Low performance in newer Kernels

Graphics / Linux Linux
, ,
1

Hello everyone!

I have installed fedora 41 on my Lenovo Legion 5i Pro (2022, gen 7) as a daily driver OS. It functioned well out-of-the-box in all scenarios so far, except gaming. The laptop uses a MUXed optimus setup, with a display output switch between iGPU and dGPU in the BIOS, with advanced optimus capability in Windows.

Output from ‘inxi -Farzy’ on affected kernel:

System:   Kernel: 6.13.6-200.fc41.x86_64 arch: x86_64 bits: 64 compiler: gcc v: 14.2.1     clocksource: tsc avail: acpi_pm     parameters: BOOT_IMAGE=(hd1,gpt3)/vmlinuz-6.13.6-200.fc41.x86_64     root=UUID=301a0013-fcf1-4cf4-9b18-9fee9b3fe413 ro rootflags=subvol=root     resume=UUID=e58e2e02-ecb9-4eae-a716-87ebcd673291 rhgb nouveau.modeset=0     splash hibernate=nocompress nvidia_drm.modeset=1 nvidia_drm.fbdev=1     ibt=off rd.driver.blacklist=nouveau modprobe.blacklist=nouveau     "acpi_osi=Windows 2022"   Desktop: KDE Plasma v: 6.3.3 tk: Qt v: N/A info: frameworks v: 6.12.0     wm: kwin_wayland vt: 2 dm: SDDM Distro: Fedora Linux 41 (KDE Plasma) Machine:   Type: Laptop System: LENOVO product: 82RF v: Legion 5 Pro 16IAH7H     serial: <superuser required> Chassis: type: 10 v: Legion 5 Pro 16IAH7H     serial: <superuser required>   Mobo: LENOVO model: LNVNB161216 v: NO DPK serial: <superuser required>     part-nu: LENOVO_MT_82RF_BU_idea_FM_Legion 5 Pro 16IAH7H     uuid: <superuser required> UEFI: LENOVO v: J2CN57WW date: 01/08/2024 Battery:   ID-1: BAT0 charge: 62.1 Wh (77.0%) condition: 80.7/80.0 Wh (100.8%)     volts: 16.2 min: 15.4 model: Sunwoda L21D4PC1 type: Li-poly serial: <filter>     status: not charging cycles: 26 CPU:   Info: model: 12th Gen Intel Core i7-12700H bits: 64 type: MST AMCP     arch: Alder Lake gen: core 12 level: v3 note: check built: 2021+     process: Intel 7 (10nm ESF) family: 6 model-id: 0x9A (154) stepping: 3     microcode: 0x436   Topology: cpus: 1x dies: 1 clusters: 8 cores: 14 threads: 20 mt: 6 tpc: 2     st: 8 smt: enabled cache: L1: 1.2 MiB desc: d-8x32 KiB, 6x48 KiB; i-6x32     KiB, 8x64 KiB L2: 11.5 MiB desc: 6x1.2 MiB, 2x2 MiB L3: 24 MiB     desc: 1x24 MiB   Speed (MHz): avg: 400 min/max: 400/4600:4700:3500 scaling:     driver: intel_pstate governor: powersave cores: 1: 400 2: 400 3: 400 4: 400     5: 400 6: 400 7: 400 8: 400 9: 400 10: 400 11: 400 12: 400 13: 400 14: 400     15: 400 16: 400 17: 400 18: 400 19: 400 20: 400 bogomips: 107520   Flags: avx avx2 ht lm nx pae sse sse2 sse3 sse4_1 sse4_2 ssse3 vmx   Vulnerabilities:   Type: gather_data_sampling status: Not affected   Type: itlb_multihit status: Not affected   Type: l1tf status: Not affected   Type: mds status: Not affected   Type: meltdown status: Not affected   Type: mmio_stale_data status: Not affected   Type: reg_file_data_sampling mitigation: Clear Register File   Type: retbleed status: Not affected   Type: spec_rstack_overflow status: Not affected   Type: spec_store_bypass mitigation: Speculative Store Bypass disabled via     prctl   Type: spectre_v1 mitigation: usercopy/swapgs barriers and __user pointer     sanitization   Type: spectre_v2 mitigation: Enhanced / Automatic IBRS; IBPB: conditional;     RSB filling; PBRSB-eIBRS: SW sequence; BHI: BHI_DIS_S   Type: srbds status: Not affected   Type: tsx_async_abort status: Not affected Graphics:   Device-1: Intel Alder Lake-P GT2 [Iris Xe Graphics] vendor: Lenovo     driver: i915 v: kernel alternate: xe arch: Xe process: Intel 10nm     built: 2021-22+ ports: active: eDP-1 empty: DP-1,DP-2 bus-ID: 00:02.0     chip-ID: 8086:46a6 class-ID: 0300   Device-2: NVIDIA GA104M [GeForce RTX 3070 Mobile / Max-Q] vendor: Lenovo     driver: nvidia v: 570.124.04 alternate: nouveau,nvidia_drm     non-free: 550/565.xx+ status: current (as of 2025-01; EOL~2026-12-xx)     arch: Ampere code: GAxxx process: TSMC n7 (7nm) built: 2020-2023 pcie:     gen: 1 speed: 2.5 GT/s lanes: 8 link-max: gen: 4 speed: 16 GT/s lanes: 16     ports: active: none empty: DP-3, DP-4, HDMI-A-1, eDP-2 bus-ID: 01:00.0     chip-ID: 10de:24dd class-ID: 0300   Display: wayland server: Xwayland v: 24.1.6 compositor: kwin_wayland     driver: X: loaded: modesetting,nvidia unloaded: nouveau     alternate: fbdev,nv,vesa dri: iris gpu: i915 display-ID: 0   Monitor-1: eDP-1 model: California Institute of eDP-1-0x1612 built: 2021     res: mode: 2560x1600 hz: 165 scale: 120% (1.2) to: 2133x1333 dpi: 188     gamma: 1.2 size: 345x215mm (13.58x8.46") diag: 407mm (16") ratio: 16:10     modes: 2560x1600   API: EGL v: 1.5 hw: drv: intel iris drv: nvidia platforms: device: 0     drv: nvidia gbm: drv: nvidia surfaceless: drv: nvidia wayland: drv: iris x11:     drv: iris   API: OpenGL v: 4.6.0 compat-v: 4.6 vendor: intel mesa v: 25.0.1 glx-v: 1.4     direct-render: yes renderer: Mesa Intel Iris Xe Graphics (ADL GT2)     device-ID: 8086:46a6 memory: 15.17 GiB unified: yes display-ID: :0.0   API: Vulkan v: 1.4.304 layers: 11 device: 0 type: integrated-gpu name: Intel     Iris Xe Graphics (ADL GT2) driver: N/A device-ID: 8086:46a6     surfaces: xcb,xlib,wayland device: 1 type: discrete-gpu name: NVIDIA     GeForce RTX 3070 Laptop GPU driver: N/A device-ID: 10de:24dd     surfaces: xcb,xlib,wayland device: 2 type: cpu name: llvmpipe (LLVM 19.1.7     256 bits) driver: N/A device-ID: 10005:0000 surfaces: xcb,xlib,wayland   Info: Tools: api: clinfo, eglinfo, glxinfo, vulkaninfo     de: kscreen-console,kscreen-doctor gpu: nvidia-settings,nvidia-smi     wl: wayland-info x11: xdriinfo, xdpyinfo, xprop, xrandr Audio:   Device-1: Intel Alder Lake PCH-P High Definition Audio vendor: Lenovo     driver: snd_hda_intel v: kernel alternate: snd_soc_avs,snd_sof_pci_intel_tgl     bus-ID: 00:1f.3 chip-ID: 8086:51c8 class-ID: 0403   Device-2: NVIDIA GA104 High Definition Audio vendor: Lenovo     driver: snd_hda_intel v: kernel pcie: gen: 1 speed: 2.5 GT/s lanes: 8     link-max: gen: 4 speed: 16 GT/s lanes: 16 bus-ID: 01:00.1     chip-ID: 10de:228b class-ID: 0403   API: ALSA v: k6.13.6-200.fc41.x86_64 status: kernel-api     tools: alsactl,alsamixer,amixer   Server-1: PipeWire v: 1.2.7 status: active with: 1: pipewire-pulse     status: active 2: wireplumber status: active 3: pipewire-alsa type: plugin     4: pw-jack type: plugin tools: pactl,pw-cat,pw-cli,wpctl Network:   Device-1: Intel Alder Lake-P PCH CNVi WiFi driver: iwlwifi v: kernel     bus-ID: 00:14.3 chip-ID: 8086:51f0 class-ID: 0280   IF: wlp0s20f3 state: up mac: <filter>   Device-2: Realtek RTL8111/8168/8211/8411 PCI Express Gigabit Ethernet     vendor: Lenovo driver: r8169 v: kernel pcie: gen: 1 speed: 2.5 GT/s lanes: 1     port: 3000 bus-ID: 34:00.0 chip-ID: 10ec:8168 class-ID: 0200   IF: enp52s0 state: down mac: <filter>   Info: services: NetworkManager,wpa_supplicant Bluetooth:   Device-1: Intel AX211 Bluetooth driver: btusb v: 0.8 type: USB rev: 2.0     speed: 12 Mb/s lanes: 1 mode: 1.1 bus-ID: 3-10:6 chip-ID: 8087:0033     class-ID: e001   Report: btmgmt ID: hci0 rfk-id: 2 state: down bt-service: enabled,running     rfk-block: hardware: no software: yes address: <filter> bt-v: 5.3 lmp-v: 12     status: discoverable: no pairing: no Drives:   Local Storage: total: 1.84 TiB used: 568.28 GiB (30.1%)   SMART Message: Unable to run smartctl. Root privileges required.   ID-1: /dev/nvme0n1 maj-min: 259:2 vendor: SanDisk model: SC930 PRO 1TB     size: 931.51 GiB block-size: physical: 512 B logical: 512 B speed: 63.2 Gb/s     lanes: 4 tech: SSD serial: <filter> fw-rev: SN12362 temp: 44.9 C     scheme: GPT   ID-2: /dev/nvme1n1 maj-min: 259:0 vendor: Samsung model: MZVL21T0HCLR-00BL2     size: 953.87 GiB block-size: physical: 512 B logical: 512 B speed: 63.2 Gb/s     lanes: 4 tech: SSD serial: <filter> fw-rev: CL1QGXA7 temp: 36.9 C     scheme: GPT Partition:   ID-1: / raw-size: 897.73 GiB size: 897.73 GiB (100.00%)     used: 567.86 GiB (63.3%) fs: btrfs dev: /dev/nvme0n1p5 maj-min: 259:12   ID-2: /boot raw-size: 1024 MiB size: 973.4 MiB (95.06%)     used: 347 MiB (35.6%) fs: ext4 dev: /dev/nvme0n1p3 maj-min: 259:10   ID-3: /boot/efi raw-size: 800 MiB size: 256 MiB (32.00%)     used: 80.8 MiB (31.5%) fs: vfat dev: /dev/nvme0n1p1 maj-min: 259:9   ID-4: /home raw-size: 897.73 GiB size: 897.73 GiB (100.00%)     used: 567.86 GiB (63.3%) fs: btrfs dev: /dev/nvme0n1p5 maj-min: 259:12 Swap:   Kernel: swappiness: 60 (default) cache-pressure: 100 (default) zswap: no   ID-1: swap-1 type: zram size: 8 GiB used: 0 KiB (0.0%) priority: 100     comp: lzo-rle avail: lzo,lz4,lz4hc,zstd,deflate,842 max-streams: 20     dev: /dev/zram0   ID-2: swap-2 type: partition size: 32 GiB used: 0 KiB (0.0%) priority: -2     dev: /dev/nvme0n1p4 maj-min: 259:11 Sensors:   System Temperatures: cpu: 61.0 C mobo: N/A   Fan Speeds (rpm): N/A Repos:   Packages: pm: dpkg pkgs: 0 pm: rpm pkgs: N/A note: see --rpm tools: dnf,yum     pm: flatpak pkgs: 40   No active dnf repos in: /etc/dnf/dnf.conf   Active yum repos in: /etc/yum.repos.d/_copr:copr.fedorainfracloud.org:gloriouseggroll:nobara-41.repo     1: copr:copr.fedorainfracloud.org:gloriouseggroll:nobara-41 ~ https://download.copr.fedorainfracloud.org/results/gloriouseggroll/nobara-41/fedora-$releasever-$basearch/   Active yum repos in: /etc/yum.repos.d/_copr:copr.fedorainfracloud.org:kwizart:kernel-longterm-6.1.repo     1: copr:copr.fedorainfracloud.org:kwizart:kernel-longterm-6.1 ~ https://download.copr.fedorainfracloud.org/results/kwizart/kernel-longterm-6.1/fedora-$releasever-$basearch/   No active yum repos in: /etc/yum.repos.d/_copr:copr.fedorainfracloud.org:kwizart:kernel-longterm-6.6.repo   Active yum repos in: /etc/yum.repos.d/_copr:copr.fedorainfracloud.org:mrduarte:LenovoLegionLinux.repo     1: copr:copr.fedorainfracloud.org:mrduarte:LenovoLegionLinux ~ https://download.copr.fedorainfracloud.org/results/mrduarte/LenovoLegionLinux/fedora-$releasever-$basearch/   Active yum repos in: /etc/yum.repos.d/_copr:copr.fedorainfracloud.org:phracek:PyCharm.repo     1: copr:copr.fedorainfracloud.org:phracek:PyCharm ~ https://download.copr.fedorainfracloud.org/results/phracek/PyCharm/fedora-$releasever-$basearch/   No active yum repos in: /etc/yum.repos.d/_copr:copr.fedorainfracloud.org:rmnscnce:kernel-lqx.repo   Active yum repos in: /etc/yum.repos.d/fedora-cisco-openh264.repo     1: fedora-cisco-openh264 ~ https://mirrors.fedoraproject.org/metalink?repo=fedora-cisco-openh264-$releasever&arch=$basearch   No active yum repos in: /etc/yum.repos.d/fedora-rawhide.repo   No active yum repos in: /etc/yum.repos.d/fedora-updates-testing.repo   Active yum repos in: /etc/yum.repos.d/fedora-updates.repo     1: updates ~ https://mirrors.nobaraproject.org/fedora-updates   Active yum repos in: /etc/yum.repos.d/fedora.repo     1: fedora ~ https://mirrors.nobaraproject.org/fedora   Active yum repos in: /etc/yum.repos.d/google-chrome.repo     1: google-chrome ~ https://dl.google.com/linux/chrome/rpm/stable/x86_64   Active yum repos in: /etc/yum.repos.d/hardware:razer.repo     1: hardware_razer ~ https://download.opensuse.org/repositories/hardware:/razer/Fedora_$releasever/   Active yum repos in: /etc/yum.repos.d/rpmfusion-nonfree-nvidia-driver.repo     1: rpmfusion-nonfree-nvidia-driver ~ https://mirrors.rpmfusion.org/metalink?repo=nonfree-fedora-nvidia-driver-$releasever&arch=$basearch   Active yum repos in: /etc/yum.repos.d/rpmfusion-nonfree-steam.repo     1: rpmfusion-nonfree-steam ~ https://mirrors.rpmfusion.org/metalink?repo=nonfree-fedora-steam-$releasever&arch=$basearch   Active yum repos in: /etc/yum.repos.d/rpmfusion-nonfree-tainted.repo     1: rpmfusion-nonfree-tainted ~ https://mirrors.rpmfusion.org/metalink?repo=nonfree-fedora-tainted-$releasever&arch=$basearch   No active yum repos in: /etc/yum.repos.d/rpmfusion-nonfree-updates-testing.repo   Active yum repos in: /etc/yum.repos.d/rpmfusion-nonfree-updates.repo     1: rpmfusion-nonfree-updates ~ https://mirrors.rpmfusion.org/metalink?repo=nonfree-fedora-updates-released-$releasever&arch=$basearch   Active yum repos in: /etc/yum.repos.d/rpmfusion-nonfree.repo     1: rpmfusion-nonfree ~ https://mirrors.rpmfusion.org/metalink?repo=nonfree-fedora-$releasever&arch=$basearch Info:   Memory: total: 32 GiB note: est. available: 31.06 GiB used: 3.57 GiB (11.5%)   Processes: 448 Power: uptime: 1m states: freeze,mem,disk suspend: deep     avail: s2idle wakeups: 0 hibernate: platform avail: shutdown, reboot,     suspend, test_resume image: 12.41 GiB services: org_kde_powerdevil,upowerd     Init: systemd v: 256 target: graphical (5) default: graphical     tool: systemctl   Compilers: gcc: 14.2.1 Shell: Bash v: 5.2.32 running-in: yakuake     inxi: 3.3.37

On the latest kernel packages from fedora, there is a massive dip in performance in games, with Palworld sitting at ~50fps at High-Epic settings with DLSS Quality, where with kernel 6.1 it sits at ~72fps. Even vkcube does not lock to 165fps. Note also the strangely high power consumption.

Screenshot from 6.13:

Screenshot_lowperf
Screenshot_lowperf2560×1600 219 KB

Checking journalctl logs, I find some messages from pnp regarding io overlaps with my nvidia gpu that I don’t see with kernel 6.1:

Mar 16 15:40:58 fedora kernel: pnp: PnP ACPI init Mar 16 15:40:58 fedora kernel: pnp 00:00: disabling [io  0x002e-0x002f] because it overlaps 0000:01:00.0 BAR 5 [io  0x0000-0x007f] Mar 16 15:40:58 fedora kernel: pnp 00:00: disabling [io  0x004e-0x004f] because it overlaps 0000:01:00.0 BAR 5 [io  0x0000-0x007f] Mar 16 15:40:58 fedora kernel: pnp 00:00: disabling [io  0x0061] because it overlaps 0000:01:00.0 BAR 5 [io  0x0000-0x007f] Mar 16 15:40:58 fedora kernel: pnp 00:00: disabling [io  0x0063] because it overlaps 0000:01:00.0 BAR 5 [io  0x0000-0x007f] Mar 16 15:40:58 fedora kernel: pnp 00:00: disabling [io  0x0065] because it overlaps 0000:01:00.0 BAR 5 [io  0x0000-0x007f] Mar 16 15:40:58 fedora kernel: pnp 00:00: disabling [io  0x0067] because it overlaps 0000:01:00.0 BAR 5 [io  0x0000-0x007f] Mar 16 15:40:58 fedora kernel: pnp 00:00: disabling [io  0x0070] because it overlaps 0000:01:00.0 BAR 5 [io  0x0000-0x007f] Mar 16 15:40:58 fedora kernel: system 00:00: [io  0x0680-0x069f] has been reserved Mar 16 15:40:58 fedora kernel: system 00:00: [io  0x164e-0x164f] has been reserved Mar 16 15:40:58 fedora kernel: system 00:01: [io  0x1854-0x1857] has been reserved Mar 16 15:40:58 fedora kernel: pnp 00:03: disabling [mem 0xc0000000-0xcfffffff] because it overlaps 0000:00:02.0 BAR 9 [mem 0x00000000-0xdfffffff 64bit pref] Mar 16 15:40:58 fedora kernel: system 00:03: [mem 0xfedc0000-0xfedc7fff] has been reserved Mar 16 15:40:58 fedora kernel: system 00:03: [mem 0xfeda0000-0xfeda0fff] has been reserved Mar 16 15:40:58 fedora kernel: system 00:03: [mem 0xfeda1000-0xfeda1fff] has been reserved Mar 16 15:40:58 fedora kernel: system 00:03: [mem 0xfed20000-0xfed7ffff] could not be reserved Mar 16 15:40:58 fedora kernel: system 00:03: [mem 0xfed90000-0xfed93fff] could not be reserved Mar 16 15:40:58 fedora kernel: system 00:03: [mem 0xfed45000-0xfed8ffff] could not be reserved Mar 16 15:40:58 fedora kernel: system 00:03: [mem 0xfee00000-0xfeefffff] has been reserved Mar 16 15:40:58 fedora kernel: system 00:04: [io  0x2000-0x20fe] has been reserved Mar 16 15:40:58 fedora kernel: pnp: PnP ACPI: found 6 devices 
0000:01:00.0 -> nvidia dGPU 0000:00:02.0 -> intel iGPU system 00:03: -> ??? # I have no idea what this is

There seem to be no other discussions that I am able to find, and anything regarding the pnp overlaps seem to give me inactive threads or old patches from 2008. As things are right now, I make do with kernel 6.1, at the expense of S3 sleep, the Xe iGPU driver, and generally any new driver features and optimisations.

Output from ‘lspci -vv’ on 6.13:

01:00.0 VGA compatible controller: NVIDIA Corporation GA104M [GeForce RTX 3070 Mobile / Max-Q] (rev a1) (prog-if 00 [VGA controller])         Subsystem: Lenovo Device 3833         Physical Slot: 1         Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx+         Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-         Latency: 0         Interrupt: pin A routed to IRQ 210         IOMMU group: 16         Region 0: Memory at 60000000 (32-bit, non-prefetchable) [size=16M]         Region 1: Memory at 4200000000 (64-bit, prefetchable) [size=8G]         Region 3: Memory at 4100000000 (64-bit, prefetchable) [size=32M]         Region 5: I/O ports at 5000 [size=128]         Expansion ROM at 61000000 [virtual] [disabled] [size=512K]         Capabilities: <access denied>         Kernel driver in use: nvidia         Kernel modules: nouveau, nvidia_drm, nvidia

Full 6.13 dmesg log here: Pastebin

In case it helps, this has happened across multiple distros (Manjaro, Nobara Live image, fedora) on two different lenovo laptops since about September 2024. The issue was first noticed after a kernel update on Manjaro on the old laptop, which prompted a distro-hop.

Previous laptop specs:
Lenovo Ideapad Gaming 3i 15IMH05
Intel Core i7 10th gen H-series
Nvidia GTX 1650 Ti (MUXless Optimus)

2

Adding second screenshot using the unaffected 6.1 kernel here due to embedded media limitation for new users:

Screenshot from 6.1:

Screenshot_fullperf
Screenshot_fullperf2560×1600 207 KB
3

Is vkcube ran the same way in the screenshots? Because the Window border looks different, one is under X and one is under Wayland?

Anyway, if you run under wayland, make sure nvidia-drm module is properly loaded and that modeset is being used.
cat /sys/module/nvidia_drm/parameters/modeset

Should return Y

4

No, both are under wayland and modesetting is enabled.
Fedora 41 doesn’t offer an X session anymore.

The command has indeed returned ‘Y’

Window border thing is likely due to my use of Khronkite, a script to make Plasma behave like a tiling window manager.

5

Interesting issue tho, I went to try a 6,1 kernel but the latest Nvidia driver just crashed.
There is some pci kernel parameter you can try:

See pci realloc:

6

Tried this with kernel 6.13.7. Unfortunately, it made no difference. pnp errors continue and performance remains kneecapped.

cat /proc/cmdline BOOT_IMAGE=(hd1,gpt3)/vmlinuz-6.13.7-200.fc41.x86_64 root=UUID=301a0013-fcf1-4cf4-9b18-9fee9b3fe413 ro rootflags=subvol=root resume=UUID=e58e2e02-ecb9-4eae-a716-87ebcd673291 rhgb nouveau.modeset=0 splash hibernate=nocompress ibt=off rd.driver.blacklist=nouveau modprobe.blacklist=nouveau nvidia_drm.modeset=1 nvidia_drm.fbdev=0 pci=realloc=off

I don’t seem to be getting any of the PCI I/O region errors from NVRM that this parameter fixes

7

Any particular reason for the crash? Any relation to the errors on my end being on every kernel except 6.1?

8

The 570 driver didn’t run on kernel 6.1 for me, i saw the sddm login screen briefly then it disappeared. Checking dmesg contained some RIPs about the nvidia driver

But even if I did get it working I might not be able to verify your issue… as I don’t have “resource conflicts”

9

Interesting development:

I compared dmesg outputs from kernel 6.1 and 6.13. I’m seeing a limited PCIe bandwidth with 6.13 for some reason. Is this the cause instead of the pnp errors? (I see the BARs get assigned regardless of what pnp spits out)

6.1:

abijay@fedora:~$ sudo journalctl -b 0 -g "pci 0000:01" Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: [10de:24dd] type 00 class 0x030000 Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: reg 0x10: [mem 0x00000000-0x00ffffff] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: reg 0x14: [mem 0x00000000-0x1ffffffff 64bit pref] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: reg 0x1c: [mem 0x00000000-0x01ffffff 64bit pref] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: reg 0x24: [io  0x0000-0x007f] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: reg 0x30: [mem 0x00000000-0x0007ffff pref] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: Max Payload Size set to 256 (was 128, max 256) Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: PME# supported from D0 D3hot Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: 126.024 Gb/s available PCIe bandwidth, limited by 16.0 GT/s PCIe x8 link at 0000:00:01.0 (capable of 252.048 Gb/s with 16.0 GT/s PCIe x16 link) Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: Adding to iommu group 19 Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: vgaarb: bridge control possible Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: vgaarb: VGA device added: decodes=io+mem,owns=none,locks=none Mar 28 13:26:19 fedora kernel: pci 0000:01:00.1: [10de:228b] type 00 class 0x040300 Mar 28 13:26:19 fedora kernel: pci 0000:01:00.1: reg 0x10: [mem 0x00000000-0x00003fff] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.1: Max Payload Size set to 256 (was 128, max 256) Mar 28 13:26:19 fedora kernel: pci 0000:01:00.1: Adding to iommu group 19 Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: BAR 1: assigned [mem 0x6000000000-0x61ffffffff 64bit pref] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: BAR 3: assigned [mem 0x6200000000-0x6201ffffff 64bit pref] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: BAR 0: assigned [mem 0x60000000-0x60ffffff] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: BAR 6: assigned [mem 0x61000000-0x6107ffff pref] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.1: BAR 0: assigned [mem 0x61080000-0x61083fff] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.0: BAR 5: assigned [io  0x5000-0x507f] Mar 28 13:26:19 fedora kernel: pci 0000:01:00.1: extending delay after power-on from D3hot to 20 msec Mar 28 13:26:19 fedora kernel: pci 0000:01:00.1: D0 power state depends on 0000:01:00.0 Mar 28 15:50:29 fedora sudo[20814]:   abijay : TTY=pts/4 ; PWD=/home/abijay ; USER=root ; COMMAND=/usr/bin/journalctl -b - -g 'pci 0000:01' Mar 28 15:50:37 fedora sudo[20848]:   abijay : TTY=pts/4 ; PWD=/home/abijay ; USER=root ; COMMAND=/usr/bin/journalctl -b 0 -g 'pci 0000:01' Mar 28 15:52:14 fedora sudo[20886]:   abijay : TTY=pts/4 ; PWD=/home/abijay ; USER=root ; COMMAND=/usr/bin/journalctl -b 0 -g 'pci 0000:01' Mar 28 15:52:24 fedora sudo[20917]:   abijay : TTY=pts/4 ; PWD=/home/abijay ; USER=root ; COMMAND=/usr/bin/journalctl -b -3 -g 'pci 0000:01' Mar 28 15:54:00 fedora sudo[21388]:   abijay : TTY=pts/4 ; PWD=/home/abijay ; USER=root ; COMMAND=/usr/bin/journalctl -b 0 -g 'pci 0000:01'

6.13:

abijay@fedora:~$ sudo journalctl -b -3 -g "pci 0000:01" Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: [10de:24dd] type 00 class 0x030000 PCIe Legacy Endpoint Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: BAR 0 [mem 0x00000000-0x00ffffff] Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: BAR 1 [mem 0x00000000-0x0fffffff 64bit pref] Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: BAR 3 [mem 0x00000000-0x01ffffff 64bit pref] Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: BAR 5 [io  0x0000-0x007f] Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: ROM [mem 0x00000000-0x0007ffff pref] Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: Max Payload Size set to 256 (was 128, max 256) Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: PME# supported from D0 D3hot Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: 16.000 Gb/s available PCIe bandwidth, limited by 2.5 GT/s PCIe x8 link at 0000:00:01.0 (capable of 252.048 Gb/s with 16.0 GT/s PCIe x16 link) Mar 28 12:15:04 fedora kernel: pci 0000:01:00.1: [10de:228b] type 00 class 0x040300 PCIe Endpoint Mar 28 12:15:04 fedora kernel: pci 0000:01:00.1: BAR 0 [mem 0x00000000-0x00003fff] Mar 28 12:15:04 fedora kernel: pci 0000:01:00.1: Max Payload Size set to 256 (was 128, max 256) Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: vgaarb: bridge control possible Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: vgaarb: VGA device added: decodes=io+mem,owns=none,locks=none Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: BAR 1 [mem 0x6000000000-0x600fffffff 64bit pref]: assigned Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: BAR 3 [mem 0x6010000000-0x6011ffffff 64bit pref]: assigned Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: BAR 0 [mem 0x60000000-0x60ffffff]: assigned Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: ROM [mem 0x61000000-0x6107ffff pref]: assigned Mar 28 12:15:04 fedora kernel: pci 0000:01:00.1: BAR 0 [mem 0x61080000-0x61083fff]: assigned Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: BAR 5 [io  0x5000-0x507f]: assigned Mar 28 12:15:04 fedora kernel: pci 0000:01:00.1: extending delay after power-on from D3hot to 20 msec Mar 28 12:15:04 fedora kernel: pci 0000:01:00.1: D0 power state depends on 0000:01:00.0 Mar 28 12:15:04 fedora kernel: pci 0000:01:00.0: Adding to iommu group 16 Mar 28 12:15:04 fedora kernel: pci 0000:01:00.1: Adding to iommu group 16
10

Okay, looking at lspci -vv outputs between both kernels, there’s clearly an issue with ‘LnkCap’ between the kernels:

6.1:

01:00.0 VGA compatible controller: NVIDIA Corporation GA104M [GeForce RTX 3070 Mobile / Max-Q] (rev a1) (prog-if 00 [VGA controller]) 	Subsystem: Lenovo Device 3833 	Physical Slot: 1 	Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx+ 	Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx- 	Latency: 0 	Interrupt: pin A routed to IRQ 181 	IOMMU group: 19 	Region 0: Memory at 60000000 (32-bit, non-prefetchable) [size=16M] 	Region 1: Memory at 6000000000 (64-bit, prefetchable) [size=8G] 	Region 3: Memory at 6200000000 (64-bit, prefetchable) [size=32M] 	Region 5: I/O ports at 5000 [size=128] 	Expansion ROM at 61000000 [virtual] [disabled] [size=512K] 	Capabilities: [60] Power Management version 3 		Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold-) 		Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=0 PME- 	Capabilities: [68] MSI: Enable+ Count=1/1 Maskable- 64bit+ 		Address: 00000000fee009b8  Data: 0000 	Capabilities: [78] Express (v2) Legacy Endpoint, IntMsgNum 0 		DevCap:	MaxPayload 256 bytes, PhantFunc 0, Latency L0s unlimited, L1 <64us 			ExtTag+ AttnBtn- AttnInd- PwrInd- RBE+ FLReset+ TEE-IO- 		DevCtl:	CorrErr- NonFatalErr- FatalErr- UnsupReq- 			RlxdOrd+ ExtTag+ PhantFunc- AuxPwr- NoSnoop+ FLReset- 			MaxPayload 256 bytes, MaxReadReq 512 bytes 		DevSta:	CorrErr- NonFatalErr- FatalErr- UnsupReq- AuxPwr- TransPend- 		LnkCap:	Port #0, Speed 16GT/s, Width x16, ASPM L0s L1, Exit Latency L0s <1us, L1 <4us 			ClockPM+ Surprise- LLActRep- BwNot- ASPMOptComp+ 		LnkCtl:	ASPM Disabled; RCB 64 bytes, LnkDisable- CommClk- 			ExtSynch- ClockPM+ AutWidDis- BWInt- AutBWInt- 		LnkSta:	Speed 16GT/s, Width x8 (downgraded) 			TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt- 		DevCap2: Completion Timeout: Range AB, TimeoutDis+ NROPrPrP- LTR+ 			 10BitTagComp+ 10BitTagReq+ OBFF Via message, ExtFmt- EETLPPrefix- 			 EmergencyPowerReduction Not Supported, EmergencyPowerReductionInit- 			 FRS- 			 AtomicOpsCap: 32bit- 64bit- 128bitCAS- 		DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis- 			 AtomicOpsCtl: ReqEn- 			 IDOReq- IDOCompl- LTR+ EmergencyPowerReductionReq- 			 10BitTagReq- OBFF Disabled, EETLPPrefixBlk- 		LnkCap2: Supported Link Speeds: 2.5-16GT/s, Crosslink- Retimer+ 2Retimers+ DRS- 		LnkCtl2: Target Link Speed: 16GT/s, EnterCompliance- SpeedDis- 			 Transmit Margin: Normal Operating Range, EnterModifiedCompliance- ComplianceSOS- 			 Compliance Preset/De-emphasis: -6dB de-emphasis, 0dB preshoot 		LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete+ EqualizationPhase1+ 			 EqualizationPhase2+ EqualizationPhase3+ LinkEqualizationRequest- 			 Retimer- 2Retimers- CrosslinkRes: unsupported 	Capabilities: [b4] Vendor Specific Information: Len=14 <?> 	Capabilities: [100 v1] Virtual Channel 		Caps:	LPEVC=0 RefClk=100ns PATEntryBits=1 		Arb:	Fixed- WRR32- WRR64- WRR128- 		Ctrl:	ArbSelect=Fixed 		Status:	InProgress- 		VC0:	Caps:	PATOffset=00 MaxTimeSlots=1 RejSnoopTrans- 			Arb:	Fixed- WRR32- WRR64- WRR128- TWRR128- WRR256- 			Ctrl:	Enable+ ID=0 ArbSelect=Fixed TC/VC=ff 			Status:	NegoPending- InProgress- 	Capabilities: [250 v1] Latency Tolerance Reporting 		Max snoop latency: 34326183936ns 		Max no snoop latency: 34326183936ns 	Capabilities: [258 v1] L1 PM Substates 		L1SubCap: PCI-PM_L1.2+ PCI-PM_L1.1+ ASPM_L1.2+ ASPM_L1.1+ L1_PM_Substates+ 			  PortCommonModeRestoreTime=255us PortTPowerOnTime=10us 		L1SubCtl1: PCI-PM_L1.2- PCI-PM_L1.1- ASPM_L1.2- ASPM_L1.1- 			   T_CommonMode=0us LTR1.2_Threshold=0ns 		L1SubCtl2: T_PwrOn=10us 	Capabilities: [128 v1] Power Budgeting <?> 	Capabilities: [420 v2] Advanced Error Reporting 		UESta:	DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- 			ECRC- UnsupReq- ACSViol- UncorrIntErr- BlockedTLP- AtomicOpBlocked- TLPBlockedErr- 			PoisonTLPBlocked- DMWrReqBlocked- IDECheck- MisIDETLP- PCRC_CHECK- TLPXlatBlocked- 		UEMsk:	DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- 			ECRC- UnsupReq- ACSViol- UncorrIntErr- BlockedTLP- AtomicOpBlocked- TLPBlockedErr- 			PoisonTLPBlocked- DMWrReqBlocked- IDECheck- MisIDETLP- PCRC_CHECK- TLPXlatBlocked- 		UESvrt:	DLP+ SDES+ TLP- FCP+ CmpltTO- CmpltAbrt- UnxCmplt- RxOF+ MalfTLP+ 			ECRC- UnsupReq- ACSViol- UncorrIntErr+ BlockedTLP- AtomicOpBlocked- TLPBlockedErr- 			PoisonTLPBlocked- DMWrReqBlocked- IDECheck- MisIDETLP- PCRC_CHECK- TLPXlatBlocked- 		CESta:	RxErr- BadTLP- BadDLLP- Rollover- Timeout- AdvNonFatalErr- CorrIntErr- HeaderOF- 		CEMsk:	RxErr- BadTLP- BadDLLP- Rollover- Timeout- AdvNonFatalErr+ CorrIntErr- HeaderOF+ 		AERCap:	First Error Pointer: 00, ECRCGenCap- ECRCGenEn- ECRCChkCap- ECRCChkEn- 			MultHdrRecCap- MultHdrRecEn- TLPPfxPres- HdrLogCap- 		HeaderLog: 00000000 00000000 00000000 00000000 	Capabilities: [600 v1] Vendor Specific Information: ID=0001 Rev=1 Len=024 <?> 	Capabilities: [900 v1] Secondary PCI Express 		LnkCtl3: LnkEquIntrruptEn- PerformEqu- 		LaneErrStat: 0 	Capabilities: [bb0 v1] Physical Resizable BAR 		BAR 0: current size: 16MB, supported: 16MB 		BAR 1: current size: 8GB, supported: 64MB 128MB 256MB 512MB 1GB 2GB 4GB 8GB 		BAR 3: current size: 32MB, supported: 32MB 	Capabilities: [c1c v1] Physical Layer 16.0 GT/s <?> 	Capabilities: [d00 v1] Lane Margining at the Receiver 		PortCap: Uses Driver+ 		PortSta: MargReady+ MargSoftReady+ 	Capabilities: [e00 v1] Data Link Feature <?> 	Kernel driver in use: nvidia 	Kernel modules: nouveau, nvidia_drm, nvidia

6.13:

01:00.0 VGA compatible controller: NVIDIA Corporation GA104M [GeForce RTX 3070 Mobile / Max-Q] (rev a1) (prog-if 00 [VGA controller]) 	Subsystem: Lenovo Device 3833 	Physical Slot: 1 	Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx+ 	Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx- 	Latency: 0 	Interrupt: pin A routed to IRQ 211 	IOMMU group: 16 	Region 0: Memory at 60000000 (32-bit, non-prefetchable) [size=16M] 	Region 1: Memory at 6000000000 (64-bit, prefetchable) [size=256M] 	Region 3: Memory at 6010000000 (64-bit, prefetchable) [size=32M] 	Region 5: I/O ports at 5000 [size=128] 	Expansion ROM at 61000000 [virtual] [disabled] [size=512K] 	Capabilities: [60] Power Management version 3 		Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold-) 		Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=0 PME- 	Capabilities: [68] MSI: Enable+ Count=1/1 Maskable- 64bit+ 		Address: 00000000fee00d78  Data: 0000 	Capabilities: [78] Express (v1) Legacy Endpoint, IntMsgNum 0 		DevCap:	MaxPayload 256 bytes, PhantFunc 0, Latency L0s unlimited, L1 <64us 			ExtTag+ AttnBtn- AttnInd- PwrInd- RBE+ FLReset+ TEE-IO- 		DevCtl:	CorrErr- NonFatalErr- FatalErr- UnsupReq- 			RlxdOrd+ ExtTag+ PhantFunc- AuxPwr- NoSnoop+ FLReset- 			MaxPayload 256 bytes, MaxReadReq 512 bytes 		DevSta:	CorrErr- NonFatalErr- FatalErr- UnsupReq- AuxPwr- TransPend- 		LnkCap:	Port #0, Speed 2.5GT/s, Width x16, ASPM L0s L1, Exit Latency L0s <512ns, L1 <4us 			ClockPM+ Surprise- LLActRep- BwNot- ASPMOptComp+ 		LnkCtl:	ASPM Disabled; RCB 64 bytes, LnkDisable- CommClk- 			ExtSynch- ClockPM+ AutWidDis- BWInt- AutBWInt- 		LnkSta:	Speed 2.5GT/s, Width x8 (downgraded) 			TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt- 	Capabilities: [b4] Vendor Specific Information: Len=14 <?> 	Capabilities: [100 v1] Virtual Channel 		Caps:	LPEVC=0 RefClk=100ns PATEntryBits=1 		Arb:	Fixed- WRR32- WRR64- WRR128- 		Ctrl:	ArbSelect=Fixed 		Status:	InProgress- 		VC0:	Caps:	PATOffset=00 MaxTimeSlots=1 RejSnoopTrans- 			Arb:	Fixed- WRR32- WRR64- WRR128- TWRR128- WRR256- 			Ctrl:	Enable+ ID=0 ArbSelect=Fixed TC/VC=ff 			Status:	NegoPending- InProgress- 	Capabilities: [250 v1] Latency Tolerance Reporting 		Max snoop latency: 34326183936ns 		Max no snoop latency: 34326183936ns 	Capabilities: [258 v1] L1 PM Substates 		L1SubCap: PCI-PM_L1.2+ PCI-PM_L1.1+ ASPM_L1.2+ ASPM_L1.1+ L1_PM_Substates+ 			  PortCommonModeRestoreTime=255us PortTPowerOnTime=10us 		L1SubCtl1: PCI-PM_L1.2- PCI-PM_L1.1- ASPM_L1.2- ASPM_L1.1- 			   T_CommonMode=0us LTR1.2_Threshold=0ns 		L1SubCtl2: T_PwrOn=10us 	Capabilities: [128 v1] Power Budgeting <?> 	Capabilities: [420 v2] Advanced Error Reporting 		UESta:	DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- 			ECRC- UnsupReq- ACSViol- UncorrIntErr- BlockedTLP- AtomicOpBlocked- TLPBlockedErr- 			PoisonTLPBlocked- DMWrReqBlocked- IDECheck- MisIDETLP- PCRC_CHECK- TLPXlatBlocked- 		UEMsk:	DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- 			ECRC- UnsupReq- ACSViol- UncorrIntErr- BlockedTLP- AtomicOpBlocked- TLPBlockedErr- 			PoisonTLPBlocked- DMWrReqBlocked- IDECheck- MisIDETLP- PCRC_CHECK- TLPXlatBlocked- 		UESvrt:	DLP+ SDES+ TLP- FCP+ CmpltTO- CmpltAbrt- UnxCmplt- RxOF+ MalfTLP+ 			ECRC- UnsupReq- ACSViol- UncorrIntErr+ BlockedTLP- AtomicOpBlocked- TLPBlockedErr- 			PoisonTLPBlocked- DMWrReqBlocked- IDECheck- MisIDETLP- PCRC_CHECK- TLPXlatBlocked- 		CESta:	RxErr- BadTLP- BadDLLP- Rollover- Timeout- AdvNonFatalErr- CorrIntErr- HeaderOF- 		CEMsk:	RxErr- BadTLP- BadDLLP- Rollover- Timeout- AdvNonFatalErr+ CorrIntErr- HeaderOF+ 		AERCap:	First Error Pointer: 00, ECRCGenCap- ECRCGenEn- ECRCChkCap- ECRCChkEn- 			MultHdrRecCap- MultHdrRecEn- TLPPfxPres- HdrLogCap- 		HeaderLog: 00000000 00000000 00000000 00000000 	Capabilities: [600 v1] Vendor Specific Information: ID=0001 Rev=1 Len=024 <?> 	Capabilities: [900 v1] Null 	Capabilities: [bb0 v1] Physical Resizable BAR 		BAR 0: current size: 16MB, supported: 16MB 		BAR 1: current size: 256MB, supported: 64MB 128MB 256MB 512MB 1GB 2GB 4GB 8GB 		BAR 3: current size: 32MB, supported: 32MB 	Capabilities: [c1c v1] Physical Layer 16.0 GT/s <?> 	Capabilities: [d00 v1] Lane Margining at the Receiver 		PortCap: Uses Driver+ 		PortSta: MargReady- MargSoftReady- 	Capabilities: [e00 v1] Data Link Feature <?> 	Kernel driver in use: nvidia 	Kernel modules: nouveau, nvidia_drm, nvidia

Can someone from the Driver team please take a look and confirm?

EDIT: I’ve also looked at other PCIe devices (M.2 NVMe SSD) with the newer kernel, and they are not affected like the dGPU is, i.e. LinkCap says 16GT/s x4 as expected on 6.13.

11

would you be able to check some kernels in between 6.1 and 6.13 to see more or less which kernel version first introduced the issue? Thanks!

12

Slight wrinkle. Fedora’s koji archive no longer has the kernel versions I want to test with, so I’ll be downloading old Manjaro live ISOs with nvidia drivers preinstalled. Will that work here?

13

I have checked lspci -vv and nvidia x server settings on Manjaro live 24.0 (kernel 6.9) and 23.0 (kernel 6.5). Both with the issue present. Screenshots attached:

Kernel 6.5:

Manjaro_6_5
Manjaro_6_51920×1200 154 KB

Kernel 6.9:

Manjaro_6_9
Manjaro_6_91920×1200 148 KB

Also, I just checked the lspci -vv output of the PCIe bridges and found that they too are limited to Gen1 speeds as well, with google saying that this is the likely cause of my GPU being limited. I’ve pasted the full output for 6.13 here: Pastebin

Output for 6.1 (Bridges at full Gen4 speeds) here: Pastebin

As an aside, is the problem described here related? (TLDR: Lenovo discovered a PCIe bug in January for hotpluggable devices that brings them down to Gen 1. Commit IDs included.)

1 Like
14

I am at my wit’s end. Can someone on the driver team please help?

15

I’ve been discussing and attempting to solve this issue in the fedora discussions forum, and have some new developments to share:

  1. The nvidia driver (MIT and proprietary kernel modules) appear to be correlated to the PCIe bandwidth limitations with kernels > 6.1.
  2. When the driver was not loaded correctly (Mismatch between kernel and userspace driver versions during an upgrade to 575), the PCIe bandwidth was back at full speed with correct speed-downgrading behaviour, though the GPU was not usable. Similar behaviour was observed without Nvidia driver installed and only nouveau loaded.

Can someone with relevant knowledge please help?

16

Found a temporary fix

According to this, it’s a lenovo BIOS issue, something about secure BIOS settings and disabling WMI, which caused configuration issues with nvidia dGPUs. Rolling back the BIOS fixed this link speed issue, though I do not know yet if a later bios has fixed this issue or not.

Lenovo’s Chinese support site has old BIOS packages available. Per the linked post, googling ‘[BIOS Ver.] lenovo cn’ should get you the site.

I will consider this the solution for this thread for now.

EDIT: Latest BIOS (J2CN61WW) does NOT fix this issue. Anyone know how to escalate this to Lenovo or get it to their BIOS/Legion team?

1 Like
17

Anyone know how to add additional tags to this Topic? Since this is a Lenovo-specific problem, I’d like to tag it as such, but I’m not sure where that option is.

18

Guess I have exactly the same laptop. Did downgrading to BIOS J2CN37WW solve all the games performance issues? I’m on J2CN40WW and I have this issue since kernel 6.6 if I remember correctly.

19

Yes, it did solve the game performance issues. I do still wonder what changed after kernel 6.1 that broke this, but I believe that it has something to do with WMI and whatever ‘secure variables’ Lenovo chose to disable between the two versions.

Curious what a diff would look like and if it can be turned into a patch for newer BIOS versions.

20

I downgraded and in fact I no longer have any problems (kernel logs was full of NVRM and DRM errors). Previously I also had the problem of correct initialization of the graphics card that came and went depending on the kernel but the performance (and initialization) problems started from memory with kernel 6.5. However not having done performance testing at the time I can tell you very little. I will do some benchmarks with cyberpunk 2077 in the next few days and can tell you how much has changed but if the problem with the PCI buses is responsible for the performance drop I am optimistic.

One has to wonder why these problems were never fixed by Lenovo but true that if it all depends on disabling WMI I guess they would never get their hands on it (why rehabilitate it for such a small group of nerds?!).

Thanks again I’ll keep you updated