Merge tag 'v4.2-rc4' into devel

Linux 4.2-rc4

45 files changed, 532 insertions, 232 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 01657830b470..e9fde72cf038 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1614,6 +1614,9 @@ struct amdgpu_uvd {
 #define AMDGPU_MAX_VCE_HANDLES	16
 #define AMDGPU_VCE_FIRMWARE_OFFSET 256
 
+#define AMDGPU_VCE_HARVEST_VCE0 (1 << 0)
+#define AMDGPU_VCE_HARVEST_VCE1 (1 << 1)
+
 struct amdgpu_vce {
 	struct amdgpu_bo	*vcpu_bo;
 	uint64_t		gpu_addr;
@@ -1626,6 +1629,7 @@ struct amdgpu_vce {
 	const struct firmware	*fw;	/* VCE firmware */
 	struct amdgpu_ring	ring[AMDGPU_MAX_VCE_RINGS];
 	struct amdgpu_irq_src	irq;
+	unsigned		harvest_config;
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d63135bf29c0..1f040d85ac47 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -669,6 +669,7 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 				  struct amdgpu_cs_parser *p)
 {
+	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_ib *ib;
 	int i, j, r;
 
@@ -694,6 +695,7 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 		for (j = 0; j < num_deps; ++j) {
 			struct amdgpu_fence *fence;
 			struct amdgpu_ring *ring;
+			struct amdgpu_ctx *ctx;
 
 			r = amdgpu_cs_get_ring(adev, deps[j].ip_type,
 					       deps[j].ip_instance,
@@ -701,14 +703,21 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 			if (r)
 				return r;
 
+			ctx = amdgpu_ctx_get(fpriv, deps[j].ctx_id);
+			if (ctx == NULL)
+				return -EINVAL;
+
 			r = amdgpu_fence_recreate(ring, p->filp,
 						  deps[j].handle,
 						  &fence);
-			if (r)
+			if (r) {
+				amdgpu_ctx_put(ctx);
 				return r;
+			}
 
 			amdgpu_sync_fence(&ib->sync, fence);
 			amdgpu_fence_unref(&fence);
+			amdgpu_ctx_put(ctx);
 		}
 	}
 
@@ -808,12 +817,16 @@ int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data,
 
 	r = amdgpu_cs_get_ring(adev, wait->in.ip_type, wait->in.ip_instance,
 			       wait->in.ring, &ring);
-	if (r)
+	if (r) {
+		amdgpu_ctx_put(ctx);
 		return r;
+	}
 
 	r = amdgpu_fence_recreate(ring, filp, wait->in.handle, &fence);
-	if (r)
+	if (r) {
+		amdgpu_ctx_put(ctx);
 		return r;
+	}
 
 	r = fence_wait_timeout(&fence->base, true, timeout);
 	amdgpu_fence_unref(&fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ba46be361c9b..d79009b65867 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1207,10 +1207,15 @@ static int amdgpu_early_init(struct amdgpu_device *adev)
 		} else {
 			if (adev->ip_blocks[i].funcs->early_init) {
 				r = adev->ip_blocks[i].funcs->early_init((void *)adev);
-				if (r)
+				if (r == -ENOENT)
+					adev->ip_block_enabled[i] = false;
+				else if (r)
 					return r;
+				else
+					adev->ip_block_enabled[i] = true;
+			} else {
+				adev->ip_block_enabled[i] = true;
 			}
-			adev->ip_block_enabled[i] = true;
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 5533434c7a8f..31ad444c6386 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -459,6 +459,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		memcpy(&dev_info.cu_bitmap[0], &cu_info.bitmap[0], sizeof(cu_info.bitmap));
 		dev_info.vram_type = adev->mc.vram_type;
 		dev_info.vram_bit_width = adev->mc.vram_width;
+		dev_info.vce_harvest_config = adev->vce.harvest_config;
 
 		return copy_to_user(out, &dev_info,
 				    min((size_t)size, sizeof(dev_info))) ? -EFAULT : 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index f75a31df30bd..ace870afc7d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -494,29 +494,67 @@ static void cz_dpm_fini(struct amdgpu_device *adev)
 	amdgpu_free_extended_power_table(adev);
 }
 
+#define ixSMUSVI_NB_CURRENTVID 0xD8230044
+#define CURRENT_NB_VID_MASK 0xff000000
+#define CURRENT_NB_VID__SHIFT 24
+#define ixSMUSVI_GFX_CURRENTVID  0xD8230048
+#define CURRENT_GFX_VID_MASK 0xff000000
+#define CURRENT_GFX_VID__SHIFT 24
+
 static void
 cz_dpm_debugfs_print_current_performance_level(struct amdgpu_device *adev,
 					       struct seq_file *m)
 {
+	struct cz_power_info *pi = cz_get_pi(adev);
 	struct amdgpu_clock_voltage_dependency_table *table =
 		&adev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
-	u32 current_index =
-		(RREG32_SMC(ixTARGET_AND_CURRENT_PROFILE_INDEX) &
-		TARGET_AND_CURRENT_PROFILE_INDEX__CURR_SCLK_INDEX_MASK) >>
-		TARGET_AND_CURRENT_PROFILE_INDEX__CURR_SCLK_INDEX__SHIFT;
-	u32 sclk, tmp;
-	u16 vddc;
-
-	if (current_index >= NUM_SCLK_LEVELS) {
-		seq_printf(m, "invalid dpm profile %d\n", current_index);
+	struct amdgpu_uvd_clock_voltage_dependency_table *uvd_table =
+		&adev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table;
+	struct amdgpu_vce_clock_voltage_dependency_table *vce_table =
+		&adev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table;
+	u32 sclk_index = REG_GET_FIELD(RREG32_SMC(ixTARGET_AND_CURRENT_PROFILE_INDEX),
+				       TARGET_AND_CURRENT_PROFILE_INDEX, CURR_SCLK_INDEX);
+	u32 uvd_index = REG_GET_FIELD(RREG32_SMC(ixTARGET_AND_CURRENT_PROFILE_INDEX_2),
+				      TARGET_AND_CURRENT_PROFILE_INDEX_2, CURR_UVD_INDEX);
+	u32 vce_index = REG_GET_FIELD(RREG32_SMC(ixTARGET_AND_CURRENT_PROFILE_INDEX_2),
+				      TARGET_AND_CURRENT_PROFILE_INDEX_2, CURR_VCE_INDEX);
+	u32 sclk, vclk, dclk, ecclk, tmp;
+	u16 vddnb, vddgfx;
+
+	if (sclk_index >= NUM_SCLK_LEVELS) {
+		seq_printf(m, "invalid sclk dpm profile %d\n", sclk_index);
 	} else {
-		sclk = table->entries[current_index].clk;
-		tmp = (RREG32_SMC(ixSMU_VOLTAGE_STATUS) &
-			SMU_VOLTAGE_STATUS__SMU_VOLTAGE_CURRENT_LEVEL_MASK) >>
-			SMU_VOLTAGE_STATUS__SMU_VOLTAGE_CURRENT_LEVEL__SHIFT;
-		vddc = cz_convert_8bit_index_to_voltage(adev, (u16)tmp);
-		seq_printf(m, "power level %d    sclk: %u vddc: %u\n",
-			   current_index, sclk, vddc);
+		sclk = table->entries[sclk_index].clk;
+		seq_printf(m, "%u sclk: %u\n", sclk_index, sclk);
+	}
+
+	tmp = (RREG32_SMC(ixSMUSVI_NB_CURRENTVID) &
+	       CURRENT_NB_VID_MASK) >> CURRENT_NB_VID__SHIFT;
+	vddnb = cz_convert_8bit_index_to_voltage(adev, (u16)tmp);
+	tmp = (RREG32_SMC(ixSMUSVI_GFX_CURRENTVID) &
+	       CURRENT_GFX_VID_MASK) >> CURRENT_GFX_VID__SHIFT;
+	vddgfx = cz_convert_8bit_index_to_voltage(adev, (u16)tmp);
+	seq_printf(m, "vddnb: %u vddgfx: %u\n", vddnb, vddgfx);
+
+	seq_printf(m, "uvd    %sabled\n", pi->uvd_power_gated ? "dis" : "en");
+	if (!pi->uvd_power_gated) {
+		if (uvd_index >= CZ_MAX_HARDWARE_POWERLEVELS) {
+			seq_printf(m, "invalid uvd dpm level %d\n", uvd_index);
+		} else {
+			vclk = uvd_table->entries[uvd_index].vclk;
+			dclk = uvd_table->entries[uvd_index].dclk;
+			seq_printf(m, "%u uvd vclk: %u dclk: %u\n", uvd_index, vclk, dclk);
+		}
+	}
+
+	seq_printf(m, "vce    %sabled\n", pi->vce_power_gated ? "dis" : "en");
+	if (!pi->vce_power_gated) {
+		if (vce_index >= CZ_MAX_HARDWARE_POWERLEVELS) {
+			seq_printf(m, "invalid vce dpm level %d\n", vce_index);
+		} else {
+			ecclk = vce_table->entries[vce_index].ecclk;
+			seq_printf(m, "%u vce ecclk: %u\n", vce_index, ecclk);
+		}
 	}
 }
 
@@ -1679,25 +1717,31 @@ static int cz_dpm_unforce_dpm_levels(struct amdgpu_device *adev)
 	if (ret)
 		return ret;
 
-	DRM_INFO("DPM unforce state min=%d, max=%d.\n",
-			pi->sclk_dpm.soft_min_clk,
-			pi->sclk_dpm.soft_max_clk);
+	DRM_DEBUG("DPM unforce state min=%d, max=%d.\n",
+		  pi->sclk_dpm.soft_min_clk,
+		  pi->sclk_dpm.soft_max_clk);
 
 	return 0;
 }
 
 static int cz_dpm_force_dpm_level(struct amdgpu_device *adev,
-				enum amdgpu_dpm_forced_level level)
+				  enum amdgpu_dpm_forced_level level)
 {
 	int ret = 0;
 
 	switch (level) {
 	case AMDGPU_DPM_FORCED_LEVEL_HIGH:
+		ret = cz_dpm_unforce_dpm_levels(adev);
+		if (ret)
+			return ret;
 		ret = cz_dpm_force_highest(adev);
 		if (ret)
 			return ret;
 		break;
 	case AMDGPU_DPM_FORCED_LEVEL_LOW:
+		ret = cz_dpm_unforce_dpm_levels(adev);
+		if (ret)
+			return ret;
 		ret = cz_dpm_force_lowest(adev);
 		if (ret)
 			return ret;
@@ -1711,6 +1755,8 @@ static int cz_dpm_force_dpm_level(struct amdgpu_device *adev,
 		break;
 	}
 
+	adev->pm.dpm.forced_level = level;
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 6e77964f1b64..e70a26f587a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2632,6 +2632,7 @@ static void dce_v10_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+	unsigned type;
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
@@ -2640,6 +2641,9 @@ static void dce_v10_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 		dce_v10_0_vga_enable(crtc, true);
 		amdgpu_atombios_crtc_blank(crtc, ATOM_DISABLE);
 		dce_v10_0_vga_enable(crtc, false);
+		/* Make sure VBLANK interrupt is still enabled */
+		type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id);
+		amdgpu_irq_update(adev, &adev->crtc_irq, type);
 		drm_vblank_post_modeset(dev, amdgpu_crtc->crtc_id);
 		dce_v10_0_crtc_load_lut(crtc);
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 7f7abb0e0be5..dcb402ee048a 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -2631,6 +2631,7 @@ static void dce_v11_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+	unsigned type;
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
@@ -2639,6 +2640,9 @@ static void dce_v11_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 		dce_v11_0_vga_enable(crtc, true);
 		amdgpu_atombios_crtc_blank(crtc, ATOM_DISABLE);
 		dce_v11_0_vga_enable(crtc, false);
+		/* Make sure VBLANK interrupt is still enabled */
+		type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id);
+		amdgpu_irq_update(adev, &adev->crtc_irq, type);
 		drm_vblank_post_modeset(dev, amdgpu_crtc->crtc_id);
 		dce_v11_0_crtc_load_lut(crtc);
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 08387dfd98a7..cc050a329c49 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2566,6 +2566,7 @@ static void dce_v8_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+	unsigned type;
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
@@ -2574,6 +2575,9 @@ static void dce_v8_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 		dce_v8_0_vga_enable(crtc, true);
 		amdgpu_atombios_crtc_blank(crtc, ATOM_DISABLE);
 		dce_v8_0_vga_enable(crtc, false);
+		/* Make sure VBLANK interrupt is still enabled */
+		type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id);
+		amdgpu_irq_update(adev, &adev->crtc_irq, type);
 		drm_vblank_post_modeset(dev, amdgpu_crtc->crtc_id);
 		dce_v8_0_crtc_load_lut(crtc);
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 7b683fb2173c..1c7c992dea37 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1813,10 +1813,7 @@ static u32 gfx_v8_0_get_rb_disabled(struct amdgpu_device *adev,
 	u32 data, mask;
 
 	data = RREG32(mmCC_RB_BACKEND_DISABLE);
-	if (data & 1)
-		data &= CC_RB_BACKEND_DISABLE__BACKEND_DISABLE_MASK;
-	else
-		data = 0;
+	data &= CC_RB_BACKEND_DISABLE__BACKEND_DISABLE_MASK;
 
 	data |= RREG32(mmGC_USER_RB_BACKEND_DISABLE);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index d62c4002e39c..d1064ca3670e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -35,6 +35,8 @@
 #include "oss/oss_2_0_d.h"
 #include "oss/oss_2_0_sh_mask.h"
 #include "gca/gfx_8_0_d.h"
+#include "smu/smu_7_1_2_d.h"
+#include "smu/smu_7_1_2_sh_mask.h"
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK	0x10
@@ -112,6 +114,10 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (idx = 0; idx < 2; ++idx) {
+
+		if (adev->vce.harvest_config & (1 << idx))
+			continue;
+
 		if(idx == 0)
 			WREG32_P(mmGRBM_GFX_INDEX, 0,
 				~GRBM_GFX_INDEX__VCE_INSTANCE_MASK);
@@ -190,10 +196,52 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 	return 0;
 }
 
+#define ixVCE_HARVEST_FUSE_MACRO__ADDRESS     0xC0014074
+#define VCE_HARVEST_FUSE_MACRO__SHIFT       27
+#define VCE_HARVEST_FUSE_MACRO__MASK        0x18000000
+
+static unsigned vce_v3_0_get_harvest_config(struct amdgpu_device *adev)
+{
+	u32 tmp;
+	unsigned ret;
+
+	if (adev->flags & AMDGPU_IS_APU)
+		tmp = (RREG32_SMC(ixVCE_HARVEST_FUSE_MACRO__ADDRESS) &
+		       VCE_HARVEST_FUSE_MACRO__MASK) >>
+			VCE_HARVEST_FUSE_MACRO__SHIFT;
+	else
+		tmp = (RREG32_SMC(ixCC_HARVEST_FUSES) &
+		       CC_HARVEST_FUSES__VCE_DISABLE_MASK) >>
+			CC_HARVEST_FUSES__VCE_DISABLE__SHIFT;
+
+	switch (tmp) {
+	case 1:
+		ret = AMDGPU_VCE_HARVEST_VCE0;
+		break;
+	case 2:
+		ret = AMDGPU_VCE_HARVEST_VCE1;
+		break;
+	case 3:
+		ret = AMDGPU_VCE_HARVEST_VCE0 | AMDGPU_VCE_HARVEST_VCE1;
+		break;
+	default:
+		ret = 0;
+	}
+
+	return ret;
+}
+
 static int vce_v3_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	adev->vce.harvest_config = vce_v3_0_get_harvest_config(adev);
+
+	if ((adev->vce.harvest_config &
+	     (AMDGPU_VCE_HARVEST_VCE0 | AMDGPU_VCE_HARVEST_VCE1)) ==
+	    (AMDGPU_VCE_HARVEST_VCE0 | AMDGPU_VCE_HARVEST_VCE1))
+		return -ENOENT;
+
 	vce_v3_0_set_ring_funcs(adev);
 	vce_v3_0_set_irq_funcs(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index fa5a4448531d..68552da40287 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -122,6 +122,32 @@ static void vi_smc_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 	spin_unlock_irqrestore(&adev->smc_idx_lock, flags);
 }
 
+/* smu_8_0_d.h */
+#define mmMP0PUB_IND_INDEX                                                      0x180
+#define mmMP0PUB_IND_DATA                                                       0x181
+
+static u32 cz_smc_rreg(struct amdgpu_device *adev, u32 reg)
+{
+	unsigned long flags;
+	u32 r;
+
+	spin_lock_irqsave(&adev->smc_idx_lock, flags);
+	WREG32(mmMP0PUB_IND_INDEX, (reg));
+	r = RREG32(mmMP0PUB_IND_DATA);
+	spin_unlock_irqrestore(&adev->smc_idx_lock, flags);
+	return r;
+}
+
+static void cz_smc_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&adev->smc_idx_lock, flags);
+	WREG32(mmMP0PUB_IND_INDEX, (reg));
+	WREG32(mmMP0PUB_IND_DATA, (v));
+	spin_unlock_irqrestore(&adev->smc_idx_lock, flags);
+}
+
 static u32 vi_uvd_ctx_rreg(struct amdgpu_device *adev, u32 reg)
 {
 	unsigned long flags;
@@ -1222,8 +1248,13 @@ static int vi_common_early_init(void *handle)
 	bool smc_enabled = false;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	adev->smc_rreg = &vi_smc_rreg;
-	adev->smc_wreg = &vi_smc_wreg;
+	if (adev->flags & AMDGPU_IS_APU) {
+		adev->smc_rreg = &cz_smc_rreg;
+		adev->smc_wreg = &cz_smc_wreg;
+	} else {
+		adev->smc_rreg = &vi_smc_rreg;
+		adev->smc_wreg = &vi_smc_wreg;
+	}
 	adev->pcie_rreg = &vi_pcie_rreg;
 	adev->pcie_wreg = &vi_pcie_wreg;
 	adev->uvd_ctx_rreg = &vi_uvd_ctx_rreg;
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 42d2ffa08716..01ffe9bffe38 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -531,8 +531,6 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 
 	drm_crtc_vblank_off(crtc);
 
-	crtc->mode = *adj;
-
 	val = dcrtc->dumb_ctrl & ~CFG_DUMB_ENA;
 	if (val != dcrtc->dumb_ctrl) {
 		dcrtc->dumb_ctrl = val;
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index 580e10acaa3a..60a688ef81c7 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -69,8 +69,9 @@ void armada_gem_free_object(struct drm_gem_object *obj)
 
 	if (dobj->obj.import_attach) {
 		/* We only ever display imported data */
-		dma_buf_unmap_attachment(dobj->obj.import_attach, dobj->sgt,
-					 DMA_TO_DEVICE);
+		if (dobj->sgt)
+			dma_buf_unmap_attachment(dobj->obj.import_attach,
+						 dobj->sgt, DMA_TO_DEVICE);
 		drm_prime_gem_destroy(&dobj->obj, NULL);
 	}
 
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index c5b06fdb459c..e939faba7fcc 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -7,6 +7,7 @@
  * published by the Free Software Foundation.
  */
 #include <drm/drmP.h>
+#include <drm/drm_plane_helper.h>
 #include "armada_crtc.h"
 #include "armada_drm.h"
 #include "armada_fb.h"
@@ -85,16 +86,8 @@ static void armada_plane_vbl(struct armada_crtc *dcrtc, void *data)
 
 	if (fb)
 		armada_drm_queue_unref_work(dcrtc->crtc.dev, fb);
-}
 
-static unsigned armada_limit(int start, unsigned size, unsigned max)
-{
-	int end = start + size;
-	if (end < 0)
-		return 0;
-	if (start < 0)
-		start = 0;
-	return (unsigned)end > max ? max - start : end - start;
+	wake_up(&dplane->vbl.wait);
 }
 
 static int
@@ -105,26 +98,39 @@ armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 {
 	struct armada_plane *dplane = drm_to_armada_plane(plane);
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct drm_rect src = {
+		.x1 = src_x,
+		.y1 = src_y,
+		.x2 = src_x + src_w,
+		.y2 = src_y + src_h,
+	};
+	struct drm_rect dest = {
+		.x1 = crtc_x,
+		.y1 = crtc_y,
+		.x2 = crtc_x + crtc_w,
+		.y2 = crtc_y + crtc_h,
+	};
+	const struct drm_rect clip = {
+		.x2 = crtc->mode.hdisplay,
+		.y2 = crtc->mode.vdisplay,
+	};
 	uint32_t val, ctrl0;
 	unsigned idx = 0;
+	bool visible;
 	int ret;
 
-	crtc_w = armada_limit(crtc_x, crtc_w, dcrtc->crtc.mode.hdisplay);
-	crtc_h = armada_limit(crtc_y, crtc_h, dcrtc->crtc.mode.vdisplay);
+	ret = drm_plane_helper_check_update(plane, crtc, fb, &src, &dest, &clip,
+					    0, INT_MAX, true, false, &visible);
+	if (ret)
+		return ret;
+
 	ctrl0 = CFG_DMA_FMT(drm_fb_to_armada_fb(fb)->fmt) |
 		CFG_DMA_MOD(drm_fb_to_armada_fb(fb)->mod) |
 		CFG_CBSH_ENA | CFG_DMA_HSMOOTH | CFG_DMA_ENA;
 
 	/* Does the position/size result in nothing to display? */
-	if (crtc_w == 0 || crtc_h == 0) {
+	if (!visible)
 		ctrl0 &= ~CFG_DMA_ENA;
-	}
-
-	/*
-	 * FIXME: if the starting point is off screen, we need to
-	 * adjust src_x, src_y, src_w, src_h appropriately, and
-	 * according to the scale.
-	 */
 
 	if (!dcrtc->plane) {
 		dcrtc->plane = plane;
@@ -134,15 +140,19 @@ armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	/* FIXME: overlay on an interlaced display */
 	/* Just updating the position/size? */
 	if (plane->fb == fb && dplane->ctrl0 == ctrl0) {
-		val = (src_h & 0xffff0000) | src_w >> 16;
+		val = (drm_rect_height(&src) & 0xffff0000) |
+		      drm_rect_width(&src) >> 16;
 		dplane->src_hw = val;
 		writel_relaxed(val, dcrtc->base + LCD_SPU_DMA_HPXL_VLN);
-		val = crtc_h << 16 | crtc_w;
+
+		val = drm_rect_height(&dest) << 16 | drm_rect_width(&dest);
 		dplane->dst_hw = val;
 		writel_relaxed(val, dcrtc->base + LCD_SPU_DZM_HPXL_VLN);
-		val = crtc_y << 16 | crtc_x;
+
+		val = dest.y1 << 16 | dest.x1;
 		dplane->dst_yx = val;
 		writel_relaxed(val, dcrtc->base + LCD_SPU_DMA_OVSA_HPXL_VLN);
+
 		return 0;
 	} else if (~dplane->ctrl0 & ctrl0 & CFG_DMA_ENA) {
 		/* Power up the Y/U/V FIFOs on ENA 0->1 transitions */
@@ -150,15 +160,14 @@ armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 			       dcrtc->base + LCD_SPU_SRAM_PARA1);
 	}
 
-	ret = wait_event_timeout(dplane->vbl.wait,
-				 list_empty(&dplane->vbl.update.node),
-				 HZ/25);
-	if (ret < 0)
-		return ret;
+	wait_event_timeout(dplane->vbl.wait,
+			   list_empty(&dplane->vbl.update.node),
+			   HZ/25);
 
 	if (plane->fb != fb) {
 		struct armada_gem_object *obj = drm_fb_obj(fb);
-		uint32_t sy, su, sv;
+		uint32_t addr[3], pixel_format;
+		int i, num_planes, hsub;
 
 		/*
 		 * Take a reference on the new framebuffer - we want to
@@ -178,26 +187,39 @@ armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 							    older_fb);
 		}
 
-		src_y >>= 16;
-		src_x >>= 16;
-		sy = obj->dev_addr + fb->offsets[0] + src_y * fb->pitches[0] +
-			src_x * fb->bits_per_pixel / 8;
-		su = obj->dev_addr + fb->offsets[1] + src_y * fb->pitches[1] +
-			src_x;
-		sv = obj->dev_addr + fb->offsets[2] + src_y * fb->pitches[2] +
-			src_x;
+		src_y = src.y1 >> 16;
+		src_x = src.x1 >> 16;
 
-		armada_reg_queue_set(dplane->vbl.regs, idx, sy,
+		pixel_format = fb->pixel_format;
+		hsub = drm_format_horz_chroma_subsampling(pixel_format);
+		num_planes = drm_format_num_planes(pixel_format);
+
+		/*
+		 * Annoyingly, shifting a YUYV-format image by one pixel
+		 * causes the U/V planes to toggle.  Toggle the UV swap.
+		 * (Unfortunately, this causes momentary colour flickering.)
+		 */
+		if (src_x & (hsub - 1) && num_planes == 1)
+			ctrl0 ^= CFG_DMA_MOD(CFG_SWAPUV);
+
+		for (i = 0; i < num_planes; i++)
+			addr[i] = obj->dev_addr + fb->offsets[i] +
+				  src_y * fb->pitches[i] +
+				  src_x * drm_format_plane_cpp(pixel_format, i);
+		for (; i < ARRAY_SIZE(addr); i++)
+			addr[i] = 0;
+
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[0],
 				     LCD_SPU_DMA_START_ADDR_Y0);
-		armada_reg_queue_set(dplane->vbl.regs, idx, su,
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[1],
 				     LCD_SPU_DMA_START_ADDR_U0);
-		armada_reg_queue_set(dplane->vbl.regs, idx, sv,
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[2],
 				     LCD_SPU_DMA_START_ADDR_V0);
-		armada_reg_queue_set(dplane->vbl.regs, idx, sy,
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[0],
 				     LCD_SPU_DMA_START_ADDR_Y1);
-		armada_reg_queue_set(dplane->vbl.regs, idx, su,
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[1],
 				     LCD_SPU_DMA_START_ADDR_U1);
-		armada_reg_queue_set(dplane->vbl.regs, idx, sv,
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[2],
 				     LCD_SPU_DMA_START_ADDR_V1);
 
 		val = fb->pitches[0] << 16 | fb->pitches[0];
@@ -208,24 +230,27 @@ armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 				     LCD_SPU_DMA_PITCH_UV);
 	}
 
-	val = (src_h & 0xffff0000) | src_w >> 16;
+	val = (drm_rect_height(&src) & 0xffff0000) | drm_rect_width(&src) >> 16;
 	if (dplane->src_hw != val) {
 		dplane->src_hw = val;
 		armada_reg_queue_set(dplane->vbl.regs, idx, val,
 				     LCD_SPU_DMA_HPXL_VLN);
 	}
-	val = crtc_h << 16 | crtc_w;
+
+	val = drm_rect_height(&dest) << 16 | drm_rect_width(&dest);
 	if (dplane->dst_hw != val) {
 		dplane->dst_hw = val;
 		armada_reg_queue_set(dplane->vbl.regs, idx, val,
 				     LCD_SPU_DZM_HPXL_VLN);
 	}
-	val = crtc_y << 16 | crtc_x;
+
+	val = dest.y1 << 16 | dest.x1;
 	if (dplane->dst_yx != val) {
 		dplane->dst_yx = val;
 		armada_reg_queue_set(dplane->vbl.regs, idx, val,
 				     LCD_SPU_DMA_OVSA_HPXL_VLN);
 	}
+
 	if (dplane->ctrl0 != ctrl0) {
 		dplane->ctrl0 = ctrl0;
 		armada_reg_queue_mod(dplane->vbl.regs, idx, ctrl0,
@@ -279,7 +304,11 @@ static int armada_plane_disable(struct drm_plane *plane)
 
 static void armada_plane_destroy(struct drm_plane *plane)
 {
-	kfree(plane);
+	struct armada_plane *dplane = drm_to_armada_plane(plane);
+
+	drm_plane_cleanup(plane);
+
+	kfree(dplane);
 }
 
 static int armada_plane_set_property(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index f69b92535505..5ae5c6923128 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -355,6 +355,7 @@ int atmel_hlcdc_crtc_create(struct drm_device *dev)
 		planes->overlays[i]->base.possible_crtcs = 1 << crtc->id;
 
 	drm_crtc_helper_add(&crtc->base, &lcdc_crtc_helper_funcs);
+	drm_crtc_vblank_reset(&crtc->base);
 
 	dc->crtc = &crtc->base;
 
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
index 60b0c13d7ff5..6fad1f9648f3 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
@@ -313,20 +313,20 @@ static int atmel_hlcdc_dc_load(struct drm_device *dev)
 
 	pm_runtime_enable(dev->dev);
 
-	ret = atmel_hlcdc_dc_modeset_init(dev);
+	ret = drm_vblank_init(dev, 1);
 	if (ret < 0) {
-		dev_err(dev->dev, "failed to initialize mode setting\n");
+		dev_err(dev->dev, "failed to initialize vblank\n");
 		goto err_periph_clk_disable;
 	}
 
-	drm_mode_config_reset(dev);
-
-	ret = drm_vblank_init(dev, 1);
+	ret = atmel_hlcdc_dc_modeset_init(dev);
 	if (ret < 0) {
-		dev_err(dev->dev, "failed to initialize vblank\n");
+		dev_err(dev->dev, "failed to initialize mode setting\n");
 		goto err_periph_clk_disable;
 	}
 
+	drm_mode_config_reset(dev);
+
 	pm_runtime_get_sync(dev->dev);
 	ret = drm_irq_install(dev, dc->hlcdc->irq);
 	pm_runtime_put_sync(dev->dev);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index b9ba06176eb1..fed748311b92 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -2706,8 +2706,11 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
 
-	/* For some reason crtc x/y offsets are signed internally. */
-	if (crtc_req->x > INT_MAX || crtc_req->y > INT_MAX)
+	/*
+	 * Universal plane src offsets are only 16.16, prevent havoc for
+	 * drivers using universal plane code internally.
+	 */
+	if (crtc_req->x & 0xffff0000 || crtc_req->y & 0xffff0000)
 		return -ERANGE;
 
 	drm_modeset_lock_all(dev);
@@ -5395,12 +5398,9 @@ void drm_mode_config_reset(struct drm_device *dev)
 		if (encoder->funcs->reset)
 			encoder->funcs->reset(encoder);
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		connector->status = connector_status_unknown;
-
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
 		if (connector->funcs->reset)
 			connector->funcs->reset(connector);
-	}
 }
 EXPORT_SYMBOL(drm_mode_config_reset);
 
diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c
index aa8bbb460c57..9cfcd0aef0df 100644
--- a/drivers/gpu/drm/drm_ioc32.c
+++ b/drivers/gpu/drm/drm_ioc32.c
@@ -70,6 +70,8 @@
 
 #define DRM_IOCTL_WAIT_VBLANK32		DRM_IOWR(0x3a, drm_wait_vblank32_t)
 
+#define DRM_IOCTL_MODE_ADDFB232		DRM_IOWR(0xb8, drm_mode_fb_cmd232_t)
+
 typedef struct drm_version_32 {
 	int version_major;	  /**< Major version */
 	int version_minor;	  /**< Minor version */
@@ -1016,6 +1018,63 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd,
 	return 0;
 }
 
+typedef struct drm_mode_fb_cmd232 {
+	u32 fb_id;
+	u32 width;
+	u32 height;
+	u32 pixel_format;
+	u32 flags;
+	u32 handles[4];
+	u32 pitches[4];
+	u32 offsets[4];
+	u64 modifier[4];
+} __attribute__((packed)) drm_mode_fb_cmd232_t;
+
+static int compat_drm_mode_addfb2(struct file *file, unsigned int cmd,
+				  unsigned long arg)
+{
+	struct drm_mode_fb_cmd232 __user *argp = (void __user *)arg;
+	struct drm_mode_fb_cmd232 req32;
+	struct drm_mode_fb_cmd2 __user *req64;
+	int i;
+	int err;
+
+	if (copy_from_user(&req32, argp, sizeof(req32)))
+		return -EFAULT;
+
+	req64 = compat_alloc_user_space(sizeof(*req64));
+
+	if (!access_ok(VERIFY_WRITE, req64, sizeof(*req64))
+	    || __put_user(req32.width, &req64->width)
+	    || __put_user(req32.height, &req64->height)
+	    || __put_user(req32.pixel_format, &req64->pixel_format)
+	    || __put_user(req32.flags, &req64->flags))
+		return -EFAULT;
+
+	for (i = 0; i < 4; i++) {
+		if (__put_user(req32.handles[i], &req64->handles[i]))
+			return -EFAULT;
+		if (__put_user(req32.pitches[i], &req64->pitches[i]))
+			return -EFAULT;
+		if (__put_user(req32.offsets[i], &req64->offsets[i]))
+			return -EFAULT;
+		if (__put_user(req32.modifier[i], &req64->modifier[i]))
+			return -EFAULT;
+	}
+
+	err = drm_ioctl(file, DRM_IOCTL_MODE_ADDFB2, (unsigned long)req64);
+	if (err)
+		return err;
+
+	if (__get_user(req32.fb_id, &req64->fb_id))
+		return -EFAULT;
+
+	if (copy_to_user(argp, &req32, sizeof(req32)))
+		return -EFAULT;
+
+	return 0;
+}
+
 static drm_ioctl_compat_t *drm_compat_ioctls[] = {
 	[DRM_IOCTL_NR(DRM_IOCTL_VERSION32)] = compat_drm_version,
 	[DRM_IOCTL_NR(DRM_IOCTL_GET_UNIQUE32)] = compat_drm_getunique,
@@ -1048,6 +1107,7 @@ static drm_ioctl_compat_t *drm_compat_ioctls[] = {
 	[DRM_IOCTL_NR(DRM_IOCTL_UPDATE_DRAW32)] = compat_drm_update_draw,
 #endif
 	[DRM_IOCTL_NR(DRM_IOCTL_WAIT_VBLANK32)] = compat_drm_wait_vblank,
+	[DRM_IOCTL_NR(DRM_IOCTL_MODE_ADDFB232)] = compat_drm_mode_addfb2,
 };
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 542fac628b28..5f27290201e0 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -826,6 +826,7 @@ struct intel_context {
 	struct kref ref;
 	int user_handle;
 	uint8_t remap_slice;
+	struct drm_i915_private *i915;
 	struct drm_i915_file_private *file_priv;
 	struct i915_ctx_hang_stats hang_stats;
 	struct i915_hw_ppgtt *ppgtt;
@@ -2036,8 +2037,6 @@ struct drm_i915_gem_object {
 	unsigned int cache_level:3;
 	unsigned int cache_dirty:1;
 
-	unsigned int has_dma_mapping:1;
-
 	unsigned int frontbuffer_bits:INTEL_FRONTBUFFER_BITS;
 
 	unsigned int pin_display;
@@ -3116,7 +3115,8 @@ void i915_debugfs_cleanup(struct drm_minor *minor);
 int i915_debugfs_connector_add(struct drm_connector *connector);
 void intel_display_crc_init(struct drm_device *dev);
 #else
-static inline int i915_debugfs_connector_add(struct drm_connector *connector) {}
+static inline int i915_debugfs_connector_add(struct drm_connector *connector)
+{ return 0; }
 static inline void intel_display_crc_init(struct drm_device *dev) {}
 #endif
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 248fd1ac7b3a..52b446b27b4d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -213,7 +213,6 @@ i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 	sg_dma_len(sg) = obj->base.size;
 
 	obj->pages = st;
-	obj->has_dma_mapping = true;
 	return 0;
 }
 
@@ -265,8 +264,6 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj)
 
 	sg_free_table(obj->pages);
 	kfree(obj->pages);
-
-	obj->has_dma_mapping = false;
 }
 
 static void
@@ -2139,6 +2136,8 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj)
 		obj->base.read_domains = obj->base.write_domain = I915_GEM_DOMAIN_CPU;
 	}
 
+	i915_gem_gtt_finish_object(obj);
+
 	if (i915_gem_object_needs_bit17_swizzle(obj))
 		i915_gem_object_save_bit_17_swizzle(obj);
 
@@ -2199,6 +2198,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	struct sg_page_iter sg_iter;
 	struct page *page;
 	unsigned long last_pfn = 0;	/* suppress gcc warning */
+	int ret;
 	gfp_t gfp;
 
 	/* Assert that the object is not currently in any GPU domain. As it
@@ -2246,8 +2246,10 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 			 */
 			i915_gem_shrink_all(dev_priv);
 			page = shmem_read_mapping_page(mapping, i);
-			if (IS_ERR(page))
+			if (IS_ERR(page)) {
+				ret = PTR_ERR(page);
 				goto err_pages;
+			}
 		}
 #ifdef CONFIG_SWIOTLB
 		if (swiotlb_nr_tbl()) {
@@ -2276,6 +2278,10 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 		sg_mark_end(sg);
 	obj->pages = st;
 
+	ret = i915_gem_gtt_prepare_object(obj);
+	if (ret)
+		goto err_pages;
+
 	if (i915_gem_object_needs_bit17_swizzle(obj))
 		i915_gem_object_do_bit_17_swizzle(obj);
 
@@ -2300,10 +2306,10 @@ err_pages:
 	 * space and so want to translate the error from shmemfs back to our
 	 * usual understanding of ENOMEM.
 	 */
-	if (PTR_ERR(page) == -ENOSPC)
-		return -ENOMEM;
-	else
-		return PTR_ERR(page);
+	if (ret == -ENOSPC)
+		ret = -ENOMEM;
+
+	return ret;
 }
 
 /* Ensure that the associated pages are gathered from the backing storage
@@ -2542,6 +2548,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	}
 
 	request->emitted_jiffies = jiffies;
+	ring->last_submitted_seqno = request->seqno;
 	list_add_tail(&request->list, &ring->request_list);
 	request->file_priv = NULL;
 
@@ -3247,10 +3254,8 @@ int i915_vma_unbind(struct i915_vma *vma)
 
 	/* Since the unbound list is global, only move to that list if
 	 * no more VMAs exist. */
-	if (list_empty(&obj->vma_list)) {
-		i915_gem_gtt_finish_object(obj);
+	if (list_empty(&obj->vma_list))
 		list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
-	}
 
 	/* And finally now the object is completely decoupled from this vma,
 	 * we can drop its hold on the backing storage and allow it to be
@@ -3768,22 +3773,16 @@ search_free:
 		goto err_remove_node;
 	}
 
-	ret = i915_gem_gtt_prepare_object(obj);
-	if (ret)
-		goto err_remove_node;
-
 	trace_i915_vma_bind(vma, flags);
 	ret = i915_vma_bind(vma, obj->cache_level, flags);
 	if (ret)
-		goto err_finish_gtt;
+		goto err_remove_node;
 
 	list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
 	list_add_tail(&vma->mm_list, &vm->inactive_list);
 
 	return vma;
 
-err_finish_gtt:
-	i915_gem_gtt_finish_object(obj);
 err_remove_node:
 	drm_mm_remove_node(&vma->node);
 err_free_vma:
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index d65cbe6afb92..48afa777e94a 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -135,8 +135,7 @@ static int get_context_size(struct drm_device *dev)
 
 void i915_gem_context_free(struct kref *ctx_ref)
 {
-	struct intel_context *ctx = container_of(ctx_ref,
-						 typeof(*ctx), ref);
+	struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref);
 
 	trace_i915_context_free(ctx);
 
@@ -195,6 +194,7 @@ __create_hw_context(struct drm_device *dev,
 
 	kref_init(&ctx->ref);
 	list_add_tail(&ctx->link, &dev_priv->context_list);
+	ctx->i915 = dev_priv;
 
 	if (dev_priv->hw_context_size) {
 		struct drm_i915_gem_object *obj =
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 7998da27c500..e9c2bfd85b52 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -256,7 +256,6 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
 		return PTR_ERR(sg);
 
 	obj->pages = sg;
-	obj->has_dma_mapping = true;
 	return 0;
 }
 
@@ -264,7 +263,6 @@ static void i915_gem_object_put_pages_dmabuf(struct drm_i915_gem_object *obj)
 {
 	dma_buf_unmap_attachment(obj->base.import_attach,
 				 obj->pages, DMA_BIDIRECTIONAL);
-	obj->has_dma_mapping = false;
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_dmabuf_ops = {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index dcc6a88c560e..56b52a4767d4 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1723,9 +1723,6 @@ void i915_gem_suspend_gtt_mappings(struct drm_device *dev)
 
 int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
 {
-	if (obj->has_dma_mapping)
-		return 0;
-
 	if (!dma_map_sg(&obj->base.dev->pdev->dev,
 			obj->pages->sgl, obj->pages->nents,
 			PCI_DMA_BIDIRECTIONAL))
@@ -1972,10 +1969,8 @@ void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj)
 
 	interruptible = do_idling(dev_priv);
 
-	if (!obj->has_dma_mapping)
-		dma_unmap_sg(&dev->pdev->dev,
-			     obj->pages->sgl, obj->pages->nents,
-			     PCI_DMA_BIDIRECTIONAL);
+	dma_unmap_sg(&dev->pdev->dev, obj->pages->sgl, obj->pages->nents,
+		     PCI_DMA_BIDIRECTIONAL);
 
 	undo_idling(dev_priv, interruptible);
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 348ed5abcdbf..8b5b784c62fe 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -416,7 +416,6 @@ _i915_gem_object_create_stolen(struct drm_device *dev,
 	if (obj->pages == NULL)
 		goto cleanup;
 
-	obj->has_dma_mapping = true;
 	i915_gem_object_pin_pages(obj);
 	obj->stolen = stolen;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index d61e74a08f82..633bd1fcab69 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -183,18 +183,8 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
 		if (IS_GEN4(dev)) {
 			uint32_t ddc2 = I915_READ(DCC2);
 
-			if (!(ddc2 & DCC2_MODIFIED_ENHANCED_DISABLE)) {
-				/* Since the swizzling may vary within an
-				 * object, we have no idea what the swizzling
-				 * is for any page in particular. Thus we
-				 * cannot migrate tiled pages using the GPU,
-				 * nor can we tell userspace what the exact
-				 * swizzling is for any object.
-				 */
+			if (!(ddc2 & DCC2_MODIFIED_ENHANCED_DISABLE))
 				dev_priv->quirks |= QUIRK_PIN_SWIZZLED_PAGES;
-				swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
-				swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
-			}
 		}
 
 		if (dcc == 0xffffffff) {
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 1f4e5a32a16e..8fd431bcdfd3 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -545,6 +545,26 @@ err:
 	return ret;
 }
 
+static int
+__i915_gem_userptr_set_pages(struct drm_i915_gem_object *obj,
+			     struct page **pvec, int num_pages)
+{
+	int ret;
+
+	ret = st_set_pages(&obj->pages, pvec, num_pages);
+	if (ret)
+		return ret;
+
+	ret = i915_gem_gtt_prepare_object(obj);
+	if (ret) {
+		sg_free_table(obj->pages);
+		kfree(obj->pages);
+		obj->pages = NULL;
+	}
+
+	return ret;
+}
+
 static void
 __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 {
@@ -584,9 +604,12 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	if (obj->userptr.work != &work->work) {
 		ret = 0;
 	} else if (pinned == num_pages) {
-		ret = st_set_pages(&obj->pages, pvec, num_pages);
+		ret = __i915_gem_userptr_set_pages(obj, pvec, num_pages);
 		if (ret == 0) {
 			list_add_tail(&obj->global_list, &to_i915(dev)->mm.unbound_list);
+			obj->get_page.sg = obj->pages->sgl;
+			obj->get_page.last = 0;
+
 			pinned = 0;
 		}
 	}
@@ -693,7 +716,7 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 			}
 		}
 	} else {
-		ret = st_set_pages(&obj->pages, pvec, num_pages);
+		ret = __i915_gem_userptr_set_pages(obj, pvec, num_pages);
 		if (ret == 0) {
 			obj->userptr.work = NULL;
 			pinned = 0;
@@ -715,6 +738,8 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj)
 	if (obj->madv != I915_MADV_WILLNEED)
 		obj->dirty = 0;
 
+	i915_gem_gtt_finish_object(obj);
+
 	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
 		struct page *page = sg_page_iter_page(&sg_iter);
 
diff --git a/drivers/gpu/drm/i915/i915_ioc32.c b/drivers/gpu/drm/i915/i915_ioc32.c
index 176de6322e4d..23aa04cded6b 100644
--- a/drivers/gpu/drm/i915/i915_ioc32.c
+++ b/drivers/gpu/drm/i915/i915_ioc32.c
@@ -204,7 +204,7 @@ long i915_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	drm_ioctl_compat_t *fn = NULL;
 	int ret;
 
-	if (nr < DRM_COMMAND_BASE)
+	if (nr < DRM_COMMAND_BASE || nr >= DRM_COMMAND_END)
 		return drm_compat_ioctl(filp, cmd, arg);
 
 	if (nr < DRM_COMMAND_BASE + ARRAY_SIZE(i915_compat_ioctls))
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e6bb72dca3ff..984e2fe6688c 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2706,18 +2706,11 @@ static void gen8_disable_vblank(struct drm_device *dev, int pipe)
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
-static struct drm_i915_gem_request *
-ring_last_request(struct intel_engine_cs *ring)
-{
-	return list_entry(ring->request_list.prev,
-			  struct drm_i915_gem_request, list);
-}
-
 static bool
-ring_idle(struct intel_engine_cs *ring)
+ring_idle(struct intel_engine_cs *ring, u32 seqno)
 {
 	return (list_empty(&ring->request_list) ||
-		i915_gem_request_completed(ring_last_request(ring), false));
+		i915_seqno_passed(seqno, ring->last_submitted_seqno));
 }
 
 static bool
@@ -2939,7 +2932,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 		acthd = intel_ring_get_active_head(ring);
 
 		if (ring->hangcheck.seqno == seqno) {
-			if (ring_idle(ring)) {
+			if (ring_idle(ring, seqno)) {
 				ring->hangcheck.action = HANGCHECK_IDLE;
 
 				if (waitqueue_active(&ring->irq_queue)) {
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 497cba5deb1e..849a2590e010 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -727,7 +727,7 @@ DECLARE_EVENT_CLASS(i915_context,
 	TP_fast_assign(
 			__entry->ctx = ctx;
 			__entry->vm = ctx->ppgtt ? &ctx->ppgtt->base : NULL;
-			__entry->dev = ctx->file_priv->dev_priv->dev->primary->index;
+			__entry->dev = ctx->i915->dev->primary->index;
 	),
 
 	TP_printk("dev=%u, ctx=%p, ctx_vm=%p",
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 647b1404c441..30e0f54ba19d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -6315,9 +6315,6 @@ static void intel_crtc_disable(struct drm_crtc *crtc)
 	struct drm_connector *connector;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	/* crtc should still be enabled when we disable it. */
-	WARN_ON(!crtc->state->enable);
-
 	intel_crtc_disable_planes(crtc);
 	dev_priv->display.crtc_disable(crtc);
 	dev_priv->display.off(crtc);
@@ -12591,7 +12588,8 @@ static int __intel_set_mode(struct drm_crtc *modeset_crtc,
 			continue;
 
 		if (!crtc_state->enable) {
-			intel_crtc_disable(crtc);
+			if (crtc->state->enable)
+				intel_crtc_disable(crtc);
 		} else if (crtc->state->enable) {
 			intel_crtc_disable_planes(crtc);
 			dev_priv->display.crtc_disable(crtc);
@@ -13276,7 +13274,7 @@ intel_check_primary_plane(struct drm_plane *plane,
 	if (ret)
 		return ret;
 
-	if (intel_crtc->active) {
+	if (crtc_state ? crtc_state->base.active : intel_crtc->active) {
 		struct intel_plane_state *old_state =
 			to_intel_plane_state(plane->state);
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index e539314ae87e..4be66f60504d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -275,6 +275,13 @@ struct  intel_engine_cs {
 	 * Do we have some not yet emitted requests outstanding?
 	 */
 	struct drm_i915_gem_request *outstanding_lazy_request;
+	/**
+	 * Seqno of request most recently submitted to request_list.
+	 * Used exclusively by hang checker to avoid grabbing lock while
+	 * inspecting request list.
+	 */
+	u32 last_submitted_seqno;
+
 	bool gpu_caches_dirty;
 
 	wait_queue_head_t irq_queue;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index a6d8a3ee7750..260389acfb77 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1274,10 +1274,12 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_reg_read *reg = data;
 	struct register_whitelist const *entry = whitelist;
+	unsigned size;
+	u64 offset;
 	int i, ret = 0;
 
 	for (i = 0; i < ARRAY_SIZE(whitelist); i++, entry++) {
-		if (entry->offset == reg->offset &&
+		if (entry->offset == (reg->offset & -entry->size) &&
 		    (1 << INTEL_INFO(dev)->gen & entry->gen_bitmask))
 			break;
 	}
@@ -1285,23 +1287,33 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 	if (i == ARRAY_SIZE(whitelist))
 		return -EINVAL;
 
+	/* We use the low bits to encode extra flags as the register should
+	 * be naturally aligned (and those that are not so aligned merely
+	 * limit the available flags for that register).
+	 */
+	offset = entry->offset;
+	size = entry->size;
+	size |= reg->offset ^ offset;
+
 	intel_runtime_pm_get(dev_priv);
 
-	switch (entry->size) {
+	switch (size) {
+	case 8 | 1:
+		reg->val = I915_READ64_2x32(offset, offset+4);
+		break;
 	case 8:
-		reg->val = I915_READ64(reg->offset);
+		reg->val = I915_READ64(offset);
 		break;
 	case 4:
-		reg->val = I915_READ(reg->offset);
+		reg->val = I915_READ(offset);
 		break;
 	case 2:
-		reg->val = I915_READ16(reg->offset);
+		reg->val = I915_READ16(offset);
 		break;
 	case 1:
-		reg->val = I915_READ8(reg->offset);
+		reg->val = I915_READ8(offset);
 		break;
 	default:
-		MISSING_CASE(entry->size);
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index 214eceefc981..e671ad369416 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -301,7 +301,7 @@ static void imx_tve_encoder_prepare(struct drm_encoder *encoder)
 
 	switch (tve->mode) {
 	case TVE_MODE_VGA:
-		imx_drm_set_bus_format_pins(encoder, MEDIA_BUS_FMT_YUV8_1X24,
+		imx_drm_set_bus_format_pins(encoder, MEDIA_BUS_FMT_GBR888_1X24,
 					    tve->hsync_pin, tve->vsync_pin);
 		break;
 	case TVE_MODE_TVOUT:
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 74a9ce40ddc4..b4deb9cf9d71 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -21,6 +21,7 @@
 #include <drm/drm_panel.h>
 #include <linux/videodev2.h>
 #include <video/of_display_timing.h>
+#include <linux/of_graph.h>
 
 #include "imx-drm.h"
 
@@ -208,7 +209,7 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 {
 	struct drm_device *drm = data;
 	struct device_node *np = dev->of_node;
-	struct device_node *panel_node;
+	struct device_node *port;
 	const u8 *edidp;
 	struct imx_parallel_display *imxpd;
 	int ret;
@@ -234,11 +235,19 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 			imxpd->bus_format = MEDIA_BUS_FMT_RGB666_1X24_CPADHI;
 	}
 
-	panel_node = of_parse_phandle(np, "fsl,panel", 0);
-	if (panel_node) {
-		imxpd->panel = of_drm_find_panel(panel_node);
-		if (!imxpd->panel)
-			return -EPROBE_DEFER;
+	/* port@1 is the output port */
+	port = of_graph_get_port_by_id(np, 1);
+	if (port) {
+		struct device_node *endpoint, *remote;
+
+		endpoint = of_get_child_by_name(port, "endpoint");
+		if (endpoint) {
+			remote = of_graph_get_remote_port_parent(endpoint);
+			if (remote)
+				imxpd->panel = of_drm_find_panel(remote);
+			if (!imxpd->panel)
+				return -EPROBE_DEFER;
+		}
 	}
 
 	imxpd->dev = dev;
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 8730562323a8..4a09947be244 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -5818,7 +5818,7 @@ int ci_dpm_init(struct radeon_device *rdev)
 			tmp |= DPM_ENABLED;
 			break;
 		default:
-			DRM_ERROR("Invalid PCC GPIO: %u!\n", gpio.shift);
+			DRM_DEBUG("Invalid PCC GPIO: %u!\n", gpio.shift);
 			break;
 		}
 		WREG32_SMC(CNB_PWRMGT_CNTL, tmp);
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 5450fa95a47e..c4777c8d0312 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -260,8 +260,10 @@ void radeon_gart_unbind(struct radeon_device *rdev, unsigned offset,
 			}
 		}
 	}
-	mb();
-	radeon_gart_tlb_flush(rdev);
+	if (rdev->gart.ptr) {
+		mb();
+		radeon_gart_tlb_flush(rdev);
+	}
 }
 
 /**
@@ -306,8 +308,10 @@ int radeon_gart_bind(struct radeon_device *rdev, unsigned offset,
 			page_base += RADEON_GPU_PAGE_SIZE;
 		}
 	}
-	mb();
-	radeon_gart_tlb_flush(rdev);
+	if (rdev->gart.ptr) {
+		mb();
+		radeon_gart_tlb_flush(rdev);
+	}
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 013ec7106e55..3dcc5733ff69 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -36,6 +36,7 @@ void radeon_gem_object_free(struct drm_gem_object *gobj)
 	if (robj) {
 		if (robj->gem_base.import_attach)
 			drm_prime_gem_destroy(&robj->gem_base, robj->tbo.sg);
+		radeon_mn_unregister(robj);
 		radeon_bo_unref(&robj);
 	}
 }
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 318165d4855c..676362769b8d 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -75,7 +75,6 @@ static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 	bo = container_of(tbo, struct radeon_bo, tbo);
 
 	radeon_update_memory_usage(bo, bo->tbo.mem.mem_type, -1);
-	radeon_mn_unregister(bo);
 
 	mutex_lock(&bo->rdev->gem.mutex);
 	list_del_init(&bo->list);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 1dbdf3230dae..787cd8fd897f 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2926,6 +2926,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = {
 	/* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 },
 	{ 0, 0, 0, 0 },
 };
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
index 01b558fe3695..9a0c2911272a 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
@@ -555,7 +555,6 @@ static struct platform_driver rockchip_drm_platform_driver = {
 	.probe = rockchip_drm_platform_probe,
 	.remove = rockchip_drm_platform_remove,
 	.driver = {
-		.owner = THIS_MODULE,
 		.name = "rockchip-drm",
 		.of_match_table = rockchip_drm_dt_ids,
 		.pm = &rockchip_drm_pm_ops,
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
index 77d52893d40f..002645bb5bbf 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
@@ -162,7 +162,8 @@ static void rockchip_drm_output_poll_changed(struct drm_device *dev)
 	struct rockchip_drm_private *private = dev->dev_private;
 	struct drm_fb_helper *fb_helper = &private->fbdev_helper;
 
-	drm_fb_helper_hotplug_event(fb_helper);
+	if (fb_helper)
+		drm_fb_helper_hotplug_event(fb_helper);
 }
 
 static const struct drm_mode_config_funcs rockchip_drm_mode_config_funcs = {
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
index eb2282cc4a56..eba5f8a52fbd 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
@@ -54,55 +54,56 @@ static void rockchip_gem_free_buf(struct rockchip_gem_object *rk_obj)
 		       &rk_obj->dma_attrs);
 }
 
-int rockchip_gem_mmap_buf(struct drm_gem_object *obj,
-			  struct vm_area_struct *vma)
+static int rockchip_drm_gem_object_mmap(struct drm_gem_object *obj,
+					struct vm_area_struct *vma)
+
 {
+	int ret;
 	struct rockchip_gem_object *rk_obj = to_rockchip_obj(obj);
 	struct drm_device *drm = obj->dev;
-	unsigned long vm_size;
 
-	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
-	vm_size = vma->vm_end - vma->vm_start;
-
-	if (vm_size > obj->size)
-		return -EINVAL;
+	/*
+	 * dma_alloc_attrs() allocated a struct page table for rk_obj, so clear
+	 * VM_PFNMAP flag that was set by drm_gem_mmap_obj()/drm_gem_mmap().
+	 */
+	vma->vm_flags &= ~VM_PFNMAP;
 
-	return dma_mmap_attrs(drm->dev, vma, rk_obj->kvaddr, rk_obj->dma_addr,
+	ret = dma_mmap_attrs(drm->dev, vma, rk_obj->kvaddr, rk_obj->dma_addr,
 			     obj->size, &rk_obj->dma_attrs);
+	if (ret)
+		drm_gem_vm_close(vma);
+
+	return ret;
 }
 
-/* drm driver mmap file operations */
-int rockchip_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+int rockchip_gem_mmap_buf(struct drm_gem_object *obj,
+			  struct vm_area_struct *vma)
 {
-	struct drm_file *priv = filp->private_data;
-	struct drm_device *dev = priv->minor->dev;
-	struct drm_gem_object *obj;
-	struct drm_vma_offset_node *node;
+	struct drm_device *drm = obj->dev;
 	int ret;
 
-	if (drm_device_is_unplugged(dev))
-		return -ENODEV;
+	mutex_lock(&drm->struct_mutex);
+	ret = drm_gem_mmap_obj(obj, obj->size, vma);
+	mutex_unlock(&drm->struct_mutex);
+	if (ret)
+		return ret;
 
-	mutex_lock(&dev->struct_mutex);
+	return rockchip_drm_gem_object_mmap(obj, vma);
+}
 
-	node = drm_vma_offset_exact_lookup(dev->vma_offset_manager,
-					   vma->vm_pgoff,
-					   vma_pages(vma));
-	if (!node) {
-		mutex_unlock(&dev->struct_mutex);
-		DRM_ERROR("failed to find vma node.\n");
-		return -EINVAL;
-	} else if (!drm_vma_node_is_allowed(node, filp)) {
-		mutex_unlock(&dev->struct_mutex);
-		return -EACCES;
-	}
+/* drm driver mmap file operations */
+int rockchip_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct drm_gem_object *obj;
+	int ret;
 
-	obj = container_of(node, struct drm_gem_object, vma_node);
-	ret = rockchip_gem_mmap_buf(obj, vma);
+	ret = drm_gem_mmap(filp, vma);
+	if (ret)
+		return ret;
 
-	mutex_unlock(&dev->struct_mutex);
+	obj = vma->vm_private_data;
 
-	return ret;
+	return rockchip_drm_gem_object_mmap(obj, vma);
 }
 
 struct rockchip_gem_object *
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index dc65161d7cad..34b78e736532 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -170,6 +170,7 @@ struct vop_win_phy {
 
 	struct vop_reg enable;
 	struct vop_reg format;
+	struct vop_reg rb_swap;
 	struct vop_reg act_info;
 	struct vop_reg dsp_info;
 	struct vop_reg dsp_st;
@@ -199,8 +200,12 @@ struct vop_data {
 static const uint32_t formats_01[] = {
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
 	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
 	DRM_FORMAT_NV12,
 	DRM_FORMAT_NV16,
 	DRM_FORMAT_NV24,
@@ -209,8 +214,12 @@ static const uint32_t formats_01[] = {
 static const uint32_t formats_234[] = {
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
 	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
 };
 
 static const struct vop_win_phy win01_data = {
@@ -218,6 +227,7 @@ static const struct vop_win_phy win01_data = {
 	.nformats = ARRAY_SIZE(formats_01),
 	.enable = VOP_REG(WIN0_CTRL0, 0x1, 0),
 	.format = VOP_REG(WIN0_CTRL0, 0x7, 1),
+	.rb_swap = VOP_REG(WIN0_CTRL0, 0x1, 12),
 	.act_info = VOP_REG(WIN0_ACT_INFO, 0x1fff1fff, 0),
 	.dsp_info = VOP_REG(WIN0_DSP_INFO, 0x0fff0fff, 0),
 	.dsp_st = VOP_REG(WIN0_DSP_ST, 0x1fff1fff, 0),
@@ -234,6 +244,7 @@ static const struct vop_win_phy win23_data = {
 	.nformats = ARRAY_SIZE(formats_234),
 	.enable = VOP_REG(WIN2_CTRL0, 0x1, 0),
 	.format = VOP_REG(WIN2_CTRL0, 0x7, 1),
+	.rb_swap = VOP_REG(WIN2_CTRL0, 0x1, 12),
 	.dsp_info = VOP_REG(WIN2_DSP_INFO0, 0x0fff0fff, 0),
 	.dsp_st = VOP_REG(WIN2_DSP_ST0, 0x1fff1fff, 0),
 	.yrgb_mst = VOP_REG(WIN2_MST0, 0xffffffff, 0),
@@ -242,15 +253,6 @@ static const struct vop_win_phy win23_data = {
 	.dst_alpha_ctl = VOP_REG(WIN2_DST_ALPHA_CTRL, 0xff, 0),
 };
 
-static const struct vop_win_phy cursor_data = {
-	.data_formats = formats_234,
-	.nformats = ARRAY_SIZE(formats_234),
-	.enable = VOP_REG(HWC_CTRL0, 0x1, 0),
-	.format = VOP_REG(HWC_CTRL0, 0x7, 1),
-	.dsp_st = VOP_REG(HWC_DSP_ST, 0x1fff1fff, 0),
-	.yrgb_mst = VOP_REG(HWC_MST, 0xffffffff, 0),
-};
-
 static const struct vop_ctrl ctrl_data = {
 	.standby = VOP_REG(SYS_CTRL, 0x1, 22),
 	.gate_en = VOP_REG(SYS_CTRL, 0x1, 23),
@@ -282,14 +284,14 @@ static const struct vop_reg_data vop_init_reg_table[] = {
 /*
  * Note: rk3288 has a dedicated 'cursor' window, however, that window requires
  * special support to get alpha blending working.  For now, just use overlay
- * window 1 for the drm cursor.
+ * window 3 for the drm cursor.
+ *
  */
 static const struct vop_win_data rk3288_vop_win_data[] = {
 	{ .base = 0x00, .phy = &win01_data, .type = DRM_PLANE_TYPE_PRIMARY },
-	{ .base = 0x40, .phy = &win01_data, .type = DRM_PLANE_TYPE_CURSOR },
+	{ .base = 0x40, .phy = &win01_data, .type = DRM_PLANE_TYPE_OVERLAY },
 	{ .base = 0x00, .phy = &win23_data, .type = DRM_PLANE_TYPE_OVERLAY },
-	{ .base = 0x50, .phy = &win23_data, .type = DRM_PLANE_TYPE_OVERLAY },
-	{ .base = 0x00, .phy = &cursor_data, .type = DRM_PLANE_TYPE_OVERLAY },
+	{ .base = 0x50, .phy = &win23_data, .type = DRM_PLANE_TYPE_CURSOR },
 };
 
 static const struct vop_data rk3288_vop = {
@@ -352,15 +354,32 @@ static inline void vop_mask_write_relaxed(struct vop *vop, uint32_t offset,
 	}
 }
 
+static bool has_rb_swapped(uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_BGR888:
+	case DRM_FORMAT_BGR565:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static enum vop_data_format vop_convert_format(uint32_t format)
 {
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
 		return VOP_FMT_ARGB8888;
 	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_BGR888:
 		return VOP_FMT_RGB888;
 	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_BGR565:
 		return VOP_FMT_RGB565;
 	case DRM_FORMAT_NV12:
 		return VOP_FMT_YUV420SP;
@@ -378,6 +397,7 @@ static bool is_alpha_support(uint32_t format)
 {
 	switch (format) {
 	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
 		return true;
 	default:
 		return false;
@@ -588,6 +608,7 @@ static int vop_update_plane_event(struct drm_plane *plane,
 	enum vop_data_format format;
 	uint32_t val;
 	bool is_alpha;
+	bool rb_swap;
 	bool visible;
 	int ret;
 	struct drm_rect dest = {
@@ -621,6 +642,7 @@ static int vop_update_plane_event(struct drm_plane *plane,
 		return 0;
 
 	is_alpha = is_alpha_support(fb->pixel_format);
+	rb_swap = has_rb_swapped(fb->pixel_format);
 	format = vop_convert_format(fb->pixel_format);
 	if (format < 0)
 		return format;
@@ -689,6 +711,7 @@ static int vop_update_plane_event(struct drm_plane *plane,
 	val = (dsp_sty - 1) << 16;
 	val |= (dsp_stx - 1) & 0xffff;
 	VOP_WIN_SET(vop, win, dsp_st, val);
+	VOP_WIN_SET(vop, win, rb_swap, rb_swap);
 
 	if (is_alpha) {
 		VOP_WIN_SET(vop, win, dst_alpha_ctl,
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 882cccdad272..ac6fe40b99f7 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -490,7 +490,8 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp)
 	else if (boot_cpu_data.x86 > 3)
 		tmp = pgprot_noncached(tmp);
 #endif
-#if defined(__ia64__) || defined(__arm__) || defined(__powerpc__)
+#if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \
+    defined(__powerpc__)
 	if (caching_flags & TTM_PL_FLAG_WC)
 		tmp = pgprot_writecombine(tmp);
 	else
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 3077f1554099..624d941aaad1 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -963,14 +963,13 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 	} else {
 		pool->npages_free += count;
 		list_splice(&ttm_dma->pages_list, &pool->free_list);
-		npages = count;
-		if (pool->npages_free > _manager->options.max_size) {
+		/*
+		 * Wait to have at at least NUM_PAGES_TO_ALLOC number of pages
+		 * to free in order to minimize calls to set_memory_wb().
+		 */
+		if (pool->npages_free >= (_manager->options.max_size +
+					  NUM_PAGES_TO_ALLOC))
 			npages = pool->npages_free - _manager->options.max_size;
-			/* free at least NUM_PAGES_TO_ALLOC number of pages
-			 * to reduce calls to set_memory_wb */
-			if (npages < NUM_PAGES_TO_ALLOC)
-				npages = NUM_PAGES_TO_ALLOC;
-		}
 	}
 	spin_unlock_irqrestore(&pool->lock, irq_flags);