[PATCH 6/6] x86/mbm: Add support for MBM counter overflow handling

[Vikas Shivappa]

This patch adds a per package timer which periodically updates the
Memory bandwidth counters for the events that are currently active.
Current patch has a periodic timer every 1s since the SDM guarantees
that the counter will not overflow in 1s but this time can be definitely
improved by calibrating on the system. The overflow is really a function
of the max memory b/w that the socket can support, max counter value and
scaling factor.

Reviewed-by: Tony Luck <tony.luck@xxxxxxxxx>
Signed-off-by: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>
---
 arch/x86/kernel/cpu/perf_event_intel_cqm.c | 140 +++++++++++++++++++++++++++--
 1 file changed, 135 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 6bca59d..a49b54e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -19,10 +19,15 @@
  */
 #define MBM_CNTR_WIDTH		24
 #define MBM_CNTR_MAX		((1U << MBM_CNTR_WIDTH) - 1)
+/*
+ * Guaranteed time in ms as per SDM where MBM counters will not overflow.
+ */
+#define MBM_CTR_OVERFLOW_TIME	1000
 
 static u32 cqm_max_rmid = -1;
 static unsigned int cqm_l3_scale; /* supposedly cacheline size */
 static bool cqm_enabled, mbm_enabled;
+unsigned int mbm_socket_max;
 
 /**
  * struct intel_pqr_state - State cache for the PQR MSR
@@ -50,6 +55,7 @@ struct intel_pqr_state {
  * interrupts disabled, which is sufficient for the protection.
  */
 static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
+static struct hrtimer *mbm_timers;
 /**
  * struct sample - mbm event's (local or total) data
  * @total_bytes    #bytes since we began monitoring
@@ -951,6 +957,11 @@ static u64 update_sample(unsigned int rmid,
 		return mbm_current->total_bytes;
 	}
 
+	/*
+	 * As per SDM, the h/w guarentees that counters will not
+	 * overflow in 1s interval. The 1s periodic timers call
+	 * update_sample to ensure the same.
+	 */
 	if (val < mbm_current->prev_msr) {
 		bytes = MBM_CNTR_MAX - mbm_current->prev_msr + val + 1;
 	} else {
@@ -1099,6 +1110,84 @@ static void __intel_mbm_event_count(void *info)
 	atomic64_add(val, &rr->value);
 }
 
+static enum hrtimer_restart mbm_hrtimer_handle(struct hrtimer *hrtimer)
+{
+	struct perf_event *iter, *iter1;
+	int ret = HRTIMER_RESTART;
+	struct list_head *head;
+	unsigned long flags;
+	u32 grp_rmid;
+
+	/*
+	 * Need to cache_lock as the timer Event Select MSR reads
+	 * can race with the mbm/cqm count() and mbm_init() reads.
+	 */
+	raw_spin_lock_irqsave(&cache_lock, flags);
+
+	if (list_empty(&cache_groups)) {
+		ret = HRTIMER_NORESTART;
+		goto out;
+	}
+
+	list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
+		grp_rmid = iter->hw.cqm_rmid;
+		if (!__rmid_valid(grp_rmid))
+			continue;
+		if (is_mbm_event(iter->attr.config))
+			update_sample(grp_rmid, iter->attr.config, 0);
+
+		head = &iter->hw.cqm_group_entry;
+		if (list_empty(head))
+			continue;
+		list_for_each_entry(iter1, head, hw.cqm_group_entry) {
+			if (!iter1->hw.is_group_event)
+				break;
+			if (is_mbm_event(iter1->attr.config))
+				update_sample(iter1->hw.cqm_rmid,
+					      iter1->attr.config, 0);
+		}
+	}
+
+	hrtimer_forward_now(hrtimer, ms_to_ktime(MBM_CTR_OVERFLOW_TIME));
+out:
+	raw_spin_unlock_irqrestore(&cache_lock, flags);
+
+	return ret;
+}
+
+static void __mbm_start_timer(void *info)
+{
+	hrtimer_start(&mbm_timers[pkg_id], ms_to_ktime(MBM_CTR_OVERFLOW_TIME),
+			     HRTIMER_MODE_REL_PINNED);
+}
+
+static void __mbm_stop_timer(void *info)
+{
+	hrtimer_cancel(&mbm_timers[pkg_id]);
+}
+
+static void mbm_start_timers(void)
+{
+	on_each_cpu_mask(&cqm_cpumask, __mbm_start_timer, NULL, 1);
+}
+
+static void mbm_stop_timers(void)
+{
+	on_each_cpu_mask(&cqm_cpumask, __mbm_stop_timer, NULL, 1);
+}
+
+static void mbm_hrtimer_init(void)
+{
+	struct hrtimer *hr;
+	int i;
+
+	for (i = 0; i < mbm_socket_max; i++) {
+		hr = &mbm_timers[i];
+		hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+		hr->function = mbm_hrtimer_handle;
+	}
+}
+
 static u64 intel_cqm_event_count(struct perf_event *event)
 {
 	unsigned long flags;
@@ -1228,8 +1317,14 @@ static int intel_cqm_event_add(struct perf_event *event, int mode)
 static void intel_cqm_event_destroy(struct perf_event *event)
 {
 	struct perf_event *group_other = NULL;
+	unsigned long flags;
 
 	mutex_lock(&cache_mutex);
+	/*
+	* Hold the cache_lock as mbm timer handlers could be
+	* scanning the list of events.
+	*/
+	raw_spin_lock_irqsave(&cache_lock, flags);
 
 	/*
 	 * If there's another event in this group...
@@ -1261,6 +1356,14 @@ static void intel_cqm_event_destroy(struct perf_event *event)
 		}
 	}
 
+	raw_spin_unlock_irqrestore(&cache_lock, flags);
+
+	/*
+	 * Stop the mbm overflow timers when the last event is destroyed.
+	*/
+	if (mbm_enabled && list_empty(&cache_groups))
+		mbm_stop_timers();
+
 	mutex_unlock(&cache_mutex);
 }
 
@@ -1268,6 +1371,7 @@ static int intel_cqm_event_init(struct perf_event *event)
 {
 	struct perf_event *group = NULL;
 	bool rotate = false;
+	unsigned long flags;
 
 	if (event->attr.type != intel_cqm_pmu.type)
 		return -ENOENT;
@@ -1293,9 +1397,21 @@ static int intel_cqm_event_init(struct perf_event *event)
 
 	mutex_lock(&cache_mutex);
 
+	/*
+	 * Start the mbm overflow timers when the first event is created.
+	*/
+	if (mbm_enabled && list_empty(&cache_groups))
+		mbm_start_timers();
+
 	/* Will also set rmid */
 	intel_cqm_setup_event(event, &group);
 
+	/*
+	* Hold the cache_lock as mbm timer handlers be
+	* scanning the list of events.
+	*/
+	raw_spin_lock_irqsave(&cache_lock, flags);
+
 	if (group) {
 		list_add_tail(&event->hw.cqm_group_entry,
 			      &group->hw.cqm_group_entry);
@@ -1314,6 +1430,7 @@ static int intel_cqm_event_init(struct perf_event *event)
 			rotate = true;
 	}
 
+	raw_spin_unlock_irqrestore(&cache_lock, flags);
 	mutex_unlock(&cache_mutex);
 
 	if (rotate)
@@ -1557,20 +1674,33 @@ static const struct x86_cpu_id intel_mbm_total_match[] = {
 
 static int intel_mbm_init(void)
 {
-	int array_size, maxid = cqm_max_rmid + 1;
+	int ret = 0, array_size, maxid = cqm_max_rmid + 1;
 
-	array_size = sizeof(struct sample) * maxid * topology_max_packages();
+	mbm_socket_max = topology_max_packages();
+	array_size = sizeof(struct sample) * maxid * mbm_socket_max;
 	mbm_local = kmalloc(array_size, GFP_KERNEL);
 	if (!mbm_local)
 		return -ENOMEM;
 
 	mbm_total = kmalloc(array_size, GFP_KERNEL);
 	if (!mbm_total) {
-		mbm_cleanup();
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
 	}
 
-	return 0;
+	array_size = sizeof(struct hrtimer) * mbm_socket_max;
+	mbm_timers = kmalloc(array_size, GFP_KERNEL);
+	if (!mbm_timers) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	mbm_hrtimer_init();
+
+out:
+	if (ret)
+		mbm_cleanup();
+
+	return ret;
 }
 
 static int __init intel_cqm_init(void)
-- 
1.9.1