Date:	Thu, 28 Apr 2016 21:43:07 -0700
From:	David Carrillo-Cisneros <davidcc@...gle.com>
To:	Peter Zijlstra <peterz@...radead.org>,
	Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
	Arnaldo Carvalho de Melo <acme@...nel.org>,
	Ingo Molnar <mingo@...hat.com>
Cc:	Vikas Shivappa <vikas.shivappa@...ux.intel.com>,
	Matt Fleming <matt.fleming@...el.com>,
	Tony Luck <tony.luck@...el.com>,
	Stephane Eranian <eranian@...gle.com>,
	Paul Turner <pjt@...gle.com>,
	David Carrillo-Cisneros <davidcc@...gle.com>, x86@...nel.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH 01/32] perf/x86/intel/cqm: temporarily remove MBM from CQM and cleanup

Removing MBM code from arch/x86/events/intel/cqm.c. MBM will be added
using the new RMID infrastucture introduced in this patch series.

Also, remove updates to CQM that are superseded by this series.

Reviewed-by: Stephane Eranian <eranian@...gle.com>
Signed-off-by: David Carrillo-Cisneros <davidcc@...gle.com>
---
 arch/x86/events/intel/cqm.c | 486 ++++----------------------------------------
 include/linux/perf_event.h  |   1 -
 2 files changed, 44 insertions(+), 443 deletions(-)

diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 7b5fd81..1b064c4 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -13,16 +13,8 @@
 #define MSR_IA32_QM_CTR		0x0c8e
 #define MSR_IA32_QM_EVTSEL	0x0c8d
 
-#define MBM_CNTR_WIDTH		24
-/*
- * 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
@@ -50,37 +42,8 @@ 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
- * @prev_msr       previous value of MSR
- */
-struct sample {
-	u64	total_bytes;
-	u64	prev_msr;
-};
 
 /*
- * samples profiled for total memory bandwidth type events
- */
-static struct sample *mbm_total;
-/*
- * samples profiled for local memory bandwidth type events
- */
-static struct sample *mbm_local;
-
-#define pkg_id	topology_physical_package_id(smp_processor_id())
-/*
- * rmid_2_index returns the index for the rmid in mbm_local/mbm_total array.
- * mbm_total[] and mbm_local[] are linearly indexed by socket# * max number of
- * rmids per socket, an example is given below
- * RMID1 of Socket0:  vrmid =  1
- * RMID1 of Socket1:  vrmid =  1 * (cqm_max_rmid + 1) + 1
- * RMID1 of Socket2:  vrmid =  2 * (cqm_max_rmid + 1) + 1
- */
-#define rmid_2_index(rmid)  ((pkg_id * (cqm_max_rmid + 1)) + rmid)
-/*
  * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
  * Also protects event->hw.cqm_rmid
  *
@@ -102,13 +65,9 @@ static cpumask_t cqm_cpumask;
 #define RMID_VAL_ERROR		(1ULL << 63)
 #define RMID_VAL_UNAVAIL	(1ULL << 62)
 
-/*
- * Event IDs are used to program IA32_QM_EVTSEL before reading event
- * counter from IA32_QM_CTR
- */
-#define QOS_L3_OCCUP_EVENT_ID	0x01
-#define QOS_MBM_TOTAL_EVENT_ID	0x02
-#define QOS_MBM_LOCAL_EVENT_ID	0x03
+#define QOS_L3_OCCUP_EVENT_ID	(1 << 0)
+
+#define QOS_EVENT_MASK	QOS_L3_OCCUP_EVENT_ID
 
 /*
  * This is central to the rotation algorithm in __intel_cqm_rmid_rotate().
@@ -252,21 +211,6 @@ static void __put_rmid(u32 rmid)
 	list_add_tail(&entry->list, &cqm_rmid_limbo_lru);
 }
 
-static void cqm_cleanup(void)
-{
-	int i;
-
-	if (!cqm_rmid_ptrs)
-		return;
-
-	for (i = 0; i < cqm_max_rmid; i++)
-		kfree(cqm_rmid_ptrs[i]);
-
-	kfree(cqm_rmid_ptrs);
-	cqm_rmid_ptrs = NULL;
-	cqm_enabled = false;
-}
-
 static int intel_cqm_setup_rmid_cache(void)
 {
 	struct cqm_rmid_entry *entry;
@@ -274,7 +218,7 @@ static int intel_cqm_setup_rmid_cache(void)
 	int r = 0;
 
 	nr_rmids = cqm_max_rmid + 1;
-	cqm_rmid_ptrs = kzalloc(sizeof(struct cqm_rmid_entry *) *
+	cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) *
 				nr_rmids, GFP_KERNEL);
 	if (!cqm_rmid_ptrs)
 		return -ENOMEM;
@@ -305,9 +249,11 @@ static int intel_cqm_setup_rmid_cache(void)
 	mutex_unlock(&cache_mutex);
 
 	return 0;
-
 fail:
-	cqm_cleanup();
+	while (r--)
+		kfree(cqm_rmid_ptrs[r]);
+
+	kfree(cqm_rmid_ptrs);
 	return -ENOMEM;
 }
 
@@ -335,13 +281,9 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
 
 	/*
 	 * Events that target same task are placed into the same cache group.
-	 * Mark it as a multi event group, so that we update ->count
-	 * for every event rather than just the group leader later.
 	 */
-	if (a->hw.target == b->hw.target) {
-		b->hw.is_group_event = true;
+	if (a->hw.target == b->hw.target)
 		return true;
-	}
 
 	/*
 	 * Are we an inherited event?
@@ -450,26 +392,10 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b)
 
 struct rmid_read {
 	u32 rmid;
-	u32 evt_type;
 	atomic64_t value;
 };
 
 static void __intel_cqm_event_count(void *info);
-static void init_mbm_sample(u32 rmid, u32 evt_type);
-static void __intel_mbm_event_count(void *info);
-
-static bool is_mbm_event(int e)
-{
-	return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID);
-}
-
-static void cqm_mask_call(struct rmid_read *rr)
-{
-	if (is_mbm_event(rr->evt_type))
-		on_each_cpu_mask(&cqm_cpumask, __intel_mbm_event_count, rr, 1);
-	else
-		on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count, rr, 1);
-}
 
 /*
  * Exchange the RMID of a group of events.
@@ -487,12 +413,12 @@ static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid)
 	 */
 	if (__rmid_valid(old_rmid) && !__rmid_valid(rmid)) {
 		struct rmid_read rr = {
-			.rmid = old_rmid,
-			.evt_type = group->attr.config,
 			.value = ATOMIC64_INIT(0),
+			.rmid = old_rmid,
 		};
 
-		cqm_mask_call(&rr);
+		on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count,
+				 &rr, 1);
 		local64_set(&group->count, atomic64_read(&rr.value));
 	}
 
@@ -504,22 +430,6 @@ static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid)
 
 	raw_spin_unlock_irq(&cache_lock);
 
-	/*
-	 * If the allocation is for mbm, init the mbm stats.
-	 * Need to check if each event in the group is mbm event
-	 * because there could be multiple type of events in the same group.
-	 */
-	if (__rmid_valid(rmid)) {
-		event = group;
-		if (is_mbm_event(event->attr.config))
-			init_mbm_sample(rmid, event->attr.config);
-
-		list_for_each_entry(event, head, hw.cqm_group_entry) {
-			if (is_mbm_event(event->attr.config))
-				init_mbm_sample(rmid, event->attr.config);
-		}
-	}
-
 	return old_rmid;
 }
 
@@ -927,72 +837,6 @@ static void intel_cqm_rmid_rotate(struct work_struct *work)
 	schedule_delayed_work(&intel_cqm_rmid_work, delay);
 }
 
-static u64 update_sample(unsigned int rmid, u32 evt_type, int first)
-{
-	struct sample *mbm_current;
-	u32 vrmid = rmid_2_index(rmid);
-	u64 val, bytes, shift;
-	u32 eventid;
-
-	if (evt_type == QOS_MBM_LOCAL_EVENT_ID) {
-		mbm_current = &mbm_local[vrmid];
-		eventid     = QOS_MBM_LOCAL_EVENT_ID;
-	} else {
-		mbm_current = &mbm_total[vrmid];
-		eventid     = QOS_MBM_TOTAL_EVENT_ID;
-	}
-
-	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
-	rdmsrl(MSR_IA32_QM_CTR, val);
-	if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
-		return mbm_current->total_bytes;
-
-	if (first) {
-		mbm_current->prev_msr = val;
-		mbm_current->total_bytes = 0;
-		return mbm_current->total_bytes;
-	}
-
-	/*
-	 * The h/w guarantees that counters will not overflow
-	 * so long as we poll them at least once per second.
-	 */
-	shift = 64 - MBM_CNTR_WIDTH;
-	bytes = (val << shift) - (mbm_current->prev_msr << shift);
-	bytes >>= shift;
-
-	bytes *= cqm_l3_scale;
-
-	mbm_current->total_bytes += bytes;
-	mbm_current->prev_msr = val;
-
-	return mbm_current->total_bytes;
-}
-
-static u64 rmid_read_mbm(unsigned int rmid, u32 evt_type)
-{
-	return update_sample(rmid, evt_type, 0);
-}
-
-static void __intel_mbm_event_init(void *info)
-{
-	struct rmid_read *rr = info;
-
-	update_sample(rr->rmid, rr->evt_type, 1);
-}
-
-static void init_mbm_sample(u32 rmid, u32 evt_type)
-{
-	struct rmid_read rr = {
-		.rmid = rmid,
-		.evt_type = evt_type,
-		.value = ATOMIC64_INIT(0),
-	};
-
-	/* on each socket, init sample */
-	on_each_cpu_mask(&cqm_cpumask, __intel_mbm_event_init, &rr, 1);
-}
-
 /*
  * Find a group and setup RMID.
  *
@@ -1005,7 +849,6 @@ static void intel_cqm_setup_event(struct perf_event *event,
 	bool conflict = false;
 	u32 rmid;
 
-	event->hw.is_group_event = false;
 	list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
 		rmid = iter->hw.cqm_rmid;
 
@@ -1013,8 +856,6 @@ static void intel_cqm_setup_event(struct perf_event *event,
 			/* All tasks in a group share an RMID */
 			event->hw.cqm_rmid = rmid;
 			*group = iter;
-			if (is_mbm_event(event->attr.config) && __rmid_valid(rmid))
-				init_mbm_sample(rmid, event->attr.config);
 			return;
 		}
 
@@ -1031,9 +872,6 @@ static void intel_cqm_setup_event(struct perf_event *event,
 	else
 		rmid = __get_rmid();
 
-	if (is_mbm_event(event->attr.config) && __rmid_valid(rmid))
-		init_mbm_sample(rmid, event->attr.config);
-
 	event->hw.cqm_rmid = rmid;
 }
 
@@ -1055,10 +893,7 @@ static void intel_cqm_event_read(struct perf_event *event)
 	if (!__rmid_valid(rmid))
 		goto out;
 
-	if (is_mbm_event(event->attr.config))
-		val = rmid_read_mbm(rmid, event->attr.config);
-	else
-		val = __rmid_read(rmid);
+	val = __rmid_read(rmid);
 
 	/*
 	 * Ignore this reading on error states and do not update the value.
@@ -1089,100 +924,10 @@ static inline bool cqm_group_leader(struct perf_event *event)
 	return !list_empty(&event->hw.cqm_groups_entry);
 }
 
-static void __intel_mbm_event_count(void *info)
-{
-	struct rmid_read *rr = info;
-	u64 val;
-
-	val = rmid_read_mbm(rr->rmid, rr->evt_type);
-	if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
-		return;
-	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;
 	struct rmid_read rr = {
-		.evt_type = event->attr.config,
 		.value = ATOMIC64_INIT(0),
 	};
 
@@ -1195,9 +940,7 @@ static u64 intel_cqm_event_count(struct perf_event *event)
 		return __perf_event_count(event);
 
 	/*
-	 * Only the group leader gets to report values except in case of
-	 * multiple events in the same group, we still need to read the
-	 * other events.This stops us
+	 * Only the group leader gets to report values. This stops us
 	 * reporting duplicate values to userspace, and gives us a clear
 	 * rule for which task gets to report the values.
 	 *
@@ -1205,7 +948,7 @@ static u64 intel_cqm_event_count(struct perf_event *event)
 	 * specific packages - we forfeit that ability when we create
 	 * task events.
 	 */
-	if (!cqm_group_leader(event) && !event->hw.is_group_event)
+	if (!cqm_group_leader(event))
 		return 0;
 
 	/*
@@ -1232,7 +975,7 @@ static u64 intel_cqm_event_count(struct perf_event *event)
 	if (!__rmid_valid(rr.rmid))
 		goto out;
 
-	cqm_mask_call(&rr);
+	on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count, &rr, 1);
 
 	raw_spin_lock_irqsave(&cache_lock, flags);
 	if (event->hw.cqm_rmid == rr.rmid)
@@ -1303,14 +1046,8 @@ 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...
@@ -1342,14 +1079,6 @@ 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);
 }
 
@@ -1357,13 +1086,11 @@ 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;
 
-	if ((event->attr.config < QOS_L3_OCCUP_EVENT_ID) ||
-	     (event->attr.config > QOS_MBM_LOCAL_EVENT_ID))
+	if (event->attr.config & ~QOS_EVENT_MASK)
 		return -EINVAL;
 
 	/* unsupported modes and filters */
@@ -1383,21 +1110,9 @@ 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);
@@ -1416,7 +1131,6 @@ 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)
@@ -1431,16 +1145,6 @@ EVENT_ATTR_STR(llc_occupancy.unit, intel_cqm_llc_unit, "Bytes");
 EVENT_ATTR_STR(llc_occupancy.scale, intel_cqm_llc_scale, NULL);
 EVENT_ATTR_STR(llc_occupancy.snapshot, intel_cqm_llc_snapshot, "1");
 
-EVENT_ATTR_STR(total_bytes, intel_cqm_total_bytes, "event=0x02");
-EVENT_ATTR_STR(total_bytes.per-pkg, intel_cqm_total_bytes_pkg, "1");
-EVENT_ATTR_STR(total_bytes.unit, intel_cqm_total_bytes_unit, "MB");
-EVENT_ATTR_STR(total_bytes.scale, intel_cqm_total_bytes_scale, "1e-6");
-
-EVENT_ATTR_STR(local_bytes, intel_cqm_local_bytes, "event=0x03");
-EVENT_ATTR_STR(local_bytes.per-pkg, intel_cqm_local_bytes_pkg, "1");
-EVENT_ATTR_STR(local_bytes.unit, intel_cqm_local_bytes_unit, "MB");
-EVENT_ATTR_STR(local_bytes.scale, intel_cqm_local_bytes_scale, "1e-6");
-
 static struct attribute *intel_cqm_events_attr[] = {
 	EVENT_PTR(intel_cqm_llc),
 	EVENT_PTR(intel_cqm_llc_pkg),
@@ -1450,38 +1154,9 @@ static struct attribute *intel_cqm_events_attr[] = {
 	NULL,
 };
 
-static struct attribute *intel_mbm_events_attr[] = {
-	EVENT_PTR(intel_cqm_total_bytes),
-	EVENT_PTR(intel_cqm_local_bytes),
-	EVENT_PTR(intel_cqm_total_bytes_pkg),
-	EVENT_PTR(intel_cqm_local_bytes_pkg),
-	EVENT_PTR(intel_cqm_total_bytes_unit),
-	EVENT_PTR(intel_cqm_local_bytes_unit),
-	EVENT_PTR(intel_cqm_total_bytes_scale),
-	EVENT_PTR(intel_cqm_local_bytes_scale),
-	NULL,
-};
-
-static struct attribute *intel_cmt_mbm_events_attr[] = {
-	EVENT_PTR(intel_cqm_llc),
-	EVENT_PTR(intel_cqm_total_bytes),
-	EVENT_PTR(intel_cqm_local_bytes),
-	EVENT_PTR(intel_cqm_llc_pkg),
-	EVENT_PTR(intel_cqm_total_bytes_pkg),
-	EVENT_PTR(intel_cqm_local_bytes_pkg),
-	EVENT_PTR(intel_cqm_llc_unit),
-	EVENT_PTR(intel_cqm_total_bytes_unit),
-	EVENT_PTR(intel_cqm_local_bytes_unit),
-	EVENT_PTR(intel_cqm_llc_scale),
-	EVENT_PTR(intel_cqm_total_bytes_scale),
-	EVENT_PTR(intel_cqm_local_bytes_scale),
-	EVENT_PTR(intel_cqm_llc_snapshot),
-	NULL,
-};
-
 static struct attribute_group intel_cqm_events_group = {
 	.name = "events",
-	.attrs = NULL,
+	.attrs = intel_cqm_events_attr,
 };
 
 PMU_FORMAT_ATTR(event, "config:0-7");
@@ -1569,12 +1244,15 @@ static struct pmu intel_cqm_pmu = {
 
 static inline void cqm_pick_event_reader(int cpu)
 {
-	int reader;
+	int phys_id = topology_physical_package_id(cpu);
+	int i;
+
+	for_each_cpu(i, &cqm_cpumask) {
+		if (phys_id == topology_physical_package_id(i))
+			return;	/* already got reader for this socket */
+	}
 
-	/* First online cpu in package becomes the reader */
-	reader = cpumask_any_and(&cqm_cpumask, topology_core_cpumask(cpu));
-	if (reader >= nr_cpu_ids)
-		cpumask_set_cpu(cpu, &cqm_cpumask);
+	cpumask_set_cpu(cpu, &cqm_cpumask);
 }
 
 static void intel_cqm_cpu_starting(unsigned int cpu)
@@ -1592,17 +1270,24 @@ static void intel_cqm_cpu_starting(unsigned int cpu)
 
 static void intel_cqm_cpu_exit(unsigned int cpu)
 {
-	int target;
+	int phys_id = topology_physical_package_id(cpu);
+	int i;
 
-	/* Is @cpu the current cqm reader for this package ? */
+	/*
+	 * Is @cpu a designated cqm reader?
+	 */
 	if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask))
 		return;
 
-	/* Find another online reader in this package */
-	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+	for_each_online_cpu(i) {
+		if (i == cpu)
+			continue;
 
-	if (target < nr_cpu_ids)
-		cpumask_set_cpu(target, &cqm_cpumask);
+		if (phys_id == topology_physical_package_id(i)) {
+			cpumask_set_cpu(i, &cqm_cpumask);
+			break;
+		}
+	}
 }
 
 static int intel_cqm_cpu_notifier(struct notifier_block *nb,
@@ -1628,70 +1313,12 @@ static const struct x86_cpu_id intel_cqm_match[] = {
 	{}
 };
 
-static void mbm_cleanup(void)
-{
-	if (!mbm_enabled)
-		return;
-
-	kfree(mbm_local);
-	kfree(mbm_total);
-	mbm_enabled = false;
-}
-
-static const struct x86_cpu_id intel_mbm_local_match[] = {
-	{ .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_MBM_LOCAL },
-	{}
-};
-
-static const struct x86_cpu_id intel_mbm_total_match[] = {
-	{ .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_MBM_TOTAL },
-	{}
-};
-
-static int intel_mbm_init(void)
-{
-	int ret = 0, array_size, maxid = cqm_max_rmid + 1;
-
-	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) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	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)
 {
-	char *str = NULL, scale[20];
+	char *str, scale[20];
 	int i, cpu, ret;
 
-	if (x86_match_cpu(intel_cqm_match))
-		cqm_enabled = true;
-
-	if (x86_match_cpu(intel_mbm_local_match) &&
-	     x86_match_cpu(intel_mbm_total_match))
-		mbm_enabled = true;
-
-	if (!cqm_enabled && !mbm_enabled)
+	if (!x86_match_cpu(intel_cqm_match))
 		return -ENODEV;
 
 	cqm_l3_scale = boot_cpu_data.x86_cache_occ_scale;
@@ -1748,41 +1375,16 @@ static int __init intel_cqm_init(void)
 		cqm_pick_event_reader(i);
 	}
 
-	if (mbm_enabled)
-		ret = intel_mbm_init();
-	if (ret && !cqm_enabled)
-		goto out;
-
-	if (cqm_enabled && mbm_enabled)
-		intel_cqm_events_group.attrs = intel_cmt_mbm_events_attr;
-	else if (!cqm_enabled && mbm_enabled)
-		intel_cqm_events_group.attrs = intel_mbm_events_attr;
-	else if (cqm_enabled && !mbm_enabled)
-		intel_cqm_events_group.attrs = intel_cqm_events_attr;
+	__perf_cpu_notifier(intel_cqm_cpu_notifier);
 
 	ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1);
-	if (ret) {
+	if (ret)
 		pr_err("Intel CQM perf registration failed: %d\n", ret);
-		goto out;
-	}
-
-	if (cqm_enabled)
+	else
 		pr_info("Intel CQM monitoring enabled\n");
-	if (mbm_enabled)
-		pr_info("Intel MBM enabled\n");
 
-	/*
-	 * Register the hot cpu notifier once we are sure cqm
-	 * is enabled to avoid notifier leak.
-	 */
-	__perf_cpu_notifier(intel_cqm_cpu_notifier);
 out:
 	cpu_notifier_register_done();
-	if (ret) {
-		kfree(str);
-		cqm_cleanup();
-		mbm_cleanup();
-	}
 
 	return ret;
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 9f64044..00bb6b5 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -121,7 +121,6 @@ struct hw_perf_event {
 		struct { /* intel_cqm */
 			int			cqm_state;
 			u32			cqm_rmid;
-			int			is_group_event;
 			struct list_head	cqm_events_entry;
 			struct list_head	cqm_groups_entry;
 			struct list_head	cqm_group_entry;
-- 
2.8.0.rc3.226.g39d4020

Powered by blists - more mailing lists