Re: [PATCH v3 06/12] fs/resctrl: Initialize the global kernel-mode policy at subsystem init

[Babu Moger]

Hi Reinette,


On 6/16/26 18:36, Reinette Chatre wrote:
> Hi Babu,
>
> On 4/30/26 4:24 PM, Babu Moger wrote:
> > kernel_mode feature needs to add the interface that lets user space
> > choose between INHERIT_CTRL_AND_MON, GLOBAL_ASSIGN_CTRL_INHERIT_MON_PER_CPU
> > and GLOBAL_ASSIGN_CTRL_ASSIGN_MON_PER_CPU.  Both the generic resctrl
> > code and the architecture layer need a single shared snapshot of the
> > supported and effective policy plus the resource group that backs the
> > global-assign modes; that snapshot is struct resctrl_kmode_cfg.
>
> This does not seem to match implementation since this implementation does
> not actually share struct resctrl_kmode_cfg as described above. Only
> resctrl_arch_get_kmode_support() exchanges this struct between fs and
> arch and as already mentioned that usage looks unnecessary. The other
> arch/fs touch points use either individual members or their properties
> (like closid/rmid).
>
> As described in response to previous patch I think this can be simplified
> while also making it more robust.

Ack.

> > Add the file-local resctrl_kcfg and a helper resctrl_kmode_init() that:
> >
> >    - Adds kmode and kmode_cur with BIT(INHERIT_CTRL_AND_MON), the
> >      universally supported mode and today's behaviour;
> >    - points k_rdtgrp at rdtgroup_default so global-assign modes have a
> >      valid backing group from boot;
>
> If the default mode is INHERIT_CTRL_AND_MON then should the default group
> not be NULL?

It will be initialized to NULL.

> >    - calls resctrl_arch_get_kmode_support() so each architecture ORs
> >      BIT(<mode>) into kmode for the policies its hardware supports
> >      (on x86, AMD PLZA contributes the two global-assign modes).
> >
> > resctrl_kmode_init() runs from resctrl_init() once the default group
>
> resctrl_kmode_init() can be dropped after changes described in response
> to previous patch. Apart from no longer being necessary I also find that
> having the kernel mode fully initialized *before* the hotplug handlers run
> to be simpler.

That means resctrl_set_kmode_support() will be called from the 
architecture layer, likely from core.c within get_rdt_alloc_resources().

The resctrl_set_kmode_support() handler would need to initialize both 
the default mode and all supported modes.

I see that this is where the hotplug handler gets registered. Therefore, 
the modes are already initialized before the hotplug handler is set up.

> > has been set up.  No user-visible behaviour changes yet; later patches
>
> (drop "later patches ...")

Sure.

Thanks
Babi