From: James Morse <james.morse@arm.com>

cpuhp callbacks aren't the only time the MSC configuration may need to
be reset. Resctrl has an API call to reset a class.
If an MPAM error interrupt arrives it indicates the driver has
misprogrammed an MSC. The safest thing to do is reset all the MSCs
and disable MPAM.

Add a helper to reset RIS via their class. Call this from mpam_disable(),
which can be scheduled from the error interrupt handler.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Ben Horgan <ben.horgan@arm.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com>
Tested-by: Gavin Shan <gshan@redhat.com>
Tested-by: Zeng Heng <zengheng4@huawei.com>
Tested-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Ben Horgan <ben.horgan@arm.com>
---
 drivers/resctrl/mpam_devices.c | 57 ++++++++++++++++++++++++++++++++--
 1 file changed, 54 insertions(+), 3 deletions(-)

diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
index 7941b093396e..7943d174b3f4 100644
--- a/drivers/resctrl/mpam_devices.c
+++ b/drivers/resctrl/mpam_devices.c
@@ -808,15 +808,13 @@ static void mpam_reset_ris_partid(struct mpam_msc_ris *ris, u16 partid)
 
 /*
  * Called via smp_call_on_cpu() to prevent migration, while still being
- * pre-emptible.
+ * pre-emptible. Caller must hold mpam_srcu.
  */
 static int mpam_reset_ris(void *arg)
 {
 	u16 partid, partid_max;
 	struct mpam_msc_ris *ris = arg;
 
-	WARN_ON_ONCE(!srcu_read_lock_held((&mpam_srcu)));
-
 	if (ris->in_reset_state)
 		return 0;
 
@@ -1337,8 +1335,55 @@ static void mpam_enable_once(void)
 	       mpam_partid_max + 1, mpam_pmg_max + 1);
 }
 
+static void mpam_reset_component_locked(struct mpam_component *comp)
+{
+	struct mpam_vmsc *vmsc;
+
+	lockdep_assert_cpus_held();
+
+	guard(srcu)(&mpam_srcu);
+	list_for_each_entry_srcu(vmsc, &comp->vmsc, comp_list,
+				 srcu_read_lock_held(&mpam_srcu)) {
+		struct mpam_msc *msc = vmsc->msc;
+		struct mpam_msc_ris *ris;
+
+		list_for_each_entry_srcu(ris, &vmsc->ris, vmsc_list,
+					 srcu_read_lock_held(&mpam_srcu)) {
+			if (!ris->in_reset_state)
+				mpam_touch_msc(msc, mpam_reset_ris, ris);
+			ris->in_reset_state = true;
+		}
+	}
+}
+
+static void mpam_reset_class_locked(struct mpam_class *class)
+{
+	struct mpam_component *comp;
+
+	lockdep_assert_cpus_held();
+
+	guard(srcu)(&mpam_srcu);
+	list_for_each_entry_srcu(comp, &class->components, class_list,
+				 srcu_read_lock_held(&mpam_srcu))
+		mpam_reset_component_locked(comp);
+}
+
+static void mpam_reset_class(struct mpam_class *class)
+{
+	cpus_read_lock();
+	mpam_reset_class_locked(class);
+	cpus_read_unlock();
+}
+
+/*
+ * Called in response to an error IRQ.
+ * All of MPAMs errors indicate a software bug, restore any modified
+ * controls to their reset values.
+ */
 void mpam_disable(struct work_struct *ignored)
 {
+	int idx;
+	struct mpam_class *class;
 	struct mpam_msc *msc, *tmp;
 
 	mutex_lock(&mpam_cpuhp_state_lock);
@@ -1348,6 +1393,12 @@ void mpam_disable(struct work_struct *ignored)
 	}
 	mutex_unlock(&mpam_cpuhp_state_lock);
 
+	idx = srcu_read_lock(&mpam_srcu);
+	list_for_each_entry_srcu(class, &mpam_classes, classes_list,
+				 srcu_read_lock_held(&mpam_srcu))
+		mpam_reset_class(class);
+	srcu_read_unlock(&mpam_srcu, idx);
+
 	mutex_lock(&mpam_list_lock);
 	list_for_each_entry_safe(msc, tmp, &mpam_all_msc, all_msc_list)
 		mpam_msc_destroy(msc);
-- 
2.43.0