On Thu, Aug 28, 2025 at 02:12:57PM +0200, Christian Bruel wrote:
> On 8/27/25 20:58, Bjorn Helgaas wrote:
> > On Wed, Aug 20, 2025 at 09:54:06AM +0200, Christian Bruel wrote:
> > > Add driver to configure the STM32MP25 SoC PCIe Gen1 2.5GT/s or Gen2 5GT/s
> > > controller based on the DesignWare PCIe core in endpoint mode.
> >
> > > +static void stm32_pcie_perst_deassert(struct dw_pcie *pci)
> > > +{
> > > + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci);
> > > + struct device *dev = pci->dev;
> > > + struct dw_pcie_ep *ep = &pci->ep;
> > > + int ret;
> > > +
> > > + dev_dbg(dev, "PERST de-asserted by host\n");
> > > +
> > > + ret = pm_runtime_resume_and_get(dev);
> > > + if (ret < 0) {
> > > + dev_err(dev, "Failed to resume runtime PM: %d\n", ret);
> > > + return;
> > > + }
> > > +
> > > + ret = stm32_pcie_enable_resources(stm32_pcie);
> > > + if (ret) {
> > > + dev_err(dev, "Failed to enable resources: %d\n", ret);
> > > + goto err_pm_put_sync;
> > > + }
> > > +
> > > + /*
> > > + * Need to reprogram the configuration space registers here because the
> > > + * DBI registers were incorrectly reset by the PHY RCC during phy_init().
> >
> > Is this incorrect reset of DBI registers a software issue or some kind
> > of hardware erratum that might be fixed someday? Or maybe it's just a
> > characteristic of the hardware and thus not really "incorrect"?
> >
> > I do see that qcom_pcie_perst_deassert() in pcie-qcom-ep.c also calls
> > dw_pcie_ep_init_registers() in the qcom_pcie_ep_perst_irq_thread()
> > path.
> >
> > So does pex_ep_event_pex_rst_deassert() (pcie-tegra194.c) in the
> > tegra_pcie_ep_pex_rst_irq() path.
> >
> > But as far as I can tell, none of the other dwc drivers need this, so
> > maybe it's something to do with the glue around the DWC core?
>
> The RCC PHY reset is connected to the Synopsys cold reset logic, which
> explains why the registers need to be restored. This point has been
> addressed in the reference manual.
OK. I dropped "incorrectly" from the comment because I think future
readers will wonder about whether or how this could be fixed, and it
sounds like it's just a feature of the hardware that we need to deal
with.
> > > + */
> > > + ret = dw_pcie_ep_init_registers(ep);
> > > + if (ret) {
> > > + dev_err(dev, "Failed to complete initialization: %d\n", ret);
> > > + goto err_disable_resources;
> > > + }
>