Re: [PATCH v8 19/25] x86/resctrl: Auto assign/unassign counters when mbm_cntr_assign is enabled

[Reinette Chatre <reinette.chatre@intel.com>]

Hi Babu,

On 10/9/24 10:39 AM, Babu Moger wrote:
> Assign/unassign counters on resctrl group creation/deletion. Two counters
> are required per group, one for MBM total event and one for MBM local
> event.
> 
> There are a limited number of counters available for assignment. If these
> counters are exhausted, the kernel will display the error message: "Out of
> MBM assignable counters". However, it is not necessary to fail the
> creation of a group due to assignment failures. Users have the flexibility
> to modify the assignments at a later time.
> 
> Signed-off-by: Babu Moger <babu.moger@amd.com>
> ---
...

> ---
>  arch/x86/kernel/cpu/resctrl/rdtgroup.c | 64 ++++++++++++++++++++++++++
>  1 file changed, 64 insertions(+)
> 
> diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> index 791258adcbda..cb2c60c0319e 100644
> --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c

...

>  static int rdt_get_tree(struct fs_context *fc)
>  {
>  	struct rdt_fs_context *ctx = rdt_fc2context(fc);
> @@ -2934,6 +2980,8 @@ static int rdt_get_tree(struct fs_context *fc)
>  		if (ret < 0)
>  			goto out_mongrp;
>  		rdtgroup_default.mon.mon_data_kn = kn_mondata;
> +
> +		rdtgroup_assign_cntrs(&rdtgroup_default);
>  	}
>  
>  	ret = rdt_pseudo_lock_init();
> @@ -2964,6 +3012,7 @@ static int rdt_get_tree(struct fs_context *fc)
>  out_psl:
>  	rdt_pseudo_lock_release();
>  out_mondata:
> +	rdtgroup_unassign_cntrs(&rdtgroup_default);
>  	if (resctrl_arch_mon_capable())
>  		kernfs_remove(kn_mondata);

I think I mentioned this before ... this addition belongs within the
"if (resctrl_arch_mon_capable())" to be symmetrical with where it was called from.

>  out_mongrp:
> @@ -3144,6 +3193,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
>  
>  	head = &rdtgrp->mon.crdtgrp_list;
>  	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
> +		rdtgroup_unassign_cntrs(sentry);
>  		free_rmid(sentry->closid, sentry->mon.rmid);
>  		list_del(&sentry->mon.crdtgrp_list);
>  
> @@ -3184,6 +3234,8 @@ static void rmdir_all_sub(void)
>  		cpumask_or(&rdtgroup_default.cpu_mask,
>  			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
>  
> +		rdtgroup_unassign_cntrs(rdtgrp);
> +
>  		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
>  
>  		kernfs_remove(rdtgrp->kn);
> @@ -3223,6 +3275,8 @@ static void rdt_kill_sb(struct super_block *sb)
>  		resctrl_arch_disable_alloc();
>  	if (resctrl_arch_mon_capable())
>  		resctrl_arch_disable_mon();
> +
> +	rdtgroup_unassign_cntrs(&rdtgroup_default);

Unassigning counters after monitoring is completely disabled seems late. I
think this can be moved earlier to be right after the counters of all the
other groups are unassigned.

>  	resctrl_mounted = false;
>  	kernfs_kill_sb(sb);
>  	mutex_unlock(&rdtgroup_mutex);
> @@ -3814,6 +3868,8 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
>  		goto out_unlock;
>  	}
>  
> +	rdtgroup_assign_cntrs(rdtgrp);
> +
>  	kernfs_activate(rdtgrp->kn);
>  
>  	/*
> @@ -3858,6 +3914,8 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
>  	if (ret)
>  		goto out_closid_free;
>  
> +	rdtgroup_assign_cntrs(rdtgrp);
> +
>  	kernfs_activate(rdtgrp->kn);
>  
>  	ret = rdtgroup_init_alloc(rdtgrp);
> @@ -3883,6 +3941,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
>  out_del_list:
>  	list_del(&rdtgrp->rdtgroup_list);
>  out_rmid_free:
> +	rdtgroup_unassign_cntrs(rdtgrp);
>  	mkdir_rdt_prepare_rmid_free(rdtgrp);
>  out_closid_free:
>  	closid_free(closid);
> @@ -3953,6 +4012,9 @@ static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
>  	update_closid_rmid(tmpmask, NULL);
>  
>  	rdtgrp->flags = RDT_DELETED;
> +
> +	rdtgroup_unassign_cntrs(rdtgrp);
> +
>  	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
>  
>  	/*
> @@ -3999,6 +4061,8 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
>  	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
>  	update_closid_rmid(tmpmask, NULL);
>  
> +	rdtgroup_unassign_cntrs(rdtgrp);
> +
>  	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
>  	closid_free(rdtgrp->closid);
>  

Reinette