On Fri, Mar 01, 2013 at 02:17:16PM -0500, Paul Gortmaker wrote: > On 13-03-01 12:56 AM, Wang YanQing wrote: > > Some UARTs add enhanced functions with unused bit in > > 16550 standard, like UART_IER_UUE bit, it cause XScale > > Which xscale platform? It would be nice to know the specifics. The "XScale" mean the XScale port detect code in autoconfig_16550a, I meet the problem in a normal pc motherboard, I should rephrase the subject use "Fix detect 16550A ports as XScale ports wrong" > > > detect wrong. Now detect UART_IER_UUE and UART_IER_RTOIE > > to reduce the annoying wrong result which cause UARTs don't > > work. > > You should ideally identify the original commit which caused > the regression. Assuming you have fully understood the problem > you should be able to do this with "git blame" and not need to > do the full bisect. > No it is not a regression, it is caused just like you say there are many 8250/16550 variations, and I meet one, that is it. > > > > > Serial controller: Device 4348:3253(CH352 PCI based Multi-I/O Controller) > > is a example. It use UART_IER_UUE as the LOWPOWER function, > > you can get the datasheet from below urls: > > > > http://wch-ic.com/download/list.asp?id=116 > > CH352DS1.PDF > > > > http://wch-ic.com/download/list.asp?id=117 > > CH352DS2.PDF. > > Rather than quote links that will expire and no longer be > valid in six months, it would be better if you described > exactly how and why these ports are different directly in > your commit long log. Device 4348:3253 use the UART_IER_UUE as the LOWPOWER function , so it is readable and writable, quote out the origin words in datasheet. " LOWPOWER:When the bit is 1, close the internal benchmark clock of serial port to set into low-power status. " That is the convict cause our XScale detect code work wrong. > What does your change do to Xscale that do not do UART_IER_RTOIE? Yes, you are right, I don't have experience with Xscale, so I will fix the problem in another way, set it fix type in 8250_pci code maybe is good. Thanks. -- To unsubscribe from this list: send the line "unsubscribe linux-serial" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html