Merge tag 'amd-drm-fixes-6.6-2023-09-13' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.6-2023-09-13:

amdgpu:
- GC 9.4.3 fixes
- Fix white screen issues with S/G display on system with >= 64G of ram
- Replay fixes
- SMU 13.0.6 fixes
- AUX backlight fix
- NBIO 4.3 SR-IOV fixes for HDP
- RAS fixes
- DP MST resume fix
- Fix segfault on systems with no vbios
- DPIA fixes

amdkfd:
- CWSR grace period fix
- Unaligned doorbell fix
- CRIU fix for GFX11
- Add missing TLB flush on gfx10 and newer

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230913195009.7714-1-alexander.deucher@amd.com

44 files changed, 385 insertions, 206 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index dc2d53081e80..a79d53bdbe13 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1293,7 +1293,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
 int amdgpu_device_pci_reset(struct amdgpu_device *adev);
 bool amdgpu_device_need_post(struct amdgpu_device *adev);
-bool amdgpu_sg_display_supported(struct amdgpu_device *adev);
 bool amdgpu_device_pcie_dynamic_switching_supported(void);
 bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev);
 bool amdgpu_device_aspm_support_quirk(void);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index cdf6087706aa..25d5fda5b243 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -478,7 +478,7 @@ void amdgpu_amdkfd_get_cu_info(struct amdgpu_device *adev, struct kfd_cu_info *c
 	cu_info->cu_active_number = acu_info.number;
 	cu_info->cu_ao_mask = acu_info.ao_cu_mask;
 	memcpy(&cu_info->cu_bitmap[0], &acu_info.bitmap[0],
-	       sizeof(acu_info.bitmap));
+	       sizeof(cu_info->cu_bitmap));
 	cu_info->num_shader_engines = adev->gfx.config.max_shader_engines;
 	cu_info->num_shader_arrays_per_engine = adev->gfx.config.max_sh_per_se;
 	cu_info->num_cu_per_sh = adev->gfx.config.max_cu_per_sh;
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 f1f2c24de081..69810b3f1c63 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -980,8 +980,7 @@ void kgd_gfx_v10_build_grace_period_packet_info(struct amdgpu_device *adev,
 						uint32_t wait_times,
 						uint32_t grace_period,
 						uint32_t *reg_offset,
-						uint32_t *reg_data,
-						uint32_t inst)
+						uint32_t *reg_data)
 {
 	*reg_data = wait_times;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h
index ecaead24e8c9..67bcaa3d4226 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h
@@ -55,5 +55,4 @@ void kgd_gfx_v10_build_grace_period_packet_info(struct amdgpu_device *adev,
 					       uint32_t wait_times,
 					       uint32_t grace_period,
 					       uint32_t *reg_offset,
-					       uint32_t *reg_data,
-					       uint32_t inst);
+					       uint32_t *reg_data);
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 fa5ee96f8845..3c45a188b701 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -1103,8 +1103,7 @@ void kgd_gfx_v9_build_grace_period_packet_info(struct amdgpu_device *adev,
 		uint32_t wait_times,
 		uint32_t grace_period,
 		uint32_t *reg_offset,
-		uint32_t *reg_data,
-		uint32_t inst)
+		uint32_t *reg_data)
 {
 	*reg_data = wait_times;
 
@@ -1120,8 +1119,7 @@ void kgd_gfx_v9_build_grace_period_packet_info(struct amdgpu_device *adev,
 			SCH_WAVE,
 			grace_period);
 
-	*reg_offset = SOC15_REG_OFFSET(GC, GET_INST(GC, inst),
-			mmCP_IQ_WAIT_TIME2);
+	*reg_offset = SOC15_REG_OFFSET(GC, 0, mmCP_IQ_WAIT_TIME2);
 }
 
 void kgd_gfx_v9_program_trap_handler_settings(struct amdgpu_device *adev,
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 936e501908ce..ce424615f59b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -100,5 +100,4 @@ void kgd_gfx_v9_build_grace_period_packet_info(struct amdgpu_device *adev,
 					       uint32_t wait_times,
 					       uint32_t grace_period,
 					       uint32_t *reg_offset,
-					       uint32_t *reg_data,
-					       uint32_t inst);
+					       uint32_t *reg_data);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3f001a50b34a..30c4f5cca02c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1245,32 +1245,6 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 }
 
 /*
- * On APUs with >= 64GB white flickering has been observed w/ SG enabled.
- * Disable S/G on such systems until we have a proper fix.
- * https://gitlab.freedesktop.org/drm/amd/-/issues/2354
- * https://gitlab.freedesktop.org/drm/amd/-/issues/2735
- */
-bool amdgpu_sg_display_supported(struct amdgpu_device *adev)
-{
-	switch (amdgpu_sg_display) {
-	case -1:
-		break;
-	case 0:
-		return false;
-	case 1:
-		return true;
-	default:
-		return false;
-	}
-	if ((totalram_pages() << (PAGE_SHIFT - 10)) +
-	    (adev->gmc.real_vram_size / 1024) >= 64000000) {
-		DRM_WARN("Disabling S/G due to >=64GB RAM\n");
-		return false;
-	}
-	return true;
-}
-
-/*
  * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic
  * speed switching. Until we have confirmation from Intel that a specific host
  * supports it, it's safer that we keep it disabled for all.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 395c1768b9fc..0ca95c4d4bfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -43,6 +43,7 @@
 #define AMDGPU_GFX_LBPW_DISABLED_MODE		0x00000008L
 
 #define AMDGPU_MAX_GC_INSTANCES		8
+#define KGD_MAX_QUEUES			128
 
 #define AMDGPU_MAX_GFX_QUEUES KGD_MAX_QUEUES
 #define AMDGPU_MAX_COMPUTE_QUEUES KGD_MAX_QUEUES
@@ -257,7 +258,7 @@ struct amdgpu_cu_info {
 	uint32_t number;
 	uint32_t ao_cu_mask;
 	uint32_t ao_cu_bitmap[4][4];
-	uint32_t bitmap[4][4];
+	uint32_t bitmap[AMDGPU_MAX_GC_INSTANCES][4][4];
 };
 
 struct amdgpu_gfx_ras {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 99f4df133ed3..d30dc0b718c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -839,7 +839,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		memcpy(&dev_info->cu_ao_bitmap[0], &adev->gfx.cu_info.ao_cu_bitmap[0],
 		       sizeof(adev->gfx.cu_info.ao_cu_bitmap));
 		memcpy(&dev_info->cu_bitmap[0], &adev->gfx.cu_info.bitmap[0],
-		       sizeof(adev->gfx.cu_info.bitmap));
+		       sizeof(dev_info->cu_bitmap));
 		dev_info->vram_type = adev->gmc.vram_type;
 		dev_info->vram_bit_width = adev->gmc.vram_width;
 		dev_info->vce_harvest_config = adev->vce.harvest_config;
@@ -940,12 +940,17 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			struct atom_context *atom_context;
 
 			atom_context = adev->mode_info.atom_context;
-			memcpy(vbios_info.name, atom_context->name, sizeof(atom_context->name));
-			memcpy(vbios_info.vbios_pn, atom_context->vbios_pn, sizeof(atom_context->vbios_pn));
-			vbios_info.version = atom_context->version;
-			memcpy(vbios_info.vbios_ver_str, atom_context->vbios_ver_str,
-						sizeof(atom_context->vbios_ver_str));
-			memcpy(vbios_info.date, atom_context->date, sizeof(atom_context->date));
+			if (atom_context) {
+				memcpy(vbios_info.name, atom_context->name,
+				       sizeof(atom_context->name));
+				memcpy(vbios_info.vbios_pn, atom_context->vbios_pn,
+				       sizeof(atom_context->vbios_pn));
+				vbios_info.version = atom_context->version;
+				memcpy(vbios_info.vbios_ver_str, atom_context->vbios_ver_str,
+				       sizeof(atom_context->vbios_ver_str));
+				memcpy(vbios_info.date, atom_context->date,
+				       sizeof(atom_context->date));
+			}
 
 			return copy_to_user(out, &vbios_info,
 						min((size_t)size, sizeof(vbios_info))) ? -EFAULT : 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 3c4600e15b86..937c54fc7174 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1052,7 +1052,8 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 	info->ce_count = obj->err_data.ce_count;
 
 	if (err_data.ce_count) {
-		if (adev->smuio.funcs &&
+		if (!adev->aid_mask &&
+		    adev->smuio.funcs &&
 		    adev->smuio.funcs->get_socket_id &&
 		    adev->smuio.funcs->get_die_id) {
 			dev_info(adev->dev, "socket: %d, die: %d "
@@ -1072,7 +1073,8 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 		}
 	}
 	if (err_data.ue_count) {
-		if (adev->smuio.funcs &&
+		if (!adev->aid_mask &&
+		    adev->smuio.funcs &&
 		    adev->smuio.funcs->get_socket_id &&
 		    adev->smuio.funcs->get_die_id) {
 			dev_info(adev->dev, "socket: %d, die: %d "
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 0aee9c8288a2..9032d7a24d7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -9449,7 +9449,7 @@ static int gfx_v10_0_get_cu_info(struct amdgpu_device *adev,
 				gfx_v10_0_set_user_wgp_inactive_bitmap_per_sh(
 					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v10_0_get_cu_active_bitmap_per_sh(adev);
-			cu_info->bitmap[i][j] = bitmap;
+			cu_info->bitmap[0][i][j] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
 				if (bitmap & mask) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 5c3db694afa8..762d7a19f1be 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -6368,7 +6368,7 @@ static int gfx_v11_0_get_cu_info(struct amdgpu_device *adev,
 			 *    SE6: {SH0,SH1} --> {bitmap[2][2], bitmap[2][3]}
 			 *    SE7: {SH0,SH1} --> {bitmap[3][2], bitmap[3][3]}
 			 */
-			cu_info->bitmap[i % 4][j + (i / 4) * 2] = bitmap;
+			cu_info->bitmap[0][i % 4][j + (i / 4) * 2] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
 				if (bitmap & mask)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index da6caff78c22..34f9211b2679 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -3577,7 +3577,7 @@ static void gfx_v6_0_get_cu_info(struct amdgpu_device *adev)
 				gfx_v6_0_set_user_cu_inactive_bitmap(
 					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v6_0_get_cu_enabled(adev);
-			cu_info->bitmap[i][j] = bitmap;
+			cu_info->bitmap[0][i][j] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
 				if (bitmap & mask) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 90b034b173c1..c2faf6b4c2fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -5119,7 +5119,7 @@ static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev)
 				gfx_v7_0_set_user_cu_inactive_bitmap(
 					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v7_0_get_cu_active_bitmap(adev);
-			cu_info->bitmap[i][j] = bitmap;
+			cu_info->bitmap[0][i][j] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
 				if (bitmap & mask) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 51c1745c8369..885ebd703260 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -7121,7 +7121,7 @@ static void gfx_v8_0_get_cu_info(struct amdgpu_device *adev)
 				gfx_v8_0_set_user_cu_inactive_bitmap(
 					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v8_0_get_cu_active_bitmap(adev);
-			cu_info->bitmap[i][j] = bitmap;
+			cu_info->bitmap[0][i][j] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k ++) {
 				if (bitmap & mask) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 458faf657042..fd61574a737c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1499,7 +1499,7 @@ static void gfx_v9_0_init_always_on_cu_mask(struct amdgpu_device *adev)
 			amdgpu_gfx_select_se_sh(adev, i, j, 0xffffffff, 0);
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k ++) {
-				if (cu_info->bitmap[i][j] & mask) {
+				if (cu_info->bitmap[0][i][j] & mask) {
 					if (counter == pg_always_on_cu_num)
 						WREG32_SOC15(GC, 0, mmRLC_PG_ALWAYS_ON_CU_MASK, cu_bitmap);
 					if (counter < always_on_cu_num)
@@ -7233,7 +7233,7 @@ static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
 			 *    SE6,SH0 --> bitmap[2][1]
 			 *    SE7,SH0 --> bitmap[3][1]
 			 */
-			cu_info->bitmap[i % 4][j + i / 4] = bitmap;
+			cu_info->bitmap[0][i % 4][j + i / 4] = bitmap;
 
 			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k ++) {
 				if (bitmap & mask) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 0a26a00074a6..18ce5fe45f6f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -4259,7 +4259,7 @@ static void gfx_v9_4_3_set_gds_init(struct amdgpu_device *adev)
 }
 
 static void gfx_v9_4_3_set_user_cu_inactive_bitmap(struct amdgpu_device *adev,
-						 u32 bitmap)
+						 u32 bitmap, int xcc_id)
 {
 	u32 data;
 
@@ -4269,15 +4269,15 @@ static void gfx_v9_4_3_set_user_cu_inactive_bitmap(struct amdgpu_device *adev,
 	data = bitmap << GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT;
 	data &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK;
 
-	WREG32_SOC15(GC, GET_INST(GC, 0), regGC_USER_SHADER_ARRAY_CONFIG, data);
+	WREG32_SOC15(GC, GET_INST(GC, xcc_id), regGC_USER_SHADER_ARRAY_CONFIG, data);
 }
 
-static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev)
+static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev, int xcc_id)
 {
 	u32 data, mask;
 
-	data = RREG32_SOC15(GC, GET_INST(GC, 0), regCC_GC_SHADER_ARRAY_CONFIG);
-	data |= RREG32_SOC15(GC, GET_INST(GC, 0), regGC_USER_SHADER_ARRAY_CONFIG);
+	data = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCC_GC_SHADER_ARRAY_CONFIG);
+	data |= RREG32_SOC15(GC, GET_INST(GC, xcc_id), regGC_USER_SHADER_ARRAY_CONFIG);
 
 	data &= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK;
 	data >>= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT;
@@ -4290,7 +4290,7 @@ static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev)
 static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev,
 				 struct amdgpu_cu_info *cu_info)
 {
-	int i, j, k, counter, active_cu_number = 0;
+	int i, j, k, counter, xcc_id, active_cu_number = 0;
 	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0;
 	unsigned disable_masks[4 * 4];
 
@@ -4309,46 +4309,38 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev,
 				    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++) {
-			mask = 1;
-			ao_bitmap = 0;
-			counter = 0;
-			gfx_v9_4_3_xcc_select_se_sh(adev, i, j, 0xffffffff, 0);
-			gfx_v9_4_3_set_user_cu_inactive_bitmap(
-				adev, disable_masks[i * adev->gfx.config.max_sh_per_se + j]);
-			bitmap = gfx_v9_4_3_get_cu_active_bitmap(adev);
-
-			/*
-			 * The bitmap(and ao_cu_bitmap) in cu_info structure is
-			 * 4x4 size array, and it's usually suitable for Vega
-			 * ASICs which has 4*2 SE/SH layout.
-			 * But for Arcturus, SE/SH layout is changed to 8*1.
-			 * To mostly reduce the impact, we make it compatible
-			 * with current bitmap array as below:
-			 *    SE4,SH0 --> bitmap[0][1]
-			 *    SE5,SH0 --> bitmap[1][1]
-			 *    SE6,SH0 --> bitmap[2][1]
-			 *    SE7,SH0 --> bitmap[3][1]
-			 */
-			cu_info->bitmap[i % 4][j + i / 4] = bitmap;
-
-			for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
-				if (bitmap & mask) {
-					if (counter < adev->gfx.config.max_cu_per_sh)
-						ao_bitmap |= mask;
-					counter++;
+	for (xcc_id = 0; xcc_id < NUM_XCC(adev->gfx.xcc_mask); xcc_id++) {
+		for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
+			for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+				mask = 1;
+				ao_bitmap = 0;
+				counter = 0;
+				gfx_v9_4_3_xcc_select_se_sh(adev, i, j, 0xffffffff, xcc_id);
+				gfx_v9_4_3_set_user_cu_inactive_bitmap(
+					adev,
+					disable_masks[i * adev->gfx.config.max_sh_per_se + j],
+					xcc_id);
+				bitmap = gfx_v9_4_3_get_cu_active_bitmap(adev, xcc_id);
+
+				cu_info->bitmap[xcc_id][i][j] = bitmap;
+
+				for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) {
+					if (bitmap & mask) {
+						if (counter < adev->gfx.config.max_cu_per_sh)
+							ao_bitmap |= mask;
+						counter++;
+					}
+					mask <<= 1;
 				}
-				mask <<= 1;
+				active_cu_number += counter;
+				if (i < 2 && j < 2)
+					ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8));
+				cu_info->ao_cu_bitmap[i][j] = ao_bitmap;
 			}
-			active_cu_number += counter;
-			if (i < 2 && j < 2)
-				ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8));
-			cu_info->ao_cu_bitmap[i % 4][j + i / 4] = ao_bitmap;
 		}
+		gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff,
+					    xcc_id);
 	}
-	gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff,
-				    0);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	cu_info->number = active_cu_number;
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c
index d5ed9e0e1a5f..e5b5b0f4940f 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c
@@ -345,6 +345,9 @@ static void nbio_v4_3_init_registers(struct amdgpu_device *adev)
 		data &= ~RCC_DEV0_EPF2_STRAP2__STRAP_NO_SOFT_RESET_DEV0_F2_MASK;
 		WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2, data);
 	}
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+			regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
 }
 
 static u32 nbio_v4_3_get_rom_offset(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 40d23738ee4e..8b2ff2b281b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -766,7 +766,7 @@ static int soc21_common_hw_init(void *handle)
 	 * for the purpose of expose those registers
 	 * to process space
 	 */
-	if (adev->nbio.funcs->remap_hdp_registers)
+	if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev))
 		adev->nbio.funcs->remap_hdp_registers(adev);
 	/* enable the doorbell aperture */
 	adev->nbio.funcs->enable_doorbell_aperture(adev, true);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 86fb7ac7982a..f76b7aee5c0a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -2087,7 +2087,8 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image,
 
 	amdgpu_amdkfd_get_cu_info(kdev->adev, &cu_info);
 	cu->num_simd_per_cu = cu_info.simd_per_cu;
-	cu->num_simd_cores = cu_info.simd_per_cu * cu_info.cu_active_number;
+	cu->num_simd_cores = cu_info.simd_per_cu *
+			(cu_info.cu_active_number / kdev->kfd->num_nodes);
 	cu->max_waves_simd = cu_info.max_waves_per_simd;
 
 	cu->wave_front_size = cu_info.wave_front_size;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.h b/drivers/gpu/drm/amd/amdkfd/kfd_crat.h
index 387a8ef49385..74c2d7a0d628 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.h
@@ -79,6 +79,10 @@ struct crat_header {
 #define CRAT_SUBTYPE_IOLINK_AFFINITY		5
 #define CRAT_SUBTYPE_MAX			6
 
+/*
+ * Do not change the value of CRAT_SIBLINGMAP_SIZE from 32
+ * as it breaks the ABI.
+ */
 #define CRAT_SIBLINGMAP_SIZE	32
 
 /*
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 b166f30f083e..8a6cb41444a4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1677,8 +1677,7 @@ static int start_cpsch(struct device_queue_manager *dqm)
 			dqm->dev->kfd2kgd->build_grace_period_packet_info(
 					dqm->dev->adev,	dqm->wait_times,
 					grace_period, &reg_offset,
-					&dqm->wait_times,
-					ffs(dqm->dev->xcc_mask) - 1);
+					&dqm->wait_times);
 	}
 
 	dqm_unlock(dqm);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index c2e0b79dcc6d..7b38537c7c99 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -162,6 +162,7 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 		return NULL;
 
 	*doorbell_off = amdgpu_doorbell_index_on_bar(kfd->adev, kfd->doorbells, inx);
+	inx *= 2;
 
 	pr_debug("Get kernel queue doorbell\n"
 			"     doorbell offset   == 0x%08X\n"
@@ -176,6 +177,7 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr)
 	unsigned int inx;
 
 	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr);
+	inx /= 2;
 
 	mutex_lock(&kfd->doorbell_mutex);
 	__clear_bit(inx, kfd->doorbell_bitmap);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index d01bb57733b3..447829c22295 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -97,18 +97,22 @@ void free_mqd_hiq_sdma(struct mqd_manager *mm, void *mqd,
 
 void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 		const uint32_t *cu_mask, uint32_t cu_mask_count,
-		uint32_t *se_mask)
+		uint32_t *se_mask, uint32_t inst)
 {
 	struct kfd_cu_info cu_info;
 	uint32_t cu_per_sh[KFD_MAX_NUM_SE][KFD_MAX_NUM_SH_PER_SE] = {0};
 	bool wgp_mode_req = KFD_GC_VERSION(mm->dev) >= IP_VERSION(10, 0, 0);
 	uint32_t en_mask = wgp_mode_req ? 0x3 : 0x1;
-	int i, se, sh, cu, cu_bitmap_sh_mul, inc = wgp_mode_req ? 2 : 1;
+	int i, se, sh, cu, cu_bitmap_sh_mul, cu_inc = wgp_mode_req ? 2 : 1;
+	uint32_t cu_active_per_node;
+	int inc = cu_inc * NUM_XCC(mm->dev->xcc_mask);
+	int xcc_inst = inst + ffs(mm->dev->xcc_mask) - 1;
 
 	amdgpu_amdkfd_get_cu_info(mm->dev->adev, &cu_info);
 
-	if (cu_mask_count > cu_info.cu_active_number)
-		cu_mask_count = cu_info.cu_active_number;
+	cu_active_per_node = cu_info.cu_active_number / mm->dev->kfd->num_nodes;
+	if (cu_mask_count > cu_active_per_node)
+		cu_mask_count = cu_active_per_node;
 
 	/* Exceeding these bounds corrupts the stack and indicates a coding error.
 	 * Returning with no CU's enabled will hang the queue, which should be
@@ -141,7 +145,8 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 	for (se = 0; se < cu_info.num_shader_engines; se++)
 		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++)
 			cu_per_sh[se][sh] = hweight32(
-				cu_info.cu_bitmap[se % 4][sh + (se / 4) * cu_bitmap_sh_mul]);
+				cu_info.cu_bitmap[xcc_inst][se % 4][sh + (se / 4) *
+				cu_bitmap_sh_mul]);
 
 	/* Symmetrically map cu_mask to all SEs & SHs:
 	 * se_mask programs up to 2 SH in the upper and lower 16 bits.
@@ -164,20 +169,33 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 	 * cu_mask[0] bit8 -> se_mask[0] bit1 (SE0,SH0,CU1)
 	 * ...
 	 *
+	 * For GFX 9.4.3, the following code only looks at a
+	 * subset of the cu_mask corresponding to the inst parameter.
+	 * If we have n XCCs under one GPU node
+	 * cu_mask[0] bit0 -> XCC0 se_mask[0] bit0 (XCC0,SE0,SH0,CU0)
+	 * cu_mask[0] bit1 -> XCC1 se_mask[0] bit0 (XCC1,SE0,SH0,CU0)
+	 * ..
+	 * cu_mask[0] bitn -> XCCn se_mask[0] bit0 (XCCn,SE0,SH0,CU0)
+	 * cu_mask[0] bit n+1 -> XCC0 se_mask[1] bit0 (XCC0,SE1,SH0,CU0)
+	 *
+	 * For example, if there are 6 XCCs under 1 KFD node, this code
+	 * running for each inst, will look at the bits as:
+	 * inst, inst + 6, inst + 12...
+	 *
 	 * First ensure all CUs are disabled, then enable user specified CUs.
 	 */
 	for (i = 0; i < cu_info.num_shader_engines; i++)
 		se_mask[i] = 0;
 
-	i = 0;
-	for (cu = 0; cu < 16; cu += inc) {
+	i = inst;
+	for (cu = 0; cu < 16; cu += cu_inc) {
 		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++) {
 			for (se = 0; se < cu_info.num_shader_engines; se++) {
 				if (cu_per_sh[se][sh] > cu) {
 					if (cu_mask[i / 32] & (en_mask << (i % 32)))
 						se_mask[se] |= en_mask << (cu + sh * 16);
 					i += inc;
-					if (i == cu_mask_count)
+					if (i >= cu_mask_count)
 						return;
 				}
 			}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index 23158db7da03..57bf5e513f4d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -138,7 +138,7 @@ void free_mqd_hiq_sdma(struct mqd_manager *mm, void *mqd,
 
 void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 		const uint32_t *cu_mask, uint32_t cu_mask_count,
-		uint32_t *se_mask);
+		uint32_t *se_mask, uint32_t inst);
 
 int kfd_hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd,
 		uint32_t pipe_id, uint32_t queue_id,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index ee1d32d957f2..1a4a69943c71 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -52,7 +52,7 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 		return;
 
 	mqd_symmetrically_map_cu_mask(mm,
-		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask, 0);
 
 	m = get_mqd(mqd);
 	m->compute_static_thread_mgmt_se0 = se_mask[0];
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 83699392c808..8b7fed913526 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -52,7 +52,7 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 		return;
 
 	mqd_symmetrically_map_cu_mask(mm,
-		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask, 0);
 
 	m = get_mqd(mqd);
 	m->compute_static_thread_mgmt_se0 = se_mask[0];
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 0bbf0edbabd4..15277f1d5cf0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -71,7 +71,7 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 	}
 
 	mqd_symmetrically_map_cu_mask(mm,
-		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask, 0);
 
 	m->compute_static_thread_mgmt_se0 = se_mask[0];
 	m->compute_static_thread_mgmt_se1 = se_mask[1];
@@ -321,6 +321,43 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 	return 0;
 }
 
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst)
+{
+	struct v11_compute_mqd *m;
+
+	m = get_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct v11_compute_mqd));
+}
+
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			struct queue_properties *qp,
+			const void *mqd_src,
+			const void *ctl_stack_src, const u32 ctl_stack_size)
+{
+	uint64_t addr;
+	struct v11_compute_mqd *m;
+
+	m = (struct v11_compute_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	m->cp_hqd_pq_doorbell_control =
+		qp->doorbell_off <<
+			CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
+	pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+			m->cp_hqd_pq_doorbell_control);
+
+	qp->is_active = 0;
+}
+
+
 static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -458,6 +495,8 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
 		mqd->mqd_size = sizeof(struct v11_compute_mqd);
 		mqd->get_wave_state = get_wave_state;
 		mqd->mqd_stride = kfd_mqd_stride;
+		mqd->checkpoint_mqd = checkpoint_mqd;
+		mqd->restore_mqd = restore_mqd;
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
 #endif
@@ -502,6 +541,8 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
 		mqd->update_mqd = update_mqd_sdma;
 		mqd->destroy_mqd = kfd_destroy_mqd_sdma;
 		mqd->is_occupied = kfd_is_occupied_sdma;
+		mqd->checkpoint_mqd = checkpoint_mqd;
+		mqd->restore_mqd = restore_mqd;
 		mqd->mqd_size = sizeof(struct v11_sdma_mqd);
 		mqd->mqd_stride = kfd_mqd_stride;
 #if defined(CONFIG_DEBUG_FS)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index e23d32f35607..42d881809dc7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -60,7 +60,7 @@ static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd)
 }
 
 static void update_cu_mask(struct mqd_manager *mm, void *mqd,
-			struct mqd_update_info *minfo)
+			struct mqd_update_info *minfo, uint32_t inst)
 {
 	struct v9_mqd *m;
 	uint32_t se_mask[KFD_MAX_NUM_SE] = {0};
@@ -69,27 +69,36 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 		return;
 
 	mqd_symmetrically_map_cu_mask(mm,
-		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask, inst);
 
 	m = get_mqd(mqd);
+
 	m->compute_static_thread_mgmt_se0 = se_mask[0];
 	m->compute_static_thread_mgmt_se1 = se_mask[1];
 	m->compute_static_thread_mgmt_se2 = se_mask[2];
 	m->compute_static_thread_mgmt_se3 = se_mask[3];
-	m->compute_static_thread_mgmt_se4 = se_mask[4];
-	m->compute_static_thread_mgmt_se5 = se_mask[5];
-	m->compute_static_thread_mgmt_se6 = se_mask[6];
-	m->compute_static_thread_mgmt_se7 = se_mask[7];
-
-	pr_debug("update cu mask to %#x %#x %#x %#x %#x %#x %#x %#x\n",
-		m->compute_static_thread_mgmt_se0,
-		m->compute_static_thread_mgmt_se1,
-		m->compute_static_thread_mgmt_se2,
-		m->compute_static_thread_mgmt_se3,
-		m->compute_static_thread_mgmt_se4,
-		m->compute_static_thread_mgmt_se5,
-		m->compute_static_thread_mgmt_se6,
-		m->compute_static_thread_mgmt_se7);
+	if (KFD_GC_VERSION(mm->dev) != IP_VERSION(9, 4, 3)) {
+		m->compute_static_thread_mgmt_se4 = se_mask[4];
+		m->compute_static_thread_mgmt_se5 = se_mask[5];
+		m->compute_static_thread_mgmt_se6 = se_mask[6];
+		m->compute_static_thread_mgmt_se7 = se_mask[7];
+
+		pr_debug("update cu mask to %#x %#x %#x %#x %#x %#x %#x %#x\n",
+			m->compute_static_thread_mgmt_se0,
+			m->compute_static_thread_mgmt_se1,
+			m->compute_static_thread_mgmt_se2,
+			m->compute_static_thread_mgmt_se3,
+			m->compute_static_thread_mgmt_se4,
+			m->compute_static_thread_mgmt_se5,
+			m->compute_static_thread_mgmt_se6,
+			m->compute_static_thread_mgmt_se7);
+	} else {
+		pr_debug("inst: %u, update cu mask to %#x %#x %#x %#x\n",
+			inst, m->compute_static_thread_mgmt_se0,
+			m->compute_static_thread_mgmt_se1,
+			m->compute_static_thread_mgmt_se2,
+			m->compute_static_thread_mgmt_se3);
+	}
 }
 
 static void set_priority(struct v9_mqd *m, struct queue_properties *q)
@@ -290,7 +299,8 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 	if (mm->dev->kfd->cwsr_enabled && q->ctx_save_restore_area_address)
 		m->cp_hqd_ctx_save_control = 0;
 
-	update_cu_mask(mm, mqd, minfo);
+	if (KFD_GC_VERSION(mm->dev) != IP_VERSION(9, 4, 3))
+		update_cu_mask(mm, mqd, minfo, 0);
 	set_priority(m, q);
 
 	q->is_active = QUEUE_IS_ACTIVE(*q);
@@ -676,6 +686,8 @@ static void update_mqd_v9_4_3(struct mqd_manager *mm, void *mqd,
 		m = get_mqd(mqd + size * xcc);
 		update_mqd(mm, m, q, minfo);
 
+		update_cu_mask(mm, mqd, minfo, xcc);
+
 		if (q->format == KFD_QUEUE_FORMAT_AQL) {
 			switch (xcc) {
 			case 0:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index 657c37822980..3e1a574d4ea6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -55,7 +55,7 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 		return;
 
 	mqd_symmetrically_map_cu_mask(mm,
-		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
+		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask, 0);
 
 	m = get_mqd(mqd);
 	m->compute_static_thread_mgmt_se0 = se_mask[0];
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
index 8ce6f5200905..1a03173e2313 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
@@ -299,8 +299,7 @@ static int pm_set_grace_period_v9(struct packet_manager *pm,
 			pm->dqm->wait_times,
 			grace_period,
 			&reg_offset,
-			&reg_data,
-			0);
+			&reg_data);
 
 	if (grace_period == USE_DEFAULT_GRACE_PERIOD)
 		reg_data = pm->dqm->wait_times;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 3d9ce44d88da..fa24e1852493 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1466,8 +1466,7 @@ void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type);
 
 static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
 {
-	return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 3) ||
-	       KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) ||
+	return KFD_GC_VERSION(dev) > IP_VERSION(9, 4, 2) ||
 	       (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) ||
 	       KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index ff98fded9534..c8c75ff7cea8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -450,8 +450,7 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 	sysfs_show_32bit_prop(buffer, offs, "cpu_cores_count",
 			      dev->node_props.cpu_cores_count);
 	sysfs_show_32bit_prop(buffer, offs, "simd_count",
-			      dev->gpu ? (dev->node_props.simd_count *
-					  NUM_XCC(dev->gpu->xcc_mask)) : 0);
+			      dev->gpu ? dev->node_props.simd_count : 0);
 	sysfs_show_32bit_prop(buffer, offs, "mem_banks_count",
 			      dev->node_props.mem_banks_count);
 	sysfs_show_32bit_prop(buffer, offs, "caches_count",
@@ -1597,14 +1596,17 @@ static int fill_in_l1_pcache(struct kfd_cache_properties **props_ext,
 static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
 				struct kfd_gpu_cache_info *pcache_info,
 				struct kfd_cu_info *cu_info,
-				int cache_type, unsigned int cu_processor_id)
+				int cache_type, unsigned int cu_processor_id,
+				struct kfd_node *knode)
 {
 	unsigned int cu_sibling_map_mask;
 	int first_active_cu;
-	int i, j, k;
+	int i, j, k, xcc, start, end;
 	struct kfd_cache_properties *pcache = NULL;
 
-	cu_sibling_map_mask = cu_info->cu_bitmap[0][0];
+	start = ffs(knode->xcc_mask) - 1;
+	end = start + NUM_XCC(knode->xcc_mask);
+	cu_sibling_map_mask = cu_info->cu_bitmap[start][0][0];
 	cu_sibling_map_mask &=
 		((1 << pcache_info[cache_type].num_cu_shared) - 1);
 	first_active_cu = ffs(cu_sibling_map_mask);
@@ -1639,16 +1641,18 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
 		cu_sibling_map_mask = cu_sibling_map_mask >> (first_active_cu - 1);
 		k = 0;
 
-		for (i = 0; i < cu_info->num_shader_engines; i++) {
-			for (j = 0; j < cu_info->num_shader_arrays_per_engine; j++) {
-				pcache->sibling_map[k] = (uint8_t)(cu_sibling_map_mask & 0xFF);
-				pcache->sibling_map[k+1] = (uint8_t)((cu_sibling_map_mask >> 8) & 0xFF);
-				pcache->sibling_map[k+2] = (uint8_t)((cu_sibling_map_mask >> 16) & 0xFF);
-				pcache->sibling_map[k+3] = (uint8_t)((cu_sibling_map_mask >> 24) & 0xFF);
-				k += 4;
-
-				cu_sibling_map_mask = cu_info->cu_bitmap[i % 4][j + i / 4];
-				cu_sibling_map_mask &= ((1 << pcache_info[cache_type].num_cu_shared) - 1);
+		for (xcc = start; xcc < end; xcc++) {
+			for (i = 0; i < cu_info->num_shader_engines; i++) {
+				for (j = 0; j < cu_info->num_shader_arrays_per_engine; j++) {
+					pcache->sibling_map[k] = (uint8_t)(cu_sibling_map_mask & 0xFF);
+					pcache->sibling_map[k+1] = (uint8_t)((cu_sibling_map_mask >> 8) & 0xFF);
+					pcache->sibling_map[k+2] = (uint8_t)((cu_sibling_map_mask >> 16) & 0xFF);
+					pcache->sibling_map[k+3] = (uint8_t)((cu_sibling_map_mask >> 24) & 0xFF);
+					k += 4;
+
+					cu_sibling_map_mask = cu_info->cu_bitmap[xcc][i % 4][j + i / 4];
+					cu_sibling_map_mask &= ((1 << pcache_info[cache_type].num_cu_shared) - 1);
+				}
 			}
 		}
 		pcache->sibling_map_size = k;
@@ -1666,7 +1670,7 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
 static void kfd_fill_cache_non_crat_info(struct kfd_topology_device *dev, struct kfd_node *kdev)
 {
 	struct kfd_gpu_cache_info *pcache_info = NULL;
-	int i, j, k;
+	int i, j, k, xcc, start, end;
 	int ct = 0;
 	unsigned int cu_processor_id;
 	int ret;
@@ -1700,37 +1704,42 @@ static void kfd_fill_cache_non_crat_info(struct kfd_topology_device *dev, struct
 	 *			then it will consider only one CU from
 	 *			the shared unit
 	 */
+	start = ffs(kdev->xcc_mask) - 1;
+	end = start + NUM_XCC(kdev->xcc_mask);
+
 	for (ct = 0; ct < num_of_cache_types; ct++) {
 		cu_processor_id = gpu_processor_id;
 		if (pcache_info[ct].cache_level == 1) {
-			for (i = 0; i < pcu_info->num_shader_engines; i++) {
-				for (j = 0; j < pcu_info->num_shader_arrays_per_engine; j++) {
-					for (k = 0; k < pcu_info->num_cu_per_sh; k += pcache_info[ct].num_cu_shared) {
+			for (xcc = start; xcc < end; xcc++) {
+				for (i = 0; i < pcu_info->num_shader_engines; i++) {
+					for (j = 0; j < pcu_info->num_shader_arrays_per_engine; j++) {
+						for (k = 0; k < pcu_info->num_cu_per_sh; k += pcache_info[ct].num_cu_shared) {
 
-						ret = fill_in_l1_pcache(&props_ext, pcache_info, pcu_info,
-										pcu_info->cu_bitmap[i % 4][j + i / 4], ct,
+							ret = fill_in_l1_pcache(&props_ext, pcache_info, pcu_info,
+										pcu_info->cu_bitmap[xcc][i % 4][j + i / 4], ct,
 										cu_processor_id, k);
 
-						if (ret < 0)
-							break;
+							if (ret < 0)
+								break;
 
-						if (!ret) {
-							num_of_entries++;
-							list_add_tail(&props_ext->list, &dev->cache_props);
-						}
+							if (!ret) {
+								num_of_entries++;
+								list_add_tail(&props_ext->list, &dev->cache_props);
+							}
 
-						/* Move to next CU block */
-						num_cu_shared = ((k + pcache_info[ct].num_cu_shared) <=
-							pcu_info->num_cu_per_sh) ?
-							pcache_info[ct].num_cu_shared :
-							(pcu_info->num_cu_per_sh - k);
-						cu_processor_id += num_cu_shared;
+							/* Move to next CU block */
+							num_cu_shared = ((k + pcache_info[ct].num_cu_shared) <=
+								pcu_info->num_cu_per_sh) ?
+								pcache_info[ct].num_cu_shared :
+								(pcu_info->num_cu_per_sh - k);
+							cu_processor_id += num_cu_shared;
+						}
 					}
 				}
 			}
 		} else {
 			ret = fill_in_l2_l3_pcache(&props_ext, pcache_info,
-								pcu_info, ct, cu_processor_id);
+					pcu_info, ct, cu_processor_id, kdev);
 
 			if (ret < 0)
 				break;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
index dea32a9e5506..27386ce9a021 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
@@ -89,7 +89,7 @@ struct kfd_mem_properties {
 	struct attribute	attr;
 };
 
-#define CACHE_SIBLINGMAP_SIZE 64
+#define CACHE_SIBLINGMAP_SIZE 128
 
 struct kfd_cache_properties {
 	struct list_head	list;
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 88ba8b66de1f..c6fd34bab358 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1274,11 +1274,15 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 
 	pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
 
-	page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF;
-	page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12);
-	page_table_end.high_part = (u32)(adev->gmc.gart_end >> 44) & 0xF;
-	page_table_end.low_part = (u32)(adev->gmc.gart_end >> 12);
-	page_table_base.high_part = upper_32_bits(pt_base) & 0xF;
+	page_table_start.high_part = upper_32_bits(adev->gmc.gart_start >>
+						   AMDGPU_GPU_PAGE_SHIFT);
+	page_table_start.low_part = lower_32_bits(adev->gmc.gart_start >>
+						  AMDGPU_GPU_PAGE_SHIFT);
+	page_table_end.high_part = upper_32_bits(adev->gmc.gart_end >>
+						 AMDGPU_GPU_PAGE_SHIFT);
+	page_table_end.low_part = lower_32_bits(adev->gmc.gart_end >>
+						AMDGPU_GPU_PAGE_SHIFT);
+	page_table_base.high_part = upper_32_bits(pt_base);
 	page_table_base.low_part = lower_32_bits(pt_base);
 
 	pa_config->system_aperture.start_addr = (uint64_t)logical_addr_low << 18;
@@ -1640,8 +1644,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		}
 		break;
 	}
-	if (init_data.flags.gpu_vm_support)
-		init_data.flags.gpu_vm_support = amdgpu_sg_display_supported(adev);
+	if (init_data.flags.gpu_vm_support &&
+	    (amdgpu_sg_display == 0))
+		init_data.flags.gpu_vm_support = false;
 
 	if (init_data.flags.gpu_vm_support)
 		adev->mode_info.gpu_vm_support = true;
@@ -2335,14 +2340,62 @@ static int dm_late_init(void *handle)
 	return detect_mst_link_for_all_connectors(adev_to_drm(adev));
 }
 
+static void resume_mst_branch_status(struct drm_dp_mst_topology_mgr *mgr)
+{
+	int ret;
+	u8 guid[16];
+	u64 tmp64;
+
+	mutex_lock(&mgr->lock);
+	if (!mgr->mst_primary)
+		goto out_fail;
+
+	if (drm_dp_read_dpcd_caps(mgr->aux, mgr->dpcd) < 0) {
+		drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n");
+		goto out_fail;
+	}
+
+	ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL,
+				 DP_MST_EN |
+				 DP_UP_REQ_EN |
+				 DP_UPSTREAM_IS_SRC);
+	if (ret < 0) {
+		drm_dbg_kms(mgr->dev, "mst write failed - undocked during suspend?\n");
+		goto out_fail;
+	}
+
+	/* Some hubs forget their guids after they resume */
+	ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16);
+	if (ret != 16) {
+		drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n");
+		goto out_fail;
+	}
+
+	if (memchr_inv(guid, 0, 16) == NULL) {
+		tmp64 = get_jiffies_64();
+		memcpy(&guid[0], &tmp64, sizeof(u64));
+		memcpy(&guid[8], &tmp64, sizeof(u64));
+
+		ret = drm_dp_dpcd_write(mgr->aux, DP_GUID, guid, 16);
+
+		if (ret != 16) {
+			drm_dbg_kms(mgr->dev, "check mstb guid failed - undocked during suspend?\n");
+			goto out_fail;
+		}
+	}
+
+	memcpy(mgr->mst_primary->guid, guid, 16);
+
+out_fail:
+	mutex_unlock(&mgr->lock);
+}
+
 static void s3_handle_mst(struct drm_device *dev, bool suspend)
 {
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
 	struct drm_dp_mst_topology_mgr *mgr;
-	int ret;
-	bool need_hotplug = false;
 
 	drm_connector_list_iter_begin(dev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
@@ -2364,18 +2417,15 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend)
 			if (!dp_is_lttpr_present(aconnector->dc_link))
 				try_to_configure_aux_timeout(aconnector->dc_link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD);
 
-			ret = drm_dp_mst_topology_mgr_resume(mgr, true);
-			if (ret < 0) {
-				dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx,
-					aconnector->dc_link);
-				need_hotplug = true;
-			}
+			/* TODO: move resume_mst_branch_status() into drm mst resume again
+			 * once topology probing work is pulled out from mst resume into mst
+			 * resume 2nd step. mst resume 2nd step should be called after old
+			 * state getting restored (i.e. drm_atomic_helper_resume()).
+			 */
+			resume_mst_branch_status(mgr);
 		}
 	}
 	drm_connector_list_iter_end(&iter);
-
-	if (need_hotplug)
-		drm_kms_helper_hotplug_event(dev);
 }
 
 static int amdgpu_dm_smu_write_watermarks_table(struct amdgpu_device *adev)
@@ -2769,7 +2819,8 @@ static int dm_resume(void *handle)
 	struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state);
 	enum dc_connection_type new_connection_type = dc_connection_none;
 	struct dc_state *dc_state;
-	int i, r, j;
+	int i, r, j, ret;
+	bool need_hotplug = false;
 
 	if (amdgpu_in_reset(adev)) {
 		dc_state = dm->cached_dc_state;
@@ -2867,7 +2918,7 @@ static int dm_resume(void *handle)
 			continue;
 
 		/*
-		 * this is the case when traversing through already created
+		 * this is the case when traversing through already created end sink
 		 * MST connectors, should be skipped
 		 */
 		if (aconnector && aconnector->mst_root)
@@ -2927,6 +2978,27 @@ static int dm_resume(void *handle)
 
 	dm->cached_state = NULL;
 
+	/* Do mst topology probing after resuming cached state*/
+	drm_connector_list_iter_begin(ddev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
+		aconnector = to_amdgpu_dm_connector(connector);
+		if (aconnector->dc_link->type != dc_connection_mst_branch ||
+		    aconnector->mst_root)
+			continue;
+
+		ret = drm_dp_mst_topology_mgr_resume(&aconnector->mst_mgr, true);
+
+		if (ret < 0) {
+			dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx,
+					aconnector->dc_link);
+			need_hotplug = true;
+		}
+	}
+	drm_connector_list_iter_end(&iter);
+
+	if (need_hotplug)
+		drm_kms_helper_hotplug_event(ddev);
+
 	amdgpu_dm_irq_resume_late(adev);
 
 	amdgpu_dm_smu_write_watermarks_table(adev);
@@ -8073,7 +8145,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		bundle->surface_updates[planes_count].plane_info =
 			&bundle->plane_infos[planes_count];
 
-		if (acrtc_state->stream->link->psr_settings.psr_feature_enabled) {
+		if (acrtc_state->stream->link->psr_settings.psr_feature_enabled ||
+		    acrtc_state->stream->link->replay_settings.replay_feature_enabled) {
 			fill_dc_dirty_rects(plane, old_plane_state,
 					    new_plane_state, new_crtc_state,
 					    &bundle->flip_addrs[planes_count],
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 a2d34be82613..9e4cc5eeda76 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -620,7 +620,7 @@ struct amdgpu_hdmi_vsdb_info {
 	unsigned int max_refresh_rate_hz;
 
 	/**
-	 * @replay mode: Replay supported
+	 * @replay_mode: Replay supported
 	 */
 	bool replay_mode;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
index 30c0644d4418..be5a6d008b29 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c
@@ -169,11 +169,23 @@ static void add_link_enc_assignment(
 /* Return first available DIG link encoder. */
 static enum engine_id find_first_avail_link_enc(
 		const struct dc_context *ctx,
-		const struct dc_state *state)
+		const struct dc_state *state,
+		enum engine_id eng_id_requested)
 {
 	enum engine_id eng_id = ENGINE_ID_UNKNOWN;
 	int i;
 
+	if (eng_id_requested != ENGINE_ID_UNKNOWN) {
+
+		for (i = 0; i < ctx->dc->res_pool->res_cap->num_dig_link_enc; i++) {
+			eng_id = state->res_ctx.link_enc_cfg_ctx.link_enc_avail[i];
+			if (eng_id == eng_id_requested)
+				return eng_id;
+		}
+	}
+
+	eng_id = ENGINE_ID_UNKNOWN;
+
 	for (i = 0; i < ctx->dc->res_pool->res_cap->num_dig_link_enc; i++) {
 		eng_id = state->res_ctx.link_enc_cfg_ctx.link_enc_avail[i];
 		if (eng_id != ENGINE_ID_UNKNOWN)
@@ -287,7 +299,7 @@ void link_enc_cfg_link_encs_assign(
 		struct dc_stream_state *streams[],
 		uint8_t stream_count)
 {
-	enum engine_id eng_id = ENGINE_ID_UNKNOWN;
+	enum engine_id eng_id = ENGINE_ID_UNKNOWN, eng_id_req = ENGINE_ID_UNKNOWN;
 	int i;
 	int j;
 
@@ -377,8 +389,14 @@ void link_enc_cfg_link_encs_assign(
 		 * assigned to that endpoint.
 		 */
 		link_enc = get_link_enc_used_by_link(state, stream->link);
-		if (link_enc == NULL)
-			eng_id = find_first_avail_link_enc(stream->ctx, state);
+		if (link_enc == NULL) {
+
+			if (stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA &&
+					stream->link->dpia_preferred_eng_id != ENGINE_ID_UNKNOWN)
+				eng_id_req = stream->link->dpia_preferred_eng_id;
+
+			eng_id = find_first_avail_link_enc(stream->ctx, state, eng_id_req);
+		}
 		else
 			eng_id =  link_enc->preferred_engine;
 
@@ -402,7 +420,9 @@ void link_enc_cfg_link_encs_assign(
 			DC_LOG_DEBUG("%s: CUR %s(%d) - enc_id(%d)\n",
 					__func__,
 					assignment.ep_id.ep_type == DISPLAY_ENDPOINT_PHY ? "PHY" : "DPIA",
-					assignment.ep_id.link_id.enum_id - 1,
+					assignment.ep_id.ep_type == DISPLAY_ENDPOINT_PHY ?
+							assignment.ep_id.link_id.enum_id :
+							assignment.ep_id.link_id.enum_id - 1,
 					assignment.eng_id);
 	}
 	for (i = 0; i < MAX_PIPES; i++) {
@@ -413,7 +433,9 @@ void link_enc_cfg_link_encs_assign(
 			DC_LOG_DEBUG("%s: NEW %s(%d) - enc_id(%d)\n",
 					__func__,
 					assignment.ep_id.ep_type == DISPLAY_ENDPOINT_PHY ? "PHY" : "DPIA",
-					assignment.ep_id.link_id.enum_id - 1,
+					assignment.ep_id.ep_type == DISPLAY_ENDPOINT_PHY ?
+							assignment.ep_id.link_id.enum_id :
+							assignment.ep_id.link_id.enum_id - 1,
 					assignment.eng_id);
 	}
 
@@ -478,7 +500,6 @@ struct dc_link *link_enc_cfg_get_link_using_link_enc(
 	if (stream)
 		link = stream->link;
 
-	// dm_output_to_console("%s: No link using DIG(%d).\n", __func__, eng_id);
 	return link;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 0d0bef8eb331..31e3183497a7 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1496,6 +1496,7 @@ struct dc_link {
 	 * object creation.
 	 */
 	enum engine_id eng_id;
+	enum engine_id dpia_preferred_eng_id;
 
 	bool test_pattern_enabled;
 	enum dp_test_pattern current_test_pattern;
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 ad967b58d7be..478281f2a5ba 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
@@ -964,7 +964,9 @@ void dce110_edp_backlight_control(
 		return;
 	}
 
-	if (link->panel_cntl) {
+	if (link->panel_cntl && !(link->dpcd_sink_ext_caps.bits.oled ||
+		link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1 ||
+		link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1)) {
 		bool is_backlight_on = link->panel_cntl->funcs->is_panel_backlight_on(link->panel_cntl);
 
 		if ((enable && is_backlight_on) || (!enable && !is_backlight_on)) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
index 1c1fb2fa0822..004beed9bd44 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -1032,6 +1032,28 @@ static const struct dce_i2c_mask i2c_masks = {
 		I2C_COMMON_MASK_SH_LIST_DCN30(_MASK)
 };
 
+/* ========================================================== */
+
+/*
+ * DPIA index | Preferred Encoder     |    Host Router
+ *   0        |      C                |       0
+ *   1        |      First Available  |       0
+ *   2        |      D                |       1
+ *   3        |      First Available  |       1
+ */
+/* ========================================================== */
+static const enum engine_id dpia_to_preferred_enc_id_table[] = {
+		ENGINE_ID_DIGC,
+		ENGINE_ID_DIGC,
+		ENGINE_ID_DIGD,
+		ENGINE_ID_DIGD
+};
+
+static enum engine_id dcn314_get_preferred_eng_id_dpia(unsigned int dpia_index)
+{
+	return dpia_to_preferred_enc_id_table[dpia_index];
+}
+
 static struct dce_i2c_hw *dcn31_i2c_hw_create(
 	struct dc_context *ctx,
 	uint32_t inst)
@@ -1785,6 +1807,7 @@ static struct resource_funcs dcn314_res_pool_funcs = {
 	.update_bw_bounding_box = dcn314_update_bw_bounding_box,
 	.patch_unknown_plane_state = dcn20_patch_unknown_plane_state,
 	.get_panel_config_defaults = dcn314_get_panel_config_defaults,
+	.get_preferred_eng_id_dpia = dcn314_get_preferred_eng_id_dpia,
 };
 
 static struct clock_source *dcn30_clock_source_create(
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 027aec70c070..eaad1260bfd1 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -65,6 +65,7 @@ struct resource_context;
 struct clk_bw_params;
 
 struct resource_funcs {
+	enum engine_id (*get_preferred_eng_id_dpia)(unsigned int dpia_index);
 	void (*destroy)(struct resource_pool **pool);
 	void (*link_init)(struct dc_link *link);
 	struct panel_cntl*(*panel_cntl_create)(
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
index 195ca9e52eda..0895742a3102 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
@@ -791,6 +791,10 @@ static bool construct_dpia(struct dc_link *link,
 	/* Set dpia port index : 0 to number of dpia ports */
 	link->ddc_hw_inst = init_params->connector_index;
 
+	// Assign Dpia preferred eng_id
+	if (link->dc->res_pool->funcs->get_preferred_eng_id_dpia)
+		link->dpia_preferred_eng_id = link->dc->res_pool->funcs->get_preferred_eng_id_dpia(link->ddc_hw_inst);
+
 	/* TODO: Create link encoder */
 
 	link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED;
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 8433f99f6667..3b5a56585c4b 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -31,12 +31,12 @@
 #include <linux/types.h>
 #include <linux/bitmap.h>
 #include <linux/dma-fence.h>
+#include "amdgpu_irq.h"
+#include "amdgpu_gfx.h"
 
 struct pci_dev;
 struct amdgpu_device;
 
-#define KGD_MAX_QUEUES 128
-
 struct kfd_dev;
 struct kgd_mem;
 
@@ -68,7 +68,7 @@ struct kfd_cu_info {
 	uint32_t wave_front_size;
 	uint32_t max_scratch_slots_per_cu;
 	uint32_t lds_size;
-	uint32_t cu_bitmap[4][4];
+	uint32_t cu_bitmap[AMDGPU_MAX_GC_INSTANCES][4][4];
 };
 
 /* For getting GPU local memory information from KGD */
@@ -326,8 +326,7 @@ struct kfd2kgd_calls {
 			uint32_t wait_times,
 			uint32_t grace_period,
 			uint32_t *reg_offset,
-			uint32_t *reg_data,
-			uint32_t inst);
+			uint32_t *reg_data);
 	void (*get_cu_occupancy)(struct amdgpu_device *adev, int pasid,
 			int *wave_cnt, int *max_waves_per_cu, uint32_t inst);
 	void (*program_trap_handler_settings)(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 199a673b8120..de80e191a92c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -336,7 +336,7 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 
 	/* Store one-time values in driver PPTable */
 	if (!pptable->Init) {
-		while (retry--) {
+		while (--retry) {
 			ret = smu_v13_0_6_get_metrics_table(smu, NULL, true);
 			if (ret)
 				return ret;