x86/intel_rdt/mbm: Basic counting of MBM events (total and local)

Check CPUID bits for whether each of the MBM events is supported.
Allocate space for each RMID for each counter in each domain to save
previous MSR counter value and running total of data.
Create files in each of the monitor directories.

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/1501017287-28083-27-git-send-email-vikas.shivappa@linux.intel.com

arch/x86/kernel/cpu/intel_rdt.c

@@ -420,6 +420,8 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
 
 static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 {
+	size_t tsize;
+
 	if (is_llc_occupancy_enabled()) {
 		d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid),
 					   sizeof(unsigned long),
@@ -427,6 +429,23 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 		if (!d->rmid_busy_llc)
 			return -ENOMEM;
 	}
+	if (is_mbm_total_enabled()) {
+		tsize = sizeof(*d->mbm_total);
+		d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+		if (!d->mbm_total) {
+			kfree(d->rmid_busy_llc);
+			return -ENOMEM;
+		}
+	}
+	if (is_mbm_local_enabled()) {
+		tsize = sizeof(*d->mbm_local);
+		d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+		if (!d->mbm_local) {
+			kfree(d->rmid_busy_llc);
+			kfree(d->mbm_total);
+			return -ENOMEM;
+		}
+	}
 
 	return 0;
 }
@@ -466,6 +485,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 
 	d->id = id;
+	cpumask_set_cpu(cpu, &d->cpu_mask);
 
 	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
 		kfree(d);
@@ -477,7 +497,6 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	cpumask_set_cpu(cpu, &d->cpu_mask);
 	list_add_tail(&d->list, add_pos);
 
 	/*
@@ -509,6 +528,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 			rmdir_mondata_subdir_allrdtgrp(r, d->id);
 		kfree(d->ctrl_val);
 		kfree(d->rmid_busy_llc);
+		kfree(d->mbm_total);
+		kfree(d->mbm_local);
 		list_del(&d->list);
 		kfree(d);
 	}

arch/x86/kernel/cpu/intel_rdt.h

@@ -19,6 +19,9 @@
 #define QOS_L3_OCCUP_EVENT_ID		0x01
 #define QOS_L3_MBM_TOTAL_EVENT_ID	0x02
 #define QOS_L3_MBM_LOCAL_EVENT_ID	0x03
+
+#define MBM_CNTR_WIDTH			24
+
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
 
@@ -50,6 +53,7 @@ union mon_data_bits {
 
 struct rmid_read {
 	struct rdtgroup		*rgrp;
+	struct rdt_domain	*d;
 	int			evtid;
 	u64			val;
 };
@@ -159,6 +163,16 @@ struct rftype {
 			 char *buf, size_t nbytes, loff_t off);
 };
 
+/**
+ * struct mbm_state - status for each MBM counter in each domain
+ * @chunks:	Total data moved (multiply by rdt_group.mon_scale to get bytes)
+ * @prev_msr	Value of IA32_QM_CTR for this RMID last time we read it
+ */
+struct mbm_state {
+	u64	chunks;
+	u64	prev_msr;
+};
+
 /**
  * struct rdt_domain - group of cpus sharing an RDT resource
  * @list:	all instances of this resource
@@ -166,6 +180,8 @@ struct rftype {
  * @cpu_mask:	which cpus share this resource
  * @rmid_busy_llc:
  *		bitmap of which limbo RMIDs are above threshold
+ * @mbm_total:	saved state for MBM total bandwidth
+ * @mbm_local:	saved state for MBM local bandwidth
  * @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
@@ -175,6 +191,8 @@ struct rdt_domain {
 	int			id;
 	struct cpumask		cpu_mask;
 	unsigned long		*rmid_busy_llc;
+	struct mbm_state	*mbm_total;
+	struct mbm_state	*mbm_local;
 	u32			*ctrl_val;
 	u32			new_ctrl;
 	bool			have_new_ctrl;
@@ -230,6 +248,21 @@ static inline bool is_llc_occupancy_enabled(void)
 	return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID));
 }
 
+static inline bool is_mbm_total_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID));
+}
+
+static inline bool is_mbm_local_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID));
+}
+
+static inline bool is_mbm_enabled(void)
+{
+	return (is_mbm_total_enabled() || is_mbm_local_enabled());
+}
+
 /**
  * struct rdt_resource - attributes of an RDT resource
  * @rid:		The index of the resource

arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c

@@ -294,6 +294,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
 	 */
 	rr->rgrp = rdtgrp;
 	rr->evtid = evtid;
+	rr->d = d;
 	rr->val = 0;
 
 	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);

arch/x86/kernel/cpu/intel_rdt_monitor.c

@@ -296,7 +296,8 @@ void free_rmid(u32 rmid)
 
 static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 {
-	u64 tval;
+	u64 chunks, shift, tval;
+	struct mbm_state *m;
 
 	tval = __rmid_read(rmid, rr->evtid);
 	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
@@ -307,6 +308,12 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 	case QOS_L3_OCCUP_EVENT_ID:
 		rr->val += tval;
 		return 0;
+	case QOS_L3_MBM_TOTAL_EVENT_ID:
+		m = &rr->d->mbm_total[rmid];
+		break;
+	case QOS_L3_MBM_LOCAL_EVENT_ID:
+		m = &rr->d->mbm_local[rmid];
+		break;
 	default:
 		/*
 		 * Code would never reach here because
@@ -314,6 +321,14 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 		 */
 		return -EINVAL;
 	}
+	shift = 64 - MBM_CNTR_WIDTH;
+	chunks = (tval << shift) - (m->prev_msr << shift);
+	chunks >>= shift;
+	m->chunks += chunks;
+	m->prev_msr = tval;
+
+	rr->val += m->chunks;
+	return 0;
 }
 
 /*
@@ -377,6 +392,16 @@ static struct mon_evt llc_occupancy_event = {
 	.evtid		= QOS_L3_OCCUP_EVENT_ID,
 };
 
+static struct mon_evt mbm_total_event = {
+	.name		= "mbm_total_bytes",
+	.evtid		= QOS_L3_MBM_TOTAL_EVENT_ID,
+};
+
+static struct mon_evt mbm_local_event = {
+	.name		= "mbm_local_bytes",
+	.evtid		= QOS_L3_MBM_LOCAL_EVENT_ID,
+};
+
 /*
  * Initialize the event list for the resource.
  *
@@ -390,6 +415,10 @@ static void l3_mon_evt_init(struct rdt_resource *r)
 
 	if (is_llc_occupancy_enabled())
 		list_add_tail(&llc_occupancy_event.list, &r->evt_list);
+	if (is_mbm_total_enabled())
+		list_add_tail(&mbm_total_event.list, &r->evt_list);
+	if (is_mbm_local_enabled())
+		list_add_tail(&mbm_local_event.list, &r->evt_list);
 }
 
 int rdt_get_mon_l3_config(struct rdt_resource *r)