Roland Dreier wrote:
Not sure I understand this:
> +int ipoib_vmalloc(struct ipoib_vmap *buf, int size)
how is this any different than the vmalloc() that already exists? Why
couldn't you just use vmalloc()?
To be honest I don't have an answer. The thought of this passed my mind but
yet it has an exported API in the kernel - I wonder why. So what do you
think of using vmalloc in this case?
_______________________________________________
general mailing list
[email protected]
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
