Re: [PATCH 45/62] net: irq: Remove IRQF_DISABLED

On Wed, Sep 07, 2011 at 08:03:14PM +0200, Thomas Gleixner wrote:

On Wed, 7 Sep 2011, David Miller wrote:

quoted

From: Thomas Gleixner <redacted>
Date: Wed, 7 Sep 2011 19:32:39 +0200 (CEST)

quoted

On Wed, 7 Sep 2011, David Miller wrote:

quoted

From: Yong Zhang <redacted>
Date: Wed,  7 Sep 2011 16:10:42 +0800

quoted

This flag is a NOOP and can be removed now.

Signed-off-by: Yong Zhang <redacted>

I have the same concerns here as I had for the sparc case.

Some of these drivers might be using IRQF_DISABLED to make sure the
IRQ cannot be delivered until it is explicitly enabled via an
enable_irq() call.

How is that being accomodated now?

Again IRQF_DISABLED never ever had that functionality. 

My bad.

But what if these interrupts want interrupts disabled during their
interrupt handler, for other reasons?

We run ALL interrupt handlers with irqs disabled always.
 

quoted

This has the potential to break tons of stuff, especially on the
really old chips which almost no developers have any more but some
user might try to use.

It won't. We removed IRQF_DISABLED from kernel/irq/* long ago

Yeah, and this is why we say it's a NOOP now :)

Thanks,
Yong