rte_lcore_has_role() return value

rte_lcore_has_role() return value

[Morten Brørup]

Pavan,

The rte_lcore_has_role() documentation says it returns bool.

Its implementation returns a true value (-1) if given a non-compliant lcore_id, e.g. LCORE_ID_ANY.

I think it should behave like rte_lcore_is_enabled(), i.e. return false if given a non-compliant lcore_id, e.g. LCORE_ID_ANY.

Use case:
A control thread in an application might or might not register itself, and the registration might not succeed.

At exit of this control thread, it should unregister itself if registered.

Fixing rte_lcore_has_role() as suggested would simplify the application from this:

	if (rte_lcore_id() != LCORE_ID_ANY &&
			rte_eal_lcore_role(rte_lcore_id()) == ROLE_NON_EAL)
		rte_thread_unregister();

To this:

	if (rte_lcore_has_role(rte_lcore_id(), ROLE_NON_EAL))
		rte_thread_unregister();

-Morten

RE: rte_lcore_has_role() return value

[Pavan Nikhilesh Bhagavatula]

Hi Morten, 

Looks like this is meant for Vipin.

+Vipin

Thanks,
Pavan.

> Pavan,
> 
> The rte_lcore_has_role() documentation says it returns bool.
> 
> Its implementation returns a true value (-1) if given a non-compliant lcore_id,
> e.g. LCORE_ID_ANY.
> 
> I think it should behave like rte_lcore_is_enabled(), i.e. return false if given a
> non-compliant lcore_id, e.g. LCORE_ID_ANY.
> 
> Use case:
> A control thread in an application might or might not register itself, and the
> registration might not succeed.
> 
> At exit of this control thread, it should unregister itself if registered.
> 
> Fixing rte_lcore_has_role() as suggested would simplify the application from
> this:
> 
> 	if (rte_lcore_id() != LCORE_ID_ANY &&
> 			rte_eal_lcore_role(rte_lcore_id()) == ROLE_NON_EAL)
> 		rte_thread_unregister();
> 
> To this:
> 
> 	if (rte_lcore_has_role(rte_lcore_id(), ROLE_NON_EAL))
> 		rte_thread_unregister();
> 
> -Morten

RE: rte_lcore_has_role() return value

[Pavan Nikhilesh Bhagavatula]

My bad, I got it confused with lcore topology patches.

I will look into this.

Thanks,
Pavan.

> -----Original Message-----
> From: Pavan Nikhilesh Bhagavatula
> Sent: Monday, May 19, 2025 7:32 PM
> To: Morten Brørup <mb@smartsharesystems.com>; Varghese, Vipin
> <vipin.varghese@amd.com>
> Cc: dev <dev@dpdk.org>
> Subject: RE: rte_lcore_has_role() return value
> 
> Hi Morten,
> 
> Looks like this is meant for Vipin.
> 
> +Vipin
> 
> Thanks,
> Pavan.
> 
> > Pavan,
> >
> > The rte_lcore_has_role() documentation says it returns bool.
> >
> > Its implementation returns a true value (-1) if given a non-compliant
> lcore_id,
> > e.g. LCORE_ID_ANY.
> >
> > I think it should behave like rte_lcore_is_enabled(), i.e. return false if given a
> > non-compliant lcore_id, e.g. LCORE_ID_ANY.
> >
> > Use case:
> > A control thread in an application might or might not register itself, and the
> > registration might not succeed.
> >
> > At exit of this control thread, it should unregister itself if registered.
> >
> > Fixing rte_lcore_has_role() as suggested would simplify the application from
> > this:
> >
> > 	if (rte_lcore_id() != LCORE_ID_ANY &&
> > 			rte_eal_lcore_role(rte_lcore_id()) == ROLE_NON_EAL)
> > 		rte_thread_unregister();
> >
> > To this:
> >
> > 	if (rte_lcore_has_role(rte_lcore_id(), ROLE_NON_EAL))
> > 		rte_thread_unregister();
> >
> > -Morten