From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ingo Molnar Date: Mon, 21 Jan 2002 22:41:03 +0000 Subject: Re: [Linux-ia64] Help with Ingo scheduler on IA64 Message-Id: List-Id: References: In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: linux-ia64@vger.kernel.org On Mon, 21 Jan 2002, David Mosberger wrote: > Ingo> Besides causing the current bug, it was superfluous in the old > Ingo> scheduler as well, so i'm only wondering aloud - perhaps there > Ingo> were more subtle reasons as well? > > No, it wasn't superfluous. It had to re-establish the original state > after disabling interrupts to switch the TLB pinning. since it went in pair with an irq-disable, it was indeed necessery. i think i understand it now. the end result: in the new scheduler it's guaranteed that switch_to() is called with local interrupts disabled, and it's not allowed to reenable them during switch_to(). Ingo