Re: [PATCH v3 0/4] New vendor support and optimizations for DWC PCIe PMU
"Yicong Yang" <[email protected]> Mon, 3 Aug 2026 16:35:52 +0800
| Newsgroups | org.kernel.vger.linux-pci,org.kernel.vger.linux-kernel |
|---|---|
| Message-ID | <[email protected]> |
On 8/1/26 7:28 PM, Will Deacon wrote: > On Wed, 08 Jul 2026 16:45:02 +0800, Yicong Yang wrote: >> This patchset mainly enable the DWC PCIe PMU on our platform (Patch 1/4). >> Besides do some optimization and refactor: >> - Patch 2/4 extend the monitoring limit on platforms with narrowed counter width (< 64 bit) >> - Patch 3/4 switch the driver to use the faux device interface >> - Patch 4/4 fix an old issue that PMU may counting when corresponding root port >> is runtime suspended. >> >> [...] > > Applied first two patches to arm64 (for-next/perf), thanks! > > [1/4] perf/dwc_pcie: Add support for Picoheart vendor devices > https://git.kernel.org/arm64/c/cf65b4d765b5 > [2/4] perf/dwc_pcie: Support narrowed time-based counter for long time monitoring > https://git.kernel.org/arm64/c/18ec1f543ae1 > > I haven't understood what you gain from the third patch. If it's purely > a dependency for the final patch, then Sashiko has left some comments > on that one: > > https://lore.kernel.org/all/[email protected]/ sure, will have a further check (these are "pre-existing" issues as reported by sashiko) and respin a new version for patch 3/4. it's a cleanup found when adding support for our platform. this driver looks to fall into the case where faux device aims to cover [1]. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/include/linux/device/faux.h#n6 thanks.