Re: [RFC] cxl-host: Fix committed check for passthrough decoder

2023-01-20 Thread Jonathan Cameron via
On Mon, 16 Jan 2023 14:37:23 + Jonathan Cameron via wrote: > On Fri, 13 Jan 2023 17:10:51 + > Fan Ni wrote: > > > On Fri, Jan 13, 2023 at 09:47:25AM +, Jonathan Cameron wrote: > > > > > On Fri, 13 Jan 2023 00:27:55 + > > > Fan Ni wrote: > > > > > > > For passthrough dec

Re: [RFC] cxl-host: Fix committed check for passthrough decoder

2023-01-16 Thread Jonathan Cameron via
On Fri, 13 Jan 2023 17:10:51 + Fan Ni wrote: > On Fri, Jan 13, 2023 at 09:47:25AM +, Jonathan Cameron wrote: > > > On Fri, 13 Jan 2023 00:27:55 + > > Fan Ni wrote: > > > > > For passthrough decoder (a decoder hosted by a cxl component with only > > > one downstream port), its cac

Re: [RFC] cxl-host: Fix committed check for passthrough decoder

2023-01-13 Thread Fan Ni
On Fri, Jan 13, 2023 at 09:47:25AM +, Jonathan Cameron wrote: > On Fri, 13 Jan 2023 00:27:55 + > Fan Ni wrote: > > > For passthrough decoder (a decoder hosted by a cxl component with only > > one downstream port), its cache_mem_registers field COMMITTED > > (see spec 2.0 8.2.5.12 - CXL H

Re: [RFC] cxl-host: Fix committed check for passthrough decoder

2023-01-13 Thread Jonathan Cameron via
On Fri, 13 Jan 2023 00:27:55 + Fan Ni wrote: > For passthrough decoder (a decoder hosted by a cxl component with only > one downstream port), its cache_mem_registers field COMMITTED > (see spec 2.0 8.2.5.12 - CXL HDM Decoder Capability Structure) will not > be set by the current Linux CXL dri

[RFC] cxl-host: Fix committed check for passthrough decoder

2023-01-12 Thread Fan Ni
For passthrough decoder (a decoder hosted by a cxl component with only one downstream port), its cache_mem_registers field COMMITTED (see spec 2.0 8.2.5.12 - CXL HDM Decoder Capability Structure) will not be set by the current Linux CXL driver. Without the fix, for a cxl topology setup with a singl