Posted Sep 9, 2004 20:14 UTC (Thu) by giraffedata
Parent article: NETIF_F_LLTX
That sounds exactly like what Linus and others in charge have resoundingly rejected over the years - interfaces where the callee indicates whether he needs the caller to guarantee serialization or not. Many such changes were proposed in the early days of the Big Kernel Lock as a way to let some modules escape the performance tyranny of the BKL while letting others escape the programming hassle of designing for parallel operation. None were ever accepted.
It seems to me that, consistent with that philosophy, instead of adding NETIF_F_LLTX, all the drivers would be changed simultaneously to do their own transmit locking (and, as usual, to hell with the drivers that aren't available for modification to the person making that change).
Or is this something different?
to post comments)