diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index c21adf60a7f2..057e1ecd83ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -59,12 +59,6 @@ static bool check_atom_bios(uint8_t *bios, size_t size)
 		return false;
 	}
 
-	tmp = bios[0x18] | (bios[0x19] << 8);
-	if (bios[tmp + 0x14] != 0x0) {
-		DRM_INFO("Not an x86 BIOS ROM\n");
-		return false;
-	}
-
 	bios_header_start = bios[0x48] | (bios[0x49] << 8);
 	if (!bios_header_start) {
 		DRM_INFO("Can't locate bios header\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index f7fceb63413c..146e05f21d35 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1497,8 +1497,11 @@ static int amdgpu_cs_wait_any_fence(struct amdgpu_device *adev,
 	memset(wait, 0, sizeof(*wait));
 	wait->out.status = (r > 0);
 	wait->out.first_signaled = first;
-	/* set return value 0 to indicate success */
-	r = array[first]->error;
+
+	if (array[first])
+		r = array[first]->error;
+	else
+		r = 0;
 
 err_free_fence_array:
 	for (i = 0; i < fence_count; i++)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index efcacb827de7..cbe5620654e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3188,9 +3188,9 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf,
 	pm_pg_lock = (*pos >> 23) & 1;
 
 	if (*pos & (1ULL << 62)) {
-		se_bank = (*pos >> 24) & 0x3FF;
-		sh_bank = (*pos >> 34) & 0x3FF;
-		instance_bank = (*pos >> 44) & 0x3FF;
+		se_bank = (*pos & GENMASK_ULL(33, 24)) >> 24;
+		sh_bank = (*pos & GENMASK_ULL(43, 34)) >> 34;
+		instance_bank = (*pos & GENMASK_ULL(53, 44)) >> 44;
 
 		if (se_bank == 0x3FF)
 			se_bank = 0xFFFFFFFF;
@@ -3264,9 +3264,9 @@ static ssize_t amdgpu_debugfs_regs_write(struct file *f, const char __user *buf,
 	pm_pg_lock = (*pos >> 23) & 1;
 
 	if (*pos & (1ULL << 62)) {
-		se_bank = (*pos >> 24) & 0x3FF;
-		sh_bank = (*pos >> 34) & 0x3FF;
-		instance_bank = (*pos >> 44) & 0x3FF;
+		se_bank = (*pos & GENMASK_ULL(33, 24)) >> 24;
+		sh_bank = (*pos & GENMASK_ULL(43, 34)) >> 34;
+		instance_bank = (*pos & GENMASK_ULL(53, 44)) >> 44;
 
 		if (se_bank == 0x3FF)
 			se_bank = 0xFFFFFFFF;
@@ -3614,12 +3614,12 @@ static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
 		return -EINVAL;
 
 	/* decode offset */
-	offset = (*pos & 0x7F);
-	se = ((*pos >> 7) & 0xFF);
-	sh = ((*pos >> 15) & 0xFF);
-	cu = ((*pos >> 23) & 0xFF);
-	wave = ((*pos >> 31) & 0xFF);
-	simd = ((*pos >> 37) & 0xFF);
+	offset = (*pos & GENMASK_ULL(6, 0));
+	se = (*pos & GENMASK_ULL(14, 7)) >> 7;
+	sh = (*pos & GENMASK_ULL(22, 15)) >> 15;
+	cu = (*pos & GENMASK_ULL(30, 23)) >> 23;
+	wave = (*pos & GENMASK_ULL(36, 31)) >> 31;
+	simd = (*pos & GENMASK_ULL(44, 37)) >> 37;
 
 	/* switch to the specific se/sh/cu */
 	mutex_lock(&adev->grbm_idx_mutex);
@@ -3664,14 +3664,14 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 		return -EINVAL;
 
 	/* decode offset */
-	offset = (*pos & 0xFFF);       /* in dwords */
-	se = ((*pos >> 12) & 0xFF);
-	sh = ((*pos >> 20) & 0xFF);
-	cu = ((*pos >> 28) & 0xFF);
-	wave = ((*pos >> 36) & 0xFF);
-	simd = ((*pos >> 44) & 0xFF);
-	thread = ((*pos >> 52) & 0xFF);
-	bank = ((*pos >> 60) & 1);
+	offset = *pos & GENMASK_ULL(11, 0);
+	se = (*pos & GENMASK_ULL(19, 12)) >> 12;
+	sh = (*pos & GENMASK_ULL(27, 20)) >> 20;
+	cu = (*pos & GENMASK_ULL(35, 28)) >> 28;
+	wave = (*pos & GENMASK_ULL(43, 36)) >> 36;
+	simd = (*pos & GENMASK_ULL(51, 44)) >> 44;
+	thread = (*pos & GENMASK_ULL(59, 52)) >> 52;
+	bank = (*pos & GENMASK_ULL(61, 60)) >> 60;
 
 	data = kmalloc_array(1024, sizeof(*data), GFP_KERNEL);
 	if (!data)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index fb72edc4c026..951d625bbdd7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -63,6 +63,11 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 			     flags, NULL, resv, 0, &bo);
 	if (r) {
 		if (r != -ERESTARTSYS) {
+			if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) {
+				flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+				goto retry;
+			}
+
 			if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) {
 				initial_domain |= AMDGPU_GEM_DOMAIN_GTT;
 				goto retry;
@@ -556,9 +561,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 
 	if (args->va_address < AMDGPU_VA_RESERVED_SIZE) {
 		dev_err(&dev->pdev->dev,
-			"va_address 0x%lX is in reserved area 0x%X\n",
-			(unsigned long)args->va_address,
-			AMDGPU_VA_RESERVED_SIZE);
+			"va_address 0x%LX is in reserved area 0x%LX\n",
+			args->va_address, AMDGPU_VA_RESERVED_SIZE);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 90af8e82b16a..ae9c106979d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -169,10 +169,14 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
 					int flags)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(gobj);
+	struct dma_buf *buf;
 
 	if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) ||
 	    bo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID)
 		return ERR_PTR(-EPERM);
 
-	return drm_gem_prime_export(dev, gobj, flags);
+	buf = drm_gem_prime_export(dev, gobj, flags);
+	if (!IS_ERR(buf))
+		buf->file->f_mapping = dev->anon_inode->i_mapping;
+	return buf;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index aa914256b4bc..bae77353447b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -94,7 +94,8 @@ struct amdgpu_bo_list_entry;
 #define AMDGPU_MMHUB				1
 
 /* hardcode that limit for now */
-#define AMDGPU_VA_RESERVED_SIZE			(8 << 20)
+#define AMDGPU_VA_RESERVED_SIZE			(8ULL << 20)
+
 /* max vmids dedicated for process */
 #define AMDGPU_VM_MAX_RESERVED_VMID	1
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 7f15bb2c5233..bc32bbde1165 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -207,6 +207,12 @@ static const u32 golden_settings_gc_9_1_rv1[] =
 	SOC15_REG_OFFSET(GC, 0, mmTD_CNTL), 0x01bd9f33, 0x00000800
 };
 
+static const u32 golden_settings_gc_9_x_common[] =
+{
+	SOC15_REG_OFFSET(GC, 0, mmGRBM_CAM_INDEX), 0xffffffff, 0x00000000,
+	SOC15_REG_OFFSET(GC, 0, mmGRBM_CAM_DATA), 0xffffffff, 0x2544c382
+};
+
 #define VEGA10_GB_ADDR_CONFIG_GOLDEN 0x2a114042
 #define RAVEN_GB_ADDR_CONFIG_GOLDEN 0x24000042
 
@@ -242,6 +248,9 @@ static void gfx_v9_0_init_golden_registers(struct amdgpu_device *adev)
 	default:
 		break;
 	}
+
+	amdgpu_program_register_sequence(adev, golden_settings_gc_9_x_common,
+					(const u32)ARRAY_SIZE(golden_settings_gc_9_x_common));
 }
 
 static void gfx_v9_0_scratch_init(struct amdgpu_device *adev)
@@ -988,12 +997,22 @@ static void gfx_v9_0_read_wave_sgprs(struct amdgpu_device *adev, uint32_t simd,
 		start + SQIND_WAVE_SGPRS_OFFSET, size, dst);
 }
 
+static void gfx_v9_0_read_wave_vgprs(struct amdgpu_device *adev, uint32_t simd,
+				     uint32_t wave, uint32_t thread,
+				     uint32_t start, uint32_t size,
+				     uint32_t *dst)
+{
+	wave_read_regs(
+		adev, simd, wave, thread,
+		start + SQIND_WAVE_VGPRS_OFFSET, size, dst);
+}
 
 static const struct amdgpu_gfx_funcs gfx_v9_0_gfx_funcs = {
 	.get_gpu_clock_counter = &gfx_v9_0_get_gpu_clock_counter,
 	.select_se_sh = &gfx_v9_0_select_se_sh,
 	.read_wave_data = &gfx_v9_0_read_wave_data,
 	.read_wave_sgprs = &gfx_v9_0_read_wave_sgprs,
+	.read_wave_vgprs = &gfx_v9_0_read_wave_vgprs,
 };
 
 static void gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 621699331e09..c8f1aebeac7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -392,7 +392,16 @@ static int gmc_v9_0_early_init(void *handle)
 static int gmc_v9_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	unsigned vm_inv_eng[AMDGPU_MAX_VMHUBS] = { 3, 3 };
+	/*
+	 * The latest engine allocation on gfx9 is:
+	 * Engine 0, 1: idle
+	 * Engine 2, 3: firmware
+	 * Engine 4~13: amdgpu ring, subject to change when ring number changes
+	 * Engine 14~15: idle
+	 * Engine 16: kfd tlb invalidation
+	 * Engine 17: Gart flushes
+	 */
+	unsigned vm_inv_eng[AMDGPU_MAX_VMHUBS] = { 4, 4 };
 	unsigned i;
 
 	for(i = 0; i < adev->num_rings; ++i) {
@@ -405,9 +414,9 @@ static int gmc_v9_0_late_init(void *handle)
 			 ring->funcs->vmhub);
 	}
 
-	/* Engine 17 is used for GART flushes */
+	/* Engine 16 is used for KFD and 17 for GART flushes */
 	for(i = 0; i < AMDGPU_MAX_VMHUBS; ++i)
-		BUG_ON(vm_inv_eng[i] > 17);
+		BUG_ON(vm_inv_eng[i] > 16);
 
 	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index a129bc5b1844..c6febbf0bf69 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1486,7 +1486,7 @@ int atomctrl_get_leakage_vddc_base_on_leakage(struct pp_hwmgr *hwmgr,
 				if (vddci_id_buf[i] == virtual_voltage_id) {
 					for (j = 0; j < profile->ucLeakageBinNum; j++) {
 						if (efuse_voltage_id <= leakage_bin[j]) {
-							*vddci = vddci_buf[j * profile->ucElbVDDC_Num + i];
+							*vddci = vddci_buf[j * profile->ucElbVDDCI_Num + i];
 							break;
 						}
 					}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 4f79c21f27ed..f8d838c2c8ee 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -753,6 +753,7 @@ static int vega10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	uint32_t config_telemetry = 0;
 	struct pp_atomfwctrl_voltage_table vol_table;
 	struct cgs_system_info sys_info = {0};
+	uint32_t reg;
 
 	data = kzalloc(sizeof(struct vega10_hwmgr), GFP_KERNEL);
 	if (data == NULL)
@@ -859,6 +860,16 @@ static int vega10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 			advanceFanControlParameters.usFanPWMMinLimit *
 			hwmgr->thermal_controller.fanInfo.ulMaxRPM / 100;
 
+	reg = soc15_get_register_offset(DF_HWID, 0,
+			mmDF_CS_AON0_DramBaseAddress0_BASE_IDX,
+			mmDF_CS_AON0_DramBaseAddress0);
+	data->mem_channels = (cgs_read_register(hwmgr->device, reg) &
+			DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK) >>
+			DF_CS_AON0_DramBaseAddress0__IntLvNumChan__SHIFT;
+	PP_ASSERT_WITH_CODE(data->mem_channels < ARRAY_SIZE(channel_number),
+			"Mem Channel Index Exceeded maximum!",
+			return -EINVAL);
+
 	return result;
 }
 
@@ -1777,7 +1788,7 @@ static int vega10_populate_all_memory_levels(struct pp_hwmgr *hwmgr)
 	struct vega10_single_dpm_table *dpm_table =
 			&(data->dpm_table.mem_table);
 	int result = 0;
-	uint32_t i, j, reg, mem_channels;
+	uint32_t i, j;
 
 	for (i = 0; i < dpm_table->count; i++) {
 		result = vega10_populate_single_memory_level(hwmgr,
@@ -1801,20 +1812,10 @@ static int vega10_populate_all_memory_levels(struct pp_hwmgr *hwmgr)
 		i++;
 	}
 
-	reg = soc15_get_register_offset(DF_HWID, 0,
-			mmDF_CS_AON0_DramBaseAddress0_BASE_IDX,
-			mmDF_CS_AON0_DramBaseAddress0);
-	mem_channels = (cgs_read_register(hwmgr->device, reg) &
-			DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK) >>
-			DF_CS_AON0_DramBaseAddress0__IntLvNumChan__SHIFT;
-	PP_ASSERT_WITH_CODE(mem_channels < ARRAY_SIZE(channel_number),
-			"Mem Channel Index Exceeded maximum!",
-			return -1);
-
-	pp_table->NumMemoryChannels = cpu_to_le16(mem_channels);
+	pp_table->NumMemoryChannels = (uint16_t)(data->mem_channels);
 	pp_table->MemoryChannelWidth =
-			cpu_to_le16(HBM_MEMORY_CHANNEL_WIDTH *
-					channel_number[mem_channels]);
+			(uint16_t)(HBM_MEMORY_CHANNEL_WIDTH *
+					channel_number[data->mem_channels]);
 
 	pp_table->LowestUclkReservedForUlv =
 			(uint8_t)(data->lowest_uclk_reserved_for_ulv);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
index b4b461c3b8ee..8f7358cc3327 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
@@ -389,6 +389,7 @@ struct vega10_hwmgr {
 	uint32_t                       config_telemetry;
 	uint32_t                       smu_version;
 	uint32_t                       acg_loop_state;
+	uint32_t                       mem_channels;
 };
 
 #define VEGA10_DPM2_NEAR_TDP_DEC                      10