On Wed, Oct 15, 2025 at 02:59:01PM +0200, Herve Codina wrote: > On Wed, 15 Oct 2025 14:27:00 +0200 > Christian Zigotzky <[email protected]> wrote: > > > > On 15 October 2025 at 01:58 pm, Herve Codina <[email protected]> > > > wrote: > > > > > > Hi Christian, > > > > > >> On Wed, 15 Oct 2025 13:30:44 +0200 > > >> Christian Zigotzky <[email protected]> wrote: > > >> > > >> Hello Herve, > > >> > > >>>> On 15 October 2025 at 10:39 am, Herve Codina > > >>>> <[email protected]> wrote: > > >>> > > >>> Hi All, > > >>> > > >>> I also observed issues with the commit f3ac2ff14834 ("PCI/ASPM: Enable > > >>> all > > >>> ClockPM and ASPM states for devicetree platforms") > > >> > > >> Thanks for reporting. > > >> > > >>> > > >>> Also tried the quirk proposed in this discussion > > >>> (quirk_disable_aspm_all) > > >>> an the quirk also fixes the timing issue. > > >> > > >> Where have you added quirk_disable_aspm_all? > > > > > > --- 8< --- > > > diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c > > > index 214ed060ca1b..a3808ab6e92e 100644 > > > --- a/drivers/pci/quirks.c > > > +++ b/drivers/pci/quirks.c > > > @@ -2525,6 +2525,17 @@ static void quirk_disable_aspm_l0s_l1(struct > > > pci_dev *dev) > > > */ > > > DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x1080, > > > quirk_disable_aspm_l0s_l1); > > > > > > +static void quirk_disable_aspm_all(struct pci_dev *dev) > > > +{ > > > + pci_info(dev, "Disabling ASPM\n"); > > > + pci_disable_link_state(dev, PCIE_LINK_STATE_ALL); > > > +} > > > + > > > +/* LAN966x PCI board */ > > > +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_EFAR, 0x9660, > > > quirk_disable_aspm_all); > > > + > > > /* > > > * Some Pericom PCIe-to-PCI bridges in reverse mode need the PCIe Retrain > > > * Link bit cleared after starting the link retrain process to allow this > > > --- 8< --- > > > > > > Best regards, > > > Hervé > > > > It is the same patch, I use for my AMD Radeon cards. > > > > In my point of view we have to add a lot of other devices. > > Yes, probably! > > > > > But if the computer does not boot, will the average user know that there is > > a problem with the power management and their graphics card? > > I am unsure whether I can deliver the kernel to average users later on. > > Also when it boots, it is not easy to know about the problem root cause. > > In my case, it was not obvious to make the relationship on my side between > my ping timings behavior and ASPM. >
Interesting. So in your case, the issue is that ASPM adds up latency of the network card? If so, it is intended. The added latency should correspond to the L0s/L1 exit latencies. If you want performance, then you should select CONFIG_PCIEASPM_PERFORMANCE using Kconfig or pass 'pcie_aspm=off' in cmdline or do, 'echo performance > /sys/module/pcie_aspm/parameters/policy' By default, enabling ASPM saves power, but it comes with a cost of reducing performance. - Mani -- மணிவண்ணன் சதாசிவம்
