[PATCH v2 0/3] drm: detect panel type from DisplayID 2.x

[PATCH v2 0/3] drm: detect panel type from DisplayID 2.x

[Chenyu Chen]

This series adds parsing of the Display Device Technology field from
the DisplayID v2.x Display Parameters Data Block (tag 0x21), enabling
panel type detection (LCD/OLED) through a standards-based source.

Previously, amdgpu_dm determined panel type only from AMD VSDB, DPCD
sink extended caps, and a Samsung luminance heuristic. A TODO comment
in dm_set_panel_type() acknowledged the need to also use DisplayID as
a source. This series resolves that by parsing the Display Parameters
block in DRM core and wiring it into amdgpu_dm's detection priority
chain as: VSDB > DPCD > DisplayID > Samsung heuristic.

Patch 1 extracts the section header processing into a helper and
removes the break so the iterator can walk through all data blocks.
The helper is invoked only once via a header_processed flag because
displayid_version() and displayid_primary_use() always return values
captured from the base section — they are fixed regardless of which
extension section the iterator is currently in, so processing the
header more than once would be redundant.

Chenyu Chen (3):
  drm/edid: extract section header processing into helper
  drm/edid: parse panel type from DisplayID 2.x Display Parameters
  drm/amd/display: use DisplayID panel type in dm_set_panel_type

 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 +--
 drivers/gpu/drm/drm_displayid_internal.h      | 25 ++++++
 drivers/gpu/drm/drm_edid.c                    | 79 +++++++++++++++----
 include/drm/drm_connector.h                   |  6 ++
 include/uapi/drm/drm_mode.h                   |  1 +
 5 files changed, 103 insertions(+), 20 deletions(-)

-- 
2.43.0

[PATCH v2 1/3] drm/edid: extract section header processing into helper

[Chenyu Chen]

Extract the DisplayID section header logging and non_desktop
detection from update_displayid_info() into a dedicated helper,
drm_displayid_process_section_header(). Remove the break so the
iterator walks through all data blocks, preparing for future
patches that will parse additional block types within the loop.

The helper is called only once for the base section via a
header_processed flag. Since version and primary_use are only
captured from the base section, and extension sections carry a
primary use of zero per spec, the non_desktop logic is unaffected.

No functional change.

Assisted-by: Copilot:Claude-Opus-4.6
Signed-off-by: Chenyu Chen <chen-yu.chen@amd.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
---
 drivers/gpu/drm/drm_edid.c | 37 +++++++++++++++++++++----------------
 1 file changed, 21 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 8031f021d4d0..04878478ab78 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -6715,30 +6715,35 @@ static void drm_reset_display_info(struct drm_connector *connector)
 	memset(&info->amd_vsdb, 0, sizeof(info->amd_vsdb));
 }
 
+static void drm_displayid_process_section_header(struct drm_connector *connector,
+				  const struct displayid_iter *iter)
+{
+	struct drm_display_info *info = &connector->display_info;
+
+	drm_dbg_kms(connector->dev,
+			"[CONNECTOR:%d:%s] DisplayID extension version 0x%02x, primary use 0x%02x\n",
+			connector->base.id, connector->name,
+			displayid_version(iter),
+			displayid_primary_use(iter));
+	if (displayid_version(iter) == DISPLAY_ID_STRUCTURE_VER_20 &&
+		(displayid_primary_use(iter) == PRIMARY_USE_HEAD_MOUNTED_VR ||
+			displayid_primary_use(iter) == PRIMARY_USE_HEAD_MOUNTED_AR))
+		info->non_desktop = true;
+}
+
 static void update_displayid_info(struct drm_connector *connector,
 				  const struct drm_edid *drm_edid)
 {
-	struct drm_display_info *info = &connector->display_info;
 	const struct displayid_block *block;
 	struct displayid_iter iter;
+	bool header_processed = false;
 
 	displayid_iter_edid_begin(drm_edid, &iter);
 	displayid_iter_for_each(block, &iter) {
-		drm_dbg_kms(connector->dev,
-			    "[CONNECTOR:%d:%s] DisplayID extension version 0x%02x, primary use 0x%02x\n",
-			    connector->base.id, connector->name,
-			    displayid_version(&iter),
-			    displayid_primary_use(&iter));
-		if (displayid_version(&iter) == DISPLAY_ID_STRUCTURE_VER_20 &&
-		    (displayid_primary_use(&iter) == PRIMARY_USE_HEAD_MOUNTED_VR ||
-		     displayid_primary_use(&iter) == PRIMARY_USE_HEAD_MOUNTED_AR))
-			info->non_desktop = true;
-
-		/*
-		 * We're only interested in the base section here, no need to
-		 * iterate further.
-		 */
-		break;
+		if (!header_processed) {
+			drm_displayid_process_section_header(connector, &iter);
+			header_processed = true;
+		}
 	}
 	displayid_iter_end(&iter);
 }
-- 
2.43.0

[PATCH v2 2/3] drm/edid: parse panel type from DisplayID 2.x Display Parameters

[Chenyu Chen]

Parse the Display Parameters Data Block (tag 0x21) defined in
DisplayID v2.1a Section 4.2.6. Extract the Display Device Technology
field from payload byte 27 bits [6:4], which indicates whether the
panel uses LCD (001b) or OLED (010b) technology.

Add a did_panel_type field to struct drm_display_info and populate it
during DisplayID iteration so downstream drivers can use it for
panel-type-dependent behavior. Add DRM_MODE_PANEL_TYPE_LCD to the
UAPI constants for use as an internal communication value between
DRM core and drivers.

Assisted-by: Copilot:Claude-Opus-4.6
Signed-off-by: Chenyu Chen <chen-yu.chen@amd.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
---
 drivers/gpu/drm/drm_displayid_internal.h | 25 ++++++++++++++
 drivers/gpu/drm/drm_edid.c               | 44 ++++++++++++++++++++++++
 include/drm/drm_connector.h              |  6 ++++
 include/uapi/drm/drm_mode.h              |  1 +
 4 files changed, 76 insertions(+)

diff --git a/drivers/gpu/drm/drm_displayid_internal.h b/drivers/gpu/drm/drm_displayid_internal.h
index 5b1b32f73516..e0f7c54d2987 100644
--- a/drivers/gpu/drm/drm_displayid_internal.h
+++ b/drivers/gpu/drm/drm_displayid_internal.h
@@ -142,6 +142,31 @@ struct displayid_formula_timing_block {
 	struct displayid_formula_timings_9 timings[];
 } __packed;
 
+/*
+ * DisplayID v2.x Display Parameters Data Block (tag 0x21).
+ *
+ * Per VESA DisplayID v2.1a, Section 4.2.6, Table 4-14:
+ * Offset 0x1E (payload byte 27) contains Native Color Depth and
+ * Display Device Technology fields.
+ *   bits [2:0] = Native Color Depth
+ *   bit  [3]   = RESERVED
+ *   bits [6:4] = Display Device Technology
+ *     000b = not specified, 001b = LCD, 010b = OLED, others reserved
+ *   bit  [7]   = Display Device Theme Preference
+ */
+#define DISPLAYID_DISPLAY_PARAMS_DEVICE_TECH	GENMASK(6, 4)
+
+struct displayid_display_params_block {
+	struct displayid_block base;
+	u8 payload[27];
+	u8 device_tech_byte; /* bits [6:4] = Display Device Technology */
+	u8 reserved;
+} __packed;
+
+#define DISPLAYID_DISPLAY_PARAMS_MIN_LEN	\
+	(sizeof(struct displayid_display_params_block) -	\
+	 sizeof(struct displayid_block))
+
 #define DISPLAYID_VESA_MSO_OVERLAP	GENMASK(3, 0)
 #define DISPLAYID_VESA_MSO_MODE		GENMASK(6, 5)
 
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 04878478ab78..d1de1a398677 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -6713,6 +6713,8 @@ static void drm_reset_display_info(struct drm_connector *connector)
 
 	info->source_physical_address = CEC_PHYS_ADDR_INVALID;
 	memset(&info->amd_vsdb, 0, sizeof(info->amd_vsdb));
+
+	info->did_panel_type = DRM_MODE_PANEL_TYPE_UNKNOWN;
 }
 
 static void drm_displayid_process_section_header(struct drm_connector *connector,
@@ -6731,6 +6733,44 @@ static void drm_displayid_process_section_header(struct drm_connector *connector
 		info->non_desktop = true;
 }
 
+static void
+drm_displayid_parse_display_params(struct drm_connector *connector,
+				   const struct displayid_block *block)
+{
+	struct drm_display_info *info = &connector->display_info;
+	const struct displayid_display_params_block *params =
+		(const struct displayid_display_params_block *)block;
+
+	u8 tech;
+
+	if (block->num_bytes < DISPLAYID_DISPLAY_PARAMS_MIN_LEN) {
+		drm_dbg_kms(connector->dev,
+			    "[CONNECTOR:%d:%s] DisplayID Display Parameters block too short (%u < %zu)\n",
+			    connector->base.id, connector->name,
+			    block->num_bytes,
+			    DISPLAYID_DISPLAY_PARAMS_MIN_LEN);
+		return;
+	}
+
+	tech = FIELD_GET(DISPLAYID_DISPLAY_PARAMS_DEVICE_TECH,
+			 params->device_tech_byte);
+
+	drm_dbg_kms(connector->dev,
+		    "[CONNECTOR:%d:%s] DisplayID Display Parameters: device technology %u\n",
+		    connector->base.id, connector->name, tech);
+
+	switch (tech) {
+	case 1: /* LCD */
+		info->did_panel_type = DRM_MODE_PANEL_TYPE_LCD;
+		break;
+	case 2: /* OLED */
+		info->did_panel_type = DRM_MODE_PANEL_TYPE_OLED;
+		break;
+	default:
+		break;
+	}
+}
+
 static void update_displayid_info(struct drm_connector *connector,
 				  const struct drm_edid *drm_edid)
 {
@@ -6744,6 +6784,10 @@ static void update_displayid_info(struct drm_connector *connector,
 			drm_displayid_process_section_header(connector, &iter);
 			header_processed = true;
 		}
+
+		if (displayid_version(&iter) == DISPLAY_ID_STRUCTURE_VER_20 &&
+		    block->tag == DATA_BLOCK_2_DISPLAY_PARAMETERS)
+			drm_displayid_parse_display_params(connector, block);
 	}
 	displayid_iter_end(&iter);
 }
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index c398dbc68bbc..b95aec34ddb7 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -899,6 +899,12 @@ struct drm_display_info {
 	 * @amd_vsdb: AMD-specific VSDB information.
 	 */
 	struct drm_amd_vsdb_info amd_vsdb;
+
+	/**
+	 * @did_panel_type: Panel type from DisplayID Display Parameters
+	 * Data Block (tag 0x21). Uses DRM_MODE_PANEL_TYPE_* constants.
+	 */
+	u8 did_panel_type;
 };
 
 int drm_display_info_set_bus_formats(struct drm_display_info *info,
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 3693d82b5279..d7ca1040b92e 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -169,6 +169,7 @@ extern "C" {
 /* Panel type property */
 #define DRM_MODE_PANEL_TYPE_UNKNOWN	0
 #define DRM_MODE_PANEL_TYPE_OLED	1
+#define DRM_MODE_PANEL_TYPE_LCD		2
 
 /*
  * DRM_MODE_ROTATE_<degrees>
-- 
2.43.0

[PATCH v2 3/3] drm/amd/display: use DisplayID panel type in dm_set_panel_type

[Chenyu Chen]

Wire up the newly parsed did_panel_type from drm_display_info into
amdgpu_dm's panel type detection path. When neither the AMD VSDB
nor DPCD determines the panel type, fall back to the DisplayID
Display Device Technology field to set PANEL_TYPE_LCD or
PANEL_TYPE_OLED accordingly.

Assisted-by: Copilot:Claude-Opus-4.6
Signed-off-by: Chenyu Chen <chen-yu.chen@amd.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

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 e42a5eecdf46..353a4982333d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3944,11 +3944,13 @@ static void dm_set_panel_type(struct amdgpu_dm_connector *aconnector)
 			link->panel_type = PANEL_TYPE_OLED;
 	}
 
-	/*
-	 * TODO: get panel type from DID2 that has device technology field
-	 * to specify if it's OLED or not. But we need to wait for DID2
-	 * support in DC and EDID parser to be able to use it here.
-	 */
+	/* If VSDB and DPCD didn't determine panel type, check DID */
+	if (link->panel_type == PANEL_TYPE_NONE) {
+		if (display_info->did_panel_type == DRM_MODE_PANEL_TYPE_LCD)
+			link->panel_type = PANEL_TYPE_LCD;
+		else if (display_info->did_panel_type == DRM_MODE_PANEL_TYPE_OLED)
+			link->panel_type = PANEL_TYPE_OLED;
+	}
 
 	if (link->panel_type == PANEL_TYPE_NONE) {
 		struct drm_amd_vsdb_info *vsdb = &display_info->amd_vsdb;
-- 
2.43.0

Re: [PATCH v2 1/3] drm/edid: extract section header processing into helper

[Jani Nikula]

On Wed, 20 May 2026, Chenyu Chen <chen-yu.chen@amd.com> wrote:
> Extract the DisplayID section header logging and non_desktop
> detection from update_displayid_info() into a dedicated helper,
> drm_displayid_process_section_header(). Remove the break so the
> iterator walks through all data blocks, preparing for future
> patches that will parse additional block types within the loop.
>
> The helper is called only once for the base section via a
> header_processed flag. Since version and primary_use are only
> captured from the base section, and extension sections carry a
> primary use of zero per spec, the non_desktop logic is unaffected.
>
> No functional change.
>
> Assisted-by: Copilot:Claude-Opus-4.6
> Signed-off-by: Chenyu Chen <chen-yu.chen@amd.com>
> Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
> ---
>  drivers/gpu/drm/drm_edid.c | 37 +++++++++++++++++++++----------------
>  1 file changed, 21 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
> index 8031f021d4d0..04878478ab78 100644
> --- a/drivers/gpu/drm/drm_edid.c
> +++ b/drivers/gpu/drm/drm_edid.c
> @@ -6715,30 +6715,35 @@ static void drm_reset_display_info(struct drm_connector *connector)
>  	memset(&info->amd_vsdb, 0, sizeof(info->amd_vsdb));
>  }
>  
> +static void drm_displayid_process_section_header(struct drm_connector *connector,
> +				  const struct displayid_iter *iter)

The name's a bit grandiose, yet loses the bit about "base section" which
was the crucial part in the comment that gets removed below.

> +{
> +	struct drm_display_info *info = &connector->display_info;
> +
> +	drm_dbg_kms(connector->dev,
> +			"[CONNECTOR:%d:%s] DisplayID extension version 0x%02x, primary use 0x%02x\n",
> +			connector->base.id, connector->name,
> +			displayid_version(iter),
> +			displayid_primary_use(iter));
> +	if (displayid_version(iter) == DISPLAY_ID_STRUCTURE_VER_20 &&
> +		(displayid_primary_use(iter) == PRIMARY_USE_HEAD_MOUNTED_VR ||
> +			displayid_primary_use(iter) == PRIMARY_USE_HEAD_MOUNTED_AR))
> +		info->non_desktop = true;
> +}

The indent is all wrong in this function.

> +
>  static void update_displayid_info(struct drm_connector *connector,
>  				  const struct drm_edid *drm_edid)
>  {
> -	struct drm_display_info *info = &connector->display_info;
>  	const struct displayid_block *block;
>  	struct displayid_iter iter;
> +	bool header_processed = false;
>  
>  	displayid_iter_edid_begin(drm_edid, &iter);
>  	displayid_iter_for_each(block, &iter) {
> -		drm_dbg_kms(connector->dev,
> -			    "[CONNECTOR:%d:%s] DisplayID extension version 0x%02x, primary use 0x%02x\n",
> -			    connector->base.id, connector->name,
> -			    displayid_version(&iter),
> -			    displayid_primary_use(&iter));
> -		if (displayid_version(&iter) == DISPLAY_ID_STRUCTURE_VER_20 &&
> -		    (displayid_primary_use(&iter) == PRIMARY_USE_HEAD_MOUNTED_VR ||
> -		     displayid_primary_use(&iter) == PRIMARY_USE_HEAD_MOUNTED_AR))
> -			info->non_desktop = true;
> -
> -		/*
> -		 * We're only interested in the base section here, no need to
> -		 * iterate further.
> -		 */
> -		break;
> +		if (!header_processed) {
> +			drm_displayid_process_section_header(connector, &iter);
> +			header_processed = true;

Every DisplayID Section has a header. Every DisplayID Data Block within
a DisplayID Section has a header. This is about handling the information
in the Base Section header only. IMO header_processed is misleading.

BR,
Jani.

> +		}
>  	}
>  	displayid_iter_end(&iter);
>  }

-- 
Jani Nikula, Intel

Re: [PATCH v2 2/3] drm/edid: parse panel type from DisplayID 2.x Display Parameters

[Jani Nikula]

On Wed, 20 May 2026, Chenyu Chen <chen-yu.chen@amd.com> wrote:
> Parse the Display Parameters Data Block (tag 0x21) defined in
> DisplayID v2.1a Section 4.2.6. Extract the Display Device Technology
> field from payload byte 27 bits [6:4], which indicates whether the
> panel uses LCD (001b) or OLED (010b) technology.
>
> Add a did_panel_type field to struct drm_display_info and populate it
> during DisplayID iteration so downstream drivers can use it for
> panel-type-dependent behavior. Add DRM_MODE_PANEL_TYPE_LCD to the
> UAPI constants for use as an internal communication value between
> DRM core and drivers.
>
> Assisted-by: Copilot:Claude-Opus-4.6
> Signed-off-by: Chenyu Chen <chen-yu.chen@amd.com>
> Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
> ---
>  drivers/gpu/drm/drm_displayid_internal.h | 25 ++++++++++++++
>  drivers/gpu/drm/drm_edid.c               | 44 ++++++++++++++++++++++++
>  include/drm/drm_connector.h              |  6 ++++
>  include/uapi/drm/drm_mode.h              |  1 +
>  4 files changed, 76 insertions(+)
>
> diff --git a/drivers/gpu/drm/drm_displayid_internal.h b/drivers/gpu/drm/drm_displayid_internal.h
> index 5b1b32f73516..e0f7c54d2987 100644
> --- a/drivers/gpu/drm/drm_displayid_internal.h
> +++ b/drivers/gpu/drm/drm_displayid_internal.h
> @@ -142,6 +142,31 @@ struct displayid_formula_timing_block {
>  	struct displayid_formula_timings_9 timings[];
>  } __packed;
>  
> +/*
> + * DisplayID v2.x Display Parameters Data Block (tag 0x21).
> + *
> + * Per VESA DisplayID v2.1a, Section 4.2.6, Table 4-14:
> + * Offset 0x1E (payload byte 27) contains Native Color Depth and
> + * Display Device Technology fields.
> + *   bits [2:0] = Native Color Depth
> + *   bit  [3]   = RESERVED
> + *   bits [6:4] = Display Device Technology
> + *     000b = not specified, 001b = LCD, 010b = OLED, others reserved
> + *   bit  [7]   = Display Device Theme Preference
> + */

Please drop the comment...

> +#define DISPLAYID_DISPLAY_PARAMS_DEVICE_TECH	GENMASK(6, 4)
> +
> +struct displayid_display_params_block {
> +	struct displayid_block base;
> +	u8 payload[27];
> +	u8 device_tech_byte; /* bits [6:4] = Display Device Technology */
> +	u8 reserved;

...and actually define the information here.

Sure, you're only interested in one thing, but don't leave the rest for
someone who comes after you, since you clearly have access to the spec,
and whoever reviews this also needs to have access to the spec.

> +} __packed;
> +
> +#define DISPLAYID_DISPLAY_PARAMS_MIN_LEN	\
> +	(sizeof(struct displayid_display_params_block) -	\
> +	 sizeof(struct displayid_block))

Is this helpful? Do you suggest we should add the define for all of the
blocks? What about when there's a minimum, and you can optionally have
more?

> +
>  #define DISPLAYID_VESA_MSO_OVERLAP	GENMASK(3, 0)
>  #define DISPLAYID_VESA_MSO_MODE		GENMASK(6, 5)
>  
> diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
> index 04878478ab78..d1de1a398677 100644
> --- a/drivers/gpu/drm/drm_edid.c
> +++ b/drivers/gpu/drm/drm_edid.c
> @@ -6713,6 +6713,8 @@ static void drm_reset_display_info(struct drm_connector *connector)
>  
>  	info->source_physical_address = CEC_PHYS_ADDR_INVALID;
>  	memset(&info->amd_vsdb, 0, sizeof(info->amd_vsdb));
> +
> +	info->did_panel_type = DRM_MODE_PANEL_TYPE_UNKNOWN;
>  }
>  
>  static void drm_displayid_process_section_header(struct drm_connector *connector,
> @@ -6731,6 +6733,44 @@ static void drm_displayid_process_section_header(struct drm_connector *connector
>  		info->non_desktop = true;
>  }
>  
> +static void
> +drm_displayid_parse_display_params(struct drm_connector *connector,
> +				   const struct displayid_block *block)
> +{
> +	struct drm_display_info *info = &connector->display_info;
> +	const struct displayid_display_params_block *params =
> +		(const struct displayid_display_params_block *)block;
> +

Superfluous blank line.

> +	u8 tech;
> +
> +	if (block->num_bytes < DISPLAYID_DISPLAY_PARAMS_MIN_LEN) {
> +		drm_dbg_kms(connector->dev,
> +			    "[CONNECTOR:%d:%s] DisplayID Display Parameters block too short (%u < %zu)\n",
> +			    connector->base.id, connector->name,
> +			    block->num_bytes,
> +			    DISPLAYID_DISPLAY_PARAMS_MIN_LEN);
> +		return;
> +	}
> +
> +	tech = FIELD_GET(DISPLAYID_DISPLAY_PARAMS_DEVICE_TECH,
> +			 params->device_tech_byte);
> +
> +	drm_dbg_kms(connector->dev,
> +		    "[CONNECTOR:%d:%s] DisplayID Display Parameters: device technology %u\n",
> +		    connector->base.id, connector->name, tech);

It would be more useful to print LCD or OLED, not the number.

> +
> +	switch (tech) {
> +	case 1: /* LCD */
> +		info->did_panel_type = DRM_MODE_PANEL_TYPE_LCD;
> +		break;
> +	case 2: /* OLED */

The comments above are useless.

> +		info->did_panel_type = DRM_MODE_PANEL_TYPE_OLED;
> +		break;
> +	default:
> +		break;
> +	}
> +}
> +
>  static void update_displayid_info(struct drm_connector *connector,
>  				  const struct drm_edid *drm_edid)
>  {
> @@ -6744,6 +6784,10 @@ static void update_displayid_info(struct drm_connector *connector,
>  			drm_displayid_process_section_header(connector, &iter);
>  			header_processed = true;
>  		}
> +
> +		if (displayid_version(&iter) == DISPLAY_ID_STRUCTURE_VER_20 &&
> +		    block->tag == DATA_BLOCK_2_DISPLAY_PARAMETERS)
> +			drm_displayid_parse_display_params(connector, block);
>  	}
>  	displayid_iter_end(&iter);
>  }
> diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
> index c398dbc68bbc..b95aec34ddb7 100644
> --- a/include/drm/drm_connector.h
> +++ b/include/drm/drm_connector.h
> @@ -899,6 +899,12 @@ struct drm_display_info {
>  	 * @amd_vsdb: AMD-specific VSDB information.
>  	 */
>  	struct drm_amd_vsdb_info amd_vsdb;
> +
> +	/**
> +	 * @did_panel_type: Panel type from DisplayID Display Parameters
> +	 * Data Block (tag 0x21). Uses DRM_MODE_PANEL_TYPE_* constants.
> +	 */
> +	u8 did_panel_type;

What does the did_ prefix give us?

>  };
>  
>  int drm_display_info_set_bus_formats(struct drm_display_info *info,
> diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
> index 3693d82b5279..d7ca1040b92e 100644
> --- a/include/uapi/drm/drm_mode.h
> +++ b/include/uapi/drm/drm_mode.h
> @@ -169,6 +169,7 @@ extern "C" {
>  /* Panel type property */
>  #define DRM_MODE_PANEL_TYPE_UNKNOWN	0
>  #define DRM_MODE_PANEL_TYPE_OLED	1
> +#define DRM_MODE_PANEL_TYPE_LCD		2

This is a UABI header.

Should we add this to the panel type property too?


BR,
Jani.


>  
>  /*
>   * DRM_MODE_ROTATE_<degrees>

-- 
Jani Nikula, Intel

Claude review: drm: detect panel type from DisplayID 2.x

[Claude Code Review Bot]

Overall Series Review

Subject: drm: detect panel type from DisplayID 2.x
Author: Chenyu Chen <chen-yu.chen@amd.com>
Patches: 6
Reviewed: 2026-05-25T22:19:21.187117

---

This 3-patch series adds panel type detection from the DisplayID v2.x Display Parameters Data Block (tag 0x21), resolving a longstanding TODO in amdgpu_dm. The approach is clean: extract a helper, parse a new block type, wire it into the driver. The code is well-structured and correctly handles the detection priority chain (VSDB > DPCD > DisplayID > Samsung heuristic).

However, there is one significant UAPI concern: **`DRM_MODE_PANEL_TYPE_LCD` is added to the UAPI header (`drm_mode.h`) but `drm_panel_type_enum_list` in `drm_connector.c` is not updated**, so the panel type property can never report "LCD" to userspace. Additionally, at the end of `dm_set_panel_type()`, the existing code only exposes `DRM_MODE_PANEL_TYPE_OLED` via the property — anything else becomes `DRM_MODE_PANEL_TYPE_UNKNOWN`. So even after this series, an LCD panel detected via DisplayID will show as "unknown" to userspace. This needs to be either fixed (update the enum list and the property-setting logic) or acknowledged as intentional for internal-only use — in which case `DRM_MODE_PANEL_TYPE_LCD` should not be in a UAPI header.

There are also minor style issues in Patch 1.

---

---
Generated by Claude Code Patch Reviewer

Claude review: drm/edid: extract section header processing into helper

[Claude Code Review Bot]

Patch Review

**Purpose:** Refactors `update_displayid_info()` to extract the header processing into `drm_displayid_process_section_header()`, removes the `break` so the iterator can walk all blocks.

**Correctness:** The logic is preserved correctly. The `header_processed` flag ensures the header is processed only once, and removing the `break` is necessary for Patch 2 to iterate to the Display Parameters block.

**Style issues:** The new helper has inconsistent indentation compared to the original code and kernel coding style:

```c
	drm_dbg_kms(connector->dev,
			"[CONNECTOR:%d:%s] DisplayID extension version 0x%02x, primary use 0x%02x\n",
			connector->base.id, connector->name,
```

The format string arguments should align with the opening parenthesis of `drm_dbg_kms`, as the original code did:

```c
		    "[CONNECTOR:%d:%s] DisplayID extension version 0x%02x, primary use 0x%02x\n",
```

Similarly, the `if` condition:

```c
	if (displayid_version(iter) == DISPLAY_ID_STRUCTURE_VER_20 &&
		(displayid_primary_use(iter) == PRIMARY_USE_HEAD_MOUNTED_VR ||
			displayid_primary_use(iter) == PRIMARY_USE_HEAD_MOUNTED_AR))
```

The original code had proper alignment with the condition on the `if`:

```c
	    (displayid_primary_use(&iter) == PRIMARY_USE_HEAD_MOUNTED_VR ||
	     displayid_primary_use(&iter) == PRIMARY_USE_HEAD_MOUNTED_AR))
```

These are minor but inconsistent with both the original code and typical kernel style.

**No functional concerns.**

---

---
Generated by Claude Code Patch Reviewer

Claude review: drm/edid: parse panel type from DisplayID 2.x Display Parameters

[Claude Code Review Bot]

Patch Review

**Purpose:** Adds parsing of the Display Device Technology field from the Display Parameters Data Block (tag 0x21).

**Struct layout:** `displayid_block` base is 3 bytes (tag + rev + num_bytes). The struct `displayid_display_params_block` places `payload[27]` then `device_tech_byte` at offset 30 from the block start (3 + 27 = 30 = 0x1E), which matches the spec reference. The `DISPLAYID_DISPLAY_PARAMS_MIN_LEN` calculation (29 bytes of payload) and the `num_bytes` check are correct.

**Parsing logic:** Using `FIELD_GET(DISPLAYID_DISPLAY_PARAMS_DEVICE_TECH, ...)` to extract bits [6:4] is correct and clean.

**UAPI concern (significant):**

```c
+#define DRM_MODE_PANEL_TYPE_LCD		2
```

This adds a new UAPI constant, but `drm_panel_type_enum_list` in `drivers/gpu/drm/drm_connector.c` currently only contains:

```c
static const struct drm_prop_enum_list drm_panel_type_enum_list[] = {
	{ DRM_MODE_PANEL_TYPE_UNKNOWN, "unknown" },
	{ DRM_MODE_PANEL_TYPE_OLED, "OLED" },
};
```

Without adding `{ DRM_MODE_PANEL_TYPE_LCD, "LCD" }` to this list, the panel type property will never report LCD to userspace. If LCD is meant to be internal-only, it shouldn't be in `include/uapi/drm/drm_mode.h`. If it's meant to be exposed, the enum list needs updating.

**`did_panel_type` field:** Adding a `u8` to `drm_display_info` is fine. The reset in `drm_reset_display_info()` is correct.

**Version gate:** The check `displayid_version(&iter) == DISPLAY_ID_STRUCTURE_VER_20` before parsing the block is correct — tag 0x21 is only valid in DisplayID v2.x.

---

---
Generated by Claude Code Patch Reviewer

Claude review: drm/amd/display: use DisplayID panel type in dm_set_panel_type

[Claude Code Review Bot]

Patch Review

**Purpose:** Wires up `did_panel_type` into amdgpu_dm's detection priority chain.

**Priority placement:** The new block is inserted correctly — after the VSDB and DPCD checks, before the Samsung luminance heuristic:

```c
+	/* If VSDB and DPCD didn't determine panel type, check DID */
+	if (link->panel_type == PANEL_TYPE_NONE) {
+		if (display_info->did_panel_type == DRM_MODE_PANEL_TYPE_LCD)
+			link->panel_type = PANEL_TYPE_LCD;
+		else if (display_info->did_panel_type == DRM_MODE_PANEL_TYPE_OLED)
+			link->panel_type = PANEL_TYPE_OLED;
+	}
```

**Effectiveness concern:** The existing end-of-function code only exposes OLED to userspace:

```c
	if (link->panel_type == PANEL_TYPE_OLED)
		drm_object_property_set_value(..., DRM_MODE_PANEL_TYPE_OLED);
	else
		drm_object_property_set_value(..., DRM_MODE_PANEL_TYPE_UNKNOWN);
```

So `PANEL_TYPE_LCD` detected via DisplayID would internally set `link->panel_type = PANEL_TYPE_LCD` (which is `1` in `dc_types.h`), but the userspace property would still read "unknown". Currently no DC code checks `panel_type == PANEL_TYPE_LCD` anywhere, so this detection has no observable effect unless there are downstream consumers added later. This may be intentional (laying groundwork), but it should be documented or the property-setting code should be updated to also handle LCD.

**Cross-domain constant mixing:** The code mixes UAPI constants (`DRM_MODE_PANEL_TYPE_LCD`) with internal DC constants (`PANEL_TYPE_LCD`). This works because they're independent enums, but it's somewhat unusual to compare a `drm_display_info` field set with UAPI values against those UAPI values and then assign internal DC enum values. This is fine functionally but worth noting for maintainability — a mapping helper could improve clarity.

**Overall for Patch 3:** The TODO removal is welcome and the fallback insertion point is correct. The main gap is that LCD detection currently has no visible effect.

---
Generated by Claude Code Patch Reviewer