Merge tag 'drm-next-2020-08-06' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "New xilinx displayport driver, AMD support for two new GPUs (more
  header files), i915 initial support for RocketLake and some work on
  their DG1 (discrete chip).

  The core also grew some lockdep annotations to try and constrain what
  drivers do with dma-fences, and added some documentation on why the
  idea of indefinite fences doesn't work.

  The long list is below.

  I do have some fixes trees outstanding, but I'll follow up with those
  later.

  core:
   - add user def flag to cmd line modes
   - dma_fence_wait added might_sleep
   - dma-fence lockdep annotations
   - indefinite fences are bad documentation
   - gem CMA functions used in more drivers
   - struct mutex removal
   - more drm_ debug macro usage
   - set/drop master api fixes
   - fix for drm/mm hole size comparison
   - drm/mm remove invalid entry optimization
   - optimise drm/mm hole handling
   - VRR debugfs added
   - uncompressed AFBC modifier support
   - multiple display id blocks in EDID
   - multiple driver sg handling fixes
   - __drm_atomic_helper_crtc_reset in all drivers
   - managed vram helpers

  ttm:
   - ttm_mem_reg handling cleanup
   - remove bo offset field
   - drop CMA memtype flag
   - drop mappable flag

  xilinx:
   - New Xilinx ZynqMP DisplayPort Subsystem driver

  nouveau:
   - add CRC support
   - start using NVIDIA published class header files
   - convert all push buffer emission to new macros
   - Proper push buffer space management for EVO/NVD channels.
   - firmware loading fixes
   - 2MiB system memory pages support on Pascal and newer

  vkms:
   - larger cursor support

  i915:
   - Rocketlake platform enablement
   - Early DG1 enablement
   - Numerous GEM refactorings
   - DP MST fixes
   - FBC, PSR, Cursor, Color, Gamma fixes
   - TGL, RKL, EHL workaround updates
   - TGL 8K display support fixes
   - SDVO/HDMI/DVI fixes

  amdgpu:
   - Initial support for Sienna Cichlid GPU
   - Initial support for Navy Flounder GPU
   - SI UVD/VCE support
   - expose rotation property
   - Add support for unique id on Arcturus
   - Enable runtime PM on vega10 boards that support BACO
   - Skip BAR resizing if the bios already did id
   - Major swSMU code cleanup
   - Fixes for DCN bandwidth calculations

  amdkfd:
   - Track SDMA usage per process
   - SMI events interface

  radeon:
   - Default to on chip GART for AGP boards on all arches
   - Runtime PM reference count fixes

  msm:
   - headers regenerated causing churn
   - a650/a640 display and GPU enablement
   - dpu dither support for 6bpc panels
   - dpu cursor fix
   - dsi/mdp5 enablement for sdm630/sdm636/sdm66

  tegra:
   - video capture prep support
   - reflection support

  mediatek:
   - convert mtk_dsi to bridge API

  meson:
   - FBC support

  sun4i:
   - iommu support

  rockchip:
   - register locking fix
   - per-pixel alpha support PX30 VOP

  mgag200:
   - ported to simple and shmem helpers
   - device init cleanups
   - use managed pci functions
   - dropped hw cursor support

  ast:
   - use managed pci functions
   - use managed VRAM helpers
   - rework cursor support

  malidp:
   - dev_groups support

  hibmc:
   - refactor hibmc_drv_vdac:

  vc4:
   - create TXP CRTC

  imx:
   - error path fixes and cleanups

  etnaviv:
   - clock handling and error handling cleanups
   - use pin_user_pages"

* tag 'drm-next-2020-08-06' of git://anongit.freedesktop.org/drm/drm: (1747 commits)
  drm/msm: use kthread_create_worker instead of kthread_run
  drm/msm/mdp5: Add MDP5 configuration for SDM636/660
  drm/msm/dsi: Add DSI configuration for SDM660
  drm/msm/mdp5: Add MDP5 configuration for SDM630
  drm/msm/dsi: Add phy configuration for SDM630/636/660
  drm/msm/a6xx: add A640/A650 hwcg
  drm/msm/a6xx: hwcg tables in gpulist
  drm/msm/dpu: add SM8250 to hw catalog
  drm/msm/dpu: add SM8150 to hw catalog
  drm/msm/dpu: intf timing path for displayport
  drm/msm/dpu: set missing flush bits for INTF_2 and INTF_3
  drm/msm/dpu: don't use INTF_INPUT_CTRL feature on sdm845
  drm/msm/dpu: move some sspp caps to dpu_caps
  drm/msm/dpu: update UBWC config for sm8150 and sm8250
  drm/msm/dpu: use right setup_blend_config for sm8150 and sm8250
  drm/msm/a6xx: set ubwc config for A640 and A650
  drm/msm/adreno: un-open-code some packets
  drm/msm: sync generated headers
  drm/msm/a6xx: add build_bw_table for A640/A650
  drm/msm/a6xx: fix crashstate capture for A650
  ...

9 files changed, 54 insertions, 75 deletions

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 8b87f130f7f1..f1940939260a 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1904,19 +1904,10 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 		goto err_free_bb;
 	}
 
-	ret = i915_gem_object_prepare_write(bb->obj, &bb->clflush);
-	if (ret)
-		goto err_free_obj;
-
 	bb->va = i915_gem_object_pin_map(bb->obj, I915_MAP_WB);
 	if (IS_ERR(bb->va)) {
 		ret = PTR_ERR(bb->va);
-		goto err_finish_shmem_access;
-	}
-
-	if (bb->clflush & CLFLUSH_BEFORE) {
-		drm_clflush_virt_range(bb->va, bb->obj->base.size);
-		bb->clflush &= ~CLFLUSH_BEFORE;
+		goto err_free_obj;
 	}
 
 	ret = copy_gma_to_hva(s->vgpu, mm,
@@ -1935,7 +1926,6 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 	INIT_LIST_HEAD(&bb->list);
 	list_add(&bb->list, &s->workload->shadow_bb);
 
-	bb->accessing = true;
 	bb->bb_start_cmd_va = s->ip_va;
 
 	if ((s->buf_type == BATCH_BUFFER_INSTRUCTION) && (!s->is_ctx_wa))
@@ -1956,8 +1946,6 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 	return 0;
 err_unmap:
 	i915_gem_object_unpin_map(bb->obj);
-err_finish_shmem_access:
-	i915_gem_object_finish_access(bb->obj);
 err_free_obj:
 	i915_gem_object_put(bb->obj);
 err_free_bb:
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index a1696e9ce4b6..7ba16ddfe75f 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -199,8 +199,10 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			SDE_PORTC_HOTPLUG_CPT |
 			SDE_PORTD_HOTPLUG_CPT);
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
-	    IS_COFFEELAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv) ||
+	    IS_KABYLAKE(dev_priv) ||
+	    IS_COFFEELAKE(dev_priv) ||
+	    IS_COMETLAKE(dev_priv)) {
 		vgpu_vreg_t(vgpu, SDEISR) &= ~(SDE_PORTA_HOTPLUG_SPT |
 				SDE_PORTE_HOTPLUG_SPT);
 		vgpu_vreg_t(vgpu, SKL_FUSE_STATUS) |=
@@ -314,8 +316,10 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 		vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED;
 	}
 
-	if ((IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
-	     IS_COFFEELAKE(dev_priv)) &&
+	if ((IS_SKYLAKE(dev_priv) ||
+	     IS_KABYLAKE(dev_priv) ||
+	     IS_COFFEELAKE(dev_priv) ||
+	     IS_COMETLAKE(dev_priv)) &&
 			intel_vgpu_has_monitor_on_port(vgpu, PORT_E)) {
 		vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTE_HOTPLUG_SPT;
 	}
@@ -498,8 +502,10 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected)
 	struct drm_i915_private *i915 = vgpu->gvt->gt->i915;
 
 	/* TODO: add more platforms support */
-	if (IS_SKYLAKE(i915) || IS_KABYLAKE(i915) ||
-	    IS_COFFEELAKE(i915)) {
+	if (IS_SKYLAKE(i915) ||
+	    IS_KABYLAKE(i915) ||
+	    IS_COFFEELAKE(i915) ||
+	    IS_COMETLAKE(i915)) {
 		if (connected) {
 			vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
 				SFUSE_STRAP_DDID_DETECTED;
@@ -527,8 +533,10 @@ void intel_vgpu_clean_display(struct intel_vgpu *vgpu)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->gt->i915;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
-	    IS_COFFEELAKE(dev_priv))
+	if (IS_SKYLAKE(dev_priv) ||
+	    IS_KABYLAKE(dev_priv) ||
+	    IS_COFFEELAKE(dev_priv) ||
+	    IS_COMETLAKE(dev_priv))
 		clean_virtual_dp_monitor(vgpu, PORT_D);
 	else
 		clean_virtual_dp_monitor(vgpu, PORT_B);
@@ -551,8 +559,10 @@ int intel_vgpu_init_display(struct intel_vgpu *vgpu, u64 resolution)
 
 	intel_vgpu_init_i2c_edid(vgpu);
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
-	    IS_COFFEELAKE(dev_priv))
+	if (IS_SKYLAKE(dev_priv) ||
+	    IS_KABYLAKE(dev_priv) ||
+	    IS_COFFEELAKE(dev_priv) ||
+	    IS_COMETLAKE(dev_priv))
 		return setup_virtual_dp_monitor(vgpu, PORT_D, GVT_DP_D,
 						resolution);
 	else
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 37fc460414a8..c3eb3838fe88 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -198,6 +198,7 @@ static void vgpu_gem_release(struct drm_i915_gem_object *gem_obj)
 }
 
 static const struct drm_i915_gem_object_ops intel_vgpu_gem_ops = {
+	.name = "i915_gem_object_vgpu",
 	.flags = I915_GEM_OBJECT_IS_PROXY,
 	.get_pages = vgpu_gem_get_pages,
 	.put_pages = vgpu_gem_put_pages,
diff --git a/drivers/gpu/drm/i915/gvt/edid.c b/drivers/gpu/drm/i915/gvt/edid.c
index 190651df5db1..22247805c345 100644
--- a/drivers/gpu/drm/i915/gvt/edid.c
+++ b/drivers/gpu/drm/i915/gvt/edid.c
@@ -149,7 +149,7 @@ static int gmbus0_mmio_write(struct intel_vgpu *vgpu,
 
 	if (IS_BROXTON(i915))
 		port = bxt_get_port_from_gmbus0(pin_select);
-	else if (IS_COFFEELAKE(i915))
+	else if (IS_COFFEELAKE(i915) || IS_COMETLAKE(i915))
 		port = cnp_get_port_from_gmbus0(pin_select);
 	else
 		port = get_port_from_gmbus0(pin_select);
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index fadd2adb8030..63bba7b4bb2f 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -59,7 +59,7 @@ unsigned long intel_gvt_get_device_type(struct intel_gvt *gvt)
 		return D_KBL;
 	else if (IS_BROXTON(i915))
 		return D_BXT;
-	else if (IS_COFFEELAKE(i915))
+	else if (IS_COFFEELAKE(i915) || IS_COMETLAKE(i915))
 		return D_CFL;
 
 	return 0;
@@ -347,7 +347,7 @@ static int gdrst_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 			gvt_dbg_mmio("vgpu%d: request GUC Reset\n", vgpu->id);
 			vgpu_vreg_t(vgpu, GUC_STATUS) |= GS_MIA_IN_RESET;
 		}
-		engine_mask &= INTEL_INFO(vgpu->gvt->gt->i915)->engine_mask;
+		engine_mask &= vgpu->gvt->gt->info.engine_mask;
 	}
 
 	/* vgpu_lock already hold by emulate mmio r/w */
@@ -1435,7 +1435,8 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
 	case GEN9_PCODE_READ_MEM_LATENCY:
 		if (IS_SKYLAKE(vgpu->gvt->gt->i915) ||
 		    IS_KABYLAKE(vgpu->gvt->gt->i915) ||
-		    IS_COFFEELAKE(vgpu->gvt->gt->i915)) {
+		    IS_COFFEELAKE(vgpu->gvt->gt->i915) ||
+		    IS_COMETLAKE(vgpu->gvt->gt->i915)) {
 			/**
 			 * "Read memory latency" command on gen9.
 			 * Below memory latency values are read
@@ -1460,7 +1461,8 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
 	case SKL_PCODE_CDCLK_CONTROL:
 		if (IS_SKYLAKE(vgpu->gvt->gt->i915) ||
 		    IS_KABYLAKE(vgpu->gvt->gt->i915) ||
-		    IS_COFFEELAKE(vgpu->gvt->gt->i915))
+		    IS_COFFEELAKE(vgpu->gvt->gt->i915) ||
+		    IS_COMETLAKE(vgpu->gvt->gt->i915))
 			*data0 = SKL_CDCLK_READY_FOR_CHANGE;
 		break;
 	case GEN6_PCODE_READ_RC6VIDS:
@@ -1722,7 +1724,8 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	int ret;
 
 	(*(u32 *)p_data) &= ~_MASKED_BIT_ENABLE(1);
-	if (IS_COFFEELAKE(vgpu->gvt->gt->i915))
+	if (IS_COFFEELAKE(vgpu->gvt->gt->i915) ||
+	    IS_COMETLAKE(vgpu->gvt->gt->i915))
 		(*(u32 *)p_data) &= ~_MASKED_BIT_ENABLE(2);
 	write_vreg(vgpu, offset, p_data, bytes);
 
@@ -1731,7 +1734,8 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		return 0;
 	}
 
-	if (IS_COFFEELAKE(vgpu->gvt->gt->i915) &&
+	if ((IS_COFFEELAKE(vgpu->gvt->gt->i915) ||
+	     IS_COMETLAKE(vgpu->gvt->gt->i915)) &&
 	    IS_MASKED_BITS_ENABLED(data, 2)) {
 		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
 		return 0;
@@ -1864,7 +1868,7 @@ static int csfe_chicken1_mmio_write(struct intel_vgpu *vgpu,
 	MMIO_F(prefix(BLT_RING_BASE), s, f, am, rm, d, r, w); \
 	MMIO_F(prefix(GEN6_BSD_RING_BASE), s, f, am, rm, d, r, w); \
 	MMIO_F(prefix(VEBOX_RING_BASE), s, f, am, rm, d, r, w); \
-	if (HAS_ENGINE(dev_priv, VCS1)) \
+	if (HAS_ENGINE(gvt->gt, VCS1)) \
 		MMIO_F(prefix(GEN8_BSD2_RING_BASE), s, f, am, rm, d, r, w); \
 } while (0)
 
@@ -3395,7 +3399,8 @@ int intel_gvt_setup_mmio_info(struct intel_gvt *gvt)
 			goto err;
 	} else if (IS_SKYLAKE(i915) ||
 		   IS_KABYLAKE(i915) ||
-		   IS_COFFEELAKE(i915)) {
+		   IS_COFFEELAKE(i915) ||
+		   IS_COMETLAKE(i915)) {
 		ret = init_bdw_mmio_info(gvt);
 		if (ret)
 			goto err;
diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c
index 540017fed908..7498878e6289 100644
--- a/drivers/gpu/drm/i915/gvt/interrupt.c
+++ b/drivers/gpu/drm/i915/gvt/interrupt.c
@@ -540,7 +540,7 @@ static void gen8_init_irq(
 	SET_BIT_INFO(irq, 4, VCS_MI_FLUSH_DW, INTEL_GVT_IRQ_INFO_GT1);
 	SET_BIT_INFO(irq, 8, VCS_AS_CONTEXT_SWITCH, INTEL_GVT_IRQ_INFO_GT1);
 
-	if (HAS_ENGINE(gvt->gt->i915, VCS1)) {
+	if (HAS_ENGINE(gvt->gt, VCS1)) {
 		SET_BIT_INFO(irq, 16, VCS2_MI_USER_INTERRUPT,
 			INTEL_GVT_IRQ_INFO_GT1);
 		SET_BIT_INFO(irq, 20, VCS2_MI_FLUSH_DW,
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 2ccaf78f96e8..86a60bdf0818 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -171,7 +171,7 @@ static void load_render_mocs(const struct intel_engine_cs *engine)
 		return;
 
 	for (ring_id = 0; ring_id < cnt; ring_id++) {
-		if (!HAS_ENGINE(engine->i915, ring_id))
+		if (!HAS_ENGINE(engine->gt, ring_id))
 			continue;
 
 		offset.reg = regs[ring_id];
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 0fb1df71c637..3c3b9842bbbd 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -348,7 +348,7 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 	u32 *cs;
 	int err;
 
-	if (IS_GEN(req->i915, 9) && is_inhibit_context(req->context))
+	if (IS_GEN(req->engine->i915, 9) && is_inhibit_context(req->context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
 	/*
@@ -509,26 +509,18 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 			bb->bb_start_cmd_va = workload->shadow_ring_buffer_va
 				+ bb->bb_offset;
 
-		if (bb->ppgtt) {
-			/* for non-priv bb, scan&shadow is only for
-			 * debugging purpose, so the content of shadow bb
-			 * is the same as original bb. Therefore,
-			 * here, rather than switch to shadow bb's gma
-			 * address, we directly use original batch buffer's
-			 * gma address, and send original bb to hardware
-			 * directly
-			 */
-			if (bb->clflush & CLFLUSH_AFTER) {
-				drm_clflush_virt_range(bb->va,
-						bb->obj->base.size);
-				bb->clflush &= ~CLFLUSH_AFTER;
-			}
-			i915_gem_object_finish_access(bb->obj);
-			bb->accessing = false;
-
-		} else {
+		/*
+		 * For non-priv bb, scan&shadow is only for
+		 * debugging purpose, so the content of shadow bb
+		 * is the same as original bb. Therefore,
+		 * here, rather than switch to shadow bb's gma
+		 * address, we directly use original batch buffer's
+		 * gma address, and send original bb to hardware
+		 * directly
+		 */
+		if (!bb->ppgtt) {
 			bb->vma = i915_gem_object_ggtt_pin(bb->obj,
-					NULL, 0, 0, 0);
+							   NULL, 0, 0, 0);
 			if (IS_ERR(bb->vma)) {
 				ret = PTR_ERR(bb->vma);
 				goto err;
@@ -539,27 +531,15 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 			if (gmadr_bytes == 8)
 				bb->bb_start_cmd_va[2] = 0;
 
-			/* No one is going to touch shadow bb from now on. */
-			if (bb->clflush & CLFLUSH_AFTER) {
-				drm_clflush_virt_range(bb->va,
-						bb->obj->base.size);
-				bb->clflush &= ~CLFLUSH_AFTER;
-			}
-
-			ret = i915_gem_object_set_to_gtt_domain(bb->obj,
-								false);
-			if (ret)
-				goto err;
-
 			ret = i915_vma_move_to_active(bb->vma,
 						      workload->req,
 						      0);
 			if (ret)
 				goto err;
-
-			i915_gem_object_finish_access(bb->obj);
-			bb->accessing = false;
 		}
+
+		/* No one is going to touch shadow bb from now on. */
+		i915_gem_object_flush_map(bb->obj);
 	}
 	return 0;
 err:
@@ -630,9 +610,6 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 
 	list_for_each_entry_safe(bb, pos, &workload->shadow_bb, list) {
 		if (bb->obj) {
-			if (bb->accessing)
-				i915_gem_object_finish_access(bb->obj);
-
 			if (bb->va && !IS_ERR(bb->va))
 				i915_gem_object_unpin_map(bb->obj);
 
@@ -939,7 +916,7 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 	context_page_num = rq->engine->context_size;
 	context_page_num = context_page_num >> PAGE_SHIFT;
 
-	if (IS_BROADWELL(rq->i915) && rq->engine->id == RCS0)
+	if (IS_BROADWELL(rq->engine->i915) && rq->engine->id == RCS0)
 		context_page_num = 19;
 
 	context_base = (void *) ctx->lrc_reg_state -
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 15d317f2a4a4..64e7a0b791c3 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -124,8 +124,6 @@ struct intel_vgpu_shadow_bb {
 	struct i915_vma *vma;
 	void *va;
 	u32 *bb_start_cmd_va;
-	unsigned int clflush;
-	bool accessing;
 	unsigned long bb_offset;
 	bool ppgtt;
 };