Merge tag 'drm-next-5.5-2019-11-01' of git://people.freedesktop.org/~agd5f/linux into drm-next

drm-next-5.5-2019-11-01:

amdgpu:
- Add EEPROM support for Arcturus
- Enable VCN encode support for Arcturus
- Misc PSP fixes
- Misc DC fixes
- swSMU cleanup

amdkfd:
- Misc cleanups
- Fix typo in cu bitmap parsing

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191101190607.3763-1-alexander.deucher@amd.com

33 files changed, 198 insertions, 111 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 4a2b413c8a25..0bb08e0e1611 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -107,7 +107,7 @@ struct amdgpu_mgpu_info
 	uint32_t			num_apu;
 };
 
-#define AMDGPU_MAX_TIMEOUT_PARAM_LENTH	256
+#define AMDGPU_MAX_TIMEOUT_PARAM_LENGTH	256
 
 /*
  * Modules parameters.
@@ -125,7 +125,7 @@ extern int amdgpu_disp_priority;
 extern int amdgpu_hw_i2c;
 extern int amdgpu_pcie_gen2;
 extern int amdgpu_msi;
-extern char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENTH];
+extern char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENGTH];
 extern int amdgpu_dpm;
 extern int amdgpu_fw_load_type;
 extern int amdgpu_aspm;
@@ -139,6 +139,7 @@ extern int amdgpu_vm_fragment_size;
 extern int amdgpu_vm_fault_stop;
 extern int amdgpu_vm_debug;
 extern int amdgpu_vm_update_mode;
+extern int amdgpu_exp_hw_support;
 extern int amdgpu_dc;
 extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 8c531793fe17..d3da9dde4ee1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -130,14 +130,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 				  adev->gfx.mec.queue_bitmap,
 				  KGD_MAX_QUEUES);
 
-		/* remove the KIQ bit as well */
-		if (adev->gfx.kiq.ring.sched.ready)
-			clear_bit(amdgpu_gfx_mec_queue_to_bit(adev,
-							  adev->gfx.kiq.ring.me - 1,
-							  adev->gfx.kiq.ring.pipe,
-							  adev->gfx.kiq.ring.queue),
-				  gpu_resources.queue_bitmap);
-
 		/* According to linux/bitmap.h we shouldn't use bitmap_clear if
 		 * nbits is not compile time constant
 		 */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index e1fbbebce4fd..b6713e0ed1b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -19,10 +19,6 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-
-#undef pr_fmt
-#define pr_fmt(fmt) "kfd2kgd: " fmt
-
 #include <linux/module.h>
 #include <linux/fdtable.h>
 #include <linux/uaccess.h>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index 0878f59ec340..61cd707158e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -19,9 +19,6 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-#undef pr_fmt
-#define pr_fmt(fmt) "kfd2kgd: " fmt
-
 #include <linux/mmu_context.h>
 #include "amdgpu.h"
 #include "amdgpu_amdkfd.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index c72246f2c08a..47c853ef1051 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -19,9 +19,6 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-
-#define pr_fmt(fmt) "kfd2kgd: " fmt
-
 #include <linux/mmu_context.h>
 
 #include "amdgpu.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index d2e7b4fe5659..ae6f5446262c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -19,9 +19,6 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-
-#define pr_fmt(fmt) "kfd2kgd: " fmt
-
 #include <linux/dma-buf.h>
 #include <linux/list.h>
 #include <linux/pagemap.h>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index cb94627fc0f4..693f17e78791 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1089,8 +1089,8 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 {
 	adev->debugfs_preempt =
 		debugfs_create_file("amdgpu_preempt_ib", 0600,
-				    adev->ddev->primary->debugfs_root,
-				    (void *)adev, &fops_ib_preempt);
+				    adev->ddev->primary->debugfs_root, adev,
+				    &fops_ib_preempt);
 	if (!(adev->debugfs_preempt)) {
 		DRM_ERROR("unable to create amdgpu_preempt_ib debugsfs file\n");
 		return -EIO;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 46218b36dc9e..d36d2b093539 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1877,6 +1877,19 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (r)
 		goto init_failed;
 
+	/*
+	 * retired pages will be loaded from eeprom and reserved here,
+	 * it should be called after amdgpu_device_ip_hw_init_phase2  since
+	 * for some ASICs the RAS EEPROM code relies on SMU fully functioning
+	 * for I2C communication which only true at this point.
+	 * recovery_init may fail, but it can free all resources allocated by
+	 * itself and its failure should not stop amdgpu init process.
+	 *
+	 * Note: theoretically, this should be called before all vram allocations
+	 * to protect retired page from abusing
+	 */
+	amdgpu_ras_recovery_init(adev);
+
 	if (adev->gmc.xgmi.num_physical_nodes > 1)
 		amdgpu_xgmi_add_device(adev);
 	amdgpu_amdkfd_device_init(adev);
@@ -2258,6 +2271,12 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 		/* displays are handled in phase1 */
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE)
 			continue;
+		/* PSP lost connection when err_event_athub occurs */
+		if (amdgpu_ras_intr_triggered() &&
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP) {
+			adev->ip_blocks[i].status.hw = false;
+			continue;
+		}
 		/* XXX handle errors */
 		r = adev->ip_blocks[i].version->funcs->suspend(adev);
 		/* XXX handle errors */
@@ -2615,9 +2634,9 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
 	else
 		adev->compute_timeout = MAX_SCHEDULE_TIMEOUT;
 
-	if (strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENTH)) {
+	if (strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {
 		while ((timeout_setting = strsep(&input, ",")) &&
-				strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENTH)) {
+				strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {
 			ret = kstrtol(timeout_setting, 0, &timeout);
 			if (ret)
 				return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index 5803fcbae22f..9cc270efee7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -911,7 +911,8 @@ int amdgpu_dpm_get_sclk(struct amdgpu_device *adev, bool low)
 	if (is_support_sw_smu(adev)) {
 		ret = smu_get_dpm_freq_range(&adev->smu, SMU_GFXCLK,
 					     low ? &clk_freq : NULL,
-					     !low ? &clk_freq : NULL);
+					     !low ? &clk_freq : NULL,
+					     true);
 		if (ret)
 			return 0;
 		return clk_freq * 100;
@@ -928,7 +929,8 @@ int amdgpu_dpm_get_mclk(struct amdgpu_device *adev, bool low)
 	if (is_support_sw_smu(adev)) {
 		ret = smu_get_dpm_freq_range(&adev->smu, SMU_UCLK,
 					     low ? &clk_freq : NULL,
-					     !low ? &clk_freq : NULL);
+					     !low ? &clk_freq : NULL,
+					     true);
 		if (ret)
 			return 0;
 		return clk_freq * 100;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index 1c5c0fd76dbf..2cfb677272af 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -298,12 +298,6 @@ enum amdgpu_pcie_gen {
 #define amdgpu_dpm_get_current_power_state(adev) \
 		((adev)->powerplay.pp_funcs->get_current_power_state((adev)->powerplay.pp_handle))
 
-#define amdgpu_smu_get_current_power_state(adev) \
-		((adev)->smu.ppt_funcs->get_current_power_state(&((adev)->smu)))
-
-#define amdgpu_smu_set_power_state(adev) \
-		((adev)->smu.ppt_funcs->set_power_state(&((adev)->smu)))
-
 #define amdgpu_dpm_get_pp_num_states(adev, data) \
 		((adev)->powerplay.pp_funcs->get_pp_num_states((adev)->powerplay.pp_handle, data))
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 7d16e6edda62..1d6ce018c8f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -84,9 +84,10 @@
  * - 3.33.0 - Fixes for GDS ENOMEM failures in AMDGPU_CS.
  * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches
  * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
+ * - 3.36.0 - Allow reading more status registers on si/cik
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	35
+#define KMS_DRIVER_MINOR	36
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
@@ -101,7 +102,7 @@ int amdgpu_disp_priority = 0;
 int amdgpu_hw_i2c = 0;
 int amdgpu_pcie_gen2 = -1;
 int amdgpu_msi = -1;
-char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENTH];
+char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENGTH];
 int amdgpu_dpm = -1;
 int amdgpu_fw_load_type = -1;
 int amdgpu_aspm = -1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 069515f57c2a..c9d1fada6188 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -319,8 +319,7 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
 	return r;
 }
 
-void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring,
-			      struct amdgpu_irq_src *irq)
+void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring)
 {
 	amdgpu_device_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
 	amdgpu_ring_fini(ring);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 35eff9e6ce16..459aa9059542 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -330,8 +330,7 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
 			     struct amdgpu_ring *ring,
 			     struct amdgpu_irq_src *irq);
 
-void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring,
-			      struct amdgpu_irq_src *irq);
+void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring);
 
 void amdgpu_gfx_kiq_fini(struct amdgpu_device *adev);
 int amdgpu_gfx_kiq_init(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index e1bad992e83b..4fb20e870e63 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -218,7 +218,7 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched);
 	struct dma_fence *fence = NULL, *finished;
 	struct amdgpu_job *job;
-	int r;
+	int r = 0;
 
 	job = to_amdgpu_job(sched_job);
 	finished = &job->base.s_fence->finished;
@@ -243,6 +243,8 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	job->fence = dma_fence_get(fence);
 
 	amdgpu_job_free_resources(job);
+
+	fence = r ? ERR_PTR(r) : fence;
 	return fence;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index d63866164496..f205f56e3358 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -161,7 +161,7 @@ static ssize_t amdgpu_get_dpm_state(struct device *dev,
 
 	if (is_support_sw_smu(adev)) {
 		if (adev->smu.ppt_funcs->get_current_power_state)
-			pm = amdgpu_smu_get_current_power_state(adev);
+			pm = smu_get_current_power_state(&adev->smu);
 		else
 			pm = adev->pm.dpm.user_state;
 	} else if (adev->powerplay.pp_funcs->get_current_power_state) {
@@ -907,7 +907,7 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_SCLK, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_SCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask);
 
@@ -954,7 +954,7 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_MCLK, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_MCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask);
 
@@ -994,7 +994,7 @@ static ssize_t amdgpu_set_pp_dpm_socclk(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_SOCCLK, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_SOCCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_SOCCLK, mask);
 
@@ -1034,7 +1034,7 @@ static ssize_t amdgpu_set_pp_dpm_fclk(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_FCLK, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_FCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_FCLK, mask);
 
@@ -1074,7 +1074,7 @@ static ssize_t amdgpu_set_pp_dpm_dcefclk(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_DCEFCLK, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_DCEFCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_DCEFCLK, mask);
 
@@ -1114,7 +1114,7 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_PCIE, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_PCIE, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask);
 
@@ -1306,7 +1306,7 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 	}
 	parameter[parameter_size] = profile_mode;
 	if (is_support_sw_smu(adev))
-		ret = smu_set_power_profile_mode(&adev->smu, parameter, parameter_size);
+		ret = smu_set_power_profile_mode(&adev->smu, parameter, parameter_size, true);
 	else if (adev->powerplay.pp_funcs->set_power_profile_mode)
 		ret = amdgpu_dpm_set_power_profile_mode(adev, parameter, parameter_size);
 	if (!ret)
@@ -2015,7 +2015,7 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev,
 	uint32_t limit = 0;
 
 	if (is_support_sw_smu(adev)) {
-		smu_get_power_limit(&adev->smu, &limit, true);
+		smu_get_power_limit(&adev->smu, &limit, true, true);
 		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_power_limit) {
 		adev->powerplay.pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, true);
@@ -2033,7 +2033,7 @@ static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev,
 	uint32_t limit = 0;
 
 	if (is_support_sw_smu(adev)) {
-		smu_get_power_limit(&adev->smu, &limit, false);
+		smu_get_power_limit(&adev->smu, &limit, false,  true);
 		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_power_limit) {
 		adev->powerplay.pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, false);
@@ -2830,6 +2830,19 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 		DRM_ERROR("failed to create device file pp_dpm_sclk\n");
 		return ret;
 	}
+
+	/* Arcturus does not support standalone mclk/socclk/fclk level setting */
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		dev_attr_pp_dpm_mclk.attr.mode &= ~S_IWUGO;
+		dev_attr_pp_dpm_mclk.store = NULL;
+
+		dev_attr_pp_dpm_socclk.attr.mode &= ~S_IWUGO;
+		dev_attr_pp_dpm_socclk.store = NULL;
+
+		dev_attr_pp_dpm_fclk.attr.mode &= ~S_IWUGO;
+		dev_attr_pp_dpm_fclk.store = NULL;
+	}
+
 	ret = device_create_file(adev->dev, &dev_attr_pp_dpm_mclk);
 	if (ret) {
 		DRM_ERROR("failed to create device file pp_dpm_mclk\n");
@@ -3013,7 +3026,8 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 		struct smu_dpm_context *smu_dpm = &adev->smu.smu_dpm;
 		smu_handle_task(&adev->smu,
 				smu_dpm->dpm_level,
-				AMD_PP_TASK_DISPLAY_CONFIG_CHANGE);
+				AMD_PP_TASK_DISPLAY_CONFIG_CHANGE,
+				true);
 	} else {
 		if (adev->powerplay.pp_funcs->dispatch_tasks) {
 			if (!amdgpu_device_has_dc_support(adev)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index b996b5bc5804..bbe9ac7e843f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -34,6 +34,8 @@
 #include "psp_v11_0.h"
 #include "psp_v12_0.h"
 
+#include "amdgpu_ras.h"
+
 static void psp_set_funcs(struct amdgpu_device *adev);
 
 static int psp_early_init(void *handle)
@@ -90,7 +92,7 @@ static int psp_sw_init(void *handle)
 
 	ret = psp_mem_training_init(psp);
 	if (ret) {
-		DRM_ERROR("Failed to initliaze memory training!\n");
+		DRM_ERROR("Failed to initialize memory training!\n");
 		return ret;
 	}
 	ret = psp_mem_training(psp, PSP_MEM_TRAIN_COLD_BOOT);
@@ -167,6 +169,13 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	while (*((unsigned int *)psp->fence_buf) != index) {
 		if (--timeout == 0)
 			break;
+		/*
+		 * Shouldn't wait for timeout when err_event_athub occurs,
+		 * because gpu reset thread triggered and lock resource should
+		 * be released for psp resume sequence.
+		 */
+		if (amdgpu_ras_intr_triggered())
+			break;
 		msleep(1);
 		amdgpu_asic_invalidate_hdp(psp->adev, NULL);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 6220394521e4..dab90c280476 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -68,6 +68,11 @@ const char *ras_block_string[] = {
 /* inject address is 52 bits */
 #define	RAS_UMC_INJECT_ADDR_LIMIT	(0x1ULL << 52)
 
+enum amdgpu_ras_retire_page_reservation {
+	AMDGPU_RAS_RETIRE_PAGE_RESERVED,
+	AMDGPU_RAS_RETIRE_PAGE_PENDING,
+	AMDGPU_RAS_RETIRE_PAGE_FAULT,
+};
 
 atomic_t amdgpu_ras_in_intr = ATOMIC_INIT(0);
 
@@ -153,8 +158,6 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
 		op = 1;
 	else if (sscanf(str, "inject %32s %8s", block_name, err) == 2)
 		op = 2;
-	else if (sscanf(str, "reboot %32s", block_name) == 1)
-		op = 3;
 	else if (str[0] && str[1] && str[2] && str[3])
 		/* ascii string, but commands are not matched. */
 		return -EINVAL;
@@ -218,12 +221,11 @@ static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
  * value to the address.
  *
  * Second member: struct ras_debug_if::op.
- * It has four kinds of operations.
+ * It has three kinds of operations.
  *
  * - 0: disable RAS on the block. Take ::head as its data.
  * - 1: enable RAS on the block. Take ::head as its data.
  * - 2: inject errors on the block. Take ::inject as its data.
- * - 3: reboot on unrecoverable error
  *
  * How to use the interface?
  * programs:
@@ -305,9 +307,6 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
 		/* data.inject.address is offset instead of absolute gpu address */
 		ret = amdgpu_ras_error_inject(adev, &data.inject);
 		break;
-	case 3:
-		amdgpu_ras_get_context(adev)->reboot = true;
-		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -559,15 +558,17 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 	if (!(!!enable ^ !!amdgpu_ras_is_feature_enabled(adev, head)))
 		return 0;
 
-	ret = psp_ras_enable_features(&adev->psp, &info, enable);
-	if (ret) {
-		DRM_ERROR("RAS ERROR: %s %s feature failed ret %d\n",
-				enable ? "enable":"disable",
-				ras_block_str(head->block),
-				ret);
-		if (ret == TA_RAS_STATUS__RESET_NEEDED)
-			return -EAGAIN;
-		return -EINVAL;
+	if (!amdgpu_ras_intr_triggered()) {
+		ret = psp_ras_enable_features(&adev->psp, &info, enable);
+		if (ret) {
+			DRM_ERROR("RAS ERROR: %s %s feature failed ret %d\n",
+					enable ? "enable":"disable",
+					ras_block_str(head->block),
+					ret);
+			if (ret == TA_RAS_STATUS__RESET_NEEDED)
+				return -EAGAIN;
+			return -EINVAL;
+		}
 	}
 
 	/* setup the obj */
@@ -815,11 +816,11 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 static char *amdgpu_ras_badpage_flags_str(unsigned int flags)
 {
 	switch (flags) {
-	case 0:
+	case AMDGPU_RAS_RETIRE_PAGE_RESERVED:
 		return "R";
-	case 1:
+	case AMDGPU_RAS_RETIRE_PAGE_PENDING:
 		return "P";
-	case 2:
+	case AMDGPU_RAS_RETIRE_PAGE_FAULT:
 	default:
 		return "F";
 	};
@@ -1037,6 +1038,17 @@ static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev)
 				adev, &amdgpu_ras_debugfs_ctrl_ops);
 	debugfs_create_file("ras_eeprom_reset", S_IWUGO | S_IRUGO, con->dir,
 				adev, &amdgpu_ras_debugfs_eeprom_ops);
+
+	/*
+	 * After one uncorrectable error happens, usually GPU recovery will
+	 * be scheduled. But due to the known problem in GPU recovery failing
+	 * to bring GPU back, below interface provides one direct way to
+	 * user to reboot system automatically in such case within
+	 * ERREVENT_ATHUB_INTERRUPT generated. Normal GPU recovery routine
+	 * will never be called.
+	 */
+	debugfs_create_bool("auto_reboot", S_IWUGO | S_IRUGO, con->dir,
+				&con->reboot);
 }
 
 void amdgpu_ras_debugfs_create(struct amdgpu_device *adev,
@@ -1289,13 +1301,13 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 		(*bps)[i] = (struct ras_badpage){
 			.bp = data->bps[i].retired_page,
 			.size = AMDGPU_GPU_PAGE_SIZE,
-			.flags = 0,
+			.flags = AMDGPU_RAS_RETIRE_PAGE_RESERVED,
 		};
 
 		if (data->last_reserved <= i)
-			(*bps)[i].flags = 1;
+			(*bps)[i].flags = AMDGPU_RAS_RETIRE_PAGE_PENDING;
 		else if (data->bps_bo[i] == NULL)
-			(*bps)[i].flags = 2;
+			(*bps)[i].flags = AMDGPU_RAS_RETIRE_PAGE_FAULT;
 	}
 
 	*count = data->count;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 20af0a17d00b..7de16c0c2f20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -216,6 +216,10 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 		ret = smu_v11_0_i2c_eeprom_control_init(&control->eeprom_accessor);
 		break;
 
+	case CHIP_ARCTURUS:
+		ret = smu_i2c_eeprom_init(&adev->smu, &control->eeprom_accessor);
+		break;
+
 	default:
 		return 0;
 	}
@@ -260,6 +264,9 @@ void amdgpu_ras_eeprom_fini(struct amdgpu_ras_eeprom_control *control)
 	case CHIP_VEGA20:
 		smu_v11_0_i2c_eeprom_control_fini(&control->eeprom_accessor);
 		break;
+	case CHIP_ARCTURUS:
+		smu_i2c_eeprom_fini(&adev->smu, &control->eeprom_accessor);
+		break;
 
 	default:
 		return;
@@ -364,7 +371,7 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 	struct eeprom_table_record *record;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 
-	if (adev->asic_type != CHIP_VEGA20)
+	if (adev->asic_type != CHIP_VEGA20 && adev->asic_type != CHIP_ARCTURUS)
 		return 0;
 
 	buffs = kcalloc(num, EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 6d34e766cd54..d5d916169226 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -486,15 +486,12 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 				struct ttm_operation_ctx *ctx,
 				struct ttm_mem_reg *new_mem)
 {
-	struct amdgpu_device *adev;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg tmp_mem;
 	struct ttm_place placements;
 	struct ttm_placement placement;
 	int r;
 
-	adev = amdgpu_ttm_adev(bo->bdev);
-
 	/* create space/pages for new_mem in GTT space */
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
@@ -545,15 +542,12 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
 				struct ttm_operation_ctx *ctx,
 				struct ttm_mem_reg *new_mem)
 {
-	struct amdgpu_device *adev;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg tmp_mem;
 	struct ttm_placement placement;
 	struct ttm_place placements;
 	int r;
 
-	adev = amdgpu_ttm_adev(bo->bdev);
-
 	/* make space in GTT for old_mem buffer */
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
@@ -1220,11 +1214,8 @@ static struct ttm_backend_func amdgpu_backend_func = {
 static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
 					   uint32_t page_flags)
 {
-	struct amdgpu_device *adev;
 	struct amdgpu_ttm_tt *gtt;
 
-	adev = amdgpu_ttm_adev(bo->bdev);
-
 	gtt = kzalloc(sizeof(struct amdgpu_ttm_tt), GFP_KERNEL);
 	if (gtt == NULL) {
 		return NULL;
@@ -1811,17 +1802,6 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 #endif
 
 	/*
-	 * retired pages will be loaded from eeprom and reserved here,
-	 * it should be called after ttm init since new bo may be created,
-	 * recovery_init may fail, but it can free all resources allocated by
-	 * itself and its failure should not stop amdgpu init process.
-	 *
-	 * Note: theoretically, this should be called before all vram allocations
-	 * to protect retired page from abusing
-	 */
-	amdgpu_ras_recovery_init(adev);
-
-	/*
 	 *The reserved vram for firmware must be pinned to the specified
 	 *place on the VRAM, so reserve it early.
 	 */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index b2c364b8695f..b4dd89af6f09 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -39,6 +39,8 @@
 #include "cikd.h"
 #include "uvd/uvd_4_2_d.h"
 
+#include "amdgpu_ras.h"
+
 /* 1 second timeout */
 #define UVD_IDLE_TIMEOUT	msecs_to_jiffies(1000)
 
@@ -372,7 +374,13 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 		if (!adev->uvd.inst[j].saved_bo)
 			return -ENOMEM;
 
-		memcpy_fromio(adev->uvd.inst[j].saved_bo, ptr, size);
+		/* re-write 0 since err_event_athub will corrupt VCPU buffer */
+		if (amdgpu_ras_intr_triggered()) {
+			DRM_WARN("UVD VCPU state may lost due to RAS ERREVENT_ATHUB_INTERRUPT\n");
+			memset(adev->uvd.inst[j].saved_bo, 0, size);
+		} else {
+			memcpy_fromio(adev->uvd.inst[j].saved_bo, ptr, size);
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index fc8b34480f66..2d64d270725d 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -966,6 +966,25 @@ static bool cik_read_bios_from_rom(struct amdgpu_device *adev,
 
 static const struct amdgpu_allowed_register_entry cik_allowed_read_registers[] = {
 	{mmGRBM_STATUS},
+	{mmGRBM_STATUS2},
+	{mmGRBM_STATUS_SE0},
+	{mmGRBM_STATUS_SE1},
+	{mmGRBM_STATUS_SE2},
+	{mmGRBM_STATUS_SE3},
+	{mmSRBM_STATUS},
+	{mmSRBM_STATUS2},
+	{mmSDMA0_STATUS_REG + SDMA0_REGISTER_OFFSET},
+	{mmSDMA0_STATUS_REG + SDMA1_REGISTER_OFFSET},
+	{mmCP_STAT},
+	{mmCP_STALLED_STAT1},
+	{mmCP_STALLED_STAT2},
+	{mmCP_STALLED_STAT3},
+	{mmCP_CPF_BUSY_STAT},
+	{mmCP_CPF_STALLED_STAT1},
+	{mmCP_CPF_STATUS},
+	{mmCP_CPC_BUSY_STAT},
+	{mmCP_CPC_STALLED_STAT1},
+	{mmCP_CPC_STATUS},
 	{mmGB_ADDR_CONFIG},
 	{mmMC_ARB_RAMCFG},
 	{mmGB_TILE_MODE0},
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index b2ad928f60ab..e7bab4f094b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -93,7 +93,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x00400014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_CPF_CLK_CTRL, 0xfcff8fff, 0xf8000100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0x60000ff0, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000000, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -140,7 +140,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x003c0014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xf8ff0fff, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000ff0, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -179,7 +179,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0x003e001f, 0x003c0014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xffffcfff, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0xffff0fff, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -1442,7 +1442,7 @@ static int gfx_v10_0_sw_fini(void *handle)
 		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
 
 	amdgpu_gfx_mqd_sw_fini(adev);
-	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring, &adev->gfx.kiq.irq);
+	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring);
 	amdgpu_gfx_kiq_fini(adev);
 
 	gfx_v10_0_pfp_fini(adev);
@@ -3106,6 +3106,7 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring *ring)
 			memcpy(mqd, adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS], sizeof(*mqd));
 		/* reset the ring */
 		ring->wptr = 0;
+		adev->wb.wb[ring->wptr_offs] = 0;
 		amdgpu_ring_clear_ring(ring);
 #ifdef BRING_UP_DEBUG
 		mutex_lock(&adev->srbm_mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 87dd55e9d72b..ffbde9136372 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -2103,7 +2103,7 @@ static int gfx_v8_0_sw_fini(void *handle)
 		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
 
 	amdgpu_gfx_mqd_sw_fini(adev);
-	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring, &adev->gfx.kiq.irq);
+	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring);
 	amdgpu_gfx_kiq_fini(adev);
 
 	gfx_v8_0_mec_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 47e256b6a0e5..39297baedfb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -703,6 +703,7 @@ static const struct soc15_reg_golden golden_settings_gc_9_4_1_arct[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_3_ARCT, 0x3fffffff, 0x2ebd9fe3),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_4_ARCT, 0x3fffffff, 0xb90f5b1),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_5_ARCT, 0x3ff, 0x135),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_CONFIG, 0xffffffff, 0x011A0000),
 };
 
 static const u32 GFX_RLC_SRM_INDEX_CNTL_ADDR_OFFSETS[] =
@@ -2153,7 +2154,7 @@ static int gfx_v9_0_sw_fini(void *handle)
 		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
 
 	amdgpu_gfx_mqd_sw_fini(adev);
-	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring, &adev->gfx.kiq.irq);
+	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring);
 	amdgpu_gfx_kiq_fini(adev);
 
 	gfx_v9_0_mec_fini(adev);
@@ -3736,8 +3737,10 @@ static int gfx_v9_0_hw_fini(void *handle)
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 
-	/* disable KCQ to avoid CPC touch memory not valid anymore */
-	gfx_v9_0_kcq_disable(adev);
+	/* DF freeze and kcq disable will fail */
+	if (!amdgpu_ras_intr_triggered())
+		/* disable KCQ to avoid CPC touch memory not valid anymore */
+		gfx_v9_0_kcq_disable(adev);
 
 	if (amdgpu_sriov_vf(adev)) {
 		gfx_v9_0_cp_gfx_enable(adev, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index b601c6740ef5..b4f32d853ca1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -155,6 +155,15 @@ static void gfxhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL2, tmp);
 
 	tmp = mmGCVM_L2_CNTL3_DEFAULT;
+	if (adev->gmc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL3, tmp);
 
 	tmp = mmGCVM_L2_CNTL4_DEFAULT;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index fb48622c2abd..6e1b25bd1fe7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -309,6 +309,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	job->vm_pd_addr = amdgpu_gmc_pd_addr(adev->gart.bo);
 	job->vm_needs_flush = true;
+	job->ibs->ptr[job->ibs->length_dw++] = ring->funcs->nop;
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 2eea702de8ee..945533634711 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -142,6 +142,15 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL2, tmp);
 
 	tmp = mmMMVM_L2_CNTL3_DEFAULT;
+	if (adev->gmc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL3, tmp);
 
 	tmp = mmMMVM_L2_CNTL4_DEFAULT;
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 46206a1a1f4d..a55a2e83fb19 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -178,6 +178,7 @@ static struct soc15_allowed_register_entry nv_allowed_read_registers[] = {
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_BUSY_STAT)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STALLED_STAT1)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STATUS)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_BUSY_STAT)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STALLED_STAT1)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STATUS)},
 	{ SOC15_REG_ENTRY(GC, 0, mmGB_ADDR_CONFIG)},
@@ -298,7 +299,7 @@ nv_asic_reset_method(struct amdgpu_device *adev)
 {
 	struct smu_context *smu = &adev->smu;
 
-	if (smu_baco_is_support(smu))
+	if (!amdgpu_sriov_vf(adev) && smu_baco_is_support(smu))
 		return AMD_RESET_METHOD_BACO;
 	else
 		return AMD_RESET_METHOD_MODE1;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index ace6e6c5629c..ffeaa2f5588d 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -244,7 +244,7 @@ static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 	/* Copy PSP KDB binary to memory */
 	memcpy(psp->fw_pri_buf, psp->kdb_start_addr, psp->kdb_bin_size);
 
-	/* Provide the sys driver to bootloader */
+	/* Provide the PSP KDB to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
 	       (uint32_t)(psp->fw_pri_mc_addr >> 20));
 	psp_gfxdrv_command_reg = PSP_BL__LOAD_KEY_DATABASE;
@@ -467,6 +467,14 @@ static int psp_v11_0_ring_create(struct psp_context *psp,
 				   0x80000000, 0x8000FFFF, false);
 
 	} else {
+		/* Wait for sOS ready for ring creation */
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64),
+				   0x80000000, 0x80000000, false);
+		if (ret) {
+			DRM_ERROR("Failed to wait for sOS ready for ring creation\n");
+			return ret;
+		}
+
 		/* Write low address of the ring to C2PMSG_69 */
 		psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr);
 		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_69, psp_ring_reg);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 4fb9f1929809..4ef4d31f5231 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -254,6 +254,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000)
 };
 
 static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index 493af42152f2..29024e64c886 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -975,6 +975,17 @@ static void si_smc_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 
 static struct amdgpu_allowed_register_entry si_allowed_read_registers[] = {
 	{GRBM_STATUS},
+	{mmGRBM_STATUS2},
+	{mmGRBM_STATUS_SE0},
+	{mmGRBM_STATUS_SE1},
+	{mmSRBM_STATUS},
+	{mmSRBM_STATUS2},
+	{DMA_STATUS_REG + DMA0_REGISTER_OFFSET},
+	{DMA_STATUS_REG + DMA1_REGISTER_OFFSET},
+	{mmCP_STAT},
+	{mmCP_STALLED_STAT1},
+	{mmCP_STALLED_STAT2},
+	{mmCP_STALLED_STAT3},
 	{GB_ADDR_CONFIG},
 	{MC_ARB_RAMCFG},
 	{GB_TILE_MODE0},
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 9be0168217f5..741b564b4aa5 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -339,6 +339,7 @@ static struct soc15_allowed_register_entry soc15_allowed_read_registers[] = {
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_BUSY_STAT)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STALLED_STAT1)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STATUS)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_BUSY_STAT)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STALLED_STAT1)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STATUS)},
 	{ SOC15_REG_ENTRY(GC, 0, mmGB_ADDR_CONFIG)},
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index b3623ed3dc42..03083e5f731a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -265,9 +265,6 @@ static int vcn_v2_5_hw_init(void *handle)
 
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
 			ring = &adev->vcn.inst[j].ring_enc[i];
-			/* disable encode rings till the robustness of the FW */
-			ring->sched.ready = false;
-			continue;
 			r = amdgpu_ring_test_helper(ring);
 			if (r)
 				goto done;