Merge tag 'amd-drm-fixes-5.10-2020-10-21' of git://people.freedesktop.org/~agd5f/linux into drm-next

amd-drm-fixes-5.10-2020-10-21:

amdgpu:
- Sienna Cichlid fixes
- MST manager resource leak fix
- GPU reset fix

amdkfd:
- Luxmark fix for Navi1x

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201022040322.4183-1-alexander.deucher@amd.com

13 files changed, 187 insertions, 31 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e8b41756c9f9..37da3537ba2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4625,7 +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) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 18be544d8c1e..96a9699f87ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -208,7 +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;
@@ -1750,6 +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 8bf6a7c056bc..4e36551ab50b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1986,7 +1986,8 @@ static int amdgpu_ras_check_asic_type(struct amdgpu_device *adev)
 {
 	if (adev->asic_type != CHIP_VEGA10 &&
 		adev->asic_type != CHIP_VEGA20 &&
-		adev->asic_type != CHIP_ARCTURUS)
+		adev->asic_type != CHIP_ARCTURUS &&
+		adev->asic_type != CHIP_SIENNA_CICHLID)
 		return 1;
 	else
 		return 0;
@@ -2030,7 +2031,6 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev,
 
 	*supported = amdgpu_ras_enable == 0 ?
 			0 : *hw_supported & amdgpu_ras_mask;
-
 	adev->ras_features = *supported;
 }
 
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_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/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 9792ec737029..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)
 {
@@ -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;
@@ -3701,8 +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);
@@ -3744,8 +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);
@@ -3806,8 +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];
@@ -3827,6 +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];
@@ -4536,12 +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) *
@@ -6950,6 +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;
 }
 
@@ -8763,6 +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;
@@ -8797,6 +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/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index 1ef2f5b1d828..4137dc710aaf 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -201,7 +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      */
@@ -223,7 +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/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/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index bb1bc7f5d149..e2b23486ba4c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5063,7 +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)
 
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h
index 35fc46d3c9c0..cbf4a58b77d9 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h
@@ -220,6 +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/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index c27806fd07e0..685a8a3b25d4 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),
@@ -452,6 +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;
@@ -948,19 +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," :
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index c30d3338825f..92b2ea4c197b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -431,10 +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;
 
@@ -447,23 +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;