Re: [PATCH v5 26/41] arm_mpam: resctrl: Add monitor initialisation and domain boilerplate
From: Zeng Heng
Date: Thu Feb 26 2026 - 22:02:10 EST
Hi Ben,
On 2026/2/26 18:26, Ben Horgan wrote:
Hi Zeng,
On 2/26/26 03:47, Zeng Heng wrote:
Hi Ben,
On 2026/2/25 1:57, Ben Horgan wrote:
Add the boilerplate that tells resctrl about the mpam monitors that are
available. resctrl expects all (non-telemetry) monitors to be on the
L3 and
so advertise them there and invent an L3 resctrl resource if required.
The
L3 cache itself has to exist as the cache ids are used as the domain
ids.
Bring the resctrl monitor domains online and offline based on the cpus
they contain.
Support for specific monitor types is left to later.
Signed-off-by: Ben Horgan <ben.horgan@xxxxxxx>
---
New patch but mostly moved from the existing patches to
separate the monitors from the controls and the boilerplate
from the specific counters.
Use l3->mon_capable in resctrl_arch_mon_capable() as
resctrl_enable_mon_event() now returns a bool.
---
drivers/resctrl/mpam_internal.h | 7 ++
drivers/resctrl/mpam_resctrl.c | 142 +++++++++++++++++++++++++++++---
2 files changed, 139 insertions(+), 10 deletions(-)
[...]
@@ -922,6 +1000,20 @@ mpam_resctrl_alloc_domain(unsigned int cpu,
struct mpam_resctrl_res *res)
} else {
pr_debug("Skipped control domain online - no controls\n");
}
+
+ if (resctrl_arch_mon_capable()) {
+ mon_d = &dom->resctrl_mon_dom;
+ mpam_resctrl_domain_hdr_init(cpu, any_mon_comp, r->rid,
&mon_d->hdr);
+ mon_d->hdr.type = RESCTRL_MON_DOMAIN;
+ err = resctrl_online_mon_domain(r, &mon_d->hdr);
+ if (err)
+ goto offline_ctrl_domain;
+
+ mpam_resctrl_domain_insert(&r->mon_domains, &mon_d->hdr);
+ } else {
+ pr_debug("Skipped monitor domain online - no monitors\n");
+ }
+
return dom;
I noticed that resctrl_arch_mon_capable() only performs checks for L3
monitoring functionality. This leads to an issue on platforms that
include L2 monitoring capabilities, where the code incorrectly enters
this branch and triggers the following warning by
mpam_resctrl_domain_insert():
[ 22.867070] ------------[ cut here ]------------
[ 22.867073] WARNING: drivers/resctrl/mpam_resctrl.c:1495 at
mpam_resctrl_domain_insert+0x74/0x80, CPU#2: cpuhp/2/25
[ 29.376035] Modules linked in:
[ 29.379080] CPU: 2 UID: 0 PID: 25 Comm: cpuhp/2 Not tainted 7.0.0-
rc1-g4288ec146462 #30 PREEMPT
[ 29.387853] Hardware name: To Be Filled By O.E.M. 183.0/To Be Filled
By O.E.M., BIOS 183.0 02/12/2026
[ 29.397058] pstate: 61400009 (nZCv daif +PAN -UAO -TCO +DIT -SSBS
BTYPE=--)
[ 29.404007] pc : mpam_resctrl_domain_insert+0x74/0x80
[ 29.409048] lr : mpam_resctrl_domain_insert+0x34/0x80
[ 29.414088] sp : ffff8000876abc60
...
[ 29.488625] Call trace:
[ 29.491060] mpam_resctrl_domain_insert+0x74/0x80 (P)
[ 29.496100] mpam_resctrl_online_cpu+0x2b4/0x428
[ 29.500706] mpam_cpu_online+0x274/0x298
[ 29.504618] cpuhp_invoke_callback+0x104/0x20c
[ 29.509052] cpuhp_thread_fun+0xa4/0x17c
[ 29.512963] smpboot_thread_fn+0x220/0x24c
[ 29.517048] kthread+0x120/0x12c
[ 29.520265] ret_from_fork+0x10/0x20
[ 29.523830] ---[ end trace 0000000000000000 ]---
Thanks for reporting this bug. It looks to be because resctrl_arch_mon_capable() is telling us if
there is any mon capable resource when really what we want to know is if this resource is mon capable.
The pattern occurs in a few places. Does this diff help?
I've adapted to the changes and local verification passes also.
diff --git a/drivers/resctrl/mpam_resctrl.c b/drivers/resctrl/mpam_resctrl.c
index 694ea8548a05..19b306017845 100644
--- a/drivers/resctrl/mpam_resctrl.c
+++ b/drivers/resctrl/mpam_resctrl.c
@@ -1543,7 +1543,7 @@ mpam_resctrl_alloc_domain(unsigned int cpu, struct mpam_resctrl_res *res)
if (!dom)
return ERR_PTR(-ENOMEM);
- if (resctrl_arch_alloc_capable()) {
+ if (r->alloc_capable) {
Yes, using r->alloc_capable and r->mon_capable here is indeed more
accurate and appropriate. I should have noticed this when reviewing
resctrl_arch_alloc_capable() and resctrl_arch_mon_capable().
Reviewed-by: Zeng Heng <zengheng4@xxxxxxxxxx>
Thanks,
Zeng Heng
dom->ctrl_comp = ctrl_comp;
ctrl_d = &dom->resctrl_ctrl_dom;
@@ -1558,7 +1558,7 @@ mpam_resctrl_alloc_domain(unsigned int cpu, struct mpam_resctrl_res *res)
pr_debug("Skipped control domain online - no controls\n");
}
- if (resctrl_arch_mon_capable()) {
+ if (r->mon_capable) {
struct mpam_component *any_mon_comp;
struct mpam_resctrl_mon *mon;
enum resctrl_event_id eventid;
@@ -1603,7 +1603,7 @@ mpam_resctrl_alloc_domain(unsigned int cpu, struct mpam_resctrl_res *res)
return dom;
offline_ctrl_domain:
- if (resctrl_arch_alloc_capable()) {
+ if (r->alloc_capable) {
mpam_resctrl_offline_domain_hdr(cpu, &ctrl_d->hdr);
resctrl_offline_ctrl_domain(r, ctrl_d);
}
@@ -1671,6 +1671,7 @@ int mpam_resctrl_online_cpu(unsigned int cpu)
guard(mutex)(&domain_list_lock);
for_each_mpam_resctrl_control(res, rid) {
struct mpam_resctrl_dom *dom;
+ struct rdt_resource *r = &res->resctrl_res;
if (!res->class)
continue; // dummy_resource;
@@ -1679,12 +1680,12 @@ int mpam_resctrl_online_cpu(unsigned int cpu)
if (!dom) {
dom = mpam_resctrl_alloc_domain(cpu, res);
} else {
- if (resctrl_arch_alloc_capable()) {
+ if (r->alloc_capable) {
struct rdt_ctrl_domain *ctrl_d = &dom->resctrl_ctrl_dom;
mpam_resctrl_online_domain_hdr(cpu, &ctrl_d->hdr);
}
- if (resctrl_arch_mon_capable()) {
+ if (r->mon_capable) {
struct rdt_l3_mon_domain *mon_d = &dom->resctrl_mon_dom;
mpam_resctrl_online_domain_hdr(cpu, &mon_d->hdr);
@@ -1712,6 +1713,7 @@ void mpam_resctrl_offline_cpu(unsigned int cpu)
struct rdt_l3_mon_domain *mon_d;
struct rdt_ctrl_domain *ctrl_d;
bool ctrl_dom_empty, mon_dom_empty;
+ struct rdt_resource *r = &res->resctrl_res;
if (!res->class)
continue; // dummy resource
@@ -1720,7 +1722,7 @@ void mpam_resctrl_offline_cpu(unsigned int cpu)
if (WARN_ON_ONCE(!dom))
continue;
- if (resctrl_arch_alloc_capable()) {
+ if (r->alloc_capable) {
ctrl_d = &dom->resctrl_ctrl_dom;
ctrl_dom_empty = mpam_resctrl_offline_domain_hdr(cpu, &ctrl_d->hdr);
if (ctrl_dom_empty)
@@ -1729,7 +1731,7 @@ void mpam_resctrl_offline_cpu(unsigned int cpu)
ctrl_dom_empty = true;
}
- if (resctrl_arch_mon_capable()) {
+ if (r->mon_capable) {
mon_d = &dom->resctrl_mon_dom;
mon_dom_empty = mpam_resctrl_offline_domain_hdr(cpu, &mon_d->hdr);
if (mon_dom_empty)
To preserve the existing public interface of resctrl_arch_mon_capable(),
please consider the following approach:
diff --git a/drivers/resctrl/mpam_resctrl.c b/drivers/resctrl/
mpam_resctrl.c
index 694ea8548a05..b06a89494ff0 100644
--- a/drivers/resctrl/mpam_resctrl.c
+++ b/drivers/resctrl/mpam_resctrl.c
@@ -1563,6 +1563,10 @@ mpam_resctrl_alloc_domain(unsigned int cpu,
struct mpam_resctrl_res *res)
if (resctrl_arch_mon_capable()) {
struct mpam_component *any_mon_comp;
struct mpam_resctrl_mon *mon;
enum resctrl_event_id eventid;
+ /* TODO: Only supports L3 monitor type currently. */
+ if (r->rid != RDT_RESOURCE_L3)
+ return dom;
Best regards,
Zeng Heng
Thanks,
Ben