma__cb *arg = _arg;
+	return ggtt_bind_vma(arg->vma, arg->cache_level, arg->flags);
+}
+
+static int ggtt_bind_vma__BKL(struct i915_vma *vma,
+			      enum i915_cache_level cache_level,
+			      u32 flags)
+{
+	struct ggtt_bind_vma__cb arg = { vma, cache_level, flags };
+	return stop_machine(ggtt_bind_vma__cb, &arg, NULL);
+}
+
 static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 				 enum i915_cache_level cache_level,
 				 u32 flags)
@@ -2995,6 +3018,9 @@ static int gen8_gmch_probe(struct drm_device *dev,
 	dev_priv->gtt.base.bind_vma = ggtt_bind_vma;
 	dev_priv->gtt.base.unbind_vma = ggtt_unbind_vma;
 
+	if (IS_CHERRYVIEW(dev))
+		dev_priv->gtt.base.bind_vma = ggtt_bind_vma__BKL;
+
 	return ret;
 }
 
@@ -3302,7 +3328,7 @@ static struct sg_table *
 intel_rotate_fb_obj_pages(struct i915_ggtt_view *ggtt_view,
 			  struct drm_i915_gem_object *obj)
 {
-	struct intel_rotation_info *rot_info = &ggtt_view->rotation_info;
+	struct intel_rotation_info *rot_info = &ggtt_view->params.rotation_info;
 	unsigned int size_pages = rot_info->size >> PAGE_SHIFT;
 	unsigned int size_pages_uv;
 	struct sg_page_iter sg_iter;
@@ -3534,7 +3560,7 @@ i915_ggtt_view_size(struct drm_i915_gem_object *obj,
 	if (view->type == I915_GGTT_VIEW_NORMAL) {
 		return obj->base.size;
 	} else if (view->type == I915_GGTT_VIEW_ROTATED) {
-		return view->rotation_info.size;
+		return view->params.rotation_info.size;
 	} else if (view->type == I915_GGTT_VIEW_PARTIAL) {
 		return view->params.partial.size << PAGE_SHIFT;
 	} else {

drivers/gpu/drm/i915/i915_gem_gtt.h

@@ -156,13 +156,10 @@ struct i915_ggtt_view {
 			u64 offset;
 			unsigned int size;
 		} partial;
+		struct intel_rotation_info rotation_info;
 	} params;
 
 	struct sg_table *pages;
-
-	union {
-		struct intel_rotation_info rotation_info;
-	};
 };
 
 extern const struct i915_ggtt_view i915_ggtt_view_normal;
@@ -556,7 +553,7 @@ i915_ggtt_view_equal(const struct i915_ggtt_view *a,
 
 	if (a->type != b->type)
 		return false;
-	if (a->type == I915_GGTT_VIEW_PARTIAL)
+	if (a->type != I915_GGTT_VIEW_NORMAL)
 		return !memcmp(&a->params, &b->params, sizeof(a->params));
 	return true;
 }

drivers/gpu/drm/i915/i915_gem_stolen.c

@@ -433,7 +433,8 @@ int i915_gem_init_stolen(struct drm_device *dev)
 					 &reserved_size);
 		break;
 	default:
-		if (IS_BROADWELL(dev_priv) || IS_SKYLAKE(dev_priv))
+		if (IS_BROADWELL(dev_priv) ||
+		    IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev))
 			bdw_get_stolen_reserved(dev_priv, &reserved_base,
 						&reserved_size);
 		else

drivers/gpu/drm/i915/i915_gem_tiling.c

@@ -176,6 +176,8 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	mutex_lock(&dev->struct_mutex);
 	if (obj->pin_display || obj->framebuffer_references) {
 		ret = -EBUSY;
@@ -269,6 +271,8 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
 
+	intel_runtime_pm_put(dev_priv);
+
 	return ret;
 }
 

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -366,6 +366,17 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	err_printf(m, "Suspend count: %u\n", error->suspend_count);
 	err_printf(m, "PCI ID: 0x%04x\n", dev->pdev->device);
 	err_printf(m, "IOMMU enabled?: %d\n", error->iommu);
+
+	if (HAS_CSR(dev)) {
+		struct intel_csr *csr = &dev_priv->csr;
+
+		err_printf(m, "DMC loaded: %s\n",
+			   yesno(csr->dmc_payload != NULL));
+		err_printf(m, "DMC fw version: %d.%d\n",
+			   CSR_VERSION_MAJOR(csr->version),
+			   CSR_VERSION_MINOR(csr->version));
+	}
+
 	err_printf(m, "EIR: 0x%08x\n", error->eir);
 	err_printf(m, "IER: 0x%08x\n", error->ier);
 	if (INTEL_INFO(dev)->gen >= 8) {
@@ -862,7 +873,7 @@ static void i915_record_ring_state(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	if (INTEL_INFO(dev)->gen >= 6) {
-		ering->rc_psmi = I915_READ(ring->mmio_base + 0x50);
+		ering->rc_psmi = I915_READ(RING_PSMI_CTL(ring->mmio_base));
 		ering->fault_reg = I915_READ(RING_FAULT_REG(ring));
 		if (INTEL_INFO(dev)->gen >= 8)
 			gen8_record_semaphore_state(dev_priv, error, ring, ering);
@@ -899,7 +910,7 @@ static void i915_record_ring_state(struct drm_device *dev,
 	ering->ctl = I915_READ_CTL(ring);
 
 	if (I915_NEED_GFX_HWS(dev)) {
-		int mmio;
+		i915_reg_t mmio;
 
 		if (IS_GEN7(dev)) {
 			switch (ring->id) {
@@ -1071,6 +1082,25 @@ static void i915_gem_record_rings(struct drm_device *dev,
 		list_for_each_entry(request, &ring->request_list, list) {
 			struct drm_i915_error_request *erq;
 
+			if (count >= error->ring[i].num_requests) {
+				/*
+				 * If the ring request list was changed in
+				 * between the point where the error request
+				 * list was created and dimensioned and this
+				 * point then just exit early to avoid crashes.
+				 *
+				 * We don't need to communicate that the
+				 * request list changed state during error
+				 * state capture and that the error state is
+				 * slightly incorrect as a consequence since we
+				 * are typically only interested in the request
+				 * list state at the point of error state
+				 * capture, not in any changes happening during
+				 * the capture.
+				 */
+				break;
+			}
+
 			erq = &error->ring[i].requests[count++];
 			erq->seqno = request->seqno;
 			erq->jiffies = request->emitted_jiffies;
@@ -1181,7 +1211,7 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 	if (IS_VALLEYVIEW(dev)) {
 		error->gtier[0] = I915_READ(GTIER);
 		error->ier = I915_READ(VLV_IER);
-		error->forcewake = I915_READ(FORCEWAKE_VLV);
+		error->forcewake = I915_READ_FW(FORCEWAKE_VLV);
 	}
 
 	if (IS_GEN7(dev))
@@ -1193,14 +1223,14 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 	}
 
 	if (IS_GEN6(dev)) {
-		error->forcewake = I915_READ(FORCEWAKE);
+		error->forcewake = I915_READ_FW(FORCEWAKE);
 		error->gab_ctl = I915_READ(GAB_CTL);
 		error->gfx_mode = I915_READ(GFX_MODE);
 	}
 
 	/* 2: Registers which belong to multiple generations */
 	if (INTEL_INFO(dev)->gen >= 7)
-		error->forcewake = I915_READ(FORCEWAKE_MT);
+		error->forcewake = I915_READ_FW(FORCEWAKE_MT);
 
 	if (INTEL_INFO(dev)->gen >= 6) {
 		error->derrmr = I915_READ(DERRMR);

drivers/gpu/drm/i915/i915_guc_reg.h

@@ -26,7 +26,7 @@
 
 /* Definitions of GuC H/W registers, bits, etc */
 
-#define GUC_STATUS			0xc000
+#define GUC_STATUS			_MMIO(0xc000)
 #define   GS_BOOTROM_SHIFT		1
 #define   GS_BOOTROM_MASK		  (0x7F << GS_BOOTROM_SHIFT)
 #define   GS_BOOTROM_RSA_FAILED		  (0x50 << GS_BOOTROM_SHIFT)
@@ -39,40 +39,41 @@
 #define   GS_MIA_MASK			  (0x07 << GS_MIA_SHIFT)
 #define   GS_MIA_CORE_STATE		  (1 << GS_MIA_SHIFT)
 
-#define SOFT_SCRATCH(n)			(0xc180 + ((n) * 4))
+#define SOFT_SCRATCH(n)			_MMIO(0xc180 + (n) * 4)
 
-#define UOS_RSA_SCRATCH(i)		(0xc200 + (i) * 4)
-#define DMA_ADDR_0_LOW			0xc300
-#define DMA_ADDR_0_HIGH			0xc304
-#define DMA_ADDR_1_LOW			0xc308
-#define DMA_ADDR_1_HIGH			0xc30c
+#define UOS_RSA_SCRATCH(i)		_MMIO(0xc200 + (i) * 4)
+#define   UOS_RSA_SCRATCH_MAX_COUNT	  64
+#define DMA_ADDR_0_LOW			_MMIO(0xc300)
+#define DMA_ADDR_0_HIGH			_MMIO(0xc304)
+#define DMA_ADDR_1_LOW			_MMIO(0xc308)
+#define DMA_ADDR_1_HIGH			_MMIO(0xc30c)
 #define   DMA_ADDRESS_SPACE_WOPCM	  (7 << 16)
 #define   DMA_ADDRESS_SPACE_GTT		  (8 << 16)
-#define DMA_COPY_SIZE			0xc310
-#define DMA_CTRL			0xc314
+#define DMA_COPY_SIZE			_MMIO(0xc310)
+#define DMA_CTRL			_MMIO(0xc314)
 #define   UOS_MOVE			  (1<<4)
 #define   START_DMA			  (1<<0)
-#define DMA_GUC_WOPCM_OFFSET		0xc340
+#define DMA_GUC_WOPCM_OFFSET		_MMIO(0xc340)
 #define   GUC_WOPCM_OFFSET_VALUE	  0x80000	/* 512KB */
-#define GUC_MAX_IDLE_COUNT		0xC3E4
+#define GUC_MAX_IDLE_COUNT		_MMIO(0xC3E4)
 
-#define GUC_WOPCM_SIZE			0xc050
+#define GUC_WOPCM_SIZE			_MMIO(0xc050)
 #define   GUC_WOPCM_SIZE_VALUE  	  (0x80 << 12)	/* 512KB */
 
 /* GuC addresses below GUC_WOPCM_TOP don't map through the GTT */
 #define	GUC_WOPCM_TOP			(GUC_WOPCM_SIZE_VALUE)
 
-#define GEN8_GT_PM_CONFIG		0x138140
-#define GEN9LP_GT_PM_CONFIG		0x138140
-#define GEN9_GT_PM_CONFIG		0x13816c
+#define GEN8_GT_PM_CONFIG		_MMIO(0x138140)
+#define GEN9LP_GT_PM_CONFIG		_MMIO(0x138140)
+#define GEN9_GT_PM_CONFIG		_MMIO(0x13816c)
 #define   GT_DOORBELL_ENABLE		  (1<<0)
 
-#define GEN8_GTCR			0x4274
+#define GEN8_GTCR			_MMIO(0x4274)
 #define   GEN8_GTCR_INVALIDATE		  (1<<0)
 
-#define GUC_ARAT_C6DIS			0xA178
+#define GUC_ARAT_C6DIS			_MMIO(0xA178)
 
-#define GUC_SHIM_CONTROL		0xc064
+#define GUC_SHIM_CONTROL		_MMIO(0xc064)
 #define   GUC_DISABLE_SRAM_INIT_TO_ZEROES	(1<<0)
 #define   GUC_ENABLE_READ_CACHE_LOGIC		(1<<1)
 #define   GUC_ENABLE_MIA_CACHING		(1<<2)
@@ -89,21 +90,21 @@
 				 GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA	| \
 				 GUC_ENABLE_MIA_CLOCK_GATING)
 
-#define HOST2GUC_INTERRUPT		0xc4c8
+#define HOST2GUC_INTERRUPT		_MMIO(0xc4c8)
 #define   HOST2GUC_TRIGGER		  (1<<0)
 
 #define DRBMISC1			0x1984
 #define   DOORBELL_ENABLE		  (1<<0)
 
-#define GEN8_DRBREGL(x)			(0x1000 + (x) * 8)
+#define GEN8_DRBREGL(x)			_MMIO(0x1000 + (x) * 8)
 #define   GEN8_DRB_VALID		  (1<<0)
-#define GEN8_DRBREGU(x)			(GEN8_DRBREGL(x) + 4)
+#define GEN8_DRBREGU(x)			_MMIO(0x1000 + (x) * 8 + 4)
 
-#define DE_GUCRMR			0x44054
+#define DE_GUCRMR			_MMIO(0x44054)
 
-#define GUC_BCS_RCS_IER			0xC550
-#define GUC_VCS2_VCS1_IER		0xC554
-#define GUC_WD_VECS_IER			0xC558
-#define GUC_PM_P24C_IER			0xC55C
+#define GUC_BCS_RCS_IER			_MMIO(0xC550)
+#define GUC_VCS2_VCS1_IER		_MMIO(0xC554)
+#define GUC_WD_VECS_IER			_MMIO(0xC558)
+#define GUC_PM_P24C_IER			_MMIO(0xC55C)
 
 #endif

drivers/gpu/drm/i915/i915_guc_submission.c

@@ -27,7 +27,7 @@
 #include "intel_guc.h"
 
 /**
- * DOC: GuC Client
+ * DOC: GuC-based command submission
  *
  * i915_guc_client:
  * We use the term client to avoid confusion with contexts. A i915_guc_client is
@@ -161,9 +161,9 @@ static int host2guc_sample_forcewake(struct intel_guc *guc,
 	data[0] = HOST2GUC_ACTION_SAMPLE_FORCEWAKE;
 	/* WaRsDisableCoarsePowerGating:skl,bxt */
 	if (!intel_enable_rc6(dev_priv->dev) ||
-	    (IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) ||
-	    (IS_SKL_GT3(dev) && (INTEL_REVID(dev) <= SKL_REVID_E0)) ||
-	    (IS_SKL_GT4(dev) && (INTEL_REVID(dev) <= SKL_REVID_E0)))
+	    IS_BXT_REVID(dev, 0, BXT_REVID_A1) ||
+	    (IS_SKL_GT3(dev) && IS_SKL_REVID(dev, 0, SKL_REVID_E0)) ||
+	    (IS_SKL_GT4(dev) && IS_SKL_REVID(dev, 0, SKL_REVID_E0)))
 		data[1] = 0;
 	else
 		/* bit 0 and 1 are for Render and Media domain separately */
@@ -258,7 +258,7 @@ static void guc_disable_doorbell(struct intel_guc *guc,
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	struct guc_doorbell_info *doorbell;
 	void *base;
-	int drbreg = GEN8_DRBREGL(client->doorbell_id);
+	i915_reg_t drbreg = GEN8_DRBREGL(client->doorbell_id);
 	int value;
 
 	base = kmap_atomic(i915_gem_object_get_page(client->client_obj, 0));
@@ -588,8 +588,7 @@ static void lr_context_update(struct drm_i915_gem_request *rq)
 /**
  * i915_guc_submit() - Submit commands through GuC
  * @client:	the guc client where commands will go through
- * @ctx:	LRC where commands come from
- * @ring:	HW engine that will excute the commands
+ * @rq:		request associated with the commands
  *
  * Return:	0 if succeed
  */
@@ -731,7 +730,8 @@ static void guc_client_free(struct drm_device *dev,
  * 		The kernel client to replace ExecList submission is created with
  * 		NORMAL priority. Priority of a client for scheduler can be HIGH,
  * 		while a preemption context can use CRITICAL.
- * @ctx		the context to own the client (we use the default render context)
+ * @ctx:	the context that owns the client (we use the default render
+ * 		context)
  *
  * Return:	An i915_guc_client object if success.
  */

drivers/gpu/drm/i915/i915_irq.c

@@ -139,7 +139,8 @@ static const u32 hpd_bxt[HPD_NUM_PINS] = {
 /*
  * We should clear IMR at preinstall/uninstall, and just check at postinstall.
  */
-static void gen5_assert_iir_is_zero(struct drm_i915_private *dev_priv, u32 reg)
+static void gen5_assert_iir_is_zero(struct drm_i915_private *dev_priv,
+				    i915_reg_t reg)
 {
 	u32 val = I915_READ(reg);
 
@@ -147,7 +148,7 @@ static void gen5_assert_iir_is_zero(struct drm_i915_private *dev_priv, u32 reg)
 		return;
 
 	WARN(1, "Interrupt register 0x%x is not zero: 0x%08x\n",
-	     reg, val);
+	     i915_mmio_reg_offset(reg), val);
 	I915_WRITE(reg, 0xffffffff);
 	POSTING_READ(reg);
 	I915_WRITE(reg, 0xffffffff);
@@ -283,17 +284,17 @@ void gen5_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask)
 	ilk_update_gt_irq(dev_priv, mask, 0);
 }
 
-static u32 gen6_pm_iir(struct drm_i915_private *dev_priv)
+static i915_reg_t gen6_pm_iir(struct drm_i915_private *dev_priv)
 {
 	return INTEL_INFO(dev_priv)->gen >= 8 ? GEN8_GT_IIR(2) : GEN6_PMIIR;
 }
 
-static u32 gen6_pm_imr(struct drm_i915_private *dev_priv)
+static i915_reg_t gen6_pm_imr(struct drm_i915_private *dev_priv)
 {
 	return INTEL_INFO(dev_priv)->gen >= 8 ? GEN8_GT_IMR(2) : GEN6_PMIMR;
 }
 
-static u32 gen6_pm_ier(struct drm_i915_private *dev_priv)
+static i915_reg_t gen6_pm_ier(struct drm_i915_private *dev_priv)
 {
 	return INTEL_INFO(dev_priv)->gen >= 8 ? GEN8_GT_IER(2) : GEN6_PMIER;
 }
@@ -350,7 +351,7 @@ void gen6_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
 void gen6_reset_rps_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t reg = gen6_pm_iir(dev_priv);
+	i915_reg_t reg = gen6_pm_iir(dev_priv);
 
 	spin_lock_irq(&dev_priv->irq_lock);
 	I915_WRITE(reg, dev_priv->pm_rps_events);
@@ -477,7 +478,7 @@ static void
 __i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
 		       u32 enable_mask, u32 status_mask)
 {
-	u32 reg = PIPESTAT(pipe);
+	i915_reg_t reg = PIPESTAT(pipe);
 	u32 pipestat = I915_READ(reg) & PIPESTAT_INT_ENABLE_MASK;
 
 	assert_spin_locked(&dev_priv->irq_lock);
@@ -504,7 +505,7 @@ static void
 __i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
 		        u32 enable_mask, u32 status_mask)
 {
-	u32 reg = PIPESTAT(pipe);
+	i915_reg_t reg = PIPESTAT(pipe);
 	u32 pipestat = I915_READ(reg) & PIPESTAT_INT_ENABLE_MASK;
 
 	assert_spin_locked(&dev_priv->irq_lock);
@@ -665,8 +666,7 @@ static u32 i8xx_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 static u32 i915_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long high_frame;
-	unsigned long low_frame;
+	i915_reg_t high_frame, low_frame;
 	u32 high1, high2, low, pixel, vbl_start, hsync_start, htotal;
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
@@ -717,9 +717,7 @@ static u32 g4x_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 	return I915_READ(PIPE_FRMCOUNT_G4X(pipe));
 }
 
-/* raw reads, only for fast reads of display block, no need for forcewake etc. */
-#define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__))
-
+/* I915_READ_FW, only for fast reads of display block, no need for forcewake etc. */
 static int __intel_get_crtc_scanline(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -733,9 +731,9 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc)
 		vtotal /= 2;
 
 	if (IS_GEN2(dev))
-		position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN2;
+		position = I915_READ_FW(PIPEDSL(pipe)) & DSL_LINEMASK_GEN2;
 	else
-		position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
+		position = I915_READ_FW(PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
 
 	/*
 	 * On HSW, the DSL reg (0x70000) appears to return 0 if we
@@ -827,7 +825,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 		 * We can split this into vertical and horizontal
 		 * scanout position.
 		 */
-		position = (__raw_i915_read32(dev_priv, PIPEFRAMEPIXEL(pipe)) & PIPE_PIXEL_MASK) >> PIPE_PIXEL_SHIFT;
+		position = (I915_READ_FW(PIPEFRAMEPIXEL(pipe)) & PIPE_PIXEL_MASK) >> PIPE_PIXEL_SHIFT;
 
 		/* convert to pixel counts */
 		vbl_start *= htotal;
@@ -1188,7 +1186,7 @@ static void ivybridge_parity_work(struct work_struct *work)
 	POSTING_READ(GEN7_MISCCPCTL);
 
 	while ((slice = ffs(dev_priv->l3_parity.which_slice)) != 0) {
-		u32 reg;
+		i915_reg_t reg;
 
 		slice--;
 		if (WARN_ON_ONCE(slice >= NUM_L3_SLICES(dev_priv->dev)))
@@ -1196,7 +1194,7 @@ static void ivybridge_parity_work(struct work_struct *work)
 
 		dev_priv->l3_parity.which_slice &= ~(1<<slice);
 
-		reg = GEN7_L3CDERRST1 + (slice * 0x200);
+		reg = GEN7_L3CDERRST1(slice);
 
 		error_status = I915_READ(reg);
 		row = GEN7_PARITY_ERROR_ROW(error_status);
@@ -1290,70 +1288,69 @@ static void snb_gt_irq_handler(struct drm_device *dev,
 		ivybridge_parity_error_irq_handler(dev, gt_iir);
 }
 
+static __always_inline void
+gen8_cs_irq_handler(struct intel_engine_cs *ring, u32 iir, int test_shift)
+{
+	if (iir & (GT_RENDER_USER_INTERRUPT << test_shift))
+		notify_ring(ring);
+	if (iir & (GT_CONTEXT_SWITCH_INTERRUPT << test_shift))
+		intel_lrc_irq_handler(ring);
+}
+
 static irqreturn_t gen8_gt_irq_handler(struct drm_i915_private *dev_priv,
 				       u32 master_ctl)
 {
 	irqreturn_t ret = IRQ_NONE;
 
 	if (master_ctl & (GEN8_GT_RCS_IRQ | GEN8_GT_BCS_IRQ)) {
-		u32 tmp = I915_READ_FW(GEN8_GT_IIR(0));
-		if (tmp) {
-			I915_WRITE_FW(GEN8_GT_IIR(0), tmp);
+		u32 iir = I915_READ_FW(GEN8_GT_IIR(0));
+		if (iir) {
+			I915_WRITE_FW(GEN8_GT_IIR(0), iir);
 			ret = IRQ_HANDLED;
 
-			if (tmp & (GT_CONTEXT_SWITCH_INTERRUPT << GEN8_RCS_IRQ_SHIFT))
-				intel_lrc_irq_handler(&dev_priv->ring[RCS]);
-			if (tmp & (GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT))
-				notify_ring(&dev_priv->ring[RCS]);
+			gen8_cs_irq_handler(&dev_priv->ring[RCS],
+					iir, GEN8_RCS_IRQ_SHIFT);
 
-			if (tmp & (GT_CONTEXT_SWITCH_INTERRUPT << GEN8_BCS_IRQ_SHIFT))
-				intel_lrc_irq_handler(&dev_priv->ring[BCS]);
-			if (tmp & (GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT))
-				notify_ring(&dev_priv->ring[BCS]);
+			gen8_cs_irq_handler(&dev_priv->ring[BCS],
+					iir, GEN8_BCS_IRQ_SHIFT);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT0)!\n");
 	}
 
 	if (master_ctl & (GEN8_GT_VCS1_IRQ | GEN8_GT_VCS2_IRQ)) {
-		u32 tmp = I915_READ_FW(GEN8_GT_IIR(1));
-		if (tmp) {
-			I915_WRITE_FW(GEN8_GT_IIR(1), tmp);
+		u32 iir = I915_READ_FW(GEN8_GT_IIR(1));
+		if (iir) {
+			I915_WRITE_FW(GEN8_GT_IIR(1), iir);
 			ret = IRQ_HANDLED;
 
-			if (tmp & (GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS1_IRQ_SHIFT))
-				intel_lrc_irq_handler(&dev_priv->ring[VCS]);
-			if (tmp & (GT_RENDER_USER_INTERRUPT << GEN8_VCS1_IRQ_SHIFT))
-				notify_ring(&dev_priv->ring[VCS]);
+			gen8_cs_irq_handler(&dev_priv->ring[VCS],
+					iir, GEN8_VCS1_IRQ_SHIFT);
 
-			if (tmp & (GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS2_IRQ_SHIFT))
-				intel_lrc_irq_handler(&dev_priv->ring[VCS2]);
-			if (tmp & (GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT))
-				notify_ring(&dev_priv->ring[VCS2]);
+			gen8_cs_irq_handler(&dev_priv->ring[VCS2],
+					iir, GEN8_VCS2_IRQ_SHIFT);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT1)!\n");
 	}
 
 	if (master_ctl & GEN8_GT_VECS_IRQ) {
-		u32 tmp = I915_READ_FW(GEN8_GT_IIR(3));
-		if (tmp) {
-			I915_WRITE_FW(GEN8_GT_IIR(3), tmp);
+		u32 iir = I915_READ_FW(GEN8_GT_IIR(3));
+		if (iir) {
+			I915_WRITE_FW(GEN8_GT_IIR(3), iir);
 			ret = IRQ_HANDLED;
 
-			if (tmp & (GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VECS_IRQ_SHIFT))
-				intel_lrc_irq_handler(&dev_priv->ring[VECS]);
-			if (tmp & (GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT))
-				notify_ring(&dev_priv->ring[VECS]);
+			gen8_cs_irq_handler(&dev_priv->ring[VECS],
+					iir, GEN8_VECS_IRQ_SHIFT);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT3)!\n");
 	}
 
 	if (master_ctl & GEN8_GT_PM_IRQ) {
-		u32 tmp = I915_READ_FW(GEN8_GT_IIR(2));
-		if (tmp & dev_priv->pm_rps_events) {
+		u32 iir = I915_READ_FW(GEN8_GT_IIR(2));
+		if (iir & dev_priv->pm_rps_events) {
 			I915_WRITE_FW(GEN8_GT_IIR(2),
-				      tmp & dev_priv->pm_rps_events);
+				      iir & dev_priv->pm_rps_events);
 			ret = IRQ_HANDLED;
-			gen6_rps_irq_handler(dev_priv, tmp);
+			gen6_rps_irq_handler(dev_priv, iir);
 		} else
 			DRM_ERROR("The master control interrupt lied (PM)!\n");
 	}
@@ -1625,7 +1622,7 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 
 	spin_lock(&dev_priv->irq_lock);
 	for_each_pipe(dev_priv, pipe) {
-		int reg;
+		i915_reg_t reg;
 		u32 mask, iir_bit = 0;
 
 		/*
@@ -2354,9 +2351,13 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 				spt_irq_handler(dev, pch_iir);
 			else
 				cpt_irq_handler(dev, pch_iir);
-		} else
-			DRM_ERROR("The master control interrupt lied (SDE)!\n");
-
+		} else {
+			/*
+			 * Like on previous PCH there seems to be something
+			 * fishy going on with forwarding PCH interrupts.
+			 */
+			DRM_DEBUG_DRIVER("The master control interrupt lied (SDE)!\n");
+		}
 	}
 
 	I915_WRITE_FW(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL);
@@ -3869,7 +3870,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
 
 		for_each_pipe(dev_priv, pipe) {
-			int reg = PIPESTAT(pipe);
+			i915_reg_t reg = PIPESTAT(pipe);
 			pipe_stats[pipe] = I915_READ(reg);
 
 			/*
@@ -4050,7 +4051,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
 
 		for_each_pipe(dev_priv, pipe) {
-			int reg = PIPESTAT(pipe);
+			i915_reg_t reg = PIPESTAT(pipe);
 			pipe_stats[pipe] = I915_READ(reg);
 
 			/* Clear the PIPE*STAT regs before the IIR */
@@ -4272,7 +4273,7 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
 
 		for_each_pipe(dev_priv, pipe) {
-			int reg = PIPESTAT(pipe);
+			i915_reg_t reg = PIPESTAT(pipe);
 			pipe_stats[pipe] = I915_READ(reg);
 
 			/*

drivers/gpu/drm/i915/i915_params.c

@@ -32,6 +32,7 @@ struct i915_params i915 __read_mostly = {
 	.panel_use_ssc = -1,
 	.vbt_sdvo_panel_type = -1,
 	.enable_rc6 = -1,
+	.enable_dc = -1,
 	.enable_fbc = -1,
 	.enable_execlists = -1,
 	.enable_hangcheck = true,
@@ -80,6 +81,11 @@ MODULE_PARM_DESC(enable_rc6,
 	"For example, 3 would enable rc6 and deep rc6, and 7 would enable everything. "
 	"default: -1 (use per-chip default)");
 
+module_param_named_unsafe(enable_dc, i915.enable_dc, int, 0400);
+MODULE_PARM_DESC(enable_dc,
+	"Enable power-saving display C-states. "
+	"(-1=auto [default]; 0=disable; 1=up to DC5; 2=up to DC6)");
+
 module_param_named_unsafe(enable_fbc, i915.enable_fbc, int, 0600);
 MODULE_PARM_DESC(enable_fbc,
 	"Enable frame buffer compression for power savings "
@@ -112,7 +118,7 @@ MODULE_PARM_DESC(enable_hangcheck,
 module_param_named_unsafe(enable_ppgtt, i915.enable_ppgtt, int, 0400);
 MODULE_PARM_DESC(enable_ppgtt,
 	"Override PPGTT usage. "
-	"(-1=auto [default], 0=disabled, 1=aliasing, 2=full)");
+	"(-1=auto [default], 0=disabled, 1=aliasing, 2=full, 3=full with extended address space)");
 
 module_param_named_unsafe(enable_execlists, i915.enable_execlists, int, 0400);
 MODULE_PARM_DESC(enable_execlists,
@@ -126,7 +132,7 @@ module_param_named_unsafe(preliminary_hw_support, i915.preliminary_hw_support, i
 MODULE_PARM_DESC(preliminary_hw_support,
 	"Enable preliminary hardware support.");
 
-module_param_named_unsafe(disable_power_well, i915.disable_power_well, int, 0600);
+module_param_named_unsafe(disable_power_well, i915.disable_power_well, int, 0400);
 MODULE_PARM_DESC(disable_power_well,
 	"Disable display power wells when possible "
 	"(-1=auto [default], 0=power wells always on, 1=power wells disabled when possible)");

drivers/gpu/drm/i915/i915_sysfs.c

@@ -35,7 +35,8 @@
 #define dev_to_drm_minor(d) dev_get_drvdata((d))
 
 #ifdef CONFIG_PM
-static u32 calc_residency(struct drm_device *dev, const u32 reg)
+static u32 calc_residency(struct drm_device *dev,
+			  i915_reg_t reg)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u64 raw_time; /* 32b value may overflow during fixed point math */

drivers/gpu/drm/i915/i915_trace.h

@@ -664,7 +664,7 @@ TRACE_EVENT(i915_flip_complete,
 );
 
 TRACE_EVENT_CONDITION(i915_reg_rw,
-	TP_PROTO(bool write, u32 reg, u64 val, int len, bool trace),
+	TP_PROTO(bool write, i915_reg_t reg, u64 val, int len, bool trace),
 
 	TP_ARGS(write, reg, val, len, trace),
 
@@ -679,7 +679,7 @@ TRACE_EVENT_CONDITION(i915_reg_rw,
 
 	TP_fast_assign(
 		__entry->val = (u64)val;
-		__entry->reg = reg;
+		__entry->reg = i915_mmio_reg_offset(reg);
 		__entry->write = write;
 		__entry->len = len;
 		),

drivers/gpu/drm/i915/i915_vgpu.c

@@ -69,13 +69,13 @@ void i915_check_vgpu(struct drm_device *dev)
 	if (!IS_HASWELL(dev))
 		return;
 
-	magic = readq(dev_priv->regs + vgtif_reg(magic));
+	magic = __raw_i915_read64(dev_priv, vgtif_reg(magic));
 	if (magic != VGT_MAGIC)
 		return;
 
 	version = INTEL_VGT_IF_VERSION_ENCODE(
-		readw(dev_priv->regs + vgtif_reg(version_major)),
-		readw(dev_priv->regs + vgtif_reg(version_minor)));
+		__raw_i915_read16(dev_priv, vgtif_reg(version_major)),
+		__raw_i915_read16(dev_priv, vgtif_reg(version_minor)));
 	if (version != INTEL_VGT_IF_VERSION) {
 		DRM_INFO("VGT interface version mismatch!\n");
 		return;

drivers/gpu/drm/i915/i915_vgpu.h

@@ -92,14 +92,10 @@ struct vgt_if {
 	uint32_t g2v_notify;
 	uint32_t rsv6[7];
 
-	uint32_t pdp0_lo;
-	uint32_t pdp0_hi;
-	uint32_t pdp1_lo;
-	uint32_t pdp1_hi;
-	uint32_t pdp2_lo;
-	uint32_t pdp2_hi;
-	uint32_t pdp3_lo;
-	uint32_t pdp3_hi;
+	struct {
+		uint32_t lo;
+		uint32_t hi;
+	} pdp[4];
 
 	uint32_t execlist_context_descriptor_lo;
 	uint32_t execlist_context_descriptor_hi;
@@ -108,7 +104,7 @@ struct vgt_if {
 } __packed;
 
 #define vgtif_reg(x) \
-	(VGT_PVINFO_PAGE + (long)&((struct vgt_if *)NULL)->x)
+	_MMIO((VGT_PVINFO_PAGE + (long)&((struct vgt_if *)NULL)->x))
 
 /* vGPU display status to be used by the host side */
 #define VGT_DRV_DISPLAY_NOT_READY 0

drivers/gpu/drm/i915/intel_atomic.c

@@ -94,6 +94,7 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc)
 	__drm_atomic_helper_crtc_duplicate_state(crtc, &crtc_state->base);
 
 	crtc_state->update_pipe = false;
+	crtc_state->disable_lp_wm = false;
 
 	return &crtc_state->base;
 }
@@ -205,8 +206,6 @@ int intel_atomic_setup_scalers(struct drm_device *dev,
 				 * but since this plane is unchanged just do the
 				 * minimum required validation.
 				 */
-				if (plane->type == DRM_PLANE_TYPE_PRIMARY)
-					intel_crtc->atomic.wait_for_flips = true;
 				crtc_state->base.planes_changed = true;
 			}
 

drivers/gpu/drm/i915/intel_atomic_plane.c

@@ -84,6 +84,7 @@ intel_plane_duplicate_state(struct drm_plane *plane)
 	state = &intel_state->base;
 
 	__drm_atomic_helper_plane_duplicate_state(plane, state);
+	intel_state->wait_req = NULL;
 
 	return state;
 }
@@ -100,6 +101,7 @@ void
 intel_plane_destroy_state(struct drm_plane *plane,
 			  struct drm_plane_state *state)
 {
+	WARN_ON(state && to_intel_plane_state(state)->wait_req);
 	drm_atomic_helper_plane_destroy_state(plane, state);
 }
 

drivers/gpu/drm/i915/intel_audio.c

@@ -161,9 +161,9 @@ static bool audio_rate_need_prog(struct intel_crtc *crtc,
 }
 
 static bool intel_eld_uptodate(struct drm_connector *connector,
-			       int reg_eldv, uint32_t bits_eldv,
-			       int reg_elda, uint32_t bits_elda,
-			       int reg_edid)
+			       i915_reg_t reg_eldv, uint32_t bits_eldv,
+			       i915_reg_t reg_elda, uint32_t bits_elda,
+			       i915_reg_t reg_edid)
 {
 	struct drm_i915_private *dev_priv = connector->dev->dev_private;
 	uint8_t *eld = connector->eld;
@@ -364,8 +364,7 @@ static void ilk_audio_codec_disable(struct intel_encoder *encoder)
 	enum port port = intel_dig_port->port;
 	enum pipe pipe = intel_crtc->pipe;
 	uint32_t tmp, eldv;
-	int aud_config;
-	int aud_cntrl_st2;
+	i915_reg_t aud_config, aud_cntrl_st2;
 
 	DRM_DEBUG_KMS("Disable audio codec on port %c, pipe %c\n",
 		      port_name(port), pipe_name(pipe));
@@ -416,10 +415,7 @@ static void ilk_audio_codec_enable(struct drm_connector *connector,
 	uint32_t eldv;
 	uint32_t tmp;
 	int len, i;
-	int hdmiw_hdmiedid;
-	int aud_config;
-	int aud_cntl_st;
-	int aud_cntrl_st2;
+	i915_reg_t hdmiw_hdmiedid, aud_config, aud_cntl_st, aud_cntrl_st2;
 
 	DRM_DEBUG_KMS("Enable audio codec on port %c, pipe %c, %u bytes ELD\n",
 		      port_name(port), pipe_name(pipe), drm_eld_size(eld));
@@ -591,7 +587,7 @@ static void i915_audio_component_codec_wake_override(struct device *dev,
 	struct drm_i915_private *dev_priv = dev_to_i915(dev);
 	u32 tmp;
 
-	if (!IS_SKYLAKE(dev_priv))
+	if (!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv))
 		return;
 
 	/*
@@ -642,10 +638,11 @@ static int i915_audio_component_sync_audio_rate(struct device *dev,
 	u32 tmp;
 	int n;
 
-	/* HSW, BDW SKL need this fix */
+	/* HSW, BDW, SKL, KBL need this fix */
 	if (!IS_SKYLAKE(dev_priv) &&
-		!IS_BROADWELL(dev_priv) &&
-		!IS_HASWELL(dev_priv))
+	    !IS_KABYLAKE(dev_priv) &&
+	    !IS_BROADWELL(dev_priv) &&
+	    !IS_HASWELL(dev_priv))
 		return 0;
 
 	mutex_lock(&dev_priv->av_mutex);

drivers/gpu/drm/i915/intel_crt.c

@@ -50,7 +50,7 @@ struct intel_crt {
 	 * encoder's enable/disable callbacks */
 	struct intel_connector *connector;
 	bool force_hotplug_required;
-	u32 adpa_reg;
+	i915_reg_t adpa_reg;
 };
 
 static struct intel_crt *intel_encoder_to_crt(struct intel_encoder *encoder)
@@ -480,12 +480,8 @@ intel_crt_load_detect(struct intel_crt *crt)
 	uint32_t vsample;
 	uint32_t vblank, vblank_start, vblank_end;
 	uint32_t dsl;
-	uint32_t bclrpat_reg;
-	uint32_t vtotal_reg;
-	uint32_t vblank_reg;
-	uint32_t vsync_reg;
-	uint32_t pipeconf_reg;
-	uint32_t pipe_dsl_reg;
+	i915_reg_t bclrpat_reg, vtotal_reg,
+		vblank_reg, vsync_reg, pipeconf_reg, pipe_dsl_reg;
 	uint8_t	st00;
 	enum drm_connector_status status;
 
@@ -518,7 +514,7 @@ intel_crt_load_detect(struct intel_crt *crt)
 		/* Wait for next Vblank to substitue
 		 * border color for Color info */
 		intel_wait_for_vblank(dev, pipe);
-		st00 = I915_READ8(VGA_MSR_WRITE);
+		st00 = I915_READ8(_VGA_MSR_WRITE);
 		status = ((st00 & (1 << 4)) != 0) ?
 			connector_status_connected :
 			connector_status_disconnected;
@@ -563,7 +559,7 @@ intel_crt_load_detect(struct intel_crt *crt)
 		do {
 			count++;
 			/* Read the ST00 VGA status register */
-			st00 = I915_READ8(VGA_MSR_WRITE);
+			st00 = I915_READ8(_VGA_MSR_WRITE);
 			if (st00 & (1 << 4))
 				detect++;
 		} while ((I915_READ(pipe_dsl_reg) == dsl));

drivers/gpu/drm/i915/intel_dp_mst.c

@@ -173,20 +173,14 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder)
 	intel_mst->port = found->port;
 
 	if (intel_dp->active_mst_links == 0) {
-		enum port port = intel_ddi_get_encoder_port(encoder);
+		intel_ddi_clk_select(encoder, intel_crtc->config);
 
 		intel_dp_set_link_params(intel_dp, intel_crtc->config);
 
-		/* FIXME: add support for SKL */
-		if (INTEL_INFO(dev)->gen < 9)
-			I915_WRITE(PORT_CLK_SEL(port),
-				   intel_crtc->config->ddi_pll_sel);
-
 		intel_ddi_init_dp_buf_reg(&intel_dig_port->base);
 
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 
-
 		intel_dp_start_link_train(intel_dp);
 		intel_dp_stop_link_train(intel_dp);
 	}
@@ -414,7 +408,10 @@ static void intel_connector_add_to_fbdev(struct intel_connector *connector)
 {
 #ifdef CONFIG_DRM_FBDEV_EMULATION
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	drm_fb_helper_add_one_connector(&dev_priv->fbdev->helper, &connector->base);
+
+	if (dev_priv->fbdev)
+		drm_fb_helper_add_one_connector(&dev_priv->fbdev->helper,
+						&connector->base);
 #endif
 }
 
@@ -422,7 +419,10 @@ static void intel_connector_remove_from_fbdev(struct intel_connector *connector)
 {
 #ifdef CONFIG_DRM_FBDEV_EMULATION
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	drm_fb_helper_remove_one_connector(&dev_priv->fbdev->helper, &connector->base);
+
+	if (dev_priv->fbdev)
+		drm_fb_helper_remove_one_connector(&dev_priv->fbdev->helper,
+						   &connector->base);
 #endif
 }
 

drivers/gpu/drm/i915/intel_dsi.c

@@ -60,7 +60,8 @@ static void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port)
 		DRM_ERROR("DPI FIFOs are not empty\n");
 }
 
-static void write_data(struct drm_i915_private *dev_priv, u32 reg,
+static void write_data(struct drm_i915_private *dev_priv,
+		       i915_reg_t reg,
 		       const u8 *data, u32 len)
 {
 	u32 i, j;
@@ -75,7 +76,8 @@ static void write_data(struct drm_i915_private *dev_priv, u32 reg,
 	}
 }
 
-static void read_data(struct drm_i915_private *dev_priv, u32 reg,
+static void read_data(struct drm_i915_private *dev_priv,
+		      i915_reg_t reg,
 		      u8 *data, u32 len)
 {
 	u32 i, j;
@@ -98,7 +100,8 @@ static ssize_t intel_dsi_host_transfer(struct mipi_dsi_host *host,
 	struct mipi_dsi_packet packet;
 	ssize_t ret;
 	const u8 *header, *data;
-	u32 data_reg, data_mask, ctrl_reg, ctrl_mask;
+	i915_reg_t data_reg, ctrl_reg;
+	u32 data_mask, ctrl_mask;
 
 	ret = mipi_dsi_create_packet(&packet, msg);
 	if (ret < 0)
@@ -377,10 +380,10 @@ static void intel_dsi_port_enable(struct intel_encoder *encoder)
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
-	u32 temp;
-	u32 port_ctrl;
 
 	if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) {
+		u32 temp;
+
 		temp = I915_READ(VLV_CHICKEN_3);
 		temp &= ~PIXEL_OVERLAP_CNT_MASK |
 					intel_dsi->pixel_overlap <<
@@ -389,8 +392,9 @@ static void intel_dsi_port_enable(struct intel_encoder *encoder)
 	}
 
 	for_each_dsi_port(port, intel_dsi->ports) {
-		port_ctrl = IS_BROXTON(dev) ? BXT_MIPI_PORT_CTRL(port) :
-						MIPI_PORT_CTRL(port);
+		i915_reg_t port_ctrl = IS_BROXTON(dev) ?
+			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(port);
+		u32 temp;
 
 		temp = I915_READ(port_ctrl);
 
@@ -416,13 +420,13 @@ static void intel_dsi_port_disable(struct intel_encoder *encoder)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
-	u32 temp;
-	u32 port_ctrl;
 
 	for_each_dsi_port(port, intel_dsi->ports) {
+		i915_reg_t port_ctrl = IS_BROXTON(dev) ?
+			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(port);
+		u32 temp;
+
 		/* de-assert ip_tg_enable signal */
-		port_ctrl = IS_BROXTON(dev) ? BXT_MIPI_PORT_CTRL(port) :
-						MIPI_PORT_CTRL(port);
 		temp = I915_READ(port_ctrl);
 		I915_WRITE(port_ctrl, temp & ~DPI_ENABLE);
 		POSTING_READ(port_ctrl);
@@ -580,11 +584,13 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
-	u32 val;
-	u32 port_ctrl = 0;
 
 	DRM_DEBUG_KMS("\n");
 	for_each_dsi_port(port, intel_dsi->ports) {
+		/* Common bit for both MIPI Port A & MIPI Port C on VLV/CHV */
+		i915_reg_t port_ctrl = IS_BROXTON(dev) ?
+			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(PORT_A);
+		u32 val;
 
 		I915_WRITE(MIPI_DEVICE_READY(port), DEVICE_READY |
 							ULPS_STATE_ENTER);
@@ -598,12 +604,6 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 							ULPS_STATE_ENTER);
 		usleep_range(2000, 2500);
 
-		if (IS_BROXTON(dev))
-			port_ctrl = BXT_MIPI_PORT_CTRL(port);
-		else if (IS_VALLEYVIEW(dev))
-			/* Common bit for both MIPI Port A & MIPI Port C */
-			port_ctrl = MIPI_PORT_CTRL(PORT_A);
-
 		/* Wait till Clock lanes are in LP-00 state for MIPI Port A
 		 * only. MIPI Port C has no similar bit for checking
 		 */
@@ -656,7 +656,6 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	struct drm_device *dev = encoder->base.dev;
 	enum intel_display_power_domain power_domain;
-	u32 dpi_enabled, func, ctrl_reg;
 	enum port port;
 
 	DRM_DEBUG_KMS("\n");
@@ -667,9 +666,11 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 
 	/* XXX: this only works for one DSI output */
 	for_each_dsi_port(port, intel_dsi->ports) {
+		i915_reg_t ctrl_reg = IS_BROXTON(dev) ?
+			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(port);
+		u32 dpi_enabled, func;
+
 		func = I915_READ(MIPI_DSI_FUNC_PRG(port));
-		ctrl_reg = IS_BROXTON(dev) ? BXT_MIPI_PORT_CTRL(port) :
-						MIPI_PORT_CTRL(port);
 		dpi_enabled = I915_READ(ctrl_reg) & DPI_ENABLE;
 
 		/* Due to some hardware limitations on BYT, MIPI Port C DPI

drivers/gpu/drm/i915/intel_guc.h

@@ -76,11 +76,17 @@ struct intel_guc_fw {
 	uint16_t			guc_fw_minor_wanted;
 	uint16_t			guc_fw_major_found;
 	uint16_t			guc_fw_minor_found;
+
+	uint32_t header_size;
+	uint32_t header_offset;
+	uint32_t rsa_size;
+	uint32_t rsa_offset;
+	uint32_t ucode_size;
+	uint32_t ucode_offset;
 };
 
 struct intel_guc {
 	struct intel_guc_fw guc_fw;
-
 	uint32_t log_flags;
 	struct drm_i915_gem_object *log_obj;
 

kernel/async.c

@@ -326,3 +326,4 @@ bool current_is_async(void)
 
 	return worker && worker->current_func == async_run_entry_fn;
 }
+EXPORT_SYMBOL_GPL(current_is_async);