On Thu, Oct 10, 2024 at 05:11:43PM +0300, Dmitry Baryshkov wrote: > On Thu, 10 Oct 2024 at 17:02, Johan Hovold <johan@xxxxxxxxxx> wrote: > > > > On Thu, Oct 10, 2024 at 04:54:19PM +0300, Dmitry Baryshkov wrote: > > > On Wed, Oct 09, 2024 at 06:17:15PM GMT, Johan Hovold wrote: > > > > The DWC PCIe controller can be used with its internal MSI controller or > > > > with an external one such as the GICv3 Interrupt Translation Service > > > > (ITS). > > > > > > > > Add the msi-map properties needed to use the GIC ITS. This will also > > > > make Linux switch to the ITS implementation, which allows for assigning > > > > affinity to individual MSIs. This specifically allows NVMe and Wi-Fi > > > > interrupts to be processed on all cores (and not just on CPU0). > > > > > > > > Note that using the GIC ITS on x1e80100 will cause Advanced Error > > > > Reporting (AER) interrupts to be received on errors unlike when using > > > > the internal MSI controller. Consequently, notifications about > > > > (correctable) errors may now be logged for errors that previously went > > > > unnoticed. > > > > > > > > Also note that PCIe5 (and PCIe3) can currently only be used with the > > > > internal MSI controller due to a platform (firmware) limitation. > > > > > > > > Signed-off-by: Johan Hovold <johan+linaro@xxxxxxxxxx> > > > > --- > > > > > > > > The PCIe Gen4 stability fixes [1] are now in 6.12-rc1 so that we can enable > > > > the GIC ITS without being flooded with link error notifications [2]. > > > > > > Cc: <stable+noautosel@xxxxxxxxxx> # Depends on driver stability fixes > > > > This patch is enabling a new feature, it is not a fix, so Bjorn please > > do not include the above tag when applying. > > This is for stopping autosel from picking up the patch, not for > picking it up. After just helping to revert random patches being > picked by autosel I start to like this header. I know what it is, but you should not be adding them to my patches. Johan
