x86/resctrl: Prepare for different scope for control/monitor operations

Resctrl assumes that control and monitor operations on a resource are
performed at the same scope.

Prepare for systems that use different scope (specifically Intel needs
to split the RDT_RESOURCE_L3 resource to use L3 scope for cache control
and NODE scope for cache occupancy and memory bandwidth monitoring).

Create separate domain lists for control and monitor operations.

Note that errors during initialization of either control or monitor
functions on a domain would previously result in that domain being
excluded from both control and monitor operations. Now the domains are
allocated independently it is no longer required to disable both control
and monitor operations if either fail.
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20240628215619.76401-4-tony.luck@intel.com

arch/x86/kernel/cpu/resctrl/ctrlmondata.c

@@ -231,7 +231,7 @@ static int parse_line(char *line, struct resctrl_schema *s,
 		return -EINVAL;
 	}
 	dom = strim(dom);
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
 		if (d->hdr.id == dom_id) {
 			data.buf = dom;
 			data.rdtgrp = rdtgrp;
@@ -306,7 +306,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 	/* Walking r->domains, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
 		hw_dom = resctrl_to_arch_dom(d);
 		msr_param.res = NULL;
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
@@ -450,7 +450,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	lockdep_assert_cpus_held();
 
 	seq_printf(s, "%*s:", max_name_width, schema->name);
-	list_for_each_entry(dom, &r->domains, hdr.list) {
+	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
 		if (sep)
 			seq_puts(s, ";");
 
@@ -556,6 +556,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
+	struct rdt_domain_hdr *hdr;
 	u32 resid, evtid, domid;
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
@@ -576,11 +577,12 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	evtid = md.u.evtid;
 
 	r = &rdt_resources_all[resid].r_resctrl;
-	d = rdt_find_domain(r, domid, NULL);
-	if (!d) {
+	hdr = rdt_find_domain(&r->mon_domains, domid, NULL);
+	if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) {
 		ret = -ENOENT;
 		goto out;
 	}
+	d = container_of(hdr, struct rdt_domain, hdr);
 
 	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 

arch/x86/kernel/cpu/resctrl/internal.h

@@ -558,8 +558,8 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn);
 int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
 int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
 			     umode_t mask);
-struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
-				   struct list_head **pos);
+struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id,
+				       struct list_head **pos);
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
@@ -578,7 +578,8 @@ int rdt_pseudo_lock_init(void);
 void rdt_pseudo_lock_release(void);
 int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
 void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
-struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
+struct rdt_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r);
+struct rdt_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r);
 int closids_supported(void);
 void closid_free(int closid);
 int alloc_rmid(u32 closid);

arch/x86/kernel/cpu/resctrl/monitor.c

@@ -490,7 +490,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
 
 	entry->busy = 0;
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
 		/*
 		 * For the first limbo RMID in the domain,
 		 * setup up the limbo worker.
@@ -687,7 +687,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	idx = resctrl_arch_rmid_idx_encode(closid, rmid);
 	pmbm_data = &dom_mbm->mbm_local[idx];
 
-	dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba);
+	dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba);
 	if (!dom_mba) {
 		pr_warn_once("Failure to get domain for MBA update\n");
 		return;

arch/x86/kernel/cpu/resctrl/pseudo_lock.c

@@ -292,7 +292,7 @@ static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
  */
 static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 {
-	enum resctrl_scope scope = plr->s->res->scope;
+	enum resctrl_scope scope = plr->s->res->ctrl_scope;
 	struct cacheinfo *ci;
 	int ret;
 
@@ -854,7 +854,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	 * associated with them.
 	 */
 	for_each_alloc_capable_rdt_resource(r) {
-		list_for_each_entry(d_i, &r->domains, hdr.list) {
+		list_for_each_entry(d_i, &r->ctrl_domains, hdr.list) {
 			if (d_i->plr)
 				cpumask_or(cpu_with_psl, cpu_with_psl,
 					   &d_i->hdr.cpu_mask);

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -98,7 +98,7 @@ void rdt_staged_configs_clear(void)
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	for_each_alloc_capable_rdt_resource(r) {
-		list_for_each_entry(dom, &r->domains, hdr.list)
+		list_for_each_entry(dom, &r->ctrl_domains, hdr.list)
 			memset(dom->staged_config, 0, sizeof(dom->staged_config));
 	}
 }
@@ -1021,7 +1021,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 	hw_shareable = r->cache.shareable_bits;
-	list_for_each_entry(dom, &r->domains, hdr.list) {
+	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
 		if (sep)
 			seq_putc(seq, ';');
 		sw_shareable = 0;
@@ -1343,7 +1343,7 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
 		if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
 			continue;
 		has_cache = true;
-		list_for_each_entry(d, &r->domains, hdr.list) {
+		list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
 			ctrl = resctrl_arch_get_config(r, d, closid,
 						       s->conf_type);
 			if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
@@ -1454,11 +1454,11 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 	struct cacheinfo *ci;
 	int num_b;
 
-	if (WARN_ON_ONCE(r->scope != RESCTRL_L2_CACHE && r->scope != RESCTRL_L3_CACHE))
+	if (WARN_ON_ONCE(r->ctrl_scope != RESCTRL_L2_CACHE && r->ctrl_scope != RESCTRL_L3_CACHE))
 		return size;
 
 	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
-	ci = get_cpu_cacheinfo_level(cpumask_any(&d->hdr.cpu_mask), r->scope);
+	ci = get_cpu_cacheinfo_level(cpumask_any(&d->hdr.cpu_mask), r->ctrl_scope);
 	if (ci)
 		size = ci->size / r->cache.cbm_len * num_b;
 
@@ -1514,7 +1514,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 		type = schema->conf_type;
 		sep = false;
 		seq_printf(s, "%*s:", max_name_width, schema->name);
-		list_for_each_entry(d, &r->domains, hdr.list) {
+		list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
 			if (sep)
 				seq_putc(s, ';');
 			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
@@ -1604,7 +1604,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
-	list_for_each_entry(dom, &r->domains, hdr.list) {
+	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
 		if (sep)
 			seq_puts(s, ";");
 
@@ -1728,7 +1728,7 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
 		return -EINVAL;
 	}
 
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
 		if (d->hdr.id == dom_id) {
 			mbm_config_write_domain(r, d, evtid, val);
 			goto next;
@@ -2276,7 +2276,7 @@ static int set_cache_qos_cfg(int level, bool enable)
 		return -ENOMEM;
 
 	r_l = &rdt_resources_all[level].r_resctrl;
-	list_for_each_entry(d, &r_l->domains, hdr.list) {
+	list_for_each_entry(d, &r_l->ctrl_domains, hdr.list) {
 		if (r_l->cache.arch_has_per_cpu_cfg)
 			/* Pick all the CPUs in the domain instance */
 			for_each_cpu(cpu, &d->hdr.cpu_mask)
@@ -2361,7 +2361,7 @@ static int set_mba_sc(bool mba_sc)
 
 	r->membw.mba_sc = mba_sc;
 
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
 		for (i = 0; i < num_closid; i++)
 			d->mbps_val[i] = MBA_MAX_MBPS;
 	}
@@ -2700,7 +2700,7 @@ static int rdt_get_tree(struct fs_context *fc)
 
 	if (is_mbm_enabled()) {
 		r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-		list_for_each_entry(dom, &r->domains, hdr.list)
+		list_for_each_entry(dom, &r->mon_domains, hdr.list)
 			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
 						   RESCTRL_PICK_ANY_CPU);
 	}
@@ -2824,10 +2824,10 @@ static int reset_all_ctrls(struct rdt_resource *r)
 
 	/*
 	 * Disable resource control for this resource by setting all
-	 * CBMs in all domains to the maximum mask value. Pick one CPU
+	 * CBMs in all ctrl_domains to the maximum mask value. Pick one CPU
 	 * from each domain to update the MSRs below.
 	 */
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
 		hw_dom = resctrl_to_arch_dom(d);
 
 		for (i = 0; i < hw_res->num_closid; i++)
@@ -3098,7 +3098,7 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
 	/* Walking r->domains, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
-	list_for_each_entry(dom, &r->domains, hdr.list) {
+	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
 		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
 		if (ret)
 			return ret;
@@ -3280,7 +3280,7 @@ static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
 	struct rdt_domain *d;
 	int ret;
 
-	list_for_each_entry(d, &s->res->domains, hdr.list) {
+	list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) {
 		ret = __init_one_rdt_domain(d, s, closid);
 		if (ret < 0)
 			return ret;
@@ -3295,7 +3295,7 @@ static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
 	struct resctrl_staged_config *cfg;
 	struct rdt_domain *d;
 
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
 		if (is_mba_sc(r)) {
 			d->mbps_val[closid] = MBA_MAX_MBPS;
 			continue;
@@ -3926,15 +3926,19 @@ static void domain_destroy_mon_state(struct rdt_domain *d)
 	kfree(d->mbm_local);
 }
 
-void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
+void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_domain *d)
 {
 	mutex_lock(&rdtgroup_mutex);
 
 	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
 		mba_sc_domain_destroy(r, d);
 
-	if (!r->mon_capable)
-		goto out_unlock;
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain *d)
+{
+	mutex_lock(&rdtgroup_mutex);
 
 	/*
 	 * If resctrl is mounted, remove all the
@@ -3960,7 +3964,6 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
 
 	domain_destroy_mon_state(d);
 
-out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
 }
 
@@ -3995,7 +3998,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 	return 0;
 }
 
-int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
+int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_domain *d)
 {
 	int err = 0;
 
@@ -4004,11 +4007,18 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
 	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) {
 		/* RDT_RESOURCE_MBA is never mon_capable */
 		err = mba_sc_domain_allocate(r, d);
-		goto out_unlock;
 	}
 
-	if (!r->mon_capable)
-		goto out_unlock;
+	mutex_unlock(&rdtgroup_mutex);
+
+	return err;
+}
+
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain *d)
+{
+	int err;
+
+	mutex_lock(&rdtgroup_mutex);
 
 	err = domain_setup_mon_state(r, d);
 	if (err)
@@ -4073,7 +4083,7 @@ void resctrl_offline_cpu(unsigned int cpu)
 	if (!l3->mon_capable)
 		goto out_unlock;
 
-	d = get_domain_from_cpu(cpu, l3);
+	d = get_mon_domain_from_cpu(cpu, l3);
 	if (d) {
 		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
 			cancel_delayed_work(&d->mbm_over);

include/linux/resctrl.h

@@ -58,15 +58,22 @@ struct resctrl_staged_config {
 	bool			have_new_ctrl;
 };
 
+enum resctrl_domain_type {
+	RESCTRL_CTRL_DOMAIN,
+	RESCTRL_MON_DOMAIN,
+};
+
 /**
  * struct rdt_domain_hdr - common header for different domain types
  * @list:		all instances of this resource
  * @id:			unique id for this instance
+ * @type:		type of this instance
  * @cpu_mask:		which CPUs share this resource
  */
 struct rdt_domain_hdr {
 	struct list_head		list;
 	int				id;
+	enum resctrl_domain_type	type;
 	struct cpumask			cpu_mask;
 };
 
@@ -169,10 +176,12 @@ enum resctrl_scope {
  * @alloc_capable:	Is allocation available on this machine
  * @mon_capable:	Is monitor feature available on this machine
  * @num_rmid:		Number of RMIDs available
- * @scope:		Scope of this resource
+ * @ctrl_scope:		Scope of this resource for control functions
+ * @mon_scope:		Scope of this resource for monitor functions
  * @cache:		Cache allocation related data
  * @membw:		If the component has bandwidth controls, their properties.
- * @domains:		RCU list of all domains for this resource
+ * @ctrl_domains:	RCU list of all control domains for this resource
+ * @mon_domains:	RCU list of all monitor domains for this resource
  * @name:		Name to use in "schemata" file.
  * @data_width:		Character width of data when displaying
  * @default_ctrl:	Specifies default cache cbm or memory B/W percent.
@@ -187,10 +196,12 @@ struct rdt_resource {
 	bool			alloc_capable;
 	bool			mon_capable;
 	int			num_rmid;
-	enum resctrl_scope	scope;
+	enum resctrl_scope	ctrl_scope;
+	enum resctrl_scope	mon_scope;
 	struct resctrl_cache	cache;
 	struct resctrl_membw	membw;
-	struct list_head	domains;
+	struct list_head	ctrl_domains;
+	struct list_head	mon_domains;
 	char			*name;
 	int			data_width;
 	u32			default_ctrl;
@@ -236,8 +247,10 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
 
 u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
 			    u32 closid, enum resctrl_conf_type type);
-int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d);
-void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
+int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_domain *d);
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain *d);
+void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_domain *d);
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain *d);
 void resctrl_online_cpu(unsigned int cpu);
 void resctrl_offline_cpu(unsigned int cpu);