Merge tag 'asoc-v5.9' of https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus

ASoC: Updates for v5.9

The biggest changes here one again come from Mormioto-san who has
continued his dilligent work cleaning up long standing issues in the
APIs, it's particularly nice to see the transition from digital_mute()
to mute_stream() finally completed. There's also been a lot of work on
the x86 code again, this time a big focus has been on cleaning up some
issues identified by various static tests, and on the Freescale systems.
Otherwise the biggest thing has been a lot of driver additions:

 - Convert users of digital_mute() to mute_stream().
 - Simplify I/O helper functions.
 - Add a helper for getting the RTD from a substream.
 - Many, many fixes and cleanups to the x86 code.
 - New drivers for Freescale MQS and i.MX6sx, Intel KeemBay I2S, Maxim
   MAX98360A and MAX98373 Soundwire, several Mediatek boards, nVidia
   Tegra 186 and 210, RealTek RL6231, Samsung Midas and Aries boards (some
   of the first phones I worked on!) and TI J721e EVM.

115 files changed, 1640 insertions, 798 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 58f9d8c3a17a..44f927641b89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -204,6 +204,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 				(mode_info->atom_context->bios + data_offset);
 			switch (crev) {
 			case 11:
+			case 12:
 				mem_channel_number = igp_info->v11.umachannelnumber;
 				/* channel width is 64 */
 				if (vram_width)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index d33cb344be69..a414da22a359 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1295,27 +1295,37 @@ static void amdgpu_ib_preempt_job_recovery(struct drm_gpu_scheduler *sched)
 static void amdgpu_ib_preempt_mark_partial_job(struct amdgpu_ring *ring)
 {
 	struct amdgpu_job *job;
-	struct drm_sched_job *s_job;
+	struct drm_sched_job *s_job, *tmp;
 	uint32_t preempt_seq;
 	struct dma_fence *fence, **ptr;
 	struct amdgpu_fence_driver *drv = &ring->fence_drv;
 	struct drm_gpu_scheduler *sched = &ring->sched;
+	bool preempted = true;
 
 	if (ring->funcs->type != AMDGPU_RING_TYPE_GFX)
 		return;
 
 	preempt_seq = le32_to_cpu(*(drv->cpu_addr + 2));
-	if (preempt_seq <= atomic_read(&drv->last_seq))
-		return;
+	if (preempt_seq <= atomic_read(&drv->last_seq)) {
+		preempted = false;
+		goto no_preempt;
+	}
 
 	preempt_seq &= drv->num_fences_mask;
 	ptr = &drv->fences[preempt_seq];
 	fence = rcu_dereference_protected(*ptr, 1);
 
+no_preempt:
 	spin_lock(&sched->job_list_lock);
-	list_for_each_entry(s_job, &sched->ring_mirror_list, node) {
+	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
+		if (dma_fence_is_signaled(&s_job->s_fence->finished)) {
+			/* remove job from ring_mirror_list */
+			list_del_init(&s_job->node);
+			sched->ops->free_job(s_job);
+			continue;
+		}
 		job = to_amdgpu_job(s_job);
-		if (job->fence == fence)
+		if (preempted && job->fence == fence)
 			/* mark the job as preempted */
 			job->preemption_status |= AMDGPU_IB_PREEMPTED;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 47207188c569..4fb4c3b69687 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -37,7 +37,8 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 
 	memset(&ti, 0, sizeof(struct amdgpu_task_info));
 
-	if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
+	if (amdgpu_gpu_recovery &&
+	    amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
 		DRM_ERROR("ring %s timeout, but soft recovered\n",
 			  s_job->sched->name);
 		return;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 775e389c9a13..ebb8a28ff002 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -696,7 +696,7 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
  * default power levels, write "r" (reset) to the file to reset them.
  *
  *
- * < For Vega20 >
+ * < For Vega20 and newer ASICs >
  *
  * Reading the file will display:
  *
@@ -778,8 +778,7 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 		tmp_str++;
 	while (isspace(*++tmp_str));
 
-	while (tmp_str[0]) {
-		sub_str = strsep(&tmp_str, delimiter);
+	while ((sub_str = strsep(&tmp_str, delimiter)) != NULL) {
 		ret = kstrtol(sub_str, 0, &parameter[parameter_size]);
 		if (ret)
 			return -EINVAL;
@@ -1039,8 +1038,7 @@ static ssize_t amdgpu_read_mask(const char *buf, size_t count, uint32_t *mask)
 	memcpy(buf_cpy, buf, bytes);
 	buf_cpy[bytes] = '\0';
 	tmp = buf_cpy;
-	while (tmp[0]) {
-		sub_str = strsep(&tmp, delimiter);
+	while ((sub_str = strsep(&tmp, delimiter)) != NULL) {
 		if (strlen(sub_str)) {
 			ret = kstrtol(sub_str, 0, &level);
 			if (ret)
@@ -1637,8 +1635,7 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 			i++;
 		memcpy(buf_cpy, buf, count-i);
 		tmp_str = buf_cpy;
-		while (tmp_str[0]) {
-			sub_str = strsep(&tmp_str, delimiter);
+		while ((sub_str = strsep(&tmp_str, delimiter)) != NULL) {
 			ret = kstrtol(sub_str, 0, &parameter[parameter_size]);
 			if (ret)
 				return -EINVAL;
@@ -1668,7 +1665,7 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 }
 
 /**
- * DOC: busy_percent
+ * DOC: gpu_busy_percent
  *
  * The amdgpu driver provides a sysfs API for reading how busy the GPU
  * is as a percentage.  The file gpu_busy_percent is used for this.
@@ -2784,7 +2781,7 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev,
 	if (r)
 		return r;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", sclk * 10 * 1000);
+	return snprintf(buf, PAGE_SIZE, "%u\n", sclk * 10 * 1000);
 }
 
 static ssize_t amdgpu_hwmon_show_sclk_label(struct device *dev,
@@ -2819,7 +2816,7 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev,
 	if (r)
 		return r;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", mclk * 10 * 1000);
+	return snprintf(buf, PAGE_SIZE, "%u\n", mclk * 10 * 1000);
 }
 
 static ssize_t amdgpu_hwmon_show_mclk_label(struct device *dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 7301fdcfb8bc..ef3269c43d4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -372,6 +372,52 @@ static int psp_tmr_load(struct psp_context *psp)
 	return ret;
 }
 
+static void psp_prep_tmr_unload_cmd_buf(struct psp_context *psp,
+					struct psp_gfx_cmd_resp *cmd)
+{
+	if (amdgpu_sriov_vf(psp->adev))
+		cmd->cmd_id = GFX_CMD_ID_DESTROY_VMR;
+	else
+		cmd->cmd_id = GFX_CMD_ID_DESTROY_TMR;
+}
+
+static int psp_tmr_unload(struct psp_context *psp)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_tmr_unload_cmd_buf(psp, cmd);
+	DRM_INFO("free PSP TMR buffer\n");
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd,
+				 psp->fence_buf_mc_addr);
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static int psp_tmr_terminate(struct psp_context *psp)
+{
+	int ret;
+	void *tmr_buf;
+	void **pptr;
+
+	ret = psp_tmr_unload(psp);
+	if (ret)
+		return ret;
+
+	/* free TMR memory buffer */
+	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
+	amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, pptr);
+
+	return 0;
+}
+
 static void psp_prep_asd_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
 				uint64_t asd_mc, uint32_t size)
 {
@@ -1779,8 +1825,6 @@ static int psp_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct psp_context *psp = &adev->psp;
-	void *tmr_buf;
-	void **pptr;
 
 	if (psp->adev->psp.ta_fw) {
 		psp_ras_terminate(psp);
@@ -1790,10 +1834,9 @@ static int psp_hw_fini(void *handle)
 
 	psp_asd_unload(psp);
 
+	psp_tmr_terminate(psp);
 	psp_ring_destroy(psp, PSP_RING_TYPE__KM);
 
-	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
-	amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, pptr);
 	amdgpu_bo_free_kernel(&psp->fw_pri_bo,
 			      &psp->fw_pri_mc_addr, &psp->fw_pri_buf);
 	amdgpu_bo_free_kernel(&psp->fence_buf_bo,
@@ -1840,6 +1883,18 @@ static int psp_suspend(void *handle)
 		}
 	}
 
+	ret = psp_asd_unload(psp);
+	if (ret) {
+		DRM_ERROR("Failed to unload asd\n");
+		return ret;
+	}
+
+	ret = psp_tmr_terminate(psp);
+	if (ret) {
+		DRM_ERROR("Falied to terminate tmr\n");
+		return ret;
+	}
+
 	ret = psp_ring_stop(psp, PSP_RING_TYPE__KM);
 	if (ret) {
 		DRM_ERROR("PSP ring stop failed\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index bd5dd4f64311..fac77a86c04b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -7513,12 +7513,17 @@ static int gfx_v10_0_ring_preempt_ib(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 	struct amdgpu_ring *kiq_ring = &kiq->ring;
+	unsigned long flags;
 
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
-	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size))
+	spin_lock_irqsave(&kiq->ring_lock, flags);
+
+	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) {
+		spin_unlock_irqrestore(&kiq->ring_lock, flags);
 		return -ENOMEM;
+	}
 
 	/* assert preemption condition */
 	amdgpu_ring_set_preempt_cond_exec(ring, false);
@@ -7529,6 +7534,8 @@ static int gfx_v10_0_ring_preempt_ib(struct amdgpu_ring *ring)
 				   ++ring->trail_seq);
 	amdgpu_ring_commit(kiq_ring);
 
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
+
 	/* poll the trailing fence */
 	for (i = 0; i < adev->usec_timeout; i++) {
 		if (ring->trail_seq ==
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index b544baf306f2..8fb66e50a57b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -314,30 +314,20 @@ static uint64_t sdma_v5_0_ring_get_rptr(struct amdgpu_ring *ring)
 static uint64_t sdma_v5_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u64 *wptr = NULL;
-	uint64_t local_wptr = 0;
+	u64 wptr;
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		wptr = ((u64 *)&adev->wb.wb[ring->wptr_offs]);
-		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", *wptr);
-		*wptr = (*wptr) >> 2;
-		DRM_DEBUG("wptr/doorbell after shift == 0x%016llx\n", *wptr);
+		wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs]));
+		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
-		u32 lowbit, highbit;
-
-		wptr = &local_wptr;
-		lowbit = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR)) >> 2;
-		highbit = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
-
-		DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n",
-				ring->me, highbit, lowbit);
-		*wptr = highbit;
-		*wptr = (*wptr) << 32;
-		*wptr |= lowbit;
+		wptr = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI));
+		wptr = wptr << 32;
+		wptr |= RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR));
+		DRM_DEBUG("wptr before shift [%i] wptr == 0x%016llx\n", ring->me, wptr);
 	}
 
-	return *wptr;
+	return wptr >> 2;
 }
 
 /**
@@ -1298,8 +1288,12 @@ static int sdma_v5_0_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		if (adev->sdma.instance[i].fw != NULL)
+			release_firmware(adev->sdma.instance[i].fw);
+
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index f0587d94294d..fee60921fccf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -40,6 +40,7 @@
 #include <drm/drm_file.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_device.h>
+#include <drm/drm_ioctl.h>
 #include <kgd_kfd_interface.h>
 #include <linux/swap.h>
 
@@ -1076,7 +1077,7 @@ static inline int kfd_devcgroup_check_permission(struct kfd_dev *kfd)
 #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
 	struct drm_device *ddev = kfd->ddev;
 
-	return devcgroup_check_permission(DEVCG_DEV_CHAR, ddev->driver->major,
+	return devcgroup_check_permission(DEVCG_DEV_CHAR, DRM_MAJOR,
 					  ddev->render->index,
 					  DEVCG_ACC_WRITE | DEVCG_ACC_READ);
 #else
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index d27221ddcdeb..0e0c42e9f6a3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -428,6 +428,7 @@ struct kfd_process *kfd_create_process(struct file *filep)
 					   (int)process->lead_thread->pid);
 		if (ret) {
 			pr_warn("Creating procfs pid directory failed");
+			kobject_put(process->kobj);
 			goto out;
 		}
 
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 7ced9f87be97..86ffa0c2880f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -974,6 +974,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	/* Update the actual used number of crtc */
 	adev->mode_info.num_crtc = adev->dm.display_indexes_num;
 
+	/* create fake encoders for MST */
+	dm_dp_create_fake_mst_encoders(adev);
+
 	/* TODO: Add_display_info? */
 
 	/* TODO use dynamic cursor width */
@@ -997,6 +1000,12 @@ error:
 
 static void amdgpu_dm_fini(struct amdgpu_device *adev)
 {
+	int i;
+
+	for (i = 0; i < adev->dm.display_indexes_num; i++) {
+		drm_encoder_cleanup(&adev->dm.mst_encoders[i].base);
+	}
+
 	amdgpu_dm_audio_fini(adev);
 
 	amdgpu_dm_destroy_drm_device(&adev->dm);
@@ -1358,7 +1367,7 @@ static int dm_late_init(void *handle)
 	struct dmcu *dmcu = NULL;
 	bool ret;
 
-	if (!adev->dm.fw_dmcu)
+	if (!adev->dm.fw_dmcu && !adev->dm.dmub_fw)
 		return detect_mst_link_for_all_connectors(adev->ddev);
 
 	dmcu = adev->dm.dc->res_pool->dmcu;
@@ -2010,6 +2019,7 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 	struct amdgpu_display_manager *dm;
 	struct drm_connector *conn_base;
 	struct amdgpu_device *adev;
+	struct dc_link *link = NULL;
 	static const u8 pre_computed_values[] = {
 		50, 51, 52, 53, 55, 56, 57, 58, 59, 61, 62, 63, 65, 66, 68, 69,
 		71, 72, 74, 75, 77, 79, 81, 82, 84, 86, 88, 90, 92, 94, 96, 98};
@@ -2017,6 +2027,10 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 	if (!aconnector || !aconnector->dc_link)
 		return;
 
+	link = aconnector->dc_link;
+	if (link->connector_signal != SIGNAL_TYPE_EDP)
+		return;
+
 	conn_base = &aconnector->base;
 	adev = conn_base->dev->dev_private;
 	dm = &adev->dm;
@@ -5024,7 +5038,8 @@ create_validate_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 	struct drm_connector *connector = &aconnector->base;
 	struct amdgpu_device *adev = connector->dev->dev_private;
 	struct dc_stream_state *stream;
-	int requested_bpc = connector->state ? connector->state->max_requested_bpc : 8;
+	const struct drm_connector_state *drm_state = dm_state ? &dm_state->base : NULL;
+	int requested_bpc = drm_state ? drm_state->max_requested_bpc : 8;
 	enum dc_status dc_result = DC_OK;
 
 	do {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index d61186ff411d..648180ccdc2e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -43,6 +43,9 @@
  */
 
 #define AMDGPU_DM_MAX_DISPLAY_INDEX 31
+
+#define AMDGPU_DM_MAX_CRTC 6
+
 /*
 #include "include/amdgpu_dal_power_if.h"
 #include "amdgpu_dm_irq.h"
@@ -328,6 +331,13 @@ struct amdgpu_display_manager {
 	 * available in FW
 	 */
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
+
+	/**
+	 * @mst_encoders:
+	 *
+	 * fake encoders used for DP MST.
+	 */
+	struct amdgpu_encoder mst_encoders[AMDGPU_DM_MAX_CRTC];
 };
 
 struct amdgpu_dm_connector {
@@ -356,7 +366,6 @@ struct amdgpu_dm_connector {
 	struct amdgpu_dm_dp_aux dm_dp_aux;
 	struct drm_dp_mst_port *port;
 	struct amdgpu_dm_connector *mst_port;
-	struct amdgpu_encoder *mst_encoder;
 	struct drm_dp_aux *dsc_aux;
 
 	/* TODO see if we can merge with ddc_bus or make a dm_connector */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 076af267b488..1d692f4f42f3 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -1058,7 +1058,6 @@ static const struct {
 		{"link_settings", &dp_link_settings_debugfs_fops},
 		{"phy_settings", &dp_phy_settings_debugfs_fop},
 		{"test_pattern", &dp_phy_test_pattern_fops},
-		{"output_bpc", &output_bpc_fops},
 		{"vrr_range", &vrr_range_fops},
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 		{"hdcp_sink_capability", &hdcp_sink_capability_fops},
@@ -1142,6 +1141,9 @@ void connector_debugfs_init(struct amdgpu_dm_connector *connector)
 	debugfs_create_file_unsafe("force_yuv420_output", 0644, dir, connector,
 				   &force_yuv420_output_fops);
 
+	debugfs_create_file("output_bpc", 0644, dir, connector,
+			    &output_bpc_fops);
+
 	connector->debugfs_dpcd_address = 0;
 	connector->debugfs_dpcd_size = 0;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index dcf84a61de37..949d10ef8304 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -510,8 +510,10 @@ static ssize_t srm_data_read(struct file *filp, struct kobject *kobj, struct bin
 
 	srm = psp_get_srm(work->hdcp.config.psp.handle, &srm_version, &srm_size);
 
-	if (!srm)
-		return -EINVAL;
+	if (!srm) {
+		ret = -EINVAL;
+		goto ret;
+	}
 
 	if (pos >= srm_size)
 		ret = 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 ae0a7ef1d595..e5ecc5affa1e 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
@@ -95,7 +95,6 @@ dm_dp_mst_connector_destroy(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector =
 		to_amdgpu_dm_connector(connector);
-	struct amdgpu_encoder *amdgpu_encoder = aconnector->mst_encoder;
 
 	if (aconnector->dc_sink) {
 		dc_link_remove_remote_sink(aconnector->dc_link,
@@ -105,8 +104,6 @@ dm_dp_mst_connector_destroy(struct drm_connector *connector)
 
 	kfree(aconnector->edid);
 
-	drm_encoder_cleanup(&amdgpu_encoder->base);
-	kfree(amdgpu_encoder);
 	drm_connector_cleanup(connector);
 	drm_dp_mst_put_port_malloc(aconnector->port);
 	kfree(aconnector);
@@ -243,7 +240,11 @@ static struct drm_encoder *
 dm_mst_atomic_best_encoder(struct drm_connector *connector,
 			   struct drm_connector_state *connector_state)
 {
-	return &to_amdgpu_dm_connector(connector)->mst_encoder->base;
+	struct drm_device *dev = connector->dev;
+	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(connector_state->crtc);
+
+	return &adev->dm.mst_encoders[acrtc->crtc_id].base;
 }
 
 static int
@@ -306,31 +307,27 @@ static const struct drm_encoder_funcs amdgpu_dm_encoder_funcs = {
 	.destroy = amdgpu_dm_encoder_destroy,
 };
 
-static struct amdgpu_encoder *
-dm_dp_create_fake_mst_encoder(struct amdgpu_dm_connector *connector)
+void
+dm_dp_create_fake_mst_encoders(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = connector->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_encoder *amdgpu_encoder;
-	struct drm_encoder *encoder;
-
-	amdgpu_encoder = kzalloc(sizeof(*amdgpu_encoder), GFP_KERNEL);
-	if (!amdgpu_encoder)
-		return NULL;
+	struct drm_device *dev = adev->ddev;
+	int i;
 
-	encoder = &amdgpu_encoder->base;
-	encoder->possible_crtcs = amdgpu_dm_get_encoder_crtc_mask(adev);
+	for (i = 0; i < adev->dm.display_indexes_num; i++) {
+		struct amdgpu_encoder *amdgpu_encoder = &adev->dm.mst_encoders[i];
+		struct drm_encoder *encoder = &amdgpu_encoder->base;
 
-	drm_encoder_init(
-		dev,
-		&amdgpu_encoder->base,
-		&amdgpu_dm_encoder_funcs,
-		DRM_MODE_ENCODER_DPMST,
-		NULL);
+		encoder->possible_crtcs = amdgpu_dm_get_encoder_crtc_mask(adev);
 
-	drm_encoder_helper_add(encoder, &amdgpu_dm_encoder_helper_funcs);
+		drm_encoder_init(
+			dev,
+			&amdgpu_encoder->base,
+			&amdgpu_dm_encoder_funcs,
+			DRM_MODE_ENCODER_DPMST,
+			NULL);
 
-	return amdgpu_encoder;
+		drm_encoder_helper_add(encoder, &amdgpu_dm_encoder_helper_funcs);
+	}
 }
 
 static struct drm_connector *
@@ -343,6 +340,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
+	int i;
 
 	aconnector = kzalloc(sizeof(*aconnector), GFP_KERNEL);
 	if (!aconnector)
@@ -369,9 +367,10 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 		master->dc_link,
 		master->connector_id);
 
-	aconnector->mst_encoder = dm_dp_create_fake_mst_encoder(master);
-	drm_connector_attach_encoder(&aconnector->base,
-				     &aconnector->mst_encoder->base);
+	for (i = 0; i < adev->dm.display_indexes_num; i++) {
+		drm_connector_attach_encoder(&aconnector->base,
+					     &adev->dm.mst_encoders[i].base);
+	}
 
 	connector->max_bpc_property = master->base.max_bpc_property;
 	if (connector->max_bpc_property)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index d2c56579a2cc..b38bd68121ce 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -35,6 +35,9 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 				       struct amdgpu_dm_connector *aconnector,
 				       int link_index);
 
+void
+dm_dp_create_fake_mst_encoders(struct amdgpu_device *adev);
+
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 				       struct dc_state *dc_state);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 6f93a6ca4cf0..d016f50e187c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2538,10 +2538,12 @@ void dc_commit_updates_for_stream(struct dc *dc,
 
 	copy_stream_update_to_stream(dc, context, stream, stream_update);
 
-	if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) {
-		DC_ERROR("Mode validation failed for stream update!\n");
-		dc_release_state(context);
-		return;
+	if (update_type > UPDATE_TYPE_FAST) {
+		if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) {
+			DC_ERROR("Mode validation failed for stream update!\n");
+			dc_release_state(context);
+			return;
+		}
 	}
 
 	commit_planes_for_stream(
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 4f0e7203dba4..470c82794f6f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -56,7 +56,7 @@ void update_stream_signal(struct dc_stream_state *stream, struct dc_sink *sink)
 	}
 }
 
-static void dc_stream_construct(struct dc_stream_state *stream,
+static bool dc_stream_construct(struct dc_stream_state *stream,
 	struct dc_sink *dc_sink_data)
 {
 	uint32_t i = 0;
@@ -118,11 +118,17 @@ static void dc_stream_construct(struct dc_stream_state *stream,
 	update_stream_signal(stream, dc_sink_data);
 
 	stream->out_transfer_func = dc_create_transfer_func();
+	if (stream->out_transfer_func == NULL) {
+		dc_sink_release(dc_sink_data);
+		return false;
+	}
 	stream->out_transfer_func->type = TF_TYPE_BYPASS;
 	stream->out_transfer_func->ctx = stream->ctx;
 
 	stream->stream_id = stream->ctx->dc_stream_id_count;
 	stream->ctx->dc_stream_id_count++;
+
+	return true;
 }
 
 static void dc_stream_destruct(struct dc_stream_state *stream)
@@ -164,13 +170,20 @@ struct dc_stream_state *dc_create_stream_for_sink(
 
 	stream = kzalloc(sizeof(struct dc_stream_state), GFP_KERNEL);
 	if (stream == NULL)
-		return NULL;
+		goto alloc_fail;
 
-	dc_stream_construct(stream, sink);
+	if (dc_stream_construct(stream, sink) == false)
+		goto construct_fail;
 
 	kref_init(&stream->refcount);
 
 	return stream;
+
+construct_fail:
+	kfree(stream);
+
+alloc_fail:
+	return NULL;
 }
 
 struct dc_stream_state *dc_copy_stream(const struct dc_stream_state *stream)
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index 3f66868df171..ea29cf95d470 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -28,8 +28,6 @@ endif
 endif
 
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc_dpi.o := $(dsc_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dsc/dc_dsc.o := $(dsc_ccflags)
 
 DSC = dc_dsc.o rc_calc.o rc_calc_dpi.o
 
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index 0ea6662a1563..0c7f247bb7de 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -22,10 +22,12 @@
  * Author: AMD
  */
 
+#include <drm/drm_dsc.h>
 #include "dc_hw_types.h"
 #include "dsc.h"
 #include <drm/drm_dp_helper.h>
 #include "dc.h"
+#include "rc_calc.h"
 
 /* This module's internal functions */
 
@@ -304,22 +306,6 @@ static inline uint32_t dsc_div_by_10_round_up(uint32_t value)
 	return (value + 9) / 10;
 }
 
-static inline uint32_t calc_dsc_bpp_x16(uint32_t stream_bandwidth_kbps, uint32_t pix_clk_100hz, uint32_t bpp_increment_div)
-{
-	uint32_t dsc_target_bpp_x16;
-	float f_dsc_target_bpp;
-	float f_stream_bandwidth_100bps = stream_bandwidth_kbps * 10.0f;
-	uint32_t precision = bpp_increment_div; // bpp_increment_div is actually precision
-
-	f_dsc_target_bpp = f_stream_bandwidth_100bps / pix_clk_100hz;
-
-	// Round down to the nearest precision stop to bring it into DSC spec range
-	dsc_target_bpp_x16 = (uint32_t)(f_dsc_target_bpp * precision);
-	dsc_target_bpp_x16 = (dsc_target_bpp_x16 * 16) / precision;
-
-	return dsc_target_bpp_x16;
-}
-
 /* Get DSC bandwidth range based on [min_bpp, max_bpp] target bitrate range, and timing's pixel clock
  * and uncompressed bandwidth.
  */
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
index 03ae15946c6d..667afbc260f9 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
@@ -23,6 +23,7 @@
  * Authors: AMD
  *
  */
+#include <drm/drm_dsc.h>
 
 #include "os_types.h"
 #include "rc_calc.h"
@@ -40,7 +41,8 @@
 	break
 
 
-void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc, enum max_min max_min, float bpp)
+static void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc,
+		       enum max_min max_min, float bpp)
 {
 	int mode = MODE_SELECT(444, 422, 420);
 	int sel = table_hash(mode, bpc, max_min);
@@ -85,7 +87,7 @@ void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc, enum ma
 	memcpy(qps, table[index].qps, sizeof(qp_set));
 }
 
-double dsc_roundf(double num)
+static double dsc_roundf(double num)
 {
 	if (num < 0.0)
 		num = num - 0.5;
@@ -95,7 +97,7 @@ double dsc_roundf(double num)
 	return (int)(num);
 }
 
-double dsc_ceil(double num)
+static double dsc_ceil(double num)
 {
 	double retval = (int)num;
 
@@ -105,7 +107,7 @@ double dsc_ceil(double num)
 	return (int)retval;
 }
 
-void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp)
+static void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp)
 {
 	int   *p = ofs;
 
@@ -160,7 +162,7 @@ void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp)
 	}
 }
 
-int median3(int a, int b, int c)
+static int median3(int a, int b, int c)
 {
 	if (a > b)
 		swap(a, b);
@@ -172,13 +174,25 @@ int median3(int a, int b, int c)
 	return b;
 }
 
-void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_comp bpc, float bpp, int slice_width, int slice_height, int minor_version)
+static void _do_calc_rc_params(struct rc_params *rc, enum colour_mode cm,
+			       enum bits_per_comp bpc, u8 drm_bpp,
+			       bool is_navite_422_or_420,
+			       int slice_width, int slice_height,
+			       int minor_version)
 {
+	float bpp;
 	float bpp_group;
 	float initial_xmit_delay_factor;
 	int padding_pixels;
 	int i;
 
+	bpp = ((float)drm_bpp / 16.0);
+	/* in native_422 or native_420 modes, the bits_per_pixel is double the
+	 * target bpp (the latter is what calc_rc_params expects)
+	 */
+	if (is_navite_422_or_420)
+		bpp /= 2.0;
+
 	rc->rc_quant_incr_limit0 = ((bpc == BPC_8) ? 11 : (bpc == BPC_10 ? 15 : 19)) - ((minor_version == 1 && cm == CM_444) ? 1 : 0);
 	rc->rc_quant_incr_limit1 = ((bpc == BPC_8) ? 11 : (bpc == BPC_10 ? 15 : 19)) - ((minor_version == 1 && cm == CM_444) ? 1 : 0);
 
@@ -251,3 +265,128 @@ void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_com
 	rc->rc_buf_thresh[13] = 8064;
 }
 
+static u32 _do_bytes_per_pixel_calc(int slice_width, u8 drm_bpp,
+				    bool is_navite_422_or_420)
+{
+	float bpp;
+	u32 bytes_per_pixel;
+	double d_bytes_per_pixel;
+
+	bpp = ((float)drm_bpp / 16.0);
+	d_bytes_per_pixel = dsc_ceil(bpp * slice_width / 8.0) / slice_width;
+	// TODO: Make sure the formula for calculating this is precise (ceiling
+	// vs. floor, and at what point they should be applied)
+	if (is_navite_422_or_420)
+		d_bytes_per_pixel /= 2;
+
+	bytes_per_pixel = (u32)dsc_ceil(d_bytes_per_pixel * 0x10000000);
+
+	return bytes_per_pixel;
+}
+
+static u32 _do_calc_dsc_bpp_x16(u32 stream_bandwidth_kbps, u32 pix_clk_100hz,
+				u32 bpp_increment_div)
+{
+	u32 dsc_target_bpp_x16;
+	float f_dsc_target_bpp;
+	float f_stream_bandwidth_100bps;
+	// bpp_increment_div is actually precision
+	u32 precision = bpp_increment_div;
+
+	f_stream_bandwidth_100bps = stream_bandwidth_kbps * 10.0f;
+	f_dsc_target_bpp = f_stream_bandwidth_100bps / pix_clk_100hz;
+
+	// Round down to the nearest precision stop to bring it into DSC spec
+	// range
+	dsc_target_bpp_x16 = (u32)(f_dsc_target_bpp * precision);
+	dsc_target_bpp_x16 = (dsc_target_bpp_x16 * 16) / precision;
+
+	return dsc_target_bpp_x16;
+}
+
+/**
+ * calc_rc_params - reads the user's cmdline mode
+ * @rc: DC internal DSC parameters
+ * @pps: DRM struct with all required DSC values
+ *
+ * This function expects a drm_dsc_config data struct with all the required DSC
+ * values previously filled out by our driver and based on this information it
+ * computes some of the DSC values.
+ *
+ * @note This calculation requires float point operation, most of it executes
+ * under kernel_fpu_{begin,end}.
+ */
+void calc_rc_params(struct rc_params *rc, const struct drm_dsc_config *pps)
+{
+	enum colour_mode mode;
+	enum bits_per_comp bpc;
+	bool is_navite_422_or_420;
+	u8 drm_bpp = pps->bits_per_pixel;
+	int slice_width  = pps->slice_width;
+	int slice_height = pps->slice_height;
+
+	mode = pps->convert_rgb ? CM_RGB : (pps->simple_422  ? CM_444 :
+					   (pps->native_422  ? CM_422 :
+					    pps->native_420  ? CM_420 : CM_444));
+	bpc = (pps->bits_per_component == 8) ? BPC_8 : (pps->bits_per_component == 10)
+					     ? BPC_10 : BPC_12;
+
+	is_navite_422_or_420 = pps->native_422 || pps->native_420;
+
+	DC_FP_START();
+	_do_calc_rc_params(rc, mode, bpc, drm_bpp, is_navite_422_or_420,
+			   slice_width, slice_height,
+			   pps->dsc_version_minor);
+	DC_FP_END();
+}
+
+/**
+ * calc_dsc_bytes_per_pixel - calculate bytes per pixel
+ * @pps: DRM struct with all required DSC values
+ *
+ * Based on the information inside drm_dsc_config, this function calculates the
+ * total of bytes per pixel.
+ *
+ * @note This calculation requires float point operation, most of it executes
+ * under kernel_fpu_{begin,end}.
+ *
+ * Return:
+ * Return the number of bytes per pixel
+ */
+u32 calc_dsc_bytes_per_pixel(const struct drm_dsc_config *pps)
+
+{
+	u32 ret;
+	u8 drm_bpp = pps->bits_per_pixel;
+	int slice_width  = pps->slice_width;
+	bool is_navite_422_or_420 = pps->native_422 || pps->native_420;
+
+	DC_FP_START();
+	ret = _do_bytes_per_pixel_calc(slice_width, drm_bpp,
+				       is_navite_422_or_420);
+	DC_FP_END();
+	return ret;
+}
+
+/**
+ * calc_dsc_bpp_x16 - retrieve the dsc bits per pixel
+ * @stream_bandwidth_kbps:
+ * @pix_clk_100hz:
+ * @bpp_increment_div:
+ *
+ * Calculate the total of bits per pixel for DSC configuration.
+ *
+ * @note This calculation requires float point operation, most of it executes
+ * under kernel_fpu_{begin,end}.
+ */
+u32 calc_dsc_bpp_x16(u32 stream_bandwidth_kbps, u32 pix_clk_100hz,
+		     u32 bpp_increment_div)
+{
+	u32 dsc_bpp;
+
+	DC_FP_START();
+	dsc_bpp =  _do_calc_dsc_bpp_x16(stream_bandwidth_kbps, pix_clk_100hz,
+					bpp_increment_div);
+	DC_FP_END();
+	return dsc_bpp;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
index b6b1f09c2009..21723fa6561e 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
@@ -77,7 +77,10 @@ struct qp_entry {
 
 typedef struct qp_entry qp_table[];
 
-void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_comp bpc, float bpp, int slice_width, int slice_height, int minor_version);
+void calc_rc_params(struct rc_params *rc, const struct drm_dsc_config *pps);
+u32 calc_dsc_bytes_per_pixel(const struct drm_dsc_config *pps);
+u32 calc_dsc_bpp_x16(u32 stream_bandwidth_kbps, u32 pix_clk_100hz,
+		     u32 bpp_increment_div);
 
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
index 1f6e63b71456..ef830aded5b1 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
@@ -27,8 +27,6 @@
 #include "dscc_types.h"
 #include "rc_calc.h"
 
-double dsc_ceil(double num);
-
 static void copy_pps_fields(struct drm_dsc_config *to, const struct drm_dsc_config *from)
 {
 	to->line_buf_depth           = from->line_buf_depth;
@@ -100,34 +98,13 @@ static void copy_rc_to_cfg(struct drm_dsc_config *dsc_cfg, const struct rc_param
 
 int dscc_compute_dsc_parameters(const struct drm_dsc_config *pps, struct dsc_parameters *dsc_params)
 {
-	enum colour_mode  mode = pps->convert_rgb ? CM_RGB :
-							(pps->simple_422  ? CM_444 :
-							(pps->native_422  ? CM_422 :
-							pps->native_420  ? CM_420 : CM_444));
-	enum bits_per_comp bpc = (pps->bits_per_component == 8) ? BPC_8 :
-							(pps->bits_per_component == 10) ? BPC_10 : BPC_12;
-	float            bpp = ((float) pps->bits_per_pixel / 16.0);
-	int              slice_width  = pps->slice_width;
-	int              slice_height = pps->slice_height;
 	int              ret;
 	struct rc_params rc;
 	struct drm_dsc_config   dsc_cfg;
 
-	double d_bytes_per_pixel = dsc_ceil(bpp * slice_width / 8.0) / slice_width;
-
-	// TODO: Make sure the formula for calculating this is precise (ceiling vs. floor, and at what point they should be applied)
-	if (pps->native_422 || pps->native_420)
-		d_bytes_per_pixel /= 2;
-
-	dsc_params->bytes_per_pixel = (uint32_t)dsc_ceil(d_bytes_per_pixel * 0x10000000);
-
-	/* in native_422 or native_420 modes, the bits_per_pixel is double the target bpp
-	 * (the latter is what calc_rc_params expects)
-	 */
-	if (pps->native_422 || pps->native_420)
-		bpp /= 2.0;
+	dsc_params->bytes_per_pixel = calc_dsc_bytes_per_pixel(pps);
 
-	calc_rc_params(&rc, mode, bpc, bpp, slice_width, slice_height, pps->dsc_version_minor);
+	calc_rc_params(&rc, pps);
 	dsc_params->pps = *pps;
 	dsc_params->pps.initial_scale_value = 8 * rc.rc_model_size / (rc.rc_model_size - rc.initial_fullness_offset);
 
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index 9431b48aecb4..bcfe34ef8c28 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -843,7 +843,7 @@ static bool build_regamma(struct pwl_float_data_ex *rgb_regamma,
 	pow_buffer_ptr = -1; // reset back to no optimize
 	ret = true;
 release:
-	kfree(coeff);
+	kvfree(coeff);
 	return ret;
 }
 
@@ -1777,7 +1777,7 @@ bool calculate_user_regamma_ramp(struct dc_transfer_func *output_tf,
 
 	kfree(rgb_regamma);
 rgb_regamma_alloc_fail:
-	kvfree(rgb_user);
+	kfree(rgb_user);
 rgb_user_alloc_fail:
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index 67476047c067..fbb3f3a0dff7 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -689,7 +689,7 @@ static int renoir_set_power_profile_mode(struct smu_context *smu, long *input, u
 		return -EINVAL;
 	}
 
-	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
+	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_ActiveProcessNotify,
 				    1 << workload_type,
 				    NULL);
 	if (ret) {
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 85e5b1ed22c2..56923a96b450 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -239,7 +239,7 @@ static void ci_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr)
 
 	switch (dev_id) {
 	case 0x67BA:
-	case 0x66B1:
+	case 0x67B1:
 		smu_data->power_tune_defaults = &defaults_hawaii_pro;
 		break;
 	case 0x67B8:
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
index 2fb97554134f..c2e0fbbccf56 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
@@ -522,9 +522,11 @@ static int vega20_smu_init(struct pp_hwmgr *hwmgr)
 	priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].version = 0x01;
 	priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].size = sizeof(DpmActivityMonitorCoeffInt_t);
 
-	ret = smu_v11_0_i2c_eeprom_control_init(&adev->pm.smu_i2c);
-	if (ret)
-		goto err4;
+	if (adev->psp.ras.ras) {
+		ret = smu_v11_0_i2c_eeprom_control_init(&adev->pm.smu_i2c);
+		if (ret)
+			goto err4;
+	}
 
 	return 0;
 
@@ -560,7 +562,8 @@ static int vega20_smu_fini(struct pp_hwmgr *hwmgr)
 			(struct vega20_smumgr *)(hwmgr->smu_backend);
 	struct amdgpu_device *adev = hwmgr->adev;
 
-	smu_v11_0_i2c_eeprom_control_fini(&adev->pm.smu_i2c);
+	if (adev->psp.ras.ras)
+		smu_v11_0_i2c_eeprom_control_fini(&adev->pm.smu_i2c);
 
 	if (priv) {
 		amdgpu_bo_free_kernel(&priv->smu_tables.entry[TABLE_PPTABLE].handle,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 3da71a088b92..0ecc18b55ffb 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -644,9 +644,6 @@ static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
 
 	/* sclk is bigger than max sclk in the dependence table */
 	*voltage |= (dep_table->entries[i - 1].vddc * VOLTAGE_SCALE) << VDDC_SHIFT;
-	vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
-			(dep_table->entries[i - 1].vddc -
-					(uint16_t)VDDC_VDDCI_DELTA));
 
 	if (SMU7_VOLTAGE_CONTROL_NONE == data->vddci_control)
 		*voltage |= (data->vbios_boot_state.vddci_bootup_value *
@@ -654,8 +651,13 @@ static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
 	else if (dep_table->entries[i - 1].vddci)
 		*voltage |= (dep_table->entries[i - 1].vddci *
 				VOLTAGE_SCALE) << VDDC_SHIFT;
-	else
+	else {
+		vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
+				(dep_table->entries[i - 1].vddc -
+						(uint16_t)VDDC_VDDCI_DELTA));
+
 		*voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
+	}
 
 	if (SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control)
 		*mvdd = data->vbios_boot_state.mvdd_bootup_value * VOLTAGE_SCALE;
diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
index 6b27242b9ee3..bca3fcff16ec 100644
--- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
+++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
@@ -173,8 +173,6 @@ static int aspeed_gfx_load(struct drm_device *drm)
 
 	drm_mode_config_reset(drm);
 
-	drm_fbdev_generic_setup(drm, 32);
-
 	return 0;
 }
 
@@ -225,6 +223,7 @@ static int aspeed_gfx_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_unload;
 
+	drm_fbdev_generic_setup(&priv->drm, 32);
 	return 0;
 
 err_unload:
diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c
index 6dad025f8da7..c751baf3d064 100644
--- a/drivers/gpu/drm/bridge/sii902x.c
+++ b/drivers/gpu/drm/bridge/sii902x.c
@@ -672,8 +672,8 @@ static void sii902x_audio_shutdown(struct device *dev, void *data)
 	clk_disable_unprepare(sii902x->audio.mclk);
 }
 
-static int sii902x_audio_digital_mute(struct device *dev,
-				      void *data, bool enable)
+static int sii902x_audio_mute(struct device *dev, void *data,
+			      bool enable, int direction)
 {
 	struct sii902x *sii902x = dev_get_drvdata(dev);
 
@@ -724,9 +724,10 @@ static int sii902x_audio_get_dai_id(struct snd_soc_component *component,
 static const struct hdmi_codec_ops sii902x_audio_codec_ops = {
 	.hw_params = sii902x_audio_hw_params,
 	.audio_shutdown = sii902x_audio_shutdown,
-	.digital_mute = sii902x_audio_digital_mute,
+	.mute_stream = sii902x_audio_mute,
 	.get_eld = sii902x_audio_get_eld,
 	.get_dai_id = sii902x_audio_get_dai_id,
+	.no_capture_mute = 1,
 };
 
 static int sii902x_audio_codec_init(struct sii902x *sii902x,
diff --git a/drivers/gpu/drm/drm_encoder_slave.c b/drivers/gpu/drm/drm_encoder_slave.c
index cf804389f5ec..e464429d32df 100644
--- a/drivers/gpu/drm/drm_encoder_slave.c
+++ b/drivers/gpu/drm/drm_encoder_slave.c
@@ -61,13 +61,8 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 
 	request_module("%s%s", I2C_MODULE_PREFIX, info->type);
 
-	client = i2c_new_device(adap, info);
-	if (!client) {
-		err = -ENOMEM;
-		goto fail;
-	}
-
-	if (!client->dev.driver) {
+	client = i2c_new_client_device(adap, info);
+	if (!i2c_client_has_driver(client)) {
 		err = -ENODEV;
 		goto fail_unregister;
 	}
@@ -84,7 +79,7 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 
 	err = encoder_drv->encoder_init(client, dev, encoder);
 	if (err)
-		goto fail_unregister;
+		goto fail_module_put;
 
 	if (info->platform_data)
 		encoder->slave_funcs->set_config(&encoder->base,
@@ -92,10 +87,10 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 
 	return 0;
 
+fail_module_put:
+	module_put(module);
 fail_unregister:
 	i2c_unregister_device(client);
-	module_put(module);
-fail:
 	return err;
 }
 EXPORT_SYMBOL(drm_i2c_encoder_init);
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 170aa7689110..5609e164805f 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -227,18 +227,9 @@ int drm_fb_helper_debug_leave(struct fb_info *info)
 }
 EXPORT_SYMBOL(drm_fb_helper_debug_leave);
 
-/**
- * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration
- * @fb_helper: driver-allocated fbdev helper, can be NULL
- *
- * This should be called from driver's drm &drm_driver.lastclose callback
- * when implementing an fbcon on top of kms using this helper. This ensures that
- * the user isn't greeted with a black screen when e.g. X dies.
- *
- * RETURNS:
- * Zero if everything went ok, negative error code otherwise.
- */
-int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper)
+static int
+__drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper,
+					    bool force)
 {
 	bool do_delayed;
 	int ret;
@@ -250,7 +241,16 @@ int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper)
 		return 0;
 
 	mutex_lock(&fb_helper->lock);
-	ret = drm_client_modeset_commit(&fb_helper->client);
+	if (force) {
+		/*
+		 * Yes this is the _locked version which expects the master lock
+		 * to be held. But for forced restores we're intentionally
+		 * racing here, see drm_fb_helper_set_par().
+		 */
+		ret = drm_client_modeset_commit_locked(&fb_helper->client);
+	} else {
+		ret = drm_client_modeset_commit(&fb_helper->client);
+	}
 
 	do_delayed = fb_helper->delayed_hotplug;
 	if (do_delayed)
@@ -262,6 +262,22 @@ int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper)
 
 	return ret;
 }
+
+/**
+ * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration
+ * @fb_helper: driver-allocated fbdev helper, can be NULL
+ *
+ * This should be called from driver's drm &drm_driver.lastclose callback
+ * when implementing an fbcon on top of kms using this helper. This ensures that
+ * the user isn't greeted with a black screen when e.g. X dies.
+ *
+ * RETURNS:
+ * Zero if everything went ok, negative error code otherwise.
+ */
+int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper)
+{
+	return __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, false);
+}
 EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked);
 
 #ifdef CONFIG_MAGIC_SYSRQ
@@ -1318,6 +1334,7 @@ int drm_fb_helper_set_par(struct fb_info *info)
 {
 	struct drm_fb_helper *fb_helper = info->par;
 	struct fb_var_screeninfo *var = &info->var;
+	bool force;
 
 	if (oops_in_progress)
 		return -EBUSY;
@@ -1327,7 +1344,25 @@ int drm_fb_helper_set_par(struct fb_info *info)
 		return -EINVAL;
 	}
 
-	drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
+	/*
+	 * Normally we want to make sure that a kms master takes precedence over
+	 * fbdev, to avoid fbdev flickering and occasionally stealing the
+	 * display status. But Xorg first sets the vt back to text mode using
+	 * the KDSET IOCTL with KD_TEXT, and only after that drops the master
+	 * status when exiting.
+	 *
+	 * In the past this was caught by drm_fb_helper_lastclose(), but on
+	 * modern systems where logind always keeps a drm fd open to orchestrate
+	 * the vt switching, this doesn't work.
+	 *
+	 * To not break the userspace ABI we have this special case here, which
+	 * is only used for the above case. Everything else uses the normal
+	 * commit function, which ensures that we never steal the display from
+	 * an active drm master.
+	 */
+	force = var->activate & FB_ACTIVATE_KD_TEXT;
+
+	__drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, force);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index ffd95bfeaa94..d00ea384dcbf 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -30,12 +30,6 @@ struct drm_dmi_panel_orientation_data {
 	int orientation;
 };
 
-static const struct drm_dmi_panel_orientation_data acer_s1003 = {
-	.width = 800,
-	.height = 1280,
-	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
-};
-
 static const struct drm_dmi_panel_orientation_data asus_t100ha = {
 	.width = 800,
 	.height = 1280,
@@ -114,13 +108,19 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"),
 		},
-		.driver_data = (void *)&acer_s1003,
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* Asus T100HA */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100HAN"),
 		},
 		.driver_data = (void *)&asus_t100ha,
+	}, {	/* Asus T101HA */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T101HA"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* GPD MicroPC (generic strings, also match on bios date) */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"),
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index 619f81435c1b..58b89ec11b0e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -61,7 +61,7 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev,
 				struct device *subdrv_dev, void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm_dev->dev_private;
-	int ret;
+	int ret = 0;
 
 	if (get_dma_ops(priv->dma_dev) != get_dma_ops(subdrv_dev)) {
 		DRM_DEV_ERROR(subdrv_dev, "Device %s lacks support for IOMMU\n",
@@ -92,7 +92,7 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev,
 	if (ret)
 		clear_dma_max_seg_size(subdrv_dev);
 
-	return 0;
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index fcee33a43aca..03be31427181 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -1498,7 +1498,6 @@ static int g2d_probe(struct platform_device *pdev)
 
 	g2d->irq = platform_get_irq(pdev, 0);
 	if (g2d->irq < 0) {
-		dev_err(dev, "failed to get irq\n");
 		ret = g2d->irq;
 		goto err_put_clk;
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index a86abc173605..3821ea76a703 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -269,8 +269,10 @@ static void mic_pre_enable(struct drm_bridge *bridge)
 		goto unlock;
 
 	ret = pm_runtime_get_sync(mic->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(mic->dev);
 		goto unlock;
+	}
 
 	mic_set_path(mic, 1);
 
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 95dd399aa9cc..68d7b1ce1b7c 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -1604,7 +1604,8 @@ static int hdmi_audio_hw_params(struct device *dev, void *data,
 	return 0;
 }
 
-static int hdmi_audio_digital_mute(struct device *dev, void *data, bool mute)
+static int hdmi_audio_mute(struct device *dev, void *data,
+			   bool mute, int direction)
 {
 	struct hdmi_context *hdata = dev_get_drvdata(dev);
 
@@ -1634,8 +1635,9 @@ static int hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf,
 static const struct hdmi_codec_ops audio_codec_ops = {
 	.hw_params = hdmi_audio_hw_params,
 	.audio_shutdown = hdmi_audio_shutdown,
-	.digital_mute = hdmi_audio_digital_mute,
+	.mute_stream = hdmi_audio_mute,
 	.get_eld = hdmi_audio_get_eld,
+	.no_capture_mute = 1,
 };
 
 static int hdmi_register_audio_device(struct hdmi_context *hdata)
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index a6fd0c29e5b8..544b9993c99e 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -307,8 +307,6 @@ static int hibmc_load(struct drm_device *dev)
 	/* reset all the states of crtc/plane/encoder/connector */
 	drm_mode_config_reset(dev);
 
-	drm_fbdev_generic_setup(dev, dev->mode_config.preferred_depth);
-
 	return 0;
 
 err:
@@ -355,6 +353,9 @@ static int hibmc_pci_probe(struct pci_dev *pdev,
 			  ret);
 		goto err_unload;
 	}
+
+	drm_fbdev_generic_setup(dev, dev->mode_config.preferred_depth);
+
 	return 0;
 
 err_unload:
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 9517f522dcb9..3010a4536da3 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1133,8 +1133,8 @@ static void tda998x_audio_shutdown(struct device *dev, void *data)
 	mutex_unlock(&priv->audio_mutex);
 }
 
-static int tda998x_audio_digital_mute(struct device *dev, void *data,
-				      bool enable)
+static int tda998x_audio_mute_stream(struct device *dev, void *data,
+				     bool enable, int direction)
 {
 	struct tda998x_priv *priv = dev_get_drvdata(dev);
 
@@ -1162,8 +1162,9 @@ static int tda998x_audio_get_eld(struct device *dev, void *data,
 static const struct hdmi_codec_ops audio_codec_ops = {
 	.hw_params = tda998x_audio_hw_params,
 	.audio_shutdown = tda998x_audio_shutdown,
-	.digital_mute = tda998x_audio_digital_mute,
+	.mute_stream = tda998x_audio_mute_stream,
 	.get_eld = tda998x_audio_get_eld,
+	.no_capture_mute = 1,
 };
 
 static int tda998x_audio_codec_init(struct tda998x_priv *priv,
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index aa22465bb56e..0575a1eea2a1 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2579,14 +2579,14 @@ static void icl_ddi_vswing_sequence(struct intel_encoder *encoder,
 
 static void
 tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, int link_clock,
-				u32 level)
+				u32 level, enum intel_output_type type)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port);
 	const struct tgl_dkl_phy_ddi_buf_trans *ddi_translations;
 	u32 n_entries, val, ln, dpcnt_mask, dpcnt_val;
 
-	if (encoder->type == INTEL_OUTPUT_HDMI) {
+	if (type == INTEL_OUTPUT_HDMI) {
 		n_entries = ARRAY_SIZE(tgl_dkl_phy_hdmi_ddi_trans);
 		ddi_translations = tgl_dkl_phy_hdmi_ddi_trans;
 	} else {
@@ -2638,7 +2638,7 @@ static void tgl_ddi_vswing_sequence(struct intel_encoder *encoder,
 	if (intel_phy_is_combo(dev_priv, phy))
 		icl_combo_phy_ddi_vswing_sequence(encoder, level, type);
 	else
-		tgl_dkl_phy_ddi_vswing_sequence(encoder, link_clock, level);
+		tgl_dkl_phy_ddi_vswing_sequence(encoder, link_clock, level, type);
 }
 
 static u32 translate_signal_level(struct intel_dp *intel_dp, int signal_levels)
@@ -2987,7 +2987,7 @@ icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
 		ln1 = intel_de_read(dev_priv, MG_DP_MODE(1, tc_port));
 	}
 
-	ln0 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X1_MODE);
+	ln0 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE);
 	ln1 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE);
 
 	/* DPPATC */
@@ -3472,7 +3472,9 @@ static void intel_ddi_post_disable_dp(struct intel_atomic_state *state,
 					  INTEL_OUTPUT_DP_MST);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 
-	intel_dp_set_infoframes(encoder, false, old_crtc_state, old_conn_state);
+	if (!is_mst)
+		intel_dp_set_infoframes(encoder, false,
+					old_crtc_state, old_conn_state);
 
 	/*
 	 * Power down sink before disabling the port, otherwise we end
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 9ea1a397d1b5..26996e1839e2 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3822,6 +3822,17 @@ skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state,
 	return true;
 }
 
+unsigned int
+intel_plane_fence_y_offset(const struct intel_plane_state *plane_state)
+{
+	int x = 0, y = 0;
+
+	intel_plane_adjust_aligned_offset(&x, &y, plane_state, 0,
+					  plane_state->color_plane[0].offset, 0);
+
+	return y;
+}
+
 static int skl_check_main_surface(struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev);
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index efb4da205ea2..3a06f72c9859 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -608,6 +608,7 @@ unsigned int i9xx_plane_max_stride(struct intel_plane *plane,
 				   u32 pixel_format, u64 modifier,
 				   unsigned int rotation);
 int bdw_get_pipemisc_bpp(struct intel_crtc *crtc);
+unsigned int intel_plane_fence_y_offset(const struct intel_plane_state *plane_state);
 
 struct intel_display_error_state *
 intel_display_capture_error_state(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index d18b406f2a7d..f29e51ce489c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -397,6 +397,14 @@ static void intel_mst_post_disable_dp(struct intel_atomic_state *state,
 	 */
 	drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port,
 				     false);
+
+	/*
+	 * BSpec 4287: disable DIP after the transcoder is disabled and before
+	 * the transcoder clock select is set to none.
+	 */
+	if (last_mst_stream)
+		intel_dp_set_infoframes(&intel_dig_port->base, false,
+					old_crtc_state, NULL);
 	/*
 	 * From TGL spec: "If multi-stream slave transcoder: Configure
 	 * Transcoder Clock Select to direct no clock to the transcoder"
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 1c26673acb2d..412572f88b67 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -48,19 +48,6 @@
 #include "intel_frontbuffer.h"
 
 /*
- * In some platforms where the CRTC's x:0/y:0 coordinates doesn't match the
- * frontbuffer's x:0/y:0 coordinates we lie to the hardware about the plane's
- * origin so the x and y offsets can actually fit the registers. As a
- * consequence, the fence doesn't really start exactly at the display plane
- * address we program because it starts at the real start of the buffer, so we
- * have to take this into consideration here.
- */
-static unsigned int get_crtc_fence_y_offset(struct intel_fbc *fbc)
-{
-	return fbc->state_cache.plane.y - fbc->state_cache.plane.adjusted_y;
-}
-
-/*
  * For SKL+, the plane source size used by the hardware is based on the value we
  * write to the PLANE_SIZE register. For BDW-, the hardware looks at the value
  * we wrote to PIPESRC.
@@ -141,7 +128,7 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv)
 			fbc_ctl2 |= FBC_CTL_CPU_FENCE;
 		intel_de_write(dev_priv, FBC_CONTROL2, fbc_ctl2);
 		intel_de_write(dev_priv, FBC_FENCE_OFF,
-			       params->crtc.fence_y_offset);
+			       params->fence_y_offset);
 	}
 
 	/* enable it... */
@@ -175,7 +162,7 @@ static void g4x_fbc_activate(struct drm_i915_private *dev_priv)
 	if (params->fence_id >= 0) {
 		dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fence_id;
 		intel_de_write(dev_priv, DPFC_FENCE_YOFF,
-			       params->crtc.fence_y_offset);
+			       params->fence_y_offset);
 	} else {
 		intel_de_write(dev_priv, DPFC_FENCE_YOFF, 0);
 	}
@@ -243,7 +230,7 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv)
 			intel_de_write(dev_priv, SNB_DPFC_CTL_SA,
 				       SNB_CPU_FENCE_ENABLE | params->fence_id);
 			intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET,
-				       params->crtc.fence_y_offset);
+				       params->fence_y_offset);
 		}
 	} else {
 		if (IS_GEN(dev_priv, 6)) {
@@ -253,7 +240,7 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv)
 	}
 
 	intel_de_write(dev_priv, ILK_DPFC_FENCE_YOFF,
-		       params->crtc.fence_y_offset);
+		       params->fence_y_offset);
 	/* enable it... */
 	intel_de_write(dev_priv, ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
@@ -320,7 +307,7 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv)
 		intel_de_write(dev_priv, SNB_DPFC_CTL_SA,
 			       SNB_CPU_FENCE_ENABLE | params->fence_id);
 		intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET,
-			       params->crtc.fence_y_offset);
+			       params->fence_y_offset);
 	} else if (dev_priv->ggtt.num_fences) {
 		intel_de_write(dev_priv, SNB_DPFC_CTL_SA, 0);
 		intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET, 0);
@@ -631,8 +618,8 @@ static bool rotation_is_valid(struct drm_i915_private *dev_priv,
 /*
  * For some reason, the hardware tracking starts looking at whatever we
  * programmed as the display plane base address register. It does not look at
- * the X and Y offset registers. That's why we look at the crtc->adjusted{x,y}
- * variables instead of just looking at the pipe/plane size.
+ * the X and Y offset registers. That's why we include the src x/y offsets
+ * instead of just looking at the plane size.
  */
 static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
 {
@@ -705,7 +692,6 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
 	cache->plane.src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 	cache->plane.adjusted_x = plane_state->color_plane[0].x;
 	cache->plane.adjusted_y = plane_state->color_plane[0].y;
-	cache->plane.y = plane_state->uapi.src.y1 >> 16;
 
 	cache->plane.pixel_blend_mode = plane_state->hw.pixel_blend_mode;
 
@@ -713,6 +699,8 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
 	cache->fb.stride = fb->pitches[0];
 	cache->fb.modifier = fb->modifier;
 
+	cache->fence_y_offset = intel_plane_fence_y_offset(plane_state);
+
 	drm_WARN_ON(&dev_priv->drm, plane_state->flags & PLANE_HAS_FENCE &&
 		    !plane_state->vma->fence);
 
@@ -731,6 +719,25 @@ static bool intel_fbc_cfb_size_changed(struct drm_i915_private *dev_priv)
 		fbc->compressed_fb.size * fbc->threshold;
 }
 
+static u16 intel_fbc_gen9_wa_cfb_stride(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_state_cache *cache = &fbc->state_cache;
+
+	if ((IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) &&
+	    cache->fb.modifier != I915_FORMAT_MOD_X_TILED)
+		return DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
+	else
+		return 0;
+}
+
+static bool intel_fbc_gen9_wa_cfb_stride_changed(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
+	return fbc->params.gen9_wa_cfb_stride != intel_fbc_gen9_wa_cfb_stride(dev_priv);
+}
+
 static bool intel_fbc_can_enable(struct drm_i915_private *dev_priv)
 {
 	struct intel_fbc *fbc = &dev_priv->fbc;
@@ -883,12 +890,13 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 	memset(params, 0, sizeof(*params));
 
 	params->fence_id = cache->fence_id;
+	params->fence_y_offset = cache->fence_y_offset;
 
 	params->crtc.pipe = crtc->pipe;
 	params->crtc.i9xx_plane = to_intel_plane(crtc->base.primary)->i9xx_plane;
-	params->crtc.fence_y_offset = get_crtc_fence_y_offset(fbc);
 
 	params->fb.format = cache->fb.format;
+	params->fb.modifier = cache->fb.modifier;
 	params->fb.stride = cache->fb.stride;
 
 	params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache);
@@ -918,6 +926,9 @@ static bool intel_fbc_can_flip_nuke(const struct intel_crtc_state *crtc_state)
 	if (params->fb.format != cache->fb.format)
 		return false;
 
+	if (params->fb.modifier != cache->fb.modifier)
+		return false;
+
 	if (params->fb.stride != cache->fb.stride)
 		return false;
 
@@ -1197,7 +1208,8 @@ void intel_fbc_enable(struct intel_atomic_state *state,
 
 	if (fbc->crtc) {
 		if (fbc->crtc != crtc ||
-		    !intel_fbc_cfb_size_changed(dev_priv))
+		    (!intel_fbc_cfb_size_changed(dev_priv) &&
+		     !intel_fbc_gen9_wa_cfb_stride_changed(dev_priv)))
 			goto out;
 
 		__intel_fbc_disable(dev_priv);
@@ -1219,12 +1231,7 @@ void intel_fbc_enable(struct intel_atomic_state *state,
 		goto out;
 	}
 
-	if ((IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) &&
-	    plane_state->hw.fb->modifier != I915_FORMAT_MOD_X_TILED)
-		cache->gen9_wa_cfb_stride =
-			DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
-	else
-		cache->gen9_wa_cfb_stride = 0;
+	cache->gen9_wa_cfb_stride = intel_fbc_gen9_wa_cfb_stride(dev_priv);
 
 	drm_dbg_kms(&dev_priv->drm, "Enabling FBC on pipe %c\n",
 		    pipe_name(crtc->pipe));
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 010f37240710..95b6d9457910 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2867,19 +2867,13 @@ intel_hdmi_connector_register(struct drm_connector *connector)
 	return ret;
 }
 
-static void intel_hdmi_destroy(struct drm_connector *connector)
+static void intel_hdmi_connector_unregister(struct drm_connector *connector)
 {
 	struct cec_notifier *n = intel_attached_hdmi(to_intel_connector(connector))->cec_notifier;
 
 	cec_notifier_conn_unregister(n);
 
-	intel_connector_destroy(connector);
-}
-
-static void intel_hdmi_connector_unregister(struct drm_connector *connector)
-{
 	intel_hdmi_remove_i2c_symlink(connector);
-
 	intel_connector_unregister(connector);
 }
 
@@ -2891,7 +2885,7 @@ static const struct drm_connector_funcs intel_hdmi_connector_funcs = {
 	.atomic_set_property = intel_digital_connector_atomic_set_property,
 	.late_register = intel_hdmi_connector_register,
 	.early_unregister = intel_hdmi_connector_unregister,
-	.destroy = intel_hdmi_destroy,
+	.destroy = intel_connector_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = intel_digital_connector_duplicate_state,
 };
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index e4aece20bc80..52db2bde44a3 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -204,25 +204,25 @@ static int __ring_active(struct intel_ring *ring)
 {
 	int err;
 
-	err = i915_active_acquire(&ring->vma->active);
+	err = intel_ring_pin(ring);
 	if (err)
 		return err;
 
-	err = intel_ring_pin(ring);
+	err = i915_active_acquire(&ring->vma->active);
 	if (err)
-		goto err_active;
+		goto err_pin;
 
 	return 0;
 
-err_active:
-	i915_active_release(&ring->vma->active);
+err_pin:
+	intel_ring_unpin(ring);
 	return err;
 }
 
 static void __ring_retire(struct intel_ring *ring)
 {
-	intel_ring_unpin(ring);
 	i915_active_release(&ring->vma->active);
+	intel_ring_unpin(ring);
 }
 
 __i915_active_call
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index da5b61085257..8691eb61e185 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -646,7 +646,7 @@ static int engine_setup_common(struct intel_engine_cs *engine)
 struct measure_breadcrumb {
 	struct i915_request rq;
 	struct intel_ring ring;
-	u32 cs[1024];
+	u32 cs[2048];
 };
 
 static int measure_breadcrumb_dw(struct intel_context *ce)
@@ -668,6 +668,8 @@ static int measure_breadcrumb_dw(struct intel_context *ce)
 
 	frame->ring.vaddr = frame->cs;
 	frame->ring.size = sizeof(frame->cs);
+	frame->ring.wrap =
+		BITS_PER_TYPE(frame->ring.size) - ilog2(frame->ring.size);
 	frame->ring.effective_size = frame->ring.size;
 	intel_ring_update_space(&frame->ring);
 	frame->rq.ring = &frame->ring;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 87e6c5bdd2dc..cb07e1d2a353 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1134,6 +1134,13 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 			list_move(&rq->sched.link, pl);
 			set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 
+			/* Check in case we rollback so far we wrap [size/2] */
+			if (intel_ring_direction(rq->ring,
+						 intel_ring_wrap(rq->ring,
+								 rq->tail),
+						 rq->ring->tail) > 0)
+				rq->context->lrc.desc |= CTX_DESC_FORCE_RESTORE;
+
 			active = rq;
 		} else {
 			struct intel_engine_cs *owner = rq->context->engine;
@@ -1498,8 +1505,9 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 * HW has a tendency to ignore us rewinding the TAIL to the end of
 	 * an earlier request.
 	 */
+	GEM_BUG_ON(ce->lrc_reg_state[CTX_RING_TAIL] != rq->ring->tail);
+	prev = rq->ring->tail;
 	tail = intel_ring_set_tail(rq->ring, rq->tail);
-	prev = ce->lrc_reg_state[CTX_RING_TAIL];
 	if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0))
 		desc |= CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state[CTX_RING_TAIL] = tail;
@@ -1895,7 +1903,8 @@ static void defer_active(struct intel_engine_cs *engine)
 
 static bool
 need_timeslice(const struct intel_engine_cs *engine,
-	       const struct i915_request *rq)
+	       const struct i915_request *rq,
+	       const struct rb_node *rb)
 {
 	int hint;
 
@@ -1903,9 +1912,28 @@ need_timeslice(const struct intel_engine_cs *engine,
 		return false;
 
 	hint = engine->execlists.queue_priority_hint;
+
+	if (rb) {
+		const struct virtual_engine *ve =
+			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
+		const struct intel_engine_cs *inflight =
+			intel_context_inflight(&ve->context);
+
+		if (!inflight || inflight == engine) {
+			struct i915_request *next;
+
+			rcu_read_lock();
+			next = READ_ONCE(ve->request);
+			if (next)
+				hint = max(hint, rq_prio(next));
+			rcu_read_unlock();
+		}
+	}
+
 	if (!list_is_last(&rq->sched.link, &engine->active.requests))
 		hint = max(hint, rq_prio(list_next_entry(rq, sched.link)));
 
+	GEM_BUG_ON(hint >= I915_PRIORITY_UNPREEMPTABLE);
 	return hint >= effective_prio(rq);
 }
 
@@ -1977,10 +2005,9 @@ static void set_timeslice(struct intel_engine_cs *engine)
 	set_timer_ms(&engine->execlists.timer, duration);
 }
 
-static void start_timeslice(struct intel_engine_cs *engine)
+static void start_timeslice(struct intel_engine_cs *engine, int prio)
 {
 	struct intel_engine_execlists *execlists = &engine->execlists;
-	const int prio = queue_prio(execlists);
 	unsigned long duration;
 
 	if (!intel_engine_has_timeslices(engine))
@@ -2140,7 +2167,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			__unwind_incomplete_requests(engine);
 
 			last = NULL;
-		} else if (need_timeslice(engine, last) &&
+		} else if (need_timeslice(engine, last, rb) &&
 			   timeslice_expired(execlists, last)) {
 			if (i915_request_completed(last)) {
 				tasklet_hi_schedule(&execlists->tasklet);
@@ -2188,7 +2215,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * Even if ELSP[1] is occupied and not worthy
 				 * of timeslices, our queue might be.
 				 */
-				start_timeslice(engine);
+				start_timeslice(engine, queue_prio(execlists));
 				return;
 			}
 		}
@@ -2223,7 +2250,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			if (last && !can_merge_rq(last, rq)) {
 				spin_unlock(&ve->base.active.lock);
-				start_timeslice(engine);
+				start_timeslice(engine, rq_prio(rq));
 				return; /* leave this for another sibling */
 			}
 
@@ -4739,6 +4766,14 @@ static int gen12_emit_flush(struct i915_request *request, u32 mode)
 	return 0;
 }
 
+static void assert_request_valid(struct i915_request *rq)
+{
+	struct intel_ring *ring __maybe_unused = rq->ring;
+
+	/* Can we unwind this request without appearing to go forwards? */
+	GEM_BUG_ON(intel_ring_direction(ring, rq->wa_tail, rq->head) <= 0);
+}
+
 /*
  * Reserve space for 2 NOOPs at the end of each request to be
  * used as a workaround for not being allowed to do lite
@@ -4751,6 +4786,9 @@ static u32 *gen8_emit_wa_tail(struct i915_request *request, u32 *cs)
 	*cs++ = MI_NOOP;
 	request->wa_tail = intel_ring_offset(request, cs);
 
+	/* Check that entire request is less than half the ring */
+	assert_request_valid(request);
+
 	return cs;
 }
 
@@ -5358,13 +5396,8 @@ static void virtual_engine_initial_hint(struct virtual_engine *ve)
 	 * typically be the first we inspect for submission.
 	 */
 	swp = prandom_u32_max(ve->num_siblings);
-	if (!swp)
-		return;
-
-	swap(ve->siblings[swp], ve->siblings[0]);
-	if (!intel_engine_has_relative_mmio(ve->siblings[0]))
-		virtual_update_register_offsets(ve->context.lrc_reg_state,
-						ve->siblings[0]);
+	if (swp)
+		swap(ve->siblings[swp], ve->siblings[0]);
 }
 
 static int virtual_context_alloc(struct intel_context *ce)
@@ -5377,15 +5410,9 @@ static int virtual_context_alloc(struct intel_context *ce)
 static int virtual_context_pin(struct intel_context *ce)
 {
 	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
-	int err;
 
 	/* Note: we must use a real engine class for setting up reg state */
-	err = __execlists_context_pin(ce, ve->siblings[0]);
-	if (err)
-		return err;
-
-	virtual_engine_initial_hint(ve);
-	return 0;
+	return __execlists_context_pin(ce, ve->siblings[0]);
 }
 
 static void virtual_context_enter(struct intel_context *ce)
@@ -5650,6 +5677,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
 	intel_engine_init_breadcrumbs(&ve->base);
 	intel_engine_init_execlists(&ve->base);
+	ve->base.breadcrumbs.irq_armed = true; /* fake HW, used for irq_work */
 
 	ve->base.cops = &virtual_context_ops;
 	ve->base.request_alloc = execlists_request_alloc;
@@ -5731,6 +5759,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 
 	ve->base.flags |= I915_ENGINE_IS_VIRTUAL;
 
+	virtual_engine_initial_hint(ve);
 	return &ve->context;
 
 err_put:
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
index 8cda1b7e17ba..bdb324167ef3 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -315,3 +315,7 @@ int intel_ring_cacheline_align(struct i915_request *rq)
 	GEM_BUG_ON(rq->ring->emit & (CACHELINE_BYTES - 1));
 	return 0;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_ring.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 90a2b9e399b0..85d2bef51524 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -179,6 +179,12 @@ wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 set)
 }
 
 static void
+wa_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr)
+{
+	wa_write_masked_or(wal, reg, clr, 0);
+}
+
+static void
 wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 {
 	wa_add(wal, reg, 0, _MASKED_BIT_ENABLE(val), val);
@@ -687,6 +693,227 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq)
 }
 
 static void
+gen4_gt_workarounds_init(struct drm_i915_private *i915,
+			 struct i915_wa_list *wal)
+{
+	/* WaDisable_RenderCache_OperationalFlush:gen4,ilk */
+	wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
+}
+
+static void
+g4x_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	gen4_gt_workarounds_init(i915, wal);
+
+	/* WaDisableRenderCachePipelinedFlush:g4x,ilk */
+	wa_masked_en(wal, CACHE_MODE_0, CM0_PIPELINED_RENDER_FLUSH_DISABLE);
+}
+
+static void
+ilk_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	g4x_gt_workarounds_init(i915, wal);
+
+	wa_masked_en(wal, _3D_CHICKEN2, _3D_CHICKEN2_WM_READ_PIPELINED);
+}
+
+static void
+snb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	/* WaDisableHiZPlanesWhenMSAAEnabled:snb */
+	wa_masked_en(wal,
+		     _3D_CHICKEN,
+		     _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB);
+
+	/* WaDisable_RenderCache_OperationalFlush:snb */
+	wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	wa_add(wal,
+	       GEN6_GT_MODE, 0,
+	       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
+	       GEN6_WIZ_HASHING_16x4);
+
+	wa_masked_dis(wal, CACHE_MODE_0, CM0_STC_EVICT_DISABLE_LRA_SNB);
+
+	wa_masked_en(wal,
+		     _3D_CHICKEN3,
+		     /* WaStripsFansDisableFastClipPerformanceFix:snb */
+		     _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL |
+		     /*
+		      * Bspec says:
+		      * "This bit must be set if 3DSTATE_CLIP clip mode is set
+		      * to normal and 3DSTATE_SF number of SF output attributes
+		      * is more than 16."
+		      */
+		   _3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH);
+}
+
+static void
+ivb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	/* WaDisableEarlyCull:ivb */
+	wa_masked_en(wal, _3D_CHICKEN3, _3D_CHICKEN_SF_DISABLE_OBJEND_CULL);
+
+	/* WaDisablePSDDualDispatchEnable:ivb */
+	if (IS_IVB_GT1(i915))
+		wa_masked_en(wal,
+			     GEN7_HALF_SLICE_CHICKEN1,
+			     GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
+
+	/* WaDisable_RenderCache_OperationalFlush:ivb */
+	wa_masked_dis(wal, CACHE_MODE_0_GEN7, RC_OP_FLUSH_ENABLE);
+
+	/* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
+	wa_masked_dis(wal,
+		      GEN7_COMMON_SLICE_CHICKEN1,
+		      GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
+
+	/* WaApplyL3ControlAndL3ChickenMode:ivb */
+	wa_write(wal, GEN7_L3CNTLREG1, GEN7_WA_FOR_GEN7_L3_CONTROL);
+	wa_write(wal, GEN7_L3_CHICKEN_MODE_REGISTER, GEN7_WA_L3_CHICKEN_MODE);
+
+	/* WaForceL3Serialization:ivb */
+	wa_write_clr(wal, GEN7_L3SQCREG4, L3SQ_URB_READ_CAM_MATCH_DISABLE);
+
+	/*
+	 * WaVSThreadDispatchOverride:ivb,vlv
+	 *
+	 * This actually overrides the dispatch
+	 * mode for all thread types.
+	 */
+	wa_write_masked_or(wal, GEN7_FF_THREAD_MODE,
+			   GEN7_FF_SCHED_MASK,
+			   GEN7_FF_TS_SCHED_HW |
+			   GEN7_FF_VS_SCHED_HW |
+			   GEN7_FF_DS_SCHED_HW);
+
+	if (0) { /* causes HiZ corruption on ivb:gt1 */
+		/* enable HiZ Raw Stall Optimization */
+		wa_masked_dis(wal, CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
+	}
+
+	/* WaDisable4x2SubspanOptimization:ivb */
+	wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	wa_add(wal, GEN7_GT_MODE, 0,
+	       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
+	       GEN6_WIZ_HASHING_16x4);
+}
+
+static void
+vlv_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	/* WaDisableEarlyCull:vlv */
+	wa_masked_en(wal, _3D_CHICKEN3, _3D_CHICKEN_SF_DISABLE_OBJEND_CULL);
+
+	/* WaPsdDispatchEnable:vlv */
+	/* WaDisablePSDDualDispatchEnable:vlv */
+	wa_masked_en(wal,
+		     GEN7_HALF_SLICE_CHICKEN1,
+		     GEN7_MAX_PS_THREAD_DEP |
+		     GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
+
+	/* WaDisable_RenderCache_OperationalFlush:vlv */
+	wa_masked_dis(wal, CACHE_MODE_0_GEN7, RC_OP_FLUSH_ENABLE);
+
+	/* WaForceL3Serialization:vlv */
+	wa_write_clr(wal, GEN7_L3SQCREG4, L3SQ_URB_READ_CAM_MATCH_DISABLE);
+
+	/*
+	 * WaVSThreadDispatchOverride:ivb,vlv
+	 *
+	 * This actually overrides the dispatch
+	 * mode for all thread types.
+	 */
+	wa_write_masked_or(wal,
+			   GEN7_FF_THREAD_MODE,
+			   GEN7_FF_SCHED_MASK,
+			   GEN7_FF_TS_SCHED_HW |
+			   GEN7_FF_VS_SCHED_HW |
+			   GEN7_FF_DS_SCHED_HW);
+
+	/*
+	 * BSpec says this must be set, even though
+	 * WaDisable4x2SubspanOptimization isn't listed for VLV.
+	 */
+	wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	wa_add(wal, GEN7_GT_MODE, 0,
+	       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
+	       GEN6_WIZ_HASHING_16x4);
+
+	/*
+	 * WaIncreaseL3CreditsForVLVB0:vlv
+	 * This is the hardware default actually.
+	 */
+	wa_write(wal, GEN7_L3SQCREG1, VLV_B0_WA_L3SQCREG1_VALUE);
+}
+
+static void
+hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	/* L3 caching of data atomics doesn't work -- disable it. */
+	wa_write(wal, HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
+
+	wa_add(wal,
+	       HSW_ROW_CHICKEN3, 0,
+	       _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE),
+		0 /* XXX does this reg exist? */);
+
+	/* WaVSRefCountFullforceMissDisable:hsw */
+	wa_write_clr(wal, GEN7_FF_THREAD_MODE, GEN7_FF_VS_REF_CNT_FFME);
+
+	wa_masked_dis(wal,
+		      CACHE_MODE_0_GEN7,
+		      /* WaDisable_RenderCache_OperationalFlush:hsw */
+		      RC_OP_FLUSH_ENABLE |
+		      /* enable HiZ Raw Stall Optimization */
+		      HIZ_RAW_STALL_OPT_DISABLE);
+
+	/* WaDisable4x2SubspanOptimization:hsw */
+	wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	wa_add(wal, GEN7_GT_MODE, 0,
+	       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
+	       GEN6_WIZ_HASHING_16x4);
+
+	/* WaSampleCChickenBitEnable:hsw */
+	wa_masked_en(wal, HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE);
+}
+
+static void
 gen9_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
 	/* WaDisableKillLogic:bxt,skl,kbl */
@@ -963,6 +1190,20 @@ gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		bxt_gt_workarounds_init(i915, wal);
 	else if (IS_SKYLAKE(i915))
 		skl_gt_workarounds_init(i915, wal);
+	else if (IS_HASWELL(i915))
+		hsw_gt_workarounds_init(i915, wal);
+	else if (IS_VALLEYVIEW(i915))
+		vlv_gt_workarounds_init(i915, wal);
+	else if (IS_IVYBRIDGE(i915))
+		ivb_gt_workarounds_init(i915, wal);
+	else if (IS_GEN(i915, 6))
+		snb_gt_workarounds_init(i915, wal);
+	else if (IS_GEN(i915, 5))
+		ilk_gt_workarounds_init(i915, wal);
+	else if (IS_G4X(i915))
+		g4x_gt_workarounds_init(i915, wal);
+	else if (IS_GEN(i915, 4))
+		gen4_gt_workarounds_init(i915, wal);
 	else if (INTEL_GEN(i915) <= 8)
 		return;
 	else
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 2b2efff6e19d..4aa4cc917d8b 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -310,22 +310,20 @@ static bool wait_until_running(struct hang *h, struct i915_request *rq)
 			  1000));
 }
 
-static void engine_heartbeat_disable(struct intel_engine_cs *engine,
-				     unsigned long *saved)
+static void engine_heartbeat_disable(struct intel_engine_cs *engine)
 {
-	*saved = engine->props.heartbeat_interval_ms;
 	engine->props.heartbeat_interval_ms = 0;
 
 	intel_engine_pm_get(engine);
 	intel_engine_park_heartbeat(engine);
 }
 
-static void engine_heartbeat_enable(struct intel_engine_cs *engine,
-				    unsigned long saved)
+static void engine_heartbeat_enable(struct intel_engine_cs *engine)
 {
 	intel_engine_pm_put(engine);
 
-	engine->props.heartbeat_interval_ms = saved;
+	engine->props.heartbeat_interval_ms =
+		engine->defaults.heartbeat_interval_ms;
 }
 
 static int igt_hang_sanitycheck(void *arg)
@@ -473,7 +471,6 @@ static int igt_reset_nop_engine(void *arg)
 	for_each_engine(engine, gt, id) {
 		unsigned int reset_count, reset_engine_count, count;
 		struct intel_context *ce;
-		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
 		int err;
 
@@ -485,7 +482,7 @@ static int igt_reset_nop_engine(void *arg)
 		reset_engine_count = i915_reset_engine_count(global, engine);
 		count = 0;
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			int i;
@@ -529,7 +526,7 @@ static int igt_reset_nop_engine(void *arg)
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 
 		pr_info("%s(%s): %d resets\n", __func__, engine->name, count);
 
@@ -564,7 +561,6 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 
 	for_each_engine(engine, gt, id) {
 		unsigned int reset_count, reset_engine_count;
-		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
 
 		if (active && !intel_engine_can_store_dword(engine))
@@ -580,7 +576,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 		reset_count = i915_reset_count(global);
 		reset_engine_count = i915_reset_engine_count(global, engine);
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			if (active) {
@@ -632,7 +628,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 
 		if (err)
 			break;
@@ -789,7 +785,6 @@ static int __igt_reset_engines(struct intel_gt *gt,
 		struct active_engine threads[I915_NUM_ENGINES] = {};
 		unsigned long device = i915_reset_count(global);
 		unsigned long count = 0, reported;
-		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
 
 		if (flags & TEST_ACTIVE &&
@@ -832,7 +827,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 
 		yield(); /* start all threads before we begin */
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			struct i915_request *rq = NULL;
@@ -906,7 +901,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 
 		pr_info("i915_reset_engine(%s:%s): %lu resets\n",
 			engine->name, test_name, count);
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 824f99c4cc7c..924bc01ef526 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -51,22 +51,20 @@ static struct i915_vma *create_scratch(struct intel_gt *gt)
 	return vma;
 }
 
-static void engine_heartbeat_disable(struct intel_engine_cs *engine,
-				     unsigned long *saved)
+static void engine_heartbeat_disable(struct intel_engine_cs *engine)
 {
-	*saved = engine->props.heartbeat_interval_ms;
 	engine->props.heartbeat_interval_ms = 0;
 
 	intel_engine_pm_get(engine);
 	intel_engine_park_heartbeat(engine);
 }
 
-static void engine_heartbeat_enable(struct intel_engine_cs *engine,
-				    unsigned long saved)
+static void engine_heartbeat_enable(struct intel_engine_cs *engine)
 {
 	intel_engine_pm_put(engine);
 
-	engine->props.heartbeat_interval_ms = saved;
+	engine->props.heartbeat_interval_ms =
+		engine->defaults.heartbeat_interval_ms;
 }
 
 static bool is_active(struct i915_request *rq)
@@ -224,7 +222,6 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 		struct intel_context *ce[2] = {};
 		struct i915_request *rq[2];
 		struct igt_live_test t;
-		unsigned long saved;
 		int n;
 
 		if (prio && !intel_engine_has_preemption(engine))
@@ -237,7 +234,7 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 			err = -EIO;
 			break;
 		}
-		engine_heartbeat_disable(engine, &saved);
+		engine_heartbeat_disable(engine);
 
 		for (n = 0; n < ARRAY_SIZE(ce); n++) {
 			struct intel_context *tmp;
@@ -345,7 +342,7 @@ err_ce:
 			intel_context_put(ce[n]);
 		}
 
-		engine_heartbeat_enable(engine, saved);
+		engine_heartbeat_enable(engine);
 		if (igt_live_test_end(&t))
 			err = -EIO;
 		if (err)
@@ -466,7 +463,6 @@ static int live_hold_reset(void *arg)
 
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
-		unsigned long heartbeat;
 		struct i915_request *rq;
 
 		ce = intel_context_create(engine);
@@ -475,7 +471,7 @@ static int live_hold_reset(void *arg)
 			break;
 		}
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 
 		rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK);
 		if (IS_ERR(rq)) {
@@ -535,7 +531,7 @@ static int live_hold_reset(void *arg)
 		i915_request_put(rq);
 
 out:
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 		intel_context_put(ce);
 		if (err)
 			break;
@@ -580,10 +576,9 @@ static int live_error_interrupt(void *arg)
 
 	for_each_engine(engine, gt, id) {
 		const struct error_phase *p;
-		unsigned long heartbeat;
 		int err = 0;
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 
 		for (p = phases; p->error[0] != GOOD; p++) {
 			struct i915_request *client[ARRAY_SIZE(phases->error)];
@@ -682,7 +677,7 @@ out:
 			}
 		}
 
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 		if (err) {
 			intel_gt_set_wedged(gt);
 			return err;
@@ -828,7 +823,7 @@ slice_semaphore_queue(struct intel_engine_cs *outer,
 		}
 	}
 
-	err = release_queue(outer, vma, n, INT_MAX);
+	err = release_queue(outer, vma, n, I915_PRIORITY_BARRIER);
 	if (err)
 		goto out;
 
@@ -895,16 +890,14 @@ static int live_timeslice_preempt(void *arg)
 		enum intel_engine_id id;
 
 		for_each_engine(engine, gt, id) {
-			unsigned long saved;
-
 			if (!intel_engine_has_preemption(engine))
 				continue;
 
 			memset(vaddr, 0, PAGE_SIZE);
 
-			engine_heartbeat_disable(engine, &saved);
+			engine_heartbeat_disable(engine);
 			err = slice_semaphore_queue(engine, vma, count);
-			engine_heartbeat_enable(engine, saved);
+			engine_heartbeat_enable(engine);
 			if (err)
 				goto err_pin;
 
@@ -1009,7 +1002,6 @@ static int live_timeslice_rewind(void *arg)
 		enum { X = 1, Z, Y };
 		struct i915_request *rq[3] = {};
 		struct intel_context *ce;
-		unsigned long heartbeat;
 		unsigned long timeslice;
 		int i, err = 0;
 		u32 *slot;
@@ -1028,7 +1020,7 @@ static int live_timeslice_rewind(void *arg)
 		 * Expect execution/evaluation order XZY
 		 */
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 		timeslice = xchg(&engine->props.timeslice_duration_ms, 1);
 
 		slot = memset32(engine->status_page.addr + 1000, 0, 4);
@@ -1122,7 +1114,7 @@ err:
 		wmb();
 
 		engine->props.timeslice_duration_ms = timeslice;
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 		for (i = 0; i < 3; i++)
 			i915_request_put(rq[i]);
 		if (igt_flush_test(gt->i915))
@@ -1202,12 +1194,11 @@ static int live_timeslice_queue(void *arg)
 			.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
 		};
 		struct i915_request *rq, *nop;
-		unsigned long saved;
 
 		if (!intel_engine_has_preemption(engine))
 			continue;
 
-		engine_heartbeat_disable(engine, &saved);
+		engine_heartbeat_disable(engine);
 		memset(vaddr, 0, PAGE_SIZE);
 
 		/* ELSP[0]: semaphore wait */
@@ -1284,7 +1275,7 @@ static int live_timeslice_queue(void *arg)
 err_rq:
 		i915_request_put(rq);
 err_heartbeat:
-		engine_heartbeat_enable(engine, saved);
+		engine_heartbeat_enable(engine);
 		if (err)
 			break;
 	}
@@ -1298,6 +1289,121 @@ err_obj:
 	return err;
 }
 
+static int live_timeslice_nopreempt(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	int err = 0;
+
+	/*
+	 * We should not timeslice into a request that is marked with
+	 * I915_REQUEST_NOPREEMPT.
+	 */
+	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+		return 0;
+
+	if (igt_spinner_init(&spin, gt))
+		return -ENOMEM;
+
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+		struct i915_request *rq;
+		unsigned long timeslice;
+
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			break;
+		}
+
+		engine_heartbeat_disable(engine);
+		timeslice = xchg(&engine->props.timeslice_duration_ms, 1);
+
+		/* Create an unpreemptible spinner */
+
+		rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK);
+		intel_context_put(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto out_heartbeat;
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		if (!igt_wait_for_spinner(&spin, rq)) {
+			i915_request_put(rq);
+			err = -ETIME;
+			goto out_spin;
+		}
+
+		set_bit(I915_FENCE_FLAG_NOPREEMPT, &rq->fence.flags);
+		i915_request_put(rq);
+
+		/* Followed by a maximum priority barrier (heartbeat) */
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(rq);
+			goto out_spin;
+		}
+
+		rq = intel_context_create_request(ce);
+		intel_context_put(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto out_spin;
+		}
+
+		rq->sched.attr.priority = I915_PRIORITY_BARRIER;
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		/*
+		 * Wait until the barrier is in ELSP, and we know timeslicing
+		 * will have been activated.
+		 */
+		if (wait_for_submit(engine, rq, HZ / 2)) {
+			i915_request_put(rq);
+			err = -ETIME;
+			goto out_spin;
+		}
+
+		/*
+		 * Since the ELSP[0] request is unpreemptible, it should not
+		 * allow the maximum priority barrier through. Wait long
+		 * enough to see if it is timesliced in by mistake.
+		 */
+		if (i915_request_wait(rq, 0, timeslice_threshold(engine)) >= 0) {
+			pr_err("%s: I915_PRIORITY_BARRIER request completed, bypassing no-preempt request\n",
+			       engine->name);
+			err = -EINVAL;
+		}
+		i915_request_put(rq);
+
+out_spin:
+		igt_spinner_end(&spin);
+out_heartbeat:
+		xchg(&engine->props.timeslice_duration_ms, timeslice);
+		engine_heartbeat_enable(engine);
+		if (err)
+			break;
+
+		if (igt_flush_test(gt->i915)) {
+			err = -EIO;
+			break;
+		}
+	}
+
+	igt_spinner_fini(&spin);
+	return err;
+}
+
 static int live_busywait_preempt(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -4153,7 +4259,6 @@ static int reset_virtual_engine(struct intel_gt *gt,
 {
 	struct intel_engine_cs *engine;
 	struct intel_context *ve;
-	unsigned long *heartbeat;
 	struct igt_spinner spin;
 	struct i915_request *rq;
 	unsigned int n;
@@ -4165,15 +4270,9 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	 * descendents are not executed while the capture is in progress.
 	 */
 
-	heartbeat = kmalloc_array(nsibling, sizeof(*heartbeat), GFP_KERNEL);
-	if (!heartbeat)
+	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
-	if (igt_spinner_init(&spin, gt)) {
-		err = -ENOMEM;
-		goto out_free;
-	}
-
 	ve = intel_execlists_create_virtual(siblings, nsibling);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
@@ -4181,7 +4280,7 @@ static int reset_virtual_engine(struct intel_gt *gt,
 	}
 
 	for (n = 0; n < nsibling; n++)
-		engine_heartbeat_disable(siblings[n], &heartbeat[n]);
+		engine_heartbeat_disable(siblings[n]);
 
 	rq = igt_spinner_create_request(&spin, ve, MI_ARB_CHECK);
 	if (IS_ERR(rq)) {
@@ -4252,13 +4351,11 @@ out_rq:
 	i915_request_put(rq);
 out_heartbeat:
 	for (n = 0; n < nsibling; n++)
-		engine_heartbeat_enable(siblings[n], heartbeat[n]);
+		engine_heartbeat_enable(siblings[n]);
 
 	intel_context_put(ve);
 out_spin:
 	igt_spinner_fini(&spin);
-out_free:
-	kfree(heartbeat);
 	return err;
 }
 
@@ -4314,6 +4411,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_timeslice_preempt),
 		SUBTEST(live_timeslice_rewind),
 		SUBTEST(live_timeslice_queue),
+		SUBTEST(live_timeslice_nopreempt),
 		SUBTEST(live_busywait_preempt),
 		SUBTEST(live_preempt),
 		SUBTEST(live_late_preempt),
@@ -4932,9 +5030,7 @@ static int live_lrc_gpr(void *arg)
 		return PTR_ERR(scratch);
 
 	for_each_engine(engine, gt, id) {
-		unsigned long heartbeat;
-
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 
 		err = __live_lrc_gpr(engine, scratch, false);
 		if (err)
@@ -4945,7 +5041,7 @@ static int live_lrc_gpr(void *arg)
 			goto err;
 
 err:
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 		if (igt_flush_test(gt->i915))
 			err = -EIO;
 		if (err)
@@ -5092,10 +5188,9 @@ static int live_lrc_timestamp(void *arg)
 	 */
 
 	for_each_engine(data.engine, gt, id) {
-		unsigned long heartbeat;
 		int i, err = 0;
 
-		engine_heartbeat_disable(data.engine, &heartbeat);
+		engine_heartbeat_disable(data.engine);
 
 		for (i = 0; i < ARRAY_SIZE(data.ce); i++) {
 			struct intel_context *tmp;
@@ -5128,7 +5223,7 @@ static int live_lrc_timestamp(void *arg)
 		}
 
 err:
-		engine_heartbeat_enable(data.engine, heartbeat);
+		engine_heartbeat_enable(data.engine);
 		for (i = 0; i < ARRAY_SIZE(data.ce); i++) {
 			if (!data.ce[i])
 				break;
diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c
index 8831ffee2061..63f87d8608c3 100644
--- a/drivers/gpu/drm/i915/gt/selftest_mocs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c
@@ -18,6 +18,20 @@ struct live_mocs {
 	void *vaddr;
 };
 
+static struct intel_context *mocs_context_create(struct intel_engine_cs *engine)
+{
+	struct intel_context *ce;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return ce;
+
+	/* We build large requests to read the registers from the ring */
+	ce->ring = __intel_context_ring_size(SZ_16K);
+
+	return ce;
+}
+
 static int request_add_sync(struct i915_request *rq, int err)
 {
 	i915_request_get(rq);
@@ -301,7 +315,7 @@ static int live_mocs_clean(void *arg)
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
 
-		ce = intel_context_create(engine);
+		ce = mocs_context_create(engine);
 		if (IS_ERR(ce)) {
 			err = PTR_ERR(ce);
 			break;
@@ -395,7 +409,7 @@ static int live_mocs_reset(void *arg)
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
 
-		ce = intel_context_create(engine);
+		ce = mocs_context_create(engine);
 		if (IS_ERR(ce)) {
 			err = PTR_ERR(ce);
 			break;
diff --git a/drivers/gpu/drm/i915/gt/selftest_ring.c b/drivers/gpu/drm/i915/gt/selftest_ring.c
new file mode 100644
index 000000000000..2a8c534dc125
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_ring.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+static struct intel_ring *mock_ring(unsigned long sz)
+{
+	struct intel_ring *ring;
+
+	ring = kzalloc(sizeof(*ring) + sz, GFP_KERNEL);
+	if (!ring)
+		return NULL;
+
+	kref_init(&ring->ref);
+	ring->size = sz;
+	ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(sz);
+	ring->effective_size = sz;
+	ring->vaddr = (void *)(ring + 1);
+	atomic_set(&ring->pin_count, 1);
+
+	intel_ring_update_space(ring);
+
+	return ring;
+}
+
+static void mock_ring_free(struct intel_ring *ring)
+{
+	kfree(ring);
+}
+
+static int check_ring_direction(struct intel_ring *ring,
+				u32 next, u32 prev,
+				int expected)
+{
+	int result;
+
+	result = intel_ring_direction(ring, next, prev);
+	if (result < 0)
+		result = -1;
+	else if (result > 0)
+		result = 1;
+
+	if (result != expected) {
+		pr_err("intel_ring_direction(%u, %u):%d != %d\n",
+		       next, prev, result, expected);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int check_ring_step(struct intel_ring *ring, u32 x, u32 step)
+{
+	u32 prev = x, next = intel_ring_wrap(ring, x + step);
+	int err = 0;
+
+	err |= check_ring_direction(ring, next, next,  0);
+	err |= check_ring_direction(ring, prev, prev,  0);
+	err |= check_ring_direction(ring, next, prev,  1);
+	err |= check_ring_direction(ring, prev, next, -1);
+
+	return err;
+}
+
+static int check_ring_offset(struct intel_ring *ring, u32 x, u32 step)
+{
+	int err = 0;
+
+	err |= check_ring_step(ring, x, step);
+	err |= check_ring_step(ring, intel_ring_wrap(ring, x + 1), step);
+	err |= check_ring_step(ring, intel_ring_wrap(ring, x - 1), step);
+
+	return err;
+}
+
+static int igt_ring_direction(void *dummy)
+{
+	struct intel_ring *ring;
+	unsigned int half = 2048;
+	int step, err = 0;
+
+	ring = mock_ring(2 * half);
+	if (!ring)
+		return -ENOMEM;
+
+	GEM_BUG_ON(ring->size != 2 * half);
+
+	/* Precision of wrap detection is limited to ring->size / 2 */
+	for (step = 1; step < half; step <<= 1) {
+		err |= check_ring_offset(ring, 0, step);
+		err |= check_ring_offset(ring, half, step);
+	}
+	err |= check_ring_step(ring, 0, half - 64);
+
+	/* And check unwrapped handling for good measure */
+	err |= check_ring_offset(ring, 0, 2 * half + 64);
+	err |= check_ring_offset(ring, 3 * half, 1);
+
+	mock_ring_free(ring);
+	return err;
+}
+
+int intel_ring_mock_selftests(void)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_ring_direction),
+	};
+
+	return i915_subtests(tests, NULL);
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index 6275d69aa9cc..c91981e75ebf 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -20,24 +20,20 @@
 /* Try to isolate the impact of cstates from determing frequency response */
 #define CPU_LATENCY 0 /* -1 to disable pm_qos, 0 to disable cstates */
 
-static unsigned long engine_heartbeat_disable(struct intel_engine_cs *engine)
+static void engine_heartbeat_disable(struct intel_engine_cs *engine)
 {
-	unsigned long old;
-
-	old = fetch_and_zero(&engine->props.heartbeat_interval_ms);
+	engine->props.heartbeat_interval_ms = 0;
 
 	intel_engine_pm_get(engine);
 	intel_engine_park_heartbeat(engine);
-
-	return old;
 }
 
-static void engine_heartbeat_enable(struct intel_engine_cs *engine,
-				    unsigned long saved)
+static void engine_heartbeat_enable(struct intel_engine_cs *engine)
 {
 	intel_engine_pm_put(engine);
 
-	engine->props.heartbeat_interval_ms = saved;
+	engine->props.heartbeat_interval_ms =
+		engine->defaults.heartbeat_interval_ms;
 }
 
 static void dummy_rps_work(struct work_struct *wrk)
@@ -48,9 +44,9 @@ static int cmp_u64(const void *A, const void *B)
 {
 	const u64 *a = A, *b = B;
 
-	if (a < b)
+	if (*a < *b)
 		return -1;
-	else if (a > b)
+	else if (*a > *b)
 		return 1;
 	else
 		return 0;
@@ -60,9 +56,9 @@ static int cmp_u32(const void *A, const void *B)
 {
 	const u32 *a = A, *b = B;
 
-	if (a < b)
+	if (*a < *b)
 		return -1;
-	else if (a > b)
+	else if (*a > *b)
 		return 1;
 	else
 		return 0;
@@ -246,7 +242,6 @@ int live_rps_clock_interval(void *arg)
 	intel_gt_check_clock_frequency(gt);
 
 	for_each_engine(engine, gt, id) {
-		unsigned long saved_heartbeat;
 		struct i915_request *rq;
 		u32 cycles;
 		u64 dt;
@@ -254,13 +249,13 @@ int live_rps_clock_interval(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		saved_heartbeat = engine_heartbeat_disable(engine);
+		engine_heartbeat_disable(engine);
 
 		rq = igt_spinner_create_request(&spin,
 						engine->kernel_context,
 						MI_NOOP);
 		if (IS_ERR(rq)) {
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			err = PTR_ERR(rq);
 			break;
 		}
@@ -271,7 +266,7 @@ int live_rps_clock_interval(void *arg)
 			pr_err("%s: RPS spinner did not start\n",
 			       engine->name);
 			igt_spinner_end(&spin);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			intel_gt_set_wedged(engine->gt);
 			err = -EIO;
 			break;
@@ -327,7 +322,7 @@ int live_rps_clock_interval(void *arg)
 		intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
 
 		igt_spinner_end(&spin);
-		engine_heartbeat_enable(engine, saved_heartbeat);
+		engine_heartbeat_enable(engine);
 
 		if (err == 0) {
 			u64 time = intel_gt_pm_interval_to_ns(gt, cycles);
@@ -405,7 +400,6 @@ int live_rps_control(void *arg)
 
 	intel_gt_pm_get(gt);
 	for_each_engine(engine, gt, id) {
-		unsigned long saved_heartbeat;
 		struct i915_request *rq;
 		ktime_t min_dt, max_dt;
 		int f, limit;
@@ -414,7 +408,7 @@ int live_rps_control(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		saved_heartbeat = engine_heartbeat_disable(engine);
+		engine_heartbeat_disable(engine);
 
 		rq = igt_spinner_create_request(&spin,
 						engine->kernel_context,
@@ -430,7 +424,7 @@ int live_rps_control(void *arg)
 			pr_err("%s: RPS spinner did not start\n",
 			       engine->name);
 			igt_spinner_end(&spin);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			intel_gt_set_wedged(engine->gt);
 			err = -EIO;
 			break;
@@ -440,7 +434,7 @@ int live_rps_control(void *arg)
 			pr_err("%s: could not set minimum frequency [%x], only %x!\n",
 			       engine->name, rps->min_freq, read_cagf(rps));
 			igt_spinner_end(&spin);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			show_pstate_limits(rps);
 			err = -EINVAL;
 			break;
@@ -457,7 +451,7 @@ int live_rps_control(void *arg)
 			pr_err("%s: could not restore minimum frequency [%x], only %x!\n",
 			       engine->name, rps->min_freq, read_cagf(rps));
 			igt_spinner_end(&spin);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			show_pstate_limits(rps);
 			err = -EINVAL;
 			break;
@@ -472,7 +466,7 @@ int live_rps_control(void *arg)
 		min_dt = ktime_sub(ktime_get(), min_dt);
 
 		igt_spinner_end(&spin);
-		engine_heartbeat_enable(engine, saved_heartbeat);
+		engine_heartbeat_enable(engine);
 
 		pr_info("%s: range:[%x:%uMHz, %x:%uMHz] limit:[%x:%uMHz], %x:%x response %lluns:%lluns\n",
 			engine->name,
@@ -635,7 +629,6 @@ int live_rps_frequency_cs(void *arg)
 	rps->work.func = dummy_rps_work;
 
 	for_each_engine(engine, gt, id) {
-		unsigned long saved_heartbeat;
 		struct i915_request *rq;
 		struct i915_vma *vma;
 		u32 *cancel, *cntr;
@@ -644,14 +637,14 @@ int live_rps_frequency_cs(void *arg)
 			int freq;
 		} min, max;
 
-		saved_heartbeat = engine_heartbeat_disable(engine);
+		engine_heartbeat_disable(engine);
 
 		vma = create_spin_counter(engine,
 					  engine->kernel_context->vm, false,
 					  &cancel, &cntr);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			break;
 		}
 
@@ -732,7 +725,7 @@ err_vma:
 		i915_vma_unpin(vma);
 		i915_vma_put(vma);
 
-		engine_heartbeat_enable(engine, saved_heartbeat);
+		engine_heartbeat_enable(engine);
 		if (igt_flush_test(gt->i915))
 			err = -EIO;
 		if (err)
@@ -778,7 +771,6 @@ int live_rps_frequency_srm(void *arg)
 	rps->work.func = dummy_rps_work;
 
 	for_each_engine(engine, gt, id) {
-		unsigned long saved_heartbeat;
 		struct i915_request *rq;
 		struct i915_vma *vma;
 		u32 *cancel, *cntr;
@@ -787,14 +779,14 @@ int live_rps_frequency_srm(void *arg)
 			int freq;
 		} min, max;
 
-		saved_heartbeat = engine_heartbeat_disable(engine);
+		engine_heartbeat_disable(engine);
 
 		vma = create_spin_counter(engine,
 					  engine->kernel_context->vm, true,
 					  &cancel, &cntr);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			break;
 		}
 
@@ -874,7 +866,7 @@ err_vma:
 		i915_vma_unpin(vma);
 		i915_vma_put(vma);
 
-		engine_heartbeat_enable(engine, saved_heartbeat);
+		engine_heartbeat_enable(engine);
 		if (igt_flush_test(gt->i915))
 			err = -EIO;
 		if (err)
@@ -1066,16 +1058,14 @@ int live_rps_interrupt(void *arg)
 	for_each_engine(engine, gt, id) {
 		/* Keep the engine busy with a spinner; expect an UP! */
 		if (pm_events & GEN6_PM_RP_UP_THRESHOLD) {
-			unsigned long saved_heartbeat;
-
 			intel_gt_pm_wait_for_idle(engine->gt);
 			GEM_BUG_ON(intel_rps_is_active(rps));
 
-			saved_heartbeat = engine_heartbeat_disable(engine);
+			engine_heartbeat_disable(engine);
 
 			err = __rps_up_interrupt(rps, engine, &spin);
 
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			if (err)
 				goto out;
 
@@ -1084,15 +1074,13 @@ int live_rps_interrupt(void *arg)
 
 		/* Keep the engine awake but idle and check for DOWN */
 		if (pm_events & GEN6_PM_RP_DOWN_THRESHOLD) {
-			unsigned long saved_heartbeat;
-
-			saved_heartbeat = engine_heartbeat_disable(engine);
+			engine_heartbeat_disable(engine);
 			intel_rc6_disable(&gt->rc6);
 
 			err = __rps_down_interrupt(rps, engine);
 
 			intel_rc6_enable(&gt->rc6);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			if (err)
 				goto out;
 		}
@@ -1168,7 +1156,6 @@ int live_rps_power(void *arg)
 	rps->work.func = dummy_rps_work;
 
 	for_each_engine(engine, gt, id) {
-		unsigned long saved_heartbeat;
 		struct i915_request *rq;
 		struct {
 			u64 power;
@@ -1178,13 +1165,13 @@ int live_rps_power(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		saved_heartbeat = engine_heartbeat_disable(engine);
+		engine_heartbeat_disable(engine);
 
 		rq = igt_spinner_create_request(&spin,
 						engine->kernel_context,
 						MI_NOOP);
 		if (IS_ERR(rq)) {
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			err = PTR_ERR(rq);
 			break;
 		}
@@ -1195,7 +1182,7 @@ int live_rps_power(void *arg)
 			pr_err("%s: RPS spinner did not start\n",
 			       engine->name);
 			igt_spinner_end(&spin);
-			engine_heartbeat_enable(engine, saved_heartbeat);
+			engine_heartbeat_enable(engine);
 			intel_gt_set_wedged(engine->gt);
 			err = -EIO;
 			break;
@@ -1208,7 +1195,7 @@ int live_rps_power(void *arg)
 		min.power = measure_power_at(rps, &min.freq);
 
 		igt_spinner_end(&spin);
-		engine_heartbeat_enable(engine, saved_heartbeat);
+		engine_heartbeat_enable(engine);
 
 		pr_info("%s: min:%llumW @ %uMHz, max:%llumW @ %uMHz\n",
 			engine->name,
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index c2578a0f2f14..ef1c35073dc0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -751,22 +751,20 @@ out_free:
 	return err;
 }
 
-static void engine_heartbeat_disable(struct intel_engine_cs *engine,
-				     unsigned long *saved)
+static void engine_heartbeat_disable(struct intel_engine_cs *engine)
 {
-	*saved = engine->props.heartbeat_interval_ms;
 	engine->props.heartbeat_interval_ms = 0;
 
 	intel_engine_pm_get(engine);
 	intel_engine_park_heartbeat(engine);
 }
 
-static void engine_heartbeat_enable(struct intel_engine_cs *engine,
-				    unsigned long saved)
+static void engine_heartbeat_enable(struct intel_engine_cs *engine)
 {
 	intel_engine_pm_put(engine);
 
-	engine->props.heartbeat_interval_ms = saved;
+	engine->props.heartbeat_interval_ms =
+		engine->defaults.heartbeat_interval_ms;
 }
 
 static int live_hwsp_rollover_kernel(void *arg)
@@ -785,10 +783,9 @@ static int live_hwsp_rollover_kernel(void *arg)
 		struct intel_context *ce = engine->kernel_context;
 		struct intel_timeline *tl = ce->timeline;
 		struct i915_request *rq[3] = {};
-		unsigned long heartbeat;
 		int i;
 
-		engine_heartbeat_disable(engine, &heartbeat);
+		engine_heartbeat_disable(engine);
 		if (intel_gt_wait_for_idle(gt, HZ / 2)) {
 			err = -EIO;
 			goto out;
@@ -839,7 +836,7 @@ static int live_hwsp_rollover_kernel(void *arg)
 out:
 		for (i = 0; i < ARRAY_SIZE(rq); i++)
 			i915_request_put(rq[i]);
-		engine_heartbeat_enable(engine, heartbeat);
+		engine_heartbeat_enable(engine);
 		if (err)
 			break;
 	}
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 5ed323254ee1..32785463ec9e 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -623,6 +623,8 @@ err_request:
 				err = -EINVAL;
 				goto out_unpin;
 			}
+		} else {
+			rsvd = 0;
 		}
 
 		expect = results[0];
diff --git a/drivers/gpu/drm/i915/gt/shaders/README b/drivers/gpu/drm/i915/gt/shaders/README
new file mode 100644
index 000000000000..e7e96d7073c7
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shaders/README
@@ -0,0 +1,46 @@
+ASM sources for auto generated shaders
+======================================
+
+The i915/gt/hsw_clear_kernel.c and i915/gt/ivb_clear_kernel.c files contain
+pre-compiled batch chunks that will clear any residual render cache during
+context switch.
+
+They are generated from their respective platform ASM files present on
+i915/gt/shaders/clear_kernel directory.
+
+The generated .c files should never be modified directly. Instead, any modification
+needs to be done on the on their respective ASM files and build instructions below
+needes to be followed.
+
+Building
+========
+
+Environment
+-----------
+
+IGT GPU tool scripts and the Mesa's i965 instruction assembler tool are used
+on building.
+
+Please make sure your Mesa tool is compiled with "-Dtools=intel" and
+"-Ddri-drivers=i965", and run this script from IGT source root directory"
+
+The instructions bellow assume:
+    *  IGT gpu tools source code is located on your home directory (~) as ~/igt
+    *  Mesa source code is located on your home directory (~) as ~/mesa
+       and built under the ~/mesa/build directory
+    *  Linux kernel source code is under your home directory (~) as ~/linux
+
+Instructions
+------------
+
+~ $ cp ~/linux/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm \
+       ~/igt/lib/i915/shaders/clear_kernel/ivb.asm
+~ $ cd ~/igt
+igt $ ./scripts/generate_clear_kernel.sh -g ivb \
+      -m ~/mesa/build/src/intel/tools/i965_asm
+
+~ $ cp ~/linux/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm \
+    ~/igt/lib/i915/shaders/clear_kernel/hsw.asm
+~ $ cd ~/igt
+igt $ ./scripts/generate_clear_kernel.sh -g hsw \
+      -m ~/mesa/build/src/intel/tools/i965_asm
\ No newline at end of file
diff --git a/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm
new file mode 100644
index 000000000000..5fdf384bb621
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+/*
+ * Kernel for PAVP buffer clear.
+ *
+ *	1. Clear all 64 GRF registers assigned to the kernel with designated value;
+ *	2. Write 32x16 block of all "0" to render target buffer which indirectly clears
+ *	   512 bytes of Render Cache.
+ */
+
+/* Store designated "clear GRF" value */
+mov(1)          f0.1<1>UW       g1.2<0,1,0>UW                   { align1 1N };
+
+/**
+ * Curbe Format
+ *
+ * DW 1.0 - Block Offset to write Render Cache
+ * DW 1.1 [15:0] - Clear Word
+ * DW 1.2 - Delay iterations
+ * DW 1.3 - Enable Instrumentation (only for debug)
+ * DW 1.4 - Rsvd (intended for context ID)
+ * DW 1.5 - [31:16]:SliceCount, [15:0]:SubSlicePerSliceCount
+ * DW 1.6 - Rsvd MBZ (intended for Enable Wait on Total Thread Count)
+ * DW 1.7 - Rsvd MBZ (inteded for Total Thread Count)
+ *
+ * Binding Table
+ *
+ * BTI 0: 2D Surface to help clear L3 (Render/Data Cache)
+ * BTI 1: Wait/Instrumentation Buffer
+ *  Size : (SliceCount * SubSliceCount  * 16 EUs/SubSlice) rows * (16 threads/EU) cols (Format R32_UINT)
+ *         Expected to be initialized to 0 by driver/another kernel
+ *  Layout:
+ *          RowN: Histogram for EU-N: (SliceID*SubSlicePerSliceCount + SSID)*16 + EUID [assume max 16 EUs / SS]
+ *          Col-k[DW-k]: Threads Executed on ThreadID-k for EU-N
+ */
+add(1)          g1.2<1>UD       g1.2<0,1,0>UD   0x00000001UD    { align1 1N }; /* Loop count to delay kernel: Init to (g1.2 + 1) */
+cmp.z.f0.0(1)   null<1>UD       g1.3<0,1,0>UD   0x00000000UD    { align1 1N };
+(+f0.0) jmpi(1) 352D                                            { align1 WE_all 1N };
+
+/**
+ * State Register has info on where this thread is running
+ *	IVB: sr0.0 :: [15:13]: MBZ, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ *	HSW: sr0.0 :: 15: MBZ, [14:13]: SliceID, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ */
+mov(8)          g3<1>UD         0x00000000UD                    { align1 1Q };
+shr(1)          g3<1>D          sr0<0,1,0>D     12D             { align1 1N };
+and(1)          g3<1>D          g3<0,1,0>D      1D              { align1 1N }; /* g3 has HSID */
+shr(1)          g3.1<1>D        sr0<0,1,0>D     13D             { align1 1N };
+and(1)          g3.1<1>D        g3.1<0,1,0>D    3D              { align1 1N }; /* g3.1 has sliceID */
+mul(1)          g3.5<1>D        g3.1<0,1,0>D    g1.10<0,1,0>UW  { align1 1N };
+add(1)          g3<1>D          g3<0,1,0>D      g3.5<0,1,0>D    { align1 1N }; /* g3 = sliceID * SubSlicePerSliceCount + HSID */
+shr(1)          g3.2<1>D        sr0<0,1,0>D     8D              { align1 1N };
+and(1)          g3.2<1>D        g3.2<0,1,0>D    15D             { align1 1N }; /* g3.2 = EUID */
+mul(1)          g3.4<1>D        g3<0,1,0>D      16D             { align1 1N };
+add(1)          g3.2<1>D        g3.2<0,1,0>D    g3.4<0,1,0>D    { align1 1N }; /* g3.2 now points to EU row number (Y-pixel = V address )  in instrumentation surf */
+
+mov(8)          g5<1>UD         0x00000000UD                    { align1 1Q };
+and(1)          g3.3<1>D        sr0<0,1,0>D     7D              { align1 1N };
+mul(1)          g3.3<1>D        g3.3<0,1,0>D    4D              { align1 1N };
+
+mov(8)          g4<1>UD         g0<8,8,1>UD                     { align1 1Q }; /* Initialize message header with g0 */
+mov(1)          g4<1>UD         g3.3<0,1,0>UD                   { align1 1N }; /* Block offset */
+mov(1)          g4.1<1>UD       g3.2<0,1,0>UD                   { align1 1N }; /* Block offset */
+mov(1)          g4.2<1>UD       0x00000003UD                    { align1 1N }; /* Block size (1 row x 4 bytes) */
+and(1)          g4.3<1>UD       g4.3<0,1,0>UW   0xffffffffUD    { align1 1N };
+
+/* Media block read to fetch current value at specified location in instrumentation buffer */
+sendc(8)        g5<1>UD         g4<8,8,1>F      0x02190001
+
+                            render MsgDesc: media block read MsgCtrl = 0x0 Surface = 1 mlen 1 rlen 1 { align1 1Q };
+add(1)          g5<1>D          g5<0,1,0>D      1D              { align1 1N };
+
+/* Media block write for updated value at specified location in instrumentation buffer */
+sendc(8)        g5<1>UD         g4<8,8,1>F      0x040a8001
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 1 mlen 2 rlen 0 { align1 1Q };
+
+/* Delay thread for specified parameter */
+add.nz.f0.0(1)  g1.2<1>UD       g1.2<0,1,0>UD   -1D             { align1 1N };
+(+f0.0) jmpi(1) -32D                                            { align1 WE_all 1N };
+
+/* Store designated "clear GRF" value */
+mov(1)          f0.1<1>UW       g1.2<0,1,0>UW                   { align1 1N };
+
+/* Initialize looping parameters */
+mov(1)          a0<1>D          0D                              { align1 1N }; /* Initialize a0.0:w=0 */
+mov(1)          a0.4<1>W        127W                            { align1 1N }; /* Loop count. Each loop contains 16 GRF's */
+
+/* Write 32x16 all "0" block */
+mov(8)          g2<1>UD         g0<8,8,1>UD                     { align1 1Q };
+mov(8)          g127<1>UD       g0<8,8,1>UD                     { align1 1Q };
+mov(2)          g2<1>UD         g1<2,2,1>UW                     { align1 1N };
+mov(1)          g2.2<1>UD       0x000f000fUD                    { align1 1N }; /* Block size (16x16) */
+and(1)          g2.3<1>UD       g2.3<0,1,0>UW   0xffffffefUD    { align1 1N };
+mov(16)         g3<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g4<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g5<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g6<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g7<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g8<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g9<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g10<1>UD        0x00000000UD                    { align1 1H };
+sendc(8)        null<1>UD       g2<8,8,1>F      0x120a8000
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+add(1)          g2<1>UD         g1<0,1,0>UW     0x0010UW        { align1 1N };
+sendc(8)        null<1>UD       g2<8,8,1>F      0x120a8000
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+
+/* Now, clear all GRF registers */
+add.nz.f0.0(1)  a0.4<1>W        a0.4<0,1,0>W    -1W             { align1 1N };
+mov(16)         g[a0]<1>UW      f0.1<0,1,0>UW                   { align1 1H };
+add(1)          a0<1>D          a0<0,1,0>D      32D             { align1 1N };
+(+f0.0) jmpi(1) -64D                                            { align1 WE_all 1N };
+
+/* Terminante the thread */
+sendc(8)        null<1>UD       g127<8,8,1>F    0x82000010
+                            thread_spawner MsgDesc: mlen 1 rlen 0           { align1 1Q EOT };
diff --git a/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm
new file mode 100644
index 000000000000..97c7ac9e3854
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+/*
+ * Kernel for PAVP buffer clear.
+ *
+ *	1. Clear all 64 GRF registers assigned to the kernel with designated value;
+ *	2. Write 32x16 block of all "0" to render target buffer which indirectly clears
+ *	   512 bytes of Render Cache.
+ */
+
+/* Store designated "clear GRF" value */
+mov(1)          f0.1<1>UW       g1.2<0,1,0>UW                   { align1 1N };
+
+/**
+ * Curbe Format
+ *
+ * DW 1.0 - Block Offset to write Render Cache
+ * DW 1.1 [15:0] - Clear Word
+ * DW 1.2 - Delay iterations
+ * DW 1.3 - Enable Instrumentation (only for debug)
+ * DW 1.4 - Rsvd (intended for context ID)
+ * DW 1.5 - [31:16]:SliceCount, [15:0]:SubSlicePerSliceCount
+ * DW 1.6 - Rsvd MBZ (intended for Enable Wait on Total Thread Count)
+ * DW 1.7 - Rsvd MBZ (inteded for Total Thread Count)
+ *
+ * Binding Table
+ *
+ * BTI 0: 2D Surface to help clear L3 (Render/Data Cache)
+ * BTI 1: Wait/Instrumentation Buffer
+ *  Size : (SliceCount * SubSliceCount  * 16 EUs/SubSlice) rows * (16 threads/EU) cols (Format R32_UINT)
+ *         Expected to be initialized to 0 by driver/another kernel
+ *  Layout :
+ *           RowN: Histogram for EU-N: (SliceID*SubSlicePerSliceCount + SSID)*16 + EUID [assume max 16 EUs / SS]
+ *           Col-k[DW-k]: Threads Executed on ThreadID-k for EU-N
+ */
+add(1)          g1.2<1>UD       g1.2<0,1,0>UD   0x00000001UD    { align1 1N }; /* Loop count to delay kernel: Init to (g1.2 + 1) */
+cmp.z.f0.0(1)   null<1>UD       g1.3<0,1,0>UD   0x00000000UD    { align1 1N };
+(+f0.0) jmpi(1) 44D                                             { align1 WE_all 1N };
+
+/**
+ * State Register has info on where this thread is running
+ *	IVB: sr0.0 :: [15:13]: MBZ, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ *	HSW: sr0.0 :: 15: MBZ, [14:13]: SliceID, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ */
+mov(8)          g3<1>UD         0x00000000UD                    { align1 1Q };
+shr(1)          g3<1>D          sr0<0,1,0>D     12D             { align1 1N };
+and(1)          g3<1>D          g3<0,1,0>D      1D              { align1 1N }; /* g3 has HSID */
+shr(1)          g3.1<1>D        sr0<0,1,0>D     13D             { align1 1N };
+and(1)          g3.1<1>D        g3.1<0,1,0>D    3D              { align1 1N }; /* g3.1 has sliceID */
+mul(1)          g3.5<1>D        g3.1<0,1,0>D    g1.10<0,1,0>UW  { align1 1N };
+add(1)          g3<1>D          g3<0,1,0>D      g3.5<0,1,0>D    { align1 1N }; /* g3 = sliceID * SubSlicePerSliceCount + HSID */
+shr(1)          g3.2<1>D        sr0<0,1,0>D     8D              { align1 1N };
+and(1)          g3.2<1>D        g3.2<0,1,0>D    15D             { align1 1N }; /* g3.2 = EUID */
+mul(1)          g3.4<1>D        g3<0,1,0>D      16D             { align1 1N };
+add(1)          g3.2<1>D        g3.2<0,1,0>D    g3.4<0,1,0>D    { align1 1N }; /* g3.2 now points to EU row number (Y-pixel = V address )  in instrumentation surf */
+
+mov(8)          g5<1>UD         0x00000000UD                    { align1 1Q };
+and(1)          g3.3<1>D        sr0<0,1,0>D     7D              { align1 1N };
+mul(1)          g3.3<1>D        g3.3<0,1,0>D    4D              { align1 1N };
+
+mov(8)          g4<1>UD         g0<8,8,1>UD                     { align1 1Q }; /* Initialize message header with g0 */
+mov(1)          g4<1>UD         g3.3<0,1,0>UD                   { align1 1N }; /* Block offset */
+mov(1)          g4.1<1>UD       g3.2<0,1,0>UD                   { align1 1N }; /* Block offset */
+mov(1)          g4.2<1>UD       0x00000003UD                    { align1 1N }; /* Block size (1 row x 4 bytes) */
+and(1)          g4.3<1>UD       g4.3<0,1,0>UW   0xffffffffUD    { align1 1N };
+
+/* Media block read to fetch current value at specified location in instrumentation buffer */
+sendc(8)        g5<1>UD         g4<8,8,1>F      0x02190001
+                            render MsgDesc: media block read MsgCtrl = 0x0 Surface = 1 mlen 1 rlen 1 { align1 1Q };
+add(1)          g5<1>D          g5<0,1,0>D      1D              { align1 1N };
+
+/* Media block write for updated value at specified location in instrumentation buffer */
+sendc(8)        g5<1>UD         g4<8,8,1>F      0x040a8001
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 1 mlen 2 rlen 0 { align1 1Q };
+/* Delay thread for specified parameter */
+add.nz.f0.0(1)  g1.2<1>UD       g1.2<0,1,0>UD   -1D             { align1 1N };
+(+f0.0) jmpi(1) -4D                                             { align1 WE_all 1N };
+
+/* Store designated "clear GRF" value */
+mov(1)          f0.1<1>UW       g1.2<0,1,0>UW                   { align1 1N };
+
+/* Initialize looping parameters */
+mov(1)          a0<1>D          0D                              { align1 1N }; /* Initialize a0.0:w=0 */
+mov(1)          a0.4<1>W        127W                            { align1 1N }; /* Loop count. Each loop contains 16 GRF's */
+
+/* Write 32x16 all "0" block */
+mov(8)          g2<1>UD         g0<8,8,1>UD                     { align1 1Q };
+mov(8)          g127<1>UD       g0<8,8,1>UD                     { align1 1Q };
+mov(2)          g2<1>UD         g1<2,2,1>UW                     { align1 1N };
+mov(1)          g2.2<1>UD       0x000f000fUD                    { align1 1N }; /* Block size (16x16) */
+and(1)          g2.3<1>UD       g2.3<0,1,0>UW   0xffffffefUD    { align1 1N };
+mov(16)         g3<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g4<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g5<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g6<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g7<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g8<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g9<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g10<1>UD        0x00000000UD                    { align1 1H };
+sendc(8)        null<1>UD       g2<8,8,1>F      0x120a8000
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+add(1)          g2<1>UD         g1<0,1,0>UW     0x0010UW        { align1 1N };
+sendc(8)        null<1>UD       g2<8,8,1>F      0x120a8000
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+
+/* Now, clear all GRF registers */
+add.nz.f0.0(1)  a0.4<1>W        a0.4<0,1,0>W    -1W             { align1 1N };
+mov(16)         g[a0]<1>UW      f0.1<0,1,0>UW                   { align1 1H };
+add(1)          a0<1>D          a0<0,1,0>D      32D             { align1 1N };
+(+f0.0) jmpi(1) -8D                                             { align1 WE_all 1N };
+
+/* Terminante the thread */
+sendc(8)        null<1>UD       g127<8,8,1>F    0x82000010
+                            thread_spawner MsgDesc: mlen 1 rlen 0           { align1 1Q EOT };
diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c
index ec47d4114554..62e6a14ad58e 100644
--- a/drivers/gpu/drm/i915/gvt/debugfs.c
+++ b/drivers/gpu/drm/i915/gvt/debugfs.c
@@ -66,7 +66,7 @@ static inline int mmio_diff_handler(struct intel_gvt *gvt,
 	vreg = vgpu_vreg(param->vgpu, offset);
 
 	if (preg != vreg) {
-		node = kmalloc(sizeof(*node), GFP_KERNEL);
+		node = kmalloc(sizeof(*node), GFP_ATOMIC);
 		if (!node)
 			return -ENOMEM;
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 3e88e3b5c43a..fadd2adb8030 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1726,13 +1726,13 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		(*(u32 *)p_data) &= ~_MASKED_BIT_ENABLE(2);
 	write_vreg(vgpu, offset, p_data, bytes);
 
-	if (data & _MASKED_BIT_ENABLE(1)) {
+	if (IS_MASKED_BITS_ENABLED(data, 1)) {
 		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
 		return 0;
 	}
 
 	if (IS_COFFEELAKE(vgpu->gvt->gt->i915) &&
-	    data & _MASKED_BIT_ENABLE(2)) {
+	    IS_MASKED_BITS_ENABLED(data, 2)) {
 		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
 		return 0;
 	}
@@ -1741,14 +1741,14 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	 * pvinfo, if not, we will treat this guest as non-gvtg-aware
 	 * guest, and stop emulating its cfg space, mmio, gtt, etc.
 	 */
-	if (((data & _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE)) ||
-			(data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE)))
-			&& !vgpu->pv_notified) {
+	if ((IS_MASKED_BITS_ENABLED(data, GFX_PPGTT_ENABLE) ||
+	    IS_MASKED_BITS_ENABLED(data, GFX_RUN_LIST_ENABLE)) &&
+	    !vgpu->pv_notified) {
 		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
 		return 0;
 	}
-	if ((data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE))
-			|| (data & _MASKED_BIT_DISABLE(GFX_RUN_LIST_ENABLE))) {
+	if (IS_MASKED_BITS_ENABLED(data, GFX_RUN_LIST_ENABLE) ||
+	    IS_MASKED_BITS_DISABLED(data, GFX_RUN_LIST_ENABLE)) {
 		enable_execlist = !!(data & GFX_RUN_LIST_ENABLE);
 
 		gvt_dbg_core("EXECLIST %s on ring %s\n",
@@ -1809,7 +1809,7 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu,
 	write_vreg(vgpu, offset, p_data, bytes);
 	data = vgpu_vreg(vgpu, offset);
 
-	if (data & _MASKED_BIT_ENABLE(RESET_CTL_REQUEST_RESET))
+	if (IS_MASKED_BITS_ENABLED(data, RESET_CTL_REQUEST_RESET))
 		data |= RESET_CTL_READY_TO_RESET;
 	else if (data & _MASKED_BIT_DISABLE(RESET_CTL_REQUEST_RESET))
 		data &= ~RESET_CTL_READY_TO_RESET;
@@ -1827,7 +1827,8 @@ static int csfe_chicken1_mmio_write(struct intel_vgpu *vgpu,
 	(*(u32 *)p_data) &= ~_MASKED_BIT_ENABLE(0x18);
 	write_vreg(vgpu, offset, p_data, bytes);
 
-	if (data & _MASKED_BIT_ENABLE(0x10) || data & _MASKED_BIT_ENABLE(0x8))
+	if (IS_MASKED_BITS_ENABLED(data, 0x10) ||
+	    IS_MASKED_BITS_ENABLED(data, 0x8))
 		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
 
 	return 0;
@@ -3055,6 +3056,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(_MMIO(0x72380), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x7239c), D_SKL_PLUS);
 	MMIO_D(_MMIO(_PLANE_SURF_3_A), D_SKL_PLUS);
+	MMIO_D(_MMIO(_PLANE_SURF_3_B), D_SKL_PLUS);
 
 	MMIO_D(CSR_SSP_BASE, D_SKL_PLUS);
 	MMIO_D(CSR_HTP_SKL, D_SKL_PLUS);
@@ -3131,8 +3133,8 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
 		 NULL, NULL);
 
-	MMIO_D(GAMT_CHKN_BIT_REG, D_KBL);
-	MMIO_D(GEN9_CTX_PREEMPT_REG, D_KBL | D_SKL);
+	MMIO_D(GAMT_CHKN_BIT_REG, D_KBL | D_CFL);
+	MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.h b/drivers/gpu/drm/i915/gvt/mmio_context.h
index 970704b18f23..3b25e7fe32f6 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.h
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.h
@@ -54,8 +54,8 @@ bool is_inhibit_context(struct intel_context *ce);
 
 int intel_vgpu_restore_inhibit_context(struct intel_vgpu *vgpu,
 				       struct i915_request *req);
-#define IS_RESTORE_INHIBIT(a)	\
-	(_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) == \
-	((a) & _MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT)))
+
+#define IS_RESTORE_INHIBIT(a) \
+	IS_MASKED_BITS_ENABLED(a, CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT)
 
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h
index 5b66e14c5b7b..b88e033cbed4 100644
--- a/drivers/gpu/drm/i915/gvt/reg.h
+++ b/drivers/gpu/drm/i915/gvt/reg.h
@@ -94,6 +94,11 @@
 #define GFX_MODE_BIT_SET_IN_MASK(val, bit) \
 		((((bit) & 0xffff0000) == 0) && !!((val) & (((bit) << 16))))
 
+#define IS_MASKED_BITS_ENABLED(_val, _b) \
+		(((_val) & _MASKED_BIT_ENABLE(_b)) == _MASKED_BIT_ENABLE(_b))
+#define IS_MASKED_BITS_DISABLED(_val, _b) \
+		((_val) & _MASKED_BIT_DISABLE(_b))
+
 #define FORCEWAKE_RENDER_GEN9_REG 0xa278
 #define FORCEWAKE_ACK_RENDER_GEN9_REG 0x0D84
 #define FORCEWAKE_BLITTER_GEN9_REG 0xa188
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index bca036ac6621..e7532e7d74e9 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -230,7 +230,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 	struct file_stats *stats = data;
 	struct i915_vma *vma;
 
-	if (!kref_get_unless_zero(&obj->base.refcount))
+	if (IS_ERR_OR_NULL(obj) || !kref_get_unless_zero(&obj->base.refcount))
 		return 0;
 
 	stats->count++;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index adb9bf34cf97..ae99a9190200 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -410,8 +410,6 @@ struct intel_fbc {
 			int adjusted_x;
 			int adjusted_y;
 
-			int y;
-
 			u16 pixel_blend_mode;
 		} plane;
 
@@ -420,6 +418,8 @@ struct intel_fbc {
 			unsigned int stride;
 			u64 modifier;
 		} fb;
+
+		unsigned int fence_y_offset;
 		u16 gen9_wa_cfb_stride;
 		s8 fence_id;
 	} state_cache;
@@ -435,15 +435,16 @@ struct intel_fbc {
 		struct {
 			enum pipe pipe;
 			enum i9xx_plane_id i9xx_plane;
-			unsigned int fence_y_offset;
 		} crtc;
 
 		struct {
 			const struct drm_format_info *format;
 			unsigned int stride;
+			u64 modifier;
 		} fb;
 
 		int cfb_size;
+		unsigned int fence_y_offset;
 		u16 gen9_wa_cfb_stride;
 		s8 fence_id;
 		bool plane_visible;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 4dc601dffc08..284cf078135a 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3125,6 +3125,7 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
 
 	val = I915_READ(GEN11_DE_HPD_IMR);
 	val &= ~hotplug_irqs;
+	val |= ~enabled_irqs & hotplug_irqs;
 	I915_WRITE(GEN11_DE_HPD_IMR, val);
 	POSTING_READ(GEN11_DE_HPD_IMR);
 
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 25329b7600c9..014f34c047d5 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1592,6 +1592,7 @@ static u32 *save_restore_register(struct i915_perf_stream *stream, u32 *cs,
 	u32 d;
 
 	cmd = save ? MI_STORE_REGISTER_MEM : MI_LOAD_REGISTER_MEM;
+	cmd |= MI_SRM_LRM_GLOBAL_GTT;
 	if (INTEL_GEN(stream->perf->i915) >= 8)
 		cmd++;
 
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index e991a707bdb7..962ded9ce73f 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -269,12 +269,48 @@ static bool exclusive_mmio_access(const struct drm_i915_private *i915)
 	return IS_GEN(i915, 7);
 }
 
+static void engine_sample(struct intel_engine_cs *engine, unsigned int period_ns)
+{
+	struct intel_engine_pmu *pmu = &engine->pmu;
+	bool busy;
+	u32 val;
+
+	val = ENGINE_READ_FW(engine, RING_CTL);
+	if (val == 0) /* powerwell off => engine idle */
+		return;
+
+	if (val & RING_WAIT)
+		add_sample(&pmu->sample[I915_SAMPLE_WAIT], period_ns);
+	if (val & RING_WAIT_SEMAPHORE)
+		add_sample(&pmu->sample[I915_SAMPLE_SEMA], period_ns);
+
+	/* No need to sample when busy stats are supported. */
+	if (intel_engine_supports_stats(engine))
+		return;
+
+	/*
+	 * While waiting on a semaphore or event, MI_MODE reports the
+	 * ring as idle. However, previously using the seqno, and with
+	 * execlists sampling, we account for the ring waiting as the
+	 * engine being busy. Therefore, we record the sample as being
+	 * busy if either waiting or !idle.
+	 */
+	busy = val & (RING_WAIT_SEMAPHORE | RING_WAIT);
+	if (!busy) {
+		val = ENGINE_READ_FW(engine, RING_MI_MODE);
+		busy = !(val & MODE_IDLE);
+	}
+	if (busy)
+		add_sample(&pmu->sample[I915_SAMPLE_BUSY], period_ns);
+}
+
 static void
 engines_sample(struct intel_gt *gt, unsigned int period_ns)
 {
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	unsigned long flags;
 
 	if ((i915->pmu.enable & ENGINE_SAMPLE_MASK) == 0)
 		return;
@@ -283,53 +319,17 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 		return;
 
 	for_each_engine(engine, gt, id) {
-		struct intel_engine_pmu *pmu = &engine->pmu;
-		spinlock_t *mmio_lock;
-		unsigned long flags;
-		bool busy;
-		u32 val;
-
 		if (!intel_engine_pm_get_if_awake(engine))
 			continue;
 
-		mmio_lock = NULL;
-		if (exclusive_mmio_access(i915))
-			mmio_lock = &engine->uncore->lock;
-
-		if (unlikely(mmio_lock))
-			spin_lock_irqsave(mmio_lock, flags);
-
-		val = ENGINE_READ_FW(engine, RING_CTL);
-		if (val == 0) /* powerwell off => engine idle */
-			goto skip;
-
-		if (val & RING_WAIT)
-			add_sample(&pmu->sample[I915_SAMPLE_WAIT], period_ns);
-		if (val & RING_WAIT_SEMAPHORE)
-			add_sample(&pmu->sample[I915_SAMPLE_SEMA], period_ns);
-
-		/* No need to sample when busy stats are supported. */
-		if (intel_engine_supports_stats(engine))
-			goto skip;
-
-		/*
-		 * While waiting on a semaphore or event, MI_MODE reports the
-		 * ring as idle. However, previously using the seqno, and with
-		 * execlists sampling, we account for the ring waiting as the
-		 * engine being busy. Therefore, we record the sample as being
-		 * busy if either waiting or !idle.
-		 */
-		busy = val & (RING_WAIT_SEMAPHORE | RING_WAIT);
-		if (!busy) {
-			val = ENGINE_READ_FW(engine, RING_MI_MODE);
-			busy = !(val & MODE_IDLE);
+		if (exclusive_mmio_access(i915)) {
+			spin_lock_irqsave(&engine->uncore->lock, flags);
+			engine_sample(engine, period_ns);
+			spin_unlock_irqrestore(&engine->uncore->lock, flags);
+		} else {
+			engine_sample(engine, period_ns);
 		}
-		if (busy)
-			add_sample(&pmu->sample[I915_SAMPLE_BUSY], period_ns);
 
-skip:
-		if (unlikely(mmio_lock))
-			spin_unlock_irqrestore(mmio_lock, flags);
 		intel_engine_pm_put_async(engine);
 	}
 }
diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h
index 5003a71113cb..8aa7866ec6b6 100644
--- a/drivers/gpu/drm/i915/i915_priolist_types.h
+++ b/drivers/gpu/drm/i915/i915_priolist_types.h
@@ -42,7 +42,7 @@ enum {
  * active request.
  */
 #define I915_PRIORITY_UNPREEMPTABLE INT_MAX
-#define I915_PRIORITY_BARRIER INT_MAX
+#define I915_PRIORITY_BARRIER (I915_PRIORITY_UNPREEMPTABLE - 1)
 
 struct i915_priolist {
 	struct list_head requests[I915_PRIORITY_COUNT];
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 7717581350bd..06cd1d28a176 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7896,7 +7896,7 @@ enum {
 
 /* GEN7 chicken */
 #define GEN7_COMMON_SLICE_CHICKEN1		_MMIO(0x7010)
-  #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1 << 10) | (1 << 26))
+  #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	(1 << 10)
   #define GEN9_RHWO_OPTIMIZATION_DISABLE	(1 << 14)
 
 #define COMMON_SLICE_CHICKEN2					_MMIO(0x7014)
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index fc14ebf9a0b7..1f9cd33b35cb 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -104,6 +104,7 @@ vma_create(struct drm_i915_gem_object *obj,
 	   struct i915_address_space *vm,
 	   const struct i915_ggtt_view *view)
 {
+	struct i915_vma *pos = ERR_PTR(-E2BIG);
 	struct i915_vma *vma;
 	struct rb_node *rb, **p;
 
@@ -184,7 +185,6 @@ vma_create(struct drm_i915_gem_object *obj,
 	rb = NULL;
 	p = &obj->vma.tree.rb_node;
 	while (*p) {
-		struct i915_vma *pos;
 		long cmp;
 
 		rb = *p;
@@ -196,16 +196,12 @@ vma_create(struct drm_i915_gem_object *obj,
 		 * and dispose of ours.
 		 */
 		cmp = i915_vma_compare(pos, vm, view);
-		if (cmp == 0) {
-			spin_unlock(&obj->vma.lock);
-			i915_vma_free(vma);
-			return pos;
-		}
-
 		if (cmp < 0)
 			p = &rb->rb_right;
-		else
+		else if (cmp > 0)
 			p = &rb->rb_left;
+		else
+			goto err_unlock;
 	}
 	rb_link_node(&vma->obj_node, rb, p);
 	rb_insert_color(&vma->obj_node, &obj->vma.tree);
@@ -228,8 +224,9 @@ vma_create(struct drm_i915_gem_object *obj,
 err_unlock:
 	spin_unlock(&obj->vma.lock);
 err_vma:
+	i915_vm_put(vm);
 	i915_vma_free(vma);
-	return ERR_PTR(-E2BIG);
+	return pos;
 }
 
 static struct i915_vma *
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 696491d71a1d..07f663cd2d1c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6830,16 +6830,6 @@ static void ilk_init_clock_gating(struct drm_i915_private *dev_priv)
 	I915_WRITE(ILK_DISPLAY_CHICKEN2,
 		   I915_READ(ILK_DISPLAY_CHICKEN2) |
 		   ILK_ELPIN_409_SELECT);
-	I915_WRITE(_3D_CHICKEN2,
-		   _3D_CHICKEN2_WM_READ_PIPELINED << 16 |
-		   _3D_CHICKEN2_WM_READ_PIPELINED);
-
-	/* WaDisableRenderCachePipelinedFlush:ilk */
-	I915_WRITE(CACHE_MODE_0,
-		   _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:ilk */
-	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
 
 	g4x_disable_trickle_feed(dev_priv);
 
@@ -6902,27 +6892,6 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
 		   I915_READ(ILK_DISPLAY_CHICKEN2) |
 		   ILK_ELPIN_409_SELECT);
 
-	/* WaDisableHiZPlanesWhenMSAAEnabled:snb */
-	I915_WRITE(_3D_CHICKEN,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB));
-
-	/* WaDisable_RenderCache_OperationalFlush:snb */
-	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
-	/*
-	 * BSpec recoomends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN6_GT_MODE,
-		   _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
-	I915_WRITE(CACHE_MODE_0,
-		   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
-
 	I915_WRITE(GEN6_UCGCTL1,
 		   I915_READ(GEN6_UCGCTL1) |
 		   GEN6_BLBUNIT_CLOCK_GATE_DISABLE |
@@ -6945,18 +6914,6 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
 		   GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
 		   GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
 
-	/* WaStripsFansDisableFastClipPerformanceFix:snb */
-	I915_WRITE(_3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL));
-
-	/*
-	 * Bspec says:
-	 * "This bit must be set if 3DSTATE_CLIP clip mode is set to normal and
-	 * 3DSTATE_SF number of SF output attributes is more than 16."
-	 */
-	I915_WRITE(_3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH));
-
 	/*
 	 * According to the spec the following bits should be
 	 * set in order to enable memory self-refresh and fbc:
@@ -6986,24 +6943,6 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen6_check_mch_setup(dev_priv);
 }
 
-static void gen7_setup_fixed_func_scheduler(struct drm_i915_private *dev_priv)
-{
-	u32 reg = I915_READ(GEN7_FF_THREAD_MODE);
-
-	/*
-	 * WaVSThreadDispatchOverride:ivb,vlv
-	 *
-	 * This actually overrides the dispatch
-	 * mode for all thread types.
-	 */
-	reg &= ~GEN7_FF_SCHED_MASK;
-	reg |= GEN7_FF_TS_SCHED_HW;
-	reg |= GEN7_FF_VS_SCHED_HW;
-	reg |= GEN7_FF_DS_SCHED_HW;
-
-	I915_WRITE(GEN7_FF_THREAD_MODE, reg);
-}
-
 static void lpt_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	/*
@@ -7230,45 +7169,10 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
 
 static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
 {
-	/* L3 caching of data atomics doesn't work -- disable it. */
-	I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
-	I915_WRITE(HSW_ROW_CHICKEN3,
-		   _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE));
-
 	/* This is required by WaCatErrorRejectionIssue:hsw */
 	I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
-			I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
-			GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
-
-	/* WaVSRefCountFullforceMissDisable:hsw */
-	I915_WRITE(GEN7_FF_THREAD_MODE,
-		   I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME);
-
-	/* WaDisable_RenderCache_OperationalFlush:hsw */
-	I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
-	/* enable HiZ Raw Stall Optimization */
-	I915_WRITE(CACHE_MODE_0_GEN7,
-		   _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
-
-	/* WaDisable4x2SubspanOptimization:hsw */
-	I915_WRITE(CACHE_MODE_1,
-		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
-
-	/*
-	 * BSpec recommends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN7_GT_MODE,
-		   _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
-	/* WaSampleCChickenBitEnable:hsw */
-	I915_WRITE(HALF_SLICE_CHICKEN3,
-		   _MASKED_BIT_ENABLE(HSW_SAMPLE_C_PERFORMANCE));
+		   I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
+		   GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
 	/* WaSwitchSolVfFArbitrationPriority:hsw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
@@ -7282,32 +7186,11 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 
 	I915_WRITE(ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE);
 
-	/* WaDisableEarlyCull:ivb */
-	I915_WRITE(_3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_DISABLE_OBJEND_CULL));
-
 	/* WaDisableBackToBackFlipFix:ivb */
 	I915_WRITE(IVB_CHICKEN3,
 		   CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
 		   CHICKEN3_DGMG_DONE_FIX_DISABLE);
 
-	/* WaDisablePSDDualDispatchEnable:ivb */
-	if (IS_IVB_GT1(dev_priv))
-		I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
-			   _MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:ivb */
-	I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
-	/* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
-	I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1,
-		   GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
-
-	/* WaApplyL3ControlAndL3ChickenMode:ivb */
-	I915_WRITE(GEN7_L3CNTLREG1,
-			GEN7_WA_FOR_GEN7_L3_CONTROL);
-	I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER,
-		   GEN7_WA_L3_CHICKEN_MODE);
 	if (IS_IVB_GT1(dev_priv))
 		I915_WRITE(GEN7_ROW_CHICKEN2,
 			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
@@ -7319,10 +7202,6 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 	}
 
-	/* WaForceL3Serialization:ivb */
-	I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
-		   ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
-
 	/*
 	 * According to the spec, bit 13 (RCZUNIT) must be set on IVB.
 	 * This implements the WaDisableRCZUnitClockGating:ivb workaround.
@@ -7337,29 +7216,6 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 
 	g4x_disable_trickle_feed(dev_priv);
 
-	gen7_setup_fixed_func_scheduler(dev_priv);
-
-	if (0) { /* causes HiZ corruption on ivb:gt1 */
-		/* enable HiZ Raw Stall Optimization */
-		I915_WRITE(CACHE_MODE_0_GEN7,
-			   _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
-	}
-
-	/* WaDisable4x2SubspanOptimization:ivb */
-	I915_WRITE(CACHE_MODE_1,
-		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
-
-	/*
-	 * BSpec recommends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN7_GT_MODE,
-		   _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
 	snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
 	snpcr &= ~GEN6_MBC_SNPCR_MASK;
 	snpcr |= GEN6_MBC_SNPCR_MED;
@@ -7373,28 +7229,11 @@ static void ivb_init_clock_gating(struct drm_i915_private *dev_priv)
 
 static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
 {
-	/* WaDisableEarlyCull:vlv */
-	I915_WRITE(_3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_DISABLE_OBJEND_CULL));
-
 	/* WaDisableBackToBackFlipFix:vlv */
 	I915_WRITE(IVB_CHICKEN3,
 		   CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
 		   CHICKEN3_DGMG_DONE_FIX_DISABLE);
 
-	/* WaPsdDispatchEnable:vlv */
-	/* WaDisablePSDDualDispatchEnable:vlv */
-	I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
-		   _MASKED_BIT_ENABLE(GEN7_MAX_PS_THREAD_DEP |
-				      GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:vlv */
-	I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
-	/* WaForceL3Serialization:vlv */
-	I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
-		   ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
-
 	/* WaDisableDopClockGating:vlv */
 	I915_WRITE(GEN7_ROW_CHICKEN2,
 		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
@@ -7404,8 +7243,6 @@ static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
 		   I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
 		   GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
-	gen7_setup_fixed_func_scheduler(dev_priv);
-
 	/*
 	 * According to the spec, bit 13 (RCZUNIT) must be set on IVB.
 	 * This implements the WaDisableRCZUnitClockGating:vlv workaround.
@@ -7420,30 +7257,6 @@ static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
 		   I915_READ(GEN7_UCGCTL4) | GEN7_L3BANK2X_CLOCK_GATE_DISABLE);
 
 	/*
-	 * BSpec says this must be set, even though
-	 * WaDisable4x2SubspanOptimization isn't listed for VLV.
-	 */
-	I915_WRITE(CACHE_MODE_1,
-		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
-
-	/*
-	 * BSpec recommends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN7_GT_MODE,
-		   _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
-	/*
-	 * WaIncreaseL3CreditsForVLVB0:vlv
-	 * This is the hardware default actually.
-	 */
-	I915_WRITE(GEN7_L3SQCREG1, VLV_B0_WA_L3SQCREG1_VALUE);
-
-	/*
 	 * WaDisableVLVClockGating_VBIIssue:vlv
 	 * Disable clock gating on th GCFG unit to prevent a delay
 	 * in the reporting of vblank events.
@@ -7495,13 +7308,6 @@ static void g4x_init_clock_gating(struct drm_i915_private *dev_priv)
 		dspclk_gate |= DSSUNIT_CLOCK_GATE_DISABLE;
 	I915_WRITE(DSPCLK_GATE_D, dspclk_gate);
 
-	/* WaDisableRenderCachePipelinedFlush */
-	I915_WRITE(CACHE_MODE_0,
-		   _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:g4x */
-	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
 	g4x_disable_trickle_feed(dev_priv);
 }
 
@@ -7517,11 +7323,6 @@ static void i965gm_init_clock_gating(struct drm_i915_private *dev_priv)
 	intel_uncore_write(uncore,
 			   MI_ARB_STATE,
 			   _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:gen4 */
-	intel_uncore_write(uncore,
-			   CACHE_MODE_0,
-			   _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
 }
 
 static void i965g_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -7534,9 +7335,6 @@ static void i965g_init_clock_gating(struct drm_i915_private *dev_priv)
 	I915_WRITE(RENCLK_GATE_D2, 0);
 	I915_WRITE(MI_ARB_STATE,
 		   _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
-
-	/* WaDisable_RenderCache_OperationalFlush:gen4 */
-	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
 }
 
 static void gen3_init_clock_gating(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index 6a2be7d0dd95..6090ce35226b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -21,6 +21,7 @@ selftest(fence, i915_sw_fence_mock_selftests)
 selftest(scatterlist, scatterlist_mock_selftests)
 selftest(syncmap, i915_syncmap_mock_selftests)
 selftest(uncore, intel_uncore_mock_selftests)
+selftest(ring, intel_ring_mock_selftests)
 selftest(engine, intel_engine_cs_mock_selftests)
 selftest(timelines, intel_timeline_mock_selftests)
 selftest(requests, i915_request_mock_selftests)
diff --git a/drivers/gpu/drm/lima/lima_pp.c b/drivers/gpu/drm/lima/lima_pp.c
index 33f01383409c..a5c95bed08c0 100644
--- a/drivers/gpu/drm/lima/lima_pp.c
+++ b/drivers/gpu/drm/lima/lima_pp.c
@@ -271,6 +271,8 @@ void lima_pp_fini(struct lima_ip *ip)
 
 int lima_pp_bcast_resume(struct lima_ip *ip)
 {
+	/* PP has been reset by individual PP resume */
+	ip->data.async_reset = false;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c
index 04e1d38d41f7..08802e5177f6 100644
--- a/drivers/gpu/drm/mcde/mcde_display.c
+++ b/drivers/gpu/drm/mcde/mcde_display.c
@@ -812,7 +812,7 @@ static void mcde_display_enable(struct drm_simple_display_pipe *pipe,
 	struct drm_crtc *crtc = &pipe->crtc;
 	struct drm_plane *plane = &pipe->plane;
 	struct drm_device *drm = crtc->dev;
-	struct mcde *mcde = drm->dev_private;
+	struct mcde *mcde = to_mcde(drm);
 	const struct drm_display_mode *mode = &cstate->mode;
 	struct drm_framebuffer *fb = plane->state->fb;
 	u32 format = fb->format->format;
diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c
index 84f3e2dbd77b..80082d6dce3a 100644
--- a/drivers/gpu/drm/mcde/mcde_drv.c
+++ b/drivers/gpu/drm/mcde/mcde_drv.c
@@ -209,7 +209,6 @@ static int mcde_modeset_init(struct drm_device *drm)
 
 	drm_mode_config_reset(drm);
 	drm_kms_helper_poll_init(drm);
-	drm_fbdev_generic_setup(drm, 32);
 
 	return 0;
 }
@@ -264,6 +263,8 @@ static int mcde_drm_bind(struct device *dev)
 	if (ret < 0)
 		goto unbind;
 
+	drm_fbdev_generic_setup(drm, 32);
+
 	return 0;
 
 unbind:
diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig
index c420f5a3d33b..aa74aac3cbcc 100644
--- a/drivers/gpu/drm/mediatek/Kconfig
+++ b/drivers/gpu/drm/mediatek/Kconfig
@@ -6,12 +6,12 @@ config DRM_MEDIATEK
 	depends on COMMON_CLK
 	depends on HAVE_ARM_SMCCC
 	depends on OF
+	depends on MTK_MMSYS
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_HELPER
 	select DRM_MIPI_DSI
 	select DRM_PANEL
 	select MEMORY
-	select MTK_MMSYS
 	select MTK_SMI
 	select VIDEOMODE_HELPERS
 	help
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index fe46c4bac64d..7cd8f415fd02 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -193,7 +193,6 @@ static int mtk_crtc_ddp_clk_enable(struct mtk_drm_crtc *mtk_crtc)
 	int ret;
 	int i;
 
-	DRM_DEBUG_DRIVER("%s\n", __func__);
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
 		ret = clk_prepare_enable(mtk_crtc->ddp_comp[i]->clk);
 		if (ret) {
@@ -213,7 +212,6 @@ static void mtk_crtc_ddp_clk_disable(struct mtk_drm_crtc *mtk_crtc)
 {
 	int i;
 
-	DRM_DEBUG_DRIVER("%s\n", __func__);
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
 		clk_disable_unprepare(mtk_crtc->ddp_comp[i]->clk);
 }
@@ -258,7 +256,6 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 	int ret;
 	int i;
 
-	DRM_DEBUG_DRIVER("%s\n", __func__);
 	if (WARN_ON(!crtc->state))
 		return -EINVAL;
 
@@ -299,7 +296,6 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 		goto err_mutex_unprepare;
 	}
 
-	DRM_DEBUG_DRIVER("mediatek_ddp_ddp_path_setup\n");
 	for (i = 0; i < mtk_crtc->ddp_comp_nr - 1; i++) {
 		mtk_mmsys_ddp_connect(mtk_crtc->mmsys_dev,
 				      mtk_crtc->ddp_comp[i]->id,
@@ -349,7 +345,6 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 	struct drm_crtc *crtc = &mtk_crtc->base;
 	int i;
 
-	DRM_DEBUG_DRIVER("%s\n", __func__);
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
 		mtk_ddp_comp_stop(mtk_crtc->ddp_comp[i]);
 		if (i == 1)
@@ -831,7 +826,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
 	mtk_crtc->cmdq_client =
-			cmdq_mbox_create(dev, drm_crtc_index(&mtk_crtc->base),
+			cmdq_mbox_create(mtk_crtc->mmsys_dev,
+					 drm_crtc_index(&mtk_crtc->base),
 					 2000);
 	if (IS_ERR(mtk_crtc->cmdq_client)) {
 		dev_dbg(dev, "mtk_crtc %d failed to create mailbox client, writing register by CPU now\n",
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 6bd369434d9d..040a8f393fe2 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -444,7 +444,6 @@ static int mtk_drm_probe(struct platform_device *pdev)
 	if (!private)
 		return -ENOMEM;
 
-	private->data = of_device_get_match_data(dev);
 	private->mmsys_dev = dev->parent;
 	if (!private->mmsys_dev) {
 		dev_err(dev, "Failed to get MMSYS device\n");
@@ -514,7 +513,8 @@ static int mtk_drm_probe(struct platform_device *pdev)
 				goto err_node;
 			}
 
-			ret = mtk_ddp_comp_init(dev, node, comp, comp_id, NULL);
+			ret = mtk_ddp_comp_init(dev->parent, node, comp,
+						comp_id, NULL);
 			if (ret) {
 				of_node_put(node);
 				goto err_node;
@@ -571,7 +571,6 @@ static int mtk_drm_sys_suspend(struct device *dev)
 	int ret;
 
 	ret = drm_mode_config_helper_suspend(drm);
-	DRM_DEBUG_DRIVER("mtk_drm_sys_suspend\n");
 
 	return ret;
 }
@@ -583,7 +582,6 @@ static int mtk_drm_sys_resume(struct device *dev)
 	int ret;
 
 	ret = drm_mode_config_helper_resume(drm);
-	DRM_DEBUG_DRIVER("mtk_drm_sys_resume\n");
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index c2bd683a87c8..92141a19681b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -164,6 +164,16 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 						   true, true);
 }
 
+static void mtk_plane_atomic_disable(struct drm_plane *plane,
+				     struct drm_plane_state *old_state)
+{
+	struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
+
+	state->pending.enable = false;
+	wmb(); /* Make sure the above parameter is set before update */
+	state->pending.dirty = true;
+}
+
 static void mtk_plane_atomic_update(struct drm_plane *plane,
 				    struct drm_plane_state *old_state)
 {
@@ -178,6 +188,11 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
 	if (!crtc || WARN_ON(!fb))
 		return;
 
+	if (!plane->state->visible) {
+		mtk_plane_atomic_disable(plane, old_state);
+		return;
+	}
+
 	gem = fb->obj[0];
 	mtk_gem = to_mtk_gem_obj(gem);
 	addr = mtk_gem->dma_addr;
@@ -200,16 +215,6 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
 	state->pending.dirty = true;
 }
 
-static void mtk_plane_atomic_disable(struct drm_plane *plane,
-				     struct drm_plane_state *old_state)
-{
-	struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
-
-	state->pending.enable = false;
-	wmb(); /* Make sure the above parameter is set before update */
-	state->pending.dirty = true;
-}
-
 static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
 	.prepare_fb = drm_gem_fb_prepare_fb,
 	.atomic_check = mtk_plane_atomic_check,
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 270bf22c98fe..02ac55c13a80 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -316,10 +316,7 @@ static void mtk_dsi_lane0_ulp_mode_leave(struct mtk_dsi *dsi)
 
 static bool mtk_dsi_clk_hs_state(struct mtk_dsi *dsi)
 {
-	u32 tmp_reg1;
-
-	tmp_reg1 = readl(dsi->regs + DSI_PHY_LCCON);
-	return ((tmp_reg1 & LC_HS_TX_EN) == 1) ? true : false;
+	return readl(dsi->regs + DSI_PHY_LCCON) & LC_HS_TX_EN;
 }
 
 static void mtk_dsi_clk_hs_mode(struct mtk_dsi *dsi, bool enter)
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 5feb760617cb..1b2fb9f35daf 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1630,8 +1630,6 @@ static int mtk_hdmi_audio_startup(struct device *dev, void *data)
 {
 	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
 
-	dev_dbg(dev, "%s\n", __func__);
-
 	mtk_hdmi_audio_enable(hdmi);
 
 	return 0;
@@ -1641,18 +1639,15 @@ static void mtk_hdmi_audio_shutdown(struct device *dev, void *data)
 {
 	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
 
-	dev_dbg(dev, "%s\n", __func__);
-
 	mtk_hdmi_audio_disable(hdmi);
 }
 
 static int
-mtk_hdmi_audio_digital_mute(struct device *dev, void *data, bool enable)
+mtk_hdmi_audio_mute(struct device *dev, void *data,
+		    bool enable, int direction)
 {
 	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
 
-	dev_dbg(dev, "%s(%d)\n", __func__, enable);
-
 	if (enable)
 		mtk_hdmi_hw_aud_mute(hdmi);
 	else
@@ -1665,8 +1660,6 @@ static int mtk_hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf,
 {
 	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
 
-	dev_dbg(dev, "%s\n", __func__);
-
 	memcpy(buf, hdmi->conn.eld, min(sizeof(hdmi->conn.eld), len));
 
 	return 0;
@@ -1692,9 +1685,10 @@ static const struct hdmi_codec_ops mtk_hdmi_audio_codec_ops = {
 	.hw_params = mtk_hdmi_audio_hw_params,
 	.audio_startup = mtk_hdmi_audio_startup,
 	.audio_shutdown = mtk_hdmi_audio_shutdown,
-	.digital_mute = mtk_hdmi_audio_digital_mute,
+	.mute_stream = mtk_hdmi_audio_mute,
 	.get_eld = mtk_hdmi_audio_get_eld,
 	.hook_plugged_cb = mtk_hdmi_audio_hook_plugged_cb,
+	.no_capture_mute = 1,
 };
 
 static int mtk_hdmi_register_audio_driver(struct device *dev)
@@ -1766,7 +1760,6 @@ static int mtk_drm_hdmi_probe(struct platform_device *pdev)
 		goto err_bridge_remove;
 	}
 
-	dev_dbg(dev, "mediatek hdmi probe success\n");
 	return 0;
 
 err_bridge_remove:
@@ -1789,7 +1782,7 @@ static int mtk_hdmi_suspend(struct device *dev)
 	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
 
 	mtk_hdmi_clk_disable_audio(hdmi);
-	dev_dbg(dev, "hdmi suspend success!\n");
+
 	return 0;
 }
 
@@ -1804,7 +1797,6 @@ static int mtk_hdmi_resume(struct device *dev)
 		return ret;
 	}
 
-	dev_dbg(dev, "hdmi resume success!\n");
 	return 0;
 }
 #endif
diff --git a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
index b55f51675205..827b93786fac 100644
--- a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
+++ b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
@@ -107,60 +107,10 @@
 #define RGS_HDMITX_5T1_EDG		(0xf << 4)
 #define RGS_HDMITX_PLUG_TST		BIT(0)
 
-static const u8 PREDIV[3][4] = {
-	{0x0, 0x0, 0x0, 0x0},	/* 27Mhz */
-	{0x1, 0x1, 0x1, 0x1},	/* 74Mhz */
-	{0x1, 0x1, 0x1, 0x1}	/* 148Mhz */
-};
-
-static const u8 TXDIV[3][4] = {
-	{0x3, 0x3, 0x3, 0x2},	/* 27Mhz */
-	{0x2, 0x1, 0x1, 0x1},	/* 74Mhz */
-	{0x1, 0x0, 0x0, 0x0}	/* 148Mhz */
-};
-
-static const u8 FBKSEL[3][4] = {
-	{0x1, 0x1, 0x1, 0x1},	/* 27Mhz */
-	{0x1, 0x0, 0x1, 0x1},	/* 74Mhz */
-	{0x1, 0x0, 0x1, 0x1}	/* 148Mhz */
-};
-
-static const u8 FBKDIV[3][4] = {
-	{19, 24, 29, 19},	/* 27Mhz */
-	{19, 24, 14, 19},	/* 74Mhz */
-	{19, 24, 14, 19}	/* 148Mhz */
-};
-
-static const u8 DIVEN[3][4] = {
-	{0x2, 0x1, 0x1, 0x2},	/* 27Mhz */
-	{0x2, 0x2, 0x2, 0x2},	/* 74Mhz */
-	{0x2, 0x2, 0x2, 0x2}	/* 148Mhz */
-};
-
-static const u8 HTPLLBP[3][4] = {
-	{0xc, 0xc, 0x8, 0xc},	/* 27Mhz */
-	{0xc, 0xf, 0xf, 0xc},	/* 74Mhz */
-	{0xc, 0xf, 0xf, 0xc}	/* 148Mhz */
-};
-
-static const u8 HTPLLBC[3][4] = {
-	{0x2, 0x3, 0x3, 0x2},	/* 27Mhz */
-	{0x2, 0x3, 0x3, 0x2},	/* 74Mhz */
-	{0x2, 0x3, 0x3, 0x2}	/* 148Mhz */
-};
-
-static const u8 HTPLLBR[3][4] = {
-	{0x1, 0x1, 0x0, 0x1},	/* 27Mhz */
-	{0x1, 0x2, 0x2, 0x1},	/* 74Mhz */
-	{0x1, 0x2, 0x2, 0x1}	/* 148Mhz */
-};
-
 static int mtk_hdmi_pll_prepare(struct clk_hw *hw)
 {
 	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
 
-	dev_dbg(hdmi_phy->dev, "%s\n", __func__);
-
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_AUTOK_EN);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_POSDIV);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3, RG_HDMITX_MHLCK_EN);
@@ -178,8 +128,6 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw)
 {
 	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
 
-	dev_dbg(hdmi_phy->dev, "%s\n", __func__);
-
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_TXDIV_EN);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_BIAS_LPF_EN);
 	usleep_range(100, 150);
diff --git a/drivers/gpu/drm/meson/meson_registers.h b/drivers/gpu/drm/meson/meson_registers.h
index 8ea00546cd4e..049c4bfe2a3a 100644
--- a/drivers/gpu/drm/meson/meson_registers.h
+++ b/drivers/gpu/drm/meson/meson_registers.h
@@ -261,6 +261,12 @@
 #define VIU_OSD_FIFO_DEPTH_VAL(val)      ((val & 0x7f) << 12)
 #define VIU_OSD_WORDS_PER_BURST(words)   (((words & 0x4) >> 1) << 22)
 #define VIU_OSD_FIFO_LIMITS(size)        ((size & 0xf) << 24)
+#define VIU_OSD_BURST_LENGTH_24          (0x0 << 31 | 0x0 << 10)
+#define VIU_OSD_BURST_LENGTH_32          (0x0 << 31 | 0x1 << 10)
+#define VIU_OSD_BURST_LENGTH_48          (0x0 << 31 | 0x2 << 10)
+#define VIU_OSD_BURST_LENGTH_64          (0x0 << 31 | 0x3 << 10)
+#define VIU_OSD_BURST_LENGTH_96          (0x1 << 31 | 0x0 << 10)
+#define VIU_OSD_BURST_LENGTH_128         (0x1 << 31 | 0x1 << 10)
 
 #define VD1_IF0_GEN_REG 0x1a50
 #define VD1_IF0_CANVAS0 0x1a51
diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c
index 304f8ff1339c..aede0c67a57f 100644
--- a/drivers/gpu/drm/meson/meson_viu.c
+++ b/drivers/gpu/drm/meson/meson_viu.c
@@ -411,13 +411,6 @@ void meson_viu_gxm_disable_osd1_afbc(struct meson_drm *priv)
 			    priv->io_base + _REG(VIU_MISC_CTRL1));
 }
 
-static inline uint32_t meson_viu_osd_burst_length_reg(uint32_t length)
-{
-	uint32_t val = (((length & 0x80) % 24) / 12);
-
-	return (((val & 0x3) << 10) | (((val & 0x4) >> 2) << 31));
-}
-
 void meson_viu_init(struct meson_drm *priv)
 {
 	uint32_t reg;
@@ -444,9 +437,9 @@ void meson_viu_init(struct meson_drm *priv)
 		VIU_OSD_FIFO_LIMITS(2);      /* fifo_lim: 2*16=32 */
 
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
-		reg |= meson_viu_osd_burst_length_reg(32);
+		reg |= VIU_OSD_BURST_LENGTH_32;
 	else
-		reg |= meson_viu_osd_burst_length_reg(64);
+		reg |= VIU_OSD_BURST_LENGTH_64;
 
 	writel_relaxed(reg, priv->io_base + _REG(VIU_OSD1_FIFO_CTRL_STAT));
 	writel_relaxed(reg, priv->io_base + _REG(VIU_OSD2_FIFO_CTRL_STAT));
diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
index 60f6472a3e58..6021f8d9efd1 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
@@ -408,7 +408,7 @@ a2xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
 	struct msm_gem_address_space *aspace;
 
 	aspace = msm_gem_address_space_create(mmu, "gpu", SZ_16M,
-		SZ_16M + 0xfff * SZ_64K);
+		0xfff * SZ_64K);
 
 	if (IS_ERR(aspace) && !IS_ERR(mmu))
 		mmu->funcs->destroy(mmu);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 096be97ce9f9..21e77d67151f 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -1121,7 +1121,7 @@ static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu)
 		return -ENODEV;
 
 	mmu = msm_iommu_new(gmu->dev, domain);
-	gmu->aspace = msm_gem_address_space_create(mmu, "gmu", 0x0, 0x7fffffff);
+	gmu->aspace = msm_gem_address_space_create(mmu, "gmu", 0x0, 0x80000000);
 	if (IS_ERR(gmu->aspace)) {
 		iommu_domain_free(domain);
 		return PTR_ERR(gmu->aspace);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index a1589e040c57..7768557cdfb2 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -893,8 +893,8 @@ static const struct adreno_gpu_funcs funcs = {
 #if defined(CONFIG_DRM_MSM_GPU_STATE)
 		.gpu_state_get = a6xx_gpu_state_get,
 		.gpu_state_put = a6xx_gpu_state_put,
-		.create_address_space = adreno_iommu_create_address_space,
 #endif
+		.create_address_space = adreno_iommu_create_address_space,
 	},
 	.get_timestamp = a6xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 89673c7ed473..5db06b590943 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -194,7 +194,7 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu,
 	struct msm_gem_address_space *aspace;
 
 	aspace = msm_gem_address_space_create(mmu, "gpu", SZ_16M,
-		0xfffffff);
+		0xffffffff - SZ_16M);
 
 	if (IS_ERR(aspace) && !IS_ERR(mmu))
 		mmu->funcs->destroy(mmu);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 63976dcd2ac8..0946a86b37b2 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -521,7 +521,7 @@ static struct msm_display_topology dpu_encoder_get_topology(
 			struct dpu_kms *dpu_kms,
 			struct drm_display_mode *mode)
 {
-	struct msm_display_topology topology;
+	struct msm_display_topology topology = {0};
 	int i, intf_count = 0;
 
 	for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++)
@@ -537,7 +537,8 @@ static struct msm_display_topology dpu_encoder_get_topology(
 	 * 1 LM, 1 INTF
 	 * 2 LM, 1 INTF (stream merge to support high resolution interfaces)
 	 *
-	 * Adding color blocks only to primary interface
+	 * Adding color blocks only to primary interface if available in
+	 * sufficient number
 	 */
 	if (intf_count == 2)
 		topology.num_lm = 2;
@@ -546,8 +547,11 @@ static struct msm_display_topology dpu_encoder_get_topology(
 	else
 		topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1;
 
-	if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_DSI)
-		topology.num_dspp = topology.num_lm;
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_DSI) {
+		if (dpu_kms->catalog->dspp &&
+			(dpu_kms->catalog->dspp_count >= topology.num_lm))
+			topology.num_dspp = topology.num_lm;
+	}
 
 	topology.num_enc = 0;
 	topology.num_intf = intf_count;
@@ -2136,7 +2140,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
 
 	dpu_enc = to_dpu_encoder_virt(enc);
 
-	mutex_init(&dpu_enc->enc_lock);
 	ret = dpu_encoder_setup_display(dpu_enc, dpu_kms, disp_info);
 	if (ret)
 		goto fail;
@@ -2151,7 +2154,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
 				0);
 
 
-	mutex_init(&dpu_enc->rc_lock);
 	INIT_DELAYED_WORK(&dpu_enc->delayed_off_work,
 			dpu_encoder_off_work);
 	dpu_enc->idle_timeout = IDLE_TIMEOUT;
@@ -2183,7 +2185,7 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev,
 
 	dpu_enc = devm_kzalloc(dev->dev, sizeof(*dpu_enc), GFP_KERNEL);
 	if (!dpu_enc)
-		return ERR_PTR(ENOMEM);
+		return ERR_PTR(-ENOMEM);
 
 	rc = drm_encoder_init(dev, &dpu_enc->base, &dpu_encoder_funcs,
 			drm_enc_mode, NULL);
@@ -2196,6 +2198,8 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev,
 
 	spin_lock_init(&dpu_enc->enc_spinlock);
 	dpu_enc->enabled = false;
+	mutex_init(&dpu_enc->enc_lock);
+	mutex_init(&dpu_enc->rc_lock);
 
 	return &dpu_enc->base;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index b8615d4fe8a3..680527e28d09 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -780,7 +780,7 @@ static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms)
 
 	mmu = msm_iommu_new(dpu_kms->dev->dev, domain);
 	aspace = msm_gem_address_space_create(mmu, "dpu1",
-		0x1000, 0xfffffff);
+		0x1000, 0x100000000 - 0x1000);
 
 	if (IS_ERR(aspace)) {
 		mmu->funcs->destroy(mmu);
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 08897184b1d9..fc6a3f8134c7 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -514,7 +514,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 			config->iommu);
 
 		aspace  = msm_gem_address_space_create(mmu,
-			"mdp4", 0x1000, 0xffffffff);
+			"mdp4", 0x1000, 0x100000000 - 0x1000);
 
 		if (IS_ERR(aspace)) {
 			if (!IS_ERR(mmu))
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 19ec48695ffb..e193865ce9a2 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -633,7 +633,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 		mmu = msm_iommu_new(iommu_dev, config->platform.iommu);
 
 		aspace = msm_gem_address_space_create(mmu, "mdp5",
-			0x1000, 0xffffffff);
+			0x1000, 0x100000000 - 0x1000);
 
 		if (IS_ERR(aspace)) {
 			if (!IS_ERR(mmu))
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index 001fbf537440..a1d94be7883a 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -71,8 +71,10 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	queue->flags = flags;
 
 	if (priv->gpu) {
-		if (prio >= priv->gpu->nr_rings)
+		if (prio >= priv->gpu->nr_rings) {
+			kfree(queue);
 			return -EINVAL;
+		}
 
 		queue->prio = prio;
 	}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index d472942102f5..519f99868e35 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -601,6 +601,9 @@ nv50_audio_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
 				(0x0100 << nv_crtc->index),
 	};
 
+	if (!nv_encoder->audio)
+		return;
+
 	nv_encoder->audio = false;
 	nvif_mthd(&disp->disp->object, 0, &args, sizeof(args));
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index e5c230d9ae24..cc9993837508 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -550,7 +550,7 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm,
 					 DMA_BIDIRECTIONAL);
 		if (dma_mapping_error(dev, *dma_addr))
 			goto out_free_page;
-		if (drm->dmem->migrate.copy_func(drm, page_size(spage),
+		if (drm->dmem->migrate.copy_func(drm, 1,
 			NOUVEAU_APER_VRAM, paddr, NOUVEAU_APER_HOST, *dma_addr))
 			goto out_dma_unmap;
 	} else {
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index ba9f9359c30e..6586d9d39874 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -562,6 +562,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
 		.end = notifier->notifier.interval_tree.last + 1,
 		.pfn_flags_mask = HMM_PFN_REQ_FAULT | HMM_PFN_REQ_WRITE,
 		.hmm_pfns = hmm_pfns,
+		.dev_private_owner = drm->dev,
 	};
 	struct mm_struct *mm = notifier->notifier.mm;
 	int ret;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
index c8ab1b5741a3..db7769cb33eb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
@@ -118,10 +118,10 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		if (retries)
 			udelay(400);
 
-		/* transaction request, wait up to 1ms for it to complete */
+		/* transaction request, wait up to 2ms for it to complete */
 		nvkm_wr32(device, 0x00e4e4 + base, 0x00010000 | ctrl);
 
-		timeout = 1000;
+		timeout = 2000;
 		do {
 			ctrl = nvkm_rd32(device, 0x00e4e4 + base);
 			udelay(1);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
index 7ef60895f43a..edb6148cbca0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
@@ -118,10 +118,10 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		if (retries)
 			udelay(400);
 
-		/* transaction request, wait up to 1ms for it to complete */
+		/* transaction request, wait up to 2ms for it to complete */
 		nvkm_wr32(device, 0x00d954 + base, 0x00010000 | ctrl);
 
-		timeout = 1000;
+		timeout = 2000;
 		do {
 			ctrl = nvkm_rd32(device, 0x00d954 + base);
 			udelay(1);
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index b6ecd1552132..5178f87d6574 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -2495,6 +2495,7 @@ static const struct panel_desc logicpd_type_28 = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
 	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE |
 		     DRM_BUS_FLAG_SYNC_DRIVE_NEGEDGE,
+	.connector_type = DRM_MODE_CONNECTOR_DPI,
 };
 
 static const struct panel_desc mitsubishi_aa070mc01 = {
@@ -2663,6 +2664,7 @@ static const struct panel_desc newhaven_nhd_43_480272ef_atxl = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
 	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE |
 		     DRM_BUS_FLAG_SYNC_DRIVE_POSEDGE,
+	.connector_type = DRM_MODE_CONNECTOR_DPI,
 };
 
 static const struct display_timing nlt_nl192108ac18_02d_timing = {
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 134aa2b01f90..f434efdeca44 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -5563,6 +5563,7 @@ static int ci_parse_power_table(struct radeon_device *rdev)
 	if (!rdev->pm.dpm.ps)
 		return -ENOMEM;
 	power_state_offset = (u8 *)state_array->states;
+	rdev->pm.dpm.num_ps = 0;
 	for (i = 0; i < state_array->ucNumEntries; i++) {
 		u8 *idx;
 		power_state = (union pplib_power_state *)power_state_offset;
@@ -5572,10 +5573,8 @@ static int ci_parse_power_table(struct radeon_device *rdev)
 		if (!rdev->pm.power_state[i].clock_info)
 			return -EINVAL;
 		ps = kzalloc(sizeof(struct ci_ps), GFP_KERNEL);
-		if (ps == NULL) {
-			kfree(rdev->pm.dpm.ps);
+		if (ps == NULL)
 			return -ENOMEM;
-		}
 		rdev->pm.dpm.ps[i].ps_priv = ps;
 		ci_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i],
 					      non_clock_info,
@@ -5597,8 +5596,8 @@ static int ci_parse_power_table(struct radeon_device *rdev)
 			k++;
 		}
 		power_state_offset += 2 + power_state->v2.ucNumDPMLevels;
+		rdev->pm.dpm.num_ps = i + 1;
 	}
-	rdev->pm.dpm.num_ps = state_array->ucNumEntries;
 
 	/* fill in the vce power states */
 	for (i = 0; i < RADEON_MAX_VCE_LEVELS; i++) {
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index b57c37ddd164..c7fbb7932f37 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -2127,7 +2127,7 @@ static int ni_init_smc_spll_table(struct radeon_device *rdev)
 		if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT))
 			ret = -EINVAL;
 
-		if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT))
+		if (fb_div & ~(SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_SHIFT))
 			ret = -EINVAL;
 
 		if (clk_v & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_SHIFT))
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index 0919f1f159a4..f65d1489dc50 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -31,6 +31,7 @@ config DRM_RCAR_DW_HDMI
 config DRM_RCAR_LVDS
 	tristate "R-Car DU LVDS Encoder Support"
 	depends on DRM && DRM_BRIDGE && OF
+	select DRM_KMS_HELPER
 	select DRM_PANEL
 	select OF_FLATTREE
 	select OF_OVERLAY
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index c634b95b50f7..a4a45daf93f2 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -817,8 +817,8 @@ out:
 	mutex_unlock(&dp->lock);
 }
 
-static int cdn_dp_audio_digital_mute(struct device *dev, void *data,
-				     bool enable)
+static int cdn_dp_audio_mute_stream(struct device *dev, void *data,
+				    bool enable, int direction)
 {
 	struct cdn_dp_device *dp = dev_get_drvdata(dev);
 	int ret;
@@ -849,8 +849,9 @@ static int cdn_dp_audio_get_eld(struct device *dev, void *data,
 static const struct hdmi_codec_ops audio_codec_ops = {
 	.hw_params = cdn_dp_audio_hw_params,
 	.audio_shutdown = cdn_dp_audio_shutdown,
-	.digital_mute = cdn_dp_audio_digital_mute,
+	.mute_stream = cdn_dp_audio_mute_stream,
 	.get_eld = cdn_dp_audio_get_eld,
+	.no_capture_mute = 1,
 };
 
 static int cdn_dp_audio_codec_init(struct cdn_dp_device *dp,
diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c
index 5b15c4974e6b..008f07923bbc 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.c
+++ b/drivers/gpu/drm/sti/sti_hdmi.c
@@ -1191,7 +1191,8 @@ static int hdmi_audio_hw_params(struct device *dev,
 	return 0;
 }
 
-static int hdmi_audio_digital_mute(struct device *dev, void *data, bool enable)
+static int hdmi_audio_mute(struct device *dev, void *data,
+			   bool enable, int direction)
 {
 	struct sti_hdmi *hdmi = dev_get_drvdata(dev);
 
@@ -1219,8 +1220,9 @@ static int hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf, size
 static const struct hdmi_codec_ops audio_codec_ops = {
 	.hw_params = hdmi_audio_hw_params,
 	.audio_shutdown = hdmi_audio_shutdown,
-	.digital_mute = hdmi_audio_digital_mute,
+	.mute_stream = hdmi_audio_mute,
 	.get_eld = hdmi_audio_get_eld,
+	.no_capture_mute = 1,
 };
 
 static int sti_hdmi_register_audio_driver(struct device *dev,
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index ce07ddc3e058..2f2c9f0a1071 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -259,9 +259,8 @@ sun4i_hdmi_connector_detect(struct drm_connector *connector, bool force)
 	struct sun4i_hdmi *hdmi = drm_connector_to_sun4i_hdmi(connector);
 	unsigned long reg;
 
-	if (readl_poll_timeout(hdmi->base + SUN4I_HDMI_HPD_REG, reg,
-			       reg & SUN4I_HDMI_HPD_HIGH,
-			       0, 500000)) {
+	reg = readl(hdmi->base + SUN4I_HDMI_HPD_REG);
+	if (!(reg & SUN4I_HDMI_HPD_HIGH)) {
 		cec_phys_addr_invalidate(hdmi->cec_adap);
 		return connector_status_disconnected;
 	}
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index 56cc037fd312..cc4fb916318f 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -363,6 +363,19 @@ static int sun8i_mixer_bind(struct device *dev, struct device *master,
 	mixer->engine.ops = &sun8i_engine_ops;
 	mixer->engine.node = dev->of_node;
 
+	if (of_find_property(dev->of_node, "iommus", NULL)) {
+		/*
+		 * This assume we have the same DMA constraints for
+		 * all our the mixers in our pipeline. This sounds
+		 * bad, but it has always been the case for us, and
+		 * DRM doesn't do per-device allocation either, so we
+		 * would need to fix DRM first...
+		 */
+		ret = of_dma_configure(drm->dev, dev->of_node, true);
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * While this function can fail, we shouldn't do anything
 	 * if this happens. Some early DE2 DT entries don't provide
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 83f31c6e891c..04d6848d19fc 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -957,6 +957,7 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm,
 	}
 
 	drm_plane_helper_add(&plane->base, &tegra_cursor_plane_helper_funcs);
+	drm_plane_create_zpos_immutable_property(&plane->base, 255);
 
 	return &plane->base;
 }
diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c
index 8183e617bf6b..22a03f7ffdc1 100644
--- a/drivers/gpu/drm/tegra/hub.c
+++ b/drivers/gpu/drm/tegra/hub.c
@@ -149,7 +149,9 @@ int tegra_display_hub_prepare(struct tegra_display_hub *hub)
 	for (i = 0; i < hub->soc->num_wgrps; i++) {
 		struct tegra_windowgroup *wgrp = &hub->wgrps[i];
 
-		tegra_windowgroup_enable(wgrp);
+		/* Skip orphaned window group whose parent DC is disabled */
+		if (wgrp->parent)
+			tegra_windowgroup_enable(wgrp);
 	}
 
 	return 0;
@@ -166,7 +168,9 @@ void tegra_display_hub_cleanup(struct tegra_display_hub *hub)
 	for (i = 0; i < hub->soc->num_wgrps; i++) {
 		struct tegra_windowgroup *wgrp = &hub->wgrps[i];
 
-		tegra_windowgroup_disable(wgrp);
+		/* Skip orphaned window group whose parent DC is disabled */
+		if (wgrp->parent)
+			tegra_windowgroup_disable(wgrp);
 	}
 }
 
@@ -944,6 +948,15 @@ static int tegra_display_hub_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
 			err);
 
+	err = devm_of_platform_populate(&pdev->dev);
+	if (err < 0)
+		goto unregister;
+
+	return err;
+
+unregister:
+	host1x_client_unregister(&hub->client);
+	pm_runtime_disable(&pdev->dev);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index f73b81c2576e..0f20e14a4cfd 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -883,8 +883,10 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 	if (!fence)
 		return 0;
 
-	if (no_wait_gpu)
+	if (no_wait_gpu) {
+		dma_fence_put(fence);
 		return -EBUSY;
+	}
 
 	dma_resv_add_shared_fence(bo->base.resv, fence);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index a43aa7275f12..fa03fab02076 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -300,8 +300,10 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 			break;
 		case -EBUSY:
 		case -ERESTARTSYS:
+			dma_fence_put(moving);
 			return VM_FAULT_NOPAGE;
 		default:
+			dma_fence_put(moving);
 			return VM_FAULT_SIGBUS;
 		}
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 9ffa9c75a5da..16b385629688 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1069,10 +1069,6 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	if (new_content_type != SAME_AS_DISPLAY) {
 		struct vmw_surface_metadata metadata = {0};
 
-		metadata.base_size.width = hdisplay;
-		metadata.base_size.height = vdisplay;
-		metadata.base_size.depth = 1;
-
 		/*
 		 * If content buffer is a buffer object, then we have to
 		 * construct surface info
@@ -1104,6 +1100,10 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 			metadata = new_vfbs->surface->metadata;
 		}
 
+		metadata.base_size.width = hdisplay;
+		metadata.base_size.height = vdisplay;
+		metadata.base_size.depth = 1;
+
 		if (vps->surf) {
 			struct drm_vmw_size cur_base_size =
 				vps->surf->metadata.base_size;
diff --git a/drivers/gpu/drm/zte/zx_hdmi.c b/drivers/gpu/drm/zte/zx_hdmi.c
index 76a16d997a23..cd79ca0a92a9 100644
--- a/drivers/gpu/drm/zte/zx_hdmi.c
+++ b/drivers/gpu/drm/zte/zx_hdmi.c
@@ -439,8 +439,8 @@ static int zx_hdmi_audio_hw_params(struct device *dev,
 	return zx_hdmi_infoframe_trans(hdmi, &frame, FSEL_AUDIO);
 }
 
-static int zx_hdmi_audio_digital_mute(struct device *dev, void *data,
-				      bool enable)
+static int zx_hdmi_audio_mute(struct device *dev, void *data,
+			      bool enable, int direction)
 {
 	struct zx_hdmi *hdmi = dev_get_drvdata(dev);
 
@@ -468,8 +468,9 @@ static const struct hdmi_codec_ops zx_hdmi_codec_ops = {
 	.audio_startup = zx_hdmi_audio_startup,
 	.hw_params = zx_hdmi_audio_hw_params,
 	.audio_shutdown = zx_hdmi_audio_shutdown,
-	.digital_mute = zx_hdmi_audio_digital_mute,
+	.mute_stream = zx_hdmi_audio_mute,
 	.get_eld = zx_hdmi_audio_get_eld,
+	.no_capture_mute = 1,
 };
 
 static struct hdmi_codec_pdata zx_hdmi_codec_pdata = {
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 6a995db51d6d..e201f62d62c0 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -686,8 +686,17 @@ EXPORT_SYMBOL(host1x_driver_register_full);
  */
 void host1x_driver_unregister(struct host1x_driver *driver)
 {
+	struct host1x *host1x;
+
 	driver_unregister(&driver->driver);
 
+	mutex_lock(&devices_lock);
+
+	list_for_each_entry(host1x, &devices, list)
+		host1x_detach_driver(host1x, driver);
+
+	mutex_unlock(&devices_lock);
+
 	mutex_lock(&drivers_lock);
 	list_del_init(&driver->list);
 	mutex_unlock(&drivers_lock);
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index d24344e91922..d0ebb70e2fdd 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -468,11 +468,18 @@ static int host1x_probe(struct platform_device *pdev)
 
 	err = host1x_register(host);
 	if (err < 0)
-		goto deinit_intr;
+		goto deinit_debugfs;
+
+	err = devm_of_platform_populate(&pdev->dev);
+	if (err < 0)
+		goto unregister;
 
 	return 0;
 
-deinit_intr:
+unregister:
+	host1x_unregister(host);
+deinit_debugfs:
+	host1x_debug_deinit(host);
 	host1x_intr_deinit(host);
 deinit_syncpt:
 	host1x_syncpt_deinit(host);