Re: [PATCH] add PCI ROMs to sysfs

[Jesse Barnes]

On Wednesday, August 4, 2004 8:57 am, Petr Vandrovec wrote:
> Test for failure? Test for no ROM devices?

If we get here, we can be sure there's a ROM device otherwise the 'rom' file 
wouldn't have been created.

> Please read it with readl. At least on my Matrox G550 reading 64KB ROM with
> byte accesses takes 1334ms, with 16bit accesses 840ms and with
> 32bit (or 64bit MMX) accesses 551ms. Straight (non-IO aware) memcpy
> takes 535ms. And put some conditional_schedule()s here, 550ms (or even
> 34ms for 4KB chunk) is IMHO too long.

memcpy_from_io maybe?  That would probably make the most sense.

Thanks for the comments.  Jon, do you want to respin it?

Thanks,
Jesse
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/