1 files changed, 499 insertions, 0 deletions
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c
new file mode 100644
index 000000000000..30827510094b
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c
@@ -0,0 +1,499 @@
+/*
+ * Resource Director Technology(RDT)
+ * - Monitoring code
+ *
+ * Copyright (C) 2017 Intel Corporation
+ *
+ * Author:
+ *    Vikas Shivappa <vikas.shivappa@intel.com>
+ *
+ * This replaces the cqm.c based on perf but we reuse a lot of
+ * code and datastructures originally from Peter Zijlstra and Matt Fleming.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * More information about RDT be found in the Intel (R) x86 Architecture
+ * Software Developer Manual June 2016, volume 3, section 17.17.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <asm/cpu_device_id.h>
+#include "intel_rdt.h"
+
+#define MSR_IA32_QM_CTR		0x0c8e
+#define MSR_IA32_QM_EVTSEL		0x0c8d
+
+struct rmid_entry {
+	u32				rmid;
+	int				busy;
+	struct list_head		list;
+};
+
+/**
+ * @rmid_free_lru    A least recently used list of free RMIDs
+ *     These RMIDs are guaranteed to have an occupancy less than the
+ *     threshold occupancy
+ */
+static LIST_HEAD(rmid_free_lru);
+
+/**
+ * @rmid_limbo_count     count of currently unused but (potentially)
+ *     dirty RMIDs.
+ *     This counts RMIDs that no one is currently using but that
+ *     may have a occupancy value > intel_cqm_threshold. User can change
+ *     the threshold occupancy value.
+ */
+unsigned int rmid_limbo_count;
+
+/**
+ * @rmid_entry - The entry in the limbo and free lists.
+ */
+static struct rmid_entry	*rmid_ptrs;
+
+/*
+ * Global boolean for rdt_monitor which is true if any
+ * resource monitoring is enabled.
+ */
+bool rdt_mon_capable;
+
+/*
+ * Global to indicate which monitoring events are enabled.
+ */
+unsigned int rdt_mon_features;
+
+/*
+ * This is the threshold cache occupancy at which we will consider an
+ * RMID available for re-allocation.
+ */
+unsigned int intel_cqm_threshold;
+
+static inline struct rmid_entry *__rmid_entry(u32 rmid)
+{
+	struct rmid_entry *entry;
+
+	entry = &rmid_ptrs[rmid];
+	WARN_ON(entry->rmid != rmid);
+
+	return entry;
+}
+
+static u64 __rmid_read(u32 rmid, u32 eventid)
+{
+	u64 val;
+
+	/*
+	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
+	 * with a valid event code for supported resource type and the bits
+	 * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
+	 * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
+	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
+	 * are error bits.
+	 */
+	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+	rdmsrl(MSR_IA32_QM_CTR, val);
+
+	return val;
+}
+
+static bool rmid_dirty(struct rmid_entry *entry)
+{
+	u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
+
+	return val >= intel_cqm_threshold;
+}
+
+/*
+ * Check the RMIDs that are marked as busy for this domain. If the
+ * reported LLC occupancy is below the threshold clear the busy bit and
+ * decrement the count. If the busy count gets to zero on an RMID, we
+ * free the RMID
+ */
+void __check_limbo(struct rdt_domain *d, bool force_free)
+{
+	struct rmid_entry *entry;
+	struct rdt_resource *r;
+	u32 crmid = 1, nrmid;
+
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	/*
+	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
+	 * are marked as busy for occupancy < threshold. If the occupancy
+	 * is less than the threshold decrement the busy counter of the
+	 * RMID and move it to the free list when the counter reaches 0.
+	 */
+	for (;;) {
+		nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid);
+		if (nrmid >= r->num_rmid)
+			break;
+
+		entry = __rmid_entry(nrmid);
+		if (force_free || !rmid_dirty(entry)) {
+			clear_bit(entry->rmid, d->rmid_busy_llc);
+			if (!--entry->busy) {
+				rmid_limbo_count--;
+				list_add_tail(&entry->list, &rmid_free_lru);
+			}
+		}
+		crmid = nrmid + 1;
+	}
+}
+
+bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d)
+{
+	return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid;
+}
+
+/*
+ * As of now the RMIDs allocation is global.
+ * However we keep track of which packages the RMIDs
+ * are used to optimize the limbo list management.
+ */
+int alloc_rmid(void)
+{
+	struct rmid_entry *entry;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (list_empty(&rmid_free_lru))
+		return rmid_limbo_count ? -EBUSY : -ENOSPC;
+
+	entry = list_first_entry(&rmid_free_lru,
+				 struct rmid_entry, list);
+	list_del(&entry->list);
+
+	return entry->rmid;
+}
+
+static void add_rmid_to_limbo(struct rmid_entry *entry)
+{
+	struct rdt_resource *r;
+	struct rdt_domain *d;
+	int cpu;
+	u64 val;
+
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	entry->busy = 0;
+	cpu = get_cpu();
+	list_for_each_entry(d, &r->domains, list) {
+		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
+			val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
+			if (val <= intel_cqm_threshold)
+				continue;
+		}
+
+		/*
+		 * For the first limbo RMID in the domain,
+		 * setup up the limbo worker.
+		 */
+		if (!has_busy_rmid(r, d))
+			cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL);
+		set_bit(entry->rmid, d->rmid_busy_llc);
+		entry->busy++;
+	}
+	put_cpu();
+
+	if (entry->busy)
+		rmid_limbo_count++;
+	else
+		list_add_tail(&entry->list, &rmid_free_lru);
+}
+
+void free_rmid(u32 rmid)
+{
+	struct rmid_entry *entry;
+
+	if (!rmid)
+		return;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	entry = __rmid_entry(rmid);
+
+	if (is_llc_occupancy_enabled())
+		add_rmid_to_limbo(entry);
+	else
+		list_add_tail(&entry->list, &rmid_free_lru);
+}
+
+static int __mon_event_count(u32 rmid, struct rmid_read *rr)
+{
+	u64 chunks, shift, tval;
+	struct mbm_state *m;
+
+	tval = __rmid_read(rmid, rr->evtid);
+	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
+		rr->val = tval;
+		return -EINVAL;
+	}
+	switch (rr->evtid) {
+	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
+		 * an invalid event id would fail the __rmid_read.
+		 */
+		return -EINVAL;
+	}
+
+	if (rr->first) {
+		m->prev_msr = tval;
+		m->chunks = 0;
+		return 0;
+	}
+
+	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;
+}
+
+/*
+ * This is called via IPI to read the CQM/MBM counters
+ * on a domain.
+ */
+void mon_event_count(void *info)
+{
+	struct rdtgroup *rdtgrp, *entry;
+	struct rmid_read *rr = info;
+	struct list_head *head;
+
+	rdtgrp = rr->rgrp;
+
+	if (__mon_event_count(rdtgrp->mon.rmid, rr))
+		return;
+
+	/*
+	 * For Ctrl groups read data from child monitor groups.
+	 */
+	head = &rdtgrp->mon.crdtgrp_list;
+
+	if (rdtgrp->type == RDTCTRL_GROUP) {
+		list_for_each_entry(entry, head, mon.crdtgrp_list) {
+			if (__mon_event_count(entry->mon.rmid, rr))
+				return;
+		}
+	}
+}
+
+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);
+	}
+}
+
+/*
+ * Handler to scan the limbo list and move the RMIDs
+ * to free list whose occupancy < threshold_occupancy.
+ */
+void cqm_handle_limbo(struct work_struct *work)
+{
+	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
+	int cpu = smp_processor_id();
+	struct rdt_resource *r;
+	struct rdt_domain *d;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+	d = get_domain_from_cpu(cpu, r);
+
+	if (!d) {
+		pr_warn_once("Failure to get domain for limbo worker\n");
+		goto out_unlock;
+	}
+
+	__check_limbo(d, false);
+
+	if (has_busy_rmid(r, d))
+		schedule_delayed_work_on(cpu, &d->cqm_limbo, delay);
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+{
+	unsigned long delay = msecs_to_jiffies(delay_ms);
+	struct rdt_resource *r;
+	int cpu;
+
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	cpu = cpumask_any(&dom->cpu_mask);
+	dom->cqm_work_cpu = cpu;
+
+	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
+}
+
+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_ms)
+{
+	unsigned long delay = msecs_to_jiffies(delay_ms);
+	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;
+	int i, nr_rmids;
+
+	nr_rmids = r->num_rmid;
+	rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL);
+	if (!rmid_ptrs)
+		return -ENOMEM;
+
+	for (i = 0; i < nr_rmids; i++) {
+		entry = &rmid_ptrs[i];
+		INIT_LIST_HEAD(&entry->list);
+
+		entry->rmid = i;
+		list_add_tail(&entry->list, &rmid_free_lru);
+	}
+
+	/*
+	 * RMID 0 is special and is always allocated. It's used for all
+	 * tasks that are not monitored.
+	 */
+	entry = __rmid_entry(0);
+	list_del(&entry->list);
+
+	return 0;
+}
+
+static struct mon_evt llc_occupancy_event = {
+	.name		= "llc_occupancy",
+	.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.
+ *
+ * Note that MBM events are also part of RDT_RESOURCE_L3 resource
+ * because as per the SDM the total and local memory bandwidth
+ * are enumerated as part of L3 monitoring.
+ */
+static void l3_mon_evt_init(struct rdt_resource *r)
+{
+	INIT_LIST_HEAD(&r->evt_list);
+
+	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)
+{
+	int ret;
+
+	r->mon_scale = boot_cpu_data.x86_cache_occ_scale;
+	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+
+	/*
+	 * A reasonable upper limit on the max threshold is the number
+	 * of lines tagged per RMID if all RMIDs have the same number of
+	 * lines tagged in the LLC.
+	 *
+	 * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
+	 */
+	intel_cqm_threshold = boot_cpu_data.x86_cache_size * 1024 / r->num_rmid;
+
+	/* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */
+	intel_cqm_threshold /= r->mon_scale;
+
+	ret = dom_data_init(r);
+	if (ret)
+		return ret;
+
+	l3_mon_evt_init(r);
+
+	r->mon_capable = true;
+	r->mon_enabled = true;
+
+	return 0;
+}