1 files changed, 293 insertions, 26 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index e5a48f05e787..e2c1599d1b37 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -325,12 +325,7 @@ static void update_cpu_closid_rmid(void *info)
 static void
 update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
 {
-	int cpu = get_cpu();
-
-	if (cpumask_test_cpu(cpu, cpu_mask))
-		update_cpu_closid_rmid(r);
-	smp_call_function_many(cpu_mask, update_cpu_closid_rmid, r, 1);
-	put_cpu();
+	on_each_cpu_mask(cpu_mask, update_cpu_closid_rmid, r, 1);
 }
 
 static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
@@ -580,8 +575,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	/*
 	 * Ensure the task's closid and rmid are written before determining if
 	 * the task is current that will decide if it will be interrupted.
+	 * This pairs with the full barrier between the rq->curr update and
+	 * resctrl_sched_in() during context switch.
 	 */
-	barrier();
+	smp_mb();
 
 	/*
 	 * By now, the task's closid and rmid are set. If the task is current
@@ -1001,8 +998,11 @@ static int rdt_mon_features_show(struct kernfs_open_file *of,
 	struct rdt_resource *r = of->kn->parent->priv;
 	struct mon_evt *mevt;
 
-	list_for_each_entry(mevt, &r->evt_list, list)
+	list_for_each_entry(mevt, &r->evt_list, list) {
 		seq_printf(seq, "%s\n", mevt->name);
+		if (mevt->configurable)
+			seq_printf(seq, "%s_config\n", mevt->name);
+	}
 
 	return 0;
 }
@@ -1213,7 +1213,7 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
 
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
-		if (r->rid == RDT_RESOURCE_MBA)
+		if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
 			continue;
 		has_cache = true;
 		list_for_each_entry(d, &r->domains, list) {
@@ -1402,7 +1402,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 					ctrl = resctrl_arch_get_config(r, d,
 								       closid,
 								       type);
-				if (r->rid == RDT_RESOURCE_MBA)
+				if (r->rid == RDT_RESOURCE_MBA ||
+				    r->rid == RDT_RESOURCE_SMBA)
 					size = ctrl;
 				else
 					size = rdtgroup_cbm_to_size(r, d, ctrl);
@@ -1419,6 +1420,248 @@ out:
 	return ret;
 }
 
+struct mon_config_info {
+	u32 evtid;
+	u32 mon_config;
+};
+
+#define INVALID_CONFIG_INDEX   UINT_MAX
+
+/**
+ * mon_event_config_index_get - get the hardware index for the
+ *                              configurable event
+ * @evtid: event id.
+ *
+ * Return: 0 for evtid == QOS_L3_MBM_TOTAL_EVENT_ID
+ *         1 for evtid == QOS_L3_MBM_LOCAL_EVENT_ID
+ *         INVALID_CONFIG_INDEX for invalid evtid
+ */
+static inline unsigned int mon_event_config_index_get(u32 evtid)
+{
+	switch (evtid) {
+	case QOS_L3_MBM_TOTAL_EVENT_ID:
+		return 0;
+	case QOS_L3_MBM_LOCAL_EVENT_ID:
+		return 1;
+	default:
+		/* Should never reach here */
+		return INVALID_CONFIG_INDEX;
+	}
+}
+
+static void mon_event_config_read(void *info)
+{
+	struct mon_config_info *mon_info = info;
+	unsigned int index;
+	u64 msrval;
+
+	index = mon_event_config_index_get(mon_info->evtid);
+	if (index == INVALID_CONFIG_INDEX) {
+		pr_warn_once("Invalid event id %d\n", mon_info->evtid);
+		return;
+	}
+	rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval);
+
+	/* Report only the valid event configuration bits */
+	mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
+}
+
+static void mondata_config_read(struct rdt_domain *d, struct mon_config_info *mon_info)
+{
+	smp_call_function_any(&d->cpu_mask, mon_event_config_read, mon_info, 1);
+}
+
+static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
+{
+	struct mon_config_info mon_info = {0};
+	struct rdt_domain *dom;
+	bool sep = false;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	list_for_each_entry(dom, &r->domains, list) {
+		if (sep)
+			seq_puts(s, ";");
+
+		memset(&mon_info, 0, sizeof(struct mon_config_info));
+		mon_info.evtid = evtid;
+		mondata_config_read(dom, &mon_info);
+
+		seq_printf(s, "%d=0x%02x", dom->id, mon_info.mon_config);
+		sep = true;
+	}
+	seq_puts(s, "\n");
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
+				       struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID);
+
+	return 0;
+}
+
+static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
+				       struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID);
+
+	return 0;
+}
+
+static void mon_event_config_write(void *info)
+{
+	struct mon_config_info *mon_info = info;
+	unsigned int index;
+
+	index = mon_event_config_index_get(mon_info->evtid);
+	if (index == INVALID_CONFIG_INDEX) {
+		pr_warn_once("Invalid event id %d\n", mon_info->evtid);
+		return;
+	}
+	wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0);
+}
+
+static int mbm_config_write_domain(struct rdt_resource *r,
+				   struct rdt_domain *d, u32 evtid, u32 val)
+{
+	struct mon_config_info mon_info = {0};
+	int ret = 0;
+
+	/* mon_config cannot be more than the supported set of events */
+	if (val > MAX_EVT_CONFIG_BITS) {
+		rdt_last_cmd_puts("Invalid event configuration\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Read the current config value first. If both are the same then
+	 * no need to write it again.
+	 */
+	mon_info.evtid = evtid;
+	mondata_config_read(d, &mon_info);
+	if (mon_info.mon_config == val)
+		goto out;
+
+	mon_info.mon_config = val;
+
+	/*
+	 * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the
+	 * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE
+	 * are scoped at the domain level. Writing any of these MSRs
+	 * on one CPU is observed by all the CPUs in the domain.
+	 */
+	smp_call_function_any(&d->cpu_mask, mon_event_config_write,
+			      &mon_info, 1);
+
+	/*
+	 * When an Event Configuration is changed, the bandwidth counters
+	 * for all RMIDs and Events will be cleared by the hardware. The
+	 * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for
+	 * every RMID on the next read to any event for every RMID.
+	 * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62)
+	 * cleared while it is tracked by the hardware. Clear the
+	 * mbm_local and mbm_total counts for all the RMIDs.
+	 */
+	resctrl_arch_reset_rmid_all(r, d);
+
+out:
+	return ret;
+}
+
+static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
+{
+	char *dom_str = NULL, *id_str;
+	unsigned long dom_id, val;
+	struct rdt_domain *d;
+	int ret = 0;
+
+next:
+	if (!tok || tok[0] == '\0')
+		return 0;
+
+	/* Start processing the strings for each domain */
+	dom_str = strim(strsep(&tok, ";"));
+	id_str = strsep(&dom_str, "=");
+
+	if (!id_str || kstrtoul(id_str, 10, &dom_id)) {
+		rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n");
+		return -EINVAL;
+	}
+
+	if (!dom_str || kstrtoul(dom_str, 16, &val)) {
+		rdt_last_cmd_puts("Non-numeric event configuration value\n");
+		return -EINVAL;
+	}
+
+	list_for_each_entry(d, &r->domains, list) {
+		if (d->id == dom_id) {
+			ret = mbm_config_write_domain(r, d, evtid, val);
+			if (ret)
+				return -EINVAL;
+			goto next;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
+					    char *buf, size_t nbytes,
+					    loff_t off)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+	int ret;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_last_cmd_clear();
+
+	buf[nbytes - 1] = '\0';
+
+	ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID);
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	return ret ?: nbytes;
+}
+
+static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
+					    char *buf, size_t nbytes,
+					    loff_t off)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+	int ret;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_last_cmd_clear();
+
+	buf[nbytes - 1] = '\0';
+
+	ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID);
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	return ret ?: nbytes;
+}
+
 /* rdtgroup information files for one cache resource. */
 static struct rftype res_common_files[] = {
 	{
@@ -1518,6 +1761,20 @@ static struct rftype res_common_files[] = {
 		.fflags		= RF_MON_INFO | RFTYPE_RES_CACHE,
 	},
 	{
+		.name		= "mbm_total_bytes_config",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= mbm_total_bytes_config_show,
+		.write		= mbm_total_bytes_config_write,
+	},
+	{
+		.name		= "mbm_local_bytes_config",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= mbm_local_bytes_config_show,
+		.write		= mbm_local_bytes_config_write,
+	},
+	{
 		.name		= "cpus",
 		.mode		= 0644,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -1623,6 +1880,15 @@ void __init thread_throttle_mode_init(void)
 	rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB;
 }
 
+void __init mbm_config_rftype_init(const char *config)
+{
+	struct rftype *rft;
+
+	rft = rdtgroup_get_rftype_by_name(config);
+	if (rft)
+		rft->fflags = RF_MON_INFO | RFTYPE_RES_CACHE;
+}
+
 /**
  * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
  * @r: The resource group with which the file is associated.
@@ -1864,13 +2130,9 @@ static int set_cache_qos_cfg(int level, bool enable)
 			/* Pick one CPU from each domain instance to update MSR */
 			cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
 	}
-	cpu = get_cpu();
-	/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
-	if (cpumask_test_cpu(cpu, cpu_mask))
-		update(&enable);
-	/* Update QOS_CFG MSR on all other cpus in cpu_mask. */
-	smp_call_function_many(cpu_mask, update, &enable, 1);
-	put_cpu();
+
+	/* Update QOS_CFG MSR on all the CPUs in cpu_mask */
+	on_each_cpu_mask(cpu_mask, update, &enable, 1);
 
 	free_cpumask_var(cpu_mask);
 
@@ -2347,7 +2609,7 @@ static int reset_all_ctrls(struct rdt_resource *r)
 	struct msr_param msr_param;
 	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
-	int i, cpu;
+	int i;
 
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
@@ -2368,13 +2630,9 @@ static int reset_all_ctrls(struct rdt_resource *r)
 		for (i = 0; i < hw_res->num_closid; i++)
 			hw_dom->ctrl_val[i] = r->default_ctrl;
 	}
-	cpu = get_cpu();
-	/* Update CBM on this cpu if it's in cpu_mask. */
-	if (cpumask_test_cpu(cpu, cpu_mask))
-		rdt_ctrl_update(&msr_param);
-	/* Update CBM on all other cpus in cpu_mask. */
-	smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-	put_cpu();
+
+	/* Update CBM on all the CPUs in cpu_mask */
+	on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
 
 	free_cpumask_var(cpu_mask);
 
@@ -2402,6 +2660,14 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
 			WRITE_ONCE(t->rmid, to->mon.rmid);
 
 			/*
+			 * Order the closid/rmid stores above before the loads
+			 * in task_curr(). This pairs with the full barrier
+			 * between the rq->curr update and resctrl_sched_in()
+			 * during context switch.
+			 */
+			smp_mb();
+
+			/*
 			 * If the task is on a CPU, set the CPU in the mask.
 			 * The detection is inaccurate as tasks might move or
 			 * schedule before the smp function call takes place.
@@ -2845,7 +3111,8 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
-		if (r->rid == RDT_RESOURCE_MBA) {
+		if (r->rid == RDT_RESOURCE_MBA ||
+		    r->rid == RDT_RESOURCE_SMBA) {
 			rdtgroup_init_mba(r, rdtgrp->closid);
 			if (is_mba_sc(r))
 				continue;