Merge tag 'drm-intel-next-2017-12-01' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

[airlied: fix conflict in intel_dsi.c]

drm-intel-next-2017-12-01:

- Init clock gate fix (Ville)
- Execlists event handling corrections (Chris, Michel)
- Improvements on GPU Cache invalidation and context switch (Chris)
- More perf OA changes (Lionel)
- More selftests improvements and fixes (Chris, Matthew)
- Clean-up on modules parameters (Chris)
- Clean-up around old ringbuffer submission and hw semaphore on old platforms (Chris)
- More Cannonlake stabilization effort (David, James)
- Display planes clean-up and improvements (Ville)
- New PMU interface for perf queries... (Tvrtko)
- ... and other subsequent PMU changes and fixes (Tvrtko, Chris)
- Remove success dmesg noise from rotation (Chris)
- New DMC for Kabylake (Anusha)
- Fixes around atomic commits (Daniel)
- GuC updates and fixes (Sagar, Michal, Chris)
- Couple gmbus/i2c fixes (Ville)
- Use exponential backoff for all our wait_for() (Chris)
- Fixes for i915/fbdev (Chris)
- Backlight fixes (Arnd)
- Updates on shrinker (Chris)
- Make Hotplug enable more robuts (Chris)
- Disable huge pages (TPH) on lack of a needed workaround (Joonas)
- New GuC images for SKL, KBL, BXT (Sagar)
- Add HW Workaround for Geminilake performance (Valtteri)
- Fixes for PPS timings (Imre)
- More IPS fixes (Maarten)
- Many fixes for Display Port on gen2-gen4 (Ville)
- Retry GPU reset making the recover from hang more robust (Chris)

* tag 'drm-intel-next-2017-12-01' of git://anongit.freedesktop.org/drm/drm-intel: (101 commits)
  drm/i915: Update DRIVER_DATE to 20171201
  drm/i915/cnl: Mask previous DDI - PLL mapping
  drm/i915: Remove unsafe i915.enable_rc6
  drm/i915: Sleep and retry a GPU reset if at first we don't succeed
  drm/i915: Interlaced DP output doesn't work on VLV/CHV
  drm/i915: Pass crtc state to intel_pipe_{enable,disable}()
  drm/i915: Wait for pipe to start on i830 as well
  drm/i915: Fix vblank timestamp/frame counter jumps on gen2
  drm/i915: Fix deadlock in i830_disable_pipe()
  drm/i915: Fix has_audio readout for DDI A
  drm/i915: Don't add the "force audio" property to DP connectors that don't support audio
  drm/i915: Disable DP audio for g4x
  drm/i915/selftests: Wake the device before executing requests on the GPU
  drm/i915: Set fake_vma.size as well as fake_vma.node.size for capture
  drm/i915: Tidy up signed/unsigned comparison
  drm/i915: Enable IPS with only sprite plane visible too, v4.
  drm/i915: Make ips_enabled a property depending on whether IPS is enabled, v3.
  drm/i915: Avoid PPS HW/SW state mismatch due to rounding
  drm/i915: Skip switch-to-kernel-context on suspend when wedged
  drm/i915/glk: Apply WaProgramL3SqcReg1DefaultForPerf for GLK too
  ...

drivers/gpu/drm/i915/Kconfig.debug

@@ -18,6 +18,7 @@ config DRM_I915_WERROR
 config DRM_I915_DEBUG
         bool "Enable additional driver debugging"
         depends on DRM_I915
+        select DEBUG_FS
         select PREEMPT_COUNT
         select I2C_CHARDEV
         select DRM_DP_AUX_CHARDEV

drivers/gpu/drm/i915/Makefile

@@ -46,6 +46,7 @@ i915-y := i915_drv.o \
 
 i915-$(CONFIG_COMPAT)   += i915_ioc32.o
 i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o intel_pipe_crc.o
+i915-$(CONFIG_PERF_EVENTS) += i915_pmu.o
 
 # GEM code
 i915-y += i915_cmd_parser.o \

drivers/gpu/drm/i915/gvt/render.c

@@ -294,8 +294,7 @@ static void switch_mmio_to_vgpu(struct intel_vgpu *vgpu, int ring_id)
 		 * write.
 		 */
 		if (mmio->in_context &&
-				((ctx_ctrl & inhibit_mask) != inhibit_mask) &&
-				i915_modparams.enable_execlists)
+		    (ctx_ctrl & inhibit_mask) != inhibit_mask)
 			continue;
 
 		if (mmio->mask)

drivers/gpu/drm/i915/i915_cmd_parser.c

@@ -26,6 +26,7 @@
  */
 
 #include "i915_drv.h"
+#include "intel_ringbuffer.h"
 
 /**
  * DOC: batch buffer command parser
@@ -940,7 +941,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 		return;
 	}
 
-	engine->needs_cmd_parser = true;
+	engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER;
 }
 
 /**
@@ -952,7 +953,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
  */
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine)
 {
-	if (!engine->needs_cmd_parser)
+	if (!intel_engine_needs_cmd_parser(engine))
 		return;
 
 	fini_hash_table(engine);
@@ -1350,7 +1351,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 
 	/* If the command parser is not enabled, report 0 - unsupported */
 	for_each_engine(engine, dev_priv, id) {
-		if (engine->needs_cmd_parser) {
+		if (intel_engine_needs_cmd_parser(engine)) {
 			active = true;
 			break;
 		}

drivers/gpu/drm/i915/i915_debugfs.c

@@ -1151,13 +1151,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		rpdownei = I915_READ(GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
 		rpcurdown = I915_READ(GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK;
 		rpprevdown = I915_READ(GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK;
-		if (INTEL_GEN(dev_priv) >= 9)
-			cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
-		else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-			cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
-		else
-			cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
-		cagf = intel_gpu_freq(dev_priv, cagf);
+		cagf = intel_gpu_freq(dev_priv,
+				      intel_get_cagf(dev_priv, rpstat));
 
 		intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
@@ -1989,75 +1984,6 @@ static int i915_context_status(struct seq_file *m, void *unused)
 	return 0;
 }
 
-static void i915_dump_lrc_obj(struct seq_file *m,
-			      struct i915_gem_context *ctx,
-			      struct intel_engine_cs *engine)
-{
-	struct i915_vma *vma = ctx->engine[engine->id].state;
-	struct page *page;
-	int j;
-
-	seq_printf(m, "CONTEXT: %s %u\n", engine->name, ctx->hw_id);
-
-	if (!vma) {
-		seq_puts(m, "\tFake context\n");
-		return;
-	}
-
-	if (vma->flags & I915_VMA_GLOBAL_BIND)
-		seq_printf(m, "\tBound in GGTT at 0x%08x\n",
-			   i915_ggtt_offset(vma));
-
-	if (i915_gem_object_pin_pages(vma->obj)) {
-		seq_puts(m, "\tFailed to get pages for context object\n\n");
-		return;
-	}
-
-	page = i915_gem_object_get_page(vma->obj, LRC_STATE_PN);
-	if (page) {
-		u32 *reg_state = kmap_atomic(page);
-
-		for (j = 0; j < 0x600 / sizeof(u32) / 4; j += 4) {
-			seq_printf(m,
-				   "\t[0x%04x] 0x%08x 0x%08x 0x%08x 0x%08x\n",
-				   j * 4,
-				   reg_state[j], reg_state[j + 1],
-				   reg_state[j + 2], reg_state[j + 3]);
-		}
-		kunmap_atomic(reg_state);
-	}
-
-	i915_gem_object_unpin_pages(vma->obj);
-	seq_putc(m, '\n');
-}
-
-static int i915_dump_lrc(struct seq_file *m, void *unused)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
-	enum intel_engine_id id;
-	int ret;
-
-	if (!i915_modparams.enable_execlists) {
-		seq_printf(m, "Logical Ring Contexts are disabled\n");
-		return 0;
-	}
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
-
-	list_for_each_entry(ctx, &dev_priv->contexts.list, link)
-		for_each_engine(engine, dev_priv, id)
-			i915_dump_lrc_obj(m, ctx, engine);
-
-	mutex_unlock(&dev->struct_mutex);
-
-	return 0;
-}
-
 static const char *swizzle_string(unsigned swizzle)
 {
 	switch (swizzle) {
@@ -3304,69 +3230,6 @@ static int i915_shrinker_info(struct seq_file *m, void *unused)
 	return 0;
 }
 
-static int i915_semaphore_status(struct seq_file *m, void *unused)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_engine_cs *engine;
-	int num_rings = INTEL_INFO(dev_priv)->num_rings;
-	enum intel_engine_id id;
-	int j, ret;
-
-	if (!i915_modparams.semaphores) {
-		seq_puts(m, "Semaphores are disabled\n");
-		return 0;
-	}
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
-	intel_runtime_pm_get(dev_priv);
-
-	if (IS_BROADWELL(dev_priv)) {
-		struct page *page;
-		uint64_t *seqno;
-
-		page = i915_gem_object_get_page(dev_priv->semaphore->obj, 0);
-
-		seqno = (uint64_t *)kmap_atomic(page);
-		for_each_engine(engine, dev_priv, id) {
-			uint64_t offset;
-
-			seq_printf(m, "%s\n", engine->name);
-
-			seq_puts(m, "  Last signal:");
-			for (j = 0; j < num_rings; j++) {
-				offset = id * I915_NUM_ENGINES + j;
-				seq_printf(m, "0x%08llx (0x%02llx) ",
-					   seqno[offset], offset * 8);
-			}
-			seq_putc(m, '\n');
-
-			seq_puts(m, "  Last wait:  ");
-			for (j = 0; j < num_rings; j++) {
-				offset = id + (j * I915_NUM_ENGINES);
-				seq_printf(m, "0x%08llx (0x%02llx) ",
-					   seqno[offset], offset * 8);
-			}
-			seq_putc(m, '\n');
-
-		}
-		kunmap_atomic(seqno);
-	} else {
-		seq_puts(m, "  Last signal:");
-		for_each_engine(engine, dev_priv, id)
-			for (j = 0; j < num_rings; j++)
-				seq_printf(m, "0x%08x\n",
-					   I915_READ(engine->semaphore.mbox.signal[j]));
-		seq_putc(m, '\n');
-	}
-
-	intel_runtime_pm_put(dev_priv);
-	mutex_unlock(&dev->struct_mutex);
-	return 0;
-}
-
 static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -4833,7 +4696,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_vbt", i915_vbt, 0},
 	{"i915_gem_framebuffer", i915_gem_framebuffer_info, 0},
 	{"i915_context_status", i915_context_status, 0},
-	{"i915_dump_lrc", i915_dump_lrc, 0},
 	{"i915_forcewake_domains", i915_forcewake_domains, 0},
 	{"i915_swizzle_info", i915_swizzle_info, 0},
 	{"i915_ppgtt_info", i915_ppgtt_info, 0},
@@ -4847,7 +4709,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_display_info", i915_display_info, 0},
 	{"i915_engine_info", i915_engine_info, 0},
 	{"i915_shrinker_info", i915_shrinker_info, 0},
-	{"i915_semaphore_status", i915_semaphore_status, 0},
 	{"i915_shared_dplls_info", i915_shared_dplls_info, 0},
 	{"i915_dp_mst_info", i915_dp_mst_info, 0},
 	{"i915_wa_registers", i915_wa_registers, 0},

drivers/gpu/drm/i915/i915_drv.c

@@ -48,6 +48,7 @@
 
 #include "i915_drv.h"
 #include "i915_trace.h"
+#include "i915_pmu.h"
 #include "i915_vgpu.h"
 #include "intel_drv.h"
 #include "intel_uc.h"
@@ -321,7 +322,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
 		value = USES_PPGTT(dev_priv);
 		break;
 	case I915_PARAM_HAS_SEMAPHORES:
-		value = i915_modparams.semaphores;
+		value = HAS_LEGACY_SEMAPHORES(dev_priv);
 		break;
 	case I915_PARAM_HAS_SECURE_BATCHES:
 		value = capable(CAP_SYS_ADMIN);
@@ -371,9 +372,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
 		if (dev_priv->engine[RCS] && dev_priv->engine[RCS]->schedule) {
 			value |= I915_SCHEDULER_CAP_ENABLED;
 			value |= I915_SCHEDULER_CAP_PRIORITY;
-
-			if (HAS_LOGICAL_RING_PREEMPTION(dev_priv) &&
-			    i915_modparams.enable_execlists)
+			if (HAS_LOGICAL_RING_PREEMPTION(dev_priv))
 				value |= I915_SCHEDULER_CAP_PREEMPTION;
 		}
 		break;
@@ -694,8 +693,6 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	/* Only enable hotplug handling once the fbdev is fully set up. */
 	intel_hpd_init(dev_priv);
 
-	drm_kms_helper_poll_init(dev);
-
 	return 0;
 
 cleanup_gem:
@@ -936,8 +933,6 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv,
 
 	intel_detect_preproduction_hw(dev_priv);
 
-	i915_perf_init(dev_priv);
-
 	return 0;
 
 err_irq:
@@ -954,7 +949,6 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv,
  */
 static void i915_driver_cleanup_early(struct drm_i915_private *dev_priv)
 {
-	i915_perf_fini(dev_priv);
 	i915_gem_load_cleanup(dev_priv);
 	intel_irq_fini(dev_priv);
 	i915_workqueues_cleanup(dev_priv);
@@ -1057,10 +1051,6 @@ static void i915_driver_cleanup_mmio(struct drm_i915_private *dev_priv)
 
 static void intel_sanitize_options(struct drm_i915_private *dev_priv)
 {
-	i915_modparams.enable_execlists =
-		intel_sanitize_enable_execlists(dev_priv,
-						i915_modparams.enable_execlists);
-
 	/*
 	 * i915.enable_ppgtt is read-only, so do an early pass to validate the
 	 * user's requested state against the hardware/driver capabilities.  We
@@ -1072,11 +1062,6 @@ static void intel_sanitize_options(struct drm_i915_private *dev_priv)
 					    i915_modparams.enable_ppgtt);
 	DRM_DEBUG_DRIVER("ppgtt mode: %i\n", i915_modparams.enable_ppgtt);
 
-	i915_modparams.semaphores =
-		intel_sanitize_semaphores(dev_priv, i915_modparams.semaphores);
-	DRM_DEBUG_DRIVER("use GPU semaphores? %s\n",
-			 yesno(i915_modparams.semaphores));
-
 	intel_uc_sanitize_options(dev_priv);
 
 	intel_gvt_sanitize_options(dev_priv);
@@ -1101,6 +1086,8 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 
 	intel_sanitize_options(dev_priv);
 
+	i915_perf_init(dev_priv);
+
 	ret = i915_ggtt_probe_hw(dev_priv);
 	if (ret)
 		return ret;
@@ -1206,6 +1193,8 @@ static void i915_driver_cleanup_hw(struct drm_i915_private *dev_priv)
 {
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 
+	i915_perf_fini(dev_priv);
+
 	if (pdev->msi_enabled)
 		pci_disable_msi(pdev);
 
@@ -1224,7 +1213,8 @@ static void i915_driver_register(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = &dev_priv->drm;
 
-	i915_gem_shrinker_init(dev_priv);
+	i915_gem_shrinker_register(dev_priv);
+	i915_pmu_register(dev_priv);
 
 	/*
 	 * Notify a valid surface after modesetting,
@@ -1263,6 +1253,13 @@ static void i915_driver_register(struct drm_i915_private *dev_priv)
 	 * cannot run before the connectors are registered.
 	 */
 	intel_fbdev_initial_config_async(dev);
+
+	/*
+	 * We need to coordinate the hotplugs with the asynchronous fbdev
+	 * configuration, for which we use the fbdev->async_cookie.
+	 */
+	if (INTEL_INFO(dev_priv)->num_pipes)
+		drm_kms_helper_poll_init(dev);
 }
 
 /**
@@ -1274,17 +1271,25 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv)
 	intel_fbdev_unregister(dev_priv);
 	intel_audio_deinit(dev_priv);
 
+	/*
+	 * After flushing the fbdev (incl. a late async config which will
+	 * have delayed queuing of a hotplug event), then flush the hotplug
+	 * events.
+	 */
+	drm_kms_helper_poll_fini(&dev_priv->drm);
+
 	intel_gpu_ips_teardown();
 	acpi_video_unregister();
 	intel_opregion_unregister(dev_priv);
 
 	i915_perf_unregister(dev_priv);
+	i915_pmu_unregister(dev_priv);
 
 	i915_teardown_sysfs(dev_priv);
 	i915_guc_log_unregister(dev_priv);
 	drm_dev_unregister(&dev_priv->drm);
 
-	i915_gem_shrinker_cleanup(dev_priv);
+	i915_gem_shrinker_unregister(dev_priv);
 }
 
 /**
@@ -1872,7 +1877,9 @@ void i915_reset(struct drm_i915_private *i915, unsigned int flags)
 {
 	struct i915_gpu_error *error = &i915->gpu_error;
 	int ret;
+	int i;
 
+	might_sleep();
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &error->flags));
 
@@ -1895,12 +1902,20 @@ void i915_reset(struct drm_i915_private *i915, unsigned int flags)
 		goto error;
 	}
 
-	ret = intel_gpu_reset(i915, ALL_ENGINES);
+	if (!intel_has_gpu_reset(i915)) {
+		DRM_DEBUG_DRIVER("GPU reset disabled\n");
+		goto error;
+	}
+
+	for (i = 0; i < 3; i++) {
+		ret = intel_gpu_reset(i915, ALL_ENGINES);
+		if (ret == 0)
+			break;
+
+		msleep(100);
+	}
 	if (ret) {
-		if (ret != -ENODEV)
-			DRM_ERROR("Failed to reset chip: %i\n", ret);
-		else
-			DRM_DEBUG_DRIVER("GPU reset disabled\n");
+		dev_err(i915->drm.dev, "Failed to reset chip\n");
 		goto error;
 	}
 
@@ -2512,7 +2527,7 @@ static int intel_runtime_suspend(struct device *kdev)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
-	if (WARN_ON_ONCE(!(dev_priv->gt_pm.rc6.enabled && intel_rc6_enabled())))
+	if (WARN_ON_ONCE(!(dev_priv->gt_pm.rc6.enabled && HAS_RC6(dev_priv))))
 		return -ENODEV;
 
 	if (WARN_ON_ONCE(!HAS_RUNTIME_PM(dev_priv)))

drivers/gpu/drm/i915/i915_drv.h

@@ -40,6 +40,7 @@
 #include <linux/hash.h>
 #include <linux/intel-iommu.h>
 #include <linux/kref.h>
+#include <linux/perf_event.h>
 #include <linux/pm_qos.h>
 #include <linux/reservation.h>
 #include <linux/shmem_fs.h>
@@ -79,8 +80,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20171117"
-#define DRIVER_TIMESTAMP	1510958822
+#define DRIVER_DATE		"20171201"
+#define DRIVER_TIMESTAMP	1512176839
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
@@ -304,9 +305,9 @@ static inline bool transcoder_is_dsi(enum transcoder transcoder)
 
 /*
  * Global legacy plane identifier. Valid only for primary/sprite
- * planes on pre-g4x, and only for primary planes on g4x+.
+ * planes on pre-g4x, and only for primary planes on g4x-bdw.
  */
-enum plane {
+enum i9xx_plane_id {
 	PLANE_A,
 	PLANE_B,
 	PLANE_C,
@@ -560,13 +561,13 @@ struct i915_hotplug {
 	for_each_power_well_rev(__dev_priv, __power_well)		        \
 		for_each_if ((__power_well)->domains & (__domain_mask))
 
-#define for_each_intel_plane_in_state(__state, plane, plane_state, __i) \
+#define for_each_new_intel_plane_in_state(__state, plane, new_plane_state, __i) \
 	for ((__i) = 0; \
 	     (__i) < (__state)->base.dev->mode_config.num_total_plane && \
 		     ((plane) = to_intel_plane((__state)->base.planes[__i].ptr), \
-		      (plane_state) = to_intel_plane_state((__state)->base.planes[__i].state), 1); \
+		      (new_plane_state) = to_intel_plane_state((__state)->base.planes[__i].new_state), 1); \
 	     (__i)++) \
-		for_each_if (plane_state)
+		for_each_if (plane)
 
 #define for_each_new_intel_crtc_in_state(__state, crtc, new_crtc_state, __i) \
 	for ((__i) = 0; \
@@ -576,7 +577,6 @@ struct i915_hotplug {
 	     (__i)++) \
 		for_each_if (crtc)
 
-
 #define for_each_oldnew_intel_plane_in_state(__state, plane, old_plane_state, new_plane_state, __i) \
 	for ((__i) = 0; \
 	     (__i) < (__state)->base.dev->mode_config.num_total_plane && \
@@ -698,7 +698,8 @@ struct drm_i915_display_funcs {
 			  struct intel_cdclk_state *cdclk_state);
 	void (*set_cdclk)(struct drm_i915_private *dev_priv,
 			  const struct intel_cdclk_state *cdclk_state);
-	int (*get_fifo_size)(struct drm_i915_private *dev_priv, int plane);
+	int (*get_fifo_size)(struct drm_i915_private *dev_priv,
+			     enum i9xx_plane_id i9xx_plane);
 	int (*compute_pipe_wm)(struct intel_crtc_state *cstate);
 	int (*compute_intermediate_wm)(struct drm_device *dev,
 				       struct intel_crtc *intel_crtc,
@@ -942,7 +943,6 @@ struct i915_gpu_state {
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct intel_overlay_error_state *overlay;
 	struct intel_display_error_state *display;
-	struct drm_i915_error_object *semaphore;
 
 	struct drm_i915_error_engine {
 		int engine_id;
@@ -1009,6 +1009,7 @@ struct i915_gpu_state {
 		long user_bo_count;
 
 		struct drm_i915_error_object *wa_ctx;
+		struct drm_i915_error_object *default_state;
 
 		struct drm_i915_error_request {
 			long jiffies;
@@ -1145,7 +1146,7 @@ struct intel_fbc {
 
 		struct {
 			enum pipe pipe;
-			enum plane plane;
+			enum i9xx_plane_id i9xx_plane;
 			unsigned int fence_y_offset;
 		} crtc;
 
@@ -2291,7 +2292,8 @@ struct drm_i915_private {
 	struct i915_gem_context *kernel_context;
 	/* Context only to be used for injecting preemption commands */
 	struct i915_gem_context *preempt_context;
-	struct i915_vma *semaphore;
+	struct intel_engine_cs *engine_class[MAX_ENGINE_CLASS + 1]
+					    [MAX_ENGINE_INSTANCE + 1];
 
 	struct drm_dma_handle *status_page_dmah;
 	struct resource mch_res;
@@ -2619,7 +2621,6 @@ struct drm_i915_private {
 
 			bool periodic;
 			int period_exponent;
-			int timestamp_frequency;
 
 			struct i915_oa_config test_config;
 
@@ -2764,6 +2765,8 @@ struct drm_i915_private {
 		int	irq;
 	} lpe_audio;
 
+	struct i915_pmu pmu;
+
 	/*
 	 * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch
 	 * will be rejected. Instead look for a better place.
@@ -3142,6 +3145,8 @@ intel_info(const struct drm_i915_private *dev_priv)
 #define HAS_BLT(dev_priv)	HAS_ENGINE(dev_priv, BCS)
 #define HAS_VEBOX(dev_priv)	HAS_ENGINE(dev_priv, VECS)
 
+#define HAS_LEGACY_SEMAPHORES(dev_priv) IS_GEN7(dev_priv)
+
 #define HAS_LLC(dev_priv)	((dev_priv)->info.has_llc)
 #define HAS_SNOOP(dev_priv)	((dev_priv)->info.has_snoop)
 #define HAS_EDRAM(dev_priv)	(!!((dev_priv)->edram_cap & EDRAM_ENABLED))
@@ -3154,6 +3159,9 @@ intel_info(const struct drm_i915_private *dev_priv)
 		((dev_priv)->info.has_logical_ring_contexts)
 #define HAS_LOGICAL_RING_PREEMPTION(dev_priv) \
 		((dev_priv)->info.has_logical_ring_preemption)
+
+#define HAS_EXECLISTS(dev_priv) HAS_LOGICAL_RING_CONTEXTS(dev_priv)
+
 #define USES_PPGTT(dev_priv)		(i915_modparams.enable_ppgtt)
 #define USES_FULL_PPGTT(dev_priv)	(i915_modparams.enable_ppgtt >= 2)
 #define USES_FULL_48BIT_PPGTT(dev_priv)	(i915_modparams.enable_ppgtt == 3)
@@ -3205,8 +3213,10 @@ intel_info(const struct drm_i915_private *dev_priv)
 #define HAS_DDI(dev_priv)		 ((dev_priv)->info.has_ddi)
 #define HAS_FPGA_DBG_UNCLAIMED(dev_priv) ((dev_priv)->info.has_fpga_dbg)
 #define HAS_PSR(dev_priv)		 ((dev_priv)->info.has_psr)
+
 #define HAS_RC6(dev_priv)		 ((dev_priv)->info.has_rc6)
 #define HAS_RC6p(dev_priv)		 ((dev_priv)->info.has_rc6p)
+#define HAS_RC6pp(dev_priv)		 (false) /* HW was never validated */
 
 #define HAS_CSR(dev_priv)	((dev_priv)->info.has_csr)
 
@@ -3302,8 +3312,6 @@ intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *dev_priv)
 int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 				int enable_ppgtt);
 
-bool intel_sanitize_semaphores(struct drm_i915_private *dev_priv, int value);
-
 /* i915_drv.c */
 void __printf(3, 4)
 __i915_printk(struct drm_i915_private *dev_priv, const char *level,
@@ -3905,7 +3913,7 @@ i915_gem_object_create_internal(struct drm_i915_private *dev_priv,
 				phys_addr_t size);
 
 /* i915_gem_shrinker.c */
-unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
+unsigned long i915_gem_shrink(struct drm_i915_private *i915,
 			      unsigned long target,
 			      unsigned long *nr_scanned,
 			      unsigned flags);
@@ -3914,9 +3922,9 @@ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
 #define I915_SHRINK_BOUND 0x4
 #define I915_SHRINK_ACTIVE 0x8
 #define I915_SHRINK_VMAPS 0x10
-unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
-void i915_gem_shrinker_init(struct drm_i915_private *dev_priv);
-void i915_gem_shrinker_cleanup(struct drm_i915_private *dev_priv);
+unsigned long i915_gem_shrink_all(struct drm_i915_private *i915);
+void i915_gem_shrinker_register(struct drm_i915_private *i915);
+void i915_gem_shrinker_unregister(struct drm_i915_private *i915);
 
 
 /* i915_gem_tiling.c */
@@ -4223,9 +4231,17 @@ void vlv_phy_reset_lanes(struct intel_encoder *encoder,
 
 int intel_gpu_freq(struct drm_i915_private *dev_priv, int val);
 int intel_freq_opcode(struct drm_i915_private *dev_priv, int val);
-u64 intel_rc6_residency_us(struct drm_i915_private *dev_priv,
+u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
 			   const i915_reg_t reg);
 
+u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat1);
+
+static inline u64 intel_rc6_residency_us(struct drm_i915_private *dev_priv,
+					 const i915_reg_t reg)
+{
+	return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(dev_priv, reg), 1000);
+}
+
 #define I915_READ8(reg)		dev_priv->uncore.funcs.mmio_readb(dev_priv, (reg), true)
 #define I915_WRITE8(reg, val)	dev_priv->uncore.funcs.mmio_writeb(dev_priv, (reg), (val), true)
 

drivers/gpu/drm/i915/i915_gem.c

@@ -3371,7 +3371,9 @@ i915_gem_idle_work_handler(struct work_struct *work)
 	synchronize_irq(dev_priv->drm.irq);
 
 	intel_engines_park(dev_priv);
-	i915_gem_timelines_mark_idle(dev_priv);
+	i915_gem_timelines_park(dev_priv);
+
+	i915_pmu_gt_parked(dev_priv);
 
 	GEM_BUG_ON(!dev_priv->gt.awake);
 	dev_priv->gt.awake = false;
@@ -4772,17 +4774,19 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 	 * state. Fortunately, the kernel_context is disposable and we do
 	 * not rely on its state.
 	 */
-	ret = i915_gem_switch_to_kernel_context(dev_priv);
-	if (ret)
-		goto err_unlock;
+	if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
+		ret = i915_gem_switch_to_kernel_context(dev_priv);
+		if (ret)
+			goto err_unlock;
 
-	ret = i915_gem_wait_for_idle(dev_priv,
-				     I915_WAIT_INTERRUPTIBLE |
-				     I915_WAIT_LOCKED);
-	if (ret && ret != -EIO)
-		goto err_unlock;
+		ret = i915_gem_wait_for_idle(dev_priv,
+					     I915_WAIT_INTERRUPTIBLE |
+					     I915_WAIT_LOCKED);
+		if (ret && ret != -EIO)
+			goto err_unlock;
 
-	assert_kernel_context_is_current(dev_priv);
+		assert_kernel_context_is_current(dev_priv);
+	}
 	i915_gem_contexts_lost(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
@@ -4997,25 +5001,6 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
-bool intel_sanitize_semaphores(struct drm_i915_private *dev_priv, int value)
-{
-	if (INTEL_INFO(dev_priv)->gen < 6)
-		return false;
-
-	/* TODO: make semaphores and Execlists play nicely together */
-	if (i915_modparams.enable_execlists)
-		return false;
-
-	if (value >= 0)
-		return value;
-
-	/* Enable semaphores on SNB when IO remapping is off */
-	if (IS_GEN6(dev_priv) && intel_vtd_active())
-		return false;
-
-	return true;
-}
-
 static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 {
 	struct i915_gem_context *ctx;
@@ -5045,7 +5030,7 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 			goto out_ctx;
 		}
 
-		err = i915_switch_context(rq);
+		err = 0;
 		if (engine->init_context)
 			err = engine->init_context(rq);
 
@@ -5134,8 +5119,6 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 {
 	int ret;
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
-
 	/*
 	 * We need to fallback to 4K pages since gvt gtt handling doesn't
 	 * support huge page entries - we will need to check either hypervisor
@@ -5147,26 +5130,27 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 
 	dev_priv->mm.unordered_timeline = dma_fence_context_alloc(1);
 
-	if (!i915_modparams.enable_execlists) {
-		dev_priv->gt.resume = intel_legacy_submission_resume;
-		dev_priv->gt.cleanup_engine = intel_engine_cleanup;
-	} else {
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 		dev_priv->gt.resume = intel_lr_context_resume;
 		dev_priv->gt.cleanup_engine = intel_logical_ring_cleanup;
+	} else {
+		dev_priv->gt.resume = intel_legacy_submission_resume;
+		dev_priv->gt.cleanup_engine = intel_engine_cleanup;
 	}
 
+	ret = i915_gem_init_userptr(dev_priv);
+	if (ret)
+		return ret;
+
 	/* This is just a security blanket to placate dragons.
 	 * On some systems, we very sporadically observe that the first TLBs
 	 * used by the CS may be stale, despite us poking the TLB reset. If
 	 * we hold the forcewake during initialisation these problems
 	 * just magically go away.
 	 */
+	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
-	ret = i915_gem_init_userptr(dev_priv);
-	if (ret)
-		goto out_unlock;
-
 	ret = i915_gem_init_ggtt(dev_priv);
 	if (ret)
 		goto out_unlock;

drivers/gpu/drm/i915/i915_gem_context.c

@@ -460,14 +460,6 @@ int i915_gem_contexts_init(struct drm_i915_private *dev_priv)
 	INIT_WORK(&dev_priv->contexts.free_work, contexts_free_worker);
 	init_llist_head(&dev_priv->contexts.free_list);
 
-	if (intel_vgpu_active(dev_priv) &&
-	    HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
-		if (!i915_modparams.enable_execlists) {
-			DRM_INFO("Only EXECLIST mode is supported in vgpu.\n");
-			return -EINVAL;
-		}
-	}
-
 	/* Using the simple ida interface, the max is limited by sizeof(int) */
 	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > INT_MAX);
 	ida_init(&dev_priv->contexts.hw_ida);
@@ -515,6 +507,7 @@ void i915_gem_contexts_lost(struct drm_i915_private *dev_priv)
 
 	for_each_engine(engine, dev_priv, id) {
 		engine->legacy_active_context = NULL;
+		engine->legacy_active_ppgtt = NULL;
 
 		if (!engine->last_retired_context)
 			continue;
@@ -574,300 +567,6 @@ void i915_gem_context_close(struct drm_file *file)
 	idr_destroy(&file_priv->context_idr);
 }
 
-static inline int
-mi_set_context(struct drm_i915_gem_request *req, u32 flags)
-{
-	struct drm_i915_private *dev_priv = req->i915;
-	struct intel_engine_cs *engine = req->engine;
-	enum intel_engine_id id;
-	const int num_rings =
-		/* Use an extended w/a on gen7 if signalling from other rings */
-		(i915_modparams.semaphores && INTEL_GEN(dev_priv) == 7) ?
-		INTEL_INFO(dev_priv)->num_rings - 1 :
-		0;
-	int len;
-	u32 *cs;
-
-	flags |= MI_MM_SPACE_GTT;
-	if (IS_HASWELL(dev_priv) || INTEL_GEN(dev_priv) >= 8)
-		/* These flags are for resource streamer on HSW+ */
-		flags |= HSW_MI_RS_SAVE_STATE_EN | HSW_MI_RS_RESTORE_STATE_EN;
-	else
-		flags |= MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN;
-
-	len = 4;
-	if (INTEL_GEN(dev_priv) >= 7)
-		len += 2 + (num_rings ? 4*num_rings + 6 : 0);
-
-	cs = intel_ring_begin(req, len);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	/* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw,bdw,chv */
-	if (INTEL_GEN(dev_priv) >= 7) {
-		*cs++ = MI_ARB_ON_OFF | MI_ARB_DISABLE;
-		if (num_rings) {
-			struct intel_engine_cs *signaller;
-
-			*cs++ = MI_LOAD_REGISTER_IMM(num_rings);
-			for_each_engine(signaller, dev_priv, id) {
-				if (signaller == engine)
-					continue;
-
-				*cs++ = i915_mmio_reg_offset(
-					   RING_PSMI_CTL(signaller->mmio_base));
-				*cs++ = _MASKED_BIT_ENABLE(
-						GEN6_PSMI_SLEEP_MSG_DISABLE);
-			}
-		}
-	}
-
-	*cs++ = MI_NOOP;
-	*cs++ = MI_SET_CONTEXT;
-	*cs++ = i915_ggtt_offset(req->ctx->engine[RCS].state) | flags;
-	/*
-	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
-	 * WaMiSetContext_Hang:snb,ivb,vlv
-	 */
-	*cs++ = MI_NOOP;
-
-	if (INTEL_GEN(dev_priv) >= 7) {
-		if (num_rings) {
-			struct intel_engine_cs *signaller;
-			i915_reg_t last_reg = {}; /* keep gcc quiet */
-
-			*cs++ = MI_LOAD_REGISTER_IMM(num_rings);
-			for_each_engine(signaller, dev_priv, id) {
-				if (signaller == engine)
-					continue;
-
-				last_reg = RING_PSMI_CTL(signaller->mmio_base);
-				*cs++ = i915_mmio_reg_offset(last_reg);
-				*cs++ = _MASKED_BIT_DISABLE(
-						GEN6_PSMI_SLEEP_MSG_DISABLE);
-			}
-
-			/* Insert a delay before the next switch! */
-			*cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
-			*cs++ = i915_mmio_reg_offset(last_reg);
-			*cs++ = i915_ggtt_offset(engine->scratch);
-			*cs++ = MI_NOOP;
-		}
-		*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
-	}
-
-	intel_ring_advance(req, cs);
-
-	return 0;
-}
-
-static int remap_l3(struct drm_i915_gem_request *req, int slice)
-{
-	u32 *cs, *remap_info = req->i915->l3_parity.remap_info[slice];
-	int i;
-
-	if (!remap_info)
-		return 0;
-
-	cs = intel_ring_begin(req, GEN7_L3LOG_SIZE/4 * 2 + 2);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	/*
-	 * Note: We do not worry about the concurrent register cacheline hang
-	 * here because no other code should access these registers other than
-	 * at initialization time.
-	 */
-	*cs++ = MI_LOAD_REGISTER_IMM(GEN7_L3LOG_SIZE/4);
-	for (i = 0; i < GEN7_L3LOG_SIZE/4; i++) {
-		*cs++ = i915_mmio_reg_offset(GEN7_L3LOG(slice, i));
-		*cs++ = remap_info[i];
-	}
-	*cs++ = MI_NOOP;
-	intel_ring_advance(req, cs);
-
-	return 0;
-}
-
-static inline bool skip_rcs_switch(struct i915_hw_ppgtt *ppgtt,
-				   struct intel_engine_cs *engine,
-				   struct i915_gem_context *to)
-{
-	if (to->remap_slice)
-		return false;
-
-	if (ppgtt && (intel_engine_flag(engine) & ppgtt->pd_dirty_rings))
-		return false;
-
-	return to == engine->legacy_active_context;
-}
-
-static bool
-needs_pd_load_pre(struct i915_hw_ppgtt *ppgtt, struct intel_engine_cs *engine)
-{
-	struct i915_gem_context *from = engine->legacy_active_context;
-
-	if (!ppgtt)
-		return false;
-
-	/* Always load the ppgtt on first use */
-	if (!from)
-		return true;
-
-	/* Same context without new entries, skip */
-	if ((!from->ppgtt || from->ppgtt == ppgtt) &&
-	    !(intel_engine_flag(engine) & ppgtt->pd_dirty_rings))
-		return false;
-
-	if (engine->id != RCS)
-		return true;
-
-	if (INTEL_GEN(engine->i915) < 8)
-		return true;
-
-	return false;
-}
-
-static bool
-needs_pd_load_post(struct i915_hw_ppgtt *ppgtt,
-		   struct i915_gem_context *to,
-		   u32 hw_flags)
-{
-	if (!ppgtt)
-		return false;
-
-	if (!IS_GEN8(to->i915))
-		return false;
-
-	if (hw_flags & MI_RESTORE_INHIBIT)
-		return true;
-
-	return false;
-}
-
-static int do_rcs_switch(struct drm_i915_gem_request *req)
-{
-	struct i915_gem_context *to = req->ctx;
-	struct intel_engine_cs *engine = req->engine;
-	struct i915_hw_ppgtt *ppgtt = to->ppgtt ?: req->i915->mm.aliasing_ppgtt;
-	struct i915_gem_context *from = engine->legacy_active_context;
-	u32 hw_flags;
-	int ret, i;
-
-	GEM_BUG_ON(engine->id != RCS);
-
-	if (skip_rcs_switch(ppgtt, engine, to))
-		return 0;
-
-	if (needs_pd_load_pre(ppgtt, engine)) {
-		/* Older GENs and non render rings still want the load first,
-		 * "PP_DCLV followed by PP_DIR_BASE register through Load
-		 * Register Immediate commands in Ring Buffer before submitting
-		 * a context."*/
-		trace_switch_mm(engine, to);
-		ret = ppgtt->switch_mm(ppgtt, req);
-		if (ret)
-			return ret;
-	}
-
-	if (i915_gem_context_is_kernel(to))
-		/*
-		 * The kernel context(s) is treated as pure scratch and is not
-		 * expected to retain any state (as we sacrifice it during
-		 * suspend and on resume it may be corrupted). This is ok,
-		 * as nothing actually executes using the kernel context; it
-		 * is purely used for flushing user contexts.
-		 */
-		hw_flags = MI_RESTORE_INHIBIT;
-	else if (ppgtt && intel_engine_flag(engine) & ppgtt->pd_dirty_rings)
-		hw_flags = MI_FORCE_RESTORE;
-	else
-		hw_flags = 0;
-
-	if (to != from || (hw_flags & MI_FORCE_RESTORE)) {
-		ret = mi_set_context(req, hw_flags);
-		if (ret)
-			return ret;
-
-		engine->legacy_active_context = to;
-	}
-
-	/* GEN8 does *not* require an explicit reload if the PDPs have been
-	 * setup, and we do not wish to move them.
-	 */
-	if (needs_pd_load_post(ppgtt, to, hw_flags)) {
-		trace_switch_mm(engine, to);
-		ret = ppgtt->switch_mm(ppgtt, req);
-		/* The hardware context switch is emitted, but we haven't
-		 * actually changed the state - so it's probably safe to bail
-		 * here. Still, let the user know something dangerous has
-		 * happened.
-		 */
-		if (ret)
-			return ret;
-	}
-
-	if (ppgtt)
-		ppgtt->pd_dirty_rings &= ~intel_engine_flag(engine);
-
-	for (i = 0; i < MAX_L3_SLICES; i++) {
-		if (!(to->remap_slice & (1<<i)))
-			continue;
-
-		ret = remap_l3(req, i);
-		if (ret)
-			return ret;
-
-		to->remap_slice &= ~(1<<i);
-	}
-
-	return 0;
-}
-
-/**
- * i915_switch_context() - perform a GPU context switch.
- * @req: request for which we'll execute the context switch
- *
- * The context life cycle is simple. The context refcount is incremented and
- * decremented by 1 and create and destroy. If the context is in use by the GPU,
- * it will have a refcount > 1. This allows us to destroy the context abstract
- * object while letting the normal object tracking destroy the backing BO.
- *
- * This function should not be used in execlists mode.  Instead the context is
- * switched by writing to the ELSP and requests keep a reference to their
- * context.
- */
-int i915_switch_context(struct drm_i915_gem_request *req)
-{
-	struct intel_engine_cs *engine = req->engine;
-
-	lockdep_assert_held(&req->i915->drm.struct_mutex);
-	if (i915_modparams.enable_execlists)
-		return 0;
-
-	if (!req->ctx->engine[engine->id].state) {
-		struct i915_gem_context *to = req->ctx;
-		struct i915_hw_ppgtt *ppgtt =
-			to->ppgtt ?: req->i915->mm.aliasing_ppgtt;
-
-		if (needs_pd_load_pre(ppgtt, engine)) {
-			int ret;
-
-			trace_switch_mm(engine, to);
-			ret = ppgtt->switch_mm(ppgtt, req);
-			if (ret)
-				return ret;
-
-			ppgtt->pd_dirty_rings &= ~intel_engine_flag(engine);
-		}
-
-		engine->legacy_active_context = to;
-		return 0;
-	}
-
-	return do_rcs_switch(req);
-}
-
 static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine)
 {
 	struct i915_gem_timeline *timeline;
@@ -899,7 +598,6 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv)
 
 	for_each_engine(engine, dev_priv, id) {
 		struct drm_i915_gem_request *req;
-		int ret;
 
 		if (engine_has_idle_kernel_context(engine))
 			continue;
@@ -922,10 +620,14 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv)
 								 GFP_KERNEL);
 		}
 
-		ret = i915_switch_context(req);
-		i915_add_request(req);
-		if (ret)
-			return ret;
+		/*
+		 * Force a flush after the switch to ensure that all rendering
+		 * and operations prior to switching to the kernel context hits
+		 * memory. This should be guaranteed by the previous request,
+		 * but an extra layer of paranoia before we declare the system
+		 * idle (on suspend etc) is advisable!
+		 */
+		__i915_add_request(req, true);
 	}
 
 	return 0;

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -271,7 +271,7 @@ static inline u64 gen8_noncanonical_addr(u64 address)
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
 {
-	return eb->engine->needs_cmd_parser && eb->batch_len;
+	return intel_engine_needs_cmd_parser(eb->engine) && eb->batch_len;
 }
 
 static int eb_create(struct i915_execbuffer *eb)
@@ -1111,14 +1111,6 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	if (err)
 		goto err_request;
 
-	err = eb->engine->emit_flush(rq, EMIT_INVALIDATE);
-	if (err)
-		goto err_request;
-
-	err = i915_switch_context(rq);
-	if (err)
-		goto err_request;
-
 	err = eb->engine->emit_bb_start(rq,
 					batch->node.start, PAGE_SIZE,
 					cache->gen > 5 ? 0 : I915_DISPATCH_SECURE);
@@ -1818,8 +1810,7 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 	/* Unconditionally flush any chipset caches (for streaming writes). */
 	i915_gem_chipset_flush(eb->i915);
 
-	/* Unconditionally invalidate GPU caches and TLBs. */
-	return eb->engine->emit_flush(eb->request, EMIT_INVALIDATE);
+	return 0;
 }
 
 static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
@@ -1965,10 +1956,6 @@ static int eb_submit(struct i915_execbuffer *eb)
 	if (err)
 		return err;
 
-	err = i915_switch_context(eb->request);
-	if (err)
-		return err;
-
 	if (eb->args->flags & I915_EXEC_GEN7_SOL_RESET) {
 		err = i915_reset_gen7_sol_offsets(eb->request);
 		if (err)

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -178,7 +178,7 @@ int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 		return 0;
 	}
 
-	if (INTEL_GEN(dev_priv) >= 8 && i915_modparams.enable_execlists) {
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 		if (has_full_48bit_ppgtt)
 			return 3;
 
@@ -2162,7 +2162,7 @@ int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv)
 	/* In the case of execlists, PPGTT is enabled by the context descriptor
 	 * and the PDPs are contained within the context itself.  We don't
 	 * need to do anything here. */
-	if (i915_modparams.enable_execlists)
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv))
 		return 0;
 
 	if (!USES_PPGTT(dev_priv))
@@ -3737,9 +3737,6 @@ intel_rotate_pages(struct intel_rotation_info *rot_info,
 				  rot_info->plane[i].stride, st, sg);
 	}
 
-	DRM_DEBUG_KMS("Created rotated page mapping for object size %zu (%ux%u tiles, %u pages)\n",
-		      obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);
-
 	kvfree(page_addr_list);
 
 	return st;
@@ -3749,8 +3746,8 @@ intel_rotate_pages(struct intel_rotation_info *rot_info,
 err_st_alloc:
 	kvfree(page_addr_list);
 
-	DRM_DEBUG_KMS("Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n",
-		      obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);
+	DRM_DEBUG_DRIVER("Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n",
+			 obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);
 
 	return ERR_PTR(ret);
 }

drivers/gpu/drm/i915/i915_gem_render_state.c

@@ -208,10 +208,6 @@ int i915_gem_render_state_emit(struct drm_i915_gem_request *rq)
 	if (err)
 		goto err_unpin;
 
-	err = engine->emit_flush(rq, EMIT_INVALIDATE);
-	if (err)
-		goto err_unpin;
-
 	err = engine->emit_bb_start(rq,
 				    so.batch_offset, so.batch_size,
 				    I915_DISPATCH_SECURE);

drivers/gpu/drm/i915/i915_gem_request.c

@@ -258,6 +258,7 @@ static void mark_busy(struct drm_i915_private *i915)
 	i915_update_gfx_val(i915);
 	if (INTEL_GEN(i915) >= 6)
 		gen6_rps_busy(i915);
+	i915_pmu_gt_unparked(i915);
 
 	intel_engines_unpark(i915);
 
@@ -624,6 +625,10 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
 	if (ret)
 		goto err_unpin;
 
+	ret = intel_ring_wait_for_space(ring, MIN_SPACE_FOR_ADD_REQUEST);
+	if (ret)
+		goto err_unreserve;
+
 	/* Move the oldest request to the slab-cache (if not in use!) */
 	req = list_first_entry_or_null(&engine->timeline->requests,
 				       typeof(*req), link);
@@ -703,22 +708,30 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
 	req->reserved_space = MIN_SPACE_FOR_ADD_REQUEST;
 	GEM_BUG_ON(req->reserved_space < engine->emit_breadcrumb_sz);
 
-	ret = engine->request_alloc(req);
-	if (ret)
-		goto err_ctx;
-
-	/* Record the position of the start of the request so that
+	/*
+	 * Record the position of the start of the request so that
 	 * should we detect the updated seqno part-way through the
 	 * GPU processing the request, we never over-estimate the
 	 * position of the head.
 	 */
 	req->head = req->ring->emit;
 
+	/* Unconditionally invalidate GPU caches and TLBs. */
+	ret = engine->emit_flush(req, EMIT_INVALIDATE);
+	if (ret)
+		goto err_unwind;
+
+	ret = engine->request_alloc(req);
+	if (ret)
+		goto err_unwind;
+
 	/* Check that we didn't interrupt ourselves with a new request */
 	GEM_BUG_ON(req->timeline->seqno != req->fence.seqno);
 	return req;
 
-err_ctx:
+err_unwind:
+	req->ring->emit = req->head;
+
 	/* Make sure we didn't add ourselves to external state before freeing */
 	GEM_BUG_ON(!list_empty(&req->active_list));
 	GEM_BUG_ON(!list_empty(&req->priotree.signalers_list));

drivers/gpu/drm/i915/i915_gem_shrinker.c

@@ -35,9 +35,9 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 
-static bool shrinker_lock(struct drm_i915_private *dev_priv, bool *unlock)
+static bool shrinker_lock(struct drm_i915_private *i915, bool *unlock)
 {
-	switch (mutex_trylock_recursive(&dev_priv->drm.struct_mutex)) {
+	switch (mutex_trylock_recursive(&i915->drm.struct_mutex)) {
 	case MUTEX_TRYLOCK_RECURSIVE:
 		*unlock = false;
 		return true;
@@ -47,7 +47,7 @@ static bool shrinker_lock(struct drm_i915_private *dev_priv, bool *unlock)
 		preempt_disable();
 		do {
 			cpu_relax();
-			if (mutex_trylock(&dev_priv->drm.struct_mutex)) {
+			if (mutex_trylock(&i915->drm.struct_mutex)) {
 				*unlock = true;
 				break;
 			}
@@ -63,12 +63,12 @@ static bool shrinker_lock(struct drm_i915_private *dev_priv, bool *unlock)
 	BUG();
 }
 
-static void shrinker_unlock(struct drm_i915_private *dev_priv, bool unlock)
+static void shrinker_unlock(struct drm_i915_private *i915, bool unlock)
 {
 	if (!unlock)
 		return;
 
-	mutex_unlock(&dev_priv->drm.struct_mutex);
+	mutex_unlock(&i915->drm.struct_mutex);
 }
 
 static bool swap_available(void)
@@ -118,7 +118,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj)
 
 /**
  * i915_gem_shrink - Shrink buffer object caches
- * @dev_priv: i915 device
+ * @i915: i915 device
  * @target: amount of memory to make available, in pages
  * @nr_scanned: optional output for number of pages scanned (incremental)
  * @flags: control flags for selecting cache types
@@ -142,7 +142,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj)
  * The number of pages of backing storage actually released.
  */
 unsigned long
-i915_gem_shrink(struct drm_i915_private *dev_priv,
+i915_gem_shrink(struct drm_i915_private *i915,
 		unsigned long target,
 		unsigned long *nr_scanned,
 		unsigned flags)
@@ -151,15 +151,15 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 		struct list_head *list;
 		unsigned int bit;
 	} phases[] = {
-		{ &dev_priv->mm.unbound_list, I915_SHRINK_UNBOUND },
-		{ &dev_priv->mm.bound_list, I915_SHRINK_BOUND },
+		{ &i915->mm.unbound_list, I915_SHRINK_UNBOUND },
+		{ &i915->mm.bound_list, I915_SHRINK_BOUND },
 		{ NULL, 0 },
 	}, *phase;
 	unsigned long count = 0;
 	unsigned long scanned = 0;
 	bool unlock;
 
-	if (!shrinker_lock(dev_priv, &unlock))
+	if (!shrinker_lock(i915, &unlock))
 		return 0;
 
 	/*
@@ -172,10 +172,10 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 	 * we will free as much as we can and hope to get a second chance.
 	 */
 	if (flags & I915_SHRINK_ACTIVE)
-		i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED);
+		i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
 
-	trace_i915_gem_shrink(dev_priv, target, flags);
-	i915_gem_retire_requests(dev_priv);
+	trace_i915_gem_shrink(i915, target, flags);
+	i915_gem_retire_requests(i915);
 
 	/*
 	 * Unbinding of objects will require HW access; Let us not wake the
@@ -183,7 +183,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 	 * we will force the wake during oom-notifier.
 	 */
 	if ((flags & I915_SHRINK_BOUND) &&
-	    !intel_runtime_pm_get_if_in_use(dev_priv))
+	    !intel_runtime_pm_get_if_in_use(i915))
 		flags &= ~I915_SHRINK_BOUND;
 
 	/*
@@ -221,7 +221,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 		 * to be able to shrink their pages, so they remain on
 		 * the unbound/bound list until actually freed.
 		 */
-		spin_lock(&dev_priv->mm.obj_lock);
+		spin_lock(&i915->mm.obj_lock);
 		while (count < target &&
 		       (obj = list_first_entry_or_null(phase->list,
 						       typeof(*obj),
@@ -244,7 +244,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 			if (!can_release_pages(obj))
 				continue;
 
-			spin_unlock(&dev_priv->mm.obj_lock);
+			spin_unlock(&i915->mm.obj_lock);
 
 			if (unsafe_drop_pages(obj)) {
 				/* May arrive from get_pages on another bo */
@@ -258,18 +258,18 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 			}
 			scanned += obj->base.size >> PAGE_SHIFT;
 
-			spin_lock(&dev_priv->mm.obj_lock);
+			spin_lock(&i915->mm.obj_lock);
 		}
 		list_splice_tail(&still_in_list, phase->list);
-		spin_unlock(&dev_priv->mm.obj_lock);
+		spin_unlock(&i915->mm.obj_lock);
 	}
 
 	if (flags & I915_SHRINK_BOUND)
-		intel_runtime_pm_put(dev_priv);
+		intel_runtime_pm_put(i915);
 
-	i915_gem_retire_requests(dev_priv);
+	i915_gem_retire_requests(i915);
 
-	shrinker_unlock(dev_priv, unlock);
+	shrinker_unlock(i915, unlock);
 
 	if (nr_scanned)
 		*nr_scanned += scanned;
@@ -278,7 +278,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 
 /**
  * i915_gem_shrink_all - Shrink buffer object caches completely
- * @dev_priv: i915 device
+ * @i915: i915 device
  *
  * This is a simple wraper around i915_gem_shrink() to aggressively shrink all
  * caches completely. It also first waits for and retires all outstanding
@@ -290,16 +290,16 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
  * Returns:
  * The number of pages of backing storage actually released.
  */
-unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
+unsigned long i915_gem_shrink_all(struct drm_i915_private *i915)
 {
 	unsigned long freed;
 
-	intel_runtime_pm_get(dev_priv);
-	freed = i915_gem_shrink(dev_priv, -1UL, NULL,
+	intel_runtime_pm_get(i915);
+	freed = i915_gem_shrink(i915, -1UL, NULL,
 				I915_SHRINK_BOUND |
 				I915_SHRINK_UNBOUND |
 				I915_SHRINK_ACTIVE);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(i915);
 
 	return freed;
 }
@@ -347,53 +347,53 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 static unsigned long
 i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 {
-	struct drm_i915_private *dev_priv =
+	struct drm_i915_private *i915 =
 		container_of(shrinker, struct drm_i915_private, mm.shrinker);
 	unsigned long freed;
 	bool unlock;
 
 	sc->nr_scanned = 0;
 
-	if (!shrinker_lock(dev_priv, &unlock))
+	if (!shrinker_lock(i915, &unlock))
 		return SHRINK_STOP;
 
-	freed = i915_gem_shrink(dev_priv,
+	freed = i915_gem_shrink(i915,
 				sc->nr_to_scan,
 				&sc->nr_scanned,
 				I915_SHRINK_BOUND |
 				I915_SHRINK_UNBOUND |
 				I915_SHRINK_PURGEABLE);
 	if (freed < sc->nr_to_scan)
-		freed += i915_gem_shrink(dev_priv,
+		freed += i915_gem_shrink(i915,
 					 sc->nr_to_scan - sc->nr_scanned,
 					 &sc->nr_scanned,
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
 	if (freed < sc->nr_to_scan && current_is_kswapd()) {
-		intel_runtime_pm_get(dev_priv);
-		freed += i915_gem_shrink(dev_priv,
+		intel_runtime_pm_get(i915);
+		freed += i915_gem_shrink(i915,
 					 sc->nr_to_scan - sc->nr_scanned,
 					 &sc->nr_scanned,
 					 I915_SHRINK_ACTIVE |
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
-		intel_runtime_pm_put(dev_priv);
+		intel_runtime_pm_put(i915);
 	}
 
-	shrinker_unlock(dev_priv, unlock);
+	shrinker_unlock(i915, unlock);
 
 	return sc->nr_scanned ? freed : SHRINK_STOP;
 }
 
 static bool
-shrinker_lock_uninterruptible(struct drm_i915_private *dev_priv, bool *unlock,
+shrinker_lock_uninterruptible(struct drm_i915_private *i915, bool *unlock,
 			      int timeout_ms)
 {
 	unsigned long timeout = jiffies + msecs_to_jiffies_timeout(timeout_ms);
 
 	do {
-		if (i915_gem_wait_for_idle(dev_priv, 0) == 0 &&
-		    shrinker_lock(dev_priv, unlock))
+		if (i915_gem_wait_for_idle(i915, 0) == 0 &&
+		    shrinker_lock(i915, unlock))
 			break;
 
 		schedule_timeout_killable(1);
@@ -412,32 +412,32 @@ shrinker_lock_uninterruptible(struct drm_i915_private *dev_priv, bool *unlock,
 static int
 i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
 {
-	struct drm_i915_private *dev_priv =
+	struct drm_i915_private *i915 =
 		container_of(nb, struct drm_i915_private, mm.oom_notifier);
 	struct drm_i915_gem_object *obj;
 	unsigned long unevictable, bound, unbound, freed_pages;
 
-	freed_pages = i915_gem_shrink_all(dev_priv);
+	freed_pages = i915_gem_shrink_all(i915);
 
 	/* Because we may be allocating inside our own driver, we cannot
 	 * assert that there are no objects with pinned pages that are not
 	 * being pointed to by hardware.
 	 */
 	unbound = bound = unevictable = 0;
-	spin_lock(&dev_priv->mm.obj_lock);
-	list_for_each_entry(obj, &dev_priv->mm.unbound_list, mm.link) {
+	spin_lock(&i915->mm.obj_lock);
+	list_for_each_entry(obj, &i915->mm.unbound_list, mm.link) {
 		if (!can_release_pages(obj))
 			unevictable += obj->base.size >> PAGE_SHIFT;
 		else
 			unbound += obj->base.size >> PAGE_SHIFT;
 	}
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, mm.link) {
+	list_for_each_entry(obj, &i915->mm.bound_list, mm.link) {
 		if (!can_release_pages(obj))
 			unevictable += obj->base.size >> PAGE_SHIFT;
 		else
 			bound += obj->base.size >> PAGE_SHIFT;
 	}
-	spin_unlock(&dev_priv->mm.obj_lock);
+	spin_unlock(&i915->mm.obj_lock);
 
 	if (freed_pages || unbound || bound)
 		pr_info("Purging GPU memory, %lu pages freed, "
@@ -455,74 +455,74 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
 static int
 i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr)
 {
-	struct drm_i915_private *dev_priv =
+	struct drm_i915_private *i915 =
 		container_of(nb, struct drm_i915_private, mm.vmap_notifier);
 	struct i915_vma *vma, *next;
 	unsigned long freed_pages = 0;
 	bool unlock;
 	int ret;
 
-	if (!shrinker_lock_uninterruptible(dev_priv, &unlock, 5000))
+	if (!shrinker_lock_uninterruptible(i915, &unlock, 5000))
 		return NOTIFY_DONE;
 
 	/* Force everything onto the inactive lists */
-	ret = i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED);
+	ret = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
 	if (ret)
 		goto out;
 
-	intel_runtime_pm_get(dev_priv);
-	freed_pages += i915_gem_shrink(dev_priv, -1UL, NULL,
+	intel_runtime_pm_get(i915);
+	freed_pages += i915_gem_shrink(i915, -1UL, NULL,
 				       I915_SHRINK_BOUND |
 				       I915_SHRINK_UNBOUND |
 				       I915_SHRINK_ACTIVE |
 				       I915_SHRINK_VMAPS);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(i915);
 
 	/* We also want to clear any cached iomaps as they wrap vmap */
 	list_for_each_entry_safe(vma, next,
-				 &dev_priv->ggtt.base.inactive_list, vm_link) {
+				 &i915->ggtt.base.inactive_list, vm_link) {
 		unsigned long count = vma->node.size >> PAGE_SHIFT;
 		if (vma->iomap && i915_vma_unbind(vma) == 0)
 			freed_pages += count;
 	}
 
 out:
-	shrinker_unlock(dev_priv, unlock);
+	shrinker_unlock(i915, unlock);
 
 	*(unsigned long *)ptr += freed_pages;
 	return NOTIFY_DONE;
 }
 
 /**
- * i915_gem_shrinker_init - Initialize i915 shrinker
- * @dev_priv: i915 device
+ * i915_gem_shrinker_register - Register the i915 shrinker
+ * @i915: i915 device
  *
  * This function registers and sets up the i915 shrinker and OOM handler.
  */
-void i915_gem_shrinker_init(struct drm_i915_private *dev_priv)
+void i915_gem_shrinker_register(struct drm_i915_private *i915)
 {
-	dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan;
-	dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count;
-	dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS;
-	dev_priv->mm.shrinker.batch = 4096;
-	WARN_ON(register_shrinker(&dev_priv->mm.shrinker));
+	i915->mm.shrinker.scan_objects = i915_gem_shrinker_scan;
+	i915->mm.shrinker.count_objects = i915_gem_shrinker_count;
+	i915->mm.shrinker.seeks = DEFAULT_SEEKS;
+	i915->mm.shrinker.batch = 4096;
+	WARN_ON(register_shrinker(&i915->mm.shrinker));
 
-	dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
-	WARN_ON(register_oom_notifier(&dev_priv->mm.oom_notifier));
+	i915->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
+	WARN_ON(register_oom_notifier(&i915->mm.oom_notifier));
 
-	dev_priv->mm.vmap_notifier.notifier_call = i915_gem_shrinker_vmap;
-	WARN_ON(register_vmap_purge_notifier(&dev_priv->mm.vmap_notifier));
+	i915->mm.vmap_notifier.notifier_call = i915_gem_shrinker_vmap;
+	WARN_ON(register_vmap_purge_notifier(&i915->mm.vmap_notifier));
 }
 
 /**
- * i915_gem_shrinker_cleanup - Clean up i915 shrinker
- * @dev_priv: i915 device
+ * i915_gem_shrinker_unregister - Unregisters the i915 shrinker
+ * @i915: i915 device
  *
  * This function unregisters the i915 shrinker and OOM handler.
  */
-void i915_gem_shrinker_cleanup(struct drm_i915_private *dev_priv)
+void i915_gem_shrinker_unregister(struct drm_i915_private *i915)
 {
-	WARN_ON(unregister_vmap_purge_notifier(&dev_priv->mm.vmap_notifier));
-	WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier));
-	unregister_shrinker(&dev_priv->mm.shrinker);
+	WARN_ON(unregister_vmap_purge_notifier(&i915->mm.vmap_notifier));
+	WARN_ON(unregister_oom_notifier(&i915->mm.oom_notifier));
+	unregister_shrinker(&i915->mm.shrinker);
 }

drivers/gpu/drm/i915/i915_gem_timeline.c

@@ -107,8 +107,8 @@ int i915_gem_timeline_init__global(struct drm_i915_private *i915)
 }
 
 /**
- * i915_gem_timelines_mark_idle -- called when the driver idles
- * @i915 - the drm_i915_private device
+ * i915_gem_timelines_park - called when the driver idles
+ * @i915: the drm_i915_private device
  *
  * When the driver is completely idle, we know that all of our sync points
  * have been signaled and our tracking is then entirely redundant. Any request
@@ -116,7 +116,7 @@ int i915_gem_timeline_init__global(struct drm_i915_private *i915)
  * the fence is signaled and therefore we will not even look them up in the
  * sync point map.
  */
-void i915_gem_timelines_mark_idle(struct drm_i915_private *i915)
+void i915_gem_timelines_park(struct drm_i915_private *i915)
 {
 	struct i915_gem_timeline *timeline;
 	int i;

drivers/gpu/drm/i915/i915_gem_timeline.h

@@ -93,7 +93,7 @@ int i915_gem_timeline_init(struct drm_i915_private *i915,
 			   struct i915_gem_timeline *tl,
 			   const char *name);
 int i915_gem_timeline_init__global(struct drm_i915_private *i915);
-void i915_gem_timelines_mark_idle(struct drm_i915_private *i915);
+void i915_gem_timelines_park(struct drm_i915_private *i915);
 void i915_gem_timeline_fini(struct i915_gem_timeline *tl);
 
 static inline int __intel_timeline_sync_set(struct intel_timeline *tl,

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -791,9 +791,10 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 
 		print_error_obj(m, dev_priv->engine[i],
 				"WA batchbuffer", ee->wa_batchbuffer);
-	}
 
-	print_error_obj(m, NULL, "Semaphores", error->semaphore);
+		print_error_obj(m, dev_priv->engine[i],
+				"NULL context", ee->default_state);
+	}
 
 	if (error->overlay)
 		intel_overlay_print_error_state(m, error->overlay);
@@ -903,8 +904,6 @@ void __i915_gpu_state_free(struct kref *error_ref)
 			kfree(ee->waiters);
 	}
 
-	i915_error_object_free(error->semaphore);
-
 	for (i = 0; i < ARRAY_SIZE(error->active_bo); i++)
 		kfree(error->active_bo[i]);
 	kfree(error->pinned_bo);
@@ -1116,34 +1115,6 @@ gen8_engine_sync_index(struct intel_engine_cs *engine,
 	return idx;
 }
 
-static void gen8_record_semaphore_state(struct i915_gpu_state *error,
-					struct intel_engine_cs *engine,
-					struct drm_i915_error_engine *ee)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	struct intel_engine_cs *to;
-	enum intel_engine_id id;
-
-	if (!error->semaphore)
-		return;
-
-	for_each_engine(to, dev_priv, id) {
-		int idx;
-		u16 signal_offset;
-		u32 *tmp;
-
-		if (engine == to)
-			continue;
-
-		signal_offset =
-			(GEN8_SIGNAL_OFFSET(engine, id) & (PAGE_SIZE - 1)) / 4;
-		tmp = error->semaphore->pages[0];
-		idx = gen8_engine_sync_index(engine, to);
-
-		ee->semaphore_mboxes[idx] = tmp[signal_offset];
-	}
-}
-
 static void gen6_record_semaphore_state(struct intel_engine_cs *engine,
 					struct drm_i915_error_engine *ee)
 {
@@ -1218,7 +1189,6 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
 	if (INTEL_GEN(dev_priv) >= 6) {
 		ee->rc_psmi = I915_READ(RING_PSMI_CTL(engine->mmio_base));
 		if (INTEL_GEN(dev_priv) >= 8) {
-			gen8_record_semaphore_state(error, engine, ee);
 			ee->fault_reg = I915_READ(GEN8_RING_FAULT_REG);
 		} else {
 			gen6_record_semaphore_state(engine, ee);
@@ -1447,15 +1417,30 @@ static void request_record_user_bo(struct drm_i915_gem_request *request,
 	ee->user_bo_count = count;
 }
 
+static struct drm_i915_error_object *
+capture_object(struct drm_i915_private *dev_priv,
+	       struct drm_i915_gem_object *obj)
+{
+	if (obj && i915_gem_object_has_pages(obj)) {
+		struct i915_vma fake = {
+			.node = { .start = U64_MAX, .size = obj->base.size },
+			.size = obj->base.size,
+			.pages = obj->mm.pages,
+			.obj = obj,
+		};
+
+		return i915_error_object_create(dev_priv, &fake);
+	} else {
+		return NULL;
+	}
+}
+
 static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 				  struct i915_gpu_state *error)
 {
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	int i;
 
-	error->semaphore =
-		i915_error_object_create(dev_priv, dev_priv->semaphore);
-
 	for (i = 0; i < I915_NUM_ENGINES; i++) {
 		struct intel_engine_cs *engine = dev_priv->engine[i];
 		struct drm_i915_error_engine *ee = &error->engine[i];
@@ -1521,6 +1506,9 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 
 		ee->wa_ctx =
 			i915_error_object_create(dev_priv, engine->wa_ctx.vma);
+
+		ee->default_state =
+			capture_object(dev_priv, engine->default_state);
 	}
 }
 

drivers/gpu/drm/i915/i915_irq.c

@@ -3068,7 +3068,7 @@ static void vlv_display_irq_reset(struct drm_i915_private *dev_priv)
 	i9xx_pipestat_irq_reset(dev_priv);
 
 	GEN3_IRQ_RESET(VLV_);
-	dev_priv->irq_mask = ~0;
+	dev_priv->irq_mask = ~0u;
 }
 
 static void vlv_display_irq_postinstall(struct drm_i915_private *dev_priv)
@@ -3093,7 +3093,7 @@ static void vlv_display_irq_postinstall(struct drm_i915_private *dev_priv)
 		enable_mask |= I915_DISPLAY_PIPE_C_EVENT_INTERRUPT |
 			I915_LPE_PIPE_C_INTERRUPT;
 
-	WARN_ON(dev_priv->irq_mask != ~0);
+	WARN_ON(dev_priv->irq_mask != ~0u);
 
 	dev_priv->irq_mask = ~enable_mask;
 

drivers/gpu/drm/i915/i915_params.c

@@ -46,17 +46,6 @@ i915_param_named_unsafe(panel_ignore_lid, int, 0600,
 	"Override lid status (0=autodetect, 1=autodetect disabled [default], "
 	"-1=force lid closed, -2=force lid open)");
 
-i915_param_named_unsafe(semaphores, int, 0400,
-	"Use semaphores for inter-ring sync "
-	"(default: -1 (use per-chip defaults))");
-
-i915_param_named_unsafe(enable_rc6, int, 0400,
-	"Enable power-saving render C-state 6. "
-	"Different stages can be selected via bitmask values "
-	"(0 = disable; 1 = enable rc6; 2 = enable deep rc6; 4 = enable deepest rc6). "
-	"For example, 3 would enable rc6 and deep rc6, and 7 would enable everything. "
-	"default: -1 (use per-chip default)");
-
 i915_param_named_unsafe(enable_dc, int, 0400,
 	"Enable power-saving display C-states. "
 	"(-1=auto [default]; 0=disable; 1=up to DC5; 2=up to DC6)");
@@ -99,10 +88,6 @@ i915_param_named_unsafe(enable_ppgtt, int, 0400,
 	"Override PPGTT usage. "
 	"(-1=auto [default], 0=disabled, 1=aliasing, 2=full, 3=full with extended address space)");
 
-i915_param_named_unsafe(enable_execlists, int, 0400,
-	"Override execlists usage. "
-	"(-1=auto [default], 0=disabled, 1=enabled)");
-
 i915_param_named_unsafe(enable_psr, int, 0600,
 	"Enable PSR "
 	"(0=disabled, 1=enabled - link mode chosen per-platform, 2=force link-standby mode, 3=force link-off mode) "

drivers/gpu/drm/i915/i915_params.h

@@ -31,15 +31,12 @@
 	param(char *, vbt_firmware, NULL) \
 	param(int, modeset, -1) \
 	param(int, panel_ignore_lid, 1) \
-	param(int, semaphores, -1) \
 	param(int, lvds_channel_mode, 0) \
 	param(int, panel_use_ssc, -1) \
 	param(int, vbt_sdvo_panel_type, -1) \
-	param(int, enable_rc6, -1) \
 	param(int, enable_dc, -1) \
 	param(int, enable_fbc, -1) \
 	param(int, enable_ppgtt, -1) \
-	param(int, enable_execlists, -1) \
 	param(int, enable_psr, -1) \
 	param(int, disable_power_well, -1) \
 	param(int, enable_ips, 1) \

drivers/gpu/drm/i915/i915_pci.c

@@ -209,6 +209,8 @@ static const struct intel_device_info intel_gm45_info __initconst = {
 	.has_hotplug = 1, \
 	.ring_mask = RENDER_RING | BSD_RING, \
 	.has_snoop = true, \
+	/* ilk does support rc6, but we do not implement [power] contexts */ \
+	.has_rc6 = 0, \
 	GEN_DEFAULT_PIPEOFFSETS, \
 	GEN_DEFAULT_PAGE_SIZES, \
 	CURSOR_OFFSETS

drivers/gpu/drm/i915/i915_perf.c

@@ -1216,9 +1216,9 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *dev_priv = stream->dev_priv;
 
-	if (i915_modparams.enable_execlists)
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 		dev_priv->perf.oa.specific_ctx_id = stream->ctx->hw_id;
-	else {
+	} else {
 		struct intel_engine_cs *engine = dev_priv->engine[RCS];
 		struct intel_ring *ring;
 		int ret;
@@ -1262,7 +1262,7 @@ static void oa_put_render_ctx_id(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *dev_priv = stream->dev_priv;
 
-	if (i915_modparams.enable_execlists) {
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 		dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
 	} else {
 		struct intel_engine_cs *engine = dev_priv->engine[RCS];
@@ -1726,10 +1726,9 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr
 							 GFP_KERNEL);
 	}
 
-	ret = i915_switch_context(req);
 	i915_add_request(req);
 
-	return ret;
+	return 0;
 }
 
 /*
@@ -2691,8 +2690,8 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv,
 
 static u64 oa_exponent_to_ns(struct drm_i915_private *dev_priv, int exponent)
 {
-	return div_u64(1000000000ULL * (2ULL << exponent),
-		       dev_priv->perf.oa.timestamp_frequency);
+	return div64_u64(1000000000ULL * (2ULL << exponent),
+			 1000ULL * INTEL_INFO(dev_priv)->cs_timestamp_frequency_khz);
 }
 
 /**
@@ -3007,7 +3006,7 @@ static bool gen8_is_valid_flex_addr(struct drm_i915_private *dev_priv, u32 addr)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(flex_eu_regs); i++) {
-		if (flex_eu_regs[i].reg == addr)
+		if (i915_mmio_reg_offset(flex_eu_regs[i]) == addr)
 			return true;
 	}
 	return false;
@@ -3015,38 +3014,47 @@ static bool gen8_is_valid_flex_addr(struct drm_i915_private *dev_priv, u32 addr)
 
 static bool gen7_is_valid_b_counter_addr(struct drm_i915_private *dev_priv, u32 addr)
 {
-	return (addr >= OASTARTTRIG1.reg && addr <= OASTARTTRIG8.reg) ||
-		(addr >= OAREPORTTRIG1.reg && addr <= OAREPORTTRIG8.reg) ||
-		(addr >= OACEC0_0.reg && addr <= OACEC7_1.reg);
+	return (addr >= i915_mmio_reg_offset(OASTARTTRIG1) &&
+		addr <= i915_mmio_reg_offset(OASTARTTRIG8)) ||
+		(addr >= i915_mmio_reg_offset(OAREPORTTRIG1) &&
+		 addr <= i915_mmio_reg_offset(OAREPORTTRIG8)) ||
+		(addr >= i915_mmio_reg_offset(OACEC0_0) &&
+		 addr <= i915_mmio_reg_offset(OACEC7_1));
 }
 
 static bool gen7_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
 {
-	return addr == HALF_SLICE_CHICKEN2.reg ||
-		(addr >= MICRO_BP0_0.reg && addr <= NOA_WRITE.reg) ||
-		(addr >= OA_PERFCNT1_LO.reg && addr <= OA_PERFCNT2_HI.reg) ||
-		(addr >= OA_PERFMATRIX_LO.reg && addr <= OA_PERFMATRIX_HI.reg);
+	return addr == i915_mmio_reg_offset(HALF_SLICE_CHICKEN2) ||
+		(addr >= i915_mmio_reg_offset(MICRO_BP0_0) &&
+		 addr <= i915_mmio_reg_offset(NOA_WRITE)) ||
+		(addr >= i915_mmio_reg_offset(OA_PERFCNT1_LO) &&
+		 addr <= i915_mmio_reg_offset(OA_PERFCNT2_HI)) ||
+		(addr >= i915_mmio_reg_offset(OA_PERFMATRIX_LO) &&
+		 addr <= i915_mmio_reg_offset(OA_PERFMATRIX_HI));
 }
 
 static bool gen8_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
 {
 	return gen7_is_valid_mux_addr(dev_priv, addr) ||
-		addr == WAIT_FOR_RC6_EXIT.reg ||
-		(addr >= RPM_CONFIG0.reg && addr <= NOA_CONFIG(8).reg);
+		addr == i915_mmio_reg_offset(WAIT_FOR_RC6_EXIT) ||
+		(addr >= i915_mmio_reg_offset(RPM_CONFIG0) &&
+		 addr <= i915_mmio_reg_offset(NOA_CONFIG(8)));
 }
 
 static bool gen10_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
 {
 	return gen8_is_valid_mux_addr(dev_priv, addr) ||
-		(addr >= OA_PERFCNT3_LO.reg && addr <= OA_PERFCNT4_HI.reg);
+		(addr >= i915_mmio_reg_offset(OA_PERFCNT3_LO) &&
+		 addr <= i915_mmio_reg_offset(OA_PERFCNT4_HI));
 }
 
 static bool hsw_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
 {
 	return gen7_is_valid_mux_addr(dev_priv, addr) ||
 		(addr >= 0x25100 && addr <= 0x2FF90) ||
-		(addr >= HSW_MBVID2_NOA0.reg && addr <= HSW_MBVID2_NOA9.reg) ||
-		addr == HSW_MBVID2_MISR0.reg;
+		(addr >= i915_mmio_reg_offset(HSW_MBVID2_NOA0) &&
+		 addr <= i915_mmio_reg_offset(HSW_MBVID2_NOA9)) ||
+		addr == i915_mmio_reg_offset(HSW_MBVID2_MISR0);
 }
 
 static bool chv_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
@@ -3061,14 +3069,14 @@ static uint32_t mask_reg_value(u32 reg, u32 val)
 	 * WaDisableSTUnitPowerOptimization workaround. Make sure the value
 	 * programmed by userspace doesn't change this.
 	 */
-	if (HALF_SLICE_CHICKEN2.reg == reg)
+	if (i915_mmio_reg_offset(HALF_SLICE_CHICKEN2) == reg)
 		val = val & ~_MASKED_BIT_ENABLE(GEN8_ST_PO_DISABLE);
 
 	/* WAIT_FOR_RC6_EXIT has only one bit fullfilling the function
 	 * indicated by its name and a bunch of selection fields used by OA
 	 * configs.
 	 */
-	if (WAIT_FOR_RC6_EXIT.reg == reg)
+	if (i915_mmio_reg_offset(WAIT_FOR_RC6_EXIT) == reg)
 		val = val & ~_MASKED_BIT_ENABLE(HSW_WAIT_FOR_RC6_EXIT_ENABLE);
 
 	return val;
@@ -3415,8 +3423,6 @@ static struct ctl_table dev_root[] = {
  */
 void i915_perf_init(struct drm_i915_private *dev_priv)
 {
-	dev_priv->perf.oa.timestamp_frequency = 0;
-
 	if (IS_HASWELL(dev_priv)) {
 		dev_priv->perf.oa.ops.is_valid_b_counter_reg =
 			gen7_is_valid_b_counter_addr;
@@ -3432,10 +3438,8 @@ void i915_perf_init(struct drm_i915_private *dev_priv)
 		dev_priv->perf.oa.ops.oa_hw_tail_read =
 			gen7_oa_hw_tail_read;
 
-		dev_priv->perf.oa.timestamp_frequency = 12500000;
-
 		dev_priv->perf.oa.oa_formats = hsw_oa_formats;
-	} else if (i915_modparams.enable_execlists) {
+	} else if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 		/* Note: that although we could theoretically also support the
 		 * legacy ringbuffer mode on BDW (and earlier iterations of
 		 * this driver, before upstreaming did this) it didn't seem
@@ -3477,23 +3481,6 @@ void i915_perf_init(struct drm_i915_private *dev_priv)
 
 				dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<16);
 			}
-
-			switch (dev_priv->info.platform) {
-			case INTEL_BROADWELL:
-				dev_priv->perf.oa.timestamp_frequency = 12500000;
-				break;
-			case INTEL_BROXTON:
-			case INTEL_GEMINILAKE:
-				dev_priv->perf.oa.timestamp_frequency = 19200000;
-				break;
-			case INTEL_SKYLAKE:
-			case INTEL_KABYLAKE:
-			case INTEL_COFFEELAKE:
-				dev_priv->perf.oa.timestamp_frequency = 12000000;
-				break;
-			default:
-				break;
-			}
 		} else if (IS_GEN10(dev_priv)) {
 			dev_priv->perf.oa.ops.is_valid_b_counter_reg =
 				gen7_is_valid_b_counter_addr;
@@ -3509,15 +3496,10 @@ void i915_perf_init(struct drm_i915_private *dev_priv)
 			dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de;
 
 			dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<16);
-
-			/* Default frequency, although we need to read it from
-			 * the register as it might vary between parts.
-			 */
-			dev_priv->perf.oa.timestamp_frequency = 12000000;
 		}
 	}
 
-	if (dev_priv->perf.oa.timestamp_frequency) {
+	if (dev_priv->perf.oa.ops.enable_metric_set) {
 		hrtimer_init(&dev_priv->perf.oa.poll_check_timer,
 				CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		dev_priv->perf.oa.poll_check_timer.function = oa_poll_check_timer_cb;
@@ -3527,8 +3509,8 @@ void i915_perf_init(struct drm_i915_private *dev_priv)
 		mutex_init(&dev_priv->perf.lock);
 		spin_lock_init(&dev_priv->perf.oa.oa_buffer.ptr_lock);
 
-		oa_sample_rate_hard_limit =
-			dev_priv->perf.oa.timestamp_frequency / 2;
+		oa_sample_rate_hard_limit = 1000 *
+			(INTEL_INFO(dev_priv)->cs_timestamp_frequency_khz / 2);
 		dev_priv->perf.sysctl_header = register_sysctl_table(dev_root);
 
 		mutex_init(&dev_priv->perf.metrics_lock);

drivers/gpu/drm/i915/i915_pmu.h

+/*
+ * Copyright © 2017 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+#ifndef __I915_PMU_H__
+#define __I915_PMU_H__
+
+enum {
+	__I915_SAMPLE_FREQ_ACT = 0,
+	__I915_SAMPLE_FREQ_REQ,
+	__I915_NUM_PMU_SAMPLERS
+};
+
+/**
+ * How many different events we track in the global PMU mask.
+ *
+ * It is also used to know to needed number of event reference counters.
+ */
+#define I915_PMU_MASK_BITS \
+	((1 << I915_PMU_SAMPLE_BITS) + \
+	 (I915_PMU_LAST + 1 - __I915_PMU_OTHER(0)))
+
+struct i915_pmu_sample {
+	u64 cur;
+};
+
+struct i915_pmu {
+	/**
+	 * @node: List node for CPU hotplug handling.
+	 */
+	struct hlist_node node;
+	/**
+	 * @base: PMU base.
+	 */
+	struct pmu base;
+	/**
+	 * @lock: Lock protecting enable mask and ref count handling.
+	 */
+	spinlock_t lock;
+	/**
+	 * @timer: Timer for internal i915 PMU sampling.
+	 */
+	struct hrtimer timer;
+	/**
+	 * @enable: Bitmask of all currently enabled events.
+	 *
+	 * Bits are derived from uAPI event numbers in a way that low 16 bits
+	 * correspond to engine event _sample_ _type_ (I915_SAMPLE_QUEUED is
+	 * bit 0), and higher bits correspond to other events (for instance
+	 * I915_PMU_ACTUAL_FREQUENCY is bit 16 etc).
+	 *
+	 * In other words, low 16 bits are not per engine but per engine
+	 * sampler type, while the upper bits are directly mapped to other
+	 * event types.
+	 */
+	u64 enable;
+	/**
+	 * @enable_count: Reference counts for the enabled events.
+	 *
+	 * Array indices are mapped in the same way as bits in the @enable field
+	 * and they are used to control sampling on/off when multiple clients
+	 * are using the PMU API.
+	 */
+	unsigned int enable_count[I915_PMU_MASK_BITS];
+	/**
+	 * @timer_enabled: Should the internal sampling timer be running.
+	 */
+	bool timer_enabled;
+	/**
+	 * @sample: Current and previous (raw) counters for sampling events.
+	 *
+	 * These counters are updated from the i915 PMU sampling timer.
+	 *
+	 * Only global counters are held here, while the per-engine ones are in
+	 * struct intel_engine_cs.
+	 */
+	struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS];
+};
+
+#ifdef CONFIG_PERF_EVENTS
+void i915_pmu_register(struct drm_i915_private *i915);
+void i915_pmu_unregister(struct drm_i915_private *i915);
+void i915_pmu_gt_parked(struct drm_i915_private *i915);
+void i915_pmu_gt_unparked(struct drm_i915_private *i915);
+#else
+static inline void i915_pmu_register(struct drm_i915_private *i915) {}
+static inline void i915_pmu_unregister(struct drm_i915_private *i915) {}
+static inline void i915_pmu_gt_parked(struct drm_i915_private *i915) {}
+static inline void i915_pmu_gt_unparked(struct drm_i915_private *i915) {}
+#endif
+
+#endif

drivers/gpu/drm/i915/i915_reg.h

@@ -186,6 +186,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define VIDEO_ENHANCEMENT_CLASS	2
 #define COPY_ENGINE_CLASS	3
 #define OTHER_CLASS		4
+#define MAX_ENGINE_CLASS	4
+
+#define MAX_ENGINE_INSTANCE    1
 
 /* PCI config space */
 

drivers/gpu/drm/i915/i915_sysfs.c

@@ -42,14 +42,30 @@ static inline struct drm_i915_private *kdev_minor_to_i915(struct device *kdev)
 static u32 calc_residency(struct drm_i915_private *dev_priv,
 			  i915_reg_t reg)
 {
-	return DIV_ROUND_CLOSEST_ULL(intel_rc6_residency_us(dev_priv, reg),
-				     1000);
+	u64 res;
+
+	intel_runtime_pm_get(dev_priv);
+	res = intel_rc6_residency_us(dev_priv, reg);
+	intel_runtime_pm_put(dev_priv);
+
+	return DIV_ROUND_CLOSEST_ULL(res, 1000);
 }
 
 static ssize_t
 show_rc6_mask(struct device *kdev, struct device_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%x\n", intel_rc6_enabled());
+	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
+	unsigned int mask;
+
+	mask = 0;
+	if (HAS_RC6(dev_priv))
+		mask |= BIT(0);
+	if (HAS_RC6p(dev_priv))
+		mask |= BIT(1);
+	if (HAS_RC6pp(dev_priv))
+		mask |= BIT(2);
+
+	return snprintf(buf, PAGE_SIZE, "%x\n", mask);
 }
 
 static ssize_t
@@ -252,14 +268,9 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 		freq = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
 		ret = intel_gpu_freq(dev_priv, (freq >> 8) & 0xff);
 	} else {
-		u32 rpstat = I915_READ(GEN6_RPSTAT1);
-		if (INTEL_GEN(dev_priv) >= 9)
-			ret = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
-		else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-			ret = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
-		else
-			ret = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
-		ret = intel_gpu_freq(dev_priv, ret);
+		ret = intel_gpu_freq(dev_priv,
+				     intel_get_cagf(dev_priv,
+						    I915_READ(GEN6_RPSTAT1)));
 	}
 	mutex_unlock(&dev_priv->pcu_lock);
 

drivers/gpu/drm/i915/intel_cdclk.c

@@ -1896,7 +1896,7 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 	min_cdclk = intel_pixel_rate_to_cdclk(dev_priv, crtc_state->pixel_rate);
 
 	/* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
-	if (IS_BROADWELL(dev_priv) && crtc_state->ips_enabled)
+	if (IS_BROADWELL(dev_priv) && hsw_crtc_state_ips_capable(crtc_state))
 		min_cdclk = DIV_ROUND_UP(min_cdclk * 100, 95);
 
 	/* BSpec says "Do not use DisplayPort with CDCLK less than 432 MHz,

drivers/gpu/drm/i915/intel_csr.c

@@ -40,9 +40,9 @@
 #define I915_CSR_CNL "i915/cnl_dmc_ver1_06.bin"
 #define CNL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 6)
 
-#define I915_CSR_KBL "i915/kbl_dmc_ver1_01.bin"
+#define I915_CSR_KBL "i915/kbl_dmc_ver1_04.bin"
 MODULE_FIRMWARE(I915_CSR_KBL);
-#define KBL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 1)
+#define KBL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 4)
 
 #define I915_CSR_SKL "i915/skl_dmc_ver1_26.bin"
 MODULE_FIRMWARE(I915_CSR_SKL);

drivers/gpu/drm/i915/intel_ddi.c

@@ -2098,6 +2098,7 @@ static void intel_ddi_clk_select(struct intel_encoder *encoder,
 	if (IS_CANNONLAKE(dev_priv)) {
 		/* Configure DPCLKA_CFGCR0 to map the DPLL to the DDI. */
 		val = I915_READ(DPCLKA_CFGCR0);
+		val &= ~DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port);
 		val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->id, port);
 		I915_WRITE(DPCLKA_CFGCR0, val);
 
@@ -2513,17 +2514,17 @@ void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 	udelay(600);
 }
 
-bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv,
-				 struct intel_crtc *intel_crtc)
+static bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv,
+				       enum transcoder cpu_transcoder)
 {
-	u32 temp;
+	if (cpu_transcoder == TRANSCODER_EDP)
+		return false;
 
-	if (intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO)) {
-		temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
-		if (temp & AUDIO_OUTPUT_ENABLE(intel_crtc->pipe))
-			return true;
-	}
-	return false;
+	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO))
+		return false;
+
+	return I915_READ(HSW_AUD_PIN_ELD_CP_VLD) &
+		AUDIO_OUTPUT_ENABLE(cpu_transcoder);
 }
 
 void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
@@ -2616,7 +2617,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 	}
 
 	pipe_config->has_audio =
-		intel_ddi_is_audio_enabled(dev_priv, intel_crtc);
+		intel_ddi_is_audio_enabled(dev_priv, cpu_transcoder);
 
 	if (encoder->type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.bpp &&
 	    pipe_config->pipe_bpp > dev_priv->vbt.edp.bpp) {

drivers/gpu/drm/i915/intel_dp.c

@@ -1643,7 +1643,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 		pipe_config->has_pch_encoder = true;
 
 	pipe_config->has_drrs = false;
-	if (port == PORT_A)
+	if (IS_G4X(dev_priv) || port == PORT_A)
 		pipe_config->has_audio = false;
 	else if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO)
 		pipe_config->has_audio = intel_dp->has_audio;
@@ -1677,6 +1677,10 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 						conn_state->scaling_mode);
 	}
 
+	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+	    adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE)
+		return false;
+
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		return false;
 
@@ -4277,6 +4281,8 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
 	struct intel_encoder *intel_encoder = &dp_to_dig_port(intel_dp)->base;
+	struct drm_connector_state *conn_state =
+		intel_dp->attached_connector->base.state;
 	u8 link_status[DP_LINK_STATUS_SIZE];
 
 	WARN_ON(!drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex));
@@ -4286,10 +4292,16 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 		return;
 	}
 
-	if (!intel_encoder->base.crtc)
+	if (!conn_state->crtc)
+		return;
+
+	WARN_ON(!drm_modeset_is_locked(&conn_state->crtc->mutex));
+
+	if (!conn_state->crtc->state->active)
 		return;
 
-	if (!to_intel_crtc(intel_encoder->base.crtc)->active)
+	if (conn_state->commit &&
+	    !try_wait_for_completion(&conn_state->commit->hw_done))
 		return;
 
 	/*
@@ -4364,9 +4376,8 @@ intel_dp_short_pulse(struct intel_dp *intel_dp)
 			DRM_DEBUG_DRIVER("CP or sink specific irq unhandled\n");
 	}
 
-	drm_modeset_lock(&dev_priv->drm.mode_config.connection_mutex, NULL);
 	intel_dp_check_link_status(intel_dp);
-	drm_modeset_unlock(&dev_priv->drm.mode_config.connection_mutex);
+
 	if (intel_dp->compliance.test_type == DP_TEST_LINK_TRAINING) {
 		DRM_DEBUG_KMS("Link Training Compliance Test requested\n");
 		/* Send a Hotplug Uevent to userspace to start modeset */
@@ -4814,8 +4825,19 @@ intel_dp_detect(struct drm_connector *connector,
 		      connector->base.id, connector->name);
 
 	/* If full detect is not performed yet, do a full detect */
-	if (!intel_dp->detect_done)
+	if (!intel_dp->detect_done) {
+		struct drm_crtc *crtc;
+		int ret;
+
+		crtc = connector->state->crtc;
+		if (crtc) {
+			ret = drm_modeset_lock(&crtc->mutex, ctx);
+			if (ret)
+				return ret;
+		}
+
 		status = intel_dp_long_pulse(intel_dp->attached_connector);
+	}
 
 	intel_dp->detect_done = false;
 
@@ -5097,7 +5119,38 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 	}
 
 	if (!intel_dp->is_mst) {
-		if (!intel_dp_short_pulse(intel_dp)) {
+		struct drm_modeset_acquire_ctx ctx;
+		struct drm_connector *connector = &intel_dp->attached_connector->base;
+		struct drm_crtc *crtc;
+		int iret;
+		bool handled = false;
+
+		drm_modeset_acquire_init(&ctx, 0);
+retry:
+		iret = drm_modeset_lock(&dev_priv->drm.mode_config.connection_mutex, &ctx);
+		if (iret)
+			goto err;
+
+		crtc = connector->state->crtc;
+		if (crtc) {
+			iret = drm_modeset_lock(&crtc->mutex, &ctx);
+			if (iret)
+				goto err;
+		}
+
+		handled = intel_dp_short_pulse(intel_dp);
+
+err:
+		if (iret == -EDEADLK) {
+			drm_modeset_backoff(&ctx);
+			goto retry;
+		}
+
+		drm_modeset_drop_locks(&ctx);
+		drm_modeset_acquire_fini(&ctx);
+		WARN(iret, "Acquiring modeset locks failed with %i\n", iret);
+
+		if (!handled) {
 			intel_dp->detect_done = false;
 			goto put_power;
 		}
@@ -5131,8 +5184,11 @@ static void
 intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
+	enum port port = dp_to_dig_port(intel_dp)->base.port;
+
+	if (!IS_G4X(dev_priv) && port != PORT_A)
+		intel_attach_force_audio_property(connector);
 
-	intel_attach_force_audio_property(connector);
 	intel_attach_broadcast_rgb_property(connector);
 
 	if (intel_dp_is_edp(intel_dp)) {
@@ -5306,6 +5362,12 @@ intel_dp_init_panel_power_sequencer(struct intel_dp *intel_dp)
 	 */
 	final->t8 = 1;
 	final->t9 = 1;
+
+	/*
+	 * HW has only a 100msec granularity for t11_t12 so round it up
+	 * accordingly.
+	 */
+	final->t11_t12 = roundup(final->t11_t12, 100 * 10);
 }
 
 static void
@@ -6034,7 +6096,8 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	drm_connector_init(dev, connector, &intel_dp_connector_funcs, type);
 	drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs);
 
-	connector->interlace_allowed = true;
+	if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
+		connector->interlace_allowed = true;
 	connector->doublescan_allowed = 0;
 
 	intel_dp_init_connector_port_info(intel_dig_port);

drivers/gpu/drm/i915/intel_drv.h

@@ -48,8 +48,9 @@
  * having timed out, since the timeout could be due to preemption or similar and
  * we've never had a chance to check the condition before the timeout.
  */
-#define _wait_for(COND, US, W) ({ \
+#define _wait_for(COND, US, Wmin, Wmax) ({ \
 	unsigned long timeout__ = jiffies + usecs_to_jiffies(US) + 1;	\
+	long wait__ = (Wmin); /* recommended min for usleep is 10 us */	\
 	int ret__;							\
 	might_sleep();							\
 	for (;;) {							\
@@ -62,12 +63,14 @@
 			ret__ = -ETIMEDOUT;				\
 			break;						\
 		}							\
-		usleep_range((W), (W) * 2);				\
+		usleep_range(wait__, wait__ * 2);			\
+		if (wait__ < (Wmax))					\
+			wait__ <<= 1;					\
 	}								\
 	ret__;								\
 })
 
-#define wait_for(COND, MS)	  	_wait_for((COND), (MS) * 1000, 1000)
+#define wait_for(COND, MS)	_wait_for((COND), (MS) * 1000, 10, 1000)
 
 /* If CONFIG_PREEMPT_COUNT is disabled, in_atomic() always reports false. */
 #if defined(CONFIG_DRM_I915_DEBUG) && defined(CONFIG_PREEMPT_COUNT)
@@ -116,7 +119,7 @@
 	int ret__; \
 	BUILD_BUG_ON(!__builtin_constant_p(US)); \
 	if ((US) > 10) \
-		ret__ = _wait_for((COND), (US), 10); \
+		ret__ = _wait_for((COND), (US), 10, 10); \
 	else \
 		ret__ = _wait_for_atomic((COND), (US), 0); \
 	ret__; \
@@ -799,7 +802,6 @@ struct intel_crtc_state {
 struct intel_crtc {
 	struct drm_crtc base;
 	enum pipe pipe;
-	enum plane plane;
 	/*
 	 * Whether the crtc and the connected output pipeline is active. Implies
 	 * that crtc->enabled is set, i.e. the current mode configuration has
@@ -844,7 +846,7 @@ struct intel_crtc {
 
 struct intel_plane {
 	struct drm_plane base;
-	u8 plane;
+	enum i9xx_plane_id i9xx_plane;
 	enum plane_id id;
 	enum pipe pipe;
 	bool can_scale;
@@ -866,6 +868,7 @@ struct intel_plane {
 			     const struct intel_plane_state *plane_state);
 	void (*disable_plane)(struct intel_plane *plane,
 			      struct intel_crtc *crtc);
+	bool (*get_hw_state)(struct intel_plane *plane);
 	int (*check_plane)(struct intel_plane *plane,
 			   struct intel_crtc_state *crtc_state,
 			   struct intel_plane_state *state);
@@ -1129,7 +1132,7 @@ intel_get_crtc_for_pipe(struct drm_i915_private *dev_priv, enum pipe pipe)
 }
 
 static inline struct intel_crtc *
-intel_get_crtc_for_plane(struct drm_i915_private *dev_priv, enum plane plane)
+intel_get_crtc_for_plane(struct drm_i915_private *dev_priv, enum i9xx_plane_id plane)
 {
 	return dev_priv->plane_to_crtc_mapping[plane];
 }
@@ -1285,8 +1288,6 @@ intel_ddi_get_crtc_new_encoder(struct intel_crtc_state *crtc_state);
 void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state);
 void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp);
 bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector);
-bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv,
-				 struct intel_crtc *intel_crtc);
 void intel_ddi_get_config(struct intel_encoder *encoder,
 			  struct intel_crtc_state *pipe_config);
 
@@ -1485,6 +1486,7 @@ bool bxt_find_best_dpll(struct intel_crtc_state *crtc_state, int target_clock,
 int chv_calc_dpll_params(int refclk, struct dpll *pll_clock);
 
 bool intel_crtc_active(struct intel_crtc *crtc);
+bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state);
 void hsw_enable_ips(const struct intel_crtc_state *crtc_state);
 void hsw_disable_ips(const struct intel_crtc_state *crtc_state);
 enum intel_display_power_domain intel_port_to_power_domain(enum port port);
@@ -1651,7 +1653,7 @@ static inline void intel_fbdev_restore_mode(struct drm_device *dev)
 
 /* intel_fbc.c */
 void intel_fbc_choose_crtc(struct drm_i915_private *dev_priv,
-			   struct drm_atomic_state *state);
+			   struct intel_atomic_state *state);
 bool intel_fbc_is_active(struct drm_i915_private *dev_priv);
 void intel_fbc_pre_update(struct intel_crtc *crtc,
 			  struct intel_crtc_state *crtc_state,
@@ -1906,15 +1908,10 @@ bool skl_ddb_allocation_overlaps(struct drm_i915_private *dev_priv,
 				 const struct skl_ddb_entry *ddb,
 				 int ignore);
 bool ilk_disable_lp_wm(struct drm_device *dev);
-int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6);
 int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
 				  struct intel_crtc_state *cstate);
 void intel_init_ipc(struct drm_i915_private *dev_priv);
 void intel_enable_ipc(struct drm_i915_private *dev_priv);
-static inline int intel_rc6_enabled(void)
-{
-	return i915_modparams.enable_rc6;
-}
 
 /* intel_sdvo.c */
 bool intel_sdvo_init(struct drm_i915_private *dev_priv,
@@ -1934,6 +1931,7 @@ void skl_update_plane(struct intel_plane *plane,
 		      const struct intel_crtc_state *crtc_state,
 		      const struct intel_plane_state *plane_state);
 void skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc);
+bool skl_plane_get_hw_state(struct intel_plane *plane);
 
 /* intel_tv.c */
 void intel_tv_init(struct drm_i915_private *dev_priv);

drivers/gpu/drm/i915/intel_dsi.c

@@ -1670,7 +1670,7 @@ static int intel_dsi_get_panel_orientation(struct intel_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	int orientation = DRM_MODE_PANEL_ORIENTATION_NORMAL;
-	enum plane plane;
+	enum i9xx_plane_id plane;
 	u32 val;
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {

drivers/gpu/drm/i915/intel_engine_cs.c

@@ -37,8 +37,6 @@
  * Resource Streamer, is 66944 bytes, which rounds to 17 pages.
  */
 #define HSW_CXT_TOTAL_SIZE		(17 * PAGE_SIZE)
-/* Same as Haswell, but 72064 bytes now. */
-#define GEN8_CXT_TOTAL_SIZE		(18 * PAGE_SIZE)
 
 #define GEN8_LR_CONTEXT_RENDER_SIZE	(20 * PAGE_SIZE)
 #define GEN9_LR_CONTEXT_RENDER_SIZE	(22 * PAGE_SIZE)
@@ -164,9 +162,7 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 		case 9:
 			return GEN9_LR_CONTEXT_RENDER_SIZE;
 		case 8:
-			return i915_modparams.enable_execlists ?
-			       GEN8_LR_CONTEXT_RENDER_SIZE :
-			       GEN8_CXT_TOTAL_SIZE;
+			return GEN8_LR_CONTEXT_RENDER_SIZE;
 		case 7:
 			if (IS_HASWELL(dev_priv))
 				return HSW_CXT_TOTAL_SIZE;
@@ -209,6 +205,15 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	GEM_BUG_ON(info->class >= ARRAY_SIZE(intel_engine_classes));
 	class_info = &intel_engine_classes[info->class];
 
+	if (GEM_WARN_ON(info->class > MAX_ENGINE_CLASS))
+		return -EINVAL;
+
+	if (GEM_WARN_ON(info->instance > MAX_ENGINE_INSTANCE))
+		return -EINVAL;
+
+	if (GEM_WARN_ON(dev_priv->engine_class[info->class][info->instance]))
+		return -EINVAL;
+
 	GEM_BUG_ON(dev_priv->engine[id]);
 	engine = kzalloc(sizeof(*engine), GFP_KERNEL);
 	if (!engine)
@@ -236,8 +241,11 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
 
+	spin_lock_init(&engine->stats.lock);
+
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
 
+	dev_priv->engine_class[info->class][info->instance] = engine;
 	dev_priv->engine[id] = engine;
 	return 0;
 }
@@ -316,7 +324,7 @@ int intel_engines_init(struct drm_i915_private *dev_priv)
 			&intel_engine_classes[engine->class];
 		int (*init)(struct intel_engine_cs *engine);
 
-		if (i915_modparams.enable_execlists)
+		if (HAS_EXECLISTS(dev_priv))
 			init = class_info->init_execlists;
 		else
 			init = class_info->init_legacy;
@@ -366,18 +374,6 @@ void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno)
 		if (HAS_VEBOX(dev_priv))
 			I915_WRITE(RING_SYNC_2(engine->mmio_base), 0);
 	}
-	if (dev_priv->semaphore) {
-		struct page *page = i915_vma_first_page(dev_priv->semaphore);
-		void *semaphores;
-
-		/* Semaphores are in noncoherent memory, flush to be safe */
-		semaphores = kmap_atomic(page);
-		memset(semaphores + GEN8_SEMAPHORE_OFFSET(engine->id, 0),
-		       0, I915_NUM_ENGINES * gen8_semaphore_seqno_size);
-		drm_clflush_virt_range(semaphores + GEN8_SEMAPHORE_OFFSET(engine->id, 0),
-				       I915_NUM_ENGINES * gen8_semaphore_seqno_size);
-		kunmap_atomic(semaphores);
-	}
 
 	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
 	clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted);
@@ -1071,6 +1067,15 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine)
 	/* WaDisableSTUnitPowerOptimization:skl,bxt,kbl,glk,cfl */
 	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
 
+	/* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */
+	if (IS_GEN9_LP(dev_priv)) {
+		u32 val = I915_READ(GEN8_L3SQCREG1);
+
+		val &= ~L3_PRIO_CREDITS_MASK;
+		val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2);
+		I915_WRITE(GEN8_L3SQCREG1, val);
+	}
+
 	/* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */
 	I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) |
 				    GEN8_LQSC_FLUSH_COHERENT_LINES));
@@ -1188,7 +1193,6 @@ static int skl_init_workarounds(struct intel_engine_cs *engine)
 static int bxt_init_workarounds(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
-	u32 val;
 	int ret;
 
 	ret = gen9_init_workarounds(engine);
@@ -1203,12 +1207,6 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine)
 	I915_WRITE(FF_SLICE_CS_CHICKEN2,
 		   _MASKED_BIT_ENABLE(GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE));
 
-	/* WaProgramL3SqcReg1DefaultForPerf:bxt */
-	val = I915_READ(GEN8_L3SQCREG1);
-	val &= ~L3_PRIO_CREDITS_MASK;
-	val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2);
-	I915_WRITE(GEN8_L3SQCREG1, val);
-
 	/* WaToEnableHwFixForPushConstHWBug:bxt */
 	WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
 			  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
@@ -1729,6 +1727,15 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *m)
 			   I915_READ(RING_MI_MODE(engine->mmio_base)),
 			   I915_READ(RING_MI_MODE(engine->mmio_base)) & (MODE_IDLE) ? " [idle]" : "");
 	}
+	if (HAS_LEGACY_SEMAPHORES(dev_priv)) {
+		drm_printf(m, "\tSYNC_0: 0x%08x\n",
+			   I915_READ(RING_SYNC_0(engine->mmio_base)));
+		drm_printf(m, "\tSYNC_1: 0x%08x\n",
+			   I915_READ(RING_SYNC_1(engine->mmio_base)));
+		if (HAS_VEBOX(dev_priv))
+			drm_printf(m, "\tSYNC_2: 0x%08x\n",
+				   I915_READ(RING_SYNC_2(engine->mmio_base)));
+	}
 
 	rcu_read_unlock();
 
@@ -1739,7 +1746,7 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *m)
 	drm_printf(m, "\tBBADDR: 0x%08x_%08x\n",
 		   upper_32_bits(addr), lower_32_bits(addr));
 
-	if (i915_modparams.enable_execlists) {
+	if (HAS_EXECLISTS(dev_priv)) {
 		const u32 *hws = &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
 		u32 ptr, read, write;
 		unsigned int idx;
@@ -1823,6 +1830,114 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *m)
 	drm_printf(m, "\n");
 }
 
+static u8 user_class_map[] = {
+	[I915_ENGINE_CLASS_RENDER] = RENDER_CLASS,
+	[I915_ENGINE_CLASS_COPY] = COPY_ENGINE_CLASS,
+	[I915_ENGINE_CLASS_VIDEO] = VIDEO_DECODE_CLASS,
+	[I915_ENGINE_CLASS_VIDEO_ENHANCE] = VIDEO_ENHANCEMENT_CLASS,
+};
+
+struct intel_engine_cs *
+intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
+{
+	if (class >= ARRAY_SIZE(user_class_map))
+		return NULL;
+
+	class = user_class_map[class];
+
+	GEM_BUG_ON(class > MAX_ENGINE_CLASS);
+
+	if (instance > MAX_ENGINE_INSTANCE)
+		return NULL;
+
+	return i915->engine_class[class][instance];
+}
+
+/**
+ * intel_enable_engine_stats() - Enable engine busy tracking on engine
+ * @engine: engine to enable stats collection
+ *
+ * Start collecting the engine busyness data for @engine.
+ *
+ * Returns 0 on success or a negative error code.
+ */
+int intel_enable_engine_stats(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (!intel_engine_supports_stats(engine))
+		return -ENODEV;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	if (engine->stats.enabled == ~0)
+		goto busy;
+	if (engine->stats.enabled++ == 0)
+		engine->stats.enabled_at = ktime_get();
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return 0;
+
+busy:
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return -EBUSY;
+}
+
+static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)
+{
+	ktime_t total = engine->stats.total;
+
+	/*
+	 * If the engine is executing something at the moment
+	 * add it to the total.
+	 */
+	if (engine->stats.active)
+		total = ktime_add(total,
+				  ktime_sub(ktime_get(), engine->stats.start));
+
+	return total;
+}
+
+/**
+ * intel_engine_get_busy_time() - Return current accumulated engine busyness
+ * @engine: engine to report on
+ *
+ * Returns accumulated time @engine was busy since engine stats were enabled.
+ */
+ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine)
+{
+	ktime_t total;
+	unsigned long flags;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	total = __intel_engine_get_busy_time(engine);
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return total;
+}
+
+/**
+ * intel_disable_engine_stats() - Disable engine busy tracking on engine
+ * @engine: engine to disable stats collection
+ *
+ * Stops collecting the engine busyness data for @engine.
+ */
+void intel_disable_engine_stats(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (!intel_engine_supports_stats(engine))
+		return;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	WARN_ON_ONCE(engine->stats.enabled == 0);
+	if (--engine->stats.enabled == 0) {
+		engine->stats.total = __intel_engine_get_busy_time(engine);
+		engine->stats.active = 0;
+	}
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_engine.c"
 #endif

drivers/gpu/drm/i915/intel_guc.c

@@ -231,8 +231,7 @@ int intel_guc_sample_forcewake(struct intel_guc *guc)
 
 	action[0] = INTEL_GUC_ACTION_SAMPLE_FORCEWAKE;
 	/* WaRsDisableCoarsePowerGating:skl,bxt */
-	if (!intel_rc6_enabled() ||
-	    NEEDS_WaRsDisableCoarsePowerGating(dev_priv))
+	if (!HAS_RC6(dev_priv) || NEEDS_WaRsDisableCoarsePowerGating(dev_priv))
 		action[1] = 0;
 	else
 		/* bit 0 and 1 are for Render and Media domain separately */

drivers/gpu/drm/i915/intel_guc.h

@@ -30,8 +30,8 @@
 #include "intel_guc_fwif.h"
 #include "intel_guc_ct.h"
 #include "intel_guc_log.h"
+#include "intel_guc_reg.h"
 #include "intel_uc_fw.h"
-#include "i915_guc_reg.h"
 #include "i915_vma.h"
 
 struct guc_preempt_work {

drivers/gpu/drm/i915/intel_guc_fw.c

@@ -30,14 +30,14 @@
 #include "intel_guc_fw.h"
 #include "i915_drv.h"
 
-#define SKL_FW_MAJOR 6
-#define SKL_FW_MINOR 1
+#define SKL_FW_MAJOR 9
+#define SKL_FW_MINOR 33
 
-#define BXT_FW_MAJOR 8
-#define BXT_FW_MINOR 7
+#define BXT_FW_MAJOR 9
+#define BXT_FW_MINOR 29
 
 #define KBL_FW_MAJOR 9
-#define KBL_FW_MINOR 14
+#define KBL_FW_MINOR 39
 
 #define GLK_FW_MAJOR 10
 #define GLK_FW_MINOR 56
@@ -130,14 +130,14 @@ static int guc_xfer_rsa(struct intel_guc *guc, struct i915_vma *vma)
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	struct intel_uc_fw *guc_fw = &guc->fw;
 	struct sg_table *sg = vma->pages;
-	u32 rsa[UOS_RSA_SCRATCH_MAX_COUNT];
+	u32 rsa[UOS_RSA_SCRATCH_COUNT];
 	int i;
 
 	if (sg_pcopy_to_buffer(sg->sgl, sg->nents, rsa, sizeof(rsa),
 			       guc_fw->rsa_offset) != sizeof(rsa))
 		return -EINVAL;
 
-	for (i = 0; i < UOS_RSA_SCRATCH_MAX_COUNT; i++)
+	for (i = 0; i < UOS_RSA_SCRATCH_COUNT; i++)
 		I915_WRITE(UOS_RSA_SCRATCH(i), rsa[i]);
 
 	return 0;

drivers/gpu/drm/i915/i915_guc_reg.h → drivers/gpu/drm/i915/intel_guc_reg.h

@@ -21,8 +21,8 @@
  * IN THE SOFTWARE.
  *
  */
-#ifndef _I915_GUC_REG_H_
-#define _I915_GUC_REG_H_
+#ifndef _INTEL_GUC_REG_H_
+#define _INTEL_GUC_REG_H_
 
 /* Definitions of GuC H/W registers, bits, etc */
 
@@ -52,7 +52,8 @@
 #define SOFT_SCRATCH_COUNT		16
 
 #define UOS_RSA_SCRATCH(i)		_MMIO(0xc200 + (i) * 4)
-#define   UOS_RSA_SCRATCH_MAX_COUNT	  64
+#define UOS_RSA_SCRATCH_COUNT		64
+
 #define DMA_ADDR_0_LOW			_MMIO(0xc300)
 #define DMA_ADDR_0_HIGH			_MMIO(0xc304)
 #define DMA_ADDR_1_LOW			_MMIO(0xc308)

drivers/gpu/drm/i915/intel_guc_submission.h

@@ -22,8 +22,8 @@
  *
  */
 
-#ifndef _I915_GUC_SUBMISSION_H_
-#define _I915_GUC_SUBMISSION_H_
+#ifndef _INTEL_GUC_SUBMISSION_H_
+#define _INTEL_GUC_SUBMISSION_H_
 
 #include <linux/spinlock.h>