Merge tag 'drm-intel-next-2015-02-14' of git://anongit.freedesktop.org/drm-intel into drm-next

- use the atomic helpers for plane_upate/disable hooks (Matt Roper)
- refactor the initial plane config code (Damien)
- ppgtt prep patches for dynamic pagetable alloc (Ben Widawsky, reworked and
  rebased by a lot of other people)
- framebuffer modifier support from Tvrtko Ursulin, drm core code from Rob Clark
- piles of workaround patches for skl from Damien and Nick Hoath
- vGPU support for xengt on the client side (Yu Zhang)
- and the usual smaller things all over

* tag 'drm-intel-next-2015-02-14' of git://anongit.freedesktop.org/drm-intel: (88 commits)
  drm/i915: Update DRIVER_DATE to 20150214
  drm/i915: Remove references to previously removed UMS config option
  drm/i915/skl: Use a LRI for WaDisableDgMirrorFixInHalfSliceChicken5
  drm/i915/skl: Fix always true comparison in a revision id check
  drm/i915/skl: Implement WaEnableLbsSlaRetryTimerDecrement
  drm/i915/skl: Implement WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken
  drm/i915: Add process identifier to requests
  drm/i915/skl: Implement WaBarrierPerformanceFixDisable
  drm/i915/skl: Implement WaCcsTlbPrefetchDisable:skl
  drm/i915/skl: Implement WaDisableChickenBitTSGBarrierAckForFFSliceCS
  drm/i915/skl: Implement WaDisableHDCInvalidation
  drm/i915/skl: Implement WaDisableLSQCROPERFforOCL
  drm/i915/skl: Implement WaDisablePartialResolveInVc
  drm/i915/skl: Introduce a SKL specific init_workarounds()
  drm/i915/skl: Document that we implement WaRsClearFWBitsAtReset
  drm/i915/skl: Implement WaSetGAPSunitClckGateDisable
  drm/i915/skl: Make the init clock gating function skylake specific
  drm/i915/skl: Provide a gen9 specific init_render_ring()
  drm/i915/skl: Document the WM read latency W/A with its name
  drm/i915/skl: Also detect eDRAM on SKL
  ...

Documentation/DocBook/drm.tmpl

@@ -3979,6 +3979,11 @@ int num_ioctls;</synopsis>
 !Fdrivers/gpu/drm/i915/i915_irq.c intel_runtime_pm_disable_interrupts
 !Fdrivers/gpu/drm/i915/i915_irq.c intel_runtime_pm_enable_interrupts
       </sect2>
+      <sect2>
+        <title>Intel GVT-g Guest Support(vGPU)</title>
+!Pdrivers/gpu/drm/i915/i915_vgpu.c Intel GVT-g guest support
+!Idrivers/gpu/drm/i915/i915_vgpu.c
+      </sect2>
     </sect1>
     <sect1>
       <title>Display Hardware Handling</title>

drivers/gpu/drm/drm_crtc.c

@@ -3272,6 +3272,12 @@ static int framebuffer_check(const struct drm_mode_fb_cmd2 *r)
 			DRM_DEBUG_KMS("bad pitch %u for plane %d\n", r->pitches[i], i);
 			return -EINVAL;
 		}
+
+		if (r->modifier[i] && !(r->flags & DRM_MODE_FB_MODIFIERS)) {
+			DRM_DEBUG_KMS("bad fb modifier %llu for plane %d\n",
+				      r->modifier[i], i);
+			return -EINVAL;
+		}
 	}
 
 	return 0;
@@ -3285,7 +3291,7 @@ static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
 	struct drm_framebuffer *fb;
 	int ret;
 
-	if (r->flags & ~DRM_MODE_FB_INTERLACED) {
+	if (r->flags & ~(DRM_MODE_FB_INTERLACED | DRM_MODE_FB_MODIFIERS)) {
 		DRM_DEBUG_KMS("bad framebuffer flags 0x%08x\n", r->flags);
 		return ERR_PTR(-EINVAL);
 	}
@@ -3301,6 +3307,12 @@ static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (r->flags & DRM_MODE_FB_MODIFIERS &&
+	    !dev->mode_config.allow_fb_modifiers) {
+		DRM_DEBUG_KMS("driver does not support fb modifiers\n");
+		return ERR_PTR(-EINVAL);
+	}
+
 	ret = framebuffer_check(r);
 	if (ret)
 		return ERR_PTR(ret);

drivers/gpu/drm/drm_crtc_helper.c

@@ -837,6 +837,7 @@ void drm_helper_mode_fill_fb_struct(struct drm_framebuffer *fb,
 	for (i = 0; i < 4; i++) {
 		fb->pitches[i] = mode_cmd->pitches[i];
 		fb->offsets[i] = mode_cmd->offsets[i];
+		fb->modifier[i] = mode_cmd->modifier[i];
 	}
 	drm_fb_get_bpp_depth(mode_cmd->pixel_format, &fb->depth,
 				    &fb->bits_per_pixel);

drivers/gpu/drm/drm_ioctl.c

@@ -321,6 +321,9 @@ static int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_
 		else
 			req->value = 64;
 		break;
+	case DRM_CAP_ADDFB2_MODIFIERS:
+		req->value = dev->mode_config.allow_fb_modifiers;
+		break;
 	default:
 		return -EINVAL;
 	}

drivers/gpu/drm/i915/Makefile

@@ -83,6 +83,9 @@ i915-y += dvo_ch7017.o \
 	  intel_sdvo.o \
 	  intel_tv.o
 
+# virtual gpu code
+i915-y += i915_vgpu.o
+
 # legacy horrors
 i915-y += i915_dma.o \
 	  i915_ums.o

drivers/gpu/drm/i915/i915_debugfs.c

@@ -1778,11 +1778,12 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 	ifbdev = dev_priv->fbdev;
 	fb = to_intel_framebuffer(ifbdev->helper.fb);
 
-	seq_printf(m, "fbcon size: %d x %d, depth %d, %d bpp, refcount %d, obj ",
+	seq_printf(m, "fbcon size: %d x %d, depth %d, %d bpp, modifier 0x%llx, refcount %d, obj ",
 		   fb->base.width,
 		   fb->base.height,
 		   fb->base.depth,
 		   fb->base.bits_per_pixel,
+		   fb->base.modifier[0],
 		   atomic_read(&fb->base.refcount.refcount));
 	describe_obj(m, fb->obj);
 	seq_putc(m, '\n');
@@ -1793,11 +1794,12 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 		if (ifbdev && &fb->base == ifbdev->helper.fb)
 			continue;
 
-		seq_printf(m, "user size: %d x %d, depth %d, %d bpp, refcount %d, obj ",
+		seq_printf(m, "user size: %d x %d, depth %d, %d bpp, modifier 0x%llx, refcount %d, obj ",
 			   fb->base.width,
 			   fb->base.height,
 			   fb->base.depth,
 			   fb->base.bits_per_pixel,
+			   fb->base.modifier[0],
 			   atomic_read(&fb->base.refcount.refcount));
 		describe_obj(m, fb->obj);
 		seq_putc(m, '\n');
@@ -4226,10 +4228,7 @@ i915_max_freq_set(void *data, u64 val)
 
 	dev_priv->rps.max_freq_softlimit = val;
 
-	if (IS_VALLEYVIEW(dev))
-		valleyview_set_rps(dev, val);
-	else
-		gen6_set_rps(dev, val);
+	intel_set_rps(dev, val);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
@@ -4304,10 +4303,7 @@ i915_min_freq_set(void *data, u64 val)
 
 	dev_priv->rps.min_freq_softlimit = val;
 
-	if (IS_VALLEYVIEW(dev))
-		valleyview_set_rps(dev, val);
-	else
-		gen6_set_rps(dev, val);
+	intel_set_rps(dev, val);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 

drivers/gpu/drm/i915/i915_dma.c

@@ -36,6 +36,7 @@
 #include "intel_drv.h"
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
+#include "i915_vgpu.h"
 #include "i915_trace.h"
 #include <linux/pci.h>
 #include <linux/console.h>
@@ -842,6 +843,13 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		}
 	}
 
+	/*
+	 * Notify a valid surface after modesetting,
+	 * when running inside a VM.
+	 */
+	if (intel_vgpu_active(dev))
+		I915_WRITE(vgtif_reg(display_ready), VGT_DRV_DISPLAY_READY);
+
 	i915_setup_sysfs(dev);
 
 	if (INTEL_INFO(dev)->num_pipes) {

drivers/gpu/drm/i915/i915_drv.c

@@ -369,6 +369,19 @@ static const struct intel_device_info intel_skylake_info = {
 	IVB_CURSOR_OFFSETS,
 };
 
+static const struct intel_device_info intel_skylake_gt3_info = {
+	.is_preliminary = 1,
+	.is_skylake = 1,
+	.gen = 9, .num_pipes = 3,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
+	.has_llc = 1,
+	.has_ddi = 1,
+	.has_fbc = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
+};
+
 /*
  * Make sure any device matches here are from most specific to most
  * general.  For example, since the Quanta match is based on the subsystem
@@ -406,7 +419,9 @@ static const struct intel_device_info intel_skylake_info = {
 	INTEL_BDW_GT3M_IDS(&intel_broadwell_gt3m_info),	\
 	INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info), \
 	INTEL_CHV_IDS(&intel_cherryview_info),	\
-	INTEL_SKL_IDS(&intel_skylake_info)
+	INTEL_SKL_GT1_IDS(&intel_skylake_info),	\
+	INTEL_SKL_GT2_IDS(&intel_skylake_info),	\
+	INTEL_SKL_GT3_IDS(&intel_skylake_gt3_info)	\
 
 static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_PCI_IDS,
@@ -1630,11 +1645,9 @@ static int __init i915_init(void)
 
 	if (!(driver.driver_features & DRIVER_MODESET)) {
 		driver.get_vblank_timestamp = NULL;
-#ifndef CONFIG_DRM_I915_UMS
 		/* Silently fail loading to not upset userspace. */
 		DRM_DEBUG_DRIVER("KMS and UMS disabled.\n");
 		return 0;
-#endif
 	}
 
 	/*
@@ -1650,10 +1663,8 @@ static int __init i915_init(void)
 
 static void __exit i915_exit(void)
 {
-#ifndef CONFIG_DRM_I915_UMS
 	if (!(driver.driver_features & DRIVER_MODESET))
 		return; /* Never loaded a driver. */
-#endif
 
 	drm_pci_exit(&driver, &i915_pci_driver);
 }

drivers/gpu/drm/i915/i915_drv.h

@@ -31,6 +31,7 @@
 #define _I915_DRV_H_
 
 #include <uapi/drm/i915_drm.h>
+#include <uapi/drm/drm_fourcc.h>
 
 #include "i915_reg.h"
 #include "intel_bios.h"
@@ -55,7 +56,7 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20150130"
+#define DRIVER_DATE		"20150214"
 
 #undef WARN_ON
 /* Many gcc seem to no see through this and fall over :( */
@@ -772,10 +773,10 @@ struct intel_context {
 };
 
 struct i915_fbc {
-	unsigned long size;
+	unsigned long uncompressed_size;
 	unsigned threshold;
 	unsigned int fb_id;
-	enum plane plane;
+	struct intel_crtc *crtc;
 	int y;
 
 	struct drm_mm_node compressed_fb;
@@ -1640,6 +1641,10 @@ struct i915_workarounds {
 	u32 count;
 };
 
+struct i915_virtual_gpu {
+	bool active;
+};
+
 struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
@@ -1652,6 +1657,8 @@ struct drm_i915_private {
 
 	struct intel_uncore uncore;
 
+	struct i915_virtual_gpu vgpu;
+
 	struct intel_gmbus gmbus[GMBUS_NUM_PORTS];
 
 
@@ -2153,6 +2160,9 @@ struct drm_i915_gem_request {
 	/** file_priv list entry for this request */
 	struct list_head client_list;
 
+	/** process identifier submitting this request */
+	struct pid *pid;
+
 	uint32_t uniq;
 
 	/**
@@ -2339,6 +2349,7 @@ struct drm_i915_cmd_table {
 })
 #define INTEL_INFO(p) 	(&__I915__(p)->info)
 #define INTEL_DEVID(p)	(INTEL_INFO(p)->device_id)
+#define INTEL_REVID(p)	(__I915__(p)->dev->pdev->revision)
 
 #define IS_I830(dev)		(INTEL_DEVID(dev) == 0x3577)
 #define IS_845G(dev)		(INTEL_DEVID(dev) == 0x2562)
@@ -2361,9 +2372,6 @@ struct drm_i915_cmd_table {
 #define IS_IVB_GT1(dev)		(INTEL_DEVID(dev) == 0x0156 || \
 				 INTEL_DEVID(dev) == 0x0152 || \
 				 INTEL_DEVID(dev) == 0x015a)
-#define IS_SNB_GT1(dev)		(INTEL_DEVID(dev) == 0x0102 || \
-				 INTEL_DEVID(dev) == 0x0106 || \
-				 INTEL_DEVID(dev) == 0x010A)
 #define IS_VALLEYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview)
 #define IS_CHERRYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview && IS_GEN8(dev))
 #define IS_HASWELL(dev)	(INTEL_INFO(dev)->is_haswell)
@@ -2386,6 +2394,12 @@ struct drm_i915_cmd_table {
 				 INTEL_DEVID(dev) == 0x0A1E)
 #define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary)
 
+#define SKL_REVID_A0		(0x0)
+#define SKL_REVID_B0		(0x1)
+#define SKL_REVID_C0		(0x2)
+#define SKL_REVID_D0		(0x3)
+#define SKL_REVID_E0		(0x4)
+
 /*
  * The genX designation typically refers to the render engine, so render
  * capability related checks should use IS_GEN, while display and other checks
@@ -2493,8 +2507,6 @@ extern int i915_max_ioctl;
 
 extern int i915_suspend_legacy(struct drm_device *dev, pm_message_t state);
 extern int i915_resume_legacy(struct drm_device *dev);
-extern int i915_master_create(struct drm_device *dev, struct drm_master *master);
-extern void i915_master_destroy(struct drm_device *dev, struct drm_master *master);
 
 /* i915_params.c */
 struct i915_params {
@@ -2577,6 +2589,10 @@ void intel_uncore_forcewake_get(struct drm_i915_private *dev_priv,
 void intel_uncore_forcewake_put(struct drm_i915_private *dev_priv,
 				enum forcewake_domains domains);
 void assert_forcewakes_inactive(struct drm_i915_private *dev_priv);
+static inline bool intel_vgpu_active(struct drm_device *dev)
+{
+	return to_i915(dev)->vgpu.active;
+}
 
 void
 i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
@@ -3182,8 +3198,7 @@ extern void i915_redisable_vga(struct drm_device *dev);
 extern void i915_redisable_vga_power_on(struct drm_device *dev);
 extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
 extern void intel_init_pch_refclk(struct drm_device *dev);
-extern void gen6_set_rps(struct drm_device *dev, u8 val);
-extern void valleyview_set_rps(struct drm_device *dev, u8 val);
+extern void intel_set_rps(struct drm_device *dev, u8 val);
 extern void intel_set_memory_cxsr(struct drm_i915_private *dev_priv,
 				  bool enable);
 extern void intel_detect_pch(struct drm_device *dev);
@@ -3196,8 +3211,6 @@ int i915_reg_read_ioctl(struct drm_device *dev, void *data,
 int i915_get_reset_stats_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file);
 
-void intel_notify_mmio_flip(struct intel_engine_cs *ring);
-
 /* overlay */
 extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
 extern void intel_overlay_print_error_state(struct drm_i915_error_state_buf *e,

drivers/gpu/drm/i915/i915_gem.c

@@ -29,6 +29,7 @@
 #include <drm/drm_vma_manager.h>
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
+#include "i915_vgpu.h"
 #include "i915_trace.h"
 #include "intel_drv.h"
 #include <linux/oom.h>
@@ -2492,6 +2493,8 @@ int __i915_add_request(struct intel_engine_cs *ring,
 		list_add_tail(&request->client_list,
 			      &file_priv->mm.request_list);
 		spin_unlock(&file_priv->mm.lock);
+
+		request->pid = get_pid(task_pid(current));
 	}
 
 	trace_i915_gem_request_add(request);
@@ -2572,6 +2575,8 @@ static void i915_gem_free_request(struct drm_i915_gem_request *request)
 	list_del(&request->list);
 	i915_gem_request_remove_from_client(request);
 
+	put_pid(request->pid);
+
 	i915_gem_request_unreference(request);
 }
 
@@ -4987,6 +4992,10 @@ i915_gem_load(struct drm_device *dev)
 	else
 		dev_priv->num_fence_regs = 8;
 
+	if (intel_vgpu_active(dev))
+		dev_priv->num_fence_regs =
+				I915_READ(vgtif_reg(avail_rs.fence_num));
+
 	/* Initialize fence registers to zero */
 	INIT_LIST_HEAD(&dev_priv->mm.fence_list);
 	i915_gem_restore_fences(dev);

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -27,6 +27,7 @@
 #include <drm/drmP.h>
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
+#include "i915_vgpu.h"
 #include "i915_trace.h"
 #include "intel_drv.h"
 
@@ -103,6 +104,9 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
 	has_aliasing_ppgtt = INTEL_INFO(dev)->gen >= 6;
 	has_full_ppgtt = INTEL_INFO(dev)->gen >= 7;
 
+	if (intel_vgpu_active(dev))
+		has_full_ppgtt = false; /* emulation is too hard */
+
 	/*
 	 * We don't allow disabling PPGTT for gen9+ as it's a requirement for
 	 * execlists, the sole mechanism available to submit work.
@@ -375,7 +379,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 	pt_vaddr = NULL;
 
 	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
-		if (WARN_ON(pdpe >= GEN8_LEGACY_PDPS))
+		if (WARN_ON(pdpe >= GEN8_LEGACY_PDPES))
 			break;
 
 		if (pt_vaddr == NULL)
@@ -486,7 +490,7 @@ bail:
 static int gen8_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt,
 					   const int max_pdp)
 {
-	struct page **pt_pages[GEN8_LEGACY_PDPS];
+	struct page **pt_pages[GEN8_LEGACY_PDPES];
 	int i, ret;
 
 	for (i = 0; i < max_pdp; i++) {
@@ -537,7 +541,7 @@ static int gen8_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt,
 		return -ENOMEM;
 
 	ppgtt->num_pd_pages = 1 << get_order(max_pdp << PAGE_SHIFT);
-	BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPS);
+	BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPES);
 
 	return 0;
 }
@@ -797,6 +801,16 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
 	return 0;
 }
 
+static int vgpu_mm_switch(struct i915_hw_ppgtt *ppgtt,
+			  struct intel_engine_cs *ring)
+{
+	struct drm_i915_private *dev_priv = to_i915(ppgtt->base.dev);
+
+	I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
+	I915_WRITE(RING_PP_DIR_BASE(ring), get_pd_offset(ppgtt));
+	return 0;
+}
+
 static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
 			  struct intel_engine_cs *ring)
 {
@@ -1032,11 +1046,14 @@ alloc:
 		goto alloc;
 	}
 
+	if (ret)
+		return ret;
+
 	if (ppgtt->node.start < dev_priv->gtt.mappable_end)
 		DRM_DEBUG("Forced to use aperture for PDEs\n");
 
 	ppgtt->num_pd_entries = GEN6_PPGTT_PD_ENTRIES;
-	return ret;
+	return 0;
 }
 
 static int gen6_ppgtt_allocate_page_tables(struct i915_hw_ppgtt *ppgtt)
@@ -1123,6 +1140,9 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	} else
 		BUG();
 
+	if (intel_vgpu_active(dev))
+		ppgtt->switch_mm = vgpu_mm_switch;
+
 	ret = gen6_ppgtt_alloc(ppgtt);
 	if (ret)
 		return ret;
@@ -1753,6 +1773,16 @@ static int i915_gem_setup_global_gtt(struct drm_device *dev,
 
 	/* Subtract the guard page ... */
 	drm_mm_init(&ggtt_vm->mm, start, end - start - PAGE_SIZE);
+
+	dev_priv->gtt.base.start = start;
+	dev_priv->gtt.base.total = end - start;
+
+	if (intel_vgpu_active(dev)) {
+		ret = intel_vgt_balloon(dev);
+		if (ret)
+			return ret;
+	}
+
 	if (!HAS_LLC(dev))
 		dev_priv->gtt.base.mm.color_adjust = i915_gtt_color_adjust;
 
@@ -1772,9 +1802,6 @@ static int i915_gem_setup_global_gtt(struct drm_device *dev,
 		vma->bound |= GLOBAL_BIND;
 	}
 
-	dev_priv->gtt.base.start = start;
-	dev_priv->gtt.base.total = end - start;
-
 	/* Clear any non-preallocated blocks */
 	drm_mm_for_each_hole(entry, &ggtt_vm->mm, hole_start, hole_end) {
 		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
@@ -1826,6 +1853,9 @@ void i915_global_gtt_cleanup(struct drm_device *dev)
 	}
 
 	if (drm_mm_initialized(&vm->mm)) {
+		if (intel_vgpu_active(dev))
+			intel_vgt_deballoon();
+
 		drm_mm_takedown(&vm->mm);
 		list_del(&vm->global_link);
 	}

drivers/gpu/drm/i915/i915_gem_gtt.h

@@ -88,7 +88,7 @@ typedef gen8_gtt_pte_t gen8_ppgtt_pde_t;
 #define GEN8_PDE_MASK			0x1ff
 #define GEN8_PTE_SHIFT			12
 #define GEN8_PTE_MASK			0x1ff
-#define GEN8_LEGACY_PDPS		4
+#define GEN8_LEGACY_PDPES		4
 #define GEN8_PTES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_gtt_pte_t))
 #define GEN8_PDES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_ppgtt_pde_t))
 
@@ -273,16 +273,16 @@ struct i915_hw_ppgtt {
 	unsigned num_pd_pages; /* gen8+ */
 	union {
 		struct page **pt_pages;
-		struct page **gen8_pt_pages[GEN8_LEGACY_PDPS];
+		struct page **gen8_pt_pages[GEN8_LEGACY_PDPES];
 	};
 	struct page *pd_pages;
 	union {
 		uint32_t pd_offset;
-		dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPS];
+		dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPES];
 	};
 	union {
 		dma_addr_t *pt_dma_addr;
-		dma_addr_t *gen8_pt_dma_addr[4];
+		dma_addr_t *gen8_pt_dma_addr[GEN8_LEGACY_PDPES];
 	};
 
 	struct drm_i915_file_private *file_priv;

drivers/gpu/drm/i915/i915_gem_stolen.c

@@ -231,7 +231,7 @@ static int i915_setup_compression(struct drm_device *dev, int size, int fb_cpp)
 			   dev_priv->mm.stolen_base + compressed_llb->start);
 	}
 
-	dev_priv->fbc.size = size / dev_priv->fbc.threshold;
+	dev_priv->fbc.uncompressed_size = size;
 
 	DRM_DEBUG_KMS("reserved %d bytes of contiguous stolen space for FBC\n",
 		      size);
@@ -253,7 +253,7 @@ int i915_gem_stolen_setup_compression(struct drm_device *dev, int size, int fb_c
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return -ENODEV;
 
-	if (size < dev_priv->fbc.size)
+	if (size < dev_priv->fbc.uncompressed_size)
 		return 0;
 
 	/* Release any current block */
@@ -266,7 +266,7 @@ void i915_gem_stolen_cleanup_compression(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (dev_priv->fbc.size == 0)
+	if (dev_priv->fbc.uncompressed_size == 0)
 		return;
 
 	drm_mm_remove_node(&dev_priv->fbc.compressed_fb);
@@ -276,7 +276,7 @@ void i915_gem_stolen_cleanup_compression(struct drm_device *dev)
 		kfree(dev_priv->fbc.compressed_llb);
 	}
 
-	dev_priv->fbc.size = 0;
+	dev_priv->fbc.uncompressed_size = 0;
 }
 
 void i915_gem_cleanup_stolen(struct drm_device *dev)

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -994,12 +994,11 @@ static void i915_gem_record_rings(struct drm_device *dev,
 					i915_error_ggtt_object_create(dev_priv,
 							     ring->scratch.obj);
 
-			if (request->file_priv) {
+			if (request->pid) {
 				struct task_struct *task;
 
 				rcu_read_lock();
-				task = pid_task(request->file_priv->file->pid,
-						PIDTYPE_PID);
+				task = pid_task(request->pid, PIDTYPE_PID);
 				if (task) {
 					strcpy(error->ring[i].comm, task->comm);
 					error->ring[i].pid = task->pid;

drivers/gpu/drm/i915/i915_irq.c

@@ -1243,10 +1243,7 @@ static void gen6_pm_rps_work(struct work_struct *work)
 
 	dev_priv->rps.last_adj = new_delay - dev_priv->rps.cur_freq;
 
-	if (IS_VALLEYVIEW(dev_priv->dev))
-		valleyview_set_rps(dev_priv->dev, new_delay);
-	else
-		gen6_set_rps(dev_priv->dev, new_delay);
+	intel_set_rps(dev_priv->dev, new_delay);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }

drivers/gpu/drm/i915/i915_reg.h

@@ -140,6 +140,7 @@
 #define GEN8_RING_PDP_LDW(ring, n)	((ring)->mmio_base+0x270 + (n) * 8)
 
 #define GAM_ECOCHK			0x4090
+#define   BDW_DISABLE_HDC_INVALIDATION	(1<<25)
 #define   ECOCHK_SNB_BIT		(1<<10)
 #define   HSW_ECOCHK_ARB_PRIO_SOL	(1<<6)
 #define   ECOCHK_PPGTT_CACHE64B		(0x3<<3)
@@ -586,6 +587,19 @@ enum punit_power_well {
 	PUNIT_POWER_WELL_NUM,
 };
 
+enum skl_disp_power_wells {
+	SKL_DISP_PW_MISC_IO,
+	SKL_DISP_PW_DDI_A_E,
+	SKL_DISP_PW_DDI_B,
+	SKL_DISP_PW_DDI_C,
+	SKL_DISP_PW_DDI_D,
+	SKL_DISP_PW_1 = 14,
+	SKL_DISP_PW_2,
+};
+
+#define SKL_POWER_WELL_STATE(pw) (1 << ((pw) * 2))
+#define SKL_POWER_WELL_REQ(pw) (1 << (((pw) * 2) + 1))
+
 #define PUNIT_REG_PWRGT_CTRL			0x60
 #define PUNIT_REG_PWRGT_STATUS			0x61
 #define   PUNIT_PWRGT_MASK(power_well)		(3 << ((power_well) * 2))
@@ -1470,6 +1484,7 @@ enum punit_power_well {
 #define CACHE_MODE_1		0x7004 /* IVB+ */
 #define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE	(1<<6)
 #define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	(1<<6)
+#define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	(1<<1)
 
 #define GEN6_BLITTER_ECOSKPD	0x221d0
 #define   GEN6_BLITTER_LOCK_SHIFT			16
@@ -5221,15 +5236,22 @@ enum punit_power_well {
 #define HSW_NDE_RSTWRN_OPT	0x46408
 #define  RESET_PCH_HANDSHAKE_ENABLE	(1<<4)
 
+#define FF_SLICE_CS_CHICKEN2			0x02e4
+#define  GEN9_TSG_BARRIER_ACK_DISABLE		(1<<8)
+
 /* GEN7 chicken */
 #define GEN7_COMMON_SLICE_CHICKEN1		0x7010
 # define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1<<10) | (1<<26))
+# define GEN9_RHWO_OPTIMIZATION_DISABLE		(1<<14)
 #define COMMON_SLICE_CHICKEN2			0x7014
 # define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE	(1<<0)
 
 #define HIZ_CHICKEN				0x7018
 # define CHV_HZ_8X8_MODE_IN_1X			(1<<15)
 
+#define GEN9_SLICE_COMMON_ECO_CHICKEN0		0x7308
+#define  DISABLE_PIXEL_MASK_CAMMING		(1<<14)
+
 #define GEN7_L3SQCREG1				0xB010
 #define  VLV_B0_WA_L3SQCREG1_VALUE		0x00D30000
 
@@ -5245,11 +5267,16 @@ enum punit_power_well {
 #define GEN7_L3SQCREG4				0xb034
 #define  L3SQ_URB_READ_CAM_MATCH_DISABLE	(1<<27)
 
+#define GEN8_L3SQCREG4				0xb118
+#define  GEN8_LQSC_RO_PERF_DIS			(1<<27)
+
 /* GEN8 chicken */
 #define HDC_CHICKEN0				0x7300
-#define  HDC_FORCE_NON_COHERENT			(1<<4)
-#define  HDC_DONOT_FETCH_MEM_WHEN_MASKED	(1<<11)
 #define  HDC_FENCE_DEST_SLM_DISABLE		(1<<14)
+#define  HDC_DONOT_FETCH_MEM_WHEN_MASKED	(1<<11)
+#define  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT	(1<<5)
+#define  HDC_FORCE_NON_COHERENT			(1<<4)
+#define  HDC_BARRIER_PERFORMANCE_DISABLE	(1<<10)
 
 /* WaCatErrorRejectionIssue */
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		0x9030
@@ -5258,6 +5285,9 @@ enum punit_power_well {
 #define HSW_SCRATCH1				0xb038
 #define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1<<27)
 
+#define BDW_SCRATCH1					0xb11c
+#define  GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE	(1<<2)
+
 /* PCH */
 
 /* south display engine interrupt: IBX */
@@ -5980,6 +6010,7 @@ enum punit_power_well {
 #define  HSW_IDICR				0x9008
 #define    IDIHASHMSK(x)			(((x) & 0x3f) << 16)
 #define  HSW_EDRAM_PRESENT			0x120010
+#define    EDRAM_ENABLED			0x1
 
 #define GEN6_UCGCTL1				0x9400
 # define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE		(1 << 16)
@@ -6003,6 +6034,7 @@ enum punit_power_well {
 #define GEN6_RSTCTL				0x9420
 
 #define GEN8_UCGCTL6				0x9430
+#define   GEN8_GAPSUNIT_CLOCK_GATE_DISABLE	(1<<24)
 #define   GEN8_SDEUNIT_CLOCK_GATE_DISABLE	(1<<14)
 
 #define GEN6_GFXPAUSE				0xA000
@@ -6185,6 +6217,7 @@ enum punit_power_well {
 
 #define GEN9_HALF_SLICE_CHICKEN5	0xe188
 #define   GEN9_DG_MIRROR_FIX_ENABLE	(1<<5)
+#define   GEN9_CCS_TLB_PREFETCH_ENABLE	(1<<3)
 
 #define GEN8_ROW_CHICKEN		0xe4f0
 #define   PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE	(1<<8)
@@ -6200,8 +6233,12 @@ enum punit_power_well {
 #define HALF_SLICE_CHICKEN3		0xe184
 #define   HSW_SAMPLE_C_PERFORMANCE	(1<<9)
 #define   GEN8_CENTROID_PIXEL_OPT_DIS	(1<<8)
+#define   GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC	(1<<5)
 #define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1<<1)
 
+#define GEN9_HALF_SLICE_CHICKEN7	0xe194
+#define   GEN9_ENABLE_YV12_BUGFIX	(1<<4)
+
 /* Audio */
 #define G4X_AUD_VID_DID			(dev_priv->info.display_mmio_offset + 0x62020)
 #define   INTEL_AUDIO_DEVCL		0x808629FB
@@ -6351,6 +6388,13 @@ enum punit_power_well {
 #define   HSW_PWR_WELL_FORCE_ON			(1<<19)
 #define HSW_PWR_WELL_CTL6			0x45414
 
+/* SKL Fuse Status */
+#define SKL_FUSE_STATUS				0x42000
+#define  SKL_FUSE_DOWNLOAD_STATUS              (1<<31)
+#define  SKL_FUSE_PG0_DIST_STATUS              (1<<27)
+#define  SKL_FUSE_PG1_DIST_STATUS              (1<<26)
+#define  SKL_FUSE_PG2_DIST_STATUS              (1<<25)
+
 /* Per-pipe DDI Function Control */
 #define TRANS_DDI_FUNC_CTL_A		0x60400
 #define TRANS_DDI_FUNC_CTL_B		0x61400

drivers/gpu/drm/i915/i915_sysfs.c

@@ -402,10 +402,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 	/* We still need *_set_rps to process the new max_delay and
 	 * update the interrupt limits and PMINTRMSK even though
 	 * frequency request may be unchanged. */
-	if (IS_VALLEYVIEW(dev))
-		valleyview_set_rps(dev, val);
-	else
-		gen6_set_rps(dev, val);
+	intel_set_rps(dev, val);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
@@ -464,10 +461,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 	/* We still need *_set_rps to process the new min_delay and
 	 * update the interrupt limits and PMINTRMSK even though
 	 * frequency request may be unchanged. */
-	if (IS_VALLEYVIEW(dev))
-		valleyview_set_rps(dev, val);
-	else
-		gen6_set_rps(dev, val);
+	intel_set_rps(dev, val);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 

drivers/gpu/drm/i915/i915_trace.h

@@ -115,7 +115,7 @@ TRACE_EVENT(i915_vma_bind,
 	    TP_STRUCT__entry(
 			     __field(struct drm_i915_gem_object *, obj)
 			     __field(struct i915_address_space *, vm)
-			     __field(u32, offset)
+			     __field(u64, offset)
 			     __field(u32, size)
 			     __field(unsigned, flags)
 			     ),
@@ -128,7 +128,7 @@ TRACE_EVENT(i915_vma_bind,
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("obj=%p, offset=%08x size=%x%s vm=%p",
+	    TP_printk("obj=%p, offset=%016llx size=%x%s vm=%p",
 		      __entry->obj, __entry->offset, __entry->size,
 		      __entry->flags & PIN_MAPPABLE ? ", mappable" : "",
 		      __entry->vm)
@@ -141,7 +141,7 @@ TRACE_EVENT(i915_vma_unbind,
 	    TP_STRUCT__entry(
 			     __field(struct drm_i915_gem_object *, obj)
 			     __field(struct i915_address_space *, vm)
-			     __field(u32, offset)
+			     __field(u64, offset)
 			     __field(u32, size)
 			     ),
 
@@ -152,7 +152,7 @@ TRACE_EVENT(i915_vma_unbind,
 			   __entry->size = vma->node.size;
 			   ),
 
-	    TP_printk("obj=%p, offset=%08x size=%x vm=%p",
+	    TP_printk("obj=%p, offset=%016llx size=%x vm=%p",
 		      __entry->obj, __entry->offset, __entry->size, __entry->vm)
 );
 

drivers/gpu/drm/i915/i915_vgpu.c

@@ -0,0 +1,264 @@
+/*
+ * Copyright(c) 2011-2015 Intel Corporation. All rights reserved.
+ *
+ * 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.
+ */
+
+#include "intel_drv.h"
+#include "i915_vgpu.h"
+
+/**
+ * DOC: Intel GVT-g guest support
+ *
+ * Intel GVT-g is a graphics virtualization technology which shares the
+ * GPU among multiple virtual machines on a time-sharing basis. Each
+ * virtual machine is presented a virtual GPU (vGPU), which has equivalent
+ * features as the underlying physical GPU (pGPU), so i915 driver can run
+ * seamlessly in a virtual machine. This file provides vGPU specific
+ * optimizations when running in a virtual machine, to reduce the complexity
+ * of vGPU emulation and to improve the overall performance.
+ *
+ * A primary function introduced here is so-called "address space ballooning"
+ * technique. Intel GVT-g partitions global graphics memory among multiple VMs,
+ * so each VM can directly access a portion of the memory without hypervisor's
+ * intervention, e.g. filling textures or queuing commands. However with the
+ * partitioning an unmodified i915 driver would assume a smaller graphics
+ * memory starting from address ZERO, then requires vGPU emulation module to
+ * translate the graphics address between 'guest view' and 'host view', for
+ * all registers and command opcodes which contain a graphics memory address.
+ * To reduce the complexity, Intel GVT-g introduces "address space ballooning",
+ * by telling the exact partitioning knowledge to each guest i915 driver, which
+ * then reserves and prevents non-allocated portions from allocation. Thus vGPU
+ * emulation module only needs to scan and validate graphics addresses without
+ * complexity of address translation.
+ *
+ */
+
+/**
+ * i915_check_vgpu - detect virtual GPU
+ * @dev: drm device *
+ *
+ * This function is called at the initialization stage, to detect whether
+ * running on a vGPU.
+ */
+void i915_check_vgpu(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	uint64_t magic;
+	uint32_t version;
+
+	BUILD_BUG_ON(sizeof(struct vgt_if) != VGT_PVINFO_SIZE);
+
+	if (!IS_HASWELL(dev))
+		return;
+
+	magic = readq(dev_priv->regs + vgtif_reg(magic));
+	if (magic != VGT_MAGIC)
+		return;
+
+	version = INTEL_VGT_IF_VERSION_ENCODE(
+		readw(dev_priv->regs + vgtif_reg(version_major)),
+		readw(dev_priv->regs + vgtif_reg(version_minor)));
+	if (version != INTEL_VGT_IF_VERSION) {
+		DRM_INFO("VGT interface version mismatch!\n");
+		return;
+	}
+
+	dev_priv->vgpu.active = true;
+	DRM_INFO("Virtual GPU for Intel GVT-g detected.\n");
+}
+
+struct _balloon_info_ {
+	/*
+	 * There are up to 2 regions per mappable/unmappable graphic
+	 * memory that might be ballooned. Here, index 0/1 is for mappable
+	 * graphic memory, 2/3 for unmappable graphic memory.
+	 */
+	struct drm_mm_node space[4];
+};
+
+static struct _balloon_info_ bl_info;
+
+/**
+ * intel_vgt_deballoon - deballoon reserved graphics address trunks
+ *
+ * This function is called to deallocate the ballooned-out graphic memory, when
+ * driver is unloaded or when ballooning fails.
+ */
+void intel_vgt_deballoon(void)
+{
+	int i;
+
+	DRM_DEBUG("VGT deballoon.\n");
+
+	for (i = 0; i < 4; i++) {
+		if (bl_info.space[i].allocated)
+			drm_mm_remove_node(&bl_info.space[i]);
+	}
+
+	memset(&bl_info, 0, sizeof(bl_info));
+}
+
+static int vgt_balloon_space(struct drm_mm *mm,
+			     struct drm_mm_node *node,
+			     unsigned long start, unsigned long end)
+{
+	unsigned long size = end - start;
+
+	if (start == end)
+		return -EINVAL;
+
+	DRM_INFO("balloon space: range [ 0x%lx - 0x%lx ] %lu KiB.\n",
+		 start, end, size / 1024);
+
+	node->start = start;
+	node->size = size;
+
+	return drm_mm_reserve_node(mm, node);
+}
+
+/**
+ * intel_vgt_balloon - balloon out reserved graphics address trunks
+ * @dev: drm device
+ *
+ * This function is called at the initialization stage, to balloon out the
+ * graphic address space allocated to other vGPUs, by marking these spaces as
+ * reserved. The ballooning related knowledge(starting address and size of
+ * the mappable/unmappable graphic memory) is described in the vgt_if structure
+ * in a reserved mmio range.
+ *
+ * To give an example, the drawing below depicts one typical scenario after
+ * ballooning. Here the vGPU1 has 2 pieces of graphic address spaces ballooned
+ * out each for the mappable and the non-mappable part. From the vGPU1 point of
+ * view, the total size is the same as the physical one, with the start address
+ * of its graphic space being zero. Yet there are some portions ballooned out(
+ * the shadow part, which are marked as reserved by drm allocator). From the
+ * host point of view, the graphic address space is partitioned by multiple
+ * vGPUs in different VMs.
+ *
+ *                        vGPU1 view         Host view
+ *             0 ------> +-----------+     +-----------+
+ *               ^       |///////////|     |   vGPU3   |
+ *               |       |///////////|     +-----------+
+ *               |       |///////////|     |   vGPU2   |
+ *               |       +-----------+     +-----------+
+ *        mappable GM    | available | ==> |   vGPU1   |
+ *               |       +-----------+     +-----------+
+ *               |       |///////////|     |           |
+ *               v       |///////////|     |   Host    |
+ *               +=======+===========+     +===========+
+ *               ^       |///////////|     |   vGPU3   |
+ *               |       |///////////|     +-----------+
+ *               |       |///////////|     |   vGPU2   |
+ *               |       +-----------+     +-----------+
+ *      unmappable GM    | available | ==> |   vGPU1   |
+ *               |       +-----------+     +-----------+
+ *               |       |///////////|     |           |
+ *               |       |///////////|     |   Host    |
+ *               v       |///////////|     |           |
+ * total GM size ------> +-----------+     +-----------+
+ *
+ * Returns:
+ * zero on success, non-zero if configuration invalid or ballooning failed
+ */
+int intel_vgt_balloon(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i915_address_space *ggtt_vm = &dev_priv->gtt.base;
+	unsigned long ggtt_vm_end = ggtt_vm->start + ggtt_vm->total;
+
+	unsigned long mappable_base, mappable_size, mappable_end;
+	unsigned long unmappable_base, unmappable_size, unmappable_end;
+	int ret;
+
+	mappable_base = I915_READ(vgtif_reg(avail_rs.mappable_gmadr.base));
+	mappable_size = I915_READ(vgtif_reg(avail_rs.mappable_gmadr.size));
+	unmappable_base = I915_READ(vgtif_reg(avail_rs.nonmappable_gmadr.base));
+	unmappable_size = I915_READ(vgtif_reg(avail_rs.nonmappable_gmadr.size));
+
+	mappable_end = mappable_base + mappable_size;
+	unmappable_end = unmappable_base + unmappable_size;
+
+	DRM_INFO("VGT ballooning configuration:\n");
+	DRM_INFO("Mappable graphic memory: base 0x%lx size %ldKiB\n",
+		 mappable_base, mappable_size / 1024);
+	DRM_INFO("Unmappable graphic memory: base 0x%lx size %ldKiB\n",
+		 unmappable_base, unmappable_size / 1024);
+
+	if (mappable_base < ggtt_vm->start ||
+	    mappable_end > dev_priv->gtt.mappable_end ||
+	    unmappable_base < dev_priv->gtt.mappable_end ||
+	    unmappable_end > ggtt_vm_end) {
+		DRM_ERROR("Invalid ballooning configuration!\n");
+		return -EINVAL;
+	}
+
+	/* Unmappable graphic memory ballooning */
+	if (unmappable_base > dev_priv->gtt.mappable_end) {
+		ret = vgt_balloon_space(&ggtt_vm->mm,
+					&bl_info.space[2],
+					dev_priv->gtt.mappable_end,
+					unmappable_base);
+
+		if (ret)
+			goto err;
+	}
+
+	/*
+	 * No need to partition out the last physical page,
+	 * because it is reserved to the guard page.
+	 */
+	if (unmappable_end < ggtt_vm_end - PAGE_SIZE) {
+		ret = vgt_balloon_space(&ggtt_vm->mm,
+					&bl_info.space[3],
+					unmappable_end,
+					ggtt_vm_end - PAGE_SIZE);
+		if (ret)
+			goto err;
+	}
+
+	/* Mappable graphic memory ballooning */
+	if (mappable_base > ggtt_vm->start) {
+		ret = vgt_balloon_space(&ggtt_vm->mm,
+					&bl_info.space[0],
+					ggtt_vm->start, mappable_base);
+
+		if (ret)
+			goto err;
+	}
+
+	if (mappable_end < dev_priv->gtt.mappable_end) {
+		ret = vgt_balloon_space(&ggtt_vm->mm,
+					&bl_info.space[1],
+					mappable_end,
+					dev_priv->gtt.mappable_end);
+
+		if (ret)
+			goto err;
+	}
+
+	DRM_INFO("VGT balloon successfully\n");
+	return 0;
+
+err:
+	DRM_ERROR("VGT balloon fail\n");
+	intel_vgt_deballoon();
+	return ret;
+}

drivers/gpu/drm/i915/i915_vgpu.h

@@ -0,0 +1,91 @@
+/*
+ * Copyright(c) 2011-2015 Intel Corporation. All rights reserved.
+ *
+ * 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_VGPU_H_
+#define _I915_VGPU_H_
+
+/* The MMIO offset of the shared info between guest and host emulator */
+#define VGT_PVINFO_PAGE	0x78000
+#define VGT_PVINFO_SIZE	0x1000
+
+/*
+ * The following structure pages are defined in GEN MMIO space
+ * for virtualization. (One page for now)
+ */
+#define VGT_MAGIC         0x4776544776544776	/* 'vGTvGTvG' */
+#define VGT_VERSION_MAJOR 1
+#define VGT_VERSION_MINOR 0
+
+#define INTEL_VGT_IF_VERSION_ENCODE(major, minor) ((major) << 16 | (minor))
+#define INTEL_VGT_IF_VERSION \
+	INTEL_VGT_IF_VERSION_ENCODE(VGT_VERSION_MAJOR, VGT_VERSION_MINOR)
+
+struct vgt_if {
+	uint64_t magic;		/* VGT_MAGIC */
+	uint16_t version_major;
+	uint16_t version_minor;
+	uint32_t vgt_id;	/* ID of vGT instance */
+	uint32_t rsv1[12];	/* pad to offset 0x40 */
+	/*
+	 *  Data structure to describe the balooning info of resources.
+	 *  Each VM can only have one portion of continuous area for now.
+	 *  (May support scattered resource in future)
+	 *  (starting from offset 0x40)
+	 */
+	struct {
+		/* Aperture register balooning */
+		struct {
+			uint32_t base;
+			uint32_t size;
+		} mappable_gmadr;	/* aperture */
+		/* GMADR register balooning */
+		struct {
+			uint32_t base;
+			uint32_t size;
+		} nonmappable_gmadr;	/* non aperture */
+		/* allowed fence registers */
+		uint32_t fence_num;
+		uint32_t rsv2[3];
+	} avail_rs;		/* available/assigned resource */
+	uint32_t rsv3[0x200 - 24];	/* pad to half page */
+	/*
+	 * The bottom half page is for response from Gfx driver to hypervisor.
+	 * Set to reserved fields temporarily by now.
+	 */
+	uint32_t rsv4;
+	uint32_t display_ready;	/* ready for display owner switch */
+	uint32_t rsv5[0x200 - 2];	/* pad to one page */
+} __packed;
+
+#define vgtif_reg(x) \
+	(VGT_PVINFO_PAGE + (long)&((struct vgt_if *)NULL)->x)
+
+/* vGPU display status to be used by the host side */
+#define VGT_DRV_DISPLAY_NOT_READY 0
+#define VGT_DRV_DISPLAY_READY     1  /* ready for display switch */
+
+extern void i915_check_vgpu(struct drm_device *dev);
+extern int intel_vgt_balloon(struct drm_device *dev);
+extern void intel_vgt_deballoon(void);
+
+#endif /* _I915_VGPU_H_ */

drivers/gpu/drm/i915/intel_display.c

@@ -2190,11 +2190,15 @@ static bool need_vtd_wa(struct drm_device *dev)
 }
 
 int
-intel_fb_align_height(struct drm_device *dev, int height, unsigned int tiling)
+intel_fb_align_height(struct drm_device *dev, int height,
+		      uint32_t pixel_format,
+		      uint64_t fb_format_modifier)
 {
 	int tile_height;
 
-	tile_height = tiling ? (IS_GEN2(dev) ? 16 : 8) : 1;
+	tile_height = fb_format_modifier == I915_FORMAT_MOD_X_TILED ?
+		(IS_GEN2(dev) ? 16 : 8) : 1;
+
 	return ALIGN(height, tile_height);
 }
 
@@ -2211,8 +2215,8 @@ intel_pin_and_fence_fb_obj(struct drm_plane *plane,
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
-	switch (obj->tiling_mode) {
-	case I915_TILING_NONE:
+	switch (fb->modifier[0]) {
+	case DRM_FORMAT_MOD_NONE:
 		if (INTEL_INFO(dev)->gen >= 9)
 			alignment = 256 * 1024;
 		else if (IS_BROADWATER(dev) || IS_CRESTLINE(dev))
@@ -2222,7 +2226,7 @@ intel_pin_and_fence_fb_obj(struct drm_plane *plane,
 		else
 			alignment = 64 * 1024;
 		break;
-	case I915_TILING_X:
+	case I915_FORMAT_MOD_X_TILED:
 		if (INTEL_INFO(dev)->gen >= 9)
 			alignment = 256 * 1024;
 		else {
@@ -2230,11 +2234,12 @@ intel_pin_and_fence_fb_obj(struct drm_plane *plane,
 			alignment = 0;
 		}
 		break;
-	case I915_TILING_Y:
+	case I915_FORMAT_MOD_Y_TILED:
 		WARN(1, "Y tiled bo slipped through, driver bug!\n");
 		return -EINVAL;
 	default:
-		BUG();
+		MISSING_CASE(fb->modifier[0]);
+		return -EINVAL;
 	}
 
 	/* Note that the w/a also requires 64 PTE of padding following the
@@ -2282,7 +2287,7 @@ err_interruptible:
 	return ret;
 }
 
-void intel_unpin_fb_obj(struct drm_i915_gem_object *obj)
+static void intel_unpin_fb_obj(struct drm_i915_gem_object *obj)
 {
 	WARN_ON(!mutex_is_locked(&obj->base.dev->struct_mutex));
 
@@ -2371,6 +2376,7 @@ intel_alloc_plane_obj(struct intel_crtc *crtc,
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_gem_object *obj = NULL;
 	struct drm_mode_fb_cmd2 mode_cmd = { 0 };
+	struct drm_framebuffer *fb = &plane_config->fb->base;
 	u32 base = plane_config->base;
 
 	if (plane_config->size == 0)
@@ -2383,16 +2389,18 @@ intel_alloc_plane_obj(struct intel_crtc *crtc,
 
 	obj->tiling_mode = plane_config->tiling;
 	if (obj->tiling_mode == I915_TILING_X)
-		obj->stride = crtc->base.primary->fb->pitches[0];
+		obj->stride = fb->pitches[0];
 
-	mode_cmd.pixel_format = crtc->base.primary->fb->pixel_format;
-	mode_cmd.width = crtc->base.primary->fb->width;
-	mode_cmd.height = crtc->base.primary->fb->height;
-	mode_cmd.pitches[0] = crtc->base.primary->fb->pitches[0];
+	mode_cmd.pixel_format = fb->pixel_format;
+	mode_cmd.width = fb->width;
+	mode_cmd.height = fb->height;
+	mode_cmd.pitches[0] = fb->pitches[0];
+	mode_cmd.modifier[0] = fb->modifier[0];
+	mode_cmd.flags = DRM_MODE_FB_MODIFIERS;
 
 	mutex_lock(&dev->struct_mutex);
 
-	if (intel_framebuffer_init(dev, to_intel_framebuffer(crtc->base.primary->fb),
+	if (intel_framebuffer_init(dev, to_intel_framebuffer(fb),
 				   &mode_cmd, obj)) {
 		DRM_DEBUG_KMS("intel fb init failed\n");
 		goto out_unref_obj;
@@ -2410,6 +2418,20 @@ out_unref_obj:
 	return false;
 }
 
+/* Update plane->state->fb to match plane->fb after driver-internal updates */
+static void
+update_state_fb(struct drm_plane *plane)
+{
+	if (plane->fb == plane->state->fb)
+		return;
+
+	if (plane->state->fb)
+		drm_framebuffer_unreference(plane->state->fb);
+	plane->state->fb = plane->fb;
+	if (plane->state->fb)
+		drm_framebuffer_reference(plane->state->fb);
+}
+
 static void
 intel_find_plane_obj(struct intel_crtc *intel_crtc,
 		     struct intel_initial_plane_config *plane_config)
@@ -2420,14 +2442,20 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc,
 	struct intel_crtc *i;
 	struct drm_i915_gem_object *obj;
 
-	if (!intel_crtc->base.primary->fb)
+	if (!plane_config->fb)
 		return;
 
-	if (intel_alloc_plane_obj(intel_crtc, plane_config))
+	if (intel_alloc_plane_obj(intel_crtc, plane_config)) {
+		struct drm_plane *primary = intel_crtc->base.primary;
+
+		primary->fb = &plane_config->fb->base;
+		primary->state->crtc = &intel_crtc->base;
+		update_state_fb(primary);
+
 		return;
+	}
 
-	kfree(intel_crtc->base.primary->fb);
-	intel_crtc->base.primary->fb = NULL;
+	kfree(plane_config->fb);
 
 	/*
 	 * Failed to alloc the obj, check to see if we should share
@@ -2447,15 +2475,20 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc,
 			continue;
 
 		if (i915_gem_obj_ggtt_offset(obj) == plane_config->base) {
+			struct drm_plane *primary = intel_crtc->base.primary;
+
 			if (obj->tiling_mode != I915_TILING_NONE)
 				dev_priv->preserve_bios_swizzle = true;
 
 			drm_framebuffer_reference(c->primary->fb);
-			intel_crtc->base.primary->fb = c->primary->fb;
+			primary->fb = c->primary->fb;
+			primary->state->crtc = &intel_crtc->base;
+			update_state_fb(intel_crtc->base.primary);
 			obj->frontbuffer_bits |= INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe);
 			break;
 		}
 	}
+
 }
 
 static void i9xx_update_primary_plane(struct drm_crtc *crtc,
@@ -2747,11 +2780,11 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc,
 	 * The stride is either expressed as a multiple of 64 bytes chunks for
 	 * linear buffers or in number of tiles for tiled buffers.
 	 */
-	switch (obj->tiling_mode) {
-	case I915_TILING_NONE:
+	switch (fb->modifier[0]) {
+	case DRM_FORMAT_MOD_NONE:
 		stride = fb->pitches[0] >> 6;
 		break;
-	case I915_TILING_X:
+	case I915_FORMAT_MOD_X_TILED:
 		plane_ctl |= PLANE_CTL_TILED_X;
 		stride = fb->pitches[0] >> 9;
 		break;
@@ -4251,11 +4284,10 @@ static void intel_crtc_disable_planes(struct drm_crtc *crtc)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
 
 	intel_crtc_wait_for_pending_flips(crtc);
 
-	if (dev_priv->fbc.plane == plane)
+	if (dev_priv->fbc.crtc == intel_crtc)
 		intel_fbc_disable(dev);
 
 	hsw_disable_ips(intel_crtc);
@@ -6587,6 +6619,10 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc,
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
+	val = I915_READ(DSPCNTR(plane));
+	if (!(val & DISPLAY_PLANE_ENABLE))
+		return;
+
 	intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL);
 	if (!intel_fb) {
 		DRM_DEBUG_KMS("failed to alloc fb\n");
@@ -6595,11 +6631,12 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc,
 
 	fb = &intel_fb->base;
 
-	val = I915_READ(DSPCNTR(plane));
-
-	if (INTEL_INFO(dev)->gen >= 4)
-		if (val & DISPPLANE_TILED)
+	if (INTEL_INFO(dev)->gen >= 4) {
+		if (val & DISPPLANE_TILED) {
 			plane_config->tiling = I915_TILING_X;
+			fb->modifier[0] = I915_FORMAT_MOD_X_TILED;
+		}
+	}
 
 	pixel_format = val & DISPPLANE_PIXFORMAT_MASK;
 	fourcc = i9xx_format_to_fourcc(pixel_format);
@@ -6625,7 +6662,8 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc,
 	fb->pitches[0] = val & 0xffffffc0;
 
 	aligned_height = intel_fb_align_height(dev, fb->height,
-					       plane_config->tiling);
+					       fb->pixel_format,
+					       fb->modifier[0]);
 
 	plane_config->size = PAGE_ALIGN(fb->pitches[0] * aligned_height);
 
@@ -6634,7 +6672,7 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc,
 		      fb->bits_per_pixel, base, fb->pitches[0],
 		      plane_config->size);
 
-	crtc->base.primary->fb = fb;
+	plane_config->fb = intel_fb;
 }
 
 static void chv_crtc_clock_get(struct intel_crtc *crtc,
@@ -7628,8 +7666,13 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 	fb = &intel_fb->base;
 
 	val = I915_READ(PLANE_CTL(pipe, 0));
-	if (val & PLANE_CTL_TILED_MASK)
+	if (!(val & PLANE_CTL_ENABLE))
+		goto error;
+
+	if (val & PLANE_CTL_TILED_MASK) {
 		plane_config->tiling = I915_TILING_X;
+		fb->modifier[0] = I915_FORMAT_MOD_X_TILED;
+	}
 
 	pixel_format = val & PLANE_CTL_FORMAT_MASK;
 	fourcc = skl_format_to_fourcc(pixel_format,
@@ -7662,7 +7705,8 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 	fb->pitches[0] = (val & 0x3ff) * stride_mult;
 
 	aligned_height = intel_fb_align_height(dev, fb->height,
-					       plane_config->tiling);
+					       fb->pixel_format,
+					       fb->modifier[0]);
 
 	plane_config->size = ALIGN(fb->pitches[0] * aligned_height, PAGE_SIZE);
 
@@ -7671,7 +7715,7 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 		      fb->bits_per_pixel, base, fb->pitches[0],
 		      plane_config->size);
 
-	crtc->base.primary->fb = fb;
+	plane_config->fb = intel_fb;
 	return;
 
 error:
@@ -7715,6 +7759,10 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc,
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
+	val = I915_READ(DSPCNTR(pipe));
+	if (!(val & DISPLAY_PLANE_ENABLE))
+		return;
+
 	intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL);
 	if (!intel_fb) {
 		DRM_DEBUG_KMS("failed to alloc fb\n");
@@ -7723,11 +7771,12 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc,
 
 	fb = &intel_fb->base;
 
-	val = I915_READ(DSPCNTR(pipe));
-
-	if (INTEL_INFO(dev)->gen >= 4)
-		if (val & DISPPLANE_TILED)
+	if (INTEL_INFO(dev)->gen >= 4) {
+		if (val & DISPPLANE_TILED) {
 			plane_config->tiling = I915_TILING_X;
+			fb->modifier[0] = I915_FORMAT_MOD_X_TILED;
+		}
+	}
 
 	pixel_format = val & DISPPLANE_PIXFORMAT_MASK;
 	fourcc = i9xx_format_to_fourcc(pixel_format);
@@ -7753,7 +7802,8 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc,
 	fb->pitches[0] = val & 0xffffffc0;
 
 	aligned_height = intel_fb_align_height(dev, fb->height,
-					       plane_config->tiling);
+					       fb->pixel_format,
+					       fb->modifier[0]);
 
 	plane_config->size = PAGE_ALIGN(fb->pitches[0] * aligned_height);
 
@@ -7762,7 +7812,7 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc,
 		      fb->bits_per_pixel, base, fb->pitches[0],
 		      plane_config->size);
 
-	crtc->base.primary->fb = fb;
+	plane_config->fb = intel_fb;
 }
 
 static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
@@ -9055,9 +9105,9 @@ static void intel_unpin_work_fn(struct work_struct *__work)
 	enum pipe pipe = to_intel_crtc(work->crtc)->pipe;
 
 	mutex_lock(&dev->struct_mutex);
-	intel_unpin_fb_obj(work->old_fb_obj);
+	intel_unpin_fb_obj(intel_fb_obj(work->old_fb));
 	drm_gem_object_unreference(&work->pending_flip_obj->base);
-	drm_gem_object_unreference(&work->old_fb_obj->base);
+	drm_framebuffer_unreference(work->old_fb);
 
 	intel_fbc_update(dev);
 
@@ -9582,69 +9632,6 @@ static int intel_queue_mmio_flip(struct drm_device *dev,
 	return 0;
 }
 
-static int intel_gen9_queue_flip(struct drm_device *dev,
-				 struct drm_crtc *crtc,
-				 struct drm_framebuffer *fb,
-				 struct drm_i915_gem_object *obj,
-				 struct intel_engine_cs *ring,
-				 uint32_t flags)
-{
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	uint32_t plane = 0, stride;
-	int ret;
-
-	switch(intel_crtc->pipe) {
-	case PIPE_A:
-		plane = MI_DISPLAY_FLIP_SKL_PLANE_1_A;
-		break;
-	case PIPE_B:
-		plane = MI_DISPLAY_FLIP_SKL_PLANE_1_B;
-		break;
-	case PIPE_C:
-		plane = MI_DISPLAY_FLIP_SKL_PLANE_1_C;
-		break;
-	default:
-		WARN_ONCE(1, "unknown plane in flip command\n");
-		return -ENODEV;
-	}
-
-	switch (obj->tiling_mode) {
-	case I915_TILING_NONE:
-		stride = fb->pitches[0] >> 6;
-		break;
-	case I915_TILING_X:
-		stride = fb->pitches[0] >> 9;
-		break;
-	default:
-		WARN_ONCE(1, "unknown tiling in flip command\n");
-		return -ENODEV;
-	}
-
-	ret = intel_ring_begin(ring, 10);
-	if (ret)
-		return ret;
-
-	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-	intel_ring_emit(ring, DERRMR);
-	intel_ring_emit(ring, ~(DERRMR_PIPEA_PRI_FLIP_DONE |
-				DERRMR_PIPEB_PRI_FLIP_DONE |
-				DERRMR_PIPEC_PRI_FLIP_DONE));
-	intel_ring_emit(ring, MI_STORE_REGISTER_MEM_GEN8(1) |
-			      MI_SRM_LRM_GLOBAL_GTT);
-	intel_ring_emit(ring, DERRMR);
-	intel_ring_emit(ring, ring->scratch.gtt_offset + 256);
-	intel_ring_emit(ring, 0);
-
-	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane);
-	intel_ring_emit(ring, stride << 6 | obj->tiling_mode);
-	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
-
-	intel_mark_page_flip_active(intel_crtc);
-	__intel_ring_advance(ring);
-
-	return 0;
-}
-
 static int intel_default_queue_flip(struct drm_device *dev,
 				    struct drm_crtc *crtc,
 				    struct drm_framebuffer *fb,
@@ -9760,7 +9747,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 
 	work->event = event;
 	work->crtc = crtc;
-	work->old_fb_obj = intel_fb_obj(old_fb);
+	work->old_fb = old_fb;
 	INIT_WORK(&work->work, intel_unpin_work_fn);
 
 	ret = drm_crtc_vblank_get(crtc);
@@ -9796,10 +9783,11 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 		goto cleanup;
 
 	/* Reference the objects for the scheduled work. */
-	drm_gem_object_reference(&work->old_fb_obj->base);
+	drm_framebuffer_reference(work->old_fb);
 	drm_gem_object_reference(&obj->base);
 
 	crtc->primary->fb = fb;
+	update_state_fb(crtc->primary);
 
 	work->pending_flip_obj = obj;
 
@@ -9811,7 +9799,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 
 	if (IS_VALLEYVIEW(dev)) {
 		ring = &dev_priv->ring[BCS];
-		if (obj->tiling_mode != work->old_fb_obj->tiling_mode)
+		if (obj->tiling_mode != intel_fb_obj(work->old_fb)->tiling_mode)
 			/* vlv: DISPLAY_FLIP fails to change tiling */
 			ring = NULL;
 	} else if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) {
@@ -9852,7 +9840,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	work->flip_queued_vblank = drm_vblank_count(dev, intel_crtc->pipe);
 	work->enable_stall_check = true;
 
-	i915_gem_track_fb(work->old_fb_obj, obj,
+	i915_gem_track_fb(intel_fb_obj(work->old_fb), obj,
 			  INTEL_FRONTBUFFER_PRIMARY(pipe));
 
 	intel_fbc_disable(dev);
@@ -9868,7 +9856,8 @@ cleanup_unpin:
 cleanup_pending:
 	atomic_dec(&intel_crtc->unpin_work_count);
 	crtc->primary->fb = old_fb;
-	drm_gem_object_unreference(&work->old_fb_obj->base);
+	update_state_fb(crtc->primary);
+	drm_framebuffer_unreference(work->old_fb);
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
 
@@ -11897,7 +11886,7 @@ intel_check_primary_plane(struct drm_plane *plane,
 		 */
 		if (intel_crtc->primary_enabled &&
 		    INTEL_INFO(dev)->gen <= 4 && !IS_G4X(dev) &&
-		    dev_priv->fbc.plane == intel_crtc->plane &&
+		    dev_priv->fbc.crtc == intel_crtc &&
 		    state->base.rotation != BIT(DRM_ROTATE_0)) {
 			intel_crtc->atomic.disable_fbc = true;
 		}
@@ -12069,8 +12058,8 @@ void intel_plane_destroy(struct drm_plane *plane)
 }
 
 const struct drm_plane_funcs intel_plane_funcs = {
-	.update_plane = drm_plane_helper_update,
-	.disable_plane = drm_plane_helper_disable,
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
 	.destroy = intel_plane_destroy,
 	.set_property = drm_atomic_helper_plane_set_property,
 	.atomic_get_property = intel_plane_atomic_get_property,
@@ -12185,13 +12174,10 @@ intel_check_cursor_plane(struct drm_plane *plane,
 	if (fb == crtc->cursor->fb)
 		return 0;
 
-	/* we only need to pin inside GTT if cursor is non-phy */
-	mutex_lock(&dev->struct_mutex);
-	if (!INTEL_INFO(dev)->cursor_needs_physical && obj->tiling_mode) {
+	if (fb->modifier[0] != DRM_FORMAT_MOD_NONE) {
 		DRM_DEBUG_KMS("cursor cannot be tiled\n");
 		ret = -EINVAL;
 	}
-	mutex_unlock(&dev->struct_mutex);
 
 finish:
 	if (intel_crtc->active) {
@@ -12672,7 +12658,24 @@ static int intel_framebuffer_init(struct drm_device *dev,
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
-	if (obj->tiling_mode == I915_TILING_Y) {
+	if (mode_cmd->flags & DRM_MODE_FB_MODIFIERS) {
+		/* Enforce that fb modifier and tiling mode match, but only for
+		 * X-tiled. This is needed for FBC. */
+		if (!!(obj->tiling_mode == I915_TILING_X) !=
+		    !!(mode_cmd->modifier[0] == I915_FORMAT_MOD_X_TILED)) {
+			DRM_DEBUG("tiling_mode doesn't match fb modifier\n");
+			return -EINVAL;
+		}
+	} else {
+		if (obj->tiling_mode == I915_TILING_X)
+			mode_cmd->modifier[0] = I915_FORMAT_MOD_X_TILED;
+		else if (obj->tiling_mode == I915_TILING_Y) {
+			DRM_DEBUG("No Y tiling for legacy addfb\n");
+			return -EINVAL;
+		}
+	}
+
+	if (mode_cmd->modifier[0] == I915_FORMAT_MOD_Y_TILED) {
 		DRM_DEBUG("hardware does not support tiling Y\n");
 		return -EINVAL;
 	}
@@ -12686,12 +12689,12 @@ static int intel_framebuffer_init(struct drm_device *dev,
 	if (INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev)) {
 		pitch_limit = 32*1024;
 	} else if (INTEL_INFO(dev)->gen >= 4) {
-		if (obj->tiling_mode)
+		if (mode_cmd->modifier[0] == I915_FORMAT_MOD_X_TILED)
 			pitch_limit = 16*1024;
 		else
 			pitch_limit = 32*1024;
 	} else if (INTEL_INFO(dev)->gen >= 3) {
-		if (obj->tiling_mode)
+		if (mode_cmd->modifier[0] == I915_FORMAT_MOD_X_TILED)
 			pitch_limit = 8*1024;
 		else
 			pitch_limit = 16*1024;
@@ -12701,12 +12704,13 @@ static int intel_framebuffer_init(struct drm_device *dev,
 
 	if (mode_cmd->pitches[0] > pitch_limit) {
 		DRM_DEBUG("%s pitch (%d) must be at less than %d\n",
-			  obj->tiling_mode ? "tiled" : "linear",
+			  mode_cmd->modifier[0] == I915_FORMAT_MOD_X_TILED ?
+			  "tiled" : "linear",
 			  mode_cmd->pitches[0], pitch_limit);
 		return -EINVAL;
 	}
 
-	if (obj->tiling_mode != I915_TILING_NONE &&
+	if (mode_cmd->modifier[0] == I915_FORMAT_MOD_X_TILED &&
 	    mode_cmd->pitches[0] != obj->stride) {
 		DRM_DEBUG("pitch (%d) must match tiling stride (%d)\n",
 			  mode_cmd->pitches[0], obj->stride);
@@ -12761,7 +12765,8 @@ static int intel_framebuffer_init(struct drm_device *dev,
 		return -EINVAL;
 
 	aligned_height = intel_fb_align_height(dev, mode_cmd->height,
-					       obj->tiling_mode);
+					       mode_cmd->pixel_format,
+					       mode_cmd->modifier[0]);
 	/* FIXME drm helper for size checks (especially planar formats)? */
 	if (obj->base.size < aligned_height * mode_cmd->pitches[0])
 		return -EINVAL;
@@ -12923,9 +12928,6 @@ static void intel_init_display(struct drm_device *dev)
 			valleyview_modeset_global_resources;
 	}
 
-	/* Default just returns -ENODEV to indicate unsupported */
-	dev_priv->display.queue_flip = intel_default_queue_flip;
-
 	switch (INTEL_INFO(dev)->gen) {
 	case 2:
 		dev_priv->display.queue_flip = intel_gen2_queue_flip;
@@ -12948,8 +12950,10 @@ static void intel_init_display(struct drm_device *dev)
 		dev_priv->display.queue_flip = intel_gen7_queue_flip;
 		break;
 	case 9:
-		dev_priv->display.queue_flip = intel_gen9_queue_flip;
-		break;
+		/* Drop through - unsupported since execlist only. */
+	default:
+		/* Default just returns -ENODEV to indicate unsupported */
+		dev_priv->display.queue_flip = intel_default_queue_flip;
 	}
 
 	intel_panel_init_backlight_funcs(dev);
@@ -13165,6 +13169,8 @@ void intel_modeset_init(struct drm_device *dev)
 	dev->mode_config.preferred_depth = 24;
 	dev->mode_config.prefer_shadow = 1;
 
+	dev->mode_config.allow_fb_modifiers = true;
+
 	dev->mode_config.funcs = &intel_mode_funcs;
 
 	intel_init_quirks(dev);
@@ -13702,6 +13708,7 @@ void intel_modeset_gem_init(struct drm_device *dev)
 				  to_intel_crtc(c)->pipe);
 			drm_framebuffer_unreference(c->primary->fb);
 			c->primary->fb = NULL;
+			update_state_fb(c->primary);
 		}
 	}
 	mutex_unlock(&dev->struct_mutex);

drivers/gpu/drm/i915/intel_dp.c

@@ -240,7 +240,7 @@ uint32_t intel_dp_pack_aux(const uint8_t *src, int src_bytes)
 	return v;
 }
 
-void intel_dp_unpack_aux(uint32_t src, uint8_t *dst, int dst_bytes)
+static void intel_dp_unpack_aux(uint32_t src, uint8_t *dst, int dst_bytes)
 {
 	int i;
 	if (dst_bytes > 4)
@@ -3803,7 +3803,7 @@ go_again:
  *  3. Use Link Training from 2.5.3.3 and 3.5.1.3
  *  4. Check link status on receipt of hot-plug interrupt
  */
-void
+static void
 intel_dp_check_link_status(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);

drivers/gpu/drm/i915/intel_drv.h

@@ -258,6 +258,7 @@ struct intel_plane_state {
 };
 
 struct intel_initial_plane_config {
+	struct intel_framebuffer *fb;
 	unsigned int tiling;
 	int size;
 	u32 base;
@@ -710,7 +711,7 @@ intel_get_crtc_for_plane(struct drm_device *dev, int plane)
 struct intel_unpin_work {
 	struct work_struct work;
 	struct drm_crtc *crtc;
-	struct drm_i915_gem_object *old_fb_obj;
+	struct drm_framebuffer *old_fb;
 	struct drm_i915_gem_object *pending_flip_obj;
 	struct drm_pending_vblank_event *event;
 	atomic_t pending;
@@ -878,7 +879,8 @@ void intel_frontbuffer_flip(struct drm_device *dev,
 }
 
 int intel_fb_align_height(struct drm_device *dev, int height,
-			  unsigned int tiling);
+			  uint32_t pixel_format,
+			  uint64_t fb_format_modifier);
 void intel_fb_obj_flush(struct drm_i915_gem_object *obj, bool retire);
 
 
@@ -932,7 +934,6 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 int intel_pin_and_fence_fb_obj(struct drm_plane *plane,
 			       struct drm_framebuffer *fb,
 			       struct intel_engine_cs *pipelined);
-void intel_unpin_fb_obj(struct drm_i915_gem_object *obj);
 struct drm_framebuffer *
 __intel_framebuffer_create(struct drm_device *dev,
 			   struct drm_mode_fb_cmd2 *mode_cmd,
@@ -1017,7 +1018,6 @@ void intel_dp_complete_link_train(struct intel_dp *intel_dp);
 void intel_dp_stop_link_train(struct intel_dp *intel_dp);
 void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode);
 void intel_dp_encoder_destroy(struct drm_encoder *encoder);
-void intel_dp_check_link_status(struct intel_dp *intel_dp);
 int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc);
 bool intel_dp_compute_config(struct intel_encoder *encoder,
 			     struct intel_crtc_state *pipe_config);
@@ -1036,13 +1036,6 @@ int intel_dp_max_link_bw(struct intel_dp *intel_dp);
 void intel_dp_hot_plug(struct intel_encoder *intel_encoder);
 void vlv_power_sequencer_reset(struct drm_i915_private *dev_priv);
 uint32_t intel_dp_pack_aux(const uint8_t *src, int src_bytes);
-void intel_dp_unpack_aux(uint32_t src, uint8_t *dst, int dst_bytes);
-int intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
-		       struct drm_framebuffer *fb, int crtc_x, int crtc_y,
-		       unsigned int crtc_w, unsigned int crtc_h,
-		       uint32_t src_x, uint32_t src_y,
-		       uint32_t src_w, uint32_t src_h);
-int intel_disable_plane(struct drm_plane *plane);
 void intel_plane_destroy(struct drm_plane *plane);
 void intel_edp_drrs_enable(struct intel_dp *intel_dp);
 void intel_edp_drrs_disable(struct intel_dp *intel_dp);
@@ -1231,9 +1224,6 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob);
 int intel_plane_init(struct drm_device *dev, enum pipe pipe, int plane);
 void intel_flush_primary_plane(struct drm_i915_private *dev_priv,
 			       enum plane plane);
-int intel_plane_set_property(struct drm_plane *plane,
-			     struct drm_property *prop,
-			     uint64_t val);
 int intel_plane_restore(struct drm_plane *plane);
 int intel_sprite_set_colorkey(struct drm_device *dev, void *data,
 			      struct drm_file *file_priv);

drivers/gpu/drm/i915/intel_dsi.c

@@ -854,7 +854,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 
 
 		/* recovery disables */
-		I915_WRITE(MIPI_EOT_DISABLE(port), val);
+		I915_WRITE(MIPI_EOT_DISABLE(port), tmp);
 
 		/* in terms of low power clock */
 		I915_WRITE(MIPI_INIT_COUNT(port), intel_dsi->init_count);

drivers/gpu/drm/i915/intel_dsi_cmd.h

@@ -1,39 +0,0 @@
-/*
- * Copyright © 2013 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.
- *
- * Author: Jani Nikula <jani.nikula@intel.com>
- */
-
-#ifndef _INTEL_DSI_DSI_H
-#define _INTEL_DSI_DSI_H
-
-#include <drm/drmP.h>
-#include <drm/drm_crtc.h>
-#include <video/mipi_display.h>
-#include "i915_drv.h"
-#include "intel_drv.h"
-#include "intel_dsi.h"
-
-void dsi_hs_mode_enable(struct intel_dsi *intel_dsi, bool enable,
-						enum port port);
-
-#endif /* _INTEL_DSI_DSI_H */

drivers/gpu/drm/i915/intel_fbc.c

@@ -78,7 +78,8 @@ static void i8xx_fbc_enable(struct drm_crtc *crtc)
 
 	dev_priv->fbc.enabled = true;
 
-	cfb_pitch = dev_priv->fbc.size / FBC_LL_SIZE;
+	/* Note: fbc.threshold == 1 for i8xx */
+	cfb_pitch = dev_priv->fbc.uncompressed_size / FBC_LL_SIZE;
 	if (fb->pitches[0] < cfb_pitch)
 		cfb_pitch = fb->pitches[0];
 
@@ -368,7 +369,7 @@ static void intel_fbc_work_fn(struct work_struct *__work)
 		if (work->crtc->primary->fb == work->fb) {
 			dev_priv->display.enable_fbc(work->crtc);
 
-			dev_priv->fbc.plane = to_intel_crtc(work->crtc)->plane;
+			dev_priv->fbc.crtc = to_intel_crtc(work->crtc);
 			dev_priv->fbc.fb_id = work->crtc->primary->fb->base.id;
 			dev_priv->fbc.y = work->crtc->y;
 		}
@@ -459,7 +460,7 @@ void intel_fbc_disable(struct drm_device *dev)
 		return;
 
 	dev_priv->display.disable_fbc(dev);
-	dev_priv->fbc.plane = -1;
+	dev_priv->fbc.crtc = NULL;
 }
 
 static bool set_no_fbc_reason(struct drm_i915_private *dev_priv,
@@ -501,15 +502,23 @@ void intel_fbc_update(struct drm_device *dev)
 	const struct drm_display_mode *adjusted_mode;
 	unsigned int max_width, max_height;
 
-	if (!HAS_FBC(dev)) {
-		set_no_fbc_reason(dev_priv, FBC_UNSUPPORTED);
+	if (!HAS_FBC(dev))
 		return;
+
+	/* disable framebuffer compression in vGPU */
+	if (intel_vgpu_active(dev))
+		i915.enable_fbc = 0;
+
+	if (i915.enable_fbc < 0) {
+		if (set_no_fbc_reason(dev_priv, FBC_CHIP_DEFAULT))
+			DRM_DEBUG_KMS("disabled per chip default\n");
+		goto out_disable;
 	}
 
-	if (!i915.powersave) {
+	if (!i915.enable_fbc || !i915.powersave) {
 		if (set_no_fbc_reason(dev_priv, FBC_MODULE_PARAM))
 			DRM_DEBUG_KMS("fbc disabled per module param\n");
-		return;
+		goto out_disable;
 	}
 
 	/*
@@ -544,16 +553,6 @@ void intel_fbc_update(struct drm_device *dev)
 	obj = intel_fb_obj(fb);
 	adjusted_mode = &intel_crtc->config->base.adjusted_mode;
 
-	if (i915.enable_fbc < 0) {
-		if (set_no_fbc_reason(dev_priv, FBC_CHIP_DEFAULT))
-			DRM_DEBUG_KMS("disabled per chip default\n");
-		goto out_disable;
-	}
-	if (!i915.enable_fbc) {
-		if (set_no_fbc_reason(dev_priv, FBC_MODULE_PARAM))
-			DRM_DEBUG_KMS("fbc disabled per module param\n");
-		goto out_disable;
-	}
 	if ((adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) ||
 	    (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)) {
 		if (set_no_fbc_reason(dev_priv, FBC_UNSUPPORTED_MODE))
@@ -617,7 +616,7 @@ void intel_fbc_update(struct drm_device *dev)
 	 * cannot be unpinned (and have its GTT offset and fence revoked)
 	 * without first being decoupled from the scanout and FBC disabled.
 	 */
-	if (dev_priv->fbc.plane == intel_crtc->plane &&
+	if (dev_priv->fbc.crtc == intel_crtc &&
 	    dev_priv->fbc.fb_id == fb->base.id &&
 	    dev_priv->fbc.y == crtc->y)
 		return;
@@ -673,6 +672,7 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
 {
 	if (!HAS_FBC(dev_priv)) {
 		dev_priv->fbc.enabled = false;
+		dev_priv->fbc.no_fbc_reason = FBC_UNSUPPORTED;
 		return;
 	}
 

drivers/gpu/drm/i915/intel_fbdev.c

@@ -594,7 +594,8 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 
 		cur_size = intel_crtc->config->base.adjusted_mode.crtc_vdisplay;
 		cur_size = intel_fb_align_height(dev, cur_size,
-						 plane_config->tiling);
+						 fb->base.pixel_format,
+						 fb->base.modifier[0]);
 		cur_size *= fb->base.pitches[0];
 		DRM_DEBUG_KMS("pipe %c area: %dx%d, bpp: %d, size: %d\n",
 			      pipe_name(intel_crtc->pipe),

drivers/gpu/drm/i915/intel_lrc.c

@@ -254,8 +254,10 @@ u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj)
 	return lrca >> 12;
 }
 
-static uint64_t execlists_ctx_descriptor(struct drm_i915_gem_object *ctx_obj)
+static uint64_t execlists_ctx_descriptor(struct intel_engine_cs *ring,
+					 struct drm_i915_gem_object *ctx_obj)
 {
+	struct drm_device *dev = ring->dev;
 	uint64_t desc;
 	uint64_t lrca = i915_gem_obj_ggtt_offset(ctx_obj);
 
@@ -272,6 +274,13 @@ static uint64_t execlists_ctx_descriptor(struct drm_i915_gem_object *ctx_obj)
 	 * signalling between Command Streamers */
 	/* desc |= GEN8_CTX_FORCE_RESTORE; */
 
+	/* WaEnableForceRestoreInCtxtDescForVCS:skl */
+	if (IS_GEN9(dev) &&
+	    INTEL_REVID(dev) <= SKL_REVID_B0 &&
+	    (ring->id == BCS || ring->id == VCS ||
+	    ring->id == VECS || ring->id == VCS2))
+		desc |= GEN8_CTX_FORCE_RESTORE;
+
 	return desc;
 }
 
@@ -286,13 +295,13 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,
 
 	/* XXX: You must always write both descriptors in the order below. */
 	if (ctx_obj1)
-		temp = execlists_ctx_descriptor(ctx_obj1);
+		temp = execlists_ctx_descriptor(ring, ctx_obj1);
 	else
 		temp = 0;
 	desc[1] = (u32)(temp >> 32);
 	desc[0] = (u32)temp;
 
-	temp = execlists_ctx_descriptor(ctx_obj0);
+	temp = execlists_ctx_descriptor(ring, ctx_obj0);
 	desc[3] = (u32)(temp >> 32);
 	desc[2] = (u32)temp;
 
@@ -776,7 +785,7 @@ int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf,
 	return 0;
 }
 
-/**
+/*
  * intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
  * @ringbuf: Logical Ringbuffer to advance.
  *
@@ -785,9 +794,10 @@ int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf,
  * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
  * point, the tail *inside* the context is updated and the ELSP written to.
  */
-void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
-					   struct intel_context *ctx,
-					   struct drm_i915_gem_request *request)
+static void
+intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
+				      struct intel_context *ctx,
+				      struct drm_i915_gem_request *request)
 {
 	struct intel_engine_cs *ring = ringbuf->ring;
 
@@ -1140,6 +1150,17 @@ static int gen8_init_render_ring(struct intel_engine_cs *ring)
 	return init_workarounds_ring(ring);
 }
 
+static int gen9_init_render_ring(struct intel_engine_cs *ring)
+{
+	int ret;
+
+	ret = gen8_init_common_ring(ring);
+	if (ret)
+		return ret;
+
+	return init_workarounds_ring(ring);
+}
+
 static int gen8_emit_bb_start(struct intel_ringbuffer *ringbuf,
 			      struct intel_context *ctx,
 			      u64 offset, unsigned flags)
@@ -1316,6 +1337,39 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
 	return 0;
 }
 
+static int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
+					      struct intel_context *ctx)
+{
+	struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+	struct render_state so;
+	struct drm_i915_file_private *file_priv = ctx->file_priv;
+	struct drm_file *file = file_priv ? file_priv->file : NULL;
+	int ret;
+
+	ret = i915_gem_render_state_prepare(ring, &so);
+	if (ret)
+		return ret;
+
+	if (so.rodata == NULL)
+		return 0;
+
+	ret = ring->emit_bb_start(ringbuf,
+			ctx,
+			so.ggtt_offset,
+			I915_DISPATCH_SECURE);
+	if (ret)
+		goto out;
+
+	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
+
+	ret = __i915_add_request(ring, file, so.obj);
+	/* intel_logical_ring_add_request moves object to inactive if it
+	 * fails */
+out:
+	i915_gem_render_state_fini(&so);
+	return ret;
+}
+
 static int gen8_init_rcs_context(struct intel_engine_cs *ring,
 		       struct intel_context *ctx)
 {
@@ -1399,7 +1453,10 @@ static int logical_render_ring_init(struct drm_device *dev)
 	if (HAS_L3_DPF(dev))
 		ring->irq_keep_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
 
-	ring->init_hw = gen8_init_render_ring;
+	if (INTEL_INFO(dev)->gen >= 9)
+		ring->init_hw = gen9_init_render_ring;
+	else
+		ring->init_hw = gen8_init_render_ring;
 	ring->init_context = gen8_init_rcs_context;
 	ring->cleanup = intel_fini_pipe_control;
 	ring->get_seqno = gen8_get_seqno;
@@ -1581,39 +1638,6 @@ cleanup_render_ring:
 	return ret;
 }
 
-int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
-				       struct intel_context *ctx)
-{
-	struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
-	struct render_state so;
-	struct drm_i915_file_private *file_priv = ctx->file_priv;
-	struct drm_file *file = file_priv ? file_priv->file : NULL;
-	int ret;
-
-	ret = i915_gem_render_state_prepare(ring, &so);
-	if (ret)
-		return ret;
-
-	if (so.rodata == NULL)
-		return 0;
-
-	ret = ring->emit_bb_start(ringbuf,
-			ctx,
-			so.ggtt_offset,
-			I915_DISPATCH_SECURE);
-	if (ret)
-		goto out;
-
-	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
-
-	ret = __i915_add_request(ring, file, so.obj);
-	/* intel_logical_ring_add_request moves object to inactive if it
-	 * fails */
-out:
-	i915_gem_render_state_fini(&so);
-	return ret;
-}
-
 static int
 populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_obj,
 		    struct intel_engine_cs *ring, struct intel_ringbuffer *ringbuf)
@@ -1659,7 +1683,8 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o
 	reg_state[CTX_LRI_HEADER_0] |= MI_LRI_FORCE_POSTED;
 	reg_state[CTX_CONTEXT_CONTROL] = RING_CONTEXT_CONTROL(ring);
 	reg_state[CTX_CONTEXT_CONTROL+1] =
-			_MASKED_BIT_ENABLE((1<<3) | MI_RESTORE_INHIBIT);
+		_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH |
+				CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
 	reg_state[CTX_RING_HEAD] = RING_HEAD(ring->mmio_base);
 	reg_state[CTX_RING_HEAD+1] = 0;
 	reg_state[CTX_RING_TAIL] = RING_TAIL(ring->mmio_base);

drivers/gpu/drm/i915/intel_lrc.h

@@ -30,6 +30,8 @@
 #define RING_ELSP(ring)			((ring)->mmio_base+0x230)
 #define RING_EXECLIST_STATUS(ring)	((ring)->mmio_base+0x234)
 #define RING_CONTEXT_CONTROL(ring)	((ring)->mmio_base+0x244)
+#define	  CTX_CTRL_INHIBIT_SYN_CTX_SWITCH	(1 << 3)
+#define	  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT	(1 << 0)
 #define RING_CONTEXT_STATUS_BUF(ring)	((ring)->mmio_base+0x370)
 #define RING_CONTEXT_STATUS_PTR(ring)	((ring)->mmio_base+0x3a0)
 
@@ -40,10 +42,6 @@ int intel_logical_rings_init(struct drm_device *dev);
 
 int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf,
 				  struct intel_context *ctx);
-void intel_logical_ring_advance_and_submit(
-				struct intel_ringbuffer *ringbuf,
-				struct intel_context *ctx,
-				struct drm_i915_gem_request *request);
 /**
  * intel_logical_ring_advance() - advance the ringbuffer tail
  * @ringbuf: Ringbuffer to advance.
@@ -70,8 +68,6 @@ int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
 			     int num_dwords);
 
 /* Logical Ring Contexts */
-int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
-				       struct intel_context *ctx);
 void intel_lr_context_free(struct intel_context *ctx);
 int intel_lr_context_deferred_create(struct intel_context *ctx,
 				     struct intel_engine_cs *ring);

drivers/gpu/drm/i915/intel_pm.c

@@ -56,24 +56,42 @@ static void gen9_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	/*
-	 * WaDisableSDEUnitClockGating:skl
-	 * This seems to be a pre-production w/a.
-	 */
-	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
-		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+	/* WaEnableLbsSlaRetryTimerDecrement:skl */
+	I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
+		   GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
+}
 
-	/*
-	 * WaDisableDgMirrorFixInHalfSliceChicken5:skl
-	 * This is a pre-production w/a.
-	 */
-	I915_WRITE(GEN9_HALF_SLICE_CHICKEN5,
-		   I915_READ(GEN9_HALF_SLICE_CHICKEN5) &
-		   ~GEN9_DG_MIRROR_FIX_ENABLE);
+static void skl_init_clock_gating(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	/* Wa4x4STCOptimizationDisable:skl */
-	I915_WRITE(CACHE_MODE_1,
-		   _MASKED_BIT_ENABLE(GEN8_4x4_STC_OPTIMIZATION_DISABLE));
+	gen9_init_clock_gating(dev);
+
+	if (INTEL_REVID(dev) == SKL_REVID_A0) {
+		/*
+		 * WaDisableSDEUnitClockGating:skl
+		 * WaSetGAPSunitClckGateDisable:skl
+		 */
+		I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
+			   GEN8_GAPSUNIT_CLOCK_GATE_DISABLE |
+			   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+	}
+
+	if (INTEL_REVID(dev) <= SKL_REVID_D0) {
+		/* WaDisableHDCInvalidation:skl */
+		I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
+			   BDW_DISABLE_HDC_INVALIDATION);
+
+		/* WaDisableChickenBitTSGBarrierAckForFFSliceCS:skl */
+		I915_WRITE(FF_SLICE_CS_CHICKEN2,
+			   I915_READ(FF_SLICE_CS_CHICKEN2) |
+			   GEN9_TSG_BARRIER_ACK_DISABLE);
+	}
+
+	if (INTEL_REVID(dev) <= SKL_REVID_E0)
+		/* WaDisableLSQCROPERFforOCL:skl */
+		I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
+			   GEN8_LQSC_RO_PERF_DIS);
 }
 
 static void i915_pineview_get_mem_freq(struct drm_device *dev)
@@ -1711,6 +1729,8 @@ static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[8])
 				GEN9_MEM_LATENCY_LEVEL_MASK;
 
 		/*
+		 * WaWmMemoryReadLatency:skl
+		 *
 		 * punit doesn't take into account the read latency so we need
 		 * to add 2us to the various latency levels we retrieve from
 		 * the punit.
@@ -3750,7 +3770,7 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
 /* gen6_set_rps is called to update the frequency request, but should also be
  * called when the range (min_delay and max_delay) is modified so that we can
  * update the GEN6_RP_INTERRUPT_LIMITS register accordingly. */
-void gen6_set_rps(struct drm_device *dev, u8 val)
+static void gen6_set_rps(struct drm_device *dev, u8 val)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -3786,6 +3806,27 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
 	trace_intel_gpu_freq_change(val * 50);
 }
 
+static void valleyview_set_rps(struct drm_device *dev, u8 val)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+	WARN_ON(val > dev_priv->rps.max_freq_softlimit);
+	WARN_ON(val < dev_priv->rps.min_freq_softlimit);
+
+	if (WARN_ONCE(IS_CHERRYVIEW(dev) && (val & 1),
+		      "Odd GPU freq value\n"))
+		val &= ~1;
+
+	if (val != dev_priv->rps.cur_freq)
+		vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
+
+	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
+
+	dev_priv->rps.cur_freq = val;
+	trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
+}
+
 /* vlv_set_rps_idle: Set the frequency to Rpn if Gfx clocks are down
  *
  * * If Gfx is Idle, then
@@ -3850,38 +3891,20 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
 
 void gen6_rps_boost(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
-
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (dev_priv->rps.enabled) {
-		if (IS_VALLEYVIEW(dev))
-			valleyview_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
-		else
-			gen6_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
+		intel_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
 		dev_priv->rps.last_adj = 0;
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
-void valleyview_set_rps(struct drm_device *dev, u8 val)
+void intel_set_rps(struct drm_device *dev, u8 val)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
-	WARN_ON(val > dev_priv->rps.max_freq_softlimit);
-	WARN_ON(val < dev_priv->rps.min_freq_softlimit);
-
-	if (WARN_ONCE(IS_CHERRYVIEW(dev) && (val & 1),
-		      "Odd GPU freq value\n"))
-		val &= ~1;
-
-	if (val != dev_priv->rps.cur_freq)
-		vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
-
-	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
-
-	dev_priv->rps.cur_freq = val;
-	trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
+	if (IS_VALLEYVIEW(dev))
+		valleyview_set_rps(dev, val);
+	else
+		gen6_set_rps(dev, val);
 }
 
 static void gen9_disable_rps(struct drm_device *dev)
@@ -5633,6 +5656,10 @@ void intel_enable_gt_powersave(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	/* Powersaving is controlled by the host when inside a VM */
+	if (intel_vgpu_active(dev))
+		return;
+
 	if (IS_IRONLAKE_M(dev)) {
 		mutex_lock(&dev->struct_mutex);
 		ironlake_enable_drps(dev);
@@ -6396,7 +6423,8 @@ void intel_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	dev_priv->display.init_clock_gating(dev);
+	if (dev_priv->display.init_clock_gating)
+		dev_priv->display.init_clock_gating(dev);
 }
 
 void intel_suspend_hw(struct drm_device *dev)
@@ -6422,7 +6450,7 @@ void intel_init_pm(struct drm_device *dev)
 	if (INTEL_INFO(dev)->gen >= 9) {
 		skl_setup_wm_latency(dev);
 
-		dev_priv->display.init_clock_gating = gen9_init_clock_gating;
+		dev_priv->display.init_clock_gating = skl_init_clock_gating;
 		dev_priv->display.update_wm = skl_update_wm;
 		dev_priv->display.update_sprite_wm = skl_update_sprite_wm;
 	} else if (HAS_PCH_SPLIT(dev)) {

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -502,6 +502,68 @@ static void ring_setup_phys_status_page(struct intel_engine_cs *ring)
 	I915_WRITE(HWS_PGA, addr);
 }
 
+static void intel_ring_setup_status_page(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	u32 mmio = 0;
+
+	/* The ring status page addresses are no longer next to the rest of
+	 * the ring registers as of gen7.
+	 */
+	if (IS_GEN7(dev)) {
+		switch (ring->id) {
+		case RCS:
+			mmio = RENDER_HWS_PGA_GEN7;
+			break;
+		case BCS:
+			mmio = BLT_HWS_PGA_GEN7;
+			break;
+		/*
+		 * VCS2 actually doesn't exist on Gen7. Only shut up
+		 * gcc switch check warning
+		 */
+		case VCS2:
+		case VCS:
+			mmio = BSD_HWS_PGA_GEN7;
+			break;
+		case VECS:
+			mmio = VEBOX_HWS_PGA_GEN7;
+			break;
+		}
+	} else if (IS_GEN6(ring->dev)) {
+		mmio = RING_HWS_PGA_GEN6(ring->mmio_base);
+	} else {
+		/* XXX: gen8 returns to sanity */
+		mmio = RING_HWS_PGA(ring->mmio_base);
+	}
+
+	I915_WRITE(mmio, (u32)ring->status_page.gfx_addr);
+	POSTING_READ(mmio);
+
+	/*
+	 * Flush the TLB for this page
+	 *
+	 * FIXME: These two bits have disappeared on gen8, so a question
+	 * arises: do we still need this and if so how should we go about
+	 * invalidating the TLB?
+	 */
+	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8) {
+		u32 reg = RING_INSTPM(ring->mmio_base);
+
+		/* ring should be idle before issuing a sync flush*/
+		WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
+
+		I915_WRITE(reg,
+			   _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE |
+					      INSTPM_SYNC_FLUSH));
+		if (wait_for((I915_READ(reg) & INSTPM_SYNC_FLUSH) == 0,
+			     1000))
+			DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n",
+				  ring->name);
+	}
+}
+
 static bool stop_ring(struct intel_engine_cs *ring)
 {
 	struct drm_i915_private *dev_priv = to_i915(ring->dev);
@@ -788,12 +850,14 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	 * workaround for for a possible hang in the unlikely event a TLB
 	 * invalidation occurs during a PSD flush.
 	 */
-	/* WaForceEnableNonCoherent:bdw */
-	/* WaHdcDisableFetchWhenMasked:bdw */
-	/* WaDisableFenceDestinationToSLM:bdw (GT3 pre-production) */
 	WA_SET_BIT_MASKED(HDC_CHICKEN0,
+			  /* WaForceEnableNonCoherent:bdw */
 			  HDC_FORCE_NON_COHERENT |
+			  /* WaForceContextSaveRestoreNonCoherent:bdw */
+			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
+			  /* WaHdcDisableFetchWhenMasked:bdw */
 			  HDC_DONOT_FETCH_MEM_WHEN_MASKED |
+			  /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */
 			  (IS_BDW_GT3(dev) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
 
 	/* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
@@ -870,6 +934,78 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 			    GEN6_WIZ_HASHING_MASK,
 			    GEN6_WIZ_HASHING_16x4);
 
+	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
+	    INTEL_REVID(dev) == SKL_REVID_D0)
+		/* WaBarrierPerformanceFixDisable:skl */
+		WA_SET_BIT_MASKED(HDC_CHICKEN0,
+				  HDC_FENCE_DEST_SLM_DISABLE |
+				  HDC_BARRIER_PERFORMANCE_DISABLE);
+
+	return 0;
+}
+
+static int gen9_init_workarounds(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* WaDisablePartialInstShootdown:skl */
+	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
+			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
+
+	/* Syncing dependencies between camera and graphics */
+	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
+			  GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
+
+	if (INTEL_REVID(dev) == SKL_REVID_A0 ||
+	    INTEL_REVID(dev) == SKL_REVID_B0) {
+		/* WaDisableDgMirrorFixInHalfSliceChicken5:skl */
+		WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
+				  GEN9_DG_MIRROR_FIX_ENABLE);
+	}
+
+	if (IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0) {
+		/* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl */
+		WA_SET_BIT_MASKED(GEN7_COMMON_SLICE_CHICKEN1,
+				  GEN9_RHWO_OPTIMIZATION_DISABLE);
+		WA_SET_BIT_MASKED(GEN9_SLICE_COMMON_ECO_CHICKEN0,
+				  DISABLE_PIXEL_MASK_CAMMING);
+	}
+
+	if (INTEL_REVID(dev) >= SKL_REVID_C0) {
+		/* WaEnableYV12BugFixInHalfSliceChicken7:skl */
+		WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
+				  GEN9_ENABLE_YV12_BUGFIX);
+	}
+
+	if (INTEL_REVID(dev) <= SKL_REVID_D0) {
+		/*
+		 *Use Force Non-Coherent whenever executing a 3D context. This
+		 * is a workaround for a possible hang in the unlikely event
+		 * a TLB invalidation occurs during a PSD flush.
+		 */
+		/* WaForceEnableNonCoherent:skl */
+		WA_SET_BIT_MASKED(HDC_CHICKEN0,
+				  HDC_FORCE_NON_COHERENT);
+	}
+
+	/* Wa4x4STCOptimizationDisable:skl */
+	WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE);
+
+	/* WaDisablePartialResolveInVc:skl */
+	WA_SET_BIT_MASKED(CACHE_MODE_1, GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE);
+
+	/* WaCcsTlbPrefetchDisable:skl */
+	WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
+			  GEN9_CCS_TLB_PREFETCH_ENABLE);
+
+	return 0;
+}
+
+static int skl_init_workarounds(struct intel_engine_cs *ring)
+{
+	gen9_init_workarounds(ring);
+
 	return 0;
 }
 
@@ -888,6 +1024,11 @@ int init_workarounds_ring(struct intel_engine_cs *ring)
 	if (IS_CHERRYVIEW(dev))
 		return chv_init_workarounds(ring);
 
+	if (IS_SKYLAKE(dev))
+		return skl_init_workarounds(ring);
+	else if (IS_GEN9(dev))
+		return gen9_init_workarounds(ring);
+
 	return 0;
 }
 
@@ -1386,68 +1527,6 @@ i8xx_ring_put_irq(struct intel_engine_cs *ring)
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
 
-void intel_ring_setup_status_page(struct intel_engine_cs *ring)
-{
-	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	u32 mmio = 0;
-
-	/* The ring status page addresses are no longer next to the rest of
-	 * the ring registers as of gen7.
-	 */
-	if (IS_GEN7(dev)) {
-		switch (ring->id) {
-		case RCS:
-			mmio = RENDER_HWS_PGA_GEN7;
-			break;
-		case BCS:
-			mmio = BLT_HWS_PGA_GEN7;
-			break;
-		/*
-		 * VCS2 actually doesn't exist on Gen7. Only shut up
-		 * gcc switch check warning
-		 */
-		case VCS2:
-		case VCS:
-			mmio = BSD_HWS_PGA_GEN7;
-			break;
-		case VECS:
-			mmio = VEBOX_HWS_PGA_GEN7;
-			break;
-		}
-	} else if (IS_GEN6(ring->dev)) {
-		mmio = RING_HWS_PGA_GEN6(ring->mmio_base);
-	} else {
-		/* XXX: gen8 returns to sanity */
-		mmio = RING_HWS_PGA(ring->mmio_base);
-	}
-
-	I915_WRITE(mmio, (u32)ring->status_page.gfx_addr);
-	POSTING_READ(mmio);
-
-	/*
-	 * Flush the TLB for this page
-	 *
-	 * FIXME: These two bits have disappeared on gen8, so a question
-	 * arises: do we still need this and if so how should we go about
-	 * invalidating the TLB?
-	 */
-	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8) {
-		u32 reg = RING_INSTPM(ring->mmio_base);
-
-		/* ring should be idle before issuing a sync flush*/
-		WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
-
-		I915_WRITE(reg,
-			   _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE |
-					      INSTPM_SYNC_FLUSH));
-		if (wait_for((I915_READ(reg) & INSTPM_SYNC_FLUSH) == 0,
-			     1000))
-			DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n",
-				  ring->name);
-	}
-}
-
 static int
 bsd_ring_flush(struct intel_engine_cs *ring,
 	       u32     invalidate_domains,
@@ -2612,19 +2691,13 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 }
 
 /**
- * Initialize the second BSD ring for Broadwell GT3.
- * It is noted that this only exists on Broadwell GT3.
+ * Initialize the second BSD ring (eg. Broadwell GT3, Skylake GT3)
  */
 int intel_init_bsd2_ring_buffer(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring = &dev_priv->ring[VCS2];
 
-	if ((INTEL_INFO(dev)->gen != 8)) {
-		DRM_ERROR("No dual-BSD ring on non-BDW machine\n");
-		return -EINVAL;
-	}
-
 	ring->name = "bsd2 ring";
 	ring->id = VCS2;
 

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -425,7 +425,6 @@ int intel_init_blt_ring_buffer(struct drm_device *dev);
 int intel_init_vebox_ring_buffer(struct drm_device *dev);
 
 u64 intel_ring_get_active_head(struct intel_engine_cs *ring);
-void intel_ring_setup_status_page(struct intel_engine_cs *ring);
 
 int init_workarounds_ring(struct intel_engine_cs *ring);
 

drivers/gpu/drm/i915/intel_runtime_pm.c

@@ -230,6 +230,136 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv,
 	}
 }
 
+#define SKL_DISPLAY_POWERWELL_2_POWER_DOMAINS (		\
+	BIT(POWER_DOMAIN_TRANSCODER_A) |		\
+	BIT(POWER_DOMAIN_PIPE_B) |			\
+	BIT(POWER_DOMAIN_TRANSCODER_B) |		\
+	BIT(POWER_DOMAIN_PIPE_C) |			\
+	BIT(POWER_DOMAIN_TRANSCODER_C) |		\
+	BIT(POWER_DOMAIN_PIPE_B_PANEL_FITTER) |		\
+	BIT(POWER_DOMAIN_PIPE_C_PANEL_FITTER) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_B_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_C_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_D_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_D_4_LANES) |		\
+	BIT(POWER_DOMAIN_AUX_B) |                       \
+	BIT(POWER_DOMAIN_AUX_C) |			\
+	BIT(POWER_DOMAIN_AUX_D) |			\
+	BIT(POWER_DOMAIN_AUDIO) |			\
+	BIT(POWER_DOMAIN_VGA) |				\
+	BIT(POWER_DOMAIN_INIT))
+#define SKL_DISPLAY_POWERWELL_1_POWER_DOMAINS (		\
+	SKL_DISPLAY_POWERWELL_2_POWER_DOMAINS |		\
+	BIT(POWER_DOMAIN_PLLS) |			\
+	BIT(POWER_DOMAIN_PIPE_A) |			\
+	BIT(POWER_DOMAIN_TRANSCODER_EDP) |		\
+	BIT(POWER_DOMAIN_PIPE_A_PANEL_FITTER) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_A_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_A_4_LANES) |		\
+	BIT(POWER_DOMAIN_AUX_A) |			\
+	BIT(POWER_DOMAIN_INIT))
+#define SKL_DISPLAY_DDI_A_E_POWER_DOMAINS (		\
+	BIT(POWER_DOMAIN_PORT_DDI_A_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_A_4_LANES) |		\
+	BIT(POWER_DOMAIN_INIT))
+#define SKL_DISPLAY_DDI_B_POWER_DOMAINS (		\
+	BIT(POWER_DOMAIN_PORT_DDI_B_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) |		\
+	BIT(POWER_DOMAIN_INIT))
+#define SKL_DISPLAY_DDI_C_POWER_DOMAINS (		\
+	BIT(POWER_DOMAIN_PORT_DDI_C_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) |		\
+	BIT(POWER_DOMAIN_INIT))
+#define SKL_DISPLAY_DDI_D_POWER_DOMAINS (		\
+	BIT(POWER_DOMAIN_PORT_DDI_D_2_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_D_4_LANES) |		\
+	BIT(POWER_DOMAIN_INIT))
+#define SKL_DISPLAY_MISC_IO_POWER_DOMAINS (		\
+	SKL_DISPLAY_POWERWELL_1_POWER_DOMAINS)
+#define SKL_DISPLAY_ALWAYS_ON_POWER_DOMAINS (		\
+	(POWER_DOMAIN_MASK & ~(SKL_DISPLAY_POWERWELL_1_POWER_DOMAINS |	\
+	SKL_DISPLAY_POWERWELL_2_POWER_DOMAINS |		\
+	SKL_DISPLAY_DDI_A_E_POWER_DOMAINS |		\
+	SKL_DISPLAY_DDI_B_POWER_DOMAINS |		\
+	SKL_DISPLAY_DDI_C_POWER_DOMAINS |		\
+	SKL_DISPLAY_DDI_D_POWER_DOMAINS |		\
+	SKL_DISPLAY_MISC_IO_POWER_DOMAINS)) |		\
+	BIT(POWER_DOMAIN_INIT))
+
+static void skl_set_power_well(struct drm_i915_private *dev_priv,
+			struct i915_power_well *power_well, bool enable)
+{
+	uint32_t tmp, fuse_status;
+	uint32_t req_mask, state_mask;
+	bool check_fuse_status = false;
+
+	tmp = I915_READ(HSW_PWR_WELL_DRIVER);
+	fuse_status = I915_READ(SKL_FUSE_STATUS);
+
+	switch (power_well->data) {
+	case SKL_DISP_PW_1:
+		if (wait_for((I915_READ(SKL_FUSE_STATUS) &
+			SKL_FUSE_PG0_DIST_STATUS), 1)) {
+			DRM_ERROR("PG0 not enabled\n");
+			return;
+		}
+		break;
+	case SKL_DISP_PW_2:
+		if (!(fuse_status & SKL_FUSE_PG1_DIST_STATUS)) {
+			DRM_ERROR("PG1 in disabled state\n");
+			return;
+		}
+		break;
+	case SKL_DISP_PW_DDI_A_E:
+	case SKL_DISP_PW_DDI_B:
+	case SKL_DISP_PW_DDI_C:
+	case SKL_DISP_PW_DDI_D:
+	case SKL_DISP_PW_MISC_IO:
+		break;
+	default:
+		WARN(1, "Unknown power well %lu\n", power_well->data);
+		return;
+	}
+
+	req_mask = SKL_POWER_WELL_REQ(power_well->data);
+	state_mask = SKL_POWER_WELL_STATE(power_well->data);
+
+	if (enable) {
+		if (!(tmp & req_mask)) {
+			I915_WRITE(HSW_PWR_WELL_DRIVER, tmp | req_mask);
+			DRM_DEBUG_KMS("Enabling %s\n", power_well->name);
+		}
+
+		if (!(tmp & state_mask)) {
+			if (wait_for((I915_READ(HSW_PWR_WELL_DRIVER) &
+				state_mask), 1))
+				DRM_ERROR("%s enable timeout\n",
+					power_well->name);
+			check_fuse_status = true;
+		}
+	} else {
+		if (tmp & req_mask) {
+			I915_WRITE(HSW_PWR_WELL_DRIVER,	tmp & ~req_mask);
+			POSTING_READ(HSW_PWR_WELL_DRIVER);
+			DRM_DEBUG_KMS("Disabling %s\n", power_well->name);
+		}
+	}
+
+	if (check_fuse_status) {
+		if (power_well->data == SKL_DISP_PW_1) {
+			if (wait_for((I915_READ(SKL_FUSE_STATUS) &
+				SKL_FUSE_PG1_DIST_STATUS), 1))
+				DRM_ERROR("PG1 distributing status timeout\n");
+		} else if (power_well->data == SKL_DISP_PW_2) {
+			if (wait_for((I915_READ(SKL_FUSE_STATUS) &
+				SKL_FUSE_PG2_DIST_STATUS), 1))
+				DRM_ERROR("PG2 distributing status timeout\n");
+		}
+	}
+}
+
 static void hsw_power_well_sync_hw(struct drm_i915_private *dev_priv,
 				   struct i915_power_well *power_well)
 {
@@ -255,6 +385,36 @@ static void hsw_power_well_disable(struct drm_i915_private *dev_priv,
 	hsw_set_power_well(dev_priv, power_well, false);
 }
 
+static bool skl_power_well_enabled(struct drm_i915_private *dev_priv,
+					struct i915_power_well *power_well)
+{
+	uint32_t mask = SKL_POWER_WELL_REQ(power_well->data) |
+		SKL_POWER_WELL_STATE(power_well->data);
+
+	return (I915_READ(HSW_PWR_WELL_DRIVER) & mask) == mask;
+}
+
+static void skl_power_well_sync_hw(struct drm_i915_private *dev_priv,
+				struct i915_power_well *power_well)
+{
+	skl_set_power_well(dev_priv, power_well, power_well->count > 0);
+
+	/* Clear any request made by BIOS as driver is taking over */
+	I915_WRITE(HSW_PWR_WELL_BIOS, 0);
+}
+
+static void skl_power_well_enable(struct drm_i915_private *dev_priv,
+				struct i915_power_well *power_well)
+{
+	skl_set_power_well(dev_priv, power_well, true);
+}
+
+static void skl_power_well_disable(struct drm_i915_private *dev_priv,
+				struct i915_power_well *power_well)
+{
+	skl_set_power_well(dev_priv, power_well, false);
+}
+
 static void i9xx_always_on_power_well_noop(struct drm_i915_private *dev_priv,
 					   struct i915_power_well *power_well)
 {
@@ -829,6 +989,13 @@ static const struct i915_power_well_ops hsw_power_well_ops = {
 	.is_enabled = hsw_power_well_enabled,
 };
 
+static const struct i915_power_well_ops skl_power_well_ops = {
+	.sync_hw = skl_power_well_sync_hw,
+	.enable = skl_power_well_enable,
+	.disable = skl_power_well_disable,
+	.is_enabled = skl_power_well_enabled,
+};
+
 static struct i915_power_well hsw_power_wells[] = {
 	{
 		.name = "always-on",
@@ -1059,6 +1226,57 @@ static struct i915_power_well *lookup_power_well(struct drm_i915_private *dev_pr
 	return NULL;
 }
 
+static struct i915_power_well skl_power_wells[] = {
+	{
+		.name = "always-on",
+		.always_on = 1,
+		.domains = SKL_DISPLAY_ALWAYS_ON_POWER_DOMAINS,
+		.ops = &i9xx_always_on_power_well_ops,
+	},
+	{
+		.name = "power well 1",
+		.domains = SKL_DISPLAY_POWERWELL_1_POWER_DOMAINS,
+		.ops = &skl_power_well_ops,
+		.data = SKL_DISP_PW_1,
+	},
+	{
+		.name = "MISC IO power well",
+		.domains = SKL_DISPLAY_MISC_IO_POWER_DOMAINS,
+		.ops = &skl_power_well_ops,
+		.data = SKL_DISP_PW_MISC_IO,
+	},
+	{
+		.name = "power well 2",
+		.domains = SKL_DISPLAY_POWERWELL_2_POWER_DOMAINS,
+		.ops = &skl_power_well_ops,
+		.data = SKL_DISP_PW_2,
+	},
+	{
+		.name = "DDI A/E power well",
+		.domains = SKL_DISPLAY_DDI_A_E_POWER_DOMAINS,
+		.ops = &skl_power_well_ops,
+		.data = SKL_DISP_PW_DDI_A_E,
+	},
+	{
+		.name = "DDI B power well",
+		.domains = SKL_DISPLAY_DDI_B_POWER_DOMAINS,
+		.ops = &skl_power_well_ops,
+		.data = SKL_DISP_PW_DDI_B,
+	},
+	{
+		.name = "DDI C power well",
+		.domains = SKL_DISPLAY_DDI_C_POWER_DOMAINS,
+		.ops = &skl_power_well_ops,
+		.data = SKL_DISP_PW_DDI_C,
+	},
+	{
+		.name = "DDI D power well",
+		.domains = SKL_DISPLAY_DDI_D_POWER_DOMAINS,
+		.ops = &skl_power_well_ops,
+		.data = SKL_DISP_PW_DDI_D,
+	},
+};
+
 #define set_power_wells(power_domains, __power_wells) ({		\
 	(power_domains)->power_wells = (__power_wells);			\
 	(power_domains)->power_well_count = ARRAY_SIZE(__power_wells);	\
@@ -1085,6 +1303,8 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 		set_power_wells(power_domains, hsw_power_wells);
 	} else if (IS_BROADWELL(dev_priv->dev)) {
 		set_power_wells(power_domains, bdw_power_wells);
+	} else if (IS_SKYLAKE(dev_priv->dev)) {
+		set_power_wells(power_domains, skl_power_wells);
 	} else if (IS_CHERRYVIEW(dev_priv->dev)) {
 		set_power_wells(power_domains, chv_power_wells);
 	} else if (IS_VALLEYVIEW(dev_priv->dev)) {

drivers/gpu/drm/i915/intel_sprite.c

@@ -245,11 +245,11 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc,
 		BUG();
 	}
 
-	switch (obj->tiling_mode) {
-	case I915_TILING_NONE:
+	switch (fb->modifier[0]) {
+	case DRM_FORMAT_MOD_NONE:
 		stride = fb->pitches[0] >> 6;
 		break;
-	case I915_TILING_X:
+	case I915_FORMAT_MOD_X_TILED:
 		plane_ctl |= PLANE_CTL_TILED_X;
 		stride = fb->pitches[0] >> 9;
 		break;
@@ -993,7 +993,7 @@ intel_pre_disable_primary(struct drm_crtc *crtc)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
 	mutex_lock(&dev->struct_mutex);
-	if (dev_priv->fbc.plane == intel_crtc->plane)
+	if (dev_priv->fbc.crtc == intel_crtc)
 		intel_fbc_disable(dev);
 	mutex_unlock(&dev->struct_mutex);
 
@@ -1076,7 +1076,6 @@ intel_check_sprite_plane(struct drm_plane *plane,
 	struct intel_crtc *intel_crtc = to_intel_crtc(state->base.crtc);
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct drm_framebuffer *fb = state->base.fb;
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	int crtc_x, crtc_y;
 	unsigned int crtc_w, crtc_h;
 	uint32_t src_x, src_y, src_w, src_h;
@@ -1106,16 +1105,6 @@ intel_check_sprite_plane(struct drm_plane *plane,
 		return -EINVAL;
 	}
 
-	/* Sprite planes can be linear or x-tiled surfaces */
-	switch (obj->tiling_mode) {
-		case I915_TILING_NONE:
-		case I915_TILING_X:
-			break;
-		default:
-			DRM_DEBUG_KMS("Unsupported tiling mode\n");
-			return -EINVAL;
-	}
-
 	/*
 	 * FIXME the following code does a bunch of fuzzy adjustments to the
 	 * coordinates and sizes. We probably need some way to decide whether

drivers/gpu/drm/i915/intel_uncore.c

@@ -23,6 +23,7 @@
 
 #include "i915_drv.h"
 #include "intel_drv.h"
+#include "i915_vgpu.h"
 
 #include <linux/pm_runtime.h>
 
@@ -328,8 +329,9 @@ static void intel_uncore_ellc_detect(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if ((IS_HASWELL(dev) || IS_BROADWELL(dev)) &&
-	    (__raw_i915_read32(dev_priv, HSW_EDRAM_PRESENT) == 1)) {
+	if ((IS_HASWELL(dev) || IS_BROADWELL(dev) ||
+	     INTEL_INFO(dev)->gen >= 9) &&
+	    (__raw_i915_read32(dev_priv, HSW_EDRAM_PRESENT) & EDRAM_ENABLED)) {
 		/* The docs do not explain exactly how the calculation can be
 		 * made. It is somewhat guessable, but for now, it's always
 		 * 128MB.
@@ -640,6 +642,14 @@ static inline void __force_wake_get(struct drm_i915_private *dev_priv,
 		dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains);
 }
 
+#define __vgpu_read(x) \
+static u##x \
+vgpu_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
+	GEN6_READ_HEADER(x); \
+	val = __raw_i915_read##x(dev_priv, reg); \
+	GEN6_READ_FOOTER; \
+}
+
 #define __gen6_read(x) \
 static u##x \
 gen6_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
@@ -703,6 +713,10 @@ gen9_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
 	GEN6_READ_FOOTER; \
 }
 
+__vgpu_read(8)
+__vgpu_read(16)
+__vgpu_read(32)
+__vgpu_read(64)
 __gen9_read(8)
 __gen9_read(16)
 __gen9_read(32)
@@ -724,6 +738,7 @@ __gen6_read(64)
 #undef __chv_read
 #undef __vlv_read
 #undef __gen6_read
+#undef __vgpu_read
 #undef GEN6_READ_FOOTER
 #undef GEN6_READ_HEADER
 
@@ -807,6 +822,14 @@ hsw_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace)
 	GEN6_WRITE_FOOTER; \
 }
 
+#define __vgpu_write(x) \
+static void vgpu_write##x(struct drm_i915_private *dev_priv, \
+			  off_t reg, u##x val, bool trace) { \
+	GEN6_WRITE_HEADER; \
+	__raw_i915_write##x(dev_priv, reg, val); \
+	GEN6_WRITE_FOOTER; \
+}
+
 static const u32 gen8_shadowed_regs[] = {
 	FORCEWAKE_MT,
 	GEN6_RPNSWREQ,
@@ -924,12 +947,17 @@ __gen6_write(8)
 __gen6_write(16)
 __gen6_write(32)
 __gen6_write(64)
+__vgpu_write(8)
+__vgpu_write(16)
+__vgpu_write(32)
+__vgpu_write(64)
 
 #undef __gen9_write
 #undef __chv_write
 #undef __gen8_write
 #undef __hsw_write
 #undef __gen6_write
+#undef __vgpu_write
 #undef GEN6_WRITE_FOOTER
 #undef GEN6_WRITE_HEADER
 
@@ -972,6 +1000,7 @@ static void fw_domain_init(struct drm_i915_private *dev_priv,
 		d->val_set = FORCEWAKE_KERNEL;
 		d->val_clear = 0;
 	} else {
+		/* WaRsClearFWBitsAtReset:bdw,skl */
 		d->val_reset = _MASKED_BIT_DISABLE(0xffff);
 		d->val_set = _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL);
 		d->val_clear = _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL);
@@ -1082,6 +1111,8 @@ void intel_uncore_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	i915_check_vgpu(dev);
+
 	intel_uncore_ellc_detect(dev);
 	intel_uncore_fw_domains_init(dev);
 	__intel_uncore_early_sanitize(dev, false);
@@ -1130,6 +1161,11 @@ void intel_uncore_init(struct drm_device *dev)
 		break;
 	}
 
+	if (intel_vgpu_active(dev)) {
+		ASSIGN_WRITE_MMIO_VFUNCS(vgpu);
+		ASSIGN_READ_MMIO_VFUNCS(vgpu);
+	}
+
 	i915_check_and_clear_faults(dev);
 }
 #undef ASSIGN_WRITE_MMIO_VFUNCS

include/drm/drm_crtc.h

@@ -202,6 +202,7 @@ struct drm_framebuffer {
 	const struct drm_framebuffer_funcs *funcs;
 	unsigned int pitches[4];
 	unsigned int offsets[4];
+	uint64_t modifier[4];
 	unsigned int width;
 	unsigned int height;
 	/* depth can be 15 or 16 */
@@ -1155,6 +1156,9 @@ struct drm_mode_config {
 	/* whether async page flip is supported or not */
 	bool async_page_flip;
 
+	/* whether the driver supports fb modifiers */
+	bool allow_fb_modifiers;
+
 	/* cursor size */
 	uint32_t cursor_width, cursor_height;
 };

include/drm/i915_pciids.h

@@ -259,21 +259,31 @@
 	INTEL_VGA_DEVICE(0x22b2, info), \
 	INTEL_VGA_DEVICE(0x22b3, info)
 
-#define INTEL_SKL_IDS(info) \
-	INTEL_VGA_DEVICE(0x1916, info), /* ULT GT2 */ \
+#define INTEL_SKL_GT1_IDS(info)	\
 	INTEL_VGA_DEVICE(0x1906, info), /* ULT GT1 */ \
-	INTEL_VGA_DEVICE(0x1926, info), /* ULT GT3 */ \
-	INTEL_VGA_DEVICE(0x1921, info), /* ULT GT2F */ \
 	INTEL_VGA_DEVICE(0x190E, info), /* ULX GT1 */ \
+	INTEL_VGA_DEVICE(0x1902, info), /* DT  GT1 */ \
+	INTEL_VGA_DEVICE(0x190B, info), /* Halo GT1 */ \
+	INTEL_VGA_DEVICE(0x190A, info) /* SRV GT1 */
+
+#define INTEL_SKL_GT2_IDS(info)	\
+	INTEL_VGA_DEVICE(0x1916, info), /* ULT GT2 */ \
+	INTEL_VGA_DEVICE(0x1921, info), /* ULT GT2F */ \
 	INTEL_VGA_DEVICE(0x191E, info), /* ULX GT2 */ \
 	INTEL_VGA_DEVICE(0x1912, info), /* DT  GT2 */ \
-	INTEL_VGA_DEVICE(0x1902, info), /* DT  GT1 */ \
 	INTEL_VGA_DEVICE(0x191B, info), /* Halo GT2 */ \
-	INTEL_VGA_DEVICE(0x192B, info), /* Halo GT3 */ \
-	INTEL_VGA_DEVICE(0x190B, info), /* Halo GT1 */ \
 	INTEL_VGA_DEVICE(0x191A, info), /* SRV GT2 */ \
-	INTEL_VGA_DEVICE(0x192A, info), /* SRV GT3 */ \
-	INTEL_VGA_DEVICE(0x190A, info), /* SRV GT1 */ \
 	INTEL_VGA_DEVICE(0x191D, info)  /* WKS GT2 */
 
+#define INTEL_SKL_GT3_IDS(info) \
+	INTEL_VGA_DEVICE(0x1926, info), /* ULT GT3 */ \
+	INTEL_VGA_DEVICE(0x192B, info), /* Halo GT3 */ \
+	INTEL_VGA_DEVICE(0x192A, info) /* SRV GT3 */ \
+
+#define INTEL_SKL_IDS(info) \
+	INTEL_SKL_GT1_IDS(info), \
+	INTEL_SKL_GT2_IDS(info), \
+	INTEL_SKL_GT3_IDS(info)
+
+
 #endif /* _I915_PCIIDS_H */

include/uapi/drm/drm.h

@@ -630,6 +630,7 @@ struct drm_gem_open {
  */
 #define DRM_CAP_CURSOR_WIDTH		0x8
 #define DRM_CAP_CURSOR_HEIGHT		0x9
+#define DRM_CAP_ADDFB2_MODIFIERS	0x10
 
 /** DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {

include/uapi/drm/drm_fourcc.h

@@ -129,4 +129,67 @@
 #define DRM_FORMAT_YUV444	fourcc_code('Y', 'U', '2', '4') /* non-subsampled Cb (1) and Cr (2) planes */
 #define DRM_FORMAT_YVU444	fourcc_code('Y', 'V', '2', '4') /* non-subsampled Cr (1) and Cb (2) planes */
 
+
+/*
+ * Format Modifiers:
+ *
+ * Format modifiers describe, typically, a re-ordering or modification
+ * of the data in a plane of an FB.  This can be used to express tiled/
+ * swizzled formats, or compression, or a combination of the two.
+ *
+ * The upper 8 bits of the format modifier are a vendor-id as assigned
+ * below.  The lower 56 bits are assigned as vendor sees fit.
+ */
+
+/* Vendor Ids: */
+#define DRM_FORMAT_MOD_NONE           0
+#define DRM_FORMAT_MOD_VENDOR_INTEL   0x01
+#define DRM_FORMAT_MOD_VENDOR_AMD     0x02
+#define DRM_FORMAT_MOD_VENDOR_NV      0x03
+#define DRM_FORMAT_MOD_VENDOR_SAMSUNG 0x04
+#define DRM_FORMAT_MOD_VENDOR_QCOM    0x05
+/* add more to the end as needed */
+
+#define fourcc_mod_code(vendor, val) \
+	((((u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | (val & 0x00ffffffffffffffL))
+
+/*
+ * Format Modifier tokens:
+ *
+ * When adding a new token please document the layout with a code comment,
+ * similar to the fourcc codes above. drm_fourcc.h is considered the
+ * authoritative source for all of these.
+ */
+
+/* Intel framebuffer modifiers */
+
+/*
+ * Intel X-tiling layout
+ *
+ * This is a tiled layout using 4Kb tiles (except on gen2 where the tiles 2Kb)
+ * in row-major layout. Within the tile bytes are laid out row-major, with
+ * a platform-dependent stride. On top of that the memory can apply
+ * platform-depending swizzling of some higher address bits into bit6.
+ *
+ * This format is highly platforms specific and not useful for cross-driver
+ * sharing. It exists since on a given platform it does uniquely identify the
+ * layout in a simple way for i915-specific userspace.
+ */
+#define I915_FORMAT_MOD_X_TILED	fourcc_mod_code(INTEL, 1)
+
+/*
+ * Intel Y-tiling layout
+ *
+ * This is a tiled layout using 4Kb tiles (except on gen2 where the tiles 2Kb)
+ * in row-major layout. Within the tile bytes are laid out in OWORD (16 bytes)
+ * chunks column-major, with a platform-dependent height. On top of that the
+ * memory can apply platform-depending swizzling of some higher address bits
+ * into bit6.
+ *
+ * This format is highly platforms specific and not useful for cross-driver
+ * sharing. It exists since on a given platform it does uniquely identify the
+ * layout in a simple way for i915-specific userspace.
+ */
+#define I915_FORMAT_MOD_Y_TILED	fourcc_mod_code(INTEL, 2)
+
 #endif /* DRM_FOURCC_H */

include/uapi/drm/drm_mode.h

@@ -336,6 +336,7 @@ struct drm_mode_fb_cmd {
 };
 
 #define DRM_MODE_FB_INTERLACED	(1<<0) /* for interlaced framebuffers */
+#define DRM_MODE_FB_MODIFIERS	(1<<1) /* enables ->modifer[] */
 
 struct drm_mode_fb_cmd2 {
 	__u32 fb_id;
@@ -356,10 +357,18 @@ struct drm_mode_fb_cmd2 {
 	 * So it would consist of Y as offsets[0] and UV as
 	 * offsets[1].  Note that offsets[0] will generally
 	 * be 0 (but this is not required).
+	 *
+	 * To accommodate tiled, compressed, etc formats, a per-plane
+	 * modifier can be specified.  The default value of zero
+	 * indicates "native" format as specified by the fourcc.
+	 * Vendor specific modifier token.  This allows, for example,
+	 * different tiling/swizzling pattern on different planes.
+	 * See discussion above of DRM_FORMAT_MOD_xxx.
 	 */
 	__u32 handles[4];
 	__u32 pitches[4]; /* pitch for each plane */
 	__u32 offsets[4]; /* offset of each plane */
+	__u64 modifier[4]; /* ie, tiling, compressed (per plane) */
 };
 
 #define DRM_MODE_FB_DIRTY_ANNOTATE_COPY 0x01