From mboxrd@z Thu Jan 1 00:00:00 1970 From: arnd@arndb.de (Arnd Bergmann) Date: Tue, 4 Feb 2014 20:27:15 +0100 Subject: [PATCH 09/10] watchdog: xilinx: Add missing binding In-Reply-To: <4c4539fe-e810-4c0a-9a01-c1e4c67ea661@AM1EHSMHS007.ehs.local> References: <3121595.GbLMuGPlvA@wuerfel> <4c4539fe-e810-4c0a-9a01-c1e4c67ea661@AM1EHSMHS007.ehs.local> Message-ID: <201402042027.15898.arnd@arndb.de> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Monday 03 February 2014, Michal Simek wrote: > On 02/03/2014 04:32 PM, Arnd Bergmann wrote: > > On Monday 03 February 2014 16:13:47 Michal Simek wrote: > >> Intention wasn't to fix binding but document current one > >> which is in mainline for a long time. > > > > Ok, I see. > > > >> Apart of this - yes, wdt-enable-once is nowayout and wdt-interval should be timeout > >> is seconds, and clock-frequency should go out and use CCF for getting clock. > > > > Could we make a common binding then, and document that the xilinx > > watchdog can optionally provide either one? > > Do you mean to have 2 DT bindings? > > This binding is used from 2011-07. > It means it was generated for all hw designs at least from this time. > I would say from DT usage on Microblaze because it is not special case > in our dt generator. I certainly wasn't suggesting to break the binding, quite the contrary. What I tried to say is that the properties look like they should be useful for different kinds of watchdogs, not just xilinx, so it would be good to have a common definition using generic strings. The xilinx driver would definitely have to keep supporting the traditional property names, but it could also support the generic names in the future. > xlnx,XXX are XXX parameters which you have to setup in tools > and get synthesized. This is valid for all xilinx IPs. We have full > IP description by generating xlnx,XXX parameters directly from tools > because we know all variants which can happen. > > Just back to your previous post: > "I'm not sure about the enable-once flag, which seems to just map to the > "nowayout" watchdog option that is not a hardware feature at all" > this is hw feature which you can select in tools because this is fpga. :-) Ah, so you mean the properties are not settings that the driver programs into the hardware, but they are hardware properties that the driver reports to user space? Arnd From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arnd Bergmann Subject: Re: [PATCH 09/10] watchdog: xilinx: Add missing binding Date: Tue, 4 Feb 2014 20:27:15 +0100 Message-ID: <201402042027.15898.arnd@arndb.de> References: <3121595.GbLMuGPlvA@wuerfel> <4c4539fe-e810-4c0a-9a01-c1e4c67ea661@AM1EHSMHS007.ehs.local> Mime-Version: 1.0 Content-Type: Text/Plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <4c4539fe-e810-4c0a-9a01-c1e4c67ea661@AM1EHSMHS007.ehs.local> Sender: linux-doc-owner@vger.kernel.org To: Michal Simek Cc: linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, monstr@monstr.eu, Mark Rutland , devicetree@vger.kernel.org, Pawel Moll , Ian Campbell , linux-doc@vger.kernel.org, Rob Herring , Rob Landley , Kumar Gala List-Id: devicetree@vger.kernel.org On Monday 03 February 2014, Michal Simek wrote: > On 02/03/2014 04:32 PM, Arnd Bergmann wrote: > > On Monday 03 February 2014 16:13:47 Michal Simek wrote: > >> Intention wasn't to fix binding but document current one > >> which is in mainline for a long time. > > > > Ok, I see. > > > >> Apart of this - yes, wdt-enable-once is nowayout and wdt-interval should be timeout > >> is seconds, and clock-frequency should go out and use CCF for getting clock. > > > > Could we make a common binding then, and document that the xilinx > > watchdog can optionally provide either one? > > Do you mean to have 2 DT bindings? > > This binding is used from 2011-07. > It means it was generated for all hw designs at least from this time. > I would say from DT usage on Microblaze because it is not special case > in our dt generator. I certainly wasn't suggesting to break the binding, quite the contrary. What I tried to say is that the properties look like they should be useful for different kinds of watchdogs, not just xilinx, so it would be good to have a common definition using generic strings. The xilinx driver would definitely have to keep supporting the traditional property names, but it could also support the generic names in the future. > xlnx,XXX are XXX parameters which you have to setup in tools > and get synthesized. This is valid for all xilinx IPs. We have full > IP description by generating xlnx,XXX parameters directly from tools > because we know all variants which can happen. > > Just back to your previous post: > "I'm not sure about the enable-once flag, which seems to just map to the > "nowayout" watchdog option that is not a hardware feature at all" > this is hw feature which you can select in tools because this is fpga. :-) Ah, so you mean the properties are not settings that the driver programs into the hardware, but they are hardware properties that the driver reports to user space? Arnd