x86/intel_rdt/mbm: Handle counter overflow

Set up a delayed work queue for each domain that will read all
the MBM counters of active RMIDs once per second to make sure
that they don't wrap around between reads from users.

[Tony: Added the initializations for the work structure and completed
the patch]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Vikas Shivappa <vikas.shivappa@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: ravi.v.shankar@intel.com
Cc: fenghua.yu@intel.com
Cc: peterz@infradead.org
Cc: eranian@google.com
Cc: vikas.shivappa@intel.com
Cc: ak@linux.intel.com
Cc: davidcc@google.com
Cc: reinette.chatre@intel.com
Link: http://lkml.kernel.org/r/1501017287-28083-29-git-send-email-vikas.shivappa@linux.intel.com

arch/x86/kernel/cpu/intel_rdt.c

@@ -348,12 +348,10 @@ void rdt_ctrl_update(void *arg)
 	int cpu = smp_processor_id();
 	struct rdt_domain *d;
 
-	list_for_each_entry(d, &r->domains, list) {
-		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
-			r->msr_update(d, m, r);
-			return;
-		}
+	d = get_domain_from_cpu(cpu, r);
+	if (d) {
+		r->msr_update(d, m, r);
+		return;
 	}
 	pr_warn_once("cpu %d not found in any domain for resource %s\n",
 		     cpu, r->name);
@@ -447,6 +445,11 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 		}
 	}
 
+	if (is_mbm_enabled()) {
+		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
+		mbm_setup_overflow_handler(d);
+	}
+
 	return 0;
 }
 
@@ -531,7 +534,13 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 		kfree(d->mbm_total);
 		kfree(d->mbm_local);
 		list_del(&d->list);
+		if (is_mbm_enabled())
+			cancel_delayed_work(&d->mbm_over);
 		kfree(d);
+	} else if (r == &rdt_resources_all[RDT_RESOURCE_L3] &&
+		   cpu == d->mbm_work_cpu && is_mbm_enabled()) {
+		cancel_delayed_work(&d->mbm_over);
+		mbm_setup_overflow_handler(d);
 	}
 }
 

arch/x86/kernel/cpu/intel_rdt.h

@@ -21,10 +21,13 @@
 #define QOS_L3_MBM_LOCAL_EVENT_ID	0x03
 
 #define MBM_CNTR_WIDTH			24
+#define MBM_OVERFLOW_INTERVAL		1000
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
 
+DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
+
 /**
  * struct mon_evt - Entry in the event list of a resource
  * @evtid:		event id
@@ -183,6 +186,9 @@ struct mbm_state {
  *		bitmap of which limbo RMIDs are above threshold
  * @mbm_total:	saved state for MBM total bandwidth
  * @mbm_local:	saved state for MBM local bandwidth
+ * @mbm_over:	worker to periodically read MBM h/w counters
+ * @mbm_work_cpu:
+ *		worker cpu for MBM h/w counters
  * @ctrl_val:	array of cache or mem ctrl values (indexed by CLOSID)
  * @new_ctrl:	new ctrl value to be loaded
  * @have_new_ctrl: did user provide new_ctrl for this domain
@@ -194,6 +200,8 @@ struct rdt_domain {
 	unsigned long		*rmid_busy_llc;
 	struct mbm_state	*mbm_total;
 	struct mbm_state	*mbm_local;
+	struct delayed_work	mbm_over;
+	int			mbm_work_cpu;
 	u32			*ctrl_val;
 	u32			new_ctrl;
 	bool			have_new_ctrl;
@@ -411,5 +419,7 @@ void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 				    struct rdt_domain *d);
 void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
 		    struct rdtgroup *rdtgrp, int evtid, int first);
+void mbm_setup_overflow_handler(struct rdt_domain *dom);
+void mbm_handle_overflow(struct work_struct *work);
 
 #endif /* _ASM_X86_INTEL_RDT_H */

arch/x86/kernel/cpu/intel_rdt_monitor.c

@@ -366,6 +366,69 @@ void mon_event_count(void *info)
 	}
 }
 
+static void mbm_update(struct rdt_domain *d, int rmid)
+{
+	struct rmid_read rr;
+
+	rr.first = false;
+	rr.d = d;
+
+	/*
+	 * This is protected from concurrent reads from user
+	 * as both the user and we hold the global mutex.
+	 */
+	if (is_mbm_total_enabled()) {
+		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
+		__mon_event_count(rmid, &rr);
+	}
+	if (is_mbm_local_enabled()) {
+		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
+		__mon_event_count(rmid, &rr);
+	}
+}
+
+void mbm_handle_overflow(struct work_struct *work)
+{
+	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
+	struct rdtgroup *prgrp, *crgrp;
+	int cpu = smp_processor_id();
+	struct list_head *head;
+	struct rdt_domain *d;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	if (!static_branch_likely(&rdt_enable_key))
+		goto out_unlock;
+
+	d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]);
+	if (!d)
+		goto out_unlock;
+
+	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
+		mbm_update(d, prgrp->mon.rmid);
+
+		head = &prgrp->mon.crdtgrp_list;
+		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
+			mbm_update(d, crgrp->mon.rmid);
+	}
+
+	schedule_delayed_work_on(cpu, &d->mbm_over, delay);
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+void mbm_setup_overflow_handler(struct rdt_domain *dom)
+{
+	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
+	int cpu;
+
+	if (!static_branch_likely(&rdt_enable_key))
+		return;
+	cpu = cpumask_any(&dom->cpu_mask);
+	dom->mbm_work_cpu = cpu;
+	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
+}
+
 static int dom_data_init(struct rdt_resource *r)
 {
 	struct rmid_entry *entry = NULL;

arch/x86/kernel/cpu/intel_rdt_rdtgroup.c

@@ -1060,6 +1060,8 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 				int flags, const char *unused_dev_name,
 				void *data)
 {
+	struct rdt_domain *dom;
+	struct rdt_resource *r;
 	struct dentry *dentry;
 	int ret;
 
@@ -1118,6 +1120,13 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 
 	if (rdt_alloc_capable || rdt_mon_capable)
 		static_branch_enable(&rdt_enable_key);
+
+	if (is_mbm_enabled()) {
+		r = &rdt_resources_all[RDT_RESOURCE_L3];
+		list_for_each_entry(dom, &r->domains, list)
+			mbm_setup_overflow_handler(dom);
+	}
+
 	goto out;
 
 out_mondata: