Merge drm/drm-next into drm-misc-next

Daniel needs -rc2 in drm-misc-next to merge some patches

Signed-off-by: Maxime Ripard <maxime@cerno.tech>

230 files changed, 4903 insertions, 1863 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 4009d2e30727..87f095dc385c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -49,6 +49,8 @@
 #include <linux/rbtree.h>
 #include <linux/hashtable.h>
 #include <linux/dma-fence.h>
+#include <linux/pci.h>
+#include <linux/aer.h>
 
 #include <drm/ttm/ttm_bo_api.h>
 #include <drm/ttm/ttm_bo_driver.h>
@@ -102,6 +104,7 @@
 #include "amdgpu_mes.h"
 #include "amdgpu_umc.h"
 #include "amdgpu_mmhub.h"
+#include "amdgpu_gfxhub.h"
 #include "amdgpu_df.h"
 
 #define MAX_GPU_INSTANCE		16
@@ -879,6 +882,9 @@ struct amdgpu_device {
 	/* mmhub */
 	struct amdgpu_mmhub		mmhub;
 
+	/* gfxhub */
+	struct amdgpu_gfxhub		gfxhub;
+
 	/* gfx */
 	struct amdgpu_gfx		gfx;
 
@@ -987,6 +993,9 @@ struct amdgpu_device {
 	atomic_t			throttling_logging_enabled;
 	struct ratelimit_state		throttling_logging_rs;
 	uint32_t			ras_features;
+
+	bool                            in_pci_err_recovery;
+	struct pci_saved_state          *pci_state;
 };
 
 static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)
@@ -1011,18 +1020,32 @@ int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
 
 void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
 			       uint32_t *buf, size_t size, bool write);
-uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
+uint32_t amdgpu_device_rreg(struct amdgpu_device *adev,
+			    uint32_t reg, uint32_t acc_flags);
+void amdgpu_device_wreg(struct amdgpu_device *adev,
+			uint32_t reg, uint32_t v,
 			uint32_t acc_flags);
-void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
-		    uint32_t acc_flags);
-void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
-		    uint32_t acc_flags);
+void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
+			     uint32_t reg, uint32_t v);
 void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value);
 uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset);
 
 u32 amdgpu_io_rreg(struct amdgpu_device *adev, u32 reg);
 void amdgpu_io_wreg(struct amdgpu_device *adev, u32 reg, u32 v);
 
+u32 amdgpu_device_indirect_rreg(struct amdgpu_device *adev,
+				u32 pcie_index, u32 pcie_data,
+				u32 reg_addr);
+u64 amdgpu_device_indirect_rreg64(struct amdgpu_device *adev,
+				  u32 pcie_index, u32 pcie_data,
+				  u32 reg_addr);
+void amdgpu_device_indirect_wreg(struct amdgpu_device *adev,
+				 u32 pcie_index, u32 pcie_data,
+				 u32 reg_addr, u32 reg_data);
+void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev,
+				   u32 pcie_index, u32 pcie_data,
+				   u32 reg_addr, u64 reg_data);
+
 bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type);
 bool amdgpu_device_has_dc_support(struct amdgpu_device *adev);
 
@@ -1033,8 +1056,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
  */
 #define AMDGPU_REGS_NO_KIQ    (1<<1)
 
-#define RREG32_NO_KIQ(reg) amdgpu_mm_rreg(adev, (reg), AMDGPU_REGS_NO_KIQ)
-#define WREG32_NO_KIQ(reg, v) amdgpu_mm_wreg(adev, (reg), (v), AMDGPU_REGS_NO_KIQ)
+#define RREG32_NO_KIQ(reg) amdgpu_device_rreg(adev, (reg), AMDGPU_REGS_NO_KIQ)
+#define WREG32_NO_KIQ(reg, v) amdgpu_device_wreg(adev, (reg), (v), AMDGPU_REGS_NO_KIQ)
 
 #define RREG32_KIQ(reg) amdgpu_kiq_rreg(adev, (reg))
 #define WREG32_KIQ(reg, v) amdgpu_kiq_wreg(adev, (reg), (v))
@@ -1042,9 +1065,9 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define RREG8(reg) amdgpu_mm_rreg8(adev, (reg))
 #define WREG8(reg, v) amdgpu_mm_wreg8(adev, (reg), (v))
 
-#define RREG32(reg) amdgpu_mm_rreg(adev, (reg), 0)
-#define DREG32(reg) printk(KERN_INFO "REGISTER: " #reg " : 0x%08X\n", amdgpu_mm_rreg(adev, (reg), 0))
-#define WREG32(reg, v) amdgpu_mm_wreg(adev, (reg), (v), 0)
+#define RREG32(reg) amdgpu_device_rreg(adev, (reg), 0)
+#define DREG32(reg) printk(KERN_INFO "REGISTER: " #reg " : 0x%08X\n", amdgpu_device_rreg(adev, (reg), 0))
+#define WREG32(reg, v) amdgpu_device_wreg(adev, (reg), (v), 0)
 #define REG_SET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK)
 #define REG_GET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK)
 #define RREG32_PCIE(reg) adev->pcie_rreg(adev, (reg))
@@ -1090,7 +1113,7 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 		WREG32_SMC(_Reg, tmp);                          \
 	} while (0)
 
-#define DREG32_SYS(sqf, adev, reg) seq_printf((sqf), #reg " : 0x%08X\n", amdgpu_mm_rreg((adev), (reg), false))
+#define DREG32_SYS(sqf, adev, reg) seq_printf((sqf), #reg " : 0x%08X\n", amdgpu_device_rreg((adev), (reg), false))
 #define RREG32_IO(reg) amdgpu_io_rreg(adev, (reg))
 #define WREG32_IO(reg, v) amdgpu_io_wreg(adev, (reg), (v))
 
@@ -1260,6 +1283,15 @@ static inline int amdgpu_dm_display_resume(struct amdgpu_device *adev) { return
 void amdgpu_register_gpu_instance(struct amdgpu_device *adev);
 void amdgpu_unregister_gpu_instance(struct amdgpu_device *adev);
 
+pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev,
+					   pci_channel_state_t state);
+pci_ers_result_t amdgpu_pci_mmio_enabled(struct pci_dev *pdev);
+pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev);
+void amdgpu_pci_resume(struct pci_dev *pdev);
+
+bool amdgpu_device_cache_pci_state(struct pci_dev *pdev);
+bool amdgpu_device_load_pci_state(struct pci_dev *pdev);
+
 #include "amdgpu_object.h"
 
 /* used by df_v3_6.c and amdgpu_pmu.c */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 4a93b880c6bf..165b02e267b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -806,8 +806,8 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 	}
 	adev->atif = atif;
 
-	if (atif->notifications.brightness_change) {
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
+	if (atif->notifications.brightness_change) {
 		if (amdgpu_device_has_dc_support(adev)) {
 #if defined(CONFIG_DRM_AMD_DC)
 			struct amdgpu_display_manager *dm = &adev->dm;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index edff1b7f282a..0544460653b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -36,6 +36,8 @@
  */
 uint64_t amdgpu_amdkfd_total_mem_size;
 
+static bool kfd_initialized;
+
 int amdgpu_amdkfd_init(void)
 {
 	struct sysinfo si;
@@ -51,19 +53,26 @@ int amdgpu_amdkfd_init(void)
 #else
 	ret = -ENOENT;
 #endif
+	kfd_initialized = !ret;
 
 	return ret;
 }
 
 void amdgpu_amdkfd_fini(void)
 {
-	kgd2kfd_exit();
+	if (kfd_initialized) {
+		kgd2kfd_exit();
+		kfd_initialized = false;
+	}
 }
 
 void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 {
 	bool vf = amdgpu_sriov_vf(adev);
 
+	if (!kfd_initialized)
+		return;
+
 	adev->kfd.dev = kgd2kfd_probe((struct kgd_dev *)adev,
 				      adev->pdev, adev->asic_type, vf);
 
@@ -572,6 +581,13 @@ uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd)
 	return adev->rev_id;
 }
 
+int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	return adev->gmc.noretry;
+}
+
 int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 				uint32_t vmid, uint64_t gpu_addr,
 				uint32_t *ib_cmd, uint32_t ib_len)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index a10507ecb750..ea391ca7f2f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -181,6 +181,7 @@ uint64_t amdgpu_amdkfd_get_unique_id(struct kgd_dev *kgd);
 uint64_t amdgpu_amdkfd_get_mmio_remap_phys_addr(struct kgd_dev *kgd);
 uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd);
 uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd);
+int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd);
 uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *src);
 
 /* Read user wptr from a specified user address space with page fault
@@ -207,11 +208,11 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
 	})
 
 /* GPUVM API */
-int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid,
+int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid,
 					void **vm, void **process_info,
 					struct dma_fence **ef);
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
-					struct file *filp, unsigned int pasid,
+					struct file *filp, u32 pasid,
 					void **vm, void **process_info,
 					struct dma_fence **ef);
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
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 df0aab0fc67e..4763bab7a4d0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -32,7 +32,6 @@
 #include "v10_structs.h"
 #include "nv.h"
 #include "nvd.h"
-#include "gfxhub_v2_0.h"
 
 enum hqd_dequeue_request_type {
 	NO_ACTION = 0,
@@ -105,7 +104,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
@@ -753,7 +752,7 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 	}
 
 	/* SDMA is on gfxhub as well for Navi1* series */
-	gfxhub_v2_0_setup_vm_pt_regs(adev, vmid, page_table_base);
+	adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
 }
 
 const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
index 5b38f848b772..50016bf9c427 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
@@ -31,7 +31,6 @@
 #include "v10_structs.h"
 #include "nv.h"
 #include "nvd.h"
-#include "gfxhub_v2_1.h"
 
 enum hqd_dequeue_request_type {
 	NO_ACTION = 0,
@@ -657,7 +656,7 @@ static void set_vm_context_page_table_base_v10_3(struct kgd_dev *kgd, uint32_t v
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 
 	/* SDMA is on gfxhub as well for Navi1* series */
-	gfxhub_v2_1_setup_vm_pt_regs(adev, vmid, page_table_base);
+	adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
 }
 
 #if 0
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 275f20399373..b91d27e39bad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -139,7 +139,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index 4997189d8b36..5ce0ce704a21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -96,7 +96,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
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 e6aede725197..43b18863a8b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -36,9 +36,7 @@
 #include "v9_structs.h"
 #include "soc15.h"
 #include "soc15d.h"
-#include "mmhub_v1_0.h"
-#include "gfxhub_v1_0.h"
-
+#include "gfx_v9_0.h"
 
 enum hqd_dequeue_request_type {
 	NO_ACTION = 0,
@@ -110,7 +108,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
@@ -703,7 +701,180 @@ void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
 
 	adev->mmhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
 
-	gfxhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
+	adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
+}
+
+static void lock_spi_csq_mutexes(struct amdgpu_device *adev)
+{
+	mutex_lock(&adev->srbm_mutex);
+	mutex_lock(&adev->grbm_idx_mutex);
+
+}
+
+static void unlock_spi_csq_mutexes(struct amdgpu_device *adev)
+{
+	mutex_unlock(&adev->grbm_idx_mutex);
+	mutex_unlock(&adev->srbm_mutex);
+}
+
+/**
+ * @get_wave_count: Read device registers to get number of waves in flight for
+ * a particular queue. The method also returns the VMID associated with the
+ * queue.
+ *
+ * @adev: Handle of device whose registers are to be read
+ * @queue_idx: Index of queue in the queue-map bit-field
+ * @wave_cnt: Output parameter updated with number of waves in flight
+ * @vmid: Output parameter updated with VMID of queue whose wave count
+ * is being collected
+ */
+static void get_wave_count(struct amdgpu_device *adev, int queue_idx,
+		int *wave_cnt, int *vmid)
+{
+	int pipe_idx;
+	int queue_slot;
+	unsigned int reg_val;
+
+	/*
+	 * Program GRBM with appropriate MEID, PIPEID, QUEUEID and VMID
+	 * parameters to read out waves in flight. Get VMID if there are
+	 * non-zero waves in flight.
+	 */
+	*vmid = 0xFF;
+	*wave_cnt = 0;
+	pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe;
+	queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe;
+	soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0);
+	reg_val = RREG32(SOC15_REG_OFFSET(GC, 0, mmSPI_CSQ_WF_ACTIVE_COUNT_0) +
+			 queue_slot);
+	*wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK;
+	if (*wave_cnt != 0)
+		*vmid = (RREG32_SOC15(GC, 0, mmCP_HQD_VMID) &
+			 CP_HQD_VMID__VMID_MASK) >> CP_HQD_VMID__VMID__SHIFT;
+}
+
+/**
+ * @kgd_gfx_v9_get_cu_occupancy: Reads relevant registers associated with each
+ * shader engine and aggregates the number of waves that are in flight for the
+ * process whose pasid is provided as a parameter. The process could have ZERO
+ * or more queues running and submitting waves to compute units.
+ *
+ * @kgd: Handle of device from which to get number of waves in flight
+ * @pasid: Identifies the process for which this query call is invoked
+ * @wave_cnt: Output parameter updated with number of waves in flight that
+ * belong to process with given pasid
+ * @max_waves_per_cu: Output parameter updated with maximum number of waves
+ * possible per Compute Unit
+ *
+ * @note: It's possible that the device has too many queues (oversubscription)
+ * in which case a VMID could be remapped to a different PASID. This could lead
+ * to an iaccurate wave count. Following is a high-level sequence:
+ *    Time T1: vmid = getVmid(); vmid is associated with Pasid P1
+ *    Time T2: passId = getPasId(vmid); vmid is associated with Pasid P2
+ * In the sequence above wave count obtained from time T1 will be incorrectly
+ * lost or added to total wave count.
+ *
+ * The registers that provide the waves in flight are:
+ *
+ *  SPI_CSQ_WF_ACTIVE_STATUS - bit-map of queues per pipe. The bit is ON if a
+ *  queue is slotted, OFF if there is no queue. A process could have ZERO or
+ *  more queues slotted and submitting waves to be run on compute units. Even
+ *  when there is a queue it is possible there could be zero wave fronts, this
+ *  can happen when queue is waiting on top-of-pipe events - e.g. waitRegMem
+ *  command
+ *
+ *  For each bit that is ON from above:
+ *
+ *    Read (SPI_CSQ_WF_ACTIVE_COUNT_0 + queue_idx) register. It provides the
+ *    number of waves that are in flight for the queue at specified index. The
+ *    index ranges from 0 to 7.
+ *
+ *    If non-zero waves are in flight, read CP_HQD_VMID register to obtain VMID
+ *    of the wave(s).
+ *
+ *    Determine if VMID from above step maps to pasid provided as parameter. If
+ *    it matches agrregate the wave count. That the VMID will not match pasid is
+ *    a normal condition i.e. a device is expected to support multiple queues
+ *    from multiple proceses.
+ *
+ *  Reading registers referenced above involves programming GRBM appropriately
+ */
+static void kgd_gfx_v9_get_cu_occupancy(struct kgd_dev *kgd, int pasid,
+		int *pasid_wave_cnt, int *max_waves_per_cu)
+{
+	int qidx;
+	int vmid;
+	int se_idx;
+	int sh_idx;
+	int se_cnt;
+	int sh_cnt;
+	int wave_cnt;
+	int queue_map;
+	int pasid_tmp;
+	int max_queue_cnt;
+	int vmid_wave_cnt = 0;
+	struct amdgpu_device *adev;
+	DECLARE_BITMAP(cp_queue_bitmap, KGD_MAX_QUEUES);
+
+	adev = get_amdgpu_device(kgd);
+	lock_spi_csq_mutexes(adev);
+	soc15_grbm_select(adev, 1, 0, 0, 0);
+
+	/*
+	 * Iterate through the shader engines and arrays of the device
+	 * to get number of waves in flight
+	 */
+	bitmap_complement(cp_queue_bitmap, adev->gfx.mec.queue_bitmap,
+			  KGD_MAX_QUEUES);
+	max_queue_cnt = adev->gfx.mec.num_pipe_per_mec *
+			adev->gfx.mec.num_queue_per_pipe;
+	sh_cnt = adev->gfx.config.max_sh_per_se;
+	se_cnt = adev->gfx.config.max_shader_engines;
+	for (se_idx = 0; se_idx < se_cnt; se_idx++) {
+		for (sh_idx = 0; sh_idx < sh_cnt; sh_idx++) {
+
+			gfx_v9_0_select_se_sh(adev, se_idx, sh_idx, 0xffffffff);
+			queue_map = RREG32(SOC15_REG_OFFSET(GC, 0,
+					   mmSPI_CSQ_WF_ACTIVE_STATUS));
+
+			/*
+			 * Assumption: queue map encodes following schema: four
+			 * pipes per each micro-engine, with each pipe mapping
+			 * eight queues. This schema is true for GFX9 devices
+			 * and must be verified for newer device families
+			 */
+			for (qidx = 0; qidx < max_queue_cnt; qidx++) {
+
+				/* Skip qeueus that are not associated with
+				 * compute functions
+				 */
+				if (!test_bit(qidx, cp_queue_bitmap))
+					continue;
+
+				if (!(queue_map & (1 << qidx)))
+					continue;
+
+				/* Get number of waves in flight and aggregate them */
+				get_wave_count(adev, qidx, &wave_cnt, &vmid);
+				if (wave_cnt != 0) {
+					pasid_tmp =
+					  RREG32(SOC15_REG_OFFSET(OSSSYS, 0,
+						 mmIH_VMID_0_LUT) + vmid);
+					if (pasid_tmp == pasid)
+						vmid_wave_cnt += wave_cnt;
+				}
+			}
+		}
+	}
+
+	gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+	soc15_grbm_select(adev, 0, 0, 0, 0);
+	unlock_spi_csq_mutexes(adev);
+
+	/* Update the output parameters and return */
+	*pasid_wave_cnt = vmid_wave_cnt;
+	*max_waves_per_cu = adev->gfx.cu_info.simd_per_cu *
+				adev->gfx.cu_info.max_waves_per_simd;
 }
 
 const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
@@ -726,4 +897,5 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
+	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
index f098e88d3a0d..fc8934b86d93 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -26,7 +26,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 		uint32_t sh_mem_config,
 		uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit,
 		uint32_t sh_mem_bases);
-int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 		unsigned int vmid);
 int kgd_gfx_v9_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id);
 int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 64d4b5ff95d6..054a1c2d5054 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -996,7 +996,7 @@ create_evict_fence_fail:
 	return ret;
 }
 
-int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid,
+int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid,
 					  void **vm, void **process_info,
 					  struct dma_fence **ef)
 {
@@ -1032,7 +1032,7 @@ amdgpu_vm_init_fail:
 }
 
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
-					   struct file *filp, unsigned int pasid,
+					   struct file *filp, u32 pasid,
 					   void **vm, void **process_info,
 					   struct dma_fence **ef)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 17c010d0431f..b4df6460e45a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -543,6 +543,7 @@ int amdgpu_mem_train_support(struct amdgpu_device *adev)
 		case HW_REV(11, 0, 0):
 		case HW_REV(11, 0, 5):
 		case HW_REV(11, 0, 7):
+		case HW_REV(11, 0, 11):
 			ret = 1;
 			break;
 		default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index 3e35a8f2c5e5..7abe9500c0c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -616,7 +616,7 @@ static bool amdgpu_atpx_detect(void)
 	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
 		vga_count++;
 
-		has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true);
+		has_atpx |= amdgpu_atpx_pci_probe_handle(pdev);
 
 		parent_pdev = pci_upstream_bridge(pdev);
 		d3_supported |= parent_pdev && parent_pdev->bridge_d3;
@@ -626,7 +626,7 @@ static bool amdgpu_atpx_detect(void)
 	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
 		vga_count++;
 
-		has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true);
+		has_atpx |= amdgpu_atpx_pci_probe_handle(pdev);
 
 		parent_pdev = pci_upstream_bridge(pdev);
 		d3_supported |= parent_pdev && parent_pdev->bridge_d3;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index a5e08dc54e4a..065937482239 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -267,7 +267,7 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 		} else {
 			r = get_user(value, (uint32_t *)buf);
 			if (!r)
-				amdgpu_mm_wreg_mmio_rlc(adev, *pos >> 2, value, 0);
+				amdgpu_mm_wreg_mmio_rlc(adev, *pos >> 2, value);
 		}
 		if (r) {
 			result = r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f7307af76452..37da3537ba2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -80,8 +80,6 @@ MODULE_FIRMWARE("amdgpu/renoir_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
-MODULE_FIRMWARE("amdgpu/sienna_cichlid_gpu_info.bin");
-MODULE_FIRMWARE("amdgpu/navy_flounder_gpu_info.bin");
 
 #define AMDGPU_RESUME_MS		2000
 
@@ -303,10 +301,10 @@ void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
 }
 
 /*
- * MMIO register access helper functions.
+ * register access helper functions.
  */
 /**
- * amdgpu_mm_rreg - read a memory mapped IO register
+ * amdgpu_device_rreg - read a memory mapped IO or indirect register
  *
  * @adev: amdgpu_device pointer
  * @reg: dword aligned register offset
@@ -314,30 +312,29 @@ void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
  *
  * Returns the 32 bit value from the offset specified.
  */
-uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
-			uint32_t acc_flags)
+uint32_t amdgpu_device_rreg(struct amdgpu_device *adev,
+			    uint32_t reg, uint32_t acc_flags)
 {
 	uint32_t ret;
 
-	if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev) &&
-	    down_read_trylock(&adev->reset_sem)) {
-		ret = amdgpu_kiq_rreg(adev, reg);
-		up_read(&adev->reset_sem);
-		return ret;
-	}
-
-	if ((reg * 4) < adev->rmmio_size)
-		ret = readl(((void __iomem *)adev->rmmio) + (reg * 4));
-	else {
-		unsigned long flags;
+	if (adev->in_pci_err_recovery)
+		return 0;
 
-		spin_lock_irqsave(&adev->mmio_idx_lock, flags);
-		writel((reg * 4), ((void __iomem *)adev->rmmio) + (mmMM_INDEX * 4));
-		ret = readl(((void __iomem *)adev->rmmio) + (mmMM_DATA * 4));
-		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
+	if ((reg * 4) < adev->rmmio_size) {
+		if (!(acc_flags & AMDGPU_REGS_NO_KIQ) &&
+		    amdgpu_sriov_runtime(adev) &&
+		    down_read_trylock(&adev->reset_sem)) {
+			ret = amdgpu_kiq_rreg(adev, reg);
+			up_read(&adev->reset_sem);
+		} else {
+			ret = readl(((void __iomem *)adev->rmmio) + (reg * 4));
+		}
+	} else {
+		ret = adev->pcie_rreg(adev, reg * 4);
 	}
 
-	trace_amdgpu_mm_rreg(adev->pdev->device, reg, ret);
+	trace_amdgpu_device_rreg(adev->pdev->device, reg, ret);
+
 	return ret;
 }
 
@@ -355,7 +352,11 @@ uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
  *
  * Returns the 8 bit value from the offset specified.
  */
-uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset) {
+uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset)
+{
+	if (adev->in_pci_err_recovery)
+		return 0;
+
 	if (offset < adev->rmmio_size)
 		return (readb(adev->rmmio + offset));
 	BUG();
@@ -376,33 +377,19 @@ uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset) {
  *
  * Writes the value specified to the offset specified.
  */
-void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value) {
+void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value)
+{
+	if (adev->in_pci_err_recovery)
+		return;
+
 	if (offset < adev->rmmio_size)
 		writeb(value, adev->rmmio + offset);
 	else
 		BUG();
 }
 
-static inline void amdgpu_mm_wreg_mmio(struct amdgpu_device *adev,
-				       uint32_t reg, uint32_t v,
-				       uint32_t acc_flags)
-{
-	trace_amdgpu_mm_wreg(adev->pdev->device, reg, v);
-
-	if ((reg * 4) < adev->rmmio_size)
-		writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
-	else {
-		unsigned long flags;
-
-		spin_lock_irqsave(&adev->mmio_idx_lock, flags);
-		writel((reg * 4), ((void __iomem *)adev->rmmio) + (mmMM_INDEX * 4));
-		writel(v, ((void __iomem *)adev->rmmio) + (mmMM_DATA * 4));
-		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
-	}
-}
-
 /**
- * amdgpu_mm_wreg - write to a memory mapped IO register
+ * amdgpu_device_wreg - write to a memory mapped IO or indirect register
  *
  * @adev: amdgpu_device pointer
  * @reg: dword aligned register offset
@@ -411,17 +398,27 @@ static inline void amdgpu_mm_wreg_mmio(struct amdgpu_device *adev,
  *
  * Writes the value specified to the offset specified.
  */
-void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
-		    uint32_t acc_flags)
+void amdgpu_device_wreg(struct amdgpu_device *adev,
+			uint32_t reg, uint32_t v,
+			uint32_t acc_flags)
 {
-	if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev) &&
-	    down_read_trylock(&adev->reset_sem)) {
-		amdgpu_kiq_wreg(adev, reg, v);
-		up_read(&adev->reset_sem);
+	if (adev->in_pci_err_recovery)
 		return;
+
+	if ((reg * 4) < adev->rmmio_size) {
+		if (!(acc_flags & AMDGPU_REGS_NO_KIQ) &&
+		    amdgpu_sriov_runtime(adev) &&
+		    down_read_trylock(&adev->reset_sem)) {
+			amdgpu_kiq_wreg(adev, reg, v);
+			up_read(&adev->reset_sem);
+		} else {
+			writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
+		}
+	} else {
+		adev->pcie_wreg(adev, reg * 4, v);
 	}
 
-	amdgpu_mm_wreg_mmio(adev, reg, v, acc_flags);
+	trace_amdgpu_device_wreg(adev->pdev->device, reg, v);
 }
 
 /*
@@ -429,18 +426,20 @@ void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
  *
  * this function is invoked only the debugfs register access
  * */
-void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
-		    uint32_t acc_flags)
+void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
+			     uint32_t reg, uint32_t v)
 {
-	if (amdgpu_sriov_fullaccess(adev) &&
-		adev->gfx.rlc.funcs &&
-		adev->gfx.rlc.funcs->is_rlcg_access_range) {
+	if (adev->in_pci_err_recovery)
+		return;
 
+	if (amdgpu_sriov_fullaccess(adev) &&
+	    adev->gfx.rlc.funcs &&
+	    adev->gfx.rlc.funcs->is_rlcg_access_range) {
 		if (adev->gfx.rlc.funcs->is_rlcg_access_range(adev, reg))
 			return adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, v);
+	} else {
+		writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
 	}
-
-	amdgpu_mm_wreg_mmio(adev, reg, v, acc_flags);
 }
 
 /**
@@ -453,6 +452,9 @@ void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, uint32_t reg, uint32_t
  */
 u32 amdgpu_io_rreg(struct amdgpu_device *adev, u32 reg)
 {
+	if (adev->in_pci_err_recovery)
+		return 0;
+
 	if ((reg * 4) < adev->rio_mem_size)
 		return ioread32(adev->rio_mem + (reg * 4));
 	else {
@@ -472,6 +474,9 @@ u32 amdgpu_io_rreg(struct amdgpu_device *adev, u32 reg)
  */
 void amdgpu_io_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 {
+	if (adev->in_pci_err_recovery)
+		return;
+
 	if ((reg * 4) < adev->rio_mem_size)
 		iowrite32(v, adev->rio_mem + (reg * 4));
 	else {
@@ -491,6 +496,9 @@ void amdgpu_io_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
  */
 u32 amdgpu_mm_rdoorbell(struct amdgpu_device *adev, u32 index)
 {
+	if (adev->in_pci_err_recovery)
+		return 0;
+
 	if (index < adev->doorbell.num_doorbells) {
 		return readl(adev->doorbell.ptr + index);
 	} else {
@@ -511,6 +519,9 @@ u32 amdgpu_mm_rdoorbell(struct amdgpu_device *adev, u32 index)
  */
 void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v)
 {
+	if (adev->in_pci_err_recovery)
+		return;
+
 	if (index < adev->doorbell.num_doorbells) {
 		writel(v, adev->doorbell.ptr + index);
 	} else {
@@ -529,6 +540,9 @@ void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v)
  */
 u64 amdgpu_mm_rdoorbell64(struct amdgpu_device *adev, u32 index)
 {
+	if (adev->in_pci_err_recovery)
+		return 0;
+
 	if (index < adev->doorbell.num_doorbells) {
 		return atomic64_read((atomic64_t *)(adev->doorbell.ptr + index));
 	} else {
@@ -549,6 +563,9 @@ u64 amdgpu_mm_rdoorbell64(struct amdgpu_device *adev, u32 index)
  */
 void amdgpu_mm_wdoorbell64(struct amdgpu_device *adev, u32 index, u64 v)
 {
+	if (adev->in_pci_err_recovery)
+		return;
+
 	if (index < adev->doorbell.num_doorbells) {
 		atomic64_set((atomic64_t *)(adev->doorbell.ptr + index), v);
 	} else {
@@ -557,6 +574,135 @@ void amdgpu_mm_wdoorbell64(struct amdgpu_device *adev, u32 index, u64 v)
 }
 
 /**
+ * amdgpu_device_indirect_rreg - read an indirect register
+ *
+ * @adev: amdgpu_device pointer
+ * @pcie_index: mmio register offset
+ * @pcie_data: mmio register offset
+ *
+ * Returns the value of indirect register @reg_addr
+ */
+u32 amdgpu_device_indirect_rreg(struct amdgpu_device *adev,
+				u32 pcie_index, u32 pcie_data,
+				u32 reg_addr)
+{
+	unsigned long flags;
+	u32 r;
+	void __iomem *pcie_index_offset;
+	void __iomem *pcie_data_offset;
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	pcie_index_offset = (void __iomem *)adev->rmmio + pcie_index * 4;
+	pcie_data_offset = (void __iomem *)adev->rmmio + pcie_data * 4;
+
+	writel(reg_addr, pcie_index_offset);
+	readl(pcie_index_offset);
+	r = readl(pcie_data_offset);
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+
+	return r;
+}
+
+/**
+ * amdgpu_device_indirect_rreg64 - read a 64bits indirect register
+ *
+ * @adev: amdgpu_device pointer
+ * @pcie_index: mmio register offset
+ * @pcie_data: mmio register offset
+ *
+ * Returns the value of indirect register @reg_addr
+ */
+u64 amdgpu_device_indirect_rreg64(struct amdgpu_device *adev,
+				  u32 pcie_index, u32 pcie_data,
+				  u32 reg_addr)
+{
+	unsigned long flags;
+	u64 r;
+	void __iomem *pcie_index_offset;
+	void __iomem *pcie_data_offset;
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	pcie_index_offset = (void __iomem *)adev->rmmio + pcie_index * 4;
+	pcie_data_offset = (void __iomem *)adev->rmmio + pcie_data * 4;
+
+	/* read low 32 bits */
+	writel(reg_addr, pcie_index_offset);
+	readl(pcie_index_offset);
+	r = readl(pcie_data_offset);
+	/* read high 32 bits */
+	writel(reg_addr + 4, pcie_index_offset);
+	readl(pcie_index_offset);
+	r |= ((u64)readl(pcie_data_offset) << 32);
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+
+	return r;
+}
+
+/**
+ * amdgpu_device_indirect_wreg - write an indirect register address
+ *
+ * @adev: amdgpu_device pointer
+ * @pcie_index: mmio register offset
+ * @pcie_data: mmio register offset
+ * @reg_addr: indirect register offset
+ * @reg_data: indirect register data
+ *
+ */
+void amdgpu_device_indirect_wreg(struct amdgpu_device *adev,
+				 u32 pcie_index, u32 pcie_data,
+				 u32 reg_addr, u32 reg_data)
+{
+	unsigned long flags;
+	void __iomem *pcie_index_offset;
+	void __iomem *pcie_data_offset;
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	pcie_index_offset = (void __iomem *)adev->rmmio + pcie_index * 4;
+	pcie_data_offset = (void __iomem *)adev->rmmio + pcie_data * 4;
+
+	writel(reg_addr, pcie_index_offset);
+	readl(pcie_index_offset);
+	writel(reg_data, pcie_data_offset);
+	readl(pcie_data_offset);
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+}
+
+/**
+ * amdgpu_device_indirect_wreg64 - write a 64bits indirect register address
+ *
+ * @adev: amdgpu_device pointer
+ * @pcie_index: mmio register offset
+ * @pcie_data: mmio register offset
+ * @reg_addr: indirect register offset
+ * @reg_data: indirect register data
+ *
+ */
+void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev,
+				   u32 pcie_index, u32 pcie_data,
+				   u32 reg_addr, u64 reg_data)
+{
+	unsigned long flags;
+	void __iomem *pcie_index_offset;
+	void __iomem *pcie_data_offset;
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	pcie_index_offset = (void __iomem *)adev->rmmio + pcie_index * 4;
+	pcie_data_offset = (void __iomem *)adev->rmmio + pcie_data * 4;
+
+	/* write low 32 bits */
+	writel(reg_addr, pcie_index_offset);
+	readl(pcie_index_offset);
+	writel((u32)(reg_data & 0xffffffffULL), pcie_data_offset);
+	readl(pcie_data_offset);
+	/* write high 32 bits */
+	writel(reg_addr + 4, pcie_index_offset);
+	readl(pcie_index_offset);
+	writel((u32)(reg_data >> 32), pcie_data_offset);
+	readl(pcie_data_offset);
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+}
+
+/**
  * amdgpu_invalid_rreg - dummy reg read function
  *
  * @adev: amdgpu device pointer
@@ -1224,11 +1370,15 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 
 	amdgpu_gmc_tmz_set(adev);
 
-	if (amdgpu_num_kcq > 8 || amdgpu_num_kcq < 0) {
+	if (amdgpu_num_kcq == -1) {
+		amdgpu_num_kcq = 8;
+	} else if (amdgpu_num_kcq > 8 || amdgpu_num_kcq < 0) {
 		amdgpu_num_kcq = 8;
 		dev_warn(adev->dev, "set kernel compute queue number to 8 due to invalid parameter provided by user\n");
 	}
 
+	amdgpu_gmc_noretry_set(adev);
+
 	return 0;
 }
 
@@ -1256,7 +1406,7 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev,
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 
 		pci_set_power_state(dev->pdev, PCI_D0);
-		pci_restore_state(dev->pdev);
+		amdgpu_device_load_pci_state(dev->pdev);
 		r = pci_enable_device(dev->pdev);
 		if (r)
 			DRM_WARN("pci_enable_device failed (%d)\n", r);
@@ -1269,7 +1419,7 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev,
 		drm_kms_helper_poll_disable(dev);
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 		amdgpu_device_suspend(dev, true);
-		pci_save_state(dev->pdev);
+		amdgpu_device_cache_pci_state(dev->pdev);
 		/* Shut down the device */
 		pci_disable_device(dev->pdev);
 		pci_set_power_state(dev->pdev, PCI_D3cold);
@@ -1631,6 +1781,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
 	case CHIP_VEGA20:
+	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
 	default:
 		return 0;
 	case CHIP_VEGA10:
@@ -1662,12 +1814,6 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 	case CHIP_NAVI12:
 		chip_name = "navi12";
 		break;
-	case CHIP_SIENNA_CICHLID:
-		chip_name = "sienna_cichlid";
-		break;
-	case CHIP_NAVY_FLOUNDER:
-		chip_name = "navy_flounder";
-		break;
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_gpu_info.bin", chip_name);
@@ -2999,6 +3145,7 @@ static const struct attribute *amdgpu_dev_attributes[] = {
 	NULL
 };
 
+
 /**
  * amdgpu_device_init - initialize the driver
  *
@@ -3170,13 +3317,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	r = amdgpu_device_get_job_timeout_settings(adev);
 	if (r) {
 		dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n");
-		return r;
+		goto failed_unmap;
 	}
 
 	/* early init functions */
 	r = amdgpu_device_ip_early_init(adev);
 	if (r)
-		return r;
+		goto failed_unmap;
 
 	/* doorbell bar mapping and doorbell index init*/
 	amdgpu_device_doorbell_init(adev);
@@ -3217,6 +3364,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		}
 	}
 
+	pci_enable_pcie_error_reporting(adev->ddev.pdev);
+
 	/* Post card if necessary */
 	if (amdgpu_device_need_post(adev)) {
 		if (!adev->bios) {
@@ -3359,16 +3508,18 @@ fence_driver_init:
 		flush_delayed_work(&adev->delayed_init_work);
 
 	r = sysfs_create_files(&adev->dev->kobj, amdgpu_dev_attributes);
-	if (r) {
+	if (r)
 		dev_err(adev->dev, "Could not create amdgpu device attr\n");
-		return r;
-	}
 
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		r = amdgpu_pmu_init(adev);
 	if (r)
 		dev_err(adev->dev, "amdgpu_pmu_init failed\n");
 
+	/* Have stored pci confspace at hand for restore in sudden PCI error */
+	if (amdgpu_device_cache_pci_state(adev->pdev))
+		pci_restore_state(pdev);
+
 	return 0;
 
 failed:
@@ -3376,6 +3527,10 @@ failed:
 	if (boco)
 		vga_switcheroo_fini_domain_pm_ops(adev->dev);
 
+failed_unmap:
+	iounmap(adev->rmmio);
+	adev->rmmio = NULL;
+
 	return r;
 }
 
@@ -3393,11 +3548,15 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	flush_delayed_work(&adev->delayed_init_work);
 	adev->shutdown = true;
 
+	kfree(adev->pci_state);
+
 	/* make sure IB test finished before entering exclusive mode
 	 * to avoid preemption on IB test
 	 * */
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev)) {
 		amdgpu_virt_request_full_gpu(adev, false);
+		amdgpu_virt_fini_data_exchange(adev);
+	}
 
 	/* disable all interrupts */
 	amdgpu_irq_disable_all(adev);
@@ -4031,6 +4190,11 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 
 	amdgpu_debugfs_wait_dump(adev);
 
+	if (amdgpu_sriov_vf(adev)) {
+		/* stop the data exchange thread */
+		amdgpu_virt_fini_data_exchange(adev);
+	}
+
 	/* block all schedulers and reset given job's ring */
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
@@ -4072,7 +4236,8 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 
 static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 			       struct list_head *device_list_handle,
-			       bool *need_full_reset_arg)
+			       bool *need_full_reset_arg,
+			       bool skip_hw_reset)
 {
 	struct amdgpu_device *tmp_adev = NULL;
 	bool need_full_reset = *need_full_reset_arg, vram_lost = false;
@@ -4082,7 +4247,7 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 	 * ASIC reset has to be done on all HGMI hive nodes ASAP
 	 * to allow proper links negotiation in FW (within 1 sec)
 	 */
-	if (need_full_reset) {
+	if (!skip_hw_reset && need_full_reset) {
 		list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
 			/* For XGMI run all resets in parallel to speed up the process */
 			if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) {
@@ -4460,7 +4625,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
 		r = amdgpu_device_pre_asic_reset(tmp_adev,
-						 NULL,
+						 (tmp_adev == adev) ? job : NULL,
 						 &need_full_reset);
 		/*TODO Should we stop ?*/
 		if (r) {
@@ -4477,7 +4642,7 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 		if (r)
 			adev->asic_reset_res = r;
 	} else {
-		r  = amdgpu_do_asic_reset(hive, device_list_handle, &need_full_reset);
+		r  = amdgpu_do_asic_reset(hive, device_list_handle, &need_full_reset, false);
 		if (r && r == -EAGAIN)
 			goto retry;
 	}
@@ -4705,3 +4870,235 @@ int amdgpu_device_baco_exit(struct drm_device *dev)
 
 	return 0;
 }
+
+static void amdgpu_cancel_all_tdr(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		if (!ring || !ring->sched.thread)
+			continue;
+
+		cancel_delayed_work_sync(&ring->sched.work_tdr);
+	}
+}
+
+/**
+ * amdgpu_pci_error_detected - Called when a PCI error is detected.
+ * @pdev: PCI device struct
+ * @state: PCI channel state
+ *
+ * Description: Called when a PCI error is detected.
+ *
+ * Return: PCI_ERS_RESULT_NEED_RESET or PCI_ERS_RESULT_DISCONNECT.
+ */
+pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	int i;
+
+	DRM_INFO("PCI error: detected callback, state(%d)!!\n", state);
+
+	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+		DRM_WARN("No support for XGMI hive yet...");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	switch (state) {
+	case pci_channel_io_normal:
+		return PCI_ERS_RESULT_CAN_RECOVER;
+	/* Fatal error, prepare for slot reset */
+	case pci_channel_io_frozen:		
+		/*		
+		 * Cancel and wait for all TDRs in progress if failing to
+		 * set  adev->in_gpu_reset in amdgpu_device_lock_adev
+		 *
+		 * Locking adev->reset_sem will prevent any external access
+		 * to GPU during PCI error recovery
+		 */
+		while (!amdgpu_device_lock_adev(adev, NULL))
+			amdgpu_cancel_all_tdr(adev);
+
+		/*
+		 * Block any work scheduling as we do for regular GPU reset
+		 * for the duration of the recovery
+		 */
+		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+			struct amdgpu_ring *ring = adev->rings[i];
+
+			if (!ring || !ring->sched.thread)
+				continue;
+
+			drm_sched_stop(&ring->sched, NULL);
+		}
+		return PCI_ERS_RESULT_NEED_RESET;
+	case pci_channel_io_perm_failure:
+		/* Permanent error, prepare for device removal */
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+/**
+ * amdgpu_pci_mmio_enabled - Enable MMIO and dump debug registers
+ * @pdev: pointer to PCI device
+ */
+pci_ers_result_t amdgpu_pci_mmio_enabled(struct pci_dev *pdev)
+{
+
+	DRM_INFO("PCI error: mmio enabled callback!!\n");
+
+	/* TODO - dump whatever for debugging purposes */
+
+	/* This called only if amdgpu_pci_error_detected returns
+	 * PCI_ERS_RESULT_CAN_RECOVER. Read/write to the device still
+	 * works, no need to reset slot.
+	 */
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+/**
+ * amdgpu_pci_slot_reset - Called when PCI slot has been reset.
+ * @pdev: PCI device struct
+ *
+ * Description: This routine is called by the pci error recovery
+ * code after the PCI slot has been reset, just before we
+ * should resume normal operations.
+ */
+pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	int r, i;
+	bool need_full_reset = true;
+	u32 memsize;
+	struct list_head device_list;
+
+	DRM_INFO("PCI error: slot reset callback!!\n");
+
+	INIT_LIST_HEAD(&device_list);
+	list_add_tail(&adev->gmc.xgmi.head, &device_list);
+
+	/* wait for asic to come out of reset */
+	msleep(500);
+
+	/* Restore PCI confspace */
+	amdgpu_device_load_pci_state(pdev);
+
+	/* confirm  ASIC came out of reset */
+	for (i = 0; i < adev->usec_timeout; i++) {
+		memsize = amdgpu_asic_get_config_memsize(adev);
+
+		if (memsize != 0xffffffff)
+			break;
+		udelay(1);
+	}
+	if (memsize == 0xffffffff) {
+		r = -ETIME;
+		goto out;
+	}
+
+	adev->in_pci_err_recovery = true;	
+	r = amdgpu_device_pre_asic_reset(adev, NULL, &need_full_reset);
+	adev->in_pci_err_recovery = false;
+	if (r)
+		goto out;
+
+	r = amdgpu_do_asic_reset(NULL, &device_list, &need_full_reset, true);
+
+out:
+	if (!r) {
+		if (amdgpu_device_cache_pci_state(adev->pdev))
+			pci_restore_state(adev->pdev);
+
+		DRM_INFO("PCIe error recovery succeeded\n");
+	} else {
+		DRM_ERROR("PCIe error recovery failed, err:%d", r);
+		amdgpu_device_unlock_adev(adev);
+	}
+
+	return r ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
+}
+
+/**
+ * amdgpu_pci_resume() - resume normal ops after PCI reset
+ * @pdev: pointer to PCI device
+ *
+ * Called when the error recovery driver tells us that its
+ * OK to resume normal operation. Use completion to allow
+ * halted scsi ops to resume.
+ */
+void amdgpu_pci_resume(struct pci_dev *pdev)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	int i;
+
+
+	DRM_INFO("PCI error: resume callback!!\n");
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		if (!ring || !ring->sched.thread)
+			continue;
+
+
+		drm_sched_resubmit_jobs(&ring->sched);
+		drm_sched_start(&ring->sched, true);
+	}
+
+	amdgpu_device_unlock_adev(adev);
+}
+
+bool amdgpu_device_cache_pci_state(struct pci_dev *pdev)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	int r;
+
+	r = pci_save_state(pdev);
+	if (!r) {
+		kfree(adev->pci_state);
+
+		adev->pci_state = pci_store_saved_state(pdev);
+
+		if (!adev->pci_state) {
+			DRM_ERROR("Failed to store PCI saved state");
+			return false;
+		}
+	} else {
+		DRM_WARN("Failed to save PCI state, err:%d\n", r);
+		return false;
+	}
+
+	return true;
+}
+
+bool amdgpu_device_load_pci_state(struct pci_dev *pdev)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	int r;
+
+	if (!adev->pci_state)
+		return false;
+
+	r = pci_load_saved_state(pdev, adev->pci_state);
+
+	if (!r) {
+		pci_restore_state(pdev);
+	} else {
+		DRM_WARN("Failed to load PCI state, err:%d\n", r);
+		return false;
+	}
+
+	return true;
+}
+
+
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h
index 61a26c15c8dd..373cdebe0e2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h
@@ -44,9 +44,9 @@ struct amdgpu_df_funcs {
 	void (*enable_ecc_force_par_wr_rmw)(struct amdgpu_device *adev,
 					    bool enable);
 	int (*pmc_start)(struct amdgpu_device *adev, uint64_t config,
-					 int is_enable);
+					 int is_add);
 	int (*pmc_stop)(struct amdgpu_device *adev, uint64_t config,
-					 int is_disable);
+					 int is_remove);
 	void (*pmc_get_count)(struct amdgpu_device *adev, uint64_t config,
 					 uint64_t *count);
 	uint64_t (*get_fica)(struct amdgpu_device *adev, uint32_t ficaa_val);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 4cba095b6c44..b25faaee6f0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -293,7 +293,7 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set,
 	   take the current one */
 	if (active && !adev->have_disp_power_ref) {
 		adev->have_disp_power_ref = true;
-		goto out;
+		return ret;
 	}
 	/* if we have no active crtcs, then drop the power ref
 	   we got before */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index f359ffb77aa5..8b30915aa972 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -32,7 +32,6 @@
 #include <drm/drm_pciids.h>
 #include <linux/console.h>
 #include <linux/module.h>
-#include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/vga_switcheroo.h>
 #include <drm/drm_probe_helper.h>
@@ -148,7 +147,7 @@ int amdgpu_async_gfx_ring = 1;
 int amdgpu_mcbp = 0;
 int amdgpu_discovery = -1;
 int amdgpu_mes = 0;
-int amdgpu_noretry;
+int amdgpu_noretry = -1;
 int amdgpu_force_asic_type = -1;
 int amdgpu_tmz = 0;
 int amdgpu_reset_method = -1; /* auto */
@@ -597,8 +596,13 @@ MODULE_PARM_DESC(mes,
 	"Enable Micro Engine Scheduler (0 = disabled (default), 1 = enabled)");
 module_param_named(mes, amdgpu_mes, int, 0444);
 
+/**
+ * DOC: noretry (int)
+ * Disable retry faults in the GPU memory controller.
+ * (0 = retry enabled, 1 = retry disabled, -1 auto (default))
+ */
 MODULE_PARM_DESC(noretry,
-	"Disable retry faults (0 = retry enabled (default), 1 = retry disabled)");
+	"Disable retry faults (0 = retry enabled, 1 = retry disabled, -1 auto (default))");
 module_param_named(noretry, amdgpu_noretry, int, 0644);
 
 /**
@@ -1062,6 +1066,7 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x7319, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	{0x1002, 0x731A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	{0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
+	{0x1002, 0x731E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	{0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	/* Navi14 */
 	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
@@ -1073,8 +1078,16 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
 
 	/* Navi12 */
-	{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
-	{0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12},
+	{0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12},
+
+	/* Sienna_Cichlid */
+	{0x1002, 0x73A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73AB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73AE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 
 	{0, 0, 0}
 };
@@ -1102,6 +1115,16 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 		return -ENODEV;
 	}
 
+	/* Due to hardware bugs, S/G Display on raven requires a 1:1 IOMMU mapping,
+	 * however, SME requires an indirect IOMMU mapping because the encryption
+	 * bit is beyond the DMA mask of the chip.
+	 */
+	if (mem_encrypt_active() && ((flags & AMD_ASIC_MASK) == CHIP_RAVEN)) {
+		dev_info(&pdev->dev,
+			 "SME is not compatible with RAVEN\n");
+		return -ENOTSUPP;
+	}
+
 #ifdef CONFIG_DRM_AMDGPU_SI
 	if (!amdgpu_si_support) {
 		switch (flags & AMD_ASIC_MASK) {
@@ -1308,7 +1331,7 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 		if (amdgpu_is_atpx_hybrid()) {
 			pci_ignore_hotplug(pdev);
 		} else {
-			pci_save_state(pdev);
+			amdgpu_device_cache_pci_state(pdev);
 			pci_disable_device(pdev);
 			pci_ignore_hotplug(pdev);
 			pci_set_power_state(pdev, PCI_D3cold);
@@ -1341,7 +1364,7 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 			pci_set_master(pdev);
 		} else {
 			pci_set_power_state(pdev, PCI_D0);
-			pci_restore_state(pdev);
+			amdgpu_device_load_pci_state(pdev);
 			ret = pci_enable_device(pdev);
 			if (ret)
 				return ret;
@@ -1514,6 +1537,13 @@ static struct drm_driver kms_driver = {
 	.patchlevel = KMS_DRIVER_PATCHLEVEL,
 };
 
+static struct pci_error_handlers amdgpu_pci_err_handler = {
+	.error_detected	= amdgpu_pci_error_detected,
+	.mmio_enabled	= amdgpu_pci_mmio_enabled,
+	.slot_reset	= amdgpu_pci_slot_reset,
+	.resume		= amdgpu_pci_resume,
+};
+
 static struct pci_driver amdgpu_kms_pci_driver = {
 	.name = DRIVER_NAME,
 	.id_table = pciidlist,
@@ -1521,6 +1551,7 @@ static struct pci_driver amdgpu_kms_pci_driver = {
 	.remove = amdgpu_pci_remove,
 	.shutdown = amdgpu_pci_shutdown,
 	.driver.pm = &amdgpu_pm_ops,
+	.err_handler = &amdgpu_pci_err_handler,
 };
 
 static int __init amdgpu_init(void)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
index e811fecc540f..8f4a8f8d8146 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
@@ -34,18 +34,31 @@
 
 static bool is_fru_eeprom_supported(struct amdgpu_device *adev)
 {
-	/* TODO: Gaming SKUs don't have the FRU EEPROM.
-	 * Use this hack to address hangs on modprobe on gaming SKUs
-	 * until a proper solution can be implemented by only supporting
-	 * the explicit chip IDs for VG20 Server cards
-	 *
-	 * TODO: Add list of supported Arcturus DIDs once confirmed
+	/* Only server cards have the FRU EEPROM
+	 * TODO: See if we can figure this out dynamically instead of
+	 * having to parse VBIOS versions.
 	 */
-	if ((adev->asic_type == CHIP_VEGA20 && adev->pdev->device == 0x66a0) ||
-	    (adev->asic_type == CHIP_VEGA20 && adev->pdev->device == 0x66a1) ||
-	    (adev->asic_type == CHIP_VEGA20 && adev->pdev->device == 0x66a4))
-		return true;
-	return false;
+	struct atom_context *atom_ctx = adev->mode_info.atom_context;
+
+	/* VBIOS is of the format ###-DXXXYY-##. For SKU identification,
+	 * we can use just the "DXXX" portion. If there were more models, we
+	 * could convert the 3 characters to a hex integer and use a switch
+	 * for ease/speed/readability. For now, 2 string comparisons are
+	 * reasonable and not too expensive
+	 */
+	switch (adev->asic_type) {
+	case CHIP_VEGA20:
+		/* D161 and D163 are the VG20 server SKUs */
+		if (strnstr(atom_ctx->vbios_version, "D161",
+			    sizeof(atom_ctx->vbios_version)) ||
+		    strnstr(atom_ctx->vbios_version, "D163",
+			    sizeof(atom_ctx->vbios_version)))
+			return true;
+		else
+			return false;
+	default:
+		return false;
+	}
 }
 
 static int amdgpu_fru_read_eeprom(struct amdgpu_device *adev, uint32_t addrptr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.h
index f29a8611d69b..1308d976d60e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.h
@@ -26,4 +26,4 @@
 
 int amdgpu_fru_get_product_info(struct amdgpu_device *adev);
 
-#endif  // __AMDGPU_PRODINFO_H__
+#endif  // __AMDGPU_FRU_EEPROM_H__
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index be08a63ef58c..8ea6fc745769 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -609,6 +609,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 	struct ww_acquire_ctx ticket;
 	struct list_head list, duplicates;
 	uint64_t va_flags;
+	uint64_t vm_size;
 	int r = 0;
 
 	if (args->va_address < AMDGPU_VA_RESERVED_SIZE) {
@@ -629,6 +630,15 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 
 	args->va_address &= AMDGPU_GMC_HOLE_MASK;
 
+	vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
+	vm_size -= AMDGPU_VA_RESERVED_SIZE;
+	if (args->va_address + args->map_size > vm_size) {
+		dev_dbg(&dev->pdev->dev,
+			"va_address 0x%llx is in top reserved area 0x%llx\n",
+			args->va_address + args->map_size, vm_size);
+		return -EINVAL;
+	}
+
 	if ((args->flags & ~valid_flags) && (args->flags & ~prt_flags)) {
 		dev_dbg(&dev->pdev->dev, "invalid flags combination 0x%08X\n",
 			args->flags);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index d6981425ec51..8c9bacfdbc30 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -693,6 +693,9 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 	struct amdgpu_ring *ring = &kiq->ring;
 
+	if (adev->in_pci_err_recovery)
+		return 0;
+
 	BUG_ON(!ring->funcs->emit_rreg);
 
 	spin_lock_irqsave(&kiq->ring_lock, flags);
@@ -757,6 +760,9 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
 
 	BUG_ON(!ring->funcs->emit_wreg);
 
+	if (adev->in_pci_err_recovery)
+		return;
+
 	spin_lock_irqsave(&kiq->ring_lock, flags);
 	amdgpu_ring_alloc(ring, 32);
 	amdgpu_ring_emit_wreg(ring, reg, v);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index a611e78dd4ba..258498cbf1eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -217,6 +217,7 @@ struct amdgpu_gfx_funcs {
 	int (*query_ras_error_count) (struct amdgpu_device *adev, void *ras_error_status);
 	void (*reset_ras_error_count) (struct amdgpu_device *adev);
 	void (*init_spm_golden)(struct amdgpu_device *adev);
+	void (*query_ras_error_status) (struct amdgpu_device *adev);
 };
 
 struct sq_work {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfxhub.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfxhub.h
new file mode 100644
index 000000000000..66ebc2e3b2ad
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfxhub.h
@@ -0,0 +1,43 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __AMDGPU_GFXHUB_H__
+#define __AMDGPU_GFXHUB_H__
+
+struct amdgpu_gfxhub_funcs {
+	u64 (*get_fb_location)(struct amdgpu_device *adev);
+	u64 (*get_mc_fb_offset)(struct amdgpu_device *adev);
+	void (*setup_vm_pt_regs)(struct amdgpu_device *adev, uint32_t vmid,
+			uint64_t page_table_base);
+	int (*gart_enable)(struct amdgpu_device *adev);
+
+	void (*gart_disable)(struct amdgpu_device *adev);
+	void (*set_fault_enable_default)(struct amdgpu_device *adev, bool value);
+	void (*init)(struct amdgpu_device *adev);
+	int (*get_xgmi_info)(struct amdgpu_device *adev);
+};
+
+struct amdgpu_gfxhub {
+	const struct amdgpu_gfxhub_funcs *funcs;
+};
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 0e35023b5703..cc86f431a3d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -409,6 +409,44 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 	}
 }
 
+/**
+ * amdgpu_noretry_set -- set per asic noretry defaults
+ * @adev: amdgpu_device pointer
+ *
+ * Set a per asic default for the no-retry parameter.
+ *
+ */
+void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
+{
+	struct amdgpu_gmc *gmc = &adev->gmc;
+
+	switch (adev->asic_type) {
+	case CHIP_RAVEN:
+		/* Raven currently has issues with noretry
+		 * regardless of what we decide for other
+		 * asics, we should leave raven with
+		 * noretry = 0 until we root cause the
+		 * issues.
+		 */
+		if (amdgpu_noretry == -1)
+			gmc->noretry = 0;
+		else
+			gmc->noretry = amdgpu_noretry;
+		break;
+	default:
+		/* default this to 0 for now, but we may want
+		 * to change this in the future for certain
+		 * GPUs as it can increase performance in
+		 * certain cases.
+		 */
+		if (amdgpu_noretry == -1)
+			gmc->noretry = 0;
+		else
+			gmc->noretry = amdgpu_noretry;
+		break;
+	}
+}
+
 void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
 				   bool enable)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index d61bbde4c7d2..aa0c83776ce0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -239,6 +239,7 @@ struct amdgpu_gmc {
 
 	struct amdgpu_xgmi xgmi;
 	struct amdgpu_irq_src	ecc_irq;
+	int noretry;
 };
 
 #define amdgpu_gmc_flush_gpu_tlb(adev, vmid, vmhub, type) ((adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid), (vmhub), (type)))
@@ -300,6 +301,7 @@ void amdgpu_gmc_ras_fini(struct amdgpu_device *adev);
 int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev);
 
 extern void amdgpu_gmc_tmz_set(struct amdgpu_device *adev);
+extern void amdgpu_gmc_noretry_set(struct amdgpu_device *adev);
 
 extern void
 amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 7521f4ab55de..6e9a9e5dbea0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -43,7 +43,7 @@ static DEFINE_IDA(amdgpu_pasid_ida);
 /* Helper to free pasid from a fence callback */
 struct amdgpu_pasid_cb {
 	struct dma_fence_cb cb;
-	unsigned int pasid;
+	u32 pasid;
 };
 
 /**
@@ -79,7 +79,7 @@ int amdgpu_pasid_alloc(unsigned int bits)
  * amdgpu_pasid_free - Free a PASID
  * @pasid: PASID to free
  */
-void amdgpu_pasid_free(unsigned int pasid)
+void amdgpu_pasid_free(u32 pasid)
 {
 	trace_amdgpu_pasid_freed(pasid);
 	ida_simple_remove(&amdgpu_pasid_ida, pasid);
@@ -105,7 +105,7 @@ static void amdgpu_pasid_free_cb(struct dma_fence *fence,
  * Free the pasid only after all the fences in resv are signaled.
  */
 void amdgpu_pasid_free_delayed(struct dma_resv *resv,
-			       unsigned int pasid)
+			       u32 pasid)
 {
 	struct dma_fence *fence, **fences;
 	struct amdgpu_pasid_cb *cb;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
index 8e58325bbca2..0c3b4fa1f936 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
@@ -71,9 +71,9 @@ struct amdgpu_vmid_mgr {
 };
 
 int amdgpu_pasid_alloc(unsigned int bits);
-void amdgpu_pasid_free(unsigned int pasid);
+void amdgpu_pasid_free(u32 pasid);
 void amdgpu_pasid_free_delayed(struct dma_resv *resv,
-			       unsigned int pasid);
+			       u32 pasid);
 
 bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
 			       struct amdgpu_vmid *id);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 456a4a93b337..efda38349a03 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -177,7 +177,7 @@ int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags)
 			break;
 		case CHIP_VEGA10:
 			/* turn runpm on if noretry=0 */
-			if (!amdgpu_noretry)
+			if (!adev->gmc.noretry)
 				adev->runpm = true;
 			break;
 		default:
@@ -282,14 +282,25 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->feature = 0;
 		break;
 	case AMDGPU_INFO_FW_TA:
-		if (query_fw->index > 1)
-			return -EINVAL;
-		if (query_fw->index == 0) {
+		switch (query_fw->index) {
+		case 0:
 			fw_info->ver = adev->psp.ta_fw_version;
 			fw_info->feature = adev->psp.ta_xgmi_ucode_version;
-		} else {
+			break;
+		case 1:
 			fw_info->ver = adev->psp.ta_fw_version;
 			fw_info->feature = adev->psp.ta_ras_ucode_version;
+			break;
+		case 2:
+			fw_info->ver = adev->psp.ta_fw_version;
+			fw_info->feature = adev->psp.ta_hdcp_ucode_version;
+			break;
+		case 3:
+			fw_info->ver = adev->psp.ta_fw_version;
+			fw_info->feature = adev->psp.ta_dtm_ucode_version;
+			break;
+		default:
+			return -EINVAL;
 		}
 		break;
 	case AMDGPU_INFO_FW_SDMA:
@@ -1080,7 +1091,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
 	struct amdgpu_bo_list *list;
 	struct amdgpu_bo *pd;
-	unsigned int pasid;
+	u32 pasid;
 	int handle;
 
 	if (!fpriv)
@@ -1385,13 +1396,31 @@ static int amdgpu_debugfs_firmware_info(struct seq_file *m, void *data)
 		   fw_info.feature, fw_info.ver);
 
 	query_fw.fw_type = AMDGPU_INFO_FW_TA;
-	for (i = 0; i < 2; i++) {
+	for (i = 0; i < 4; i++) {
 		query_fw.index = i;
 		ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
 		if (ret)
 			continue;
-		seq_printf(m, "TA %s feature version: %u, firmware version: 0x%08x\n",
-				i ? "RAS" : "XGMI", fw_info.feature, fw_info.ver);
+		switch (query_fw.index) {
+		case 0:
+			seq_printf(m, "TA %s feature version: 0x%08x, firmware version: 0x%08x\n",
+					"RAS", fw_info.feature, fw_info.ver);
+			break;
+		case 1:
+			seq_printf(m, "TA %s feature version: 0x%08x, firmware version: 0x%08x\n",
+					"XGMI", fw_info.feature, fw_info.ver);
+			break;
+		case 2:
+			seq_printf(m, "TA %s feature version: 0x%08x, firmware version: 0x%08x\n",
+					"HDCP", fw_info.feature, fw_info.ver);
+			break;
+		case 3:
+			seq_printf(m, "TA %s feature version: 0x%08x, firmware version: 0x%08x\n",
+					"DTM", fw_info.feature, fw_info.ver);
+			break;
+		default:
+			return -EINVAL;
+		}
 	}
 
 	/* SMC */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
index 0c43d7fe893c..1ae9bdae7311 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
@@ -40,6 +40,7 @@ struct amdgpu_mmhub_funcs {
 				uint64_t page_table_base);
 	void (*update_power_gating)(struct amdgpu_device *adev,
                                 bool enable);
+	void (*query_ras_error_status)(struct amdgpu_device *adev);
 };
 
 struct amdgpu_mmhub {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index 04a430e0e2e1..a04decb934b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -46,6 +46,7 @@
 
 #include <drm/drm_dp_mst_helper.h>
 #include "modules/inc/mod_freesync.h"
+#include "amdgpu_dm_irq_params.h"
 
 struct amdgpu_bo;
 struct amdgpu_device;
@@ -404,7 +405,8 @@ struct amdgpu_crtc {
 	struct amdgpu_flip_work *pflip_works;
 	enum amdgpu_flip_status pflip_status;
 	int deferred_flip_completion;
-	u32 last_flip_vblank;
+	/* parameters access from DM IRQ handler */
+	struct dm_irq_params dm_irq_params;
 	/* pll sharing */
 	struct amdgpu_atom_ss ss;
 	bool ss_enabled;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index d6c38e24f130..96a9699f87ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -161,10 +161,12 @@ static int psp_sw_init(void *handle)
 	struct psp_context *psp = &adev->psp;
 	int ret;
 
-	ret = psp_init_microcode(psp);
-	if (ret) {
-		DRM_ERROR("Failed to load psp firmware!\n");
-		return ret;
+	if (!amdgpu_sriov_vf(adev)) {
+		ret = psp_init_microcode(psp);
+		if (ret) {
+			DRM_ERROR("Failed to load psp firmware!\n");
+			return ret;
+		}
 	}
 
 	ret = psp_memory_training_init(psp);
@@ -178,7 +180,7 @@ static int psp_sw_init(void *handle)
 		return ret;
 	}
 
-	if (adev->asic_type == CHIP_NAVI10) {
+	if (adev->asic_type == CHIP_NAVI10 || adev->asic_type == CHIP_SIENNA_CICHLID) {
 		ret= psp_sysfs_init(adev);
 		if (ret) {
 			return ret;
@@ -206,7 +208,8 @@ static int psp_sw_fini(void *handle)
 		adev->psp.ta_fw = NULL;
 	}
 
-	if (adev->asic_type == CHIP_NAVI10)
+	if (adev->asic_type == CHIP_NAVI10 ||
+	    adev->asic_type == CHIP_SIENNA_CICHLID)
 		psp_sysfs_fini(adev);
 
 	return 0;
@@ -219,6 +222,9 @@ int psp_wait_for(struct psp_context *psp, uint32_t reg_index,
 	int i;
 	struct amdgpu_device *adev = psp->adev;
 
+	if (psp->adev->in_pci_err_recovery)
+		return 0;
+
 	for (i = 0; i < adev->usec_timeout; i++) {
 		val = RREG32(reg_index);
 		if (check_changed) {
@@ -245,6 +251,9 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	bool ras_intr = false;
 	bool skip_unsupport = false;
 
+	if (psp->adev->in_pci_err_recovery)
+		return 0;
+
 	mutex_lock(&psp->mutex);
 
 	memset(psp->cmd_buf_mem, 0, PSP_CMD_BUFFER_SIZE);
@@ -929,6 +938,7 @@ static int psp_ras_load(struct psp_context *psp)
 {
 	int ret;
 	struct psp_gfx_cmd_resp *cmd;
+	struct ta_ras_shared_memory *ras_cmd;
 
 	/*
 	 * TODO: bypass the loading in sriov for now
@@ -952,11 +962,20 @@ static int psp_ras_load(struct psp_context *psp)
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 			psp->fence_buf_mc_addr);
 
+	ras_cmd = (struct ta_ras_shared_memory*)psp->ras.ras_shared_buf;
+
 	if (!ret) {
-		psp->ras.ras_initialized = true;
 		psp->ras.session_id = cmd->resp.session_id;
+
+		if (!ras_cmd->ras_status)
+			psp->ras.ras_initialized = true;
+		else
+			dev_warn(psp->adev->dev, "RAS Init Status: 0x%X\n", ras_cmd->ras_status);
 	}
 
+	if (ret || ras_cmd->ras_status)
+		amdgpu_ras_fini(psp->adev);
+
 	kfree(cmd);
 
 	return ret;
@@ -1732,6 +1751,12 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode,
 	case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM:
 		*type = GFX_FW_TYPE_RLC_RESTORE_LIST_SRM_MEM;
 		break;
+	case AMDGPU_UCODE_ID_RLC_IRAM:
+		*type = GFX_FW_TYPE_RLC_IRAM;
+		break;
+	case AMDGPU_UCODE_ID_RLC_DRAM:
+		*type = GFX_FW_TYPE_RLC_DRAM_BOOT;
+		break;
 	case AMDGPU_UCODE_ID_SMC:
 		*type = GFX_FW_TYPE_SMU;
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index e5ea14774c0c..4e36551ab50b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1027,58 +1027,6 @@ static ssize_t amdgpu_ras_sysfs_features_read(struct device *dev,
 	return scnprintf(buf, PAGE_SIZE, "feature mask: 0x%x\n", con->features);
 }
 
-static void amdgpu_ras_sysfs_add_bad_page_node(struct amdgpu_device *adev)
-{
-	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-	struct attribute_group group;
-	struct bin_attribute *bin_attrs[] = {
-		&con->badpages_attr,
-		NULL,
-	};
-
-	con->badpages_attr = (struct bin_attribute) {
-		.attr = {
-			.name = "gpu_vram_bad_pages",
-			.mode = S_IRUGO,
-		},
-		.size = 0,
-		.private = NULL,
-		.read = amdgpu_ras_sysfs_badpages_read,
-	};
-
-	group.name = RAS_FS_NAME;
-	group.bin_attrs = bin_attrs;
-
-	sysfs_bin_attr_init(bin_attrs[0]);
-
-	sysfs_update_group(&adev->dev->kobj, &group);
-}
-
-static int amdgpu_ras_sysfs_create_feature_node(struct amdgpu_device *adev)
-{
-	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-	struct attribute *attrs[] = {
-		&con->features_attr.attr,
-		NULL
-	};
-	struct attribute_group group = {
-		.name = RAS_FS_NAME,
-		.attrs = attrs,
-	};
-
-	con->features_attr = (struct device_attribute) {
-		.attr = {
-			.name = "features",
-			.mode = S_IRUGO,
-		},
-			.show = amdgpu_ras_sysfs_features_read,
-	};
-
-	sysfs_attr_init(attrs[0]);
-
-	return sysfs_create_group(&adev->dev->kobj, &group);
-}
-
 static void amdgpu_ras_sysfs_remove_bad_page_node(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
@@ -1300,13 +1248,43 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev)
 /* debugfs end */
 
 /* ras fs */
-
+static BIN_ATTR(gpu_vram_bad_pages, S_IRUGO,
+		amdgpu_ras_sysfs_badpages_read, NULL, 0);
+static DEVICE_ATTR(features, S_IRUGO,
+		amdgpu_ras_sysfs_features_read, NULL);
 static int amdgpu_ras_fs_init(struct amdgpu_device *adev)
 {
-	amdgpu_ras_sysfs_create_feature_node(adev);
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct attribute_group group = {
+		.name = RAS_FS_NAME,
+	};
+	struct attribute *attrs[] = {
+		&con->features_attr.attr,
+		NULL
+	};
+	struct bin_attribute *bin_attrs[] = {
+		NULL,
+		NULL,
+	};
+	int r;
 
-	if (amdgpu_bad_page_threshold != 0)
-		amdgpu_ras_sysfs_add_bad_page_node(adev);
+	/* add features entry */
+	con->features_attr = dev_attr_features;
+	group.attrs = attrs;
+	sysfs_attr_init(attrs[0]);
+
+	if (amdgpu_bad_page_threshold != 0) {
+		/* add bad_page_features entry */
+		bin_attr_gpu_vram_bad_pages.private = NULL;
+		con->badpages_attr = bin_attr_gpu_vram_bad_pages;
+		bin_attrs[0] = &con->badpages_attr;
+		group.bin_attrs = bin_attrs;
+		sysfs_bin_attr_init(bin_attrs[0]);
+	}
+
+	r = sysfs_create_group(&adev->dev->kobj, &group);
+	if (r)
+		dev_err(adev->dev, "Failed to create RAS sysfs group!");
 
 	return 0;
 }
@@ -1498,6 +1476,45 @@ static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev)
 	}
 }
 
+/* Parse RdRspStatus and WrRspStatus */
+void amdgpu_ras_error_status_query(struct amdgpu_device *adev,
+		struct ras_query_if *info)
+{
+	/*
+	 * Only two block need to query read/write
+	 * RspStatus at current state
+	 */
+	switch (info->head.block) {
+	case AMDGPU_RAS_BLOCK__GFX:
+		if (adev->gfx.funcs->query_ras_error_status)
+			adev->gfx.funcs->query_ras_error_status(adev);
+		break;
+	case AMDGPU_RAS_BLOCK__MMHUB:
+		if (adev->mmhub.funcs->query_ras_error_status)
+			adev->mmhub.funcs->query_ras_error_status(adev);
+		break;
+	default:
+		break;
+	}
+}
+
+static void amdgpu_ras_query_err_status(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct ras_manager *obj;
+
+	if (!con)
+		return;
+
+	list_for_each_entry(obj, &con->head, node) {
+		struct ras_query_if info = {
+			.head = obj->head,
+		};
+
+		amdgpu_ras_error_status_query(adev, &info);
+	}
+}
+
 /* recovery begin */
 
 /* return 0 on success.
@@ -1568,8 +1585,10 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 		}
 
 		list_for_each_entry(remote_adev,
-				device_list_handle, gmc.xgmi.head)
+				device_list_handle, gmc.xgmi.head) {
+			amdgpu_ras_query_err_status(remote_adev);
 			amdgpu_ras_log_on_err_counter(remote_adev);
+		}
 
 		amdgpu_put_xgmi_hive(hive);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
index 60bb3e8b3118..aeaaae713c59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
@@ -168,12 +168,16 @@ struct amdgpu_rlc {
 	u32 save_restore_list_cntl_size_bytes;
 	u32 save_restore_list_gpm_size_bytes;
 	u32 save_restore_list_srm_size_bytes;
+	u32 rlc_iram_ucode_size_bytes;
+	u32 rlc_dram_ucode_size_bytes;
 
 	u32 *register_list_format;
 	u32 *register_restore;
 	u8 *save_restore_list_cntl;
 	u8 *save_restore_list_gpm;
 	u8 *save_restore_list_srm;
+	u8 *rlc_iram_ucode;
+	u8 *rlc_dram_ucode;
 
 	bool is_rlc_v2_1;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 63e734a125fb..ee9480d14cbc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -35,7 +35,7 @@
 #define AMDGPU_JOB_GET_TIMELINE_NAME(job) \
 	 job->base.s_fence->finished.ops->get_timeline_name(&job->base.s_fence->finished)
 
-TRACE_EVENT(amdgpu_mm_rreg,
+TRACE_EVENT(amdgpu_device_rreg,
 	    TP_PROTO(unsigned did, uint32_t reg, uint32_t value),
 	    TP_ARGS(did, reg, value),
 	    TP_STRUCT__entry(
@@ -54,7 +54,7 @@ TRACE_EVENT(amdgpu_mm_rreg,
 		      (unsigned long)__entry->value)
 );
 
-TRACE_EVENT(amdgpu_mm_wreg,
+TRACE_EVENT(amdgpu_device_wreg,
 	    TP_PROTO(unsigned did, uint32_t reg, uint32_t value),
 	    TP_ARGS(did, reg, value),
 	    TP_STRUCT__entry(
@@ -321,6 +321,49 @@ DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_cs,
 	    TP_ARGS(mapping)
 );
 
+TRACE_EVENT(amdgpu_vm_update_ptes,
+	    TP_PROTO(struct amdgpu_vm_update_params *p,
+		     uint64_t start, uint64_t end,
+		     unsigned int nptes, uint64_t dst,
+		     uint64_t incr, uint64_t flags,
+		     pid_t pid, uint64_t vm_ctx),
+	TP_ARGS(p, start, end, nptes, dst, incr, flags, pid, vm_ctx),
+	TP_STRUCT__entry(
+			 __field(u64, start)
+			 __field(u64, end)
+			 __field(u64, flags)
+			 __field(unsigned int, nptes)
+			 __field(u64, incr)
+			 __field(pid_t, pid)
+			 __field(u64, vm_ctx)
+			 __dynamic_array(u64, dst, nptes)
+	),
+
+	TP_fast_assign(
+			unsigned int i;
+
+			__entry->start = start;
+			__entry->end = end;
+			__entry->flags = flags;
+			__entry->incr = incr;
+			__entry->nptes = nptes;
+			__entry->pid = pid;
+			__entry->vm_ctx = vm_ctx;
+			for (i = 0; i < nptes; ++i) {
+				u64 addr = p->pages_addr ? amdgpu_vm_map_gart(
+					p->pages_addr, dst) : dst;
+
+				((u64 *)__get_dynamic_array(dst))[i] = addr;
+				dst += incr;
+			}
+	),
+	TP_printk("pid:%u vm_ctx:0x%llx start:0x%010llx end:0x%010llx,"
+		  " flags:0x%llx, incr:%llu, dst:\n%s", __entry->pid,
+		  __entry->vm_ctx, __entry->start, __entry->end,
+		  __entry->flags, __entry->incr,  __print_array(
+		  __get_dynamic_array(dst), __entry->nptes, 8))
+);
+
 TRACE_EVENT(amdgpu_vm_set_ptes,
 	    TP_PROTO(uint64_t pe, uint64_t addr, unsigned count,
 		     uint32_t incr, uint64_t flags, bool direct),
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index f3416cc1bd04..bd6e6641c3fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1043,6 +1043,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_bo_device *bdev,
 
 release_sg:
 	kfree(ttm->sg);
+	ttm->sg = NULL;
 	return r;
 }
 
@@ -1186,7 +1187,12 @@ static int amdgpu_ttm_backend_bind(struct ttm_bo_device *bdev,
 }
 
 /**
- * amdgpu_ttm_alloc_gart - Allocate GART memory for buffer object
+ * amdgpu_ttm_alloc_gart - Make sure buffer object is accessible either
+ * through AGP or GART aperture.
+ *
+ * If bo is accessible through AGP aperture, then use AGP aperture
+ * to access bo; otherwise allocate logical space in GART aperture
+ * and map bo to GART aperture.
  */
 int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 55fe19a2f332..b313ce4c3e97 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -500,6 +500,8 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL &&
 	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM &&
 	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM &&
+	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_IRAM &&
+	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_DRAM &&
 		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_ERAM &&
 		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_INTV &&
 		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCUB)) {
@@ -556,6 +558,14 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 		ucode->ucode_size = adev->gfx.rlc.save_restore_list_srm_size_bytes;
 		memcpy(ucode->kaddr, adev->gfx.rlc.save_restore_list_srm,
 		       ucode->ucode_size);
+	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_IRAM) {
+		ucode->ucode_size = adev->gfx.rlc.rlc_iram_ucode_size_bytes;
+		memcpy(ucode->kaddr, adev->gfx.rlc.rlc_iram_ucode,
+		       ucode->ucode_size);
+	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_DRAM) {
+		ucode->ucode_size = adev->gfx.rlc.rlc_dram_ucode_size_bytes;
+		memcpy(ucode->kaddr, adev->gfx.rlc.rlc_dram_ucode,
+		       ucode->ucode_size);
 	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_CP_MES) {
 		ucode->ucode_size = le32_to_cpu(mes_hdr->mes_ucode_size_bytes);
 		memcpy(ucode->kaddr, (void *)((uint8_t *)adev->mes.fw->data +
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 3c23c6293ff9..0e43b46d3ab5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -222,6 +222,15 @@ struct rlc_firmware_header_v2_1 {
 	uint32_t save_restore_list_srm_offset_bytes;
 };
 
+/* version_major=2, version_minor=1 */
+struct rlc_firmware_header_v2_2 {
+	struct rlc_firmware_header_v2_1 v2_1;
+	uint32_t rlc_iram_ucode_size_bytes;
+	uint32_t rlc_iram_ucode_offset_bytes;
+	uint32_t rlc_dram_ucode_size_bytes;
+	uint32_t rlc_dram_ucode_offset_bytes;
+};
+
 /* version_major=1, version_minor=0 */
 struct sdma_firmware_header_v1_0 {
 	struct common_firmware_header header;
@@ -339,6 +348,8 @@ enum AMDGPU_UCODE_ID {
 	AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL,
 	AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM,
 	AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM,
+	AMDGPU_UCODE_ID_RLC_IRAM,
+	AMDGPU_UCODE_ID_RLC_DRAM,
 	AMDGPU_UCODE_ID_RLC_G,
 	AMDGPU_UCODE_ID_STORAGE,
 	AMDGPU_UCODE_ID_SMC,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 495c3d7bb2b2..f3b7287e84c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -68,6 +68,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 
 	INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler);
 	mutex_init(&adev->vcn.vcn_pg_lock);
+	mutex_init(&adev->vcn.vcn1_jpeg1_workaround);
 	atomic_set(&adev->vcn.total_submission_cnt, 0);
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++)
 		atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0);
@@ -237,6 +238,7 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 	}
 
 	release_firmware(adev->vcn.fw);
+	mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround);
 	mutex_destroy(&adev->vcn.vcn_pg_lock);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 7a9b804bc988..17691158f783 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -220,6 +220,7 @@ struct amdgpu_vcn {
 	struct amdgpu_vcn_inst	 inst[AMDGPU_MAX_VCN_INSTANCES];
 	struct amdgpu_vcn_reg	 internal;
 	struct mutex		 vcn_pg_lock;
+	struct mutex		vcn1_jpeg1_workaround;
 	atomic_t		 total_submission_cnt;
 
 	unsigned	harvest_config;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index f76961d17246..d0aea5e39531 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -31,6 +31,12 @@
 #include "soc15.h"
 #include "nv.h"
 
+#define POPULATE_UCODE_INFO(vf2pf_info, ucode, ver) \
+	do { \
+		vf2pf_info->ucode_info[ucode].id = ucode; \
+		vf2pf_info->ucode_info[ucode].version = ver; \
+	} while (0)
+
 bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev)
 {
 	/* By now all MMIO pages except mailbox are blocked */
@@ -239,10 +245,10 @@ void amdgpu_virt_free_mm_table(struct amdgpu_device *adev)
 }
 
 
-int amdgpu_virt_fw_reserve_get_checksum(void *obj,
-					unsigned long obj_size,
-					unsigned int key,
-					unsigned int chksum)
+unsigned int amd_sriov_msg_checksum(void *obj,
+				unsigned long obj_size,
+				unsigned int key,
+				unsigned int checksum)
 {
 	unsigned int ret = key;
 	unsigned long i = 0;
@@ -252,9 +258,9 @@ int amdgpu_virt_fw_reserve_get_checksum(void *obj,
 	/* calculate checksum */
 	for (i = 0; i < obj_size; ++i)
 		ret += *(pos + i);
-	/* minus the chksum itself */
-	pos = (char *)&chksum;
-	for (i = 0; i < sizeof(chksum); ++i)
+	/* minus the checksum itself */
+	pos = (char *)&checksum;
+	for (i = 0; i < sizeof(checksum); ++i)
 		ret -= *(pos + i);
 	return ret;
 }
@@ -415,33 +421,188 @@ static void amdgpu_virt_add_bad_page(struct amdgpu_device *adev,
 	}
 }
 
-void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
+static int amdgpu_virt_read_pf2vf_data(struct amdgpu_device *adev)
 {
-	uint32_t pf2vf_size = 0;
-	uint32_t checksum = 0;
+	struct amd_sriov_msg_pf2vf_info_header *pf2vf_info = adev->virt.fw_reserve.p_pf2vf;
+	uint32_t checksum;
 	uint32_t checkval;
-	char *str;
+
+	if (adev->virt.fw_reserve.p_pf2vf == NULL)
+		return -EINVAL;
+
+	if (pf2vf_info->size > 1024) {
+		DRM_ERROR("invalid pf2vf message size\n");
+		return -EINVAL;
+	}
+
+	switch (pf2vf_info->version) {
+	case 1:
+		checksum = ((struct amdgim_pf2vf_info_v1 *)pf2vf_info)->checksum;
+		checkval = amd_sriov_msg_checksum(
+			adev->virt.fw_reserve.p_pf2vf, pf2vf_info->size,
+			adev->virt.fw_reserve.checksum_key, checksum);
+		if (checksum != checkval) {
+			DRM_ERROR("invalid pf2vf message\n");
+			return -EINVAL;
+		}
+
+		adev->virt.gim_feature =
+			((struct amdgim_pf2vf_info_v1 *)pf2vf_info)->feature_flags;
+		break;
+	case 2:
+		/* TODO: missing key, need to add it later */
+		checksum = ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->checksum;
+		checkval = amd_sriov_msg_checksum(
+			adev->virt.fw_reserve.p_pf2vf, pf2vf_info->size,
+			0, checksum);
+		if (checksum != checkval) {
+			DRM_ERROR("invalid pf2vf message\n");
+			return -EINVAL;
+		}
+
+		adev->virt.vf2pf_update_interval_ms =
+			((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->vf2pf_update_interval_ms;
+		adev->virt.gim_feature =
+			((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->feature_flags.all;
+
+		break;
+	default:
+		DRM_ERROR("invalid pf2vf version\n");
+		return -EINVAL;
+	}
+
+	/* correct too large or too little interval value */
+	if (adev->virt.vf2pf_update_interval_ms < 200 || adev->virt.vf2pf_update_interval_ms > 10000)
+		adev->virt.vf2pf_update_interval_ms = 2000;
+
+	return 0;
+}
+
+static void amdgpu_virt_populate_vf2pf_ucode_info(struct amdgpu_device *adev)
+{
+	struct amd_sriov_msg_vf2pf_info *vf2pf_info;
+	vf2pf_info = (struct amd_sriov_msg_vf2pf_info *) adev->virt.fw_reserve.p_vf2pf;
+
+	if (adev->virt.fw_reserve.p_vf2pf == NULL)
+		return;
+
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_VCE,      adev->vce.fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_UVD,      adev->uvd.fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MC,       adev->gmc.fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ME,       adev->gfx.me_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_PFP,      adev->gfx.pfp_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_CE,       adev->gfx.ce_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC,      adev->gfx.rlc_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLC, adev->gfx.rlc_srlc_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLG, adev->gfx.rlc_srlg_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLS, adev->gfx.rlc_srls_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC,      adev->gfx.mec_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC2,     adev->gfx.mec2_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SOS,      adev->psp.sos_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ASD,      adev->psp.asd_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_RAS,   adev->psp.ta_ras_ucode_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_XGMI,  adev->psp.ta_xgmi_ucode_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SMC,      adev->pm.fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SDMA,     adev->sdma.instance[0].fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SDMA2,    adev->sdma.instance[1].fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_VCN,      adev->vcn.fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_DMCU,     adev->dm.dmcu_fw_version);
+}
+
+static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev)
+{
+	struct amd_sriov_msg_vf2pf_info *vf2pf_info;
+	struct ttm_resource_manager *vram_man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
+
+	vf2pf_info = (struct amd_sriov_msg_vf2pf_info *) adev->virt.fw_reserve.p_vf2pf;
+
+	if (adev->virt.fw_reserve.p_vf2pf == NULL)
+		return -EINVAL;
+
+	memset(vf2pf_info, 0, sizeof(struct amd_sriov_msg_vf2pf_info));
+
+	vf2pf_info->header.size = sizeof(struct amd_sriov_msg_vf2pf_info);
+	vf2pf_info->header.version = AMD_SRIOV_MSG_FW_VRAM_VF2PF_VER;
+
+#ifdef MODULE
+	if (THIS_MODULE->version != NULL)
+		strcpy(vf2pf_info->driver_version, THIS_MODULE->version);
+	else
+#endif
+		strcpy(vf2pf_info->driver_version, "N/A");
+
+	vf2pf_info->pf2vf_version_required = 0; // no requirement, guest understands all
+	vf2pf_info->driver_cert = 0;
+	vf2pf_info->os_info.all = 0;
+
+	vf2pf_info->fb_usage = amdgpu_vram_mgr_usage(vram_man) >> 20;
+	vf2pf_info->fb_vis_usage = amdgpu_vram_mgr_vis_usage(vram_man) >> 20;
+	vf2pf_info->fb_size = adev->gmc.real_vram_size >> 20;
+	vf2pf_info->fb_vis_size = adev->gmc.visible_vram_size >> 20;
+
+	amdgpu_virt_populate_vf2pf_ucode_info(adev);
+
+	/* TODO: read dynamic info */
+	vf2pf_info->gfx_usage = 0;
+	vf2pf_info->compute_usage = 0;
+	vf2pf_info->encode_usage = 0;
+	vf2pf_info->decode_usage = 0;
+
+	vf2pf_info->checksum =
+		amd_sriov_msg_checksum(
+		vf2pf_info, vf2pf_info->header.size, 0, 0);
+
+	return 0;
+}
+
+void amdgpu_virt_update_vf2pf_work_item(struct work_struct *work)
+{
+	struct amdgpu_device *adev = container_of(work, struct amdgpu_device, virt.vf2pf_work.work);
+
+	amdgpu_virt_read_pf2vf_data(adev);
+	amdgpu_virt_write_vf2pf_data(adev);
+
+	schedule_delayed_work(&(adev->virt.vf2pf_work), adev->virt.vf2pf_update_interval_ms);
+}
+
+void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev)
+{
+	if (adev->virt.vf2pf_update_interval_ms != 0) {
+		DRM_INFO("clean up the vf2pf work item\n");
+		flush_delayed_work(&adev->virt.vf2pf_work);
+		cancel_delayed_work_sync(&adev->virt.vf2pf_work);
+	}
+}
+
+void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
+{
 	uint64_t bp_block_offset = 0;
 	uint32_t bp_block_size = 0;
-	struct amdgim_pf2vf_info_v2 *pf2vf_v2 = NULL;
+	struct amd_sriov_msg_pf2vf_info *pf2vf_v2 = NULL;
 
 	adev->virt.fw_reserve.p_pf2vf = NULL;
 	adev->virt.fw_reserve.p_vf2pf = NULL;
+	adev->virt.vf2pf_update_interval_ms = 0;
 
 	if (adev->mman.fw_vram_usage_va != NULL) {
+		adev->virt.vf2pf_update_interval_ms = 2000;
+
 		adev->virt.fw_reserve.p_pf2vf =
-			(struct amd_sriov_msg_pf2vf_info_header *)(
-			adev->mman.fw_vram_usage_va + AMDGIM_DATAEXCHANGE_OFFSET);
-		AMDGPU_FW_VRAM_PF2VF_READ(adev, header.size, &pf2vf_size);
-		AMDGPU_FW_VRAM_PF2VF_READ(adev, checksum, &checksum);
-		AMDGPU_FW_VRAM_PF2VF_READ(adev, feature_flags, &adev->virt.gim_feature);
-
-		/* pf2vf message must be in 4K */
-		if (pf2vf_size > 0 && pf2vf_size < 4096) {
-			if (adev->virt.fw_reserve.p_pf2vf->version == 2) {
-				pf2vf_v2 = (struct amdgim_pf2vf_info_v2 *)adev->virt.fw_reserve.p_pf2vf;
-				bp_block_offset = ((uint64_t)pf2vf_v2->bp_block_offset_L & 0xFFFFFFFF) |
-						((((uint64_t)pf2vf_v2->bp_block_offset_H) << 32) & 0xFFFFFFFF00000000);
+			(struct amd_sriov_msg_pf2vf_info_header *)
+			(adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
+		adev->virt.fw_reserve.p_vf2pf =
+			(struct amd_sriov_msg_vf2pf_info_header *)
+			(adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_VF2PF_OFFSET_KB << 10));
+
+		amdgpu_virt_read_pf2vf_data(adev);
+		amdgpu_virt_write_vf2pf_data(adev);
+
+		/* bad page handling for version 2 */
+		if (adev->virt.fw_reserve.p_pf2vf->version == 2) {
+				pf2vf_v2 = (struct amd_sriov_msg_pf2vf_info *)adev->virt.fw_reserve.p_pf2vf;
+
+				bp_block_offset = ((uint64_t)pf2vf_v2->bp_block_offset_low & 0xFFFFFFFF) |
+						((((uint64_t)pf2vf_v2->bp_block_offset_high) << 32) & 0xFFFFFFFF00000000);
 				bp_block_size = pf2vf_v2->bp_block_size;
 
 				if (bp_block_size && !adev->virt.ras_init_done)
@@ -450,37 +611,11 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 				if (adev->virt.ras_init_done)
 					amdgpu_virt_add_bad_page(adev, bp_block_offset, bp_block_size);
 			}
+	}
 
-			checkval = amdgpu_virt_fw_reserve_get_checksum(
-				adev->virt.fw_reserve.p_pf2vf, pf2vf_size,
-				adev->virt.fw_reserve.checksum_key, checksum);
-			if (checkval == checksum) {
-				adev->virt.fw_reserve.p_vf2pf =
-					((void *)adev->virt.fw_reserve.p_pf2vf +
-					pf2vf_size);
-				memset((void *)adev->virt.fw_reserve.p_vf2pf, 0,
-					sizeof(amdgim_vf2pf_info));
-				AMDGPU_FW_VRAM_VF2PF_WRITE(adev, header.version,
-					AMDGPU_FW_VRAM_VF2PF_VER);
-				AMDGPU_FW_VRAM_VF2PF_WRITE(adev, header.size,
-					sizeof(amdgim_vf2pf_info));
-				AMDGPU_FW_VRAM_VF2PF_READ(adev, driver_version,
-					&str);
-#ifdef MODULE
-				if (THIS_MODULE->version != NULL)
-					strcpy(str, THIS_MODULE->version);
-				else
-#endif
-					strcpy(str, "N/A");
-				AMDGPU_FW_VRAM_VF2PF_WRITE(adev, driver_cert,
-					0);
-				AMDGPU_FW_VRAM_VF2PF_WRITE(adev, checksum,
-					amdgpu_virt_fw_reserve_get_checksum(
-					adev->virt.fw_reserve.p_vf2pf,
-					pf2vf_size,
-					adev->virt.fw_reserve.checksum_key, 0));
-			}
-		}
+	if (adev->virt.vf2pf_update_interval_ms != 0) {
+		INIT_DELAYED_WORK(&adev->virt.vf2pf_work, amdgpu_virt_update_vf2pf_work_item);
+		schedule_delayed_work(&(adev->virt.vf2pf_work), adev->virt.vf2pf_update_interval_ms);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index b2046c3a404d..8dd624c20f89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -24,6 +24,8 @@
 #ifndef AMDGPU_VIRT_H
 #define AMDGPU_VIRT_H
 
+#include "amdgv_sriovmsg.h"
+
 #define AMDGPU_SRIOV_CAPS_SRIOV_VBIOS  (1 << 0) /* vBIOS is sr-iov ready */
 #define AMDGPU_SRIOV_CAPS_ENABLE_IOV   (1 << 1) /* sr-iov is enabled on this GPU */
 #define AMDGPU_SRIOV_CAPS_IS_VF        (1 << 2) /* this GPU is a virtual function */
@@ -79,7 +81,10 @@ struct amdgpu_virt_fw_reserve {
 	struct amd_sriov_msg_vf2pf_info_header *p_vf2pf;
 	unsigned int checksum_key;
 };
+
 /*
+ * Legacy GIM header
+ *
  * Defination between PF and VF
  * Structures forcibly aligned to 4 to keep the same style as PF.
  */
@@ -101,15 +106,7 @@ enum AMDGIM_FEATURE_FLAG {
 	AMDGIM_FEATURE_PP_ONE_VF = (1 << 4),
 };
 
-struct amd_sriov_msg_pf2vf_info_header {
-	/* the total structure size in byte. */
-	uint32_t size;
-	/* version of this structure, written by the GIM */
-	uint32_t version;
-	/* reserved */
-	uint32_t reserved[2];
-} __aligned(4);
-struct  amdgim_pf2vf_info_v1 {
+struct amdgim_pf2vf_info_v1 {
 	/* header contains size and version */
 	struct amd_sriov_msg_pf2vf_info_header header;
 	/* max_width * max_height */
@@ -128,54 +125,6 @@ struct  amdgim_pf2vf_info_v1 {
 	unsigned int checksum;
 } __aligned(4);
 
-struct  amdgim_pf2vf_info_v2 {
-	/* header contains size and version */
-	struct amd_sriov_msg_pf2vf_info_header header;
-	/* use private key from mailbox 2 to create chueksum */
-	uint32_t checksum;
-	/* The features flags of the GIM driver supports. */
-	uint32_t feature_flags;
-	/* max_width * max_height */
-	uint32_t uvd_enc_max_pixels_count;
-	/* 16x16 pixels/sec, codec independent */
-	uint32_t uvd_enc_max_bandwidth;
-	/* max_width * max_height */
-	uint32_t vce_enc_max_pixels_count;
-	/* 16x16 pixels/sec, codec independent */
-	uint32_t vce_enc_max_bandwidth;
-	/* Bad pages block position in BYTE */
-	uint32_t bp_block_offset_L;
-	uint32_t bp_block_offset_H;
-	/* Bad pages block size in BYTE */
-	uint32_t bp_block_size;
-	/* MEC FW position in kb from the start of VF visible frame buffer */
-	uint32_t mecfw_kboffset_L;
-	uint32_t mecfw_kboffset_H;
-	/* MEC FW size in KB */
-	uint32_t mecfw_ksize;
-	/* UVD FW position in kb from the start of VF visible frame buffer */
-	uint32_t uvdfw_kboffset_L;
-	uint32_t uvdfw_kboffset_H;
-	/* UVD FW size in KB */
-	uint32_t uvdfw_ksize;
-	/* VCE FW position in kb from the start of VF visible frame buffer */
-	uint32_t vcefw_kboffset_L;
-	uint32_t vcefw_kboffset_H;
-	/* VCE FW size in KB */
-	uint32_t vcefw_ksize;
-	uint32_t reserved[AMDGIM_GET_STRUCTURE_RESERVED_SIZE(256, 0, 0, (18 + sizeof(struct amd_sriov_msg_pf2vf_info_header)/sizeof(uint32_t)), 0)];
-} __aligned(4);
-
-
-struct amd_sriov_msg_vf2pf_info_header {
-	/* the total structure size in byte. */
-	uint32_t size;
-	/*version of this structure, written by the guest */
-	uint32_t version;
-	/* reserved */
-	uint32_t reserved[2];
-} __aligned(4);
-
 struct amdgim_vf2pf_info_v1 {
 	/* header contains size and version */
 	struct amd_sriov_msg_vf2pf_info_header header;
@@ -237,31 +186,6 @@ struct amdgim_vf2pf_info_v2 {
 	uint32_t reserved[AMDGIM_GET_STRUCTURE_RESERVED_SIZE(256, 64, 0, (12 + sizeof(struct amd_sriov_msg_vf2pf_info_header)/sizeof(uint32_t)), 0)];
 } __aligned(4);
 
-#define AMDGPU_FW_VRAM_VF2PF_VER 2
-typedef struct amdgim_vf2pf_info_v2 amdgim_vf2pf_info ;
-
-#define AMDGPU_FW_VRAM_VF2PF_WRITE(adev, field, val) \
-	do { \
-		((amdgim_vf2pf_info *)adev->virt.fw_reserve.p_vf2pf)->field = (val); \
-	} while (0)
-
-#define AMDGPU_FW_VRAM_VF2PF_READ(adev, field, val) \
-	do { \
-		(*val) = ((amdgim_vf2pf_info *)adev->virt.fw_reserve.p_vf2pf)->field; \
-	} while (0)
-
-#define AMDGPU_FW_VRAM_PF2VF_READ(adev, field, val) \
-	do { \
-		if (!adev->virt.fw_reserve.p_pf2vf) \
-			*(val) = 0; \
-		else { \
-			if (adev->virt.fw_reserve.p_pf2vf->version == 1) \
-				*(val) = ((struct amdgim_pf2vf_info_v1 *)adev->virt.fw_reserve.p_pf2vf)->field; \
-			if (adev->virt.fw_reserve.p_pf2vf->version == 2) \
-				*(val) = ((struct amdgim_pf2vf_info_v2 *)adev->virt.fw_reserve.p_pf2vf)->field; \
-		} \
-	} while (0)
-
 struct amdgpu_virt_ras_err_handler_data {
 	/* point to bad page records array */
 	struct eeprom_table_record *bps;
@@ -285,7 +209,7 @@ struct amdgpu_virt {
 	struct work_struct		flr_work;
 	struct amdgpu_mm_table		mm_table;
 	const struct amdgpu_virt_ops	*ops;
-	struct amdgpu_vf_error_buffer   vf_errors;
+	struct amdgpu_vf_error_buffer	vf_errors;
 	struct amdgpu_virt_fw_reserve	fw_reserve;
 	uint32_t gim_feature;
 	uint32_t reg_access_mode;
@@ -293,6 +217,10 @@ struct amdgpu_virt {
 	bool tdr_debug;
 	struct amdgpu_virt_ras_err_handler_data *virt_eh_data;
 	bool ras_init_done;
+
+	/* vf2pf message */
+	struct delayed_work vf2pf_work;
+	uint32_t vf2pf_update_interval_ms;
 };
 
 #define amdgpu_sriov_enabled(adev) \
@@ -341,11 +269,9 @@ void amdgpu_virt_request_init_data(struct amdgpu_device *adev);
 int amdgpu_virt_wait_reset(struct amdgpu_device *adev);
 int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev);
 void amdgpu_virt_free_mm_table(struct amdgpu_device *adev);
-int amdgpu_virt_fw_reserve_get_checksum(void *obj, unsigned long obj_size,
-					unsigned int key,
-					unsigned int chksum);
 void amdgpu_virt_release_ras_err_handler_data(struct amdgpu_device *adev);
 void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev);
+void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev);
 void amdgpu_detect_virtualization(struct amdgpu_device *adev);
 
 bool amdgpu_virt_can_access_debugfs(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index f0e6fafd0938..38b59a4fc04c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1502,6 +1502,8 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
 
 			pt = cursor.entry->base.bo;
 			shift = parent_shift;
+			frag_end = max(frag_end, ALIGN(frag_start + 1,
+				   1ULL << shift));
 		}
 
 		/* Looks good so far, calculate parameters for the update */
@@ -1513,19 +1515,26 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
 		entry_end = min(entry_end, end);
 
 		do {
+			struct amdgpu_vm *vm = params->vm;
 			uint64_t upd_end = min(entry_end, frag_end);
 			unsigned nptes = (upd_end - frag_start) >> shift;
+			uint64_t upd_flags = flags | AMDGPU_PTE_FRAG(frag);
 
 			/* This can happen when we set higher level PDs to
 			 * silent to stop fault floods.
 			 */
 			nptes = max(nptes, 1u);
+
+			trace_amdgpu_vm_update_ptes(params, frag_start, upd_end,
+						    nptes, dst, incr, upd_flags,
+						    vm->task_info.pid,
+						    vm->immediate.fence_context);
 			amdgpu_vm_update_flags(params, pt, cursor.level,
 					       pe_start, dst, nptes, incr,
-					       flags | AMDGPU_PTE_FRAG(frag));
+					       upd_flags);
 
 			pe_start += nptes * 8;
-			dst += (uint64_t)nptes * AMDGPU_GPU_PAGE_SIZE << shift;
+			dst += nptes * incr;
 
 			frag_start = upd_end;
 			if (frag_start >= frag_end) {
@@ -2795,7 +2804,7 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
  * 0 for success, error for failure.
  */
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		   int vm_context, unsigned int pasid)
+		   int vm_context, u32 pasid)
 {
 	struct amdgpu_bo_param bp;
 	struct amdgpu_bo *root;
@@ -2966,7 +2975,7 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
  * 0 for success, -errno for errors.
  */
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			   unsigned int pasid)
+			   u32 pasid)
 {
 	bool pte_support_ats = (adev->asic_type == CHIP_RAVEN);
 	int r;
@@ -3264,7 +3273,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
  * @pasid: PASID identifier for VM
  * @task_info: task_info to fill.
  */
-void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
 			 struct amdgpu_task_info *task_info)
 {
 	struct amdgpu_vm *vm;
@@ -3308,7 +3317,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
  * Try to gracefully handle a VM fault. Return true if the fault was handled and
  * shouldn't be reported any more.
  */
-bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
+bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 			    uint64_t addr)
 {
 	struct amdgpu_bo *root;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 770025a5e500..58c83a7ad0fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -98,7 +98,7 @@ struct amdgpu_bo_list_entry;
 #define AMDGPU_PTE_MTYPE_NV10(a)       ((uint64_t)(a) << 48)
 #define AMDGPU_PTE_MTYPE_NV10_MASK     AMDGPU_PTE_MTYPE_NV10(7ULL)
 
-/* How to programm VM fault handling */
+/* How to program VM fault handling */
 #define AMDGPU_VM_FAULT_STOP_NEVER	0
 #define AMDGPU_VM_FAULT_STOP_FIRST	1
 #define AMDGPU_VM_FAULT_STOP_ALWAYS	2
@@ -112,8 +112,8 @@ struct amdgpu_bo_list_entry;
 #define AMDGPU_MMHUB_0				1
 #define AMDGPU_MMHUB_1				2
 
-/* hardcode that limit for now */
-#define AMDGPU_VA_RESERVED_SIZE			(1ULL << 20)
+/* Reserve 2MB at top/bottom of address space for kernel use */
+#define AMDGPU_VA_RESERVED_SIZE			(2ULL << 20)
 
 /* max vmids dedicated for process */
 #define AMDGPU_VM_MAX_RESERVED_VMID	1
@@ -372,8 +372,8 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
 
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout);
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		   int vm_context, unsigned int pasid);
-int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned int pasid);
+		   int vm_context, u32 pasid);
+int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid);
 void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
@@ -430,9 +430,9 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 				  struct amdgpu_job *job);
 void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
 
-void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
 			     struct amdgpu_task_info *task_info);
-bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
+bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 			    uint64_t addr);
 
 void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
index 39c704a1fb0e..0786e7555554 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
@@ -59,7 +59,7 @@ static int amdgpu_vm_cpu_prepare(struct amdgpu_vm_update_params *p,
  *
  * @p: see amdgpu_vm_update_params definition
  * @bo: PD/PT to update
- * @pe: kmap addr of the page entry
+ * @pe: byte offset of the PDE/PTE, relative to start of PDB/PTB
  * @addr: dst addr to write into pe
  * @count: number of page entries to update
  * @incr: increase next addr by incr bytes
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
index 189d46ea603b..db790574dc2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
@@ -155,7 +155,7 @@ static void amdgpu_vm_sdma_copy_ptes(struct amdgpu_vm_update_params *p,
  *
  * @p: see amdgpu_vm_update_params definition
  * @bo: PD/PT to update
- * @pe: addr of the page entry
+ * @pe: byte offset of the PDE/PTE, relative to start of PDB/PTB
  * @addr: dst addr to write into pe
  * @count: number of page entries to update
  * @incr: increase next addr by incr bytes
@@ -187,7 +187,7 @@ static void amdgpu_vm_sdma_set_ptes(struct amdgpu_vm_update_params *p,
  *
  * @p: see amdgpu_vm_update_params definition
  * @bo: PD/PT to update
- * @pe: addr of the page entry
+ * @pe: byte offset of the PDE/PTE, relative to start of PDB/PTB
  * @addr: dst addr to write into pe
  * @count: number of page entries to update
  * @incr: increase next addr by incr bytes
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
new file mode 100644
index 000000000000..5355827ed0ae
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
@@ -0,0 +1,276 @@
+/*
+ * Copyright 2018-2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef AMDGV_SRIOV_MSG__H_
+#define AMDGV_SRIOV_MSG__H_
+
+/* unit in kilobytes */
+#define AMD_SRIOV_MSG_VBIOS_OFFSET              0
+#define AMD_SRIOV_MSG_VBIOS_SIZE_KB             64
+#define AMD_SRIOV_MSG_DATAEXCHANGE_OFFSET_KB    AMD_SRIOV_MSG_VBIOS_SIZE_KB
+#define AMD_SRIOV_MSG_DATAEXCHANGE_SIZE_KB      4
+
+/*
+ * layout
+ * 0           64KB        65KB        66KB
+ * |   VBIOS   |   PF2VF   |   VF2PF   |   Bad Page   | ...
+ * |   64KB    |   1KB     |   1KB     |
+ */
+#define AMD_SRIOV_MSG_SIZE_KB                   1
+#define AMD_SRIOV_MSG_PF2VF_OFFSET_KB           AMD_SRIOV_MSG_DATAEXCHANGE_OFFSET_KB
+#define AMD_SRIOV_MSG_VF2PF_OFFSET_KB           (AMD_SRIOV_MSG_PF2VF_OFFSET_KB + AMD_SRIOV_MSG_SIZE_KB)
+#define AMD_SRIOV_MSG_BAD_PAGE_OFFSET_KB        (AMD_SRIOV_MSG_VF2PF_OFFSET_KB + AMD_SRIOV_MSG_SIZE_KB)
+
+/*
+ * PF2VF history log:
+ * v1 defined in amdgim
+ * v2 current
+ *
+ * VF2PF history log:
+ * v1 defined in amdgim
+ * v2 defined in amdgim
+ * v3 current
+ */
+#define AMD_SRIOV_MSG_FW_VRAM_PF2VF_VER			2
+#define AMD_SRIOV_MSG_FW_VRAM_VF2PF_VER			3
+
+#define AMD_SRIOV_MSG_RESERVE_UCODE		24
+
+enum amd_sriov_ucode_engine_id {
+	AMD_SRIOV_UCODE_ID_VCE = 0,
+	AMD_SRIOV_UCODE_ID_UVD,
+	AMD_SRIOV_UCODE_ID_MC,
+	AMD_SRIOV_UCODE_ID_ME,
+	AMD_SRIOV_UCODE_ID_PFP,
+	AMD_SRIOV_UCODE_ID_CE,
+	AMD_SRIOV_UCODE_ID_RLC,
+	AMD_SRIOV_UCODE_ID_RLC_SRLC,
+	AMD_SRIOV_UCODE_ID_RLC_SRLG,
+	AMD_SRIOV_UCODE_ID_RLC_SRLS,
+	AMD_SRIOV_UCODE_ID_MEC,
+	AMD_SRIOV_UCODE_ID_MEC2,
+	AMD_SRIOV_UCODE_ID_SOS,
+	AMD_SRIOV_UCODE_ID_ASD,
+	AMD_SRIOV_UCODE_ID_TA_RAS,
+	AMD_SRIOV_UCODE_ID_TA_XGMI,
+	AMD_SRIOV_UCODE_ID_SMC,
+	AMD_SRIOV_UCODE_ID_SDMA,
+	AMD_SRIOV_UCODE_ID_SDMA2,
+	AMD_SRIOV_UCODE_ID_VCN,
+	AMD_SRIOV_UCODE_ID_DMCU,
+	AMD_SRIOV_UCODE_ID__MAX
+};
+
+#pragma pack(push, 1) 	// PF2VF / VF2PF data areas are byte packed
+
+union amd_sriov_msg_feature_flags {
+	struct {
+		uint32_t  error_log_collect  : 1;
+		uint32_t  host_load_ucodes   : 1;
+		uint32_t  host_flr_vramlost  : 1;
+		uint32_t  mm_bw_management   : 1;
+		uint32_t  pp_one_vf_mode     : 1;
+		uint32_t  reserved           : 27;
+	} flags;
+	uint32_t      all;
+};
+
+union amd_sriov_msg_os_info {
+	struct {
+		uint32_t  windows            : 1;
+		uint32_t  reserved           : 31;
+	} info;
+	uint32_t      all;
+};
+
+struct amd_sriov_msg_pf2vf_info_header {
+	/* the total structure size in byte */
+	uint32_t size;
+	/* version of this structure, written by the HOST */
+	uint32_t version;
+	/* reserved */
+	uint32_t reserved[2];
+};
+
+struct amd_sriov_msg_pf2vf_info {
+	/* header contains size and version */
+	struct amd_sriov_msg_pf2vf_info_header header;
+	/* use private key from mailbox 2 to create checksum */
+	uint32_t checksum;
+	/* The features flags of the HOST driver supports */
+	union amd_sriov_msg_feature_flags feature_flags;
+	/* (max_width * max_height * fps) / (16 * 16) */
+	uint32_t hevc_enc_max_mb_per_second;
+	/* (max_width * max_height) / (16 * 16) */
+	uint32_t hevc_enc_max_mb_per_frame;
+	/* (max_width * max_height * fps) / (16 * 16) */
+	uint32_t avc_enc_max_mb_per_second;
+	/* (max_width * max_height) / (16 * 16) */
+	uint32_t avc_enc_max_mb_per_frame;
+	/* MEC FW position in BYTE from the start of VF visible frame buffer */
+	uint64_t mecfw_offset;
+	/* MEC FW size in BYTE */
+	uint32_t mecfw_size;
+	/* UVD FW position in BYTE from the start of VF visible frame buffer */
+	uint64_t uvdfw_offset;
+	/* UVD FW size in BYTE */
+	uint32_t uvdfw_size;
+	/* VCE FW position in BYTE from the start of VF visible frame buffer */
+	uint64_t vcefw_offset;
+	/* VCE FW size in BYTE */
+	uint32_t vcefw_size;
+	/* Bad pages block position in BYTE */
+	uint32_t bp_block_offset_low;
+	uint32_t bp_block_offset_high;
+	/* Bad pages block size in BYTE */
+	uint32_t bp_block_size;
+	/* frequency for VF to update the VF2PF area in msec, 0 = manual */
+	uint32_t vf2pf_update_interval_ms;
+	/* identification in ROCm SMI */
+	uint64_t uuid;
+	uint32_t fcn_idx;
+	/* reserved */
+	uint32_t reserved[256-26];
+};
+
+struct amd_sriov_msg_vf2pf_info_header {
+	/* the total structure size in byte */
+	uint32_t size;
+	/* version of this structure, written by the guest */
+	uint32_t version;
+	/* reserved */
+	uint32_t reserved[2];
+};
+
+struct amd_sriov_msg_vf2pf_info {
+	/* header contains size and version */
+	struct amd_sriov_msg_vf2pf_info_header header;
+	uint32_t checksum;
+	/* driver version */
+	uint8_t  driver_version[64];
+	/* driver certification, 1=WHQL, 0=None */
+	uint32_t driver_cert;
+	/* guest OS type and version */
+	union amd_sriov_msg_os_info os_info;
+	/* guest fb information in the unit of MB */
+	uint32_t fb_usage;
+	/* guest gfx engine usage percentage */
+	uint32_t gfx_usage;
+	/* guest gfx engine health percentage */
+	uint32_t gfx_health;
+	/* guest compute engine usage percentage */
+	uint32_t compute_usage;
+	/* guest compute engine health percentage */
+	uint32_t compute_health;
+	/* guest avc engine usage percentage. 0xffff means N/A */
+	uint32_t avc_enc_usage;
+	/* guest avc engine health percentage. 0xffff means N/A */
+	uint32_t avc_enc_health;
+	/* guest hevc engine usage percentage. 0xffff means N/A */
+	uint32_t hevc_enc_usage;
+	/* guest hevc engine usage percentage. 0xffff means N/A */
+	uint32_t hevc_enc_health;
+	/* combined encode/decode usage */
+	uint32_t encode_usage;
+	uint32_t decode_usage;
+	/* Version of PF2VF that VF understands */
+	uint32_t pf2vf_version_required;
+	/* additional FB usage */
+	uint32_t fb_vis_usage;
+	uint32_t fb_vis_size;
+	uint32_t fb_size;
+	/* guest ucode data, each one is 1.25 Dword */
+	struct {
+		uint8_t  id;
+		uint32_t version;
+	} ucode_info[AMD_SRIOV_MSG_RESERVE_UCODE];
+
+	/* reserved */
+	uint32_t reserved[256-68];
+};
+
+/* mailbox message send from guest to host  */
+enum amd_sriov_mailbox_request_message {
+	MB_REQ_MSG_REQ_GPU_INIT_ACCESS = 1,
+	MB_REQ_MSG_REL_GPU_INIT_ACCESS,
+	MB_REQ_MSG_REQ_GPU_FINI_ACCESS,
+	MB_REQ_MSG_REL_GPU_FINI_ACCESS,
+	MB_REQ_MSG_REQ_GPU_RESET_ACCESS,
+	MB_REQ_MSG_REQ_GPU_INIT_DATA,
+
+	MB_REQ_MSG_LOG_VF_ERROR       = 200,
+};
+
+/* mailbox message send from host to guest  */
+enum amd_sriov_mailbox_response_message {
+	MB_RES_MSG_CLR_MSG_BUF = 0,
+	MB_RES_MSG_READY_TO_ACCESS_GPU = 1,
+	MB_RES_MSG_FLR_NOTIFICATION,
+	MB_RES_MSG_FLR_NOTIFICATION_COMPLETION,
+	MB_RES_MSG_SUCCESS,
+	MB_RES_MSG_FAIL,
+	MB_RES_MSG_QUERY_ALIVE,
+	MB_RES_MSG_GPU_INIT_DATA_READY,
+
+	MB_RES_MSG_TEXT_MESSAGE = 255
+};
+
+/* version data stored in MAILBOX_MSGBUF_RCV_DW1 for future expansion */
+enum amd_sriov_gpu_init_data_version {
+	GPU_INIT_DATA_READY_V1 = 1,
+};
+
+#pragma pack(pop)	// Restore previous packing option
+
+/* checksum function between host and guest */
+unsigned int amd_sriov_msg_checksum(void *obj,
+				unsigned long obj_size,
+				unsigned int key,
+				unsigned int checksum);
+
+/* assertion at compile time */
+#ifdef __linux__
+#define stringification(s) _stringification(s)
+#define _stringification(s) #s
+
+_Static_assert(
+	sizeof(struct amd_sriov_msg_vf2pf_info) == AMD_SRIOV_MSG_SIZE_KB << 10,
+	"amd_sriov_msg_vf2pf_info must be " stringification(AMD_SRIOV_MSG_SIZE_KB) " KB");
+
+_Static_assert(
+	sizeof(struct amd_sriov_msg_pf2vf_info) == AMD_SRIOV_MSG_SIZE_KB << 10,
+	"amd_sriov_msg_pf2vf_info must be " stringification(AMD_SRIOV_MSG_SIZE_KB) " KB");
+
+_Static_assert(
+	AMD_SRIOV_MSG_RESERVE_UCODE % 4 == 0,
+	"AMD_SRIOV_MSG_RESERVE_UCODE must be multiple of 4");
+
+_Static_assert(
+	AMD_SRIOV_MSG_RESERVE_UCODE > AMD_SRIOV_UCODE_ID__MAX,
+	"AMD_SRIOV_MSG_RESERVE_UCODE must be bigger than AMD_SRIOV_UCODE_ID__MAX");
+
+#undef _stringification
+#undef stringification
+#endif
+
+#endif /* AMDGV_SRIOV_MSG__H_ */
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index 401c99f0b2d0..db953e95f3d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -316,14 +316,9 @@ static int cik_ih_sw_fini(void *handle)
 
 static int cik_ih_hw_init(void *handle)
 {
-	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = cik_ih_irq_init(adev);
-	if (r)
-		return r;
-
-	return 0;
+	return cik_ih_irq_init(adev);
 }
 
 static int cik_ih_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index cc93577dee03..b4d4b76538d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -47,6 +47,9 @@ static void dce_virtual_set_display_funcs(struct amdgpu_device *adev);
 static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev);
 static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
 					      int index);
+static int dce_virtual_pageflip(struct amdgpu_device *adev,
+				unsigned crtc_id);
+static enum hrtimer_restart dce_virtual_vblank_timer_handle(struct hrtimer *vblank_timer);
 static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *adev,
 							int crtc,
 							enum amdgpu_interrupt_state state);
@@ -171,8 +174,10 @@ static void dce_virtual_crtc_commit(struct drm_crtc *crtc)
 static void dce_virtual_crtc_disable(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
 
-	drm_crtc_vblank_off(crtc);
+	if (dev->num_crtcs)
+		drm_crtc_vblank_off(crtc);
 
 	amdgpu_crtc->enabled = false;
 	amdgpu_crtc->pll_id = ATOM_PPLL_INVALID;
@@ -247,6 +252,11 @@ static int dce_virtual_crtc_init(struct amdgpu_device *adev, int index)
 	amdgpu_crtc->vsync_timer_enabled = AMDGPU_IRQ_STATE_DISABLE;
 	drm_crtc_helper_add(&amdgpu_crtc->base, &dce_virtual_crtc_helper_funcs);
 
+	hrtimer_init(&amdgpu_crtc->vblank_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_set_expires(&amdgpu_crtc->vblank_timer, DCE_VIRTUAL_VBLANK_PERIOD);
+	amdgpu_crtc->vblank_timer.function = dce_virtual_vblank_timer_handle;
+	hrtimer_start(&amdgpu_crtc->vblank_timer,
+		      DCE_VIRTUAL_VBLANK_PERIOD, HRTIMER_MODE_REL);
 	return 0;
 }
 
@@ -476,7 +486,7 @@ static int dce_virtual_hw_fini(void *handle)
 
 	for (i = 0; i<adev->mode_info.num_crtc; i++)
 		if (adev->mode_info.crtcs[i])
-			dce_virtual_set_crtc_vblank_interrupt_state(adev, i, AMDGPU_IRQ_STATE_DISABLE);
+			hrtimer_cancel(&adev->mode_info.crtcs[i]->vblank_timer);
 
 	return 0;
 }
@@ -698,9 +708,15 @@ static enum hrtimer_restart dce_virtual_vblank_timer_handle(struct hrtimer *vbla
 						       struct amdgpu_crtc, vblank_timer);
 	struct drm_device *ddev = amdgpu_crtc->base.dev;
 	struct amdgpu_device *adev = drm_to_adev(ddev);
+	struct amdgpu_irq_src *source = adev->irq.client[AMDGPU_IRQ_CLIENTID_LEGACY].sources
+		[VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER];
+	int irq_type = amdgpu_display_crtc_idx_to_irq_type(adev,
+						amdgpu_crtc->crtc_id);
 
-	drm_handle_vblank(ddev, amdgpu_crtc->crtc_id);
-	dce_virtual_pageflip(adev, amdgpu_crtc->crtc_id);
+	if (amdgpu_irq_enabled(adev, source, irq_type)) {
+		drm_handle_vblank(ddev, amdgpu_crtc->crtc_id);
+		dce_virtual_pageflip(adev, amdgpu_crtc->crtc_id);
+	}
 	hrtimer_start(vblank_timer, DCE_VIRTUAL_VBLANK_PERIOD,
 		      HRTIMER_MODE_REL);
 
@@ -716,21 +732,6 @@ static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *ad
 		return;
 	}
 
-	if (state && !adev->mode_info.crtcs[crtc]->vsync_timer_enabled) {
-		DRM_DEBUG("Enable software vsync timer\n");
-		hrtimer_init(&adev->mode_info.crtcs[crtc]->vblank_timer,
-			     CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		hrtimer_set_expires(&adev->mode_info.crtcs[crtc]->vblank_timer,
-				    DCE_VIRTUAL_VBLANK_PERIOD);
-		adev->mode_info.crtcs[crtc]->vblank_timer.function =
-			dce_virtual_vblank_timer_handle;
-		hrtimer_start(&adev->mode_info.crtcs[crtc]->vblank_timer,
-			      DCE_VIRTUAL_VBLANK_PERIOD, HRTIMER_MODE_REL);
-	} else if (!state && adev->mode_info.crtcs[crtc]->vsync_timer_enabled) {
-		DRM_DEBUG("Disable software vsync timer\n");
-		hrtimer_cancel(&adev->mode_info.crtcs[crtc]->vblank_timer);
-	}
-
 	adev->mode_info.crtcs[crtc]->vsync_timer_enabled = state;
 	DRM_DEBUG("[FM]set crtc %d vblank interrupt state %d\n", crtc, state);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
index 2eab808fffeb..7b89fd2aa44a 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -455,7 +455,8 @@ static int df_v3_6_pmc_get_ctrl_settings(struct amdgpu_device *adev,
 					  uint32_t *lo_base_addr,
 					  uint32_t *hi_base_addr,
 					  uint32_t *lo_val,
-					  uint32_t *hi_val)
+					  uint32_t *hi_val,
+					  bool is_enable)
 {
 
 	uint32_t eventsel, instance, unitmask;
@@ -477,7 +478,8 @@ static int df_v3_6_pmc_get_ctrl_settings(struct amdgpu_device *adev,
 	instance_5432 = (instance >> 2) & 0xf;
 	instance_76 = (instance >> 6) & 0x3;
 
-	*lo_val = (unitmask << 8) | (instance_10 << 6) | eventsel | (1 << 22);
+	*lo_val = (unitmask << 8) | (instance_10 << 6) | eventsel;
+	*lo_val = is_enable ? *lo_val | (1 << 22) : *lo_val & ~(1 << 22);
 	*hi_val = (instance_76 << 29) | instance_5432;
 
 	DRM_DEBUG_DRIVER("config=%llx addr=%08x:%08x val=%08x:%08x",
@@ -572,14 +574,14 @@ static void df_v3_6_reset_perfmon_cntr(struct amdgpu_device *adev,
 }
 
 static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config,
-			     int is_enable)
+			     int is_add)
 {
 	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
 	int err = 0, ret = 0;
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
-		if (is_enable)
+		if (is_add)
 			return df_v3_6_pmc_add_cntr(adev, config);
 
 		df_v3_6_reset_perfmon_cntr(adev, config);
@@ -589,7 +591,8 @@ static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config,
 					&lo_base_addr,
 					&hi_base_addr,
 					&lo_val,
-					&hi_val);
+					&hi_val,
+					true);
 
 		if (ret)
 			return ret;
@@ -612,7 +615,7 @@ static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config,
 }
 
 static int df_v3_6_pmc_stop(struct amdgpu_device *adev, uint64_t config,
-			    int is_disable)
+			    int is_remove)
 {
 	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
 	int ret = 0;
@@ -624,15 +627,17 @@ static int df_v3_6_pmc_stop(struct amdgpu_device *adev, uint64_t config,
 			&lo_base_addr,
 			&hi_base_addr,
 			&lo_val,
-			&hi_val);
+			&hi_val,
+			false);
 
 		if (ret)
 			return ret;
 
-		df_v3_6_reset_perfmon_cntr(adev, config);
 
-		if (is_disable)
+		if (is_remove) {
+			df_v3_6_reset_perfmon_cntr(adev, config);
 			df_v3_6_pmc_release_cntr(adev, config);
+		}
 
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index d502e30f67d9..56fdbe626d30 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -112,6 +112,22 @@
 #define mmCP_HYP_ME_UCODE_DATA			0x5817
 #define mmCP_HYP_ME_UCODE_DATA_BASE_IDX		1
 
+//CC_GC_SA_UNIT_DISABLE
+#define mmCC_GC_SA_UNIT_DISABLE                 0x0fe9
+#define mmCC_GC_SA_UNIT_DISABLE_BASE_IDX        0
+#define CC_GC_SA_UNIT_DISABLE__SA_DISABLE__SHIFT	0x8
+#define CC_GC_SA_UNIT_DISABLE__SA_DISABLE_MASK		0x0000FF00L
+//GC_USER_SA_UNIT_DISABLE
+#define mmGC_USER_SA_UNIT_DISABLE               0x0fea
+#define mmGC_USER_SA_UNIT_DISABLE_BASE_IDX      0
+#define GC_USER_SA_UNIT_DISABLE__SA_DISABLE__SHIFT	0x8
+#define GC_USER_SA_UNIT_DISABLE__SA_DISABLE_MASK	0x0000FF00L
+//PA_SC_ENHANCE_3
+#define mmPA_SC_ENHANCE_3                       0x1085
+#define mmPA_SC_ENHANCE_3_BASE_IDX              0
+#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO__SHIFT 0x3
+#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO_MASK   0x00000008L
+
 MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
 MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
 MODULE_FIRMWARE("amdgpu/navi10_me.bin");
@@ -3091,6 +3107,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CM_CTRL1, 0xff8fff0f, 0x580f1008),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL3, 0xf7ffffff, 0x10f80988),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmLDS_CONFIG,  0x00000020, 0x00000020),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_CL_ENHANCE, 0xf17fffff, 0x01200007),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_TIMEOUT_COUNTER, 0xffffffff, 0x00000800),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0xffffffbf, 0x00000820),
@@ -3188,6 +3205,8 @@ static int gfx_v10_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev);
 static void gfx_v10_0_ring_emit_ce_meta(struct amdgpu_ring *ring, bool resume);
 static void gfx_v10_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume);
 static void gfx_v10_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure);
+static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev);
+static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev);
 
 static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask)
 {
@@ -3560,7 +3579,7 @@ static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev)
 		break;
 	}
 
-	if (adev->gfx.cp_fw_write_wait == false)
+	if (!adev->gfx.cp_fw_write_wait)
 		DRM_WARN_ONCE("CP firmware version too old, please update!");
 }
 
@@ -3586,6 +3605,17 @@ static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev)
 			le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length);
 }
 
+static void gfx_v10_0_init_rlc_iram_dram_microcode(struct amdgpu_device *adev)
+{
+	const struct rlc_firmware_header_v2_2 *rlc_hdr;
+
+	rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data;
+	adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes);
+	adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes);
+	adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes);
+	adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes);
+}
+
 static bool gfx_v10_0_navi10_gfxoff_should_enable(struct amdgpu_device *adev)
 {
 	bool ret = false;
@@ -3610,6 +3640,9 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev)
 		if (!gfx_v10_0_navi10_gfxoff_should_enable(adev))
 			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		break;
+	case CHIP_NAVY_FLOUNDER:
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
+		break;
 	default:
 		break;
 	}
@@ -3698,8 +3731,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
 		version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
 		version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
-		if (version_major == 2 && version_minor == 1)
-			adev->gfx.rlc.is_rlc_v2_1 = true;
 
 		adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
 		adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
@@ -3741,8 +3772,12 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
 			adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
 
-		if (adev->gfx.rlc.is_rlc_v2_1)
-			gfx_v10_0_init_rlc_ext_microcode(adev);
+		if (version_major == 2) {
+			if (version_minor >= 1)
+				gfx_v10_0_init_rlc_ext_microcode(adev);
+			if (version_minor == 2)
+				gfx_v10_0_init_rlc_iram_dram_microcode(adev);
+		}
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks);
@@ -3803,8 +3838,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 			adev->firmware.fw_size +=
 				ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
 		}
-		if (adev->gfx.rlc.is_rlc_v2_1 &&
-		    adev->gfx.rlc.save_restore_list_cntl_size_bytes &&
+		if (adev->gfx.rlc.save_restore_list_cntl_size_bytes &&
 		    adev->gfx.rlc.save_restore_list_gpm_size_bytes &&
 		    adev->gfx.rlc.save_restore_list_srm_size_bytes) {
 			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL];
@@ -3824,6 +3858,21 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 			info->fw = adev->gfx.rlc_fw;
 			adev->firmware.fw_size +=
 				ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE);
+
+			if (adev->gfx.rlc.rlc_iram_ucode_size_bytes &&
+			    adev->gfx.rlc.rlc_dram_ucode_size_bytes) {
+				info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM];
+				info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM;
+				info->fw = adev->gfx.rlc_fw;
+				adev->firmware.fw_size +=
+					ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE);
+
+				info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM];
+				info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM;
+				info->fw = adev->gfx.rlc_fw;
+				adev->firmware.fw_size +=
+					ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE);
+			}
 		}
 
 		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1];
@@ -4533,12 +4582,17 @@ static void gfx_v10_0_setup_rb(struct amdgpu_device *adev)
 	int i, j;
 	u32 data;
 	u32 active_rbs = 0;
+	u32 bitmap;
 	u32 rb_bitmap_width_per_sh = adev->gfx.config.max_backends_per_se /
 					adev->gfx.config.max_sh_per_se;
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+			bitmap = i * adev->gfx.config.max_sh_per_se + j;
+			if ((adev->asic_type == CHIP_SIENNA_CICHLID) &&
+			    ((gfx_v10_3_get_disabled_sa(adev) >> bitmap) & 1))
+				continue;
 			gfx_v10_0_select_se_sh(adev, i, j, 0xffffffff);
 			data = gfx_v10_0_get_rb_active_bitmap(adev);
 			active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) *
@@ -6947,6 +7001,9 @@ static int gfx_v10_0_hw_init(void *handle)
 	if (r)
 		return r;
 
+	if (adev->asic_type == CHIP_SIENNA_CICHLID)
+		gfx_v10_3_program_pbb_mode(adev);
+
 	return r;
 }
 
@@ -6980,15 +7037,19 @@ static int gfx_v10_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);
+
+	if (!adev->in_pci_err_recovery) {
 #ifndef BRING_UP_DEBUG
-	if (amdgpu_async_gfx_ring) {
-		r = gfx_v10_0_kiq_disable_kgq(adev);
-		if (r)
-			DRM_ERROR("KGQ disable failed\n");
-	}
+		if (amdgpu_async_gfx_ring) {
+			r = gfx_v10_0_kiq_disable_kgq(adev);
+			if (r)
+				DRM_ERROR("KGQ disable failed\n");
+		}
 #endif
-	if (amdgpu_gfx_disable_kcq(adev))
-		DRM_ERROR("KCQ disable failed\n");
+		if (amdgpu_gfx_disable_kcq(adev))
+			DRM_ERROR("KCQ disable failed\n");
+	}
+
 	if (amdgpu_sriov_vf(adev)) {
 		gfx_v10_0_cp_gfx_enable(adev, false);
 		/* Program KIQ position of RLC_CP_SCHEDULERS during destroy */
@@ -8756,6 +8817,10 @@ static int gfx_v10_0_get_cu_info(struct amdgpu_device *adev,
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+			bitmap = i * adev->gfx.config.max_sh_per_se + j;
+			if ((adev->asic_type == CHIP_SIENNA_CICHLID) &&
+			    ((gfx_v10_3_get_disabled_sa(adev) >> bitmap) & 1))
+				continue;
 			mask = 1;
 			ao_bitmap = 0;
 			counter = 0;
@@ -8790,6 +8855,47 @@ static int gfx_v10_0_get_cu_info(struct amdgpu_device *adev,
 	return 0;
 }
 
+static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev)
+{
+	uint32_t efuse_setting, vbios_setting, disabled_sa, max_sa_mask;
+
+	efuse_setting = RREG32_SOC15(GC, 0, mmCC_GC_SA_UNIT_DISABLE);
+	efuse_setting &= CC_GC_SA_UNIT_DISABLE__SA_DISABLE_MASK;
+	efuse_setting >>= CC_GC_SA_UNIT_DISABLE__SA_DISABLE__SHIFT;
+
+	vbios_setting = RREG32_SOC15(GC, 0, mmGC_USER_SA_UNIT_DISABLE);
+	vbios_setting &= GC_USER_SA_UNIT_DISABLE__SA_DISABLE_MASK;
+	vbios_setting >>= GC_USER_SA_UNIT_DISABLE__SA_DISABLE__SHIFT;
+
+	max_sa_mask = amdgpu_gfx_create_bitmask(adev->gfx.config.max_sh_per_se *
+						adev->gfx.config.max_shader_engines);
+	disabled_sa = efuse_setting | vbios_setting;
+	disabled_sa &= max_sa_mask;
+
+	return disabled_sa;
+}
+
+static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev)
+{
+	uint32_t max_sa_per_se, max_sa_per_se_mask, max_shader_engines;
+	uint32_t disabled_sa_mask, se_index, disabled_sa_per_se;
+
+	disabled_sa_mask = gfx_v10_3_get_disabled_sa(adev);
+
+	max_sa_per_se = adev->gfx.config.max_sh_per_se;
+	max_sa_per_se_mask = (1 << max_sa_per_se) - 1;
+	max_shader_engines = adev->gfx.config.max_shader_engines;
+
+	for (se_index = 0; max_shader_engines > se_index; se_index++) {
+		disabled_sa_per_se = disabled_sa_mask >> (se_index * max_sa_per_se);
+		disabled_sa_per_se &= max_sa_per_se_mask;
+		if (disabled_sa_per_se == max_sa_per_se_mask) {
+			WREG32_FIELD15(GC, 0, PA_SC_ENHANCE_3, FORCE_PBB_WORKLOAD_MODE_TO_ZERO, 1);
+			break;
+		}
+	}
+}
+
 const struct amdgpu_ip_block_version gfx_v10_0_ip_block =
 {
 	.type = AMD_IP_BLOCK_TYPE_GFX,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 93c63ff3b35e..6959aebae6d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -49,6 +49,7 @@
 #include "amdgpu_ras.h"
 
 #include "gfx_v9_4.h"
+#include "gfx_v9_0.h"
 
 #include "asic_reg/pwr/pwr_10_0_offset.h"
 #include "asic_reg/pwr/pwr_10_0_sh_mask.h"
@@ -788,7 +789,6 @@ static void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev);
 static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
                                  struct amdgpu_cu_info *cu_info);
 static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev);
-static void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 instance);
 static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring);
 static u64 gfx_v9_0_ring_get_rptr_compute(struct amdgpu_ring *ring);
 static int gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
@@ -2075,6 +2075,7 @@ static const struct amdgpu_gfx_funcs gfx_v9_4_gfx_funcs = {
 	.ras_error_inject = &gfx_v9_4_ras_error_inject,
 	.query_ras_error_count = &gfx_v9_4_query_ras_error_count,
 	.reset_ras_error_count = &gfx_v9_4_reset_ras_error_count,
+	.query_ras_error_status = &gfx_v9_4_query_ras_error_status,
 };
 
 static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
@@ -2196,7 +2197,6 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 static int gfx_v9_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 				      int mec, int pipe, int queue)
 {
-	int r;
 	unsigned irq_type;
 	struct amdgpu_ring *ring = &adev->gfx.compute_ring[ring_id];
 	unsigned int hw_prio;
@@ -2221,13 +2221,8 @@ static int gfx_v9_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 	hw_prio = amdgpu_gfx_is_high_priority_compute_queue(adev, ring->queue) ?
 			AMDGPU_GFX_PIPE_PRIO_HIGH : AMDGPU_GFX_PIPE_PRIO_NORMAL;
 	/* type-2 packets are deprecated on MEC, use type-3 instead */
-	r = amdgpu_ring_init(adev, ring, 1024,
-			     &adev->gfx.eop_irq, irq_type, hw_prio);
-	if (r)
-		return r;
-
-
-	return 0;
+	return amdgpu_ring_init(adev, ring, 1024,
+				&adev->gfx.eop_irq, irq_type, hw_prio);
 }
 
 static int gfx_v9_0_sw_init(void *handle)
@@ -2402,7 +2397,8 @@ static void gfx_v9_0_tiling_mode_table_init(struct amdgpu_device *adev)
 	/* TODO */
 }
 
-static void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 instance)
+void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num,
+			   u32 instance)
 {
 	u32 data;
 
@@ -2560,14 +2556,14 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
 			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
 					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
 			tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, RETRY_DISABLE,
-					    !!amdgpu_noretry);
+					    !!adev->gmc.noretry);
 			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, tmp);
 			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_BASES, 0);
 		} else {
 			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
 					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
 			tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, RETRY_DISABLE,
-					    !!amdgpu_noretry);
+					    !!adev->gmc.noretry);
 			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, tmp);
 			tmp = REG_SET_FIELD(0, SH_MEM_BASES, PRIVATE_BASE,
 				(adev->gmc.private_aperture_start >> 48));
@@ -2800,7 +2796,7 @@ static void pwr_10_0_gfxip_control_over_cgpg(struct amdgpu_device *adev,
 	uint32_t default_data = 0;
 
 	default_data = data = RREG32(SOC15_REG_OFFSET(PWR, 0, mmPWR_MISC_CNTL_STATUS));
-	if (enable == true) {
+	if (enable) {
 		/* enable GFXIP control over CGPG */
 		data |= PWR_MISC_CNTL_STATUS__PWR_GFX_RLC_CGPG_EN_MASK;
 		if(default_data != data)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h
index fa5a3fbaf6ab..dfe8d4841f58 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.h
@@ -26,9 +26,7 @@
 
 extern const struct amdgpu_ip_block_version gfx_v9_0_ip_block;
 
-void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num);
-
-uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev);
-int gfx_v9_0_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info);
+void gfx_v9_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num,
+			   u32 instance);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
index bd85aed3523a..bc699d680ce8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c
@@ -992,3 +992,32 @@ int gfx_v9_4_ras_error_inject(struct amdgpu_device *adev, void *inject_if)
 
 	return ret;
 }
+
+static const struct soc15_reg_entry gfx_v9_4_rdrsp_status_regs =
+	{ SOC15_REG_ENTRY(GC, 0, mmGCEA_ERR_STATUS), 0, 1, 32 };
+
+void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev)
+{
+	uint32_t i, j;
+	uint32_t reg_value;
+
+	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
+		return;
+
+	mutex_lock(&adev->grbm_idx_mutex);
+
+	for (i = 0; i < gfx_v9_4_rdrsp_status_regs.se_num; i++) {
+		for (j = 0; j < gfx_v9_4_rdrsp_status_regs.instance;
+		     j++) {
+			gfx_v9_4_select_se_sh(adev, i, 0, j);
+			reg_value = RREG32(SOC15_REG_ENTRY_OFFSET(
+				gfx_v9_4_rdrsp_status_regs));
+			if (reg_value)
+				dev_warn(adev->dev, "GCEA err detected at instance: %d, status: 0x%x!\n",
+						j, reg_value);
+		}
+	}
+
+	gfx_v9_4_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+	mutex_unlock(&adev->grbm_idx_mutex);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h
index 1ffecc5c0f0a..875f18473a98 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h
@@ -34,4 +34,6 @@ int gfx_v9_4_ras_error_inject(struct amdgpu_device *adev,
 
 void gfx_v9_4_reset_ras_error_count(struct amdgpu_device *adev);
 
+void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev);
+
 #endif /* __GFX_V9_4_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index 529e46386a50..fad887a66886 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -245,7 +245,7 @@ static void gfxhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
@@ -403,3 +403,13 @@ void gfxhub_v1_0_init(struct amdgpu_device *adev)
 	hub->eng_addr_distance = mmVM_INVALIDATE_ENG1_ADDR_RANGE_LO32 -
 		mmVM_INVALIDATE_ENG0_ADDR_RANGE_LO32;
 }
+
+
+const struct amdgpu_gfxhub_funcs gfxhub_v1_0_funcs = {
+	.get_mc_fb_offset = gfxhub_v1_0_get_mc_fb_offset,
+	.setup_vm_pt_regs = gfxhub_v1_0_setup_vm_pt_regs,
+	.gart_enable = gfxhub_v1_0_gart_enable,
+	.gart_disable = gfxhub_v1_0_gart_disable,
+	.set_fault_enable_default = gfxhub_v1_0_set_fault_enable_default,
+	.init = gfxhub_v1_0_init,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.h b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.h
index 92d3a70cd9b1..0c46672bbf49 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.h
@@ -33,4 +33,5 @@ u64 gfxhub_v1_0_get_mc_fb_offset(struct amdgpu_device *adev);
 void gfxhub_v1_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
 				uint64_t page_table_base);
 
+extern const struct amdgpu_gfxhub_funcs gfxhub_v1_0_funcs;
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
index c0ab71df0d90..1e24b6d51e41 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
@@ -21,6 +21,7 @@
  *
  */
 #include "amdgpu.h"
+#include "gfxhub_v1_0.h"
 #include "gfxhub_v1_1.h"
 
 #include "gc/gc_9_2_1_offset.h"
@@ -28,7 +29,7 @@
 
 #include "soc15_common.h"
 
-int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
+static int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 {
 	u32 xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_CNTL);
 	u32 max_region =
@@ -66,3 +67,13 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 
 	return 0;
 }
+
+const struct amdgpu_gfxhub_funcs gfxhub_v1_1_funcs = {
+	.get_mc_fb_offset = gfxhub_v1_0_get_mc_fb_offset,
+	.setup_vm_pt_regs = gfxhub_v1_0_setup_vm_pt_regs,
+	.gart_enable = gfxhub_v1_0_gart_enable,
+	.gart_disable = gfxhub_v1_0_gart_disable,
+	.set_fault_enable_default = gfxhub_v1_0_set_fault_enable_default,
+	.init = gfxhub_v1_0_init,
+	.get_xgmi_info = gfxhub_v1_1_get_xgmi_info,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.h b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.h
index d753cf28a0a6..ae5759ffbee3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.h
@@ -24,6 +24,6 @@
 #ifndef __GFXHUB_V1_1_H__
 #define __GFXHUB_V1_1_H__
 
-int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev);
+extern const struct amdgpu_gfxhub_funcs gfxhub_v1_1_funcs;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index b882ac59879a..456360bf58fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -102,7 +102,7 @@ gfxhub_v2_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
 		GCVM_L2_PROTECTION_FAULT_STATUS, RW));
 }
 
-u64 gfxhub_v2_0_get_fb_location(struct amdgpu_device *adev)
+static u64 gfxhub_v2_0_get_fb_location(struct amdgpu_device *adev)
 {
 	u64 base = RREG32_SOC15(GC, 0, mmGCMC_VM_FB_LOCATION_BASE);
 
@@ -112,12 +112,12 @@ u64 gfxhub_v2_0_get_fb_location(struct amdgpu_device *adev)
 	return base;
 }
 
-u64 gfxhub_v2_0_get_mc_fb_offset(struct amdgpu_device *adev)
+static u64 gfxhub_v2_0_get_mc_fb_offset(struct amdgpu_device *adev)
 {
 	return (u64)RREG32_SOC15(GC, 0, mmGCMC_VM_FB_OFFSET) << 24;
 }
 
-void gfxhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+static void gfxhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
 				uint64_t page_table_base)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0];
@@ -153,11 +153,6 @@ static void gfxhub_v2_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	uint64_t value;
 
 	if (!amdgpu_sriov_vf(adev)) {
-		/*
-		 * the new L1 policy will block SRIOV guest from writing
-		 * these regs, and they will be programed at host.
-		 * so skip programing these regs.
-		 */
 		/* Disable AGP. */
 		WREG32_SOC15(GC, 0, mmGCMC_VM_AGP_BASE, 0);
 		WREG32_SOC15(GC, 0, mmGCMC_VM_AGP_TOP, 0);
@@ -318,7 +313,7 @@ static void gfxhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
@@ -347,7 +342,7 @@ static void gfxhub_v2_0_program_invalidation(struct amdgpu_device *adev)
 	}
 }
 
-int gfxhub_v2_0_gart_enable(struct amdgpu_device *adev)
+static int gfxhub_v2_0_gart_enable(struct amdgpu_device *adev)
 {
 	/* GART Enable. */
 	gfxhub_v2_0_init_gart_aperture_regs(adev);
@@ -363,7 +358,7 @@ int gfxhub_v2_0_gart_enable(struct amdgpu_device *adev)
 	return 0;
 }
 
-void gfxhub_v2_0_gart_disable(struct amdgpu_device *adev)
+static void gfxhub_v2_0_gart_disable(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0];
 	u32 tmp;
@@ -394,7 +389,7 @@ void gfxhub_v2_0_gart_disable(struct amdgpu_device *adev)
  * @adev: amdgpu_device pointer
  * @value: true redirects VM faults to the default page
  */
-void gfxhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev,
+static void gfxhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev,
 					  bool value)
 {
 	u32 tmp;
@@ -436,7 +431,7 @@ static const struct amdgpu_vmhub_funcs gfxhub_v2_0_vmhub_funcs = {
 	.get_invalidate_req = gfxhub_v2_0_get_invalidate_req,
 };
 
-void gfxhub_v2_0_init(struct amdgpu_device *adev)
+static void gfxhub_v2_0_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0];
 
@@ -477,3 +472,13 @@ void gfxhub_v2_0_init(struct amdgpu_device *adev)
 
 	hub->vmhub_funcs = &gfxhub_v2_0_vmhub_funcs;
 }
+
+const struct amdgpu_gfxhub_funcs gfxhub_v2_0_funcs = {
+	.get_fb_location = gfxhub_v2_0_get_fb_location,
+	.get_mc_fb_offset = gfxhub_v2_0_get_mc_fb_offset,
+	.setup_vm_pt_regs = gfxhub_v2_0_setup_vm_pt_regs,
+	.gart_enable = gfxhub_v2_0_gart_enable,
+	.gart_disable = gfxhub_v2_0_gart_disable,
+	.set_fault_enable_default = gfxhub_v2_0_set_fault_enable_default,
+	.init = gfxhub_v2_0_init,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h
index 392b8cd94fc0..9ddc35cd53d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h
@@ -24,14 +24,6 @@
 #ifndef __GFXHUB_V2_0_H__
 #define __GFXHUB_V2_0_H__
 
-u64 gfxhub_v2_0_get_fb_location(struct amdgpu_device *adev);
-int gfxhub_v2_0_gart_enable(struct amdgpu_device *adev);
-void gfxhub_v2_0_gart_disable(struct amdgpu_device *adev);
-void gfxhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev,
-					  bool value);
-void gfxhub_v2_0_init(struct amdgpu_device *adev);
-u64 gfxhub_v2_0_get_mc_fb_offset(struct amdgpu_device *adev);
-void gfxhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
-				uint64_t page_table_base);
+extern const struct amdgpu_gfxhub_funcs gfxhub_v2_0_funcs;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
index 237a9ff5afa0..724bb29e9bb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
@@ -102,7 +102,7 @@ gfxhub_v2_1_print_l2_protection_fault_status(struct amdgpu_device *adev,
 		GCVM_L2_PROTECTION_FAULT_STATUS, RW));
 }
 
-u64 gfxhub_v2_1_get_fb_location(struct amdgpu_device *adev)
+static u64 gfxhub_v2_1_get_fb_location(struct amdgpu_device *adev)
 {
 	u64 base = RREG32_SOC15(GC, 0, mmGCMC_VM_FB_LOCATION_BASE);
 
@@ -112,12 +112,12 @@ u64 gfxhub_v2_1_get_fb_location(struct amdgpu_device *adev)
 	return base;
 }
 
-u64 gfxhub_v2_1_get_mc_fb_offset(struct amdgpu_device *adev)
+static u64 gfxhub_v2_1_get_mc_fb_offset(struct amdgpu_device *adev)
 {
 	return (u64)RREG32_SOC15(GC, 0, mmGCMC_VM_FB_OFFSET) << 24;
 }
 
-void gfxhub_v2_1_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+static void gfxhub_v2_1_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
 				uint64_t page_table_base)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0];
@@ -319,7 +319,7 @@ static void gfxhub_v2_1_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
@@ -348,7 +348,7 @@ static void gfxhub_v2_1_program_invalidation(struct amdgpu_device *adev)
 	}
 }
 
-int gfxhub_v2_1_gart_enable(struct amdgpu_device *adev)
+static int gfxhub_v2_1_gart_enable(struct amdgpu_device *adev)
 {
 	if (amdgpu_sriov_vf(adev)) {
 		/*
@@ -376,7 +376,7 @@ int gfxhub_v2_1_gart_enable(struct amdgpu_device *adev)
 	return 0;
 }
 
-void gfxhub_v2_1_gart_disable(struct amdgpu_device *adev)
+static void gfxhub_v2_1_gart_disable(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0];
 	u32 tmp;
@@ -405,7 +405,7 @@ void gfxhub_v2_1_gart_disable(struct amdgpu_device *adev)
  * @adev: amdgpu_device pointer
  * @value: true redirects VM faults to the default page
  */
-void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev,
+static void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev,
 					  bool value)
 {
 	u32 tmp;
@@ -454,7 +454,7 @@ static const struct amdgpu_vmhub_funcs gfxhub_v2_1_vmhub_funcs = {
 	.get_invalidate_req = gfxhub_v2_1_get_invalidate_req,
 };
 
-void gfxhub_v2_1_init(struct amdgpu_device *adev)
+static void gfxhub_v2_1_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB_0];
 
@@ -496,7 +496,7 @@ void gfxhub_v2_1_init(struct amdgpu_device *adev)
 	hub->vmhub_funcs = &gfxhub_v2_1_vmhub_funcs;
 }
 
-int gfxhub_v2_1_get_xgmi_info(struct amdgpu_device *adev)
+static int gfxhub_v2_1_get_xgmi_info(struct amdgpu_device *adev)
 {
 	u32 xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmGCMC_VM_XGMI_LFB_CNTL);
 	u32 max_region =
@@ -531,3 +531,14 @@ int gfxhub_v2_1_get_xgmi_info(struct amdgpu_device *adev)
 
 	return 0;
 }
+
+const struct amdgpu_gfxhub_funcs gfxhub_v2_1_funcs = {
+	.get_fb_location = gfxhub_v2_1_get_fb_location,
+	.get_mc_fb_offset = gfxhub_v2_1_get_mc_fb_offset,
+	.setup_vm_pt_regs = gfxhub_v2_1_setup_vm_pt_regs,
+	.gart_enable = gfxhub_v2_1_gart_enable,
+	.gart_disable = gfxhub_v2_1_gart_disable,
+	.set_fault_enable_default = gfxhub_v2_1_set_fault_enable_default,
+	.init = gfxhub_v2_1_init,
+	.get_xgmi_info = gfxhub_v2_1_get_xgmi_info,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.h b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.h
index 3452a4e9a3da..f75c2eccfad9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.h
@@ -24,16 +24,6 @@
 #ifndef __GFXHUB_V2_1_H__
 #define __GFXHUB_V2_1_H__
 
-u64 gfxhub_v2_1_get_fb_location(struct amdgpu_device *adev);
-int gfxhub_v2_1_gart_enable(struct amdgpu_device *adev);
-void gfxhub_v2_1_gart_disable(struct amdgpu_device *adev);
-void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev,
-					  bool value);
-void gfxhub_v2_1_init(struct amdgpu_device *adev);
-u64 gfxhub_v2_1_get_mc_fb_offset(struct amdgpu_device *adev);
-void gfxhub_v2_1_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
-				uint64_t page_table_base);
-
-int gfxhub_v2_1_get_xgmi_info(struct amdgpu_device *adev);
+extern const struct amdgpu_gfxhub_funcs gfxhub_v2_1_funcs;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 31359e519d69..dbc8b76b9b78 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -634,11 +634,26 @@ static void gmc_v10_0_set_mmhub_funcs(struct amdgpu_device *adev)
 	adev->mmhub.funcs = &mmhub_v2_0_funcs;
 }
 
+static void gmc_v10_0_set_gfxhub_funcs(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_SIENNA_CICHLID:
+	case CHIP_NAVY_FLOUNDER:
+		adev->gfxhub.funcs = &gfxhub_v2_1_funcs;
+		break;
+	default:
+		adev->gfxhub.funcs = &gfxhub_v2_0_funcs;
+		break;
+	}
+}
+
+
 static int gmc_v10_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	gmc_v10_0_set_mmhub_funcs(adev);
+	gmc_v10_0_set_gfxhub_funcs(adev);
 	gmc_v10_0_set_gmc_funcs(adev);
 	gmc_v10_0_set_irq_funcs(adev);
 	gmc_v10_0_set_umc_funcs(adev);
@@ -676,11 +691,7 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev,
 {
 	u64 base = 0;
 
-	if (adev->asic_type == CHIP_SIENNA_CICHLID ||
-	    adev->asic_type == CHIP_NAVY_FLOUNDER)
-		base = gfxhub_v2_1_get_fb_location(adev);
-	else
-		base = gfxhub_v2_0_get_fb_location(adev);
+	base = adev->gfxhub.funcs->get_fb_location(adev);
 
 	/* add the xgmi offset of the physical node */
 	base += adev->gmc.xgmi.physical_node_id * adev->gmc.xgmi.node_segment_size;
@@ -689,11 +700,7 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev,
 	amdgpu_gmc_gart_location(adev, mc);
 
 	/* base offset of vram pages */
-	if (adev->asic_type == CHIP_SIENNA_CICHLID ||
-	    adev->asic_type == CHIP_NAVY_FLOUNDER)
-		adev->vm_manager.vram_base_offset = gfxhub_v2_1_get_mc_fb_offset(adev);
-	else
-		adev->vm_manager.vram_base_offset = gfxhub_v2_0_get_mc_fb_offset(adev);
+	adev->vm_manager.vram_base_offset = adev->gfxhub.funcs->get_mc_fb_offset(adev);
 
 	/* add the xgmi offset of the physical node */
 	adev->vm_manager.vram_base_offset +=
@@ -777,11 +784,7 @@ static int gmc_v10_0_sw_init(void *handle)
 	int r, vram_width = 0, vram_type = 0, vram_vendor = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->asic_type == CHIP_SIENNA_CICHLID ||
-	    adev->asic_type == CHIP_NAVY_FLOUNDER)
-		gfxhub_v2_1_init(adev);
-	else
-		gfxhub_v2_0_init(adev);
+	adev->gfxhub.funcs->init(adev);
 
 	adev->mmhub.funcs->init(adev);
 
@@ -852,7 +855,7 @@ static int gmc_v10_0_sw_init(void *handle)
 	}
 
 	if (adev->gmc.xgmi.supported) {
-		r = gfxhub_v2_1_get_xgmi_info(adev);
+		r = adev->gfxhub.funcs->get_xgmi_info(adev);
 		if (r)
 			return r;
 	}
@@ -944,11 +947,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	if (adev->asic_type == CHIP_SIENNA_CICHLID ||
-	    adev->asic_type == CHIP_NAVY_FLOUNDER)
-		r = gfxhub_v2_1_gart_enable(adev);
-	else
-		r = gfxhub_v2_0_gart_enable(adev);
+	r = adev->gfxhub.funcs->gart_enable(adev);
 	if (r)
 		return r;
 
@@ -969,11 +968,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
 
-	if (adev->asic_type == CHIP_SIENNA_CICHLID ||
-	    adev->asic_type == CHIP_NAVY_FLOUNDER)
-		gfxhub_v2_1_set_fault_enable_default(adev, value);
-	else
-		gfxhub_v2_0_set_fault_enable_default(adev, value);
+	adev->gfxhub.funcs->set_fault_enable_default(adev, value);
 	adev->mmhub.funcs->set_fault_enable_default(adev, value);
 	gmc_v10_0_flush_gpu_tlb(adev, 0, AMDGPU_MMHUB_0, 0);
 	gmc_v10_0_flush_gpu_tlb(adev, 0, AMDGPU_GFXHUB_0, 0);
@@ -1014,11 +1009,7 @@ static int gmc_v10_0_hw_init(void *handle)
  */
 static void gmc_v10_0_gart_disable(struct amdgpu_device *adev)
 {
-	if (adev->asic_type == CHIP_SIENNA_CICHLID ||
-	    adev->asic_type == CHIP_NAVY_FLOUNDER)
-		gfxhub_v2_1_gart_disable(adev);
-	else
-		gfxhub_v2_0_gart_disable(adev);
+	adev->gfxhub.funcs->gart_disable(adev);
 	adev->mmhub.funcs->gart_disable(adev);
 	amdgpu_gart_table_vram_unpin(adev);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 91629c2b1d5c..3ebbddb63705 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -269,7 +269,6 @@ static const char *mmhub_client_ids_arcturus[][2] = {
 	[14][1] = "HDP",
 	[15][1] = "SDMA0",
 	[32+15][1] = "SDMA1",
-	[32+15][1] = "SDMA1",
 	[64+15][1] = "SDMA2",
 	[96+15][1] = "SDMA3",
 	[128+15][1] = "SDMA4",
@@ -1165,6 +1164,19 @@ static void gmc_v9_0_set_mmhub_funcs(struct amdgpu_device *adev)
 	}
 }
 
+static void gmc_v9_0_set_gfxhub_funcs(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_ARCTURUS:
+	case CHIP_VEGA20:
+		adev->gfxhub.funcs = &gfxhub_v1_1_funcs;
+		break;
+	default:
+		adev->gfxhub.funcs = &gfxhub_v1_0_funcs;
+		break;
+	}
+}
+
 static int gmc_v9_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1173,6 +1185,7 @@ static int gmc_v9_0_early_init(void *handle)
 	gmc_v9_0_set_irq_funcs(adev);
 	gmc_v9_0_set_umc_funcs(adev);
 	gmc_v9_0_set_mmhub_funcs(adev);
+	gmc_v9_0_set_gfxhub_funcs(adev);
 
 	adev->gmc.shared_aperture_start = 0x2000000000000000ULL;
 	adev->gmc.shared_aperture_end =
@@ -1194,21 +1207,16 @@ static int gmc_v9_0_late_init(void *handle)
 	r = amdgpu_gmc_allocate_vm_inv_eng(adev);
 	if (r)
 		return r;
-	/* Check if ecc is available */
+
+	/*
+	 * Workaround performance drop issue with VBIOS enables partial
+	 * writes, while disables HBM ECC for vega10.
+	 */
 	if (!amdgpu_sriov_vf(adev) && (adev->asic_type == CHIP_VEGA10)) {
-		r = amdgpu_atomfirmware_mem_ecc_supported(adev);
-		if (!r) {
-			DRM_INFO("ECC is not present.\n");
+		if (!(adev->ras_features & (1 << AMDGPU_RAS_BLOCK__UMC))) {
 			if (adev->df.funcs->enable_ecc_force_par_wr_rmw)
 				adev->df.funcs->enable_ecc_force_par_wr_rmw(adev, false);
-		} else
-			DRM_INFO("ECC is active.\n");
-
-		r = amdgpu_atomfirmware_sram_ecc_supported(adev);
-		if (!r)
-			DRM_INFO("SRAM ECC is not present.\n");
-		else
-			DRM_INFO("SRAM ECC is active.\n");
+		}
 	}
 
 	if (adev->mmhub.funcs && adev->mmhub.funcs->reset_ras_error_count)
@@ -1235,7 +1243,7 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
 	amdgpu_gmc_gart_location(adev, mc);
 	amdgpu_gmc_agp_location(adev, mc);
 	/* base offset of vram pages */
-	adev->vm_manager.vram_base_offset = gfxhub_v1_0_get_mc_fb_offset(adev);
+	adev->vm_manager.vram_base_offset = adev->gfxhub.funcs->get_mc_fb_offset(adev);
 
 	/* XXX: add the xgmi offset of the physical node? */
 	adev->vm_manager.vram_base_offset +=
@@ -1270,7 +1278,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 
 #ifdef CONFIG_X86_64
 	if (adev->flags & AMD_IS_APU) {
-		adev->gmc.aper_base = gfxhub_v1_0_get_mc_fb_offset(adev);
+		adev->gmc.aper_base = adev->gfxhub.funcs->get_mc_fb_offset(adev);
 		adev->gmc.aper_size = adev->gmc.real_vram_size;
 	}
 #endif
@@ -1340,7 +1348,7 @@ static int gmc_v9_0_sw_init(void *handle)
 	int r, vram_width = 0, vram_type = 0, vram_vendor = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	gfxhub_v1_0_init(adev);
+	adev->gfxhub.funcs->init(adev);
 
 	adev->mmhub.funcs->init(adev);
 
@@ -1454,7 +1462,7 @@ static int gmc_v9_0_sw_init(void *handle)
 	adev->need_swiotlb = drm_need_swiotlb(44);
 
 	if (adev->gmc.xgmi.supported) {
-		r = gfxhub_v1_1_get_xgmi_info(adev);
+		r = adev->gfxhub.funcs->get_xgmi_info(adev);
 		if (r)
 			return r;
 	}
@@ -1546,8 +1554,11 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev)
  */
 void gmc_v9_0_restore_registers(struct amdgpu_device *adev)
 {
-	if (adev->asic_type == CHIP_RAVEN)
+	if (adev->asic_type == CHIP_RAVEN) {
 		WREG32_SOC15(DCE, 0, mmDCHUBBUB_SDPIF_MMIO_CNTRL_0, adev->gmc.sdpif_register);
+		WARN_ON(adev->gmc.sdpif_register !=
+			RREG32_SOC15(DCE, 0, mmDCHUBBUB_SDPIF_MMIO_CNTRL_0));
+	}
 }
 
 /**
@@ -1567,7 +1578,7 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	r = gfxhub_v1_0_gart_enable(adev);
+	r = adev->gfxhub.funcs->gart_enable(adev);
 	if (r)
 		return r;
 
@@ -1634,7 +1645,7 @@ static int gmc_v9_0_hw_init(void *handle)
 		value = true;
 
 	if (!amdgpu_sriov_vf(adev)) {
-		gfxhub_v1_0_set_fault_enable_default(adev, value);
+		adev->gfxhub.funcs->set_fault_enable_default(adev, value);
 		adev->mmhub.funcs->set_fault_enable_default(adev, value);
 	}
 	for (i = 0; i < adev->num_vmhubs; ++i)
@@ -1657,7 +1668,7 @@ static int gmc_v9_0_hw_init(void *handle)
  */
 static void gmc_v9_0_gart_disable(struct amdgpu_device *adev)
 {
-	gfxhub_v1_0_gart_disable(adev);
+	adev->gfxhub.funcs->gart_disable(adev);
 	adev->mmhub.funcs->gart_disable(adev);
 	amdgpu_gart_table_vram_unpin(adev);
 }
@@ -1681,14 +1692,9 @@ static int gmc_v9_0_hw_fini(void *handle)
 
 static int gmc_v9_0_suspend(void *handle)
 {
-	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = gmc_v9_0_hw_fini(adev);
-	if (r)
-		return r;
-
-	return 0;
+	return gmc_v9_0_hw_fini(adev);
 }
 
 static int gmc_v9_0_resume(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
index bc300283b6ab..c600b61b5f45 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
@@ -33,6 +33,7 @@
 
 static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev);
+static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring);
 
 static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
 {
@@ -564,8 +565,8 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = {
 	.insert_start = jpeg_v1_0_decode_ring_insert_start,
 	.insert_end = jpeg_v1_0_decode_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = vcn_v1_0_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
+	.begin_use = jpeg_v1_0_ring_begin_use,
+	.end_use = vcn_v1_0_ring_end_use,
 	.emit_wreg = jpeg_v1_0_decode_ring_emit_wreg,
 	.emit_reg_wait = jpeg_v1_0_decode_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
@@ -586,3 +587,22 @@ static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev)
 {
 	adev->jpeg.inst->irq.funcs = &jpeg_v1_0_irq_funcs;
 }
+
+static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct	amdgpu_device *adev = ring->adev;
+	bool	set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
+	int		cnt = 0;
+
+	mutex_lock(&adev->vcn.vcn1_jpeg1_workaround);
+
+	if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_dec))
+		DRM_ERROR("JPEG dec: vcn dec ring may not be empty\n");
+
+	for (cnt = 0; cnt < adev->vcn.num_enc_rings; cnt++) {
+		if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_enc[cnt]))
+			DRM_ERROR("JPEG dec: vcn enc ring[%d] may not be empty\n", cnt);
+	}
+
+	vcn_v1_0_set_pg_for_begin_use(ring, set_clocks);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c
index 4b746584a797..1c22d8393b21 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c
@@ -832,7 +832,6 @@ static int mes_v10_1_queue_init(struct amdgpu_device *adev)
 static int mes_v10_1_ring_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	int r;
 
 	ring = &adev->mes.ring;
 
@@ -849,11 +848,7 @@ static int mes_v10_1_ring_init(struct amdgpu_device *adev)
 	ring->no_scheduler = true;
 	sprintf(ring->name, "mes_%d.%d.%d", ring->me, ring->pipe, ring->queue);
 
-	r = amdgpu_ring_init(adev, ring, 1024, NULL, 0, AMDGPU_RING_PRIO_DEFAULT);
-	if (r)
-		return r;
-
-	return 0;
+	return amdgpu_ring_init(adev, ring, 1024, NULL, 0, AMDGPU_RING_PRIO_DEFAULT);
 }
 
 static int mes_v10_1_mqd_sw_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 45a902b1acb7..f84701c562bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -268,7 +268,7 @@ static void mmhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 2d88278c50bf..2063700f0bc6 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -201,11 +201,6 @@ static void mmhub_v2_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(MMHUB, 0, mmMMMC_VM_AGP_BOT, 0x00FFFFFF);
 
 	if (!amdgpu_sriov_vf(adev)) {
-		/*
-		 * the new L1 policy will block SRIOV guest from writing
-		 * these regs, and they will be programed at host.
-		 * so skip programing these regs.
-		 */
 		/* Program the system aperture low logical page number. */
 		WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 			     adev->gmc.vram_start >> 18);
@@ -374,7 +369,7 @@ static void mmhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 6c6ad529c65c..66748bb01b52 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -330,7 +330,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT1_CNTL,
 				    hubid * MMHUB_INSTANCE_REGISTER_OFFSET +
 				    i * hub->ctx_distance, tmp);
@@ -1624,6 +1624,34 @@ static void mmhub_v9_4_reset_ras_error_count(struct amdgpu_device *adev)
 	}
 }
 
+static const struct soc15_reg_entry mmhub_v9_4_err_status_regs[] = {
+	{ SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_ERR_STATUS), 0, 0, 0 },
+	{ SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_ERR_STATUS), 0, 0, 0 },
+	{ SOC15_REG_ENTRY(MMHUB, 0, mmMMEA2_ERR_STATUS), 0, 0, 0 },
+	{ SOC15_REG_ENTRY(MMHUB, 0, mmMMEA3_ERR_STATUS), 0, 0, 0 },
+	{ SOC15_REG_ENTRY(MMHUB, 0, mmMMEA4_ERR_STATUS), 0, 0, 0 },
+	{ SOC15_REG_ENTRY(MMHUB, 0, mmMMEA5_ERR_STATUS), 0, 0, 0 },
+	{ SOC15_REG_ENTRY(MMHUB, 0, mmMMEA6_ERR_STATUS), 0, 0, 0 },
+	{ SOC15_REG_ENTRY(MMHUB, 0, mmMMEA7_ERR_STATUS), 0, 0, 0 },
+};
+
+static void mmhub_v9_4_query_ras_error_status(struct amdgpu_device *adev)
+{
+	int i;
+	uint32_t reg_value;
+
+	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__MMHUB))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(mmhub_v9_4_err_status_regs); i++) {
+		reg_value =
+			RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_err_status_regs[i]));
+		if (reg_value)
+			dev_warn(adev->dev, "MMHUB EA err detected at instance: %d, status: 0x%x!\n",
+					i, reg_value);
+	}
+}
+
 const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = {
 	.ras_late_init = amdgpu_mmhub_ras_late_init,
 	.query_ras_error_count = mmhub_v9_4_query_ras_error_count,
@@ -1636,4 +1664,5 @@ const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = {
 	.set_clockgating = mmhub_v9_4_set_clockgating,
 	.get_clockgating = mmhub_v9_4_get_clockgating,
 	.setup_vm_pt_regs = mmhub_v9_4_setup_vm_pt_regs,
+	.query_ras_error_status = mmhub_v9_4_query_ras_error_status,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 9c07014d9bd6..f5ce9a9f4cf5 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -262,7 +262,8 @@ flr_done:
 
 	/* Trigger recovery for world switch failure if no TDR */
 	if (amdgpu_device_should_recover_gpu(adev)
-		&& (amdgpu_device_has_job_running(adev) || adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
+		&& (!amdgpu_device_has_job_running(adev) ||
+		adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT))
 		amdgpu_device_gpu_recover(adev, NULL);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index 9c23abf9b140..666ed99cc14b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -283,7 +283,7 @@ flr_done:
 
 	/* Trigger recovery for world switch failure if no TDR */
 	if (amdgpu_device_should_recover_gpu(adev)
-		&& (amdgpu_device_has_job_running(adev) ||
+		&& (!amdgpu_device_has_job_running(adev) ||
 		adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
 		adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
 		adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 4d1402356262..03462c857498 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -69,75 +69,40 @@ static const struct amd_ip_funcs nv_common_ip_funcs;
  */
 static u32 nv_pcie_rreg(struct amdgpu_device *adev, u32 reg)
 {
-	unsigned long flags, address, data;
-	u32 r;
+	unsigned long address, data;
 	address = adev->nbio.funcs->get_pcie_index_offset(adev);
 	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
-	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
-	WREG32(address, reg);
-	(void)RREG32(address);
-	r = RREG32(data);
-	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
-	return r;
+	return amdgpu_device_indirect_rreg(adev, address, data, reg);
 }
 
 static void nv_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 {
-	unsigned long flags, address, data;
+	unsigned long address, data;
 
 	address = adev->nbio.funcs->get_pcie_index_offset(adev);
 	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
-	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
-	WREG32(address, reg);
-	(void)RREG32(address);
-	WREG32(data, v);
-	(void)RREG32(data);
-	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+	amdgpu_device_indirect_wreg(adev, address, data, reg, v);
 }
 
 static u64 nv_pcie_rreg64(struct amdgpu_device *adev, u32 reg)
 {
-	unsigned long flags, address, data;
-	u64 r;
+	unsigned long address, data;
 	address = adev->nbio.funcs->get_pcie_index_offset(adev);
 	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
-	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
-	/* read low 32 bit */
-	WREG32(address, reg);
-	(void)RREG32(address);
-	r = RREG32(data);
-
-	/* read high 32 bit*/
-	WREG32(address, reg + 4);
-	(void)RREG32(address);
-	r |= ((u64)RREG32(data) << 32);
-	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
-	return r;
+	return amdgpu_device_indirect_rreg64(adev, address, data, reg);
 }
 
 static void nv_pcie_wreg64(struct amdgpu_device *adev, u32 reg, u64 v)
 {
-	unsigned long flags, address, data;
+	unsigned long address, data;
 
 	address = adev->nbio.funcs->get_pcie_index_offset(adev);
 	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
-	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
-	/* write low 32 bit */
-	WREG32(address, reg);
-	(void)RREG32(address);
-	WREG32(data, (u32)(v & 0xffffffffULL));
-	(void)RREG32(data);
-
-	/* write high 32 bit */
-	WREG32(address, reg + 4);
-	(void)RREG32(address);
-	WREG32(data, (u32)(v >> 32));
-	(void)RREG32(data);
-	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+	amdgpu_device_indirect_wreg64(adev, address, data, reg, v);
 }
 
 static u32 nv_didt_rreg(struct amdgpu_device *adev, u32 reg)
@@ -311,7 +276,7 @@ static int nv_asic_mode1_reset(struct amdgpu_device *adev)
 	/* disable BM */
 	pci_clear_master(adev->pdev);
 
-	pci_save_state(adev->pdev);
+	amdgpu_device_cache_pci_state(adev->pdev);
 
 	if (amdgpu_dpm_is_mode1_reset_supported(adev)) {
 		dev_info(adev->dev, "GPU smu mode1 reset\n");
@@ -323,7 +288,7 @@ static int nv_asic_mode1_reset(struct amdgpu_device *adev)
 
 	if (ret)
 		dev_err(adev->dev, "GPU mode1 reset failed\n");
-	pci_restore_state(adev->pdev);
+	amdgpu_device_load_pci_state(adev->pdev);
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
@@ -490,6 +455,14 @@ void nv_set_virt_ops(struct amdgpu_device *adev)
 	adev->virt.ops = &xgpu_nv_virt_ops;
 }
 
+static bool nv_is_blockchain_sku(struct pci_dev *pdev)
+{
+	if (pdev->device == 0x731E &&
+	    (pdev->revision == 0xC6 || pdev->revision == 0xC7))
+		return true;
+	return false;
+}
+
 int nv_set_ip_blocks(struct amdgpu_device *adev)
 {
 	int r;
@@ -518,7 +491,8 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
-		else if (amdgpu_device_has_dc_support(adev))
+		else if (amdgpu_device_has_dc_support(adev) &&
+			 !nv_is_blockchain_sku(adev->pdev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
@@ -526,7 +500,8 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
 		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
+		if (!nv_is_blockchain_sku(adev->pdev))
+			amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 		if (adev->enable_mes)
 			amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block);
@@ -621,7 +596,7 @@ static void nv_invalidate_hdp(struct amdgpu_device *adev,
 				struct amdgpu_ring *ring)
 {
 	if (!ring || !ring->funcs->emit_wreg) {
-		WREG32_SOC15_NO_KIQ(NBIO, 0, mmHDP_READ_CACHE_INVALIDATE, 1);
+		WREG32_SOC15_NO_KIQ(HDP, 0, mmHDP_READ_CACHE_INVALIDATE, 1);
 	} else {
 		amdgpu_ring_emit_wreg(ring, SOC15_REG_OFFSET(
 					HDP, 0, mmHDP_READ_CACHE_INVALIDATE), 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index cbc04a5c0fe1..4137dc710aaf 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -83,19 +83,6 @@ struct psp_gfx_ctrl
 */
 #define GFX_FLAG_RESPONSE               0x80000000
 
-/* Gbr IH registers ID */
-enum ih_reg_id {
-	IH_RB		= 0,		// IH_RB_CNTL
-	IH_RB_RNG1	= 1,		// IH_RB_CNTL_RING1
-	IH_RB_RNG2	= 2,		// IH_RB_CNTL_RING2
-};
-
-/* Command to setup Gibraltar IH register */
-struct psp_gfx_cmd_gbr_ih_reg {
-	uint32_t		reg_value;	/* Value to be set to the IH_RB_CNTL... register*/
-	enum ih_reg_id		reg_id;		/* ID of the register */
-};
-
 /* TEE Gfx Command IDs for the ring buffer interface. */
 enum psp_gfx_cmd_id
 {
@@ -214,7 +201,7 @@ enum psp_gfx_fw_type {
 	GFX_FW_TYPE_UVD1        = 23,   /* UVD1                     VG-20   */
 	GFX_FW_TYPE_TOC         = 24,   /* TOC                      NV-10   */
 	GFX_FW_TYPE_RLC_P                           = 25,   /* RLC P                    NV      */
-	GFX_FW_TYPE_RLX6                            = 26,   /* RLX6                     NV      */
+	GFX_FW_TYPE_RLC_IRAM                        = 26,   /* RLC_IRAM                 NV      */
 	GFX_FW_TYPE_GLOBAL_TAP_DELAYS               = 27,   /* GLOBAL TAP DELAYS        NV      */
 	GFX_FW_TYPE_SE0_TAP_DELAYS                  = 28,   /* SE0 TAP DELAYS           NV      */
 	GFX_FW_TYPE_SE1_TAP_DELAYS                  = 29,   /* SE1 TAP DELAYS           NV      */
@@ -236,7 +223,7 @@ enum psp_gfx_fw_type {
 	GFX_FW_TYPE_ACCUM_CTRL_RAM                  = 45,   /* ACCUM CTRL RAM           NV      */
 	GFX_FW_TYPE_RLCP_CAM                        = 46,   /* RLCP CAM                 NV      */
 	GFX_FW_TYPE_RLC_SPP_CAM_EXT                 = 47,   /* RLC SPP CAM EXT          NV      */
-	GFX_FW_TYPE_RLX6_DRAM_BOOT                  = 48,   /* RLX6 DRAM BOOT           NV      */
+	GFX_FW_TYPE_RLC_DRAM_BOOT                   = 48,   /* RLC DRAM BOOT            NV      */
 	GFX_FW_TYPE_VCN0_RAM                        = 49,   /* VCN_RAM                  NV + RN */
 	GFX_FW_TYPE_VCN1_RAM                        = 50,   /* VCN_RAM                  NV + RN */
 	GFX_FW_TYPE_DMUB                            = 51,   /* DMUB                          RN */
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index e16874f30d5d..6c5d9612abcb 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -58,7 +58,7 @@ MODULE_FIRMWARE("amdgpu/arcturus_ta.bin");
 MODULE_FIRMWARE("amdgpu/sienna_cichlid_sos.bin");
 MODULE_FIRMWARE("amdgpu/sienna_cichlid_ta.bin");
 MODULE_FIRMWARE("amdgpu/navy_flounder_sos.bin");
-MODULE_FIRMWARE("amdgpu/navy_flounder_asd.bin");
+MODULE_FIRMWARE("amdgpu/navy_flounder_ta.bin");
 
 /* address block */
 #define smnMP1_FIRMWARE_FLAGS		0x3010024
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 856c50386c86..86fb1eddf5a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -592,6 +592,9 @@ static int sdma_v4_0_init_microcode(struct amdgpu_device *adev)
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
 
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	DRM_DEBUG("\n");
 
 	switch (adev->asic_type) {
@@ -1000,7 +1003,7 @@ static void sdma_v4_0_page_stop(struct amdgpu_device *adev)
 		sdma[i] = &adev->sdma.instance[i].page;
 
 		if ((adev->mman.buffer_funcs_ring == sdma[i]) &&
-			(unset == false)) {
+			(!unset)) {
 			amdgpu_ttm_set_buffer_funcs_status(adev, false);
 			unset = true;
 		}
@@ -1063,6 +1066,15 @@ static void sdma_v4_0_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
 			WREG32_SDMA(i, mmSDMA0_PHASE2_QUANTUM, phase_quantum);
 		}
 		WREG32_SDMA(i, mmSDMA0_CNTL, f32_cntl);
+
+		/*
+		 * Enable SDMA utilization. Its only supported on
+		 * Arcturus for the moment and firmware version 14
+		 * and above.
+		 */
+		if (adev->asic_type == CHIP_ARCTURUS &&
+		    adev->sdma.instance[i].fw_version >= 14)
+			WREG32_SDMA(i, mmSDMA0_PUB_DUMMY_REG2, enable);
 	}
 
 }
@@ -1080,7 +1092,7 @@ static void sdma_v4_0_enable(struct amdgpu_device *adev, bool enable)
 	u32 f32_cntl;
 	int i;
 
-	if (enable == false) {
+	if (!enable) {
 		sdma_v4_0_gfx_stop(adev);
 		sdma_v4_0_rlc_stop(adev);
 		if (adev->sdma.has_page_queue)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index e2232dd12d8e..9c72b95b7463 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -203,6 +203,9 @@ static int sdma_v5_0_init_microcode(struct amdgpu_device *adev)
 	const struct common_firmware_header *header = NULL;
 	const struct sdma_firmware_header_v1_0 *hdr;
 
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	DRM_DEBUG("\n");
 
 	switch (adev->asic_type) {
@@ -616,7 +619,7 @@ static void sdma_v5_0_enable(struct amdgpu_device *adev, bool enable)
 	u32 f32_cntl;
 	int i;
 
-	if (enable == false) {
+	if (!enable) {
 		sdma_v5_0_gfx_stop(adev);
 		sdma_v5_0_rlc_stop(adev);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 46a9617fee5f..9f3952723c63 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -148,6 +148,9 @@ static int sdma_v5_2_init_microcode(struct amdgpu_device *adev)
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
 
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	DRM_DEBUG("\n");
 
 	switch (adev->asic_type) {
@@ -559,7 +562,7 @@ static void sdma_v5_2_enable(struct amdgpu_device *adev, bool enable)
 	u32 f32_cntl;
 	int i;
 
-	if (enable == false) {
+	if (!enable) {
 		sdma_v5_2_gfx_stop(adev);
 		sdma_v5_2_rlc_stop(adev);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index 455d5e366c69..e5e336fd9e94 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -1339,7 +1339,7 @@ static void si_vga_set_state(struct amdgpu_device *adev, bool state)
 	uint32_t temp;
 
 	temp = RREG32(CONFIG_CNTL);
-	if (state == false) {
+	if (!state) {
 		temp &= ~(1<<0);
 		temp |= (1<<1);
 	} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 2f93c475d6d8..afcccc6c0fc6 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -101,75 +101,40 @@
  */
 static u32 soc15_pcie_rreg(struct amdgpu_device *adev, u32 reg)
 {
-	unsigned long flags, address, data;
-	u32 r;
+	unsigned long address, data;
 	address = adev->nbio.funcs->get_pcie_index_offset(adev);
 	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
-	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
-	WREG32(address, reg);
-	(void)RREG32(address);
-	r = RREG32(data);
-	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
-	return r;
+	return amdgpu_device_indirect_rreg(adev, address, data, reg);
 }
 
 static void soc15_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 {
-	unsigned long flags, address, data;
+	unsigned long address, data;
 
 	address = adev->nbio.funcs->get_pcie_index_offset(adev);
 	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
-	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
-	WREG32(address, reg);
-	(void)RREG32(address);
-	WREG32(data, v);
-	(void)RREG32(data);
-	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+	amdgpu_device_indirect_wreg(adev, address, data, reg, v);
 }
 
 static u64 soc15_pcie_rreg64(struct amdgpu_device *adev, u32 reg)
 {
-	unsigned long flags, address, data;
-	u64 r;
+	unsigned long address, data;
 	address = adev->nbio.funcs->get_pcie_index_offset(adev);
 	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
-	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
-	/* read low 32 bit */
-	WREG32(address, reg);
-	(void)RREG32(address);
-	r = RREG32(data);
-
-	/* read high 32 bit*/
-	WREG32(address, reg + 4);
-	(void)RREG32(address);
-	r |= ((u64)RREG32(data) << 32);
-	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
-	return r;
+	return amdgpu_device_indirect_rreg64(adev, address, data, reg);
 }
 
 static void soc15_pcie_wreg64(struct amdgpu_device *adev, u32 reg, u64 v)
 {
-	unsigned long flags, address, data;
+	unsigned long address, data;
 
 	address = adev->nbio.funcs->get_pcie_index_offset(adev);
 	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
-	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
-	/* write low 32 bit */
-	WREG32(address, reg);
-	(void)RREG32(address);
-	WREG32(data, (u32)(v & 0xffffffffULL));
-	(void)RREG32(data);
-
-	/* write high 32 bit */
-	WREG32(address, reg + 4);
-	(void)RREG32(address);
-	WREG32(data, (u32)(v >> 32));
-	(void)RREG32(data);
-	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+	amdgpu_device_indirect_wreg64(adev, address, data, reg, v);
 }
 
 static u32 soc15_uvd_ctx_rreg(struct amdgpu_device *adev, u32 reg)
@@ -484,13 +449,13 @@ static int soc15_asic_mode1_reset(struct amdgpu_device *adev)
 	/* disable BM */
 	pci_clear_master(adev->pdev);
 
-	pci_save_state(adev->pdev);
+	amdgpu_device_cache_pci_state(adev->pdev);
 
 	ret = psp_gpu_reset(adev);
 	if (ret)
 		dev_err(adev->dev, "GPU mode1 reset failed\n");
 
-	pci_restore_state(adev->pdev);
+	amdgpu_device_load_pci_state(adev->pdev);
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
@@ -697,12 +662,12 @@ static void soc15_reg_base_init(struct amdgpu_device *adev)
 		 * it doesn't support SRIOV. */
 		if (amdgpu_discovery) {
 			r = amdgpu_discovery_reg_base_init(adev);
-			if (r) {
-				DRM_WARN("failed to init reg base from ip discovery table, "
-					 "fallback to legacy init method\n");
-				vega10_reg_base_init(adev);
-			}
+			if (r == 0)
+				break;
+			DRM_WARN("failed to init reg base from ip discovery table, "
+				 "fallback to legacy init method\n");
 		}
+		vega10_reg_base_init(adev);
 		break;
 	case CHIP_VEGA20:
 		vega20_reg_base_init(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 3cafba726587..b0c0c438fc93 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -348,7 +348,7 @@ static int uvd_v4_2_start(struct amdgpu_device *adev)
 	/* Set the write pointer delay */
 	WREG32(mmUVD_RBC_RB_WPTR_CNTL, 0);
 
-	/* programm the 4GB memory segment for rptr and ring buffer */
+	/* program the 4GB memory segment for rptr and ring buffer */
 	WREG32(mmUVD_LMI_EXT40_ADDR, upper_32_bits(ring->gpu_addr) |
 				   (0x7 << 16) | (0x1 << 31));
 
@@ -541,7 +541,7 @@ static void uvd_v4_2_mc_resume(struct amdgpu_device *adev)
 	uint64_t addr;
 	uint32_t size;
 
-	/* programm the VCPU memory controller bits 0-27 */
+	/* program the VCPU memory controller bits 0-27 */
 	addr = (adev->uvd.inst->gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3;
 	size = AMDGPU_UVD_FIRMWARE_SIZE(adev) >> 3;
 	WREG32(mmUVD_VCPU_CACHE_OFFSET0, addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index a566ff926e90..6e57001f6d0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -253,7 +253,7 @@ static void uvd_v5_0_mc_resume(struct amdgpu_device *adev)
 	uint64_t offset;
 	uint32_t size;
 
-	/* programm memory controller bits 0-27 */
+	/* program memory controller bits 0-27 */
 	WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
 			lower_32_bits(adev->uvd.inst->gpu_addr));
 	WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
@@ -404,7 +404,7 @@ static int uvd_v5_0_start(struct amdgpu_device *adev)
 	/* set the wb address */
 	WREG32(mmUVD_RBC_RB_RPTR_ADDR, (upper_32_bits(ring->gpu_addr) >> 2));
 
-	/* programm the RB_BASE for ring buffer */
+	/* program the RB_BASE for ring buffer */
 	WREG32(mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
 			lower_32_bits(ring->gpu_addr));
 	WREG32(mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 0a880bc101b8..666bfa4a0b8e 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -583,7 +583,7 @@ static void uvd_v6_0_mc_resume(struct amdgpu_device *adev)
 	uint64_t offset;
 	uint32_t size;
 
-	/* programm memory controller bits 0-27 */
+	/* program memory controller bits 0-27 */
 	WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
 			lower_32_bits(adev->uvd.inst->gpu_addr));
 	WREG32(mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
@@ -825,7 +825,7 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
 	/* set the wb address */
 	WREG32(mmUVD_RBC_RB_RPTR_ADDR, (upper_32_bits(ring->gpu_addr) >> 2));
 
-	/* programm the RB_BASE for ring buffer */
+	/* program the RB_BASE for ring buffer */
 	WREG32(mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
 			lower_32_bits(ring->gpu_addr));
 	WREG32(mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
@@ -1240,8 +1240,8 @@ static int uvd_v6_0_process_interrupt(struct amdgpu_device *adev,
 		break;
 	}
 
-	if (false == int_handled)
-			DRM_ERROR("Unhandled interrupt: %d %d\n",
+	if (!int_handled)
+		DRM_ERROR("Unhandled interrupt: %d %d\n",
 			  entry->src_id, entry->src_data[0]);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index e07e3fae99b5..b44c8677ce8d 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -1073,7 +1073,7 @@ static int uvd_v7_0_start(struct amdgpu_device *adev)
 		WREG32_SOC15(UVD, k, mmUVD_RBC_RB_RPTR_ADDR,
 				(upper_32_bits(ring->gpu_addr) >> 2));
 
-		/* programm the RB_BASE for ring buffer */
+		/* program the RB_BASE for ring buffer */
 		WREG32_SOC15(UVD, k, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
 				lower_32_bits(ring->gpu_addr));
 		WREG32_SOC15(UVD, k, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 927c330fad21..86e1ef732ebe 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -54,6 +54,7 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
 				int inst_idx, struct dpg_pause_state *new_state);
 
 static void vcn_v1_0_idle_work_handler(struct work_struct *work);
+static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring);
 
 /**
  * vcn_v1_0_early_init - set function pointers
@@ -910,7 +911,7 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR_ADDR,
 			(upper_32_bits(ring->gpu_addr) >> 2));
 
-	/* programm the RB_BASE for ring buffer */
+	/* program the RB_BASE for ring buffer */
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
 			lower_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
@@ -1068,7 +1069,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR_ADDR,
 								(upper_32_bits(ring->gpu_addr) >> 2));
 
-	/* programm the RB_BASE for ring buffer */
+	/* program the RB_BASE for ring buffer */
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
 								lower_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
@@ -1804,11 +1805,24 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work)
 	}
 }
 
-void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
+static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
 {
-	struct amdgpu_device *adev = ring->adev;
+	struct	amdgpu_device *adev = ring->adev;
 	bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
 
+	mutex_lock(&adev->vcn.vcn1_jpeg1_workaround);
+
+	if (amdgpu_fence_wait_empty(&ring->adev->jpeg.inst->ring_dec))
+		DRM_ERROR("VCN dec: jpeg dec ring may not be empty\n");
+
+	vcn_v1_0_set_pg_for_begin_use(ring, set_clocks);
+
+}
+
+void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks)
+{
+	struct amdgpu_device *adev = ring->adev;
+
 	if (set_clocks) {
 		amdgpu_gfx_off_ctrl(adev, false);
 		if (adev->pm.dpm_enabled)
@@ -1844,6 +1858,12 @@ void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
 	}
 }
 
+void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring)
+{
+	schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
+	mutex_unlock(&ring->adev->vcn.vcn1_jpeg1_workaround);
+}
+
 static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
 	.name = "vcn_v1_0",
 	.early_init = vcn_v1_0_early_init,
@@ -1891,7 +1911,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
 	.insert_end = vcn_v1_0_dec_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = vcn_v1_0_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
+	.end_use = vcn_v1_0_ring_end_use,
 	.emit_wreg = vcn_v1_0_dec_ring_emit_wreg,
 	.emit_reg_wait = vcn_v1_0_dec_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
@@ -1923,7 +1943,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = {
 	.insert_end = vcn_v1_0_enc_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = vcn_v1_0_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
+	.end_use = vcn_v1_0_ring_end_use,
 	.emit_wreg = vcn_v1_0_enc_ring_emit_wreg,
 	.emit_reg_wait = vcn_v1_0_enc_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
index f67d7391fc21..1f1cc7f0ece7 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
@@ -24,7 +24,8 @@
 #ifndef __VCN_V1_0_H__
 #define __VCN_V1_0_H__
 
-void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring);
+void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring);
+void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks);
 
 extern const struct amdgpu_ip_block_version vcn_v1_0_ip_block;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 23a9eb5b2c8a..e5d29dee0c88 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -900,7 +900,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR_ADDR,
 		(upper_32_bits(ring->gpu_addr) >> 2));
 
-	/* programm the RB_BASE for ring buffer */
+	/* program the RB_BASE for ring buffer */
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
 		lower_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
@@ -1060,7 +1060,7 @@ static int vcn_v2_0_start(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_CNTL, tmp);
 
 	fw_shared->multi_queue.decode_queue_mode |= FW_QUEUE_RING_RESET;
-	/* programm the RB_BASE for ring buffer */
+	/* program the RB_BASE for ring buffer */
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
 		lower_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 139fac0d8e76..0f1d3ef8baa7 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -882,7 +882,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 	WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_RPTR_ADDR,
 		(upper_32_bits(ring->gpu_addr) >> 2));
 
-	/* programm the RB_BASE for ring buffer */
+	/* program the RB_BASE for ring buffer */
 	WREG32_SOC15(VCN, inst_idx, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
 		lower_32_bits(ring->gpu_addr));
 	WREG32_SOC15(VCN, inst_idx, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
@@ -1062,7 +1062,7 @@ static int vcn_v2_5_start(struct amdgpu_device *adev)
 		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp);
 
 		fw_shared->multi_queue.decode_queue_mode |= FW_QUEUE_RING_RESET;
-		/* programm the RB_BASE for ring buffer */
+		/* program the RB_BASE for ring buffer */
 		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
 			lower_32_bits(ring->gpu_addr));
 		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 589d6cd8adec..e074f7ed388c 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -746,18 +746,18 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst)
 		| UVD_SUVD_CGC_GATE__IME_HEVC_MASK
 		| UVD_SUVD_CGC_GATE__EFC_MASK
 		| UVD_SUVD_CGC_GATE__SAOE_MASK
-		| 0x08000000
+		| UVD_SUVD_CGC_GATE__SRE_AV1_MASK
 		| UVD_SUVD_CGC_GATE__FBC_PCLK_MASK
 		| UVD_SUVD_CGC_GATE__FBC_CCLK_MASK
-		| 0x40000000
+		| UVD_SUVD_CGC_GATE__SCM_AV1_MASK
 		| UVD_SUVD_CGC_GATE__SMPA_MASK);
 	WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE, data);
 
 	data = RREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE2);
 	data |= (UVD_SUVD_CGC_GATE2__MPBE0_MASK
 		| UVD_SUVD_CGC_GATE2__MPBE1_MASK
-		| 0x00000004
-		| 0x00000008
+		| UVD_SUVD_CGC_GATE2__SIT_AV1_MASK
+		| UVD_SUVD_CGC_GATE2__SDB_AV1_MASK
 		| UVD_SUVD_CGC_GATE2__MPC1_MASK);
 	WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE2, data);
 
@@ -776,8 +776,8 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst)
 		| UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK
 		| UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK
 		| UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK
-		| 0x00008000
-		| 0x00010000
+		| UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK
+		| UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK
 		| UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK
 		| UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK
 		| UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK);
@@ -892,8 +892,8 @@ static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst)
 		| UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK
 		| UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK
 		| UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK
-		| 0x00008000
-		| 0x00010000
+		| UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK
+		| UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK
 		| UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK
 		| UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK
 		| UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK);
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index 24b471734117..dcb1d89d776e 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -91,7 +91,7 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
 	uint32_t context_id = ihre->data & 0xfffffff;
 	unsigned int vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
-	unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16;
+	u32 pasid = (ihre->ring_id & 0xffff0000) >> 16;
 
 	if (pasid == 0)
 		return;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index b7b16adb0615..222f1df1a6b6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -97,6 +97,7 @@ void kfd_chardev_exit(void)
 	device_destroy(kfd_class, MKDEV(kfd_char_dev_major, 0));
 	class_destroy(kfd_class);
 	unregister_chrdev(kfd_char_dev_major, kfd_dev_name);
+	kfd_device = NULL;
 }
 
 struct device *kfd_chardev(void)
@@ -1290,18 +1291,6 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
 		return -EINVAL;
 	}
 
-	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) {
-		if (args->size != kfd_doorbell_process_slice(dev))
-			return -EINVAL;
-		offset = kfd_get_process_doorbells(dev, p);
-	} else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) {
-		if (args->size != PAGE_SIZE)
-			return -EINVAL;
-		offset = amdgpu_amdkfd_get_mmio_remap_phys_addr(dev->kgd);
-		if (!offset)
-			return -ENOMEM;
-	}
-
 	mutex_lock(&p->mutex);
 
 	pdd = kfd_bind_process_to_device(dev, p);
@@ -1310,6 +1299,24 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
 		goto err_unlock;
 	}
 
+	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) {
+		if (args->size != kfd_doorbell_process_slice(dev)) {
+			err = -EINVAL;
+			goto err_unlock;
+		}
+		offset = kfd_get_process_doorbells(pdd);
+	} else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) {
+		if (args->size != PAGE_SIZE) {
+			err = -EINVAL;
+			goto err_unlock;
+		}
+		offset = amdgpu_amdkfd_get_mmio_remap_phys_addr(dev->kgd);
+		if (!offset) {
+			err = -ENOMEM;
+			goto err_unlock;
+		}
+	}
+
 	err = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 		dev->kgd, args->va_addr, args->size,
 		pdd->vm, (struct kgd_mem **) &mem, &offset,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 3fac06b281ce..5e2254b9e931 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -797,7 +797,8 @@ int kfd_create_crat_image_acpi(void **crat_image, size_t *size)
 		return -ENODATA;
 	}
 
-	pcrat_image = kmemdup(crat_table, crat_table->length, GFP_KERNEL);
+	pcrat_image = kvmalloc(crat_table->length, GFP_KERNEL);
+	memcpy(pcrat_image, crat_table, crat_table->length);
 	if (!pcrat_image)
 		return -ENOMEM;
 
@@ -809,11 +810,10 @@ int kfd_create_crat_image_acpi(void **crat_image, size_t *size)
 
 /* Memory required to create Virtual CRAT.
  * Since there is no easy way to predict the amount of memory required, the
- * following amount are allocated for CPU and GPU Virtual CRAT. This is
+ * following amount is allocated for GPU Virtual CRAT. This is
  * expected to cover all known conditions. But to be safe additional check
  * is put in the code to ensure we don't overwrite.
  */
-#define VCRAT_SIZE_FOR_CPU	(2 * PAGE_SIZE)
 #define VCRAT_SIZE_FOR_GPU	(4 * PAGE_SIZE)
 
 /* kfd_fill_cu_for_cpu - Fill in Compute info for the given CPU NUMA node
@@ -964,7 +964,7 @@ static int kfd_create_vcrat_image_cpu(void *pcrat_image, size_t *size)
 #endif
 	int ret = 0;
 
-	if (!pcrat_image || avail_size < VCRAT_SIZE_FOR_CPU)
+	if (!pcrat_image)
 		return -EINVAL;
 
 	/* Fill in CRAT Header.
@@ -1364,30 +1364,37 @@ int kfd_create_crat_image_virtual(void **crat_image, size_t *size,
 				  uint32_t proximity_domain)
 {
 	void *pcrat_image = NULL;
-	int ret = 0;
+	int ret = 0, num_nodes;
+	size_t dyn_size;
 
 	if (!crat_image)
 		return -EINVAL;
 
 	*crat_image = NULL;
 
-	/* Allocate one VCRAT_SIZE_FOR_CPU for CPU virtual CRAT image and
-	 * VCRAT_SIZE_FOR_GPU for GPU virtual CRAT image. This should cover
-	 * all the current conditions. A check is put not to overwrite beyond
-	 * allocated size
+	/* Allocate the CPU Virtual CRAT size based on the number of online
+	 * nodes. Allocate VCRAT_SIZE_FOR_GPU for GPU virtual CRAT image.
+	 * This should cover all the current conditions. A check is put not
+	 * to overwrite beyond allocated size for GPUs
 	 */
 	switch (flags) {
 	case COMPUTE_UNIT_CPU:
-		pcrat_image = kmalloc(VCRAT_SIZE_FOR_CPU, GFP_KERNEL);
+		num_nodes = num_online_nodes();
+		dyn_size = sizeof(struct crat_header) +
+			num_nodes * (sizeof(struct crat_subtype_computeunit) +
+			sizeof(struct crat_subtype_memory) +
+			(num_nodes - 1) * sizeof(struct crat_subtype_iolink));
+		pcrat_image = kvmalloc(dyn_size, GFP_KERNEL);
 		if (!pcrat_image)
 			return -ENOMEM;
-		*size = VCRAT_SIZE_FOR_CPU;
+		*size = dyn_size;
+		pr_debug("CRAT size is %ld", dyn_size);
 		ret = kfd_create_vcrat_image_cpu(pcrat_image, size);
 		break;
 	case COMPUTE_UNIT_GPU:
 		if (!kdev)
 			return -EINVAL;
-		pcrat_image = kmalloc(VCRAT_SIZE_FOR_GPU, GFP_KERNEL);
+		pcrat_image = kvmalloc(VCRAT_SIZE_FOR_GPU, GFP_KERNEL);
 		if (!pcrat_image)
 			return -ENOMEM;
 		*size = VCRAT_SIZE_FOR_GPU;
@@ -1406,7 +1413,7 @@ int kfd_create_crat_image_virtual(void **crat_image, size_t *size,
 	if (!ret)
 		*crat_image = pcrat_image;
 	else
-		kfree(pcrat_image);
+		kvfree(pcrat_image);
 
 	return ret;
 }
@@ -1419,5 +1426,5 @@ int kfd_create_crat_image_virtual(void **crat_image, size_t *size,
  */
 void kfd_destroy_crat_image(void *crat_image)
 {
-	kfree(crat_image);
+	kvfree(crat_image);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index 27bcc5b472f6..b258a3dae767 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -45,7 +45,7 @@ static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev)
 }
 
 static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
-				unsigned int pasid, uint64_t vmid0_address,
+				u32 pasid, uint64_t vmid0_address,
 				uint32_t *packet_buff, size_t size_in_bytes)
 {
 	struct pm4__release_mem *rm_packet;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
index a04a1fe1d0d9..f9c6df1fdc5c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
@@ -275,7 +275,7 @@ struct kfd_dbgdev {
 };
 
 struct kfd_dbgmgr {
-	unsigned int pasid;
+	u32 pasid;
 	struct kfd_dev *dev;
 	struct kfd_dbgdev *dbgdev;
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 0e71a0543f98..903170e59342 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -503,8 +503,8 @@ static const struct kfd_device_info *kfd_supported_devices[][2] = {
 #ifdef KFD_SUPPORT_IOMMU_V2
 	[CHIP_KAVERI] = {&kaveri_device_info, NULL},
 	[CHIP_CARRIZO] = {&carrizo_device_info, NULL},
-	[CHIP_RAVEN] = {&raven_device_info, NULL},
 #endif
+	[CHIP_RAVEN] = {&raven_device_info, NULL},
 	[CHIP_HAWAII] = {&hawaii_device_info, NULL},
 	[CHIP_TONGA] = {&tonga_device_info, NULL},
 	[CHIP_FIJI] = {&fiji_device_info, &fiji_vf_device_info},
@@ -583,6 +583,8 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
 
 	atomic_set(&kfd->sram_ecc_flag, 0);
 
+	ida_init(&kfd->doorbell_ida);
+
 	return kfd;
 }
 
@@ -716,6 +718,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
 	kfd->unique_id = amdgpu_amdkfd_get_unique_id(kfd->kgd);
 
+	kfd->noretry = amdgpu_amdkfd_get_noretry(kfd->kgd);
+
 	if (kfd_interrupt_init(kfd)) {
 		dev_err(kfd_device, "Error initializing interrupts\n");
 		goto kfd_interrupt_error;
@@ -798,6 +802,7 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
 		kfd_interrupt_exit(kfd);
 		kfd_topology_remove_device(kfd);
 		kfd_doorbell_fini(kfd);
+		ida_destroy(&kfd->doorbell_ida);
 		kfd_gtt_sa_fini(kfd);
 		amdgpu_amdkfd_free_gtt_mem(kfd->kgd, kfd->gtt_mem);
 		if (kfd->gws)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 560adc57a050..c0ae04a08625 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -40,7 +40,7 @@
 #define CIK_HPD_EOP_BYTES (1U << CIK_HPD_EOP_BYTES_LOG2)
 
 static int set_pasid_vmid_mapping(struct device_queue_manager *dqm,
-					unsigned int pasid, unsigned int vmid);
+				  u32 pasid, unsigned int vmid);
 
 static int execute_queues_cpsch(struct device_queue_manager *dqm,
 				enum kfd_unmap_queues_filter filter,
@@ -191,9 +191,8 @@ static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
 	}
 
 	q->properties.doorbell_off =
-		kfd_get_doorbell_dw_offset_in_bar(dev, q->process,
+		kfd_get_doorbell_dw_offset_in_bar(dev, qpd_to_pdd(qpd),
 					  q->doorbell_id);
-
 	return 0;
 }
 
@@ -650,9 +649,10 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 		goto out;
 
 	pdd = qpd_to_pdd(qpd);
-	pr_info_ratelimited("Evicting PASID 0x%x queues\n",
+	pr_debug_ratelimited("Evicting PASID 0x%x queues\n",
 			    pdd->process->pasid);
 
+	pdd->last_evict_timestamp = get_jiffies_64();
 	/* Mark all queues as evicted. Deactivate all active queues on
 	 * the qpd.
 	 */
@@ -700,7 +700,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 		goto out;
 
 	pdd = qpd_to_pdd(qpd);
-	pr_info_ratelimited("Evicting PASID 0x%x queues\n",
+	pr_debug_ratelimited("Evicting PASID 0x%x queues\n",
 			    pdd->process->pasid);
 
 	/* Mark all queues as evicted. Deactivate all active queues on
@@ -714,6 +714,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 		q->properties.is_active = false;
 		decrement_queue_count(dqm, q->properties.type);
 	}
+	pdd->last_evict_timestamp = get_jiffies_64();
 	retval = execute_queues_cpsch(dqm,
 				qpd->is_debug ?
 				KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES :
@@ -732,6 +733,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
 	uint64_t pd_base;
+	uint64_t eviction_duration;
 	int retval, ret = 0;
 
 	pdd = qpd_to_pdd(qpd);
@@ -746,7 +748,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 		goto out;
 	}
 
-	pr_info_ratelimited("Restoring PASID 0x%x queues\n",
+	pr_debug_ratelimited("Restoring PASID 0x%x queues\n",
 			    pdd->process->pasid);
 
 	/* Update PD Base in QPD */
@@ -799,6 +801,8 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 			ret = retval;
 	}
 	qpd->evicted = 0;
+	eviction_duration = get_jiffies_64() - pdd->last_evict_timestamp;
+	atomic64_add(eviction_duration, &pdd->evict_duration_counter);
 out:
 	if (mm)
 		mmput(mm);
@@ -812,6 +816,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 	struct queue *q;
 	struct kfd_process_device *pdd;
 	uint64_t pd_base;
+	uint64_t eviction_duration;
 	int retval = 0;
 
 	pdd = qpd_to_pdd(qpd);
@@ -826,7 +831,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 		goto out;
 	}
 
-	pr_info_ratelimited("Restoring PASID 0x%x queues\n",
+	pr_debug_ratelimited("Restoring PASID 0x%x queues\n",
 			    pdd->process->pasid);
 
 	/* Update PD Base in QPD */
@@ -845,6 +850,8 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 	retval = execute_queues_cpsch(dqm,
 				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	qpd->evicted = 0;
+	eviction_duration = get_jiffies_64() - pdd->last_evict_timestamp;
+	atomic64_add(eviction_duration, &pdd->evict_duration_counter);
 out:
 	dqm_unlock(dqm);
 	return retval;
@@ -924,7 +931,7 @@ out:
 }
 
 static int
-set_pasid_vmid_mapping(struct device_queue_manager *dqm, unsigned int pasid,
+set_pasid_vmid_mapping(struct device_queue_manager *dqm, u32 pasid,
 			unsigned int vmid)
 {
 	return dqm->dev->kfd2kgd->set_pasid_vmid_mapping(
@@ -1192,6 +1199,8 @@ static int stop_cpsch(struct device_queue_manager *dqm)
 	dqm->sched_running = false;
 	dqm_unlock(dqm);
 
+	pm_release_ib(&dqm->packets);
+
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
 	pm_uninit(&dqm->packets, hanging);
 
@@ -1302,7 +1311,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	if (q->properties.is_active) {
 		increment_queue_count(dqm, q->properties.type);
 
-		retval = execute_queues_cpsch(dqm,
+		execute_queues_cpsch(dqm,
 				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	}
 
@@ -1955,8 +1964,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm)
 	kfree(dqm);
 }
 
-int kfd_process_vm_fault(struct device_queue_manager *dqm,
-			 unsigned int pasid)
+int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid)
 {
 	struct kfd_process_device *pdd;
 	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
@@ -1964,6 +1972,7 @@ int kfd_process_vm_fault(struct device_queue_manager *dqm,
 
 	if (!p)
 		return -EINVAL;
+	WARN(debug_evictions, "Evicting pid %d", p->lead_thread->pid);
 	pdd = kfd_get_process_device_data(dqm->dev, p);
 	if (pdd)
 		ret = dqm->ops.evict_process_queues(dqm, &pdd->qpd);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c
index 72e4d61ac752..ad0593342333 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c
@@ -58,8 +58,9 @@ static int update_qpd_v10(struct device_queue_manager *dqm,
 	/* check if sh_mem_config register already configured */
 	if (qpd->sh_mem_config == 0) {
 		qpd->sh_mem_config =
-				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
-					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
+			(SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
+				SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) |
+			(3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT);
 #if 0
 		/* TODO:
 		 *    This shouldn't be an issue with Navi10.  Verify.
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
index 309f63a0b34a..eca6331efa94 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
@@ -61,7 +61,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm,
 		qpd->sh_mem_config =
 				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
 					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
-		if (amdgpu_noretry &&
+		if (dqm->dev->noretry &&
 		    !dqm->dev->use_iommu_v2)
 			qpd->sh_mem_config |=
 				1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index 8e0c00b9555e..768d153acff4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -31,9 +31,6 @@
  * kernel queues using the first doorbell page reserved for the kernel.
  */
 
-static DEFINE_IDA(doorbell_ida);
-static unsigned int max_doorbell_slices;
-
 /*
  * Each device exposes a doorbell aperture, a PCI MMIO aperture that
  * receives 32-bit writes that are passed to queues as wptr values.
@@ -84,9 +81,9 @@ int kfd_doorbell_init(struct kfd_dev *kfd)
 	else
 		return -ENOSPC;
 
-	if (!max_doorbell_slices ||
-	    doorbell_process_limit < max_doorbell_slices)
-		max_doorbell_slices = doorbell_process_limit;
+	if (!kfd->max_doorbell_slices ||
+	    doorbell_process_limit < kfd->max_doorbell_slices)
+		kfd->max_doorbell_slices = doorbell_process_limit;
 
 	kfd->doorbell_base = kfd->shared_resources.doorbell_physical_address +
 				doorbell_start_offset;
@@ -130,6 +127,7 @@ int kfd_doorbell_mmap(struct kfd_dev *dev, struct kfd_process *process,
 		      struct vm_area_struct *vma)
 {
 	phys_addr_t address;
+	struct kfd_process_device *pdd;
 
 	/*
 	 * For simplicitly we only allow mapping of the entire doorbell
@@ -138,9 +136,12 @@ int kfd_doorbell_mmap(struct kfd_dev *dev, struct kfd_process *process,
 	if (vma->vm_end - vma->vm_start != kfd_doorbell_process_slice(dev))
 		return -EINVAL;
 
-	/* Calculate physical address of doorbell */
-	address = kfd_get_process_doorbells(dev, process);
+	pdd = kfd_get_process_device_data(dev, process);
+	if (!pdd)
+		return -EINVAL;
 
+	/* Calculate physical address of doorbell */
+	address = kfd_get_process_doorbells(pdd);
 	vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE |
 				VM_DONTDUMP | VM_PFNMAP;
 
@@ -226,7 +227,7 @@ void write_kernel_doorbell64(void __iomem *db, u64 value)
 }
 
 unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd,
-					struct kfd_process *process,
+					struct kfd_process_device *pdd,
 					unsigned int doorbell_id)
 {
 	/*
@@ -236,7 +237,7 @@ unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd,
 	 * units regardless of the ASIC-dependent doorbell size.
 	 */
 	return kfd->doorbell_base_dw_offset +
-		process->doorbell_index
+		pdd->doorbell_index
 		* kfd_doorbell_process_slice(kfd) / sizeof(u32) +
 		doorbell_id * kfd->device_info->doorbell_size / sizeof(u32);
 }
@@ -251,25 +252,24 @@ uint64_t kfd_get_number_elems(struct kfd_dev *kfd)
 
 }
 
-phys_addr_t kfd_get_process_doorbells(struct kfd_dev *dev,
-					struct kfd_process *process)
+phys_addr_t kfd_get_process_doorbells(struct kfd_process_device *pdd)
 {
-	return dev->doorbell_base +
-		process->doorbell_index * kfd_doorbell_process_slice(dev);
+	return pdd->dev->doorbell_base +
+		pdd->doorbell_index * kfd_doorbell_process_slice(pdd->dev);
 }
 
-int kfd_alloc_process_doorbells(struct kfd_process *process)
+int kfd_alloc_process_doorbells(struct kfd_dev *kfd, unsigned int *doorbell_index)
 {
-	int r = ida_simple_get(&doorbell_ida, 1, max_doorbell_slices,
+	int r = ida_simple_get(&kfd->doorbell_ida, 1, kfd->max_doorbell_slices,
 				GFP_KERNEL);
 	if (r > 0)
-		process->doorbell_index = r;
+		*doorbell_index = r;
 
 	return r;
 }
 
-void kfd_free_process_doorbells(struct kfd_process *process)
+void kfd_free_process_doorbells(struct kfd_dev *kfd, unsigned int doorbell_index)
 {
-	if (process->doorbell_index)
-		ida_simple_remove(&doorbell_ida, process->doorbell_index);
+	if (doorbell_index)
+		ida_simple_remove(&kfd->doorbell_ida, doorbell_index);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index a9583b95fcc1..ba2c2ce0c55a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -460,7 +460,7 @@ static void set_event_from_interrupt(struct kfd_process *p,
 	}
 }
 
-void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
+void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
 				uint32_t valid_id_bits)
 {
 	struct kfd_event *ev = NULL;
@@ -872,7 +872,7 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 }
 
 #ifdef KFD_SUPPORT_IOMMU_V2
-void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_iommu_event(struct kfd_dev *dev, u32 pasid,
 		unsigned long address, bool is_write_requested,
 		bool is_execute_requested)
 {
@@ -950,7 +950,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 }
 #endif /* KFD_SUPPORT_IOMMU_V2 */
 
-void kfd_signal_hw_exception_event(unsigned int pasid)
+void kfd_signal_hw_exception_event(u32 pasid)
 {
 	/*
 	 * Because we are called from arbitrary context (workqueue) as opposed
@@ -971,7 +971,7 @@ void kfd_signal_hw_exception_event(unsigned int pasid)
 	kfd_unref_process(p);
 }
 
-void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
 				struct kfd_vm_fault_info *info)
 {
 	struct kfd_event *ev;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
index c7ac6c73af86..c8fe5dbdad55 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
@@ -79,7 +79,7 @@ struct kfd_event {
 #define KFD_EVENT_TYPE_DEBUG 5
 #define KFD_EVENT_TYPE_MEMORY 8
 
-extern void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
-					uint32_t valid_id_bits);
+extern void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
+				       uint32_t valid_id_bits);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 5a64915abaf7..66bbca61e3ef 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -139,7 +139,7 @@ void kfd_iommu_unbind_process(struct kfd_process *p)
 }
 
 /* Callback for process shutdown invoked by the IOMMU driver */
-static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
+static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, u32 pasid)
 {
 	struct kfd_dev *dev = kfd_device_by_pci_dev(pdev);
 	struct kfd_process *p;
@@ -185,8 +185,8 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
 }
 
 /* This function called by IOMMU driver on PPR failure */
-static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
-		unsigned long address, u16 flags)
+static int iommu_invalid_ppr_cb(struct pci_dev *pdev, u32 pasid,
+				unsigned long address, u16 flags)
 {
 	struct kfd_dev *dev;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index f4b7f7e6c40e..5e90fe642192 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -70,6 +70,7 @@ err_create_wq:
 err_topology:
 	kfd_chardev_exit();
 err_ioctl:
+	pr_err("KFD is disabled due to module initialization failure\n");
 	return err;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
index 2a07c4f2cd0d..af5816f51e55 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
@@ -51,7 +51,7 @@ unsigned int kfd_get_pasid_limit(void)
 	return 1U << pasid_bits;
 }
 
-unsigned int kfd_pasid_alloc(void)
+u32 kfd_pasid_alloc(void)
 {
 	int r = amdgpu_pasid_alloc(pasid_bits);
 
@@ -63,7 +63,7 @@ unsigned int kfd_pasid_alloc(void)
 	return 0;
 }
 
-void kfd_pasid_free(unsigned int pasid)
+void kfd_pasid_free(u32 pasid)
 {
 	amdgpu_pasid_free(pasid);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 023629f28495..c77cf23032ac 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -314,6 +314,11 @@ struct kfd_dev {
 	spinlock_t smi_lock;
 
 	uint32_t reset_seq_num;
+
+	struct ida doorbell_ida;
+	unsigned int max_doorbell_slices;
+
+	int noretry;
 };
 
 enum kfd_mempool {
@@ -631,7 +636,7 @@ enum kfd_pdd_bound {
 	PDD_BOUND_SUSPENDED,
 };
 
-#define MAX_SYSFS_FILENAME_LEN 11
+#define MAX_SYSFS_FILENAME_LEN 15
 
 /*
  * SDMA counter runs at 100MHz frequency.
@@ -692,6 +697,39 @@ struct kfd_process_device {
 	uint64_t sdma_past_activity_counter;
 	struct attribute attr_sdma;
 	char sdma_filename[MAX_SYSFS_FILENAME_LEN];
+
+	/* Eviction activity tracking */
+	uint64_t last_evict_timestamp;
+	atomic64_t evict_duration_counter;
+	struct attribute attr_evict;
+
+	struct kobject *kobj_stats;
+	unsigned int doorbell_index;
+
+	/*
+	 * @cu_occupancy: Reports occupancy of Compute Units (CU) of a process
+	 * that is associated with device encoded by "this" struct instance. The
+	 * value reflects CU usage by all of the waves launched by this process
+	 * on this device. A very important property of occupancy parameter is
+	 * that its value is a snapshot of current use.
+	 *
+	 * Following is to be noted regarding how this parameter is reported:
+	 *
+	 *  The number of waves that a CU can launch is limited by couple of
+	 *  parameters. These are encoded by struct amdgpu_cu_info instance
+	 *  that is part of every device definition. For GFX9 devices this
+	 *  translates to 40 waves (simd_per_cu * max_waves_per_simd) when waves
+	 *  do not use scratch memory and 32 waves (max_scratch_slots_per_cu)
+	 *  when they do use scratch memory. This could change for future
+	 *  devices and therefore this example should be considered as a guide.
+	 *
+	 *  All CU's of a device are available for the process. This may not be true
+	 *  under certain conditions - e.g. CU masking.
+	 *
+	 *  Finally number of CU's that are occupied by a process is affected by both
+	 *  number of CU's a device has along with number of other competing processes
+	 */
+	struct attribute attr_cu_occupancy;
 };
 
 #define qpd_to_pdd(x) container_of(x, struct kfd_process_device, qpd)
@@ -728,8 +766,7 @@ struct kfd_process {
 	/* We want to receive a notification when the mm_struct is destroyed */
 	struct mmu_notifier mmu_notifier;
 
-	uint16_t pasid;
-	unsigned int doorbell_index;
+	u32 pasid;
 
 	/*
 	 * List of kfd_process_device structures,
@@ -805,7 +842,7 @@ int kfd_process_create_wq(void);
 void kfd_process_destroy_wq(void);
 struct kfd_process *kfd_create_process(struct file *filep);
 struct kfd_process *kfd_get_process(const struct task_struct *);
-struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid);
+struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid);
 struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm);
 void kfd_unref_process(struct kfd_process *p);
 int kfd_process_evict_queues(struct kfd_process *p);
@@ -846,8 +883,8 @@ int kfd_pasid_init(void);
 void kfd_pasid_exit(void);
 bool kfd_set_pasid_limit(unsigned int new_limit);
 unsigned int kfd_get_pasid_limit(void);
-unsigned int kfd_pasid_alloc(void);
-void kfd_pasid_free(unsigned int pasid);
+u32 kfd_pasid_alloc(void);
+void kfd_pasid_free(u32 pasid);
 
 /* Doorbells */
 size_t kfd_doorbell_process_slice(struct kfd_dev *kfd);
@@ -862,13 +899,13 @@ u32 read_kernel_doorbell(u32 __iomem *db);
 void write_kernel_doorbell(void __iomem *db, u32 value);
 void write_kernel_doorbell64(void __iomem *db, u64 value);
 unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd,
-					struct kfd_process *process,
+					struct kfd_process_device *pdd,
 					unsigned int doorbell_id);
-phys_addr_t kfd_get_process_doorbells(struct kfd_dev *dev,
-					struct kfd_process *process);
-int kfd_alloc_process_doorbells(struct kfd_process *process);
-void kfd_free_process_doorbells(struct kfd_process *process);
-
+phys_addr_t kfd_get_process_doorbells(struct kfd_process_device *pdd);
+int kfd_alloc_process_doorbells(struct kfd_dev *kfd,
+				unsigned int *doorbell_index);
+void kfd_free_process_doorbells(struct kfd_dev *kfd,
+				unsigned int doorbell_index);
 /* GTT Sub-Allocator */
 
 int kfd_gtt_sa_allocate(struct kfd_dev *kfd, unsigned int size,
@@ -933,7 +970,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm);
 struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 					enum kfd_queue_type type);
 void kernel_queue_uninit(struct kernel_queue *kq, bool hanging);
-int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid);
+int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid);
 
 /* Process Queue Manager */
 struct process_queue_node {
@@ -1055,12 +1092,12 @@ int kfd_wait_on_events(struct kfd_process *p,
 		       uint32_t num_events, void __user *data,
 		       bool all, uint32_t user_timeout_ms,
 		       uint32_t *wait_result);
-void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
+void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
 				uint32_t valid_id_bits);
 void kfd_signal_iommu_event(struct kfd_dev *dev,
-		unsigned int pasid, unsigned long address,
-		bool is_write_requested, bool is_execute_requested);
-void kfd_signal_hw_exception_event(unsigned int pasid);
+			    u32 pasid, unsigned long address,
+			    bool is_write_requested, bool is_execute_requested);
+void kfd_signal_hw_exception_event(u32 pasid);
 int kfd_set_event(struct kfd_process *p, uint32_t event_id);
 int kfd_reset_event(struct kfd_process *p, uint32_t event_id);
 int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
@@ -1071,7 +1108,7 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint64_t *event_page_offset, uint32_t *event_slot_index);
 int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
 
-void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
 				struct kfd_vm_fault_info *info);
 
 void kfd_signal_reset_event(struct kfd_dev *dev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index a0e12a79ab7d..65803e153a22 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -249,6 +249,52 @@ cleanup:
 	}
 }
 
+/**
+ * @kfd_get_cu_occupancy() - Collect number of waves in-flight on this device
+ * by current process. Translates acquired wave count into number of compute units
+ * that are occupied.
+ *
+ * @atr: Handle of attribute that allows reporting of wave count. The attribute
+ * handle encapsulates GPU device it is associated with, thereby allowing collection
+ * of waves in flight, etc
+ *
+ * @buffer: Handle of user provided buffer updated with wave count
+ *
+ * Return: Number of bytes written to user buffer or an error value
+ */
+static int kfd_get_cu_occupancy(struct attribute *attr, char *buffer)
+{
+	int cu_cnt;
+	int wave_cnt;
+	int max_waves_per_cu;
+	struct kfd_dev *dev = NULL;
+	struct kfd_process *proc = NULL;
+	struct kfd_process_device *pdd = NULL;
+
+	pdd = container_of(attr, struct kfd_process_device, attr_cu_occupancy);
+	dev = pdd->dev;
+	if (dev->kfd2kgd->get_cu_occupancy == NULL)
+		return -EINVAL;
+
+	cu_cnt = 0;
+	proc = pdd->process;
+	if (pdd->qpd.queue_count == 0) {
+		pr_debug("Gpu-Id: %d has no active queues for process %d\n",
+			 dev->id, proc->pasid);
+		return snprintf(buffer, PAGE_SIZE, "%d\n", cu_cnt);
+	}
+
+	/* Collect wave count from device if it supports */
+	wave_cnt = 0;
+	max_waves_per_cu = 0;
+	dev->kfd2kgd->get_cu_occupancy(dev->kgd, proc->pasid, &wave_cnt,
+			&max_waves_per_cu);
+
+	/* Translate wave count to number of compute units */
+	cu_cnt = (wave_cnt + (max_waves_per_cu - 1)) / max_waves_per_cu;
+	return snprintf(buffer, PAGE_SIZE, "%d\n", cu_cnt);
+}
+
 static ssize_t kfd_procfs_show(struct kobject *kobj, struct attribute *attr,
 			       char *buffer)
 {
@@ -345,6 +391,32 @@ static ssize_t kfd_procfs_queue_show(struct kobject *kobj,
 	return 0;
 }
 
+static ssize_t kfd_procfs_stats_show(struct kobject *kobj,
+				     struct attribute *attr, char *buffer)
+{
+	if (strcmp(attr->name, "evicted_ms") == 0) {
+		struct kfd_process_device *pdd = container_of(attr,
+				struct kfd_process_device,
+				attr_evict);
+		uint64_t evict_jiffies;
+
+		evict_jiffies = atomic64_read(&pdd->evict_duration_counter);
+
+		return snprintf(buffer,
+				PAGE_SIZE,
+				"%llu\n",
+				jiffies64_to_msecs(evict_jiffies));
+
+	/* Sysfs handle that gets CU occupancy is per device */
+	} else if (strcmp(attr->name, "cu_occupancy") == 0) {
+		return kfd_get_cu_occupancy(attr, buffer);
+	} else {
+		pr_err("Invalid attribute");
+	}
+
+	return 0;
+}
+
 static struct attribute attr_queue_size = {
 	.name = "size",
 	.mode = KFD_SYSFS_FILE_MODE
@@ -376,6 +448,19 @@ static struct kobj_type procfs_queue_type = {
 	.default_attrs = procfs_queue_attrs,
 };
 
+static const struct sysfs_ops procfs_stats_ops = {
+	.show = kfd_procfs_stats_show,
+};
+
+static struct attribute *procfs_stats_attrs[] = {
+	NULL
+};
+
+static struct kobj_type procfs_stats_type = {
+	.sysfs_ops = &procfs_stats_ops,
+	.default_attrs = procfs_stats_attrs,
+};
+
 int kfd_procfs_add_queue(struct queue *q)
 {
 	struct kfd_process *proc;
@@ -417,6 +502,72 @@ static int kfd_sysfs_create_file(struct kfd_process *p, struct attribute *attr,
 	return ret;
 }
 
+static int kfd_procfs_add_sysfs_stats(struct kfd_process *p)
+{
+	int ret = 0;
+	struct kfd_process_device *pdd;
+	char stats_dir_filename[MAX_SYSFS_FILENAME_LEN];
+
+	if (!p)
+		return -EINVAL;
+
+	if (!p->kobj)
+		return -EFAULT;
+
+	/*
+	 * Create sysfs files for each GPU:
+	 * - proc/<pid>/stats_<gpuid>/
+	 * - proc/<pid>/stats_<gpuid>/evicted_ms
+	 * - proc/<pid>/stats_<gpuid>/cu_occupancy
+	 */
+	list_for_each_entry(pdd, &p->per_device_data, per_device_list) {
+		struct kobject *kobj_stats;
+
+		snprintf(stats_dir_filename, MAX_SYSFS_FILENAME_LEN,
+				"stats_%u", pdd->dev->id);
+		kobj_stats = kfd_alloc_struct(kobj_stats);
+		if (!kobj_stats)
+			return -ENOMEM;
+
+		ret = kobject_init_and_add(kobj_stats,
+						&procfs_stats_type,
+						p->kobj,
+						stats_dir_filename);
+
+		if (ret) {
+			pr_warn("Creating KFD proc/stats_%s folder failed",
+					stats_dir_filename);
+			kobject_put(kobj_stats);
+			goto err;
+		}
+
+		pdd->kobj_stats = kobj_stats;
+		pdd->attr_evict.name = "evicted_ms";
+		pdd->attr_evict.mode = KFD_SYSFS_FILE_MODE;
+		sysfs_attr_init(&pdd->attr_evict);
+		ret = sysfs_create_file(kobj_stats, &pdd->attr_evict);
+		if (ret)
+			pr_warn("Creating eviction stats for gpuid %d failed",
+					(int)pdd->dev->id);
+
+		/* Add sysfs file to report compute unit occupancy */
+		if (pdd->dev->kfd2kgd->get_cu_occupancy != NULL) {
+			pdd->attr_cu_occupancy.name = "cu_occupancy";
+			pdd->attr_cu_occupancy.mode = KFD_SYSFS_FILE_MODE;
+			sysfs_attr_init(&pdd->attr_cu_occupancy);
+			ret = sysfs_create_file(kobj_stats,
+						&pdd->attr_cu_occupancy);
+			if (ret)
+				pr_warn("Creating %s failed for gpuid: %d",
+					pdd->attr_cu_occupancy.name,
+					(int)pdd->dev->id);
+		}
+	}
+err:
+	return ret;
+}
+
+
 static int kfd_procfs_add_sysfs_files(struct kfd_process *p)
 {
 	int ret = 0;
@@ -452,7 +603,6 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p)
 	return ret;
 }
 
-
 void kfd_procfs_del_queue(struct queue *q)
 {
 	if (!q)
@@ -660,6 +810,11 @@ struct kfd_process *kfd_create_process(struct file *filep)
 		if (!process->kobj_queues)
 			pr_warn("Creating KFD proc/queues folder failed");
 
+		ret = kfd_procfs_add_sysfs_stats(process);
+		if (ret)
+			pr_warn("Creating sysfs stats dir for pid %d failed",
+				(int)process->lead_thread->pid);
+
 		ret = kfd_procfs_add_sysfs_files(process);
 		if (ret)
 			pr_warn("Creating sysfs usage file for pid %d failed",
@@ -781,6 +936,8 @@ static void kfd_process_destroy_pdds(struct kfd_process *p)
 		kfree(pdd->qpd.doorbell_bitmap);
 		idr_destroy(&pdd->alloc_idr);
 
+		kfd_free_process_doorbells(pdd->dev, pdd->doorbell_index);
+
 		/*
 		 * before destroying pdd, make sure to report availability
 		 * for auto suspend
@@ -816,6 +973,12 @@ static void kfd_process_wq_release(struct work_struct *work)
 		list_for_each_entry(pdd, &p->per_device_data, per_device_list) {
 			sysfs_remove_file(p->kobj, &pdd->attr_vram);
 			sysfs_remove_file(p->kobj, &pdd->attr_sdma);
+			sysfs_remove_file(p->kobj, &pdd->attr_evict);
+			if (pdd->dev->kfd2kgd->get_cu_occupancy != NULL)
+				sysfs_remove_file(p->kobj, &pdd->attr_cu_occupancy);
+			kobject_del(pdd->kobj_stats);
+			kobject_put(pdd->kobj_stats);
+			pdd->kobj_stats = NULL;
 		}
 
 		kobject_del(p->kobj);
@@ -833,8 +996,6 @@ static void kfd_process_wq_release(struct work_struct *work)
 	kfd_event_free_process(p);
 
 	kfd_pasid_free(p->pasid);
-	kfd_free_process_doorbells(p);
-
 	mutex_destroy(&p->mutex);
 
 	put_task_struct(p->lead_thread);
@@ -1012,9 +1173,6 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 	if (process->pasid == 0)
 		goto err_alloc_pasid;
 
-	if (kfd_alloc_process_doorbells(process) < 0)
-		goto err_alloc_doorbells;
-
 	err = pqm_init(&process->pqm, process);
 	if (err != 0)
 		goto err_process_pqm_init;
@@ -1042,8 +1200,6 @@ err_register_notifier:
 err_init_apertures:
 	pqm_uninit(&process->pqm);
 err_process_pqm_init:
-	kfd_free_process_doorbells(process);
-err_alloc_doorbells:
 	kfd_pasid_free(process->pasid);
 err_alloc_pasid:
 	mutex_destroy(&process->mutex);
@@ -1106,10 +1262,14 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 	if (!pdd)
 		return NULL;
 
+	if (kfd_alloc_process_doorbells(dev, &pdd->doorbell_index) < 0) {
+		pr_err("Failed to alloc doorbell for pdd\n");
+		goto err_free_pdd;
+	}
+
 	if (init_doorbell_bitmap(&pdd->qpd, dev)) {
 		pr_err("Failed to init doorbell for process\n");
-		kfree(pdd);
-		return NULL;
+		goto err_free_pdd;
 	}
 
 	pdd->dev = dev;
@@ -1125,12 +1285,17 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 	pdd->runtime_inuse = false;
 	pdd->vram_usage = 0;
 	pdd->sdma_past_activity_counter = 0;
+	atomic64_set(&pdd->evict_duration_counter, 0);
 	list_add(&pdd->per_device_list, &p->per_device_data);
 
 	/* Init idr used for memory handle translation */
 	idr_init(&pdd->alloc_idr);
 
 	return pdd;
+
+err_free_pdd:
+	kfree(pdd);
+	return NULL;
 }
 
 /**
@@ -1307,7 +1472,7 @@ void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd,
 }
 
 /* This increments the process->ref counter. */
-struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid)
+struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid)
 {
 	struct kfd_process *p, *ret_p = NULL;
 	unsigned int temp;
@@ -1488,6 +1653,7 @@ void kfd_suspend_all_processes(void)
 	unsigned int temp;
 	int idx = srcu_read_lock(&kfd_processes_srcu);
 
+	WARN(debug_evictions, "Evicting all processes");
 	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
 		cancel_delayed_work_sync(&p->eviction_work);
 		cancel_delayed_work_sync(&p->restore_work);
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index f24abf428534..60dfdd432aba 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -42,6 +42,7 @@ config DRM_AMD_DC_SI
 config DEBUG_KERNEL_DC
 	bool "Enable kgdb break in DC"
 	depends on DRM_AMD_DC
+	depends on KGDB
 	help
 	  Choose this option if you want to hit kdgb_break in assert.
 
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 b24c14bfab31..e2b23486ba4c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -228,17 +228,14 @@ static u32 dm_vblank_get_counter(struct amdgpu_device *adev, int crtc)
 		return 0;
 	else {
 		struct amdgpu_crtc *acrtc = adev->mode_info.crtcs[crtc];
-		struct dm_crtc_state *acrtc_state = to_dm_crtc_state(
-				acrtc->base.state);
 
-
-		if (acrtc_state->stream == NULL) {
+		if (acrtc->dm_irq_params.stream == NULL) {
 			DRM_ERROR("dc_stream_state is NULL for crtc '%d'!\n",
 				  crtc);
 			return 0;
 		}
 
-		return dc_stream_get_vblank_counter(acrtc_state->stream);
+		return dc_stream_get_vblank_counter(acrtc->dm_irq_params.stream);
 	}
 }
 
@@ -251,10 +248,8 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
 		return -EINVAL;
 	else {
 		struct amdgpu_crtc *acrtc = adev->mode_info.crtcs[crtc];
-		struct dm_crtc_state *acrtc_state = to_dm_crtc_state(
-						acrtc->base.state);
 
-		if (acrtc_state->stream ==  NULL) {
+		if (acrtc->dm_irq_params.stream ==  NULL) {
 			DRM_ERROR("dc_stream_state is NULL for crtc '%d'!\n",
 				  crtc);
 			return 0;
@@ -264,7 +259,7 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc,
 		 * TODO rework base driver to use values directly.
 		 * for now parse it back into reg-format
 		 */
-		dc_stream_get_scanoutpos(acrtc_state->stream,
+		dc_stream_get_scanoutpos(acrtc->dm_irq_params.stream,
 					 &v_blank_start,
 					 &v_blank_end,
 					 &h_position,
@@ -323,6 +318,14 @@ get_crtc_by_otg_inst(struct amdgpu_device *adev,
 	return NULL;
 }
 
+static inline bool amdgpu_dm_vrr_active_irq(struct amdgpu_crtc *acrtc)
+{
+	return acrtc->dm_irq_params.freesync_config.state ==
+		       VRR_STATE_ACTIVE_VARIABLE ||
+	       acrtc->dm_irq_params.freesync_config.state ==
+		       VRR_STATE_ACTIVE_FIXED;
+}
+
 static inline bool amdgpu_dm_vrr_active(struct dm_crtc_state *dm_state)
 {
 	return dm_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE ||
@@ -343,7 +346,6 @@ static void dm_pflip_high_irq(void *interrupt_params)
 	struct amdgpu_device *adev = irq_params->adev;
 	unsigned long flags;
 	struct drm_pending_vblank_event *e;
-	struct dm_crtc_state *acrtc_state;
 	uint32_t vpos, hpos, v_blank_start, v_blank_end;
 	bool vrr_active;
 
@@ -375,12 +377,11 @@ static void dm_pflip_high_irq(void *interrupt_params)
 	if (!e)
 		WARN_ON(1);
 
-	acrtc_state = to_dm_crtc_state(amdgpu_crtc->base.state);
-	vrr_active = amdgpu_dm_vrr_active(acrtc_state);
+	vrr_active = amdgpu_dm_vrr_active_irq(amdgpu_crtc);
 
 	/* Fixed refresh rate, or VRR scanout position outside front-porch? */
 	if (!vrr_active ||
-	    !dc_stream_get_scanoutpos(acrtc_state->stream, &v_blank_start,
+	    !dc_stream_get_scanoutpos(amdgpu_crtc->dm_irq_params.stream, &v_blank_start,
 				      &v_blank_end, &hpos, &vpos) ||
 	    (vpos < v_blank_start)) {
 		/* Update to correct count and vblank timestamp if racing with
@@ -425,7 +426,7 @@ static void dm_pflip_high_irq(void *interrupt_params)
 	 * of pageflip completion, so last_flip_vblank is the forbidden count
 	 * for queueing new pageflips if vsync + VRR is enabled.
 	 */
-	amdgpu_crtc->last_flip_vblank =
+	amdgpu_crtc->dm_irq_params.last_flip_vblank =
 		amdgpu_get_vblank_counter_kms(&amdgpu_crtc->base);
 
 	amdgpu_crtc->pflip_status = AMDGPU_FLIP_NONE;
@@ -441,17 +442,17 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 	struct common_irq_params *irq_params = interrupt_params;
 	struct amdgpu_device *adev = irq_params->adev;
 	struct amdgpu_crtc *acrtc;
-	struct dm_crtc_state *acrtc_state;
 	unsigned long flags;
+	int vrr_active;
 
 	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VUPDATE);
 
 	if (acrtc) {
-		acrtc_state = to_dm_crtc_state(acrtc->base.state);
+		vrr_active = amdgpu_dm_vrr_active_irq(acrtc);
 
 		DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d\n",
 			      acrtc->crtc_id,
-			      amdgpu_dm_vrr_active(acrtc_state));
+			      vrr_active);
 
 		/* Core vblank handling is done here after end of front-porch in
 		 * vrr mode, as vblank timestamping will give valid results
@@ -459,22 +460,22 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 		 * page-flip completion events that have been queued to us
 		 * if a pageflip happened inside front-porch.
 		 */
-		if (amdgpu_dm_vrr_active(acrtc_state)) {
+		if (vrr_active) {
 			drm_crtc_handle_vblank(&acrtc->base);
 
 			/* BTR processing for pre-DCE12 ASICs */
-			if (acrtc_state->stream &&
+			if (acrtc->dm_irq_params.stream &&
 			    adev->family < AMDGPU_FAMILY_AI) {
 				spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 				mod_freesync_handle_v_update(
 				    adev->dm.freesync_module,
-				    acrtc_state->stream,
-				    &acrtc_state->vrr_params);
+				    acrtc->dm_irq_params.stream,
+				    &acrtc->dm_irq_params.vrr_params);
 
 				dc_stream_adjust_vmin_vmax(
 				    adev->dm.dc,
-				    acrtc_state->stream,
-				    &acrtc_state->vrr_params.adjust);
+				    acrtc->dm_irq_params.stream,
+				    &acrtc->dm_irq_params.vrr_params.adjust);
 				spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 			}
 		}
@@ -493,18 +494,17 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	struct common_irq_params *irq_params = interrupt_params;
 	struct amdgpu_device *adev = irq_params->adev;
 	struct amdgpu_crtc *acrtc;
-	struct dm_crtc_state *acrtc_state;
 	unsigned long flags;
+	int vrr_active;
 
 	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK);
 	if (!acrtc)
 		return;
 
-	acrtc_state = to_dm_crtc_state(acrtc->base.state);
+	vrr_active = amdgpu_dm_vrr_active_irq(acrtc);
 
 	DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d, planes:%d\n", acrtc->crtc_id,
-			 amdgpu_dm_vrr_active(acrtc_state),
-			 acrtc_state->active_planes);
+		      vrr_active, acrtc->dm_irq_params.active_planes);
 
 	/**
 	 * Core vblank handling at start of front-porch is only possible
@@ -512,7 +512,7 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	 * valid results while done in front-porch. Otherwise defer it
 	 * to dm_vupdate_high_irq after end of front-porch.
 	 */
-	if (!amdgpu_dm_vrr_active(acrtc_state))
+	if (!vrr_active)
 		drm_crtc_handle_vblank(&acrtc->base);
 
 	/**
@@ -527,14 +527,16 @@ static void dm_crtc_high_irq(void *interrupt_params)
 
 	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 
-	if (acrtc_state->stream && acrtc_state->vrr_params.supported &&
-	    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
+	if (acrtc->dm_irq_params.stream &&
+	    acrtc->dm_irq_params.vrr_params.supported &&
+	    acrtc->dm_irq_params.freesync_config.state ==
+		    VRR_STATE_ACTIVE_VARIABLE) {
 		mod_freesync_handle_v_update(adev->dm.freesync_module,
-					     acrtc_state->stream,
-					     &acrtc_state->vrr_params);
+					     acrtc->dm_irq_params.stream,
+					     &acrtc->dm_irq_params.vrr_params);
 
-		dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc_state->stream,
-					   &acrtc_state->vrr_params.adjust);
+		dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc->dm_irq_params.stream,
+					   &acrtc->dm_irq_params.vrr_params.adjust);
 	}
 
 	/*
@@ -549,7 +551,7 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	 */
 	if (adev->family >= AMDGPU_FAMILY_RV &&
 	    acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED &&
-	    acrtc_state->active_planes == 0) {
+	    acrtc->dm_irq_params.active_planes == 0) {
 		if (acrtc->event) {
 			drm_crtc_send_vblank_event(&acrtc->base, acrtc->event);
 			acrtc->event = NULL;
@@ -878,6 +880,45 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+static void amdgpu_check_debugfs_connector_property_change(struct amdgpu_device *adev,
+							   struct drm_atomic_state *state)
+{
+	struct drm_connector *connector;
+	struct drm_crtc *crtc;
+	struct amdgpu_dm_connector *amdgpu_dm_connector;
+	struct drm_connector_state *conn_state;
+	struct dm_crtc_state *acrtc_state;
+	struct drm_crtc_state *crtc_state;
+	struct dc_stream_state *stream;
+	struct drm_device *dev = adev_to_drm(adev);
+
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+
+		amdgpu_dm_connector = to_amdgpu_dm_connector(connector);
+		conn_state = connector->state;
+
+		if (!(conn_state && conn_state->crtc))
+			continue;
+
+		crtc = conn_state->crtc;
+		acrtc_state = to_dm_crtc_state(crtc->state);
+
+		if (!(acrtc_state && acrtc_state->stream))
+			continue;
+
+		stream = acrtc_state->stream;
+
+		if (amdgpu_dm_connector->dsc_settings.dsc_force_enable ||
+		    amdgpu_dm_connector->dsc_settings.dsc_num_slices_v ||
+		    amdgpu_dm_connector->dsc_settings.dsc_num_slices_h ||
+		    amdgpu_dm_connector->dsc_settings.dsc_bits_per_pixel) {
+			conn_state = drm_atomic_get_connector_state(state, connector);
+			crtc_state = drm_atomic_get_crtc_state(state, crtc);
+			crtc_state->mode_changed = true;
+		}
+	}
+}
+
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
 	struct dc_init_data init_data;
@@ -1425,9 +1466,6 @@ static int dm_late_init(void *handle)
 	struct dmcu *dmcu = NULL;
 	bool ret = true;
 
-	if (!adev->dm.fw_dmcu && !adev->dm.dmub_fw)
-		return detect_mst_link_for_all_connectors(adev_to_drm(adev));
-
 	dmcu = adev->dm.dc->res_pool->dmcu;
 
 	for (i = 0; i < 16; i++)
@@ -3373,9 +3411,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		goto fail;
 	}
 
-	/* No userspace support. */
-	dm->dc->debug.disable_tri_buf = true;
-
 	return 0;
 fail:
 	kfree(aencoder);
@@ -4689,9 +4724,10 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 							     dc_link_get_link_cap(aconnector->dc_link));
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-		if (dsc_caps.is_dsc_supported) {
+		if (aconnector->dsc_settings.dsc_force_enable != DSC_CLK_FORCE_DISABLE && dsc_caps.is_dsc_supported) {
 			/* Set DSC policy according to dsc_clock_en */
-			dc_dsc_policy_set_enable_dsc_when_not_needed(aconnector->dsc_settings.dsc_clock_en);
+			dc_dsc_policy_set_enable_dsc_when_not_needed(
+				aconnector->dsc_settings.dsc_force_enable == DSC_CLK_FORCE_ENABLE);
 
 			if (dc_dsc_compute_config(aconnector->dc_link->ctx->dc->res_pool->dscs[0],
 						  &dsc_caps,
@@ -4701,16 +4737,14 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 						  &stream->timing.dsc_cfg))
 				stream->timing.flags.DSC = 1;
 			/* Overwrite the stream flag if DSC is enabled through debugfs */
-			if (aconnector->dsc_settings.dsc_clock_en)
+			if (aconnector->dsc_settings.dsc_force_enable == DSC_CLK_FORCE_ENABLE)
 				stream->timing.flags.DSC = 1;
 
-			if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_slice_width)
-				stream->timing.dsc_cfg.num_slices_h = DIV_ROUND_UP(stream->timing.h_addressable,
-									aconnector->dsc_settings.dsc_slice_width);
+			if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_num_slices_h)
+				stream->timing.dsc_cfg.num_slices_h = aconnector->dsc_settings.dsc_num_slices_h;
 
-			if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_slice_height)
-				stream->timing.dsc_cfg.num_slices_v = DIV_ROUND_UP(stream->timing.v_addressable,
-									aconnector->dsc_settings.dsc_slice_height);
+			if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_num_slices_v)
+				stream->timing.dsc_cfg.num_slices_v = aconnector->dsc_settings.dsc_num_slices_v;
 
 			if (stream->timing.flags.DSC && aconnector->dsc_settings.dsc_bits_per_pixel)
 				stream->timing.dsc_cfg.bits_per_pixel = aconnector->dsc_settings.dsc_bits_per_pixel;
@@ -4809,7 +4843,6 @@ dm_crtc_duplicate_state(struct drm_crtc *crtc)
 	}
 
 	state->active_planes = cur->active_planes;
-	state->vrr_params = cur->vrr_params;
 	state->vrr_infopacket = cur->vrr_infopacket;
 	state->abm_level = cur->abm_level;
 	state->vrr_supported = cur->vrr_supported;
@@ -5030,7 +5063,13 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector)
 	struct amdgpu_device *adev = drm_to_adev(connector->dev);
 	struct amdgpu_display_manager *dm = &adev->dm;
 
-	drm_atomic_private_obj_fini(&aconnector->mst_mgr.base);
+	/*
+	 * Call only if mst_mgr was iniitalized before since it's not done
+	 * for all connector types.
+	 */
+	if (aconnector->mst_mgr.dev)
+		drm_dp_mst_topology_mgr_destroy(&aconnector->mst_mgr);
+
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\
 	defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
 
@@ -5427,19 +5466,6 @@ static void dm_crtc_helper_disable(struct drm_crtc *crtc)
 {
 }
 
-static bool does_crtc_have_active_cursor(struct drm_crtc_state *new_crtc_state)
-{
-	struct drm_device *dev = new_crtc_state->crtc->dev;
-	struct drm_plane *plane;
-
-	drm_for_each_plane_mask(plane, dev, new_crtc_state->plane_mask) {
-		if (plane->type == DRM_PLANE_TYPE_CURSOR)
-			return true;
-	}
-
-	return false;
-}
-
 static int count_crtc_active_planes(struct drm_crtc_state *new_crtc_state)
 {
 	struct drm_atomic_state *state = new_crtc_state->state;
@@ -5503,19 +5529,20 @@ static int dm_crtc_helper_atomic_check(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	/* In some use cases, like reset, no stream is attached */
-	if (!dm_crtc_state->stream)
-		return 0;
-
 	/*
-	 * We want at least one hardware plane enabled to use
-	 * the stream with a cursor enabled.
+	 * We require the primary plane to be enabled whenever the CRTC is, otherwise
+	 * drm_mode_cursor_universal may end up trying to enable the cursor plane while all other
+	 * planes are disabled, which is not supported by the hardware. And there is legacy
+	 * userspace which stops using the HW cursor altogether in response to the resulting EINVAL.
 	 */
-	if (state->enable && state->active &&
-	    does_crtc_have_active_cursor(state) &&
-	    dm_crtc_state->active_planes == 0)
+	if (state->enable &&
+	    !(state->plane_mask & drm_plane_mask(crtc->primary)))
 		return -EINVAL;
 
+	/* In some use cases, like reset, no stream is attached */
+	if (!dm_crtc_state->stream)
+		return 0;
+
 	if (dc_validate_stream(dc, dm_crtc_state->stream) == DC_OK)
 		return 0;
 
@@ -6862,6 +6889,7 @@ static void update_freesync_state_on_stream(
 	struct mod_vrr_params vrr_params;
 	struct dc_info_packet vrr_infopacket = {0};
 	struct amdgpu_device *adev = dm->adev;
+	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(new_crtc_state->base.crtc);
 	unsigned long flags;
 
 	if (!new_stream)
@@ -6876,7 +6904,7 @@ static void update_freesync_state_on_stream(
 		return;
 
 	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
-	vrr_params = new_crtc_state->vrr_params;
+        vrr_params = acrtc->dm_irq_params.vrr_params;
 
 	if (surface) {
 		mod_freesync_handle_preflip(
@@ -6907,7 +6935,7 @@ static void update_freesync_state_on_stream(
 		&vrr_infopacket);
 
 	new_crtc_state->freesync_timing_changed |=
-		(memcmp(&new_crtc_state->vrr_params.adjust,
+		(memcmp(&acrtc->dm_irq_params.vrr_params.adjust,
 			&vrr_params.adjust,
 			sizeof(vrr_params.adjust)) != 0);
 
@@ -6916,10 +6944,10 @@ static void update_freesync_state_on_stream(
 			&vrr_infopacket,
 			sizeof(vrr_infopacket)) != 0);
 
-	new_crtc_state->vrr_params = vrr_params;
+	acrtc->dm_irq_params.vrr_params = vrr_params;
 	new_crtc_state->vrr_infopacket = vrr_infopacket;
 
-	new_stream->adjust = new_crtc_state->vrr_params.adjust;
+	new_stream->adjust = acrtc->dm_irq_params.vrr_params.adjust;
 	new_stream->vrr_infopacket = vrr_infopacket;
 
 	if (new_crtc_state->freesync_vrr_info_changed)
@@ -6931,7 +6959,7 @@ static void update_freesync_state_on_stream(
 	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 }
 
-static void pre_update_freesync_state_on_stream(
+static void update_stream_irq_parameters(
 	struct amdgpu_display_manager *dm,
 	struct dm_crtc_state *new_crtc_state)
 {
@@ -6939,6 +6967,7 @@ static void pre_update_freesync_state_on_stream(
 	struct mod_vrr_params vrr_params;
 	struct mod_freesync_config config = new_crtc_state->freesync_config;
 	struct amdgpu_device *adev = dm->adev;
+	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(new_crtc_state->base.crtc);
 	unsigned long flags;
 
 	if (!new_stream)
@@ -6952,7 +6981,7 @@ static void pre_update_freesync_state_on_stream(
 		return;
 
 	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
-	vrr_params = new_crtc_state->vrr_params;
+	vrr_params = acrtc->dm_irq_params.vrr_params;
 
 	if (new_crtc_state->vrr_supported &&
 	    config.min_refresh_in_uhz &&
@@ -6969,11 +6998,14 @@ static void pre_update_freesync_state_on_stream(
 				      &config, &vrr_params);
 
 	new_crtc_state->freesync_timing_changed |=
-		(memcmp(&new_crtc_state->vrr_params.adjust,
-			&vrr_params.adjust,
-			sizeof(vrr_params.adjust)) != 0);
+		(memcmp(&acrtc->dm_irq_params.vrr_params.adjust,
+			&vrr_params.adjust, sizeof(vrr_params.adjust)) != 0);
 
-	new_crtc_state->vrr_params = vrr_params;
+	new_crtc_state->freesync_config = config;
+	/* Copy state for access from DM IRQ handler */
+	acrtc->dm_irq_params.freesync_config = config;
+	acrtc->dm_irq_params.active_planes = new_crtc_state->active_planes;
+	acrtc->dm_irq_params.vrr_params = vrr_params;
 	spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 }
 
@@ -7197,7 +7229,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			 * on late submission of flips.
 			 */
 			spin_lock_irqsave(&pcrtc->dev->event_lock, flags);
-			last_flip_vblank = acrtc_attach->last_flip_vblank;
+			last_flip_vblank = acrtc_attach->dm_irq_params.last_flip_vblank;
 			spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags);
 		}
 
@@ -7281,7 +7313,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			spin_lock_irqsave(&pcrtc->dev->event_lock, flags);
 			dc_stream_adjust_vmin_vmax(
 				dm->dc, acrtc_state->stream,
-				&acrtc_state->vrr_params.adjust);
+				&acrtc_attach->dm_irq_params.vrr_params.adjust);
 			spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags);
 		}
 		mutex_lock(&dm->dc_lock);
@@ -7431,34 +7463,6 @@ static int amdgpu_dm_atomic_commit(struct drm_device *dev,
 				   struct drm_atomic_state *state,
 				   bool nonblock)
 {
-	struct drm_crtc *crtc;
-	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
-	struct amdgpu_device *adev = drm_to_adev(dev);
-	int i;
-
-	/*
-	 * We evade vblank and pflip interrupts on CRTCs that are undergoing
-	 * a modeset, being disabled, or have no active planes.
-	 *
-	 * It's done in atomic commit rather than commit tail for now since
-	 * some of these interrupt handlers access the current CRTC state and
-	 * potentially the stream pointer itself.
-	 *
-	 * Since the atomic state is swapped within atomic commit and not within
-	 * commit tail this would leave to new state (that hasn't been committed yet)
-	 * being accesssed from within the handlers.
-	 *
-	 * TODO: Fix this so we can do this in commit tail and not have to block
-	 * in atomic check.
-	 */
-	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
-		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
-
-		if (old_crtc_state->active &&
-		    (!new_crtc_state->active ||
-		     drm_atomic_crtc_needs_modeset(new_crtc_state)))
-			manage_dm_interrupts(adev, acrtc, false);
-	}
 	/*
 	 * Add check here for SoC's that support hardware cursor plane, to
 	 * unset legacy_cursor_update
@@ -7509,6 +7513,20 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		dc_resource_state_copy_construct_current(dm->dc, dc_state);
 	}
 
+	for_each_oldnew_crtc_in_state (state, crtc, old_crtc_state,
+				       new_crtc_state, i) {
+		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
+
+		dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
+
+		if (old_crtc_state->active &&
+		    (!new_crtc_state->active ||
+		     drm_atomic_crtc_needs_modeset(new_crtc_state))) {
+			manage_dm_interrupts(adev, acrtc, false);
+			dc_stream_release(dm_old_crtc_state->stream);
+		}
+	}
+
 	/* update changed items */
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
@@ -7604,7 +7622,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 			if (!status)
 				status = dc_stream_get_status_from_state(dc_state,
 									 dm_new_crtc_state->stream);
-
 			if (!status)
 				DC_ERR("got no status for stream %p on acrtc%p\n", dm_new_crtc_state->stream, acrtc);
 			else
@@ -7730,8 +7747,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
 		dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
 
-		/* Update freesync active state. */
-		pre_update_freesync_state_on_stream(dm, dm_new_crtc_state);
+		/* For freesync config update on crtc state and params for irq */
+		update_stream_irq_parameters(dm, dm_new_crtc_state);
 
 		/* Handle vrr on->off / off->on transitions */
 		amdgpu_dm_handle_vrr_transition(dm_old_crtc_state,
@@ -7747,10 +7764,15 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
 
+		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
+
 		if (new_crtc_state->active &&
 		    (!old_crtc_state->active ||
 		     drm_atomic_crtc_needs_modeset(new_crtc_state))) {
+			dc_stream_retain(dm_new_crtc_state->stream);
+			acrtc->dm_irq_params.stream = dm_new_crtc_state->stream;
 			manage_dm_interrupts(adev, acrtc, true);
+
 #ifdef CONFIG_DEBUG_FS
 			/**
 			 * Frontend may have changed so reapply the CRC capture
@@ -7994,8 +8016,6 @@ static void reset_freesync_config_for_crtc(
 {
 	new_crtc_state->vrr_supported = false;
 
-	memset(&new_crtc_state->vrr_params, 0,
-	       sizeof(new_crtc_state->vrr_params));
 	memset(&new_crtc_state->vrr_infopacket, 0,
 	       sizeof(new_crtc_state->vrr_infopacket));
 }
@@ -8566,6 +8586,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	int ret, i;
 	bool lock_and_validation_needed = false;
 
+	amdgpu_check_debugfs_connector_property_change(adev, state);
+
 	ret = drm_atomic_helper_check_modeset(dev, state);
 	if (ret)
 		goto fail;
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 a7856ae2e5f5..34f6369bf51f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -149,6 +149,8 @@ struct amdgpu_dm_backlight_caps {
  * @cached_state: Caches device atomic state for suspend/resume
  * @cached_dc_state: Cached state of content streams
  * @compressor: Frame buffer compression buffer. See &struct dm_comressor_info
+ * @force_timing_sync: set via debugfs. When set, indicates that all connected
+ *		       displays will be forced to synchronize.
  */
 struct amdgpu_display_manager {
 
@@ -340,13 +342,19 @@ struct amdgpu_display_manager {
 	 * fake encoders used for DP MST.
 	 */
 	struct amdgpu_encoder mst_encoders[AMDGPU_DM_MAX_CRTC];
-        bool force_timing_sync;
+	bool force_timing_sync;
+};
+
+enum dsc_clock_force_state {
+	DSC_CLK_FORCE_DEFAULT = 0,
+	DSC_CLK_FORCE_ENABLE,
+	DSC_CLK_FORCE_DISABLE,
 };
 
 struct dsc_preferred_settings {
-	bool dsc_clock_en;
-	uint32_t dsc_slice_width;
-	uint32_t dsc_slice_height;
+	enum dsc_clock_force_state dsc_force_enable;
+	uint32_t dsc_num_slices_v;
+	uint32_t dsc_num_slices_h;
 	uint32_t dsc_bits_per_pixel;
 };
 
@@ -434,7 +442,6 @@ struct dm_crtc_state {
 
 	bool vrr_supported;
 	struct mod_freesync_config freesync_config;
-	struct mod_vrr_params vrr_params;
 	struct dc_info_packet vrr_infopacket;
 
 	int abm_level;
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 94fcb086154c..8cd646eef096 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
@@ -111,7 +111,6 @@ static int parse_write_buffer_into_params(char *wr_buf, uint32_t wr_buf_size,
 
 	if (*param_nums > max_param_num)
 		*param_nums = max_param_num;
-;
 
 	wr_buf_ptr = wr_buf; /* reset buf pointer */
 	wr_buf_count = 0; /* number of char already checked */
@@ -265,7 +264,7 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
 	if (!wr_buf)
 		return -ENOSPC;
 
-	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+	if (parse_write_buffer_into_params(wr_buf, size,
 					   (long *)param, buf,
 					   max_param_num,
 					   &param_nums)) {
@@ -424,7 +423,7 @@ static ssize_t dp_phy_settings_write(struct file *f, const char __user *buf,
 	if (!wr_buf)
 		return -ENOSPC;
 
-	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+	if (parse_write_buffer_into_params(wr_buf, size,
 					   (long *)param, buf,
 					   max_param_num,
 					   &param_nums)) {
@@ -576,7 +575,7 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us
 	if (!wr_buf)
 		return -ENOSPC;
 
-	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+	if (parse_write_buffer_into_params(wr_buf, size,
 					   (long *)param, buf,
 					   max_param_num,
 					   &param_nums)) {
@@ -909,7 +908,7 @@ static ssize_t dp_dpcd_address_write(struct file *f, const char __user *buf,
 	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
 
 	if (size < sizeof(connector->debugfs_dpcd_address))
-		return 0;
+		return -EINVAL;
 
 	r = copy_from_user(&connector->debugfs_dpcd_address,
 			buf, sizeof(connector->debugfs_dpcd_address));
@@ -924,7 +923,7 @@ static ssize_t dp_dpcd_size_write(struct file *f, const char __user *buf,
 	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
 
 	if (size < sizeof(connector->debugfs_dpcd_size))
-		return 0;
+		return -EINVAL;
 
 	r = copy_from_user(&connector->debugfs_dpcd_size,
 			buf, sizeof(connector->debugfs_dpcd_size));
@@ -944,8 +943,8 @@ static ssize_t dp_dpcd_data_write(struct file *f, const char __user *buf,
 	struct dc_link *link = connector->dc_link;
 	uint32_t write_size = connector->debugfs_dpcd_size;
 
-	if (size < write_size)
-		return 0;
+	if (!write_size || size < write_size)
+		return -EINVAL;
 
 	data = kzalloc(write_size, GFP_KERNEL);
 	if (!data)
@@ -968,7 +967,7 @@ static ssize_t dp_dpcd_data_read(struct file *f, char __user *buf,
 	struct dc_link *link = connector->dc_link;
 	uint32_t read_size = connector->debugfs_dpcd_size;
 
-	if (size < read_size)
+	if (!read_size || size < read_size)
 		return 0;
 
 	data = kzalloc(read_size, GFP_KERNEL);
@@ -1059,12 +1058,17 @@ static int dp_dsc_fec_support_show(struct seq_file *m, void *data)
  *
  *	echo 1 > /sys/kernel/debug/dri/0/DP-X/trigger_hotplug
  *
+ * This function can perform HPD unplug:
+ *
+ *	echo 0 > /sys/kernel/debug/dri/0/DP-X/trigger_hotplug
+ *
  */
 static ssize_t dp_trigger_hotplug(struct file *f, const char __user *buf,
 							size_t size, loff_t *pos)
 {
 	struct amdgpu_dm_connector *aconnector = file_inode(f)->i_private;
 	struct drm_connector *connector = &aconnector->base;
+	struct dc_link *link = NULL;
 	struct drm_device *dev = connector->dev;
 	enum dc_connection_type new_connection_type = dc_connection_none;
 	char *wr_buf = NULL;
@@ -1086,11 +1090,13 @@ static ssize_t dp_trigger_hotplug(struct file *f, const char __user *buf,
 		return -ENOSPC;
 	}
 
-	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+	if (parse_write_buffer_into_params(wr_buf, size,
 						(long *)param, buf,
 						max_param_num,
-						&param_nums))
+						&param_nums)) {
+		kfree(wr_buf);
 		return -EINVAL;
+	}
 
 	if (param_nums <= 0) {
 		DRM_DEBUG_DRIVER("user data not be read\n");
@@ -1115,11 +1121,33 @@ static ssize_t dp_trigger_hotplug(struct file *f, const char __user *buf,
 		drm_modeset_unlock_all(dev);
 
 		drm_kms_helper_hotplug_event(dev);
+	} else if (param[0] == 0) {
+		if (!aconnector->dc_link)
+			goto unlock;
 
-unlock:
-		mutex_unlock(&aconnector->hpd_lock);
+		link = aconnector->dc_link;
+
+		if (link->local_sink) {
+			dc_sink_release(link->local_sink);
+			link->local_sink = NULL;
+		}
+
+		link->dpcd_sink_count = 0;
+		link->type = dc_connection_none;
+		link->dongle_max_pix_clk = 0;
+
+		amdgpu_dm_update_connector_after_detect(aconnector);
+
+		drm_modeset_lock_all(dev);
+		dm_restore_drm_connector_state(dev, connector);
+		drm_modeset_unlock_all(dev);
+
+		drm_kms_helper_hotplug_event(dev);
 	}
 
+unlock:
+	mutex_unlock(&aconnector->hpd_lock);
+
 	kfree(wr_buf);
 	return size;
 }
@@ -1200,9 +1228,14 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf,
  *
  * The write function: dp_dsc_clock_en_write
  * enables to force DSC on the connector.
- * User can write to either force enable DSC
+ * User can write to either force enable or force disable DSC
  * on the next modeset or set it to driver default
  *
+ * Accepted inputs:
+ * 0 - default DSC enablement policy
+ * 1 - force enable DSC on the connector
+ * 2 - force disable DSC on the connector (might cause fail in atomic_check)
+ *
  * Writing DSC settings is done with the following command:
  * - To force enable DSC (you need to specify
  * connector like DP-1):
@@ -1238,7 +1271,7 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf,
 		return -ENOSPC;
 	}
 
-	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+	if (parse_write_buffer_into_params(wr_buf, size,
 					    (long *)param, buf,
 					    max_param_num,
 					    &param_nums)) {
@@ -1262,7 +1295,12 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf,
 	if (!pipe_ctx || !pipe_ctx->stream)
 		goto done;
 
-	aconnector->dsc_settings.dsc_clock_en = param[0];
+	if (param[0] == 1)
+		aconnector->dsc_settings.dsc_force_enable = DSC_CLK_FORCE_ENABLE;
+	else if (param[0] == 2)
+		aconnector->dsc_settings.dsc_force_enable = DSC_CLK_FORCE_DISABLE;
+	else
+		aconnector->dsc_settings.dsc_force_enable = DSC_CLK_FORCE_DEFAULT;
 
 done:
 	kfree(wr_buf);
@@ -1387,7 +1425,7 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf,
 		return -ENOSPC;
 	}
 
-	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+	if (parse_write_buffer_into_params(wr_buf, size,
 					    (long *)param, buf,
 					    max_param_num,
 					    &param_nums)) {
@@ -1411,7 +1449,12 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf,
 	if (!pipe_ctx || !pipe_ctx->stream)
 		goto done;
 
-	aconnector->dsc_settings.dsc_slice_width = param[0];
+	if (param[0] > 0)
+		aconnector->dsc_settings.dsc_num_slices_h = DIV_ROUND_UP(
+					pipe_ctx->stream->timing.h_addressable,
+					param[0]);
+	else
+		aconnector->dsc_settings.dsc_num_slices_h = 0;
 
 done:
 	kfree(wr_buf);
@@ -1536,7 +1579,7 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf,
 		return -ENOSPC;
 	}
 
-	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+	if (parse_write_buffer_into_params(wr_buf, size,
 					    (long *)param, buf,
 					    max_param_num,
 					    &param_nums)) {
@@ -1560,7 +1603,12 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf,
 	if (!pipe_ctx || !pipe_ctx->stream)
 		goto done;
 
-	aconnector->dsc_settings.dsc_slice_height = param[0];
+	if (param[0] > 0)
+		aconnector->dsc_settings.dsc_num_slices_v = DIV_ROUND_UP(
+					pipe_ctx->stream->timing.v_addressable,
+					param[0]);
+	else
+		aconnector->dsc_settings.dsc_num_slices_v = 0;
 
 done:
 	kfree(wr_buf);
@@ -1678,7 +1726,7 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bu
 		return -ENOSPC;
 	}
 
-	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+	if (parse_write_buffer_into_params(wr_buf, size,
 					    (long *)param, buf,
 					    max_param_num,
 					    &param_nums)) {
@@ -2098,6 +2146,7 @@ static const struct {
 	const struct file_operations *fops;
 } dp_debugfs_entries[] = {
 		{"link_settings", &dp_link_settings_debugfs_fops},
+		{"trigger_hotplug", &dp_trigger_hotplug_debugfs_fops},
 		{"phy_settings", &dp_phy_settings_debugfs_fop},
 		{"test_pattern", &dp_phy_test_pattern_fops},
 #ifdef CONFIG_DRM_AMD_DC_HDCP
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 694c5bc93665..c2cd184f0bbd 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
@@ -604,7 +604,7 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev, struct
 	int i = 0;
 
 	hdcp_work = kcalloc(max_caps, sizeof(*hdcp_work), GFP_KERNEL);
-	if (hdcp_work == NULL)
+	if (ZERO_OR_NULL_PTR(hdcp_work))
 		return NULL;
 
 	hdcp_work->srm = kcalloc(PSP_HDCP_SRM_FIRST_GEN_MAX_SIZE, sizeof(*hdcp_work->srm), GFP_KERNEL);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
new file mode 100644
index 000000000000..45825a34f8eb
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __AMDGPU_DM_IRQ_PARAMS_H__
+#define __AMDGPU_DM_IRQ_PARAMS_H__
+
+struct dm_irq_params {
+	u32 last_flip_vblank;
+	struct mod_vrr_params vrr_params;
+	struct dc_stream_state *stream;
+	int active_planes;
+	struct mod_freesync_config freesync_config;
+};
+
+#endif /* __AMDGPU_DM_IRQ_PARAMS_H__ */
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 adbb44822e94..eee19edeeee5 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
@@ -159,7 +159,20 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto
 	u8 dsc_caps[16] = { 0 };
 
 	aconnector->dsc_aux = drm_dp_mst_dsc_aux_for_port(port);
+#if defined(CONFIG_HP_HOOK_WORKAROUND)
+	/*
+	 * drm_dp_mst_dsc_aux_for_port() will return NULL for certain configs
+	 * because it only check the dsc/fec caps of the "port variable" and not the dock
+	 *
+	 * This case will return NULL: DSC capabe MST dock connected to a non fec/dsc capable display
+	 *
+	 * Workaround: explicitly check the use case above and use the mst dock's aux as dsc_aux
+	 *
+	 */
 
+	if (!aconnector->dsc_aux && !port->parent->port_parent)
+		aconnector->dsc_aux = &aconnector->mst_port->dm_dp_aux.aux;
+#endif
 	if (!aconnector->dsc_aux)
 		return false;
 
@@ -453,9 +466,9 @@ struct dsc_mst_fairness_params {
 	struct dc_dsc_bw_range bw_range;
 	bool compression_possible;
 	struct drm_dp_mst_port *port;
-	bool clock_overwrite;
-	uint32_t slice_width_overwrite;
-	uint32_t slice_height_overwrite;
+	enum dsc_clock_force_state clock_force_enable;
+	uint32_t num_slices_h;
+	uint32_t num_slices_v;
 	uint32_t bpp_overwrite;
 };
 
@@ -496,15 +509,11 @@ static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *p
 			else
 				params[i].timing->dsc_cfg.bits_per_pixel = vars[i].bpp_x16;
 
-			if (params[i].slice_width_overwrite)
-				params[i].timing->dsc_cfg.num_slices_h = DIV_ROUND_UP(
-										params[i].timing->h_addressable,
-										params[i].slice_width_overwrite);
+			if (params[i].num_slices_h)
+				params[i].timing->dsc_cfg.num_slices_h = params[i].num_slices_h;
 
-			if (params[i].slice_height_overwrite)
-				params[i].timing->dsc_cfg.num_slices_v = DIV_ROUND_UP(
-										params[i].timing->v_addressable,
-										params[i].slice_height_overwrite);
+			if (params[i].num_slices_v)
+				params[i].timing->dsc_cfg.num_slices_v = params[i].num_slices_v;
 		} else {
 			params[i].timing->flags.DSC = 0;
 		}
@@ -638,7 +647,7 @@ static void try_disable_dsc(struct drm_atomic_state *state,
 	for (i = 0; i < count; i++) {
 		if (vars[i].dsc_enabled
 				&& vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16
-				&& !params[i].clock_overwrite) {
+				&& params[i].clock_force_enable == DSC_CLK_FORCE_DEFAULT) {
 			kbps_increase[i] = params[i].bw_range.stream_kbps - params[i].bw_range.max_kbps;
 			tried[i] = false;
 			remaining_to_try += 1;
@@ -718,11 +727,11 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 		params[count].sink = stream->sink;
 		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
 		params[count].port = aconnector->port;
-		params[count].clock_overwrite = aconnector->dsc_settings.dsc_clock_en;
-		if (params[count].clock_overwrite)
+		params[count].clock_force_enable = aconnector->dsc_settings.dsc_force_enable;
+		if (params[count].clock_force_enable == DSC_CLK_FORCE_ENABLE)
 			debugfs_overwrite = true;
-		params[count].slice_width_overwrite = aconnector->dsc_settings.dsc_slice_width;
-		params[count].slice_height_overwrite = aconnector->dsc_settings.dsc_slice_height;
+		params[count].num_slices_h = aconnector->dsc_settings.dsc_num_slices_h;
+		params[count].num_slices_v = aconnector->dsc_settings.dsc_num_slices_v;
 		params[count].bpp_overwrite = aconnector->dsc_settings.dsc_bits_per_pixel;
 		params[count].compression_possible = stream->sink->dsc_caps.dsc_dec_caps.is_dsc_supported;
 		dc_dsc_get_policy_for_timing(params[count].timing, &dsc_policy);
@@ -756,7 +765,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
 
 	/* Try max compression */
 	for (i = 0; i < count; i++) {
-		if (params[i].compression_possible) {
+		if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) {
 			vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps);
 			vars[i].dsc_enabled = true;
 			vars[i].bpp_x16 = params[i].bw_range.min_target_bpp_x16;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index c5f2216e59c4..6e575ffe34d0 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -592,9 +592,6 @@ void pp_rv_set_wm_ranges(struct pp_smu *pp,
 	if (pp_funcs && pp_funcs->set_watermarks_for_clocks_ranges)
 		pp_funcs->set_watermarks_for_clocks_ranges(pp_handle,
 							   &wm_with_clock_ranges);
-	else if (adev->smu.ppt_funcs)
-		smu_set_watermarks_for_clock_ranges(&adev->smu,
-				&wm_with_clock_ranges);
 }
 
 void pp_rv_set_pme_wa_enable(struct pp_smu *pp)
@@ -667,49 +664,8 @@ static enum pp_smu_status pp_nv_set_wm_ranges(struct pp_smu *pp,
 {
 	const struct dc_context *ctx = pp->dm;
 	struct amdgpu_device *adev = ctx->driver_context;
-	struct dm_pp_wm_sets_with_clock_ranges_soc15 wm_with_clock_ranges;
-	struct dm_pp_clock_range_for_dmif_wm_set_soc15 *wm_dce_clocks =
-			wm_with_clock_ranges.wm_dmif_clocks_ranges;
-	struct dm_pp_clock_range_for_mcif_wm_set_soc15 *wm_soc_clocks =
-			wm_with_clock_ranges.wm_mcif_clocks_ranges;
-	int32_t i;
 
-	wm_with_clock_ranges.num_wm_dmif_sets = ranges->num_reader_wm_sets;
-	wm_with_clock_ranges.num_wm_mcif_sets = ranges->num_writer_wm_sets;
-
-	for (i = 0; i < wm_with_clock_ranges.num_wm_dmif_sets; i++) {
-		if (ranges->reader_wm_sets[i].wm_inst > 3)
-			wm_dce_clocks[i].wm_set_id = WM_SET_A;
-		else
-			wm_dce_clocks[i].wm_set_id =
-					ranges->reader_wm_sets[i].wm_inst;
-		wm_dce_clocks[i].wm_max_dcfclk_clk_in_khz =
-			ranges->reader_wm_sets[i].max_drain_clk_mhz * 1000;
-		wm_dce_clocks[i].wm_min_dcfclk_clk_in_khz =
-			ranges->reader_wm_sets[i].min_drain_clk_mhz * 1000;
-		wm_dce_clocks[i].wm_max_mem_clk_in_khz =
-			ranges->reader_wm_sets[i].max_fill_clk_mhz * 1000;
-		wm_dce_clocks[i].wm_min_mem_clk_in_khz =
-			ranges->reader_wm_sets[i].min_fill_clk_mhz * 1000;
-	}
-
-	for (i = 0; i < wm_with_clock_ranges.num_wm_mcif_sets; i++) {
-		if (ranges->writer_wm_sets[i].wm_inst > 3)
-			wm_soc_clocks[i].wm_set_id = WM_SET_A;
-		else
-			wm_soc_clocks[i].wm_set_id =
-					ranges->writer_wm_sets[i].wm_inst;
-		wm_soc_clocks[i].wm_max_socclk_clk_in_khz =
-			ranges->writer_wm_sets[i].max_fill_clk_mhz * 1000;
-		wm_soc_clocks[i].wm_min_socclk_clk_in_khz =
-			ranges->writer_wm_sets[i].min_fill_clk_mhz * 1000;
-		wm_soc_clocks[i].wm_max_mem_clk_in_khz =
-			ranges->writer_wm_sets[i].max_drain_clk_mhz * 1000;
-		wm_soc_clocks[i].wm_min_mem_clk_in_khz =
-			ranges->writer_wm_sets[i].min_drain_clk_mhz * 1000;
-	}
-
-	smu_set_watermarks_for_clock_ranges(&adev->smu,	&wm_with_clock_ranges);
+	smu_set_watermarks_for_clock_ranges(&adev->smu, ranges);
 
 	return PP_SMU_RESULT_OK;
 }
@@ -810,7 +766,7 @@ pp_nv_set_hard_min_uclk_by_freq(struct pp_smu *pp, int mhz)
 }
 
 static enum pp_smu_status pp_nv_set_pstate_handshake_support(
-	struct pp_smu *pp, BOOLEAN pstate_handshake_supported)
+	struct pp_smu *pp, bool pstate_handshake_supported)
 {
 	const struct dc_context *ctx = pp->dm;
 	struct amdgpu_device *adev = ctx->driver_context;
@@ -920,60 +876,8 @@ static enum pp_smu_status pp_rn_set_wm_ranges(struct pp_smu *pp,
 {
 	const struct dc_context *ctx = pp->dm;
 	struct amdgpu_device *adev = ctx->driver_context;
-	struct smu_context *smu = &adev->smu;
-	struct dm_pp_wm_sets_with_clock_ranges_soc15 wm_with_clock_ranges;
-	struct dm_pp_clock_range_for_dmif_wm_set_soc15 *wm_dce_clocks =
-			wm_with_clock_ranges.wm_dmif_clocks_ranges;
-	struct dm_pp_clock_range_for_mcif_wm_set_soc15 *wm_soc_clocks =
-			wm_with_clock_ranges.wm_mcif_clocks_ranges;
-	int32_t i;
-
-	if (!smu->ppt_funcs)
-		return PP_SMU_RESULT_UNSUPPORTED;
-
-	wm_with_clock_ranges.num_wm_dmif_sets = ranges->num_reader_wm_sets;
-	wm_with_clock_ranges.num_wm_mcif_sets = ranges->num_writer_wm_sets;
-
-	for (i = 0; i < wm_with_clock_ranges.num_wm_dmif_sets; i++) {
-		if (ranges->reader_wm_sets[i].wm_inst > 3)
-			wm_dce_clocks[i].wm_set_id = WM_SET_A;
-		else
-			wm_dce_clocks[i].wm_set_id =
-					ranges->reader_wm_sets[i].wm_inst;
-
-		wm_dce_clocks[i].wm_min_dcfclk_clk_in_khz =
-			ranges->reader_wm_sets[i].min_drain_clk_mhz;
-
-		wm_dce_clocks[i].wm_max_dcfclk_clk_in_khz =
-			ranges->reader_wm_sets[i].max_drain_clk_mhz;
-
-		wm_dce_clocks[i].wm_min_mem_clk_in_khz =
-			ranges->reader_wm_sets[i].min_fill_clk_mhz;
-
-		wm_dce_clocks[i].wm_max_mem_clk_in_khz =
-			ranges->reader_wm_sets[i].max_fill_clk_mhz;
-	}
-
-	for (i = 0; i < wm_with_clock_ranges.num_wm_mcif_sets; i++) {
-		if (ranges->writer_wm_sets[i].wm_inst > 3)
-			wm_soc_clocks[i].wm_set_id = WM_SET_A;
-		else
-			wm_soc_clocks[i].wm_set_id =
-					ranges->writer_wm_sets[i].wm_inst;
-		wm_soc_clocks[i].wm_min_socclk_clk_in_khz =
-				ranges->writer_wm_sets[i].min_fill_clk_mhz;
-
-		wm_soc_clocks[i].wm_max_socclk_clk_in_khz =
-			ranges->writer_wm_sets[i].max_fill_clk_mhz;
-
-		wm_soc_clocks[i].wm_min_mem_clk_in_khz =
-			ranges->writer_wm_sets[i].min_drain_clk_mhz;
-
-		wm_soc_clocks[i].wm_max_mem_clk_in_khz =
-			ranges->writer_wm_sets[i].max_drain_clk_mhz;
-	}
 
-	smu_set_watermarks_for_clock_ranges(&adev->smu, &wm_with_clock_ranges);
+	smu_set_watermarks_for_clock_ranges(&adev->smu, ranges);
 
 	return PP_SMU_RESULT_OK;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 2d5c7daaee23..29d64e7e304f 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -847,6 +847,73 @@ static enum bp_result bios_parser_get_spread_spectrum_info(
 	return result;
 }
 
+static enum bp_result get_soc_bb_info_v4_4(
+	struct bios_parser *bp,
+	struct bp_soc_bb_info *soc_bb_info)
+{
+	enum bp_result result = BP_RESULT_OK;
+	struct atom_display_controller_info_v4_4 *disp_cntl_tbl = NULL;
+
+	if (!soc_bb_info)
+		return BP_RESULT_BADINPUT;
+
+	if (!DATA_TABLES(dce_info))
+		return BP_RESULT_BADBIOSTABLE;
+
+	if (!DATA_TABLES(smu_info))
+		return BP_RESULT_BADBIOSTABLE;
+
+	disp_cntl_tbl =  GET_IMAGE(struct atom_display_controller_info_v4_4,
+							DATA_TABLES(dce_info));
+	if (!disp_cntl_tbl)
+		return BP_RESULT_BADBIOSTABLE;
+
+	soc_bb_info->dram_clock_change_latency_100ns = disp_cntl_tbl->max_mclk_chg_lat;
+	soc_bb_info->dram_sr_enter_exit_latency_100ns = disp_cntl_tbl->max_sr_enter_exit_lat;
+	soc_bb_info->dram_sr_exit_latency_100ns = disp_cntl_tbl->max_sr_exit_lat;
+
+	return result;
+}
+
+static enum bp_result bios_parser_get_soc_bb_info(
+	struct dc_bios *dcb,
+	struct bp_soc_bb_info *soc_bb_info)
+{
+	struct bios_parser *bp = BP_FROM_DCB(dcb);
+	enum bp_result result = BP_RESULT_UNSUPPORTED;
+	struct atom_common_table_header *header;
+	struct atom_data_revision tbl_revision;
+
+	if (!soc_bb_info) /* check for bad input */
+		return BP_RESULT_BADINPUT;
+
+	if (!DATA_TABLES(dce_info))
+		return BP_RESULT_UNSUPPORTED;
+
+	header = GET_IMAGE(struct atom_common_table_header,
+						DATA_TABLES(dce_info));
+	get_atom_data_table_revision(header, &tbl_revision);
+
+	switch (tbl_revision.major) {
+	case 4:
+		switch (tbl_revision.minor) {
+		case 1:
+		case 2:
+		case 3:
+			break;
+		case 4:
+			result = get_soc_bb_info_v4_4(bp, soc_bb_info);
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return result;
+}
+
 static enum bp_result get_embedded_panel_info_v2_1(
 		struct bios_parser *bp,
 		struct embedded_panel_info *info)
@@ -2222,7 +2289,9 @@ static const struct dc_vbios_funcs vbios_funcs = {
 
 	.get_atom_dc_golden_table = bios_get_atom_dc_golden_table,
 
-	.enable_lvtma_control = bios_parser_enable_lvtma_control
+	.enable_lvtma_control = bios_parser_enable_lvtma_control,
+
+	.get_soc_bb_info = bios_parser_get_soc_bb_info,
 };
 
 static bool bios_parser2_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
index d031bd3d3072..807dca8f7d7a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
@@ -79,8 +79,7 @@ int dce112_set_clock(struct clk_mgr *clk_mgr_base, int requested_clk_khz)
 	memset(&dce_clk_params, 0, sizeof(dce_clk_params));
 
 	/* Make sure requested clock isn't lower than minimum threshold*/
-	if (requested_clk_khz > 0)
-		requested_clk_khz = max(requested_clk_khz,
+	requested_clk_khz = max(requested_clk_khz,
 				clk_mgr_dce->base.dentist_vco_freq_khz / 62);
 
 	dce_clk_params.target_clock_frequency = requested_clk_khz;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
index c11c6b3a787d..0267644717b2 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
@@ -80,7 +80,7 @@ static const struct state_dependent_clocks dce60_max_clks_by_state[] = {
 /* ClocksStatePerformance */
 { .display_clk_khz = 600000, .pixel_clk_khz = 400000 } };
 
-int dce60_get_dp_ref_freq_khz(struct clk_mgr *clk_mgr_base)
+static int dce60_get_dp_ref_freq_khz(struct clk_mgr *clk_mgr_base)
 {
 	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
 	int dprefclk_wdivider;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index 543afa34d87a..2f8fee05547a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -761,6 +761,7 @@ void rn_clk_mgr_construct(
 {
 	struct dc_debug_options *debug = &ctx->dc->debug;
 	struct dpm_clocks clock_table = { 0 };
+	enum pp_smu_status status = 0;
 
 	clk_mgr->base.ctx = ctx;
 	clk_mgr->base.funcs = &dcn21_funcs;
@@ -783,7 +784,6 @@ void rn_clk_mgr_construct(
 	} else {
 		struct clk_log_info log_info = {0};
 
-		clk_mgr->smu_ver = rn_vbios_smu_get_smu_version(clk_mgr);
 		clk_mgr->periodic_retraining_disabled = rn_vbios_smu_is_periodic_retraining_disabled(clk_mgr);
 
 		/* SMU Version 55.51.0 and up no longer have an issue
@@ -818,8 +818,10 @@ void rn_clk_mgr_construct(
 	clk_mgr->base.bw_params = &rn_bw_params;
 
 	if (pp_smu && pp_smu->rn_funcs.get_dpm_clock_table) {
-		pp_smu->rn_funcs.get_dpm_clock_table(&pp_smu->rn_funcs.pp_smu, &clock_table);
-		if (ctx->dc_bios && ctx->dc_bios->integrated_info) {
+		status = pp_smu->rn_funcs.get_dpm_clock_table(&pp_smu->rn_funcs.pp_smu, &clock_table);
+
+		if (status == PP_SMU_RESULT_OK &&
+		    ctx->dc_bios && ctx->dc_bios->integrated_info) {
 			rn_clk_mgr_helper_populate_bw_params (clk_mgr->base.bw_params, &clock_table, ctx->dc_bios->integrated_info);
 		}
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index dc463d99ef50..45ad05f6e03b 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -735,6 +735,8 @@ static bool dc_construct(struct dc *dc,
 	dc->clk_mgr->force_smu_not_present = init_params->force_smu_not_present;
 #endif
 
+	dc->debug.force_ignore_link_settings = init_params->force_ignore_link_settings;
+
 	if (dc->res_pool->funcs->update_bw_bounding_box)
 		dc->res_pool->funcs->update_bw_bounding_box(dc, dc->clk_mgr->bw_params);
 
@@ -842,6 +844,60 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 	dc_release_state(current_ctx);
 }
 
+static void disable_vbios_mode_if_required(
+		struct dc *dc,
+		struct dc_state *context)
+{
+	unsigned int i, j;
+
+	/* check if timing_changed, disable stream*/
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct dc_stream_state *stream = NULL;
+		struct dc_link *link = NULL;
+		struct pipe_ctx *pipe = NULL;
+
+		pipe = &context->res_ctx.pipe_ctx[i];
+		stream = pipe->stream;
+		if (stream == NULL)
+			continue;
+
+		if (stream->link->local_sink &&
+			stream->link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
+			link = stream->link;
+		}
+
+		if (link != NULL) {
+			unsigned int enc_inst, tg_inst = 0;
+			unsigned int pix_clk_100hz;
+
+			enc_inst = link->link_enc->funcs->get_dig_frontend(link->link_enc);
+			if (enc_inst != ENGINE_ID_UNKNOWN) {
+				for (j = 0; j < dc->res_pool->stream_enc_count; j++) {
+					if (dc->res_pool->stream_enc[j]->id == enc_inst) {
+						tg_inst = dc->res_pool->stream_enc[j]->funcs->dig_source_otg(
+							dc->res_pool->stream_enc[j]);
+						break;
+					}
+				}
+
+				dc->res_pool->dp_clock_source->funcs->get_pixel_clk_frequency_100hz(
+					dc->res_pool->dp_clock_source,
+					tg_inst, &pix_clk_100hz);
+
+				if (link->link_status.link_active) {
+					uint32_t requested_pix_clk_100hz =
+						pipe->stream_res.pix_clk_params.requested_pix_clk_100hz;
+
+					if (pix_clk_100hz != requested_pix_clk_100hz) {
+						core_link_disable_stream(pipe);
+						pipe->stream->dpms_off = false;
+					}
+				}
+			}
+		}
+	}
+}
+
 static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context)
 {
 	int i;
@@ -1246,6 +1302,19 @@ void dc_trigger_sync(struct dc *dc, struct dc_state *context)
 	}
 }
 
+static uint8_t get_stream_mask(struct dc *dc, struct dc_state *context)
+{
+	int i;
+	unsigned int stream_mask = 0;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (context->res_ctx.pipe_ctx[i].stream)
+			stream_mask |= 1 << i;
+	}
+
+	return stream_mask;
+}
+
 /*
  * Applies given context to HW and copy it into current context.
  * It's up to the user to release the src context afterwards.
@@ -1265,15 +1334,17 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 	for (i = 0; i < context->stream_count; i++)
 		dc_streams[i] =  context->streams[i];
 
-	if (!dcb->funcs->is_accelerated_mode(dcb))
+	if (!dcb->funcs->is_accelerated_mode(dcb)) {
+		disable_vbios_mode_if_required(dc, context);
 		dc->hwss.enable_accelerated_mode(dc, context);
+	}
 
-	for (i = 0; i < context->stream_count; i++) {
+	for (i = 0; i < context->stream_count; i++)
 		if (context->streams[i]->apply_seamless_boot_optimization)
 			dc->optimize_seamless_boot_streams++;
-	}
 
-	if (dc->optimize_seamless_boot_streams == 0)
+	if (context->stream_count > dc->optimize_seamless_boot_streams ||
+		context->stream_count == 0)
 		dc->hwss.prepare_bandwidth(dc, context);
 
 	disable_dangling_plane(dc, context);
@@ -1355,13 +1426,19 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 
 	dc_enable_stereo(dc, context, dc_streams, context->stream_count);
 
-	if (dc->optimize_seamless_boot_streams == 0) {
+	if (context->stream_count > dc->optimize_seamless_boot_streams ||
+		context->stream_count == 0) {
 		/* Must wait for no flips to be pending before doing optimize bw */
 		wait_for_no_pipes_pending(dc, context);
 		/* pplib is notified if disp_num changed */
 		dc->hwss.optimize_bandwidth(dc, context);
 	}
 
+	context->stream_mask = get_stream_mask(dc, context);
+
+	if (context->stream_mask != dc->current_state->stream_mask)
+		dc_dmub_srv_notify_stream_mask(dc->ctx->dmub_srv, context->stream_mask);
+
 	for (i = 0; i < context->stream_count; i++)
 		context->streams[i]->mode_changed = false;
 
@@ -1481,13 +1558,8 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc)
 	return true;
 }
 
-struct dc_state *dc_create_state(struct dc *dc)
+static void init_state(struct dc *dc, struct dc_state *context)
 {
-	struct dc_state *context = kvzalloc(sizeof(struct dc_state),
-					    GFP_KERNEL);
-
-	if (!context)
-		return NULL;
 	/* Each context must have their own instance of VBA and in order to
 	 * initialize and obtain IP and SOC the base DML instance from DC is
 	 * initially copied into every context
@@ -1495,6 +1567,17 @@ struct dc_state *dc_create_state(struct dc *dc)
 #ifdef CONFIG_DRM_AMD_DC_DCN
 	memcpy(&context->bw_ctx.dml, &dc->dml, sizeof(struct display_mode_lib));
 #endif
+}
+
+struct dc_state *dc_create_state(struct dc *dc)
+{
+	struct dc_state *context = kvzalloc(sizeof(struct dc_state),
+					    GFP_KERNEL);
+
+	if (!context)
+		return NULL;
+
+	init_state(dc, context);
 
 	kref_init(&context->refcount);
 
@@ -2415,8 +2498,7 @@ static void commit_planes_for_stream(struct dc *dc,
 				plane_state->triplebuffer_flips = false;
 				if (update_type == UPDATE_TYPE_FAST &&
 					dc->hwss.program_triplebuffer != NULL &&
-					!plane_state->flip_immediate &&
-					!dc->debug.disable_tri_buf) {
+					!plane_state->flip_immediate && dc->debug.enable_tri_buf) {
 						/*triple buffer for VUpdate  only*/
 						plane_state->triplebuffer_flips = true;
 				}
@@ -2443,8 +2525,7 @@ static void commit_planes_for_stream(struct dc *dc,
 
 			ASSERT(!pipe_ctx->plane_state->triplebuffer_flips);
 
-			if (dc->hwss.program_triplebuffer != NULL &&
-				!dc->debug.disable_tri_buf) {
+			if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) {
 				/*turn off triple buffer for full update*/
 				dc->hwss.program_triplebuffer(
 					dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips);
@@ -2509,8 +2590,7 @@ static void commit_planes_for_stream(struct dc *dc,
 				if (pipe_ctx->plane_state != plane_state)
 					continue;
 				/*program triple buffer after lock based on flip type*/
-				if (dc->hwss.program_triplebuffer != NULL &&
-					!dc->debug.disable_tri_buf) {
+				if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) {
 					/*only enable triplebuffer for  fast_update*/
 					dc->hwss.program_triplebuffer(
 						dc, pipe_ctx, plane_state->triplebuffer_flips);
@@ -2965,7 +3045,7 @@ bool dc_set_psr_allow_active(struct dc *dc, bool enable)
 			if (enable && !link->psr_settings.psr_allow_active)
 				return dc_link_set_psr_allow_active(link, true, false);
 			else if (!enable && link->psr_settings.psr_allow_active)
-				return dc_link_set_psr_allow_active(link, false, false);
+				return dc_link_set_psr_allow_active(link, false, true);
 		}
 	}
 
@@ -3018,4 +3098,10 @@ void dc_lock_memory_clock_frequency(struct dc *dc)
 		if (dc->current_state->res_ctx.pipe_ctx[i].plane_state)
 			core_link_enable_stream(dc->current_state, &dc->current_state->res_ctx.pipe_ctx[i]);
 }
+
+bool dc_is_plane_eligible_for_idle_optimizaitons(struct dc *dc,
+						 struct dc_plane_state *plane)
+{
+	return false;
+}
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
index c026b393f3c5..2a9080400bdd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
@@ -177,7 +177,7 @@ static bool is_ycbcr709_limited_type(
 		ret = true;
 	return ret;
 }
-enum dc_color_space_type get_color_space_type(enum dc_color_space color_space)
+static enum dc_color_space_type get_color_space_type(enum dc_color_space color_space)
 {
 	enum dc_color_space_type type = COLOR_SPACE_RGB_TYPE;
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 437d1a7a16fe..fec87a2e210c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -2441,7 +2441,7 @@ enum dc_status dc_link_validate_mode_timing(
 	/* A hack to avoid failing any modes for EDID override feature on
 	 * topology change such as lower quality cable for DP or different dongle
 	 */
-	if (link->remote_sinks[0])
+	if (link->remote_sinks[0] && link->remote_sinks[0]->sink_signal == SIGNAL_TYPE_VIRTUAL)
 		return DC_OK;
 
 	/* Passive Dongle */
@@ -2566,7 +2566,7 @@ bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, bool
 	link->psr_settings.psr_allow_active = allow_active;
 
 	if (psr != NULL && link->psr_settings.psr_feature_enabled)
-		psr->funcs->psr_enable(psr, allow_active);
+		psr->funcs->psr_enable(psr, allow_active, wait);
 	else if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_settings.psr_feature_enabled)
 		dmcu->funcs->set_psr_enable(dmcu, allow_active, wait);
 	else
@@ -2946,7 +2946,7 @@ enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx)
 	pbn = get_pbn_from_timing(pipe_ctx);
 	avg_time_slots_per_mtp = dc_fixpt_div(pbn, pbn_per_slot);
 
-	stream_encoder->funcs->set_mst_bandwidth(
+	stream_encoder->funcs->set_throttled_vcp_size(
 		stream_encoder,
 		avg_time_slots_per_mtp);
 
@@ -2974,7 +2974,7 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx)
 	 */
 
 	/* slot X.Y */
-	stream_encoder->funcs->set_mst_bandwidth(
+	stream_encoder->funcs->set_throttled_vcp_size(
 		stream_encoder,
 		avg_time_slots_per_mtp);
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index b984eecca58b..dec12de37642 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -148,14 +148,6 @@ static uint32_t dal_ddc_i2c_payloads_get_count(struct i2c_payloads *p)
 	return p->payloads.count;
 }
 
-static void dal_ddc_i2c_payloads_destroy(struct i2c_payloads *p)
-{
-	if (!p)
-		return;
-
-	dal_vector_destruct(&p->payloads);
-}
-
 #define DDC_MIN(a, b) (((a) < (b)) ? (a) : (b))
 
 void dal_ddc_i2c_payloads_add(
@@ -582,7 +574,7 @@ bool dal_ddc_service_query_ddc_data(
 				ddc->link,
 				&command);
 
-		dal_ddc_i2c_payloads_destroy(&payloads);
+		dal_vector_destruct(&payloads.payloads);
 	}
 
 	return success;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index d1d95d3e248a..ff1e9963ec7a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -49,14 +49,31 @@ static struct dc_link_settings get_common_supported_link_settings(
 		struct dc_link_settings link_setting_a,
 		struct dc_link_settings link_setting_b);
 
-static uint32_t get_training_aux_rd_interval(
-	struct dc_link *link,
-	uint32_t default_wait_in_micro_secs)
+static uint32_t get_cr_training_aux_rd_interval(struct dc_link *link,
+		const struct dc_link_settings *link_settings)
 {
 	union training_aux_rd_interval training_rd_interval;
+	uint32_t wait_in_micro_secs = 100;
 
 	memset(&training_rd_interval, 0, sizeof(training_rd_interval));
+	core_link_read_dpcd(
+			link,
+			DP_TRAINING_AUX_RD_INTERVAL,
+			(uint8_t *)&training_rd_interval,
+			sizeof(training_rd_interval));
+	if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
+		wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
+	return wait_in_micro_secs;
+}
 
+static uint32_t get_eq_training_aux_rd_interval(
+	struct dc_link *link,
+	const struct dc_link_settings *link_settings)
+{
+	union training_aux_rd_interval training_rd_interval;
+	uint32_t wait_in_micro_secs = 400;
+
+	memset(&training_rd_interval, 0, sizeof(training_rd_interval));
 	/* overwrite the delay if rev > 1.1*/
 	if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
 		/* DP 1.2 or later - retrieve delay through
@@ -68,10 +85,10 @@ static uint32_t get_training_aux_rd_interval(
 			sizeof(training_rd_interval));
 
 		if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
-			default_wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
+			wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
 	}
 
-	return default_wait_in_micro_secs;
+	return wait_in_micro_secs;
 }
 
 static void wait_for_training_aux_rd_interval(
@@ -101,7 +118,16 @@ static void dpcd_set_training_pattern(
 		dpcd_pattern.v1_4.TRAINING_PATTERN_SET);
 }
 
-static enum dc_dp_training_pattern get_supported_tp(struct dc_link *link)
+static enum dc_dp_training_pattern decide_cr_training_pattern(
+		const struct dc_link_settings *link_settings)
+{
+	enum dc_dp_training_pattern pattern = DP_TRAINING_PATTERN_SEQUENCE_1;
+
+	return pattern;
+}
+
+static enum dc_dp_training_pattern decide_eq_training_pattern(struct dc_link *link,
+		const struct dc_link_settings *link_settings)
 {
 	enum dc_dp_training_pattern highest_tp = DP_TRAINING_PATTERN_SEQUENCE_2;
 	struct encoder_feature_support *features = &link->link_enc->features;
@@ -132,7 +158,6 @@ static void dpcd_set_link_settings(
 
 	union down_spread_ctrl downspread = { {0} };
 	union lane_count_set lane_count_set = { {0} };
-	enum dc_dp_training_pattern dp_tr_pattern;
 
 	downspread.raw = (uint8_t)
 	(lt_settings->link_settings.link_spread);
@@ -143,9 +168,8 @@ static void dpcd_set_link_settings(
 	lane_count_set.bits.ENHANCED_FRAMING = lt_settings->enhanced_framing;
 	lane_count_set.bits.POST_LT_ADJ_REQ_GRANTED = 0;
 
-	dp_tr_pattern = get_supported_tp(link);
 
-	if (dp_tr_pattern != DP_TRAINING_PATTERN_SEQUENCE_4) {
+	if (lt_settings->pattern_for_eq < DP_TRAINING_PATTERN_SEQUENCE_4) {
 		lane_count_set.bits.POST_LT_ADJ_REQ_GRANTED =
 				link->dpcd_caps.max_ln_count.bits.POST_LT_ADJ_REQ_SUPPORTED;
 	}
@@ -373,34 +397,30 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 static bool is_cr_done(enum dc_lane_count ln_count,
 	union lane_status *dpcd_lane_status)
 {
-	bool done = true;
 	uint32_t lane;
 	/*LANEx_CR_DONE bits All 1's?*/
 	for (lane = 0; lane < (uint32_t)(ln_count); lane++) {
 		if (!dpcd_lane_status[lane].bits.CR_DONE_0)
-			done = false;
+			return false;
 	}
-	return done;
-
+	return true;
 }
 
 static bool is_ch_eq_done(enum dc_lane_count ln_count,
 	union lane_status *dpcd_lane_status,
 	union lane_align_status_updated *lane_status_updated)
 {
-	bool done = true;
 	uint32_t lane;
 	if (!lane_status_updated->bits.INTERLANE_ALIGN_DONE)
-		done = false;
+		return false;
 	else {
 		for (lane = 0; lane < (uint32_t)(ln_count); lane++) {
 			if (!dpcd_lane_status[lane].bits.SYMBOL_LOCKED_0 ||
 				!dpcd_lane_status[lane].bits.CHANNEL_EQ_DONE_0)
-				done = false;
+				return false;
 		}
 	}
-	return done;
-
+	return true;
 }
 
 static void update_drive_settings(
@@ -979,7 +999,7 @@ static void start_clock_recovery_pattern_early(struct dc_link *link,
 {
 	DC_LOG_HW_LINK_TRAINING("%s\n GPU sends TPS1. Wait 400us.\n",
 			__func__);
-	dp_set_hw_training_pattern(link, DP_TRAINING_PATTERN_SEQUENCE_1, offset);
+	dp_set_hw_training_pattern(link, lt_settings->pattern_for_cr, offset);
 	dp_set_hw_lane_settings(link, lt_settings, offset);
 	udelay(400);
 }
@@ -994,7 +1014,6 @@ static enum link_training_result perform_clock_recovery_sequence(
 	uint32_t wait_time_microsec;
 	struct link_training_settings req_settings;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
-	enum dc_dp_training_pattern tr_pattern = DP_TRAINING_PATTERN_SEQUENCE_1;
 	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX];
 	union lane_align_status_updated dpcd_lane_status_updated;
 
@@ -1002,7 +1021,7 @@ static enum link_training_result perform_clock_recovery_sequence(
 	retry_count = 0;
 
 	if (!link->ctx->dc->work_arounds.lt_early_cr_pattern)
-		dp_set_hw_training_pattern(link, tr_pattern, offset);
+		dp_set_hw_training_pattern(link, lt_settings->pattern_for_cr, offset);
 
 	/* najeeb - The synaptics MST hub can put the LT in
 	* infinite loop by switching the VS
@@ -1029,7 +1048,7 @@ static enum link_training_result perform_clock_recovery_sequence(
 			dpcd_set_lt_pattern_and_lane_settings(
 					link,
 					lt_settings,
-					tr_pattern,
+					lt_settings->pattern_for_cr,
 					offset);
 		else
 			dpcd_set_lane_settings(
@@ -1113,7 +1132,7 @@ static inline enum link_training_result perform_link_training_int(
 	 * TPS4 must be used instead of POST_LT_ADJ_REQ.
 	 */
 	if (link->dpcd_caps.max_ln_count.bits.POST_LT_ADJ_REQ_SUPPORTED != 1 ||
-			get_supported_tp(link) == DP_TRAINING_PATTERN_SEQUENCE_4)
+			lt_settings->pattern_for_eq == DP_TRAINING_PATTERN_SEQUENCE_4)
 		return status;
 
 	if (status == LINK_TRAINING_SUCCESS &&
@@ -1245,17 +1264,21 @@ static void initialize_training_settings(
 	if (overrides->cr_pattern_time != NULL)
 		lt_settings->cr_pattern_time = *overrides->cr_pattern_time;
 	else
-		lt_settings->cr_pattern_time = get_training_aux_rd_interval(link, 100);
+		lt_settings->cr_pattern_time = get_cr_training_aux_rd_interval(link, link_setting);
 
 	if (overrides->eq_pattern_time != NULL)
 		lt_settings->eq_pattern_time = *overrides->eq_pattern_time;
 	else
-		lt_settings->eq_pattern_time = get_training_aux_rd_interval(link, 400);
+		lt_settings->eq_pattern_time = get_eq_training_aux_rd_interval(link, link_setting);
 
+	if (overrides->pattern_for_cr != NULL)
+		lt_settings->pattern_for_cr = *overrides->pattern_for_cr;
+	else
+		lt_settings->pattern_for_cr = decide_cr_training_pattern(link_setting);
 	if (overrides->pattern_for_eq != NULL)
 		lt_settings->pattern_for_eq = *overrides->pattern_for_eq;
 	else
-		lt_settings->pattern_for_eq = get_supported_tp(link);
+		lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_setting);
 
 	if (overrides->enhanced_framing != NULL)
 		lt_settings->enhanced_framing = *overrides->enhanced_framing;
@@ -1457,7 +1480,6 @@ bool dc_link_dp_perform_link_training_skip_aux(
 	const struct dc_link_settings *link_setting)
 {
 	struct link_training_settings lt_settings;
-	enum dc_dp_training_pattern pattern_for_cr = DP_TRAINING_PATTERN_SEQUENCE_1;
 
 	initialize_training_settings(
 			link,
@@ -1468,7 +1490,7 @@ bool dc_link_dp_perform_link_training_skip_aux(
 	/* 1. Perform_clock_recovery_sequence. */
 
 	/* transmit training pattern for clock recovery */
-	dp_set_hw_training_pattern(link, pattern_for_cr, DPRX);
+	dp_set_hw_training_pattern(link, lt_settings.pattern_for_cr, DPRX);
 
 	/* call HWSS to set lane settings*/
 	dp_set_hw_lane_settings(link, &lt_settings, DPRX);
@@ -1610,6 +1632,9 @@ bool perform_link_training_with_retries(
 
 	for (j = 0; j < attempts; ++j) {
 
+		DC_LOG_HW_LINK_TRAINING("%s: Beginning link training attempt %u of %d\n",
+			__func__, (unsigned int)j + 1, attempts);
+
 		dp_enable_link_phy(
 			link,
 			signal,
@@ -1638,6 +1663,9 @@ bool perform_link_training_with_retries(
 		if (j == (attempts - 1))
 			break;
 
+		DC_LOG_WARNING("%s: Link training attempt %u of %d failed\n",
+			__func__, (unsigned int)j + 1, attempts);
+
 		dp_disable_link_phy(link, signal);
 
 		msleep(delay_between_attempts);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
index dd88eb348dfa..11a619befb42 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
@@ -104,6 +104,12 @@ void dp_enable_link_phy(
 	struct clock_source *dp_cs =
 			link->dc->res_pool->dp_clock_source;
 	unsigned int i;
+
+	if (link->connector_signal == SIGNAL_TYPE_EDP) {
+		link->dc->hwss.edp_power_control(link, true);
+		link->dc->hwss.edp_wait_for_hpd_ready(link, true);
+	}
+
 	/* If the current pixel clock source is not DTO(happens after
 	 * switching from HDMI passive dongle to DP on the same connector),
 	 * switch the pixel clock source to DTO.
@@ -223,6 +229,8 @@ void dp_disable_link_phy(struct dc_link *link, enum signal_type signal)
 		dp_receiver_power_ctrl(link, false);
 
 	if (signal == SIGNAL_TYPE_EDP) {
+		if (link->dc->hwss.edp_backlight_control)
+			link->dc->hwss.edp_backlight_control(link, false);
 		link->link_enc->funcs->disable_output(link->link_enc, signal);
 		link->dc->hwss.edp_power_control(link, false);
 	} else {
@@ -485,13 +493,15 @@ void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 				OPTC_DSC_DISABLED, 0, 0);
 
 		/* disable DSC in stream encoder */
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
-			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_config(
-					pipe_ctx->stream_res.stream_enc,
-					OPTC_DSC_DISABLED, 0, 0);
-
-			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet(
-					pipe_ctx->stream_res.stream_enc, false, NULL);
+		if (dc_is_dp_signal(stream->signal)) {
+
+			if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+				pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_config(
+						pipe_ctx->stream_res.stream_enc,
+						OPTC_DSC_DISABLED, 0, 0);
+				pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet(
+							pipe_ctx->stream_res.stream_enc, false, NULL);
+			}
 		}
 
 		/* disable DSC block */
@@ -528,7 +538,6 @@ out:
 bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
-	struct dc *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 
 	if (!pipe_ctx->stream->timing.flags.DSC || !dsc)
@@ -551,7 +560,7 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 
 		DC_LOG_DSC(" ");
 		dsc->funcs->dsc_get_packed_pps(dsc, &dsc_cfg, &dsc_packed_pps[0]);
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+		if (dc_is_dp_signal(stream->signal)) {
 			DC_LOG_DSC("Setting stream encoder DSC PPS SDP for engine %d\n", (int)pipe_ctx->stream_res.stream_enc->id);
 			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet(
 									pipe_ctx->stream_res.stream_enc,
@@ -560,7 +569,7 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 		}
 	} else {
 		/* disable DSC PPS in stream encoder */
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+		if (dc_is_dp_signal(stream->signal)) {
 			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet(
 						pipe_ctx->stream_res.stream_enc, false, NULL);
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index c6b737dd8425..e430148e47cf 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -782,11 +782,18 @@ static void calculate_recout(struct pipe_ctx *pipe_ctx)
 
 	calculate_split_count_and_index(pipe_ctx, &split_count, &split_idx);
 
-	data->recout.x = stream->dst.x;
-	if (stream->src.x < surf_clip.x)
-		data->recout.x += (surf_clip.x - stream->src.x) * stream->dst.width
+	/*
+	 * Only the leftmost ODM pipe should be offset by a nonzero distance
+	 */
+	if (!pipe_ctx->prev_odm_pipe) {
+		data->recout.x = stream->dst.x;
+		if (stream->src.x < surf_clip.x)
+			data->recout.x += (surf_clip.x - stream->src.x) * stream->dst.width
 						/ stream->src.width;
 
+	} else
+		data->recout.x = 0;
+
 	data->recout.width = surf_clip.width * stream->dst.width / stream->src.width;
 	if (data->recout.width + data->recout.x > stream->dst.x + stream->dst.width)
 		data->recout.width = stream->dst.x + stream->dst.width - data->recout.x;
@@ -957,7 +964,7 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx)
 {
 	const struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	const struct dc_stream_state *stream = pipe_ctx->stream;
-	struct pipe_ctx *odm_pipe = pipe_ctx->prev_odm_pipe;
+	struct pipe_ctx *odm_pipe = pipe_ctx;
 	struct scaler_data *data = &pipe_ctx->plane_res.scl_data;
 	struct rect src = pipe_ctx->plane_state->src_rect;
 	int recout_skip_h, recout_skip_v, surf_size_h, surf_size_v;
@@ -988,21 +995,24 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx)
 		swap(src.width, src.height);
 	}
 
+	/*modified recout_skip_h calculation due to odm having no recout offset*/
+	while (odm_pipe->prev_odm_pipe) {
+		odm_idx++;
+		odm_pipe = odm_pipe->prev_odm_pipe;
+	}
+	/*odm_pipe is the leftmost pipe in the ODM group*/
+	recout_skip_h = odm_idx * data->recout.width;
+
 	/* Recout matching initial vp offset = recout_offset - (stream dst offset +
 	 *			((surf dst offset - stream src offset) * 1/ stream scaling ratio)
 	 *			- (surf surf_src offset * 1/ full scl ratio))
 	 */
-	recout_skip_h = data->recout.x - (stream->dst.x + (plane_state->dst_rect.x - stream->src.x)
+	recout_skip_h += odm_pipe->plane_res.scl_data.recout.x
+				- (stream->dst.x + (plane_state->dst_rect.x - stream->src.x)
 					* stream->dst.width / stream->src.width -
 					src.x * plane_state->dst_rect.width / src.width
 					* stream->dst.width / stream->src.width);
-	/*modified recout_skip_h calculation due to odm having no recout offset*/
-	while (odm_pipe) {
-		odm_idx++;
-		odm_pipe = odm_pipe->prev_odm_pipe;
-	}
-	if (odm_idx)
-		recout_skip_h += odm_idx * data->recout.width;
+
 
 	recout_skip_v = data->recout.y - (stream->dst.y + (plane_state->dst_rect.y - stream->src.y)
 					* stream->dst.height / stream->src.height -
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 f42a17d765e3..d48fd87d3b95 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -123,7 +123,6 @@ static bool dc_stream_construct(struct dc_stream_state *stream,
 		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++;
@@ -298,7 +297,7 @@ bool dc_stream_set_cursor_attributes(
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 	/* disable idle optimizations while updating cursor */
 	if (dc->idle_optimizations_allowed) {
-		dc->hwss.apply_idle_power_optimizations(dc, false);
+		dc_allow_idle_optimizations(dc, false);
 		reset_idle_optimizations = true;
 	}
 
@@ -326,7 +325,7 @@ bool dc_stream_set_cursor_attributes(
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 	/* re-enable idle optimizations if necessary */
 	if (reset_idle_optimizations)
-		dc->hwss.apply_idle_power_optimizations(dc, true);
+		dc_allow_idle_optimizations(dc, true);
 
 #endif
 	return true;
@@ -359,9 +358,8 @@ bool dc_stream_set_cursor_position(
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 
 	/* disable idle optimizations if enabling cursor */
-	if (dc->idle_optimizations_allowed &&
-			!stream->cursor_position.enable && position->enable) {
-		dc->hwss.apply_idle_power_optimizations(dc, false);
+	if (dc->idle_optimizations_allowed && !stream->cursor_position.enable && position->enable) {
+		dc_allow_idle_optimizations(dc, false);
 		reset_idle_optimizations = true;
 	}
 
@@ -392,7 +390,7 @@ bool dc_stream_set_cursor_position(
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 	/* re-enable idle optimizations if necessary */
 	if (reset_idle_optimizations)
-		dc->hwss.apply_idle_power_optimizations(dc, true);
+		dc_allow_idle_optimizations(dc, true);
 
 #endif
 	return true;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
index ea1229a3e2b2..3d7d27435f15 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
@@ -48,22 +48,17 @@ static void dc_plane_construct(struct dc_context *ctx, struct dc_plane_state *pl
 	plane_state->in_transfer_func = dc_create_transfer_func();
 	if (plane_state->in_transfer_func != NULL) {
 		plane_state->in_transfer_func->type = TF_TYPE_BYPASS;
-		plane_state->in_transfer_func->ctx = ctx;
 	}
 	plane_state->in_shaper_func = dc_create_transfer_func();
 	if (plane_state->in_shaper_func != NULL) {
 		plane_state->in_shaper_func->type = TF_TYPE_BYPASS;
-		plane_state->in_shaper_func->ctx = ctx;
 	}
 
 	plane_state->lut3d_func = dc_create_3dlut_func();
-	if (plane_state->lut3d_func != NULL) {
-		plane_state->lut3d_func->ctx = ctx;
-	}
+
 	plane_state->blend_tf = dc_create_transfer_func();
 	if (plane_state->blend_tf != NULL) {
 		plane_state->blend_tf->type = TF_TYPE_BYPASS;
-		plane_state->blend_tf->ctx = ctx;
 	}
 
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 1d9c8e09c08b..82fe0ab56e3a 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -42,7 +42,7 @@
 #include "inc/hw/dmcu.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.2.99"
+#define DC_VER "3.2.104"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -476,7 +476,7 @@ struct dc_debug_options {
 	unsigned int force_odm_combine_4to1; //bit vector based on otg inst
 #endif
 	unsigned int force_fclk_khz;
-	bool disable_tri_buf;
+	bool enable_tri_buf;
 	bool dmub_offload_enabled;
 	bool dmcub_emulation;
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
@@ -503,6 +503,7 @@ struct dc_debug_options {
 	bool usbc_combo_phy_reset_wa;
 	bool disable_dsc;
 	bool enable_dram_clock_change_one_display_vactive;
+	bool force_ignore_link_settings;
 };
 
 struct dc_debug_data {
@@ -660,6 +661,7 @@ struct dc_init_data {
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 	bool force_smu_not_present;
 #endif
+	bool force_ignore_link_settings;
 };
 
 struct dc_callback_init {
@@ -745,7 +747,6 @@ struct dc_transfer_func {
 	enum dc_transfer_func_predefined tf;
 	/* FP16 1.0 reference level in nits, default is 80 nits, only for PQ*/
 	uint32_t sdr_ref_white_level;
-	struct dc_context *ctx;
 	union {
 		struct pwl_params pwl;
 		struct dc_transfer_func_distributed_points tf_pts;
@@ -772,7 +773,6 @@ struct dc_3dlut {
 	struct tetrahedral_params lut_3d;
 	struct fixed31_32 hdr_multiplier;
 	union dc_3dlut_state state;
-	struct dc_context *ctx;
 };
 /*
  * This structure is filled in by dc_surface_get_status and contains
@@ -1250,6 +1250,9 @@ enum dc_status dc_set_clock(struct dc *dc, enum dc_clock_type clock_type, uint32
 void dc_get_clock(struct dc *dc, enum dc_clock_type clock_type, struct dc_clock_config *clock_cfg);
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 
+bool dc_is_plane_eligible_for_idle_optimizations(struct dc *dc,
+						 struct dc_plane_state *plane);
+
 void dc_allow_idle_optimizations(struct dc *dc, bool allow);
 
 /*
diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
index 0811f941f430..e146e3cba8eb 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
@@ -140,6 +140,10 @@ struct dc_vbios_funcs {
 	enum bp_result (*enable_lvtma_control)(
 		struct dc_bios *bios,
 		uint8_t uc_pwr_on);
+
+	enum bp_result (*get_soc_bb_info)(
+		struct dc_bios *dcb,
+		struct bp_soc_bb_info *soc_bb_info);
 };
 
 struct bios_registers {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index eea2429ac67d..b98754811977 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -132,3 +132,19 @@ void dc_dmub_srv_wait_phy_init(struct dc_dmub_srv *dc_dmub_srv)
 		/* Continue spinning so we don't hang the ASIC. */
 	}
 }
+
+bool dc_dmub_srv_notify_stream_mask(struct dc_dmub_srv *dc_dmub_srv,
+				    unsigned int stream_mask)
+{
+	struct dmub_srv *dmub;
+	const uint32_t timeout = 30;
+
+	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
+		return false;
+
+	dmub = dc_dmub_srv->dmub;
+
+	return dmub_srv_send_gpint_command(
+		       dmub, DMUB_GPINT__IDLE_OPT_NOTIFY_STREAM_MASK,
+		       stream_mask, timeout) == DMUB_STATUS_OK;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
index a3a09ccb6d26..bb4ab61887e4 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
@@ -56,4 +56,6 @@ void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv);
 
 void dc_dmub_srv_wait_phy_init(struct dc_dmub_srv *dc_dmub_srv);
 
+bool dc_dmub_srv_notify_stream_mask(struct dc_dmub_srv *dc_dmub_srv,
+				    unsigned int stream_mask);
 #endif /* _DMUB_DC_SRV_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index a8a3b0643505..80a2191a3115 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -123,6 +123,7 @@ struct dc_link_training_overrides {
 
 	uint16_t *cr_pattern_time;
 	uint16_t *eq_pattern_time;
+	enum dc_dp_training_pattern *pattern_for_cr;
 	enum dc_dp_training_pattern *pattern_for_eq;
 
 	enum dc_link_spread *downspread;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index e002ef706e1d..266b93a705d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -237,6 +237,8 @@ enum dc_detect_reason {
 	DETECT_REASON_BOOT,
 	DETECT_REASON_HPD,
 	DETECT_REASON_HPDRX,
+	DETECT_REASON_FALLBACK,
+	DETECT_REASON_RETRAIN
 };
 
 bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index aa8e0955db48..c47a19719de2 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -122,7 +122,7 @@ struct dc_context {
 };
 
 
-#define DC_MAX_EDID_BUFFER_SIZE 1024
+#define DC_MAX_EDID_BUFFER_SIZE 1280
 #define DC_EDID_BLOCK_SIZE 128
 #define MAX_SURFACE_NUM 4
 #define NUM_PIXEL_FORMATS 10
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 9cc65dc1970f..49ae5ff12da6 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -1149,7 +1149,8 @@ static uint32_t dcn3_get_pix_clk_dividers(
 static const struct clock_source_funcs dcn3_clk_src_funcs = {
 	.cs_power_down = dce110_clock_source_power_down,
 	.program_pix_clk = dcn3_program_pix_clk,
-	.get_pix_clk_dividers = dcn3_get_pix_clk_dividers
+	.get_pix_clk_dividers = dcn3_get_pix_clk_dividers,
+	.get_pixel_clk_frequency_100hz = get_pixel_clk_frequency_100hz
 };
 #endif
 /*****************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
index df7f826eebd8..74f7619d4154 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
@@ -159,11 +159,15 @@ static uint32_t dce_panel_cntl_hw_init(struct panel_cntl *panel_cntl)
 static bool dce_is_panel_backlight_on(struct panel_cntl *panel_cntl)
 {
 	struct dce_panel_cntl *dce_panel_cntl = TO_DCE_PANEL_CNTL(panel_cntl);
-	uint32_t value;
+	uint32_t blon, blon_ovrd, pwrseq_target_state;
 
-	REG_GET(PWRSEQ_CNTL, LVTMA_BLON, &value);
+	REG_GET_2(PWRSEQ_CNTL, LVTMA_BLON, &blon, LVTMA_BLON_OVRD, &blon_ovrd);
+	REG_GET(PWRSEQ_CNTL, LVTMA_PWRSEQ_TARGET_STATE, &pwrseq_target_state);
 
-	return value;
+	if (blon_ovrd)
+		return blon;
+	else
+		return pwrseq_target_state;
 }
 
 static bool dce_is_panel_powered_on(struct panel_cntl *panel_cntl)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h
index 99c68ca9c7e0..6bd1196083a3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h
@@ -54,15 +54,17 @@
 	SR(BL_PWM_CNTL2), \
 	SR(BL_PWM_PERIOD_CNTL), \
 	SR(BL_PWM_GRP1_REG_LOCK), \
-	SR(BIOS_SCRATCH_2)
+	NBIO_SR(BIOS_SCRATCH_2)
 
 #define DCE_PANEL_CNTL_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
 #define DCE_PANEL_CNTL_MASK_SH_LIST(mask_sh) \
 	DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_CNTL, LVTMA_BLON, mask_sh),\
+	DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_CNTL, LVTMA_BLON_OVRD, mask_sh),\
 	DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_CNTL, LVTMA_DIGON, mask_sh),\
 	DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_CNTL, LVTMA_DIGON_OVRD, mask_sh),\
+	DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_CNTL, LVTMA_PWRSEQ_TARGET_STATE, mask_sh), \
 	DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_STATE, LVTMA_PWRSEQ_TARGET_STATE_R, mask_sh), \
 	DCE_PANEL_CNTL_SF(LVTMA_PWRSEQ_REF_DIV, BL_PWM_REF_DIV, mask_sh), \
 	DCE_PANEL_CNTL_SF(BL_PWM_PERIOD_CNTL, BL_PWM_PERIOD, mask_sh), \
@@ -76,8 +78,10 @@
 
 #define DCE_PANEL_CNTL_REG_FIELD_LIST(type) \
 	type LVTMA_BLON;\
+	type LVTMA_BLON_OVRD;\
 	type LVTMA_DIGON;\
 	type LVTMA_DIGON_OVRD;\
+	type LVTMA_PWRSEQ_TARGET_STATE; \
 	type LVTMA_PWRSEQ_TARGET_STATE_R; \
 	type BL_PWM_REF_DIV; \
 	type BL_PWM_EN; \
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
index 4cdaaf4d881c..5054bb567b74 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
@@ -710,7 +710,7 @@ static void dce110_stream_encoder_lvds_set_stream_attribute(
 	ASSERT(crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB);
 }
 
-static void dce110_stream_encoder_set_mst_bandwidth(
+static void dce110_stream_encoder_set_throttled_vcp_size(
 	struct stream_encoder *enc,
 	struct fixed31_32 avg_time_slots_per_mtp)
 {
@@ -1621,8 +1621,8 @@ static const struct stream_encoder_funcs dce110_str_enc_funcs = {
 		dce110_stream_encoder_dvi_set_stream_attribute,
 	.lvds_set_stream_attribute =
 		dce110_stream_encoder_lvds_set_stream_attribute,
-	.set_mst_bandwidth =
-		dce110_stream_encoder_set_mst_bandwidth,
+	.set_throttled_vcp_size =
+		dce110_stream_encoder_set_throttled_vcp_size,
 	.update_hdmi_info_packets =
 		dce110_stream_encoder_update_hdmi_info_packets,
 	.stop_hdmi_info_packets =
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
index 5167d6b8a48d..67af67ef2865 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
@@ -119,10 +119,11 @@ static bool dmub_psr_set_version(struct dmub_psr *dmub, struct dc_stream_state *
 /**
  * Enable/Disable PSR.
  */
-static void dmub_psr_enable(struct dmub_psr *dmub, bool enable)
+static void dmub_psr_enable(struct dmub_psr *dmub, bool enable, bool wait)
 {
 	union dmub_rb_cmd cmd;
 	struct dc_context *dc = dmub->ctx;
+	uint32_t retry_count, psr_state = 0;
 
 	cmd.psr_enable.header.type = DMUB_CMD__PSR;
 
@@ -136,6 +137,30 @@ static void dmub_psr_enable(struct dmub_psr *dmub, bool enable)
 	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd);
 	dc_dmub_srv_cmd_execute(dc->dmub_srv);
 	dc_dmub_srv_wait_idle(dc->dmub_srv);
+
+	/* Below loops 1000 x 500us = 500 ms.
+	 *  Exit PSR may need to wait 1-2 frames to power up. Timeout after at
+	 *  least a few frames. Should never hit the max retry assert below.
+	 */
+	if (wait) {
+		for (retry_count = 0; retry_count <= 1000; retry_count++) {
+			dmub_psr_get_state(dmub, &psr_state);
+
+			if (enable) {
+				if (psr_state != 0)
+					break;
+			} else {
+				if (psr_state == 0)
+					break;
+			}
+
+			udelay(500);
+		}
+
+		/* assert if max retry hit */
+		if (retry_count >= 1000)
+			ASSERT(0);
+	}
 }
 
 /**
@@ -231,10 +256,11 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub,
 	copy_settings_data->smu_optimizations_en		= psr_context->allow_smu_optimizations;
 	copy_settings_data->frame_delay				= psr_context->frame_delay;
 	copy_settings_data->frame_cap_ind			= psr_context->psrFrameCaptureIndicationReq;
+	copy_settings_data->init_sdp_deadline			= psr_context->sdpTransmitLineNumDeadline;
+	copy_settings_data->debug.u32All = 0;
 	copy_settings_data->debug.bitfields.visual_confirm	= dc->dc->debug.visual_confirm == VISUAL_CONFIRM_PSR ?
 									true : false;
-	copy_settings_data->debug.bitfields.use_hw_lock_mgr	= 1;
-	copy_settings_data->init_sdp_deadline			= psr_context->sdpTransmitLineNumDeadline;
+	copy_settings_data->debug.bitfields.use_hw_lock_mgr		= 1;
 
 	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd);
 	dc_dmub_srv_cmd_execute(dc->dmub_srv);
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h
index f404fecd6410..dc121ed92d2e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h
@@ -36,7 +36,7 @@ struct dmub_psr {
 
 struct dmub_psr_funcs {
 	bool (*psr_copy_settings)(struct dmub_psr *dmub, struct dc_link *link, struct psr_context *psr_context);
-	void (*psr_enable)(struct dmub_psr *dmub, bool enable);
+	void (*psr_enable)(struct dmub_psr *dmub, bool enable, bool wait);
 	void (*psr_get_state)(struct dmub_psr *dmub, uint32_t *psr_state);
 	void (*psr_set_level)(struct dmub_psr *dmub, uint16_t psr_level);
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 0603ddca7bd0..3ac6c7b65a45 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -810,37 +810,66 @@ void dce110_edp_power_control(
 
 	if (power_up !=
 		link->panel_cntl->funcs->is_panel_powered_on(link->panel_cntl)) {
+
+		unsigned long long current_ts = dm_get_timestamp(ctx);
+		unsigned long long time_since_edp_poweroff_ms =
+				div64_u64(dm_get_elapse_time_in_ns(
+						ctx,
+						current_ts,
+						link->link_trace.time_stamp.edp_poweroff), 1000000);
+		unsigned long long time_since_edp_poweron_ms =
+				div64_u64(dm_get_elapse_time_in_ns(
+						ctx,
+						current_ts,
+						link->link_trace.time_stamp.edp_poweron), 1000000);
+		DC_LOG_HW_RESUME_S3(
+				"%s: transition: power_up=%d current_ts=%llu edp_poweroff=%llu edp_poweron=%llu time_since_edp_poweroff_ms=%llu time_since_edp_poweron_ms=%llu",
+				__func__,
+				power_up,
+				current_ts,
+				link->link_trace.time_stamp.edp_poweroff,
+				link->link_trace.time_stamp.edp_poweron,
+				time_since_edp_poweroff_ms,
+				time_since_edp_poweron_ms);
+
 		/* Send VBIOS command to prompt eDP panel power */
 		if (power_up) {
-			unsigned long long current_ts = dm_get_timestamp(ctx);
-			unsigned long long duration_in_ms =
-					div64_u64(dm_get_elapse_time_in_ns(
-							ctx,
-							current_ts,
-							link->link_trace.time_stamp.edp_poweroff), 1000000);
-			unsigned long long wait_time_ms = 0;
-
-			/* max 500ms from LCDVDD off to on */
-			unsigned long long edp_poweroff_time_ms = 500;
+			/* edp requires a min of 500ms from LCDVDD off to on */
+			unsigned long long remaining_min_edp_poweroff_time_ms = 500;
 
+			/* add time defined by a patch, if any (usually patch extra_t12_ms is 0) */
 			if (link->local_sink != NULL)
-				edp_poweroff_time_ms =
-						500 + link->local_sink->edid_caps.panel_patch.extra_t12_ms;
-			if (link->link_trace.time_stamp.edp_poweroff == 0)
-				wait_time_ms = edp_poweroff_time_ms;
-			else if (duration_in_ms < edp_poweroff_time_ms)
-				wait_time_ms = edp_poweroff_time_ms - duration_in_ms;
-
-			if (wait_time_ms) {
-				msleep(wait_time_ms);
-				dm_output_to_console("%s: wait %lld ms to power on eDP.\n",
-						__func__, wait_time_ms);
+				remaining_min_edp_poweroff_time_ms +=
+					link->local_sink->edid_caps.panel_patch.extra_t12_ms;
+
+			/* Adjust remaining_min_edp_poweroff_time_ms if this is not the first time. */
+			if (link->link_trace.time_stamp.edp_poweroff != 0) {
+				if (time_since_edp_poweroff_ms < remaining_min_edp_poweroff_time_ms)
+					remaining_min_edp_poweroff_time_ms =
+						remaining_min_edp_poweroff_time_ms - time_since_edp_poweroff_ms;
+				else
+					remaining_min_edp_poweroff_time_ms = 0;
 			}
 
+			if (remaining_min_edp_poweroff_time_ms) {
+				DC_LOG_HW_RESUME_S3(
+						"%s: remaining_min_edp_poweroff_time_ms=%llu: begin wait.\n",
+						__func__, remaining_min_edp_poweroff_time_ms);
+				msleep(remaining_min_edp_poweroff_time_ms);
+				DC_LOG_HW_RESUME_S3(
+						"%s: remaining_min_edp_poweroff_time_ms=%llu: end wait.\n",
+						__func__, remaining_min_edp_poweroff_time_ms);
+				dm_output_to_console("%s: wait %lld ms to power on eDP.\n",
+						__func__, remaining_min_edp_poweroff_time_ms);
+			} else {
+				DC_LOG_HW_RESUME_S3(
+						"%s: remaining_min_edp_poweroff_time_ms=%llu: no wait required.\n",
+						__func__, remaining_min_edp_poweroff_time_ms);
+			}
 		}
 
 		DC_LOG_HW_RESUME_S3(
-				"%s: Panel Power action: %s\n",
+				"%s: BEGIN: Panel Power action: %s\n",
 				__func__, (power_up ? "On":"Off"));
 
 		cntl.action = power_up ?
@@ -864,12 +893,23 @@ void dce110_edp_power_control(
 
 		bp_result = link_transmitter_control(ctx->dc_bios, &cntl);
 
+		DC_LOG_HW_RESUME_S3(
+				"%s: END: Panel Power action: %s bp_result=%u\n",
+				__func__, (power_up ? "On":"Off"),
+				bp_result);
+
 		if (!power_up)
 			/*save driver power off time stamp*/
 			link->link_trace.time_stamp.edp_poweroff = dm_get_timestamp(ctx);
 		else
 			link->link_trace.time_stamp.edp_poweron = dm_get_timestamp(ctx);
 
+		DC_LOG_HW_RESUME_S3(
+				"%s: updated values: edp_poweroff=%llu edp_poweron=%llu\n",
+				__func__,
+				link->link_trace.time_stamp.edp_poweroff,
+				link->link_trace.time_stamp.edp_poweron);
+
 		if (bp_result != BP_RESULT_OK)
 			DC_LOG_ERROR(
 					"%s: Panel Power bp_result: %d\n",
@@ -1614,7 +1654,7 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context)
 		// enable fastboot if backend is enabled on eDP
 		if (edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc)) {
 			/* Set optimization flag on eDP stream*/
-			if (edp_stream) {
+			if (edp_stream && edp_link->link_status.link_active) {
 				edp_stream->apply_edp_fast_boot_optimization = true;
 				can_apply_edp_fast_boot = true;
 			}
@@ -2697,7 +2737,7 @@ static void program_output_csc(struct dc *dc,
 	}
 }
 
-void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx)
+static void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position;
 	struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp;
@@ -2742,7 +2782,7 @@ void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx)
 		mi->funcs->set_cursor_position(mi, &pos_cpy, &param);
 }
 
-void dce110_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
+static void dce110_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_cursor_attributes *attributes = &pipe_ctx->stream->cursor_attributes;
 
@@ -2850,6 +2890,7 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.setup_stereo = NULL,
 	.set_avmute = dce110_set_avmute,
 	.wait_for_mpcc_disconnect = dce110_wait_for_mpcc_disconnect,
+	.edp_backlight_control = dce110_edp_backlight_control,
 	.edp_power_control = dce110_edp_power_control,
 	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
 	.set_cursor_position = dce110_set_cursor_position,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
index 47a39eb9400b..7a00fe525dfb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
@@ -325,8 +325,6 @@ bool cm_helper_translate_curve_to_hw_format(
 	if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS)
 		return false;
 
-	PERF_TRACE_CTX(output_tf->ctx);
-
 	corner_points = lut_params->corner_points;
 	rgb_resulted = lut_params->rgb_resulted;
 	hw_points = 0;
@@ -524,8 +522,6 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 	if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS)
 		return false;
 
-	PERF_TRACE_CTX(output_tf->ctx);
-
 	corner_points = lut_params->corner_points;
 	rgb_resulted = lut_params->rgb_resulted;
 	hw_points = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index cedf359a00f5..db5615a51fea 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -734,6 +734,9 @@ bool hubp1_is_flip_pending(struct hubp *hubp)
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
 	struct dc_plane_address earliest_inuse_address;
 
+	if (hubp && hubp->power_gated)
+		return false;
+
 	REG_GET(DCSURF_FLIP_CONTROL,
 			SURFACE_FLIP_PENDING, &flip_pending);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 8ca94f506195..d0f3bf953d02 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2765,7 +2765,7 @@ bool dcn10_disconnect_pipes(
 		struct dc *dc,
 		struct dc_state *context)
 {
-		bool found_stream = false;
+		bool found_pipe = false;
 		int i, j;
 		struct dce_hwseq *hws = dc->hwseq;
 		struct dc_state *old_ctx = dc->current_state;
@@ -2805,26 +2805,28 @@ bool dcn10_disconnect_pipes(
 					old_ctx->res_ctx.pipe_ctx[i].top_pipe) {
 
 					/* Find the top pipe in the new ctx for the bottom pipe that we
-					 * want to remove by comparing the streams. If both pipes are being
-					 * disabled then do it in the regular pipe programming sequence
+					 * want to remove by comparing the streams and planes. If both
+					 * pipes are being disabled then do it in the regular pipe
+					 * programming sequence
 					 */
 					for (j = 0; j < dc->res_pool->pipe_count; j++) {
 						if (old_ctx->res_ctx.pipe_ctx[i].top_pipe->stream == context->res_ctx.pipe_ctx[j].stream &&
+							old_ctx->res_ctx.pipe_ctx[i].top_pipe->plane_state == context->res_ctx.pipe_ctx[j].plane_state &&
 							!context->res_ctx.pipe_ctx[j].top_pipe &&
 							!context->res_ctx.pipe_ctx[j].update_flags.bits.disable) {
-							found_stream = true;
+							found_pipe = true;
 							break;
 						}
 					}
 
 					// Disconnect if the top pipe lost it's pipe split
-					if (found_stream && !context->res_ctx.pipe_ctx[j].bottom_pipe) {
+					if (found_pipe && !context->res_ctx.pipe_ctx[j].bottom_pipe) {
 						hws->funcs.plane_atomic_disconnect(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
 						DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx);
 						mpcc_disconnected = true;
 					}
 				}
-				found_stream = false;
+				found_pipe = false;
 			}
 		}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
index a1d1559bb5d7..b24c8ae8b1ec 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
@@ -66,6 +66,7 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.get_hw_state = dcn10_get_hw_state,
 	.clear_status_bits = dcn10_clear_status_bits,
 	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_backlight_control = dce110_edp_backlight_control,
 	.edp_power_control = dce110_edp_power_control,
 	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
 	.set_cursor_position = dcn10_set_cursor_position,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index 2972392f9788..800be2693fac 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -288,6 +288,17 @@ void optc1_program_timing(
 	if (optc1_is_two_pixels_per_containter(&patched_crtc_timing) || optc1->opp_count == 2)
 		h_div = H_TIMING_DIV_BY2;
 
+	if (REG(OPTC_DATA_FORMAT_CONTROL)) {
+		uint32_t data_fmt = 0;
+
+		if (patched_crtc_timing.pixel_encoding == PIXEL_ENCODING_YCBCR422)
+			data_fmt = 1;
+		else if (patched_crtc_timing.pixel_encoding == PIXEL_ENCODING_YCBCR420)
+			data_fmt = 2;
+
+		REG_UPDATE(OPTC_DATA_FORMAT_CONTROL, OPTC_DATA_FORMAT, data_fmt);
+	}
+
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 	if (optc1->tg_mask->OTG_H_TIMING_DIV_MODE != 0) {
 		if (optc1->opp_count == 4)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 1abd81e17f09..a78712caf124 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -798,7 +798,7 @@ static const struct encoder_feature_support link_enc_feature = {
 		.max_hdmi_deep_color = COLOR_DEPTH_121212,
 		.max_hdmi_pixel_clock = 600000,
 		.hdmi_ycbcr420_supported = true,
-		.dp_ycbcr420_supported = false,
+		.dp_ycbcr420_supported = true,
 		.flags.bits.IS_HBR2_CAPABLE = true,
 		.flags.bits.IS_HBR3_CAPABLE = true,
 		.flags.bits.IS_TPS3_CAPABLE = true,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index 842abb4c475b..f70fcadf1ee5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -619,7 +619,7 @@ void enc1_stream_encoder_dvi_set_stream_attribute(
 	enc1_stream_encoder_set_stream_attribute_helper(enc1, crtc_timing);
 }
 
-void enc1_stream_encoder_set_mst_bandwidth(
+void enc1_stream_encoder_set_throttled_vcp_size(
 	struct stream_encoder *enc,
 	struct fixed31_32 avg_time_slots_per_mtp)
 {
@@ -896,10 +896,10 @@ void enc1_stream_encoder_dp_blank(
 	 */
 	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_DIS_DEFER, 2);
 	/* Larger delay to wait until VBLANK - use max retry of
-	 * 10us*5000=50ms. This covers 41.7ms of minimum 24 Hz mode +
+	 * 10us*10200=102ms. This covers 100.0ms of minimum 10 Hz mode +
 	 * a little more because we may not trust delay accuracy.
 	 */
-	max_retries = DP_BLANK_MAX_RETRY * 250;
+	max_retries = DP_BLANK_MAX_RETRY * 501;
 
 	/* disable DP stream */
 	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, 0);
@@ -1616,8 +1616,8 @@ static const struct stream_encoder_funcs dcn10_str_enc_funcs = {
 		enc1_stream_encoder_hdmi_set_stream_attribute,
 	.dvi_set_stream_attribute =
 		enc1_stream_encoder_dvi_set_stream_attribute,
-	.set_mst_bandwidth =
-		enc1_stream_encoder_set_mst_bandwidth,
+	.set_throttled_vcp_size =
+		enc1_stream_encoder_set_throttled_vcp_size,
 	.update_hdmi_info_packets =
 		enc1_stream_encoder_update_hdmi_info_packets,
 	.stop_hdmi_info_packets =
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
index 30eae7459d50..b99d2527cf03 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
@@ -588,7 +588,7 @@ void enc1_stream_encoder_dvi_set_stream_attribute(
 	struct dc_crtc_timing *crtc_timing,
 	bool is_dual_link);
 
-void enc1_stream_encoder_set_mst_bandwidth(
+void enc1_stream_encoder_set_throttled_vcp_size(
 	struct stream_encoder *enc,
 	struct fixed31_32 avg_time_slots_per_mtp);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index bb920d0e0b89..368818d2dfc6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -908,6 +908,9 @@ bool hubp2_is_flip_pending(struct hubp *hubp)
 	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
 	struct dc_plane_address earliest_inuse_address;
 
+	if (hubp && hubp->power_gated)
+		return false;
+
 	REG_GET(DCSURF_FLIP_CONTROL,
 			SURFACE_FLIP_PENDING, &flip_pending);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index c8cfd3ba1c15..01530e686f43 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1251,6 +1251,11 @@ static void dcn20_detect_pipe_changes(struct pipe_ctx *old_pipe, struct pipe_ctx
 		return;
 	}
 
+	/* Detect plane change */
+	if (old_pipe->plane_state != new_pipe->plane_state) {
+		new_pipe->update_flags.bits.plane_changed = true;
+	}
+
 	/* Detect top pipe only changes */
 	if (!new_pipe->top_pipe && !new_pipe->prev_odm_pipe) {
 		/* Detect odm changes */
@@ -1392,6 +1397,7 @@ static void dcn20_update_dchubp_dpp(
 			&pipe_ctx->ttu_regs);
 
 	if (pipe_ctx->update_flags.bits.enable ||
+			pipe_ctx->update_flags.bits.plane_changed ||
 			plane_state->update_flags.bits.bpp_change ||
 			plane_state->update_flags.bits.input_csc_change ||
 			plane_state->update_flags.bits.color_space_change ||
@@ -1414,6 +1420,7 @@ static void dcn20_update_dchubp_dpp(
 	}
 
 	if (pipe_ctx->update_flags.bits.mpcc
+			|| pipe_ctx->update_flags.bits.plane_changed
 			|| plane_state->update_flags.bits.global_alpha_change
 			|| plane_state->update_flags.bits.per_pixel_alpha_change) {
 		// MPCC inst is equal to pipe index in practice
@@ -1515,6 +1522,7 @@ static void dcn20_update_dchubp_dpp(
 	}
 
 	if (pipe_ctx->update_flags.bits.enable ||
+			pipe_ctx->update_flags.bits.plane_changed ||
 			pipe_ctx->update_flags.bits.opp_changed ||
 			plane_state->update_flags.bits.pixel_format_change ||
 			plane_state->update_flags.bits.horizontal_mirror_change ||
@@ -1539,7 +1547,9 @@ static void dcn20_update_dchubp_dpp(
 		hubp->power_gated = false;
 	}
 
-	if (pipe_ctx->update_flags.bits.enable || plane_state->update_flags.bits.addr_update)
+	if (pipe_ctx->update_flags.bits.enable ||
+		pipe_ctx->update_flags.bits.plane_changed ||
+		plane_state->update_flags.bits.addr_update)
 		hws->funcs.update_plane_addr(dc, pipe_ctx);
 
 
@@ -1632,16 +1642,26 @@ void dcn20_program_front_end_for_ctx(
 	struct dce_hwseq *hws = dc->hwseq;
 	DC_LOGGER_INIT(dc->ctx->logger);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+	/* Carry over GSL groups in case the context is changing. */
+       for (i = 0; i < dc->res_pool->pipe_count; i++) {
+               struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+               struct pipe_ctx *old_pipe_ctx =
+                       &dc->current_state->res_ctx.pipe_ctx[i];
+
+               if (pipe_ctx->stream == old_pipe_ctx->stream)
+                       pipe_ctx->stream_res.gsl_group =
+                               old_pipe_ctx->stream_res.gsl_group;
+       }
+
+	if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) {
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
-		if (!pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe && pipe_ctx->plane_state) {
-			ASSERT(!pipe_ctx->plane_state->triplebuffer_flips);
-			if (dc->hwss.program_triplebuffer != NULL &&
-				!dc->debug.disable_tri_buf) {
+			if (!pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe && pipe_ctx->plane_state) {
+				ASSERT(!pipe_ctx->plane_state->triplebuffer_flips);
 				/*turn off triple buffer for full update*/
 				dc->hwss.program_triplebuffer(
-					dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips);
+						dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips);
 			}
 		}
 	}
@@ -1909,9 +1929,9 @@ void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	if (pipe_ctx->stream_res.dsc) {
 		struct pipe_ctx *odm_pipe = pipe_ctx->next_odm_pipe;
 
-		dcn20_dsc_pg_control(hws, pipe_ctx->stream_res.dsc->inst, true);
+		hws->funcs.dsc_pg_control(hws, pipe_ctx->stream_res.dsc->inst, true);
 		while (odm_pipe) {
-			dcn20_dsc_pg_control(hws, odm_pipe->stream_res.dsc->inst, true);
+			hws->funcs.dsc_pg_control(hws, odm_pipe->stream_res.dsc->inst, true);
 			odm_pipe = odm_pipe->next_odm_pipe;
 		}
 	}
@@ -1924,9 +1944,9 @@ void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	if (pipe_ctx->stream_res.dsc) {
 		struct pipe_ctx *odm_pipe = pipe_ctx->next_odm_pipe;
 
-		dcn20_dsc_pg_control(hws, pipe_ctx->stream_res.dsc->inst, false);
+		hws->funcs.dsc_pg_control(hws, pipe_ctx->stream_res.dsc->inst, false);
 		while (odm_pipe) {
-			dcn20_dsc_pg_control(hws, odm_pipe->stream_res.dsc->inst, false);
+			hws->funcs.dsc_pg_control(hws, odm_pipe->stream_res.dsc->inst, false);
 			odm_pipe = odm_pipe->next_odm_pipe;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
index 966e1790b9bf..072193c5ffe6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
@@ -68,6 +68,7 @@ static const struct hw_sequencer_funcs dcn20_funcs = {
 	.get_hw_state = dcn10_get_hw_state,
 	.clear_status_bits = dcn10_clear_status_bits,
 	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_backlight_control = dce110_edp_backlight_control,
 	.edp_power_control = dce110_edp_power_control,
 	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
 	.set_cursor_position = dcn10_set_cursor_position,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
index 8c16967fe018..d8b18c515d06 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
@@ -239,7 +239,6 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c
 	int mpcc_hactive = (timing->h_addressable + timing->h_border_left + timing->h_border_right)
 			/ opp_cnt;
 	uint32_t memory_mask;
-	uint32_t data_fmt = 0;
 
 	ASSERT(opp_cnt == 2);
 
@@ -262,13 +261,6 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c
 		REG_SET(OPTC_MEMORY_CONFIG, 0,
 			OPTC_MEM_SEL, memory_mask);
 
-	if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
-		data_fmt = 1;
-	else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
-		data_fmt = 2;
-
-	REG_UPDATE(OPTC_DATA_FORMAT_CONTROL, OPTC_DATA_FORMAT, data_fmt);
-
 	REG_SET_3(OPTC_DATA_SOURCE_SELECT, 0,
 			OPTC_NUM_OF_INPUT_SEGMENT, 1,
 			OPTC_SEG0_SRC_SEL, opp_id[0],
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 1b9874445134..d50a9c370637 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -150,7 +150,6 @@ struct _vcs_dpi_ip_params_st dcn2_0_ip = {
 	.dispclk_delay_subtotal = 87, //
 	.dcfclk_cstate_latency = 10, // SRExitTime
 	.max_inter_dcn_tile_repeaters = 8,
-
 	.xfc_supported = true,
 	.xfc_fill_bw_overhead_percent = 10.0,
 	.xfc_fill_constant_bytes = 0,
@@ -298,8 +297,8 @@ static struct _vcs_dpi_soc_bounding_box_st dcn2_0_soc = {
 			},
 		},
 	.num_states = 5,
-	.sr_exit_time_us = 8.6,
-	.sr_enter_plus_exit_time_us = 10.9,
+	.sr_exit_time_us = 11.6,
+	.sr_enter_plus_exit_time_us = 13.9,
 	.urgent_latency_us = 4.0,
 	.urgent_latency_pixel_data_only_us = 4.0,
 	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
@@ -409,8 +408,8 @@ static struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = {
 			},
 		},
 	.num_states = 5,
-	.sr_exit_time_us = 8.6,
-	.sr_enter_plus_exit_time_us = 10.9,
+	.sr_exit_time_us = 11.6,
+	.sr_enter_plus_exit_time_us = 13.9,
 	.urgent_latency_us = 4.0,
 	.urgent_latency_pixel_data_only_us = 4.0,
 	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
@@ -1075,7 +1074,6 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.disable_pplib_wm_range = false,
 		.scl_reset_length10 = true,
 		.sanity_checks = false,
-		.disable_tri_buf = true,
 		.underflow_assert_delay_us = 0xFFFFFFFF,
 };
 
@@ -1092,6 +1090,7 @@ static const struct dc_debug_options debug_defaults_diags = {
 		.disable_stutter = true,
 		.scl_reset_length10 = true,
 		.underflow_assert_delay_us = 0xFFFFFFFF,
+		.enable_tri_buf = true,
 };
 
 void dcn20_dpp_destroy(struct dpp **dpp)
@@ -2203,9 +2202,9 @@ int dcn20_populate_dml_pipes_from_context(
 		/* todo: default max for now, until there is logic reflecting this in dc*/
 		pipes[pipe_cnt].dout.output_bpc = 12;
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
-		/*fill up the audio sample rate*/
+		/*fill up the audio sample rate (unit in kHz)*/
 		get_audio_check(&res_ctx->pipe_ctx[i].stream->audio_info, &aud_check);
-		pipes[pipe_cnt].dout.max_audio_sample_rate = aud_check.max_audiosample_rate;
+		pipes[pipe_cnt].dout.max_audio_sample_rate = aud_check.max_audiosample_rate / 1000;
 #endif
 		/*
 		 * For graphic plane, cursor number is 1, nv12 is 0
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
index e3984f02b7b3..4075ae111530 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
@@ -561,8 +561,8 @@ static const struct stream_encoder_funcs dcn20_str_enc_funcs = {
 		enc1_stream_encoder_hdmi_set_stream_attribute,
 	.dvi_set_stream_attribute =
 		enc1_stream_encoder_dvi_set_stream_attribute,
-	.set_mst_bandwidth =
-		enc1_stream_encoder_set_mst_bandwidth,
+	.set_throttled_vcp_size =
+		enc1_stream_encoder_set_throttled_vcp_size,
 	.update_hdmi_info_packets =
 		enc2_stream_encoder_update_hdmi_info_packets,
 	.stop_hdmi_info_packets =
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
index 2ba880c3943c..2b7396c9fcb4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
@@ -69,6 +69,7 @@ static const struct hw_sequencer_funcs dcn21_funcs = {
 	.get_hw_state = dcn10_get_hw_state,
 	.clear_status_bits = dcn10_clear_status_bits,
 	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_backlight_control = dce110_edp_backlight_control,
 	.edp_power_control = dce110_edp_power_control,
 	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
 	.set_cursor_position = dcn10_set_cursor_position,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index 78743ae37851..e73785e74cba 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -894,6 +894,8 @@ static const struct dc_debug_options debug_defaults_diags = {
 		.disable_pplib_wm_range = true,
 		.disable_stutter = true,
 		.disable_48mhz_pwrdwn = true,
+		.disable_psr = true,
+		.enable_tri_buf = true
 };
 
 enum dcn20_clk_src_array_id {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
index 025637a83c3b..bd2a068f9863 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
@@ -31,9 +31,21 @@ DCN30 = dcn30_init.o dcn30_hubbub.o dcn30_hubp.o dcn30_dpp.o dcn30_optc.o \
 	dcn30_dio_link_encoder.o dcn30_resource.o
 
 
-CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse -mpreferred-stack-boundary=4
-
+ifdef CONFIG_X86
 CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -msse
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -maltivec
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -maltivec
+endif
+
+ifdef CONFIG_ARM64
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mgeneral-regs-only
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mgeneral-regs-only
+endif
+
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
@@ -45,8 +57,10 @@ ifdef IS_OLD_GCC
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
 # (8B stack alignment).
 CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -mpreferred-stack-boundary=4
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -mpreferred-stack-boundary=4
 else
 CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -msse2
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -msse2
 endif
 
 AMD_DAL_DCN30 = $(addprefix $(AMDDALPATH)/dc/dcn30/,$(DCN30))
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
index a139a87a1a81..41a1d0e9b7e2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c
@@ -122,8 +122,6 @@ bool cm3_helper_translate_curve_to_hw_format(
 	if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS)
 		return false;
 
-	PERF_TRACE_CTX(output_tf->ctx);
-
 	corner_points = lut_params->corner_points;
 	rgb_resulted = lut_params->rgb_resulted;
 	hw_points = 0;
@@ -314,8 +312,6 @@ bool cm3_helper_translate_curve_to_degamma_hw_format(
 	if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS)
 		return false;
 
-	PERF_TRACE_CTX(output_tf->ctx);
-
 	corner_points = lut_params->corner_points;
 	rgb_resulted = lut_params->rgb_resulted;
 	hw_points = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c
index f5e80a0db72b..6c0f7ef0a3df 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c
@@ -790,8 +790,8 @@ static const struct stream_encoder_funcs dcn30_str_enc_funcs = {
 		enc3_stream_encoder_hdmi_set_stream_attribute,
 	.dvi_set_stream_attribute =
 		enc3_stream_encoder_dvi_set_stream_attribute,
-	.set_mst_bandwidth =
-		enc1_stream_encoder_set_mst_bandwidth,
+	.set_throttled_vcp_size =
+		enc1_stream_encoder_set_throttled_vcp_size,
 	.update_hdmi_info_packets =
 		enc3_stream_encoder_update_hdmi_info_packets,
 	.stop_hdmi_info_packets =
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index a5d750ed569e..204773ffc376 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -35,7 +35,6 @@
 #include "dcn30_dpp.h"
 #include "dcn10/dcn10_cm_common.h"
 #include "dcn30_cm_common.h"
-#include "clk_mgr.h"
 #include "reg_helper.h"
 #include "abm.h"
 #include "clk_mgr.h"
@@ -220,15 +219,13 @@ static void dcn30_set_writeback(
 		struct dc_writeback_info *wb_info,
 		struct dc_state *context)
 {
-	struct dwbc *dwb;
 	struct mcif_wb *mcif_wb;
 	struct mcif_buf_params *mcif_buf_params;
 
 	ASSERT(wb_info->dwb_pipe_inst < MAX_DWB_PIPES);
 	ASSERT(wb_info->wb_enabled);
 	ASSERT(wb_info->mpcc_inst >= 0);
-	ASSERT(wb_info->mpcc_inst < 4);
-	dwb = dc->res_pool->dwbc[wb_info->dwb_pipe_inst];
+	ASSERT(wb_info->mpcc_inst < dc->res_pool->mpcc_count);
 	mcif_wb = dc->res_pool->mcif_wb[wb_info->dwb_pipe_inst];
 	mcif_buf_params = &wb_info->mcif_buf_params;
 
@@ -692,26 +689,23 @@ void dcn30_program_dmdata_engine(struct pipe_ctx *pipe_ctx)
 
 bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable)
 {
-	unsigned int surface_size;
-
 	if (!dc->ctx->dmub_srv)
 		return false;
 
 	if (enable) {
-		if (dc->current_state
-				&& dc->current_state->stream_count == 1 // single display only
-				&& dc->current_state->stream_status[0].plane_count == 1 // single surface only
-				&& dc->current_state->stream_status[0].plane_states[0]->address.page_table_base.quad_part == 0 // no VM
-				// Only 8 and 16 bit formats
-				&& dc->current_state->stream_status[0].plane_states[0]->format <= SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F
-				&& dc->current_state->stream_status[0].plane_states[0]->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB8888) {
-
-			surface_size = dc->current_state->stream_status[0].plane_states[0]->plane_size.surface_pitch *
-					dc->current_state->stream_status[0].plane_states[0]->plane_size.surface_size.height *
-					(dc->current_state->stream_status[0].plane_states[0]->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4);
-
+		if (dc->current_state) {
+			int i;
+
+			/* First, check no-memory-requests case */
+			for (i = 0; i < dc->current_state->stream_count; i++) {
+				if (dc->current_state->stream_status[i]
+					    .plane_count)
+					/* Fail eligibility on a visible stream */
+					break;
+			}
 		}
 
+		/* No applicable optimizations */
 		return false;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
index 19daa456e3bf..7c90c2222506 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
@@ -69,6 +69,7 @@ static const struct hw_sequencer_funcs dcn30_funcs = {
 	.get_hw_state = dcn10_get_hw_state,
 	.clear_status_bits = dcn10_clear_status_bits,
 	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_backlight_control = dce110_edp_backlight_control,
 	.edp_power_control = dce110_edp_power_control,
 	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
 	.set_cursor_position = dcn10_set_cursor_position,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c
index 224c8d145eba..b1f228fc119a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c
@@ -179,8 +179,7 @@ void optc3_set_dsc_config(struct timing_generator *optc,
 
 }
 
-
-static void optc3_set_odm_bypass(struct timing_generator *optc,
+void optc3_set_odm_bypass(struct timing_generator *optc,
 		const struct dc_crtc_timing *dc_crtc_timing)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
@@ -210,7 +209,6 @@ static void optc3_set_odm_combine(struct timing_generator *optc, int *opp_id, in
 	int mpcc_hactive = (timing->h_addressable + timing->h_border_left + timing->h_border_right)
 			/ opp_cnt;
 	uint32_t memory_mask = 0;
-	uint32_t data_fmt = 0;
 
 	/* TODO: In pseudocode but does not affect maximus, delete comment if we dont need on asic
 	 * REG_SET(OTG_GLOBAL_CONTROL2, 0, GLOBAL_UPDATE_LOCK_EN, 1);
@@ -241,13 +239,6 @@ static void optc3_set_odm_combine(struct timing_generator *optc, int *opp_id, in
 		REG_SET(OPTC_MEMORY_CONFIG, 0,
 			OPTC_MEM_SEL, memory_mask);
 
-	if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
-		data_fmt = 1;
-	else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
-		data_fmt = 2;
-
-	REG_UPDATE(OPTC_DATA_FORMAT_CONTROL, OPTC_DATA_FORMAT, data_fmt);
-
 	if (opp_cnt == 2) {
 		REG_SET_3(OPTC_DATA_SOURCE_SELECT, 0,
 				OPTC_NUM_OF_INPUT_SEGMENT, 1,
@@ -277,7 +268,7 @@ static void optc3_set_odm_combine(struct timing_generator *optc, int *opp_id, in
  *
  * Options: any time,  start of frame, dp start of frame (range timing)
  */
-void optc3_set_timing_double_buffer(struct timing_generator *optc, bool enable)
+static void optc3_set_timing_double_buffer(struct timing_generator *optc, bool enable)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 	uint32_t mode = enable ? 2 : 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.h
index 33f13c1e7520..379616831636 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.h
@@ -339,4 +339,8 @@ void optc3_set_dsc_config(struct timing_generator *optc,
 
 void optc3_set_timing_db_mode(struct timing_generator *optc, bool enable);
 
+void optc3_set_odm_bypass(struct timing_generator *optc,
+		const struct dc_crtc_timing *dc_crtc_timing);
+void optc3_tg_init(struct timing_generator *optc);
+
 #endif /* __DC_OPTC_DCN30_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index 8be4f21169d0..2455d210ccf6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -79,6 +79,7 @@
 
 #include "reg_helper.h"
 #include "dce/dmub_abm.h"
+#include "dce/dmub_psr.h"
 #include "dce/dce_aux.h"
 #include "dce/dce_i2c.h"
 
@@ -832,7 +833,7 @@ static const struct dc_plane_cap plane_cap = {
 };
 
 static const struct dc_debug_options debug_defaults_drv = {
-	.disable_dmcu = true,
+	.disable_dmcu = true, //No DMCU on DCN30
 	.force_abm_enable = false,
 	.timing_trace = false,
 	.clock_trace = true,
@@ -849,10 +850,11 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.underflow_assert_delay_us = 0xFFFFFFFF,
 	.dwb_fi_phase = -1, // -1 = disable,
 	.dmub_command_table = true,
+	.disable_psr = false,
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
-	.disable_dmcu = true,
+	.disable_dmcu = true, //No dmcu on DCN30
 	.force_abm_enable = false,
 	.timing_trace = true,
 	.clock_trace = true,
@@ -865,6 +867,8 @@ static const struct dc_debug_options debug_defaults_diags = {
 	.scl_reset_length10 = true,
 	.dwb_fi_phase = -1, // -1 = disable
 	.dmub_command_table = true,
+	.disable_psr = true,
+	.enable_tri_buf = true,
 };
 
 void dcn30_dpp_destroy(struct dpp **dpp)
@@ -1312,6 +1316,9 @@ static void dcn30_resource_destruct(struct dcn30_resource_pool *pool)
 			dce_abm_destroy(&pool->base.multiple_abms[i]);
 	}
 
+	if (pool->base.psr != NULL)
+		dmub_psr_destroy(&pool->base.psr);
+
 	if (pool->base.dccg != NULL)
 		dcn_dccg_destroy(&pool->base.dccg);
 }
@@ -1821,6 +1828,22 @@ static bool init_soc_bounding_box(struct dc *dc,
 	loaded_ip->max_num_dpp = pool->base.pipe_count;
 	loaded_ip->clamp_min_dcfclk = dc->config.clamp_min_dcfclk;
 	dcn20_patch_bounding_box(dc, loaded_bb);
+
+	if (!bb && dc->ctx->dc_bios->funcs->get_soc_bb_info) {
+		struct bp_soc_bb_info bb_info = {0};
+
+		if (dc->ctx->dc_bios->funcs->get_soc_bb_info(dc->ctx->dc_bios, &bb_info) == BP_RESULT_OK) {
+			if (bb_info.dram_clock_change_latency_100ns > 0)
+				dcn3_0_soc.dram_clock_change_latency_us = bb_info.dram_clock_change_latency_100ns * 10;
+
+			if (bb_info.dram_sr_enter_exit_latency_100ns > 0)
+				dcn3_0_soc.sr_enter_plus_exit_time_us = bb_info.dram_sr_enter_exit_latency_100ns * 10;
+
+			if (bb_info.dram_sr_exit_latency_100ns > 0)
+				dcn3_0_soc.sr_exit_time_us = bb_info.dram_sr_exit_latency_100ns * 10;
+		}
+	}
+
 	return true;
 }
 
@@ -1876,6 +1899,48 @@ static bool dcn30_split_stream_for_mpc_or_odm(
 	return true;
 }
 
+static struct pipe_ctx *dcn30_find_split_pipe(
+		struct dc *dc,
+		struct dc_state *context,
+		int old_index)
+{
+	struct pipe_ctx *pipe = NULL;
+	int i;
+
+	if (old_index >= 0 && context->res_ctx.pipe_ctx[old_index].stream == NULL) {
+		pipe = &context->res_ctx.pipe_ctx[old_index];
+		pipe->pipe_idx = old_index;
+	}
+
+	if (!pipe)
+		for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) {
+			if (dc->current_state->res_ctx.pipe_ctx[i].top_pipe == NULL
+					&& dc->current_state->res_ctx.pipe_ctx[i].prev_odm_pipe == NULL) {
+				if (context->res_ctx.pipe_ctx[i].stream == NULL) {
+					pipe = &context->res_ctx.pipe_ctx[i];
+					pipe->pipe_idx = i;
+					break;
+				}
+			}
+		}
+
+	/*
+	 * May need to fix pipes getting tossed from 1 opp to another on flip
+	 * Add for debugging transient underflow during topology updates:
+	 * ASSERT(pipe);
+	 */
+	if (!pipe)
+		for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) {
+			if (context->res_ctx.pipe_ctx[i].stream == NULL) {
+				pipe = &context->res_ctx.pipe_ctx[i];
+				pipe->pipe_idx = i;
+				break;
+			}
+		}
+
+	return pipe;
+}
+
 static bool dcn30_internal_validate_bw(
 		struct dc *dc,
 		struct dc_state *context,
@@ -2001,6 +2066,7 @@ static bool dcn30_internal_validate_bw(
 				dcn20_release_dsc(&context->res_ctx, dc->res_pool, &pipe->stream_res.dsc);
 			memset(&pipe->plane_res, 0, sizeof(pipe->plane_res));
 			memset(&pipe->stream_res, 0, sizeof(pipe->stream_res));
+			repopulate_pipes = true;
 		} else if (pipe->top_pipe && pipe->top_pipe->plane_state == pipe->plane_state) {
 			struct pipe_ctx *top_pipe = pipe->top_pipe;
 			struct pipe_ctx *bottom_pipe = pipe->bottom_pipe;
@@ -2015,6 +2081,7 @@ static bool dcn30_internal_validate_bw(
 			pipe->stream = NULL;
 			memset(&pipe->plane_res, 0, sizeof(pipe->plane_res));
 			memset(&pipe->stream_res, 0, sizeof(pipe->stream_res));
+			repopulate_pipes = true;
 		} else
 			ASSERT(0); /* Should never try to merge master pipe */
 
@@ -2022,8 +2089,10 @@ static bool dcn30_internal_validate_bw(
 
 	for (i = 0, pipe_idx = -1; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 		struct pipe_ctx *hsplit_pipe = NULL;
 		bool odm;
+		int old_index = -1;
 
 		if (!pipe->stream || newly_split[i])
 			continue;
@@ -2035,7 +2104,20 @@ static bool dcn30_internal_validate_bw(
 			continue;
 
 		if (split[i]) {
-			hsplit_pipe = find_idle_secondary_pipe(&context->res_ctx, dc->res_pool, pipe);
+			if (odm) {
+				if (split[i] == 4 && old_pipe->next_odm_pipe && old_pipe->next_odm_pipe->next_odm_pipe)
+					old_index = old_pipe->next_odm_pipe->next_odm_pipe->pipe_idx;
+				else if (old_pipe->next_odm_pipe)
+					old_index = old_pipe->next_odm_pipe->pipe_idx;
+			} else {
+				if (split[i] == 4 && old_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe &&
+						old_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state)
+					old_index = old_pipe->bottom_pipe->bottom_pipe->pipe_idx;
+				else if (old_pipe->bottom_pipe &&
+						old_pipe->bottom_pipe->plane_state == old_pipe->plane_state)
+					old_index = old_pipe->bottom_pipe->pipe_idx;
+			}
+			hsplit_pipe = dcn30_find_split_pipe(dc, context, old_index);
 			ASSERT(hsplit_pipe);
 			if (!hsplit_pipe)
 				goto validate_fail;
@@ -2049,8 +2131,16 @@ static bool dcn30_internal_validate_bw(
 			repopulate_pipes = true;
 		}
 		if (split[i] == 4) {
-			struct pipe_ctx *pipe_4to1 = find_idle_secondary_pipe(&context->res_ctx, dc->res_pool, pipe);
+			struct pipe_ctx *pipe_4to1;
 
+			if (odm && old_pipe->next_odm_pipe)
+				old_index = old_pipe->next_odm_pipe->pipe_idx;
+			else if (!odm && old_pipe->bottom_pipe &&
+						old_pipe->bottom_pipe->plane_state == old_pipe->plane_state)
+				old_index = old_pipe->bottom_pipe->pipe_idx;
+			else
+				old_index = -1;
+			pipe_4to1 = dcn30_find_split_pipe(dc, context, old_index);
 			ASSERT(pipe_4to1);
 			if (!pipe_4to1)
 				goto validate_fail;
@@ -2060,7 +2150,16 @@ static bool dcn30_internal_validate_bw(
 				goto validate_fail;
 			newly_split[pipe_4to1->pipe_idx] = true;
 
-			pipe_4to1 = find_idle_secondary_pipe(&context->res_ctx, dc->res_pool, pipe);
+			if (odm && old_pipe->next_odm_pipe && old_pipe->next_odm_pipe->next_odm_pipe
+					&& old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe)
+				old_index = old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe->pipe_idx;
+			else if (!odm && old_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe &&
+					old_pipe->bottom_pipe->bottom_pipe->bottom_pipe &&
+					old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state)
+				old_index = old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->pipe_idx;
+			else
+				old_index = -1;
+			pipe_4to1 = dcn30_find_split_pipe(dc, context, old_index);
 			ASSERT(pipe_4to1);
 			if (!pipe_4to1)
 				goto validate_fail;
@@ -2104,7 +2203,7 @@ validate_out:
 	return out;
 }
 
-static void dcn30_calculate_wm(
+void dcn30_calculate_wm_and_dlg(
 		struct dc *dc, struct dc_state *context,
 		display_e2e_pipe_params_st *pipes,
 		int pipe_cnt,
@@ -2112,6 +2211,8 @@ static void dcn30_calculate_wm(
 {
 	int i, pipe_idx;
 	double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb];
+	bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] !=
+			dm_dram_clock_change_unsupported;
 
 	if (context->bw_ctx.dml.soc.min_dcfclk > dcfclk)
 		dcfclk = context->bw_ctx.dml.soc.min_dcfclk;
@@ -2145,30 +2246,12 @@ static void dcn30_calculate_wm(
 	pipes[0].clks_cfg.voltage = vlevel;
 	pipes[0].clks_cfg.dcfclk_mhz = dcfclk;
 
-	/* Set C:
-	 * DCFCLK: Min Required
-	 * FCLK(proportional to UCLK): 1GHz or Max
-	 * pstate latency overriden to 5us
-	 */
-	if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) {
-		context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.pstate_latency_us;
-		context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us;
-		context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us;
-	}
-	context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.c.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-
 	/* Set D:
 	 * DCFCLK: Min Required
 	 * FCLK(proportional to UCLK): 1GHz or Max
 	 * sr_enter_exit = 4, sr_exit = 2us
 	 */
+	/*
 	if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].valid) {
 		context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].dml_input.pstate_latency_us;
 		context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].dml_input.sr_enter_plus_exit_time_us;
@@ -2182,26 +2265,72 @@ static void dcn30_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.d.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	*/
 
-	/* Set A:
+	/* Set C:
 	 * DCFCLK: Min Required
 	 * FCLK(proportional to UCLK): 1GHz or Max
-	 *
-	 * Set A calculated last so that following calculations are based on Set A
+	 * pstate latency overridden to 5us
 	 */
-	if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].valid) {
-		context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us;
-		context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_enter_plus_exit_time_us;
-		context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_exit_time_us;
+	if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) {
+		unsigned int min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed;
+		unsigned int min_dram_speed_mts_margin = 160;
+
+		context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->dummy_pstate_table[0].dummy_pstate_latency_us;
+
+		if (context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] == dm_dram_clock_change_unsupported)
+			min_dram_speed_mts = dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz * 16;
+
+		for (i = 3; i > 0; i--) {
+			if ((min_dram_speed_mts + min_dram_speed_mts_margin > dc->clk_mgr->bw_params->dummy_pstate_table[i].dram_speed_mts) &&
+					(min_dram_speed_mts - min_dram_speed_mts_margin < dc->clk_mgr->bw_params->dummy_pstate_table[i].dram_speed_mts))
+				context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->dummy_pstate_table[i].dummy_pstate_latency_us;
+		}
+
+		context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us;
+		context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us;
+	}
+	context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.c.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+
+	if (!pstate_en) {
+		/* The only difference between A and C is p-state latency, if p-state is not supported we want to
+		 * calculate DLG based on dummy p-state latency, and max out the set A p-state watermark
+		 */
+		context->bw_ctx.bw.dcn.watermarks.a = context->bw_ctx.bw.dcn.watermarks.c;
+		context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = 0x13FFFF;
+	} else {
+		/* Set A:
+		 * DCFCLK: Min Required
+		 * FCLK(proportional to UCLK): 1GHz or Max
+		 *
+		 * Set A calculated last so that following calculations are based on Set A
+		 */
+		if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].valid) {
+			context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us;
+			context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_enter_plus_exit_time_us;
+			context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_exit_time_us;
+		}
+		context->bw_ctx.bw.dcn.watermarks.a.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+		context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+		context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+		context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+		context->bw_ctx.bw.dcn.watermarks.a.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+		context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+		context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+		context->bw_ctx.bw.dcn.watermarks.a.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	}
-	context->bw_ctx.bw.dcn.watermarks.a.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.a.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-	context->bw_ctx.bw.dcn.watermarks.a.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+
+	context->perf_params.stutter_period_us = context->bw_ctx.dml.vba.StutterPeriod;
+
+	/* Make set D = set A until set D is enabled */
+	context->bw_ctx.bw.dcn.watermarks.d = context->bw_ctx.bw.dcn.watermarks.a;
 
 	for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) {
 		if (!context->res_ctx.pipe_ctx[i].stream)
@@ -2221,6 +2350,13 @@ static void dcn30_calculate_wm(
 
 		pipe_idx++;
 	}
+
+	dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
+
+	if (!pstate_en)
+		/* Restore full p-state latency */
+		context->bw_ctx.dml.soc.dram_clock_change_latency_us =
+				dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us;
 }
 
 bool dcn30_validate_bandwidth(struct dc *dc,
@@ -2253,8 +2389,7 @@ bool dcn30_validate_bandwidth(struct dc *dc,
 		goto validate_out;
 	}
 
-	dcn30_calculate_wm(dc, context, pipes, pipe_cnt, vlevel);
-	dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
+	dc->res_pool->funcs->calculate_wm_and_dlg(dc, context, pipes, pipe_cnt, vlevel);
 
 	BW_VAL_TRACE_END_WATERMARKS();
 
@@ -2422,6 +2557,7 @@ static const struct resource_funcs dcn30_res_pool_funcs = {
 	.link_enc_create = dcn30_link_encoder_create,
 	.panel_cntl_create = dcn30_panel_cntl_create,
 	.validate_bandwidth = dcn30_validate_bandwidth,
+	.calculate_wm_and_dlg = dcn30_calculate_wm_and_dlg,
 	.populate_dml_pipes = dcn30_populate_dml_pipes_from_context,
 	.acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,
@@ -2623,6 +2759,14 @@ static bool dcn30_resource_construct(
 		}
 	}
 	pool->base.timing_generator_count = i;
+	/* PSR */
+	pool->base.psr = dmub_psr_create(ctx);
+
+	if (pool->base.psr == NULL) {
+		dm_error("DC: failed to create PSR obj!\n");
+		BREAK_TO_DEBUGGER();
+		goto create_fail;
+	}
 
 	/* ABM */
 	for (i = 0; i < pool->base.res_cap->num_timing_generator; i++) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h
index c9d5f94092a0..d163812af858 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.h
@@ -55,6 +55,11 @@ unsigned int dcn30_calc_max_scaled_time(
 
 bool dcn30_validate_bandwidth(struct dc *dc, struct dc_state *context,
 		bool fast_validate);
+void dcn30_calculate_wm_and_dlg(
+		struct dc *dc, struct dc_state *context,
+		display_e2e_pipe_params_st *pipes,
+		int pipe_cnt,
+		int vlevel);
 void dcn30_populate_dml_writeback_from_context(
 		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
index ae608c329366..3586934df25f 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
@@ -30,8 +30,6 @@
  * interface to PPLIB/SMU to setup clocks and pstate requirements on SoC
  */
 
-typedef bool BOOLEAN;
-
 enum pp_smu_ver {
 	/*
 	 * PP_SMU_INTERFACE_X should be interpreted as the interface defined
@@ -240,7 +238,7 @@ struct pp_smu_funcs_nv {
 	 * DC hardware
 	 */
 	enum pp_smu_status (*set_pstate_handshake_support)(struct pp_smu *pp,
-			BOOLEAN pstate_handshake_supported);
+			bool pstate_handshake_supported);
 };
 
 #define PP_SMU_NUM_SOCCLK_DPM_LEVELS  8
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
index 80170f9721ce..860e72a51534 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
@@ -2635,15 +2635,14 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP
 	}
 
 	if (mode_lib->vba.DRAMClockChangeSupportsVActive &&
-			mode_lib->vba.MinActiveDRAMClockChangeMargin > 60) {
+			mode_lib->vba.MinActiveDRAMClockChangeMargin > 60 &&
+			mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
 		mode_lib->vba.DRAMClockChangeWatermark += 25;
 
 		for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) {
-			if (mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
-				if (mode_lib->vba.DRAMClockChangeWatermark >
-				dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
-					mode_lib->vba.MinTTUVBlank[k] += 25;
-			}
+			if (mode_lib->vba.DRAMClockChangeWatermark >
+			dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
+				mode_lib->vba.MinTTUVBlank[k] += 25;
 		}
 
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h
index 1e557ddcb638..d0b90947f540 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h
@@ -33,7 +33,7 @@ struct display_mode_lib;
 
 // Function: dml_rq_dlg_get_rq_reg
 //  Main entry point for test to get the register values out of this DML class.
-//  This function calls <get_rq_param> and <extract_rq_regs> fucntions to calculate
+//  This function calls <get_rq_param> and <extract_rq_regs> functions to calculate
 //  and then populate the rq_regs struct
 // Input:
 //  pipe_src_param - pipe source configuration (e.g. vp, pitch, etc.)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h
index 0d53e871a9d1..27cf8bed9376 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h
@@ -33,7 +33,7 @@ struct display_mode_lib;
 
 // Function: dml_rq_dlg_get_rq_reg
 //  Main entry point for test to get the register values out of this DML class.
-//  This function calls <get_rq_param> and <extract_rq_regs> fucntions to calculate
+//  This function calls <get_rq_param> and <extract_rq_regs> functions to calculate
 //  and then populate the rq_regs struct
 // Input:
 //  pipe_src_param - pipe source configuration (e.g. vp, pitch, etc.)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index a576eed94d9b..367c82b5ab4c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -1294,7 +1294,7 @@ static unsigned int CalculateVMAndRowBytes(
 	unsigned int MacroTileHeight;
 	unsigned int ExtraDPDEBytesFrame;
 	unsigned int PDEAndMetaPTEBytesFrame;
-	unsigned int PixelPTEReqHeightPTEs;
+	unsigned int PixelPTEReqHeightPTEs = 0;
 
 	if (DCCEnable == true) {
 		*MetaRequestHeight = 8 * BlockHeight256Bytes;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
index 2beb284f89b0..9e0ae18e71fa 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
@@ -597,7 +597,8 @@ static void CalculateStutterEfficiency(
 		double meta_row_bw[],
 		double dpte_row_bw[],
 		double *StutterEfficiencyNotIncludingVBlank,
-		double *StutterEfficiency);
+		double *StutterEfficiency,
+		double *StutterPeriodOut);
 
 static void CalculateSwathAndDETConfiguration(
 		bool ForceSingleDPP,
@@ -3134,7 +3135,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 			v->meta_row_bw,
 			v->dpte_row_bw,
 			&v->StutterEfficiencyNotIncludingVBlank,
-			&v->StutterEfficiency);
+			&v->StutterEfficiency,
+			&v->StutterPeriod);
 }
 
 static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib)
@@ -3235,7 +3237,7 @@ static bool CalculateBytePerPixelAnd256BBlockSizes(
 		*BytePerPixelDETC = 0;
 		*BytePerPixelY = 4;
 		*BytePerPixelC = 0;
-	} else if (SourcePixelFormat == dm_444_16 || SourcePixelFormat == dm_444_16) {
+	} else if (SourcePixelFormat == dm_444_16) {
 		*BytePerPixelDETY = 2;
 		*BytePerPixelDETC = 0;
 		*BytePerPixelY = 2;
@@ -5305,7 +5307,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			ViewportExceedsSurface = true;
 
 		if (v->SourcePixelFormat[k] != dm_444_64 && v->SourcePixelFormat[k] != dm_444_32 && v->SourcePixelFormat[k] != dm_444_16
-				&& v->SourcePixelFormat[k] != dm_444_16 && v->SourcePixelFormat[k] != dm_444_8 && v->SourcePixelFormat[k] != dm_rgbe) {
+				&& v->SourcePixelFormat[k] != dm_444_8 && v->SourcePixelFormat[k] != dm_rgbe) {
 			if (v->ViewportWidthChroma[k] > v->SurfaceWidthC[k] || v->ViewportHeightChroma[k] > v->SurfaceHeightC[k]) {
 				ViewportExceedsSurface = true;
 			}
@@ -5515,7 +5517,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 			if (WritebackPixelFormat[k] == dm_444_64) {
 				WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2;
 			}
-			if (mode_lib->vba.WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave || mode_lib->vba.WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave) {
+			if (mode_lib->vba.WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave) {
 				WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding * 2;
 			}
 			WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - mode_lib->vba.WritebackDRAMClockChangeWatermark;
@@ -5556,7 +5558,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		}
 	}
 
-	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) {
+	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0 && PrefetchMode == 0) {
 		*DRAMClockChangeSupport = dm_dram_clock_change_vactive;
 	} else if (((mode_lib->vba.SynchronizedVBlank == true || mode_lib->vba.TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0)) {
 		*DRAMClockChangeSupport = dm_dram_clock_change_vblank;
@@ -6151,7 +6153,8 @@ static void CalculateStutterEfficiency(
 		double meta_row_bw[],
 		double dpte_row_bw[],
 		double *StutterEfficiencyNotIncludingVBlank,
-		double *StutterEfficiency)
+		double *StutterEfficiency,
+		double *StutterPeriodOut)
 {
 	double FullDETBufferingTimeY[DC__NUM_DPP__MAX] = { 0 };
 	double FrameTimeForMinFullDETBufferingTime = 0;
@@ -6262,6 +6265,9 @@ static void CalculateStutterEfficiency(
 	}
 
 	*StutterEfficiency =  (*StutterEfficiencyNotIncludingVBlank / 100.0 * (FrameTimeForMinFullDETBufferingTime - SmallestVBlank) + SmallestVBlank) / FrameTimeForMinFullDETBufferingTime * 100;
+
+	if (StutterPeriodOut)
+		*StutterPeriodOut = StutterPeriod;
 }
 
 static void CalculateSwathAndDETConfiguration(
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
index 5bb10f6e300d..416bf6fb67bd 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
@@ -279,7 +279,7 @@ static bool CalculateBytePerPixelAnd256BBlockSizes(
 		*BytePerPixelDETC = 0;
 		*BytePerPixelY = 4;
 		*BytePerPixelC = 0;
-	} else if (SourcePixelFormat == dm_444_16 || SourcePixelFormat == dm_444_16) {
+	} else if (SourcePixelFormat == dm_444_16) {
 		*BytePerPixelDETY = 2;
 		*BytePerPixelDETC = 0;
 		*BytePerPixelY = 2;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h
index e5b17e1104c6..c04965cceff3 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h
@@ -32,7 +32,7 @@ struct display_mode_lib;
 
 // Function: dml_rq_dlg_get_rq_reg
 //  Main entry point for test to get the register values out of this DML class.
-//  This function calls <get_rq_param> and <extract_rq_regs> fucntions to calculate
+//  This function calls <get_rq_param> and <extract_rq_regs> functions to calculate
 //  and then populate the rq_regs struct
 // Input:
 //  pipe_param - pipe source configuration (e.g. vp, pitch, scaling, dest, etc.)
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c b/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c
index cf98aa827a9a..e883864cff3c 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dce120/hw_factory_dce120.c
@@ -162,7 +162,7 @@ static void define_hpd_registers(struct hw_gpio_pin *pin, uint32_t en)
 }
 
 
-/* fucntion table */
+/* function table */
 static const struct hw_factory_funcs funcs = {
 	.init_ddc_data = dal_hw_ddc_init,
 	.init_generic = NULL,
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c
index b38c96c9fed3..7d36b56346a6 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn10/hw_factory_dcn10.c
@@ -194,7 +194,7 @@ static void define_hpd_registers(struct hw_gpio_pin *pin, uint32_t en)
 }
 
 
-/* fucntion table */
+/* function table */
 static const struct hw_factory_funcs funcs = {
 	.init_ddc_data = dal_hw_ddc_init,
 	.init_generic = dal_hw_generic_init,
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c
index 83f798cb8b21..9b63c6c0cc84 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c
@@ -221,7 +221,7 @@ static void define_generic_registers(struct hw_gpio_pin *pin, uint32_t en)
 	generic->base.regs = &generic_regs[en].gpio;
 }
 
-/* fucntion table */
+/* function table */
 static const struct hw_factory_funcs funcs = {
 	.init_ddc_data = dal_hw_ddc_init,
 	.init_generic = dal_hw_generic_init,
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
index 907c5911eb9e..2f57ee6deabc 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
@@ -202,7 +202,7 @@ static void define_hpd_registers(struct hw_gpio_pin *pin, uint32_t en)
 }
 
 
-/* fucntion table */
+/* function table */
 static const struct hw_factory_funcs funcs = {
 	.init_ddc_data = dal_hw_ddc_init,
 	.init_generic = dal_hw_generic_init,
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c
index 7e7fb6572107..21583699f992 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c
@@ -117,6 +117,12 @@ static const struct ddc_registers ddc_data_regs_dcn[] = {
 	ddc_data_regs_dcn2(4),
 	ddc_data_regs_dcn2(5),
 	ddc_data_regs_dcn2(6),
+	{
+			DDC_GPIO_VGA_REG_LIST(DATA),
+			.ddc_setup = 0,
+			.phy_aux_cntl = 0,
+			.dc_gpio_aux_ctrl_5 = 0
+	}
 };
 
 static const struct ddc_registers ddc_clk_regs_dcn[] = {
@@ -126,6 +132,12 @@ static const struct ddc_registers ddc_clk_regs_dcn[] = {
 	ddc_clk_regs_dcn2(4),
 	ddc_clk_regs_dcn2(5),
 	ddc_clk_regs_dcn2(6),
+	{
+			DDC_GPIO_VGA_REG_LIST(CLK),
+			.ddc_setup = 0,
+			.phy_aux_cntl = 0,
+			.dc_gpio_aux_ctrl_5 = 0
+	}
 };
 
 static const struct ddc_sh_mask ddc_shift[] = {
@@ -218,7 +230,7 @@ static void define_hpd_registers(struct hw_gpio_pin *pin, uint32_t en)
 }
 
 
-/* fucntion table */
+/* function table */
 static const struct hw_factory_funcs funcs = {
 	.init_ddc_data = dal_hw_ddc_init,
 	.init_generic = dal_hw_generic_init,
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
index f67c18375bfd..dac427b68fd7 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
@@ -63,13 +63,13 @@ enum gpio_result dal_gpio_open_ex(
 	enum gpio_mode mode)
 {
 	if (gpio->pin) {
-		ASSERT_CRITICAL(false);
+		BREAK_TO_DEBUGGER();
 		return GPIO_RESULT_ALREADY_OPENED;
 	}
 
 	// No action if allocation failed during gpio construct
 	if (!gpio->hw_container.ddc) {
-		ASSERT_CRITICAL(false);
+		BREAK_TO_DEBUGGER();
 		return GPIO_RESULT_NON_SPECIFIC_ERROR;
 	}
 	gpio->mode = mode;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index 329395ee7461..6e6bc66e49f0 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -101,7 +101,7 @@ struct resource_funcs {
 					struct dc *dc,
 					struct dc_state *context,
 					bool fast_validate);
-	void (*calculate_wm)(
+	void (*calculate_wm_and_dlg)(
 				struct dc *dc, struct dc_state *context,
 				display_e2e_pipe_params_st *pipes,
 				int pipe_cnt,
@@ -300,6 +300,7 @@ union pipe_update_flags {
 		uint32_t gamut_remap : 1;
 		uint32_t scaler : 1;
 		uint32_t viewport : 1;
+		uint32_t plane_changed : 1;
 	} bits;
 	uint32_t raw;
 };
@@ -396,6 +397,7 @@ struct dc_state {
 	struct dc_stream_state *streams[MAX_PIPES];
 	struct dc_stream_status stream_status[MAX_PIPES];
 	uint8_t stream_count;
+	uint8_t stream_mask;
 
 	struct resource_context res_ctx;
 
@@ -410,6 +412,10 @@ struct dc_state {
 	struct clk_mgr *clk_mgr;
 
 	struct kref refcount;
+
+	struct {
+		unsigned int stutter_period_us;
+	} perf_params;
 };
 
 #endif /* _CORE_TYPES_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
index 11ce06e69d3f..0184cefb083b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
@@ -143,7 +143,7 @@ struct stream_encoder_funcs {
 		struct stream_encoder *enc,
 		struct dc_crtc_timing *crtc_timing);
 
-	void (*set_mst_bandwidth)(
+	void (*set_throttled_vcp_size)(
 		struct stream_encoder *enc,
 		struct fixed31_32 avg_time_slots_per_mtp);
 
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index 330acaaed79a..95cb56929e79 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -94,36 +94,27 @@
  * general debug capabilities
  *
  */
-#if defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB)
-#define ASSERT_CRITICAL(expr) do {	\
-	if (WARN_ON(!(expr))) { \
-		kgdb_breakpoint(); \
-	} \
-} while (0)
+#ifdef CONFIG_DEBUG_KERNEL_DC
+#define dc_breakpoint()		kgdb_breakpoint()
 #else
-#define ASSERT_CRITICAL(expr) do {	\
-	if (WARN_ON(!(expr))) { \
-		; \
-	} \
-} while (0)
+#define dc_breakpoint()		do {} while (0)
 #endif
 
-#if defined(CONFIG_DEBUG_KERNEL_DC)
-#define ASSERT(expr) ASSERT_CRITICAL(expr)
+#define ASSERT_CRITICAL(expr) do {		\
+		if (WARN_ON(!(expr)))		\
+			dc_breakpoint();	\
+	} while (0)
 
-#else
-#define ASSERT(expr) WARN_ON_ONCE(!(expr))
-#endif
+#define ASSERT(expr) do {			\
+		if (WARN_ON_ONCE(!(expr)))	\
+			dc_breakpoint();	\
+	} while (0)
 
-#if defined(CONFIG_DEBUG_KERNEL_DC) && (defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB))
 #define BREAK_TO_DEBUGGER() \
 	do { \
 		DRM_DEBUG_DRIVER("%s():%d\n", __func__, __LINE__); \
-		kgdb_breakpoint(); \
+		dc_breakpoint(); \
 	} while (0)
-#else
-#define BREAK_TO_DEBUGGER() DRM_DEBUG_DRIVER("%s():%d\n", __func__, __LINE__)
-#endif
 
 #define DC_ERR(...)  do { \
 	dm_error(__VA_ARGS__); \
diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
index 944c0327763c..1053b165c139 100644
--- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
@@ -46,9 +46,10 @@ static void virtual_stream_encoder_dvi_set_stream_attribute(
 	struct dc_crtc_timing *crtc_timing,
 	bool is_dual_link) {}
 
-static void virtual_stream_encoder_set_mst_bandwidth(
+static void virtual_stream_encoder_set_throttled_vcp_size(
 	struct stream_encoder *enc,
-	struct fixed31_32 avg_time_slots_per_mtp) {}
+	struct fixed31_32 avg_time_slots_per_mtp)
+{}
 
 static void virtual_stream_encoder_update_hdmi_info_packets(
 	struct stream_encoder *enc,
@@ -98,6 +99,12 @@ static void virtual_setup_stereo_sync(
 			bool enable)
 {}
 
+static void virtual_stream_encoder_set_dsc_pps_info_packet(
+		struct stream_encoder *enc,
+		bool enable,
+		uint8_t *dsc_packed_pps)
+{}
+
 static const struct stream_encoder_funcs virtual_str_enc_funcs = {
 	.dp_set_odm_combine =
 		virtual_enc_dp_set_odm_combine,
@@ -107,8 +114,8 @@ static const struct stream_encoder_funcs virtual_str_enc_funcs = {
 		virtual_stream_encoder_hdmi_set_stream_attribute,
 	.dvi_set_stream_attribute =
 		virtual_stream_encoder_dvi_set_stream_attribute,
-	.set_mst_bandwidth =
-		virtual_stream_encoder_set_mst_bandwidth,
+	.set_throttled_vcp_size =
+		virtual_stream_encoder_set_throttled_vcp_size,
 	.update_hdmi_info_packets =
 		virtual_stream_encoder_update_hdmi_info_packets,
 	.stop_hdmi_info_packets =
@@ -127,6 +134,7 @@ static const struct stream_encoder_funcs virtual_str_enc_funcs = {
 	.hdmi_reset_stream_attribute = virtual_stream_encoder_reset_hdmi_stream_attribute,
 	.dig_connect_to_otg = virtual_dig_connect_to_otg,
 	.setup_stereo_sync = virtual_setup_stereo_sync,
+	.dp_set_dsc_pps_info_packet = virtual_stream_encoder_set_dsc_pps_info_packet,
 };
 
 bool virtual_stream_encoder_construct(
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index d7e7f2eda92f..d103ec1eaa73 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -36,10 +36,10 @@
 
 /* Firmware versioning. */
 #ifdef DMUB_EXPOSE_VERSION
-#define DMUB_FW_VERSION_GIT_HASH 0x4e5b2f46f
+#define DMUB_FW_VERSION_GIT_HASH 0x9cf8f05fe
 #define DMUB_FW_VERSION_MAJOR 0
 #define DMUB_FW_VERSION_MINOR 0
-#define DMUB_FW_VERSION_REVISION 29
+#define DMUB_FW_VERSION_REVISION 35
 #define DMUB_FW_VERSION_TEST 0
 #define DMUB_FW_VERSION_VBIOS 0
 #define DMUB_FW_VERSION_HOTFIX 0
@@ -57,6 +57,7 @@
 
 #define SET_ABM_PIPE_GRADUALLY_DISABLE           0
 #define SET_ABM_PIPE_IMMEDIATELY_DISABLE         255
+#define SET_ABM_PIPE_IMMEDIATE_KEEP_GAIN_DISABLE 254
 #define SET_ABM_PIPE_NORMAL                      1
 
 /* Maximum number of streams on any ASIC. */
@@ -69,10 +70,6 @@
 #define PHYSICAL_ADDRESS_LOC union large_integer
 #endif
 
-#if defined(__cplusplus)
-extern "C" {
-#endif
-
 #ifndef dmub_memcpy
 #define dmub_memcpy(dest, source, bytes) memcpy((dest), (source), (bytes))
 #endif
@@ -81,6 +78,10 @@ extern "C" {
 #define dmub_memset(dest, val, bytes) memset((dest), (val), (bytes))
 #endif
 
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
 #ifndef dmub_udelay
 #define dmub_udelay(microseconds) udelay(microseconds)
 #endif
@@ -97,6 +98,7 @@ union dmub_psr_debug_flags {
 	struct {
 		uint32_t visual_confirm : 1;
 		uint32_t use_hw_lock_mgr : 1;
+		uint32_t log_line_nums : 1;
 	} bitfields;
 
 	uint32_t u32All;
@@ -169,7 +171,7 @@ union dmub_fw_boot_status {
 		uint32_t dal_fw : 1;
 		uint32_t mailbox_rdy : 1;
 		uint32_t optimized_init_done : 1;
-		uint32_t reserved : 29;
+		uint32_t restore_required : 1;
 	} bits;
 	uint32_t all;
 };
@@ -178,6 +180,7 @@ enum dmub_fw_boot_status_bit {
 	DMUB_FW_BOOT_STATUS_BIT_DAL_FIRMWARE = (1 << 0),
 	DMUB_FW_BOOT_STATUS_BIT_MAILBOX_READY = (1 << 1),
 	DMUB_FW_BOOT_STATUS_BIT_OPTIMIZED_INIT_DONE = (1 << 2),
+	DMUB_FW_BOOT_STATUS_BIT_RESTORE_REQUIRED = (1 << 3),
 };
 
 /* Register bit definition for SCRATCH15 */
@@ -297,9 +300,17 @@ enum dmub_cmd_type {
 	DMUB_CMD__PSR = 64,
 	DMUB_CMD__ABM = 66,
 	DMUB_CMD__HW_LOCK = 69,
+	DMUB_CMD__DP_AUX_ACCESS = 70,
+	DMUB_CMD__OUTBOX1_ENABLE = 71,
 	DMUB_CMD__VBIOS = 128,
 };
 
+enum dmub_out_cmd_type {
+	DMUB_OUT_CMD__NULL = 0,
+	DMUB_OUT_CMD__DP_AUX_REPLY = 1,
+	DMUB_OUT_CMD__DP_HPD_NOTIFY = 2,
+};
+
 #pragma pack(push, 1)
 
 struct dmub_cmd_header {
@@ -455,6 +466,78 @@ struct dmub_rb_cmd_dpphy_init {
 	uint8_t reserved[60];
 };
 
+enum dp_aux_request_action {
+	DP_AUX_REQ_ACTION_I2C_WRITE		= 0x00,
+	DP_AUX_REQ_ACTION_I2C_READ		= 0x10,
+	DP_AUX_REQ_ACTION_I2C_STATUS_REQ	= 0x20,
+	DP_AUX_REQ_ACTION_I2C_WRITE_MOT		= 0x40,
+	DP_AUX_REQ_ACTION_I2C_READ_MOT		= 0x50,
+	DP_AUX_REQ_ACTION_I2C_STATUS_REQ_MOT	= 0x60,
+	DP_AUX_REQ_ACTION_DPCD_WRITE		= 0x80,
+	DP_AUX_REQ_ACTION_DPCD_READ		= 0x90
+};
+
+/* DP AUX command */
+struct aux_transaction_parameters {
+	uint8_t is_i2c_over_aux;
+	uint8_t action;
+	uint8_t length;
+	uint8_t pad;
+	uint32_t address;
+	uint8_t data[16];
+};
+
+struct dmub_cmd_dp_aux_control_data {
+	uint32_t handle;
+	uint8_t port_index;
+	uint8_t sw_crc_enabled;
+	uint16_t timeout;
+	struct aux_transaction_parameters dpaux;
+};
+
+struct dmub_rb_cmd_dp_aux_access {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_dp_aux_control_data aux_control;
+};
+
+struct dmub_rb_cmd_outbox1_enable {
+	struct dmub_cmd_header header;
+	uint32_t enable;
+};
+
+/* DP AUX Reply command - OutBox Cmd */
+struct aux_reply_data {
+	uint8_t command;
+	uint8_t length;
+	uint8_t pad[2];
+	uint8_t data[16];
+};
+
+struct aux_reply_control_data {
+	uint32_t handle;
+	uint8_t phy_port_index;
+	uint8_t result;
+	uint16_t pad;
+};
+
+struct dmub_rb_cmd_dp_aux_reply {
+	struct dmub_cmd_header header;
+	struct aux_reply_control_data control;
+	struct aux_reply_data reply_data;
+};
+
+struct dp_hpd_data {
+	uint8_t phy_port_index;
+	uint8_t hpd_type;
+	uint8_t hpd_status;
+	uint8_t pad;
+};
+
+struct dmub_rb_cmd_dp_hpd_notify {
+	struct dmub_cmd_header header;
+	struct dp_hpd_data hpd_data;
+};
+
 /*
  * Command IDs should be treated as stable ABI.
  * Do not reuse or modify IDs.
@@ -684,8 +767,15 @@ union dmub_rb_cmd {
 	struct dmub_rb_cmd_abm_set_ambient_level abm_set_ambient_level;
 	struct dmub_rb_cmd_abm_set_pwm_frac abm_set_pwm_frac;
 	struct dmub_rb_cmd_abm_init_config abm_init_config;
+	struct dmub_rb_cmd_dp_aux_access dp_aux_access;
+	struct dmub_rb_cmd_outbox1_enable outbox1_enable;
 };
 
+union dmub_rb_out_cmd {
+	struct dmub_rb_cmd_common cmd_common;
+	struct dmub_rb_cmd_dp_aux_reply dp_aux_reply;
+	struct dmub_rb_cmd_dp_hpd_notify dp_hpd_notify;
+};
 #pragma pack(pop)
 
 
@@ -758,6 +848,25 @@ static inline bool dmub_rb_push_front(struct dmub_rb *rb,
 	return true;
 }
 
+static inline bool dmub_rb_out_push_front(struct dmub_rb *rb,
+				      const union dmub_rb_out_cmd *cmd)
+{
+	uint8_t *dst = (uint8_t *)(rb->base_address) + rb->wrpt;
+	const uint8_t *src = (uint8_t *)cmd;
+
+	if (dmub_rb_full(rb))
+		return false;
+
+	dmub_memcpy(dst, src, DMUB_RB_CMD_SIZE);
+
+	rb->wrpt += DMUB_RB_CMD_SIZE;
+
+	if (rb->wrpt >= rb->capacity)
+		rb->wrpt %= rb->capacity;
+
+	return true;
+}
+
 static inline bool dmub_rb_front(struct dmub_rb *rb,
 				 union dmub_rb_cmd  *cmd)
 {
@@ -771,6 +880,23 @@ static inline bool dmub_rb_front(struct dmub_rb *rb,
 	return true;
 }
 
+static inline bool dmub_rb_out_front(struct dmub_rb *rb,
+				 union dmub_rb_out_cmd  *cmd)
+{
+	const uint64_t volatile *src = (const uint64_t volatile *)(rb->base_address) + rb->rptr / sizeof(uint64_t);
+	uint64_t *dst = (uint64_t *)cmd;
+	int i;
+
+	if (dmub_rb_empty(rb))
+		return false;
+
+	// copying data
+	for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
+		*dst++ = *src++;
+
+	return true;
+}
+
 static inline bool dmub_rb_pop_front(struct dmub_rb *rb)
 {
 	if (dmub_rb_empty(rb))
@@ -791,12 +917,10 @@ static inline void dmub_rb_flush_pending(const struct dmub_rb *rb)
 
 	while (rptr != wptr) {
 		uint64_t volatile *data = (uint64_t volatile *)rb->base_address + rptr / sizeof(uint64_t);
-		//uint64_t volatile *p = (uint64_t volatile *)data;
-		uint64_t temp;
 		int i;
 
 		for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
-			temp = *data++;
+			*data++;
 
 		rptr += DMUB_RB_CMD_SIZE;
 		if (rptr >= rb->capacity)
diff --git a/drivers/gpu/drm/amd/display/include/bios_parser_types.h b/drivers/gpu/drm/amd/display/include/bios_parser_types.h
index 21011edea337..7c782924c941 100644
--- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h
+++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h
@@ -318,4 +318,10 @@ struct bp_encoder_cap_info {
 	uint32_t RESERVED:27;
 };
 
+struct bp_soc_bb_info {
+	uint32_t dram_clock_change_latency_100ns;
+	uint32_t dram_sr_exit_latency_100ns;
+	uint32_t dram_sr_enter_exit_latency_100ns;
+};
+
 #endif /*__DAL_BIOS_PARSER_TYPES_H__ */
diff --git a/drivers/gpu/drm/amd/display/include/link_service_types.h b/drivers/gpu/drm/amd/display/include/link_service_types.h
index 550f46e9b95f..7392a89e771f 100644
--- a/drivers/gpu/drm/amd/display/include/link_service_types.h
+++ b/drivers/gpu/drm/amd/display/include/link_service_types.h
@@ -80,6 +80,7 @@ struct link_training_settings {
 
 	uint16_t cr_pattern_time;
 	uint16_t eq_pattern_time;
+	enum dc_dp_training_pattern pattern_for_cr;
 	enum dc_dp_training_pattern pattern_for_eq;
 
 	bool enhanced_framing;
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
index e9fbd94f8635..20e554e771d1 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
@@ -470,6 +470,14 @@ enum mod_hdcp_status mod_hdcp_process_event(struct mod_hdcp *hdcp,
 		if (reset_status != MOD_HDCP_STATUS_SUCCESS)
 			push_error_status(hdcp, reset_status);
 	}
+
+	/* Clear CP_IRQ status if needed */
+	if (event_ctx.event == MOD_HDCP_EVENT_CPIRQ) {
+		status = mod_hdcp_clear_cp_irq_status(hdcp);
+		if (status != MOD_HDCP_STATUS_SUCCESS)
+			push_error_status(hdcp, status);
+	}
+
 	return status;
 }
 
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
index b0cefed2eb02..6c678cfb82e3 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
@@ -386,6 +386,7 @@ enum mod_hdcp_status mod_hdcp_write_eks(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_write_repeater_auth_ack(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_write_stream_manage(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_write_content_type(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_clear_cp_irq_status(struct mod_hdcp *hdcp);
 
 /* hdcp version helpers */
 static inline uint8_t is_dp_hdcp(struct mod_hdcp *hdcp)
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
index bb5130f4228d..f7b5583ee609 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
@@ -30,6 +30,8 @@
 #define KSV_READ_SIZE 0xf	/* 0x6803b - 0x6802c */
 #define HDCP_MAX_AUX_TRANSACTION_SIZE 16
 
+#define DP_CP_IRQ (1 << 2)
+
 enum mod_hdcp_ddc_message_id {
 	MOD_HDCP_MESSAGE_ID_INVALID = -1,
 
@@ -645,3 +647,18 @@ enum mod_hdcp_status mod_hdcp_write_content_type(struct mod_hdcp *hdcp)
 		status = MOD_HDCP_STATUS_INVALID_OPERATION;
 	return status;
 }
+
+enum mod_hdcp_status mod_hdcp_clear_cp_irq_status(struct mod_hdcp *hdcp)
+{
+	uint8_t clear_cp_irq_bit = DP_CP_IRQ;
+	uint32_t size = 1;
+
+	if (is_dp_hdcp(hdcp)) {
+		uint32_t cp_irq_addrs = (hdcp->connection.link.dp.rev >= 0x14)
+				? DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0:DP_DEVICE_SERVICE_IRQ_VECTOR;
+		return hdcp->config.ddc.funcs.write_dpcd(hdcp->config.ddc.handle, cp_irq_addrs,
+				&clear_cp_irq_bit, size) ? MOD_HDCP_STATUS_SUCCESS : MOD_HDCP_STATUS_DDC_FAILURE;
+	}
+
+	return MOD_HDCP_STATUS_INVALID_OPERATION;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
index d3192b9d0c3d..47f8ee2832ff 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
@@ -27,7 +27,7 @@
 #define MOD_HDCP_LOG_H_
 
 #ifdef CONFIG_DRM_AMD_DC_HDCP
-#define HDCP_LOG_ERR(hdcp, ...) DRM_WARN(__VA_ARGS__)
+#define HDCP_LOG_ERR(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
 #define HDCP_LOG_VER(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
 #define HDCP_LOG_FSM(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
 #define HDCP_LOG_TOP(hdcp, ...) pr_debug("[HDCP_TOP]:"__VA_ARGS__)
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index fb1161dd7ea8..3a367a5968ae 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -88,7 +88,7 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp,
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	if (!psp->dtm_context.dtm_initialized) {
-		DRM_ERROR("Failed to add display topology, DTM TA is not initialized.");
+		DRM_INFO("Failed to add display topology, DTM TA is not initialized.");
 		display->state = MOD_HDCP_DISPLAY_INACTIVE;
 		return MOD_HDCP_STATUS_FAILURE;
 	}
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index e98c84ef206f..10dc481ecbc4 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -47,6 +47,40 @@ enum amd_apu_flags {
 	AMD_APU_IS_RENOIR = 0x00000008UL,
 };
 
+/**
+* DOC: IP Blocks
+*
+* GPUs are composed of IP (intellectual property) blocks. These
+* IP blocks provide various functionalities: display, graphics,
+* video decode, etc. The IP blocks that comprise a particular GPU
+* are listed in the GPU's respective SoC file. amdgpu_device.c
+* acquires the list of IP blocks for the GPU in use on initialization.
+* It can then operate on this list to perform standard driver operations
+* such as: init, fini, suspend, resume, etc.
+* 
+*
+* IP block implementations are named using the following convention:
+* <functionality>_v<version> (E.g.: gfx_v6_0).
+*/
+
+/**
+* enum amd_ip_block_type - Used to classify IP blocks by functionality.
+*
+* @AMD_IP_BLOCK_TYPE_COMMON: GPU Family
+* @AMD_IP_BLOCK_TYPE_GMC: Graphics Memory Controller
+* @AMD_IP_BLOCK_TYPE_IH: Interrupt Handler
+* @AMD_IP_BLOCK_TYPE_SMC: System Management Controller
+* @AMD_IP_BLOCK_TYPE_PSP: Platform Security Processor
+* @AMD_IP_BLOCK_TYPE_DCE: Display and Compositing Engine
+* @AMD_IP_BLOCK_TYPE_GFX: Graphics and Compute Engine
+* @AMD_IP_BLOCK_TYPE_SDMA: System DMA Engine
+* @AMD_IP_BLOCK_TYPE_UVD: Unified Video Decoder
+* @AMD_IP_BLOCK_TYPE_VCE: Video Compression Engine
+* @AMD_IP_BLOCK_TYPE_ACP: Audio Co-Processor
+* @AMD_IP_BLOCK_TYPE_VCN: Video Core/Codec Next
+* @AMD_IP_BLOCK_TYPE_MES: Micro-Engine Scheduler
+* @AMD_IP_BLOCK_TYPE_JPEG: JPEG Engine
+*/
 enum amd_ip_block_type {
 	AMD_IP_BLOCK_TYPE_COMMON,
 	AMD_IP_BLOCK_TYPE_GMC,
@@ -128,6 +162,34 @@ enum amd_powergating_state {
 #define AMD_PG_SUPPORT_ATHUB			(1 << 16)
 #define AMD_PG_SUPPORT_JPEG			(1 << 17)
 
+/**
+ * enum PP_FEATURE_MASK - Used to mask power play features.
+ *
+ * @PP_SCLK_DPM_MASK: Dynamic adjustment of the system (graphics) clock.
+ * @PP_MCLK_DPM_MASK: Dynamic adjustment of the memory clock.
+ * @PP_PCIE_DPM_MASK: Dynamic adjustment of PCIE clocks and lanes.
+ * @PP_SCLK_DEEP_SLEEP_MASK: System (graphics) clock deep sleep.
+ * @PP_POWER_CONTAINMENT_MASK: Power containment.
+ * @PP_UVD_HANDSHAKE_MASK: Unified video decoder handshake.
+ * @PP_SMC_VOLTAGE_CONTROL_MASK: Dynamic voltage control.
+ * @PP_VBI_TIME_SUPPORT_MASK: Vertical blank interval support.
+ * @PP_ULV_MASK: Ultra low voltage.
+ * @PP_ENABLE_GFX_CG_THRU_SMU: SMU control of GFX engine clockgating.
+ * @PP_CLOCK_STRETCH_MASK: Clock stretching.
+ * @PP_OD_FUZZY_FAN_CONTROL_MASK: Overdrive fuzzy fan control.
+ * @PP_SOCCLK_DPM_MASK: Dynamic adjustment of the SoC clock.
+ * @PP_DCEFCLK_DPM_MASK: Dynamic adjustment of the Display Controller Engine Fabric clock.
+ * @PP_OVERDRIVE_MASK: Over- and under-clocking support.
+ * @PP_GFXOFF_MASK: Dynamic graphics engine power control.
+ * @PP_ACG_MASK: Adaptive clock generator.
+ * @PP_STUTTER_MODE: Stutter mode.
+ * @PP_AVFS_MASK: Adaptive voltage and frequency scaling.
+ *
+ * To override these settings on boot, append amdgpu.ppfeaturemask=<mask> to
+ * the kernel's command line parameters. This is usually done through a system's
+ * boot loader (E.g. GRUB). If manually loading the driver, pass
+ * ppfeaturemask=<mask> as a modprobe parameter.
+ */
 enum PP_FEATURE_MASK {
 	PP_SCLK_DPM_MASK = 0x1,
 	PP_MCLK_DPM_MASK = 0x2,
@@ -165,56 +227,59 @@ enum DC_DEBUG_MASK {
 };
 
 enum amd_dpm_forced_level;
+
 /**
  * struct amd_ip_funcs - general hooks for managing amdgpu IP Blocks
+ * @name: Name of IP block
+ * @early_init: sets up early driver state (pre sw_init),
+ *              does not configure hw - Optional
+ * @late_init: sets up late driver/hw state (post hw_init) - Optional
+ * @sw_init: sets up driver state, does not configure hw
+ * @sw_fini: tears down driver state, does not configure hw
+ * @hw_init: sets up the hw state
+ * @hw_fini: tears down the hw state
+ * @late_fini: final cleanup
+ * @suspend: handles IP specific hw/sw changes for suspend
+ * @resume: handles IP specific hw/sw changes for resume
+ * @is_idle: returns current IP block idle status
+ * @wait_for_idle: poll for idle
+ * @check_soft_reset: check soft reset the IP block
+ * @pre_soft_reset: pre soft reset the IP block
+ * @soft_reset: soft reset the IP block
+ * @post_soft_reset: post soft reset the IP block
+ * @set_clockgating_state: enable/disable cg for the IP block
+ * @set_powergating_state: enable/disable pg for the IP block
+ * @get_clockgating_state: get current clockgating status
+ * @enable_umd_pstate: enable UMD powerstate
+ *
+ * These hooks provide an interface for controlling the operational state
+ * of IP blocks. After acquiring a list of IP blocks for the GPU in use,
+ * the driver can make chip-wide state changes by walking this list and
+ * making calls to hooks from each IP block. This list is ordered to ensure
+ * that the driver initializes the IP blocks in a safe sequence.
  */
 struct amd_ip_funcs {
-	/** @name: Name of IP block */
 	char *name;
-	/**
-	 * @early_init:
-	 *
-	 * sets up early driver state (pre sw_init),
-	 * does not configure hw - Optional
-	 */
 	int (*early_init)(void *handle);
-	/** @late_init: sets up late driver/hw state (post hw_init) - Optional */
 	int (*late_init)(void *handle);
-	/** @sw_init: sets up driver state, does not configure hw */
 	int (*sw_init)(void *handle);
-	/** @sw_fini: tears down driver state, does not configure hw */
 	int (*sw_fini)(void *handle);
-	/** @hw_init: sets up the hw state */
 	int (*hw_init)(void *handle);
-	/** @hw_fini: tears down the hw state */
 	int (*hw_fini)(void *handle);
-	/** @late_fini: final cleanup */
 	void (*late_fini)(void *handle);
-	/** @suspend: handles IP specific hw/sw changes for suspend */
 	int (*suspend)(void *handle);
-	/** @resume: handles IP specific hw/sw changes for resume */
 	int (*resume)(void *handle);
-	/** @is_idle: returns current IP block idle status */
 	bool (*is_idle)(void *handle);
-	/** @wait_for_idle: poll for idle */
 	int (*wait_for_idle)(void *handle);
-	/** @check_soft_reset: check soft reset the IP block */
 	bool (*check_soft_reset)(void *handle);
-	/** @pre_soft_reset: pre soft reset the IP block */
 	int (*pre_soft_reset)(void *handle);
-	/** @soft_reset: soft reset the IP block */
 	int (*soft_reset)(void *handle);
-	/** @post_soft_reset: post soft reset the IP block */
 	int (*post_soft_reset)(void *handle);
-	/** @set_clockgating_state: enable/disable cg for the IP block */
 	int (*set_clockgating_state)(void *handle,
 				     enum amd_clockgating_state state);
-	/** @set_powergating_state: enable/disable pg for the IP block */
 	int (*set_powergating_state)(void *handle,
 				     enum amd_powergating_state state);
-	/** @get_clockgating_state: get current clockgating status */
 	void (*get_clockgating_state)(void *handle, u32 *flags);
-	/** @enable_umd_pstate: enable UMD powerstate */
 	int (*enable_umd_pstate)(void *handle, enum amd_dpm_forced_level *level);
 };
 
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h
index 1116779252e6..e245e912535e 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h
@@ -2727,6 +2727,7 @@
 #define mmDB_STENCIL_WRITE_BASE_DEFAULT                                          0x00000000
 #define mmDB_RESERVED_REG_1_DEFAULT                                              0x00000000
 #define mmDB_RESERVED_REG_3_DEFAULT                                              0x00000000
+#define mmDB_VRS_OVERRIDE_CNTL_DEFAULT                                           0x00000000
 #define mmDB_Z_READ_BASE_HI_DEFAULT                                              0x00000000
 #define mmDB_STENCIL_READ_BASE_HI_DEFAULT                                        0x00000000
 #define mmDB_Z_WRITE_BASE_HI_DEFAULT                                             0x00000000
@@ -3062,6 +3063,7 @@
 #define mmPA_SU_OVER_RASTERIZATION_CNTL_DEFAULT                                  0x00000000
 #define mmPA_STEREO_CNTL_DEFAULT                                                 0x00000000
 #define mmPA_STATE_STEREO_X_DEFAULT                                              0x00000000
+#define mmPA_CL_VRS_CNTL_DEFAULT                                                 0x00000000
 #define mmPA_SU_POINT_SIZE_DEFAULT                                               0x00000000
 #define mmPA_SU_POINT_MINMAX_DEFAULT                                             0x00000000
 #define mmPA_SU_LINE_CNTL_DEFAULT                                                0x00000000
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h
index cbaad7d83194..66a4151fa676 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h
@@ -5379,6 +5379,8 @@
 #define mmDB_RESERVED_REG_1_BASE_IDX                                                                   1
 #define mmDB_RESERVED_REG_3                                                                            0x0017
 #define mmDB_RESERVED_REG_3_BASE_IDX                                                                   1
+#define mmDB_VRS_OVERRIDE_CNTL                                                                         0x0019
+#define mmDB_VRS_OVERRIDE_CNTL_BASE_IDX                                                                1
 #define mmDB_Z_READ_BASE_HI                                                                            0x001a
 #define mmDB_Z_READ_BASE_HI_BASE_IDX                                                                   1
 #define mmDB_STENCIL_READ_BASE_HI                                                                      0x001b
@@ -6049,6 +6051,8 @@
 #define mmPA_STEREO_CNTL_BASE_IDX                                                                      1
 #define mmPA_STATE_STEREO_X                                                                            0x0211
 #define mmPA_STATE_STEREO_X_BASE_IDX                                                                   1
+#define mmPA_CL_VRS_CNTL                                                                               0x0212
+#define mmPA_CL_VRS_CNTL_BASE_IDX                                                                      1
 #define mmPA_SU_POINT_SIZE                                                                             0x0280
 #define mmPA_SU_POINT_SIZE_BASE_IDX                                                                    1
 #define mmPA_SU_POINT_MINMAX                                                                           0x0281
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h
index c2d035ef3e94..aed799d9a0e8 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h
@@ -9777,6 +9777,7 @@
 #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_HTILE__SHIFT                                                         0x3
 #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_QUAD__SHIFT                                                          0x4
 #define DB_EXCEPTION_CONTROL__FORCE_SUMMARIZE__SHIFT                                                          0x8
+#define DB_EXCEPTION_CONTROL__FORCE_VRS_RATE_FINE__SHIFT                                                      0x10
 #define DB_EXCEPTION_CONTROL__DTAG_WATERMARK__SHIFT                                                           0x18
 #define DB_EXCEPTION_CONTROL__EARLY_Z_PANIC_DISABLE_MASK                                                      0x00000001L
 #define DB_EXCEPTION_CONTROL__LATE_Z_PANIC_DISABLE_MASK                                                       0x00000002L
@@ -9784,6 +9785,7 @@
 #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_HTILE_MASK                                                           0x00000008L
 #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_QUAD_MASK                                                            0x00000010L
 #define DB_EXCEPTION_CONTROL__FORCE_SUMMARIZE_MASK                                                            0x00000F00L
+#define DB_EXCEPTION_CONTROL__FORCE_VRS_RATE_FINE_MASK                                                        0x00FF0000L
 #define DB_EXCEPTION_CONTROL__DTAG_WATERMARK_MASK                                                             0x7F000000L
 //DB_DFSM_CONFIG
 #define DB_DFSM_CONFIG__BYPASS_DFSM__SHIFT                                                                    0x0
@@ -10076,6 +10078,7 @@
 #define CB_HW_CONTROL_3__DISABLE_NACK_PROCESSING_CM__SHIFT                                                    0x18
 #define CB_HW_CONTROL_3__DISABLE_NACK_COLOR_RD_WR_OPT__SHIFT                                                  0x19
 #define CB_HW_CONTROL_3__DISABLE_BLENDER_CLOCK_GATING__SHIFT                                                  0x1a
+#define CB_HW_CONTROL_3__DISABLE_DCC_VRS_OPT__SHIFT                                                           0x1c
 #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT__SHIFT                                                     0x1e
 #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_BC__SHIFT                                                  0x1f
 #define CB_HW_CONTROL_3__DISABLE_SLOW_MODE_EMPTY_HALF_QUAD_KILL_MASK                                          0x00000001L
@@ -10103,12 +10106,15 @@
 #define CB_HW_CONTROL_3__DISABLE_NACK_PROCESSING_CM_MASK                                                      0x01000000L
 #define CB_HW_CONTROL_3__DISABLE_NACK_COLOR_RD_WR_OPT_MASK                                                    0x02000000L
 #define CB_HW_CONTROL_3__DISABLE_BLENDER_CLOCK_GATING_MASK                                                    0x04000000L
+#define CB_HW_CONTROL_3__DISABLE_DCC_VRS_OPT_MASK                                                             0x10000000L
 #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_MASK                                                       0x40000000L
 #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_BC_MASK                                                    0x80000000L
 //CB_HW_CONTROL
 #define CB_HW_CONTROL__ALLOW_MRT_WITH_DUAL_SOURCE__SHIFT                                                      0x0
+#define CB_HW_CONTROL__DISABLE_VRS_FILLRATE_OPTIMIZATION__SHIFT                                               0x1
 #define CB_HW_CONTROL__DISABLE_FILLRATE_OPT_FIX_WITH_CFC__SHIFT                                               0x3
 #define CB_HW_CONTROL__DISABLE_POST_DCC_WITH_CFC_FIX__SHIFT                                                   0x4
+#define CB_HW_CONTROL__DISABLE_COMPRESS_1FRAG_WHEN_VRS_RATE_HINT_EN__SHIFT                                    0x5
 #define CB_HW_CONTROL__RMI_CREDITS__SHIFT                                                                     0x6
 #define CB_HW_CONTROL__CHICKEN_BITS__SHIFT                                                                    0xc
 #define CB_HW_CONTROL__DISABLE_FMASK_MULTI_MGCG_DOMAINS__SHIFT                                                0xf
@@ -10129,8 +10135,10 @@
 #define CB_HW_CONTROL__DISABLE_CC_IB_SERIALIZER_STATE_OPT__SHIFT                                              0x1e
 #define CB_HW_CONTROL__DISABLE_PIXEL_IN_QUAD_FIX_FOR_LINEAR_SURFACE__SHIFT                                    0x1f
 #define CB_HW_CONTROL__ALLOW_MRT_WITH_DUAL_SOURCE_MASK                                                        0x00000001L
+#define CB_HW_CONTROL__DISABLE_VRS_FILLRATE_OPTIMIZATION_MASK                                                 0x00000002L
 #define CB_HW_CONTROL__DISABLE_FILLRATE_OPT_FIX_WITH_CFC_MASK                                                 0x00000008L
 #define CB_HW_CONTROL__DISABLE_POST_DCC_WITH_CFC_FIX_MASK                                                     0x00000010L
+#define CB_HW_CONTROL__DISABLE_COMPRESS_1FRAG_WHEN_VRS_RATE_HINT_EN_MASK                                      0x00000020L
 #define CB_HW_CONTROL__RMI_CREDITS_MASK                                                                       0x00000FC0L
 #define CB_HW_CONTROL__CHICKEN_BITS_MASK                                                                      0x00007000L
 #define CB_HW_CONTROL__DISABLE_FMASK_MULTI_MGCG_DOMAINS_MASK                                                  0x00008000L
@@ -19881,6 +19889,7 @@
 #define DB_RENDER_OVERRIDE2__PRESERVE_SRESULTS__SHIFT                                                         0x16
 #define DB_RENDER_OVERRIDE2__DISABLE_FAST_PASS__SHIFT                                                         0x17
 #define DB_RENDER_OVERRIDE2__ALLOW_PARTIAL_RES_HIER_KILL__SHIFT                                               0x19
+#define DB_RENDER_OVERRIDE2__FORCE_VRS_RATE_FINE__SHIFT                                                       0x1a
 #define DB_RENDER_OVERRIDE2__CENTROID_COMPUTATION_MODE__SHIFT                                                 0x1b
 #define DB_RENDER_OVERRIDE2__PARTIAL_SQUAD_LAUNCH_CONTROL_MASK                                                0x00000003L
 #define DB_RENDER_OVERRIDE2__PARTIAL_SQUAD_LAUNCH_COUNTDOWN_MASK                                              0x0000001CL
@@ -19898,6 +19907,7 @@
 #define DB_RENDER_OVERRIDE2__PRESERVE_SRESULTS_MASK                                                           0x00400000L
 #define DB_RENDER_OVERRIDE2__DISABLE_FAST_PASS_MASK                                                           0x00800000L
 #define DB_RENDER_OVERRIDE2__ALLOW_PARTIAL_RES_HIER_KILL_MASK                                                 0x02000000L
+#define DB_RENDER_OVERRIDE2__FORCE_VRS_RATE_FINE_MASK                                                         0x04000000L
 #define DB_RENDER_OVERRIDE2__CENTROID_COMPUTATION_MODE_MASK                                                   0x18000000L
 //DB_HTILE_DATA_BASE
 #define DB_HTILE_DATA_BASE__BASE_256B__SHIFT                                                                  0x0
@@ -20021,6 +20031,13 @@
 //DB_RESERVED_REG_3
 #define DB_RESERVED_REG_3__FIELD_1__SHIFT                                                                     0x0
 #define DB_RESERVED_REG_3__FIELD_1_MASK                                                                       0x003FFFFFL
+//DB_VRS_OVERRIDE_CNTL
+#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_COMBINER_MODE__SHIFT                                          0x0
+#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_X__SHIFT                                                      0x4
+#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_Y__SHIFT                                                      0x6
+#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_COMBINER_MODE_MASK                                            0x00000007L
+#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_X_MASK                                                        0x00000030L
+#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_Y_MASK                                                        0x000000C0L
 //DB_Z_READ_BASE_HI
 #define DB_Z_READ_BASE_HI__BASE_HI__SHIFT                                                                     0x0
 #define DB_Z_READ_BASE_HI__BASE_HI_MASK                                                                       0x000000FFL
@@ -22598,6 +22615,7 @@
 #define PA_CL_VS_OUT_CNTL__VS_OUT_MISC_SIDE_BUS_ENA__SHIFT                                                    0x18
 #define PA_CL_VS_OUT_CNTL__USE_VTX_GS_CUT_FLAG__SHIFT                                                         0x19
 #define PA_CL_VS_OUT_CNTL__USE_VTX_LINE_WIDTH__SHIFT                                                          0x1b
+#define PA_CL_VS_OUT_CNTL__USE_VTX_VRS_RATE__SHIFT                                                            0x1c
 #define PA_CL_VS_OUT_CNTL__BYPASS_VTX_RATE_COMBINER__SHIFT                                                    0x1d
 #define PA_CL_VS_OUT_CNTL__BYPASS_PRIM_RATE_COMBINER__SHIFT                                                   0x1e
 #define PA_CL_VS_OUT_CNTL__CLIP_DIST_ENA_0_MASK                                                               0x00000001L
@@ -22627,6 +22645,7 @@
 #define PA_CL_VS_OUT_CNTL__VS_OUT_MISC_SIDE_BUS_ENA_MASK                                                      0x01000000L
 #define PA_CL_VS_OUT_CNTL__USE_VTX_GS_CUT_FLAG_MASK                                                           0x02000000L
 #define PA_CL_VS_OUT_CNTL__USE_VTX_LINE_WIDTH_MASK                                                            0x08000000L
+#define PA_CL_VS_OUT_CNTL__USE_VTX_VRS_RATE_MASK                                                              0x10000000L
 #define PA_CL_VS_OUT_CNTL__BYPASS_VTX_RATE_COMBINER_MASK                                                      0x20000000L
 #define PA_CL_VS_OUT_CNTL__BYPASS_PRIM_RATE_COMBINER_MASK                                                     0x40000000L
 //PA_CL_NANINF_CNTL
@@ -22740,6 +22759,19 @@
 //PA_STATE_STEREO_X
 #define PA_STATE_STEREO_X__STEREO_X_OFFSET__SHIFT                                                             0x0
 #define PA_STATE_STEREO_X__STEREO_X_OFFSET_MASK                                                               0xFFFFFFFFL
+//PA_CL_VRS_CNTL
+#define PA_CL_VRS_CNTL__VERTEX_RATE_COMBINER_MODE__SHIFT                                                      0x0
+#define PA_CL_VRS_CNTL__PRIMITIVE_RATE_COMBINER_MODE__SHIFT                                                   0x3
+#define PA_CL_VRS_CNTL__HTILE_RATE_COMBINER_MODE__SHIFT                                                       0x6
+#define PA_CL_VRS_CNTL__SAMPLE_ITER_COMBINER_MODE__SHIFT                                                      0x9
+#define PA_CL_VRS_CNTL__EXPOSE_VRS_PIXELS_MASK__SHIFT                                                         0xd
+#define PA_CL_VRS_CNTL__CMASK_RATE_HINT_FORCE_ZERO__SHIFT                                                     0xe
+#define PA_CL_VRS_CNTL__VERTEX_RATE_COMBINER_MODE_MASK                                                        0x00000007L
+#define PA_CL_VRS_CNTL__PRIMITIVE_RATE_COMBINER_MODE_MASK                                                     0x00000038L
+#define PA_CL_VRS_CNTL__HTILE_RATE_COMBINER_MODE_MASK                                                         0x000001C0L
+#define PA_CL_VRS_CNTL__SAMPLE_ITER_COMBINER_MODE_MASK                                                        0x00000E00L
+#define PA_CL_VRS_CNTL__EXPOSE_VRS_PIXELS_MASK_MASK                                                           0x00002000L
+#define PA_CL_VRS_CNTL__CMASK_RATE_HINT_FORCE_ZERO_MASK                                                       0x00004000L
 //PA_SU_POINT_SIZE
 #define PA_SU_POINT_SIZE__HEIGHT__SHIFT                                                                       0x0
 #define PA_SU_POINT_SIZE__WIDTH__SHIFT                                                                        0x10
@@ -23088,6 +23120,7 @@
 #define DB_HTILE_SURFACE__DST_OUTSIDE_ZERO_TO_ONE__SHIFT                                                      0x10
 #define DB_HTILE_SURFACE__RESERVED_FIELD_6__SHIFT                                                             0x11
 #define DB_HTILE_SURFACE__PIPE_ALIGNED__SHIFT                                                                 0x12
+#define DB_HTILE_SURFACE__VRS_HTILE_ENCODING__SHIFT                                                           0x13
 #define DB_HTILE_SURFACE__RESERVED_FIELD_1_MASK                                                               0x00000001L
 #define DB_HTILE_SURFACE__FULL_CACHE_MASK                                                                     0x00000002L
 #define DB_HTILE_SURFACE__RESERVED_FIELD_2_MASK                                                               0x00000004L
@@ -23097,6 +23130,7 @@
 #define DB_HTILE_SURFACE__DST_OUTSIDE_ZERO_TO_ONE_MASK                                                        0x00010000L
 #define DB_HTILE_SURFACE__RESERVED_FIELD_6_MASK                                                               0x00020000L
 #define DB_HTILE_SURFACE__PIPE_ALIGNED_MASK                                                                   0x00040000L
+#define DB_HTILE_SURFACE__VRS_HTILE_ENCODING_MASK                                                             0x00180000L
 //DB_SRESULTS_COMPARE_STATE0
 #define DB_SRESULTS_COMPARE_STATE0__COMPAREFUNC0__SHIFT                                                       0x0
 #define DB_SRESULTS_COMPARE_STATE0__COMPAREVALUE0__SHIFT                                                      0x4
@@ -24954,6 +24988,7 @@
 #define CB_COLOR0_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT                                                          0x1a
 #define CB_COLOR0_ATTRIB3__RESOURCE_LEVEL__SHIFT                                                              0x1b
 #define CB_COLOR0_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT                                                            0x1e
+#define CB_COLOR0_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT                                                        0x1f
 #define CB_COLOR0_ATTRIB3__MIP0_DEPTH_MASK                                                                    0x00001FFFL
 #define CB_COLOR0_ATTRIB3__META_LINEAR_MASK                                                                   0x00002000L
 #define CB_COLOR0_ATTRIB3__COLOR_SW_MODE_MASK                                                                 0x0007C000L
@@ -24962,6 +24997,7 @@
 #define CB_COLOR0_ATTRIB3__CMASK_PIPE_ALIGNED_MASK                                                            0x04000000L
 #define CB_COLOR0_ATTRIB3__RESOURCE_LEVEL_MASK                                                                0x38000000L
 #define CB_COLOR0_ATTRIB3__DCC_PIPE_ALIGNED_MASK                                                              0x40000000L
+#define CB_COLOR0_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK                                                          0x80000000L
 //CB_COLOR1_ATTRIB3
 #define CB_COLOR1_ATTRIB3__MIP0_DEPTH__SHIFT                                                                  0x0
 #define CB_COLOR1_ATTRIB3__META_LINEAR__SHIFT                                                                 0xd
@@ -24971,6 +25007,7 @@
 #define CB_COLOR1_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT                                                          0x1a
 #define CB_COLOR1_ATTRIB3__RESOURCE_LEVEL__SHIFT                                                              0x1b
 #define CB_COLOR1_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT                                                            0x1e
+#define CB_COLOR1_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT                                                        0x1f
 #define CB_COLOR1_ATTRIB3__MIP0_DEPTH_MASK                                                                    0x00001FFFL
 #define CB_COLOR1_ATTRIB3__META_LINEAR_MASK                                                                   0x00002000L
 #define CB_COLOR1_ATTRIB3__COLOR_SW_MODE_MASK                                                                 0x0007C000L
@@ -24979,6 +25016,7 @@
 #define CB_COLOR1_ATTRIB3__CMASK_PIPE_ALIGNED_MASK                                                            0x04000000L
 #define CB_COLOR1_ATTRIB3__RESOURCE_LEVEL_MASK                                                                0x38000000L
 #define CB_COLOR1_ATTRIB3__DCC_PIPE_ALIGNED_MASK                                                              0x40000000L
+#define CB_COLOR1_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK                                                          0x80000000L
 //CB_COLOR2_ATTRIB3
 #define CB_COLOR2_ATTRIB3__MIP0_DEPTH__SHIFT                                                                  0x0
 #define CB_COLOR2_ATTRIB3__META_LINEAR__SHIFT                                                                 0xd
@@ -24988,6 +25026,7 @@
 #define CB_COLOR2_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT                                                          0x1a
 #define CB_COLOR2_ATTRIB3__RESOURCE_LEVEL__SHIFT                                                              0x1b
 #define CB_COLOR2_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT                                                            0x1e
+#define CB_COLOR2_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT                                                        0x1f
 #define CB_COLOR2_ATTRIB3__MIP0_DEPTH_MASK                                                                    0x00001FFFL
 #define CB_COLOR2_ATTRIB3__META_LINEAR_MASK                                                                   0x00002000L
 #define CB_COLOR2_ATTRIB3__COLOR_SW_MODE_MASK                                                                 0x0007C000L
@@ -24996,6 +25035,7 @@
 #define CB_COLOR2_ATTRIB3__CMASK_PIPE_ALIGNED_MASK                                                            0x04000000L
 #define CB_COLOR2_ATTRIB3__RESOURCE_LEVEL_MASK                                                                0x38000000L
 #define CB_COLOR2_ATTRIB3__DCC_PIPE_ALIGNED_MASK                                                              0x40000000L
+#define CB_COLOR2_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK                                                          0x80000000L
 //CB_COLOR3_ATTRIB3
 #define CB_COLOR3_ATTRIB3__MIP0_DEPTH__SHIFT                                                                  0x0
 #define CB_COLOR3_ATTRIB3__META_LINEAR__SHIFT                                                                 0xd
@@ -25005,6 +25045,7 @@
 #define CB_COLOR3_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT                                                          0x1a
 #define CB_COLOR3_ATTRIB3__RESOURCE_LEVEL__SHIFT                                                              0x1b
 #define CB_COLOR3_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT                                                            0x1e
+#define CB_COLOR3_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT                                                        0x1f
 #define CB_COLOR3_ATTRIB3__MIP0_DEPTH_MASK                                                                    0x00001FFFL
 #define CB_COLOR3_ATTRIB3__META_LINEAR_MASK                                                                   0x00002000L
 #define CB_COLOR3_ATTRIB3__COLOR_SW_MODE_MASK                                                                 0x0007C000L
@@ -25013,6 +25054,7 @@
 #define CB_COLOR3_ATTRIB3__CMASK_PIPE_ALIGNED_MASK                                                            0x04000000L
 #define CB_COLOR3_ATTRIB3__RESOURCE_LEVEL_MASK                                                                0x38000000L
 #define CB_COLOR3_ATTRIB3__DCC_PIPE_ALIGNED_MASK                                                              0x40000000L
+#define CB_COLOR3_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK                                                          0x80000000L
 //CB_COLOR4_ATTRIB3
 #define CB_COLOR4_ATTRIB3__MIP0_DEPTH__SHIFT                                                                  0x0
 #define CB_COLOR4_ATTRIB3__META_LINEAR__SHIFT                                                                 0xd
@@ -25022,6 +25064,7 @@
 #define CB_COLOR4_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT                                                          0x1a
 #define CB_COLOR4_ATTRIB3__RESOURCE_LEVEL__SHIFT                                                              0x1b
 #define CB_COLOR4_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT                                                            0x1e
+#define CB_COLOR4_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT                                                        0x1f
 #define CB_COLOR4_ATTRIB3__MIP0_DEPTH_MASK                                                                    0x00001FFFL
 #define CB_COLOR4_ATTRIB3__META_LINEAR_MASK                                                                   0x00002000L
 #define CB_COLOR4_ATTRIB3__COLOR_SW_MODE_MASK                                                                 0x0007C000L
@@ -25030,6 +25073,7 @@
 #define CB_COLOR4_ATTRIB3__CMASK_PIPE_ALIGNED_MASK                                                            0x04000000L
 #define CB_COLOR4_ATTRIB3__RESOURCE_LEVEL_MASK                                                                0x38000000L
 #define CB_COLOR4_ATTRIB3__DCC_PIPE_ALIGNED_MASK                                                              0x40000000L
+#define CB_COLOR4_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK                                                          0x80000000L
 //CB_COLOR5_ATTRIB3
 #define CB_COLOR5_ATTRIB3__MIP0_DEPTH__SHIFT                                                                  0x0
 #define CB_COLOR5_ATTRIB3__META_LINEAR__SHIFT                                                                 0xd
@@ -25039,6 +25083,7 @@
 #define CB_COLOR5_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT                                                          0x1a
 #define CB_COLOR5_ATTRIB3__RESOURCE_LEVEL__SHIFT                                                              0x1b
 #define CB_COLOR5_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT                                                            0x1e
+#define CB_COLOR5_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT                                                        0x1f
 #define CB_COLOR5_ATTRIB3__MIP0_DEPTH_MASK                                                                    0x00001FFFL
 #define CB_COLOR5_ATTRIB3__META_LINEAR_MASK                                                                   0x00002000L
 #define CB_COLOR5_ATTRIB3__COLOR_SW_MODE_MASK                                                                 0x0007C000L
@@ -25047,6 +25092,7 @@
 #define CB_COLOR5_ATTRIB3__CMASK_PIPE_ALIGNED_MASK                                                            0x04000000L
 #define CB_COLOR5_ATTRIB3__RESOURCE_LEVEL_MASK                                                                0x38000000L
 #define CB_COLOR5_ATTRIB3__DCC_PIPE_ALIGNED_MASK                                                              0x40000000L
+#define CB_COLOR5_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK                                                          0x80000000L
 //CB_COLOR6_ATTRIB3
 #define CB_COLOR6_ATTRIB3__MIP0_DEPTH__SHIFT                                                                  0x0
 #define CB_COLOR6_ATTRIB3__META_LINEAR__SHIFT                                                                 0xd
@@ -25056,6 +25102,7 @@
 #define CB_COLOR6_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT                                                          0x1a
 #define CB_COLOR6_ATTRIB3__RESOURCE_LEVEL__SHIFT                                                              0x1b
 #define CB_COLOR6_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT                                                            0x1e
+#define CB_COLOR6_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT                                                        0x1f
 #define CB_COLOR6_ATTRIB3__MIP0_DEPTH_MASK                                                                    0x00001FFFL
 #define CB_COLOR6_ATTRIB3__META_LINEAR_MASK                                                                   0x00002000L
 #define CB_COLOR6_ATTRIB3__COLOR_SW_MODE_MASK                                                                 0x0007C000L
@@ -25064,6 +25111,7 @@
 #define CB_COLOR6_ATTRIB3__CMASK_PIPE_ALIGNED_MASK                                                            0x04000000L
 #define CB_COLOR6_ATTRIB3__RESOURCE_LEVEL_MASK                                                                0x38000000L
 #define CB_COLOR6_ATTRIB3__DCC_PIPE_ALIGNED_MASK                                                              0x40000000L
+#define CB_COLOR6_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK                                                          0x80000000L
 //CB_COLOR7_ATTRIB3
 #define CB_COLOR7_ATTRIB3__MIP0_DEPTH__SHIFT                                                                  0x0
 #define CB_COLOR7_ATTRIB3__META_LINEAR__SHIFT                                                                 0xd
@@ -25073,6 +25121,7 @@
 #define CB_COLOR7_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT                                                          0x1a
 #define CB_COLOR7_ATTRIB3__RESOURCE_LEVEL__SHIFT                                                              0x1b
 #define CB_COLOR7_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT                                                            0x1e
+#define CB_COLOR7_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT                                                        0x1f
 #define CB_COLOR7_ATTRIB3__MIP0_DEPTH_MASK                                                                    0x00001FFFL
 #define CB_COLOR7_ATTRIB3__META_LINEAR_MASK                                                                   0x00002000L
 #define CB_COLOR7_ATTRIB3__COLOR_SW_MODE_MASK                                                                 0x0007C000L
@@ -25081,6 +25130,7 @@
 #define CB_COLOR7_ATTRIB3__CMASK_PIPE_ALIGNED_MASK                                                            0x04000000L
 #define CB_COLOR7_ATTRIB3__RESOURCE_LEVEL_MASK                                                                0x38000000L
 #define CB_COLOR7_ATTRIB3__DCC_PIPE_ALIGNED_MASK                                                              0x40000000L
+#define CB_COLOR7_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK                                                          0x80000000L
 
 
 // addressBlock: gc_gfxudec
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_offset.h
index f41556abfbbc..629a8a3b55e9 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_offset.h
@@ -205,6 +205,8 @@
 #define mmGCEA_EDC_CNT2_BASE_IDX                                                                       0
 #define mmGCEA_EDC_CNT3                                                                                0x071b
 #define mmGCEA_EDC_CNT3_BASE_IDX                                                                       0
+#define mmGCEA_ERR_STATUS                                                                              0x0712
+#define mmGCEA_ERR_STATUS_BASE_IDX                                                                     0
 
 // addressBlock: gc_gfxudec
 // base address: 0x30000
@@ -261,4 +263,4 @@
 #define mmRLC_EDC_CNT2                                                                                 0x4d41
 #define mmRLC_EDC_CNT2_BASE_IDX                                                                        1
 
-#endif
\ No newline at end of file
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_offset.h
index 07aceffb108a..524ba4421c17 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_offset.h
@@ -151,6 +151,8 @@
 #define mmUVD_LMI_CTRL2_BASE_IDX                                                                       1
 #define mmUVD_MASTINT_EN                                                                               0x0540
 #define mmUVD_MASTINT_EN_BASE_IDX                                                                      1
+#define mmUVD_FW_STATUS                                                                                0x0557
+#define mmUVD_FW_STATUS_BASE_IDX                                                                       1
 #define mmJPEG_CGC_CTRL                                                                                0x0565
 #define mmJPEG_CGC_CTRL_BASE_IDX                                                                       1
 #define mmUVD_LMI_CTRL                                                                                 0x0566
@@ -219,4 +221,5 @@
 #define mmUVD_CONTEXT_ID2_BASE_IDX                                                                     1
 
 
+
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_sh_mask.h
index b427f73bd536..919be1842bd5 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_7_0_sh_mask.h
@@ -807,5 +807,25 @@
 #define UVD_CONTEXT_ID2__CONTEXT_ID2__SHIFT                                                                   0x0
 #define UVD_CONTEXT_ID2__CONTEXT_ID2_MASK                                                                     0xFFFFFFFFL
 
+//UVD_FW_STATUS
+#define UVD_FW_STATUS__BUSY__SHIFT                                                                            0x0
+#define UVD_FW_STATUS__ACTIVE__SHIFT                                                                          0x1
+#define UVD_FW_STATUS__SEND_EFUSE_REQ__SHIFT                                                                  0x2
+#define UVD_FW_STATUS__DONE__SHIFT                                                                            0x8
+#define UVD_FW_STATUS__PASS__SHIFT                                                                            0x10
+#define UVD_FW_STATUS__FAIL__SHIFT                                                                            0x11
+#define UVD_FW_STATUS__INVALID_LEN__SHIFT                                                                     0x12
+#define UVD_FW_STATUS__INVALID_0_PADDING__SHIFT                                                               0x13
+#define UVD_FW_STATUS__INVALID_NONCE__SHIFT                                                                   0x14
+#define UVD_FW_STATUS__BUSY_MASK                                                                              0x00000001L
+#define UVD_FW_STATUS__ACTIVE_MASK                                                                            0x00000002L
+#define UVD_FW_STATUS__SEND_EFUSE_REQ_MASK                                                                    0x00000004L
+#define UVD_FW_STATUS__DONE_MASK                                                                              0x00000100L
+#define UVD_FW_STATUS__PASS_MASK                                                                              0x00010000L
+#define UVD_FW_STATUS__FAIL_MASK                                                                              0x00020000L
+#define UVD_FW_STATUS__INVALID_LEN_MASK                                                                       0x00040000L
+#define UVD_FW_STATUS__INVALID_0_PADDING_MASK                                                                 0x00080000L
+#define UVD_FW_STATUS__INVALID_NONCE_MASK                                                                     0x00100000L
+
 
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h
index c0efd90808f2..58cf7adb9d54 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h
@@ -2393,6 +2393,7 @@
 #define VCN_FEATURES__HAS_MJPEG2_IDCT_DEC__SHIFT                                                              0x7
 #define VCN_FEATURES__HAS_SCLR_DEC__SHIFT                                                                     0x8
 #define VCN_FEATURES__HAS_VP9_DEC__SHIFT                                                                      0x9
+#define VCN_FEATURES__HAS_AV1_DEC__SHIFT                                                                      0xa
 #define VCN_FEATURES__HAS_EFC_ENC__SHIFT                                                                      0xb
 #define VCN_FEATURES__HAS_EFC_HDR2SDR_ENC__SHIFT                                                              0xc
 #define VCN_FEATURES__HAS_DUAL_MJPEG_DEC__SHIFT                                                               0xd
@@ -2407,6 +2408,7 @@
 #define VCN_FEATURES__HAS_MJPEG2_IDCT_DEC_MASK                                                                0x00000080L
 #define VCN_FEATURES__HAS_SCLR_DEC_MASK                                                                       0x00000100L
 #define VCN_FEATURES__HAS_VP9_DEC_MASK                                                                        0x00000200L
+#define VCN_FEATURES__HAS_AV1_DEC_MASK                                                                        0x00000400L
 #define VCN_FEATURES__HAS_EFC_ENC_MASK                                                                        0x00000800L
 #define VCN_FEATURES__HAS_EFC_HDR2SDR_ENC_MASK                                                                0x00001000L
 #define VCN_FEATURES__HAS_DUAL_MJPEG_DEC_MASK                                                                 0x00002000L
@@ -2809,8 +2811,10 @@
 #define UVD_SUVD_CGC_GATE__IME_HEVC__SHIFT                                                                    0x18
 #define UVD_SUVD_CGC_GATE__EFC__SHIFT                                                                         0x19
 #define UVD_SUVD_CGC_GATE__SAOE__SHIFT                                                                        0x1a
+#define UVD_SUVD_CGC_GATE__SRE_AV1__SHIFT                                                                     0x1b
 #define UVD_SUVD_CGC_GATE__FBC_PCLK__SHIFT                                                                    0x1c
 #define UVD_SUVD_CGC_GATE__FBC_CCLK__SHIFT                                                                    0x1d
+#define UVD_SUVD_CGC_GATE__SCM_AV1__SHIFT                                                                     0x1e
 #define UVD_SUVD_CGC_GATE__SMPA__SHIFT                                                                        0x1f
 #define UVD_SUVD_CGC_GATE__SRE_MASK                                                                           0x00000001L
 #define UVD_SUVD_CGC_GATE__SIT_MASK                                                                           0x00000002L
@@ -2839,8 +2843,10 @@
 #define UVD_SUVD_CGC_GATE__IME_HEVC_MASK                                                                      0x01000000L
 #define UVD_SUVD_CGC_GATE__EFC_MASK                                                                           0x02000000L
 #define UVD_SUVD_CGC_GATE__SAOE_MASK                                                                          0x04000000L
+#define UVD_SUVD_CGC_GATE__SRE_AV1_MASK                                                                       0x08000000L
 #define UVD_SUVD_CGC_GATE__FBC_PCLK_MASK                                                                      0x10000000L
 #define UVD_SUVD_CGC_GATE__FBC_CCLK_MASK                                                                      0x20000000L
+#define UVD_SUVD_CGC_GATE__SCM_AV1_MASK                                                                       0x40000000L
 #define UVD_SUVD_CGC_GATE__SMPA_MASK                                                                          0x80000000L
 //UVD_SUVD_CGC_STATUS
 #define UVD_SUVD_CGC_STATUS__SRE_VCLK__SHIFT                                                                  0x0
@@ -2873,6 +2879,8 @@
 #define UVD_SUVD_CGC_STATUS__IME_HEVC_DCLK__SHIFT                                                             0x1b
 #define UVD_SUVD_CGC_STATUS__EFC_DCLK__SHIFT                                                                  0x1c
 #define UVD_SUVD_CGC_STATUS__SAOE_DCLK__SHIFT                                                                 0x1d
+#define UVD_SUVD_CGC_STATUS__SRE_AV1_VCLK__SHIFT                                                              0x1e
+#define UVD_SUVD_CGC_STATUS__SCM_AV1_DCLK__SHIFT                                                              0x1f
 #define UVD_SUVD_CGC_STATUS__SRE_VCLK_MASK                                                                    0x00000001L
 #define UVD_SUVD_CGC_STATUS__SRE_DCLK_MASK                                                                    0x00000002L
 #define UVD_SUVD_CGC_STATUS__SIT_DCLK_MASK                                                                    0x00000004L
@@ -2903,6 +2911,8 @@
 #define UVD_SUVD_CGC_STATUS__IME_HEVC_DCLK_MASK                                                               0x08000000L
 #define UVD_SUVD_CGC_STATUS__EFC_DCLK_MASK                                                                    0x10000000L
 #define UVD_SUVD_CGC_STATUS__SAOE_DCLK_MASK                                                                   0x20000000L
+#define UVD_SUVD_CGC_STATUS__SRE_AV1_VCLK_MASK                                                                0x40000000L
+#define UVD_SUVD_CGC_STATUS__SCM_AV1_DCLK_MASK                                                                0x80000000L
 //UVD_SUVD_CGC_CTRL
 #define UVD_SUVD_CGC_CTRL__SRE_MODE__SHIFT                                                                    0x0
 #define UVD_SUVD_CGC_CTRL__SIT_MODE__SHIFT                                                                    0x1
@@ -2919,6 +2929,8 @@
 #define UVD_SUVD_CGC_CTRL__SMPA_MODE__SHIFT                                                                   0xc
 #define UVD_SUVD_CGC_CTRL__MPBE0_MODE__SHIFT                                                                  0xd
 #define UVD_SUVD_CGC_CTRL__MPBE1_MODE__SHIFT                                                                  0xe
+#define UVD_SUVD_CGC_CTRL__SIT_AV1_MODE__SHIFT                                                                0xf
+#define UVD_SUVD_CGC_CTRL__SDB_AV1_MODE__SHIFT                                                                0x10
 #define UVD_SUVD_CGC_CTRL__MPC1_MODE__SHIFT                                                                   0x11
 #define UVD_SUVD_CGC_CTRL__FBC_PCLK__SHIFT                                                                    0x1c
 #define UVD_SUVD_CGC_CTRL__FBC_CCLK__SHIFT                                                                    0x1d
@@ -2937,6 +2949,8 @@
 #define UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK                                                                     0x00001000L
 #define UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK                                                                    0x00002000L
 #define UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK                                                                    0x00004000L
+#define UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK                                                                  0x00008000L
+#define UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK                                                                  0x00010000L
 #define UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK                                                                     0x00020000L
 #define UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK                                                                      0x10000000L
 #define UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK                                                                      0x20000000L
@@ -3658,6 +3672,8 @@
 #define UVD_SUVD_CGC_STATUS2__SMPA_VCLK__SHIFT                                                                0x0
 #define UVD_SUVD_CGC_STATUS2__SMPA_DCLK__SHIFT                                                                0x1
 #define UVD_SUVD_CGC_STATUS2__MPBE1_DCLK__SHIFT                                                               0x3
+#define UVD_SUVD_CGC_STATUS2__SIT_AV1_DCLK__SHIFT                                                             0x4
+#define UVD_SUVD_CGC_STATUS2__SDB_AV1_DCLK__SHIFT                                                             0x5
 #define UVD_SUVD_CGC_STATUS2__MPC1_DCLK__SHIFT                                                                0x6
 #define UVD_SUVD_CGC_STATUS2__MPC1_SCLK__SHIFT                                                                0x7
 #define UVD_SUVD_CGC_STATUS2__MPC1_VCLK__SHIFT                                                                0x8
@@ -3666,6 +3682,8 @@
 #define UVD_SUVD_CGC_STATUS2__SMPA_VCLK_MASK                                                                  0x00000001L
 #define UVD_SUVD_CGC_STATUS2__SMPA_DCLK_MASK                                                                  0x00000002L
 #define UVD_SUVD_CGC_STATUS2__MPBE1_DCLK_MASK                                                                 0x00000008L
+#define UVD_SUVD_CGC_STATUS2__SIT_AV1_DCLK_MASK                                                               0x00000010L
+#define UVD_SUVD_CGC_STATUS2__SDB_AV1_DCLK_MASK                                                               0x00000020L
 #define UVD_SUVD_CGC_STATUS2__MPC1_DCLK_MASK                                                                  0x00000040L
 #define UVD_SUVD_CGC_STATUS2__MPC1_SCLK_MASK                                                                  0x00000080L
 #define UVD_SUVD_CGC_STATUS2__MPC1_VCLK_MASK                                                                  0x00000100L
@@ -3674,25 +3692,41 @@
 //UVD_SUVD_CGC_GATE2
 #define UVD_SUVD_CGC_GATE2__MPBE0__SHIFT                                                                      0x0
 #define UVD_SUVD_CGC_GATE2__MPBE1__SHIFT                                                                      0x1
+#define UVD_SUVD_CGC_GATE2__SIT_AV1__SHIFT                                                                    0x2
+#define UVD_SUVD_CGC_GATE2__SDB_AV1__SHIFT                                                                    0x3
 #define UVD_SUVD_CGC_GATE2__MPC1__SHIFT                                                                       0x4
 #define UVD_SUVD_CGC_GATE2__MPBE0_MASK                                                                        0x00000001L
 #define UVD_SUVD_CGC_GATE2__MPBE1_MASK                                                                        0x00000002L
+#define UVD_SUVD_CGC_GATE2__SIT_AV1_MASK                                                                      0x00000004L
+#define UVD_SUVD_CGC_GATE2__SDB_AV1_MASK                                                                      0x00000008L
 #define UVD_SUVD_CGC_GATE2__MPC1_MASK                                                                         0x00000010L
 //UVD_SUVD_INT_STATUS2
 #define UVD_SUVD_INT_STATUS2__SMPA_FUNC_INT__SHIFT                                                            0x0
 #define UVD_SUVD_INT_STATUS2__SMPA_ERR_INT__SHIFT                                                             0x5
+#define UVD_SUVD_INT_STATUS2__SDB_AV1_FUNC_INT__SHIFT                                                         0x6
+#define UVD_SUVD_INT_STATUS2__SDB_AV1_ERR_INT__SHIFT                                                          0xb
 #define UVD_SUVD_INT_STATUS2__SMPA_FUNC_INT_MASK                                                              0x0000001FL
 #define UVD_SUVD_INT_STATUS2__SMPA_ERR_INT_MASK                                                               0x00000020L
+#define UVD_SUVD_INT_STATUS2__SDB_AV1_FUNC_INT_MASK                                                           0x000007C0L
+#define UVD_SUVD_INT_STATUS2__SDB_AV1_ERR_INT_MASK                                                            0x00000800L
 //UVD_SUVD_INT_EN2
 #define UVD_SUVD_INT_EN2__SMPA_FUNC_INT_EN__SHIFT                                                             0x0
 #define UVD_SUVD_INT_EN2__SMPA_ERR_INT_EN__SHIFT                                                              0x5
+#define UVD_SUVD_INT_EN2__SDB_AV1_FUNC_INT_EN__SHIFT                                                          0x6
+#define UVD_SUVD_INT_EN2__SDB_AV1_ERR_INT_EN__SHIFT                                                           0xb
 #define UVD_SUVD_INT_EN2__SMPA_FUNC_INT_EN_MASK                                                               0x0000001FL
 #define UVD_SUVD_INT_EN2__SMPA_ERR_INT_EN_MASK                                                                0x00000020L
+#define UVD_SUVD_INT_EN2__SDB_AV1_FUNC_INT_EN_MASK                                                            0x000007C0L
+#define UVD_SUVD_INT_EN2__SDB_AV1_ERR_INT_EN_MASK                                                             0x00000800L
 //UVD_SUVD_INT_ACK2
 #define UVD_SUVD_INT_ACK2__SMPA_FUNC_INT_ACK__SHIFT                                                           0x0
 #define UVD_SUVD_INT_ACK2__SMPA_ERR_INT_ACK__SHIFT                                                            0x5
+#define UVD_SUVD_INT_ACK2__SDB_AV1_FUNC_INT_ACK__SHIFT                                                        0x6
+#define UVD_SUVD_INT_ACK2__SDB_AV1_ERR_INT_ACK__SHIFT                                                         0xb
 #define UVD_SUVD_INT_ACK2__SMPA_FUNC_INT_ACK_MASK                                                             0x0000001FL
 #define UVD_SUVD_INT_ACK2__SMPA_ERR_INT_ACK_MASK                                                              0x00000020L
+#define UVD_SUVD_INT_ACK2__SDB_AV1_FUNC_INT_ACK_MASK                                                          0x000007C0L
+#define UVD_SUVD_INT_ACK2__SDB_AV1_ERR_INT_ACK_MASK                                                           0x00000800L
 
 
 // addressBlock: uvd0_ecpudec
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index fc592f60e6a0..95c656d205ed 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -212,6 +212,15 @@ struct tile_config {
  * IH ring entry. This function allows the KFD ISR to get the VMID
  * from the fault status register as early as possible.
  *
+ * @get_cu_occupancy: Function pointer that returns to caller the number
+ * of wave fronts that are in flight for all of the queues of a process
+ * as identified by its pasid. It is important to note that the value
+ * returned by this function is a snapshot of current moment and cannot
+ * guarantee any minimum for the number of waves in-flight. This function
+ * is defined for devices that belong to GFX9 and later GFX families. Care
+ * must be taken in calling this function as it is not defined for devices
+ * that belong to GFX8 and below GFX families.
+ *
  * This structure contains function pointers to services that the kgd driver
  * provides to amdkfd driver.
  *
@@ -222,7 +231,7 @@ struct kfd2kgd_calls {
 			uint32_t sh_mem_config,	uint32_t sh_mem_ape1_base,
 			uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases);
 
-	int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, unsigned int pasid,
+	int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid);
 
 	int (*init_interrupts)(struct kgd_dev *kgd, uint32_t pipe_id);
@@ -286,6 +295,9 @@ struct kfd2kgd_calls {
 	void (*set_vm_context_page_table_base)(struct kgd_dev *kgd,
 			uint32_t vmid, uint64_t page_table_base);
 	uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd);
+
+	void (*get_cu_occupancy)(struct kgd_dev *kgd, int pasid, int *wave_cnt,
+			int *max_waves_per_cu);
 };
 
 #endif	/* KGD_KFD_INTERFACE_H_INCLUDED */
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 0aec28fda058..94132c70d7af 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -281,6 +281,7 @@ struct amd_pm_funcs {
 	int (*get_power_limit)(void *handle, uint32_t *limit, bool default_limit);
 	int (*get_power_profile_mode)(void *handle, char *buf);
 	int (*set_power_profile_mode)(void *handle, long *input, uint32_t size);
+	int (*set_fine_grain_clk_vol)(void *handle, uint32_t type, long *input, uint32_t size);
 	int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size);
 	int (*set_mp1_state)(void *handle, enum pp_mp1_state mp1_state);
 	int (*smu_i2c_bus_access)(void *handle, bool acquire);
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 2d924e88a215..529816637c73 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -827,6 +827,18 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 			return -EINVAL;
 		}
 	} else {
+
+		if (adev->powerplay.pp_funcs->set_fine_grain_clk_vol) {
+			ret = amdgpu_dpm_set_fine_grain_clk_vol(adev, type,
+								parameter,
+								parameter_size);
+			if (ret) {
+				pm_runtime_mark_last_busy(ddev->dev);
+				pm_runtime_put_autosuspend(ddev->dev);
+				return -EINVAL;
+			}
+		}
+
 		if (adev->powerplay.pp_funcs->odn_edit_dpm_table) {
 			ret = amdgpu_dpm_odn_edit_dpm_table(adev, type,
 						parameter, parameter_size);
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index dff4a5f99bb0..f6e0e7d8a007 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -349,6 +349,10 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->set_power_profile_mode(\
 			(adev)->powerplay.pp_handle, parameter, size))
 
+#define amdgpu_dpm_set_fine_grain_clk_vol(adev, type, parameter, size) \
+		((adev)->powerplay.pp_funcs->set_fine_grain_clk_vol(\
+			(adev)->powerplay.pp_handle, type, parameter, size))
+
 #define amdgpu_dpm_odn_edit_dpm_table(adev, type, parameter, size) \
 		((adev)->powerplay.pp_funcs->odn_edit_dpm_table(\
 			(adev)->powerplay.pp_handle, type, parameter, size))
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
index d22a759b6b43..44fd0cd069de 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
@@ -270,6 +270,7 @@ struct smu_table_context
 	 */
 	struct smu_table		driver_table;
 	struct smu_table		memory_pool;
+	struct smu_table		dummy_read_1_table;
 	uint8_t                         thermal_controller_type;
 
 	void				*overdrive_table;
@@ -452,6 +453,7 @@ struct smu_context
 
 	struct work_struct throttling_logging_work;
 	atomic64_t throttle_int_counter;
+	struct work_struct interrupt_work;
 
 	unsigned fan_max_rpm;
 	unsigned manual_fan_speed_rpm;
@@ -500,7 +502,7 @@ struct pptable_funcs {
 	bool (*is_dpm_running)(struct smu_context *smu);
 	int (*get_fan_speed_rpm)(struct smu_context *smu, uint32_t *speed);
 	int (*set_watermarks_table)(struct smu_context *smu,
-				    struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges);
+				    struct pp_smu_wm_range_sets *clock_ranges);
 	int (*get_thermal_temperature_range)(struct smu_context *smu, struct smu_temperature_range *range);
 	int (*get_uclk_dpm_states)(struct smu_context *smu, uint32_t *clocks_in_khz, uint32_t *num_states);
 	int (*set_default_od_settings)(struct smu_context *smu);
@@ -590,7 +592,6 @@ struct pptable_funcs {
 	int (*mode2_reset)(struct smu_context *smu);
 	int (*get_dpm_ultimate_freq)(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *min, uint32_t *max);
 	int (*set_soft_freq_limited_range)(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t min, uint32_t max);
-	int (*disable_umc_cdr_12gbps_workaround)(struct smu_context *smu);
 	int (*set_power_source)(struct smu_context *smu, enum smu_power_src_type power_src);
 	void (*log_thermal_throttling_event)(struct smu_context *smu);
 	size_t (*get_pp_feature_mask)(struct smu_context *smu, char *buf);
@@ -600,6 +601,8 @@ struct pptable_funcs {
 	int (*gfx_ulv_control)(struct smu_context *smu, bool enablement);
 	int (*deep_sleep_control)(struct smu_context *smu, bool enablement);
 	int (*get_fan_parameters)(struct smu_context *smu);
+	int (*post_init)(struct smu_context *smu);
+	void (*interrupt_work)(struct smu_context *smu);
 };
 
 typedef enum {
@@ -703,7 +706,6 @@ int smu_set_fan_speed_percent(struct smu_context *smu, uint32_t speed);
 int smu_get_fan_speed_rpm(struct smu_context *smu, uint32_t *speed);
 
 int smu_set_deep_sleep_dcefclk(struct smu_context *smu, int clk);
-int smu_set_active_display_count(struct smu_context *smu, uint32_t count);
 
 int smu_get_clock_by_type(struct smu_context *smu,
 			  enum amd_pp_clock_type type,
@@ -755,7 +757,7 @@ enum amd_pm_state_type smu_get_current_power_state(struct smu_context *smu);
 int smu_write_watermarks_table(struct smu_context *smu);
 int smu_set_watermarks_for_clock_ranges(
 		struct smu_context *smu,
-		struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges);
+		struct pp_smu_wm_range_sets *clock_ranges);
 
 /* smu to display interface */
 extern int smu_display_configuration_change(struct smu_context *smu, const
diff --git a/drivers/gpu/drm/amd/pm/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
index 1b3529efc91e..3898a95ec28b 100644
--- a/drivers/gpu/drm/amd/pm/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
@@ -340,6 +340,9 @@ struct pp_hwmgr_func {
 	int (*odn_edit_dpm_table)(struct pp_hwmgr *hwmgr,
 					enum PP_OD_DPM_TABLE_COMMAND type,
 					long *input, uint32_t size);
+	int (*set_fine_grain_clk_vol)(struct pp_hwmgr *hwmgr,
+				      enum PP_OD_DPM_TABLE_COMMAND type,
+				      long *input, uint32_t size);
 	int (*set_power_limit)(struct pp_hwmgr *hwmgr, uint32_t n);
 	int (*powergate_mmhub)(struct pp_hwmgr *hwmgr);
 	int (*smus_notify_pwe)(struct pp_hwmgr *hwmgr);
@@ -347,6 +350,8 @@ struct pp_hwmgr_func {
 	int (*enable_mgpu_fan_boost)(struct pp_hwmgr *hwmgr);
 	int (*set_hard_min_dcefclk_by_freq)(struct pp_hwmgr *hwmgr, uint32_t clock);
 	int (*set_hard_min_fclk_by_freq)(struct pp_hwmgr *hwmgr, uint32_t clock);
+	int (*set_hard_min_gfxclk_by_freq)(struct pp_hwmgr *hwmgr, uint32_t clock);
+	int (*set_soft_max_gfxclk_by_freq)(struct pp_hwmgr *hwmgr, uint32_t clock);
 	int (*get_asic_baco_capability)(struct pp_hwmgr *hwmgr, bool *cap);
 	int (*get_asic_baco_state)(struct pp_hwmgr *hwmgr, enum BACO_STATE *state);
 	int (*set_asic_baco_state)(struct pp_hwmgr *hwmgr, enum BACO_STATE state);
diff --git a/drivers/gpu/drm/amd/pm/inc/smu10_driver_if.h b/drivers/gpu/drm/amd/pm/inc/smu10_driver_if.h
index dea8fe93da63..c498158771cc 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu10_driver_if.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu10_driver_if.h
@@ -54,7 +54,8 @@ typedef struct {
 	uint16_t MaxMclk;
 
 	uint8_t  WmSetting;
-	uint8_t  Padding[3];
+	uint8_t  WmType;
+	uint8_t  Padding[2];
 } WatermarkRowGeneric_t;
 
 #define NUM_WM_RANGES 4
diff --git a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h
index 5ef9c92f57c4..1275246769d9 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_sienna_cichlid.h
@@ -27,9 +27,9 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if 
 // any structure is changed in this file
-#define SMU11_DRIVER_IF_VERSION 0x35
+#define SMU11_DRIVER_IF_VERSION 0x39
 
-#define PPTABLE_Sienna_Cichlid_SMU_VERSION 5
+#define PPTABLE_Sienna_Cichlid_SMU_VERSION 6
 
 #define NUM_GFXCLK_DPM_LEVELS  16
 #define NUM_SMNCLK_DPM_LEVELS  2
@@ -169,7 +169,7 @@ typedef enum {
 #define DPM_OVERRIDE_DISABLE_DFLL_PLL_SHUTDOWN       0x00000200
 #define DPM_OVERRIDE_DISABLE_MEMORY_TEMPERATURE_READ 0x00000400
 #define DPM_OVERRIDE_DISABLE_VOLT_LINK_VCN_DCEFCLK   0x00000800
-#define DPM_OVERRIDE_ENABLE_FAST_FCLK_TIMER          0x00001000
+#define DPM_OVERRIDE_DISABLE_FAST_FCLK_TIMER         0x00001000
 #define DPM_OVERRIDE_DISABLE_VCN_PG                  0x00002000
 #define DPM_OVERRIDE_DISABLE_FMAX_VMAX               0x00004000
 
@@ -793,8 +793,18 @@ typedef struct {
 
   // SECTION: Sku Reserved
   uint8_t          CustomerVariant;
-  uint8_t          Spare[3];
-  uint32_t         SkuReserved[14];
+
+  //VC BTC parameters are only applicable to VDD_GFX domain
+  uint8_t          VcBtcEnabled;
+  uint16_t         VcBtcVminT0;                 // T0_VMIN
+  uint16_t         VcBtcFixedVminAgingOffset;   // FIXED_VMIN_AGING_OFFSET 
+  uint16_t         VcBtcVmin2PsmDegrationGb;    // VMIN_TO_PSM_DEGRADATION_GB 
+  uint32_t         VcBtcPsmA;                   // A_PSM
+  uint32_t         VcBtcPsmB;                   // B_PSM
+  uint32_t         VcBtcVminA;                  // A_VMIN
+  uint32_t         VcBtcVminB;                  // B_VMIN  
+  
+  uint32_t         SkuReserved[9];
 
 
   // MAJOR SECTION: BOARD PARAMETERS
@@ -952,7 +962,7 @@ typedef struct {
   uint8_t                FanLinearPwmPoints[NUM_OD_FAN_MAX_POINTS];
   uint8_t                FanLinearTempPoints[NUM_OD_FAN_MAX_POINTS];
   uint16_t               MaxOpTemp;            // Degree Celcius
-  uint16_t               Padding_16[1];
+  int16_t                VddGfxOffset;         // in mV
   uint8_t                FanZeroRpmEnable;
   uint8_t                FanZeroRpmStopTemp;
   uint8_t                FanMode;
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_11_0_cdr_table.h b/drivers/gpu/drm/amd/pm/inc/smu_11_0_cdr_table.h
new file mode 100644
index 000000000000..beab6d7b28b7
--- /dev/null
+++ b/drivers/gpu/drm/amd/pm/inc/smu_11_0_cdr_table.h
@@ -0,0 +1,194 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+
+#ifndef SMU_11_0_CDR_TABLE
+#define SMU_11_0_CDR_TABLE
+
+
+#pragma pack(push, 1)
+
+/// CDR table : PRBS sequence for DQ toggles
+
+/*static unsigned int NoDbiPrbs7[] =
+{
+//256 bytes, 256 byte aligned
+0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+};
+
+
+static unsigned int DbiPrbs7[] =
+{
+// 256 bytes, 256 byte aligned
+0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+};
+*/
+
+
+//4096 bytes, 256 byte aligned
+static unsigned int NoDbiPrbs7[] =
+{
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+    0x0f0f0f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0x0f0f0f0f, 0x0f0f0f0f, 0xf0f0f0f0, 0xf0f00f0f,
+    0x0f0f0f0f, 0xf0f00f0f, 0x0f0ff0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0xf0f00f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0x0f0ff0f0, 0xf0f00f0f,
+    0xf0f00f0f, 0x0f0ff0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0ff0f0, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f0f0f0, 0x0f0f0f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f00f0f, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0f0f0, 0xf0f0ffff,
+};
+
+// 4096 bytes, 256 byte aligned
+static unsigned int DbiPrbs7[] =
+{
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x0000ffff, 0xffffffff, 0xffffffff, 0x00000000, 0xffffffff, 0xffffffff, 0x0000ffff, 0x0000ffff, 0xffffffff, 0x00000000, 0x00000000, 0xffffffff, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0x00000000, 0xffffffff, 0x00000000, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0xffff0000, 0x00000000, 0x00000000, 0xffff0000, 0xffffffff, 0xffffffff, 0x00000000, 0x0000ffff,
+    0xffffffff, 0x0000ffff, 0xffff0000, 0xffffffff, 0x00000000, 0xffff0000, 0x0000ffff, 0x0000ffff, 0x00000000, 0xffff0000, 0x00000000, 0x0000ffff, 0x00000000, 0xffffffff, 0xffff0000, 0x0000ffff,
+    0x0000ffff, 0xffff0000, 0xffff0000, 0x00000000, 0xffff0000, 0x00000000, 0xffffffff, 0x00000000, 0xffffffff, 0x0000ffff, 0x0000ffff, 0x0000ffff, 0x00000000, 0x00000000, 0x00000000, 0x0000ffff,
+};
+
+#pragma pack(pop)
+
+#endif
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h
index 7b585e205a5a..cbf4a58b77d9 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h
@@ -173,6 +173,9 @@
 	__SMU_DUMMY_MAP(GmiPwrDnControl), \
 	__SMU_DUMMY_MAP(DAL_DISABLE_DUMMY_PSTATE_CHANGE), \
 	__SMU_DUMMY_MAP(DAL_ENABLE_DUMMY_PSTATE_CHANGE), \
+	__SMU_DUMMY_MAP(SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_HIGH), \
+	__SMU_DUMMY_MAP(SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_LOW), \
+	__SMU_DUMMY_MAP(GET_UMC_FW_WA), \
 	__SMU_DUMMY_MAP(Mode1Reset), \
 
 #undef __SMU_DUMMY_MAP
@@ -217,6 +220,7 @@ enum smu_clk_type {
        __SMU_DUMMY_MAP(DPM_MP0CLK),                    	\
        __SMU_DUMMY_MAP(DPM_LINK),                      	\
        __SMU_DUMMY_MAP(DPM_DCEFCLK),                   	\
+       __SMU_DUMMY_MAP(DPM_XGMI),			\
        __SMU_DUMMY_MAP(DS_GFXCLK),                     	\
        __SMU_DUMMY_MAP(DS_SOCCLK),                     	\
        __SMU_DUMMY_MAP(DS_LCLK),                       	\
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
index 1f9575a4dfe7..2d1c3babaa3a 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
@@ -30,8 +30,8 @@
 #define SMU11_DRIVER_IF_VERSION_NV10 0x36
 #define SMU11_DRIVER_IF_VERSION_NV12 0x36
 #define SMU11_DRIVER_IF_VERSION_NV14 0x36
-#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x35
-#define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0x4
+#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x39
+#define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0x5
 
 /* MP Apertures */
 #define MP0_Public			0x03800000
@@ -280,5 +280,7 @@ int smu_v11_0_gfx_ulv_control(struct smu_context *smu,
 int smu_v11_0_deep_sleep_control(struct smu_context *smu,
 				 bool enablement);
 
+void smu_v11_0_interrupt_work(struct smu_context *smu);
+
 #endif
 #endif
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_ppsmc.h
index fa0174dc7e0e..26181b679098 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0_ppsmc.h
@@ -125,7 +125,12 @@
 
 #define PPSMC_MSG_SetMGpuFanBoostLimitRpm        0x4C
 
-#define PPSMC_Message_Count                      0x4D
+#define PPSMC_MSG_SetDriverDummyTableDramAddrHigh 0x4E
+#define PPSMC_MSG_SetDriverDummyTableDramAddrLow  0x4F
+
+#define PPSMC_MSG_GetUMCFWWA                     0x50
+
+#define PPSMC_Message_Count                      0x51
 
 typedef uint32_t PPSMC_Result;
 typedef uint32_t PPSMC_Msg;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
index a6321f2063c1..eab9768029c1 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
@@ -911,6 +911,19 @@ static int pp_set_power_profile_mode(void *handle, long *input, uint32_t size)
 	return ret;
 }
 
+static int pp_set_fine_grain_clk_vol(void *handle, uint32_t type, long *input, uint32_t size)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
+
+	if (hwmgr->hwmgr_func->set_fine_grain_clk_vol == NULL)
+		return 0;
+
+	return hwmgr->hwmgr_func->set_fine_grain_clk_vol(hwmgr, type, input, size);
+}
+
 static int pp_odn_edit_dpm_table(void *handle, uint32_t type, long *input, uint32_t size)
 {
 	struct pp_hwmgr *hwmgr = handle;
@@ -920,7 +933,7 @@ static int pp_odn_edit_dpm_table(void *handle, uint32_t type, long *input, uint3
 
 	if (hwmgr->hwmgr_func->odn_edit_dpm_table == NULL) {
 		pr_info_ratelimited("%s was not implemented.\n", __func__);
-		return -EINVAL;
+		return 0;
 	}
 
 	return hwmgr->hwmgr_func->odn_edit_dpm_table(hwmgr, type, input, size);
@@ -1645,6 +1658,7 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.set_powergating_by_smu = pp_set_powergating_by_smu,
 	.get_power_profile_mode = pp_get_power_profile_mode,
 	.set_power_profile_mode = pp_set_power_profile_mode,
+	.set_fine_grain_clk_vol = pp_set_fine_grain_clk_vol,
 	.odn_edit_dpm_table = pp_odn_edit_dpm_table,
 	.set_mp1_state = pp_dpm_set_mp1_state,
 	.set_power_limit = pp_set_power_limit,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index 9ee8cf8267c8..cf60f3992303 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -242,6 +242,34 @@ static int smu10_set_hard_min_fclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t cloc
 	return 0;
 }
 
+static int smu10_set_hard_min_gfxclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t clock)
+{
+	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
+
+	if (clock && smu10_data->gfx_actual_soft_min_freq != clock) {
+		smu10_data->gfx_actual_soft_min_freq = clock;
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+					PPSMC_MSG_SetHardMinGfxClk,
+					smu10_data->gfx_actual_soft_min_freq,
+					NULL);
+	}
+	return 0;
+}
+
+static int smu10_set_soft_max_gfxclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t clock)
+{
+	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
+
+	if (clock && smu10_data->gfx_max_freq_limit != (clock * 100))  {
+		smu10_data->gfx_max_freq_limit = clock * 100;
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+					PPSMC_MSG_SetSoftMaxGfxClk,
+					clock,
+					NULL);
+	}
+	return 0;
+}
+
 static int smu10_set_active_display_count(struct pp_hwmgr *hwmgr, uint32_t count)
 {
 	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
@@ -527,6 +555,9 @@ static int smu10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	hwmgr->pstate_sclk = SMU10_UMD_PSTATE_GFXCLK * 100;
 	hwmgr->pstate_mclk = SMU10_UMD_PSTATE_FCLK * 100;
 
+	/* enable the pp_od_clk_voltage sysfs file */
+	hwmgr->od_enabled = 1;
+
 	return result;
 }
 
@@ -563,6 +594,8 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 	struct smu10_hwmgr *data = hwmgr->backend;
 	uint32_t min_sclk = hwmgr->display_config->min_core_set_clock;
 	uint32_t min_mclk = hwmgr->display_config->min_mem_set_clock/100;
+	uint32_t index_fclk = data->clock_vol_info.vdd_dep_on_fclk->count - 1;
+	uint32_t index_socclk = data->clock_vol_info.vdd_dep_on_socclk->count - 1;
 
 	if (hwmgr->smu_version < 0x1E3700) {
 		pr_info("smu firmware version too old, can not set dpm level\n");
@@ -648,7 +681,7 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 						NULL);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinVcn,
-						SMU10_UMD_PSTATE_VCE,
+						SMU10_UMD_PSTATE_PROFILE_VCE,
 						NULL);
 
 		smum_send_msg_to_smc_with_parameter(hwmgr,
@@ -665,7 +698,7 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 						NULL);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMaxVcn,
-						SMU10_UMD_PSTATE_VCE,
+						SMU10_UMD_PSTATE_PROFILE_VCE,
 						NULL);
 		break;
 	case AMD_DPM_FORCED_LEVEL_AUTO:
@@ -676,13 +709,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinFclkByFreq,
 						hwmgr->display_config->num_display > 3 ?
-						SMU10_UMD_PSTATE_PEAK_FCLK :
+						data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk :
 						min_mclk,
 						NULL);
 
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinSocclkByFreq,
-						SMU10_UMD_PSTATE_MIN_SOCCLK,
+						data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk,
 						NULL);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinVcn,
@@ -695,11 +728,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 						NULL);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMaxFclkByFreq,
-						SMU10_UMD_PSTATE_PEAK_FCLK,
+						data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk,
 						NULL);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMaxSocclkByFreq,
-						SMU10_UMD_PSTATE_PEAK_SOCCLK,
+						data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk,
 						NULL);
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMaxVcn,
@@ -947,6 +980,26 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 					((mclk_table->entries[i].clk / 100)
 					 == now) ? "*" : "");
 		break;
+	case OD_SCLK:
+		if (hwmgr->od_enabled) {
+			size = sprintf(buf, "%s:\n", "OD_SCLK");
+
+			size += sprintf(buf + size, "0: %10uMhz\n",
+			(data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : data->gfx_min_freq_limit/100);
+			size += sprintf(buf + size, "1: %10uMhz\n", data->gfx_max_freq_limit/100);
+		}
+		break;
+	case OD_RANGE:
+		if (hwmgr->od_enabled) {
+			uint32_t min_freq, max_freq = 0;
+			smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
+			smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+
+			size = sprintf(buf, "%s:\n", "OD_RANGE");
+			size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
+				min_freq, max_freq);
+		}
+		break;
 	default:
 		break;
 	}
@@ -1181,8 +1234,19 @@ static int smu10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 	struct smu10_hwmgr *data = hwmgr->backend;
 	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
 	Watermarks_t *table = &(data->water_marks_table);
+	struct amdgpu_device *adev = hwmgr->adev;
+	int i;
 
 	smu_set_watermarks_for_clocks_ranges(table,wm_with_clock_ranges);
+
+	if (adev->apu_flags & AMD_APU_IS_RAVEN2) {
+		for (i = 0; i < NUM_WM_RANGES; i++)
+			table->WatermarkRow[WM_DCFCLK][i].WmType = (uint8_t)0;
+
+		for (i = 0; i < NUM_WM_RANGES; i++)
+			table->WatermarkRow[WM_SOCCLK][i].WmType = (uint8_t)0;
+	}
+
 	smum_smc_table_manager(hwmgr, (uint8_t *)table, (uint16_t)SMU10_WMTABLE, false);
 	data->water_marks_exist = true;
 	return 0;
@@ -1348,6 +1412,32 @@ static int smu10_asic_reset(struct pp_hwmgr *hwmgr, enum SMU_ASIC_RESET_MODE mod
 						   NULL);
 }
 
+static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr,
+					enum PP_OD_DPM_TABLE_COMMAND type,
+					long *input, uint32_t size)
+{
+	if (!hwmgr->od_enabled) {
+		pr_err("Fine grain not support\n");
+		return -EINVAL;
+	}
+
+	if (size != 2) {
+		pr_err("Input parameter number not correct\n");
+		return -EINVAL;
+	}
+
+	if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) {
+		if (input[0] == 0)
+			smu10_set_hard_min_gfxclk_by_freq(hwmgr, input[1]);
+		else if (input[0] == 1)
+			smu10_set_soft_max_gfxclk_by_freq(hwmgr, input[1]);
+		else
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.backend_init = smu10_hwmgr_backend_init,
 	.backend_fini = smu10_hwmgr_backend_fini,
@@ -1388,9 +1478,12 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.powergate_sdma = smu10_powergate_sdma,
 	.set_hard_min_dcefclk_by_freq = smu10_set_hard_min_dcefclk_by_freq,
 	.set_hard_min_fclk_by_freq = smu10_set_hard_min_fclk_by_freq,
+	.set_hard_min_gfxclk_by_freq = smu10_set_hard_min_gfxclk_by_freq,
+	.set_soft_max_gfxclk_by_freq = smu10_set_soft_max_gfxclk_by_freq,
 	.get_power_profile_mode = smu10_get_power_profile_mode,
 	.set_power_profile_mode = smu10_set_power_profile_mode,
 	.asic_reset = smu10_asic_reset,
+	.set_fine_grain_clk_vol = smu10_set_fine_grain_clk_vol,
 };
 
 int smu10_init_function_pointers(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h
index 0f969de10fab..6c9b5f060902 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h
@@ -284,7 +284,7 @@ struct smu10_hwmgr {
 	uint32_t                        dclk_soft_min;
 	uint32_t                        gfx_actual_soft_min_freq;
 	uint32_t                        gfx_min_freq_limit;
-	uint32_t                        gfx_max_freq_limit;
+	uint32_t                        gfx_max_freq_limit; /* in 10Khz*/
 
 	bool                           vcn_power_gated;
 	bool                           vcn_dpg_mode;
@@ -310,6 +310,7 @@ int smu10_init_function_pointers(struct pp_hwmgr *hwmgr);
 #define SMU10_UMD_PSTATE_SOCCLK                 626
 #define SMU10_UMD_PSTATE_FCLK                   933
 #define SMU10_UMD_PSTATE_VCE                    0x03C00320
+#define SMU10_UMD_PSTATE_PROFILE_VCE            0x02AD0229
 
 #define SMU10_UMD_PSTATE_PEAK_SOCCLK            757
 #define SMU10_UMD_PSTATE_PEAK_FCLK              1200
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index 4a3b64aa21ce..1e8919b0acdb 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -1585,9 +1585,19 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 	data->current_profile_setting.sclk_down_hyst = 100;
 	data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT;
 	data->current_profile_setting.bupdate_mclk = 1;
-	data->current_profile_setting.mclk_up_hyst = 0;
-	data->current_profile_setting.mclk_down_hyst = 100;
-	data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT;
+	if (adev->gmc.vram_width == 256) {
+		data->current_profile_setting.mclk_up_hyst = 10;
+		data->current_profile_setting.mclk_down_hyst = 60;
+		data->current_profile_setting.mclk_activity = 25;
+	} else if (adev->gmc.vram_width == 128) {
+		data->current_profile_setting.mclk_up_hyst = 5;
+		data->current_profile_setting.mclk_down_hyst = 16;
+		data->current_profile_setting.mclk_activity = 20;
+	} else if (adev->gmc.vram_width == 64) {
+		data->current_profile_setting.mclk_up_hyst = 3;
+		data->current_profile_setting.mclk_down_hyst = 16;
+		data->current_profile_setting.mclk_activity = 20;
+	}
 	hwmgr->workload_mask = 1 << hwmgr->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
 	hwmgr->power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
 	hwmgr->default_power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
@@ -2873,7 +2883,7 @@ static int smu7_vblank_too_short(struct pp_hwmgr *hwmgr,
 		if (hwmgr->is_kicker)
 			switch_limit_us = data->is_memory_gddr5 ? 450 : 150;
 		else
-			switch_limit_us = data->is_memory_gddr5 ? 190 : 150;
+			switch_limit_us = data->is_memory_gddr5 ? 200 : 150;
 		break;
 	case CHIP_VEGAM:
 		switch_limit_us = 30;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index c378a000c934..7eada3098ffc 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -4659,7 +4659,7 @@ static int vega10_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
 	if ((data->water_marks_bitmap & WaterMarksExist) &&
 			!(data->water_marks_bitmap & WaterMarksLoaded)) {
 		result = smum_smc_table_manager(hwmgr, (uint8_t *)wm_table, WMTABLE, false);
-		PP_ASSERT_WITH_CODE(result, "Failed to update WMTABLE!", return EINVAL);
+		PP_ASSERT_WITH_CODE(result, "Failed to update WMTABLE!", return -EINVAL);
 		data->water_marks_bitmap |= WaterMarksLoaded;
 	}
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
index f0680dd58508..dc206fa88c5e 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@@ -2444,7 +2444,7 @@ static int vega12_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
 			!(data->water_marks_bitmap & WaterMarksLoaded)) {
 		result = smum_smc_table_manager(hwmgr,
 						(uint8_t *)wm_table, TABLE_WATERMARKS, false);
-		PP_ASSERT_WITH_CODE(result, "Failed to update WMTABLE!", return EINVAL);
+		PP_ASSERT_WITH_CODE(result, "Failed to update WMTABLE!", return -EINVAL);
 		data->water_marks_bitmap |= WaterMarksLoaded;
 	}
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.c
index adfbcbe5d113..8a9aee85043e 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu9_smumgr.c
@@ -61,9 +61,6 @@ static uint32_t smu9_wait_for_response(struct pp_hwmgr *hwmgr)
 	uint32_t reg;
 	uint32_t ret;
 
-	/* Due to the L1 policy problem under SRIOV, we have to use
-	 * mmMP1_SMN_C2PMSG_103 as the driver response register
-	 */
 	if (hwmgr->pp_one_vf) {
 		reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_103);
 
@@ -148,10 +145,6 @@ int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
 
 	smu9_wait_for_response(hwmgr);
 
-	/* Due to the L1 policy problem under SRIOV, we have to use
-	 * mmMP1_SMN_C2PMSG_101 as the driver message register and
-	 * mmMP1_SMN_C2PMSG_102 as the driver parameter register.
-	 */
 	if (hwmgr->pp_one_vf) {
 		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_103, 0);
 		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_102, parameter);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c
index 1e222c5d91a4..daf122f24f23 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c
@@ -209,11 +209,13 @@ static int vega10_smu_init(struct pp_hwmgr *hwmgr)
 	int ret;
 	struct cgs_firmware_info info = {0};
 
-	ret = cgs_get_firmware_info(hwmgr->device,
-				    CGS_UCODE_ID_SMU,
-				    &info);
-	if (ret || !info.kptr)
-		return -EINVAL;
+	if (!amdgpu_sriov_vf((struct amdgpu_device *)hwmgr->adev)) {
+		ret = cgs_get_firmware_info(hwmgr->device,
+						CGS_UCODE_ID_SMU,
+						&info);
+		if (ret || !info.kptr)
+			return -EINVAL;
+	}
 
 	priv = kzalloc(sizeof(struct vega10_smumgr), GFP_KERNEL);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 7a55ece1f124..fc4f95fa87cf 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -361,20 +361,16 @@ static int smu_get_driver_allowed_feature_mask(struct smu_context *smu)
 	int ret = 0;
 	uint32_t allowed_feature_mask[SMU_FEATURE_MAX/32];
 
-	mutex_lock(&feature->mutex);
 	bitmap_zero(feature->allowed, SMU_FEATURE_MAX);
-	mutex_unlock(&feature->mutex);
 
 	ret = smu_get_allowed_feature_mask(smu, allowed_feature_mask,
 					     SMU_FEATURE_MAX/32);
 	if (ret)
 		return ret;
 
-	mutex_lock(&feature->mutex);
 	bitmap_or(feature->allowed, feature->allowed,
 		      (unsigned long *)allowed_feature_mask,
 		      feature->feature_num);
-	mutex_unlock(&feature->mutex);
 
 	return ret;
 }
@@ -421,6 +417,9 @@ static int smu_early_init(void *handle)
 	smu->pm_enabled = !!amdgpu_dpm;
 	smu->is_apu = false;
 	mutex_init(&smu->mutex);
+	mutex_init(&smu->smu_baco.mutex);
+	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
+	smu->smu_baco.platform_support = false;
 
 	return smu_set_funcs(adev);
 }
@@ -473,20 +472,15 @@ static int smu_late_init(void *handle)
 	if (!smu->pm_enabled)
 		return 0;
 
-	ret = smu_set_default_od_settings(smu);
+	ret = smu_post_init(smu);
 	if (ret) {
-		dev_err(adev->dev, "Failed to setup default OD settings!\n");
+		dev_err(adev->dev, "Failed to post smu init!\n");
 		return ret;
 	}
 
-	/*
-	 * Set initialized values (get from vbios) to dpm tables context such as
-	 * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each
-	 * type of clks.
-	 */
-	ret = smu_set_default_dpm_table(smu);
+	ret = smu_set_default_od_settings(smu);
 	if (ret) {
-		dev_err(adev->dev, "Failed to setup default dpm clock tables!\n");
+		dev_err(adev->dev, "Failed to setup default OD settings!\n");
 		return ret;
 	}
 
@@ -578,9 +572,6 @@ static int smu_fini_fb_allocations(struct smu_context *smu)
 	struct smu_table *tables = smu_table->tables;
 	struct smu_table *driver_table = &(smu_table->driver_table);
 
-	if (!tables)
-		return 0;
-
 	if (tables[SMU_TABLE_PMSTATUSLOG].mc_address)
 		amdgpu_bo_free_kernel(&tables[SMU_TABLE_PMSTATUSLOG].bo,
 				      &tables[SMU_TABLE_PMSTATUSLOG].mc_address,
@@ -657,6 +648,45 @@ static int smu_free_memory_pool(struct smu_context *smu)
 	return 0;
 }
 
+static int smu_alloc_dummy_read_table(struct smu_context *smu)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct smu_table *dummy_read_1_table =
+			&smu_table->dummy_read_1_table;
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
+
+	dummy_read_1_table->size = 0x40000;
+	dummy_read_1_table->align = PAGE_SIZE;
+	dummy_read_1_table->domain = AMDGPU_GEM_DOMAIN_VRAM;
+
+	ret = amdgpu_bo_create_kernel(adev,
+				      dummy_read_1_table->size,
+				      dummy_read_1_table->align,
+				      dummy_read_1_table->domain,
+				      &dummy_read_1_table->bo,
+				      &dummy_read_1_table->mc_address,
+				      &dummy_read_1_table->cpu_addr);
+	if (ret)
+		dev_err(adev->dev, "VRAM allocation for dummy read table failed!\n");
+
+	return ret;
+}
+
+static void smu_free_dummy_read_table(struct smu_context *smu)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct smu_table *dummy_read_1_table =
+			&smu_table->dummy_read_1_table;
+
+
+	amdgpu_bo_free_kernel(&dummy_read_1_table->bo,
+			      &dummy_read_1_table->mc_address,
+			      &dummy_read_1_table->cpu_addr);
+
+	memset(dummy_read_1_table, 0, sizeof(struct smu_table));
+}
+
 static int smu_smc_table_sw_init(struct smu_context *smu)
 {
 	int ret;
@@ -692,6 +722,10 @@ static int smu_smc_table_sw_init(struct smu_context *smu)
 	if (ret)
 		return ret;
 
+	ret = smu_alloc_dummy_read_table(smu);
+	if (ret)
+		return ret;
+
 	ret = smu_i2c_init(smu, &smu->adev->pm.smu_i2c);
 	if (ret)
 		return ret;
@@ -705,6 +739,8 @@ static int smu_smc_table_sw_fini(struct smu_context *smu)
 
 	smu_i2c_fini(smu, &smu->adev->pm.smu_i2c);
 
+	smu_free_dummy_read_table(smu);
+
 	ret = smu_free_memory_pool(smu);
 	if (ret)
 		return ret;
@@ -736,6 +772,19 @@ static void smu_throttling_logging_work_fn(struct work_struct *work)
 	smu_log_thermal_throttling(smu);
 }
 
+static void smu_interrupt_work_fn(struct work_struct *work)
+{
+	struct smu_context *smu = container_of(work, struct smu_context,
+					       interrupt_work);
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs && smu->ppt_funcs->interrupt_work)
+		smu->ppt_funcs->interrupt_work(smu);
+
+	mutex_unlock(&smu->mutex);
+}
+
 static int smu_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -749,15 +798,12 @@ static int smu_sw_init(void *handle)
 	bitmap_zero(smu->smu_feature.enabled, SMU_FEATURE_MAX);
 	bitmap_zero(smu->smu_feature.allowed, SMU_FEATURE_MAX);
 
-	mutex_init(&smu->smu_baco.mutex);
-	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
-	smu->smu_baco.platform_support = false;
-
 	mutex_init(&smu->sensor_lock);
 	mutex_init(&smu->metrics_lock);
 	mutex_init(&smu->message_lock);
 
 	INIT_WORK(&smu->throttling_logging_work, smu_throttling_logging_work_fn);
+	INIT_WORK(&smu->interrupt_work, smu_interrupt_work_fn);
 	atomic64_set(&smu->throttle_int_counter, 0);
 	smu->watermarks_bitmap = 0;
 	smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
@@ -788,10 +834,13 @@ static int smu_sw_init(void *handle)
 
 	smu->smu_dpm.dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
 	smu->smu_dpm.requested_dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
-	ret = smu_init_microcode(smu);
-	if (ret) {
-		dev_err(adev->dev, "Failed to load smu firmware!\n");
-		return ret;
+
+	if (!amdgpu_sriov_vf(adev)) {
+		ret = smu_init_microcode(smu);
+		if (ret) {
+			dev_err(adev->dev, "Failed to load smu firmware!\n");
+			return ret;
+		}
 	}
 
 	ret = smu_smc_table_sw_init(smu);
@@ -969,21 +1018,25 @@ static int smu_smc_hw_setup(struct smu_context *smu)
 		return ret;
 	}
 
-	ret = smu_disable_umc_cdr_12gbps_workaround(smu);
+	/*
+	 * Set initialized values (get from vbios) to dpm tables context such as
+	 * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each
+	 * type of clks.
+	 */
+	ret = smu_set_default_dpm_table(smu);
 	if (ret) {
-		dev_err(adev->dev, "Workaround failed to disable UMC CDR feature on 12Gbps SKU!\n");
+		dev_err(adev->dev, "Failed to setup default dpm clock tables!\n");
 		return ret;
 	}
 
 	/*
-	 * For Navi1X, manually switch it to AC mode as PMFW
-	 * may boot it with DC mode.
+	 * Set initialized values (get from vbios) to dpm tables context such as
+	 * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each
+	 * type of clks.
 	 */
-	ret = smu_set_power_source(smu,
-				   adev->pm.ac_power ? SMU_POWER_SOURCE_AC :
-				   SMU_POWER_SOURCE_DC);
+	ret = smu_set_default_dpm_table(smu);
 	if (ret) {
-		dev_err(adev->dev, "Failed to switch to %s mode!\n", adev->pm.ac_power ? "AC" : "DC");
+		dev_err(adev->dev, "Failed to setup default dpm clock tables!\n");
 		return ret;
 	}
 
@@ -1129,7 +1182,7 @@ static int smu_disable_dpms(struct smu_context *smu)
 	 */
 	if (smu->uploading_custom_pp_table &&
 	    (adev->asic_type >= CHIP_NAVI10) &&
-	    (adev->asic_type <= CHIP_NAVI12))
+	    (adev->asic_type <= CHIP_NAVY_FLOUNDER))
 		return 0;
 
 	/*
@@ -1168,6 +1221,7 @@ static int smu_smc_hw_cleanup(struct smu_context *smu)
 	int ret = 0;
 
 	cancel_work_sync(&smu->throttling_logging_work);
+	cancel_work_sync(&smu->interrupt_work);
 
 	ret = smu_disable_thermal_alert(smu);
 	if (ret) {
@@ -1188,7 +1242,6 @@ static int smu_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct smu_context *smu = &adev->smu;
-	int ret = 0;
 
 	if (amdgpu_sriov_vf(adev)&& !amdgpu_sriov_is_pp_one_vf(adev))
 		return 0;
@@ -1204,17 +1257,15 @@ static int smu_hw_fini(void *handle)
 
 	adev->pm.dpm_enabled = false;
 
-	ret = smu_smc_hw_cleanup(smu);
-	if (ret)
-		return ret;
-
-	return 0;
+	return smu_smc_hw_cleanup(smu);
 }
 
 int smu_reset(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
-	int ret = 0;
+	int ret;
+
+	amdgpu_gfx_off_ctrl(smu->adev, false);
 
 	ret = smu_hw_fini(adev);
 	if (ret)
@@ -1225,8 +1276,12 @@ int smu_reset(struct smu_context *smu)
 		return ret;
 
 	ret = smu_late_init(adev);
+	if (ret)
+		return ret;
 
-	return ret;
+	amdgpu_gfx_off_ctrl(smu->adev, true);
+
+	return 0;
 }
 
 static int smu_suspend(void *handle)
@@ -1784,25 +1839,19 @@ int smu_write_watermarks_table(struct smu_context *smu)
 }
 
 int smu_set_watermarks_for_clock_ranges(struct smu_context *smu,
-		struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges)
+		struct pp_smu_wm_range_sets *clock_ranges)
 {
 	int ret = 0;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
 		return -EOPNOTSUPP;
 
+	if (smu->disable_watermark)
+		return 0;
+
 	mutex_lock(&smu->mutex);
 
-	if (!smu->disable_watermark &&
-			smu_feature_is_enabled(smu, SMU_FEATURE_DPM_DCEFCLK_BIT) &&
-			smu_feature_is_enabled(smu, SMU_FEATURE_DPM_SOCCLK_BIT)) {
-		ret = smu_set_watermarks_table(smu, clock_ranges);
-
-		if (!(smu->watermarks_bitmap & WATERMARKS_EXIST)) {
-			smu->watermarks_bitmap |= WATERMARKS_EXIST;
-			smu->watermarks_bitmap &= ~WATERMARKS_LOADED;
-		}
-	}
+	ret = smu_set_watermarks_table(smu, clock_ranges);
 
 	mutex_unlock(&smu->mutex);
 
@@ -2269,19 +2318,6 @@ int smu_set_deep_sleep_dcefclk(struct smu_context *smu, int clk)
 	return ret;
 }
 
-int smu_set_active_display_count(struct smu_context *smu, uint32_t count)
-{
-	int ret = 0;
-
-	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
-		return -EOPNOTSUPP;
-
-	if (smu->ppt_funcs->set_active_display_count)
-		ret = smu->ppt_funcs->set_active_display_count(smu, count);
-
-	return ret;
-}
-
 int smu_get_clock_by_type(struct smu_context *smu,
 			  enum amd_pp_clock_type type,
 			  struct amd_pp_clocks *clocks)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 2ce6ad9c6609..fc376281e629 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -386,11 +386,9 @@ static int arcturus_check_powerplay_table(struct smu_context *smu)
 		table_context->power_play_table;
 	struct smu_baco_context *smu_baco = &smu->smu_baco;
 
-	mutex_lock(&smu_baco->mutex);
 	if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_BACO ||
 	    powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO)
 		smu_baco->platform_support = true;
-	mutex_unlock(&smu_baco->mutex);
 
 	table_context->thermal_controller_type =
 		powerplay_table->thermal_controller_type;
@@ -2390,6 +2388,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.gfx_ulv_control = smu_v11_0_gfx_ulv_control,
 	.deep_sleep_control = smu_v11_0_deep_sleep_control,
 	.get_fan_parameters = arcturus_get_fan_parameters,
+	.interrupt_work = smu_v11_0_interrupt_work,
 };
 
 void arcturus_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 42d53cca7360..ef1a62e86a0e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -45,6 +45,7 @@
 
 #include "asic_reg/mp/mp_11_0_sh_mask.h"
 #include "smu_cmn.h"
+#include "smu_11_0_cdr_table.h"
 
 /*
  * DO NOT use these for err/warn/info/debug messages.
@@ -139,6 +140,9 @@ static struct cmn2asic_msg_mapping navi10_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(GetVoltageByDpm,		PPSMC_MSG_GetVoltageByDpm,		0),
 	MSG_MAP(GetVoltageByDpmOverdrive,	PPSMC_MSG_GetVoltageByDpmOverdrive,	0),
 	MSG_MAP(SetMGpuFanBoostLimitRpm,	PPSMC_MSG_SetMGpuFanBoostLimitRpm,	0),
+	MSG_MAP(SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_HIGH, PPSMC_MSG_SetDriverDummyTableDramAddrHigh, 0),
+	MSG_MAP(SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_LOW, PPSMC_MSG_SetDriverDummyTableDramAddrLow, 0),
+	MSG_MAP(GET_UMC_FW_WA,			PPSMC_MSG_GetUMCFWWA,			0),
 };
 
 static struct cmn2asic_mapping navi10_clk_map[SMU_CLK_COUNT] = {
@@ -279,9 +283,6 @@ navi10_get_allowed_feature_mask(struct smu_context *smu,
 				| FEATURE_MASK(FEATURE_FW_CTF_BIT)
 				| FEATURE_MASK(FEATURE_OUT_OF_BAND_MONITOR_BIT);
 
-	if (adev->pm.pp_feature & PP_SOCCLK_DPM_MASK)
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT);
-
 	if (adev->pm.pp_feature & PP_SCLK_DPM_MASK)
 		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_GFXCLK_BIT);
 
@@ -291,11 +292,6 @@ navi10_get_allowed_feature_mask(struct smu_context *smu,
 	if (adev->pm.pp_feature & PP_DCEFCLK_DPM_MASK)
 		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT);
 
-	if (adev->pm.pp_feature & PP_MCLK_DPM_MASK)
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_UCLK_BIT)
-				| FEATURE_MASK(FEATURE_MEM_VDDCI_SCALING_BIT)
-				| FEATURE_MASK(FEATURE_MEM_MVDD_SCALING_BIT);
-
 	if (adev->pm.pp_feature & PP_ULV_MASK)
 		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFX_ULV_BIT);
 
@@ -320,19 +316,24 @@ navi10_get_allowed_feature_mask(struct smu_context *smu,
 	if (smu->dc_controlled_by_gpio)
 		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_ACDC_BIT);
 
-	/* disable DPM UCLK and DS SOCCLK on navi10 A0 secure board */
-	if (is_asic_secure(smu)) {
-		/* only for navi10 A0 */
-		if ((adev->asic_type == CHIP_NAVI10) &&
-			(adev->rev_id == 0)) {
-			*(uint64_t *)feature_mask &=
-					~(FEATURE_MASK(FEATURE_DPM_UCLK_BIT)
-					  | FEATURE_MASK(FEATURE_MEM_VDDCI_SCALING_BIT)
-					  | FEATURE_MASK(FEATURE_MEM_MVDD_SCALING_BIT));
-			*(uint64_t *)feature_mask &=
-					~FEATURE_MASK(FEATURE_DS_SOCCLK_BIT);
-		}
-	}
+	if (adev->pm.pp_feature & PP_SOCCLK_DPM_MASK)
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT);
+
+	/* DPM UCLK enablement should be skipped for navi10 A0 secure board */
+	if (!(is_asic_secure(smu) &&
+	     (adev->asic_type == CHIP_NAVI10) &&
+	     (adev->rev_id == 0)) &&
+	    (adev->pm.pp_feature & PP_MCLK_DPM_MASK))
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_UCLK_BIT)
+				| FEATURE_MASK(FEATURE_MEM_VDDCI_SCALING_BIT)
+				| FEATURE_MASK(FEATURE_MEM_MVDD_SCALING_BIT);
+
+	/* DS SOCCLK enablement should be skipped for navi10 A0 secure board */
+	if (is_asic_secure(smu) &&
+	    (adev->asic_type == CHIP_NAVI10) &&
+	    (adev->rev_id == 0))
+		*(uint64_t *)feature_mask &=
+				~FEATURE_MASK(FEATURE_DS_SOCCLK_BIT);
 
 	return 0;
 }
@@ -347,11 +348,9 @@ static int navi10_check_powerplay_table(struct smu_context *smu)
 	if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_HARDWAREDC)
 		smu->dc_controlled_by_gpio = true;
 
-	mutex_lock(&smu_baco->mutex);
 	if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_BACO ||
 	    powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO)
 		smu_baco->platform_support = true;
-	mutex_unlock(&smu_baco->mutex);
 
 	table_context->thermal_controller_type =
 		powerplay_table->thermal_controller_type;
@@ -1362,14 +1361,9 @@ static int navi10_get_fan_speed_rpm(struct smu_context *smu,
 	if (!speed)
 		return -EINVAL;
 
-	switch (smu_v11_0_get_fan_control_mode(smu)) {
-	case AMD_FAN_CTRL_AUTO:
-		return navi10_get_smu_metrics_data(smu,
-						   METRICS_CURR_FANSPEED,
-						   speed);
-	default:
-		return smu_v11_0_get_fan_speed_rpm(smu, speed);
-	}
+	return navi10_get_smu_metrics_data(smu,
+					   METRICS_CURR_FANSPEED,
+					   speed);
 }
 
 static int navi10_get_fan_parameters(struct smu_context *smu)
@@ -1602,57 +1596,43 @@ static int navi10_notify_smc_display_config(struct smu_context *smu)
 }
 
 static int navi10_set_watermarks_table(struct smu_context *smu,
-				       struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges)
+				       struct pp_smu_wm_range_sets *clock_ranges)
 {
 	Watermarks_t *table = smu->smu_table.watermarks_table;
 	int ret = 0;
 	int i;
 
 	if (clock_ranges) {
-		if (clock_ranges->num_wm_dmif_sets > 4 ||
-		    clock_ranges->num_wm_mcif_sets > 4)
+		if (clock_ranges->num_reader_wm_sets > NUM_WM_RANGES ||
+		    clock_ranges->num_writer_wm_sets > NUM_WM_RANGES)
 			return -EINVAL;
 
-		for (i = 0; i < clock_ranges->num_wm_dmif_sets; i++) {
-			table->WatermarkRow[1][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz /
-				1000));
-			table->WatermarkRow[1][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz /
-				1000));
-			table->WatermarkRow[1][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz /
-				1000));
-			table->WatermarkRow[1][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz /
-				1000));
-			table->WatermarkRow[1][i].WmSetting = (uint8_t)
-					clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id;
+		for (i = 0; i < clock_ranges->num_reader_wm_sets; i++) {
+			table->WatermarkRow[WM_DCEFCLK][i].MinClock =
+				clock_ranges->reader_wm_sets[i].min_drain_clk_mhz;
+			table->WatermarkRow[WM_DCEFCLK][i].MaxClock =
+				clock_ranges->reader_wm_sets[i].max_drain_clk_mhz;
+			table->WatermarkRow[WM_DCEFCLK][i].MinUclk =
+				clock_ranges->reader_wm_sets[i].min_fill_clk_mhz;
+			table->WatermarkRow[WM_DCEFCLK][i].MaxUclk =
+				clock_ranges->reader_wm_sets[i].max_fill_clk_mhz;
+
+			table->WatermarkRow[WM_DCEFCLK][i].WmSetting =
+				clock_ranges->reader_wm_sets[i].wm_inst;
 		}
 
-		for (i = 0; i < clock_ranges->num_wm_mcif_sets; i++) {
-			table->WatermarkRow[0][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz /
-				1000));
-			table->WatermarkRow[0][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz /
-				1000));
-			table->WatermarkRow[0][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz /
-				1000));
-			table->WatermarkRow[0][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz /
-				1000));
-			table->WatermarkRow[0][i].WmSetting = (uint8_t)
-					clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id;
+		for (i = 0; i < clock_ranges->num_writer_wm_sets; i++) {
+			table->WatermarkRow[WM_SOCCLK][i].MinClock =
+				clock_ranges->writer_wm_sets[i].min_fill_clk_mhz;
+			table->WatermarkRow[WM_SOCCLK][i].MaxClock =
+				clock_ranges->writer_wm_sets[i].max_fill_clk_mhz;
+			table->WatermarkRow[WM_SOCCLK][i].MinUclk =
+				clock_ranges->writer_wm_sets[i].min_drain_clk_mhz;
+			table->WatermarkRow[WM_SOCCLK][i].MaxUclk =
+				clock_ranges->writer_wm_sets[i].max_drain_clk_mhz;
+
+			table->WatermarkRow[WM_SOCCLK][i].WmSetting =
+				clock_ranges->writer_wm_sets[i].wm_inst;
 		}
 
 		smu->watermarks_bitmap |= WATERMARKS_EXIST;
@@ -2196,59 +2176,46 @@ static int navi10_run_btc(struct smu_context *smu)
 	return ret;
 }
 
-static int navi10_dummy_pstate_control(struct smu_context *smu, bool enable)
+static bool navi10_need_umc_cdr_workaround(struct smu_context *smu)
 {
-	int result = 0;
-
-	if (!enable)
-		result = smu_cmn_send_smc_msg(smu, SMU_MSG_DAL_DISABLE_DUMMY_PSTATE_CHANGE, NULL);
-	else
-		result = smu_cmn_send_smc_msg(smu, SMU_MSG_DAL_ENABLE_DUMMY_PSTATE_CHANGE, NULL);
-
-	return result;
-}
+	struct amdgpu_device *adev = smu->adev;
 
-static inline bool navi10_need_umc_cdr_12gbps_workaround(struct amdgpu_device *adev)
-{
-	if (adev->asic_type != CHIP_NAVI10)
+	if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_UCLK_BIT))
 		return false;
 
-	if (adev->pdev->device == 0x731f &&
-	    (adev->pdev->revision == 0xc2 ||
-	     adev->pdev->revision == 0xc3 ||
-	     adev->pdev->revision == 0xca ||
-	     adev->pdev->revision == 0xcb))
+	if (adev->asic_type == CHIP_NAVI10 ||
+	    adev->asic_type == CHIP_NAVI14)
 		return true;
-	else
-		return false;
+
+	return false;
 }
 
-static int navi10_disable_umc_cdr_12gbps_workaround(struct smu_context *smu)
+static int navi10_umc_hybrid_cdr_workaround(struct smu_context *smu)
 {
 	uint32_t uclk_count, uclk_min, uclk_max;
-	uint32_t smu_version;
 	int ret = 0;
 
-	if (!navi10_need_umc_cdr_12gbps_workaround(smu->adev))
-		return 0;
-
-	ret = smu_cmn_get_smc_version(smu, NULL, &smu_version);
-	if (ret)
-		return ret;
-
-	/* This workaround is available only for 42.50 or later SMC firmwares */
-	if (smu_version < 0x2A3200)
+	/* This workaround can be applied only with uclk dpm enabled */
+	if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_UCLK_BIT))
 		return 0;
 
 	ret = smu_v11_0_get_dpm_level_count(smu, SMU_UCLK, &uclk_count);
 	if (ret)
 		return ret;
 
-	ret = smu_v11_0_get_dpm_freq_by_index(smu, SMU_UCLK, (uint16_t)0, &uclk_min);
+	ret = smu_v11_0_get_dpm_freq_by_index(smu, SMU_UCLK, (uint16_t)(uclk_count - 1), &uclk_max);
 	if (ret)
 		return ret;
 
-	ret = smu_v11_0_get_dpm_freq_by_index(smu, SMU_UCLK, (uint16_t)(uclk_count - 1), &uclk_max);
+	/*
+	 * The NAVI10_UMC_HYBRID_CDR_WORKAROUND_UCLK_THRESHOLD is 750Mhz.
+	 * This workaround is needed only when the max uclk frequency
+	 * not greater than that.
+	 */
+	if (uclk_max > 0x2EE)
+		return 0;
+
+	ret = smu_v11_0_get_dpm_freq_by_index(smu, SMU_UCLK, (uint16_t)0, &uclk_min);
 	if (ret)
 		return ret;
 
@@ -2265,8 +2232,97 @@ static int navi10_disable_umc_cdr_12gbps_workaround(struct smu_context *smu)
 	/*
 	 * In this case, SMU already disabled dummy pstate during enablement
 	 * of UCLK DPM, we have to re-enabled it.
-	 * */
-	return navi10_dummy_pstate_control(smu, true);
+	 */
+	return smu_cmn_send_smc_msg(smu, SMU_MSG_DAL_ENABLE_DUMMY_PSTATE_CHANGE, NULL);
+}
+
+static int navi10_set_dummy_pstates_table_location(struct smu_context *smu)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct smu_table *dummy_read_table =
+				&smu_table->dummy_read_1_table;
+	char *dummy_table = dummy_read_table->cpu_addr;
+	int ret = 0;
+	uint32_t i;
+
+	for (i = 0; i < 0x40000; i += 0x1000 * 2) {
+		memcpy(dummy_table, &NoDbiPrbs7[0], 0x1000);
+		dummy_table += 0x1000;
+		memcpy(dummy_table, &DbiPrbs7[0], 0x1000);
+		dummy_table += 0x1000;
+	}
+
+	amdgpu_asic_flush_hdp(smu->adev, NULL);
+
+	ret = smu_cmn_send_smc_msg_with_param(smu,
+					      SMU_MSG_SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_HIGH,
+					      upper_32_bits(dummy_read_table->mc_address),
+					      NULL);
+	if (ret)
+		return ret;
+
+	return smu_cmn_send_smc_msg_with_param(smu,
+					       SMU_MSG_SET_DRIVER_DUMMY_TABLE_DRAM_ADDR_LOW,
+					       lower_32_bits(dummy_read_table->mc_address),
+					       NULL);
+}
+
+static int navi10_run_umc_cdr_workaround(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint8_t umc_fw_greater_than_v136 = false;
+	uint8_t umc_fw_disable_cdr = false;
+	uint32_t pmfw_version;
+	uint32_t param;
+	int ret = 0;
+
+	if (!navi10_need_umc_cdr_workaround(smu))
+		return 0;
+
+	ret = smu_cmn_get_smc_version(smu, NULL, &pmfw_version);
+	if (ret) {
+		dev_err(adev->dev, "Failed to get smu version!\n");
+		return ret;
+	}
+
+	/*
+	 * The messages below are only supported by Navi10 42.53.0 and later
+	 * PMFWs and Navi14 53.29.0 and later PMFWs.
+	 * - PPSMC_MSG_SetDriverDummyTableDramAddrHigh
+	 * - PPSMC_MSG_SetDriverDummyTableDramAddrLow
+	 * - PPSMC_MSG_GetUMCFWWA
+	 */
+	if (((adev->asic_type == CHIP_NAVI10) && (pmfw_version >= 0x2a3500)) ||
+	    ((adev->asic_type == CHIP_NAVI14) && (pmfw_version >= 0x351D00))) {
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+						      SMU_MSG_GET_UMC_FW_WA,
+						      0,
+						      &param);
+		if (ret)
+			return ret;
+
+		/* First bit indicates if the UMC f/w is above v137 */
+		umc_fw_greater_than_v136 = param & 0x1;
+
+		/* Second bit indicates if hybrid-cdr is disabled */
+		umc_fw_disable_cdr = param & 0x2;
+
+		/* w/a only allowed if UMC f/w is <= 136 */
+		if (umc_fw_greater_than_v136)
+			return 0;
+
+		if (umc_fw_disable_cdr) {
+			if (adev->asic_type == CHIP_NAVI10)
+				return navi10_umc_hybrid_cdr_workaround(smu);
+		} else {
+			return navi10_set_dummy_pstates_table_location(smu);
+		}
+	} else {
+		if (adev->asic_type == CHIP_NAVI10)
+			return navi10_umc_hybrid_cdr_workaround(smu);
+	}
+
+	return 0;
 }
 
 static void navi10_fill_i2c_req(SwI2cRequest_t  *req, bool write,
@@ -2275,8 +2331,6 @@ static void navi10_fill_i2c_req(SwI2cRequest_t  *req, bool write,
 {
 	int i;
 
-	BUG_ON(numbytes > MAX_SW_I2C_COMMANDS);
-
 	req->I2CcontrollerPort = 0;
 	req->I2CSpeed = 2;
 	req->SlaveAddress = address;
@@ -2314,6 +2368,12 @@ static int navi10_i2c_read_data(struct i2c_adapter *control,
 	struct smu_table_context *smu_table = &adev->smu.smu_table;
 	struct smu_table *table = &smu_table->driver_table;
 
+	if (numbytes > MAX_SW_I2C_COMMANDS) {
+		dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n",
+			numbytes, MAX_SW_I2C_COMMANDS);
+		return -EINVAL;
+	}
+
 	memset(&req, 0, sizeof(req));
 	navi10_fill_i2c_req(&req, false, address, numbytes, data);
 
@@ -2350,6 +2410,12 @@ static int navi10_i2c_write_data(struct i2c_adapter *control,
 	SwI2cRequest_t req;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 
+	if (numbytes > MAX_SW_I2C_COMMANDS) {
+		dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n",
+			numbytes, MAX_SW_I2C_COMMANDS);
+		return -EINVAL;
+	}
+
 	memset(&req, 0, sizeof(req));
 	navi10_fill_i2c_req(&req, true, address, numbytes, data);
 
@@ -2463,29 +2529,6 @@ static const struct i2c_algorithm navi10_i2c_algo = {
 	.functionality = navi10_i2c_func,
 };
 
-static int navi10_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control)
-{
-	struct amdgpu_device *adev = to_amdgpu_device(control);
-	int res;
-
-	control->owner = THIS_MODULE;
-	control->class = I2C_CLASS_SPD;
-	control->dev.parent = &adev->pdev->dev;
-	control->algo = &navi10_i2c_algo;
-	snprintf(control->name, sizeof(control->name), "AMDGPU SMU");
-
-	res = i2c_add_adapter(control);
-	if (res)
-		DRM_ERROR("Failed to register hw i2c, err: %d\n", res);
-
-	return res;
-}
-
-static void navi10_i2c_control_fini(struct smu_context *smu, struct i2c_adapter *control)
-{
-	i2c_del_adapter(control);
-}
-
 static ssize_t navi10_get_gpu_metrics(struct smu_context *smu,
 				      void **table)
 {
@@ -2578,13 +2621,44 @@ static int navi10_enable_mgpu_fan_boost(struct smu_context *smu)
 					       NULL);
 }
 
+static int navi10_post_smu_init(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = navi10_run_umc_cdr_workaround(smu);
+	if (ret) {
+		dev_err(adev->dev, "Failed to apply umc cdr workaround!\n");
+		return ret;
+	}
+
+	if (!smu->dc_controlled_by_gpio) {
+		/*
+		 * For Navi1X, manually switch it to AC mode as PMFW
+		 * may boot it with DC mode.
+		 */
+		ret = smu_v11_0_set_power_source(smu,
+						 adev->pm.ac_power ?
+						 SMU_POWER_SOURCE_AC :
+						 SMU_POWER_SOURCE_DC);
+		if (ret) {
+			dev_err(adev->dev, "Failed to switch to %s mode!\n",
+					adev->pm.ac_power ? "AC" : "DC");
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
 static const struct pptable_funcs navi10_ppt_funcs = {
 	.get_allowed_feature_mask = navi10_get_allowed_feature_mask,
 	.set_default_dpm_table = navi10_set_default_dpm_table,
 	.dpm_set_vcn_enable = navi10_dpm_set_vcn_enable,
 	.dpm_set_jpeg_enable = navi10_dpm_set_jpeg_enable,
-	.i2c_init = navi10_i2c_control_init,
-	.i2c_fini = navi10_i2c_control_fini,
 	.print_clk_levels = navi10_print_clk_levels,
 	.force_clk_levels = navi10_force_clk_levels,
 	.populate_umd_state_clk = navi10_populate_umd_state_clk,
@@ -2652,7 +2726,6 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.set_default_od_settings = navi10_set_default_od_settings,
 	.od_edit_dpm_table = navi10_od_edit_dpm_table,
 	.run_btc = navi10_run_btc,
-	.disable_umc_cdr_12gbps_workaround = navi10_disable_umc_cdr_12gbps_workaround,
 	.set_power_source = smu_v11_0_set_power_source,
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
 	.set_pp_feature_mask = smu_cmn_set_pp_feature_mask,
@@ -2661,6 +2734,8 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.gfx_ulv_control = smu_v11_0_gfx_ulv_control,
 	.deep_sleep_control = smu_v11_0_deep_sleep_control,
 	.get_fan_parameters = navi10_get_fan_parameters,
+	.post_init = navi10_post_smu_init,
+	.interrupt_work = smu_v11_0_interrupt_work,
 };
 
 void navi10_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 5c22611d5878..895d89bea7fa 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -151,14 +151,17 @@ static struct cmn2asic_mapping sienna_cichlid_feature_mask_map[SMU_FEATURE_COUNT
 	FEA_MAP(DPM_GFXCLK),
 	FEA_MAP(DPM_GFX_GPO),
 	FEA_MAP(DPM_UCLK),
+	FEA_MAP(DPM_FCLK),
 	FEA_MAP(DPM_SOCCLK),
 	FEA_MAP(DPM_MP0CLK),
 	FEA_MAP(DPM_LINK),
 	FEA_MAP(DPM_DCEFCLK),
+	FEA_MAP(DPM_XGMI),
 	FEA_MAP(MEM_VDDCI_SCALING),
 	FEA_MAP(MEM_MVDD_SCALING),
 	FEA_MAP(DS_GFXCLK),
 	FEA_MAP(DS_SOCCLK),
+	FEA_MAP(DS_FCLK),
 	FEA_MAP(DS_LCLK),
 	FEA_MAP(DS_DCEFCLK),
 	FEA_MAP(DS_UCLK),
@@ -298,11 +301,9 @@ static int sienna_cichlid_check_powerplay_table(struct smu_context *smu)
 		table_context->power_play_table;
 	struct smu_baco_context *smu_baco = &smu->smu_baco;
 
-	mutex_lock(&smu_baco->mutex);
 	if (powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_BACO ||
 	    powerplay_table->platform_caps & SMU_11_0_7_PP_PLATFORM_CAP_MACO)
 		smu_baco->platform_support = true;
-	mutex_unlock(&smu_baco->mutex);
 
 	table_context->thermal_controller_type =
 		powerplay_table->thermal_controller_type;
@@ -454,6 +455,9 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu,
 	case METRICS_CURR_DCEFCLK:
 		*value = metrics->CurrClock[PPCLK_DCEFCLK];
 		break;
+	case METRICS_CURR_FCLK:
+		*value = metrics->CurrClock[PPCLK_FCLK];
+		break;
 	case METRICS_AVERAGE_GFXCLK:
 		if (metrics->AverageGfxActivity <= SMU_11_0_7_GFX_BUSY_THRESHOLD)
 			*value = metrics->AverageGfxclkFrequencyPostDs;
@@ -950,19 +954,23 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu,
 			freq_values[1] = cur_value;
 			mark_index = cur_value == freq_values[0] ? 0 :
 				     cur_value == freq_values[2] ? 2 : 1;
-			if (mark_index != 1)
-				freq_values[1] = (freq_values[0] + freq_values[2]) / 2;
 
-			for (i = 0; i < 3; i++) {
+			count = 3;
+			if (mark_index != 1) {
+				count = 2;
+				freq_values[1] = freq_values[2];
+			}
+
+			for (i = 0; i < count; i++) {
 				size += sprintf(buf + size, "%d: %uMhz %s\n", i, freq_values[i],
-						i == mark_index ? "*" : "");
+						cur_value  == freq_values[i] ? "*" : "");
 			}
 
 		}
 		break;
 	case SMU_PCIE:
-		gen_speed = smu_v11_0_get_current_pcie_link_speed(smu);
-		lane_width = smu_v11_0_get_current_pcie_link_width(smu);
+		gen_speed = smu_v11_0_get_current_pcie_link_speed_level(smu);
+		lane_width = smu_v11_0_get_current_pcie_link_width_level(smu);
 		for (i = 0; i < NUM_LINK_LEVELS; i++)
 			size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
 					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 0) ? "2.5GT/s," :
@@ -1169,14 +1177,9 @@ static int sienna_cichlid_get_fan_speed_rpm(struct smu_context *smu,
 	if (!speed)
 		return -EINVAL;
 
-	switch (smu_v11_0_get_fan_control_mode(smu)) {
-	case AMD_FAN_CTRL_AUTO:
-		return sienna_cichlid_get_smu_metrics_data(smu,
-							   METRICS_CURR_FANSPEED,
-							   speed);
-	default:
-		return smu_v11_0_get_fan_speed_rpm(smu, speed);
-	}
+	return sienna_cichlid_get_smu_metrics_data(smu,
+						METRICS_CURR_FANSPEED,
+						speed);
 }
 
 static int sienna_cichlid_get_fan_parameters(struct smu_context *smu)
@@ -1409,58 +1412,43 @@ static int sienna_cichlid_notify_smc_display_config(struct smu_context *smu)
 }
 
 static int sienna_cichlid_set_watermarks_table(struct smu_context *smu,
-					       struct dm_pp_wm_sets_with_clock_ranges_soc15
-					       *clock_ranges)
+					       struct pp_smu_wm_range_sets *clock_ranges)
 {
 	Watermarks_t *table = smu->smu_table.watermarks_table;
 	int ret = 0;
 	int i;
 
 	if (clock_ranges) {
-		if (clock_ranges->num_wm_dmif_sets > 4 ||
-		    clock_ranges->num_wm_mcif_sets > 4)
+		if (clock_ranges->num_reader_wm_sets > NUM_WM_RANGES ||
+		    clock_ranges->num_writer_wm_sets > NUM_WM_RANGES)
 			return -EINVAL;
 
-		for (i = 0; i < clock_ranges->num_wm_dmif_sets; i++) {
-			table->WatermarkRow[1][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz /
-				1000));
-			table->WatermarkRow[1][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz /
-				1000));
-			table->WatermarkRow[1][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz /
-				1000));
-			table->WatermarkRow[1][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz /
-				1000));
-			table->WatermarkRow[1][i].WmSetting = (uint8_t)
-					clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id;
+		for (i = 0; i < clock_ranges->num_reader_wm_sets; i++) {
+			table->WatermarkRow[WM_DCEFCLK][i].MinClock =
+				clock_ranges->reader_wm_sets[i].min_drain_clk_mhz;
+			table->WatermarkRow[WM_DCEFCLK][i].MaxClock =
+				clock_ranges->reader_wm_sets[i].max_drain_clk_mhz;
+			table->WatermarkRow[WM_DCEFCLK][i].MinUclk =
+				clock_ranges->reader_wm_sets[i].min_fill_clk_mhz;
+			table->WatermarkRow[WM_DCEFCLK][i].MaxUclk =
+				clock_ranges->reader_wm_sets[i].max_fill_clk_mhz;
+
+			table->WatermarkRow[WM_DCEFCLK][i].WmSetting =
+				clock_ranges->reader_wm_sets[i].wm_inst;
 		}
 
-		for (i = 0; i < clock_ranges->num_wm_mcif_sets; i++) {
-			table->WatermarkRow[0][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz /
-				1000));
-			table->WatermarkRow[0][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz /
-				1000));
-			table->WatermarkRow[0][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz /
-				1000));
-			table->WatermarkRow[0][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz /
-				1000));
-			table->WatermarkRow[0][i].WmSetting = (uint8_t)
-					clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id;
+		for (i = 0; i < clock_ranges->num_writer_wm_sets; i++) {
+			table->WatermarkRow[WM_SOCCLK][i].MinClock =
+				clock_ranges->writer_wm_sets[i].min_fill_clk_mhz;
+			table->WatermarkRow[WM_SOCCLK][i].MaxClock =
+				clock_ranges->writer_wm_sets[i].max_fill_clk_mhz;
+			table->WatermarkRow[WM_SOCCLK][i].MinUclk =
+				clock_ranges->writer_wm_sets[i].min_drain_clk_mhz;
+			table->WatermarkRow[WM_SOCCLK][i].MaxUclk =
+				clock_ranges->writer_wm_sets[i].max_drain_clk_mhz;
+
+			table->WatermarkRow[WM_SOCCLK][i].WmSetting =
+				clock_ranges->writer_wm_sets[i].wm_inst;
 		}
 
 		smu->watermarks_bitmap |= WATERMARKS_EXIST;
@@ -2291,11 +2279,6 @@ static void sienna_cichlid_dump_pptable(struct smu_context *smu)
 	dev_info(smu->adev->dev, "SkuReserved[6] = 0x%x\n", pptable->SkuReserved[6]);
 	dev_info(smu->adev->dev, "SkuReserved[7] = 0x%x\n", pptable->SkuReserved[7]);
 	dev_info(smu->adev->dev, "SkuReserved[8] = 0x%x\n", pptable->SkuReserved[8]);
-	dev_info(smu->adev->dev, "SkuReserved[9] = 0x%x\n", pptable->SkuReserved[9]);
-	dev_info(smu->adev->dev, "SkuReserved[10] = 0x%x\n", pptable->SkuReserved[10]);
-	dev_info(smu->adev->dev, "SkuReserved[11] = 0x%x\n", pptable->SkuReserved[11]);
-	dev_info(smu->adev->dev, "SkuReserved[12] = 0x%x\n", pptable->SkuReserved[12]);
-	dev_info(smu->adev->dev, "SkuReserved[13] = 0x%x\n", pptable->SkuReserved[13]);
 
 	dev_info(smu->adev->dev, "GamingClk[0] = 0x%x\n", pptable->GamingClk[0]);
 	dev_info(smu->adev->dev, "GamingClk[1] = 0x%x\n", pptable->GamingClk[1]);
@@ -2444,8 +2427,6 @@ static void sienna_cichlid_fill_i2c_req(SwI2cRequest_t  *req, bool write,
 {
 	int i;
 
-	BUG_ON(numbytes > MAX_SW_I2C_COMMANDS);
-
 	req->I2CcontrollerPort = 0;
 	req->I2CSpeed = 2;
 	req->SlaveAddress = address;
@@ -2483,6 +2464,12 @@ static int sienna_cichlid_i2c_read_data(struct i2c_adapter *control,
 	struct smu_table_context *smu_table = &adev->smu.smu_table;
 	struct smu_table *table = &smu_table->driver_table;
 
+	if (numbytes > MAX_SW_I2C_COMMANDS) {
+		dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n",
+			numbytes, MAX_SW_I2C_COMMANDS);
+		return -EINVAL;
+	}
+
 	memset(&req, 0, sizeof(req));
 	sienna_cichlid_fill_i2c_req(&req, false, address, numbytes, data);
 
@@ -2519,6 +2506,12 @@ static int sienna_cichlid_i2c_write_data(struct i2c_adapter *control,
 	SwI2cRequest_t req;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 
+	if (numbytes > MAX_SW_I2C_COMMANDS) {
+		dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n",
+			numbytes, MAX_SW_I2C_COMMANDS);
+		return -EINVAL;
+	}
+
 	memset(&req, 0, sizeof(req));
 	sienna_cichlid_fill_i2c_req(&req, true, address, numbytes, data);
 
@@ -2806,6 +2799,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.gfx_ulv_control = smu_v11_0_gfx_ulv_control,
 	.deep_sleep_control = smu_v11_0_deep_sleep_control,
 	.get_fan_parameters = sienna_cichlid_get_fan_parameters,
+	.interrupt_work = smu_v11_0_interrupt_work,
 };
 
 void sienna_cichlid_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index f5aeb0b5cf97..2380759ddf48 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -322,39 +322,42 @@ int smu_v11_0_setup_pptable(struct smu_context *smu)
 	void *table;
 	uint16_t version_major, version_minor;
 
-	hdr = (const struct smc_firmware_header_v1_0 *) adev->pm.fw->data;
-	version_major = le16_to_cpu(hdr->header.header_version_major);
-	version_minor = le16_to_cpu(hdr->header.header_version_minor);
-	if ((version_major == 2 && smu->smu_table.boot_values.pp_table_id > 0) ||
-	    adev->asic_type == CHIP_NAVY_FLOUNDER) {
-		dev_info(adev->dev, "use driver provided pptable %d\n", smu->smu_table.boot_values.pp_table_id);
-		switch (version_minor) {
-		case 0:
-			ret = smu_v11_0_set_pptable_v2_0(smu, &table, &size);
-			break;
-		case 1:
-			ret = smu_v11_0_set_pptable_v2_1(smu, &table, &size,
-							 smu->smu_table.boot_values.pp_table_id);
-			break;
-		default:
-			ret = -EINVAL;
-			break;
+	if (!amdgpu_sriov_vf(adev)) {
+		hdr = (const struct smc_firmware_header_v1_0 *) adev->pm.fw->data;
+		version_major = le16_to_cpu(hdr->header.header_version_major);
+		version_minor = le16_to_cpu(hdr->header.header_version_minor);
+		if ((version_major == 2 && smu->smu_table.boot_values.pp_table_id > 0) ||
+			adev->asic_type == CHIP_NAVY_FLOUNDER) {
+			dev_info(adev->dev, "use driver provided pptable %d\n", smu->smu_table.boot_values.pp_table_id);
+			switch (version_minor) {
+			case 0:
+				ret = smu_v11_0_set_pptable_v2_0(smu, &table, &size);
+				break;
+			case 1:
+				ret = smu_v11_0_set_pptable_v2_1(smu, &table, &size,
+								smu->smu_table.boot_values.pp_table_id);
+				break;
+			default:
+				ret = -EINVAL;
+				break;
+			}
+			if (ret)
+				return ret;
+			goto out;
 		}
-		if (ret)
-			return ret;
+	}
 
-	} else {
-		dev_info(adev->dev, "use vbios provided pptable\n");
-		index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
-						    powerplayinfo);
+	dev_info(adev->dev, "use vbios provided pptable\n");
+	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
+						powerplayinfo);
 
-		ret = amdgpu_atombios_get_data_table(adev, index, &atom_table_size, &frev, &crev,
-					      (uint8_t **)&table);
-		if (ret)
-			return ret;
-		size = atom_table_size;
-	}
+	ret = amdgpu_atombios_get_data_table(adev, index, &atom_table_size, &frev, &crev,
+						(uint8_t **)&table);
+	if (ret)
+		return ret;
+	size = atom_table_size;
 
+out:
 	if (!smu->smu_table.power_play_table)
 		smu->smu_table.power_play_table = table;
 	if (!smu->smu_table.power_play_table_size)
@@ -453,9 +456,6 @@ int smu_v11_0_init_power(struct smu_context *smu)
 {
 	struct smu_power_context *smu_power = &smu->smu_power;
 
-	if (smu_power->power_context || smu_power->power_context_size != 0)
-		return -EINVAL;
-
 	smu_power->power_context = kzalloc(sizeof(struct smu_11_0_dpm_context),
 					   GFP_KERNEL);
 	if (!smu_power->power_context)
@@ -469,9 +469,6 @@ int smu_v11_0_fini_power(struct smu_context *smu)
 {
 	struct smu_power_context *smu_power = &smu->smu_power;
 
-	if (!smu_power->power_context || smu_power->power_context_size == 0)
-		return -EINVAL;
-
 	kfree(smu_power->power_context);
 	smu_power->power_context = NULL;
 	smu_power->power_context_size = 0;
@@ -700,18 +697,16 @@ int smu_v11_0_set_tool_table_location(struct smu_context *smu)
 
 int smu_v11_0_init_display_count(struct smu_context *smu, uint32_t count)
 {
-	int ret = 0;
 	struct amdgpu_device *adev = smu->adev;
 
 	/* Navy_Flounder do not support to change display num currently */
 	if (adev->asic_type == CHIP_NAVY_FLOUNDER)
 		return 0;
 
-	if (!smu->pm_enabled)
-		return ret;
-
-	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_NumOfDisplays, count, NULL);
-	return ret;
+	return smu_cmn_send_smc_msg_with_param(smu,
+					       SMU_MSG_NumOfDisplays,
+					       count,
+					       NULL);
 }
 
 
@@ -721,7 +716,6 @@ int smu_v11_0_set_allowed_mask(struct smu_context *smu)
 	int ret = 0;
 	uint32_t feature_mask[2];
 
-	mutex_lock(&feature->mutex);
 	if (bitmap_empty(feature->allowed, SMU_FEATURE_MAX) || feature->feature_num < 64)
 		goto failed;
 
@@ -738,7 +732,6 @@ int smu_v11_0_set_allowed_mask(struct smu_context *smu)
 		goto failed;
 
 failed:
-	mutex_unlock(&feature->mutex);
 	return ret;
 }
 
@@ -775,9 +768,6 @@ int smu_v11_0_notify_display_change(struct smu_context *smu)
 {
 	int ret = 0;
 
-	if (!smu->pm_enabled)
-		return ret;
-
 	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_UCLK_BIT) &&
 	    smu->adev->gmc.vram_type == AMDGPU_VRAM_TYPE_HBM)
 		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetUclkFastSwitch, 1, NULL);
@@ -947,12 +937,45 @@ int smu_v11_0_set_power_limit(struct smu_context *smu, uint32_t n)
 	return 0;
 }
 
+static int smu_v11_0_ack_ac_dc_interrupt(struct smu_context *smu)
+{
+	return smu_cmn_send_smc_msg(smu,
+				SMU_MSG_ReenableAcDcInterrupt,
+				NULL);
+}
+
+static int smu_v11_0_process_pending_interrupt(struct smu_context *smu)
+{
+	int ret = 0;
+
+	if (smu->dc_controlled_by_gpio &&
+	    smu_cmn_feature_is_enabled(smu, SMU_FEATURE_ACDC_BIT))
+		ret = smu_v11_0_ack_ac_dc_interrupt(smu);
+
+	return ret;
+}
+
+void smu_v11_0_interrupt_work(struct smu_context *smu)
+{
+	if (smu_v11_0_ack_ac_dc_interrupt(smu))
+		dev_err(smu->adev->dev, "Ack AC/DC interrupt Failed!\n");
+}
+
 int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 {
-	if (smu->smu_table.thermal_controller_type)
-		return amdgpu_irq_get(smu->adev, &smu->irq_source, 0);
+	int ret = 0;
 
-	return 0;
+	if (smu->smu_table.thermal_controller_type) {
+		ret = amdgpu_irq_get(smu->adev, &smu->irq_source, 0);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * After init there might have been missed interrupts triggered
+	 * before driver registers for interrupt (Ex. AC/DC).
+	 */
+	return smu_v11_0_process_pending_interrupt(smu);
 }
 
 int smu_v11_0_disable_thermal_alert(struct smu_context *smu)
@@ -1177,12 +1200,10 @@ int smu_v11_0_get_fan_speed_rpm(struct smu_context *smu,
 int smu_v11_0_set_xgmi_pstate(struct smu_context *smu,
 				     uint32_t pstate)
 {
-	int ret = 0;
-	ret = smu_cmn_send_smc_msg_with_param(smu,
-					  SMU_MSG_SetXgmiMode,
-					  pstate ? XGMI_MODE_PSTATE_D0 : XGMI_MODE_PSTATE_D3,
+	return smu_cmn_send_smc_msg_with_param(smu,
+					       SMU_MSG_SetXgmiMode,
+					       pstate ? XGMI_MODE_PSTATE_D0 : XGMI_MODE_PSTATE_D3,
 					  NULL);
-	return ret;
 }
 
 static int smu_v11_0_set_irq_state(struct amdgpu_device *adev,
@@ -1250,13 +1271,6 @@ static int smu_v11_0_set_irq_state(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int smu_v11_0_ack_ac_dc_interrupt(struct smu_context *smu)
-{
-	return smu_cmn_send_smc_msg(smu,
-				SMU_MSG_ReenableAcDcInterrupt,
-				NULL);
-}
-
 #define THM_11_0__SRCID__THM_DIG_THERM_L2H		0		/* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH  */
 #define THM_11_0__SRCID__THM_DIG_THERM_H2L		1		/* ASIC_TEMP < CG_THERMAL_INT.DIG_THERM_INTL  */
 
@@ -1312,11 +1326,11 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 			switch (ctxid) {
 			case 0x3:
 				dev_dbg(adev->dev, "Switched to AC mode!\n");
-				smu_v11_0_ack_ac_dc_interrupt(&adev->smu);
+				schedule_work(&smu->interrupt_work);
 				break;
 			case 0x4:
 				dev_dbg(adev->dev, "Switched to DC mode!\n");
-				smu_v11_0_ack_ac_dc_interrupt(&adev->smu);
+				schedule_work(&smu->interrupt_work);
 				break;
 			case 0x7:
 				/*
@@ -1413,11 +1427,7 @@ int smu_v11_0_get_max_sustainable_clocks_by_dc(struct smu_context *smu,
 
 int smu_v11_0_set_azalia_d3_pme(struct smu_context *smu)
 {
-	int ret = 0;
-
-	ret = smu_cmn_send_smc_msg(smu, SMU_MSG_BacoAudioD3PME, NULL);
-
-	return ret;
+	return smu_cmn_send_smc_msg(smu, SMU_MSG_BacoAudioD3PME, NULL);
 }
 
 static int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, enum smu_v11_0_baco_seq baco_seq)
@@ -1428,13 +1438,8 @@ static int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, enum smu_v
 bool smu_v11_0_baco_is_support(struct smu_context *smu)
 {
 	struct smu_baco_context *smu_baco = &smu->smu_baco;
-	bool baco_support;
 
-	mutex_lock(&smu_baco->mutex);
-	baco_support = smu_baco->platform_support;
-	mutex_unlock(&smu_baco->mutex);
-
-	if (!baco_support)
+	if (!smu_baco->platform_support)
 		return false;
 
 	/* Arcturus does not support this bit mask */
@@ -1521,13 +1526,7 @@ int smu_v11_0_baco_enter(struct smu_context *smu)
 
 int smu_v11_0_baco_exit(struct smu_context *smu)
 {
-	int ret = 0;
-
-	ret = smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_EXIT);
-	if (ret)
-		return ret;
-
-	return ret;
+	return smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_EXIT);
 }
 
 int smu_v11_0_mode1_reset(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index 3b9ac72c7571..66c1026489be 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -222,14 +222,16 @@ static int renoir_get_profiling_clk_mask(struct smu_context *smu,
 			*sclk_mask = 0;
 	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) {
 		if (mclk_mask)
-			*mclk_mask = 0;
+			/* mclk levels are in reverse order */
+			*mclk_mask = NUM_MEMCLK_DPM_LEVELS - 1;
 	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
 		if(sclk_mask)
 			/* The sclk as gfxclk and has three level about max/min/current */
 			*sclk_mask = 3 - 1;
 
 		if(mclk_mask)
-			*mclk_mask = NUM_MEMCLK_DPM_LEVELS - 1;
+			/* mclk levels are in reverse order */
+			*mclk_mask = 0;
 
 		if(soc_mask)
 			*soc_mask = NUM_SOCCLK_DPM_LEVELS - 1;
@@ -323,7 +325,7 @@ static int renoir_get_dpm_ultimate_freq(struct smu_context *smu,
 		case SMU_UCLK:
 		case SMU_FCLK:
 		case SMU_MCLK:
-			ret = renoir_get_dpm_clk_limited(smu, clk_type, 0, min);
+			ret = renoir_get_dpm_clk_limited(smu, clk_type, NUM_MEMCLK_DPM_LEVELS - 1, min);
 			if (ret)
 				goto failed;
 			break;
@@ -832,9 +834,59 @@ static int renoir_set_performance_level(struct smu_context *smu,
 		ret = renoir_force_dpm_limit_value(smu, false);
 		break;
 	case AMD_DPM_FORCED_LEVEL_AUTO:
-	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
 		ret = renoir_unforce_dpm_levels(smu);
 		break;
+	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+						      SMU_MSG_SetHardMinGfxClk,
+						      RENOIR_UMD_PSTATE_GFXCLK,
+						      NULL);
+		if (ret)
+			return ret;
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+						      SMU_MSG_SetHardMinFclkByFreq,
+						      RENOIR_UMD_PSTATE_FCLK,
+						      NULL);
+		if (ret)
+			return ret;
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+						      SMU_MSG_SetHardMinSocclkByFreq,
+						      RENOIR_UMD_PSTATE_SOCCLK,
+						      NULL);
+		if (ret)
+			return ret;
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+						      SMU_MSG_SetHardMinVcn,
+						      RENOIR_UMD_PSTATE_VCNCLK,
+						      NULL);
+		if (ret)
+			return ret;
+
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+						      SMU_MSG_SetSoftMaxGfxClk,
+						      RENOIR_UMD_PSTATE_GFXCLK,
+						      NULL);
+		if (ret)
+			return ret;
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+						      SMU_MSG_SetSoftMaxFclkByFreq,
+						      RENOIR_UMD_PSTATE_FCLK,
+						      NULL);
+		if (ret)
+			return ret;
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+						      SMU_MSG_SetSoftMaxSocclkByFreq,
+						      RENOIR_UMD_PSTATE_SOCCLK,
+						      NULL);
+		if (ret)
+			return ret;
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+						      SMU_MSG_SetSoftMaxVcn,
+						      RENOIR_UMD_PSTATE_VCNCLK,
+						      NULL);
+		if (ret)
+			return ret;
+		break;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
 		ret = renoir_get_profiling_clk_mask(smu, level,
@@ -863,50 +915,48 @@ static int renoir_set_performance_level(struct smu_context *smu,
  */
 static int renoir_set_watermarks_table(
 		struct smu_context *smu,
-		struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges)
+		struct pp_smu_wm_range_sets *clock_ranges)
 {
 	Watermarks_t *table = smu->smu_table.watermarks_table;
 	int ret = 0;
 	int i;
 
 	if (clock_ranges) {
-		if (clock_ranges->num_wm_dmif_sets > 4 ||
-				clock_ranges->num_wm_mcif_sets > 4)
+		if (clock_ranges->num_reader_wm_sets > NUM_WM_RANGES ||
+		    clock_ranges->num_writer_wm_sets > NUM_WM_RANGES)
 			return -EINVAL;
 
 		/* save into smu->smu_table.tables[SMU_TABLE_WATERMARKS]->cpu_addr*/
-		for (i = 0; i < clock_ranges->num_wm_dmif_sets; i++) {
+		for (i = 0; i < clock_ranges->num_reader_wm_sets; i++) {
 			table->WatermarkRow[WM_DCFCLK][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz));
+				clock_ranges->reader_wm_sets[i].min_drain_clk_mhz;
 			table->WatermarkRow[WM_DCFCLK][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz));
+				clock_ranges->reader_wm_sets[i].max_drain_clk_mhz;
 			table->WatermarkRow[WM_DCFCLK][i].MinMclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz));
+				clock_ranges->reader_wm_sets[i].min_fill_clk_mhz;
 			table->WatermarkRow[WM_DCFCLK][i].MaxMclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz));
-			table->WatermarkRow[WM_DCFCLK][i].WmSetting = (uint8_t)
-					clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id;
+				clock_ranges->reader_wm_sets[i].max_fill_clk_mhz;
+
+			table->WatermarkRow[WM_DCFCLK][i].WmSetting =
+				clock_ranges->reader_wm_sets[i].wm_inst;
+			table->WatermarkRow[WM_DCFCLK][i].WmType =
+				clock_ranges->reader_wm_sets[i].wm_type;
 		}
 
-		for (i = 0; i < clock_ranges->num_wm_mcif_sets; i++) {
+		for (i = 0; i < clock_ranges->num_writer_wm_sets; i++) {
 			table->WatermarkRow[WM_SOCCLK][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz));
+				clock_ranges->writer_wm_sets[i].min_fill_clk_mhz;
 			table->WatermarkRow[WM_SOCCLK][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz));
+				clock_ranges->writer_wm_sets[i].max_fill_clk_mhz;
 			table->WatermarkRow[WM_SOCCLK][i].MinMclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz));
+				clock_ranges->writer_wm_sets[i].min_drain_clk_mhz;
 			table->WatermarkRow[WM_SOCCLK][i].MaxMclk =
-				cpu_to_le16((uint16_t)
-				(clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz));
-			table->WatermarkRow[WM_SOCCLK][i].WmSetting = (uint8_t)
-					clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id;
+				clock_ranges->writer_wm_sets[i].max_drain_clk_mhz;
+
+			table->WatermarkRow[WM_SOCCLK][i].WmSetting =
+				clock_ranges->writer_wm_sets[i].wm_inst;
+			table->WatermarkRow[WM_SOCCLK][i].WmType =
+				clock_ranges->writer_wm_sets[i].wm_type;
 		}
 
 		smu->watermarks_bitmap |= WATERMARKS_EXIST;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.h
index 8c3f004cdf8d..11c3c22fecbe 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.h
@@ -29,5 +29,6 @@ extern void renoir_set_ppt_funcs(struct smu_context *smu);
 #define RENOIR_UMD_PSTATE_GFXCLK       700
 #define RENOIR_UMD_PSTATE_SOCCLK       678
 #define RENOIR_UMD_PSTATE_FCLK         800
+#define RENOIR_UMD_PSTATE_VCNCLK       0x022D01D8
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index a58ea08cd115..92b2ea4c197b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -112,6 +112,9 @@ int smu_cmn_send_smc_msg_with_param(struct smu_context *smu,
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0, index = 0;
 
+	if (smu->adev->in_pci_err_recovery)
+		return 0;
+
 	index = smu_cmn_to_asic_specific_index(smu,
 					       CMN2ASIC_MAPPING_MSG,
 					       msg);
@@ -343,9 +346,9 @@ int smu_cmn_get_enabled_mask(struct smu_context *smu,
 	return ret;
 }
 
-static int smu_cmn_feature_update_enable_state(struct smu_context *smu,
-					       uint64_t feature_mask,
-					       bool enabled)
+int smu_cmn_feature_update_enable_state(struct smu_context *smu,
+					uint64_t feature_mask,
+					bool enabled)
 {
 	struct smu_feature *feature = &smu->smu_feature;
 	int ret = 0;
@@ -428,10 +431,9 @@ size_t smu_cmn_get_pp_feature_mask(struct smu_context *smu,
 				   char *buf)
 {
 	uint32_t feature_mask[2] = { 0 };
-	int32_t feature_index = 0;
+	int feature_index = 0;
 	uint32_t count = 0;
-	uint32_t sort_feature[SMU_FEATURE_COUNT];
-	uint64_t hw_feature_count = 0;
+	int8_t sort_feature[SMU_FEATURE_COUNT];
 	size_t size = 0;
 	int ret = 0, i;
 
@@ -444,23 +446,31 @@ size_t smu_cmn_get_pp_feature_mask(struct smu_context *smu,
 	size =  sprintf(buf + size, "features high: 0x%08x low: 0x%08x\n",
 			feature_mask[1], feature_mask[0]);
 
+	memset(sort_feature, -1, sizeof(sort_feature));
+
 	for (i = 0; i < SMU_FEATURE_COUNT; i++) {
 		feature_index = smu_cmn_to_asic_specific_index(smu,
 							       CMN2ASIC_MAPPING_FEATURE,
 							       i);
 		if (feature_index < 0)
 			continue;
+
 		sort_feature[feature_index] = i;
-		hw_feature_count++;
 	}
 
-	for (i = 0; i < hw_feature_count; i++) {
+	size += sprintf(buf + size, "%-2s. %-20s  %-3s : %-s\n",
+			"No", "Feature", "Bit", "State");
+
+	for (i = 0; i < SMU_FEATURE_COUNT; i++) {
+		if (sort_feature[i] < 0)
+			continue;
+
 		size += sprintf(buf + size, "%02d. %-20s (%2d) : %s\n",
-			       count++,
-			       smu_get_feature_name(smu, sort_feature[i]),
-			       i,
-			       !!smu_cmn_feature_is_enabled(smu, sort_feature[i]) ?
-			       "enabled" : "disabled");
+				count++,
+				smu_get_feature_name(smu, sort_feature[i]),
+				i,
+				!!smu_cmn_feature_is_enabled(smu, sort_feature[i]) ?
+				"enabled" : "disabled");
 	}
 
 	return size;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index 6d00ad740c27..ab577be23c15 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -52,6 +52,10 @@ int smu_cmn_get_enabled_mask(struct smu_context *smu,
 			     uint32_t *feature_mask,
 			     uint32_t num);
 
+int smu_cmn_feature_update_enable_state(struct smu_context *smu,
+					uint64_t feature_mask,
+					bool enabled);
+
 int smu_cmn_feature_set_enabled(struct smu_context *smu,
 				enum smu_feature_mask mask,
 				bool enable);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
index 38c10177ed21..c5adbe46ba0d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
@@ -42,6 +42,7 @@
 #define smu_check_fw_version(smu)					smu_ppt_funcs(check_fw_version, 0, smu)
 #define smu_write_pptable(smu)						smu_ppt_funcs(write_pptable, 0, smu)
 #define smu_set_min_dcef_deep_sleep(smu, clk)				smu_ppt_funcs(set_min_dcef_deep_sleep, 0, smu, clk)
+#define smu_set_active_display_count(smu, count)			smu_ppt_funcs(set_active_display_count, 0, smu, count)
 #define smu_set_driver_table_location(smu)				smu_ppt_funcs(set_driver_table_location, 0, smu)
 #define smu_set_tool_table_location(smu)				smu_ppt_funcs(set_tool_table_location, 0, smu)
 #define smu_notify_memory_pool_location(smu)				smu_ppt_funcs(notify_memory_pool_location, 0, smu)
@@ -83,7 +84,6 @@
 #define smu_asic_set_performance_level(smu, level)			smu_ppt_funcs(set_performance_level, -EINVAL, smu, level)
 #define smu_dump_pptable(smu)						smu_ppt_funcs(dump_pptable, 0, smu)
 #define smu_update_pcie_parameters(smu, pcie_gen_cap, pcie_width_cap)	smu_ppt_funcs(update_pcie_parameters, 0, smu, pcie_gen_cap, pcie_width_cap)
-#define smu_disable_umc_cdr_12gbps_workaround(smu)			smu_ppt_funcs(disable_umc_cdr_12gbps_workaround, 0, smu)
 #define smu_set_power_source(smu, power_src)				smu_ppt_funcs(set_power_source, 0, smu, power_src)
 #define smu_i2c_init(smu, control)					smu_ppt_funcs(i2c_init, 0, smu, control)
 #define smu_i2c_fini(smu, control)					smu_ppt_funcs(i2c_fini, 0, smu, control)
@@ -95,6 +95,7 @@
 #define smu_gfx_ulv_control(smu, enablement)				smu_ppt_funcs(gfx_ulv_control, 0, smu, enablement)
 #define smu_deep_sleep_control(smu, enablement)				smu_ppt_funcs(deep_sleep_control, 0, smu, enablement)
 #define smu_get_fan_parameters(smu)					smu_ppt_funcs(get_fan_parameters, 0, smu)
+#define smu_post_init(smu)						smu_ppt_funcs(post_init, 0, smu)
 
 #endif
 #endif