1 files changed, 209 insertions, 50 deletions

diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 77d08229d855..0320360cd7a6 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -123,14 +123,8 @@ void rdt_staged_configs_clear(void)
 
 static bool resctrl_is_mbm_enabled(void)
 {
-	return (resctrl_arch_is_mbm_total_enabled() ||
-		resctrl_arch_is_mbm_local_enabled());
-}
-
-static bool resctrl_is_mbm_event(int e)
-{
-	return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
-		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
+	return (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID) ||
+		resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID));
 }
 
 /*
@@ -196,7 +190,7 @@ static int closid_alloc(void)
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) &&
-	    resctrl_arch_is_llc_occupancy_enabled()) {
+	    resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) {
 		cleanest_closid = resctrl_find_cleanest_closid();
 		if (cleanest_closid < 0)
 			return cleanest_closid;
@@ -981,7 +975,7 @@ static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
 	return 0;
 }
 
-static void *rdt_kn_parent_priv(struct kernfs_node *kn)
+void *rdt_kn_parent_priv(struct kernfs_node *kn)
 {
 	/*
 	 * The parent pointer is only valid within RCU section since it can be
@@ -1141,7 +1135,7 @@ static int rdt_num_rmids_show(struct kernfs_open_file *of,
 {
 	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 
-	seq_printf(seq, "%d\n", r->num_rmid);
+	seq_printf(seq, "%d\n", r->mon.num_rmid);
 
 	return 0;
 }
@@ -1152,9 +1146,12 @@ static int rdt_mon_features_show(struct kernfs_open_file *of,
 	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 	struct mon_evt *mevt;
 
-	list_for_each_entry(mevt, &r->evt_list, list) {
+	for_each_mon_event(mevt) {
+		if (mevt->rid != r->rid || !mevt->enabled)
+			continue;
 		seq_printf(seq, "%s\n", mevt->name);
-		if (mevt->configurable)
+		if (mevt->configurable &&
+		    !resctrl_arch_mbm_cntr_assign_enabled(r))
 			seq_printf(seq, "%s_config\n", mevt->name);
 	}
 
@@ -1735,9 +1732,9 @@ next:
 	}
 
 	/* Value from user cannot be more than the supported set of events */
-	if ((val & r->mbm_cfg_mask) != val) {
+	if ((val & r->mon.mbm_cfg_mask) != val) {
 		rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
-				    r->mbm_cfg_mask);
+				    r->mon.mbm_cfg_mask);
 		return -EINVAL;
 	}
 
@@ -1803,6 +1800,44 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
 	return ret ?: nbytes;
 }
 
+/*
+ * resctrl_bmec_files_show() — Controls the visibility of BMEC-related resctrl
+ * files. When @show is true, the files are displayed; when false, the files
+ * are hidden.
+ * Don't treat kernfs_find_and_get failure as an error, since this function may
+ * be called regardless of whether BMEC is supported or the event is enabled.
+ */
+void resctrl_bmec_files_show(struct rdt_resource *r, struct kernfs_node *l3_mon_kn,
+			     bool show)
+{
+	struct kernfs_node *kn_config, *mon_kn = NULL;
+	char name[32];
+
+	if (!l3_mon_kn) {
+		sprintf(name, "%s_MON", r->name);
+		mon_kn = kernfs_find_and_get(kn_info, name);
+		if (!mon_kn)
+			return;
+		l3_mon_kn = mon_kn;
+	}
+
+	kn_config = kernfs_find_and_get(l3_mon_kn, "mbm_total_bytes_config");
+	if (kn_config) {
+		kernfs_show(kn_config, show);
+		kernfs_put(kn_config);
+	}
+
+	kn_config = kernfs_find_and_get(l3_mon_kn, "mbm_local_bytes_config");
+	if (kn_config) {
+		kernfs_show(kn_config, show);
+		kernfs_put(kn_config);
+	}
+
+	/* Release the reference only if it was acquired */
+	if (mon_kn)
+		kernfs_put(mon_kn);
+}
+
 /* rdtgroup information files for one cache resource. */
 static struct rftype res_common_files[] = {
 	{
@@ -1813,6 +1848,13 @@ static struct rftype res_common_files[] = {
 		.fflags		= RFTYPE_TOP_INFO,
 	},
 	{
+		.name		= "mbm_assign_on_mkdir",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= resctrl_mbm_assign_on_mkdir_show,
+		.write		= resctrl_mbm_assign_on_mkdir_write,
+	},
+	{
 		.name		= "num_closids",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -1827,6 +1869,12 @@ static struct rftype res_common_files[] = {
 		.fflags		= RFTYPE_MON_INFO,
 	},
 	{
+		.name		= "available_mbm_cntrs",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= resctrl_available_mbm_cntrs_show,
+	},
+	{
 		.name		= "num_rmids",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -1841,6 +1889,12 @@ static struct rftype res_common_files[] = {
 		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
 	},
 	{
+		.name		= "num_mbm_cntrs",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= resctrl_num_mbm_cntrs_show,
+	},
+	{
 		.name		= "min_cbm_bits",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -1916,6 +1970,28 @@ static struct rftype res_common_files[] = {
 		.write		= mbm_local_bytes_config_write,
 	},
 	{
+		.name		= "event_filter",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= event_filter_show,
+		.write		= event_filter_write,
+	},
+	{
+		.name		= "mbm_L3_assignments",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= mbm_L3_assignments_show,
+		.write		= mbm_L3_assignments_write,
+	},
+	{
+		.name		= "mbm_assign_mode",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= resctrl_mbm_assign_mode_show,
+		.write		= resctrl_mbm_assign_mode_write,
+		.fflags		= RFTYPE_MON_INFO | RFTYPE_RES_CACHE,
+	},
+	{
 		.name		= "cpus",
 		.mode		= 0644,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -2168,10 +2244,48 @@ int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
 	return ret;
 }
 
+static int resctrl_mkdir_event_configs(struct rdt_resource *r, struct kernfs_node *l3_mon_kn)
+{
+	struct kernfs_node *kn_subdir, *kn_subdir2;
+	struct mon_evt *mevt;
+	int ret;
+
+	kn_subdir = kernfs_create_dir(l3_mon_kn, "event_configs", l3_mon_kn->mode, NULL);
+	if (IS_ERR(kn_subdir))
+		return PTR_ERR(kn_subdir);
+
+	ret = rdtgroup_kn_set_ugid(kn_subdir);
+	if (ret)
+		return ret;
+
+	for_each_mon_event(mevt) {
+		if (mevt->rid != r->rid || !mevt->enabled || !resctrl_is_mbm_event(mevt->evtid))
+			continue;
+
+		kn_subdir2 = kernfs_create_dir(kn_subdir, mevt->name, kn_subdir->mode, mevt);
+		if (IS_ERR(kn_subdir2)) {
+			ret = PTR_ERR(kn_subdir2);
+			goto out;
+		}
+
+		ret = rdtgroup_kn_set_ugid(kn_subdir2);
+		if (ret)
+			goto out;
+
+		ret = rdtgroup_add_files(kn_subdir2, RFTYPE_ASSIGN_CONFIG);
+		if (ret)
+			break;
+	}
+
+out:
+	return ret;
+}
+
 static int rdtgroup_mkdir_info_resdir(void *priv, char *name,
 				      unsigned long fflags)
 {
 	struct kernfs_node *kn_subdir;
+	struct rdt_resource *r;
 	int ret;
 
 	kn_subdir = kernfs_create_dir(kn_info, name,
@@ -2184,8 +2298,25 @@ static int rdtgroup_mkdir_info_resdir(void *priv, char *name,
 		return ret;
 
 	ret = rdtgroup_add_files(kn_subdir, fflags);
-	if (!ret)
-		kernfs_activate(kn_subdir);
+	if (ret)
+		return ret;
+
+	if ((fflags & RFTYPE_MON_INFO) == RFTYPE_MON_INFO) {
+		r = priv;
+		if (r->mon.mbm_cntr_assignable) {
+			ret = resctrl_mkdir_event_configs(r, kn_subdir);
+			if (ret)
+				return ret;
+			/*
+			 * Hide BMEC related files if mbm_event mode
+			 * is enabled.
+			 */
+			if (resctrl_arch_mbm_cntr_assign_enabled(r))
+				resctrl_bmec_files_show(r, kn_subdir, false);
+		}
+	}
+
+	kernfs_activate(kn_subdir);
 
 	return ret;
 }
@@ -2608,10 +2739,8 @@ static int rdt_get_tree(struct fs_context *fc)
 		goto out_root;
 
 	ret = schemata_list_create();
-	if (ret) {
-		schemata_list_destroy();
-		goto out_ctx;
-	}
+	if (ret)
+		goto out_schemata_free;
 
 	ret = closid_init();
 	if (ret)
@@ -2637,6 +2766,8 @@ static int rdt_get_tree(struct fs_context *fc)
 		if (ret < 0)
 			goto out_info;
 
+		rdtgroup_assign_cntrs(&rdtgroup_default);
+
 		ret = mkdir_mondata_all(rdtgroup_default.kn,
 					&rdtgroup_default, &kn_mondata);
 		if (ret < 0)
@@ -2675,15 +2806,16 @@ out_mondata:
 	if (resctrl_arch_mon_capable())
 		kernfs_remove(kn_mondata);
 out_mongrp:
-	if (resctrl_arch_mon_capable())
+	if (resctrl_arch_mon_capable()) {
+		rdtgroup_unassign_cntrs(&rdtgroup_default);
 		kernfs_remove(kn_mongrp);
+	}
 out_info:
 	kernfs_remove(kn_info);
 out_closid_exit:
 	closid_exit();
 out_schemata_free:
 	schemata_list_destroy();
-out_ctx:
 	rdt_disable_ctx();
 out_root:
 	rdtgroup_destroy_root();
@@ -2822,6 +2954,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
 
 	head = &rdtgrp->mon.crdtgrp_list;
 	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
+		rdtgroup_unassign_cntrs(sentry);
 		free_rmid(sentry->closid, sentry->mon.rmid);
 		list_del(&sentry->mon.crdtgrp_list);
 
@@ -2862,6 +2995,8 @@ static void rmdir_all_sub(void)
 		cpumask_or(&rdtgroup_default.cpu_mask,
 			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
 
+		rdtgroup_unassign_cntrs(rdtgrp);
+
 		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 
 		kernfs_remove(rdtgrp->kn);
@@ -2946,6 +3081,7 @@ static void resctrl_fs_teardown(void)
 		return;
 
 	rmdir_all_sub();
+	rdtgroup_unassign_cntrs(&rdtgroup_default);
 	mon_put_kn_priv();
 	rdt_pseudo_lock_release();
 	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
@@ -3057,10 +3193,9 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 	struct mon_evt *mevt;
 	int ret, domid;
 
-	if (WARN_ON(list_empty(&r->evt_list)))
-		return -EPERM;
-
-	list_for_each_entry(mevt, &r->evt_list, list) {
+	for_each_mon_event(mevt) {
+		if (mevt->rid != r->rid || !mevt->enabled)
+			continue;
 		domid = do_sum ? d->ci_id : d->hdr.id;
 		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
 		if (WARN_ON_ONCE(!priv))
@@ -3427,9 +3562,12 @@ static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp)
 	}
 	rdtgrp->mon.rmid = ret;
 
+	rdtgroup_assign_cntrs(rdtgrp);
+
 	ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
 	if (ret) {
 		rdt_last_cmd_puts("kernfs subdir error\n");
+		rdtgroup_unassign_cntrs(rdtgrp);
 		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 		return ret;
 	}
@@ -3439,8 +3577,10 @@ static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp)
 
 static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
 {
-	if (resctrl_arch_mon_capable())
+	if (resctrl_arch_mon_capable()) {
+		rdtgroup_unassign_cntrs(rgrp);
 		free_rmid(rgrp->closid, rgrp->mon.rmid);
+	}
 }
 
 /*
@@ -3716,6 +3856,9 @@ static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 	update_closid_rmid(tmpmask, NULL);
 
 	rdtgrp->flags = RDT_DELETED;
+
+	rdtgroup_unassign_cntrs(rdtgrp);
+
 	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 
 	/*
@@ -3763,6 +3906,8 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
 	update_closid_rmid(tmpmask, NULL);
 
+	rdtgroup_unassign_cntrs(rdtgrp);
+
 	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 	closid_free(rdtgrp->closid);
 
@@ -4022,9 +4167,14 @@ static void rdtgroup_setup_default(void)
 
 static void domain_destroy_mon_state(struct rdt_mon_domain *d)
 {
+	int idx;
+
+	kfree(d->cntr_cfg);
 	bitmap_free(d->rmid_busy_llc);
-	kfree(d->mbm_total);
-	kfree(d->mbm_local);
+	for_each_mbm_idx(idx) {
+		kfree(d->mbm_states[idx]);
+		d->mbm_states[idx] = NULL;
+	}
 }
 
 void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
@@ -4050,7 +4200,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d
 
 	if (resctrl_is_mbm_enabled())
 		cancel_delayed_work(&d->mbm_over);
-	if (resctrl_arch_is_llc_occupancy_enabled() && has_busy_rmid(d)) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && has_busy_rmid(d)) {
 		/*
 		 * When a package is going down, forcefully
 		 * decrement rmid->ebusy. There is no way to know
@@ -4084,32 +4234,41 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d
 static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-	size_t tsize;
+	size_t tsize = sizeof(*d->mbm_states[0]);
+	enum resctrl_event_id eventid;
+	int idx;
 
-	if (resctrl_arch_is_llc_occupancy_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) {
 		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
 		if (!d->rmid_busy_llc)
 			return -ENOMEM;
 	}
-	if (resctrl_arch_is_mbm_total_enabled()) {
-		tsize = sizeof(*d->mbm_total);
-		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
-		if (!d->mbm_total) {
-			bitmap_free(d->rmid_busy_llc);
-			return -ENOMEM;
-		}
+
+	for_each_mbm_event_id(eventid) {
+		if (!resctrl_is_mon_event_enabled(eventid))
+			continue;
+		idx = MBM_STATE_IDX(eventid);
+		d->mbm_states[idx] = kcalloc(idx_limit, tsize, GFP_KERNEL);
+		if (!d->mbm_states[idx])
+			goto cleanup;
 	}
-	if (resctrl_arch_is_mbm_local_enabled()) {
-		tsize = sizeof(*d->mbm_local);
-		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
-		if (!d->mbm_local) {
-			bitmap_free(d->rmid_busy_llc);
-			kfree(d->mbm_total);
-			return -ENOMEM;
-		}
+
+	if (resctrl_is_mbm_enabled() && r->mon.mbm_cntr_assignable) {
+		tsize = sizeof(*d->cntr_cfg);
+		d->cntr_cfg = kcalloc(r->mon.num_mbm_cntrs, tsize, GFP_KERNEL);
+		if (!d->cntr_cfg)
+			goto cleanup;
 	}
 
 	return 0;
+cleanup:
+	bitmap_free(d->rmid_busy_llc);
+	for_each_mbm_idx(idx) {
+		kfree(d->mbm_states[idx]);
+		d->mbm_states[idx] = NULL;
+	}
+
+	return -ENOMEM;
 }
 
 int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
@@ -4144,7 +4303,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
 					   RESCTRL_PICK_ANY_CPU);
 	}
 
-	if (resctrl_arch_is_llc_occupancy_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID))
 		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
 
 	/*
@@ -4219,7 +4378,7 @@ void resctrl_offline_cpu(unsigned int cpu)
 			cancel_delayed_work(&d->mbm_over);
 			mbm_setup_overflow_handler(d, 0, cpu);
 		}
-		if (resctrl_arch_is_llc_occupancy_enabled() &&
+		if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) &&
 		    cpu == d->cqm_work_cpu && has_busy_rmid(d)) {
 			cancel_delayed_work(&d->cqm_limbo);
 			cqm_setup_limbo_handler(d, 0, cpu);