Merge tag 'x86_cache_for_v6.14_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 resource control updates from Borislav Petkov:

 - Extend resctrl with the capability of total memory bandwidth
   monitoring, thus accomodating systems which support only total but
   not local memory bandwidth monitoring. Add the respective new mount
   options

 - The usual cleanups

* tag 'x86_cache_for_v6.14_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/resctrl: Document the new "mba_MBps_event" file
  x86/resctrl: Add write option to "mba_MBps_event" file
  x86/resctrl: Add "mba_MBps_event" file to CTRL_MON directories
  x86/resctrl: Make mba_sc use total bandwidth if local is not supported
  x86/resctrl: Compute memory bandwidth for all supported events
  x86/resctrl: Modify update_mba_bw() to use per CTRL_MON group event
  x86/resctrl: Prepare for per-CTRL_MON group mba_MBps control
  x86/resctrl: Introduce resctrl_file_fflags_init() to initialize fflags
  x86/resctrl: Use kthread_run_on_cpu()

7 files changed, 178 insertions, 87 deletions

diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst
index a824affd741d1..6768fc1fad166 100644
--- a/Documentation/arch/x86/resctrl.rst
+++ b/Documentation/arch/x86/resctrl.rst
@@ -384,6 +384,16 @@ When monitoring is enabled all MON groups will also contain:
 	Available only with debug option. The identifier used by hardware
 	for the monitor group. On x86 this is the RMID.
 
+When the "mba_MBps" mount option is used all CTRL_MON groups will also contain:
+
+"mba_MBps_event":
+	Reading this file shows which memory bandwidth event is used
+	as input to the software feedback loop that keeps memory bandwidth
+	below the value specified in the schemata file. Writing the
+	name of one of the supported memory bandwidth events found in
+	/sys/fs/resctrl/info/L3_MON/mon_features changes the input
+	event.
+
 Resource allocation rules
 -------------------------
 
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index b681c2e07dbf8..3d1735ed8d1ff 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -234,7 +234,9 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r)
 		r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD;
 	else
 		r->membw.throttle_mode = THREAD_THROTTLE_MAX;
-	thread_throttle_mode_init();
+
+	resctrl_file_fflags_init("thread_throttle_mode",
+				 RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
 
 	r->alloc_capable = true;
 
@@ -961,6 +963,11 @@ static __init bool get_rdt_mon_resources(void)
 	if (!rdt_mon_features)
 		return false;
 
+	if (is_mbm_local_enabled())
+		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+	else if (is_mbm_total_enabled())
+		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
+
 	return !rdt_get_mon_l3_config(r);
 }
 
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 200d89a640270..536351159cc23 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -518,6 +518,76 @@ static int smp_mon_event_count(void *arg)
 	return 0;
 }
 
+ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+	buf[nbytes - 1] = '\0';
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+	rdt_last_cmd_clear();
+
+	if (!strcmp(buf, "mbm_local_bytes")) {
+		if (is_mbm_local_enabled())
+			rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+		else
+			ret = -EINVAL;
+	} else if (!strcmp(buf, "mbm_total_bytes")) {
+		if (is_mbm_total_enabled())
+			rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID;
+		else
+			ret = -EINVAL;
+	} else {
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		rdt_last_cmd_printf("Unsupported event id '%s'\n", buf);
+
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret ?: nbytes;
+}
+
+int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
+				 struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp) {
+		switch (rdtgrp->mba_mbps_event) {
+		case QOS_L3_MBM_LOCAL_EVENT_ID:
+			seq_puts(s, "mbm_local_bytes\n");
+			break;
+		case QOS_L3_MBM_TOTAL_EVENT_ID:
+			seq_puts(s, "mbm_total_bytes\n");
+			break;
+		default:
+			pr_warn_once("Bad event %d\n", rdtgrp->mba_mbps_event);
+			ret = -EINVAL;
+			break;
+		}
+	} else {
+		ret = -ENOENT;
+	}
+
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
 		    cpumask_t *cpumask, int evtid, int first)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 955999aecfca9..20c898f09b7e7 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -283,6 +283,7 @@ struct pseudo_lock_region {
  *				monitor only or ctrl_mon group
  * @mon:			mongroup related data
  * @mode:			mode of resource group
+ * @mba_mbps_event:		input monitoring event id when mba_sc is enabled
  * @plr:			pseudo-locked region
  */
 struct rdtgroup {
@@ -295,6 +296,7 @@ struct rdtgroup {
 	enum rdt_group_type		type;
 	struct mongroup			mon;
 	enum rdtgrp_mode		mode;
+	enum resctrl_event_id		mba_mbps_event;
 	struct pseudo_lock_region	*plr;
 };
 
@@ -508,6 +510,7 @@ extern struct mutex rdtgroup_mutex;
 extern struct rdt_hw_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
 extern struct dentry *debugfs_resctrl;
+extern enum resctrl_event_id mba_mbps_default_event;
 
 enum resctrl_res_level {
 	RDT_RESOURCE_L3,
@@ -607,6 +610,10 @@ 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,
 			   struct seq_file *s, void *v);
+ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off);
+int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
+				 struct seq_file *s, void *v);
 bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
 			   unsigned long cbm, int closid, bool exclusive);
 unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d,
@@ -647,10 +654,8 @@ void cqm_handle_limbo(struct work_struct *work);
 bool has_busy_rmid(struct rdt_mon_domain *d);
 void __check_limbo(struct rdt_mon_domain *d, bool force_free);
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
-void __init thread_throttle_mode_init(void);
-void __init mbm_config_rftype_init(const char *config);
+void resctrl_file_fflags_init(const char *config, unsigned long fflags);
 void rdt_staged_configs_clear(void);
 bool closid_allocated(unsigned int closid);
 int resctrl_find_cleanest_closid(void);
-
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 5fcb3d635d915..94a1d97804614 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -663,9 +663,12 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
  */
 static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
-	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-	struct mbm_state *m = &rr->d->mbm_local[idx];
 	u64 cur_bw, bytes, cur_bytes;
+	struct mbm_state *m;
+
+	m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
+	if (WARN_ON_ONCE(!m))
+		return;
 
 	cur_bytes = rr->val;
 	bytes = cur_bytes - m->prev_bw_bytes;
@@ -752,20 +755,20 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	u32 closid, rmid, cur_msr_val, new_msr_val;
 	struct mbm_state *pmbm_data, *cmbm_data;
 	struct rdt_ctrl_domain *dom_mba;
+	enum resctrl_event_id evt_id;
 	struct rdt_resource *r_mba;
-	u32 cur_bw, user_bw, idx;
 	struct list_head *head;
 	struct rdtgroup *entry;
-
-	if (!is_mbm_local_enabled())
-		return;
+	u32 cur_bw, user_bw;
 
 	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+	evt_id = rgrp->mba_mbps_event;
 
 	closid = rgrp->closid;
 	rmid = rgrp->mon.rmid;
-	idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-	pmbm_data = &dom_mbm->mbm_local[idx];
+	pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id);
+	if (WARN_ON_ONCE(!pmbm_data))
+		return;
 
 	dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba);
 	if (!dom_mba) {
@@ -784,7 +787,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	 */
 	head = &rgrp->mon.crdtgrp_list;
 	list_for_each_entry(entry, head, mon.crdtgrp_list) {
-		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+		cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id);
+		if (WARN_ON_ONCE(!cmbm_data))
+			return;
 		cur_bw += cmbm_data->prev_bw;
 	}
 
@@ -813,54 +818,45 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
 }
 
-static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
-		       u32 closid, u32 rmid)
+static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
+				 u32 closid, u32 rmid, enum resctrl_event_id evtid)
 {
 	struct rmid_read rr = {0};
 
 	rr.r = r;
 	rr.d = d;
+	rr.evtid = evtid;
+	rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+	if (IS_ERR(rr.arch_mon_ctx)) {
+		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+				    PTR_ERR(rr.arch_mon_ctx));
+		return;
+	}
+
+	__mon_event_count(closid, rmid, &rr);
 
 	/*
-	 * This is protected from concurrent reads from user
-	 * as both the user and we hold the global mutex.
+	 * If the software controller is enabled, compute the
+	 * bandwidth for this event id.
 	 */
-	if (is_mbm_total_enabled()) {
-		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
-		rr.val = 0;
-		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-		if (IS_ERR(rr.arch_mon_ctx)) {
-			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-					    PTR_ERR(rr.arch_mon_ctx));
-			return;
-		}
-
-		__mon_event_count(closid, rmid, &rr);
+	if (is_mba_sc(NULL))
+		mbm_bw_count(closid, rmid, &rr);
 
-		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-	}
-	if (is_mbm_local_enabled()) {
-		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
-		rr.val = 0;
-		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-		if (IS_ERR(rr.arch_mon_ctx)) {
-			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-					    PTR_ERR(rr.arch_mon_ctx));
-			return;
-		}
-
-		__mon_event_count(closid, rmid, &rr);
+	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
+}
 
-		/*
-		 * Call the MBA software controller only for the
-		 * control groups and when user has enabled
-		 * the software controller explicitly.
-		 */
-		if (is_mba_sc(NULL))
-			mbm_bw_count(closid, rmid, &rr);
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
+		       u32 closid, u32 rmid)
+{
+	/*
+	 * This is protected from concurrent reads from user as both
+	 * the user and overflow handler hold the global mutex.
+	 */
+	if (is_mbm_total_enabled())
+		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
 
-		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-	}
+	if (is_mbm_local_enabled())
+		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
 /*
@@ -1224,11 +1220,13 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 
 		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
 			mbm_total_event.configurable = true;
-			mbm_config_rftype_init("mbm_total_bytes_config");
+			resctrl_file_fflags_init("mbm_total_bytes_config",
+						 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 		}
 		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
 			mbm_local_event.configurable = true;
-			mbm_config_rftype_init("mbm_local_bytes_config");
+			resctrl_file_fflags_init("mbm_local_bytes_config",
+						 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 		}
 	}
 
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 972e6b6b0481f..6c60c16a9dd03 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -1205,20 +1205,14 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 	plr->cpu = cpu;
 
 	if (sel == 1)
-		thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
-						cpu_to_node(cpu),
-						"pseudo_lock_measure/%u",
-						cpu);
+		thread = kthread_run_on_cpu(measure_cycles_lat_fn, plr,
+					    cpu, "pseudo_lock_measure/%u");
 	else if (sel == 2)
-		thread = kthread_create_on_node(measure_l2_residency, plr,
-						cpu_to_node(cpu),
-						"pseudo_lock_measure/%u",
-						cpu);
+		thread = kthread_run_on_cpu(measure_l2_residency, plr,
+					    cpu, "pseudo_lock_measure/%u");
 	else if (sel == 3)
-		thread = kthread_create_on_node(measure_l3_residency, plr,
-						cpu_to_node(cpu),
-						"pseudo_lock_measure/%u",
-						cpu);
+		thread = kthread_run_on_cpu(measure_l3_residency, plr,
+					    cpu, "pseudo_lock_measure/%u");
 	else
 		goto out;
 
@@ -1226,8 +1220,6 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 		ret = PTR_ERR(thread);
 		goto out;
 	}
-	kthread_bind(thread, cpu);
-	wake_up_process(thread);
 
 	ret = wait_event_interruptible(plr->lock_thread_wq,
 				       plr->thread_done == 1);
@@ -1315,18 +1307,14 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 	plr->thread_done = 0;
 
-	thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp,
-					cpu_to_node(plr->cpu),
-					"pseudo_lock/%u", plr->cpu);
+	thread = kthread_run_on_cpu(pseudo_lock_fn, rdtgrp,
+				    plr->cpu, "pseudo_lock/%u");
 	if (IS_ERR(thread)) {
 		ret = PTR_ERR(thread);
 		rdt_last_cmd_printf("Locking thread returned error %d\n", ret);
 		goto out_cstates;
 	}
 
-	kthread_bind(thread, plr->cpu);
-	wake_up_process(thread);
-
 	ret = wait_event_interruptible(plr->lock_thread_wq,
 				       plr->thread_done == 1);
 	if (ret < 0) {
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index d906a1cd84917..6419e04d8a7b2 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -65,6 +65,15 @@ static void rdtgroup_destroy_root(void);
 
 struct dentry *debugfs_resctrl;
 
+/*
+ * Memory bandwidth monitoring event to use for the default CTRL_MON group
+ * and each new CTRL_MON group created by the user.  Only relevant when
+ * the filesystem is mounted with the "mba_MBps" option so it does not
+ * matter that it remains uninitialized on systems that do not support
+ * the "mba_MBps" option.
+ */
+enum resctrl_event_id mba_mbps_default_event;
+
 static bool resctrl_debug;
 
 void rdt_last_cmd_clear(void)
@@ -1942,6 +1951,13 @@ static struct rftype res_common_files[] = {
 		.fflags		= RFTYPE_CTRL_BASE,
 	},
 	{
+		.name		= "mba_MBps_event",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_mba_mbps_event_write,
+		.seq_show	= rdtgroup_mba_mbps_event_show,
+	},
+	{
 		.name		= "mode",
 		.mode		= 0644,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -2020,24 +2036,13 @@ static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
 	return NULL;
 }
 
-void __init thread_throttle_mode_init(void)
-{
-	struct rftype *rft;
-
-	rft = rdtgroup_get_rftype_by_name("thread_throttle_mode");
-	if (!rft)
-		return;
-
-	rft->fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB;
-}
-
-void __init mbm_config_rftype_init(const char *config)
+void resctrl_file_fflags_init(const char *config, unsigned long fflags)
 {
 	struct rftype *rft;
 
 	rft = rdtgroup_get_rftype_by_name(config);
 	if (rft)
-		rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE;
+		rft->fflags = fflags;
 }
 
 /**
@@ -2343,7 +2348,7 @@ static bool supports_mba_mbps(void)
 	struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 
-	return (is_mbm_local_enabled() &&
+	return (is_mbm_enabled() &&
 		r->alloc_capable && is_mba_linear() &&
 		r->ctrl_scope == rmbm->mon_scope);
 }
@@ -2357,6 +2362,7 @@ static int set_mba_sc(bool mba_sc)
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 	u32 num_closid = resctrl_arch_get_num_closid(r);
 	struct rdt_ctrl_domain *d;
+	unsigned long fflags;
 	int i;
 
 	if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
@@ -2364,11 +2370,16 @@ static int set_mba_sc(bool mba_sc)
 
 	r->membw.mba_sc = mba_sc;
 
+	rdtgroup_default.mba_mbps_event = mba_mbps_default_event;
+
 	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
 		for (i = 0; i < num_closid; i++)
 			d->mbps_val[i] = MBA_MAX_MBPS;
 	}
 
+	fflags = mba_sc ? RFTYPE_CTRL_BASE | RFTYPE_MON_BASE : 0;
+	resctrl_file_fflags_init("mba_MBps_event", fflags);
+
 	return 0;
 }
 
@@ -2768,7 +2779,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		ctx->enable_cdpl2 = true;
 		return 0;
 	case Opt_mba_mbps:
-		msg = "mba_MBps requires local MBM and linear scale MBA at L3 scope";
+		msg = "mba_MBps requires MBM and linear scale MBA at L3 scope";
 		if (!supports_mba_mbps())
 			return invalfc(fc, msg);
 		ctx->enable_mba_mbps = true;
@@ -3622,6 +3633,8 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 			rdt_last_cmd_puts("kernfs subdir error\n");
 			goto out_del_list;
 		}
+		if (is_mba_sc(NULL))
+			rdtgrp->mba_mbps_event = mba_mbps_default_event;
 	}
 
 	goto out_unlock;