Re: [RFC] new bus architecture (+ byte-endianess)

David S. Miller (davem@redhat.com)
Mon, 7 Jun 1999 16:41:22 -0700


Date: Tue, 8 Jun 1999 00:37:49 +0200
From: Martin Mares <mj@ucw.cz>

BTW what should happen if the IOMMU address space is full? I
guess we cannot block in acquire_dma() since it can be run from a
BH.

In the ports where we do have to allocate IOMMU space, this condition
is considered hard and irrecoverable fatal error. In all of our
stress testing it has never been triggered.

And I think it should remain this way, there is no reason we should
now ask all these drivers to check return codes from these interfaces,
because on many systems we'd like it to be just a NOP empty macro.

Later,
David S. Miller
davem@redhat.com

-
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/