1 files changed, 188 insertions, 74 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index beccb0e87ba7..536351159cc2 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -19,6 +19,8 @@
 #include <linux/kernfs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/tick.h>
+
 #include "internal.h"
 
 /*
@@ -27,10 +29,10 @@
  * hardware. The allocated bandwidth percentage is rounded to the next
  * control step available on the hardware.
  */
-static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
+static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
-	unsigned long bw;
 	int ret;
+	u32 bw;
 
 	/*
 	 * Only linear delay values is supported for current Intel SKUs.
@@ -40,16 +42,21 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 		return false;
 	}
 
-	ret = kstrtoul(buf, 10, &bw);
+	ret = kstrtou32(buf, 10, &bw);
 	if (ret) {
-		rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
+		rdt_last_cmd_printf("Invalid MB value %s\n", buf);
 		return false;
 	}
 
-	if ((bw < r->membw.min_bw || bw > r->default_ctrl) &&
-	    !is_mba_sc(r)) {
-		rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
-				    r->membw.min_bw, r->default_ctrl);
+	/* Nothing else to do if software controller is enabled. */
+	if (is_mba_sc(r)) {
+		*data = bw;
+		return true;
+	}
+
+	if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+		rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n",
+				    bw, r->membw.min_bw, r->default_ctrl);
 		return false;
 	}
 
@@ -58,16 +65,16 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 }
 
 int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
-	     struct rdt_domain *d)
+	     struct rdt_ctrl_domain *d)
 {
 	struct resctrl_staged_config *cfg;
 	u32 closid = data->rdtgrp->closid;
 	struct rdt_resource *r = s->res;
-	unsigned long bw_val;
+	u32 bw_val;
 
 	cfg = &d->staged_config[s->conf_type];
 	if (cfg->have_new_ctrl) {
-		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
+		rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
 		return -EINVAL;
 	}
 
@@ -137,7 +144,7 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
  * resource type.
  */
 int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
-	      struct rdt_domain *d)
+	      struct rdt_ctrl_domain *d)
 {
 	struct rdtgroup *rdtgrp = data->rdtgrp;
 	struct resctrl_staged_config *cfg;
@@ -146,7 +153,7 @@ int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
 
 	cfg = &d->staged_config[s->conf_type];
 	if (cfg->have_new_ctrl) {
-		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
+		rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
 		return -EINVAL;
 	}
 
@@ -206,10 +213,13 @@ static int parse_line(char *line, struct resctrl_schema *s,
 	struct resctrl_staged_config *cfg;
 	struct rdt_resource *r = s->res;
 	struct rdt_parse_data data;
+	struct rdt_ctrl_domain *d;
 	char *dom = NULL, *id;
-	struct rdt_domain *d;
 	unsigned long dom_id;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
 	    (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
 		rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
@@ -226,8 +236,8 @@ next:
 		return -EINVAL;
 	}
 	dom = strim(dom);
-	list_for_each_entry(d, &r->domains, list) {
-		if (d->id == dom_id) {
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
 			data.buf = dom;
 			data.rdtgrp = rdtgrp;
 			if (r->parse_ctrlval(&data, s, d))
@@ -267,39 +277,24 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
 	}
 }
 
-static bool apply_config(struct rdt_hw_domain *hw_dom,
-			 struct resctrl_staged_config *cfg, u32 idx,
-			 cpumask_var_t cpu_mask)
-{
-	struct rdt_domain *dom = &hw_dom->d_resctrl;
-
-	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
-		cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask);
-		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
-
-		return true;
-	}
-
-	return false;
-}
-
-int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
 {
+	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	u32 idx = get_config_index(closid, t);
 	struct msr_param msr_param;
 
-	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+	if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask))
 		return -EINVAL;
 
 	hw_dom->ctrl_val[idx] = cfg_val;
 
 	msr_param.res = r;
+	msr_param.dom = d;
 	msr_param.low = idx;
 	msr_param.high = idx + 1;
-	hw_res->msr_update(d, &msr_param, r);
+	hw_res->msr_update(&msr_param);
 
 	return 0;
 }
@@ -307,48 +302,42 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 {
 	struct resctrl_staged_config *cfg;
-	struct rdt_hw_domain *hw_dom;
+	struct rdt_hw_ctrl_domain *hw_dom;
 	struct msr_param msr_param;
+	struct rdt_ctrl_domain *d;
 	enum resctrl_conf_type t;
-	cpumask_var_t cpu_mask;
-	struct rdt_domain *d;
 	u32 idx;
 
-	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
-		return -ENOMEM;
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
 
-	msr_param.res = NULL;
-	list_for_each_entry(d, &r->domains, list) {
-		hw_dom = resctrl_to_arch_dom(d);
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+		hw_dom = resctrl_to_arch_ctrl_dom(d);
+		msr_param.res = NULL;
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
 			if (!cfg->have_new_ctrl)
 				continue;
 
 			idx = get_config_index(closid, t);
-			if (!apply_config(hw_dom, cfg, idx, cpu_mask))
+			if (cfg->new_ctrl == hw_dom->ctrl_val[idx])
 				continue;
+			hw_dom->ctrl_val[idx] = cfg->new_ctrl;
 
 			if (!msr_param.res) {
 				msr_param.low = idx;
 				msr_param.high = msr_param.low + 1;
 				msr_param.res = r;
+				msr_param.dom = d;
 			} else {
 				msr_param.low = min(msr_param.low, idx);
 				msr_param.high = max(msr_param.high, idx + 1);
 			}
 		}
+		if (msr_param.res)
+			smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	}
 
-	if (cpumask_empty(cpu_mask))
-		goto done;
-
-	/* Update resource control msr on all the CPUs. */
-	on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-
-done:
-	free_cpumask_var(cpu_mask);
-
 	return 0;
 }
 
@@ -379,11 +368,9 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 		return -EINVAL;
 	buf[nbytes - 1] = '\0';
 
-	cpus_read_lock();
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
 		rdtgroup_kn_unlock(of->kn);
-		cpus_read_unlock();
 		return -ENOENT;
 	}
 	rdt_last_cmd_clear();
@@ -445,14 +432,13 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 out:
 	rdt_staged_configs_clear();
 	rdtgroup_kn_unlock(of->kn);
-	cpus_read_unlock();
 	return ret ?: nbytes;
 }
 
-u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
+u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 			    u32 closid, enum resctrl_conf_type type)
 {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
 	u32 idx = get_config_index(closid, type);
 
 	return hw_dom->ctrl_val[idx];
@@ -461,12 +447,15 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
 static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
 {
 	struct rdt_resource *r = schema->res;
-	struct rdt_domain *dom;
+	struct rdt_ctrl_domain *dom;
 	bool sep = false;
 	u32 ctrl_val;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	seq_printf(s, "%*s:", max_name_width, schema->name);
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
 		if (sep)
 			seq_puts(s, ";");
 
@@ -476,7 +465,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 			ctrl_val = resctrl_arch_get_config(r, dom, closid,
 							   schema->conf_type);
 
-		seq_printf(s, r->format_str, dom->id, max_data_width,
+		seq_printf(s, r->format_str, dom->hdr.id, max_data_width,
 			   ctrl_val);
 		sep = true;
 	}
@@ -505,7 +494,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			} else {
 				seq_printf(s, "%s:%d=%x\n",
 					   rdtgrp->plr->s->res->name,
-					   rdtgrp->plr->d->id,
+					   rdtgrp->plr->d->hdr.id,
 					   rdtgrp->plr->cbm);
 			}
 		} else {
@@ -522,32 +511,132 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 	return ret;
 }
 
+static int smp_mon_event_count(void *arg)
+{
+	mon_event_count(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_domain *d, struct rdtgroup *rdtgrp,
-		    int evtid, int first)
+		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+		    cpumask_t *cpumask, int evtid, int first)
 {
+	int cpu;
+
+	/* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	/*
-	 * setup the parameters to send to the IPI to read the data.
+	 * Setup the parameters to pass to mon_event_count() to read the data.
 	 */
 	rr->rgrp = rdtgrp;
 	rr->evtid = evtid;
 	rr->r = r;
 	rr->d = d;
-	rr->val = 0;
 	rr->first = first;
+	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
+	if (IS_ERR(rr->arch_mon_ctx)) {
+		rr->err = -EINVAL;
+		return;
+	}
+
+	cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU);
+
+	/*
+	 * cpumask_any_housekeeping() prefers housekeeping CPUs, but
+	 * are all the CPUs nohz_full? If yes, pick a CPU to IPI.
+	 * MPAM's resctrl_arch_rmid_read() is unable to read the
+	 * counters on some platforms if its called in IRQ context.
+	 */
+	if (tick_nohz_full_cpu(cpu))
+		smp_call_function_any(cpumask, mon_event_count, rr, 1);
+	else
+		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
 
-	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
+	struct rdt_domain_hdr *hdr;
+	struct rmid_read rr = {0};
+	struct rdt_mon_domain *d;
 	u32 resid, evtid, domid;
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
 	union mon_data_bits md;
-	struct rdt_domain *d;
-	struct rmid_read rr;
 	int ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
@@ -560,15 +649,40 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	resid = md.u.rid;
 	domid = md.u.domid;
 	evtid = md.u.evtid;
-
 	r = &rdt_resources_all[resid].r_resctrl;
-	d = rdt_find_domain(r, domid, NULL);
-	if (IS_ERR_OR_NULL(d)) {
+
+	if (md.u.sum) {
+		/*
+		 * This file requires summing across all domains that share
+		 * the L3 cache id that was provided in the "domid" field of the
+		 * mon_data_bits union. Search all domains in the resource for
+		 * one that matches this cache id.
+		 */
+		list_for_each_entry(d, &r->mon_domains, hdr.list) {
+			if (d->ci->id == domid) {
+				rr.ci = d->ci;
+				mon_event_read(&rr, r, NULL, rdtgrp,
+					       &d->ci->shared_cpu_map, evtid, false);
+				goto checkresult;
+			}
+		}
 		ret = -ENOENT;
 		goto out;
+	} else {
+		/*
+		 * This file provides data from a single domain. Search
+		 * the resource to find the domain with "domid".
+		 */
+		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_mon_domain, hdr);
+		mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false);
 	}
 
-	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
+checkresult:
 
 	if (rr.err == -EIO)
 		seq_puts(m, "Error\n");