Messages in this thread |  | | Date | Mon, 16 Oct 2000 17:40:47 +0100 | From | Stephen Tweedie <> | Subject | Re: mapping user space buffer to kernel address space |
| |
Hi,
On Fri, Oct 13, 2000 at 12:30:49PM +0100, Malcolm Beattie wrote:
> free_kiovec(1, &iobuf); /* does an implicit unlock_kiovec */ > > It doesn't do an unmap_kiobuf(iobuf) so I don't understand where > the per-page map->count that map_user_kiobuf incremented gets > decremented again. Anyone?
The 2.4 raw code I'm looking at does an explicit unmap_kiobuf after each brw_kiovec().
> Lowlevel I/O on a kiovec can be done > with something like an ll_rw_kiovec which sct said was going to get > put in but since I haven't read anything more recent than > 2.4.0-test5 at the moment, I can't say if it's there or what it > looks like.
It's being maintained inside the SGI XFS tree right now. They've got it pretty stable under XFS load so I'll probably put together the ll_rw_kio functionality using their low level code the next time I do a kiovec release. I believe that the XFS tree has 2.4.0-test9 support for this code.
Cheers, Stephen - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org Please read the FAQ at http://www.tux.org/lkml/
|  |