Merge v5.6-rc5 into drm-next

Requested my mripard for some misc patches that need this as a base.

Signed-off-by: Dave Airlie <airlied@redhat.com>

53 files changed, 722 insertions, 325 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 8b17f182d532..7cefa230dec1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -52,7 +52,7 @@
  * 1. Primary ring
  * 2. Async ring
  */
-#define GFX10_NUM_GFX_RINGS	2
+#define GFX10_NUM_GFX_RINGS_NV1X	1
 #define GFX10_MEC_HPD_SIZE	2048
 
 #define F32_CE_PROGRAM_RAM_SIZE		65536
@@ -1304,7 +1304,7 @@ static int gfx_v10_0_sw_init(void *handle)
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
 		adev->gfx.me.num_me = 1;
-		adev->gfx.me.num_pipe_per_me = 2;
+		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
 		adev->gfx.mec.num_mec = 2;
 		adev->gfx.mec.num_pipe_per_mec = 4;
@@ -2710,18 +2710,20 @@ static int gfx_v10_0_cp_gfx_start(struct amdgpu_device *adev)
 	amdgpu_ring_commit(ring);
 
 	/* submit cs packet to copy state 0 to next available state */
-	ring = &adev->gfx.gfx_ring[1];
-	r = amdgpu_ring_alloc(ring, 2);
-	if (r) {
-		DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
-		return r;
-	}
-
-	amdgpu_ring_write(ring, PACKET3(PACKET3_CLEAR_STATE, 0));
-	amdgpu_ring_write(ring, 0);
+	if (adev->gfx.num_gfx_rings > 1) {
+		/* maximum supported gfx ring is 2 */
+		ring = &adev->gfx.gfx_ring[1];
+		r = amdgpu_ring_alloc(ring, 2);
+		if (r) {
+			DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
+			return r;
+		}
 
-	amdgpu_ring_commit(ring);
+		amdgpu_ring_write(ring, PACKET3(PACKET3_CLEAR_STATE, 0));
+		amdgpu_ring_write(ring, 0);
 
+		amdgpu_ring_commit(ring);
+	}
 	return 0;
 }
 
@@ -2818,39 +2820,41 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
 	mutex_unlock(&adev->srbm_mutex);
 
 	/* Init gfx ring 1 for pipe 1 */
-	mutex_lock(&adev->srbm_mutex);
-	gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1);
-	ring = &adev->gfx.gfx_ring[1];
-	rb_bufsz = order_base_2(ring->ring_size / 8);
-	tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz);
-	tmp = REG_SET_FIELD(tmp, CP_RB1_CNTL, RB_BLKSZ, rb_bufsz - 2);
-	WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
-	/* Initialize the ring buffer's write pointers */
-	ring->wptr = 0;
-	WREG32_SOC15(GC, 0, mmCP_RB1_WPTR, lower_32_bits(ring->wptr));
-	WREG32_SOC15(GC, 0, mmCP_RB1_WPTR_HI, upper_32_bits(ring->wptr));
-	/* Set the wb address wether it's enabled or not */
-	rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
-	WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR, lower_32_bits(rptr_addr));
-	WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR_HI, upper_32_bits(rptr_addr) &
-		CP_RB1_RPTR_ADDR_HI__RB_RPTR_ADDR_HI_MASK);
-	wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
-	WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO,
-		lower_32_bits(wptr_gpu_addr));
-	WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI,
-		upper_32_bits(wptr_gpu_addr));
-
-	mdelay(1);
-	WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
-
-	rb_addr = ring->gpu_addr >> 8;
-	WREG32_SOC15(GC, 0, mmCP_RB1_BASE, rb_addr);
-	WREG32_SOC15(GC, 0, mmCP_RB1_BASE_HI, upper_32_bits(rb_addr));
-	WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1);
-
-	gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
-	mutex_unlock(&adev->srbm_mutex);
-
+	if (adev->gfx.num_gfx_rings > 1) {
+		mutex_lock(&adev->srbm_mutex);
+		gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1);
+		/* maximum supported gfx ring is 2 */
+		ring = &adev->gfx.gfx_ring[1];
+		rb_bufsz = order_base_2(ring->ring_size / 8);
+		tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz);
+		tmp = REG_SET_FIELD(tmp, CP_RB1_CNTL, RB_BLKSZ, rb_bufsz - 2);
+		WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
+		/* Initialize the ring buffer's write pointers */
+		ring->wptr = 0;
+		WREG32_SOC15(GC, 0, mmCP_RB1_WPTR, lower_32_bits(ring->wptr));
+		WREG32_SOC15(GC, 0, mmCP_RB1_WPTR_HI, upper_32_bits(ring->wptr));
+		/* Set the wb address wether it's enabled or not */
+		rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4);
+		WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR, lower_32_bits(rptr_addr));
+		WREG32_SOC15(GC, 0, mmCP_RB1_RPTR_ADDR_HI, upper_32_bits(rptr_addr) &
+			     CP_RB1_RPTR_ADDR_HI__RB_RPTR_ADDR_HI_MASK);
+		wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+		WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO,
+			     lower_32_bits(wptr_gpu_addr));
+		WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI,
+			     upper_32_bits(wptr_gpu_addr));
+
+		mdelay(1);
+		WREG32_SOC15(GC, 0, mmCP_RB1_CNTL, tmp);
+
+		rb_addr = ring->gpu_addr >> 8;
+		WREG32_SOC15(GC, 0, mmCP_RB1_BASE, rb_addr);
+		WREG32_SOC15(GC, 0, mmCP_RB1_BASE_HI, upper_32_bits(rb_addr));
+		WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1);
+
+		gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
+		mutex_unlock(&adev->srbm_mutex);
+	}
 	/* Switch to pipe 0 */
 	mutex_lock(&adev->srbm_mutex);
 	gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID0);
@@ -3508,6 +3512,7 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		/* reset ring buffer */
 		ring->wptr = 0;
+		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
 		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
@@ -3961,7 +3966,8 @@ static int gfx_v10_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	adev->gfx.num_gfx_rings = GFX10_NUM_GFX_RINGS;
+	adev->gfx.num_gfx_rings = GFX10_NUM_GFX_RINGS_NV1X;
+
 	adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
 
 	gfx_v10_0_set_kiq_pm4_funcs(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 6a49fe452f29..ab6880958511 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3664,6 +3664,7 @@ static int gfx_v9_0_kcq_init_queue(struct amdgpu_ring *ring)
 
 		/* reset ring buffer */
 		ring->wptr = 0;
+		atomic64_set((atomic64_t *)&adev->wb.wb[ring->wptr_offs], 0);
 		amdgpu_ring_clear_ring(ring);
 	} else {
 		amdgpu_ring_clear_ring(ring);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 1c0449adcef6..48661b9bb2b8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1435,6 +1435,73 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend)
 		drm_kms_helper_hotplug_event(dev);
 }
 
+static int amdgpu_dm_smu_write_watermarks_table(struct amdgpu_device *adev)
+{
+	struct smu_context *smu = &adev->smu;
+	int ret = 0;
+
+	if (!is_support_sw_smu(adev))
+		return 0;
+
+	/* This interface is for dGPU Navi1x.Linux dc-pplib interface depends
+	 * on window driver dc implementation.
+	 * For Navi1x, clock settings of dcn watermarks are fixed. the settings
+	 * should be passed to smu during boot up and resume from s3.
+	 * boot up: dc calculate dcn watermark clock settings within dc_create,
+	 * dcn20_resource_construct
+	 * then call pplib functions below to pass the settings to smu:
+	 * smu_set_watermarks_for_clock_ranges
+	 * smu_set_watermarks_table
+	 * navi10_set_watermarks_table
+	 * smu_write_watermarks_table
+	 *
+	 * For Renoir, clock settings of dcn watermark are also fixed values.
+	 * dc has implemented different flow for window driver:
+	 * dc_hardware_init / dc_set_power_state
+	 * dcn10_init_hw
+	 * notify_wm_ranges
+	 * set_wm_ranges
+	 * -- Linux
+	 * smu_set_watermarks_for_clock_ranges
+	 * renoir_set_watermarks_table
+	 * smu_write_watermarks_table
+	 *
+	 * For Linux,
+	 * dc_hardware_init -> amdgpu_dm_init
+	 * dc_set_power_state --> dm_resume
+	 *
+	 * therefore, this function apply to navi10/12/14 but not Renoir
+	 * *
+	 */
+	switch(adev->asic_type) {
+	case CHIP_NAVI10:
+	case CHIP_NAVI14:
+	case CHIP_NAVI12:
+		break;
+	default:
+		return 0;
+	}
+
+	mutex_lock(&smu->mutex);
+
+	/* pass data to smu controller */
+	if ((smu->watermarks_bitmap & WATERMARKS_EXIST) &&
+			!(smu->watermarks_bitmap & WATERMARKS_LOADED)) {
+		ret = smu_write_watermarks_table(smu);
+
+		if (ret) {
+			mutex_unlock(&smu->mutex);
+			DRM_ERROR("Failed to update WMTABLE!\n");
+			return ret;
+		}
+		smu->watermarks_bitmap |= WATERMARKS_LOADED;
+	}
+
+	mutex_unlock(&smu->mutex);
+
+	return 0;
+}
+
 /**
  * dm_hw_init() - Initialize DC device
  * @handle: The base driver device containing the amdgpu_dm device.
@@ -1713,6 +1780,8 @@ static int dm_resume(void *handle)
 
 	amdgpu_dm_irq_resume_late(adev);
 
+	amdgpu_dm_smu_write_watermarks_table(adev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 0ef0eeb16778..4837640530ad 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -454,6 +454,7 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 					   aconnector->dc_sink);
 		dc_sink_release(aconnector->dc_sink);
 		aconnector->dc_sink = NULL;
+		aconnector->dc_link->cur_link_settings.lane_count = 0;
 	}
 
 	drm_connector_unregister(connector);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index e441c149ff40..deccab0228d2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -830,8 +830,8 @@ static void hubbub1_det_request_size(
 
 	hubbub1_get_blk256_size(&blk256_width, &blk256_height, bpe);
 
-	swath_bytes_horz_wc = height * blk256_height * bpe;
-	swath_bytes_vert_wc = width * blk256_width * bpe;
+	swath_bytes_horz_wc = width * blk256_height * bpe;
+	swath_bytes_vert_wc = height * blk256_width * bpe;
 
 	*req128_horz_wc = (2 * swath_bytes_horz_wc <= detile_buf_size) ?
 			false : /* full 256B request */
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 9f2428fd98f6..7a4f377005a1 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -222,7 +222,7 @@ int smu_set_soft_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 {
 	int ret = 0;
 
-	if (min <= 0 && max <= 0)
+	if (min < 0 && max < 0)
 		return -EINVAL;
 
 	if (!smu_clk_dpm_is_enabled(smu, clk_type))
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index 810994017f49..6024139d5a29 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -111,8 +111,8 @@ static struct smu_12_0_cmn2aisc_mapping renoir_clk_map[SMU_CLK_COUNT] = {
 	CLK_MAP(GFXCLK, CLOCK_GFXCLK),
 	CLK_MAP(SCLK,	CLOCK_GFXCLK),
 	CLK_MAP(SOCCLK, CLOCK_SOCCLK),
-	CLK_MAP(UCLK, CLOCK_UMCCLK),
-	CLK_MAP(MCLK, CLOCK_UMCCLK),
+	CLK_MAP(UCLK, CLOCK_FCLK),
+	CLK_MAP(MCLK, CLOCK_FCLK),
 };
 
 static struct smu_12_0_cmn2aisc_mapping renoir_table_map[SMU_TABLE_COUNT] = {
@@ -280,7 +280,7 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 		break;
 	case SMU_MCLK:
 		count = NUM_MEMCLK_DPM_LEVELS;
-		cur_value = metrics.ClockFrequency[CLOCK_UMCCLK];
+		cur_value = metrics.ClockFrequency[CLOCK_FCLK];
 		break;
 	case SMU_DCEFCLK:
 		count = NUM_DCFCLK_DPM_LEVELS;
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
index 870e6db2907e..518e6597bf2d 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
@@ -458,9 +458,6 @@ int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_
 {
 	int ret = 0;
 
-	if (max < min)
-		return -EINVAL;
-
 	switch (clk_type) {
 	case SMU_GFXCLK:
 	case SMU_SCLK:
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
index 5139c3724890..694c15bc7313 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
@@ -210,8 +210,7 @@ static int anx6345_dp_link_training(struct anx6345 *anx6345)
 	if (err)
 		return err;
 
-	dpcd[0] = drm_dp_max_link_rate(anx6345->dpcd);
-	dpcd[0] = drm_dp_link_rate_to_bw_code(dpcd[0]);
+	dpcd[0] = dp_bw;
 	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
 			   SP_DP_MAIN_LINK_BW_SET_REG, dpcd[0]);
 	if (err)
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 402a690d1fe5..e4c0ea03ae3a 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -298,7 +298,7 @@ static inline int tc_poll_timeout(struct tc_data *tc, unsigned int addr,
 
 static int tc_aux_wait_busy(struct tc_data *tc)
 {
-	return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 1000, 100000);
+	return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 100, 100000);
 }
 
 static int tc_aux_write_data(struct tc_data *tc, const void *data,
@@ -641,7 +641,7 @@ static int tc_aux_link_setup(struct tc_data *tc)
 	if (ret)
 		goto err;
 
-	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000);
+	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 100, 100000);
 	if (ret == -ETIMEDOUT) {
 		dev_err(tc->dev, "Timeout waiting for PHY to become ready");
 		return ret;
@@ -877,7 +877,7 @@ static int tc_wait_link_training(struct tc_data *tc)
 	int ret;
 
 	ret = tc_poll_timeout(tc, DP0_LTSTAT, LT_LOOPDONE,
-			      LT_LOOPDONE, 1, 1000);
+			      LT_LOOPDONE, 500, 100000);
 	if (ret) {
 		dev_err(tc->dev, "Link training timeout waiting for LT_LOOPDONE!\n");
 		return ret;
@@ -950,7 +950,7 @@ static int tc_main_link_enable(struct tc_data *tc)
 	dp_phy_ctrl &= ~(DP_PHY_RST | PHY_M1_RST | PHY_M0_RST);
 	ret = regmap_write(tc->regmap, DP_PHY_CTRL, dp_phy_ctrl);
 
-	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000);
+	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 500, 100000);
 	if (ret) {
 		dev_err(dev, "timeout waiting for phy become ready");
 		return ret;
diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c
index 40c4d4a5517b..e3eb6364c0f7 100644
--- a/drivers/gpu/drm/bridge/ti-tfp410.c
+++ b/drivers/gpu/drm/bridge/ti-tfp410.c
@@ -150,7 +150,8 @@ static int tfp410_attach(struct drm_bridge *bridge,
 					  dvi->next_bridge->type,
 					  dvi->next_bridge->ddc);
 	if (ret) {
-		dev_err(dvi->dev, "drm_connector_init() failed: %d\n", ret);
+		dev_err(dvi->dev, "drm_connector_init_with_ddc() failed: %d\n",
+			ret);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index 841794e19eb6..7443114bd713 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -951,7 +951,8 @@ bool drm_client_rotation(struct drm_mode_set *modeset, unsigned int *rotation)
 	 * depending on the hardware this may require the framebuffer
 	 * to be in a specific tiling format.
 	 */
-	if ((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180 ||
+	if (((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_0 &&
+	     (*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180) ||
 	    !plane->rotation_property)
 		return false;
 
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index a421a2eed48a..df31e5782eed 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -254,11 +254,16 @@ static void *drm_gem_shmem_vmap_locked(struct drm_gem_shmem_object *shmem)
 	if (ret)
 		goto err_zero_use;
 
-	if (obj->import_attach)
+	if (obj->import_attach) {
 		shmem->vaddr = dma_buf_vmap(obj->import_attach->dmabuf);
-	else
+	} else {
+		pgprot_t prot = PAGE_KERNEL;
+
+		if (!shmem->map_cached)
+			prot = pgprot_writecombine(prot);
 		shmem->vaddr = vmap(shmem->pages, obj->size >> PAGE_SHIFT,
-				    VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+				    VM_MAP, prot);
+	}
 
 	if (!shmem->vaddr) {
 		DRM_DEBUG_KMS("Failed to vmap pages\n");
@@ -540,8 +545,9 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	}
 
 	vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND;
-	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
-	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
+	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+	if (!shmem->map_cached)
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
 	vma->vm_ops = &drm_gem_shmem_vm_ops;
 
 	return 0;
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 10336b144c72..d4d64518e11b 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1698,6 +1698,13 @@ static int drm_mode_parse_cmdline_options(const char *str,
 	if (rotation && freestanding)
 		return -EINVAL;
 
+	if (!(rotation & DRM_MODE_ROTATE_MASK))
+		rotation |= DRM_MODE_ROTATE_0;
+
+	/* Make sure there is exactly one rotation defined */
+	if (!is_power_of_2(rotation & DRM_MODE_ROTATE_MASK))
+		return -EINVAL;
+
 	mode->rotation_reflection = rotation;
 
 	return 0;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 669d3857502a..342d2a723a0e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1773,8 +1773,9 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(dsi->supplies),
 				      dsi->supplies);
 	if (ret) {
-		dev_info(dev, "failed to get regulators: %d\n", ret);
-		return -EPROBE_DEFER;
+		if (ret != -EPROBE_DEFER)
+			dev_info(dev, "failed to get regulators: %d\n", ret);
+		return ret;
 	}
 
 	dsi->clks = devm_kcalloc(dev,
@@ -1787,9 +1788,10 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 		dsi->clks[i] = devm_clk_get(dev, clk_names[i]);
 		if (IS_ERR(dsi->clks[i])) {
 			if (strcmp(clk_names[i], "sclk_mipi") == 0) {
-				strcpy(clk_names[i], OLD_SCLK_MIPI_CLK_NAME);
-				i--;
-				continue;
+				dsi->clks[i] = devm_clk_get(dev,
+							OLD_SCLK_MIPI_CLK_NAME);
+				if (!IS_ERR(dsi->clks[i]))
+					continue;
 			}
 
 			dev_info(dev, "failed to get the clock: %s\n",
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 3e5f1a77286d..1a7c828fc41d 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -1805,18 +1805,10 @@ static int hdmi_resources_init(struct hdmi_context *hdata)
 
 	hdata->reg_hdmi_en = devm_regulator_get_optional(dev, "hdmi-en");
 
-	if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV) {
+	if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV)
 		if (IS_ERR(hdata->reg_hdmi_en))
 			return PTR_ERR(hdata->reg_hdmi_en);
 
-		ret = regulator_enable(hdata->reg_hdmi_en);
-		if (ret) {
-			DRM_DEV_ERROR(dev,
-				      "failed to enable hdmi-en regulator\n");
-			return ret;
-		}
-	}
-
 	return hdmi_bridge_init(hdata);
 }
 
@@ -2023,6 +2015,15 @@ static int hdmi_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (!IS_ERR(hdata->reg_hdmi_en)) {
+		ret = regulator_enable(hdata->reg_hdmi_en);
+		if (ret) {
+			DRM_DEV_ERROR(dev,
+			      "failed to enable hdmi-en regulator\n");
+			goto err_hdmiphy;
+		}
+	}
+
 	pm_runtime_enable(dev);
 
 	audio_infoframe = &hdata->audio.infoframe;
@@ -2047,7 +2048,8 @@ err_unregister_audio:
 
 err_rpm_disable:
 	pm_runtime_disable(dev);
-
+	if (!IS_ERR(hdata->reg_hdmi_en))
+		regulator_disable(hdata->reg_hdmi_en);
 err_hdmiphy:
 	if (hdata->hdmiphy_port)
 		put_device(&hdata->hdmiphy_port->dev);
diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h b/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h
index 0da860200410..e2ac09894a6d 100644
--- a/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h
+++ b/drivers/gpu/drm/hisilicon/kirin/kirin_ade_reg.h
@@ -83,7 +83,6 @@
 #define VSIZE_OFST			20
 #define LDI_INT_EN			0x741C
 #define FRAME_END_INT_EN_OFST		1
-#define UNDERFLOW_INT_EN_OFST		2
 #define LDI_CTRL			0x7420
 #define BPP_OFST			3
 #define DATA_GATE_EN			BIT(2)
diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
index 73cd28a6ea07..86000127d4ee 100644
--- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
+++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
@@ -46,7 +46,6 @@ struct ade_hw_ctx {
 	struct clk *media_noc_clk;
 	struct clk *ade_pix_clk;
 	struct reset_control *reset;
-	struct work_struct display_reset_wq;
 	bool power_on;
 	int irq;
 
@@ -136,7 +135,6 @@ static void ade_init(struct ade_hw_ctx *ctx)
 	 */
 	ade_update_bits(base + ADE_CTRL, FRM_END_START_OFST,
 			FRM_END_START_MASK, REG_EFFECTIVE_IN_ADEEN_FRMEND);
-	ade_update_bits(base + LDI_INT_EN, UNDERFLOW_INT_EN_OFST, MASK(1), 1);
 }
 
 static bool ade_crtc_mode_fixup(struct drm_crtc *crtc,
@@ -304,17 +302,6 @@ static void ade_crtc_disable_vblank(struct drm_crtc *crtc)
 			MASK(1), 0);
 }
 
-static void drm_underflow_wq(struct work_struct *work)
-{
-	struct ade_hw_ctx *ctx = container_of(work, struct ade_hw_ctx,
-					      display_reset_wq);
-	struct drm_device *drm_dev = ctx->crtc->dev;
-	struct drm_atomic_state *state;
-
-	state = drm_atomic_helper_suspend(drm_dev);
-	drm_atomic_helper_resume(drm_dev, state);
-}
-
 static irqreturn_t ade_irq_handler(int irq, void *data)
 {
 	struct ade_hw_ctx *ctx = data;
@@ -331,12 +318,6 @@ static irqreturn_t ade_irq_handler(int irq, void *data)
 				MASK(1), 1);
 		drm_crtc_handle_vblank(crtc);
 	}
-	if (status & BIT(UNDERFLOW_INT_EN_OFST)) {
-		ade_update_bits(base + LDI_INT_CLR, UNDERFLOW_INT_EN_OFST,
-				MASK(1), 1);
-		DRM_ERROR("LDI underflow!");
-		schedule_work(&ctx->display_reset_wq);
-	}
 
 	return IRQ_HANDLED;
 }
@@ -919,7 +900,6 @@ static void *ade_hw_ctx_alloc(struct platform_device *pdev,
 	if (ret)
 		return ERR_PTR(-EIO);
 
-	INIT_WORK(&ctx->display_reset_wq, drm_underflow_wq);
 	ctx->crtc = crtc;
 
 	return ctx;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index ef7c74cff28a..43912e9b683d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -570,7 +570,7 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 
 	obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+		return false;
 
 	mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
 	i915_gem_object_put(obj);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 8a5054f21bf8..24c99d0838af 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -147,24 +147,32 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 
 			fence = i915_active_fence_get(&tl->last_request);
 			if (fence) {
+				mutex_unlock(&tl->mutex);
+
 				timeout = dma_fence_wait_timeout(fence,
 								 interruptible,
 								 timeout);
 				dma_fence_put(fence);
+
+				/* Retirement is best effort */
+				if (!mutex_trylock(&tl->mutex)) {
+					active_count++;
+					goto out_active;
+				}
 			}
 		}
 
 		if (!retire_requests(tl) || flush_submission(gt))
 			active_count++;
+		mutex_unlock(&tl->mutex);
 
-		spin_lock(&timelines->lock);
+out_active:	spin_lock(&timelines->lock);
 
-		/* Resume iteration after dropping lock */
+		/* Resume list iteration after reacquiring spinlock */
 		list_safe_reset_next(tl, tn, link);
 		if (atomic_dec_and_test(&tl->active_count))
 			list_del(&tl->link);
 
-		mutex_unlock(&tl->mutex);
 
 		/* Defer the final release to after the spinlock */
 		if (refcount_dec_and_test(&tl->kref.refcount)) {
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 887e0dc701f7..06cef3c18f26 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -580,24 +580,19 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
-	u32 val;
-
 	/* Wa_1409142259:tgl */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 
-	/* Wa_1604555607:tgl */
-	val = intel_uncore_read(engine->uncore, FF_MODE2);
-	val &= ~FF_MODE2_TDS_TIMER_MASK;
-	val |= FF_MODE2_TDS_TIMER_128;
 	/*
-	 * FIXME: FF_MODE2 register is not readable till TGL B0. We can
-	 * enable verification of WA from the later steppings, which enables
-	 * the read of FF_MODE2.
+	 * Wa_1604555607:gen12 and Wa_1608008084:gen12
+	 * FF_MODE2 register will return the wrong value when read. The default
+	 * value for this register is zero for all fields and there are no bit
+	 * masks. So instead of doing a RMW we should just write the TDS timer
+	 * value for Wa_1604555607.
 	 */
-	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, val,
-	       IS_TGL_REVID(engine->i915, TGL_REVID_A0, TGL_REVID_A0) ? 0 :
-			    FF_MODE2_TDS_TIMER_MASK);
+	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK,
+	       FF_MODE2_TDS_TIMER_128, 0);
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 2477a1e5a166..ae139f0877ae 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -151,12 +151,12 @@ static void dmabuf_gem_object_free(struct kref *kref)
 			dmabuf_obj = container_of(pos,
 					struct intel_vgpu_dmabuf_obj, list);
 			if (dmabuf_obj == obj) {
+				list_del(pos);
 				intel_gvt_hypervisor_put_vfio_device(vgpu);
 				idr_remove(&vgpu->object_idr,
 					   dmabuf_obj->dmabuf_id);
 				kfree(dmabuf_obj->info);
 				kfree(dmabuf_obj);
-				list_del(pos);
 				break;
 			}
 		}
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 85bd9bf4f6ee..487af6ea9972 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -560,9 +560,9 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 
 		intel_vgpu_reset_mmio(vgpu, dmlr);
 		populate_pvinfo_page(vgpu);
-		intel_vgpu_reset_display(vgpu);
 
 		if (dmlr) {
+			intel_vgpu_reset_display(vgpu);
 			intel_vgpu_reset_cfg_space(vgpu);
 			/* only reset the failsafe mode when dmlr reset */
 			vgpu->failsafe = false;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index e34c79df6ebc..79391d92ab7e 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1970,9 +1970,10 @@ out:
 	return i915_vma_get(oa_bo->vma);
 }
 
-static int emit_oa_config(struct i915_perf_stream *stream,
-			  struct i915_oa_config *oa_config,
-			  struct intel_context *ce)
+static struct i915_request *
+emit_oa_config(struct i915_perf_stream *stream,
+	       struct i915_oa_config *oa_config,
+	       struct intel_context *ce)
 {
 	struct i915_request *rq;
 	struct i915_vma *vma;
@@ -1980,7 +1981,7 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 
 	vma = get_oa_vma(stream, oa_config);
 	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+		return ERR_CAST(vma);
 
 	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
@@ -2005,13 +2006,17 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 	err = rq->engine->emit_bb_start(rq,
 					vma->node.start, 0,
 					I915_DISPATCH_SECURE);
+	if (err)
+		goto err_add_request;
+
+	i915_request_get(rq);
 err_add_request:
 	i915_request_add(rq);
 err_vma_unpin:
 	i915_vma_unpin(vma);
 err_vma_put:
 	i915_vma_put(vma);
-	return err;
+	return err ? ERR_PTR(err) : rq;
 }
 
 static struct intel_context *oa_context(struct i915_perf_stream *stream)
@@ -2019,7 +2024,8 @@ static struct intel_context *oa_context(struct i915_perf_stream *stream)
 	return stream->pinned_ctx ?: stream->engine->kernel_context;
 }
 
-static int hsw_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+hsw_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 
@@ -2422,7 +2428,8 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
 	return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
 }
 
-static int gen8_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen8_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2464,7 +2471,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	 */
 	ret = lrc_configure_all_contexts(stream, oa_config);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
 }
@@ -2476,7 +2483,8 @@ static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream)
 			     0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
 }
 
-static int gen12_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen12_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2507,7 +2515,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	 */
 	ret = gen12_configure_all_contexts(stream, oa_config);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	/*
 	 * For Gen12, performance counters are context
@@ -2517,7 +2525,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	if (stream->ctx) {
 		ret = gen12_configure_oar_context(stream, true);
 		if (ret)
-			return ret;
+			return ERR_PTR(ret);
 	}
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
@@ -2715,6 +2723,20 @@ static const struct i915_perf_stream_ops i915_oa_stream_ops = {
 	.read = i915_oa_read,
 };
 
+static int i915_perf_stream_enable_sync(struct i915_perf_stream *stream)
+{
+	struct i915_request *rq;
+
+	rq = stream->perf->ops.enable_metric_set(stream);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
+	i915_request_put(rq);
+
+	return 0;
+}
+
 /**
  * i915_oa_stream_init - validate combined props for OA stream and init
  * @stream: An i915 perf stream
@@ -2849,7 +2871,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	stream->ops = &i915_oa_stream_ops;
 	perf->exclusive_stream = stream;
 
-	ret = perf->ops.enable_metric_set(stream);
+	ret = i915_perf_stream_enable_sync(stream);
 	if (ret) {
 		DRM_DEBUG("Unable to enable metric set\n");
 		goto err_enable;
@@ -3167,7 +3189,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		return -EINVAL;
 
 	if (config != stream->oa_config) {
-		int err;
+		struct i915_request *rq;
 
 		/*
 		 * If OA is bound to a specific context, emit the
@@ -3178,11 +3200,13 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		 * When set globally, we use a low priority kernel context,
 		 * so it will effectively take effect when idle.
 		 */
-		err = emit_oa_config(stream, config, oa_context(stream));
-		if (err == 0)
+		rq = emit_oa_config(stream, config, oa_context(stream));
+		if (!IS_ERR(rq)) {
 			config = xchg(&stream->oa_config, config);
-		else
-			ret = err;
+			i915_request_put(rq);
+		} else {
+			ret = PTR_ERR(rq);
+		}
 	}
 
 	i915_oa_config_put(config);
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 45e581455f5d..a0e22f00f6cf 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -339,7 +339,8 @@ struct i915_oa_ops {
 	 * counter reports being sampled. May apply system constraints such as
 	 * disabling EU clock gating as required.
 	 */
-	int (*enable_metric_set)(struct i915_perf_stream *stream);
+	struct i915_request *
+		(*enable_metric_set)(struct i915_perf_stream *stream);
 
 	/**
 	 * @disable_metric_set: Remove system constraints associated with using
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index d53af93b919b..e5a55801f753 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -290,7 +290,7 @@ bool i915_request_retire(struct i915_request *rq)
 	spin_unlock_irq(&rq->lock);
 
 	remove_from_client(rq);
-	list_del(&rq->link);
+	list_del_rcu(&rq->link);
 
 	intel_context_exit(rq->context);
 	intel_context_unpin(rq->context);
@@ -736,6 +736,8 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->infix = rq->ring->emit; /* end of header; start of user payload */
 
 	intel_context_mark_active(ce);
+	list_add_tail_rcu(&rq->link, &tl->requests);
+
 	return rq;
 
 err_unwind:
@@ -792,13 +794,23 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 	GEM_BUG_ON(i915_request_timeline(rq) ==
 		   rcu_access_pointer(signal->timeline));
 
+	if (i915_request_started(signal))
+		return 0;
+
 	fence = NULL;
 	rcu_read_lock();
 	spin_lock_irq(&signal->lock);
-	if (!i915_request_started(signal) &&
-	    !list_is_first(&signal->link,
-			   &rcu_dereference(signal->timeline)->requests)) {
-		struct i915_request *prev = list_prev_entry(signal, link);
+	do {
+		struct list_head *pos = READ_ONCE(signal->link.prev);
+		struct i915_request *prev;
+
+		/* Confirm signal has not been retired, the link is valid */
+		if (unlikely(i915_request_started(signal)))
+			break;
+
+		/* Is signal the earliest request on its timeline? */
+		if (pos == &rcu_dereference(signal->timeline)->requests)
+			break;
 
 		/*
 		 * Peek at the request before us in the timeline. That
@@ -806,13 +818,18 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 		 * after acquiring a reference to it, confirm that it is
 		 * still part of the signaler's timeline.
 		 */
-		if (i915_request_get_rcu(prev)) {
-			if (list_next_entry(prev, link) == signal)
-				fence = &prev->fence;
-			else
-				i915_request_put(prev);
+		prev = list_entry(pos, typeof(*prev), link);
+		if (!i915_request_get_rcu(prev))
+			break;
+
+		/* After the strong barrier, confirm prev is still attached */
+		if (unlikely(READ_ONCE(prev->link.next) != &signal->link)) {
+			i915_request_put(prev);
+			break;
 		}
-	}
+
+		fence = &prev->fence;
+	} while (0);
 	spin_unlock_irq(&signal->lock);
 	rcu_read_unlock();
 	if (!fence)
@@ -1253,8 +1270,6 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 							 0);
 	}
 
-	list_add_tail(&rq->link, &timeline->requests);
-
 	/*
 	 * Make sure that no request gazumped us - if it was allocated after
 	 * our i915_request_alloc() and called __i915_request_add() before
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 0dfcd1787e65..fe85e487e477 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -486,6 +486,7 @@ static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc)
 	}
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
 	if (mtk_crtc->cmdq_client) {
+		mbox_flush(mtk_crtc->cmdq_client->chan, 2000);
 		cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE);
 		cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
 		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event);
@@ -636,10 +637,18 @@ static const struct drm_crtc_helper_funcs mtk_crtc_helper_funcs = {
 
 static int mtk_drm_crtc_init(struct drm_device *drm,
 			     struct mtk_drm_crtc *mtk_crtc,
-			     struct drm_plane *primary,
-			     struct drm_plane *cursor, unsigned int pipe)
+			     unsigned int pipe)
 {
-	int ret;
+	struct drm_plane *primary = NULL;
+	struct drm_plane *cursor = NULL;
+	int i, ret;
+
+	for (i = 0; i < mtk_crtc->layer_nr; i++) {
+		if (mtk_crtc->planes[i].type == DRM_PLANE_TYPE_PRIMARY)
+			primary = &mtk_crtc->planes[i];
+		else if (mtk_crtc->planes[i].type == DRM_PLANE_TYPE_CURSOR)
+			cursor = &mtk_crtc->planes[i];
+	}
 
 	ret = drm_crtc_init_with_planes(drm, &mtk_crtc->base, primary, cursor,
 					&mtk_crtc_funcs, NULL);
@@ -689,11 +698,12 @@ static int mtk_drm_crtc_num_comp_planes(struct mtk_drm_crtc *mtk_crtc,
 }
 
 static inline
-enum drm_plane_type mtk_drm_crtc_plane_type(unsigned int plane_idx)
+enum drm_plane_type mtk_drm_crtc_plane_type(unsigned int plane_idx,
+					    unsigned int num_planes)
 {
 	if (plane_idx == 0)
 		return DRM_PLANE_TYPE_PRIMARY;
-	else if (plane_idx == 1)
+	else if (plane_idx == (num_planes - 1))
 		return DRM_PLANE_TYPE_CURSOR;
 	else
 		return DRM_PLANE_TYPE_OVERLAY;
@@ -712,7 +722,8 @@ static int mtk_drm_crtc_init_comp_planes(struct drm_device *drm_dev,
 		ret = mtk_plane_init(drm_dev,
 				&mtk_crtc->planes[mtk_crtc->layer_nr],
 				BIT(pipe),
-				mtk_drm_crtc_plane_type(mtk_crtc->layer_nr),
+				mtk_drm_crtc_plane_type(mtk_crtc->layer_nr,
+							num_planes),
 				mtk_ddp_comp_supported_rotations(comp));
 		if (ret)
 			return ret;
@@ -807,9 +818,7 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 			return ret;
 	}
 
-	ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, &mtk_crtc->planes[0],
-				mtk_crtc->layer_nr > 1 ? &mtk_crtc->planes[1] :
-				NULL, pipe);
+	ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, pipe);
 	if (ret < 0)
 		return ret;
 
@@ -828,7 +837,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 			drm_crtc_index(&mtk_crtc->base));
 		mtk_crtc->cmdq_client = NULL;
 	}
-	ret = of_property_read_u32_index(dev->of_node, "mediatek,gce-events",
+	ret = of_property_read_u32_index(priv->mutex_node,
+					 "mediatek,gce-events",
 					 drm_crtc_index(&mtk_crtc->base),
 					 &mtk_crtc->cmdq_event);
 	if (ret)
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 1f5a112bb034..57c88de9a329 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -471,6 +471,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 	/* Only DMA capable components need the LARB property */
 	comp->larb_dev = NULL;
 	if (type != MTK_DISP_OVL &&
+	    type != MTK_DISP_OVL_2L &&
 	    type != MTK_DISP_RDMA &&
 	    type != MTK_DISP_WDMA)
 		return 0;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 914cc7619cd7..c2bd683a87c8 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -80,6 +80,7 @@ static int mtk_plane_atomic_async_check(struct drm_plane *plane,
 					struct drm_plane_state *state)
 {
 	struct drm_crtc_state *crtc_state;
+	int ret;
 
 	if (plane != state->crtc->cursor)
 		return -EINVAL;
@@ -90,6 +91,11 @@ static int mtk_plane_atomic_async_check(struct drm_plane *plane,
 	if (!plane->state->fb)
 		return -EINVAL;
 
+	ret = mtk_drm_crtc_plane_check(state->crtc, plane,
+				       to_mtk_plane_state(state));
+	if (ret)
+		return ret;
+
 	if (state->state)
 		crtc_state = drm_atomic_get_existing_crtc_state(state->state,
 								state->crtc);
@@ -115,6 +121,7 @@ static void mtk_plane_atomic_async_update(struct drm_plane *plane,
 	plane->state->src_y = new_state->src_y;
 	plane->state->src_h = new_state->src_h;
 	plane->state->src_w = new_state->src_w;
+	swap(plane->state->fb, new_state->fb);
 	state->pending.async_dirty = true;
 
 	mtk_drm_crtc_async_update(new_state->crtc, plane, new_state);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 983afeaee737..748cd379065f 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -796,12 +796,41 @@ bool a6xx_gmu_isidle(struct a6xx_gmu *gmu)
 	return true;
 }
 
+#define GBIF_CLIENT_HALT_MASK             BIT(0)
+#define GBIF_ARB_HALT_MASK                BIT(1)
+
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+{
+	struct msm_gpu *gpu = &adreno_gpu->base;
+
+	if (!a6xx_has_gbif(adreno_gpu)) {
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
+		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
+								0xf) == 0xf);
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+
+		return;
+	}
+
+	/* Halt new client requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
+	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
+
+	/* Halt all AXI requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
+	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
+
+	/* The GBIF halt needs to be explicitly cleared */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+}
+
 /* Gracefully try to shut down the GMU and by extension the GPU */
 static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 {
 	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
-	struct msm_gpu *gpu = &adreno_gpu->base;
 	u32 val;
 
 	/*
@@ -819,11 +848,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 			return;
 		}
 
-		/* Clear the VBIF pipe before shutting down */
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
-		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & 0xf)
-			== 0xf);
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+		a6xx_bus_clear_pending_transactions(adreno_gpu);
 
 		/* tell the GMU we want to slumber */
 		a6xx_gmu_notify_slumber(gmu);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index daf07800cde0..68af24150de5 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -378,18 +378,6 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	int ret;
 
-	/*
-	 * During a previous slumber, GBIF halt is asserted to ensure
-	 * no further transaction can go through GPU before GPU
-	 * headswitch is turned off.
-	 *
-	 * This halt is deasserted once headswitch goes off but
-	 * incase headswitch doesn't goes off clear GBIF halt
-	 * here to ensure GPU wake-up doesn't fail because of
-	 * halted GPU transactions.
-	 */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
-
 	/* Make sure the GMU keeps the GPU on while we set it up */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
 
@@ -470,10 +458,12 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	/* Select CP0 to always count cycles */
 	gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT);
 
-	gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1);
-	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1);
-	gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1);
-	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21);
+	if (adreno_is_a630(adreno_gpu)) {
+		gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1);
+		gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1);
+		gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1);
+		gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21);
+	}
 
 	/* Enable fault detection */
 	gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL,
@@ -748,39 +738,6 @@ static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL),
 };
 
-#define GBIF_CLIENT_HALT_MASK             BIT(0)
-#define GBIF_ARB_HALT_MASK                BIT(1)
-
-static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
-{
-	struct msm_gpu *gpu = &adreno_gpu->base;
-
-	if(!a6xx_has_gbif(adreno_gpu)){
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
-		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
-								0xf) == 0xf);
-		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
-
-		return;
-	}
-
-	/* Halt new client requests on GBIF */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
-	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
-			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
-
-	/* Halt all AXI requests on GBIF */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
-	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
-			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
-
-	/*
-	 * GMU needs DDR access in slumber path. Deassert GBIF halt now
-	 * to allow for GMU to access system memory.
-	 */
-	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
-}
-
 static int a6xx_pm_resume(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -805,16 +762,6 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	devfreq_suspend_device(gpu->devfreq.devfreq);
 
-	/*
-	 * Make sure the GMU is idle before continuing (because some transitions
-	 * may use VBIF
-	 */
-	a6xx_gmu_wait_for_idle(&a6xx_gpu->gmu);
-
-	/* Clear the VBIF pipe before shutting down */
-	/* FIXME: This accesses the GPU - do we need to make sure it is on? */
-	a6xx_bus_clear_pending_transactions(adreno_gpu);
-
 	return a6xx_gmu_stop(a6xx_gpu);
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index eda11abc5f01..e450e0b97211 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -7,6 +7,7 @@
 
 #include "a6xx_gmu.h"
 #include "a6xx_gmu.xml.h"
+#include "a6xx_gpu.h"
 
 #define HFI_MSG_ID(val) [val] = #val
 
@@ -216,48 +217,82 @@ static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu)
 		NULL, 0);
 }
 
-static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
+static void a618_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
 {
-	struct a6xx_hfi_msg_bw_table msg = { 0 };
+	/* Send a single "off" entry since the 618 GMU doesn't do bus scaling */
+	msg->bw_level_num = 1;
+
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x01;
+
+	msg->ddr_cmds_addrs[0] = 0x50000;
+	msg->ddr_cmds_addrs[1] = 0x5003c;
+	msg->ddr_cmds_addrs[2] = 0x5000c;
+
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
 
 	/*
-	 * The sdm845 GMU doesn't do bus frequency scaling on its own but it
-	 * does need at least one entry in the list because it might be accessed
-	 * when the GMU is shutting down. Send a single "off" entry.
+	 * These are the CX (CNOC) votes - these are used by the GMU but the
+	 * votes are known and fixed for the target
 	 */
+	msg->cnoc_cmds_num = 1;
+	msg->cnoc_wait_bitmask = 0x01;
+
+	msg->cnoc_cmds_addrs[0] = 0x5007c;
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+}
 
-	msg.bw_level_num = 1;
+static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
+{
+	/* Send a single "off" entry since the 630 GMU doesn't do bus scaling */
+	msg->bw_level_num = 1;
 
-	msg.ddr_cmds_num = 3;
-	msg.ddr_wait_bitmask = 0x07;
+	msg->ddr_cmds_num = 3;
+	msg->ddr_wait_bitmask = 0x07;
 
-	msg.ddr_cmds_addrs[0] = 0x50000;
-	msg.ddr_cmds_addrs[1] = 0x5005c;
-	msg.ddr_cmds_addrs[2] = 0x5000c;
+	msg->ddr_cmds_addrs[0] = 0x50000;
+	msg->ddr_cmds_addrs[1] = 0x5005c;
+	msg->ddr_cmds_addrs[2] = 0x5000c;
 
-	msg.ddr_cmds_data[0][0] =  0x40000000;
-	msg.ddr_cmds_data[0][1] =  0x40000000;
-	msg.ddr_cmds_data[0][2] =  0x40000000;
+	msg->ddr_cmds_data[0][0] =  0x40000000;
+	msg->ddr_cmds_data[0][1] =  0x40000000;
+	msg->ddr_cmds_data[0][2] =  0x40000000;
 
 	/*
 	 * These are the CX (CNOC) votes.  This is used but the values for the
 	 * sdm845 GMU are known and fixed so we can hard code them.
 	 */
 
-	msg.cnoc_cmds_num = 3;
-	msg.cnoc_wait_bitmask = 0x05;
+	msg->cnoc_cmds_num = 3;
+	msg->cnoc_wait_bitmask = 0x05;
 
-	msg.cnoc_cmds_addrs[0] = 0x50034;
-	msg.cnoc_cmds_addrs[1] = 0x5007c;
-	msg.cnoc_cmds_addrs[2] = 0x5004c;
+	msg->cnoc_cmds_addrs[0] = 0x50034;
+	msg->cnoc_cmds_addrs[1] = 0x5007c;
+	msg->cnoc_cmds_addrs[2] = 0x5004c;
 
-	msg.cnoc_cmds_data[0][0] =  0x40000000;
-	msg.cnoc_cmds_data[0][1] =  0x00000000;
-	msg.cnoc_cmds_data[0][2] =  0x40000000;
+	msg->cnoc_cmds_data[0][0] =  0x40000000;
+	msg->cnoc_cmds_data[0][1] =  0x00000000;
+	msg->cnoc_cmds_data[0][2] =  0x40000000;
+
+	msg->cnoc_cmds_data[1][0] =  0x60000001;
+	msg->cnoc_cmds_data[1][1] =  0x20000001;
+	msg->cnoc_cmds_data[1][2] =  0x60000001;
+}
+
+
+static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
+{
+	struct a6xx_hfi_msg_bw_table msg = { 0 };
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 
-	msg.cnoc_cmds_data[1][0] =  0x60000001;
-	msg.cnoc_cmds_data[1][1] =  0x20000001;
-	msg.cnoc_cmds_data[1][2] =  0x60000001;
+	if (adreno_is_a618(adreno_gpu))
+		a618_build_bw_table(&msg);
+	else
+		a6xx_build_bw_table(&msg);
 
 	return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_BW_TABLE, &msg, sizeof(msg),
 		NULL, 0);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index 528632690f1e..a05282dede91 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -255,13 +255,13 @@ static const struct dpu_format dpu_format_map[] = {
 
 	INTERLEAVED_RGB_FMT(RGB565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
 	INTERLEAVED_RGB_FMT(BGR565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
index 29705e773a4b..80d3cfc14007 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
@@ -12,6 +12,7 @@
 
 #define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base)
 
+#define HW_REV				0x0
 #define HW_INTR_STATUS			0x0010
 
 /* Max BW defined in KBps */
@@ -22,6 +23,17 @@ struct dpu_irq_controller {
 	struct irq_domain *domain;
 };
 
+struct dpu_hw_cfg {
+	u32 val;
+	u32 offset;
+};
+
+struct dpu_mdss_hw_init_handler {
+	u32 hw_rev;
+	u32 hw_reg_count;
+	struct dpu_hw_cfg* hw_cfg;
+};
+
 struct dpu_mdss {
 	struct msm_mdss base;
 	void __iomem *mmio;
@@ -32,6 +44,44 @@ struct dpu_mdss {
 	u32 num_paths;
 };
 
+static struct dpu_hw_cfg hw_cfg[] = {
+    {
+	/* UBWC global settings */
+	.val = 0x1E,
+	.offset = 0x144,
+    }
+};
+
+static struct dpu_mdss_hw_init_handler cfg_handler[] = {
+    { .hw_rev = DPU_HW_VER_620,
+      .hw_reg_count = ARRAY_SIZE(hw_cfg),
+      .hw_cfg = hw_cfg
+    },
+};
+
+static void dpu_mdss_hw_init(struct dpu_mdss *dpu_mdss, u32 hw_rev)
+{
+	int i;
+	u32 count = 0;
+	struct dpu_hw_cfg *hw_cfg = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) {
+		if (cfg_handler[i].hw_rev == hw_rev) {
+			hw_cfg = cfg_handler[i].hw_cfg;
+			count = cfg_handler[i].hw_reg_count;
+			break;
+	    }
+	}
+
+	for (i = 0; i < count; i++ ) {
+		writel_relaxed(hw_cfg->val,
+			dpu_mdss->mmio + hw_cfg->offset);
+		hw_cfg++;
+	}
+
+    return;
+}
+
 static int dpu_mdss_parse_data_bus_icc_path(struct drm_device *dev,
 						struct dpu_mdss *dpu_mdss)
 {
@@ -174,12 +224,18 @@ static int dpu_mdss_enable(struct msm_mdss *mdss)
 	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
 	struct dss_module_power *mp = &dpu_mdss->mp;
 	int ret;
+	u32 mdss_rev;
 
 	dpu_mdss_icc_request_bw(mdss);
 
 	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
-	if (ret)
+	if (ret) {
 		DPU_ERROR("clock enable failed, ret:%d\n", ret);
+		return ret;
+	}
+
+	mdss_rev = readl_relaxed(dpu_mdss->mmio + HW_REV);
+	dpu_mdss_hw_init(dpu_mdss, mdss_rev);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index b3d0a0fe76b9..998bef1190a3 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -1191,8 +1191,8 @@ static void mdp5_crtc_wait_for_pp_done(struct drm_crtc *crtc)
 	ret = wait_for_completion_timeout(&mdp5_crtc->pp_completion,
 						msecs_to_jiffies(50));
 	if (ret == 0)
-		dev_warn(dev->dev, "pp done time out, lm=%d\n",
-			 mdp5_cstate->pipeline.mixer->lm);
+		dev_warn_ratelimited(dev->dev, "pp done time out, lm=%d\n",
+				     mdp5_cstate->pipeline.mixer->lm);
 }
 
 static void mdp5_crtc_wait_for_flush_done(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 6af26ab5b09d..4b363bd7ddff 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -336,7 +336,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 	return num;
 }
 
-static int dsi_mgr_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status dsi_mgr_connector_mode_valid(struct drm_connector *connector,
 				struct drm_display_mode *mode)
 {
 	int id = dsi_mgr_connector_get_id(connector);
@@ -506,6 +506,7 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 	struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1);
 	struct mipi_dsi_host *host = msm_dsi->host;
 	struct drm_panel *panel = msm_dsi->panel;
+	struct msm_dsi_pll *src_pll;
 	bool is_dual_dsi = IS_DUAL_DSI();
 	int ret;
 
@@ -539,6 +540,10 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 								id, ret);
 	}
 
+	/* Save PLL status if it is a clock source */
+	src_pll = msm_dsi_phy_get_pll(msm_dsi->phy);
+	msm_dsi_pll_save_state(src_pll);
+
 	ret = msm_dsi_host_power_off(host);
 	if (ret)
 		pr_err("%s: host %d power off failed,%d\n", __func__, id, ret);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index b0cfa67d2a57..f509ebd77500 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -724,10 +724,6 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy)
 	if (!phy || !phy->cfg->ops.disable)
 		return;
 
-	/* Save PLL status if it is a clock source */
-	if (phy->usecase != MSM_DSI_PHY_SLAVE)
-		msm_dsi_pll_save_state(phy->pll);
-
 	phy->cfg->ops.disable(phy);
 
 	dsi_phy_regulator_disable(phy);
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
index 1c894548dd72..6ac04fc303f5 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -411,6 +411,12 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw)
 	if (pll_10nm->slave)
 		dsi_pll_enable_pll_bias(pll_10nm->slave);
 
+	rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0);
+	if (rc) {
+		pr_err("vco_set_rate failed, rc=%d\n", rc);
+		return rc;
+	}
+
 	/* Start PLL */
 	pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_PLL_CNTRL,
 		  0x01);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 890315291b01..bb737f9281e6 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -458,6 +458,8 @@ nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state)
 		asyw->clr.ntfy = armw->ntfy.handle != 0;
 		asyw->clr.sema = armw->sema.handle != 0;
 		asyw->clr.xlut = armw->xlut.handle != 0;
+		if (asyw->clr.xlut && asyw->visible)
+			asyw->set.xlut = asyw->xlut.handle != 0;
 		asyw->clr.csc  = armw->csc.valid;
 		if (wndw->func->image_clr)
 			asyw->clr.image = armw->image.handle[0] != 0;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index c7d700916eae..8ebbe1656008 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2579,6 +2579,7 @@ nv166_chipset = {
 static const struct nvkm_device_chip
 nv167_chipset = {
 	.name = "TU117",
+	.acr = tu102_acr_new,
 	.bar = tu102_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2607,6 +2608,7 @@ nv167_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
+	.gr = tu102_gr_new,
 	.nvdec[0] = gm107_nvdec_new,
 	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
@@ -2615,6 +2617,7 @@ nv167_chipset = {
 static const struct nvkm_device_chip
 nv168_chipset = {
 	.name = "TU116",
+	.acr = tu102_acr_new,
 	.bar = tu102_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2643,6 +2646,7 @@ nv168_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
+	.gr = tu102_gr_new,
 	.nvdec[0] = gm107_nvdec_new,
 	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c
index 454668b1cf54..a9efa4d78be9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c
@@ -164,6 +164,32 @@ MODULE_FIRMWARE("nvidia/tu106/gr/sw_nonctx.bin");
 MODULE_FIRMWARE("nvidia/tu106/gr/sw_bundle_init.bin");
 MODULE_FIRMWARE("nvidia/tu106/gr/sw_method_init.bin");
 
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/tu117/gr/sw_method_init.bin");
+
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/tu116/gr/sw_method_init.bin");
+
 static const struct gf100_gr_fwif
 tu102_gr_fwif[] = {
 	{ 0, gm200_gr_load, &tu102_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr },
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c
index 7f4b89d82d32..d28d8f36ae24 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c
@@ -107,6 +107,12 @@ MODULE_FIRMWARE("nvidia/tu104/acr/ucode_unload.bin");
 MODULE_FIRMWARE("nvidia/tu106/acr/unload_bl.bin");
 MODULE_FIRMWARE("nvidia/tu106/acr/ucode_unload.bin");
 
+MODULE_FIRMWARE("nvidia/tu116/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/ucode_unload.bin");
+
+MODULE_FIRMWARE("nvidia/tu117/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/acr/ucode_unload.bin");
+
 static const struct nvkm_acr_hsf_fwif
 tu102_acr_unload_fwif[] = {
 	{  0, nvkm_acr_hsfw_load, &gp108_acr_unload_0 },
@@ -130,6 +136,8 @@ tu102_acr_asb_0 = {
 MODULE_FIRMWARE("nvidia/tu102/acr/ucode_asb.bin");
 MODULE_FIRMWARE("nvidia/tu104/acr/ucode_asb.bin");
 MODULE_FIRMWARE("nvidia/tu106/acr/ucode_asb.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/ucode_asb.bin");
+MODULE_FIRMWARE("nvidia/tu117/acr/ucode_asb.bin");
 
 static const struct nvkm_acr_hsf_fwif
 tu102_acr_asb_fwif[] = {
@@ -154,6 +162,12 @@ MODULE_FIRMWARE("nvidia/tu104/acr/ucode_ahesasc.bin");
 MODULE_FIRMWARE("nvidia/tu106/acr/bl.bin");
 MODULE_FIRMWARE("nvidia/tu106/acr/ucode_ahesasc.bin");
 
+MODULE_FIRMWARE("nvidia/tu116/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/tu116/acr/ucode_ahesasc.bin");
+
+MODULE_FIRMWARE("nvidia/tu117/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/tu117/acr/ucode_ahesasc.bin");
+
 static const struct nvkm_acr_hsf_fwif
 tu102_acr_ahesasc_fwif[] = {
 	{  0, nvkm_acr_hsfw_load, &tu102_acr_ahesasc_0 },
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
index 389bad312bf2..10ff5d053f7e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
@@ -51,3 +51,5 @@ MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin");
 MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin");
 MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin");
 MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin");
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index 8fd8726313ae..7914b1570841 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -280,12 +280,8 @@ static void panfrost_job_cleanup(struct kref *ref)
 	}
 
 	if (job->bos) {
-		struct panfrost_gem_object *bo;
-
-		for (i = 0; i < job->bo_count; i++) {
-			bo = to_panfrost_bo(job->bos[i]);
+		for (i = 0; i < job->bo_count; i++)
 			drm_gem_object_put_unlocked(job->bos[i]);
-		}
 
 		kvfree(job->bos);
 	}
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 23314f41717b..ed28aeba6d59 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -151,7 +151,12 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu)
 	as = mmu->as;
 	if (as >= 0) {
 		int en = atomic_inc_return(&mmu->as_count);
-		WARN_ON(en >= NUM_JOB_SLOTS);
+
+		/*
+		 * AS can be retained by active jobs or a perfcnt context,
+		 * hence the '+ 1' here.
+		 */
+		WARN_ON(en >= (NUM_JOB_SLOTS + 1));
 
 		list_move(&mmu->list, &pfdev->as_lru_list);
 		goto out;
@@ -596,33 +601,27 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
 		source_id = (fault_status >> 16);
 
 		/* Page fault only */
-		if ((status & mask) == BIT(i)) {
-			WARN_ON(exception_type < 0xC1 || exception_type > 0xC4);
-
+		ret = -1;
+		if ((status & mask) == BIT(i) && (exception_type & 0xF8) == 0xC0)
 			ret = panfrost_mmu_map_fault_addr(pfdev, i, addr);
-			if (!ret) {
-				mmu_write(pfdev, MMU_INT_CLEAR, BIT(i));
-				status &= ~mask;
-				continue;
-			}
-		}
 
-		/* terminal fault, print info about the fault */
-		dev_err(pfdev->dev,
-			"Unhandled Page fault in AS%d at VA 0x%016llX\n"
-			"Reason: %s\n"
-			"raw fault status: 0x%X\n"
-			"decoded fault status: %s\n"
-			"exception type 0x%X: %s\n"
-			"access type 0x%X: %s\n"
-			"source id 0x%X\n",
-			i, addr,
-			"TODO",
-			fault_status,
-			(fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"),
-			exception_type, panfrost_exception_name(pfdev, exception_type),
-			access_type, access_type_name(pfdev, fault_status),
-			source_id);
+		if (ret)
+			/* terminal fault, print info about the fault */
+			dev_err(pfdev->dev,
+				"Unhandled Page fault in AS%d at VA 0x%016llX\n"
+				"Reason: %s\n"
+				"raw fault status: 0x%X\n"
+				"decoded fault status: %s\n"
+				"exception type 0x%X: %s\n"
+				"access type 0x%X: %s\n"
+				"source id 0x%X\n",
+				i, addr,
+				"TODO",
+				fault_status,
+				(fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"),
+				exception_type, panfrost_exception_name(pfdev, exception_type),
+				access_type, access_type_name(pfdev, fault_status),
+				source_id);
 
 		mmu_write(pfdev, MMU_INT_CLEAR, mask);
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
index 684820448be3..6913578d5aa7 100644
--- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
+++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
@@ -73,7 +73,7 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev,
 	struct panfrost_file_priv *user = file_priv->driver_priv;
 	struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
 	struct drm_gem_shmem_object *bo;
-	u32 cfg;
+	u32 cfg, as;
 	int ret;
 
 	if (user == perfcnt->user)
@@ -126,12 +126,8 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev,
 
 	perfcnt->user = user;
 
-	/*
-	 * Always use address space 0 for now.
-	 * FIXME: this needs to be updated when we start using different
-	 * address space.
-	 */
-	cfg = GPU_PERFCNT_CFG_AS(0) |
+	as = panfrost_mmu_as_get(pfdev, perfcnt->mapping->mmu);
+	cfg = GPU_PERFCNT_CFG_AS(as) |
 	      GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_MANUAL);
 
 	/*
@@ -195,6 +191,7 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev,
 	drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, perfcnt->buf);
 	perfcnt->buf = NULL;
 	panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv);
+	panfrost_mmu_as_put(pfdev, perfcnt->mapping->mmu);
 	panfrost_gem_mapping_put(perfcnt->mapping);
 	perfcnt->mapping = NULL;
 	pm_runtime_mark_last_busy(pfdev->dev);
diff --git a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
index ceac7af9a172..29e367db6118 100644
--- a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
+++ b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
@@ -53,6 +53,7 @@ cmdline_test(drm_cmdline_test_rotate_0)
 cmdline_test(drm_cmdline_test_rotate_90)
 cmdline_test(drm_cmdline_test_rotate_180)
 cmdline_test(drm_cmdline_test_rotate_270)
+cmdline_test(drm_cmdline_test_rotate_multiple)
 cmdline_test(drm_cmdline_test_rotate_invalid_val)
 cmdline_test(drm_cmdline_test_rotate_truncated)
 cmdline_test(drm_cmdline_test_hmirror)
diff --git a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
index 520f3e66a384..d96cd890def6 100644
--- a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
+++ b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
@@ -856,6 +856,17 @@ static int drm_cmdline_test_rotate_270(void *ignored)
 	return 0;
 }
 
+static int drm_cmdline_test_rotate_multiple(void *ignored)
+{
+	struct drm_cmdline_mode mode = { };
+
+	FAIL_ON(drm_mode_parse_command_line_for_connector("720x480,rotate=0,rotate=90",
+							  &no_connector,
+							  &mode));
+
+	return 0;
+}
+
 static int drm_cmdline_test_rotate_invalid_val(void *ignored)
 {
 	struct drm_cmdline_mode mode = { };
@@ -888,7 +899,7 @@ static int drm_cmdline_test_hmirror(void *ignored)
 	FAIL_ON(!mode.specified);
 	FAIL_ON(mode.xres != 720);
 	FAIL_ON(mode.yres != 480);
-	FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_X);
+	FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_X));
 
 	FAIL_ON(mode.refresh_specified);
 
@@ -913,7 +924,7 @@ static int drm_cmdline_test_vmirror(void *ignored)
 	FAIL_ON(!mode.specified);
 	FAIL_ON(mode.xres != 720);
 	FAIL_ON(mode.yres != 480);
-	FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_Y);
+	FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_Y));
 
 	FAIL_ON(mode.refresh_specified);
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index 7c24f8f832a5..4a64f7ae437a 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -107,48 +107,128 @@ static const struct de2_fmt_info de2_formats[] = {
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XRGB4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_ABGR4444,
 		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR4444,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XBGR4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_RGBA4444,
 		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA4444,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_RGBX4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_BGRA4444,
 		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA4444,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_BGRX4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_ARGB1555,
 		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB1555,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XRGB1555,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB1555,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_ABGR1555,
 		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR1555,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XBGR1555,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR1555,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_RGBA5551,
 		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA5551,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_RGBX5551,
+		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA5551,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_BGRA5551,
 		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA5551,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_BGRX5551,
+		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA5551,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_ARGB2101010,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB2101010,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_ABGR2101010,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR2101010,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_RGBA1010102,
+		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA1010102,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_BGRA1010102,
+		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA1010102,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_UYVY,
 		.de2_fmt = SUN8I_MIXER_FBFMT_UYVY,
 		.rgb = false,
@@ -197,12 +277,6 @@ static const struct de2_fmt_info de2_formats[] = {
 		.csc = SUN8I_CSC_MODE_YUV2RGB,
 	},
 	{
-		.drm_fmt = DRM_FORMAT_YUV444,
-		.de2_fmt = SUN8I_MIXER_FBFMT_RGB888,
-		.rgb = true,
-		.csc = SUN8I_CSC_MODE_YUV2RGB,
-	},
-	{
 		.drm_fmt = DRM_FORMAT_YUV422,
 		.de2_fmt = SUN8I_MIXER_FBFMT_YUV422,
 		.rgb = false,
@@ -221,12 +295,6 @@ static const struct de2_fmt_info de2_formats[] = {
 		.csc = SUN8I_CSC_MODE_YUV2RGB,
 	},
 	{
-		.drm_fmt = DRM_FORMAT_YVU444,
-		.de2_fmt = SUN8I_MIXER_FBFMT_RGB888,
-		.rgb = true,
-		.csc = SUN8I_CSC_MODE_YVU2RGB,
-	},
-	{
 		.drm_fmt = DRM_FORMAT_YVU422,
 		.de2_fmt = SUN8I_MIXER_FBFMT_YUV422,
 		.rgb = false,
@@ -244,6 +312,18 @@ static const struct de2_fmt_info de2_formats[] = {
 		.rgb = false,
 		.csc = SUN8I_CSC_MODE_YVU2RGB,
 	},
+	{
+		.drm_fmt = DRM_FORMAT_P010,
+		.de2_fmt = SUN8I_MIXER_FBFMT_P010_YUV,
+		.rgb = false,
+		.csc = SUN8I_CSC_MODE_YUV2RGB,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_P210,
+		.de2_fmt = SUN8I_MIXER_FBFMT_P210_YUV,
+		.rgb = false,
+		.csc = SUN8I_CSC_MODE_YUV2RGB,
+	},
 };
 
 const struct de2_fmt_info *sun8i_mixer_format_info(u32 format)
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h
index c6cc94057faf..345b28b0a80a 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.h
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h
@@ -93,6 +93,10 @@
 #define SUN8I_MIXER_FBFMT_ABGR1555	17
 #define SUN8I_MIXER_FBFMT_RGBA5551	18
 #define SUN8I_MIXER_FBFMT_BGRA5551	19
+#define SUN8I_MIXER_FBFMT_ARGB2101010	20
+#define SUN8I_MIXER_FBFMT_ABGR2101010	21
+#define SUN8I_MIXER_FBFMT_RGBA1010102	22
+#define SUN8I_MIXER_FBFMT_BGRA1010102	23
 
 #define SUN8I_MIXER_FBFMT_YUYV		0
 #define SUN8I_MIXER_FBFMT_UYVY		1
@@ -109,6 +113,13 @@
 /* format 12 is semi-planar YUV411 UVUV */
 /* format 13 is semi-planar YUV411 VUVU */
 #define SUN8I_MIXER_FBFMT_YUV411	14
+/* format 15 doesn't exist */
+/* format 16 is P010 YVU */
+#define SUN8I_MIXER_FBFMT_P010_YUV	17
+/* format 18 is P210 YVU */
+#define SUN8I_MIXER_FBFMT_P210_YUV	19
+/* format 20 is packed YVU444 10-bit */
+/* format 21 is packed YUV444 10-bit */
 
 /*
  * Sub-engines listed bellow are unused for now. The EN registers are here only
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index 42d445d23773..b8398ca18b0f 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -398,24 +398,66 @@ static const struct drm_plane_funcs sun8i_vi_layer_funcs = {
 };
 
 /*
- * While all RGB formats are supported, VI planes don't support
- * alpha blending, so there is no point having formats with alpha
- * channel if their opaque analog exist.
+ * While DE2 VI layer supports same RGB formats as UI layer, alpha
+ * channel is ignored. This structure lists all unique variants
+ * where alpha channel is replaced with "don't care" (X) channel.
  */
 static const u32 sun8i_vi_layer_formats[] = {
+	DRM_FORMAT_BGR565,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_BGRX4444,
+	DRM_FORMAT_BGRX5551,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_RGBX4444,
+	DRM_FORMAT_RGBX5551,
+	DRM_FORMAT_RGBX8888,
+	DRM_FORMAT_XBGR1555,
+	DRM_FORMAT_XBGR4444,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_XRGB4444,
+	DRM_FORMAT_XRGB8888,
+
+	DRM_FORMAT_NV16,
+	DRM_FORMAT_NV12,
+	DRM_FORMAT_NV21,
+	DRM_FORMAT_NV61,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_VYUY,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_YUV411,
+	DRM_FORMAT_YUV420,
+	DRM_FORMAT_YUV422,
+	DRM_FORMAT_YVU411,
+	DRM_FORMAT_YVU420,
+	DRM_FORMAT_YVU422,
+};
+
+static const u32 sun8i_vi_layer_de3_formats[] = {
 	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_ABGR4444,
+	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_ARGB2101010,
 	DRM_FORMAT_ARGB4444,
+	DRM_FORMAT_ARGB8888,
 	DRM_FORMAT_BGR565,
 	DRM_FORMAT_BGR888,
+	DRM_FORMAT_BGRA1010102,
 	DRM_FORMAT_BGRA5551,
 	DRM_FORMAT_BGRA4444,
+	DRM_FORMAT_BGRA8888,
 	DRM_FORMAT_BGRX8888,
 	DRM_FORMAT_RGB565,
 	DRM_FORMAT_RGB888,
+	DRM_FORMAT_RGBA1010102,
 	DRM_FORMAT_RGBA4444,
 	DRM_FORMAT_RGBA5551,
+	DRM_FORMAT_RGBA8888,
 	DRM_FORMAT_RGBX8888,
 	DRM_FORMAT_XBGR8888,
 	DRM_FORMAT_XRGB8888,
@@ -424,6 +466,8 @@ static const u32 sun8i_vi_layer_formats[] = {
 	DRM_FORMAT_NV12,
 	DRM_FORMAT_NV21,
 	DRM_FORMAT_NV61,
+	DRM_FORMAT_P010,
+	DRM_FORMAT_P210,
 	DRM_FORMAT_UYVY,
 	DRM_FORMAT_VYUY,
 	DRM_FORMAT_YUYV,
@@ -431,11 +475,9 @@ static const u32 sun8i_vi_layer_formats[] = {
 	DRM_FORMAT_YUV411,
 	DRM_FORMAT_YUV420,
 	DRM_FORMAT_YUV422,
-	DRM_FORMAT_YUV444,
 	DRM_FORMAT_YVU411,
 	DRM_FORMAT_YVU420,
 	DRM_FORMAT_YVU422,
-	DRM_FORMAT_YVU444,
 };
 
 struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
@@ -443,19 +485,27 @@ struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
 					       int index)
 {
 	u32 supported_encodings, supported_ranges;
+	unsigned int plane_cnt, format_count;
 	struct sun8i_vi_layer *layer;
-	unsigned int plane_cnt;
+	const u32 *formats;
 	int ret;
 
 	layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL);
 	if (!layer)
 		return ERR_PTR(-ENOMEM);
 
+	if (mixer->cfg->is_de3) {
+		formats = sun8i_vi_layer_de3_formats;
+		format_count = ARRAY_SIZE(sun8i_vi_layer_de3_formats);
+	} else {
+		formats = sun8i_vi_layer_formats;
+		format_count = ARRAY_SIZE(sun8i_vi_layer_formats);
+	}
+
 	/* possible crtcs are set later */
 	ret = drm_universal_plane_init(drm, &layer->plane, 0,
 				       &sun8i_vi_layer_funcs,
-				       sun8i_vi_layer_formats,
-				       ARRAY_SIZE(sun8i_vi_layer_formats),
+				       formats, format_count,
 				       NULL, DRM_PLANE_TYPE_OVERLAY, NULL);
 	if (ret) {
 		dev_err(drm->dev, "Couldn't initialize layer\n");
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index f1f670642c97..52d2b71f1588 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -514,6 +514,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 		fbo->base.base.resv = &fbo->base.base._resv;
 
 	dma_resv_init(&fbo->base.base._resv);
+	fbo->base.base.dev = NULL;
 	ret = dma_resv_trylock(&fbo->base.base._resv);
 	WARN_ON(!ret);
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index c5cad949eb8d..d2c529a31939 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -43,8 +43,8 @@ static int virtio_gpu_resource_id_get(struct virtio_gpu_device *vgdev,
 		 * "f91a9dd35715 Fix unlinking resources from hash
 		 * table." (Feb 2019) fixes the bug.
 		 */
-		static int handle;
-		handle++;
+		static atomic_t seqno = ATOMIC_INIT(0);
+		int handle = atomic_inc_return(&seqno);
 		*resid = handle + 1;
 	} else {
 		int handle = ida_alloc(&vgdev->resource_ida, GFP_KERNEL);
@@ -124,6 +124,7 @@ struct drm_gem_object *virtio_gpu_create_object(struct drm_device *dev,
 		return NULL;
 
 	bo->base.base.funcs = &virtio_gpu_shmem_funcs;
+	bo->base.map_cached = true;
 	return &bo->base.base;
 }