mpc85xx_edac.c: Should the mpc85xx_l2_isr be shared irqs?

mpc85xx_edac.c: Should the mpc85xx_l2_isr be shared irqs?

[Xufeng Zhang]

Hi All,

I detected below error when booting p1021mds after enabled EDAC feature:
EDAC MC: Ver: 2.1.0 Jul 17 2012
Freescale(R) MPC85xx EDAC driver, (C) 2006 Montavista Software
EDAC MC0: Giving out device to 'MPC85xx_edac' 'mpc85xx_mc_err': DEV mpc85xx_mc_e
rr
IRQ 45/[EDAC] MC err: IRQF_DISABLED is not guaranteed on shared IRQs
MPC85xx_edac acquired irq 45 for MC
MPC85xx_edac MC err registered
EDAC DEVICE0: Giving out device to module 'MPC85xx_edac' controller 'mpc85xx_l2_
err': DEV 'mpc85xx_l2_err' (INTERRUPT)
mpc85xx_l2_err_probe: Unable to requiest irq 45 for MPC85xx L2 err

Then kernel hang.

When request irq for l2-cache, since it share the same irq with memory
controller,
I think the code should be:
--- a/drivers/edac/mpc85xx_edac.c
+++ b/drivers/edac/mpc85xx_edac.c
@@ -577,7 +577,7 @@ static int __devinit mpc85xx_l2_err_probe(struct
of_device *op,
 	if (edac_op_state == EDAC_OPSTATE_INT) {
 		pdata->irq = irq_of_parse_and_map(op->node, 0);
 		res = devm_request_irq(&op->dev, pdata->irq,
-				       mpc85xx_l2_isr, IRQF_DISABLED,
+				       mpc85xx_l2_isr, IRQF_DISABLED | IRQF_SHARED,
 				       "[EDAC] L2 err", edac_dev);
 		if (res < 0) {
 			printk(KERN_ERR





Thanks,
Xufeng Zhang

Re: mpc85xx_edac.c: Should the mpc85xx_l2_isr be shared irqs?

[Scott Wood]

On Wed, Jul 18, 2012 at 05:00:29PM +0800, Xufeng Zhang wrote:
> Hi All,
> 
> I detected below error when booting p1021mds after enabled EDAC feature:
> EDAC MC: Ver: 2.1.0 Jul 17 2012
> Freescale(R) MPC85xx EDAC driver, (C) 2006 Montavista Software
> EDAC MC0: Giving out device to 'MPC85xx_edac' 'mpc85xx_mc_err': DEV mpc85xx_mc_e
> rr
> IRQ 45/[EDAC] MC err: IRQF_DISABLED is not guaranteed on shared IRQs
> MPC85xx_edac acquired irq 45 for MC
> MPC85xx_edac MC err registered
> EDAC DEVICE0: Giving out device to module 'MPC85xx_edac' controller 'mpc85xx_l2_
> err': DEV 'mpc85xx_l2_err' (INTERRUPT)
> mpc85xx_l2_err_probe: Unable to requiest irq 45 for MPC85xx L2 err
> 
> Then kernel hang.
> 
> When request irq for l2-cache, since it share the same irq with memory
> controller,
> I think the code should be:
>  			printk(KERN_ERR
> 
> 
> 
> 
> 
> Thanks,
> Xufeng Zhang
> 
> 
> --- a/drivers/edac/mpc85xx_edac.c
> +++ b/drivers/edac/mpc85xx_edac.c
> @@ -577,7 +577,7 @@ static int __devinit mpc85xx_l2_err_probe(struct
> of_device *op,
>  	if (edac_op_state == EDAC_OPSTATE_INT) {
>  		pdata->irq = irq_of_parse_and_map(op->node, 0);
>  		res = devm_request_irq(&op->dev, pdata->irq,
> -				       mpc85xx_l2_isr, IRQF_DISABLED,
> +				       mpc85xx_l2_isr, IRQF_DISABLED | IRQF_SHARED,
>  				       "[EDAC] L2 err", edac_dev);
>  		if (res < 0) {

Sorry for the delayed response...  That "IRQF_DISABLED is not guaranteed"
message was removed in v2.6.35 (along with the rest of IRQF_DISABLED
support) which was almost two years old even back when your e-mail was
sent.  Even back then, as far as I can tell your patch would be
introducing, not fixing, that message.

It does look like this interrupt should be shared, though.

The deprecated IRQF_DISABLED should be removed.

-Scott