Messages in this thread | | | Date | Thu, 19 Apr 2012 23:18:39 +0200 | From | Roland Stigge <> | Subject | Re: [PATCH v4] i2c: Add device tree support to i2c-pnx.c |
| |
Hi!
On 19/04/12 22:39, Wolfram Sang wrote: >> If we have a solution soon, I will prepare a new version of the >> patch, of course, in the next days. > > Thanks. One question, though: Will it really block dt-conversion? > The whole conversion should not be depending on the i2c-driver?
Technically, it would certainly be possible to convert some drivers and leave others. But I would highly prefer to convert i2c also. With LPC32xx, there are typically many I2C clients depending on DT on a reasonable DT enabled mach.
I'm fine with "timeout" also, when you accept it into pnx-i2c.c and will certainly provide a "timeout" patch update so you can pick the version which suits best.
Another solution would be to not use timeout with the dt enabled i2c-pnx for now (using the hard coded default timeout as the current i2c-pnx.c does) and possibly introduce the (anyway optional) "timeout" later.
Actually, that would be my favour.
What do you think?
>>> Did you change this, too? Timeouts are better readable in dec >>> :) >> >> Right. But even when removing the "0x" in the timeout line >> above, it's still hex, see >> Documentation/devicetree/booting-without-of.txt >> >> Or did I get sth. wrong? > > I think the document is probably outdated :( "clock-frequency" is > also without 0x and dec.
Interesting! When the documentation is outdated - how does the parser actually decide between hex (e.g. regs/addresses) and dec (e.g. clock-frequency) in the absence of "0x"?
Thanks in advance,
Roland
| |