Merge tag 'drm-fixes-2021-01-29' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Weekly fixes for graphics, nothing too major, nouveau has a few
  regression fixes for various fallout from header changes previously,
  vc4 has two fixes, two amdgpu, and a smattering of i915 fixes.

  All seems on course for a quieter rc7, fingers crossed.

  nouveau:
   - fix svm init conditions
   - fix nv50 modesetting regression
   - fix cursor plane modifiers
   - fix > 64x64 cursor regression

  vc4:
   - Fix LBM size calculation
   - Fix high resolutions for hvs5

  i915:
   - Fix ICL MG PHY vswing
   - Fix subplatform handling
   - Fix selftest memleak
   - Clear CACHE_MODE prior to clearing residuals
   - Always flush the active worker before returning from the wait
   - Always try to reserve GGTT address 0x0

  amdgpu:
   - Fix a fan control regression on some boards
   - Fix clang warning"

* tag 'drm-fixes-2021-01-29' of git://anongit.freedesktop.org/drm/drm:
  drm/nouveau/kms/gk104-gp1xx: Fix > 64x64 cursors
  drm/nouveau/kms/nv50-: Report max cursor size to userspace
  drivers/nouveau/kms/nv50-: Reject format modifiers for cursor planes
  drm/nouveau/svm: fail NOUVEAU_SVM_INIT ioctl on unsupported devices
  drm/nouveau/dispnv50: Restore pushing of all data.
  amdgpu: fix clang build warning
  Revert "drm/amdgpu/swsmu: drop set_fan_speed_percent (v2)"
  drm/i915/gt: Always try to reserve GGTT address 0x0
  drm/i915: Always flush the active worker before returning from the wait
  drm/i915/selftest: Fix potential memory leak
  drm/i915: Check for all subplatform bits
  drm/i915: Fix ICL MG PHY vswing handling
  drm/i915/gt: Clear CACHE_MODE prior to clearing residuals
  drm/vc4: Correct POS1_SCL for hvs5
  drm/vc4: Correct lbm size and calculation
  drm/nouveau/nvif: fix method count when pushing an array

26 files changed, 300 insertions, 165 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
index c20331eb62e0..dfd77b3cc84d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
@@ -32,8 +32,8 @@ DCN30 = dcn30_init.o dcn30_hubbub.o dcn30_hubp.o dcn30_dpp.o dcn30_optc.o \
 
 
 ifdef CONFIG_X86
-CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -msse
-CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -msse
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -msse
 endif
 
 ifdef CONFIG_PPC64
@@ -45,6 +45,8 @@ ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
 endif
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -mhard-float
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -mhard-float
 endif
 
 ifdef CONFIG_X86
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
index 3ca7d911d25c..09264716d1dc 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
@@ -14,7 +14,7 @@ DCN301 = dcn301_init.o dcn301_resource.o dcn301_dccg.o \
 		dcn301_dio_link_encoder.o dcn301_hwseq.o dcn301_panel_cntl.o dcn301_hubbub.o
 
 ifdef CONFIG_X86
-CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -mhard-float -msse
+CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -msse
 endif
 
 ifdef CONFIG_PPC64
@@ -25,6 +25,7 @@ ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
 endif
+CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o += -mhard-float
 endif
 
 ifdef CONFIG_X86
diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/Makefile b/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
index 8d4924b7dc22..101620a8867a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
@@ -13,7 +13,7 @@
 DCN3_02 = dcn302_init.o dcn302_hwseq.o dcn302_resource.o
 
 ifdef CONFIG_X86
-CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o := -mhard-float -msse
+CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o := -msse
 endif
 
 ifdef CONFIG_PPC64
@@ -24,6 +24,7 @@ ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
 endif
+CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o += -mhard-float
 endif
 
 ifdef CONFIG_X86
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
index 4bdbcce7092d..0d797fa9f5cc 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
@@ -553,6 +553,7 @@ struct pptable_funcs {
 					     *clock_req);
 	uint32_t (*get_fan_control_mode)(struct smu_context *smu);
 	int (*set_fan_control_mode)(struct smu_context *smu, uint32_t mode);
+	int (*set_fan_speed_percent)(struct smu_context *smu, uint32_t speed);
 	int (*set_fan_speed_rpm)(struct smu_context *smu, uint32_t speed);
 	int (*set_xgmi_pstate)(struct smu_context *smu, uint32_t pstate);
 	int (*gfx_off_control)(struct smu_context *smu, bool enable);
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
index 13de692a4213..5d0b29653ffa 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
@@ -203,6 +203,9 @@ int
 smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 			       uint32_t mode);
 
+int
+smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed);
+
 int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 				       uint32_t speed);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 8b867a6d52b5..e84c737e3967 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2151,19 +2151,14 @@ int smu_get_fan_speed_percent(struct smu_context *smu, uint32_t *speed)
 int smu_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
 {
 	int ret = 0;
-	uint32_t rpm;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->set_fan_speed_rpm) {
-		if (speed > 100)
-			speed = 100;
-		rpm = speed * smu->fan_max_rpm / 100;
-		ret = smu->ppt_funcs->set_fan_speed_rpm(smu, rpm);
-	}
+	if (smu->ppt_funcs->set_fan_speed_percent)
+		ret = smu->ppt_funcs->set_fan_speed_percent(smu, speed);
 
 	mutex_unlock(&smu->mutex);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index cd7b411457ff..16db0b506b0d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -2326,6 +2326,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
+	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
 	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 51e83123f72a..cd7efa923195 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -2456,6 +2456,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
+	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
 	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 12b36eb0ff6a..d68d3dfee51d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -2802,6 +2802,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
+	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
 	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index b279dbbbce6b..5aeb5f5a0447 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1174,6 +1174,35 @@ smu_v11_0_set_fan_static_mode(struct smu_context *smu, uint32_t mode)
 }
 
 int
+smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t duty100, duty;
+	uint64_t tmp64;
+
+	if (speed > 100)
+		speed = 100;
+
+	if (smu_v11_0_auto_fan_control(smu, 0))
+		return -EINVAL;
+
+	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1),
+				CG_FDO_CTRL1, FMAX_DUTY100);
+	if (!duty100)
+		return -EINVAL;
+
+	tmp64 = (uint64_t)speed * duty100;
+	do_div(tmp64, 100);
+	duty = (uint32_t)tmp64;
+
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL0,
+		     REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL0),
+				   CG_FDO_CTRL0, FDO_STATIC_DUTY, duty));
+
+	return smu_v11_0_set_fan_static_mode(smu, FDO_PWM_MODE_STATIC);
+}
+
+int
 smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 			       uint32_t mode)
 {
@@ -1181,7 +1210,7 @@ smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 
 	switch (mode) {
 	case AMD_FAN_CTRL_NONE:
-		ret = smu_v11_0_set_fan_speed_rpm(smu, smu->fan_max_rpm);
+		ret = smu_v11_0_set_fan_speed_percent(smu, 100);
 		break;
 	case AMD_FAN_CTRL_MANUAL:
 		ret = smu_v11_0_auto_fan_control(smu, 0);
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index d5ace48b1ace..bf17365857ca 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2755,12 +2755,11 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 	u32 val;
 
 	ddi_translations = icl_get_mg_buf_trans(encoder, crtc_state, &n_entries);
-	/* The table does not have values for level 3 and level 9. */
-	if (level >= n_entries || level == 3 || level == 9) {
+	if (level >= n_entries) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "DDI translation not found for level %d. Using %d instead.",
-			    level, n_entries - 2);
-		level = n_entries - 2;
+			    level, n_entries - 1);
+		level = n_entries - 1;
 	}
 
 	/* Set MG_TX_LINK_PARAMS cri_use_fs32 to 0. */
diff --git a/drivers/gpu/drm/i915/gt/gen7_renderclear.c b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
index 94465374ca2f..e961ad6a3129 100644
--- a/drivers/gpu/drm/i915/gt/gen7_renderclear.c
+++ b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
@@ -390,6 +390,16 @@ static void emit_batch(struct i915_vma * const vma,
 						     &cb_kernel_ivb,
 						     desc_count);
 
+	/* Reset inherited context registers */
+	gen7_emit_pipeline_invalidate(&cmds);
+	batch_add(&cmds, MI_LOAD_REGISTER_IMM(2));
+	batch_add(&cmds, i915_mmio_reg_offset(CACHE_MODE_0_GEN7));
+	batch_add(&cmds, 0xffff0000);
+	batch_add(&cmds, i915_mmio_reg_offset(CACHE_MODE_1));
+	batch_add(&cmds, 0xffff0000 | PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
+	gen7_emit_pipeline_flush(&cmds);
+
+	/* Switch to the media pipeline and our base address */
 	gen7_emit_pipeline_invalidate(&cmds);
 	batch_add(&cmds, PIPELINE_SELECT | PIPELINE_SELECT_MEDIA);
 	batch_add(&cmds, MI_NOOP);
@@ -399,9 +409,11 @@ static void emit_batch(struct i915_vma * const vma,
 	gen7_emit_state_base_address(&cmds, descriptors);
 	gen7_emit_pipeline_invalidate(&cmds);
 
+	/* Set the clear-residual kernel state */
 	gen7_emit_vfe_state(&cmds, bv, urb_size - 1, 0, 0);
 	gen7_emit_interface_descriptor_load(&cmds, descriptors, desc_count);
 
+	/* Execute the kernel on all HW threads */
 	for (i = 0; i < num_primitives(bv); i++)
 		gen7_emit_media_object(&cmds, i);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index cf94525be2c1..db8c66dde655 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -526,16 +526,39 @@ static int init_ggtt(struct i915_ggtt *ggtt)
 
 	mutex_init(&ggtt->error_mutex);
 	if (ggtt->mappable_end) {
-		/* Reserve a mappable slot for our lockless error capture */
-		ret = drm_mm_insert_node_in_range(&ggtt->vm.mm,
-						  &ggtt->error_capture,
-						  PAGE_SIZE, 0,
-						  I915_COLOR_UNEVICTABLE,
-						  0, ggtt->mappable_end,
-						  DRM_MM_INSERT_LOW);
-		if (ret)
-			return ret;
+		/*
+		 * Reserve a mappable slot for our lockless error capture.
+		 *
+		 * We strongly prefer taking address 0x0 in order to protect
+		 * other critical buffers against accidental overwrites,
+		 * as writing to address 0 is a very common mistake.
+		 *
+		 * Since 0 may already be in use by the system (e.g. the BIOS
+		 * framebuffer), we let the reservation fail quietly and hope
+		 * 0 remains reserved always.
+		 *
+		 * If we fail to reserve 0, and then fail to find any space
+		 * for an error-capture, remain silent. We can afford not
+		 * to reserve an error_capture node as we have fallback
+		 * paths, and we trust that 0 will remain reserved. However,
+		 * the only likely reason for failure to insert is a driver
+		 * bug, which we expect to cause other failures...
+		 */
+		ggtt->error_capture.size = I915_GTT_PAGE_SIZE;
+		ggtt->error_capture.color = I915_COLOR_UNEVICTABLE;
+		if (drm_mm_reserve_node(&ggtt->vm.mm, &ggtt->error_capture))
+			drm_mm_insert_node_in_range(&ggtt->vm.mm,
+						    &ggtt->error_capture,
+						    ggtt->error_capture.size, 0,
+						    ggtt->error_capture.color,
+						    0, ggtt->mappable_end,
+						    DRM_MM_INSERT_LOW);
 	}
+	if (drm_mm_node_allocated(&ggtt->error_capture))
+		drm_dbg(&ggtt->vm.i915->drm,
+			"Reserved GGTT:[%llx, %llx] for use by error capture\n",
+			ggtt->error_capture.start,
+			ggtt->error_capture.start + ggtt->error_capture.size);
 
 	/*
 	 * The upper portion of the GuC address space has a sizeable hole
@@ -548,9 +571,9 @@ static int init_ggtt(struct i915_ggtt *ggtt)
 
 	/* Clear any non-preallocated blocks */
 	drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) {
-		drm_dbg_kms(&ggtt->vm.i915->drm,
-			    "clearing unused GTT space: [%lx, %lx]\n",
-			    hole_start, hole_end);
+		drm_dbg(&ggtt->vm.i915->drm,
+			"clearing unused GTT space: [%lx, %lx]\n",
+			hole_start, hole_end);
 		ggtt->vm.clear_range(&ggtt->vm, hole_start,
 				     hole_end - hole_start);
 	}
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 10a865f3dc09..9ed19b8bca60 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -631,24 +631,26 @@ static int flush_lazy_signals(struct i915_active *ref)
 
 int __i915_active_wait(struct i915_active *ref, int state)
 {
-	int err;
-
 	might_sleep();
 
-	if (!i915_active_acquire_if_busy(ref))
-		return 0;
-
 	/* Any fence added after the wait begins will not be auto-signaled */
-	err = flush_lazy_signals(ref);
-	i915_active_release(ref);
-	if (err)
-		return err;
+	if (i915_active_acquire_if_busy(ref)) {
+		int err;
 
-	if (!i915_active_is_idle(ref) &&
-	    ___wait_var_event(ref, i915_active_is_idle(ref),
-			      state, 0, 0, schedule()))
-		return -EINTR;
+		err = flush_lazy_signals(ref);
+		i915_active_release(ref);
+		if (err)
+			return err;
 
+		if (___wait_var_event(ref, i915_active_is_idle(ref),
+				      state, 0, 0, schedule()))
+			return -EINTR;
+	}
+
+	/*
+	 * After the wait is complete, the caller may free the active.
+	 * We have to flush any concurrent retirement before returning.
+	 */
 	flush_work(&ref->work);
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 632c713227dc..c6964f82a1bb 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1346,7 +1346,7 @@ intel_subplatform(const struct intel_runtime_info *info, enum intel_platform p)
 {
 	const unsigned int pi = __platform_mask_index(info, p);
 
-	return info->platform_mask[pi] & INTEL_SUBPLATFORM_BITS;
+	return info->platform_mask[pi] & ((1 << INTEL_SUBPLATFORM_BITS) - 1);
 }
 
 static __always_inline bool
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index c53a222e3dec..713770fb2b92 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1880,7 +1880,7 @@ static int igt_cs_tlb(void *arg)
 	vma = i915_vma_instance(out, vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
-		goto out_put_batch;
+		goto out_put_out;
 	}
 
 	err = i915_vma_pin(vma, 0, 0,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base507c.c b/drivers/gpu/drm/nouveau/dispnv50/base507c.c
index 302d4e6fc52f..788db043a342 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/base507c.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/base507c.c
@@ -88,7 +88,11 @@ base507c_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 			  NVVAL(NV507C, SET_CONVERSION, OFS, 0x64));
 	} else {
 		PUSH_MTHD(push, NV507C, SET_PROCESSING,
-			  NVDEF(NV507C, SET_PROCESSING, USE_GAIN_OFS, DISABLE));
+			  NVDEF(NV507C, SET_PROCESSING, USE_GAIN_OFS, DISABLE),
+
+					SET_CONVERSION,
+			  NVVAL(NV507C, SET_CONVERSION, GAIN, 0) |
+			  NVVAL(NV507C, SET_CONVERSION, OFS, 0));
 	}
 
 	PUSH_MTHD(push, NV507C, SURFACE_SET_OFFSET(0, 0), asyw->image.offset[0] >> 8);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base827c.c b/drivers/gpu/drm/nouveau/dispnv50/base827c.c
index 18d34096f125..093d4ba6910e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/base827c.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/base827c.c
@@ -49,7 +49,11 @@ base827c_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 			  NVVAL(NV827C, SET_CONVERSION, OFS, 0x64));
 	} else {
 		PUSH_MTHD(push, NV827C, SET_PROCESSING,
-			  NVDEF(NV827C, SET_PROCESSING, USE_GAIN_OFS, DISABLE));
+			  NVDEF(NV827C, SET_PROCESSING, USE_GAIN_OFS, DISABLE),
+
+					SET_CONVERSION,
+			  NVVAL(NV827C, SET_CONVERSION, GAIN, 0) |
+			  NVVAL(NV827C, SET_CONVERSION, OFS, 0));
 	}
 
 	PUSH_MTHD(push, NV827C, SURFACE_SET_OFFSET(0, 0), asyw->image.offset[0] >> 8,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index c6367035970e..5f4f09a601d4 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2663,6 +2663,14 @@ nv50_display_create(struct drm_device *dev)
 	else
 		nouveau_display(dev)->format_modifiers = disp50xx_modifiers;
 
+	if (disp->disp->object.oclass >= GK104_DISP) {
+		dev->mode_config.cursor_width = 256;
+		dev->mode_config.cursor_height = 256;
+	} else {
+		dev->mode_config.cursor_width = 64;
+		dev->mode_config.cursor_height = 64;
+	}
+
 	/* create crtc objects to represent the hw heads */
 	if (disp->disp->object.oclass >= GV100_DISP)
 		crtcs = nvif_rd32(&device->object, 0x610060) & 0xff;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head917d.c b/drivers/gpu/drm/nouveau/dispnv50/head917d.c
index a5d827403660..ea9f8667305e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head917d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head917d.c
@@ -22,6 +22,7 @@
 #include "head.h"
 #include "core.h"
 
+#include "nvif/push.h"
 #include <nvif/push507c.h>
 
 #include <nvhw/class/cl917d.h>
@@ -73,6 +74,31 @@ head917d_base(struct nv50_head *head, struct nv50_head_atom *asyh)
 	return 0;
 }
 
+static int
+head917d_curs_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nvif_push *push = nv50_disp(head->base.base.dev)->core->chan.push;
+	const int i = head->base.index;
+	int ret;
+
+	ret = PUSH_WAIT(push, 5);
+	if (ret)
+		return ret;
+
+	PUSH_MTHD(push, NV917D, HEAD_SET_CONTROL_CURSOR(i),
+		  NVDEF(NV917D, HEAD_SET_CONTROL_CURSOR, ENABLE, ENABLE) |
+		  NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, FORMAT, asyh->curs.format) |
+		  NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, SIZE, asyh->curs.layout) |
+		  NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, HOT_SPOT_X, 0) |
+		  NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, HOT_SPOT_Y, 0) |
+		  NVDEF(NV917D, HEAD_SET_CONTROL_CURSOR, COMPOSITION, ALPHA_BLEND),
+
+				HEAD_SET_OFFSET_CURSOR(i), asyh->curs.offset >> 8);
+
+	PUSH_MTHD(push, NV917D, HEAD_SET_CONTEXT_DMA_CURSOR(i), asyh->curs.handle);
+	return 0;
+}
+
 int
 head917d_curs_layout(struct nv50_head *head, struct nv50_wndw_atom *asyw,
 		     struct nv50_head_atom *asyh)
@@ -101,7 +127,7 @@ head917d = {
 	.core_clr = head907d_core_clr,
 	.curs_layout = head917d_curs_layout,
 	.curs_format = head507d_curs_format,
-	.curs_set = head907d_curs_set,
+	.curs_set = head917d_curs_set,
 	.curs_clr = head907d_curs_clr,
 	.base = head917d_base,
 	.ovly = head907d_ovly,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index ce451242f79e..271de3a63f21 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -702,6 +702,11 @@ nv50_wndw_init(struct nv50_wndw *wndw)
 	nvif_notify_get(&wndw->notify);
 }
 
+static const u64 nv50_cursor_format_modifiers[] = {
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
 int
 nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev,
 	       enum drm_plane_type type, const char *name, int index,
@@ -713,6 +718,7 @@ nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev,
 	struct nvif_mmu *mmu = &drm->client.mmu;
 	struct nv50_disp *disp = nv50_disp(dev);
 	struct nv50_wndw *wndw;
+	const u64 *format_modifiers;
 	int nformat;
 	int ret;
 
@@ -728,10 +734,13 @@ nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev,
 
 	for (nformat = 0; format[nformat]; nformat++);
 
-	ret = drm_universal_plane_init(dev, &wndw->plane, heads, &nv50_wndw,
-				       format, nformat,
-				       nouveau_display(dev)->format_modifiers,
-				       type, "%s-%d", name, index);
+	if (type == DRM_PLANE_TYPE_CURSOR)
+		format_modifiers = nv50_cursor_format_modifiers;
+	else
+		format_modifiers = nouveau_display(dev)->format_modifiers;
+
+	ret = drm_universal_plane_init(dev, &wndw->plane, heads, &nv50_wndw, format, nformat,
+				       format_modifiers, type, "%s-%d", name, index);
 	if (ret) {
 		kfree(*pwndw);
 		*pwndw = NULL;
diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h b/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h
index 2a2612d6e1e0..fb223723a38a 100644
--- a/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h
+++ b/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h
@@ -66,6 +66,10 @@
 #define NV917D_HEAD_SET_CONTROL_CURSOR_COMPOSITION_ALPHA_BLEND                  (0x00000000)
 #define NV917D_HEAD_SET_CONTROL_CURSOR_COMPOSITION_PREMULT_ALPHA_BLEND          (0x00000001)
 #define NV917D_HEAD_SET_CONTROL_CURSOR_COMPOSITION_XOR                          (0x00000002)
+#define NV917D_HEAD_SET_OFFSET_CURSOR(a)                                        (0x00000484 + (a)*0x00000300)
+#define NV917D_HEAD_SET_OFFSET_CURSOR_ORIGIN                                    31:0
+#define NV917D_HEAD_SET_CONTEXT_DMA_CURSOR(a)                                   (0x0000048C + (a)*0x00000300)
+#define NV917D_HEAD_SET_CONTEXT_DMA_CURSOR_HANDLE                               31:0
 #define NV917D_HEAD_SET_DITHER_CONTROL(a)                                       (0x000004A0 + (a)*0x00000300)
 #define NV917D_HEAD_SET_DITHER_CONTROL_ENABLE                                   0:0
 #define NV917D_HEAD_SET_DITHER_CONTROL_ENABLE_DISABLE                           (0x00000000)
diff --git a/drivers/gpu/drm/nouveau/include/nvif/push.h b/drivers/gpu/drm/nouveau/include/nvif/push.h
index 168d7694ede5..6d3a8a3d2087 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/push.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/push.h
@@ -123,131 +123,131 @@ PUSH_KICK(struct nvif_push *push)
 } while(0)
 #endif
 
-#define PUSH_1(X,f,ds,n,c,o,p,s,mA,dA) do {                            \
-	PUSH_##o##_HDR((p), s, mA, (c)+(n));                           \
-	PUSH_##f(X, (p), X##mA, 1, o, (dA), ds, "");                   \
+#define PUSH_1(X,f,ds,n,o,p,s,mA,dA) do {                             \
+	PUSH_##o##_HDR((p), s, mA, (ds)+(n));                         \
+	PUSH_##f(X, (p), X##mA, 1, o, (dA), ds, "");                  \
 } while(0)
-#define PUSH_2(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (1?PUSH_##o##_INC), "mthd1");       \
-	PUSH_1(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_2(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (1?PUSH_##o##_INC), "mthd1");      \
+	PUSH_1(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_3(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd2");       \
-	PUSH_2(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_3(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd2");      \
+	PUSH_2(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_4(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd3");       \
-	PUSH_3(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_4(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd3");      \
+	PUSH_3(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_5(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd4");       \
-	PUSH_4(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_5(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd4");      \
+	PUSH_4(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_6(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd5");       \
-	PUSH_5(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_6(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd5");      \
+	PUSH_5(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_7(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd6");       \
-	PUSH_6(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_7(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd6");      \
+	PUSH_6(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_8(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd7");       \
-	PUSH_7(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_8(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd7");      \
+	PUSH_7(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_9(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd8");       \
-	PUSH_8(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_9(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd8");      \
+	PUSH_8(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_10(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd9");       \
-	PUSH_9(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_10(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                 \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd9");      \
+	PUSH_9(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
 
-#define PUSH_1D(X,o,p,s,mA,dA)                            \
-	PUSH_1(X, DATA_, 1, 1, 0, o, (p), s, X##mA, (dA))
-#define PUSH_2D(X,o,p,s,mA,dA,mB,dB)                      \
-	PUSH_2(X, DATA_, 1, 1, 0, o, (p), s, X##mB, (dB), \
-					     X##mA, (dA))
-#define PUSH_3D(X,o,p,s,mA,dA,mB,dB,mC,dC)                \
-	PUSH_3(X, DATA_, 1, 1, 0, o, (p), s, X##mC, (dC), \
-					     X##mB, (dB), \
-					     X##mA, (dA))
-#define PUSH_4D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD)          \
-	PUSH_4(X, DATA_, 1, 1, 0, o, (p), s, X##mD, (dD), \
-					     X##mC, (dC), \
-					     X##mB, (dB), \
-					     X##mA, (dA))
-#define PUSH_5D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE)    \
-	PUSH_5(X, DATA_, 1, 1, 0, o, (p), s, X##mE, (dE), \
-					     X##mD, (dD), \
-					     X##mC, (dC), \
-					     X##mB, (dB), \
-					     X##mA, (dA))
+#define PUSH_1D(X,o,p,s,mA,dA)                         \
+	PUSH_1(X, DATA_, 1, 0, o, (p), s, X##mA, (dA))
+#define PUSH_2D(X,o,p,s,mA,dA,mB,dB)                   \
+	PUSH_2(X, DATA_, 1, 0, o, (p), s, X##mB, (dB), \
+					  X##mA, (dA))
+#define PUSH_3D(X,o,p,s,mA,dA,mB,dB,mC,dC)             \
+	PUSH_3(X, DATA_, 1, 0, o, (p), s, X##mC, (dC), \
+					  X##mB, (dB), \
+					  X##mA, (dA))
+#define PUSH_4D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD)       \
+	PUSH_4(X, DATA_, 1, 0, o, (p), s, X##mD, (dD), \
+					  X##mC, (dC), \
+					  X##mB, (dB), \
+					  X##mA, (dA))
+#define PUSH_5D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE) \
+	PUSH_5(X, DATA_, 1, 0, o, (p), s, X##mE, (dE), \
+					  X##mD, (dD), \
+					  X##mC, (dC), \
+					  X##mB, (dB), \
+					  X##mA, (dA))
 #define PUSH_6D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF) \
-	PUSH_6(X, DATA_, 1, 1, 0, o, (p), s, X##mF, (dF),    \
-					     X##mE, (dE),    \
-					     X##mD, (dD),    \
-					     X##mC, (dC),    \
-					     X##mB, (dB),    \
-					     X##mA, (dA))
+	PUSH_6(X, DATA_, 1, 0, o, (p), s, X##mF, (dF),       \
+					  X##mE, (dE),       \
+					  X##mD, (dD),       \
+					  X##mC, (dC),       \
+					  X##mB, (dB),       \
+					  X##mA, (dA))
 #define PUSH_7D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG) \
-	PUSH_7(X, DATA_, 1, 1, 0, o, (p), s, X##mG, (dG),          \
-					     X##mF, (dF),          \
-					     X##mE, (dE),          \
-					     X##mD, (dD),          \
-					     X##mC, (dC),          \
-					     X##mB, (dB),          \
-					     X##mA, (dA))
+	PUSH_7(X, DATA_, 1, 0, o, (p), s, X##mG, (dG),             \
+					  X##mF, (dF),             \
+					  X##mE, (dE),             \
+					  X##mD, (dD),             \
+					  X##mC, (dC),             \
+					  X##mB, (dB),             \
+					  X##mA, (dA))
 #define PUSH_8D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH) \
-	PUSH_8(X, DATA_, 1, 1, 0, o, (p), s, X##mH, (dH),                \
-					     X##mG, (dG),                \
-					     X##mF, (dF),                \
-					     X##mE, (dE),                \
-					     X##mD, (dD),                \
-					     X##mC, (dC),                \
-					     X##mB, (dB),                \
-					     X##mA, (dA))
+	PUSH_8(X, DATA_, 1, 0, o, (p), s, X##mH, (dH),                   \
+					  X##mG, (dG),                   \
+					  X##mF, (dF),                   \
+					  X##mE, (dE),                   \
+					  X##mD, (dD),                   \
+					  X##mC, (dC),                   \
+					  X##mB, (dB),                   \
+					  X##mA, (dA))
 #define PUSH_9D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH,mI,dI) \
-	PUSH_9(X, DATA_, 1, 1, 0, o, (p), s, X##mI, (dI),                      \
-					     X##mH, (dH),                      \
-					     X##mG, (dG),                      \
-					     X##mF, (dF),                      \
-					     X##mE, (dE),                      \
-					     X##mD, (dD),                      \
-					     X##mC, (dC),                      \
-					     X##mB, (dB),                      \
-					     X##mA, (dA))
+	PUSH_9(X, DATA_, 1, 0, o, (p), s, X##mI, (dI),                         \
+					  X##mH, (dH),                         \
+					  X##mG, (dG),                         \
+					  X##mF, (dF),                         \
+					  X##mE, (dE),                         \
+					  X##mD, (dD),                         \
+					  X##mC, (dC),                         \
+					  X##mB, (dB),                         \
+					  X##mA, (dA))
 #define PUSH_10D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH,mI,dI,mJ,dJ) \
-	PUSH_10(X, DATA_, 1, 1, 0, o, (p), s, X##mJ, (dJ),                            \
-					      X##mI, (dI),                            \
-					      X##mH, (dH),                            \
-					      X##mG, (dG),                            \
-					      X##mF, (dF),                            \
-					      X##mE, (dE),                            \
-					      X##mD, (dD),                            \
-					      X##mC, (dC),                            \
-					      X##mB, (dB),                            \
-					      X##mA, (dA))
+	PUSH_10(X, DATA_, 1, 0, o, (p), s, X##mJ, (dJ),                               \
+					   X##mI, (dI),                               \
+					   X##mH, (dH),                               \
+					   X##mG, (dG),                               \
+					   X##mF, (dF),                               \
+					   X##mE, (dE),                               \
+					   X##mD, (dD),                               \
+					   X##mC, (dC),                               \
+					   X##mB, (dB),                               \
+					   X##mA, (dA))
 
-#define PUSH_1P(X,o,p,s,mA,dp,ds)                           \
-	PUSH_1(X, DATAp, ds, ds, 0, o, (p), s, X##mA, (dp))
-#define PUSH_2P(X,o,p,s,mA,dA,mB,dp,ds)                     \
-	PUSH_2(X, DATAp, ds, ds, 0, o, (p), s, X##mB, (dp), \
-					       X##mA, (dA))
-#define PUSH_3P(X,o,p,s,mA,dA,mB,dB,mC,dp,ds)               \
-	PUSH_3(X, DATAp, ds, ds, 0, o, (p), s, X##mC, (dp), \
-					       X##mB, (dB), \
-					       X##mA, (dA))
+#define PUSH_1P(X,o,p,s,mA,dp,ds)                       \
+	PUSH_1(X, DATAp, ds, 0, o, (p), s, X##mA, (dp))
+#define PUSH_2P(X,o,p,s,mA,dA,mB,dp,ds)                 \
+	PUSH_2(X, DATAp, ds, 0, o, (p), s, X##mB, (dp), \
+					   X##mA, (dA))
+#define PUSH_3P(X,o,p,s,mA,dA,mB,dB,mC,dp,ds)           \
+	PUSH_3(X, DATAp, ds, 0, o, (p), s, X##mC, (dp), \
+					   X##mB, (dB), \
+					   X##mA, (dA))
 
 #define PUSH_(A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,IMPL,...) IMPL
 #define PUSH(A...) PUSH_(A, PUSH_10P, PUSH_10D,          \
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 4f69e4c3dafd..1c3f890377d2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -315,6 +315,10 @@ nouveau_svmm_init(struct drm_device *dev, void *data,
 	struct drm_nouveau_svm_init *args = data;
 	int ret;
 
+	/* We need to fail if svm is disabled */
+	if (!cli->drm->svm)
+		return -ENOSYS;
+
 	/* Allocate tracking for SVM-enabled VMM. */
 	if (!(svmm = kzalloc(sizeof(*svmm), GFP_KERNEL)))
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index cccd341e5d67..3b722252d1fb 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -620,11 +620,11 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 	 * for now we just allocate globally.
 	 */
 	if (!hvs->hvs5)
-		/* 96kB */
-		drm_mm_init(&hvs->lbm_mm, 0, 96 * 1024);
+		/* 48k words of 2x12-bit pixels */
+		drm_mm_init(&hvs->lbm_mm, 0, 48 * 1024);
 	else
-		/* 70k words */
-		drm_mm_init(&hvs->lbm_mm, 0, 70 * 2 * 1024);
+		/* 60k words of 4x12-bit pixels */
+		drm_mm_init(&hvs->lbm_mm, 0, 60 * 1024);
 
 	/* Upload filter kernels.  We only have the one for now, so we
 	 * keep it around for the lifetime of the driver.
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 6b39cc2ca18d..5612cab55227 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -437,6 +437,7 @@ static void vc4_write_ppf(struct vc4_plane_state *vc4_state, u32 src, u32 dst)
 static u32 vc4_lbm_size(struct drm_plane_state *state)
 {
 	struct vc4_plane_state *vc4_state = to_vc4_plane_state(state);
+	struct vc4_dev *vc4 = to_vc4_dev(state->plane->dev);
 	u32 pix_per_line;
 	u32 lbm;
 
@@ -472,7 +473,11 @@ static u32 vc4_lbm_size(struct drm_plane_state *state)
 		lbm = pix_per_line * 16;
 	}
 
-	lbm = roundup(lbm, 32);
+	/* Align it to 64 or 128 (hvs5) bytes */
+	lbm = roundup(lbm, vc4->hvs->hvs5 ? 128 : 64);
+
+	/* Each "word" of the LBM memory contains 2 or 4 (hvs5) pixels */
+	lbm /= vc4->hvs->hvs5 ? 4 : 2;
 
 	return lbm;
 }
@@ -912,9 +917,9 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 		if (!vc4_state->is_unity) {
 			vc4_dlist_write(vc4_state,
 					VC4_SET_FIELD(vc4_state->crtc_w,
-						      SCALER_POS1_SCL_WIDTH) |
+						      SCALER5_POS1_SCL_WIDTH) |
 					VC4_SET_FIELD(vc4_state->crtc_h,
-						      SCALER_POS1_SCL_HEIGHT));
+						      SCALER5_POS1_SCL_HEIGHT));
 		}
 
 		/* Position Word 2: Source Image Size */