Re: Gut crypto_yeild() when CONFIG_PREEMPT is defined?

[William Lee Irwin III <wli@xxxxxxxxxxxxxx>]

On Wed, Jul 14, 2004 at 03:17:25PM -0700, Adam J. Richter wrote:
> 	I don't understand the benefit of the change you have
> described.  The benefit of the change I described is that it would
> eliminate some instructions, making encryption and decryption run
> a bit faster in the CONFIG_PREEMPT case.

The BKL must be dropped voluntarily, e.g. via schedule() or
unlock_kernel(), to allow preemption when the BKL is held.


-- wli

-
Linux-crypto:  cryptography in and on the Linux system
Archive:       http://mail.nl.linux.org/linux-crypto/