Messages in this thread | | | Date | Fri, 6 Nov 1998 12:15:52 -0500 (EST) | From | "Benjamin C.R. LaHaise" <> | Subject | Re: MAX_DMA_ADDRESS, virt_to_bus (and 3c505.c bug) |
| |
On Fri, 6 Nov 1998, Alan Cox wrote:
> (skb->data+skb->len) > > and you ought to check it doesnt span a page. The 85230 driver has the > right bits in for that now. I've never seen a frame spanning a 64K boundary > on x86, and the mm may actually mean it cant occur.
As all allocations start from a get_free_page, which only returns chunks on their natural boundries (ie 4K on 4K boundry... 64K on 64K boundry). Given that, unless the slab will allocate order > 4 chunks to satisfy packet allocations... and it will. Oh well. At least you can be reasonably sure that the packet won't cross the 16MB barrier.
-ben
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |