[RFC PATCH 30/38] arm_mpam: resctrl: Call resctrl_exit() in the event of errors
James Morse
james.morse at arm.com
Fri Dec 5 13:58:53 PST 2025
All of MPAMs errors indicate a software bug, e.g. an out-of-bounds
partid has been generated. When this happens, the mpam driver
is disabled.
If resctrl_init() succeeded, also call resctrl_exit() to
remove resctrl.
mpam_devices.c calls mpam_resctrl_teardown_class() when a class
becomes incomplete, and can no longer be used by resctrl. If
resctrl was using this class, then resctrl_exit() is called.
This in turn removes the kernfs hierarchy from the filesystem
and free()s memory that was allocated by resctrl.
Signed-off-by: James Morse <james.morse at arm.com>
---
drivers/resctrl/mpam_devices.c | 32 +++++++++++--
drivers/resctrl/mpam_internal.h | 4 ++
drivers/resctrl/mpam_resctrl.c | 80 +++++++++++++++++++++++++++++++++
3 files changed, 112 insertions(+), 4 deletions(-)
diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
index fccebfd980d8..1334093fc03e 100644
--- a/drivers/resctrl/mpam_devices.c
+++ b/drivers/resctrl/mpam_devices.c
@@ -73,6 +73,14 @@ static DECLARE_WORK(mpam_broken_work, &mpam_disable);
/* When mpam is disabled, the printed reason to aid debugging */
static char *mpam_disable_reason;
+/*
+ * Whether resctrl has been setup. Used by cpuhp in preference to
+ * mpam_is_enabled(). The disable call after an error interrupt makes
+ * mpam_is_enabled() false before the cpuhp callbacks are made.
+ * Reads/writes should hold mpam_cpuhp_state_lock, (or be cpuhp callbacks).
+ */
+static bool mpam_resctrl_enabled;
+
/*
* An MSC is a physical container for controls and monitors, each identified by
* their RIS index. These share a base-address, interrupts and some MMIO
@@ -1627,7 +1635,7 @@ static int mpam_cpu_online(unsigned int cpu)
mpam_reprogram_msc(msc);
}
- if (mpam_is_enabled())
+ if (mpam_resctrl_enabled)
mpam_resctrl_online_cpu(cpu);
return 0;
@@ -1673,7 +1681,7 @@ static int mpam_cpu_offline(unsigned int cpu)
{
struct mpam_msc *msc;
- if (mpam_is_enabled())
+ if (mpam_resctrl_enabled)
mpam_resctrl_offline_cpu(cpu);
guard(srcu)(&mpam_srcu);
@@ -2535,6 +2543,7 @@ static void mpam_enable_once(void)
}
static_branch_enable(&mpam_enabled);
+ mpam_resctrl_enabled = true;
mpam_register_cpuhp_callbacks(mpam_cpu_online, mpam_cpu_offline,
"mpam:online");
@@ -2594,24 +2603,39 @@ void mpam_reset_class(struct mpam_class *class)
void mpam_disable(struct work_struct *ignored)
{
int idx;
+ bool do_resctrl_exit;
struct mpam_class *class;
struct mpam_msc *msc, *tmp;
+ if (mpam_is_enabled())
+ static_branch_disable(&mpam_enabled);
+
mutex_lock(&mpam_cpuhp_state_lock);
if (mpam_cpuhp_state) {
cpuhp_remove_state(mpam_cpuhp_state);
mpam_cpuhp_state = 0;
}
+
+ /*
+ * Removing the cpuhp state called mpam_cpu_offline() and told resctrl
+ * all the CPUs are offline.
+ */
+ do_resctrl_exit = mpam_resctrl_enabled;
+ mpam_resctrl_enabled = false;
mutex_unlock(&mpam_cpuhp_state_lock);
- static_branch_disable(&mpam_enabled);
+ if (do_resctrl_exit)
+ mpam_resctrl_exit();
mpam_unregister_irqs();
idx = srcu_read_lock(&mpam_srcu);
list_for_each_entry_srcu(class, &mpam_classes, classes_list,
- srcu_read_lock_held(&mpam_srcu))
+ srcu_read_lock_held(&mpam_srcu)) {
mpam_reset_class(class);
+ if (do_resctrl_exit)
+ mpam_resctrl_teardown_class(class);
+ }
srcu_read_unlock(&mpam_srcu, idx);
mutex_lock(&mpam_list_lock);
diff --git a/drivers/resctrl/mpam_internal.h b/drivers/resctrl/mpam_internal.h
index 3a68ebd498fa..b13d5e55e701 100644
--- a/drivers/resctrl/mpam_internal.h
+++ b/drivers/resctrl/mpam_internal.h
@@ -450,12 +450,16 @@ int mpam_get_cpumask_from_cache_id(unsigned long cache_id, u32 cache_level,
#ifdef CONFIG_RESCTRL_FS
int mpam_resctrl_setup(void);
+void mpam_resctrl_exit(void);
int mpam_resctrl_online_cpu(unsigned int cpu);
void mpam_resctrl_offline_cpu(unsigned int cpu);
+void mpam_resctrl_teardown_class(struct mpam_class *class);
#else
static inline int mpam_resctrl_setup(void) { return 0; }
+static inline void mpam_resctrl_exit(void) { }
static inline int mpam_resctrl_online_cpu(unsigned int cpu) { return 0; }
static inline void mpam_resctrl_offline_cpu(unsigned int cpu) { }
+static inline void mpam_resctrl_teardown_class(struct mpam_class *class) { }
#endif /* CONFIG_RESCTRL_FS */
/*
diff --git a/drivers/resctrl/mpam_resctrl.c b/drivers/resctrl/mpam_resctrl.c
index eb3caee45470..506063bd3348 100644
--- a/drivers/resctrl/mpam_resctrl.c
+++ b/drivers/resctrl/mpam_resctrl.c
@@ -52,6 +52,12 @@ static bool exposed_mon_capable;
*/
static bool cdp_enabled;
+/*
+ * If resctrl_init() succeeded, resctrl_exit() can be used to remove support
+ * for the filesystem in the event of an error.
+ */
+static bool resctrl_enabled;
+
/*
* L3 local/total may come from different classes - what is the number of MBWU
* 'on L3'?
@@ -310,6 +316,9 @@ static int resctrl_arch_mon_ctx_alloc_no_wait(enum resctrl_event_id evtid)
{
struct mpam_resctrl_mon *mon = &mpam_resctrl_counters[evtid];
+ if (!mpam_is_enabled())
+ return -EINVAL;
+
if (!mon->class)
return -EINVAL;
@@ -352,6 +361,9 @@ static void resctrl_arch_mon_ctx_free_no_wait(enum resctrl_event_id evtid,
{
struct mpam_resctrl_mon *mon = &mpam_resctrl_counters[evtid];
+ if (!mpam_is_enabled())
+ return;
+
if (!mon->class)
return;
@@ -449,6 +461,9 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
resctrl_arch_rmid_read_context_check();
+ if (!mpam_is_enabled())
+ return -EINVAL;
+
if (eventid >= QOS_NUM_EVENTS || !mon->class)
return -EINVAL;
@@ -1343,6 +1358,9 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d,
lockdep_assert_cpus_held();
lockdep_assert_irqs_enabled();
+ if (!mpam_is_enabled())
+ return -EINVAL;
+
/*
* No need to check the CPU as mpam_apply_config() doesn't care, and
* resctrl_arch_update_domains() relies on this.
@@ -1408,6 +1426,9 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
lockdep_assert_cpus_held();
lockdep_assert_irqs_enabled();
+ if (!mpam_is_enabled())
+ return -EINVAL;
+
list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
for (t = 0; t < CDP_NUM_TYPES; t++) {
cfg = &d->staged_config[t];
@@ -1769,11 +1790,70 @@ int mpam_resctrl_setup(void)
}
err = resctrl_init();
+ if (!err)
+ WRITE_ONCE(resctrl_enabled, true);
}
return err;
}
+void mpam_resctrl_exit(void)
+{
+ if (!READ_ONCE(resctrl_enabled))
+ return;
+
+ WRITE_ONCE(resctrl_enabled, false);
+ resctrl_exit();
+}
+
+static void mpam_resctrl_teardown_mon(struct mpam_resctrl_mon *mon, struct mpam_class *class)
+{
+ u32 num_mbwu_mon = l3_num_allocated_mbwu;
+
+ if (!mon->mbwu_idx_to_mon)
+ return;
+
+ if (mon->assigned_counters) {
+ __free_mbwu_mon(class, mon->assigned_counters, num_mbwu_mon);
+ mon->assigned_counters = NULL;
+ kfree(mon->mbwu_idx_to_mon);
+ } else {
+ __free_mbwu_mon(class, mon->mbwu_idx_to_mon, num_mbwu_mon);
+ }
+ mon->mbwu_idx_to_mon = NULL;
+}
+
+/*
+ * The driver is detaching an MSC from this class, if resctrl was using it,
+ * pull on resctrl_exit().
+ */
+void mpam_resctrl_teardown_class(struct mpam_class *class)
+{
+ int i;
+ struct mpam_resctrl_res *res;
+ struct mpam_resctrl_mon *mon;
+
+ might_sleep();
+
+ for (i = 0; i < RDT_NUM_RESOURCES; i++) {
+ res = &mpam_resctrl_controls[i];
+ if (res->class == class) {
+ res->class = NULL;
+ break;
+ }
+ }
+ for (i = 0; i < QOS_NUM_EVENTS; i++) {
+ mon = &mpam_resctrl_counters[i];
+ if (mon->class == class) {
+ mon->class = NULL;
+
+ mpam_resctrl_teardown_mon(mon, class);
+
+ break;
+ }
+ }
+}
+
#ifdef CONFIG_MPAM_KUNIT_TEST
#include "test_mpam_resctrl.c"
#endif
--
2.39.5
More information about the linux-arm-kernel
mailing list