Merge tag 'drm-fixes-5.4-2019-09-25' of git://people.freedesktop.org/~agd5f/linux into drm-next

drm-fixes-5.4-2019-09-25:

amdgpu:
- Fix a 64 bit divide
- Prevent a memory leak in a failure case in dc
- Load proper gfx firmware on navi14 variants

drm-fixes-5.4-2019-09-19:

amdgpu:
- Add more navi12 and navi14 PCI ids
- Misc fixes for renoir
- Fix bandwidth issues with multiple displays on vega20
- Support for Dali
- Fix a possible oops with KFD on hawaii
- Fix for backlight level after resume on some APUs
- Other misc fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925213500.3490-1-alexander.deucher@amd.com

29 files changed, 256 insertions, 48 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index 61bd10310604..5803fcbae22f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -948,6 +948,7 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 	case AMD_IP_BLOCK_TYPE_UVD:
 	case AMD_IP_BLOCK_TYPE_VCN:
 	case AMD_IP_BLOCK_TYPE_VCE:
+	case AMD_IP_BLOCK_TYPE_SDMA:
 		if (swsmu)
 			ret = smu_dpm_set_power_gate(&adev->smu, block_type, gate);
 		else
@@ -956,7 +957,6 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 		break;
 	case AMD_IP_BLOCK_TYPE_GMC:
 	case AMD_IP_BLOCK_TYPE_ACP:
-	case AMD_IP_BLOCK_TYPE_SDMA:
 		ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu(
 				(adev)->powerplay.pp_handle, block_type, gate));
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 48a2070e72f2..5da72ca6f3e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1011,11 +1011,16 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	{0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	/* Navi14 */
-	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
 
 	/* Renoir */
 	{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT},
 
+	/* Navi12 */
+	{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
+
 	{0, 0, 0}
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 7850084a05e3..60655834d649 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -143,7 +143,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	/* ring tests don't use a job */
 	if (job) {
 		vm = job->vm;
-		fence_ctx = job->base.s_fence->scheduled.context;
+		fence_ctx = job->base.s_fence ?
+			job->base.s_fence->scheduled.context : 0;
 	} else {
 		vm = NULL;
 		fence_ctx = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 0e2ec608530b..f6147528be64 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -677,6 +677,9 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK)
 			sh_num = 0xffffffff;
 
+		if (info->read_mmr_reg.count > 128)
+			return -EINVAL;
+
 		regs = kmalloc_array(info->read_mmr_reg.count, sizeof(*regs), GFP_KERNEL);
 		if (!regs)
 			return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index db28823891ac..638c821611ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -70,6 +70,11 @@ MODULE_FIRMWARE("amdgpu/navi10_mec.bin");
 MODULE_FIRMWARE("amdgpu/navi10_mec2.bin");
 MODULE_FIRMWARE("amdgpu/navi10_rlc.bin");
 
+MODULE_FIRMWARE("amdgpu/navi14_ce_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_pfp_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_me_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_mec_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_mec2_wks.bin");
 MODULE_FIRMWARE("amdgpu/navi14_ce.bin");
 MODULE_FIRMWARE("amdgpu/navi14_pfp.bin");
 MODULE_FIRMWARE("amdgpu/navi14_me.bin");
@@ -594,7 +599,8 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev)
 static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 {
 	const char *chip_name;
-	char fw_name[30];
+	char fw_name[40];
+	char wks[10];
 	int err;
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
@@ -607,12 +613,16 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 
 	DRM_DEBUG("\n");
 
+	memset(wks, 0, sizeof(wks));
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
 		chip_name = "navi10";
 		break;
 	case CHIP_NAVI14:
 		chip_name = "navi14";
+		if (!(adev->pdev->device == 0x7340 &&
+		      adev->pdev->revision != 0x00))
+			snprintf(wks, sizeof(wks), "_wks");
 		break;
 	case CHIP_NAVI12:
 		chip_name = "navi12";
@@ -621,7 +631,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -632,7 +642,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -643,7 +653,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -708,7 +718,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	if (adev->gfx.rlc.is_rlc_v2_1)
 		gfx_v10_0_init_rlc_ext_microcode(adev);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -719,7 +729,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev);
 	if (!err) {
 		err = amdgpu_ucode_validate(adev->gfx.mec2_fw);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 83d45f98a461..dcadc73bffd2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1650,7 +1650,6 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
-	case CHIP_RENOIR:
 		gfx_v9_0_init_lbpw(adev);
 		break;
 	case CHIP_VEGA20:
@@ -3026,7 +3025,6 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
-	case CHIP_RENOIR:
 		if (amdgpu_lbpw == 0)
 			gfx_v9_0_enable_lbpw(adev, false);
 		else
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index ff18b3a57892..78452cf0115d 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1889,8 +1889,9 @@ static int sdma_v4_0_hw_init(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs &&
-			adev->powerplay.pp_funcs->set_powergating_by_smu)
+	if ((adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs &&
+			adev->powerplay.pp_funcs->set_powergating_by_smu) ||
+			adev->asic_type == CHIP_RENOIR)
 		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, false);
 
 	if (!amdgpu_sriov_vf(adev))
@@ -1917,8 +1918,9 @@ static int sdma_v4_0_hw_fini(void *handle)
 	sdma_v4_0_ctx_switch_enable(adev, false);
 	sdma_v4_0_enable(adev, false);
 
-	if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs
-			&& adev->powerplay.pp_funcs->set_powergating_by_smu)
+	if ((adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs
+			&& adev->powerplay.pp_funcs->set_powergating_by_smu) ||
+			adev->asic_type == CHIP_RENOIR)
 		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, true);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
index 4a5951036927..c44723c267c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
@@ -493,7 +493,15 @@ static void smu_v11_0_i2c_fini(struct i2c_adapter *control)
 	}
 
 	/* Restore clock gating */
-	smu_v11_0_i2c_set_clock_gating(control, true);
+
+	/*
+	 * TODO Reenabling clock gating seems to break subsequent SMU operation
+	 *      on the I2C bus. My guess is that SMU doesn't disable clock gating like
+	 *      we do here before working with the bus. So for now just don't restore
+	 *      it but later work with SMU to see if they have this issue and can
+	 *      update their code appropriately
+	 */
+	/* smu_v11_0_i2c_set_clock_gating(control, true); */
 
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index a8cf82d46109..901fe3590165 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -694,10 +694,10 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x003f8000, 0x8f6f896f,
 	0x88776f77, 0x8a6eff6e,
 	0x023f8000, 0xb9eef807,
-	0xb970f812, 0xb971f813,
-	0x8ff08870, 0xf4051bb8,
+	0xb97af812, 0xb97bf813,
+	0x8ffa887a, 0xf4051bbd,
 	0xfa000000, 0xbf8cc07f,
-	0xf4051c38, 0xfa000008,
+	0xf4051ebd, 0xfa000008,
 	0xbf8cc07f, 0x87ee6e6e,
 	0xbf840001, 0xbe80206e,
 	0xb971f803, 0x8771ff71,
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
index 35986219ce5f..cdaa523ce6be 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -187,12 +187,12 @@ L_FETCH_2ND_TRAP:
 	// Read second-level TBA/TMA from first-level TMA and jump if available.
 	// ttmp[2:5] and ttmp12 can be used (others hold SPI-initialized debug data)
 	// ttmp12 holds SQ_WAVE_STATUS
-	s_getreg_b32	ttmp4, hwreg(HW_REG_SHADER_TMA_LO)
-	s_getreg_b32	ttmp5, hwreg(HW_REG_SHADER_TMA_HI)
-	s_lshl_b64	[ttmp4, ttmp5], [ttmp4, ttmp5], 0x8
-	s_load_dwordx2	[ttmp2, ttmp3], [ttmp4, ttmp5], 0x0 glc:1		// second-level TBA
+	s_getreg_b32	ttmp14, hwreg(HW_REG_SHADER_TMA_LO)
+	s_getreg_b32	ttmp15, hwreg(HW_REG_SHADER_TMA_HI)
+	s_lshl_b64	[ttmp14, ttmp15], [ttmp14, ttmp15], 0x8
+	s_load_dwordx2	[ttmp2, ttmp3], [ttmp14, ttmp15], 0x0 glc:1		// second-level TBA
 	s_waitcnt	lgkmcnt(0)
-	s_load_dwordx2	[ttmp4, ttmp5], [ttmp4, ttmp5], 0x8 glc:1		// second-level TMA
+	s_load_dwordx2	[ttmp14, ttmp15], [ttmp14, ttmp15], 0x8 glc:1		// second-level TMA
 	s_waitcnt	lgkmcnt(0)
 	s_and_b64	[ttmp2, ttmp3], [ttmp2, ttmp3], [ttmp2, ttmp3]
 	s_cbranch_scc0	L_NO_NEXT_TRAP						// second-level trap handler not been set
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 09f70ba71711..8cab6da512a0 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2113,6 +2113,7 @@ static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd)
 }
 
 static const struct backlight_ops amdgpu_dm_backlight_ops = {
+	.options = BL_CORE_SUSPENDRESUME,
 	.get_brightness = amdgpu_dm_backlight_get_brightness,
 	.update_status	= amdgpu_dm_backlight_update_status,
 };
@@ -2384,6 +2385,8 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 
 	if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY)
 		dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true;
+	if (adev->asic_type == CHIP_RENOIR)
+		dm->dc->debug.disable_stutter = true;
 
 	return 0;
 fail:
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 383f4f8db8f4..9b2cb57bf2ba 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -708,6 +708,10 @@ static void hack_bounding_box(struct dcn_bw_internal_vars *v,
 
 unsigned int get_highest_allowed_voltage_level(uint32_t hw_internal_rev)
 {
+	/* for dali, the highest voltage level we want is 0 */
+	if (ASICREV_IS_DALI(hw_internal_rev))
+		return 0;
+
 	/* we are ok with all levels */
 	return 4;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
index 5cc3acccda2a..b1e657e137a9 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
@@ -98,11 +98,14 @@ uint32_t dce110_get_min_vblank_time_us(const struct dc_state *context)
 		struct dc_stream_state *stream = context->streams[j];
 		uint32_t vertical_blank_in_pixels = 0;
 		uint32_t vertical_blank_time = 0;
+		uint32_t vertical_total_min = stream->timing.v_total;
+		struct dc_crtc_timing_adjust adjust = stream->adjust;
+		if (adjust.v_total_max != adjust.v_total_min)
+			vertical_total_min = adjust.v_total_min;
 
 		vertical_blank_in_pixels = stream->timing.h_total *
-			(stream->timing.v_total
+			(vertical_total_min
 			 - stream->timing.v_addressable);
-
 		vertical_blank_time = vertical_blank_in_pixels
 			* 10000 / stream->timing.pix_clk_100hz;
 
@@ -171,6 +174,10 @@ void dce11_pplib_apply_display_requirements(
 	struct dc_state *context)
 {
 	struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg;
+	int memory_type_multiplier = MEMORY_TYPE_MULTIPLIER_CZ;
+
+	if (dc->bw_vbios && dc->bw_vbios->memory_type == bw_def_hbm)
+		memory_type_multiplier = MEMORY_TYPE_HBM;
 
 	pp_display_cfg->all_displays_in_sync =
 		context->bw_ctx.bw.dce.all_displays_in_sync;
@@ -183,8 +190,20 @@ void dce11_pplib_apply_display_requirements(
 	pp_display_cfg->cpu_pstate_separation_time =
 			context->bw_ctx.bw.dce.blackout_recovery_time_us;
 
-	pp_display_cfg->min_memory_clock_khz = context->bw_ctx.bw.dce.yclk_khz
-		/ MEMORY_TYPE_MULTIPLIER_CZ;
+	/*
+	 * TODO: determine whether the bandwidth has reached memory's limitation
+	 * , then change minimum memory clock based on real-time bandwidth
+	 * limitation.
+	 */
+	if (ASICREV_IS_VEGA20_P(dc->ctx->asic_id.hw_internal_rev) && (context->stream_count >= 2)) {
+		pp_display_cfg->min_memory_clock_khz = max(pp_display_cfg->min_memory_clock_khz,
+							   (uint32_t) div64_s64(
+								   div64_s64(dc->bw_vbios->high_yclk.value,
+									     memory_type_multiplier), 10000));
+	} else {
+		pp_display_cfg->min_memory_clock_khz = context->bw_ctx.bw.dce.yclk_khz
+			/ memory_type_multiplier;
+	}
 
 	pp_display_cfg->min_engine_clock_khz = determine_sclk_from_bounding_box(
 			dc,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
index 1488ffddf4e3..31b698bf9cfc 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
@@ -148,7 +148,7 @@ static void dce_mi_program_pte_vm(
 			pte->min_pte_before_flip_horiz_scan;
 
 	REG_UPDATE(GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT,
-			GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT, 0xff);
+			GRPH_PIPE_OUTSTANDING_REQUEST_LIMIT, 0x7f);
 
 	REG_UPDATE_3(DVMM_PTE_CONTROL,
 			DVMM_PAGE_WIDTH, page_width,
@@ -157,7 +157,7 @@ static void dce_mi_program_pte_vm(
 
 	REG_UPDATE_2(DVMM_PTE_ARB_CONTROL,
 			DVMM_PTE_REQ_PER_CHUNK, pte->pte_req_per_chunk,
-			DVMM_MAX_PTE_REQ_OUTSTANDING, 0xff);
+			DVMM_MAX_PTE_REQ_OUTSTANDING, 0x7f);
 }
 
 static void program_urgency_watermark(
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index afc61055eca1..1787b9bf800a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -1091,6 +1091,7 @@ struct resource_pool *dce100_create_resource_pool(
 	if (construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
+	kfree(pool);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index c66fe170e1e8..318e9c2e2ca8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -1462,6 +1462,7 @@ struct resource_pool *dce110_create_resource_pool(
 	if (construct(num_virtual_links, dc, pool, asic_id))
 		return &pool->base;
 
+	kfree(pool);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 3ac4c7e73050..83e1878161c9 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -987,6 +987,10 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 	struct dm_pp_clock_levels_with_latency mem_clks = {0};
 	struct dm_pp_wm_sets_with_clock_ranges clk_ranges = {0};
 	struct dm_pp_clock_levels clks = {0};
+	int memory_type_multiplier = MEMORY_TYPE_MULTIPLIER_CZ;
+
+	if (dc->bw_vbios && dc->bw_vbios->memory_type == bw_def_hbm)
+		memory_type_multiplier = MEMORY_TYPE_HBM;
 
 	/*do system clock  TODO PPLIB: after PPLIB implement,
 	 * then remove old way
@@ -1026,12 +1030,12 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 				&clks);
 
 		dc->bw_vbios->low_yclk = bw_frc_to_fixed(
-			clks.clocks_in_khz[0] * MEMORY_TYPE_MULTIPLIER_CZ, 1000);
+			clks.clocks_in_khz[0] * memory_type_multiplier, 1000);
 		dc->bw_vbios->mid_yclk = bw_frc_to_fixed(
-			clks.clocks_in_khz[clks.num_levels>>1] * MEMORY_TYPE_MULTIPLIER_CZ,
+			clks.clocks_in_khz[clks.num_levels>>1] * memory_type_multiplier,
 			1000);
 		dc->bw_vbios->high_yclk = bw_frc_to_fixed(
-			clks.clocks_in_khz[clks.num_levels-1] * MEMORY_TYPE_MULTIPLIER_CZ,
+			clks.clocks_in_khz[clks.num_levels-1] * memory_type_multiplier,
 			1000);
 
 		return;
@@ -1067,12 +1071,12 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 	 * YCLK = UMACLK*m_memoryTypeMultiplier
 	 */
 	dc->bw_vbios->low_yclk = bw_frc_to_fixed(
-		mem_clks.data[0].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ, 1000);
+		mem_clks.data[0].clocks_in_khz * memory_type_multiplier, 1000);
 	dc->bw_vbios->mid_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ,
+		mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * memory_type_multiplier,
 		1000);
 	dc->bw_vbios->high_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ,
+		mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * memory_type_multiplier,
 		1000);
 
 	/* Now notify PPLib/SMU about which Watermarks sets they should select
@@ -1338,6 +1342,7 @@ struct resource_pool *dce112_create_resource_pool(
 	if (construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
+	kfree(pool);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 7d08154e9662..8b85e5274bba 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -847,6 +847,8 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 	int i;
 	unsigned int clk;
 	unsigned int latency;
+	/*original logic in dal3*/
+	int memory_type_multiplier = MEMORY_TYPE_MULTIPLIER_CZ;
 
 	/*do system clock*/
 	if (!dm_pp_get_clock_levels_by_type_with_latency(
@@ -905,13 +907,16 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 	 * ALSO always convert UMA clock (from PPLIB)  to YCLK (HW formula):
 	 * YCLK = UMACLK*m_memoryTypeMultiplier
 	 */
+	if (dc->bw_vbios->memory_type == bw_def_hbm)
+		memory_type_multiplier = MEMORY_TYPE_HBM;
+
 	dc->bw_vbios->low_yclk = bw_frc_to_fixed(
-		mem_clks.data[0].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ, 1000);
+		mem_clks.data[0].clocks_in_khz * memory_type_multiplier, 1000);
 	dc->bw_vbios->mid_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ,
+		mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * memory_type_multiplier,
 		1000);
 	dc->bw_vbios->high_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * MEMORY_TYPE_MULTIPLIER_CZ,
+		mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * memory_type_multiplier,
 		1000);
 
 	/* Now notify PPLib/SMU about which Watermarks sets they should select
@@ -1203,6 +1208,7 @@ struct resource_pool *dce120_create_resource_pool(
 	if (construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
+	kfree(pool);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 5a89e462e7cc..59305e411a66 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1570,6 +1570,7 @@ struct resource_pool *dcn10_create_resource_pool(
 	if (construct(init_data->num_virtual_links, dc, pool))
 		return &pool->base;
 
+	kfree(pool);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index 3ca5139f1273..de182185fe1f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -23,6 +23,8 @@
  *
  */
 
+#include <linux/slab.h>
+
 #include "dm_services.h"
 #include "dc.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
index 34485d9de78a..8572678f8d4f 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
@@ -35,12 +35,10 @@
 
 #include "hw_factory_dcn21.h"
 
-
 #include "dcn/dcn_2_1_0_offset.h"
 #include "dcn/dcn_2_1_0_sh_mask.h"
 #include "renoir_ip_offset.h"
 
-
 #include "reg_helper.h"
 #include "../hpd_regs.h"
 /* begin *********************
@@ -136,6 +134,39 @@ static const struct ddc_sh_mask ddc_mask[] = {
 	DDC_MASK_SH_LIST_DCN2(_MASK, 6)
 };
 
+#include "../generic_regs.h"
+
+/* set field name */
+#define SF_GENERIC(reg_name, field_name, post_fix)\
+	.field_name = reg_name ## __ ## field_name ## post_fix
+
+#define generic_regs(id) \
+{\
+	GENERIC_REG_LIST(id)\
+}
+
+static const struct generic_registers generic_regs[] = {
+	generic_regs(A),
+};
+
+static const struct generic_sh_mask generic_shift[] = {
+	GENERIC_MASK_SH_LIST(__SHIFT, A),
+};
+
+static const struct generic_sh_mask generic_mask[] = {
+	GENERIC_MASK_SH_LIST(_MASK, A),
+};
+
+static void define_generic_registers(struct hw_gpio_pin *pin, uint32_t en)
+{
+	struct hw_generic *generic = HW_GENERIC_FROM_BASE(pin);
+
+	generic->regs = &generic_regs[en];
+	generic->shifts = &generic_shift[en];
+	generic->masks = &generic_mask[en];
+	generic->base.regs = &generic_regs[en].gpio;
+}
+
 static void define_ddc_registers(
 		struct hw_gpio_pin *pin,
 		uint32_t en)
@@ -181,7 +212,8 @@ static const struct hw_factory_funcs funcs = {
 	.get_hpd_pin = dal_hw_hpd_get_pin,
 	.get_generic_pin = dal_hw_generic_get_pin,
 	.define_hpd_registers = define_hpd_registers,
-	.define_ddc_registers = define_ddc_registers
+	.define_ddc_registers = define_ddc_registers,
+	.define_generic_registers = define_generic_registers
 };
 /*
  * dal_hw_factory_dcn10_init
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
index ad7c43746291..fbb58fb8c318 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
@@ -58,7 +58,6 @@
 #define SF_HPD(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
-
 /* macros to expend register list macro defined in HW object header file
  * end *********************/
 
@@ -71,7 +70,7 @@ static bool offset_to_id(
 {
 	switch (offset) {
 	/* GENERIC */
-	case REG(DC_GENERICA):
+	case REG(DC_GPIO_GENERIC_A):
 		*id = GPIO_ID_GENERIC;
 		switch (mask) {
 		case DC_GPIO_GENERIC_A__DC_GPIO_GENERICA_A_MASK:
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index 1cc1c8ce633b..bef224bf803e 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -31,6 +31,8 @@
 #include "dm_pp_smu.h"
 
 #define MEMORY_TYPE_MULTIPLIER_CZ 4
+#define MEMORY_TYPE_HBM 2
+
 
 enum dce_version resource_parse_asic_id(
 		struct hw_asic_id asic_id);
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 1f16892f0add..1be6c44fd32f 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -137,10 +137,13 @@
 #define RAVEN1_F0 0xF0
 #define RAVEN_UNKNOWN 0xFF
 
+#define PICASSO_15D8_REV_E3 0xE3
+#define PICASSO_15D8_REV_E4 0xE4
+
 #define ASICREV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN)
 #define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0))
-#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0))
-
+#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < PICASSO_15D8_REV_E3))
+#define ASICREV_IS_DALI(eChipRev) ((eChipRev >= PICASSO_15D8_REV_E3) && (eChipRev < RAVEN1_F0))
 
 #define ASICREV_IS_RV1_F0(eChipRev) ((eChipRev >= RAVEN1_F0) && (eChipRev < RAVEN_UNKNOWN))
 
diff --git a/drivers/gpu/drm/amd/include/renoir_ip_offset.h b/drivers/gpu/drm/amd/include/renoir_ip_offset.h
index 554714c8e000..094648cac392 100644
--- a/drivers/gpu/drm/amd/include/renoir_ip_offset.h
+++ b/drivers/gpu/drm/amd/include/renoir_ip_offset.h
@@ -155,7 +155,7 @@ static const struct IP_BASE MP0_BASE ={ { { { 0x00016000, 0x0243FC00, 0x00DC0000
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } } } };
-static const struct IP_BASE MP1_BASE ={ { { { 0x00016200, 0x02400400, 0x00E80000, 0x00EC0000, 0x00F00000 } },
+static const struct IP_BASE MP1_BASE ={ { { { 0x00016000, 0x02400400, 0x00E80000, 0x00EC0000, 0x00F00000 } },
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } },
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index fa636cb462c1..fa8ad7db2b3a 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -1531,6 +1531,7 @@ static int pp_asic_reset_mode_2(void *handle)
 static int pp_smu_i2c_bus_access(void *handle, bool acquire)
 {
 	struct pp_hwmgr *hwmgr = handle;
+	int ret = 0;
 
 	if (!hwmgr || !hwmgr->pm_en)
 		return -EINVAL;
@@ -1540,7 +1541,11 @@ static int pp_smu_i2c_bus_access(void *handle, bool acquire)
 		return -EINVAL;
 	}
 
-	return hwmgr->hwmgr_func->smu_i2c_bus_access(hwmgr, acquire);
+	mutex_lock(&hwmgr->smu_lock);
+	ret = hwmgr->hwmgr_func->smu_i2c_bus_access(hwmgr, acquire);
+	mutex_unlock(&hwmgr->smu_lock);
+
+	return ret;
 }
 
 static const struct amd_pm_funcs pp_dpm_funcs = {
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 22f3c60d380f..33960fb38a5d 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -354,6 +354,9 @@ int smu_dpm_set_power_gate(struct smu_context *smu, uint32_t block_type,
 	case AMD_IP_BLOCK_TYPE_GFX:
 		ret = smu_gfx_off_control(smu, gate);
 		break;
+	case AMD_IP_BLOCK_TYPE_SDMA:
+		ret = smu_powergate_sdma(smu, gate);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index 2a6da546fb55..e62bfba51562 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -177,12 +177,82 @@ static int renoir_get_dpm_uclk_limited(struct smu_context *smu, uint32_t *clock,
 
 }
 
+static int renoir_print_clk_levels(struct smu_context *smu,
+			enum smu_clk_type clk_type, char *buf)
+{
+	int i, size = 0, ret = 0;
+	uint32_t cur_value = 0, value = 0, count = 0, min = 0, max = 0;
+	DpmClocks_t *clk_table = smu->smu_table.clocks_table;
+	SmuMetrics_t metrics = {0};
+
+	if (!clk_table || clk_type >= SMU_CLK_COUNT)
+		return -EINVAL;
+
+	ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
+			       (void *)&metrics, false);
+	if (ret)
+		return ret;
+
+	switch (clk_type) {
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		/* retirve table returned paramters unit is MHz */
+		cur_value = metrics.ClockFrequency[CLOCK_GFXCLK];
+		ret = smu_get_dpm_freq_range(smu, SMU_GFXCLK, &min, &max);
+		if (!ret) {
+			/* driver only know min/max gfx_clk, Add level 1 for all other gfx clks */
+			if (cur_value  == max)
+				i = 2;
+			else if (cur_value == min)
+				i = 0;
+			else
+				i = 1;
+
+			size += sprintf(buf + size, "0: %uMhz %s\n", min,
+					i == 0 ? "*" : "");
+			size += sprintf(buf + size, "1: %uMhz %s\n",
+					i == 1 ? cur_value : RENOIR_UMD_PSTATE_GFXCLK,
+					i == 1 ? "*" : "");
+			size += sprintf(buf + size, "2: %uMhz %s\n", max,
+					i == 2 ? "*" : "");
+		}
+		return size;
+	case SMU_SOCCLK:
+		count = NUM_SOCCLK_DPM_LEVELS;
+		cur_value = metrics.ClockFrequency[CLOCK_SOCCLK];
+		break;
+	case SMU_MCLK:
+		count = NUM_MEMCLK_DPM_LEVELS;
+		cur_value = metrics.ClockFrequency[CLOCK_UMCCLK];
+		break;
+	case SMU_DCEFCLK:
+		count = NUM_DCFCLK_DPM_LEVELS;
+		cur_value = metrics.ClockFrequency[CLOCK_DCFCLK];
+		break;
+	case SMU_FCLK:
+		count = NUM_FCLK_DPM_LEVELS;
+		cur_value = metrics.ClockFrequency[CLOCK_FCLK];
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	for (i = 0; i < count; i++) {
+		GET_DPM_CUR_FREQ(clk_table, clk_type, i, value);
+		size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
+				cur_value == value ? "*" : "");
+	}
+
+	return size;
+}
+
 static const struct pptable_funcs renoir_ppt_funcs = {
 	.get_smu_msg_index = renoir_get_smu_msg_index,
 	.get_smu_table_index = renoir_get_smu_table_index,
 	.tables_init = renoir_tables_init,
 	.set_power_state = NULL,
 	.get_dpm_uclk_limited = renoir_get_dpm_uclk_limited,
+	.print_clk_levels = renoir_print_clk_levels,
 };
 
 void renoir_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h
index e9b7237c0f7f..2a390ddd37dd 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h
@@ -25,4 +25,29 @@
 
 extern void renoir_set_ppt_funcs(struct smu_context *smu);
 
+/* UMD PState Renoir Msg Parameters in MHz */
+#define RENOIR_UMD_PSTATE_GFXCLK       700
+#define RENOIR_UMD_PSTATE_SOCCLK       678
+#define RENOIR_UMD_PSTATE_FCLK         800
+
+#define GET_DPM_CUR_FREQ(table, clk_type, dpm_level, freq)		\
+	do {								\
+		switch (clk_type) {					\
+		case SMU_SOCCLK:					\
+			freq = table->SocClocks[dpm_level].Freq;	\
+			break;						\
+		case SMU_MCLK:						\
+			freq = table->MemClocks[dpm_level].Freq;	\
+			break;						\
+		case SMU_DCEFCLK:					\
+			freq = table->DcfClocks[dpm_level].Freq;	\
+			break;						\
+		case SMU_FCLK:						\
+			freq = table->FClocks[dpm_level].Freq;		\
+			break;						\
+		default:						\
+			break;						\
+		}							\
+	} while (0)
+
 #endif