[PATCH 21/21] x86/intel_rdt/mbm: Handle counter overflow

[Vikas Shivappa]

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@xxxxxxxxx>
Signed-off-by: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>
---
 arch/x86/kernel/cpu/intel_rdt.c          | 34 +++++++++++++++----
 arch/x86/kernel/cpu/intel_rdt.h          |  9 +++++
 arch/x86/kernel/cpu/intel_rdt_monitor.c  | 57 ++++++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c |  9 +++++
 4 files changed, 103 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 7762e32..fe5c22a 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -318,6 +318,19 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 		wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]);
 }
 
+struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
+{
+	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))
+			return d;
+	}
+
+	return NULL;
+}
+
 void rdt_ctrl_update(void *arg)
 {
 	struct msr_param *m = arg;
@@ -325,12 +338,10 @@ 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);
@@ -413,6 +424,12 @@ static bool domain_setup_mbm_state(struct rdt_resource *r, struct rdt_domain *d)
 			return false;
 		}
 	}
+
+	if (is_mbm_enabled()) {
+		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
+		mbm_setup_overflow_handler(d);
+	}
+
 	return true;
 }
 
@@ -495,7 +512,12 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 		kfree(d->mbm_total);
 		kfree(d->mbm_local);
 		list_del(&d->list);
+		cancel_delayed_work(&d->mbm_over);
 		kfree(d);
+	} else if (r == &rdt_resources_all[RDT_RESOURCE_L3] &&
+		   cpu == d->mbm_work_cpu) {
+		cancel_delayed_work(&d->mbm_over);
+		mbm_setup_overflow_handler(d);
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index f0896ac..652efdbe 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -21,6 +21,7 @@
 #define QOS_L3_MBM_LOCAL_EVENT_ID	0x03
 
 #define MBM_CNTR_WIDTH         24
+#define MBM_OVERFLOW_INTERVAL	1000
 
 #define RMID_VAL_ERROR		(1ULL << 63)
 #define RMID_VAL_UNAVAIL	(1ULL << 62)
@@ -179,6 +180,9 @@ struct mbm_state {
  * @cpu_mask:	which cpus share this resource
  * @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
@@ -189,6 +193,8 @@ struct rdt_domain {
 	struct cpumask		cpu_mask;
 	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;
@@ -389,6 +395,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
+struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int alloc_rmid(void);
 void free_rmid(u32 rmid);
 void rdt_get_mon_l3_config(struct rdt_resource *r);
@@ -400,5 +407,7 @@ 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 */
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c
index a196f4d..d78a635 100644
--- a/arch/x86/kernel/cpu/intel_rdt_monitor.c
+++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c
@@ -271,6 +271,63 @@ 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;
+
+	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);
+	int cpu = smp_processor_id();
+	struct rdtgroup *pr, *cr;
+	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(pr, &rdt_all_groups, rdtgroup_list) {
+		mbm_update(d, pr->rmid);
+
+		list_for_each_entry(cr, &pr->crdtgrp_list, crdtgrp_list)
+			mbm_update(d, cr->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;
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 1b84485..a78f7f7 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -1092,6 +1092,8 @@ 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;
 
@@ -1150,6 +1152,13 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 
 	if (rdt_alloc_enabled || rdt_mon_features)
 		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:
-- 
1.9.1