*** DONE Unresolved Issue: Lenovo x13 2-in-1 With Wrong 34" TFT Screen Resolution :issues:blog: CLOSED: [2025-09-14 Sun 17:13] SCHEDULED: <2025-09-14 Sun> :PROPERTIES: :CREATED: [2025-09-14 Sun 12:15] :ID: 2025-09-14-fix-wrong-34-TFT-resolution :END: :LOGBOOK: - State "DONE" from "STARTED" [2025-09-14 Sun 17:13] :END: # - [2025-09-14 Sun 12:15] ich dachte, ich hätte schon irgendwo einen Task dazu, finde ihn aber nicht. Problem description: Lenovo x13 2-in-1 Gen 5 with Debian 13 GNOME 48: I can't select the native screen resolution for the external 34" TFT which is 2560x1080. Hostname = Cosmo. In the GNOME screen configuration dialog, I may only choose a resolution (among others) that is similar but not correct: 2560x1440 **** Testing Another, Almost Identical Device Testing a different Lenovo x13 2-in-1 Gen 5 (hostname = Jackson; same generation, different battery, i7 CPU instead of i5) with the same OS + GNOME: display resolution is detected and selected correctly! - [X] do a firmware-update - did install but did not fix the issue. - Firmware is now identical on both devices. ***** Compare output of =lspci -v= Cosmo: (wrong resolution) #+BEGIN_EXAMPLE 00:02.0 VGA compatible controller: Intel Corporation Meteor Lake-P [Intel Graphics] (rev 08) (prog-if 00 [VGA controller]) Subsystem: Lenovo Device 232a Flags: bus master, fast devsel, latency 0, IRQ 192, IOMMU group 0 Memory at 4058000000 (64-bit, prefetchable) [size=16M] Memory at 4000000000 (64-bit, prefetchable) [size=256M] Expansion ROM at 000c0000 [virtual] [disabled] [size=128K] Capabilities: [40] Vendor Specific Information: Len=0c Capabilities: [70] Express Root Complex Integrated Endpoint, IntMsgNum 0 Capabilities: [ac] MSI: Enable+ Count=1/1 Maskable+ 64bit+ Capabilities: [d0] Power Management version 3 Capabilities: [100] Null Capabilities: [110] Process Address Space ID (PASID) Capabilities: [200] Address Translation Service (ATS) Capabilities: [420] Physical Resizable BAR Capabilities: [320] Single Root I/O Virtualization (SR-IOV) Capabilities: [400] Latency Tolerance Reporting Kernel driver in use: i915 Kernel modules: i915, xe #+END_EXAMPLE jackson: (resolution OK) #+BEGIN_EXAMPLE 00:02.0 VGA compatible controller: Intel Corporation Meteor Lake-P [Intel Graphics] (rev 08) (prog-if 00 [VGA controller]) Subsystem: Lenovo Device 232a Flags: bus master, fast devsel, latency 0, IRQ 192, IOMMU group 0 Memory at 4058000000 (64-bit, prefetchable) [size=16M] Memory at 4000000000 (64-bit, prefetchable) [size=256M] Expansion ROM at 000c0000 [virtual] [disabled] [size=128K] Capabilities: [40] Vendor Specific Information: Intel Capabilities v1 CapA: Peg60Dis- Peg12Dis- Peg11Dis- Peg10Dis- PeLWUDis- DmiWidth=x4 EccDis- ForceEccEn- VTdDis- DmiG2Dis- PegG2Dis- DDRMaxSize=Unlimited 1NDis- CDDis- DDPCDis- X2APICEn- PDCDis- IGDis- CDID=0 CRID=0 DDROCCAP+ OCEn- DDRWrtVrefEn+ DDR3LEn+ CapB: ImguDis- OCbySSKUCap- OCbySSKUEn- SMTCap- CacheSzCap 0x0 SoftBinCap- DDR3MaxFreqWithRef100=Disabled PegG3Dis- PkgTyp- AddGfxEn- AddGfxCap- PegX16Dis- DmiG3Dis- GmmDis- DDR3MaxFreq=2932MHz LPDDR3En- Capabilities: [70] Express Root Complex Integrated Endpoint, IntMsgNum 0 Capabilities: [ac] MSI: Enable+ Count=1/1 Maskable+ 64bit+ Capabilities: [d0] Power Management version 3 Capabilities: [100] Null Capabilities: [110] Process Address Space ID (PASID) Capabilities: [200] Address Translation Service (ATS) Capabilities: [420] Physical Resizable BAR Capabilities: [320] Single Root I/O Virtualization (SR-IOV) Capabilities: [400] Latency Tolerance Reporting Kernel driver in use: i915 Kernel modules: i915, xe #+END_EXAMPLE So I've got the same graphics hardware, same kernel driver, same version. However, the difference is: #+BEGIN_EXAMPLE non-working host: Capabilities: [40] Vendor Specific Information: Len=0c vs. working host: Capabilities: [40] Vendor Specific Information: Intel Capabilities v1 CapA: Peg60Dis- Peg12Dis- Peg11Dis- Peg10Dis- PeLWUDis- DmiWidth=x4 EccDis- ForceEccEn- VTdDis- DmiG2Dis- PegG2Dis- DDRMaxSize=Unlimited 1NDis- CDDis- DDPCDis- X2APICEn- PDCDis- IGDis- CDID=0 CRID=0 DDROCCAP+ OCEn- DDRWrtVrefEn+ DDR3LEn+ CapB: ImguDis- OCbySSKUCap- OCbySSKUEn- SMTCap- CacheSzCap 0x0 SoftBinCap- DDR3MaxFreqWithRef100=Disabled PegG3Dis- PkgTyp- AddGfxEn- AddGfxCap- PegX16Dis- DmiG3Dis- GmmDis- DDR3MaxFreq=2932MHz LPDDR3En- #+END_EXAMPLE ***** STARTED Find Out What This Difference Means and How to Get Cosmo to the Same Capabilities :PROPERTIES: :END: Any idea? Drop me a line. **** My Cry For Help :PROPERTIES: :END: - [2025-09-14 Sun 17:41] Mastodon-thread: https://graz.social/@publicvoit/115203409039346508 **** TODO Check Driver SCHEDULED: <2025-09-15 Mon> :PROPERTIES: :END: - https://graz.social/@gnomon@mastodon.social/115203465545303106 - since you're using the i915 driver instead of the xe driver per your dmesg output, what is the value of your 'enable_guc' kernel parameter, and what are the specific versions of the firmware blobs at /lib/firmware/i915/mtl_* ? - I'm not sure that this is necessarily your problem but it's the first thing I would check after looking at the info you provided. **** TODO Compare BIOS settings :PROPERTIES: :END: - Why? https://graz.social/@alienghic@timeloop.cafe/115203647620325001 - uh. something different about the ACPI? Not that I could find how to check or update that. - Do they both have the same grub settings? There's some settings that can change how the kernel detects hardware. - It seems like one system is able to detecting more information about the - Oh did you go into the bios settings and compare them? Maybe something is set slightly differently? **** TODO Compare GRUB settings :PROPERTIES: :END: - Why? https://graz.social/@alienghic@timeloop.cafe/115203647620325001 - uh. something different about the ACPI? Not that I could find how to check or update that. - Do they both have the same grub settings? There's some settings that can change how the kernel detects hardware. - It seems like one system is able to detecting more information about the - Oh did you go into the bios settings and compare them? Maybe something is set slightly differently?