[PATCH AUTOSEL 5.14 007/252] drm/amdgpu: Fix amdgpu_ras_eeprom_init()

[PATCH AUTOSEL 5.14 007/252] drm/amdgpu: Fix amdgpu_ras_eeprom_init()

[Sasha Levin]

From: Luben Tuikov <luben.tuikov@amd.com>

[ Upstream commit dce4400e6516d18313d23de45b5be8a18980b00e ]

No need to account for the 2 bytes of EEPROM
address--this is now well abstracted away by
the fixes the the lower layers.

Cc: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Cc: Alexander Deucher <Alexander.Deucher@amd.com>
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Acked-by: Alexander Deucher <Alexander.Deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 38222de921d1..8dd151c9e459 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -325,7 +325,7 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
 		return ret;
 	}
 
-	__decode_table_header_from_buff(hdr, &buff[2]);
+	__decode_table_header_from_buff(hdr, buff);
 
 	if (hdr->header == EEPROM_TABLE_HDR_VAL) {
 		control->num_recs = (hdr->tbl_size - EEPROM_TABLE_HEADER_SIZE) /
-- 
2.30.2

[PATCH AUTOSEL 5.14 008/252] drm/amdgpu: Fix koops when accessing RAS EEPROM

[Sasha Levin]

From: Luben Tuikov <luben.tuikov@amd.com>

[ Upstream commit 1d9d2ca85b32605ac9c74c8fa42d0c1cfbe019d4 ]

Debugfs RAS EEPROM files are available when
the ASIC supports RAS, and when the debugfs is
enabled, an also when "ras_enable" module
parameter is set to 0. However in this case,
we get a kernel oops when accessing some of
the "ras_..." controls in debugfs. The reason
for this is that struct amdgpu_ras::adev is
unset. This commit sets it, thus enabling access
to those facilities. Note that this facilitates
EEPROM access and not necessarily RAS features or
functionality.

Cc: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: John Clements <john.clements@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Acked-by: Alexander Deucher <Alexander.Deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index fc66aca28594..95d5842385b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1966,11 +1966,20 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	bool exc_err_limit = false;
 	int ret;
 
-	if (adev->ras_enabled && con)
-		data = &con->eh_data;
-	else
+	if (!con)
+		return 0;
+
+	/* Allow access to RAS EEPROM via debugfs, when the ASIC
+	 * supports RAS and debugfs is enabled, but when
+	 * adev->ras_enabled is unset, i.e. when "ras_enable"
+	 * module parameter is set to 0.
+	 */
+	con->adev = adev;
+
+	if (!adev->ras_enabled)
 		return 0;
 
+	data = &con->eh_data;
 	*data = kmalloc(sizeof(**data), GFP_KERNEL | __GFP_ZERO);
 	if (!*data) {
 		ret = -ENOMEM;
@@ -1980,7 +1989,6 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 	mutex_init(&con->recovery_lock);
 	INIT_WORK(&con->recovery_work, amdgpu_ras_do_recovery);
 	atomic_set(&con->in_recovery, 0);
-	con->adev = adev;
 
 	max_eeprom_records_len = amdgpu_ras_eeprom_get_record_max_length();
 	amdgpu_ras_validate_threshold(adev, max_eeprom_records_len);
-- 
2.30.2

[PATCH AUTOSEL 5.14 052/252] drm/amd/display: Fix timer_per_pixel unit error

[Sasha Levin]

From: Oliver Logush <oliver.logush@amd.com>

[ Upstream commit 23e55639b87fb16a9f0f66032ecb57060df6c46c ]

[why]
The units of the time_per_pixel variable were incorrect, this had to be
changed for the code to properly function.

[how]
The change was very straightforward, only required one line of code to
be changed where the calculation was done.

Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Oliver Logush <oliver.logush@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index b173fa3653b5..c78933a9d31c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -2462,7 +2462,7 @@ void dcn20_set_mcif_arb_params(
 				wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 				wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 			}
-			wb_arb_params->time_per_pixel = 16.0 / context->res_ctx.pipe_ctx[i].stream->phy_pix_clk; /* 4 bit fraction, ms */
+			wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */
 			wb_arb_params->slice_lines = 32;
 			wb_arb_params->arbitration_slice = 2;
 			wb_arb_params->max_scaled_time = dcn20_calc_max_scaled_time(wb_arb_params->time_per_pixel,
-- 
2.30.2

[PATCH AUTOSEL 5.14 061/252] drm/amd/display: Fixed hardware power down bypass during headless boot

[Sasha Levin]

From: Jake Wang <haonan.wang2@amd.com>

[ Upstream commit 3addbde269f21ffc735f6d3d0c2237664923824e ]

[Why]
During headless boot, DIG may be on which causes HW/SW discrepancies.
To avoid this we power down hardware on boot if DIG is turned on. With
introduction of multiple eDP, hardware power down is being bypassed
under certain conditions.

[How]
Fixed hardware power down bypass, and ensured hardware will power down
if DIG is on and seamless boot is not enabled.

Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Jake Wang <haonan.wang2@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../amd/display/dc/dcn10/dcn10_hw_sequencer.c | 27 +++++++++----------
 .../drm/amd/display/dc/dcn30/dcn30_hwseq.c    | 25 ++++++++---------
 .../drm/amd/display/dc/dcn31/dcn31_hwseq.c    |  5 +++-
 3 files changed, 27 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index c545eddabdcc..dee1ce5f9609 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1502,25 +1502,22 @@ void dcn10_init_hw(struct dc *dc)
 void dcn10_power_down_on_boot(struct dc *dc)
 {
 	struct dc_link *edp_links[MAX_NUM_EDP];
-	struct dc_link *edp_link;
+	struct dc_link *edp_link = NULL;
 	int edp_num;
 	int i = 0;
 
 	get_edp_links(dc, edp_links, &edp_num);
-
-	if (edp_num) {
-		for (i = 0; i < edp_num; i++) {
-			edp_link = edp_links[i];
-			if (edp_link->link_enc->funcs->is_dig_enabled &&
-					edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) &&
-					dc->hwseq->funcs.edp_backlight_control &&
-					dc->hwss.power_down &&
-					dc->hwss.edp_power_control) {
-				dc->hwseq->funcs.edp_backlight_control(edp_link, false);
-				dc->hwss.power_down(dc);
-				dc->hwss.edp_power_control(edp_link, false);
-			}
-		}
+	if (edp_num)
+		edp_link = edp_links[0];
+
+	if (edp_link && edp_link->link_enc->funcs->is_dig_enabled &&
+			edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) &&
+			dc->hwseq->funcs.edp_backlight_control &&
+			dc->hwss.power_down &&
+			dc->hwss.edp_power_control) {
+		dc->hwseq->funcs.edp_backlight_control(edp_link, false);
+		dc->hwss.power_down(dc);
+		dc->hwss.edp_power_control(edp_link, false);
 	} else {
 		for (i = 0; i < dc->link_count; i++) {
 			struct dc_link *link = dc->links[i];
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index c68e3a708a33..2e8ab9775fa3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -580,22 +580,19 @@ void dcn30_init_hw(struct dc *dc)
 	 */
 	if (dc->config.power_down_display_on_boot) {
 		struct dc_link *edp_links[MAX_NUM_EDP];
-		struct dc_link *edp_link;
+		struct dc_link *edp_link = NULL;
 
 		get_edp_links(dc, edp_links, &edp_num);
-		if (edp_num) {
-			for (i = 0; i < edp_num; i++) {
-				edp_link = edp_links[i];
-				if (edp_link->link_enc->funcs->is_dig_enabled &&
-						edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) &&
-						dc->hwss.edp_backlight_control &&
-						dc->hwss.power_down &&
-						dc->hwss.edp_power_control) {
-					dc->hwss.edp_backlight_control(edp_link, false);
-					dc->hwss.power_down(dc);
-					dc->hwss.edp_power_control(edp_link, false);
-				}
-			}
+		if (edp_num)
+			edp_link = edp_links[0];
+		if (edp_link && edp_link->link_enc->funcs->is_dig_enabled &&
+				edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) &&
+				dc->hwss.edp_backlight_control &&
+				dc->hwss.power_down &&
+				dc->hwss.edp_power_control) {
+			dc->hwss.edp_backlight_control(edp_link, false);
+			dc->hwss.power_down(dc);
+			dc->hwss.edp_power_control(edp_link, false);
 		} else {
 			for (i = 0; i < dc->link_count; i++) {
 				struct dc_link *link = dc->links[i];
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 8a2119d8ca0d..8189606537c5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -226,6 +226,7 @@ void dcn31_init_hw(struct dc *dc)
 	if (dc->config.power_down_display_on_boot) {
 		struct dc_link *edp_links[MAX_NUM_EDP];
 		struct dc_link *edp_link;
+		bool power_down = false;
 
 		get_edp_links(dc, edp_links, &edp_num);
 		if (edp_num) {
@@ -239,9 +240,11 @@ void dcn31_init_hw(struct dc *dc)
 					dc->hwss.edp_backlight_control(edp_link, false);
 					dc->hwss.power_down(dc);
 					dc->hwss.edp_power_control(edp_link, false);
+					power_down = true;
 				}
 			}
-		} else {
+		}
+		if (!power_down) {
 			for (i = 0; i < dc->link_count; i++) {
 				struct dc_link *link = dc->links[i];
 
-- 
2.30.2

[PATCH AUTOSEL 5.14 062/252] drm/amdgpu: Fix a printing message

[Sasha Levin]

From: Oak Zeng <Oak.Zeng@amd.com>

[ Upstream commit 95f71f12aa45d65b7f2ccab95569795edffd379a ]

The printing message "PSP loading VCN firmware" is mis-leading because
people might think driver is loading VCN firmware. Actually when this
message is printed, driver is just preparing some VCN ucode, not loading
VCN firmware yet. The actual VCN firmware loading will be in the PSP block
hw_init. Fix the printing message

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Christian Konig <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 284bb42d6c86..121ee9f2b8d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -119,7 +119,7 @@ static int vcn_v1_0_sw_init(void *handle)
 		adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw;
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 8af567c546db..f4686e918e0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -122,7 +122,7 @@ static int vcn_v2_0_sw_init(void *handle)
 		adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw;
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 888b17d84691..e0c0c3734432 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -152,7 +152,7 @@ static int vcn_v2_5_sw_init(void *handle)
 			adev->firmware.fw_size +=
 				ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 		}
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 47d4f04cbd69..2f017560948e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -160,7 +160,7 @@ static int vcn_v3_0_sw_init(void *handle)
 			adev->firmware.fw_size +=
 				ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 		}
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
-- 
2.30.2

[PATCH AUTOSEL 5.14 063/252] drm/amd/amdgpu: Update debugfs link_settings output link_rate field in hex

[Sasha Levin]

From: Anson Jacob <Anson.Jacob@amd.com>

[ Upstream commit 1a394b3c3de2577f200cb623c52a5c2b82805cec ]

link_rate is updated via debugfs using hex values, set it to output
in hex as well.

eg: Resolution: 1920x1080@144Hz
cat /sys/kernel/debug/dri/0/DP-1/link_settings
Current:  4  0x14  0  Verified:  4  0x1e  0  Reported:  4  0x1e  16  Preferred:  0  0x0  0

echo "4 0x1e" > /sys/kernel/debug/dri/0/DP-1/link_settings

cat /sys/kernel/debug/dri/0/DP-1/link_settings
Current:  4  0x1e  0  Verified:  4  0x1e  0  Reported:  4  0x1e  16  Preferred:  4  0x1e  0

Signed-off-by: Anson Jacob <Anson.Jacob@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../amd/display/amdgpu_dm/amdgpu_dm_debugfs.c    | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index f1145086a468..1d15a9af9956 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -197,29 +197,29 @@ static ssize_t dp_link_settings_read(struct file *f, char __user *buf,
 
 	rd_buf_ptr = rd_buf;
 
-	str_len = strlen("Current:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Current:  %d  %d  %d  ",
+	str_len = strlen("Current:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Current:  %d  0x%x  %d  ",
 			link->cur_link_settings.lane_count,
 			link->cur_link_settings.link_rate,
 			link->cur_link_settings.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Verified:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Verified:  %d  %d  %d  ",
+	str_len = strlen("Verified:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Verified:  %d  0x%x  %d  ",
 			link->verified_link_cap.lane_count,
 			link->verified_link_cap.link_rate,
 			link->verified_link_cap.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Reported:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Reported:  %d  %d  %d  ",
+	str_len = strlen("Reported:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Reported:  %d  0x%x  %d  ",
 			link->reported_link_cap.lane_count,
 			link->reported_link_cap.link_rate,
 			link->reported_link_cap.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Preferred:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  %d  %d\n",
+	str_len = strlen("Preferred:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  0x%x  %d\n",
 			link->preferred_link_setting.lane_count,
 			link->preferred_link_setting.link_rate,
 			link->preferred_link_setting.link_spread);
-- 
2.30.2

[PATCH AUTOSEL 5.14 084/252] drm/amd/display: Fix PSR command version

[Sasha Levin]

From: Mikita Lipski <mikita.lipski@amd.com>

[ Upstream commit af1f2b19fd7d404d299355cc95930efee5b3ed8b ]

[why]
For dual eDP when setting the new settings we need to set
command version to DMUB_CMD_PSR_CONTROL_VERSION_1, otherwise
DMUB will not read panel_inst parameter.
[how]
Instead of PSR_VERSION_1 pass DMUB_CMD_PSR_CONTROL_VERSION_1

Reviewed-by: Wood Wyatt <Wyatt.Wood@amd.com>
Acked-by: Solomon Chiu <solomon.chiu@amd.com>
Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
index 10d42ae0cffe..3428334c6c57 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
@@ -207,7 +207,7 @@ static void dmub_psr_set_level(struct dmub_psr *dmub, uint16_t psr_level, uint8_
 	cmd.psr_set_level.header.sub_type = DMUB_CMD__PSR_SET_LEVEL;
 	cmd.psr_set_level.header.payload_bytes = sizeof(struct dmub_cmd_psr_set_level_data);
 	cmd.psr_set_level.psr_set_level_data.psr_level = psr_level;
-	cmd.psr_set_level.psr_set_level_data.cmd_version = PSR_VERSION_1;
+	cmd.psr_set_level.psr_set_level_data.cmd_version = DMUB_CMD_PSR_CONTROL_VERSION_1;
 	cmd.psr_set_level.psr_set_level_data.panel_inst = panel_inst;
 	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd);
 	dc_dmub_srv_cmd_execute(dc->dmub_srv);
@@ -293,7 +293,7 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub,
 	copy_settings_data->debug.bitfields.use_hw_lock_mgr		= 1;
 	copy_settings_data->fec_enable_status = (link->fec_state == dc_link_fec_enabled);
 	copy_settings_data->fec_enable_delay_in100us = link->dc->debug.fec_enable_delay_in100us;
-	copy_settings_data->cmd_version =  PSR_VERSION_1;
+	copy_settings_data->cmd_version =  DMUB_CMD_PSR_CONTROL_VERSION_1;
 	copy_settings_data->panel_inst = panel_inst;
 
 	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd);
-- 
2.30.2

[PATCH AUTOSEL 5.14 135/252] drm/amd/display: fix missing writeback disablement if plane is removed

[Sasha Levin]

From: Roy Chan <roy.chan@amd.com>

[ Upstream commit 82367e7f22d085092728f45fd5fbb15e3fb997c0 ]

[Why]
If the plane has been removed, the writeback disablement logic
doesn't run

[How]
fix the logic order

Acked-by: Anson Jacob <Anson.Jacob@amd.com>
Signed-off-by: Roy Chan <roy.chan@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 14 ++++++++------
 drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c | 12 +++++++++++-
 2 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 5c2853654cca..a47ba1d45be9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1723,13 +1723,15 @@ void dcn20_program_front_end_for_ctx(
 
 				pipe = pipe->bottom_pipe;
 			}
-			/* Program secondary blending tree and writeback pipes */
-			pipe = &context->res_ctx.pipe_ctx[i];
-			if (!pipe->prev_odm_pipe && pipe->stream->num_wb_info > 0
-					&& (pipe->update_flags.raw || pipe->plane_state->update_flags.raw || pipe->stream->update_flags.raw)
-					&& hws->funcs.program_all_writeback_pipes_in_tree)
-				hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
 		}
+		/* Program secondary blending tree and writeback pipes */
+		pipe = &context->res_ctx.pipe_ctx[i];
+		if (!pipe->top_pipe && !pipe->prev_odm_pipe
+				&& pipe->stream && pipe->stream->num_wb_info > 0
+				&& (pipe->update_flags.raw || (pipe->plane_state && pipe->plane_state->update_flags.raw)
+					|| pipe->stream->update_flags.raw)
+				&& hws->funcs.program_all_writeback_pipes_in_tree)
+			hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index 2e8ab9775fa3..fafed1e4a998 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -398,12 +398,22 @@ void dcn30_program_all_writeback_pipes_in_tree(
 			for (i_pipe = 0; i_pipe < dc->res_pool->pipe_count; i_pipe++) {
 				struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i_pipe];
 
+				if (!pipe_ctx->plane_state)
+					continue;
+
 				if (pipe_ctx->plane_state == wb_info.writeback_source_plane) {
 					wb_info.mpcc_inst = pipe_ctx->plane_res.mpcc_inst;
 					break;
 				}
 			}
-			ASSERT(wb_info.mpcc_inst != -1);
+
+			if (wb_info.mpcc_inst == -1) {
+				/* Disable writeback pipe and disconnect from MPCC
+				 * if source plane has been removed
+				 */
+				dc->hwss.disable_writeback(dc, wb_info.dwb_pipe_inst);
+				continue;
+			}
 
 			ASSERT(wb_info.dwb_pipe_inst < dc->res_pool->res_cap->num_dwb);
 			dwb = dc->res_pool->dwbc[wb_info.dwb_pipe_inst];
-- 
2.30.2

[PATCH AUTOSEL 5.14 136/252] drm/amd/display: fix incorrect CM/TF programming sequence in dwb

[Sasha Levin]

From: Roy Chan <roy.chan@amd.com>

[ Upstream commit 781e1e23131cce56fb557e6ec2260480a6bd08cc ]

[How]
the programming sequeune was for old asic.
the correct programming sequeunce should be similar to the one
used in mpc. the fix is copied from the mpc programming sequeunce.

Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Anson Jacob <Anson.Jacob@amd.com>
Signed-off-by: Roy Chan <roy.chan@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../drm/amd/display/dc/dcn30/dcn30_dwb_cm.c   | 90 +++++++++++++------
 1 file changed, 64 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c
index 3fe9e41e4dbd..6a3d3a0ec0a3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c
@@ -49,6 +49,11 @@
 static void dwb3_get_reg_field_ogam(struct dcn30_dwbc *dwbc30,
 	struct dcn3_xfer_func_reg *reg)
 {
+	reg->shifts.field_region_start_base = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_BASE_B;
+	reg->masks.field_region_start_base = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_START_BASE_B;
+	reg->shifts.field_offset = dwbc30->dwbc_shift->DWB_OGAM_RAMA_OFFSET_B;
+	reg->masks.field_offset = dwbc30->dwbc_mask->DWB_OGAM_RAMA_OFFSET_B;
+
 	reg->shifts.exp_region0_lut_offset = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION0_LUT_OFFSET;
 	reg->masks.exp_region0_lut_offset = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION0_LUT_OFFSET;
 	reg->shifts.exp_region0_num_segments = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION0_NUM_SEGMENTS;
@@ -66,8 +71,6 @@ static void dwb3_get_reg_field_ogam(struct dcn30_dwbc *dwbc30,
 	reg->masks.field_region_end_base = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_END_BASE_B;
 	reg->shifts.field_region_linear_slope = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_SLOPE_B;
 	reg->masks.field_region_linear_slope = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_START_SLOPE_B;
-	reg->masks.field_offset = dwbc30->dwbc_mask->DWB_OGAM_RAMA_OFFSET_B;
-	reg->shifts.field_offset = dwbc30->dwbc_shift->DWB_OGAM_RAMA_OFFSET_B;
 	reg->shifts.exp_region_start = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_B;
 	reg->masks.exp_region_start = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_START_B;
 	reg->shifts.exp_resion_start_segment = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_SEGMENT_B;
@@ -147,18 +150,19 @@ static enum dc_lut_mode dwb3_get_ogam_current(
 	uint32_t state_mode;
 	uint32_t ram_select;
 
-	REG_GET(DWB_OGAM_CONTROL,
-		DWB_OGAM_MODE, &state_mode);
-	REG_GET(DWB_OGAM_CONTROL,
-		DWB_OGAM_SELECT, &ram_select);
+	REG_GET_2(DWB_OGAM_CONTROL,
+		DWB_OGAM_MODE_CURRENT, &state_mode,
+		DWB_OGAM_SELECT_CURRENT, &ram_select);
 
 	if (state_mode == 0) {
 		mode = LUT_BYPASS;
 	} else if (state_mode == 2) {
 		if (ram_select == 0)
 			mode = LUT_RAM_A;
-		else
+		else if (ram_select == 1)
 			mode = LUT_RAM_B;
+		else
+			mode = LUT_BYPASS;
 	} else {
 		// Reserved value
 		mode = LUT_BYPASS;
@@ -172,10 +176,10 @@ static void dwb3_configure_ogam_lut(
 	struct dcn30_dwbc *dwbc30,
 	bool is_ram_a)
 {
-	REG_UPDATE(DWB_OGAM_LUT_CONTROL,
-		DWB_OGAM_LUT_READ_COLOR_SEL, 7);
-	REG_UPDATE(DWB_OGAM_CONTROL,
-		DWB_OGAM_SELECT, is_ram_a == true ? 0 : 1);
+	REG_UPDATE_2(DWB_OGAM_LUT_CONTROL,
+		DWB_OGAM_LUT_WRITE_COLOR_MASK, 7,
+		DWB_OGAM_LUT_HOST_SEL, (is_ram_a == true) ? 0 : 1);
+
 	REG_SET(DWB_OGAM_LUT_INDEX, 0, DWB_OGAM_LUT_INDEX, 0);
 }
 
@@ -185,17 +189,45 @@ static void dwb3_program_ogam_pwl(struct dcn30_dwbc *dwbc30,
 {
 	uint32_t i;
 
-    // triple base implementation
-	for (i = 0; i < num/2; i++) {
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+0].red_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+0].green_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+0].blue_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+1].red_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+1].green_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+1].blue_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+2].red_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+2].green_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+2].blue_reg);
+	uint32_t last_base_value_red = rgb[num-1].red_reg + rgb[num-1].delta_red_reg;
+	uint32_t last_base_value_green = rgb[num-1].green_reg + rgb[num-1].delta_green_reg;
+	uint32_t last_base_value_blue = rgb[num-1].blue_reg + rgb[num-1].delta_blue_reg;
+
+	if (is_rgb_equal(rgb,  num)) {
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].red_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_red);
+
+	} else {
+
+		REG_UPDATE(DWB_OGAM_LUT_CONTROL,
+				DWB_OGAM_LUT_WRITE_COLOR_MASK, 4);
+
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].red_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_red);
+
+		REG_SET(DWB_OGAM_LUT_INDEX, 0, DWB_OGAM_LUT_INDEX, 0);
+
+		REG_UPDATE(DWB_OGAM_LUT_CONTROL,
+				DWB_OGAM_LUT_WRITE_COLOR_MASK, 2);
+
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].green_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_green);
+
+		REG_SET(DWB_OGAM_LUT_INDEX, 0, DWB_OGAM_LUT_INDEX, 0);
+
+		REG_UPDATE(DWB_OGAM_LUT_CONTROL,
+				DWB_OGAM_LUT_WRITE_COLOR_MASK, 1);
+
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].blue_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_blue);
 	}
 }
 
@@ -211,6 +243,8 @@ static bool dwb3_program_ogam_lut(
 		return false;
 	}
 
+	REG_SET(DWB_OGAM_CONTROL, 0, DWB_OGAM_MODE, 2);
+
 	current_mode = dwb3_get_ogam_current(dwbc30);
 	if (current_mode == LUT_BYPASS || current_mode == LUT_RAM_A)
 		next_mode = LUT_RAM_B;
@@ -227,8 +261,7 @@ static bool dwb3_program_ogam_lut(
 	dwb3_program_ogam_pwl(
 		dwbc30, params->rgb_resulted, params->hw_points_num);
 
-	REG_SET(DWB_OGAM_CONTROL, 0, DWB_OGAM_MODE, 2);
-	REG_SET(DWB_OGAM_CONTROL, 0, DWB_OGAM_SELECT, next_mode == LUT_RAM_A ? 0 : 1);
+	REG_UPDATE(DWB_OGAM_CONTROL, DWB_OGAM_SELECT, next_mode == LUT_RAM_A ? 0 : 1);
 
 	return true;
 }
@@ -271,14 +304,19 @@ static void dwb3_program_gamut_remap(
 
 	struct color_matrices_reg gam_regs;
 
-	REG_UPDATE(DWB_GAMUT_REMAP_COEF_FORMAT, DWB_GAMUT_REMAP_COEF_FORMAT, coef_format);
-
 	if (regval == NULL || select == CM_GAMUT_REMAP_MODE_BYPASS) {
 		REG_SET(DWB_GAMUT_REMAP_MODE, 0,
 				DWB_GAMUT_REMAP_MODE, 0);
 		return;
 	}
 
+	REG_UPDATE(DWB_GAMUT_REMAP_COEF_FORMAT, DWB_GAMUT_REMAP_COEF_FORMAT, coef_format);
+
+	gam_regs.shifts.csc_c11 = dwbc30->dwbc_shift->DWB_GAMUT_REMAPA_C11;
+	gam_regs.masks.csc_c11  = dwbc30->dwbc_mask->DWB_GAMUT_REMAPA_C11;
+	gam_regs.shifts.csc_c12 = dwbc30->dwbc_shift->DWB_GAMUT_REMAPA_C12;
+	gam_regs.masks.csc_c12 = dwbc30->dwbc_mask->DWB_GAMUT_REMAPA_C12;
+
 	switch (select) {
 	case CM_GAMUT_REMAP_MODE_RAMA_COEFF:
 		gam_regs.csc_c11_c12 = REG(DWB_GAMUT_REMAPA_C11_C12);
-- 
2.30.2

[PATCH AUTOSEL 5.14 147/252] gpu: drm: amd: amdgpu: amdgpu_i2c: fix possible uninitialized-variable access in amdgpu_i2c_router_select_ddc_port()

[Sasha Levin]

From: Tuo Li <islituo@gmail.com>

[ Upstream commit a211260c34cfadc6068fece8c9e99e0fe1e2a2b6 ]

The variable val is declared without initialization, and its address is
passed to amdgpu_i2c_get_byte(). In this function, the value of val is
accessed in:
  DRM_DEBUG("i2c 0x%02x 0x%02x read failed\n",
       addr, *val);

Also, when amdgpu_i2c_get_byte() returns, val may remain uninitialized,
but it is accessed in:
  val &= ~amdgpu_connector->router.ddc_mux_control_pin;

To fix this possible uninitialized-variable access, initialize val to 0 in
amdgpu_i2c_router_select_ddc_port().

Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Tuo Li <islituo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
index bca4dddd5a15..82608df43396 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
@@ -339,7 +339,7 @@ static void amdgpu_i2c_put_byte(struct amdgpu_i2c_chan *i2c_bus,
 void
 amdgpu_i2c_router_select_ddc_port(const struct amdgpu_connector *amdgpu_connector)
 {
-	u8 val;
+	u8 val = 0;
 
 	if (!amdgpu_connector->router.ddc_valid)
 		return;
-- 
2.30.2

[PATCH AUTOSEL 5.14 148/252] drm/display: fix possible null-pointer dereference in dcn10_set_clock()

[Sasha Levin]

From: Tuo Li <islituo@gmail.com>

[ Upstream commit 554594567b1fa3da74f88ec7b2dc83d000c58e98 ]

The variable dc->clk_mgr is checked in:
  if (dc->clk_mgr && dc->clk_mgr->funcs->get_clock)

This indicates dc->clk_mgr can be NULL.
However, it is dereferenced in:
    if (!dc->clk_mgr->funcs->get_clock)

To fix this null-pointer dereference, check dc->clk_mgr and the function
pointer dc->clk_mgr->funcs->get_clock earlier, and return if one of them
is NULL.

Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Tuo Li <islituo@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index dee1ce5f9609..75fa4adcf5f4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -3628,13 +3628,12 @@ enum dc_status dcn10_set_clock(struct dc *dc,
 	struct dc_clock_config clock_cfg = {0};
 	struct dc_clocks *current_clocks = &context->bw_ctx.bw.dcn.clk;
 
-	if (dc->clk_mgr && dc->clk_mgr->funcs->get_clock)
-				dc->clk_mgr->funcs->get_clock(dc->clk_mgr,
-						context, clock_type, &clock_cfg);
-
-	if (!dc->clk_mgr->funcs->get_clock)
+	if (!dc->clk_mgr || !dc->clk_mgr->funcs->get_clock)
 		return DC_FAIL_UNSUPPORTED_1;
 
+	dc->clk_mgr->funcs->get_clock(dc->clk_mgr,
+		context, clock_type, &clock_cfg);
+
 	if (clk_khz > clock_cfg.max_clock_khz)
 		return DC_FAIL_CLK_EXCEED_MAX;
 
@@ -3652,7 +3651,7 @@ enum dc_status dcn10_set_clock(struct dc *dc,
 	else
 		return DC_ERROR_UNEXPECTED;
 
-	if (dc->clk_mgr && dc->clk_mgr->funcs->update_clocks)
+	if (dc->clk_mgr->funcs->update_clocks)
 				dc->clk_mgr->funcs->update_clocks(dc->clk_mgr,
 				context, true);
 	return DC_OK;
-- 
2.30.2

[PATCH AUTOSEL 5.14 225/252] drm/amdkfd: Account for SH/SE count when setting up cu masks.

[Sasha Levin]

From: Sean Keely <Sean.Keely@amd.com>

[ Upstream commit 1ec06c2dee679e9f089e78ed20cb74ee90155f61 ]

On systems with multiple SH per SE compute_static_thread_mgmt_se#
is split into independent masks, one for each SH, in the upper and
lower 16 bits.  We need to detect this and apply cu masking to each
SH.  The cu mask bits are assigned first to each SE, then to
alternate SHs, then finally to higher CU id.  This ensures that
the maximum number of SPIs are engaged as early as possible while
balancing CU assignment to each SH.

v2: Use max SH/SE rather than max SH in cu_per_sh.

v3: Fix comment blocks, ensure se_mask is initially zero filled,
    and correctly assign se.sh.cu positions to unset bits in cu_mask.

Signed-off-by: Sean Keely <Sean.Keely@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c | 84 +++++++++++++++-----
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h |  1 +
 2 files changed, 64 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index 88813dad731f..c021519af810 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -98,36 +98,78 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 		uint32_t *se_mask)
 {
 	struct kfd_cu_info cu_info;
-	uint32_t cu_per_se[KFD_MAX_NUM_SE] = {0};
-	int i, se, sh, cu = 0;
-
+	uint32_t cu_per_sh[KFD_MAX_NUM_SE][KFD_MAX_NUM_SH_PER_SE] = {0};
+	int i, se, sh, cu;
 	amdgpu_amdkfd_get_cu_info(mm->dev->kgd, &cu_info);
 
 	if (cu_mask_count > cu_info.cu_active_number)
 		cu_mask_count = cu_info.cu_active_number;
 
+	/* Exceeding these bounds corrupts the stack and indicates a coding error.
+	 * Returning with no CU's enabled will hang the queue, which should be
+	 * attention grabbing.
+	 */
+	if (cu_info.num_shader_engines > KFD_MAX_NUM_SE) {
+		pr_err("Exceeded KFD_MAX_NUM_SE, chip reports %d\n", cu_info.num_shader_engines);
+		return;
+	}
+	if (cu_info.num_shader_arrays_per_engine > KFD_MAX_NUM_SH_PER_SE) {
+		pr_err("Exceeded KFD_MAX_NUM_SH, chip reports %d\n",
+			cu_info.num_shader_arrays_per_engine * cu_info.num_shader_engines);
+		return;
+	}
+	/* Count active CUs per SH.
+	 *
+	 * Some CUs in an SH may be disabled.	HW expects disabled CUs to be
+	 * represented in the high bits of each SH's enable mask (the upper and lower
+	 * 16 bits of se_mask) and will take care of the actual distribution of
+	 * disabled CUs within each SH automatically.
+	 * Each half of se_mask must be filled only on bits 0-cu_per_sh[se][sh]-1.
+	 *
+	 * See note on Arcturus cu_bitmap layout in gfx_v9_0_get_cu_info.
+	 */
 	for (se = 0; se < cu_info.num_shader_engines; se++)
 		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++)
-			cu_per_se[se] += hweight32(cu_info.cu_bitmap[se % 4][sh + (se / 4)]);
-
-	/* Symmetrically map cu_mask to all SEs:
-	 * cu_mask[0] bit0 -> se_mask[0] bit0;
-	 * cu_mask[0] bit1 -> se_mask[1] bit0;
-	 * ... (if # SE is 4)
-	 * cu_mask[0] bit4 -> se_mask[0] bit1;
+			cu_per_sh[se][sh] = hweight32(cu_info.cu_bitmap[se % 4][sh + (se / 4)]);
+
+	/* Symmetrically map cu_mask to all SEs & SHs:
+	 * se_mask programs up to 2 SH in the upper and lower 16 bits.
+	 *
+	 * Examples
+	 * Assuming 1 SH/SE, 4 SEs:
+	 * cu_mask[0] bit0 -> se_mask[0] bit0
+	 * cu_mask[0] bit1 -> se_mask[1] bit0
+	 * ...
+	 * cu_mask[0] bit4 -> se_mask[0] bit1
+	 * ...
+	 *
+	 * Assuming 2 SH/SE, 4 SEs
+	 * cu_mask[0] bit0 -> se_mask[0] bit0 (SE0,SH0,CU0)
+	 * cu_mask[0] bit1 -> se_mask[1] bit0 (SE1,SH0,CU0)
+	 * ...
+	 * cu_mask[0] bit4 -> se_mask[0] bit16 (SE0,SH1,CU0)
+	 * cu_mask[0] bit5 -> se_mask[1] bit16 (SE1,SH1,CU0)
+	 * ...
+	 * cu_mask[0] bit8 -> se_mask[0] bit1 (SE0,SH0,CU1)
 	 * ...
+	 *
+	 * First ensure all CUs are disabled, then enable user specified CUs.
 	 */
-	se = 0;
-	for (i = 0; i < cu_mask_count; i++) {
-		if (cu_mask[i / 32] & (1 << (i % 32)))
-			se_mask[se] |= 1 << cu;
-
-		do {
-			se++;
-			if (se == cu_info.num_shader_engines) {
-				se = 0;
-				cu++;
+	for (i = 0; i < cu_info.num_shader_engines; i++)
+		se_mask[i] = 0;
+
+	i = 0;
+	for (cu = 0; cu < 16; cu++) {
+		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] & (1 << (i % 32)))
+						se_mask[se] |= 1 << (cu + sh * 16);
+					i++;
+					if (i == cu_mask_count)
+						return;
+				}
 			}
-		} while (cu >= cu_per_se[se] && cu < 32);
+		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index b5e2ea7550d4..6e6918ccedfd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -27,6 +27,7 @@
 #include "kfd_priv.h"
 
 #define KFD_MAX_NUM_SE 8
+#define KFD_MAX_NUM_SH_PER_SE 2
 
 /**
  * struct mqd_manager
-- 
2.30.2