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

From: Moger, Babu
Date: Fri Oct 18 2024 - 10:23:19 EST


Hi Reinette,

On 10/15/2024 10:30 PM, Reinette Chatre wrote:
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@xxxxxxx>
---
...

---
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.

Sure.


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.

Sure. Right after rmdir_all_sub().


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


Thanks
- Babu Moger