Skip to contentSkip to conversation

x86/resctrl: Add support for Sub-NUMA cluster (SNC) systems

PATCH Superseded Tony Luck 12 participants 331 messages Jul 13, 2023 – Feb 13, 2024 Page 3 of 4

Subsystems (4)

v3 of 23 Superseded Latest is v23 →

lore
Share & tools
lore
reviewer
#215 lore raw

Re: [PATCH v11 1/8] x86/resctrl: Prepare for new domain scope

In reply to Tony Luck

Hi Tony,

Quoted 117 lines · Tony Luck

Resctrl resources operate on subsets of CPUs in the system with the defining attribute of each subset being an instance of a particular level of cache. E.g. all CPUs sharing an L3 cache would be part of the same domain.

In preparation for features that are scoped at the NUMA node level change the code from explicit references to "cache_level" to a more generic scope. At this point the only options for this scope are groups of CPUs that share an L2 cache or L3 cache.

Clean up the error handling when looking up domains. Report invalid id's before calling rdt_find_domain() in preparation for better messages when scope can be other than cache scope. This means that rdt_find_domain() will never return an error. So remove checks for error from the callsites.

---
Changes since v10:
Reinette: Move a blank line in domain_add_cpu()
Reniette: Fix warning message in domain_remove_cpu()

 include/linux/resctrl.h                   |  9 +++--
 arch/x86/kernel/cpu/resctrl/core.c        | 42 +++++++++++++++--------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  2 +-
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  6 +++-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  5 ++-
 5 files changed, 45 insertions(+), 19 deletions(-)
include/linux/resctrl.h +7 -2
index 66942d7fba7f..7d4eb7df611d 100644
@@ -144,13 +144,18 @@ struct resctrl_membw {
 struct rdt_parse_data;
 struct resctrl_schema;
 
+enum resctrl_scope {
+	RESCTRL_L2_CACHE = 2,
+	RESCTRL_L3_CACHE = 3,
+};
+
 /**
  * struct rdt_resource - attributes of a resctrl resource
  * @rid:		The index of the resource
  * @alloc_capable:	Is allocation available on this machine
  * @mon_capable:	Is monitor feature available on this machine
  * @num_rmid:		Number of RMIDs available
- * @cache_level:	Which cache level defines scope of this resource
+ * @scope:		Scope of this resource
  * @cache:		Cache allocation related data
  * @membw:		If the component has bandwidth controls, their properties.
  * @domains:		All domains for this resource
@@ -168,7 +173,7 @@ struct rdt_resource {
 	bool			alloc_capable;
 	bool			mon_capable;
 	int			num_rmid;
-	int			cache_level;
+	enum resctrl_scope	scope;
 	struct resctrl_cache	cache;
 	struct resctrl_membw	membw;
 	struct list_head	domains;
arch/x86/kernel/cpu/resctrl/core.c +6 -7
index 19e0681f0435..9f8d87abd751 100644
@@ -65,7 +65,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_L3,
 			.name			= "L3",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_L3),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -79,7 +79,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_L2,
 			.name			= "L2",
-			.cache_level		= 2,
+			.scope			= RESCTRL_L2_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_L2),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -93,7 +93,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_MBA,
 			.name			= "MB",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_MBA),
 			.parse_ctrlval		= parse_bw,
 			.format_str		= "%d=%*u",
@@ -105,7 +105,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_SMBA,
 			.name			= "SMBA",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_SMBA),
 			.parse_ctrlval		= parse_bw,
 			.format_str		= "%d=%*u",
@@ -401,9 +401,6 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	struct rdt_domain *d;
 	struct list_head *l;
 
-	if (id < 0)
-		return ERR_PTR(-ENODEV);
-
 	list_for_each(l, &r->domains) {
 		d = list_entry(l, struct rdt_domain, list);
 		/* When id is found, return its domain. */
@@ -491,6 +488,19 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
 	return 0;
 }
 
+static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
+{

arch/x86/kernel/cpu/resctrl/core.c static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom) · line 502

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +10 -0
+	switch (scope) {
+	case RESCTRL_L2_CACHE:
+	case RESCTRL_L3_CACHE:
+		return get_cpu_cacheinfo_id(cpu, scope);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}

This function is meanigfull when you introduce node scope RESCTRL_NODE.

Can you please move this to patch 5?

Thanks
Babu

Quoted 108 lines
arch/x86/kernel/cpu/resctrl/core.c +12 -7
+
 /*
  * domain_add_cpu - Add a cpu to a resource's domain list.
  *
@@ -506,18 +516,19 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+	int id = get_domain_id_from_scope(cpu, r->scope);
 	struct list_head *add_pos = NULL;
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 	int err;
 
-	d = rdt_find_domain(r, id, &add_pos);
-	if (IS_ERR(d)) {
-		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
+	if (id < 0) {
+		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->scope, r->name);
 		return;
 	}
 
+	d = rdt_find_domain(r, id, &add_pos);
 	if (d) {
 		cpumask_set_cpu(cpu, &d->cpu_mask);
 		if (r->cache.arch_has_per_cpu_cfg)
@@ -556,13 +567,16 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+	int id = get_domain_id_from_scope(cpu, r->scope);
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 
+	if (id < 0)
+		return;
+
 	d = rdt_find_domain(r, id, NULL);
-	if (IS_ERR_OR_NULL(d)) {
-		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
+	if (!d) {
+		pr_warn("Couldn't find domain with id=%d for CPU %d\n", id, cpu);
 		return;
 	}
 	hw_dom = resctrl_to_arch_dom(d);
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +1 -1
index beccb0e87ba7..3f8891d57fac 100644
@@ -563,7 +563,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 	r = &rdt_resources_all[resid].r_resctrl;
 	d = rdt_find_domain(r, domid, NULL);
-	if (IS_ERR_OR_NULL(d)) {
+	if (!d) {
 		ret = -ENOENT;
 		goto out;
 	}
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +5 -1
index 8f559eeae08e..2a682da9f43a 100644
@@ -292,10 +292,14 @@ 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;
 	struct cpu_cacheinfo *ci;
 	int ret;
 	int i;
 
+	if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
+		return -ENODEV;
+
 	/* Pick the first cpu we find that is associated with the cache. */
 	plr->cpu = cpumask_first(&plr->d->cpu_mask);
 
@@ -311,7 +315,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
 
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == plr->s->res->cache_level) {
+		if (ci->info_list[i].level == scope) {
 			plr->line_size = ci->info_list[i].coherency_line_size;
 			return 0;
 		}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +4 -1
index 69a1de92384a..c44be64d65ec 100644
@@ -1413,10 +1413,13 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 	unsigned int size = 0;
 	int num_b, i;
 
+	if (WARN_ON_ONCE(r->scope != RESCTRL_L2_CACHE && r->scope != RESCTRL_L3_CACHE))
+		return size;
+
 	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
 	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == r->cache_level) {
+		if (ci->info_list[i].level == r->scope) {
 			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
 			break;
 		}
Signature · 2 lines
Thanks
Babu Moger
author maintainer
#216 lore raw

RE: [PATCH v11 1/8] x86/resctrl: Prepare for new domain scope

Quoted 15 lines

arch/x86/kernel/cpu/resctrl/core.c static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom) · line 502

Quoted 12 lines
arch/x86/kernel/cpu/resctrl/core.c +12 -0
+static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
+{
+   switch (scope) {
+   case RESCTRL_L2_CACHE:
+   case RESCTRL_L3_CACHE:
+           return get_cpu_cacheinfo_id(cpu, scope);
+   default:
+           break;
+   }
+
+   return -EINVAL;
+}

This function is meanigfull when you introduce node scope RESCTRL_NODE.

Quoted 1 line

Can you please move this to patch 5?

Code has been this way since v5. I'll note your opinion and if others agree I'll move it. But I think this is a reasonable part of the first step moving away from purely cache scope for domains.

-Tony

maintainer Reviewed-by on v11 1/8
#217 lore raw

Re: [PATCH v11 1/8] x86/resctrl: Prepare for new domain scope

In reply to Tony Luck

Hi Tony,

arch/x86/kernel/cpu/resctrl/core.c static void domain_add_cpu(int cpu, struct rdt_resource *r) · line 576

Quoted 12 lines · Tony Luck
arch/x86/kernel/cpu/resctrl/core.c +4 -1
@@ -556,13 +567,16 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+	int id = get_domain_id_from_scope(cpu, r->scope);
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 
+	if (id < 0)
+		return;
+

Apologies for this late comment to this code that has been like this for a few versions. Something must have gone really wrong if id < 0 so I do not think a silent failure is ideal. Could the same warning as above be included here? That is:

	pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
		     cpu, r->scope, r->name);

If you agree, please do ensure that this change propagates to domain_remove_cpu_ctrl() and domain_remove_cpu_mon() in patches that follow, in which case the text is expected to adjust to "Can't find control domain id" and "Can't find monitor domain id" respectively. (btw ... is the switching between "Can't" and "Couldn't" intentional?)

With this change please feel free to include:

Reinette

author maintainer
#218 lore raw

PATCH v11 2/8 x86/resctrl: Prepare to split rdt_domain structure

In reply to Tony Luck

The rdt_domain structure is used for both control and monitor features. It is about to be split into separate structures for these two usages because the scope for control and monitoring features for a resource will be different for future resources.

To allow for common code that scans a list of domains looking for a specific domain id, move all the common fields ("list", "id", "cpu_mask") into their own structure within the rdt_domain structure.

---
 include/linux/resctrl.h                   | 16 ++++--
 arch/x86/kernel/cpu/resctrl/core.c        | 26 +++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 22 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 10 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 14 +++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 60 +++++++++++------------
 6 files changed, 78 insertions(+), 70 deletions(-)
include/linux/resctrl.h +12 -4
index 7d4eb7df611d..c4067150a6b7 100644
@@ -53,10 +53,20 @@ struct resctrl_staged_config {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * struct rdt_domain_hdr - common header for different domain types
  * @list:		all instances of this resource
  * @id:			unique id for this instance
  * @cpu_mask:		which CPUs share this resource
+ */
+struct rdt_domain_hdr {
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+};
+
+/**
+ * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * @hdr:		common header for different domain types
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
  * @mbm_local:		saved state for MBM local bandwidth
@@ -71,9 +81,7 @@ struct resctrl_staged_config {
  *			by closid
  */
 struct rdt_domain {
-	struct list_head		list;
-	int				id;
-	struct cpumask			cpu_mask;
+	struct rdt_domain_hdr		hdr;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;
arch/x86/kernel/cpu/resctrl/core.c +13 -13
index 9f8d87abd751..c0659e84c9e3 100644
@@ -356,9 +356,9 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
 {
 	struct rdt_domain *d;
 
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->cpu_mask))
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
 			return d;
 	}
 
@@ -402,12 +402,12 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	struct list_head *l;
 
 	list_for_each(l, &r->domains) {
-		d = list_entry(l, struct rdt_domain, list);
+		d = list_entry(l, struct rdt_domain, hdr.list);
 		/* When id is found, return its domain. */
-		if (id == d->id)
+		if (id == d->hdr.id)
 			return d;
 		/* Stop searching when finding id's position in sorted list. */
-		if (id < d->id)
+		if (id < d->hdr.id)
 			break;
 	}
 
@@ -530,7 +530,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 	d = rdt_find_domain(r, id, &add_pos);
 	if (d) {
-		cpumask_set_cpu(cpu, &d->cpu_mask);
+		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 		if (r->cache.arch_has_per_cpu_cfg)
 			rdt_domain_reconfigure_cdp(r);
 		return;
@@ -541,8 +541,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 
 	d = &hw_dom->d_resctrl;
-	d->id = id;
-	cpumask_set_cpu(cpu, &d->cpu_mask);
+	d->hdr.id = id;
+	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	rdt_domain_reconfigure_cdp(r);
 
@@ -556,11 +556,11 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	list_add_tail(&d->list, add_pos);
+	list_add_tail(&d->hdr.list, add_pos);
 
 	err = resctrl_online_domain(r, d);
 	if (err) {
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 		domain_free(hw_dom);
 	}
 }
@@ -581,10 +581,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 	}
 	hw_dom = resctrl_to_arch_dom(d);
 
-	cpumask_clear_cpu(cpu, &d->cpu_mask);
-	if (cpumask_empty(&d->cpu_mask)) {
+	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
+	if (cpumask_empty(&d->hdr.cpu_mask)) {
 		resctrl_offline_domain(r, d);
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 
 		/*
 		 * rdt_domain "d" is going to be freed below, so clear
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +11 -11
index 3f8891d57fac..23f8258d36a8 100644
@@ -67,7 +67,7 @@ int parse_bw(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;
 	}
 
@@ -146,7 +146,7 @@ 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;
 	}
 
@@ -226,8 +226,8 @@ static int parse_line(char *line, struct resctrl_schema *s,
 		return -EINVAL;
 	}
 	dom = strim(dom);
-	list_for_each_entry(d, &r->domains, list) {
-		if (d->id == dom_id) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
 			data.buf = dom;
 			data.rdtgrp = rdtgrp;
 			if (r->parse_ctrlval(&data, s, d))
@@ -274,7 +274,7 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
 	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);
+		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
 		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
 
 		return true;
@@ -291,7 +291,7 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 		return -ENOMEM;
 
 	msr_param.res = NULL;
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		hw_dom = resctrl_to_arch_dom(d);
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	u32 ctrl_val;
 
 	seq_printf(s, "%*s:", max_name_width, schema->name);
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
 		if (sep)
 			seq_puts(s, ";");
 
@@ -476,7 +476,7 @@ 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 +505,7 @@ 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 {
@@ -536,7 +536,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	rr->val = 0;
 	rr->first = first;
 
-	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	smp_call_function_any(&d->hdr.cpu_mask, mon_event_count, rr, 1);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
arch/x86/kernel/cpu/resctrl/monitor.c +5 -5
index f136ac046851..dd0ea1bc0092 100644
@@ -238,7 +238,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	u64 msr_val, chunks;
 	int ret;
 
-	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+	if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask))
 		return -EINVAL;
 
 	ret = __rmid_read(rmid, eventid, &msr_val);
@@ -340,8 +340,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
 	entry->busy = 0;
 	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, list) {
-		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
 			err = resctrl_arch_rmid_read(r, d, entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
 						     &val);
@@ -661,7 +661,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
 	dom->cqm_work_cpu = cpu;
 
 	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
@@ -708,7 +708,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
 
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		return;
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
 	dom->mbm_work_cpu = cpu;
 	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
 }
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +7 -7
index 2a682da9f43a..fcbd99e2eb66 100644
@@ -221,7 +221,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
 	int cpu;
 	int ret;
 
-	for_each_cpu(cpu, &plr->d->cpu_mask) {
+	for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
 		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
 		if (!pm_req) {
 			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
@@ -301,7 +301,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 		return -ENODEV;
 
 	/* Pick the first cpu we find that is associated with the cache. */
-	plr->cpu = cpumask_first(&plr->d->cpu_mask);
+	plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 
 	if (!cpu_online(plr->cpu)) {
 		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
@@ -856,10 +856,10 @@ 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, list) {
+		list_for_each_entry(d_i, &r->domains, hdr.list) {
 			if (d_i->plr)
 				cpumask_or(cpu_with_psl, cpu_with_psl,
-					   &d_i->cpu_mask);
+					   &d_i->hdr.cpu_mask);
 		}
 	}
 
@@ -867,7 +867,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	 * Next test if new pseudo-locked region would intersect with
 	 * existing region.
 	 */
-	if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+	if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
 		ret = true;
 
 	free_cpumask_var(cpu_with_psl);
@@ -1199,7 +1199,7 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 	}
 
 	plr->thread_done = 0;
-	cpu = cpumask_first(&plr->d->cpu_mask);
+	cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 	if (!cpu_online(cpu)) {
 		ret = -ENODEV;
 		goto out;
@@ -1529,7 +1529,7 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
 	 * may be scheduled elsewhere and invalidate entries in the
 	 * pseudo-locked region.
 	 */
-	if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) {
+	if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
 		mutex_unlock(&rdtgroup_mutex);
 		return -EINVAL;
 	}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +30 -30

220 lines not on this page · raw message

Signature · 1 line
2.41.0
reviewer
#219 lore raw

Re: [PATCH v11 2/8] x86/resctrl: Prepare to split rdt_domain structure

Hi Tony,

Sorry for the late review. The patches look good for the most part. But we can simplify a little more. Please see my comments below.

Quoted 28 lines · Tony Luck

The rdt_domain structure is used for both control and monitor features. It is about to be split into separate structures for these two usages because the scope for control and monitoring features for a resource will be different for future resources.

To allow for common code that scans a list of domains looking for a specific domain id, move all the common fields ("list", "id", "cpu_mask") into their own structure within the rdt_domain structure.

---
 include/linux/resctrl.h                   | 16 ++++--
 arch/x86/kernel/cpu/resctrl/core.c        | 26 +++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 22 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 10 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 14 +++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 60 +++++++++++------------
 6 files changed, 78 insertions(+), 70 deletions(-)
include/linux/resctrl.h +0 -1
index 7d4eb7df611d..c4067150a6b7 100644
@@ -53,10 +53,20 @@ struct resctrl_staged_config {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource

include/linux/resctrl.h struct resctrl_staged_config { · line 65

Quoted 10 lines
include/linux/resctrl.h +7 -0
+ * struct rdt_domain_hdr - common header for different domain types
  * @list:		all instances of this resource
  * @id:			unique id for this instance
  * @cpu_mask:		which CPUs share this resource
+ */
+struct rdt_domain_hdr {
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+};

I like the idea of separating the domains, one for control and another for monitor. I have some comments on how it can be done to simplify the code. Adding the hdr adds a little complexity to the code.

How about converting the current rdt_domain to explicitly to rdt_mon_domain?

Something like this.

struct rdt_mon_domain {
        struct list_head                list;
        int                             id;
        struct cpumask                  cpu_mask;
        unsigned long                   *rmid_busy_llc;
        struct mbm_state                *mbm_total;
        struct mbm_state                *mbm_local;
        struct delayed_work             mbm_over;
        struct delayed_work             cqm_limbo;
        int                             mbm_work_cpu;
        int                             cqm_work_cpu;
};

Then introduce rdt_ctrl_domain to which separates into two doamins.

struct rdt_ctrl_domain {
        struct list_head                list;
        int                             id;
        struct cpumask                  cpu_mask;
        struct pseudo_lock_region       *plr;
        struct resctrl_staged_config    staged_config[CDP_NUM_TYPES];
        u32                             *mbps_val;
};

I feel this will be easy to understand and makes the code simpler. Changes will be minimal.

Thanks
Babu

Quoted 547 lines
include/linux/resctrl.h +5 -3
+
+/**
+ * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * @hdr:		common header for different domain types
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
  * @mbm_local:		saved state for MBM local bandwidth
@@ -71,9 +81,7 @@ struct resctrl_staged_config {
  *			by closid
  */
 struct rdt_domain {
-	struct list_head		list;
-	int				id;
-	struct cpumask			cpu_mask;
+	struct rdt_domain_hdr		hdr;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;
arch/x86/kernel/cpu/resctrl/core.c +13 -13
index 9f8d87abd751..c0659e84c9e3 100644
@@ -356,9 +356,9 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
 {
 	struct rdt_domain *d;
 
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->cpu_mask))
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
 			return d;
 	}
 
@@ -402,12 +402,12 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	struct list_head *l;
 
 	list_for_each(l, &r->domains) {
-		d = list_entry(l, struct rdt_domain, list);
+		d = list_entry(l, struct rdt_domain, hdr.list);
 		/* When id is found, return its domain. */
-		if (id == d->id)
+		if (id == d->hdr.id)
 			return d;
 		/* Stop searching when finding id's position in sorted list. */
-		if (id < d->id)
+		if (id < d->hdr.id)
 			break;
 	}
 
@@ -530,7 +530,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 	d = rdt_find_domain(r, id, &add_pos);
 	if (d) {
-		cpumask_set_cpu(cpu, &d->cpu_mask);
+		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 		if (r->cache.arch_has_per_cpu_cfg)
 			rdt_domain_reconfigure_cdp(r);
 		return;
@@ -541,8 +541,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 
 	d = &hw_dom->d_resctrl;
-	d->id = id;
-	cpumask_set_cpu(cpu, &d->cpu_mask);
+	d->hdr.id = id;
+	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	rdt_domain_reconfigure_cdp(r);
 
@@ -556,11 +556,11 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	list_add_tail(&d->list, add_pos);
+	list_add_tail(&d->hdr.list, add_pos);
 
 	err = resctrl_online_domain(r, d);
 	if (err) {
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 		domain_free(hw_dom);
 	}
 }
@@ -581,10 +581,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 	}
 	hw_dom = resctrl_to_arch_dom(d);
 
-	cpumask_clear_cpu(cpu, &d->cpu_mask);
-	if (cpumask_empty(&d->cpu_mask)) {
+	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
+	if (cpumask_empty(&d->hdr.cpu_mask)) {
 		resctrl_offline_domain(r, d);
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 
 		/*
 		 * rdt_domain "d" is going to be freed below, so clear
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +11 -11
index 3f8891d57fac..23f8258d36a8 100644
@@ -67,7 +67,7 @@ int parse_bw(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;
 	}
 
@@ -146,7 +146,7 @@ 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;
 	}
 
@@ -226,8 +226,8 @@ static int parse_line(char *line, struct resctrl_schema *s,
 		return -EINVAL;
 	}
 	dom = strim(dom);
-	list_for_each_entry(d, &r->domains, list) {
-		if (d->id == dom_id) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
 			data.buf = dom;
 			data.rdtgrp = rdtgrp;
 			if (r->parse_ctrlval(&data, s, d))
@@ -274,7 +274,7 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
 	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);
+		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
 		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
 
 		return true;
@@ -291,7 +291,7 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 		return -ENOMEM;
 
 	msr_param.res = NULL;
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		hw_dom = resctrl_to_arch_dom(d);
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	u32 ctrl_val;
 
 	seq_printf(s, "%*s:", max_name_width, schema->name);
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
 		if (sep)
 			seq_puts(s, ";");
 
@@ -476,7 +476,7 @@ 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 +505,7 @@ 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 {
@@ -536,7 +536,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	rr->val = 0;
 	rr->first = first;
 
-	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	smp_call_function_any(&d->hdr.cpu_mask, mon_event_count, rr, 1);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
arch/x86/kernel/cpu/resctrl/monitor.c +5 -5
index f136ac046851..dd0ea1bc0092 100644
@@ -238,7 +238,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	u64 msr_val, chunks;
 	int ret;
 
-	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+	if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask))
 		return -EINVAL;
 
 	ret = __rmid_read(rmid, eventid, &msr_val);
@@ -340,8 +340,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
 	entry->busy = 0;
 	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, list) {
-		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
 			err = resctrl_arch_rmid_read(r, d, entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
 						     &val);
@@ -661,7 +661,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
 	dom->cqm_work_cpu = cpu;
 
 	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
@@ -708,7 +708,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
 
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		return;
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
 	dom->mbm_work_cpu = cpu;
 	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
 }
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +7 -7
index 2a682da9f43a..fcbd99e2eb66 100644
@@ -221,7 +221,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
 	int cpu;
 	int ret;
 
-	for_each_cpu(cpu, &plr->d->cpu_mask) {
+	for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
 		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
 		if (!pm_req) {
 			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
@@ -301,7 +301,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 		return -ENODEV;
 
 	/* Pick the first cpu we find that is associated with the cache. */
-	plr->cpu = cpumask_first(&plr->d->cpu_mask);
+	plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 
 	if (!cpu_online(plr->cpu)) {
 		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
@@ -856,10 +856,10 @@ 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, list) {
+		list_for_each_entry(d_i, &r->domains, hdr.list) {
 			if (d_i->plr)
 				cpumask_or(cpu_with_psl, cpu_with_psl,
-					   &d_i->cpu_mask);
+					   &d_i->hdr.cpu_mask);
 		}
 	}
 
@@ -867,7 +867,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	 * Next test if new pseudo-locked region would intersect with
 	 * existing region.
 	 */
-	if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+	if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
 		ret = true;
 
 	free_cpumask_var(cpu_with_psl);
@@ -1199,7 +1199,7 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 	}
 
 	plr->thread_done = 0;
-	cpu = cpumask_first(&plr->d->cpu_mask);
+	cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 	if (!cpu_online(cpu)) {
 		ret = -ENODEV;
 		goto out;
@@ -1529,7 +1529,7 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
 	 * may be scheduled elsewhere and invalidate entries in the
 	 * pseudo-locked region.
 	 */
-	if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) {
+	if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
 		mutex_unlock(&rdtgroup_mutex);
 		return -EINVAL;
 	}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +30 -30
index c44be64d65ec..04d32602ac33 100644
@@ -91,7 +91,7 @@ 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, list)
+		list_for_each_entry(dom, &r->domains, hdr.list)
 			memset(dom->staged_config, 0, sizeof(dom->staged_config));
 	}
 }
@@ -295,7 +295,7 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 				rdt_last_cmd_puts("Cache domain offline\n");
 				ret = -ENODEV;
 			} else {
-				mask = &rdtgrp->plr->d->cpu_mask;
+				mask = &rdtgrp->plr->d->hdr.cpu_mask;
 				seq_printf(s, is_cpu_list(of) ?
 					   "%*pbl\n" : "%*pb\n",
 					   cpumask_pr_args(mask));
@@ -984,12 +984,12 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 
 	mutex_lock(&rdtgroup_mutex);
 	hw_shareable = r->cache.shareable_bits;
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
 		if (sep)
 			seq_putc(seq, ';');
 		sw_shareable = 0;
 		exclusive = 0;
-		seq_printf(seq, "%d=", dom->id);
+		seq_printf(seq, "%d=", dom->hdr.id);
 		for (i = 0; i < closids_supported(); i++) {
 			if (!closid_allocated(i))
 				continue;
@@ -1302,7 +1302,7 @@ 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, list) {
+		list_for_each_entry(d, &r->domains, hdr.list) {
 			ctrl = resctrl_arch_get_config(r, d, closid,
 						       s->conf_type);
 			if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
@@ -1417,7 +1417,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 		return size;
 
 	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
-	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
+	ci = get_cpu_cacheinfo(cpumask_any(&d->hdr.cpu_mask));
 	for (i = 0; i < ci->num_leaves; i++) {
 		if (ci->info_list[i].level == r->scope) {
 			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
@@ -1465,7 +1465,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 			size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res,
 						    rdtgrp->plr->d,
 						    rdtgrp->plr->cbm);
-			seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+			seq_printf(s, "%d=%u\n", rdtgrp->plr->d->hdr.id, size);
 		}
 		goto out;
 	}
@@ -1477,7 +1477,7 @@ 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, list) {
+		list_for_each_entry(d, &r->domains, hdr.list) {
 			if (sep)
 				seq_putc(s, ';');
 			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
@@ -1495,7 +1495,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 				else
 					size = rdtgroup_cbm_to_size(r, d, ctrl);
 			}
-			seq_printf(s, "%d=%u", d->id, size);
+			seq_printf(s, "%d=%u", d->hdr.id, size);
 			sep = true;
 		}
 		seq_putc(s, '\n');
@@ -1555,7 +1555,7 @@ static void mon_event_config_read(void *info)
 
 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);
+	smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_read, mon_info, 1);
 }
 
 static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
@@ -1566,7 +1566,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 
 	mutex_lock(&rdtgroup_mutex);
 
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
 		if (sep)
 			seq_puts(s, ";");
 
@@ -1574,7 +1574,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 		mon_info.evtid = evtid;
 		mondata_config_read(dom, &mon_info);
 
-		seq_printf(s, "%d=0x%02x", dom->id, mon_info.mon_config);
+		seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config);
 		sep = true;
 	}
 	seq_puts(s, "\n");
@@ -1646,7 +1646,7 @@ static int mbm_config_write_domain(struct rdt_resource *r,
 	 * 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,
+	smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_write,
 			      &mon_info, 1);
 
 	/*
@@ -1689,8 +1689,8 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
 		return -EINVAL;
 	}
 
-	list_for_each_entry(d, &r->domains, list) {
-		if (d->id == dom_id) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
 			ret = mbm_config_write_domain(r, d, evtid, val);
 			if (ret)
 				return -EINVAL;
@@ -2232,14 +2232,14 @@ 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, list) {
+	list_for_each_entry(d, &r_l->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->cpu_mask)
+			for_each_cpu(cpu, &d->hdr.cpu_mask)
 				cpumask_set_cpu(cpu, cpu_mask);
 		else
 			/* Pick one CPU from each domain instance to update MSR */
-			cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+			cpumask_set_cpu(cpumask_any(&d->hdr.cpu_mask), cpu_mask);
 	}
 
 	/* Update QOS_CFG MSR on all the CPUs in cpu_mask */
@@ -2268,7 +2268,7 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
 static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d)
 {
 	u32 num_closid = resctrl_arch_get_num_closid(r);
-	int cpu = cpumask_any(&d->cpu_mask);
+	int cpu = cpumask_any(&d->hdr.cpu_mask);
 	int i;
 
 	d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
@@ -2317,7 +2317,7 @@ static int set_mba_sc(bool mba_sc)
 
 	r->membw.mba_sc = mba_sc;
 
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		for (i = 0; i < num_closid; i++)
 			d->mbps_val[i] = MBA_MAX_MBPS;
 	}
@@ -2653,7 +2653,7 @@ 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, list)
+		list_for_each_entry(dom, &r->domains, hdr.list)
 			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
 	}
 
@@ -2780,9 +2780,9 @@ static int reset_all_ctrls(struct rdt_resource *r)
 	 * CBMs in all domains to the maximum mask value. Pick one CPU
 	 * from each domain to update the MSRs below.
 	 */
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		hw_dom = resctrl_to_arch_dom(d);
-		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+		cpumask_set_cpu(cpumask_any(&d->hdr.cpu_mask), cpu_mask);
 
 		for (i = 0; i < hw_res->num_closid; i++)
 			hw_dom->ctrl_val[i] = r->default_ctrl;
@@ -2986,7 +2986,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 	char name[32];
 	int ret;
 
-	sprintf(name, "mon_%s_%02d", r->name, d->id);
+	sprintf(name, "mon_%s_%02d", r->name, d->hdr.id);
 	/* create the directory */
 	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
 	if (IS_ERR(kn))
@@ -3002,7 +3002,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 	}
 
 	priv.u.rid = r->rid;
-	priv.u.domid = d->id;
+	priv.u.domid = d->hdr.id;
 	list_for_each_entry(mevt, &r->evt_list, list) {
 		priv.u.evtid = mevt->evtid;
 		ret = mon_addfile(kn, mevt->name, priv.priv);
@@ -3050,7 +3050,7 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
 	struct rdt_domain *dom;
 	int ret;
 
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
 		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
 		if (ret)
 			return ret;
@@ -3209,7 +3209,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s,
 	 */
 	tmp_cbm = cfg->new_ctrl;
 	if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
-		rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->id);
+		rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->hdr.id);
 		return -ENOSPC;
 	}
 	cfg->have_new_ctrl = true;
@@ -3232,7 +3232,7 @@ 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, list) {
+	list_for_each_entry(d, &s->res->domains, hdr.list) {
 		ret = __init_one_rdt_domain(d, s, closid);
 		if (ret < 0)
 			return ret;
@@ -3247,7 +3247,7 @@ 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, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		if (is_mba_sc(r)) {
 			d->mbps_val[closid] = MBA_MAX_MBPS;
 			continue;
@@ -3864,7 +3864,7 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
 	 * per domain monitor data directories.
 	 */
 	if (static_branch_unlikely(&rdt_mon_enable_key))
-		rmdir_mondata_subdir_allrdtgrp(r, d->id);
+		rmdir_mondata_subdir_allrdtgrp(r, d->hdr.id);
 
 	if (is_mbm_enabled())
 		cancel_delayed_work(&d->mbm_over);
Signature · 2 lines
Thanks
Babu Moger
author maintainer
#220 lore raw

Re: [PATCH v11 2/8] x86/resctrl: Prepare to split rdt_domain structure

Quoted 79 lines · Babu

Hi Tony,

Sorry for the late review. The patches look good for the most part. But we can simplify a little more. Please see my comments below.

Quoted 28 lines · Tony Luck

The rdt_domain structure is used for both control and monitor features. It is about to be split into separate structures for these two usages because the scope for control and monitoring features for a resource will be different for future resources.

To allow for common code that scans a list of domains looking for a specific domain id, move all the common fields ("list", "id", "cpu_mask") into their own structure within the rdt_domain structure.

---
 include/linux/resctrl.h                   | 16 ++++--
 arch/x86/kernel/cpu/resctrl/core.c        | 26 +++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 22 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 10 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 14 +++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 60 +++++++++++------------
 6 files changed, 78 insertions(+), 70 deletions(-)
include/linux/resctrl.h +0 -1
index 7d4eb7df611d..c4067150a6b7 100644
@@ -53,10 +53,20 @@ struct resctrl_staged_config {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource

include/linux/resctrl.h struct resctrl_staged_config { · line 65

Quoted 10 lines
include/linux/resctrl.h +7 -0
+ * struct rdt_domain_hdr - common header for different domain types
  * @list:		all instances of this resource
  * @id:			unique id for this instance
  * @cpu_mask:		which CPUs share this resource
+ */
+struct rdt_domain_hdr {
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+};

I like the idea of separating the domains, one for control and another for monitor. I have some comments on how it can be done to simplify the code. Adding the hdr adds a little complexity to the code.

How about converting the current rdt_domain to explicitly to rdt_mon_domain?

Something like this.

struct rdt_mon_domain {
        struct list_head                list;
        int                             id;
        struct cpumask                  cpu_mask;
        unsigned long                   *rmid_busy_llc;
        struct mbm_state                *mbm_total;
        struct mbm_state                *mbm_local;
        struct delayed_work             mbm_over;
        struct delayed_work             cqm_limbo;
        int                             mbm_work_cpu;
        int                             cqm_work_cpu;
};

Then introduce rdt_ctrl_domain to which separates into two doamins.

struct rdt_ctrl_domain {
        struct list_head                list;
        int                             id;
        struct cpumask                  cpu_mask;
        struct pseudo_lock_region       *plr;
        struct resctrl_staged_config    staged_config[CDP_NUM_TYPES];
        u32                             *mbps_val;
};
Quoted 2 lines

I feel this will be easy to understand and makes the code simpler. Changes will be minimal.

Babu,

I went in this direction because of rdt_find_domain() which is used to search either of the "ctrl" or "mon" lists. So it needs to be sure that the "list" and "id" fields are at identical offsets in both the rdt_ctrl_domain and rdt_mon_domain structures. Best way to guarantee[1] that is to create the "hdr" entry (which later acquired the cpu_mask field as a common element after a comment from Reinette).

One way to avoid this would be to essentially duplicate rdt_find_domain() into rdt_find_ctrl_domain() and rdt_find_mon_domain() ... but I fear the function is just big enough to get complaints that the two copies should somehow be merged.

-Tony

[1] In v5 I tried using a comment in each to say they must be the same, but Reinette didn't like comments within declarations:
https://lore.kernel.org/all/[email protected]/

reviewer
#221 lore raw

Re: [PATCH v11 2/8] x86/resctrl: Prepare to split rdt_domain structure

Quoted 92 lines · Tony Luck
Quoted 79 lines · Babu

Hi Tony,

Sorry for the late review. The patches look good for the most part. But we can simplify a little more. Please see my comments below.

Quoted 28 lines · Tony Luck

The rdt_domain structure is used for both control and monitor features. It is about to be split into separate structures for these two usages because the scope for control and monitoring features for a resource will be different for future resources.

To allow for common code that scans a list of domains looking for a specific domain id, move all the common fields ("list", "id", "cpu_mask") into their own structure within the rdt_domain structure.

---
 include/linux/resctrl.h                   | 16 ++++--
 arch/x86/kernel/cpu/resctrl/core.c        | 26 +++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 22 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 10 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 14 +++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 60 +++++++++++------------
 6 files changed, 78 insertions(+), 70 deletions(-)
include/linux/resctrl.h +0 -1
index 7d4eb7df611d..c4067150a6b7 100644
@@ -53,10 +53,20 @@ struct resctrl_staged_config {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource

include/linux/resctrl.h struct resctrl_staged_config { · line 65

Quoted 10 lines
include/linux/resctrl.h +7 -0
+ * struct rdt_domain_hdr - common header for different domain types
  * @list:		all instances of this resource
  * @id:			unique id for this instance
  * @cpu_mask:		which CPUs share this resource
+ */
+struct rdt_domain_hdr {
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+};

I like the idea of separating the domains, one for control and another for monitor. I have some comments on how it can be done to simplify the code. Adding the hdr adds a little complexity to the code.

How about converting the current rdt_domain to explicitly to rdt_mon_domain?

Something like this.

struct rdt_mon_domain {
        struct list_head                list;
        int                             id;
        struct cpumask                  cpu_mask;
        unsigned long                   *rmid_busy_llc;
        struct mbm_state                *mbm_total;
        struct mbm_state                *mbm_local;
        struct delayed_work             mbm_over;
        struct delayed_work             cqm_limbo;
        int                             mbm_work_cpu;
        int                             cqm_work_cpu;
};

Then introduce rdt_ctrl_domain to which separates into two doamins.

struct rdt_ctrl_domain {
        struct list_head                list;
        int                             id;
        struct cpumask                  cpu_mask;
        struct pseudo_lock_region       *plr;
        struct resctrl_staged_config    staged_config[CDP_NUM_TYPES];
        u32                             *mbps_val;
};
Quoted 2 lines

I feel this will be easy to understand and makes the code simpler. Changes will be minimal.

Babu,

I went in this direction because of rdt_find_domain() which is used to search either of the "ctrl" or "mon" lists. So it needs to be sure that the "list" and "id" fields are at identical offsets in both the rdt_ctrl_domain and rdt_mon_domain structures. Best way to guarantee[1] that is to create the "hdr" entry (which later acquired the cpu_mask field as a common element after a comment from Reinette).

Quoted 2 lines

One way to avoid this would be to essentially duplicate rdt_find_domain() into rdt_find_ctrl_domain() and rdt_find_mon_domain()

It could been solved by passing a flag(0 or mon and 1 for ctrl) as we know where this is being called.

Quoted 2 lines

... but I fear the function is just big enough to get complaints that the two copies should somehow be merged.

Ok. That is fine. Lets go with current implementation. Thanks for showing the discussion.

Quoted 6 lines

-Tony

[1] In v5 I tried using a comment in each to say they must be the same, but Reinette didn't like comments within declarations:
https://lore.kernel.org/all/[email protected]/

Signature · 2 lines
Thanks
Babu Moger
maintainer Reviewed-by on v11 2/8
#222 lore raw

Re: [PATCH v11 2/8] x86/resctrl: Prepare to split rdt_domain structure

In reply to Tony Luck

Hi Tony,

Quoted 11 lines · Tony Luck

The rdt_domain structure is used for both control and monitor features. It is about to be split into separate structures for these two usages because the scope for control and monitoring features for a resource will be different for future resources.

To allow for common code that scans a list of domains looking for a specific domain id, move all the common fields ("list", "id", "cpu_mask") into their own structure within the rdt_domain structure.

---

Reinette

author maintainer
#223 lore raw

PATCH v11 3/8 x86/resctrl: Prepare for different scope for control/monitor operations

In reply to Tony Luck

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.

---
Changes since v10:
Reinette: Took your rewritten comment for rdt_find_domain()
Reinette: Fixed error handling in domain_add_cpu_mon(),

	  domain_remove_cpu_{ctrl,mon}()

Tony: s/domain_add_cpu - Add a cpu/domain_add_cpu - Add a CPU/

 include/linux/resctrl.h                   |  25 ++-
 arch/x86/kernel/cpu/resctrl/internal.h    |   6 +-
 arch/x86/kernel/cpu/resctrl/core.c        | 202 ++++++++++++++++------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  12 +-
 arch/x86/kernel/cpu/resctrl/monitor.c     |   4 +-
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |   4 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  55 +++---
 7 files changed, 213 insertions(+), 95 deletions(-)
include/linux/resctrl.h +19 -6
index c4067150a6b7..35e700edc6e6 100644
@@ -52,15 +52,22 @@ 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;
 };
 
@@ -163,10 +170,12 @@ 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:		All domains for this resource
+ * @ctrl_domains:	Control domains for this resource
+ * @mon_domains:	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.
@@ -181,10 +190,12 @@ 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;
@@ -230,8 +241,10 @@ 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);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
arch/x86/kernel/cpu/resctrl/internal.h +3 -3
index a4f1aa15f0a2..24bf9d7989a9 100644
@@ -520,8 +520,8 @@ 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,
@@ -540,7 +540,7 @@ 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);
 int closids_supported(void);
 void closid_free(int closid);
 int alloc_rmid(void);
arch/x86/kernel/cpu/resctrl/core.c +150 -52

328 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +7 -5
index 23f8258d36a8..0b4136c42762 100644
@@ -226,7 +226,7 @@ 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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 		return -ENOMEM;
 
 	msr_param.res = NULL;
-	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 (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	u32 ctrl_val;
 
 	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, ";");
 
@@ -542,6 +542,7 @@ 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;
@@ -562,11 +563,12 @@ 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/monitor.c +2 -2
index dd0ea1bc0092..ec5ad926c5dc 100644
@@ -340,7 +340,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
 	entry->busy = 0;
 	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
 		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
 			err = resctrl_arch_rmid_read(r, d, entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
@@ -535,7 +535,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	rmid = rgrp->mon.rmid;
 	pmbm_data = &dom_mbm->mbm_local[rmid];
 
-	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 +2 -2
index fcbd99e2eb66..ed6d59af1cef 100644
@@ -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 cpu_cacheinfo *ci;
 	int ret;
 	int i;
@@ -856,7 +856,7 @@ 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 +30 -25

170 lines not on this page · raw message

Signature · 1 line
2.41.0
maintainer
#224 lore raw

Re: [PATCH v11 3/8] x86/resctrl: Prepare for different scope for control/monitor operations

Hi Tony,

On 11/9/2023 3:09 PM, Tony Luck wrote:

...

Quoted 6 lines
arch/x86/kernel/cpu/resctrl/core.c +4 -0
+static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
+{
+	int id = get_domain_id_from_scope(cpu, r->ctrl_scope);
 	struct rdt_hw_domain *hw_dom;
+	struct rdt_domain_hdr *hdr;
 	struct rdt_domain *d;

arch/x86/kernel/cpu/resctrl/core.c static void domain_add_cpu(int cpu, struct rdt_resource *r) · line 632

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +3 -3
 
 	if (id < 0)
 		return;
 
-	d = rdt_find_domain(r, id, NULL);
-	if (!d) {
-		pr_warn("Couldn't find domain with id=%d for CPU %d\n", id, cpu);
+	hdr = rdt_find_domain(&r->ctrl_domains, id, NULL);
+	if (!hdr) {
+		pr_warn("Couldn't find control scope id=%d for CPU %d\n", id, cpu);

This error message seems strange to me. Shouldn't this just be "Couldn't find control domain with id=..."? Also, can the resource name be added in error message to help user dig into cause of error?

Quoted 27 lines
arch/x86/kernel/cpu/resctrl/core.c +13 -1
 		return;
 	}
+
+	if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
+		return;
+
+	d = container_of(hdr, struct rdt_domain, hdr);
 	hw_dom = resctrl_to_arch_dom(d);
 
 	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
 	if (cpumask_empty(&d->hdr.cpu_mask)) {
-		resctrl_offline_domain(r, d);
+		resctrl_offline_ctrl_domain(r, d);
 		list_del(&d->hdr.list);
 
 		/*
@@ -596,6 +654,38 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 
 		return;
 	}
+}
+
+static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
+{
+	int id = get_domain_id_from_scope(cpu, r->mon_scope);
+	struct rdt_hw_domain *hw_dom;
+	struct rdt_domain_hdr *hdr;

arch/x86/kernel/cpu/resctrl/core.c static void domain_remove_cpu(int cpu, struct rdt_resource *r) · line 673

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +10 -0
+	struct rdt_domain *d;
+
+	if (id < 0)
+		return;
+
+	hdr = rdt_find_domain(&r->mon_domains, id, NULL);
+	if (!hdr) {
+		pr_warn("Couldn't find monitor scope id=%d for CPU %d\n", id, cpu);
+		return;
+	}

Similar to above, can this be "Couldn't find monitor domain with id..."? Can resource name be added here also?

The rest of the patch looks good to me.

Reinette

author maintainer
#225 lore raw

PATCH v11 4/8 x86/resctrl: Split the rdt_domain and rdt_hw_domain structures

In reply to Tony Luck

The same rdt_domain structure is used for both control and monitor functions. But this results in wasted memory as some of the fields are only used by control functions, while most are only used for monitor functions.

Split into separate rdt_ctrl_domain and rdt_mon_domain structures with just the fields required for control and monitoring respectively.

Similar split of the rdt_hw_domain structure into rdt_hw_ctrl_domain and rdt_hw_mon_domain.

---
Changes since v10:
Reinette: Remove struct cpumask cpu_mask; that had snuck bac into the
defintion of "struct rdt_domain"

 include/linux/resctrl.h                   | 48 +++++++------
 arch/x86/kernel/cpu/resctrl/internal.h    | 60 ++++++++++------
 arch/x86/kernel/cpu/resctrl/core.c        | 87 ++++++++++++-----------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 32 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 40 +++++------
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  6 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 62 ++++++++--------
 7 files changed, 182 insertions(+), 153 deletions(-)
include/linux/resctrl.h +28 -20
index 35e700edc6e6..058a940c3239 100644
@@ -72,7 +72,23 @@ struct rdt_domain_hdr {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource
+ * @hdr:		common header for different domain types
+ * @plr:		pseudo-locked region (if any) associated with domain
+ * @staged_config:	parsed configuration to be applied
+ * @mbps_val:		When mba_sc is enabled, this holds the array of user
+ *			specified control values for mba_sc in MBps, indexed
+ *			by closid
+ */
+struct rdt_ctrl_domain {
+	struct rdt_domain_hdr		hdr;
+	struct pseudo_lock_region	*plr;
+	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
+	u32				*mbps_val;
+};
+
+/**
+ * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
  * @hdr:		common header for different domain types
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
@@ -81,13 +97,8 @@ struct rdt_domain_hdr {
  * @cqm_limbo:		worker to periodically read CQM h/w counters
  * @mbm_work_cpu:	worker CPU for MBM h/w counters
  * @cqm_work_cpu:	worker CPU for CQM h/w counters
- * @plr:		pseudo-locked region (if any) associated with domain
- * @staged_config:	parsed configuration to be applied
- * @mbps_val:		When mba_sc is enabled, this holds the array of user
- *			specified control values for mba_sc in MBps, indexed
- *			by closid
  */
-struct rdt_domain {
+struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
@@ -96,9 +107,6 @@ struct rdt_domain {
 	struct delayed_work		cqm_limbo;
 	int				mbm_work_cpu;
 	int				cqm_work_cpu;
-	struct pseudo_lock_region	*plr;
-	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
-	u32				*mbps_val;
 };
 
 /**
@@ -202,7 +210,7 @@ struct rdt_resource {
 	const char		*format_str;
 	int			(*parse_ctrlval)(struct rdt_parse_data *data,
 						 struct resctrl_schema *s,
-						 struct rdt_domain *d);
+						 struct rdt_ctrl_domain *d);
 	struct list_head	evt_list;
 	unsigned long		fflags;
 	bool			cdp_capable;
@@ -236,15 +244,15 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
  * Update the ctrl_val and apply this config right now.
  * Must be called on one of the domain's CPUs.
  */
-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);
 
-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);
-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);
+int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
+void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
@@ -260,7 +268,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain *d);
  * Return:
  * 0 on success, or -EIO, -EINVAL etc on error.
  */
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 rmid, enum resctrl_event_id eventid, u64 *val);
 
 /**
@@ -273,7 +281,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 			     u32 rmid, enum resctrl_event_id eventid);
 
 /**
@@ -285,7 +293,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d);
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d);
 
 extern unsigned int resctrl_rmid_realloc_threshold;
 extern unsigned int resctrl_rmid_realloc_limit;
arch/x86/kernel/cpu/resctrl/internal.h +38 -22

131 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/core.c +46 -41

246 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +16 -16
index 0b4136c42762..08fc97ce4135 100644
@@ -58,7 +58,7 @@ 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;
@@ -137,7 +137,7 @@ 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;
@@ -206,8 +206,8 @@ 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;
 
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
@@ -267,11 +267,11 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
 	}
 }
 
-static bool apply_config(struct rdt_hw_domain *hw_dom,
+static bool apply_config(struct rdt_hw_ctrl_domain *hw_dom,
 			 struct resctrl_staged_config *cfg, u32 idx,
 			 cpumask_var_t cpu_mask)
 {
-	struct rdt_domain *dom = &hw_dom->d_resctrl;
+	struct rdt_ctrl_domain *dom = &hw_dom->d_resctrl;
 
 	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
 		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
@@ -283,11 +283,11 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
 	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;
 
@@ -307,11 +307,11 @@ 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))
@@ -319,7 +319,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 
 	msr_param.res = NULL;
 	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		hw_dom = resctrl_to_arch_dom(d);
+		hw_dom = resctrl_to_arch_ctrl_dom(d);
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
 			if (!cfg->have_new_ctrl)
@@ -449,10 +449,10 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	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];
@@ -461,7 +461,7 @@ 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;
 
@@ -523,7 +523,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 }
 
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
 		    int evtid, int first)
 {
 	/*
@@ -543,11 +543,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
 	struct rdt_domain_hdr *hdr;
+	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;
 
@@ -568,7 +568,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		ret = -ENOENT;
 		goto out;
 	}
-	d = container_of(hdr, struct rdt_domain, hdr);
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
 
 	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
arch/x86/kernel/cpu/resctrl/monitor.c +20 -20
index ec5ad926c5dc..4e145f5620b0 100644
@@ -170,7 +170,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 	return 0;
 }
 
-static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
+static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_dom,
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
 {
@@ -189,10 +189,10 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 	return NULL;
 }
 
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 			     u32 rmid, enum resctrl_event_id eventid)
 {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct arch_mbm_state *am;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
@@ -208,9 +208,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
  * Assumes that hardware counters are also reset and thus that there is
  * no need to record initial non-zero counts.
  */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d)
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 
 	if (is_mbm_total_enabled())
 		memset(hw_dom->arch_mbm_total, 0,
@@ -229,11 +229,11 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 	return chunks >> shift;
 }
 
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 rmid, enum resctrl_event_id eventid, u64 *val)
 {
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
 	u64 msr_val, chunks;
 	int ret;
@@ -266,7 +266,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  * decrement the count. If the busy count gets to zero on an RMID, we
  * free the RMID
  */
-void __check_limbo(struct rdt_domain *d, bool force_free)
+void __check_limbo(struct rdt_mon_domain *d, bool force_free)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	struct rmid_entry *entry;
@@ -305,7 +305,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 	}
 }
 
-bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d)
+bool has_busy_rmid(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid;
 }
@@ -334,7 +334,7 @@ int alloc_rmid(void)
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_domain *d;
+	struct rdt_mon_domain *d;
 	int cpu, err;
 	u64 val = 0;
 
@@ -383,7 +383,7 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid,
+static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 rmid,
 				       enum resctrl_event_id evtid)
 {
 	switch (evtid) {
@@ -516,13 +516,13 @@ void mon_event_count(void *info)
  * throttle MSRs already have low percentage values.  To avoid
  * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
  */
-static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
+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;
 	u32 cur_bw, delta_bw, user_bw;
 	struct rdt_resource *r_mba;
-	struct rdt_domain *dom_mba;
 	struct list_head *head;
 	struct rdtgroup *entry;
 
@@ -600,7 +600,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	}
 }
 
-static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, int rmid)
 {
 	struct rmid_read rr;
 
@@ -640,13 +640,13 @@ void cqm_handle_limbo(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
 	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
 	struct rdt_resource *r;
-	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, cqm_limbo.work);
+	d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
 
@@ -656,7 +656,7 @@ void cqm_handle_limbo(struct work_struct *work)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
@@ -672,9 +672,9 @@ void mbm_handle_overflow(struct work_struct *work)
 	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
 	struct rdtgroup *prgrp, *crgrp;
 	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
 	struct list_head *head;
 	struct rdt_resource *r;
-	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
 
@@ -682,7 +682,7 @@ void mbm_handle_overflow(struct work_struct *work)
 		goto out_unlock;
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, mbm_over.work);
+	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		mbm_update(r, d, prgrp->mon.rmid);
@@ -701,7 +701,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +3 -3
index ed6d59af1cef..08d35f828bc3 100644
@@ -814,7 +814,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
  * Return: true if @cbm overlaps with pseudo-locked region on @d, false
  * otherwise.
  */
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm)
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
 {
 	unsigned int cbm_len;
 	unsigned long cbm_b;
@@ -841,11 +841,11 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm
  *         if it is not possible to test due to memory allocation issue,
  *         false otherwise.
  */
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
 {
+	struct rdt_ctrl_domain *d_i;
 	cpumask_var_t cpu_with_psl;
 	struct rdt_resource *r;
-	struct rdt_domain *d_i;
 	bool ret = false;
 
 	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
arch/x86/kernel/cpu/resctrl/rdtgroup.c +31 -31

252 lines not on this page · raw message

Signature · 1 line
2.41.0
maintainer Reviewed-by on v11 4/8
#226 lore raw

Re: [PATCH v11 4/8] x86/resctrl: Split the rdt_domain and rdt_hw_domain structures

Hi Tony,

Quoted 8 lines · Tony Luck

The same rdt_domain structure is used for both control and monitor functions. But this results in wasted memory as some of the fields are only used by control functions, while most are only used for monitor functions.

Split into separate rdt_ctrl_domain and rdt_mon_domain structures with just the fields required for control and monitoring respectively.

Quoted 6 lines

Similar split of the rdt_hw_domain structure into rdt_hw_ctrl_domain and rdt_hw_mon_domain.

---

Reinette

author maintainer
#227 lore raw

PATCH v11 5/8 x86/resctrl: Add node-scope to the options for feature scope

In reply to Tony Luck

Currently supported resctrl features are all domain scoped the same as the scope of the L2 or L3 caches.

Add RESCTRL_NODE as a new option for features that are scoped at the same granularity as NUMA nodes. This is needed for Intel's Sub-NUMA Cluster (SNC) feature where monitoring features are node scoped.

---
 include/linux/resctrl.h            | 1 +
 arch/x86/kernel/cpu/resctrl/core.c | 2 ++
 2 files changed, 3 insertions(+)
include/linux/resctrl.h +1 -0
index 058a940c3239..b8a3a11b970d 100644
@@ -170,6 +170,7 @@ struct resctrl_schema;
 enum resctrl_scope {
 	RESCTRL_L2_CACHE = 2,
 	RESCTRL_L3_CACHE = 3,
+	RESCTRL_NODE,
 };
 
 /**
arch/x86/kernel/cpu/resctrl/core.c +2 -0
index cee8b87566fa..0f2b5ee429b0 100644
@@ -502,6 +502,8 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
 	case RESCTRL_L2_CACHE:
 	case RESCTRL_L3_CACHE:
 		return get_cpu_cacheinfo_id(cpu, scope);
+	case RESCTRL_NODE:
+		return cpu_to_node(cpu);
 	default:
 		break;
 	}
Signature · 1 line
2.41.0
maintainer Reviewed-by on v11 5/8
#228 lore raw

Re: [PATCH v11 5/8] x86/resctrl: Add node-scope to the options for feature scope

Hi Tony,

Quoted 10 lines · Tony Luck

Currently supported resctrl features are all domain scoped the same as the scope of the L2 or L3 caches.

Add RESCTRL_NODE as a new option for features that are scoped at the same granularity as NUMA nodes. This is needed for Intel's Sub-NUMA Cluster (SNC) feature where monitoring features are node scoped.

---

Please follow guidance in section "Ordering of commit tags" from Documentation/process/maintainer-tip.rst

With that addressed (thus adding Reviewed-by tags after your author SOB):

Reinette

author maintainer
#229 lore raw

PATCH v11 6/8 x86/resctrl: Introduce snc_nodes_per_l3_cache

In reply to Tony Luck

Intel Sub-NUMA Cluster (SNC) is a feature that subdivides the CPU cores and memory controllers on a socket into two or more groups. These are presented to the operating system as NUMA nodes.

This may enable some workloads to have slightly lower latency to memory as the memory controller(s) in an SNC node are electrically closer to the CPU cores on that SNC node. This cost may be offset by lower bandwidth since the memory accesses for each core can only be interleaved between the memory controllers on the same SNC node.

Resctrl monitoring on an Intel system depends upon attaching RMIDs to tasks to track L3 cache occupancy and memory bandwidth. There is an MSR that controls how the RMIDs are shared between SNC nodes.

The default mode divides them numerically. E.g. when there are two SNC nodes on a socket the lower number half of the RMIDs are given to the first node, the remainder to the second node. This would be difficult to use with the Linux resctrl interface as specific RMID values assigned to resctrl groups are not visible to users.

The other mode divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

Even with this renumbering SNC mode requires several changes in resctrl behavior for correct operation.

Add a global integer "snc_nodes_per_l3_cache" that will show how many SNC nodes share each L3 cache. When this is "1", SNC mode is either not implemented, or not enabled, but all places that need to check it are updated to take appropriate action when SNC mode is enabled.

Code that needs to take action when SNC is enabled is:
1) The number of logical RMIDs per L3 cache available for use is the number of physical RMIDs divided by the number of SNC nodes.
2) Likewise the "mon_scale" value must be divided by the number of SNC nodes.
3) The RMID renumbering operates when using the value from the IA32_PQR_ASSOC MSR to count accesses by a task. When reading an RMID counter, code must adjust from the logical RMID used to the physical RMID value for the SNC node that it wishes to read and load the adjusted value into the IA32_QM_EVTSEL MSR.
4) The L3 cache is divided between the SNC nodes. So the value reported in the resctrl "size" file is divided by the number of SNC nodes because the effective amount of cache that can be allocated is reduced by that factor.
5) The "-o mba_MBps" mount option must be disabled in SNC mode because the monitoring is being done per SNC node, while the bandwidth allocation is still done at the L3 cache scope. Trying to use this feedback loop might result in contradictory changes to the throttling level coming from each of the SNC node bandwidth measurements.

---
 arch/x86/kernel/cpu/resctrl/internal.h |  2 ++
 arch/x86/kernel/cpu/resctrl/core.c     |  6 ++++++
 arch/x86/kernel/cpu/resctrl/monitor.c  | 16 +++++++++++++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  5 +++--
 4 files changed, 24 insertions(+), 5 deletions(-)
arch/x86/kernel/cpu/resctrl/internal.h +2 -0
index ce3a70657842..e7a75a439c16 100644
@@ -446,6 +446,8 @@ DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
 extern struct dentry *debugfs_resctrl;
 
+extern unsigned int snc_nodes_per_l3_cache;
+
 enum resctrl_res_level {
 	RDT_RESOURCE_L3,
 	RDT_RESOURCE_L2,
arch/x86/kernel/cpu/resctrl/core.c +6 -0
index 0f2b5ee429b0..f10b68b45342 100644
@@ -48,6 +48,12 @@ int max_name_width, max_data_width;
  */
 bool rdt_alloc_capable;
 
+/*
+ * Number of SNC nodes that share each L3 cache.  Default is 1 for
+ * systems that do not support SNC, or have SNC disabled.
+ */
+unsigned int snc_nodes_per_l3_cache = 1;
+
 static void
 mba_wrmsr_intel(struct rdt_ctrl_domain *d, struct msr_param *m,
 		struct rdt_resource *r);
arch/x86/kernel/cpu/resctrl/monitor.c +13 -3
index 4e145f5620b0..30b7c3b9b517 100644
@@ -148,8 +148,18 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
 
 static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 {
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	int cpu = smp_processor_id();
+	int rmid_offset = 0;
 	u64 msr_val;
 
+	/*
+	 * When SNC mode is on, need to compute the offset to read the
+	 * physical RMID counter for the node to which this CPU belongs.
+	 */
+	if (snc_nodes_per_l3_cache > 1)
+		rmid_offset = (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid;
+
 	/*
 	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
 	 * with a valid event code for supported resource type and the bits
@@ -158,7 +168,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
 	 * are error bits.
 	 */
-	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid + rmid_offset);
 	rdmsrl(MSR_IA32_QM_CTR, msr_val);
 
 	if (msr_val & RMID_VAL_ERROR)
@@ -783,8 +793,8 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	int ret;
 
 	resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
-	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
-	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_nodes_per_l3_cache;
+	r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache;
 	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
 
 	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
arch/x86/kernel/cpu/resctrl/rdtgroup.c +3 -2
index 21bbd832f3f2..79d57dade568 100644
@@ -1425,7 +1425,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 		}
 	}
 
-	return size;
+	return size / snc_nodes_per_l3_cache;
 }
 
 /*
@@ -2298,7 +2298,8 @@ static bool supports_mba_mbps(void)
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 
 	return (is_mbm_local_enabled() &&
-		r->alloc_capable && is_mba_linear());
+		r->alloc_capable && is_mba_linear() &&
+		snc_nodes_per_l3_cache == 1);
 }
 
 /*
Signature · 1 line
2.41.0
maintainer Reviewed-by on v11 6/8
#230 lore raw

Re: [PATCH v11 6/8] x86/resctrl: Introduce snc_nodes_per_l3_cache

Hi Tony,

Quoted 43 lines · Tony Luck

Intel Sub-NUMA Cluster (SNC) is a feature that subdivides the CPU cores and memory controllers on a socket into two or more groups. These are presented to the operating system as NUMA nodes.

This may enable some workloads to have slightly lower latency to memory as the memory controller(s) in an SNC node are electrically closer to the CPU cores on that SNC node. This cost may be offset by lower bandwidth since the memory accesses for each core can only be interleaved between the memory controllers on the same SNC node.

Resctrl monitoring on an Intel system depends upon attaching RMIDs to tasks to track L3 cache occupancy and memory bandwidth. There is an MSR that controls how the RMIDs are shared between SNC nodes.

The default mode divides them numerically. E.g. when there are two SNC nodes on a socket the lower number half of the RMIDs are given to the first node, the remainder to the second node. This would be difficult to use with the Linux resctrl interface as specific RMID values assigned to resctrl groups are not visible to users.

The other mode divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

Even with this renumbering SNC mode requires several changes in resctrl behavior for correct operation.

Add a global integer "snc_nodes_per_l3_cache" that will show how many SNC nodes share each L3 cache. When this is "1", SNC mode is either not implemented, or not enabled, but all places that need to check it are updated to take appropriate action when SNC mode is enabled.

Code that needs to take action when SNC is enabled is:
1) The number of logical RMIDs per L3 cache available for use is the number of physical RMIDs divided by the number of SNC nodes.
2) Likewise the "mon_scale" value must be divided by the number of SNC nodes.
3) The RMID renumbering operates when using the value from the IA32_PQR_ASSOC MSR to count accesses by a task. When reading an RMID counter, code must adjust from the logical RMID used to the physical RMID value for the SNC node that it wishes to read and load the adjusted value into the IA32_QM_EVTSEL MSR.
4) The L3 cache is divided between the SNC nodes. So the value reported in the resctrl "size" file is divided by the number of SNC

Quoted 9 lines

nodes because the effective amount of cache that can be allocated is reduced by that factor.
5) The "-o mba_MBps" mount option must be disabled in SNC mode because the monitoring is being done per SNC node, while the bandwidth allocation is still done at the L3 cache scope. Trying to use this feedback loop might result in contradictory changes to the throttling level coming from each of the SNC node bandwidth measurements.

The latter part of this changelog stopped being in imperative mood. To reduce confusion I slightly reworked it below to address the parts I noticed. I often get it wrong myself so please check again.

Add a global integer "snc_nodes_per_l3_cache" that shows how many SNC nodes share each L3 cache. When "snc_nodes_per_l3_cache" is "1", SNC mode is either not implemented, or not enabled.

Update all places to take appropriate action when SNC mode is enabled:
1) The number of logical RMIDs per L3 cache available for use is the number of physical RMIDs divided by the number of SNC nodes.
2) Likewise the "mon_scale" value must be divided by the number of SNC nodes.
3) The RMID renumbering operates when using the value from the IA32_PQR_ASSOC MSR to count accesses by a task. When reading an RMID counter, adjust from the logical RMID to the physical RMID value for the SNC node that it wishes to read and load the adjusted value into the IA32_QM_EVTSEL MSR.
4) Divide the L3 cache between the SNC nodes. Divide the value reported in the resctrl "size" file by the number of SNC nodes because the effective amount of cache that can be allocated is reduced by that factor.
5) Disable the "-o mba_MBps" mount option in SNC mode because the monitoring is being done per SNC node, while the bandwidth allocation is still done at the L3 cache scope. Trying to use this feedback loop might result in contradictory changes to the throttling level coming from each of the SNC node bandwidth measurements.

Quoted 3 lines

---

(same comment as previous patch about commit tag ordering)

Reinette

author maintainer
#231 lore raw

PATCH v11 7/8 x86/resctrl: Sub NUMA Cluster detection and enable

In reply to Tony Luck

There isn't a simple hardware bit that indicates whether a CPU is running in Sub NUMA Cluster (SNC) mode. Infer the state by comparing the ratio of NUMA nodes to L3 cache instances.

When SNC mode is detected, reconfigure the RMID counters by updating the MSR_RMID_SNC_CONFIG MSR on each socket as CPUs are seen.

Clearing bit zero of the MSR divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

---
Changes since v10:
Reinette: Revert two places where I'd globally swapped "h/w" for
"hardware" in comments for functions that were not touched by this patch.

 arch/x86/include/asm/msr-index.h   |  1 +
 arch/x86/kernel/cpu/resctrl/core.c | 96 ++++++++++++++++++++++++++++++
 2 files changed, 97 insertions(+)
arch/x86/include/asm/msr-index.h +1 -0
index e3fa9cecd599..4285a5ee81fe 100644
@@ -1109,6 +1109,7 @@
 #define MSR_IA32_QM_CTR			0xc8e
 #define MSR_IA32_PQR_ASSOC		0xc8f
 #define MSR_IA32_L3_CBM_BASE		0xc90
+#define MSR_RMID_SNC_CONFIG		0xca0
 #define MSR_IA32_L2_CBM_BASE		0xd10
 #define MSR_IA32_MBA_THRTL_BASE		0xd50
 
arch/x86/kernel/cpu/resctrl/core.c +96 -0

129 lines not on this page · raw message

Signature · 1 line
2.41.0
maintainer Reviewed-by on v11 7/8
#232 lore raw

Re: [PATCH v11 7/8] x86/resctrl: Sub NUMA Cluster detection and enable

Hi Tony,

Quoted 7 lines · Tony Luck

There isn't a simple hardware bit that indicates whether a CPU is running in Sub NUMA Cluster (SNC) mode. Infer the state by comparing the ratio of NUMA nodes to L3 cache instances.

When SNC mode is detected, reconfigure the RMID counters by updating the MSR_RMID_SNC_CONFIG MSR on each socket as CPUs are seen.

Quoted 6 lines

Clearing bit zero of the MSR divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

---

(note ordering of commit tags)

Reinette

author maintainer
#233 lore raw

PATCH v11 8/8 x86/resctrl: Update documentation with Sub-NUMA cluster changes

In reply to Tony Luck

With Sub-NUMA Cluster mode enabled the scope of monitoring resources is per-NODE instead of per-L3 cache. Suffixes of directories with "L3" in their name refer to Sub-NUMA nodes instead of L3 cache ids.

Users should be aware that SNC mode also affects the amount of L3 cache available for allocation within each SNC node.

---
 Documentation/arch/x86/resctrl.rst | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)
Documentation/arch/x86/resctrl.rst +20 -3
index a6279df64a9d..d1db200db5f9 100644
@@ -366,9 +366,9 @@ When control is enabled all CTRL_MON groups will also contain:
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
-	This contains a set of files organized by L3 domain and by
-	RDT event. E.g. on a system with two L3 domains there will
-	be subdirectories "mon_L3_00" and "mon_L3_01".	Each of these
+	This contains a set of files organized by L3 domain or by NUMA
+	node (depending on whether Sub-NUMA Cluster (SNC) mode is disabled
+	or enabled respectively) and by RDT event.  Each of these
 	directories have one file per event (e.g. "llc_occupancy",
 	"mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
 	files provide a read out of the current value of the event for
@@ -478,6 +478,23 @@ if non-contiguous 1s value is supported. On a system with a 20-bit mask
 each bit represents 5% of the capacity of the cache. You could partition
 the cache into four equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
 
+Notes on Sub-NUMA Cluster mode
+==============================
+When SNC mode is enabled Linux may load balance tasks between Sub-NUMA
+nodes much more readily than between regular NUMA nodes since the CPUs
+on Sub-NUMA nodes share the same L3 cache and the system may report
+the NUMA distance between Sub-NUMA nodes with a lower value than used
+for regular NUMA nodes.  Users who do not bind tasks to the CPUs of a
+specific Sub-NUMA node must read the "llc_occupancy", "mbm_total_bytes",
+and "mbm_local_bytes" for all Sub-NUMA nodes where the tasks may execute
+to get the full view of traffic for which the tasks were the source.
+
+The cache allocation feature still provides the same number of
+bits in a mask to control allocation into the L3 cache. But each
+of those ways has its capacity reduced because the cache is divided
+between the SNC nodes. The values reported in the resctrl
+"size" files are adjusted accordingly.
+
 Memory bandwidth Allocation and monitoring
 ==========================================
 
Signature · 1 line
2.41.0
reviewer
#234 lore raw

Re: [PATCH v11 8/8] x86/resctrl: Update documentation with Sub-NUMA cluster changes

Hi Tony,

If you make any updates to this:
(but not critical)

Quoted 18 lines · Tony Luck

With Sub-NUMA Cluster mode enabled the scope of monitoring resources is per-NODE instead of per-L3 cache. Suffixes of directories with "L3" in their name refer to Sub-NUMA nodes instead of L3 cache ids.

Users should be aware that SNC mode also affects the amount of L3 cache available for allocation within each SNC node.

---
 Documentation/arch/x86/resctrl.rst | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)
Documentation/arch/x86/resctrl.rst +0 -0
index a6279df64a9d..d1db200db5f9 100644

Documentation/arch/x86/resctrl.rst When control is enabled all CTRL_MON groups will also contain: · line 372

Quoted 10 lines
Documentation/arch/x86/resctrl.rst +3 -3
@@ -366,9 +366,9 @@ When control is enabled all CTRL_MON groups will also contain:
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
-	This contains a set of files organized by L3 domain and by
-	RDT event. E.g. on a system with two L3 domains there will
-	be subdirectories "mon_L3_00" and "mon_L3_01".	Each of these
+	This contains a set of files organized by L3 domain or by NUMA
+	node (depending on whether Sub-NUMA Cluster (SNC) mode is disabled
+	or enabled respectively) and by RDT event.  Each of these
 	directories have one file per event (e.g. "llc_occupancy",

has

Quoted 9 lines
Documentation/arch/x86/resctrl.rst +3 -0
 	"mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
 	files provide a read out of the current value of the event for
@@ -478,6 +478,23 @@ if non-contiguous 1s value is supported. On a system with a 20-bit mask
 each bit represents 5% of the capacity of the cache. You could partition
 the cache into four equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
 
+Notes on Sub-NUMA Cluster mode
+==============================
+When SNC mode is enabled Linux may load balance tasks between Sub-NUMA

Documentation/arch/x86/resctrl.rst if non-contiguous 1s value is supported. On a system with a 20-bit mask · line 493

Quoted 10 lines
Documentation/arch/x86/resctrl.rst +10 -0
+nodes much more readily than between regular NUMA nodes since the CPUs
+on Sub-NUMA nodes share the same L3 cache and the system may report
+the NUMA distance between Sub-NUMA nodes with a lower value than used
+for regular NUMA nodes.  Users who do not bind tasks to the CPUs of a
+specific Sub-NUMA node must read the "llc_occupancy", "mbm_total_bytes",
+and "mbm_local_bytes" for all Sub-NUMA nodes where the tasks may execute
+to get the full view of traffic for which the tasks were the source.
+
+The cache allocation feature still provides the same number of
+bits in a mask to control allocation into the L3 cache. But each

cache, but each

Quoted 7 lines
Documentation/arch/x86/resctrl.rst +4 -0
+of those ways has its capacity reduced because the cache is divided
+between the SNC nodes. The values reported in the resctrl
+"size" files are adjusted accordingly.
+
 Memory bandwidth Allocation and monitoring
 ==========================================
 
Signature · 1 line
~Randy
maintainer Reviewed-by on v11 8/8
#235 lore raw

Re: [PATCH v11 8/8] x86/resctrl: Update documentation with Sub-NUMA cluster changes

In reply to Tony Luck

Hi Tony,

Quoted 10 lines · Tony Luck

With Sub-NUMA Cluster mode enabled the scope of monitoring resources is per-NODE instead of per-L3 cache. Suffixes of directories with "L3" in their name refer to Sub-NUMA nodes instead of L3 cache ids.

Users should be aware that SNC mode also affects the amount of L3 cache available for allocation within each SNC node.

---

(note about order of commit tags)

Reinette

author maintainer
#238 lore raw

v12 cover Add support for Sub-NUMA cluster (SNC) systems

In reply to Tony Luck

The Sub-NUMA cluster feature on some Intel processors partitions the CPUs that share an L3 cache into two or more sets. This plays havoc with the Resource Director Technology (RDT) monitoring features. Prior to this patch Intel has advised that SNC and RDT are incompatible.

Some of these CPU support an MSR that can partition the RMID counters in the same way. This allows monitoring features to be used. With the caveat that users must be aware that Linux may migrate tasks more frequently between SNC nodes than between "regular" NUMA nodes, so reading counters from all SNC nodes may be needed to get a complete picture of activity for tasks.

Cache and memory bandwidth allocation features continue to operate at the scope of the L3 cache.

Changes since v11:

Global: (comment from Reinette)
Reorder tags with Signed-off-by: first, then Reviewed/Tested

Patch1: (comment from Reinette)
Add error message to domain_remove_cpu() [matching the one in domain_add_cpu()] for the case where get_cpu_cacheinfo_id() failed to find a cache ID for the current CPU.

Patch3: (comment from Reinette)
When splitting the domain_add_cpu() and domain_remove_cpu() functions add "control" and "monitor" to the warning messages. Fix the:
pr_warn("Couldn't find control scope id=%d for CPU %d\n", id, cpu);
message:
s/Couldn't/Can't/
s/control scope/control domain with/
Add resource name.
Ditto for similar monitor message.

Patch6: (comment from Reinette)
Used Reinette's rewrite into imperative mood for latter part of commit message.

Patch8: (comment from Randy)
s/have/has/ s/cache. But/cache, but/

Added Reinette's "Reviewed-by:" to all patches except patch 3.

Added Shaopeng Tan's Reviewed and Tested to all patches.

Rebased to v6.7-rc3

Tony Luck (8):
x86/resctrl: Prepare for new domain scope x86/resctrl: Prepare to split rdt_domain structure x86/resctrl: Prepare for different scope for control/monitor
operations
x86/resctrl: Split the rdt_domain and rdt_hw_domain structures x86/resctrl: Add node-scope to the options for feature scope x86/resctrl: Introduce snc_nodes_per_l3_cache x86/resctrl: Sub NUMA Cluster detection and enable x86/resctrl: Update documentation with Sub-NUMA cluster changes

 Documentation/arch/x86/resctrl.rst        |  25 +-
 include/linux/resctrl.h                   |  85 +++--
 arch/x86/include/asm/msr-index.h          |   1 +
 arch/x86/kernel/cpu/resctrl/internal.h    |  66 ++--
 arch/x86/kernel/cpu/resctrl/core.c        | 411 +++++++++++++++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  58 +--
 arch/x86/kernel/cpu/resctrl/monitor.c     |  68 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  26 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 149 ++++----
 9 files changed, 607 insertions(+), 282 deletions(-)

base-commit: 2cc14f52aeb78ce3f29677c2de1f06c0e91471ab

Signature · 1 line
2.41.0
author maintainer
#239 lore raw

PATCH v12 1/8 x86/resctrl: Prepare for new domain scope

Resctrl resources operate on subsets of CPUs in the system with the defining attribute of each subset being an instance of a particular level of cache. E.g. all CPUs sharing an L3 cache would be part of the same domain.

In preparation for features that are scoped at the NUMA node level change the code from explicit references to "cache_level" to a more generic scope. At this point the only options for this scope are groups of CPUs that share an L2 cache or L3 cache.

Clean up the error handling when looking up domains. Report invalid id's before calling rdt_find_domain() in preparation for better messages when scope can be other than cache scope. This means that rdt_find_domain() will never return an error. So remove checks for error from the callsites.

---
 include/linux/resctrl.h                   |  9 ++++-
 arch/x86/kernel/cpu/resctrl/core.c        | 45 ++++++++++++++++-------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  2 +-
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  6 ++-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  5 ++-
 5 files changed, 48 insertions(+), 19 deletions(-)
include/linux/resctrl.h +7 -2
index 66942d7fba7f..7d4eb7df611d 100644
@@ -144,13 +144,18 @@ struct resctrl_membw {
 struct rdt_parse_data;
 struct resctrl_schema;
 
+enum resctrl_scope {
+	RESCTRL_L2_CACHE = 2,
+	RESCTRL_L3_CACHE = 3,
+};
+
 /**
  * struct rdt_resource - attributes of a resctrl resource
  * @rid:		The index of the resource
  * @alloc_capable:	Is allocation available on this machine
  * @mon_capable:	Is monitor feature available on this machine
  * @num_rmid:		Number of RMIDs available
- * @cache_level:	Which cache level defines scope of this resource
+ * @scope:		Scope of this resource
  * @cache:		Cache allocation related data
  * @membw:		If the component has bandwidth controls, their properties.
  * @domains:		All domains for this resource
@@ -168,7 +173,7 @@ struct rdt_resource {
 	bool			alloc_capable;
 	bool			mon_capable;
 	int			num_rmid;
-	int			cache_level;
+	enum resctrl_scope	scope;
 	struct resctrl_cache	cache;
 	struct resctrl_membw	membw;
 	struct list_head	domains;
arch/x86/kernel/cpu/resctrl/core.c +31 -14

105 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +1 -1
index beccb0e87ba7..3f8891d57fac 100644
@@ -563,7 +563,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 	r = &rdt_resources_all[resid].r_resctrl;
 	d = rdt_find_domain(r, domid, NULL);
-	if (IS_ERR_OR_NULL(d)) {
+	if (!d) {
 		ret = -ENOENT;
 		goto out;
 	}
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +5 -1
index 8f559eeae08e..2a682da9f43a 100644
@@ -292,10 +292,14 @@ 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;
 	struct cpu_cacheinfo *ci;
 	int ret;
 	int i;
 
+	if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
+		return -ENODEV;
+
 	/* Pick the first cpu we find that is associated with the cache. */
 	plr->cpu = cpumask_first(&plr->d->cpu_mask);
 
@@ -311,7 +315,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
 
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == plr->s->res->cache_level) {
+		if (ci->info_list[i].level == scope) {
 			plr->line_size = ci->info_list[i].coherency_line_size;
 			return 0;
 		}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +4 -1
index 69a1de92384a..c44be64d65ec 100644
@@ -1413,10 +1413,13 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 	unsigned int size = 0;
 	int num_b, i;
 
+	if (WARN_ON_ONCE(r->scope != RESCTRL_L2_CACHE && r->scope != RESCTRL_L3_CACHE))
+		return size;
+
 	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
 	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == r->cache_level) {
+		if (ci->info_list[i].level == r->scope) {
 			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
 			break;
 		}
Signature · 1 line
2.41.0
author maintainer
#240 lore raw

PATCH v12 2/8 x86/resctrl: Prepare to split rdt_domain structure

In reply to Tony Luck

The rdt_domain structure is used for both control and monitor features. It is about to be split into separate structures for these two usages because the scope for control and monitoring features for a resource will be different for future resources.

To allow for common code that scans a list of domains looking for a specific domain id, move all the common fields ("list", "id", "cpu_mask") into their own structure within the rdt_domain structure.

---
 include/linux/resctrl.h                   | 16 ++++--
 arch/x86/kernel/cpu/resctrl/core.c        | 26 +++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 22 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 10 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 14 +++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 60 +++++++++++------------
 6 files changed, 78 insertions(+), 70 deletions(-)
include/linux/resctrl.h +12 -4
index 7d4eb7df611d..c4067150a6b7 100644
@@ -53,10 +53,20 @@ struct resctrl_staged_config {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * struct rdt_domain_hdr - common header for different domain types
  * @list:		all instances of this resource
  * @id:			unique id for this instance
  * @cpu_mask:		which CPUs share this resource
+ */
+struct rdt_domain_hdr {
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+};
+
+/**
+ * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * @hdr:		common header for different domain types
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
  * @mbm_local:		saved state for MBM local bandwidth
@@ -71,9 +81,7 @@ struct resctrl_staged_config {
  *			by closid
  */
 struct rdt_domain {
-	struct list_head		list;
-	int				id;
-	struct cpumask			cpu_mask;
+	struct rdt_domain_hdr		hdr;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;
arch/x86/kernel/cpu/resctrl/core.c +13 -13
index fd113bc29d4e..62a989fd950d 100644
@@ -356,9 +356,9 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
 {
 	struct rdt_domain *d;
 
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->cpu_mask))
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
 			return d;
 	}
 
@@ -402,12 +402,12 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	struct list_head *l;
 
 	list_for_each(l, &r->domains) {
-		d = list_entry(l, struct rdt_domain, list);
+		d = list_entry(l, struct rdt_domain, hdr.list);
 		/* When id is found, return its domain. */
-		if (id == d->id)
+		if (id == d->hdr.id)
 			return d;
 		/* Stop searching when finding id's position in sorted list. */
-		if (id < d->id)
+		if (id < d->hdr.id)
 			break;
 	}
 
@@ -530,7 +530,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 	d = rdt_find_domain(r, id, &add_pos);
 	if (d) {
-		cpumask_set_cpu(cpu, &d->cpu_mask);
+		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 		if (r->cache.arch_has_per_cpu_cfg)
 			rdt_domain_reconfigure_cdp(r);
 		return;
@@ -541,8 +541,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 
 	d = &hw_dom->d_resctrl;
-	d->id = id;
-	cpumask_set_cpu(cpu, &d->cpu_mask);
+	d->hdr.id = id;
+	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	rdt_domain_reconfigure_cdp(r);
 
@@ -556,11 +556,11 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	list_add_tail(&d->list, add_pos);
+	list_add_tail(&d->hdr.list, add_pos);
 
 	err = resctrl_online_domain(r, d);
 	if (err) {
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 		domain_free(hw_dom);
 	}
 }
@@ -584,10 +584,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 	}
 	hw_dom = resctrl_to_arch_dom(d);
 
-	cpumask_clear_cpu(cpu, &d->cpu_mask);
-	if (cpumask_empty(&d->cpu_mask)) {
+	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
+	if (cpumask_empty(&d->hdr.cpu_mask)) {
 		resctrl_offline_domain(r, d);
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 
 		/*
 		 * rdt_domain "d" is going to be freed below, so clear
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +11 -11
index 3f8891d57fac..23f8258d36a8 100644
@@ -67,7 +67,7 @@ int parse_bw(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;
 	}
 
@@ -146,7 +146,7 @@ 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;
 	}
 
@@ -226,8 +226,8 @@ static int parse_line(char *line, struct resctrl_schema *s,
 		return -EINVAL;
 	}
 	dom = strim(dom);
-	list_for_each_entry(d, &r->domains, list) {
-		if (d->id == dom_id) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
 			data.buf = dom;
 			data.rdtgrp = rdtgrp;
 			if (r->parse_ctrlval(&data, s, d))
@@ -274,7 +274,7 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
 	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);
+		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
 		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
 
 		return true;
@@ -291,7 +291,7 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 		return -ENOMEM;
 
 	msr_param.res = NULL;
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		hw_dom = resctrl_to_arch_dom(d);
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	u32 ctrl_val;
 
 	seq_printf(s, "%*s:", max_name_width, schema->name);
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
 		if (sep)
 			seq_puts(s, ";");
 
@@ -476,7 +476,7 @@ 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 +505,7 @@ 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 {
@@ -536,7 +536,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	rr->val = 0;
 	rr->first = first;
 
-	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	smp_call_function_any(&d->hdr.cpu_mask, mon_event_count, rr, 1);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
arch/x86/kernel/cpu/resctrl/monitor.c +5 -5
index f136ac046851..dd0ea1bc0092 100644
@@ -238,7 +238,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	u64 msr_val, chunks;
 	int ret;
 
-	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+	if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask))
 		return -EINVAL;
 
 	ret = __rmid_read(rmid, eventid, &msr_val);
@@ -340,8 +340,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
 	entry->busy = 0;
 	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, list) {
-		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
 			err = resctrl_arch_rmid_read(r, d, entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
 						     &val);
@@ -661,7 +661,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
 	dom->cqm_work_cpu = cpu;
 
 	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
@@ -708,7 +708,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
 
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		return;
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
 	dom->mbm_work_cpu = cpu;
 	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
 }
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +7 -7
index 2a682da9f43a..fcbd99e2eb66 100644
@@ -221,7 +221,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
 	int cpu;
 	int ret;
 
-	for_each_cpu(cpu, &plr->d->cpu_mask) {
+	for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
 		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
 		if (!pm_req) {
 			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
@@ -301,7 +301,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 		return -ENODEV;
 
 	/* Pick the first cpu we find that is associated with the cache. */
-	plr->cpu = cpumask_first(&plr->d->cpu_mask);
+	plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 
 	if (!cpu_online(plr->cpu)) {
 		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
@@ -856,10 +856,10 @@ 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, list) {
+		list_for_each_entry(d_i, &r->domains, hdr.list) {
 			if (d_i->plr)
 				cpumask_or(cpu_with_psl, cpu_with_psl,
-					   &d_i->cpu_mask);
+					   &d_i->hdr.cpu_mask);
 		}
 	}
 
@@ -867,7 +867,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	 * Next test if new pseudo-locked region would intersect with
 	 * existing region.
 	 */
-	if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+	if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
 		ret = true;
 
 	free_cpumask_var(cpu_with_psl);
@@ -1199,7 +1199,7 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 	}
 
 	plr->thread_done = 0;
-	cpu = cpumask_first(&plr->d->cpu_mask);
+	cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 	if (!cpu_online(cpu)) {
 		ret = -ENODEV;
 		goto out;
@@ -1529,7 +1529,7 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
 	 * may be scheduled elsewhere and invalidate entries in the
 	 * pseudo-locked region.
 	 */
-	if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) {
+	if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
 		mutex_unlock(&rdtgroup_mutex);
 		return -EINVAL;
 	}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +30 -30

220 lines not on this page · raw message

Signature · 1 line
2.41.0
author maintainer
#241 lore raw

PATCH v12 3/8 x86/resctrl: Prepare for different scope for control/monitor operations

In reply to Tony Luck

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.

---
 include/linux/resctrl.h                   |  25 ++-
 arch/x86/kernel/cpu/resctrl/internal.h    |   6 +-
 arch/x86/kernel/cpu/resctrl/core.c        | 211 ++++++++++++++++------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  12 +-
 arch/x86/kernel/cpu/resctrl/monitor.c     |   4 +-
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |   4 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  55 +++---
 7 files changed, 220 insertions(+), 97 deletions(-)
include/linux/resctrl.h +19 -6
index c4067150a6b7..35e700edc6e6 100644
@@ -52,15 +52,22 @@ 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;
 };
 
@@ -163,10 +170,12 @@ 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:		All domains for this resource
+ * @ctrl_domains:	Control domains for this resource
+ * @mon_domains:	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.
@@ -181,10 +190,12 @@ 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;
@@ -230,8 +241,10 @@ 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);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
arch/x86/kernel/cpu/resctrl/internal.h +3 -3
index a4f1aa15f0a2..24bf9d7989a9 100644
@@ -520,8 +520,8 @@ 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,
@@ -540,7 +540,7 @@ 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);
 int closids_supported(void);
 void closid_free(int closid);
 int alloc_rmid(void);
arch/x86/kernel/cpu/resctrl/core.c +157 -54

338 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +7 -5
index 23f8258d36a8..0b4136c42762 100644
@@ -226,7 +226,7 @@ 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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 		return -ENOMEM;
 
 	msr_param.res = NULL;
-	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 (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	u32 ctrl_val;
 
 	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, ";");
 
@@ -542,6 +542,7 @@ 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;
@@ -562,11 +563,12 @@ 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/monitor.c +2 -2
index dd0ea1bc0092..ec5ad926c5dc 100644
@@ -340,7 +340,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
 	entry->busy = 0;
 	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
 		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
 			err = resctrl_arch_rmid_read(r, d, entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
@@ -535,7 +535,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	rmid = rgrp->mon.rmid;
 	pmbm_data = &dom_mbm->mbm_local[rmid];
 
-	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 +2 -2
index fcbd99e2eb66..ed6d59af1cef 100644
@@ -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 cpu_cacheinfo *ci;
 	int ret;
 	int i;
@@ -856,7 +856,7 @@ 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 +30 -25

170 lines not on this page · raw message

Signature · 1 line
2.41.0
maintainer Reviewed-by on v12 3/8
#242 lore raw

Re: [PATCH v12 3/8] x86/resctrl: Prepare for different scope for control/monitor operations

Hi Tony,

Quoted 15 lines · Tony Luck

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.

Quoted 4 lines

---

According to Documentation/process/maintainer-tip.rst the "Tested-by" tag should go before the "Reviewed-by" tag. Please check the whole series.

Reinette

author maintainer
#243 lore raw

PATCH v12 4/8 x86/resctrl: Split the rdt_domain and rdt_hw_domain structures

In reply to Tony Luck

The same rdt_domain structure is used for both control and monitor functions. But this results in wasted memory as some of the fields are only used by control functions, while most are only used for monitor functions.

Split into separate rdt_ctrl_domain and rdt_mon_domain structures with just the fields required for control and monitoring respectively.

Similar split of the rdt_hw_domain structure into rdt_hw_ctrl_domain and rdt_hw_mon_domain.

---
 include/linux/resctrl.h                   | 48 +++++++------
 arch/x86/kernel/cpu/resctrl/internal.h    | 60 ++++++++++------
 arch/x86/kernel/cpu/resctrl/core.c        | 87 ++++++++++++-----------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 32 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 40 +++++------
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  6 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 62 ++++++++--------
 7 files changed, 182 insertions(+), 153 deletions(-)
include/linux/resctrl.h +28 -20
index 35e700edc6e6..058a940c3239 100644
@@ -72,7 +72,23 @@ struct rdt_domain_hdr {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource
+ * @hdr:		common header for different domain types
+ * @plr:		pseudo-locked region (if any) associated with domain
+ * @staged_config:	parsed configuration to be applied
+ * @mbps_val:		When mba_sc is enabled, this holds the array of user
+ *			specified control values for mba_sc in MBps, indexed
+ *			by closid
+ */
+struct rdt_ctrl_domain {
+	struct rdt_domain_hdr		hdr;
+	struct pseudo_lock_region	*plr;
+	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
+	u32				*mbps_val;
+};
+
+/**
+ * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
  * @hdr:		common header for different domain types
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
@@ -81,13 +97,8 @@ struct rdt_domain_hdr {
  * @cqm_limbo:		worker to periodically read CQM h/w counters
  * @mbm_work_cpu:	worker CPU for MBM h/w counters
  * @cqm_work_cpu:	worker CPU for CQM h/w counters
- * @plr:		pseudo-locked region (if any) associated with domain
- * @staged_config:	parsed configuration to be applied
- * @mbps_val:		When mba_sc is enabled, this holds the array of user
- *			specified control values for mba_sc in MBps, indexed
- *			by closid
  */
-struct rdt_domain {
+struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
@@ -96,9 +107,6 @@ struct rdt_domain {
 	struct delayed_work		cqm_limbo;
 	int				mbm_work_cpu;
 	int				cqm_work_cpu;
-	struct pseudo_lock_region	*plr;
-	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
-	u32				*mbps_val;
 };
 
 /**
@@ -202,7 +210,7 @@ struct rdt_resource {
 	const char		*format_str;
 	int			(*parse_ctrlval)(struct rdt_parse_data *data,
 						 struct resctrl_schema *s,
-						 struct rdt_domain *d);
+						 struct rdt_ctrl_domain *d);
 	struct list_head	evt_list;
 	unsigned long		fflags;
 	bool			cdp_capable;
@@ -236,15 +244,15 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
  * Update the ctrl_val and apply this config right now.
  * Must be called on one of the domain's CPUs.
  */
-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);
 
-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);
-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);
+int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
+void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
@@ -260,7 +268,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain *d);
  * Return:
  * 0 on success, or -EIO, -EINVAL etc on error.
  */
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 rmid, enum resctrl_event_id eventid, u64 *val);
 
 /**
@@ -273,7 +281,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 			     u32 rmid, enum resctrl_event_id eventid);
 
 /**
@@ -285,7 +293,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d);
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d);
 
 extern unsigned int resctrl_rmid_realloc_threshold;
 extern unsigned int resctrl_rmid_realloc_limit;
arch/x86/kernel/cpu/resctrl/internal.h +38 -22

131 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/core.c +46 -41

246 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +16 -16
index 0b4136c42762..08fc97ce4135 100644
@@ -58,7 +58,7 @@ 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;
@@ -137,7 +137,7 @@ 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;
@@ -206,8 +206,8 @@ 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;
 
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
@@ -267,11 +267,11 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
 	}
 }
 
-static bool apply_config(struct rdt_hw_domain *hw_dom,
+static bool apply_config(struct rdt_hw_ctrl_domain *hw_dom,
 			 struct resctrl_staged_config *cfg, u32 idx,
 			 cpumask_var_t cpu_mask)
 {
-	struct rdt_domain *dom = &hw_dom->d_resctrl;
+	struct rdt_ctrl_domain *dom = &hw_dom->d_resctrl;
 
 	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
 		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
@@ -283,11 +283,11 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
 	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;
 
@@ -307,11 +307,11 @@ 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))
@@ -319,7 +319,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 
 	msr_param.res = NULL;
 	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		hw_dom = resctrl_to_arch_dom(d);
+		hw_dom = resctrl_to_arch_ctrl_dom(d);
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
 			if (!cfg->have_new_ctrl)
@@ -449,10 +449,10 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	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];
@@ -461,7 +461,7 @@ 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;
 
@@ -523,7 +523,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 }
 
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
 		    int evtid, int first)
 {
 	/*
@@ -543,11 +543,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
 	struct rdt_domain_hdr *hdr;
+	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;
 
@@ -568,7 +568,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		ret = -ENOENT;
 		goto out;
 	}
-	d = container_of(hdr, struct rdt_domain, hdr);
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
 
 	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
arch/x86/kernel/cpu/resctrl/monitor.c +20 -20
index ec5ad926c5dc..4e145f5620b0 100644
@@ -170,7 +170,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 	return 0;
 }
 
-static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
+static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_dom,
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
 {
@@ -189,10 +189,10 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 	return NULL;
 }
 
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 			     u32 rmid, enum resctrl_event_id eventid)
 {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct arch_mbm_state *am;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
@@ -208,9 +208,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
  * Assumes that hardware counters are also reset and thus that there is
  * no need to record initial non-zero counts.
  */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d)
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 
 	if (is_mbm_total_enabled())
 		memset(hw_dom->arch_mbm_total, 0,
@@ -229,11 +229,11 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 	return chunks >> shift;
 }
 
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 rmid, enum resctrl_event_id eventid, u64 *val)
 {
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
 	u64 msr_val, chunks;
 	int ret;
@@ -266,7 +266,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  * decrement the count. If the busy count gets to zero on an RMID, we
  * free the RMID
  */
-void __check_limbo(struct rdt_domain *d, bool force_free)
+void __check_limbo(struct rdt_mon_domain *d, bool force_free)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	struct rmid_entry *entry;
@@ -305,7 +305,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 	}
 }
 
-bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d)
+bool has_busy_rmid(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid;
 }
@@ -334,7 +334,7 @@ int alloc_rmid(void)
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_domain *d;
+	struct rdt_mon_domain *d;
 	int cpu, err;
 	u64 val = 0;
 
@@ -383,7 +383,7 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid,
+static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 rmid,
 				       enum resctrl_event_id evtid)
 {
 	switch (evtid) {
@@ -516,13 +516,13 @@ void mon_event_count(void *info)
  * throttle MSRs already have low percentage values.  To avoid
  * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
  */
-static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
+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;
 	u32 cur_bw, delta_bw, user_bw;
 	struct rdt_resource *r_mba;
-	struct rdt_domain *dom_mba;
 	struct list_head *head;
 	struct rdtgroup *entry;
 
@@ -600,7 +600,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	}
 }
 
-static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, int rmid)
 {
 	struct rmid_read rr;
 
@@ -640,13 +640,13 @@ void cqm_handle_limbo(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
 	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
 	struct rdt_resource *r;
-	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, cqm_limbo.work);
+	d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
 
@@ -656,7 +656,7 @@ void cqm_handle_limbo(struct work_struct *work)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
@@ -672,9 +672,9 @@ void mbm_handle_overflow(struct work_struct *work)
 	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
 	struct rdtgroup *prgrp, *crgrp;
 	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
 	struct list_head *head;
 	struct rdt_resource *r;
-	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
 
@@ -682,7 +682,7 @@ void mbm_handle_overflow(struct work_struct *work)
 		goto out_unlock;
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, mbm_over.work);
+	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		mbm_update(r, d, prgrp->mon.rmid);
@@ -701,7 +701,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +3 -3
index ed6d59af1cef..08d35f828bc3 100644
@@ -814,7 +814,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
  * Return: true if @cbm overlaps with pseudo-locked region on @d, false
  * otherwise.
  */
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm)
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
 {
 	unsigned int cbm_len;
 	unsigned long cbm_b;
@@ -841,11 +841,11 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm
  *         if it is not possible to test due to memory allocation issue,
  *         false otherwise.
  */
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
 {
+	struct rdt_ctrl_domain *d_i;
 	cpumask_var_t cpu_with_psl;
 	struct rdt_resource *r;
-	struct rdt_domain *d_i;
 	bool ret = false;
 
 	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
arch/x86/kernel/cpu/resctrl/rdtgroup.c +31 -31

252 lines not on this page · raw message

Signature · 1 line
2.41.0
author maintainer
#244 lore raw

PATCH v12 5/8 x86/resctrl: Add node-scope to the options for feature scope

In reply to Tony Luck

Currently supported resctrl features are all domain scoped the same as the scope of the L2 or L3 caches.

Add RESCTRL_NODE as a new option for features that are scoped at the same granularity as NUMA nodes. This is needed for Intel's Sub-NUMA Cluster (SNC) feature where monitoring features are node scoped.

---
 include/linux/resctrl.h            | 1 +
 arch/x86/kernel/cpu/resctrl/core.c | 2 ++
 2 files changed, 3 insertions(+)
include/linux/resctrl.h +1 -0
index 058a940c3239..b8a3a11b970d 100644
@@ -170,6 +170,7 @@ struct resctrl_schema;
 enum resctrl_scope {
 	RESCTRL_L2_CACHE = 2,
 	RESCTRL_L3_CACHE = 3,
+	RESCTRL_NODE,
 };
 
 /**
arch/x86/kernel/cpu/resctrl/core.c +2 -0
index 797cb3bf417a..c9315ce8f7bd 100644
@@ -502,6 +502,8 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
 	case RESCTRL_L2_CACHE:
 	case RESCTRL_L3_CACHE:
 		return get_cpu_cacheinfo_id(cpu, scope);
+	case RESCTRL_NODE:
+		return cpu_to_node(cpu);
 	default:
 		break;
 	}
Signature · 1 line
2.41.0
author maintainer
#245 lore raw

PATCH v12 6/8 x86/resctrl: Introduce snc_nodes_per_l3_cache

In reply to Tony Luck

Intel Sub-NUMA Cluster (SNC) is a feature that subdivides the CPU cores and memory controllers on a socket into two or more groups. These are presented to the operating system as NUMA nodes.

This may enable some workloads to have slightly lower latency to memory as the memory controller(s) in an SNC node are electrically closer to the CPU cores on that SNC node. This cost may be offset by lower bandwidth since the memory accesses for each core can only be interleaved between the memory controllers on the same SNC node.

Resctrl monitoring on an Intel system depends upon attaching RMIDs to tasks to track L3 cache occupancy and memory bandwidth. There is an MSR that controls how the RMIDs are shared between SNC nodes.

The default mode divides them numerically. E.g. when there are two SNC nodes on a socket the lower number half of the RMIDs are given to the first node, the remainder to the second node. This would be difficult to use with the Linux resctrl interface as specific RMID values assigned to resctrl groups are not visible to users.

The other mode divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

Even with this renumbering SNC mode requires several changes in resctrl behavior for correct operation.

Add a global integer "snc_nodes_per_l3_cache" that shows how many SNC nodes share each L3 cache. When "snc_nodes_per_l3_cache" is "1", SNC mode is either not implemented, or not enabled.

Update all places to take appropriate action when SNC mode is enabled:
1) The number of logical RMIDs per L3 cache available for use is the number of physical RMIDs divided by the number of SNC nodes.
2) Likewise the "mon_scale" value must be divided by the number of SNC nodes.
3) The RMID renumbering operates when using the value from the IA32_PQR_ASSOC MSR to count accesses by a task. When reading an RMID counter, adjust from the logical RMID to the physical RMID value for the SNC node that it wishes to read and load the adjusted value into the IA32_QM_EVTSEL MSR.
4) Divide the L3 cache between the SNC nodes. Divide the value reported in the resctrl "size" file by the number of SNC nodes because the effective amount of cache that can be allocated is reduced by that factor.
5) Disable the "-o mba_MBps" mount option in SNC mode because the monitoring is being done per SNC node, while the bandwidth allocation is still done at the L3 cache scope. Trying to use this feedback loop might result in contradictory changes to the throttling level coming from each of the SNC node bandwidth measurements.

---
 arch/x86/kernel/cpu/resctrl/internal.h |  2 ++
 arch/x86/kernel/cpu/resctrl/core.c     |  6 ++++++
 arch/x86/kernel/cpu/resctrl/monitor.c  | 16 +++++++++++++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  5 +++--
 4 files changed, 24 insertions(+), 5 deletions(-)
arch/x86/kernel/cpu/resctrl/internal.h +2 -0
index ce3a70657842..e7a75a439c16 100644
@@ -446,6 +446,8 @@ DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
 extern struct dentry *debugfs_resctrl;
 
+extern unsigned int snc_nodes_per_l3_cache;
+
 enum resctrl_res_level {
 	RDT_RESOURCE_L3,
 	RDT_RESOURCE_L2,
arch/x86/kernel/cpu/resctrl/core.c +6 -0
index c9315ce8f7bd..cf5aba8a74bf 100644
@@ -48,6 +48,12 @@ int max_name_width, max_data_width;
  */
 bool rdt_alloc_capable;
 
+/*
+ * Number of SNC nodes that share each L3 cache.  Default is 1 for
+ * systems that do not support SNC, or have SNC disabled.
+ */
+unsigned int snc_nodes_per_l3_cache = 1;
+
 static void
 mba_wrmsr_intel(struct rdt_ctrl_domain *d, struct msr_param *m,
 		struct rdt_resource *r);
arch/x86/kernel/cpu/resctrl/monitor.c +13 -3
index 4e145f5620b0..30b7c3b9b517 100644
@@ -148,8 +148,18 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
 
 static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 {
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	int cpu = smp_processor_id();
+	int rmid_offset = 0;
 	u64 msr_val;
 
+	/*
+	 * When SNC mode is on, need to compute the offset to read the
+	 * physical RMID counter for the node to which this CPU belongs.
+	 */
+	if (snc_nodes_per_l3_cache > 1)
+		rmid_offset = (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid;
+
 	/*
 	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
 	 * with a valid event code for supported resource type and the bits
@@ -158,7 +168,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
 	 * are error bits.
 	 */
-	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid + rmid_offset);
 	rdmsrl(MSR_IA32_QM_CTR, msr_val);
 
 	if (msr_val & RMID_VAL_ERROR)
@@ -783,8 +793,8 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	int ret;
 
 	resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
-	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
-	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_nodes_per_l3_cache;
+	r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache;
 	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
 
 	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
arch/x86/kernel/cpu/resctrl/rdtgroup.c +3 -2
index 21bbd832f3f2..79d57dade568 100644
@@ -1425,7 +1425,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 		}
 	}
 
-	return size;
+	return size / snc_nodes_per_l3_cache;
 }
 
 /*
@@ -2298,7 +2298,8 @@ static bool supports_mba_mbps(void)
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 
 	return (is_mbm_local_enabled() &&
-		r->alloc_capable && is_mba_linear());
+		r->alloc_capable && is_mba_linear() &&
+		snc_nodes_per_l3_cache == 1);
 }
 
 /*
Signature · 1 line
2.41.0
author maintainer
#246 lore raw

PATCH v12 7/8 x86/resctrl: Sub NUMA Cluster detection and enable

In reply to Tony Luck

There isn't a simple hardware bit that indicates whether a CPU is running in Sub NUMA Cluster (SNC) mode. Infer the state by comparing the ratio of NUMA nodes to L3 cache instances.

When SNC mode is detected, reconfigure the RMID counters by updating the MSR_RMID_SNC_CONFIG MSR on each socket as CPUs are seen.

Clearing bit zero of the MSR divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

---
 arch/x86/include/asm/msr-index.h   |  1 +
 arch/x86/kernel/cpu/resctrl/core.c | 96 ++++++++++++++++++++++++++++++
 2 files changed, 97 insertions(+)
arch/x86/include/asm/msr-index.h +1 -0
index 1d51e1850ed0..94d29d81e6db 100644
@@ -1111,6 +1111,7 @@
 #define MSR_IA32_QM_CTR			0xc8e
 #define MSR_IA32_PQR_ASSOC		0xc8f
 #define MSR_IA32_L3_CBM_BASE		0xc90
+#define MSR_RMID_SNC_CONFIG		0xca0
 #define MSR_IA32_L2_CBM_BASE		0xd10
 #define MSR_IA32_MBA_THRTL_BASE		0xd50
 
arch/x86/kernel/cpu/resctrl/core.c +96 -0

129 lines not on this page · raw message

Signature · 1 line
2.41.0
#247 lore raw

Re: [PATCH v12 7/8] x86/resctrl: Sub NUMA Cluster detection and enable

Hi Tony,

Quoted 129 lines · Tony Luck

There isn't a simple hardware bit that indicates whether a CPU is running in Sub NUMA Cluster (SNC) mode. Infer the state by comparing the ratio of NUMA nodes to L3 cache instances.

When SNC mode is detected, reconfigure the RMID counters by updating the MSR_RMID_SNC_CONFIG MSR on each socket as CPUs are seen.

Clearing bit zero of the MSR divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

---
 arch/x86/include/asm/msr-index.h   |  1 +
 arch/x86/kernel/cpu/resctrl/core.c | 96 ++++++++++++++++++++++++++++++
 2 files changed, 97 insertions(+)
arch/x86/include/asm/msr-index.h +1 -0
index 1d51e1850ed0..94d29d81e6db 100644
@@ -1111,6 +1111,7 @@
 #define MSR_IA32_QM_CTR			0xc8e
 #define MSR_IA32_PQR_ASSOC		0xc8f
 #define MSR_IA32_L3_CBM_BASE		0xc90
+#define MSR_RMID_SNC_CONFIG		0xca0
 #define MSR_IA32_L2_CBM_BASE		0xd10
 #define MSR_IA32_MBA_THRTL_BASE		0xd50
 
arch/x86/kernel/cpu/resctrl/core.c +65 -0
index cf5aba8a74bf..3293ab4c58b0 100644
@@ -16,11 +16,14 @@
 
 #define pr_fmt(fmt)	"resctrl: " fmt
 
+#include <linux/cpu.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/cacheinfo.h>
 #include <linux/cpuhotplug.h>
+#include <linux/mod_devicetable.h>
 
+#include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
 #include <asm/resctrl.h>
 #include "internal.h"
@@ -740,11 +743,42 @@ static void clear_closid_rmid(int cpu)
 	wrmsr(MSR_IA32_PQR_ASSOC, 0, 0);
 }
 
+/*
+ * The power-on reset value of MSR_RMID_SNC_CONFIG is 0x1
+ * which indicates that RMIDs are configured in legacy mode.
+ * This mode is incompatible with Linux resctrl semantics
+ * as RMIDs are partitioned between SNC nodes, which requires
+ * a user to know which RMID is allocated to a task.
+ * Clearing bit 0 reconfigures the RMID counters for use
+ * in Sub NUMA Cluster mode. This mode is better for Linux.
+ * The RMID space is divided between all SNC nodes with the
+ * RMIDs renumbered to start from zero in each node when
+ * couning operations from tasks. Code to read the counters
+ * must adjust RMID counter numbers based on SNC node. See
+ * __rmid_read() for code that does this.
+ */
+static void snc_remap_rmids(int cpu)
+{
+	u64 val;
+
+	/* Only need to enable once per package. */
+	if (cpumask_first(topology_core_cpumask(cpu)) != cpu)
+		return;
+
+	rdmsrl(MSR_RMID_SNC_CONFIG, val);
+	val &= ~BIT_ULL(0);
+	wrmsrl(MSR_RMID_SNC_CONFIG, val);
+}
+
 static int resctrl_online_cpu(unsigned int cpu)
 {
 	struct rdt_resource *r;
 
 	mutex_lock(&rdtgroup_mutex);
+
+	if (snc_nodes_per_l3_cache > 1)
+		snc_remap_rmids(cpu);
+
 	for_each_capable_rdt_resource(r)
 		domain_add_cpu(cpu, r);
 	/* The cpu is set in default rdtgroup after online. */
@@ -999,11 +1033,73 @@ static __init bool get_rdt_resources(void)
 	return (rdt_mon_capable || rdt_alloc_capable);
 }
 
+/* CPU models that support MSR_RMID_SNC_CONFIG */
+static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, 0),
+	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 0),
+	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, 0),
+	X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, 0),
+	{}
+};
+
+/*
+ * There isn't a simple hardware bit that indicates whether a CPU is running
+ * in Sub NUMA Cluster (SNC) mode. Infer the state by comparing the
+ * ratio of NUMA nodes to L3 cache instances.
+ * It is not possible to accurately determine SNC state if the system is
+ * booted with a maxcpus=N parameter. That distorts the ratio of SNC nodes
+ * to L3 caches. It will be OK if system is booted with hyperthreading
+ * disabled (since this doesn't affect the ratio).
+ */
+static __init int snc_get_config(void)
+{
+	unsigned long *node_caches;
+	int mem_only_nodes = 0;
+	int cpu, node, ret;
+	int num_l3_caches;
+
+	if (!x86_match_cpu(snc_cpu_ids))
+		return 1;
+
+	node_caches = bitmap_zalloc(nr_node_ids, GFP_KERNEL);
+	if (!node_caches)
+		return 1;

arch/x86/kernel/cpu/resctrl/core.c static __init bool get_rdt_resources(void) · line 1076

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +10 -0
+
+	cpus_read_lock();
+
+	if (num_online_cpus() != num_present_cpus())
+		pr_warn("Some CPUs offline, SNC detection may be incorrect\n");
+
+	for_each_node(node) {
+		cpu = cpumask_first(cpumask_of_node(node));
+		if (cpu < nr_cpu_ids)
+			set_bit(get_cpu_cacheinfo_id(cpu, 3), node_caches);

Are we sure get_cpu_cacheinfo_id() is an valid index here? Looking at the function it could be -1 or larger than nr_node_ids.

Fam

Quoted 31 lines
arch/x86/kernel/cpu/resctrl/core.c +21 -0
+		else
+			mem_only_nodes++;
+	}
+	cpus_read_unlock();
+
+	num_l3_caches = bitmap_weight(node_caches, nr_node_ids);
+	kfree(node_caches);
+
+	if (!num_l3_caches)
+		return 1;
+
+	ret = (nr_node_ids - mem_only_nodes) / num_l3_caches;
+
+	if (ret > 1)
+		rdt_resources_all[RDT_RESOURCE_L3].r_resctrl.mon_scope = RESCTRL_NODE;
+
+	return ret;
+}
+
 static __init void rdt_init_res_defs_intel(void)
 {
 	struct rdt_hw_resource *hw_res;
 	struct rdt_resource *r;
 
+	snc_nodes_per_l3_cache = snc_get_config();
+
 	for_each_rdt_resource(r) {
 		hw_res = resctrl_to_arch_res(r);
 
Signature · 1 line
2.41.
author maintainer
#248 lore raw

Re: [PATCH v12 7/8] x86/resctrl: Sub NUMA Cluster detection and enable

Quoted 18 lines · Fam Zheng
Quoted 18 lines
(quoted diff) +18 -0
+static __init int snc_get_config(void)
+{
+	unsigned long *node_caches;
+	int mem_only_nodes = 0;
+	int cpu, node, ret;
+	int num_l3_caches;
+
+	if (!x86_match_cpu(snc_cpu_ids))
+		return 1;
+
+	node_caches = bitmap_zalloc(nr_node_ids, GFP_KERNEL);
+	if (!node_caches)
+		return 1;
+
+	cpus_read_lock();
+
+	if (num_online_cpus() != num_present_cpus())
+		pr_warn("Some CPUs offline, SNC detection may be incorrect\n");
Quoted 8 lines

Review

Quoted 5 lines
(quoted diff) +5 -0
+
+	for_each_node(node) {
+		cpu = cpumask_first(cpumask_of_node(node));
+		if (cpu < nr_cpu_ids)
+			set_bit(get_cpu_cacheinfo_id(cpu, 3), node_caches);

Are we sure get_cpu_cacheinfo_id() is an valid index here? Looking at the function it could be -1 or larger than nr_node_ids.

Fam,

Return -1 is possible (in the case where first CPU on a node doesn't have an L3 cache). Larger than nr_node_ids seems a bit more speculative. It would mean a system with multiple L3 cache instances per node. I suppose that's theoretically possible. In the limit case every CPU may have its own personal L3 cache, but still have multiple CPUs grouped together on a node.

Patch below (to be folded into part7 of next version). Increases the size of the bitmap. Checks for get_cpu_cacheinfo_id() returning -1. Patch just ignores the node in this case. I'm never quite sure how much code to add for "Can't happen" scenarios.

-Tony

arch/x86/kernel/cpu/resctrl/core.c +8 -4
index 3293ab4c58b0..85f8a1b3feaf 100644
@@ -1056,12 +1056,13 @@ static __init int snc_get_config(void)
 	unsigned long *node_caches;
 	int mem_only_nodes = 0;
 	int cpu, node, ret;
+	int cache_id;
 	int num_l3_caches;
 
 	if (!x86_match_cpu(snc_cpu_ids))
 		return 1;
 
-	node_caches = bitmap_zalloc(nr_node_ids, GFP_KERNEL);
+	node_caches = bitmap_zalloc(num_online_cpus(), GFP_KERNEL);
 	if (!node_caches)
 		return 1;
 
@@ -1072,10 +1073,13 @@ static __init int snc_get_config(void)
 
 	for_each_node(node) {
 		cpu = cpumask_first(cpumask_of_node(node));
-		if (cpu < nr_cpu_ids)
-			set_bit(get_cpu_cacheinfo_id(cpu, 3), node_caches);
-		else
+		if (cpu < nr_cpu_ids) {
+			cache_id = get_cpu_cacheinfo_id(cpu, 3);
+			if (cache_id != -1)
+				set_bit(cache_id, node_caches);
+		} else {
 			mem_only_nodes++;
+		}
 	}
 	cpus_read_unlock();
 
Signature · 1 line
2.41.0
maintainer
#249 lore raw

Re: [PATCH v12 7/8] x86/resctrl: Sub NUMA Cluster detection and enable

Hi Tony,

Quoted 37 lines · Tony Luck
Quoted 18 lines · Fam Zheng
Quoted 18 lines
(quoted diff) +18 -0
+static __init int snc_get_config(void)
+{
+	unsigned long *node_caches;
+	int mem_only_nodes = 0;
+	int cpu, node, ret;
+	int num_l3_caches;
+
+	if (!x86_match_cpu(snc_cpu_ids))
+		return 1;
+
+	node_caches = bitmap_zalloc(nr_node_ids, GFP_KERNEL);
+	if (!node_caches)
+		return 1;
+
+	cpus_read_lock();
+
+	if (num_online_cpus() != num_present_cpus())
+		pr_warn("Some CPUs offline, SNC detection may be incorrect\n");
Quoted 8 lines

Review

Quoted 5 lines
(quoted diff) +5 -0
+
+	for_each_node(node) {
+		cpu = cpumask_first(cpumask_of_node(node));
+		if (cpu < nr_cpu_ids)
+			set_bit(get_cpu_cacheinfo_id(cpu, 3), node_caches);

Are we sure get_cpu_cacheinfo_id() is an valid index here? Looking at the function it could be -1 or larger than nr_node_ids.

Fam,

Return -1 is possible (in the case where first CPU on a node doesn't have an L3 cache). Larger than nr_node_ids seems a bit more speculative. It would mean a system with multiple L3 cache instances per node. I suppose that's theoretically possible. In the limit case every CPU may have its own personal L3 cache, but still have multiple CPUs grouped together on a node.

Quoted 5 lines

Patch below (to be folded into part7 of next version). Increases the size of the bitmap. Checks for get_cpu_cacheinfo_id() returning -1. Patch just ignores the node in this case. I'm never quite sure how much code to add for "Can't happen" scenarios.

Thank you.

arch/x86/kernel/cpu/resctrl/core.c static __init int snc_get_config(void) · line 1060

Quoted 13 lines
(quoted diff) +0 -1
-Tony
arch/x86/kernel/cpu/resctrl/core.c +1 -0
index 3293ab4c58b0..85f8a1b3feaf 100644
@@ -1056,12 +1056,13 @@ static __init int snc_get_config(void)
 	unsigned long *node_caches;
 	int mem_only_nodes = 0;
 	int cpu, node, ret;
+	int cache_id;
 	int num_l3_caches;

Please do maintain reverse fir order.

arch/x86/kernel/cpu/resctrl/core.c static __init int snc_get_config(void) · line 1062

Quoted 3 lines
arch/x86/kernel/cpu/resctrl/core.c +0 -0
 	if (!x86_match_cpu(snc_cpu_ids))
 		return 1;

I understand and welcome this change as motivated by robustness. Apart from that, with this being a model specific feature for this particular group of systems, it it not clear to me in which scenarios this could run on a system where a present CPU does not have access to L3 cache.

arch/x86/kernel/cpu/resctrl/core.c static __init int snc_get_config(void) · line 1065

Quoted 3 lines
arch/x86/kernel/cpu/resctrl/core.c +1 -1
-	node_caches = bitmap_zalloc(nr_node_ids, GFP_KERNEL);
+	node_caches = bitmap_zalloc(num_online_cpus(), GFP_KERNEL);

Please do take care to take new bitmap size into account in all places. From what I can tell there is a later bitmap_weight() call that still uses nr_node_ids as size.

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +0 -3
 	if (!node_caches)
 		return 1;
 
@@ -1072,10 +1073,13 @@ static __init int snc_get_config(void)
 
 	for_each_node(node) {
 		cpu = cpumask_first(cpumask_of_node(node));
-		if (cpu < nr_cpu_ids)
-			set_bit(get_cpu_cacheinfo_id(cpu, 3), node_caches);
-		else

arch/x86/kernel/cpu/resctrl/core.c static __init int snc_get_config(void) · line 1085

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +6 -0
+		if (cpu < nr_cpu_ids) {
+			cache_id = get_cpu_cacheinfo_id(cpu, 3);
+			if (cache_id != -1)
+				set_bit(cache_id, node_caches);
+		} else {
 			mem_only_nodes++;
+		}
 	}
 	cpus_read_unlock();
 

Could this code be made even more robust by checking the computed snc_nodes_per_l3_cache against the limited actually possible values? Forcing it to 1 if something went wrong?

Reinette

author maintainer
#250 lore raw

Re: [PATCH v12 7/8] x86/resctrl: Sub NUMA Cluster detection and enable

Quoted 13 lines · Reinette Chatre

Hi Tony,

arch/x86/kernel/cpu/resctrl/core.c static __init int snc_get_config(void) · line 1060

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +1 -0
index 3293ab4c58b0..85f8a1b3feaf 100644
@@ -1056,12 +1056,13 @@ static __init int snc_get_config(void)
 	unsigned long *node_caches;
 	int mem_only_nodes = 0;
 	int cpu, node, ret;
+	int cache_id;
 	int num_l3_caches;

Please do maintain reverse fir order.

Fixed.

Quoted 9 lines

arch/x86/kernel/cpu/resctrl/core.c static __init int snc_get_config(void) · line 1062

Quoted 4 lines
arch/x86/kernel/cpu/resctrl/core.c +0 -0
 	if (!x86_match_cpu(snc_cpu_ids))
 		return 1;

I understand and welcome this change as motivated by robustness. Apart from that, with this being a model specific feature for this particular group of systems, it it not clear to me in which scenarios this could run on a system where a present CPU does not have access to L3 cache.

Agreed that on these systems there should always be an L3 cache. Should I drop the check for "-1"?

Quoted 7 lines

arch/x86/kernel/cpu/resctrl/core.c static __init int snc_get_config(void) · line 1063

Quoted 3 lines
arch/x86/kernel/cpu/resctrl/core.c +1 -1
-	node_caches = bitmap_zalloc(nr_node_ids, GFP_KERNEL);
+	node_caches = bitmap_zalloc(num_online_cpus(), GFP_KERNEL);

Please do take care to take new bitmap size into account in all places. From what I can tell there is a later bitmap_weight() call that still uses nr_node_ids as size.

Oops. I was also using num_online_cpus() before cpus_read_lock(), so things could theoretically change before the bitmap_weight() call. I switched to using num_present_cpus() in both places.

Quoted 16 lines
Quoted 16 lines
arch/x86/kernel/cpu/resctrl/core.c +5 -3
 	if (!node_caches)
 		return 1;
 
@@ -1072,10 +1073,13 @@ static __init int snc_get_config(void)
 
 	for_each_node(node) {
 		cpu = cpumask_first(cpumask_of_node(node));
-		if (cpu < nr_cpu_ids)
-			set_bit(get_cpu_cacheinfo_id(cpu, 3), node_caches);
-		else
+		if (cpu < nr_cpu_ids) {
+			cache_id = get_cpu_cacheinfo_id(cpu, 3);
+			if (cache_id != -1)
+				set_bit(cache_id, node_caches);
+		} else {
 			mem_only_nodes++;
Quoted 8 lines

arch/x86/kernel/cpu/resctrl/core.c static __init int snc_get_config(void) · line 1085

Quoted 4 lines
arch/x86/kernel/cpu/resctrl/core.c +1 -0
+		}
 	}
 	cpus_read_unlock();
 

Could this code be made even more robust by checking the computed snc_nodes_per_l3_cache against the limited actually possible values? Forcing it to 1 if something went wrong?

Added a couple of extra sanity checks. See updated incremental patch below.

-Tony

arch/x86/kernel/cpu/resctrl/core.c +23 -6
index 3293ab4c58b0..3684c6bf8224 100644
@@ -1057,11 +1057,12 @@ static __init int snc_get_config(void)
 	int mem_only_nodes = 0;
 	int cpu, node, ret;
 	int num_l3_caches;
+	int cache_id;
 
 	if (!x86_match_cpu(snc_cpu_ids))
 		return 1;
 
-	node_caches = bitmap_zalloc(nr_node_ids, GFP_KERNEL);
+	node_caches = bitmap_zalloc(num_present_cpus(), GFP_KERNEL);
 	if (!node_caches)
 		return 1;
 
@@ -1072,23 +1073,39 @@ static __init int snc_get_config(void)
 
 	for_each_node(node) {
 		cpu = cpumask_first(cpumask_of_node(node));
-		if (cpu < nr_cpu_ids)
-			set_bit(get_cpu_cacheinfo_id(cpu, 3), node_caches);
-		else
+		if (cpu < nr_cpu_ids) {
+			cache_id = get_cpu_cacheinfo_id(cpu, 3);
+			if (cache_id != -1)
+				set_bit(cache_id, node_caches);
+		} else {
 			mem_only_nodes++;
+		}
 	}
 	cpus_read_unlock();
 
-	num_l3_caches = bitmap_weight(node_caches, nr_node_ids);
+	num_l3_caches = bitmap_weight(node_caches, num_present_cpus());
 	kfree(node_caches);
 
 	if (!num_l3_caches)
 		return 1;
 
+	/* sanity check #1: Number of CPU nodes must be multiple of num_l3_caches */
+	if ((nr_node_ids - mem_only_nodes) % num_l3_caches)
+		return 1;
+
 	ret = (nr_node_ids - mem_only_nodes) / num_l3_caches;
 
-	if (ret > 1)
+	/* sanity check #2: Only valid results are 1, 2, 4 */
+	switch (ret) {
+	case 1:
+		break;
+	case 2:
+	case 4:
 		rdt_resources_all[RDT_RESOURCE_L3].r_resctrl.mon_scope = RESCTRL_NODE;
+		break;
+	default:
+		return 1;
+	}
 
 	return ret;
 }
Signature · 1 line
2.41.0
maintainer
#251 lore raw

Re: [PATCH v12 7/8] x86/resctrl: Sub NUMA Cluster detection and enable

Hi Tony,

Quoted 1 line · Tony Luck

On Thu, Nov 30, 2023 at 01:47:10PM -0800, Reinette Chatre wrote:

...

Quoted 10 lines
Quoted 7 lines

Review

Quoted 2 lines
(quoted diff) +0 -0
 	if (!x86_match_cpu(snc_cpu_ids))
 		return 1;

I understand and welcome this change as motivated by robustness. Apart from that, with this being a model specific feature for this particular group of systems, it it not clear to me in which scenarios this could run on a system where a present CPU does not have access to L3 cache.

Agreed that on these systems there should always be an L3 cache. Should I drop the check for "-1"?

Please do keep it. I welcome the additional robustness. The static checker I tried did not complain about this but I expect that it is something that could trigger checks.

Quoted 9 lines
Quoted 8 lines

Review

Quoted 4 lines
(quoted diff) +1 -1
-	node_caches = bitmap_zalloc(nr_node_ids, GFP_KERNEL);
+	node_caches = bitmap_zalloc(num_online_cpus(), GFP_KERNEL);

Please do take care to take new bitmap size into account in all places. From what I can tell there is a later bitmap_weight() call that still uses nr_node_ids as size.

Quoted 3 lines

Oops. I was also using num_online_cpus() before cpus_read_lock(), so things could theoretically change before the bitmap_weight() call. I switched to using num_present_cpus() in both places.

Thanks for catching this. I am not sure if num_present_cpus() is the right choice. I found its comment to say "If HOTPLUG is enabled, then cpu_present_mask varies dynamically ...". num_possible_cpus() seems more appropriate when looking for something that does not change while not holding the hotplug lock. Reading its description more closely also makes me wonder if the later

	num_online_cpus() != num_present_cpus()
should also maybe be 
	num_online_cpus() != num_possible_cpus() ?

It seems to more closely match the intention.

Quoted 25 lines
Quoted 16 lines
Quoted 16 lines
arch/x86/kernel/cpu/resctrl/core.c +5 -3
 	if (!node_caches)
 		return 1;
@@ -1072,10 +1073,13 @@ static __init int snc_get_config(void)
 
 	for_each_node(node) {
 		cpu = cpumask_first(cpumask_of_node(node));
-		if (cpu < nr_cpu_ids)
-			set_bit(get_cpu_cacheinfo_id(cpu, 3), node_caches);
-		else
+		if (cpu < nr_cpu_ids) {
+			cache_id = get_cpu_cacheinfo_id(cpu, 3);
+			if (cache_id != -1)
+				set_bit(cache_id, node_caches);
+		} else {
 			mem_only_nodes++;
Quoted 8 lines

arch/x86/kernel/cpu/resctrl/core.c static __init int snc_get_config(void) · line 1085

Quoted 4 lines
arch/x86/kernel/cpu/resctrl/core.c +1 -0
+		}
 	}
 	cpus_read_unlock();
 

Could this code be made even more robust by checking the computed snc_nodes_per_l3_cache against the limited actually possible values? Forcing it to 1 if something went wrong?

Quoted 2 lines

Added a couple of extra sanity checks. See updated incremental patch below.

Thank you very much. The additional checks look good to me.

Reinette

author maintainer
#252 lore raw

Re: [PATCH v12 7/8] x86/resctrl: Sub NUMA Cluster detection and enable

Quoted 31 lines · Reinette Chatre

Hi Tony,

Quoted 1 line · Tony Luck

On Thu, Nov 30, 2023 at 01:47:10PM -0800, Reinette Chatre wrote:

...

Quoted 10 lines
Quoted 7 lines

Review

Quoted 2 lines
(quoted diff) +0 -0
 	if (!x86_match_cpu(snc_cpu_ids))
 		return 1;

I understand and welcome this change as motivated by robustness. Apart from that, with this being a model specific feature for this particular group of systems, it it not clear to me in which scenarios this could run on a system where a present CPU does not have access to L3 cache.

Agreed that on these systems there should always be an L3 cache. Should I drop the check for "-1"?

Please do keep it. I welcome the additional robustness. The static checker I tried did not complain about this but I expect that it is something that could trigger checks.

Quoted 9 lines
Quoted 8 lines

Review

Quoted 4 lines
(quoted diff) +1 -1
-	node_caches = bitmap_zalloc(nr_node_ids, GFP_KERNEL);
+	node_caches = bitmap_zalloc(num_online_cpus(), GFP_KERNEL);

Please do take care to take new bitmap size into account in all places. From what I can tell there is a later bitmap_weight() call that still uses nr_node_ids as size.

Quoted 7 lines
Quoted 3 lines

Oops. I was also using num_online_cpus() before cpus_read_lock(), so things could theoretically change before the bitmap_weight() call. I switched to using num_present_cpus() in both places.

Thanks for catching this. I am not sure if num_present_cpus() is the right choice. I found its comment to say "If HOTPLUG is enabled, then cpu_present_mask varies dynamically ...". num_possible_cpus() seems more appropriate when looking

I can size the bitmask based on num_possible_cpus().

Quoted 6 lines

for something that does not change while not holding the hotplug lock. Reading its description more closely also makes me wonder if the later

	num_online_cpus() != num_present_cpus()
should also maybe be 
	num_online_cpus() != num_possible_cpus() ?

It seems to more closely match the intention.

This seems problematic. On a system that does support physical CPU hotplug num_possible_cpus() may be some very large number. Reserving space for CPUs that can be added later. None of those CPUs can be online (obviously!). So this test would fail on such a system.

Quoted 25 lines
Quoted 25 lines
Quoted 24 lines
Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +0 -3
 	if (!node_caches)
 		return 1;
@@ -1072,10 +1073,13 @@ static __init int snc_get_config(void)
 
 	for_each_node(node) {
 		cpu = cpumask_first(cpumask_of_node(node));
-		if (cpu < nr_cpu_ids)
-			set_bit(get_cpu_cacheinfo_id(cpu, 3), node_caches);
-		else

arch/x86/kernel/cpu/resctrl/core.c static __init int snc_get_config(void) · line 1085

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +6 -0
+		if (cpu < nr_cpu_ids) {
+			cache_id = get_cpu_cacheinfo_id(cpu, 3);
+			if (cache_id != -1)
+				set_bit(cache_id, node_caches);
+		} else {
 			mem_only_nodes++;
+		}
 	}
 	cpus_read_unlock();
 

Could this code be made even more robust by checking the computed snc_nodes_per_l3_cache against the limited actually possible values? Forcing it to 1 if something went wrong?

Quoted 6 lines
Quoted 2 lines

Added a couple of extra sanity checks. See updated incremental patch below.

Thank you very much. The additional checks look good to me.

Reinette

Thanks for looking at this. I'm applying changes to my local tree. I'll give folks a little more time to find additonal issues in v12 and post v13 next week.

-Tony

maintainer
#253 lore raw

Re: [PATCH v12 7/8] x86/resctrl: Sub NUMA Cluster detection and enable

Hi Tony,

Quoted 13 lines · Tony Luck
Quoted 11 lines · Reinette Chatre

Hi Tony,

Quoted 1 line · Tony Luck

On Thu, Nov 30, 2023 at 01:47:10PM -0800, Reinette Chatre wrote:

for something that does not change while not holding the hotplug lock. Reading its description more closely also makes me wonder if the later

	num_online_cpus() != num_present_cpus()
should also maybe be 
	num_online_cpus() != num_possible_cpus() ?

It seems to more closely match the intention.

Quoted 4 lines

This seems problematic. On a system that does support physical CPU hotplug num_possible_cpus() may be some very large number. Reserving space for CPUs that can be added later. None of those CPUs can be online (obviously!). So this test would fail on such a system.

Thank you for clarifying. It was not obvious to me how these bitmaps are different with physical hotplug.

Reinette

author maintainer
#254 lore raw

PATCH v12 8/8 x86/resctrl: Update documentation with Sub-NUMA cluster changes

In reply to Tony Luck

With Sub-NUMA Cluster mode enabled the scope of monitoring resources is per-NODE instead of per-L3 cache. Suffixes of directories with "L3" in their name refer to Sub-NUMA nodes instead of L3 cache ids.

Users should be aware that SNC mode also affects the amount of L3 cache available for allocation within each SNC node.

---
 Documentation/arch/x86/resctrl.rst | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)
Documentation/arch/x86/resctrl.rst +21 -4
index a6279df64a9d..49ff789db1d8 100644
@@ -366,10 +366,10 @@ When control is enabled all CTRL_MON groups will also contain:
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
-	This contains a set of files organized by L3 domain and by
-	RDT event. E.g. on a system with two L3 domains there will
-	be subdirectories "mon_L3_00" and "mon_L3_01".	Each of these
-	directories have one file per event (e.g. "llc_occupancy",
+	This contains a set of files organized by L3 domain or by NUMA
+	node (depending on whether Sub-NUMA Cluster (SNC) mode is disabled
+	or enabled respectively) and by RDT event.  Each of these
+	directories has one file per event (e.g. "llc_occupancy",
 	"mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
 	files provide a read out of the current value of the event for
 	all tasks in the group. In CTRL_MON groups these files provide
@@ -478,6 +478,23 @@ if non-contiguous 1s value is supported. On a system with a 20-bit mask
 each bit represents 5% of the capacity of the cache. You could partition
 the cache into four equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
 
+Notes on Sub-NUMA Cluster mode
+==============================
+When SNC mode is enabled Linux may load balance tasks between Sub-NUMA
+nodes much more readily than between regular NUMA nodes since the CPUs
+on Sub-NUMA nodes share the same L3 cache and the system may report
+the NUMA distance between Sub-NUMA nodes with a lower value than used
+for regular NUMA nodes.  Users who do not bind tasks to the CPUs of a
+specific Sub-NUMA node must read the "llc_occupancy", "mbm_total_bytes",
+and "mbm_local_bytes" for all Sub-NUMA nodes where the tasks may execute
+to get the full view of traffic for which the tasks were the source.
+
+The cache allocation feature still provides the same number of
+bits in a mask to control allocation into the L3 cache, but each
+of those ways has its capacity reduced because the cache is divided
+between the SNC nodes. The values reported in the resctrl
+"size" files are adjusted accordingly.
+
 Memory bandwidth Allocation and monitoring
 ==========================================
 
Signature · 1 line
2.41.0
reviewer
#255 lore raw

Re: [PATCH v12 8/8] x86/resctrl: Update documentation with Sub-NUMA cluster changes

Quoted 36 lines · Tony Luck

With Sub-NUMA Cluster mode enabled the scope of monitoring resources is per-NODE instead of per-L3 cache. Suffixes of directories with "L3" in their name refer to Sub-NUMA nodes instead of L3 cache ids.

Users should be aware that SNC mode also affects the amount of L3 cache available for allocation within each SNC node.

---
 Documentation/arch/x86/resctrl.rst | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)
Documentation/arch/x86/resctrl.rst +4 -4
index a6279df64a9d..49ff789db1d8 100644
@@ -366,10 +366,10 @@ When control is enabled all CTRL_MON groups will also contain:
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
-	This contains a set of files organized by L3 domain and by
-	RDT event. E.g. on a system with two L3 domains there will
-	be subdirectories "mon_L3_00" and "mon_L3_01".	Each of these
-	directories have one file per event (e.g. "llc_occupancy",
+	This contains a set of files organized by L3 domain or by NUMA
+	node (depending on whether Sub-NUMA Cluster (SNC) mode is disabled
+	or enabled respectively) and by RDT event.  Each of these
+	directories has one file per event (e.g. "llc_occupancy",
 	"mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
 	files provide a read out of the current value of the event for
 	all tasks in the group. In CTRL_MON groups these files provide

Documentation/arch/x86/resctrl.rst if non-contiguous 1s value is supported. On a system with a 20-bit mask · line 483

Quoted 6 lines
Documentation/arch/x86/resctrl.rst +3 -0
@@ -478,6 +478,23 @@ if non-contiguous 1s value is supported. On a system with a 20-bit mask
 each bit represents 5% of the capacity of the cache. You could partition
 the cache into four equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
 
+Notes on Sub-NUMA Cluster mode
+==============================
+When SNC mode is enabled Linux may load balance tasks between Sub-NUMA

enabled, Linux

Thanks
Babu

Quoted 17 lines
Documentation/arch/x86/resctrl.rst +14 -0
+nodes much more readily than between regular NUMA nodes since the CPUs
+on Sub-NUMA nodes share the same L3 cache and the system may report
+the NUMA distance between Sub-NUMA nodes with a lower value than used
+for regular NUMA nodes.  Users who do not bind tasks to the CPUs of a
+specific Sub-NUMA node must read the "llc_occupancy", "mbm_total_bytes",
+and "mbm_local_bytes" for all Sub-NUMA nodes where the tasks may execute
+to get the full view of traffic for which the tasks were the source.
+
+The cache allocation feature still provides the same number of
+bits in a mask to control allocation into the L3 cache, but each
+of those ways has its capacity reduced because the cache is divided
+between the SNC nodes. The values reported in the resctrl
+"size" files are adjusted accordingly.
+
 Memory bandwidth Allocation and monitoring
 ==========================================
 
Signature · 2 lines
Thanks
Babu Moger
author maintainer
#256 lore raw

RE: [PATCH v12 8/8] x86/resctrl: Update documentation with Sub-NUMA cluster changes

Quoted 5 lines

Documentation/arch/x86/resctrl.rst if non-contiguous 1s value is supported. On a system with a 20-bit mask · line 483

Quoted 3 lines
Documentation/arch/x86/resctrl.rst +3 -0
+Notes on Sub-NUMA Cluster mode
+==============================
+When SNC mode is enabled Linux may load balance tasks between Sub-NUMA

enabled, Linux

Babu,

Thanks. I've added that "," ready for next version.

-Tony

author maintainer
#257 lore raw

v13 cover Add support for Sub-NUMA cluster (SNC) systems

In reply to Tony Luck

The Sub-NUMA cluster feature on some Intel processors partitions the CPUs that share an L3 cache into two or more sets. This plays havoc with the Resource Director Technology (RDT) monitoring features. Prior to this patch Intel has advised that SNC and RDT are incompatible.

Some of these CPU support an MSR that can partition the RMID counters in the same way. This allows monitoring features to be used. With the caveat that users must be aware that Linux may migrate tasks more frequently between SNC nodes than between "regular" NUMA nodes, so reading counters from all SNC nodes may be needed to get a complete picture of activity for tasks.

Cache and memory bandwidth allocation features continue to operate at the scope of the L3 cache.

Changes since v12:

All:
Reinette - put commit tags in right order for TIP (Tested-by before Reviewed-by)

Patch 7:
Fam Zheng - Check for -1 return from get_cpu_cacheinfo_id() and increase size of bitmap tracking # of L3 instances. Reinette - Add extra sanity checks. Note that this patch has some additional tweaks beyond the e-mail discussion.
1) "3" is a valid return in addition to 1, 2, 4
2) Added a warning if the sanity checks fail that prints number of CPU nodes and number of L3 cache instances that were found.

Patch 8:
Babu - Fix grammar with an additional comma.

Tony Luck (8):
x86/resctrl: Prepare for new domain scope x86/resctrl: Prepare to split rdt_domain structure x86/resctrl: Prepare for different scope for control/monitor
operations
x86/resctrl: Split the rdt_domain and rdt_hw_domain structures x86/resctrl: Add node-scope to the options for feature scope x86/resctrl: Introduce snc_nodes_per_l3_cache x86/resctrl: Sub NUMA Cluster detection and enable x86/resctrl: Update documentation with Sub-NUMA cluster changes

 Documentation/arch/x86/resctrl.rst        |  25 +-
 include/linux/resctrl.h                   |  85 +++--
 arch/x86/include/asm/msr-index.h          |   1 +
 arch/x86/kernel/cpu/resctrl/internal.h    |  66 ++--
 arch/x86/kernel/cpu/resctrl/core.c        | 433 +++++++++++++++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  58 +--
 arch/x86/kernel/cpu/resctrl/monitor.c     |  68 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  26 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 149 ++++----
 9 files changed, 629 insertions(+), 282 deletions(-)

base-commit: 2cc14f52aeb78ce3f29677c2de1f06c0e91471ab

Signature · 1 line
2.41.0
author maintainer
#258 lore raw

PATCH v13 1/8 x86/resctrl: Prepare for new domain scope

Resctrl resources operate on subsets of CPUs in the system with the defining attribute of each subset being an instance of a particular level of cache. E.g. all CPUs sharing an L3 cache would be part of the same domain.

In preparation for features that are scoped at the NUMA node level change the code from explicit references to "cache_level" to a more generic scope. At this point the only options for this scope are groups of CPUs that share an L2 cache or L3 cache.

Clean up the error handling when looking up domains. Report invalid id's before calling rdt_find_domain() in preparation for better messages when scope can be other than cache scope. This means that rdt_find_domain() will never return an error. So remove checks for error from the callsites.

---
 include/linux/resctrl.h                   |  9 ++++-
 arch/x86/kernel/cpu/resctrl/core.c        | 45 ++++++++++++++++-------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  2 +-
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  6 ++-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  5 ++-
 5 files changed, 48 insertions(+), 19 deletions(-)
include/linux/resctrl.h +7 -2
index 66942d7fba7f..7d4eb7df611d 100644
@@ -144,13 +144,18 @@ struct resctrl_membw {
 struct rdt_parse_data;
 struct resctrl_schema;
 
+enum resctrl_scope {
+	RESCTRL_L2_CACHE = 2,
+	RESCTRL_L3_CACHE = 3,
+};
+
 /**
  * struct rdt_resource - attributes of a resctrl resource
  * @rid:		The index of the resource
  * @alloc_capable:	Is allocation available on this machine
  * @mon_capable:	Is monitor feature available on this machine
  * @num_rmid:		Number of RMIDs available
- * @cache_level:	Which cache level defines scope of this resource
+ * @scope:		Scope of this resource
  * @cache:		Cache allocation related data
  * @membw:		If the component has bandwidth controls, their properties.
  * @domains:		All domains for this resource
@@ -168,7 +173,7 @@ struct rdt_resource {
 	bool			alloc_capable;
 	bool			mon_capable;
 	int			num_rmid;
-	int			cache_level;
+	enum resctrl_scope	scope;
 	struct resctrl_cache	cache;
 	struct resctrl_membw	membw;
 	struct list_head	domains;
arch/x86/kernel/cpu/resctrl/core.c +31 -14

105 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +1 -1
index beccb0e87ba7..3f8891d57fac 100644
@@ -563,7 +563,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 	r = &rdt_resources_all[resid].r_resctrl;
 	d = rdt_find_domain(r, domid, NULL);
-	if (IS_ERR_OR_NULL(d)) {
+	if (!d) {
 		ret = -ENOENT;
 		goto out;
 	}
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +5 -1
index 8f559eeae08e..2a682da9f43a 100644
@@ -292,10 +292,14 @@ 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;
 	struct cpu_cacheinfo *ci;
 	int ret;
 	int i;
 
+	if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
+		return -ENODEV;
+
 	/* Pick the first cpu we find that is associated with the cache. */
 	plr->cpu = cpumask_first(&plr->d->cpu_mask);
 
@@ -311,7 +315,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
 
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == plr->s->res->cache_level) {
+		if (ci->info_list[i].level == scope) {
 			plr->line_size = ci->info_list[i].coherency_line_size;
 			return 0;
 		}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +4 -1
index 69a1de92384a..c44be64d65ec 100644
@@ -1413,10 +1413,13 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 	unsigned int size = 0;
 	int num_b, i;
 
+	if (WARN_ON_ONCE(r->scope != RESCTRL_L2_CACHE && r->scope != RESCTRL_L3_CACHE))
+		return size;
+
 	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
 	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == r->cache_level) {
+		if (ci->info_list[i].level == r->scope) {
 			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
 			break;
 		}
Signature · 1 line
2.41.0
Reviewed-by Babu Moger on v13 1/8
#259 lore raw

Re: [PATCH v13 1/8] x86/resctrl: Prepare for new domain scope

Quoted 15 lines · Tony Luck

Resctrl resources operate on subsets of CPUs in the system with the defining attribute of each subset being an instance of a particular level of cache. E.g. all CPUs sharing an L3 cache would be part of the same domain.

In preparation for features that are scoped at the NUMA node level change the code from explicit references to "cache_level" to a more generic scope. At this point the only options for this scope are groups of CPUs that share an L2 cache or L3 cache.

Clean up the error handling when looking up domains. Report invalid id's before calling rdt_find_domain() in preparation for better messages when scope can be other than cache scope. This means that rdt_find_domain() will never return an error. So remove checks for error from the callsites.

Quoted 4 lines
Quoted 218 lines
---
  include/linux/resctrl.h                   |  9 ++++-
  arch/x86/kernel/cpu/resctrl/core.c        | 45 ++++++++++++++++-------
  arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  2 +-
  arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  6 ++-
  arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  5 ++-
  5 files changed, 48 insertions(+), 19 deletions(-)
include/linux/resctrl.h +7 -2
index 66942d7fba7f..7d4eb7df611d 100644
@@ -144,13 +144,18 @@ struct resctrl_membw {
  struct rdt_parse_data;
  struct resctrl_schema;
 
+enum resctrl_scope {
+	RESCTRL_L2_CACHE = 2,
+	RESCTRL_L3_CACHE = 3,
+};
+
  /**
   * struct rdt_resource - attributes of a resctrl resource
   * @rid:		The index of the resource
   * @alloc_capable:	Is allocation available on this machine
   * @mon_capable:	Is monitor feature available on this machine
   * @num_rmid:		Number of RMIDs available
- * @cache_level:	Which cache level defines scope of this resource
+ * @scope:		Scope of this resource
   * @cache:		Cache allocation related data
   * @membw:		If the component has bandwidth controls, their properties.
   * @domains:		All domains for this resource
@@ -168,7 +173,7 @@ struct rdt_resource {
  	bool			alloc_capable;
  	bool			mon_capable;
  	int			num_rmid;
-	int			cache_level;
+	enum resctrl_scope	scope;
  	struct resctrl_cache	cache;
  	struct resctrl_membw	membw;
  	struct list_head	domains;
arch/x86/kernel/cpu/resctrl/core.c +31 -14
index 19e0681f0435..fd113bc29d4e 100644
@@ -65,7 +65,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
  		.r_resctrl = {
  			.rid			= RDT_RESOURCE_L3,
  			.name			= "L3",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
  			.domains		= domain_init(RDT_RESOURCE_L3),
  			.parse_ctrlval		= parse_cbm,
  			.format_str		= "%d=%0*x",
@@ -79,7 +79,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
  		.r_resctrl = {
  			.rid			= RDT_RESOURCE_L2,
  			.name			= "L2",
-			.cache_level		= 2,
+			.scope			= RESCTRL_L2_CACHE,
  			.domains		= domain_init(RDT_RESOURCE_L2),
  			.parse_ctrlval		= parse_cbm,
  			.format_str		= "%d=%0*x",
@@ -93,7 +93,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
  		.r_resctrl = {
  			.rid			= RDT_RESOURCE_MBA,
  			.name			= "MB",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
  			.domains		= domain_init(RDT_RESOURCE_MBA),
  			.parse_ctrlval		= parse_bw,
  			.format_str		= "%d=%*u",
@@ -105,7 +105,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
  		.r_resctrl = {
  			.rid			= RDT_RESOURCE_SMBA,
  			.name			= "SMBA",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
  			.domains		= domain_init(RDT_RESOURCE_SMBA),
  			.parse_ctrlval		= parse_bw,
  			.format_str		= "%d=%*u",
@@ -401,9 +401,6 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
  	struct rdt_domain *d;
  	struct list_head *l;
 
-	if (id < 0)
-		return ERR_PTR(-ENODEV);
-
  	list_for_each(l, &r->domains) {
  		d = list_entry(l, struct rdt_domain, list);
  		/* When id is found, return its domain. */
@@ -491,6 +488,19 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
  	return 0;
  }
 
+static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
+{
+	switch (scope) {
+	case RESCTRL_L2_CACHE:
+	case RESCTRL_L3_CACHE:
+		return get_cpu_cacheinfo_id(cpu, scope);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
  /*
   * domain_add_cpu - Add a cpu to a resource's domain list.
   *
@@ -506,18 +516,19 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
   */
  static void domain_add_cpu(int cpu, struct rdt_resource *r)
  {
-	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+	int id = get_domain_id_from_scope(cpu, r->scope);
  	struct list_head *add_pos = NULL;
  	struct rdt_hw_domain *hw_dom;
  	struct rdt_domain *d;
  	int err;
 
-	d = rdt_find_domain(r, id, &add_pos);
-	if (IS_ERR(d)) {
-		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
+	if (id < 0) {
+		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->scope, r->name);
  		return;
  	}
 
+	d = rdt_find_domain(r, id, &add_pos);
  	if (d) {
  		cpumask_set_cpu(cpu, &d->cpu_mask);
  		if (r->cache.arch_has_per_cpu_cfg)
@@ -556,13 +567,19 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
  static void domain_remove_cpu(int cpu, struct rdt_resource *r)
  {
-	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+	int id = get_domain_id_from_scope(cpu, r->scope);
  	struct rdt_hw_domain *hw_dom;
  	struct rdt_domain *d;
 
+	if (id < 0) {
+		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->scope, r->name);
+		return;
+	}
+
  	d = rdt_find_domain(r, id, NULL);
-	if (IS_ERR_OR_NULL(d)) {
-		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
+	if (!d) {
+		pr_warn("Couldn't find domain with id=%d for CPU %d\n", id, cpu);
  		return;
  	}
  	hw_dom = resctrl_to_arch_dom(d);
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +1 -1
index beccb0e87ba7..3f8891d57fac 100644
@@ -563,7 +563,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
  	r = &rdt_resources_all[resid].r_resctrl;
  	d = rdt_find_domain(r, domid, NULL);
-	if (IS_ERR_OR_NULL(d)) {
+	if (!d) {
  		ret = -ENOENT;
  		goto out;
  	}
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +5 -1
index 8f559eeae08e..2a682da9f43a 100644
@@ -292,10 +292,14 @@ 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;
  	struct cpu_cacheinfo *ci;
  	int ret;
  	int i;
 
+	if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
+		return -ENODEV;
+
  	/* Pick the first cpu we find that is associated with the cache. */
  	plr->cpu = cpumask_first(&plr->d->cpu_mask);
 
@@ -311,7 +315,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
  	plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
 
  	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == plr->s->res->cache_level) {
+		if (ci->info_list[i].level == scope) {
  			plr->line_size = ci->info_list[i].coherency_line_size;
  			return 0;
  		}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +4 -1
index 69a1de92384a..c44be64d65ec 100644
@@ -1413,10 +1413,13 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
  	unsigned int size = 0;
  	int num_b, i;
 
+	if (WARN_ON_ONCE(r->scope != RESCTRL_L2_CACHE && r->scope != RESCTRL_L3_CACHE))
+		return size;
+
  	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
  	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
  	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == r->cache_level) {
+		if (ci->info_list[i].level == r->scope) {
  			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
  			break;
  		}
author maintainer
#260 lore raw

PATCH v13 2/8 x86/resctrl: Prepare to split rdt_domain structure

In reply to Tony Luck

The rdt_domain structure is used for both control and monitor features. It is about to be split into separate structures for these two usages because the scope for control and monitoring features for a resource will be different for future resources.

To allow for common code that scans a list of domains looking for a specific domain id, move all the common fields ("list", "id", "cpu_mask") into their own structure within the rdt_domain structure.

---
 include/linux/resctrl.h                   | 16 ++++--
 arch/x86/kernel/cpu/resctrl/core.c        | 26 +++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 22 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 10 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 14 +++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 60 +++++++++++------------
 6 files changed, 78 insertions(+), 70 deletions(-)
include/linux/resctrl.h +12 -4
index 7d4eb7df611d..c4067150a6b7 100644
@@ -53,10 +53,20 @@ struct resctrl_staged_config {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * struct rdt_domain_hdr - common header for different domain types
  * @list:		all instances of this resource
  * @id:			unique id for this instance
  * @cpu_mask:		which CPUs share this resource
+ */
+struct rdt_domain_hdr {
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+};
+
+/**
+ * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * @hdr:		common header for different domain types
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
  * @mbm_local:		saved state for MBM local bandwidth
@@ -71,9 +81,7 @@ struct resctrl_staged_config {
  *			by closid
  */
 struct rdt_domain {
-	struct list_head		list;
-	int				id;
-	struct cpumask			cpu_mask;
+	struct rdt_domain_hdr		hdr;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;
arch/x86/kernel/cpu/resctrl/core.c +13 -13
index fd113bc29d4e..62a989fd950d 100644
@@ -356,9 +356,9 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
 {
 	struct rdt_domain *d;
 
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->cpu_mask))
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
 			return d;
 	}
 
@@ -402,12 +402,12 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	struct list_head *l;
 
 	list_for_each(l, &r->domains) {
-		d = list_entry(l, struct rdt_domain, list);
+		d = list_entry(l, struct rdt_domain, hdr.list);
 		/* When id is found, return its domain. */
-		if (id == d->id)
+		if (id == d->hdr.id)
 			return d;
 		/* Stop searching when finding id's position in sorted list. */
-		if (id < d->id)
+		if (id < d->hdr.id)
 			break;
 	}
 
@@ -530,7 +530,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 	d = rdt_find_domain(r, id, &add_pos);
 	if (d) {
-		cpumask_set_cpu(cpu, &d->cpu_mask);
+		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 		if (r->cache.arch_has_per_cpu_cfg)
 			rdt_domain_reconfigure_cdp(r);
 		return;
@@ -541,8 +541,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 
 	d = &hw_dom->d_resctrl;
-	d->id = id;
-	cpumask_set_cpu(cpu, &d->cpu_mask);
+	d->hdr.id = id;
+	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	rdt_domain_reconfigure_cdp(r);
 
@@ -556,11 +556,11 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	list_add_tail(&d->list, add_pos);
+	list_add_tail(&d->hdr.list, add_pos);
 
 	err = resctrl_online_domain(r, d);
 	if (err) {
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 		domain_free(hw_dom);
 	}
 }
@@ -584,10 +584,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 	}
 	hw_dom = resctrl_to_arch_dom(d);
 
-	cpumask_clear_cpu(cpu, &d->cpu_mask);
-	if (cpumask_empty(&d->cpu_mask)) {
+	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
+	if (cpumask_empty(&d->hdr.cpu_mask)) {
 		resctrl_offline_domain(r, d);
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 
 		/*
 		 * rdt_domain "d" is going to be freed below, so clear
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +11 -11
index 3f8891d57fac..23f8258d36a8 100644
@@ -67,7 +67,7 @@ int parse_bw(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;
 	}
 
@@ -146,7 +146,7 @@ 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;
 	}
 
@@ -226,8 +226,8 @@ static int parse_line(char *line, struct resctrl_schema *s,
 		return -EINVAL;
 	}
 	dom = strim(dom);
-	list_for_each_entry(d, &r->domains, list) {
-		if (d->id == dom_id) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
 			data.buf = dom;
 			data.rdtgrp = rdtgrp;
 			if (r->parse_ctrlval(&data, s, d))
@@ -274,7 +274,7 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
 	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);
+		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
 		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
 
 		return true;
@@ -291,7 +291,7 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 		return -ENOMEM;
 
 	msr_param.res = NULL;
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		hw_dom = resctrl_to_arch_dom(d);
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	u32 ctrl_val;
 
 	seq_printf(s, "%*s:", max_name_width, schema->name);
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
 		if (sep)
 			seq_puts(s, ";");
 
@@ -476,7 +476,7 @@ 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 +505,7 @@ 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 {
@@ -536,7 +536,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	rr->val = 0;
 	rr->first = first;
 
-	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	smp_call_function_any(&d->hdr.cpu_mask, mon_event_count, rr, 1);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
arch/x86/kernel/cpu/resctrl/monitor.c +5 -5
index f136ac046851..dd0ea1bc0092 100644
@@ -238,7 +238,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	u64 msr_val, chunks;
 	int ret;
 
-	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+	if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask))
 		return -EINVAL;
 
 	ret = __rmid_read(rmid, eventid, &msr_val);
@@ -340,8 +340,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
 	entry->busy = 0;
 	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, list) {
-		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
 			err = resctrl_arch_rmid_read(r, d, entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
 						     &val);
@@ -661,7 +661,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
 	dom->cqm_work_cpu = cpu;
 
 	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
@@ -708,7 +708,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
 
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		return;
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
 	dom->mbm_work_cpu = cpu;
 	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
 }
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +7 -7
index 2a682da9f43a..fcbd99e2eb66 100644
@@ -221,7 +221,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
 	int cpu;
 	int ret;
 
-	for_each_cpu(cpu, &plr->d->cpu_mask) {
+	for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
 		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
 		if (!pm_req) {
 			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
@@ -301,7 +301,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 		return -ENODEV;
 
 	/* Pick the first cpu we find that is associated with the cache. */
-	plr->cpu = cpumask_first(&plr->d->cpu_mask);
+	plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 
 	if (!cpu_online(plr->cpu)) {
 		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
@@ -856,10 +856,10 @@ 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, list) {
+		list_for_each_entry(d_i, &r->domains, hdr.list) {
 			if (d_i->plr)
 				cpumask_or(cpu_with_psl, cpu_with_psl,
-					   &d_i->cpu_mask);
+					   &d_i->hdr.cpu_mask);
 		}
 	}
 
@@ -867,7 +867,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	 * Next test if new pseudo-locked region would intersect with
 	 * existing region.
 	 */
-	if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+	if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
 		ret = true;
 
 	free_cpumask_var(cpu_with_psl);
@@ -1199,7 +1199,7 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 	}
 
 	plr->thread_done = 0;
-	cpu = cpumask_first(&plr->d->cpu_mask);
+	cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 	if (!cpu_online(cpu)) {
 		ret = -ENODEV;
 		goto out;
@@ -1529,7 +1529,7 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
 	 * may be scheduled elsewhere and invalidate entries in the
 	 * pseudo-locked region.
 	 */
-	if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) {
+	if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
 		mutex_unlock(&rdtgroup_mutex);
 		return -EINVAL;
 	}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +30 -30

220 lines not on this page · raw message

Signature · 1 line
2.41.0
Reviewed-by Babu Moger on v13 2/8
#261 lore raw

Re: [PATCH v13 2/8] x86/resctrl: Prepare to split rdt_domain structure

Quoted 5 lines · Tony Luck

The rdt_domain structure is used for both control and monitor features. It is about to be split into separate structures for these two usages because the scope for control and monitoring features for a resource will be different for future resources.

Quoted 8 lines

To allow for common code that scans a list of domains looking for a specific domain id, move all the common fields ("list", "id", "cpu_mask") into their own structure within the rdt_domain structure.

Quoted 575 lines
---
  include/linux/resctrl.h                   | 16 ++++--
  arch/x86/kernel/cpu/resctrl/core.c        | 26 +++++-----
  arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 22 ++++-----
  arch/x86/kernel/cpu/resctrl/monitor.c     | 10 ++--
  arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 14 +++---
  arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 60 +++++++++++------------
  6 files changed, 78 insertions(+), 70 deletions(-)
include/linux/resctrl.h +12 -4
index 7d4eb7df611d..c4067150a6b7 100644
@@ -53,10 +53,20 @@ struct resctrl_staged_config {
  };
 
  /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * struct rdt_domain_hdr - common header for different domain types
   * @list:		all instances of this resource
   * @id:			unique id for this instance
   * @cpu_mask:		which CPUs share this resource
+ */
+struct rdt_domain_hdr {
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+};
+
+/**
+ * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * @hdr:		common header for different domain types
   * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
   * @mbm_total:		saved state for MBM total bandwidth
   * @mbm_local:		saved state for MBM local bandwidth
@@ -71,9 +81,7 @@ struct resctrl_staged_config {
   *			by closid
   */
  struct rdt_domain {
-	struct list_head		list;
-	int				id;
-	struct cpumask			cpu_mask;
+	struct rdt_domain_hdr		hdr;
  	unsigned long			*rmid_busy_llc;
  	struct mbm_state		*mbm_total;
  	struct mbm_state		*mbm_local;
arch/x86/kernel/cpu/resctrl/core.c +13 -13
index fd113bc29d4e..62a989fd950d 100644
@@ -356,9 +356,9 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
  {
  	struct rdt_domain *d;
 
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
  		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->cpu_mask))
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
  			return d;
  	}
 
@@ -402,12 +402,12 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
  	struct list_head *l;
 
  	list_for_each(l, &r->domains) {
-		d = list_entry(l, struct rdt_domain, list);
+		d = list_entry(l, struct rdt_domain, hdr.list);
  		/* When id is found, return its domain. */
-		if (id == d->id)
+		if (id == d->hdr.id)
  			return d;
  		/* Stop searching when finding id's position in sorted list. */
-		if (id < d->id)
+		if (id < d->hdr.id)
  			break;
  	}
 
@@ -530,7 +530,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
  	d = rdt_find_domain(r, id, &add_pos);
  	if (d) {
-		cpumask_set_cpu(cpu, &d->cpu_mask);
+		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
  		if (r->cache.arch_has_per_cpu_cfg)
  			rdt_domain_reconfigure_cdp(r);
  		return;
@@ -541,8 +541,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
  		return;
 
  	d = &hw_dom->d_resctrl;
-	d->id = id;
-	cpumask_set_cpu(cpu, &d->cpu_mask);
+	d->hdr.id = id;
+	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
  	rdt_domain_reconfigure_cdp(r);
 
@@ -556,11 +556,11 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
  		return;
  	}
 
-	list_add_tail(&d->list, add_pos);
+	list_add_tail(&d->hdr.list, add_pos);
 
  	err = resctrl_online_domain(r, d);
  	if (err) {
-		list_del(&d->list);
+		list_del(&d->hdr.list);
  		domain_free(hw_dom);
  	}
  }
@@ -584,10 +584,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
  	}
  	hw_dom = resctrl_to_arch_dom(d);
 
-	cpumask_clear_cpu(cpu, &d->cpu_mask);
-	if (cpumask_empty(&d->cpu_mask)) {
+	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
+	if (cpumask_empty(&d->hdr.cpu_mask)) {
  		resctrl_offline_domain(r, d);
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 
  		/*
  		 * rdt_domain "d" is going to be freed below, so clear
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +11 -11
index 3f8891d57fac..23f8258d36a8 100644
@@ -67,7 +67,7 @@ int parse_bw(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;
  	}
 
@@ -146,7 +146,7 @@ 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;
  	}
 
@@ -226,8 +226,8 @@ static int parse_line(char *line, struct resctrl_schema *s,
  		return -EINVAL;
  	}
  	dom = strim(dom);
-	list_for_each_entry(d, &r->domains, list) {
-		if (d->id == dom_id) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
  			data.buf = dom;
  			data.rdtgrp = rdtgrp;
  			if (r->parse_ctrlval(&data, s, d))
@@ -274,7 +274,7 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
  	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);
+		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
  		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
 
  		return true;
@@ -291,7 +291,7 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
  		return -ENOMEM;
 
  	msr_param.res = NULL;
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
  		hw_dom = resctrl_to_arch_dom(d);
  		for (t = 0; t < CDP_NUM_TYPES; t++) {
  			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
  	u32 ctrl_val;
 
  	seq_printf(s, "%*s:", max_name_width, schema->name);
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
  		if (sep)
  			seq_puts(s, ";");
 
@@ -476,7 +476,7 @@ 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 +505,7 @@ 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 {
@@ -536,7 +536,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
  	rr->val = 0;
  	rr->first = first;
 
-	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	smp_call_function_any(&d->hdr.cpu_mask, mon_event_count, rr, 1);
  }
 
  int rdtgroup_mondata_show(struct seq_file *m, void *arg)
arch/x86/kernel/cpu/resctrl/monitor.c +5 -5
index f136ac046851..dd0ea1bc0092 100644
@@ -238,7 +238,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  	u64 msr_val, chunks;
  	int ret;
 
-	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+	if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask))
  		return -EINVAL;
 
  	ret = __rmid_read(rmid, eventid, &msr_val);
@@ -340,8 +340,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
  	entry->busy = 0;
  	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, list) {
-		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
  			err = resctrl_arch_rmid_read(r, d, entry->rmid,
  						     QOS_L3_OCCUP_EVENT_ID,
  						     &val);
@@ -661,7 +661,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
  	unsigned long delay = msecs_to_jiffies(delay_ms);
  	int cpu;
 
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
  	dom->cqm_work_cpu = cpu;
 
  	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
@@ -708,7 +708,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
 
  	if (!static_branch_likely(&rdt_mon_enable_key))
  		return;
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
  	dom->mbm_work_cpu = cpu;
  	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
  }
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +7 -7
index 2a682da9f43a..fcbd99e2eb66 100644
@@ -221,7 +221,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
  	int cpu;
  	int ret;
 
-	for_each_cpu(cpu, &plr->d->cpu_mask) {
+	for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
  		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
  		if (!pm_req) {
  			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
@@ -301,7 +301,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
  		return -ENODEV;
 
  	/* Pick the first cpu we find that is associated with the cache. */
-	plr->cpu = cpumask_first(&plr->d->cpu_mask);
+	plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 
  	if (!cpu_online(plr->cpu)) {
  		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
@@ -856,10 +856,10 @@ 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, list) {
+		list_for_each_entry(d_i, &r->domains, hdr.list) {
  			if (d_i->plr)
  				cpumask_or(cpu_with_psl, cpu_with_psl,
-					   &d_i->cpu_mask);
+					   &d_i->hdr.cpu_mask);
  		}
  	}
 
@@ -867,7 +867,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
  	 * Next test if new pseudo-locked region would intersect with
  	 * existing region.
  	 */
-	if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+	if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
  		ret = true;
 
  	free_cpumask_var(cpu_with_psl);
@@ -1199,7 +1199,7 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
  	}
 
  	plr->thread_done = 0;
-	cpu = cpumask_first(&plr->d->cpu_mask);
+	cpu = cpumask_first(&plr->d->hdr.cpu_mask);
  	if (!cpu_online(cpu)) {
  		ret = -ENODEV;
  		goto out;
@@ -1529,7 +1529,7 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
  	 * may be scheduled elsewhere and invalidate entries in the
  	 * pseudo-locked region.
  	 */
-	if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) {
+	if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
  		mutex_unlock(&rdtgroup_mutex);
  		return -EINVAL;
  	}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +30 -30
index c44be64d65ec..04d32602ac33 100644
@@ -91,7 +91,7 @@ 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, list)
+		list_for_each_entry(dom, &r->domains, hdr.list)
  			memset(dom->staged_config, 0, sizeof(dom->staged_config));
  	}
  }
@@ -295,7 +295,7 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
  				rdt_last_cmd_puts("Cache domain offline\n");
  				ret = -ENODEV;
  			} else {
-				mask = &rdtgrp->plr->d->cpu_mask;
+				mask = &rdtgrp->plr->d->hdr.cpu_mask;
  				seq_printf(s, is_cpu_list(of) ?
  					   "%*pbl\n" : "%*pb\n",
  					   cpumask_pr_args(mask));
@@ -984,12 +984,12 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 
  	mutex_lock(&rdtgroup_mutex);
  	hw_shareable = r->cache.shareable_bits;
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
  		if (sep)
  			seq_putc(seq, ';');
  		sw_shareable = 0;
  		exclusive = 0;
-		seq_printf(seq, "%d=", dom->id);
+		seq_printf(seq, "%d=", dom->hdr.id);
  		for (i = 0; i < closids_supported(); i++) {
  			if (!closid_allocated(i))
  				continue;
@@ -1302,7 +1302,7 @@ 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, list) {
+		list_for_each_entry(d, &r->domains, hdr.list) {
  			ctrl = resctrl_arch_get_config(r, d, closid,
  						       s->conf_type);
  			if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
@@ -1417,7 +1417,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
  		return size;
 
  	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
-	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
+	ci = get_cpu_cacheinfo(cpumask_any(&d->hdr.cpu_mask));
  	for (i = 0; i < ci->num_leaves; i++) {
  		if (ci->info_list[i].level == r->scope) {
  			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
@@ -1465,7 +1465,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
  			size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res,
  						    rdtgrp->plr->d,
  						    rdtgrp->plr->cbm);
-			seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+			seq_printf(s, "%d=%u\n", rdtgrp->plr->d->hdr.id, size);
  		}
  		goto out;
  	}
@@ -1477,7 +1477,7 @@ 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, list) {
+		list_for_each_entry(d, &r->domains, hdr.list) {
  			if (sep)
  				seq_putc(s, ';');
  			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
@@ -1495,7 +1495,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
  				else
  					size = rdtgroup_cbm_to_size(r, d, ctrl);
  			}
-			seq_printf(s, "%d=%u", d->id, size);
+			seq_printf(s, "%d=%u", d->hdr.id, size);
  			sep = true;
  		}
  		seq_putc(s, '\n');
@@ -1555,7 +1555,7 @@ static void mon_event_config_read(void *info)
 
  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);
+	smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_read, mon_info, 1);
  }
 
  static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
@@ -1566,7 +1566,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 
  	mutex_lock(&rdtgroup_mutex);
 
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
  		if (sep)
  			seq_puts(s, ";");
 
@@ -1574,7 +1574,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
  		mon_info.evtid = evtid;
  		mondata_config_read(dom, &mon_info);
 
-		seq_printf(s, "%d=0x%02x", dom->id, mon_info.mon_config);
+		seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config);
  		sep = true;
  	}
  	seq_puts(s, "\n");
@@ -1646,7 +1646,7 @@ static int mbm_config_write_domain(struct rdt_resource *r,
  	 * 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,
+	smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_write,
  			      &mon_info, 1);
 
  	/*
@@ -1689,8 +1689,8 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
  		return -EINVAL;
  	}
 
-	list_for_each_entry(d, &r->domains, list) {
-		if (d->id == dom_id) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
  			ret = mbm_config_write_domain(r, d, evtid, val);
  			if (ret)
  				return -EINVAL;
@@ -2232,14 +2232,14 @@ 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, list) {
+	list_for_each_entry(d, &r_l->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->cpu_mask)
+			for_each_cpu(cpu, &d->hdr.cpu_mask)
  				cpumask_set_cpu(cpu, cpu_mask);
  		else
  			/* Pick one CPU from each domain instance to update MSR */
-			cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+			cpumask_set_cpu(cpumask_any(&d->hdr.cpu_mask), cpu_mask);
  	}
 
  	/* Update QOS_CFG MSR on all the CPUs in cpu_mask */
@@ -2268,7 +2268,7 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
  static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d)
  {
  	u32 num_closid = resctrl_arch_get_num_closid(r);
-	int cpu = cpumask_any(&d->cpu_mask);
+	int cpu = cpumask_any(&d->hdr.cpu_mask);
  	int i;
 
  	d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
@@ -2317,7 +2317,7 @@ static int set_mba_sc(bool mba_sc)
 
  	r->membw.mba_sc = mba_sc;
 
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
  		for (i = 0; i < num_closid; i++)
  			d->mbps_val[i] = MBA_MAX_MBPS;
  	}
@@ -2653,7 +2653,7 @@ 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, list)
+		list_for_each_entry(dom, &r->domains, hdr.list)
  			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
  	}
 
@@ -2780,9 +2780,9 @@ static int reset_all_ctrls(struct rdt_resource *r)
  	 * CBMs in all domains to the maximum mask value. Pick one CPU
  	 * from each domain to update the MSRs below.
  	 */
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
  		hw_dom = resctrl_to_arch_dom(d);
-		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+		cpumask_set_cpu(cpumask_any(&d->hdr.cpu_mask), cpu_mask);
 
  		for (i = 0; i < hw_res->num_closid; i++)
  			hw_dom->ctrl_val[i] = r->default_ctrl;
@@ -2986,7 +2986,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
  	char name[32];
  	int ret;
 
-	sprintf(name, "mon_%s_%02d", r->name, d->id);
+	sprintf(name, "mon_%s_%02d", r->name, d->hdr.id);
  	/* create the directory */
  	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
  	if (IS_ERR(kn))
@@ -3002,7 +3002,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
  	}
 
  	priv.u.rid = r->rid;
-	priv.u.domid = d->id;
+	priv.u.domid = d->hdr.id;
  	list_for_each_entry(mevt, &r->evt_list, list) {
  		priv.u.evtid = mevt->evtid;
  		ret = mon_addfile(kn, mevt->name, priv.priv);
@@ -3050,7 +3050,7 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
  	struct rdt_domain *dom;
  	int ret;
 
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
  		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
  		if (ret)
  			return ret;
@@ -3209,7 +3209,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s,
  	 */
  	tmp_cbm = cfg->new_ctrl;
  	if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
-		rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->id);
+		rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->hdr.id);
  		return -ENOSPC;
  	}
  	cfg->have_new_ctrl = true;
@@ -3232,7 +3232,7 @@ 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, list) {
+	list_for_each_entry(d, &s->res->domains, hdr.list) {
  		ret = __init_one_rdt_domain(d, s, closid);
  		if (ret < 0)
  			return ret;
@@ -3247,7 +3247,7 @@ 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, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
  		if (is_mba_sc(r)) {
  			d->mbps_val[closid] = MBA_MAX_MBPS;
  			continue;
@@ -3864,7 +3864,7 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
  	 * per domain monitor data directories.
  	 */
  	if (static_branch_unlikely(&rdt_mon_enable_key))
-		rmdir_mondata_subdir_allrdtgrp(r, d->id);
+		rmdir_mondata_subdir_allrdtgrp(r, d->hdr.id);
 
  	if (is_mbm_enabled())
  		cancel_delayed_work(&d->mbm_over);
author maintainer
#262 lore raw

PATCH v13 3/8 x86/resctrl: Prepare for different scope for control/monitor operations

In reply to Tony Luck

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.

---
 include/linux/resctrl.h                   |  25 ++-
 arch/x86/kernel/cpu/resctrl/internal.h    |   6 +-
 arch/x86/kernel/cpu/resctrl/core.c        | 211 ++++++++++++++++------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  12 +-
 arch/x86/kernel/cpu/resctrl/monitor.c     |   4 +-
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |   4 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  55 +++---
 7 files changed, 220 insertions(+), 97 deletions(-)
include/linux/resctrl.h +19 -6
index c4067150a6b7..35e700edc6e6 100644
@@ -52,15 +52,22 @@ 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;
 };
 
@@ -163,10 +170,12 @@ 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:		All domains for this resource
+ * @ctrl_domains:	Control domains for this resource
+ * @mon_domains:	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.
@@ -181,10 +190,12 @@ 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;
@@ -230,8 +241,10 @@ 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);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
arch/x86/kernel/cpu/resctrl/internal.h +3 -3
index a4f1aa15f0a2..24bf9d7989a9 100644
@@ -520,8 +520,8 @@ 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,
@@ -540,7 +540,7 @@ 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);
 int closids_supported(void);
 void closid_free(int closid);
 int alloc_rmid(void);
arch/x86/kernel/cpu/resctrl/core.c +157 -54

338 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +7 -5
index 23f8258d36a8..0b4136c42762 100644
@@ -226,7 +226,7 @@ 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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 		return -ENOMEM;
 
 	msr_param.res = NULL;
-	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 (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	u32 ctrl_val;
 
 	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, ";");
 
@@ -542,6 +542,7 @@ 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;
@@ -562,11 +563,12 @@ 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/monitor.c +2 -2
index dd0ea1bc0092..ec5ad926c5dc 100644
@@ -340,7 +340,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
 	entry->busy = 0;
 	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
 		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
 			err = resctrl_arch_rmid_read(r, d, entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
@@ -535,7 +535,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	rmid = rgrp->mon.rmid;
 	pmbm_data = &dom_mbm->mbm_local[rmid];
 
-	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 +2 -2
index fcbd99e2eb66..ed6d59af1cef 100644
@@ -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 cpu_cacheinfo *ci;
 	int ret;
 	int i;
@@ -856,7 +856,7 @@ 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 +30 -25

170 lines not on this page · raw message

Signature · 1 line
2.41.0
Reviewed-by Babu Moger on v13 3/8
#263 lore raw

Re: [PATCH v13 3/8] x86/resctrl: Prepare for different scope for control/monitor operations

Quoted 15 lines · Tony Luck

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.

Quoted 4 lines
Quoted 738 lines
---
  include/linux/resctrl.h                   |  25 ++-
  arch/x86/kernel/cpu/resctrl/internal.h    |   6 +-
  arch/x86/kernel/cpu/resctrl/core.c        | 211 ++++++++++++++++------
  arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  12 +-
  arch/x86/kernel/cpu/resctrl/monitor.c     |   4 +-
  arch/x86/kernel/cpu/resctrl/pseudo_lock.c |   4 +-
  arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  55 +++---
  7 files changed, 220 insertions(+), 97 deletions(-)
include/linux/resctrl.h +19 -6
index c4067150a6b7..35e700edc6e6 100644
@@ -52,15 +52,22 @@ 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;
  };
 
@@ -163,10 +170,12 @@ 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:		All domains for this resource
+ * @ctrl_domains:	Control domains for this resource
+ * @mon_domains:	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.
@@ -181,10 +190,12 @@ 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;
@@ -230,8 +241,10 @@ 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);
 
  /**
   * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
arch/x86/kernel/cpu/resctrl/internal.h +3 -3
index a4f1aa15f0a2..24bf9d7989a9 100644
@@ -520,8 +520,8 @@ 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,
@@ -540,7 +540,7 @@ 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);
  int closids_supported(void);
  void closid_free(int closid);
  int alloc_rmid(void);
arch/x86/kernel/cpu/resctrl/core.c +8 -5
index 62a989fd950d..1fd85533b4ca 100644
@@ -57,7 +57,8 @@ static void
  mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
  	      struct rdt_resource *r);
 
-#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
+#define ctrl_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.ctrl_domains)
+#define mon_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.mon_domains)
 
  struct rdt_hw_resource rdt_resources_all[] = {
  	[RDT_RESOURCE_L3] =
@@ -65,8 +66,10 @@ struct rdt_hw_resource rdt_resources_all[] = {
  		.r_resctrl = {
  			.rid			= RDT_RESOURCE_L3,
  			.name			= "L3",
-			.scope			= RESCTRL_L3_CACHE,
-			.domains		= domain_init(RDT_RESOURCE_L3),
+			.ctrl_scope		= RESCTRL_L3_CACHE,
+			.mon_scope		= RESCTRL_L3_CACHE,
+			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L3),
+			.mon_domains		= mon_domain_init(RDT_RESOURCE_L3),
  			.parse_ctrlval		= parse_cbm,
  			.format_str		= "%d=%0*x", .fflags = RFTYPE_RES_CACHE, @@ -79,8 +82,8 @@ struct 
 rdt_hw_resource rdt_resources_all[] = { .r_resctrl = { .rid = RDT_RESOURCE_L2, .name = "L2",
-			.scope			= RESCTRL_L2_CACHE,
-			.domains		= domain_init(RDT_RESOURCE_L2),
+			.ctrl_scope		= RESCTRL_L2_CACHE,
+			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L2),
  			.parse_ctrlval		= parse_cbm,
  			.format_str		= "%d=%0*x", .fflags = RFTYPE_RES_CACHE, @@ -93,8 +96,8 @@ struct 

rdt_hw_resource rdt_resources_all[] = { .r_resctrl = { .rid = RDT_RESOURCE_MBA, .name = "MB",

arch/x86/kernel/cpu/resctrl/core.c +149 -49
-			.scope			= RESCTRL_L3_CACHE,
-			.domains		= domain_init(RDT_RESOURCE_MBA),
+			.ctrl_scope		= RESCTRL_L3_CACHE,
+			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_MBA),
  			.parse_ctrlval		= parse_bw,
  			.format_str		= "%d=%*u",
  			.fflags			= RFTYPE_RES_MB,
@@ -105,8 +108,8 @@ struct rdt_hw_resource rdt_resources_all[] = {
  		.r_resctrl = {
  			.rid			= RDT_RESOURCE_SMBA,
  			.name			= "SMBA",
-			.scope			= RESCTRL_L3_CACHE,
-			.domains		= domain_init(RDT_RESOURCE_SMBA),
+			.ctrl_scope		= RESCTRL_L3_CACHE,
+			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_SMBA),
  			.parse_ctrlval		= parse_bw,
  			.format_str		= "%d=%*u",
  			.fflags			= RFTYPE_RES_MB,
@@ -352,11 +355,11 @@ cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
  		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
  }
 
-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 *d;
 
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
  		/* Find the domain that contains this CPU */
  		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
  			return d;
@@ -378,7 +381,7 @@ void rdt_ctrl_update(void *arg)
  	int cpu = smp_processor_id();
  	struct rdt_domain *d;
 
-	d = get_domain_from_cpu(cpu, r);
+	d = get_ctrl_domain_from_cpu(cpu, r);
  	if (d) {
  		hw_res->msr_update(d, m, r);
  		return;
@@ -388,26 +391,26 @@ void rdt_ctrl_update(void *arg)
  }
 
  /*
- * rdt_find_domain - Find a domain in a resource that matches input resource id
+ * rdt_find_domain - Search for a domain id in a resource domain list.
   *
- * Search resource r's domain list to find the resource id. If the resource
- * id is found in a domain, return the domain. Otherwise, if requested by
- * caller, return the first domain whose id is bigger than the input id.
- * The domain list is sorted by id in ascending order.
+ * Search the domain list to find the domain id. If the domain id is
+ * found, return the domain. NULL otherwise.  If the domain id is not
+ * found (and NULL returned) then the first domain with id bigger than
+ * the input id can be returned to the caller via @pos.
   */
-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)
  {
-	struct rdt_domain *d;
+	struct rdt_domain_hdr *d;
  	struct list_head *l;
 
-	list_for_each(l, &r->domains) {
-		d = list_entry(l, struct rdt_domain, hdr.list);
+	list_for_each(l, h) {
+		d = list_entry(l, struct rdt_domain_hdr, list);
  		/* When id is found, return its domain. */
-		if (id == d->hdr.id)
+		if (id == d->id)
  			return d;
  		/* Stop searching when finding id's position in sorted list. */
-		if (id < d->hdr.id)
+		if (id < d->id)
  			break;
  	}
 
@@ -501,35 +504,28 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
  	return -EINVAL;
  }
 
-/*
- * domain_add_cpu - Add a cpu to a resource's domain list.
- *
- * If an existing domain in the resource r's domain list matches the cpu's
- * resource id, add the cpu in the domain.
- *
- * Otherwise, a new domain is allocated and inserted into the right position
- * in the domain list sorted by id in ascending order.
- *
- * The order in the domain list is visible to users when we print entries
- * in the schemata file and schemata input is validated to have the same order
- * as this list.
- */
-static void domain_add_cpu(int cpu, struct rdt_resource *r)
+static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
  {
-	int id = get_domain_id_from_scope(cpu, r->scope);
+	int id = get_domain_id_from_scope(cpu, r->ctrl_scope);
  	struct list_head *add_pos = NULL;
  	struct rdt_hw_domain *hw_dom;
+	struct rdt_domain_hdr *hdr;
  	struct rdt_domain *d;
  	int err;
 
  	if (id < 0) {
-		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
-			     cpu, r->scope, r->name);
+		pr_warn_once("Can't find control domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->ctrl_scope, r->name);
  		return;
  	}
 
-	d = rdt_find_domain(r, id, &add_pos);
-	if (d) {
+	hdr = rdt_find_domain(&r->ctrl_domains, id, &add_pos);
+	if (hdr) {
+		if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
+			return;
+
+		d = container_of(hdr, struct rdt_domain, hdr);
+
  		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
  		if (r->cache.arch_has_per_cpu_cfg)
  			rdt_domain_reconfigure_cdp(r);
@@ -542,51 +538,114 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
  	d = &hw_dom->d_resctrl;
  	d->hdr.id = id;
+	d->hdr.type = RESCTRL_CTRL_DOMAIN;
  	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
  	rdt_domain_reconfigure_cdp(r);
 
-	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
+	if (domain_setup_ctrlval(r, d)) {
  		domain_free(hw_dom);
  		return;
  	}
 
-	if (r->mon_capable && arch_domain_mbm_alloc(r->num_rmid, hw_dom)) {
+	list_add_tail(&d->hdr.list, add_pos);
+
+	err = resctrl_online_ctrl_domain(r, d);
+	if (err) {
+		list_del(&d->hdr.list);
+		domain_free(hw_dom);
+	}
+}
+
+static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
+{
+	int id = get_domain_id_from_scope(cpu, r->mon_scope);
+	struct list_head *add_pos = NULL;
+	struct rdt_hw_domain *hw_dom;
+	struct rdt_domain_hdr *hdr;
+	struct rdt_domain *d;
+	int err;
+
+	if (id < 0) {
+		pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->mon_scope, r->name);
+		return;
+	}
+
+	hdr = rdt_find_domain(&r->mon_domains, id, &add_pos);
+	if (hdr) {
+		if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN))
+			return;
+
+		d = container_of(hdr, struct rdt_domain, hdr);
+
+		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
+		return;
+	}
+
+	hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu));
+	if (!hw_dom)
+		return;
+
+	d = &hw_dom->d_resctrl;
+	d->hdr.id = id;
+	d->hdr.type = RESCTRL_MON_DOMAIN;
+	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
+
+	if (arch_domain_mbm_alloc(r->num_rmid, hw_dom)) {
  		domain_free(hw_dom);
  		return;
  	}
 
  	list_add_tail(&d->hdr.list, add_pos);
 
-	err = resctrl_online_domain(r, d);
+	err = resctrl_online_mon_domain(r, d);
  	if (err) {
  		list_del(&d->hdr.list);
  		domain_free(hw_dom);
  	}
  }
 
-static void domain_remove_cpu(int cpu, struct rdt_resource *r)
+/*
+ * domain_add_cpu - Add a CPU to either/both resource's domain lists.
+ */
+static void domain_add_cpu(int cpu, struct rdt_resource *r)
  {
-	int id = get_domain_id_from_scope(cpu, r->scope);
+	if (r->alloc_capable)
+		domain_add_cpu_ctrl(cpu, r);
+	if (r->mon_capable)
+		domain_add_cpu_mon(cpu, r);
+}
+
+static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
+{
+	int id = get_domain_id_from_scope(cpu, r->ctrl_scope);
  	struct rdt_hw_domain *hw_dom;
+	struct rdt_domain_hdr *hdr;
  	struct rdt_domain *d;
 
  	if (id < 0) {
-		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
-			     cpu, r->scope, r->name);
+		pr_warn_once("Can't find control domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->ctrl_scope, r->name);
  		return;
  	}
 
-	d = rdt_find_domain(r, id, NULL);
-	if (!d) {
-		pr_warn("Couldn't find domain with id=%d for CPU %d\n", id, cpu);
+	hdr = rdt_find_domain(&r->ctrl_domains, id, NULL);
+	if (!hdr) {
+		pr_warn("Can't find control domain for id=%d for CPU %d for resource %s\n",
+			id, cpu, r->name);
  		return;
  	}
+
+	if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
+		return;
+
+	d = container_of(hdr, struct rdt_domain, hdr);
  	hw_dom = resctrl_to_arch_dom(d);
 
  	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
  	if (cpumask_empty(&d->hdr.cpu_mask)) {
-		resctrl_offline_domain(r, d);
+		resctrl_offline_ctrl_domain(r, d);
  		list_del(&d->hdr.list);
 
  		/*
@@ -599,6 +658,42 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 
  		return;
  	}
+}
+
+static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
+{
+	int id = get_domain_id_from_scope(cpu, r->mon_scope);
+	struct rdt_hw_domain *hw_dom;
+	struct rdt_domain_hdr *hdr;
+	struct rdt_domain *d;
+
+	if (id < 0) {
+		pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->mon_scope, r->name);
+		return;
+	}
+
+	hdr = rdt_find_domain(&r->mon_domains, id, NULL);
+	if (!hdr) {
+		pr_warn("Can't find monitor domain for id=%d for CPU %d for resource %s\n",
+			id, cpu, r->name);
+		return;
+	}
+
+	if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN))
+		return;
+
+	d = container_of(hdr, struct rdt_domain, hdr);
+	hw_dom = resctrl_to_arch_dom(d);
+
+	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
+	if (cpumask_empty(&d->hdr.cpu_mask)) {
+		resctrl_offline_mon_domain(r, d);
+		list_del(&d->hdr.list);
+		domain_free(hw_dom);
+
+		return;
+	}
 
  	if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
  		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
@@ -613,6 +708,14 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
  	}
  }
 
+static void domain_remove_cpu(int cpu, struct rdt_resource *r)
+{
+	if (r->alloc_capable)
+		domain_remove_cpu_ctrl(cpu, r);
+	if (r->mon_capable)
+		domain_remove_cpu_mon(cpu, r);
+}
+
  static void clear_closid_rmid(int cpu)
  {
  	struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state);
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +7 -5
index 23f8258d36a8..0b4136c42762 100644
@@ -226,7 +226,7 @@ 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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
  		return -ENOMEM;
 
  	msr_param.res = NULL;
-	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 (t = 0; t < CDP_NUM_TYPES; t++) {
  			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
  	u32 ctrl_val;
 
  	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, ";");
 
@@ -542,6 +542,7 @@ 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;
@@ -562,11 +563,12 @@ 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/monitor.c +2 -2
index dd0ea1bc0092..ec5ad926c5dc 100644
@@ -340,7 +340,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
  	entry->busy = 0;
  	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
  		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
  			err = resctrl_arch_rmid_read(r, d, entry->rmid,
  						     QOS_L3_OCCUP_EVENT_ID,
@@ -535,7 +535,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
  	rmid = rgrp->mon.rmid;
  	pmbm_data = &dom_mbm->mbm_local[rmid];
 
-	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 +2 -2
index fcbd99e2eb66..ed6d59af1cef 100644
@@ -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 cpu_cacheinfo *ci;
  	int ret;
  	int i;
@@ -856,7 +856,7 @@ 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 +30 -25
index 04d32602ac33..760013ed1bff 100644
@@ -91,7 +91,7 @@ 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));
  	}
  }
@@ -984,7 +984,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 
  	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;
@@ -1302,7 +1302,7 @@ 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)) {
@@ -1413,13 +1413,13 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
  	unsigned int size = 0;
  	int num_b, i;
 
-	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(cpumask_any(&d->hdr.cpu_mask));
  	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == r->scope) {
+		if (ci->info_list[i].level == r->ctrl_scope) {
  			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
  			break;
  		}
@@ -1477,7 +1477,7 @@ 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) {
@@ -1566,7 +1566,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 
  	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, ";");
 
@@ -1689,7 +1689,7 @@ 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) {
  			ret = mbm_config_write_domain(r, d, evtid, val);
  			if (ret)
@@ -2232,7 +2232,7 @@ 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)
@@ -2317,7 +2317,7 @@ 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;
  	}
@@ -2653,7 +2653,7 @@ 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);
  	}
 
@@ -2777,10 +2777,10 @@ 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);
  		cpumask_set_cpu(cpumask_any(&d->hdr.cpu_mask), cpu_mask);
 
@@ -3050,7 +3050,7 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
  	struct rdt_domain *dom;
  	int ret;
 
-	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;
@@ -3232,7 +3232,7 @@ 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;
@@ -3247,7 +3247,7 @@ 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;
@@ -3849,15 +3849,17 @@ 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)
  {
  	lockdep_assert_held(&rdtgroup_mutex);
 
  	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
  		mba_sc_domain_destroy(r, d);
+}
 
-	if (!r->mon_capable)
-		return;
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain *d)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
 
  	/*
  	 * If resctrl is mounted, remove all the
@@ -3914,18 +3916,21 @@ 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;
-
  	lockdep_assert_held(&rdtgroup_mutex);
 
  	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
-		/* RDT_RESOURCE_MBA is never mon_capable */
  		return mba_sc_domain_allocate(r, d);
 
-	if (!r->mon_capable)
-		return 0;
+	return 0;
+}
+
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain *d)
+{
+	int err;
+
+	lockdep_assert_held(&rdtgroup_mutex);
 
  	err = domain_setup_mon_state(r, d);
  	if (err)
author maintainer
#264 lore raw

PATCH v13 4/8 x86/resctrl: Split the rdt_domain and rdt_hw_domain structures

In reply to Tony Luck

The same rdt_domain structure is used for both control and monitor functions. But this results in wasted memory as some of the fields are only used by control functions, while most are only used for monitor functions.

Split into separate rdt_ctrl_domain and rdt_mon_domain structures with just the fields required for control and monitoring respectively.

Similar split of the rdt_hw_domain structure into rdt_hw_ctrl_domain and rdt_hw_mon_domain.

---
 include/linux/resctrl.h                   | 48 +++++++------
 arch/x86/kernel/cpu/resctrl/internal.h    | 60 ++++++++++------
 arch/x86/kernel/cpu/resctrl/core.c        | 87 ++++++++++++-----------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 32 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 40 +++++------
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  6 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 62 ++++++++--------
 7 files changed, 182 insertions(+), 153 deletions(-)
include/linux/resctrl.h +28 -20
index 35e700edc6e6..058a940c3239 100644
@@ -72,7 +72,23 @@ struct rdt_domain_hdr {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource
+ * @hdr:		common header for different domain types
+ * @plr:		pseudo-locked region (if any) associated with domain
+ * @staged_config:	parsed configuration to be applied
+ * @mbps_val:		When mba_sc is enabled, this holds the array of user
+ *			specified control values for mba_sc in MBps, indexed
+ *			by closid
+ */
+struct rdt_ctrl_domain {
+	struct rdt_domain_hdr		hdr;
+	struct pseudo_lock_region	*plr;
+	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
+	u32				*mbps_val;
+};
+
+/**
+ * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
  * @hdr:		common header for different domain types
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
@@ -81,13 +97,8 @@ struct rdt_domain_hdr {
  * @cqm_limbo:		worker to periodically read CQM h/w counters
  * @mbm_work_cpu:	worker CPU for MBM h/w counters
  * @cqm_work_cpu:	worker CPU for CQM h/w counters
- * @plr:		pseudo-locked region (if any) associated with domain
- * @staged_config:	parsed configuration to be applied
- * @mbps_val:		When mba_sc is enabled, this holds the array of user
- *			specified control values for mba_sc in MBps, indexed
- *			by closid
  */
-struct rdt_domain {
+struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
@@ -96,9 +107,6 @@ struct rdt_domain {
 	struct delayed_work		cqm_limbo;
 	int				mbm_work_cpu;
 	int				cqm_work_cpu;
-	struct pseudo_lock_region	*plr;
-	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
-	u32				*mbps_val;
 };
 
 /**
@@ -202,7 +210,7 @@ struct rdt_resource {
 	const char		*format_str;
 	int			(*parse_ctrlval)(struct rdt_parse_data *data,
 						 struct resctrl_schema *s,
-						 struct rdt_domain *d);
+						 struct rdt_ctrl_domain *d);
 	struct list_head	evt_list;
 	unsigned long		fflags;
 	bool			cdp_capable;
@@ -236,15 +244,15 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
  * Update the ctrl_val and apply this config right now.
  * Must be called on one of the domain's CPUs.
  */
-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);
 
-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);
-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);
+int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
+void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
@@ -260,7 +268,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain *d);
  * Return:
  * 0 on success, or -EIO, -EINVAL etc on error.
  */
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 rmid, enum resctrl_event_id eventid, u64 *val);
 
 /**
@@ -273,7 +281,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 			     u32 rmid, enum resctrl_event_id eventid);
 
 /**
@@ -285,7 +293,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d);
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d);
 
 extern unsigned int resctrl_rmid_realloc_threshold;
 extern unsigned int resctrl_rmid_realloc_limit;
arch/x86/kernel/cpu/resctrl/internal.h +38 -22

131 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/core.c +46 -41

246 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +16 -16
index 0b4136c42762..08fc97ce4135 100644
@@ -58,7 +58,7 @@ 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;
@@ -137,7 +137,7 @@ 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;
@@ -206,8 +206,8 @@ 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;
 
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
@@ -267,11 +267,11 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
 	}
 }
 
-static bool apply_config(struct rdt_hw_domain *hw_dom,
+static bool apply_config(struct rdt_hw_ctrl_domain *hw_dom,
 			 struct resctrl_staged_config *cfg, u32 idx,
 			 cpumask_var_t cpu_mask)
 {
-	struct rdt_domain *dom = &hw_dom->d_resctrl;
+	struct rdt_ctrl_domain *dom = &hw_dom->d_resctrl;
 
 	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
 		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
@@ -283,11 +283,11 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
 	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;
 
@@ -307,11 +307,11 @@ 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))
@@ -319,7 +319,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 
 	msr_param.res = NULL;
 	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		hw_dom = resctrl_to_arch_dom(d);
+		hw_dom = resctrl_to_arch_ctrl_dom(d);
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
 			if (!cfg->have_new_ctrl)
@@ -449,10 +449,10 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	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];
@@ -461,7 +461,7 @@ 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;
 
@@ -523,7 +523,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 }
 
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
 		    int evtid, int first)
 {
 	/*
@@ -543,11 +543,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
 	struct rdt_domain_hdr *hdr;
+	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;
 
@@ -568,7 +568,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		ret = -ENOENT;
 		goto out;
 	}
-	d = container_of(hdr, struct rdt_domain, hdr);
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
 
 	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
arch/x86/kernel/cpu/resctrl/monitor.c +20 -20
index ec5ad926c5dc..4e145f5620b0 100644
@@ -170,7 +170,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 	return 0;
 }
 
-static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
+static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_dom,
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
 {
@@ -189,10 +189,10 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 	return NULL;
 }
 
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 			     u32 rmid, enum resctrl_event_id eventid)
 {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct arch_mbm_state *am;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
@@ -208,9 +208,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
  * Assumes that hardware counters are also reset and thus that there is
  * no need to record initial non-zero counts.
  */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d)
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 
 	if (is_mbm_total_enabled())
 		memset(hw_dom->arch_mbm_total, 0,
@@ -229,11 +229,11 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 	return chunks >> shift;
 }
 
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 rmid, enum resctrl_event_id eventid, u64 *val)
 {
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
 	u64 msr_val, chunks;
 	int ret;
@@ -266,7 +266,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  * decrement the count. If the busy count gets to zero on an RMID, we
  * free the RMID
  */
-void __check_limbo(struct rdt_domain *d, bool force_free)
+void __check_limbo(struct rdt_mon_domain *d, bool force_free)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	struct rmid_entry *entry;
@@ -305,7 +305,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 	}
 }
 
-bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d)
+bool has_busy_rmid(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid;
 }
@@ -334,7 +334,7 @@ int alloc_rmid(void)
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_domain *d;
+	struct rdt_mon_domain *d;
 	int cpu, err;
 	u64 val = 0;
 
@@ -383,7 +383,7 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid,
+static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 rmid,
 				       enum resctrl_event_id evtid)
 {
 	switch (evtid) {
@@ -516,13 +516,13 @@ void mon_event_count(void *info)
  * throttle MSRs already have low percentage values.  To avoid
  * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
  */
-static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
+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;
 	u32 cur_bw, delta_bw, user_bw;
 	struct rdt_resource *r_mba;
-	struct rdt_domain *dom_mba;
 	struct list_head *head;
 	struct rdtgroup *entry;
 
@@ -600,7 +600,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	}
 }
 
-static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, int rmid)
 {
 	struct rmid_read rr;
 
@@ -640,13 +640,13 @@ void cqm_handle_limbo(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
 	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
 	struct rdt_resource *r;
-	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, cqm_limbo.work);
+	d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
 
@@ -656,7 +656,7 @@ void cqm_handle_limbo(struct work_struct *work)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
@@ -672,9 +672,9 @@ void mbm_handle_overflow(struct work_struct *work)
 	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
 	struct rdtgroup *prgrp, *crgrp;
 	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
 	struct list_head *head;
 	struct rdt_resource *r;
-	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
 
@@ -682,7 +682,7 @@ void mbm_handle_overflow(struct work_struct *work)
 		goto out_unlock;
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, mbm_over.work);
+	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		mbm_update(r, d, prgrp->mon.rmid);
@@ -701,7 +701,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +3 -3
index ed6d59af1cef..08d35f828bc3 100644
@@ -814,7 +814,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
  * Return: true if @cbm overlaps with pseudo-locked region on @d, false
  * otherwise.
  */
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm)
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
 {
 	unsigned int cbm_len;
 	unsigned long cbm_b;
@@ -841,11 +841,11 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm
  *         if it is not possible to test due to memory allocation issue,
  *         false otherwise.
  */
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
 {
+	struct rdt_ctrl_domain *d_i;
 	cpumask_var_t cpu_with_psl;
 	struct rdt_resource *r;
-	struct rdt_domain *d_i;
 	bool ret = false;
 
 	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
arch/x86/kernel/cpu/resctrl/rdtgroup.c +31 -31

252 lines not on this page · raw message

Signature · 1 line
2.41.0
Reviewed-by Babu Moger on v13 4/8
#265 lore raw

Re: [PATCH v13 4/8] x86/resctrl: Split the rdt_domain and rdt_hw_domain structures

Quoted 8 lines · Tony Luck

The same rdt_domain structure is used for both control and monitor functions. But this results in wasted memory as some of the fields are only used by control functions, while most are only used for monitor functions.

Split into separate rdt_ctrl_domain and rdt_mon_domain structures with just the fields required for control and monitoring respectively.

Quoted 8 lines

Similar split of the rdt_hw_domain structure into rdt_hw_ctrl_domain and rdt_hw_mon_domain.

Quoted 1,148 lines
---
  include/linux/resctrl.h                   | 48 +++++++------
  arch/x86/kernel/cpu/resctrl/internal.h    | 60 ++++++++++------
  arch/x86/kernel/cpu/resctrl/core.c        | 87 ++++++++++++-----------
  arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 32 ++++-----
  arch/x86/kernel/cpu/resctrl/monitor.c     | 40 +++++------
  arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  6 +-
  arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 62 ++++++++--------
  7 files changed, 182 insertions(+), 153 deletions(-)
include/linux/resctrl.h +28 -20
index 35e700edc6e6..058a940c3239 100644
@@ -72,7 +72,23 @@ struct rdt_domain_hdr {
  };
 
  /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource
+ * @hdr:		common header for different domain types
+ * @plr:		pseudo-locked region (if any) associated with domain
+ * @staged_config:	parsed configuration to be applied
+ * @mbps_val:		When mba_sc is enabled, this holds the array of user
+ *			specified control values for mba_sc in MBps, indexed
+ *			by closid
+ */
+struct rdt_ctrl_domain {
+	struct rdt_domain_hdr		hdr;
+	struct pseudo_lock_region	*plr;
+	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
+	u32				*mbps_val;
+};
+
+/**
+ * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
   * @hdr:		common header for different domain types
   * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
   * @mbm_total:		saved state for MBM total bandwidth
@@ -81,13 +97,8 @@ struct rdt_domain_hdr {
   * @cqm_limbo:		worker to periodically read CQM h/w counters
   * @mbm_work_cpu:	worker CPU for MBM h/w counters
   * @cqm_work_cpu:	worker CPU for CQM h/w counters
- * @plr:		pseudo-locked region (if any) associated with domain
- * @staged_config:	parsed configuration to be applied
- * @mbps_val:		When mba_sc is enabled, this holds the array of user
- *			specified control values for mba_sc in MBps, indexed
- *			by closid
   */
-struct rdt_domain {
+struct rdt_mon_domain {
  	struct rdt_domain_hdr		hdr;
  	unsigned long			*rmid_busy_llc;
  	struct mbm_state		*mbm_total;
@@ -96,9 +107,6 @@ struct rdt_domain {
  	struct delayed_work		cqm_limbo;
  	int				mbm_work_cpu;
  	int				cqm_work_cpu;
-	struct pseudo_lock_region	*plr;
-	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
-	u32				*mbps_val;
  };
 
  /**
@@ -202,7 +210,7 @@ struct rdt_resource {
  	const char		*format_str;
  	int			(*parse_ctrlval)(struct rdt_parse_data *data,
  						 struct resctrl_schema *s,
-						 struct rdt_domain *d);
+						 struct rdt_ctrl_domain *d);
  	struct list_head	evt_list;
  	unsigned long		fflags;
  	bool			cdp_capable;
@@ -236,15 +244,15 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
   * Update the ctrl_val and apply this config right now.
   * Must be called on one of the domain's CPUs.
   */
-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);
 
-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);
-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);
+int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
+void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
 
  /**
   * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
@@ -260,7 +268,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain *d);
   * Return:
   * 0 on success, or -EIO, -EINVAL etc on error.
   */
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
  			   u32 rmid, enum resctrl_event_id eventid, u64 *val);
 
  /**
@@ -273,7 +281,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
   *
   * This can be called from any CPU.
   */
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
  			     u32 rmid, enum resctrl_event_id eventid);
 
  /**
@@ -285,7 +293,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
   *
   * This can be called from any CPU.
   */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d);
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d);
 
  extern unsigned int resctrl_rmid_realloc_threshold;
  extern unsigned int resctrl_rmid_realloc_limit;
arch/x86/kernel/cpu/resctrl/internal.h +38 -22
index 24bf9d7989a9..ce3a70657842 100644
@@ -107,7 +107,7 @@ union mon_data_bits {
  struct rmid_read {
  	struct rdtgroup		*rgrp;
  	struct rdt_resource	*r;
-	struct rdt_domain	*d;
+	struct rdt_mon_domain	*d;
  	enum resctrl_event_id	evtid;
  	bool			first;
  	int			err;
@@ -192,7 +192,7 @@ struct mongroup {
   */
  struct pseudo_lock_region {
  	struct resctrl_schema	*s;
-	struct rdt_domain	*d;
+	struct rdt_ctrl_domain	*d;
  	u32			cbm;
  	wait_queue_head_t	lock_thread_wq;
  	int			thread_done;
@@ -319,25 +319,41 @@ struct arch_mbm_state {
  };
 
  /**
- * struct rdt_hw_domain - Arch private attributes of a set of CPUs that share
- *			  a resource
+ * struct rdt_hw_ctrl_domain - Arch private attributes of a set of CPUs that share
+ *			       a resource for a control function
   * @d_resctrl:	Properties exposed to the resctrl file system
   * @ctrl_val:	array of cache or mem ctrl values (indexed by CLOSID)
+ *
+ * Members of this structure are accessed via helpers that provide abstraction.
+ */
+struct rdt_hw_ctrl_domain {
+	struct rdt_ctrl_domain		d_resctrl;
+	u32				*ctrl_val;
+};
+
+/**
+ * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs that share
+ *			      a resource for a monitor function
+ * @d_resctrl:	Properties exposed to the resctrl file system
   * @arch_mbm_total:	arch private state for MBM total bandwidth
   * @arch_mbm_local:	arch private state for MBM local bandwidth
   *
   * Members of this structure are accessed via helpers that provide abstraction.
   */
-struct rdt_hw_domain {
-	struct rdt_domain		d_resctrl;
-	u32				*ctrl_val;
+struct rdt_hw_mon_domain {
+	struct rdt_mon_domain		d_resctrl;
  	struct arch_mbm_state		*arch_mbm_total;
  	struct arch_mbm_state		*arch_mbm_local;
  };
 
-static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
+static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctrl_domain *r)
+{
+	return container_of(r, struct rdt_hw_ctrl_domain, d_resctrl);
+}
+
+static inline struct rdt_hw_mon_domain *resctrl_to_arch_mon_dom(struct rdt_mon_domain *r)
  {
-	return container_of(r, struct rdt_hw_domain, d_resctrl);
+	return container_of(r, struct rdt_hw_mon_domain, d_resctrl);
  }
 
  /**
@@ -405,7 +421,7 @@ struct rdt_hw_resource {
  	struct rdt_resource	r_resctrl;
  	u32			num_closid;
  	unsigned int		msr_base;
-	void (*msr_update)	(struct rdt_domain *d, struct msr_param *m,
+	void (*msr_update)	(struct rdt_ctrl_domain *d, struct msr_param *m,
  				 struct rdt_resource *r);
  	unsigned int		mon_scale;
  	unsigned int		mbm_width;
@@ -418,9 +434,9 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r
  }
 
  int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
-	      struct rdt_domain *d);
+	      struct rdt_ctrl_domain *d);
  int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
-	     struct rdt_domain *d);
+	     struct rdt_ctrl_domain *d);
 
  extern struct mutex rdtgroup_mutex;
 
@@ -526,21 +542,21 @@ 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);
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
+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_domain *d,
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d,
  				  unsigned long cbm);
  enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
  int rdtgroup_tasks_assigned(struct rdtgroup *r);
  int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
  int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm);
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm);
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d);
  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_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r);
+struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r);
  int closids_supported(void);
  void closid_free(int closid);
  int alloc_rmid(void);
@@ -550,17 +566,17 @@ bool __init rdt_cpu_has(int flag);
  void mon_event_count(void *info);
  int rdtgroup_mondata_show(struct seq_file *m, void *arg);
  void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
  		    int evtid, int first);
-void mbm_setup_overflow_handler(struct rdt_domain *dom,
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom,
  				unsigned long delay_ms);
  void mbm_handle_overflow(struct work_struct *work);
  void __init intel_rdt_mbm_apply_quirk(void);
  bool is_mba_sc(struct rdt_resource *r);
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms);
  void cqm_handle_limbo(struct work_struct *work);
-bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
-void __check_limbo(struct rdt_domain *d, bool force_free);
+bool has_busy_rmid(struct rdt_resource *r, 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);
arch/x86/kernel/cpu/resctrl/core.c +46 -41
index 1fd85533b4ca..797cb3bf417a 100644
@@ -49,12 +49,12 @@ int max_name_width, max_data_width;
  bool rdt_alloc_capable;
 
  static void
-mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
+mba_wrmsr_intel(struct rdt_ctrl_domain *d, struct msr_param *m,
  		struct rdt_resource *r);
  static void
-cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+cat_wrmsr(struct rdt_ctrl_domain *d, struct msr_param *m, struct rdt_resource *r);
  static void
-mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
+mba_wrmsr_amd(struct rdt_ctrl_domain *d, struct msr_param *m,
  	      struct rdt_resource *r);
 
  #define ctrl_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.ctrl_domains)
@@ -307,11 +307,11 @@ static void rdt_get_cdp_l2_config(void)
  }
 
  static void
-mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+mba_wrmsr_amd(struct rdt_ctrl_domain *d, struct msr_param *m, struct rdt_resource *r)
  {
-	unsigned int i;
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+	unsigned int i;
 
  	for (i = m->low; i < m->high; i++)
  		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
@@ -332,12 +332,12 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
  }
 
  static void
-mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
+mba_wrmsr_intel(struct rdt_ctrl_domain *d, struct msr_param *m,
  		struct rdt_resource *r)
  {
-	unsigned int i;
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+	unsigned int i;
 
  	/*  Write the delay values for mba. */
  	for (i = m->low; i < m->high; i++)
@@ -345,19 +345,19 @@ mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
  }
 
  static void
-cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+cat_wrmsr(struct rdt_ctrl_domain *d, struct msr_param *m, struct rdt_resource *r)
  {
-	unsigned int i;
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+	unsigned int i;
 
  	for (i = m->low; i < m->high; i++)
  		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
  }
 
-struct rdt_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r)
+struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r)
  {
-	struct rdt_domain *d;
+	struct rdt_ctrl_domain *d;
 
  	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
  		/* Find the domain that contains this CPU */
@@ -379,7 +379,7 @@ void rdt_ctrl_update(void *arg)
  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
  	struct rdt_resource *r = m->res;
  	int cpu = smp_processor_id();
-	struct rdt_domain *d;
+	struct rdt_ctrl_domain *d;
 
  	d = get_ctrl_domain_from_cpu(cpu, r);
  	if (d) {
@@ -434,18 +434,23 @@ static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc)
  		*dc = r->default_ctrl;
  }
 
-static void domain_free(struct rdt_hw_domain *hw_dom)
+static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom)
+{
+	kfree(hw_dom->ctrl_val);
+	kfree(hw_dom);
+}
+
+static void mon_domain_free(struct rdt_hw_mon_domain *hw_dom)
  {
  	kfree(hw_dom->arch_mbm_total);
  	kfree(hw_dom->arch_mbm_local);
-	kfree(hw_dom->ctrl_val);
  	kfree(hw_dom);
  }
 
-static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
+static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain *d)
  {
+	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);
  	struct msr_param m;
  	u32 *dc;
 
@@ -468,7 +473,7 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
   * @num_rmid:	The size of the MBM counter array
   * @hw_dom:	The domain that owns the allocated arrays
   */
-static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
+static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom)
  {
  	size_t tsize;
 
@@ -507,10 +512,10 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
  static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
  {
  	int id = get_domain_id_from_scope(cpu, r->ctrl_scope);
+	struct rdt_hw_ctrl_domain *hw_dom;
  	struct list_head *add_pos = NULL;
-	struct rdt_hw_domain *hw_dom;
  	struct rdt_domain_hdr *hdr;
-	struct rdt_domain *d;
+	struct rdt_ctrl_domain *d;
  	int err;
 
  	if (id < 0) {
@@ -524,7 +529,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
  		if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
  			return;
 
-		d = container_of(hdr, struct rdt_domain, hdr);
+		d = container_of(hdr, struct rdt_ctrl_domain, hdr);
 
  		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
  		if (r->cache.arch_has_per_cpu_cfg)
@@ -544,7 +549,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
  	rdt_domain_reconfigure_cdp(r);
 
  	if (domain_setup_ctrlval(r, d)) {
-		domain_free(hw_dom);
+		ctrl_domain_free(hw_dom);
  		return;
  	}
 
@@ -553,17 +558,17 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
  	err = resctrl_online_ctrl_domain(r, d);
  	if (err) {
  		list_del(&d->hdr.list);
-		domain_free(hw_dom);
+		ctrl_domain_free(hw_dom);
  	}
  }
 
  static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
  {
  	int id = get_domain_id_from_scope(cpu, r->mon_scope);
+	struct rdt_hw_mon_domain *hw_dom;
  	struct list_head *add_pos = NULL;
-	struct rdt_hw_domain *hw_dom;
  	struct rdt_domain_hdr *hdr;
-	struct rdt_domain *d;
+	struct rdt_mon_domain *d;
  	int err;
 
  	if (id < 0) {
@@ -577,7 +582,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
  		if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN))
  			return;
 
-		d = container_of(hdr, struct rdt_domain, hdr);
+		d = container_of(hdr, struct rdt_mon_domain, hdr);
 
  		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
  		return;
@@ -593,7 +598,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
  	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
  	if (arch_domain_mbm_alloc(r->num_rmid, hw_dom)) {
-		domain_free(hw_dom);
+		mon_domain_free(hw_dom);
  		return;
  	}
 
@@ -602,7 +607,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
  	err = resctrl_online_mon_domain(r, d);
  	if (err) {
  		list_del(&d->hdr.list);
-		domain_free(hw_dom);
+		mon_domain_free(hw_dom);
  	}
  }
 
@@ -620,9 +625,9 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
  static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
  {
  	int id = get_domain_id_from_scope(cpu, r->ctrl_scope);
-	struct rdt_hw_domain *hw_dom;
+	struct rdt_hw_ctrl_domain *hw_dom;
  	struct rdt_domain_hdr *hdr;
-	struct rdt_domain *d;
+	struct rdt_ctrl_domain *d;
 
  	if (id < 0) {
  		pr_warn_once("Can't find control domain id for CPU:%d scope:%d for resource %s\n",
@@ -640,8 +645,8 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
  	if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
  		return;
 
-	d = container_of(hdr, struct rdt_domain, hdr);
-	hw_dom = resctrl_to_arch_dom(d);
+	d = container_of(hdr, struct rdt_ctrl_domain, hdr);
+	hw_dom = resctrl_to_arch_ctrl_dom(d);
 
  	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
  	if (cpumask_empty(&d->hdr.cpu_mask)) {
@@ -649,12 +654,12 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
  		list_del(&d->hdr.list);
 
  		/*
-		 * rdt_domain "d" is going to be freed below, so clear
+		 * rdt_ctrl_domain "d" is going to be freed below, so clear
  		 * its pointer from pseudo_lock_region struct.
  		 */
  		if (d->plr)
  			d->plr->d = NULL;
-		domain_free(hw_dom);
+		ctrl_domain_free(hw_dom);
 
  		return;
  	}
@@ -663,9 +668,9 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
  static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
  {
  	int id = get_domain_id_from_scope(cpu, r->mon_scope);
-	struct rdt_hw_domain *hw_dom;
+	struct rdt_hw_mon_domain *hw_dom;
  	struct rdt_domain_hdr *hdr;
-	struct rdt_domain *d;
+	struct rdt_mon_domain *d;
 
  	if (id < 0) {
  		pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n",
@@ -683,14 +688,14 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
  	if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN))
  		return;
 
-	d = container_of(hdr, struct rdt_domain, hdr);
-	hw_dom = resctrl_to_arch_dom(d);
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
+	hw_dom = resctrl_to_arch_mon_dom(d);
 
  	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
  	if (cpumask_empty(&d->hdr.cpu_mask)) {
  		resctrl_offline_mon_domain(r, d);
  		list_del(&d->hdr.list);
-		domain_free(hw_dom);
+		mon_domain_free(hw_dom);
 
  		return;
  	}
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +16 -16
index 0b4136c42762..08fc97ce4135 100644
@@ -58,7 +58,7 @@ 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;
@@ -137,7 +137,7 @@ 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;
@@ -206,8 +206,8 @@ 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;
 
  	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
@@ -267,11 +267,11 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
  	}
  }
 
-static bool apply_config(struct rdt_hw_domain *hw_dom,
+static bool apply_config(struct rdt_hw_ctrl_domain *hw_dom,
  			 struct resctrl_staged_config *cfg, u32 idx,
  			 cpumask_var_t cpu_mask)
  {
-	struct rdt_domain *dom = &hw_dom->d_resctrl;
+	struct rdt_ctrl_domain *dom = &hw_dom->d_resctrl;
 
  	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
  		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
@@ -283,11 +283,11 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
  	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;
 
@@ -307,11 +307,11 @@ 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))
@@ -319,7 +319,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 
  	msr_param.res = NULL;
  	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		hw_dom = resctrl_to_arch_dom(d);
+		hw_dom = resctrl_to_arch_ctrl_dom(d);
  		for (t = 0; t < CDP_NUM_TYPES; t++) {
  			cfg = &hw_dom->d_resctrl.staged_config[t];
  			if (!cfg->have_new_ctrl)
@@ -449,10 +449,10 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
  	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];
@@ -461,7 +461,7 @@ 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;
 
@@ -523,7 +523,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
  }
 
  void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
  		    int evtid, int first)
  {
  	/*
@@ -543,11 +543,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
  {
  	struct kernfs_open_file *of = m->private;
  	struct rdt_domain_hdr *hdr;
+	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;
 
@@ -568,7 +568,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
  		ret = -ENOENT;
  		goto out;
  	}
-	d = container_of(hdr, struct rdt_domain, hdr);
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
 
  	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
arch/x86/kernel/cpu/resctrl/monitor.c +20 -20
index ec5ad926c5dc..4e145f5620b0 100644
@@ -170,7 +170,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
  	return 0;
  }
 
-static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
+static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_dom,
  						 u32 rmid,
  						 enum resctrl_event_id eventid)
  {
@@ -189,10 +189,10 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
  	return NULL;
  }
 
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
  			     u32 rmid, enum resctrl_event_id eventid)
  {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
  	struct arch_mbm_state *am;
 
  	am = get_arch_mbm_state(hw_dom, rmid, eventid);
@@ -208,9 +208,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
   * Assumes that hardware counters are also reset and thus that there is
   * no need to record initial non-zero counts.
   */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d)
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
  {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 
  	if (is_mbm_total_enabled())
  		memset(hw_dom->arch_mbm_total, 0,
@@ -229,11 +229,11 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
  	return chunks >> shift;
  }
 
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
  			   u32 rmid, enum resctrl_event_id eventid, u64 *val)
  {
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
  	struct arch_mbm_state *am;
  	u64 msr_val, chunks;
  	int ret;
@@ -266,7 +266,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
   * decrement the count. If the busy count gets to zero on an RMID, we
   * free the RMID
   */
-void __check_limbo(struct rdt_domain *d, bool force_free)
+void __check_limbo(struct rdt_mon_domain *d, bool force_free)
  {
  	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
  	struct rmid_entry *entry;
@@ -305,7 +305,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
  	}
  }
 
-bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d)
+bool has_busy_rmid(struct rdt_resource *r, struct rdt_mon_domain *d)
  {
  	return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid;
  }
@@ -334,7 +334,7 @@ int alloc_rmid(void)
  static void add_rmid_to_limbo(struct rmid_entry *entry)
  {
  	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_domain *d;
+	struct rdt_mon_domain *d;
  	int cpu, err;
  	u64 val = 0;
 
@@ -383,7 +383,7 @@ void free_rmid(u32 rmid)
  		list_add_tail(&entry->list, &rmid_free_lru);
  }
 
-static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid,
+static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 rmid,
  				       enum resctrl_event_id evtid)
  {
  	switch (evtid) {
@@ -516,13 +516,13 @@ void mon_event_count(void *info)
   * throttle MSRs already have low percentage values.  To avoid
   * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
   */
-static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
+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;
  	u32 cur_bw, delta_bw, user_bw;
  	struct rdt_resource *r_mba;
-	struct rdt_domain *dom_mba;
  	struct list_head *head;
  	struct rdtgroup *entry;
 
@@ -600,7 +600,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
  	}
  }
 
-static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, int rmid)
  {
  	struct rmid_read rr;
 
@@ -640,13 +640,13 @@ void cqm_handle_limbo(struct work_struct *work)
  {
  	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
  	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
  	struct rdt_resource *r;
-	struct rdt_domain *d;
 
  	mutex_lock(&rdtgroup_mutex);
 
  	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, cqm_limbo.work);
+	d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
 
  	__check_limbo(d, false);
 
@@ -656,7 +656,7 @@ void cqm_handle_limbo(struct work_struct *work)
  	mutex_unlock(&rdtgroup_mutex);
  }
 
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms)
  {
  	unsigned long delay = msecs_to_jiffies(delay_ms);
  	int cpu;
@@ -672,9 +672,9 @@ void mbm_handle_overflow(struct work_struct *work)
  	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
  	struct rdtgroup *prgrp, *crgrp;
  	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
  	struct list_head *head;
  	struct rdt_resource *r;
-	struct rdt_domain *d;
 
  	mutex_lock(&rdtgroup_mutex);
 
@@ -682,7 +682,7 @@ void mbm_handle_overflow(struct work_struct *work)
  		goto out_unlock;
 
  	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, mbm_over.work);
+	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
 
  	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
  		mbm_update(r, d, prgrp->mon.rmid);
@@ -701,7 +701,7 @@ void mbm_handle_overflow(struct work_struct *work)
  	mutex_unlock(&rdtgroup_mutex);
  }
 
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms)
  {
  	unsigned long delay = msecs_to_jiffies(delay_ms);
  	int cpu;
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +3 -3
index ed6d59af1cef..08d35f828bc3 100644
@@ -814,7 +814,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
   * Return: true if @cbm overlaps with pseudo-locked region on @d, false
   * otherwise.
   */
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm)
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
  {
  	unsigned int cbm_len;
  	unsigned long cbm_b;
@@ -841,11 +841,11 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm
   *         if it is not possible to test due to memory allocation issue,
   *         false otherwise.
   */
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
  {
+	struct rdt_ctrl_domain *d_i;
  	cpumask_var_t cpu_with_psl;
  	struct rdt_resource *r;
-	struct rdt_domain *d_i;
  	bool ret = false;
 
  	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
arch/x86/kernel/cpu/resctrl/rdtgroup.c +31 -31
index 760013ed1bff..21bbd832f3f2 100644
@@ -85,8 +85,8 @@ void rdt_last_cmd_printf(const char *fmt, ...)
 
  void rdt_staged_configs_clear(void)
  {
+	struct rdt_ctrl_domain *dom;
  	struct rdt_resource *r;
-	struct rdt_domain *dom;
 
  	lockdep_assert_held(&rdtgroup_mutex);
 
@@ -976,7 +976,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
  	unsigned long sw_shareable = 0, hw_shareable = 0;
  	unsigned long exclusive = 0, pseudo_locked = 0;
  	struct rdt_resource *r = s->res;
-	struct rdt_domain *dom;
+	struct rdt_ctrl_domain *dom;
  	int i, hwb, swb, excl, psl;
  	enum rdtgrp_mode mode;
  	bool sep = false;
@@ -1205,7 +1205,7 @@ static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
   *
   * Return: false if CBM does not overlap, true if it does.
   */
-static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_ctrl_domain *d,
  				    unsigned long cbm, int closid,
  				    enum resctrl_conf_type type, bool exclusive)
  {
@@ -1260,7 +1260,7 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d
   *
   * Return: true if CBM overlap detected, false if there is no overlap
   */
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
+bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
  			   unsigned long cbm, int closid, bool exclusive)
  {
  	enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
@@ -1291,10 +1291,10 @@ bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
  static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
  {
  	int closid = rdtgrp->closid;
+	struct rdt_ctrl_domain *d;
  	struct resctrl_schema *s;
  	struct rdt_resource *r;
  	bool has_cache = false;
-	struct rdt_domain *d;
  	u32 ctrl;
 
  	list_for_each_entry(s, &resctrl_schema_all, list) {
@@ -1407,7 +1407,7 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
   * bitmap functions work correctly.
   */
  unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
-				  struct rdt_domain *d, unsigned long cbm)
+				  struct rdt_ctrl_domain *d, unsigned long cbm)
  {
  	struct cpu_cacheinfo *ci;
  	unsigned int size = 0;
@@ -1439,9 +1439,9 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
  {
  	struct resctrl_schema *schema;
  	enum resctrl_conf_type type;
+	struct rdt_ctrl_domain *d;
  	struct rdtgroup *rdtgrp;
  	struct rdt_resource *r;
-	struct rdt_domain *d;
  	unsigned int size;
  	int ret = 0;
  	u32 closid;
@@ -1553,7 +1553,7 @@ static void mon_event_config_read(void *info)
  	mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
  }
 
-static void mondata_config_read(struct rdt_domain *d, struct mon_config_info *mon_info)
+static void mondata_config_read(struct rdt_mon_domain *d, struct mon_config_info *mon_info)
  {
  	smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_read, mon_info, 1);
  }
@@ -1561,7 +1561,7 @@ static void mondata_config_read(struct rdt_domain *d, struct mon_config_info *mo
  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;
+	struct rdt_mon_domain *dom;
  	bool sep = false;
 
  	mutex_lock(&rdtgroup_mutex);
@@ -1618,7 +1618,7 @@ static void mon_event_config_write(void *info)
  }
 
  static int mbm_config_write_domain(struct rdt_resource *r,
-				   struct rdt_domain *d, u32 evtid, u32 val)
+				   struct rdt_mon_domain *d, u32 evtid, u32 val)
  {
  	struct mon_config_info mon_info = {0};
  	int ret = 0;
@@ -1668,7 +1668,7 @@ 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;
+	struct rdt_mon_domain *d;
  	int ret = 0;
 
  next:
@@ -2216,9 +2216,9 @@ static inline bool is_mba_linear(void)
  static int set_cache_qos_cfg(int level, bool enable)
  {
  	void (*update)(void *arg);
+	struct rdt_ctrl_domain *d;
  	struct rdt_resource *r_l;
  	cpumask_var_t cpu_mask;
-	struct rdt_domain *d;
  	int cpu;
 
  	if (level == RDT_RESOURCE_L3)
@@ -2265,7 +2265,7 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
  		l3_qos_cfg_update(&hw_res->cdp_enabled);
  }
 
-static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d)
+static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_ctrl_domain *d)
  {
  	u32 num_closid = resctrl_arch_get_num_closid(r);
  	int cpu = cpumask_any(&d->hdr.cpu_mask);
@@ -2283,7 +2283,7 @@ static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d)
  }
 
  static void mba_sc_domain_destroy(struct rdt_resource *r,
-				  struct rdt_domain *d)
+				  struct rdt_ctrl_domain *d)
  {
  	kfree(d->mbps_val);
  	d->mbps_val = NULL;
@@ -2309,7 +2309,7 @@ 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_domain *d;
+	struct rdt_ctrl_domain *d;
  	int i;
 
  	if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
@@ -2578,7 +2578,7 @@ static int rdt_get_tree(struct fs_context *fc)
  {
  	struct rdt_fs_context *ctx = rdt_fc2context(fc);
  	unsigned long flags = RFTYPE_CTRL_BASE;
-	struct rdt_domain *dom;
+	struct rdt_mon_domain *dom;
  	struct rdt_resource *r;
  	int ret;
 
@@ -2762,10 +2762,10 @@ static int rdt_init_fs_context(struct fs_context *fc)
  static int reset_all_ctrls(struct rdt_resource *r)
  {
  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	struct rdt_hw_domain *hw_dom;
+	struct rdt_hw_ctrl_domain *hw_dom;
  	struct msr_param msr_param;
+	struct rdt_ctrl_domain *d;
  	cpumask_var_t cpu_mask;
-	struct rdt_domain *d;
  	int i;
 
  	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
@@ -2781,7 +2781,7 @@ static int reset_all_ctrls(struct rdt_resource *r)
  	 * from each domain to update the MSRs below.
  	 */
  	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		hw_dom = resctrl_to_arch_dom(d);
+		hw_dom = resctrl_to_arch_ctrl_dom(d);
  		cpumask_set_cpu(cpumask_any(&d->hdr.cpu_mask), cpu_mask);
 
  		for (i = 0; i < hw_res->num_closid; i++)
@@ -2976,7 +2976,7 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
  }
 
  static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
-				struct rdt_domain *d,
+				struct rdt_mon_domain *d,
  				struct rdt_resource *r, struct rdtgroup *prgrp)
  {
  	union mon_data_bits priv;
@@ -3025,7 +3025,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
   * and "monitor" groups with given domain id.
   */
  static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-					   struct rdt_domain *d)
+					   struct rdt_mon_domain *d)
  {
  	struct kernfs_node *parent_kn;
  	struct rdtgroup *prgrp, *crgrp;
@@ -3047,7 +3047,7 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
  				       struct rdt_resource *r,
  				       struct rdtgroup *prgrp)
  {
-	struct rdt_domain *dom;
+	struct rdt_mon_domain *dom;
  	int ret;
 
  	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
@@ -3149,7 +3149,7 @@ static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r)
   * Set the RDT domain up to start off with all usable allocations. That is,
   * all shareable and unused bits. All-zero CBM is invalid.
   */
-static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s,
+static int __init_one_rdt_domain(struct rdt_ctrl_domain *d, struct resctrl_schema *s,
  				 u32 closid)
  {
  	enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
@@ -3229,7 +3229,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s,
   */
  static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
  {
-	struct rdt_domain *d;
+	struct rdt_ctrl_domain *d;
  	int ret;
 
  	list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) {
@@ -3245,7 +3245,7 @@ static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
  static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
  {
  	struct resctrl_staged_config *cfg;
-	struct rdt_domain *d;
+	struct rdt_ctrl_domain *d;
 
  	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
  		if (is_mba_sc(r)) {
@@ -3842,14 +3842,14 @@ static void __init rdtgroup_setup_default(void)
  	mutex_unlock(&rdtgroup_mutex);
  }
 
-static void domain_destroy_mon_state(struct rdt_domain *d)
+static void domain_destroy_mon_state(struct rdt_mon_domain *d)
  {
  	bitmap_free(d->rmid_busy_llc);
  	kfree(d->mbm_total);
  	kfree(d->mbm_local);
  }
 
-void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_domain *d)
+void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
  {
  	lockdep_assert_held(&rdtgroup_mutex);
 
@@ -3857,7 +3857,7 @@ void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_domain *d)
  		mba_sc_domain_destroy(r, d);
  }
 
-void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain *d)
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
  {
  	lockdep_assert_held(&rdtgroup_mutex);
 
@@ -3886,7 +3886,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain *d)
  	domain_destroy_mon_state(d);
  }
 
-static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
+static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
  {
  	size_t tsize;
 
@@ -3916,7 +3916,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
  	return 0;
  }
 
-int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_domain *d)
+int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
  {
  	lockdep_assert_held(&rdtgroup_mutex);
 
@@ -3926,7 +3926,7 @@ int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_domain *d)
  	return 0;
  }
 
-int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain *d)
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
  {
  	int err;
 
author maintainer
#266 lore raw

PATCH v13 5/8 x86/resctrl: Add node-scope to the options for feature scope

In reply to Tony Luck

Currently supported resctrl features are all domain scoped the same as the scope of the L2 or L3 caches.

Add RESCTRL_NODE as a new option for features that are scoped at the same granularity as NUMA nodes. This is needed for Intel's Sub-NUMA Cluster (SNC) feature where monitoring features are node scoped.

---
 include/linux/resctrl.h            | 1 +
 arch/x86/kernel/cpu/resctrl/core.c | 2 ++
 2 files changed, 3 insertions(+)
include/linux/resctrl.h +1 -0
index 058a940c3239..b8a3a11b970d 100644
@@ -170,6 +170,7 @@ struct resctrl_schema;
 enum resctrl_scope {
 	RESCTRL_L2_CACHE = 2,
 	RESCTRL_L3_CACHE = 3,
+	RESCTRL_NODE,
 };
 
 /**
arch/x86/kernel/cpu/resctrl/core.c +2 -0
index 797cb3bf417a..c9315ce8f7bd 100644
@@ -502,6 +502,8 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
 	case RESCTRL_L2_CACHE:
 	case RESCTRL_L3_CACHE:
 		return get_cpu_cacheinfo_id(cpu, scope);
+	case RESCTRL_NODE:
+		return cpu_to_node(cpu);
 	default:
 		break;
 	}
Signature · 1 line
2.41.0
Reviewed-by Babu Moger on v13 5/8
#267 lore raw

Re: [PATCH v13 5/8] x86/resctrl: Add node-scope to the options for feature scope

Quoted 7 lines · Tony Luck

Currently supported resctrl features are all domain scoped the same as the scope of the L2 or L3 caches.

Add RESCTRL_NODE as a new option for features that are scoped at the same granularity as NUMA nodes. This is needed for Intel's Sub-NUMA Cluster (SNC) feature where monitoring features are node scoped.

Quoted 5 lines
Quoted 30 lines
---
  include/linux/resctrl.h            | 1 +
  arch/x86/kernel/cpu/resctrl/core.c | 2 ++
  2 files changed, 3 insertions(+)
include/linux/resctrl.h +1 -0
index 058a940c3239..b8a3a11b970d 100644
@@ -170,6 +170,7 @@ struct resctrl_schema;
  enum resctrl_scope {
  	RESCTRL_L2_CACHE = 2,
  	RESCTRL_L3_CACHE = 3,
+	RESCTRL_NODE,
  };
 
  /**
arch/x86/kernel/cpu/resctrl/core.c +2 -0
index 797cb3bf417a..c9315ce8f7bd 100644
@@ -502,6 +502,8 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
  	case RESCTRL_L2_CACHE:
  	case RESCTRL_L3_CACHE:
  		return get_cpu_cacheinfo_id(cpu, scope);
+	case RESCTRL_NODE:
+		return cpu_to_node(cpu);
  	default:
  		break;
  	}
author maintainer
#268 lore raw

PATCH v13 6/8 x86/resctrl: Introduce snc_nodes_per_l3_cache

In reply to Tony Luck

Intel Sub-NUMA Cluster (SNC) is a feature that subdivides the CPU cores and memory controllers on a socket into two or more groups. These are presented to the operating system as NUMA nodes.

This may enable some workloads to have slightly lower latency to memory as the memory controller(s) in an SNC node are electrically closer to the CPU cores on that SNC node. This cost may be offset by lower bandwidth since the memory accesses for each core can only be interleaved between the memory controllers on the same SNC node.

Resctrl monitoring on an Intel system depends upon attaching RMIDs to tasks to track L3 cache occupancy and memory bandwidth. There is an MSR that controls how the RMIDs are shared between SNC nodes.

The default mode divides them numerically. E.g. when there are two SNC nodes on a socket the lower number half of the RMIDs are given to the first node, the remainder to the second node. This would be difficult to use with the Linux resctrl interface as specific RMID values assigned to resctrl groups are not visible to users.

The other mode divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

Even with this renumbering SNC mode requires several changes in resctrl behavior for correct operation.

Add a global integer "snc_nodes_per_l3_cache" that shows how many SNC nodes share each L3 cache. When "snc_nodes_per_l3_cache" is "1", SNC mode is either not implemented, or not enabled.

Update all places to take appropriate action when SNC mode is enabled:
1) The number of logical RMIDs per L3 cache available for use is the number of physical RMIDs divided by the number of SNC nodes.
2) Likewise the "mon_scale" value must be divided by the number of SNC nodes.
3) The RMID renumbering operates when using the value from the IA32_PQR_ASSOC MSR to count accesses by a task. When reading an RMID counter, adjust from the logical RMID to the physical RMID value for the SNC node that it wishes to read and load the adjusted value into the IA32_QM_EVTSEL MSR.
4) Divide the L3 cache between the SNC nodes. Divide the value reported in the resctrl "size" file by the number of SNC nodes because the effective amount of cache that can be allocated is reduced by that factor.
5) Disable the "-o mba_MBps" mount option in SNC mode because the monitoring is being done per SNC node, while the bandwidth allocation is still done at the L3 cache scope. Trying to use this feedback loop might result in contradictory changes to the throttling level coming from each of the SNC node bandwidth measurements.

---
 arch/x86/kernel/cpu/resctrl/internal.h |  2 ++
 arch/x86/kernel/cpu/resctrl/core.c     |  6 ++++++
 arch/x86/kernel/cpu/resctrl/monitor.c  | 16 +++++++++++++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  5 +++--
 4 files changed, 24 insertions(+), 5 deletions(-)
arch/x86/kernel/cpu/resctrl/internal.h +2 -0
index ce3a70657842..e7a75a439c16 100644
@@ -446,6 +446,8 @@ DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
 extern struct dentry *debugfs_resctrl;
 
+extern unsigned int snc_nodes_per_l3_cache;
+
 enum resctrl_res_level {
 	RDT_RESOURCE_L3,
 	RDT_RESOURCE_L2,
arch/x86/kernel/cpu/resctrl/core.c +6 -0
index c9315ce8f7bd..cf5aba8a74bf 100644
@@ -48,6 +48,12 @@ int max_name_width, max_data_width;
  */
 bool rdt_alloc_capable;
 
+/*
+ * Number of SNC nodes that share each L3 cache.  Default is 1 for
+ * systems that do not support SNC, or have SNC disabled.
+ */
+unsigned int snc_nodes_per_l3_cache = 1;
+
 static void
 mba_wrmsr_intel(struct rdt_ctrl_domain *d, struct msr_param *m,
 		struct rdt_resource *r);
arch/x86/kernel/cpu/resctrl/monitor.c +13 -3
index 4e145f5620b0..30b7c3b9b517 100644
@@ -148,8 +148,18 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
 
 static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 {
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	int cpu = smp_processor_id();
+	int rmid_offset = 0;
 	u64 msr_val;
 
+	/*
+	 * When SNC mode is on, need to compute the offset to read the
+	 * physical RMID counter for the node to which this CPU belongs.
+	 */
+	if (snc_nodes_per_l3_cache > 1)
+		rmid_offset = (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid;
+
 	/*
 	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
 	 * with a valid event code for supported resource type and the bits
@@ -158,7 +168,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
 	 * are error bits.
 	 */
-	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid + rmid_offset);
 	rdmsrl(MSR_IA32_QM_CTR, msr_val);
 
 	if (msr_val & RMID_VAL_ERROR)
@@ -783,8 +793,8 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	int ret;
 
 	resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
-	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
-	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_nodes_per_l3_cache;
+	r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache;
 	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
 
 	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
arch/x86/kernel/cpu/resctrl/rdtgroup.c +3 -2
index 21bbd832f3f2..79d57dade568 100644
@@ -1425,7 +1425,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 		}
 	}
 
-	return size;
+	return size / snc_nodes_per_l3_cache;
 }
 
 /*
@@ -2298,7 +2298,8 @@ static bool supports_mba_mbps(void)
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 
 	return (is_mbm_local_enabled() &&
-		r->alloc_capable && is_mba_linear());
+		r->alloc_capable && is_mba_linear() &&
+		snc_nodes_per_l3_cache == 1);
 }
 
 /*
Signature · 1 line
2.41.0
Reviewed-by Babu Moger on v13 6/8
#269 lore raw

Re: [PATCH v13 6/8] x86/resctrl: Introduce snc_nodes_per_l3_cache

Quoted 51 lines · Tony Luck

Intel Sub-NUMA Cluster (SNC) is a feature that subdivides the CPU cores and memory controllers on a socket into two or more groups. These are presented to the operating system as NUMA nodes.

This may enable some workloads to have slightly lower latency to memory as the memory controller(s) in an SNC node are electrically closer to the CPU cores on that SNC node. This cost may be offset by lower bandwidth since the memory accesses for each core can only be interleaved between the memory controllers on the same SNC node.

Resctrl monitoring on an Intel system depends upon attaching RMIDs to tasks to track L3 cache occupancy and memory bandwidth. There is an MSR that controls how the RMIDs are shared between SNC nodes.

The default mode divides them numerically. E.g. when there are two SNC nodes on a socket the lower number half of the RMIDs are given to the first node, the remainder to the second node. This would be difficult to use with the Linux resctrl interface as specific RMID values assigned to resctrl groups are not visible to users.

The other mode divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

Even with this renumbering SNC mode requires several changes in resctrl behavior for correct operation.

Add a global integer "snc_nodes_per_l3_cache" that shows how many SNC nodes share each L3 cache. When "snc_nodes_per_l3_cache" is "1", SNC mode is either not implemented, or not enabled.

Update all places to take appropriate action when SNC mode is enabled:
1) The number of logical RMIDs per L3 cache available for use is the number of physical RMIDs divided by the number of SNC nodes.
2) Likewise the "mon_scale" value must be divided by the number of SNC nodes.
3) The RMID renumbering operates when using the value from the IA32_PQR_ASSOC MSR to count accesses by a task. When reading an RMID counter, adjust from the logical RMID to the physical RMID value for the SNC node that it wishes to read and load the adjusted value into the IA32_QM_EVTSEL MSR.
4) Divide the L3 cache between the SNC nodes. Divide the value reported in the resctrl "size" file by the number of SNC nodes because the effective amount of cache that can be allocated is reduced by that factor.
5) Disable the "-o mba_MBps" mount option in SNC mode because the monitoring is being done per SNC node, while the bandwidth allocation is still done at the L3 cache scope. Trying to use this feedback loop might result in contradictory changes to the throttling level coming from each of the SNC node bandwidth measurements.

Quoted 5 lines
Quoted 103 lines
---
  arch/x86/kernel/cpu/resctrl/internal.h |  2 ++
  arch/x86/kernel/cpu/resctrl/core.c     |  6 ++++++
  arch/x86/kernel/cpu/resctrl/monitor.c  | 16 +++++++++++++---
  arch/x86/kernel/cpu/resctrl/rdtgroup.c |  5 +++--
  4 files changed, 24 insertions(+), 5 deletions(-)
arch/x86/kernel/cpu/resctrl/internal.h +2 -0
index ce3a70657842..e7a75a439c16 100644
@@ -446,6 +446,8 @@ DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
  extern struct dentry *debugfs_resctrl;
 
+extern unsigned int snc_nodes_per_l3_cache;
+
  enum resctrl_res_level {
  	RDT_RESOURCE_L3,
  	RDT_RESOURCE_L2,
arch/x86/kernel/cpu/resctrl/core.c +6 -0
index c9315ce8f7bd..cf5aba8a74bf 100644
@@ -48,6 +48,12 @@ int max_name_width, max_data_width;
   */
  bool rdt_alloc_capable;
 
+/*
+ * Number of SNC nodes that share each L3 cache.  Default is 1 for
+ * systems that do not support SNC, or have SNC disabled.
+ */
+unsigned int snc_nodes_per_l3_cache = 1;
+
  static void
  mba_wrmsr_intel(struct rdt_ctrl_domain *d, struct msr_param *m,
  		struct rdt_resource *r);
arch/x86/kernel/cpu/resctrl/monitor.c +13 -3
index 4e145f5620b0..30b7c3b9b517 100644
@@ -148,8 +148,18 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
 
  static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
  {
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	int cpu = smp_processor_id();
+	int rmid_offset = 0;
  	u64 msr_val;
 
+	/*
+	 * When SNC mode is on, need to compute the offset to read the
+	 * physical RMID counter for the node to which this CPU belongs.
+	 */
+	if (snc_nodes_per_l3_cache > 1)
+		rmid_offset = (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid;
+
  	/*
  	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
  	 * with a valid event code for supported resource type and the bits
@@ -158,7 +168,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
  	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
  	 * are error bits.
  	 */
-	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid + rmid_offset);
  	rdmsrl(MSR_IA32_QM_CTR, msr_val);
 
  	if (msr_val & RMID_VAL_ERROR)
@@ -783,8 +793,8 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
  	int ret;
 
  	resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
-	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
-	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_nodes_per_l3_cache;
+	r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache;
  	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
 
  	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
arch/x86/kernel/cpu/resctrl/rdtgroup.c +3 -2
index 21bbd832f3f2..79d57dade568 100644
@@ -1425,7 +1425,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
  		}
  	}
 
-	return size;
+	return size / snc_nodes_per_l3_cache;
  }
 
  /*
@@ -2298,7 +2298,8 @@ static bool supports_mba_mbps(void)
  	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 
  	return (is_mbm_local_enabled() &&
-		r->alloc_capable && is_mba_linear());
+		r->alloc_capable && is_mba_linear() &&
+		snc_nodes_per_l3_cache == 1);
  }
 
  /*
author maintainer
#270 lore raw

PATCH v13 7/8 x86/resctrl: Sub NUMA Cluster detection and enable

In reply to Tony Luck

There isn't a simple hardware bit that indicates whether a CPU is running in Sub NUMA Cluster (SNC) mode. Infer the state by comparing the ratio of NUMA nodes to L3 cache instances.

When SNC mode is detected, reconfigure the RMID counters by updating the MSR_RMID_SNC_CONFIG MSR on each socket as CPUs are seen.

Clearing bit zero of the MSR divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

---
 arch/x86/include/asm/msr-index.h   |   1 +
 arch/x86/kernel/cpu/resctrl/core.c | 118 +++++++++++++++++++++++++++++
 2 files changed, 119 insertions(+)
arch/x86/include/asm/msr-index.h +1 -0
index 1d51e1850ed0..94d29d81e6db 100644
@@ -1111,6 +1111,7 @@
 #define MSR_IA32_QM_CTR			0xc8e
 #define MSR_IA32_PQR_ASSOC		0xc8f
 #define MSR_IA32_L3_CBM_BASE		0xc90
+#define MSR_RMID_SNC_CONFIG		0xca0
 #define MSR_IA32_L2_CBM_BASE		0xd10
 #define MSR_IA32_MBA_THRTL_BASE		0xd50
 
arch/x86/kernel/cpu/resctrl/core.c +118 -0

151 lines not on this page · raw message

Signature · 1 line
2.41.0
Reviewed-by Babu Moger on v13 7/8
#271 lore raw

Re: [PATCH v13 7/8] x86/resctrl: Sub NUMA Cluster detection and enable

Quoted 7 lines · Tony Luck

There isn't a simple hardware bit that indicates whether a CPU is running in Sub NUMA Cluster (SNC) mode. Infer the state by comparing the ratio of NUMA nodes to L3 cache instances.

When SNC mode is detected, reconfigure the RMID counters by updating the MSR_RMID_SNC_CONFIG MSR on each socket as CPUs are seen.

Quoted 8 lines

Clearing bit zero of the MSR divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

Quoted 175 lines
---
  arch/x86/include/asm/msr-index.h   |   1 +
  arch/x86/kernel/cpu/resctrl/core.c | 118 +++++++++++++++++++++++++++++
  2 files changed, 119 insertions(+)
arch/x86/include/asm/msr-index.h +1 -0
index 1d51e1850ed0..94d29d81e6db 100644
@@ -1111,6 +1111,7 @@
  #define MSR_IA32_QM_CTR			0xc8e
  #define MSR_IA32_PQR_ASSOC		0xc8f
  #define MSR_IA32_L3_CBM_BASE		0xc90
+#define MSR_RMID_SNC_CONFIG		0xca0
  #define MSR_IA32_L2_CBM_BASE		0xd10
  #define MSR_IA32_MBA_THRTL_BASE		0xd50
 
arch/x86/kernel/cpu/resctrl/core.c +118 -0
index cf5aba8a74bf..1de1c4499b7d 100644
@@ -16,11 +16,14 @@
 
  #define pr_fmt(fmt)	"resctrl: " fmt
 
+#include <linux/cpu.h>
  #include <linux/slab.h>
  #include <linux/err.h>
  #include <linux/cacheinfo.h>
  #include <linux/cpuhotplug.h>
+#include <linux/mod_devicetable.h>
 
+#include <asm/cpu_device_id.h>
  #include <asm/intel-family.h>
  #include <asm/resctrl.h>
  #include "internal.h"
@@ -740,11 +743,42 @@ static void clear_closid_rmid(int cpu)
  	wrmsr(MSR_IA32_PQR_ASSOC, 0, 0);
  }
 
+/*
+ * The power-on reset value of MSR_RMID_SNC_CONFIG is 0x1
+ * which indicates that RMIDs are configured in legacy mode.
+ * This mode is incompatible with Linux resctrl semantics
+ * as RMIDs are partitioned between SNC nodes, which requires
+ * a user to know which RMID is allocated to a task.
+ * Clearing bit 0 reconfigures the RMID counters for use
+ * in Sub NUMA Cluster mode. This mode is better for Linux.
+ * The RMID space is divided between all SNC nodes with the
+ * RMIDs renumbered to start from zero in each node when
+ * couning operations from tasks. Code to read the counters
+ * must adjust RMID counter numbers based on SNC node. See
+ * __rmid_read() for code that does this.
+ */
+static void snc_remap_rmids(int cpu)
+{
+	u64 val;
+
+	/* Only need to enable once per package. */
+	if (cpumask_first(topology_core_cpumask(cpu)) != cpu)
+		return;
+
+	rdmsrl(MSR_RMID_SNC_CONFIG, val);
+	val &= ~BIT_ULL(0);
+	wrmsrl(MSR_RMID_SNC_CONFIG, val);
+}
+
  static int resctrl_online_cpu(unsigned int cpu)
  {
  	struct rdt_resource *r;
 
  	mutex_lock(&rdtgroup_mutex);
+
+	if (snc_nodes_per_l3_cache > 1)
+		snc_remap_rmids(cpu);
+
  	for_each_capable_rdt_resource(r)
  		domain_add_cpu(cpu, r);
  	/* The cpu is set in default rdtgroup after online. */
@@ -999,11 +1033,95 @@ static __init bool get_rdt_resources(void)
  	return (rdt_mon_capable || rdt_alloc_capable);
  }
 
+/* CPU models that support MSR_RMID_SNC_CONFIG */
+static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, 0),
+	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 0),
+	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, 0),
+	X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, 0),
+	{}
+};
+
+/*
+ * There isn't a simple hardware bit that indicates whether a CPU is running
+ * in Sub NUMA Cluster (SNC) mode. Infer the state by comparing the
+ * ratio of NUMA nodes to L3 cache instances.
+ * It is not possible to accurately determine SNC state if the system is
+ * booted with a maxcpus=N parameter. That distorts the ratio of SNC nodes
+ * to L3 caches. It will be OK if system is booted with hyperthreading
+ * disabled (since this doesn't affect the ratio).
+ */
+static __init int snc_get_config(void)
+{
+	unsigned long *node_caches;
+	int mem_only_nodes = 0;
+	int cpu, node, ret;
+	int num_l3_caches;
+	int cache_id;
+
+	if (!x86_match_cpu(snc_cpu_ids))
+		return 1;
+
+	node_caches = bitmap_zalloc(num_possible_cpus(), GFP_KERNEL);
+	if (!node_caches)
+		return 1;
+
+	cpus_read_lock();
+
+	if (num_online_cpus() != num_present_cpus())
+		pr_warn("Some CPUs offline, SNC detection may be incorrect\n");
+
+	for_each_node(node) {
+		cpu = cpumask_first(cpumask_of_node(node));
+		if (cpu < nr_cpu_ids) {
+			cache_id = get_cpu_cacheinfo_id(cpu, 3);
+			if (cache_id != -1)
+				set_bit(cache_id, node_caches);
+		} else {
+			mem_only_nodes++;
+		}
+	}
+	cpus_read_unlock();
+
+	num_l3_caches = bitmap_weight(node_caches, num_possible_cpus());
+	kfree(node_caches);
+
+	if (!num_l3_caches)
+		goto insane;
+
+	/* sanity check #1: Number of CPU nodes must be multiple of num_l3_caches */
+	if ((nr_node_ids - mem_only_nodes) % num_l3_caches)
+		goto insane;
+
+	ret = (nr_node_ids - mem_only_nodes) / num_l3_caches;
+
+	/* sanity check #2: Only valid results are 1, 2, 3, 4 */
+	switch (ret) {
+	case 1:
+		break;
+	case 2:
+	case 3:
+	case 4:
+		rdt_resources_all[RDT_RESOURCE_L3].r_resctrl.mon_scope = RESCTRL_NODE;
+		break;
+	default:
+		goto insane;
+	}
+
+	return ret;
+insane:
+	pr_warn("SNC insanity: CPU nodes = %d num_l3_caches = %d\n",
+		(nr_node_ids - mem_only_nodes), num_l3_caches);
+	return 1;
+}
+
  static __init void rdt_init_res_defs_intel(void)
  {
  	struct rdt_hw_resource *hw_res;
  	struct rdt_resource *r;
 
+	snc_nodes_per_l3_cache = snc_get_config();
+
  	for_each_rdt_resource(r) {
  		hw_res = resctrl_to_arch_res(r);
 
author maintainer
#272 lore raw

PATCH v13 8/8 x86/resctrl: Update documentation with Sub-NUMA cluster changes

In reply to Tony Luck

With Sub-NUMA Cluster mode enabled the scope of monitoring resources is per-NODE instead of per-L3 cache. Suffixes of directories with "L3" in their name refer to Sub-NUMA nodes instead of L3 cache ids.

Users should be aware that SNC mode also affects the amount of L3 cache available for allocation within each SNC node.

---
 Documentation/arch/x86/resctrl.rst | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)
Documentation/arch/x86/resctrl.rst +21 -4
index a6279df64a9d..15f1cff6ee76 100644
@@ -366,10 +366,10 @@ When control is enabled all CTRL_MON groups will also contain:
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
-	This contains a set of files organized by L3 domain and by
-	RDT event. E.g. on a system with two L3 domains there will
-	be subdirectories "mon_L3_00" and "mon_L3_01".	Each of these
-	directories have one file per event (e.g. "llc_occupancy",
+	This contains a set of files organized by L3 domain or by NUMA
+	node (depending on whether Sub-NUMA Cluster (SNC) mode is disabled
+	or enabled respectively) and by RDT event.  Each of these
+	directories has one file per event (e.g. "llc_occupancy",
 	"mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
 	files provide a read out of the current value of the event for
 	all tasks in the group. In CTRL_MON groups these files provide
@@ -478,6 +478,23 @@ if non-contiguous 1s value is supported. On a system with a 20-bit mask
 each bit represents 5% of the capacity of the cache. You could partition
 the cache into four equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
 
+Notes on Sub-NUMA Cluster mode
+==============================
+When SNC mode is enabled, Linux may load balance tasks between Sub-NUMA
+nodes much more readily than between regular NUMA nodes since the CPUs
+on Sub-NUMA nodes share the same L3 cache and the system may report
+the NUMA distance between Sub-NUMA nodes with a lower value than used
+for regular NUMA nodes.  Users who do not bind tasks to the CPUs of a
+specific Sub-NUMA node must read the "llc_occupancy", "mbm_total_bytes",
+and "mbm_local_bytes" for all Sub-NUMA nodes where the tasks may execute
+to get the full view of traffic for which the tasks were the source.
+
+The cache allocation feature still provides the same number of
+bits in a mask to control allocation into the L3 cache, but each
+of those ways has its capacity reduced because the cache is divided
+between the SNC nodes. The values reported in the resctrl
+"size" files are adjusted accordingly.
+
 Memory bandwidth Allocation and monitoring
 ==========================================
 
Signature · 1 line
2.41.0
Reviewed-by Babu Moger on v13 8/8
#273 lore raw

Re: [PATCH v13 8/8] x86/resctrl: Update documentation with Sub-NUMA cluster changes

Quoted 4 lines · Tony Luck

With Sub-NUMA Cluster mode enabled the scope of monitoring resources is per-NODE instead of per-L3 cache. Suffixes of directories with "L3" in their name refer to Sub-NUMA nodes instead of L3 cache ids.

Quoted 8 lines

Users should be aware that SNC mode also affects the amount of L3 cache available for allocation within each SNC node.

Quoted 47 lines
---
  Documentation/arch/x86/resctrl.rst | 25 +++++++++++++++++++++----
  1 file changed, 21 insertions(+), 4 deletions(-)
Documentation/arch/x86/resctrl.rst +21 -4
index a6279df64a9d..15f1cff6ee76 100644
@@ -366,10 +366,10 @@ When control is enabled all CTRL_MON groups will also contain:
  When monitoring is enabled all MON groups will also contain:
 
  "mon_data":
-	This contains a set of files organized by L3 domain and by
-	RDT event. E.g. on a system with two L3 domains there will
-	be subdirectories "mon_L3_00" and "mon_L3_01".	Each of these
-	directories have one file per event (e.g. "llc_occupancy",
+	This contains a set of files organized by L3 domain or by NUMA
+	node (depending on whether Sub-NUMA Cluster (SNC) mode is disabled
+	or enabled respectively) and by RDT event.  Each of these
+	directories has one file per event (e.g. "llc_occupancy",
  	"mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
  	files provide a read out of the current value of the event for
  	all tasks in the group. In CTRL_MON groups these files provide
@@ -478,6 +478,23 @@ if non-contiguous 1s value is supported. On a system with a 20-bit mask
  each bit represents 5% of the capacity of the cache. You could partition
  the cache into four equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
 
+Notes on Sub-NUMA Cluster mode
+==============================
+When SNC mode is enabled, Linux may load balance tasks between Sub-NUMA
+nodes much more readily than between regular NUMA nodes since the CPUs
+on Sub-NUMA nodes share the same L3 cache and the system may report
+the NUMA distance between Sub-NUMA nodes with a lower value than used
+for regular NUMA nodes.  Users who do not bind tasks to the CPUs of a
+specific Sub-NUMA node must read the "llc_occupancy", "mbm_total_bytes",
+and "mbm_local_bytes" for all Sub-NUMA nodes where the tasks may execute
+to get the full view of traffic for which the tasks were the source.
+
+The cache allocation feature still provides the same number of
+bits in a mask to control allocation into the L3 cache, but each
+of those ways has its capacity reduced because the cache is divided
+between the SNC nodes. The values reported in the resctrl
+"size" files are adjusted accordingly.
+
  Memory bandwidth Allocation and monitoring
  ==========================================
 
#274 lore raw

Re: [PATCH v13 0/8] Add support for Sub-NUMA cluster (SNC) systems

In reply to Tony Luck

Hi Tony,

Tested the series on AMD system. Just ran few basic tests. Everything looking good.

Thanks

Babu

Quoted 61 lines · Tony Luck

The Sub-NUMA cluster feature on some Intel processors partitions the CPUs that share an L3 cache into two or more sets. This plays havoc with the Resource Director Technology (RDT) monitoring features. Prior to this patch Intel has advised that SNC and RDT are incompatible.

Some of these CPU support an MSR that can partition the RMID counters in the same way. This allows monitoring features to be used. With the caveat that users must be aware that Linux may migrate tasks more frequently between SNC nodes than between "regular" NUMA nodes, so reading counters from all SNC nodes may be needed to get a complete picture of activity for tasks.

Cache and memory bandwidth allocation features continue to operate at the scope of the L3 cache.

Changes since v12:

All:
Reinette - put commit tags in right order for TIP (Tested-by before Reviewed-by)

Patch 7:
Fam Zheng - Check for -1 return from get_cpu_cacheinfo_id() and increase size of bitmap tracking # of L3 instances. Reinette - Add extra sanity checks. Note that this patch has some additional tweaks beyond the e-mail discussion.
1) "3" is a valid return in addition to 1, 2, 4
2) Added a warning if the sanity checks fail that prints number of CPU nodes and number of L3 cache instances that were found.

Patch 8:
Babu - Fix grammar with an additional comma.

Tony Luck (8):
x86/resctrl: Prepare for new domain scope x86/resctrl: Prepare to split rdt_domain structure x86/resctrl: Prepare for different scope for control/monitor
operations
x86/resctrl: Split the rdt_domain and rdt_hw_domain structures x86/resctrl: Add node-scope to the options for feature scope x86/resctrl: Introduce snc_nodes_per_l3_cache x86/resctrl: Sub NUMA Cluster detection and enable x86/resctrl: Update documentation with Sub-NUMA cluster changes

  Documentation/arch/x86/resctrl.rst        |  25 +-
  include/linux/resctrl.h                   |  85 +++--
  arch/x86/include/asm/msr-index.h          |   1 +
  arch/x86/kernel/cpu/resctrl/internal.h    |  66 ++--
  arch/x86/kernel/cpu/resctrl/core.c        | 433 +++++++++++++++++-----
  arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  58 +--
  arch/x86/kernel/cpu/resctrl/monitor.c     |  68 ++--
  arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  26 +-
  arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 149 ++++----
  9 files changed, 629 insertions(+), 282 deletions(-)

base-commit: 2cc14f52aeb78ce3f29677c2de1f06c0e91471ab

author maintainer
#275 lore raw

RE: [PATCH v13 0/8] Add support for Sub-NUMA cluster (SNC) systems

Quoted 2 lines

Tested the series on AMD system. Just ran few basic tests. Everything looking good.

Babu,

Thanks for testing. I'll add your Tested-by tag if[1] I make a v14.

-Tony

[1] realistically not if, but when :-(

author maintainer
#276 lore raw

Re: [PATCH v13 0/8] Add support for Sub-NUMA cluster (SNC) systems

In reply to Tony Luck

On Mon, Dec 04, 2023 at 10:53:49AM -0800, Tony Luck wrote:

Boris: I've collected "Reviewed-by:" from Reinette for all patches. Babu sent a Tested-by for the series, and Reviewed-by for each patch just now.

So it's ready to got into your to-be-reviewed queue.

Thanks

-Tony

Quoted 64 lines

The Sub-NUMA cluster feature on some Intel processors partitions the CPUs that share an L3 cache into two or more sets. This plays havoc with the Resource Director Technology (RDT) monitoring features. Prior to this patch Intel has advised that SNC and RDT are incompatible.

Some of these CPU support an MSR that can partition the RMID counters in the same way. This allows monitoring features to be used. With the caveat that users must be aware that Linux may migrate tasks more frequently between SNC nodes than between "regular" NUMA nodes, so reading counters from all SNC nodes may be needed to get a complete picture of activity for tasks.

Cache and memory bandwidth allocation features continue to operate at the scope of the L3 cache.

Changes since v12:

All:
Reinette - put commit tags in right order for TIP (Tested-by before Reviewed-by)

Patch 7:
Fam Zheng - Check for -1 return from get_cpu_cacheinfo_id() and increase size of bitmap tracking # of L3 instances. Reinette - Add extra sanity checks. Note that this patch has some additional tweaks beyond the e-mail discussion.
1) "3" is a valid return in addition to 1, 2, 4
2) Added a warning if the sanity checks fail that prints number of CPU nodes and number of L3 cache instances that were found.

Patch 8:
Babu - Fix grammar with an additional comma.

Tony Luck (8):
x86/resctrl: Prepare for new domain scope x86/resctrl: Prepare to split rdt_domain structure x86/resctrl: Prepare for different scope for control/monitor
operations
x86/resctrl: Split the rdt_domain and rdt_hw_domain structures x86/resctrl: Add node-scope to the options for feature scope x86/resctrl: Introduce snc_nodes_per_l3_cache x86/resctrl: Sub NUMA Cluster detection and enable x86/resctrl: Update documentation with Sub-NUMA cluster changes

 Documentation/arch/x86/resctrl.rst        |  25 +-
 include/linux/resctrl.h                   |  85 +++--
 arch/x86/include/asm/msr-index.h          |   1 +
 arch/x86/kernel/cpu/resctrl/internal.h    |  66 ++--
 arch/x86/kernel/cpu/resctrl/core.c        | 433 +++++++++++++++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  58 +--
 arch/x86/kernel/cpu/resctrl/monitor.c     |  68 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  26 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 149 ++++----
 9 files changed, 629 insertions(+), 282 deletions(-)

base-commit: 2cc14f52aeb78ce3f29677c2de1f06c0e91471ab

Signature · 1 line
2.41.0
author maintainer
#277 lore raw

v14 cover Add support for Sub-NUMA cluster (SNC) systems

In reply to Tony Luck

The Sub-NUMA cluster feature on some Intel processors partitions the CPUs that share an L3 cache into two or more sets. This plays havoc with the Resource Director Technology (RDT) monitoring features. Prior to this patch Intel has advised that SNC and RDT are incompatible.

Some of these CPU support an MSR that can partition the RMID counters in the same way. This allows monitoring features to be used. With the caveat that users must be aware that Linux may migrate tasks more frequently between SNC nodes than between "regular" NUMA nodes, so reading counters from all SNC nodes may be needed to get a complete picture of activity for tasks.

Cache and memory bandwidth allocation features continue to operate at the scope of the L3 cache.

---
Changes since v13:

Rebase to tip x86/cache
fc747eebef73 ("x86/resctrl: Remove redundant variable in mbm_config_write_domain()")

Applied all Reviewed and Tested tags

Tony Luck (8):
x86/resctrl: Prepare for new domain scope x86/resctrl: Prepare to split rdt_domain structure x86/resctrl: Prepare for different scope for control/monitor
operations
x86/resctrl: Split the rdt_domain and rdt_hw_domain structures x86/resctrl: Add node-scope to the options for feature scope x86/resctrl: Introduce snc_nodes_per_l3_cache x86/resctrl: Sub NUMA Cluster detection and enable x86/resctrl: Update documentation with Sub-NUMA cluster changes

 Documentation/arch/x86/resctrl.rst        |  25 +-
 include/linux/resctrl.h                   |  85 +++--
 arch/x86/include/asm/msr-index.h          |   1 +
 arch/x86/kernel/cpu/resctrl/internal.h    |  66 ++--
 arch/x86/kernel/cpu/resctrl/core.c        | 433 +++++++++++++++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  58 +--
 arch/x86/kernel/cpu/resctrl/monitor.c     |  68 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  26 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 149 ++++----
 9 files changed, 629 insertions(+), 282 deletions(-)

base-commit: fc747eebef734563cf68a512f57937c8f231834a

Signature · 1 line
2.43.0
author maintainer
#278 lore raw

PATCH v14 1/8 x86/resctrl: Prepare for new domain scope

Resctrl resources operate on subsets of CPUs in the system with the defining attribute of each subset being an instance of a particular level of cache. E.g. all CPUs sharing an L3 cache would be part of the same domain.

In preparation for features that are scoped at the NUMA node level change the code from explicit references to "cache_level" to a more generic scope. At this point the only options for this scope are groups of CPUs that share an L2 cache or L3 cache.

Clean up the error handling when looking up domains. Report invalid id's before calling rdt_find_domain() in preparation for better messages when scope can be other than cache scope. This means that rdt_find_domain() will never return an error. So remove checks for error from the callsites.

---
 include/linux/resctrl.h                   |  9 ++++-
 arch/x86/kernel/cpu/resctrl/core.c        | 45 ++++++++++++++++-------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  2 +-
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  6 ++-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  5 ++-
 5 files changed, 48 insertions(+), 19 deletions(-)
include/linux/resctrl.h +7 -2
index 66942d7fba7f..7d4eb7df611d 100644
@@ -144,13 +144,18 @@ struct resctrl_membw {
 struct rdt_parse_data;
 struct resctrl_schema;
 
+enum resctrl_scope {
+	RESCTRL_L2_CACHE = 2,
+	RESCTRL_L3_CACHE = 3,
+};
+
 /**
  * struct rdt_resource - attributes of a resctrl resource
  * @rid:		The index of the resource
  * @alloc_capable:	Is allocation available on this machine
  * @mon_capable:	Is monitor feature available on this machine
  * @num_rmid:		Number of RMIDs available
- * @cache_level:	Which cache level defines scope of this resource
+ * @scope:		Scope of this resource
  * @cache:		Cache allocation related data
  * @membw:		If the component has bandwidth controls, their properties.
  * @domains:		All domains for this resource
@@ -168,7 +173,7 @@ struct rdt_resource {
 	bool			alloc_capable;
 	bool			mon_capable;
 	int			num_rmid;
-	int			cache_level;
+	enum resctrl_scope	scope;
 	struct resctrl_cache	cache;
 	struct resctrl_membw	membw;
 	struct list_head	domains;
arch/x86/kernel/cpu/resctrl/core.c +31 -14

105 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +1 -1
index beccb0e87ba7..3f8891d57fac 100644
@@ -563,7 +563,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 	r = &rdt_resources_all[resid].r_resctrl;
 	d = rdt_find_domain(r, domid, NULL);
-	if (IS_ERR_OR_NULL(d)) {
+	if (!d) {
 		ret = -ENOENT;
 		goto out;
 	}
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +5 -1
index 8f559eeae08e..2a682da9f43a 100644
@@ -292,10 +292,14 @@ 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;
 	struct cpu_cacheinfo *ci;
 	int ret;
 	int i;
 
+	if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
+		return -ENODEV;
+
 	/* Pick the first cpu we find that is associated with the cache. */
 	plr->cpu = cpumask_first(&plr->d->cpu_mask);
 
@@ -311,7 +315,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
 
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == plr->s->res->cache_level) {
+		if (ci->info_list[i].level == scope) {
 			plr->line_size = ci->info_list[i].coherency_line_size;
 			return 0;
 		}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +4 -1
index aa24343f1d23..1a9b2cd99b5f 100644
@@ -1413,10 +1413,13 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 	unsigned int size = 0;
 	int num_b, i;
 
+	if (WARN_ON_ONCE(r->scope != RESCTRL_L2_CACHE && r->scope != RESCTRL_L3_CACHE))
+		return size;
+
 	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
 	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == r->cache_level) {
+		if (ci->info_list[i].level == r->scope) {
 			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
 			break;
 		}
Signature · 1 line
2.43.0
author maintainer
#279 lore raw

PATCH v14 2/8 x86/resctrl: Prepare to split rdt_domain structure

In reply to Tony Luck

The rdt_domain structure is used for both control and monitor features. It is about to be split into separate structures for these two usages because the scope for control and monitoring features for a resource will be different for future resources.

To allow for common code that scans a list of domains looking for a specific domain id, move all the common fields ("list", "id", "cpu_mask") into their own structure within the rdt_domain structure.

---
 include/linux/resctrl.h                   | 16 ++++--
 arch/x86/kernel/cpu/resctrl/core.c        | 26 +++++-----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 22 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 10 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 14 +++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 60 +++++++++++------------
 6 files changed, 78 insertions(+), 70 deletions(-)
include/linux/resctrl.h +12 -4
index 7d4eb7df611d..c4067150a6b7 100644
@@ -53,10 +53,20 @@ struct resctrl_staged_config {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * struct rdt_domain_hdr - common header for different domain types
  * @list:		all instances of this resource
  * @id:			unique id for this instance
  * @cpu_mask:		which CPUs share this resource
+ */
+struct rdt_domain_hdr {
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+};
+
+/**
+ * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * @hdr:		common header for different domain types
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
  * @mbm_local:		saved state for MBM local bandwidth
@@ -71,9 +81,7 @@ struct resctrl_staged_config {
  *			by closid
  */
 struct rdt_domain {
-	struct list_head		list;
-	int				id;
-	struct cpumask			cpu_mask;
+	struct rdt_domain_hdr		hdr;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;
arch/x86/kernel/cpu/resctrl/core.c +13 -13
index 268965c7c7ef..625f75899d7b 100644
@@ -354,9 +354,9 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
 {
 	struct rdt_domain *d;
 
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->cpu_mask))
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
 			return d;
 	}
 
@@ -400,12 +400,12 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	struct list_head *l;
 
 	list_for_each(l, &r->domains) {
-		d = list_entry(l, struct rdt_domain, list);
+		d = list_entry(l, struct rdt_domain, hdr.list);
 		/* When id is found, return its domain. */
-		if (id == d->id)
+		if (id == d->hdr.id)
 			return d;
 		/* Stop searching when finding id's position in sorted list. */
-		if (id < d->id)
+		if (id < d->hdr.id)
 			break;
 	}
 
@@ -528,7 +528,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 	d = rdt_find_domain(r, id, &add_pos);
 	if (d) {
-		cpumask_set_cpu(cpu, &d->cpu_mask);
+		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 		if (r->cache.arch_has_per_cpu_cfg)
 			rdt_domain_reconfigure_cdp(r);
 		return;
@@ -539,8 +539,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 
 	d = &hw_dom->d_resctrl;
-	d->id = id;
-	cpumask_set_cpu(cpu, &d->cpu_mask);
+	d->hdr.id = id;
+	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	rdt_domain_reconfigure_cdp(r);
 
@@ -554,11 +554,11 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	list_add_tail(&d->list, add_pos);
+	list_add_tail(&d->hdr.list, add_pos);
 
 	err = resctrl_online_domain(r, d);
 	if (err) {
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 		domain_free(hw_dom);
 	}
 }
@@ -582,10 +582,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 	}
 	hw_dom = resctrl_to_arch_dom(d);
 
-	cpumask_clear_cpu(cpu, &d->cpu_mask);
-	if (cpumask_empty(&d->cpu_mask)) {
+	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
+	if (cpumask_empty(&d->hdr.cpu_mask)) {
 		resctrl_offline_domain(r, d);
-		list_del(&d->list);
+		list_del(&d->hdr.list);
 
 		/*
 		 * rdt_domain "d" is going to be freed below, so clear
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +11 -11
index 3f8891d57fac..23f8258d36a8 100644
@@ -67,7 +67,7 @@ int parse_bw(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;
 	}
 
@@ -146,7 +146,7 @@ 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;
 	}
 
@@ -226,8 +226,8 @@ static int parse_line(char *line, struct resctrl_schema *s,
 		return -EINVAL;
 	}
 	dom = strim(dom);
-	list_for_each_entry(d, &r->domains, list) {
-		if (d->id == dom_id) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
 			data.buf = dom;
 			data.rdtgrp = rdtgrp;
 			if (r->parse_ctrlval(&data, s, d))
@@ -274,7 +274,7 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
 	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);
+		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
 		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
 
 		return true;
@@ -291,7 +291,7 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 		return -ENOMEM;
 
 	msr_param.res = NULL;
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
 		hw_dom = resctrl_to_arch_dom(d);
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	u32 ctrl_val;
 
 	seq_printf(s, "%*s:", max_name_width, schema->name);
-	list_for_each_entry(dom, &r->domains, list) {
+	list_for_each_entry(dom, &r->domains, hdr.list) {
 		if (sep)
 			seq_puts(s, ";");
 
@@ -476,7 +476,7 @@ 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 +505,7 @@ 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 {
@@ -536,7 +536,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	rr->val = 0;
 	rr->first = first;
 
-	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	smp_call_function_any(&d->hdr.cpu_mask, mon_event_count, rr, 1);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
arch/x86/kernel/cpu/resctrl/monitor.c +5 -5
index 3a6c069614eb..310ab05f0cb7 100644
@@ -238,7 +238,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	u64 msr_val, chunks;
 	int ret;
 
-	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+	if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask))
 		return -EINVAL;
 
 	ret = __rmid_read(rmid, eventid, &msr_val);
@@ -340,8 +340,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
 	entry->busy = 0;
 	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, list) {
-		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
+	list_for_each_entry(d, &r->domains, hdr.list) {
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
 			err = resctrl_arch_rmid_read(r, d, entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
 						     &val);
@@ -639,7 +639,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
 	dom->cqm_work_cpu = cpu;
 
 	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
@@ -686,7 +686,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
 
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		return;
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any(&dom->hdr.cpu_mask);
 	dom->mbm_work_cpu = cpu;
 	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
 }
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +7 -7
index 2a682da9f43a..fcbd99e2eb66 100644
@@ -221,7 +221,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
 	int cpu;
 	int ret;
 
-	for_each_cpu(cpu, &plr->d->cpu_mask) {
+	for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
 		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
 		if (!pm_req) {
 			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
@@ -301,7 +301,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 		return -ENODEV;
 
 	/* Pick the first cpu we find that is associated with the cache. */
-	plr->cpu = cpumask_first(&plr->d->cpu_mask);
+	plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 
 	if (!cpu_online(plr->cpu)) {
 		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
@@ -856,10 +856,10 @@ 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, list) {
+		list_for_each_entry(d_i, &r->domains, hdr.list) {
 			if (d_i->plr)
 				cpumask_or(cpu_with_psl, cpu_with_psl,
-					   &d_i->cpu_mask);
+					   &d_i->hdr.cpu_mask);
 		}
 	}
 
@@ -867,7 +867,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	 * Next test if new pseudo-locked region would intersect with
 	 * existing region.
 	 */
-	if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+	if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
 		ret = true;
 
 	free_cpumask_var(cpu_with_psl);
@@ -1199,7 +1199,7 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 	}
 
 	plr->thread_done = 0;
-	cpu = cpumask_first(&plr->d->cpu_mask);
+	cpu = cpumask_first(&plr->d->hdr.cpu_mask);
 	if (!cpu_online(cpu)) {
 		ret = -ENODEV;
 		goto out;
@@ -1529,7 +1529,7 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
 	 * may be scheduled elsewhere and invalidate entries in the
 	 * pseudo-locked region.
 	 */
-	if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) {
+	if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
 		mutex_unlock(&rdtgroup_mutex);
 		return -EINVAL;
 	}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +30 -30

220 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#280 lore raw

PATCH v14 3/8 x86/resctrl: Prepare for different scope for control/monitor operations

In reply to Tony Luck

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.

---
 include/linux/resctrl.h                   |  25 ++-
 arch/x86/kernel/cpu/resctrl/internal.h    |   6 +-
 arch/x86/kernel/cpu/resctrl/core.c        | 211 ++++++++++++++++------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  12 +-
 arch/x86/kernel/cpu/resctrl/monitor.c     |   4 +-
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |   4 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  55 +++---
 7 files changed, 220 insertions(+), 97 deletions(-)
include/linux/resctrl.h +19 -6
index c4067150a6b7..35e700edc6e6 100644
@@ -52,15 +52,22 @@ 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;
 };
 
@@ -163,10 +170,12 @@ 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:		All domains for this resource
+ * @ctrl_domains:	Control domains for this resource
+ * @mon_domains:	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.
@@ -181,10 +190,12 @@ 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;
@@ -230,8 +241,10 @@ 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);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
arch/x86/kernel/cpu/resctrl/internal.h +3 -3
index 52e7e7deee10..c2b0f563ddf9 100644
@@ -518,8 +518,8 @@ 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,
@@ -538,7 +538,7 @@ 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);
 int closids_supported(void);
 void closid_free(int closid);
 int alloc_rmid(void);
arch/x86/kernel/cpu/resctrl/core.c +157 -54

338 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +7 -5
index 23f8258d36a8..0b4136c42762 100644
@@ -226,7 +226,7 @@ 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;
@@ -318,7 +318,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 		return -ENOMEM;
 
 	msr_param.res = NULL;
-	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 (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -466,7 +466,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	u32 ctrl_val;
 
 	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, ";");
 
@@ -542,6 +542,7 @@ 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;
@@ -562,11 +563,12 @@ 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/monitor.c +2 -2
index 310ab05f0cb7..749f6662e7ca 100644
@@ -340,7 +340,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 
 	entry->busy = 0;
 	cpu = get_cpu();
-	list_for_each_entry(d, &r->domains, hdr.list) {
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
 		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) {
 			err = resctrl_arch_rmid_read(r, d, entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
@@ -532,7 +532,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	rmid = rgrp->mon.rmid;
 	pmbm_data = &dom_mbm->mbm_local[rmid];
 
-	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 +2 -2
index fcbd99e2eb66..ed6d59af1cef 100644
@@ -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 cpu_cacheinfo *ci;
 	int ret;
 	int i;
@@ -856,7 +856,7 @@ 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 +30 -25

170 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#281 lore raw

PATCH v14 4/8 x86/resctrl: Split the rdt_domain and rdt_hw_domain structures

In reply to Tony Luck

The same rdt_domain structure is used for both control and monitor functions. But this results in wasted memory as some of the fields are only used by control functions, while most are only used for monitor functions.

Split into separate rdt_ctrl_domain and rdt_mon_domain structures with just the fields required for control and monitoring respectively.

Similar split of the rdt_hw_domain structure into rdt_hw_ctrl_domain and rdt_hw_mon_domain.

---
 include/linux/resctrl.h                   | 48 +++++++------
 arch/x86/kernel/cpu/resctrl/internal.h    | 60 ++++++++++------
 arch/x86/kernel/cpu/resctrl/core.c        | 87 ++++++++++++-----------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 32 ++++-----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 40 +++++------
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  6 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 62 ++++++++--------
 7 files changed, 182 insertions(+), 153 deletions(-)
include/linux/resctrl.h +28 -20
index 35e700edc6e6..058a940c3239 100644
@@ -72,7 +72,23 @@ struct rdt_domain_hdr {
 };
 
 /**
- * struct rdt_domain - group of CPUs sharing a resctrl resource
+ * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource
+ * @hdr:		common header for different domain types
+ * @plr:		pseudo-locked region (if any) associated with domain
+ * @staged_config:	parsed configuration to be applied
+ * @mbps_val:		When mba_sc is enabled, this holds the array of user
+ *			specified control values for mba_sc in MBps, indexed
+ *			by closid
+ */
+struct rdt_ctrl_domain {
+	struct rdt_domain_hdr		hdr;
+	struct pseudo_lock_region	*plr;
+	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
+	u32				*mbps_val;
+};
+
+/**
+ * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
  * @hdr:		common header for different domain types
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
@@ -81,13 +97,8 @@ struct rdt_domain_hdr {
  * @cqm_limbo:		worker to periodically read CQM h/w counters
  * @mbm_work_cpu:	worker CPU for MBM h/w counters
  * @cqm_work_cpu:	worker CPU for CQM h/w counters
- * @plr:		pseudo-locked region (if any) associated with domain
- * @staged_config:	parsed configuration to be applied
- * @mbps_val:		When mba_sc is enabled, this holds the array of user
- *			specified control values for mba_sc in MBps, indexed
- *			by closid
  */
-struct rdt_domain {
+struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
@@ -96,9 +107,6 @@ struct rdt_domain {
 	struct delayed_work		cqm_limbo;
 	int				mbm_work_cpu;
 	int				cqm_work_cpu;
-	struct pseudo_lock_region	*plr;
-	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
-	u32				*mbps_val;
 };
 
 /**
@@ -202,7 +210,7 @@ struct rdt_resource {
 	const char		*format_str;
 	int			(*parse_ctrlval)(struct rdt_parse_data *data,
 						 struct resctrl_schema *s,
-						 struct rdt_domain *d);
+						 struct rdt_ctrl_domain *d);
 	struct list_head	evt_list;
 	unsigned long		fflags;
 	bool			cdp_capable;
@@ -236,15 +244,15 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
  * Update the ctrl_val and apply this config right now.
  * Must be called on one of the domain's CPUs.
  */
-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);
 
-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);
-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);
+int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
+void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
@@ -260,7 +268,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain *d);
  * Return:
  * 0 on success, or -EIO, -EINVAL etc on error.
  */
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 rmid, enum resctrl_event_id eventid, u64 *val);
 
 /**
@@ -273,7 +281,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 			     u32 rmid, enum resctrl_event_id eventid);
 
 /**
@@ -285,7 +293,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d);
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d);
 
 extern unsigned int resctrl_rmid_realloc_threshold;
 extern unsigned int resctrl_rmid_realloc_limit;
arch/x86/kernel/cpu/resctrl/internal.h +38 -22

131 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/core.c +46 -41

246 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +16 -16
index 0b4136c42762..08fc97ce4135 100644
@@ -58,7 +58,7 @@ 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;
@@ -137,7 +137,7 @@ 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;
@@ -206,8 +206,8 @@ 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;
 
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
@@ -267,11 +267,11 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
 	}
 }
 
-static bool apply_config(struct rdt_hw_domain *hw_dom,
+static bool apply_config(struct rdt_hw_ctrl_domain *hw_dom,
 			 struct resctrl_staged_config *cfg, u32 idx,
 			 cpumask_var_t cpu_mask)
 {
-	struct rdt_domain *dom = &hw_dom->d_resctrl;
+	struct rdt_ctrl_domain *dom = &hw_dom->d_resctrl;
 
 	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
 		cpumask_set_cpu(cpumask_any(&dom->hdr.cpu_mask), cpu_mask);
@@ -283,11 +283,11 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
 	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;
 
@@ -307,11 +307,11 @@ 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))
@@ -319,7 +319,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 
 	msr_param.res = NULL;
 	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		hw_dom = resctrl_to_arch_dom(d);
+		hw_dom = resctrl_to_arch_ctrl_dom(d);
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
 			if (!cfg->have_new_ctrl)
@@ -449,10 +449,10 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	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];
@@ -461,7 +461,7 @@ 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;
 
@@ -523,7 +523,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 }
 
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
 		    int evtid, int first)
 {
 	/*
@@ -543,11 +543,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
 	struct rdt_domain_hdr *hdr;
+	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;
 
@@ -568,7 +568,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		ret = -ENOENT;
 		goto out;
 	}
-	d = container_of(hdr, struct rdt_domain, hdr);
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
 
 	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
arch/x86/kernel/cpu/resctrl/monitor.c +20 -20
index 749f6662e7ca..e51bafc1945b 100644
@@ -170,7 +170,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 	return 0;
 }
 
-static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
+static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_dom,
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
 {
@@ -189,10 +189,10 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 	return NULL;
 }
 
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 			     u32 rmid, enum resctrl_event_id eventid)
 {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct arch_mbm_state *am;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
@@ -208,9 +208,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
  * Assumes that hardware counters are also reset and thus that there is
  * no need to record initial non-zero counts.
  */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d)
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 
 	if (is_mbm_total_enabled())
 		memset(hw_dom->arch_mbm_total, 0,
@@ -229,11 +229,11 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 	return chunks >> shift;
 }
 
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 rmid, enum resctrl_event_id eventid, u64 *val)
 {
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
 	u64 msr_val, chunks;
 	int ret;
@@ -266,7 +266,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  * decrement the count. If the busy count gets to zero on an RMID, we
  * free the RMID
  */
-void __check_limbo(struct rdt_domain *d, bool force_free)
+void __check_limbo(struct rdt_mon_domain *d, bool force_free)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	struct rmid_entry *entry;
@@ -305,7 +305,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 	}
 }
 
-bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d)
+bool has_busy_rmid(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid;
 }
@@ -334,7 +334,7 @@ int alloc_rmid(void)
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_domain *d;
+	struct rdt_mon_domain *d;
 	int cpu, err;
 	u64 val = 0;
 
@@ -383,7 +383,7 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid,
+static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 rmid,
 				       enum resctrl_event_id evtid)
 {
 	switch (evtid) {
@@ -513,12 +513,12 @@ void mon_event_count(void *info)
  * throttle MSRs already have low percentage values.  To avoid
  * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
  */
-static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
+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;
 	struct rdt_resource *r_mba;
-	struct rdt_domain *dom_mba;
 	struct list_head *head;
 	struct rdtgroup *entry;
 	u32 cur_bw, user_bw;
@@ -578,7 +578,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_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_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, int rmid)
 {
 	struct rmid_read rr;
 
@@ -618,13 +618,13 @@ void cqm_handle_limbo(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
 	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
 	struct rdt_resource *r;
-	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, cqm_limbo.work);
+	d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
 
@@ -634,7 +634,7 @@ void cqm_handle_limbo(struct work_struct *work)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
@@ -650,9 +650,9 @@ void mbm_handle_overflow(struct work_struct *work)
 	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
 	struct rdtgroup *prgrp, *crgrp;
 	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
 	struct list_head *head;
 	struct rdt_resource *r;
-	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
 
@@ -660,7 +660,7 @@ void mbm_handle_overflow(struct work_struct *work)
 		goto out_unlock;
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, mbm_over.work);
+	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		mbm_update(r, d, prgrp->mon.rmid);
@@ -679,7 +679,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +3 -3
index ed6d59af1cef..08d35f828bc3 100644
@@ -814,7 +814,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
  * Return: true if @cbm overlaps with pseudo-locked region on @d, false
  * otherwise.
  */
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm)
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
 {
 	unsigned int cbm_len;
 	unsigned long cbm_b;
@@ -841,11 +841,11 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm
  *         if it is not possible to test due to memory allocation issue,
  *         false otherwise.
  */
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
 {
+	struct rdt_ctrl_domain *d_i;
 	cpumask_var_t cpu_with_psl;
 	struct rdt_resource *r;
-	struct rdt_domain *d_i;
 	bool ret = false;
 
 	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
arch/x86/kernel/cpu/resctrl/rdtgroup.c +31 -31

252 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#282 lore raw

PATCH v14 5/8 x86/resctrl: Add node-scope to the options for feature scope

In reply to Tony Luck

Currently supported resctrl features are all domain scoped the same as the scope of the L2 or L3 caches.

Add RESCTRL_NODE as a new option for features that are scoped at the same granularity as NUMA nodes. This is needed for Intel's Sub-NUMA Cluster (SNC) feature where monitoring features are node scoped.

---
 include/linux/resctrl.h            | 1 +
 arch/x86/kernel/cpu/resctrl/core.c | 2 ++
 2 files changed, 3 insertions(+)
include/linux/resctrl.h +1 -0
index 058a940c3239..b8a3a11b970d 100644
@@ -170,6 +170,7 @@ struct resctrl_schema;
 enum resctrl_scope {
 	RESCTRL_L2_CACHE = 2,
 	RESCTRL_L3_CACHE = 3,
+	RESCTRL_NODE,
 };
 
 /**
arch/x86/kernel/cpu/resctrl/core.c +2 -0
index d7c0651d337d..27523841f9fd 100644
@@ -500,6 +500,8 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
 	case RESCTRL_L2_CACHE:
 	case RESCTRL_L3_CACHE:
 		return get_cpu_cacheinfo_id(cpu, scope);
+	case RESCTRL_NODE:
+		return cpu_to_node(cpu);
 	default:
 		break;
 	}
Signature · 1 line
2.43.0
author maintainer
#283 lore raw

PATCH v14 6/8 x86/resctrl: Introduce snc_nodes_per_l3_cache

In reply to Tony Luck

Intel Sub-NUMA Cluster (SNC) is a feature that subdivides the CPU cores and memory controllers on a socket into two or more groups. These are presented to the operating system as NUMA nodes.

This may enable some workloads to have slightly lower latency to memory as the memory controller(s) in an SNC node are electrically closer to the CPU cores on that SNC node. This cost may be offset by lower bandwidth since the memory accesses for each core can only be interleaved between the memory controllers on the same SNC node.

Resctrl monitoring on an Intel system depends upon attaching RMIDs to tasks to track L3 cache occupancy and memory bandwidth. There is an MSR that controls how the RMIDs are shared between SNC nodes.

The default mode divides them numerically. E.g. when there are two SNC nodes on a socket the lower number half of the RMIDs are given to the first node, the remainder to the second node. This would be difficult to use with the Linux resctrl interface as specific RMID values assigned to resctrl groups are not visible to users.

The other mode divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

Even with this renumbering SNC mode requires several changes in resctrl behavior for correct operation.

Add a global integer "snc_nodes_per_l3_cache" that shows how many SNC nodes share each L3 cache. When "snc_nodes_per_l3_cache" is "1", SNC mode is either not implemented, or not enabled.

Update all places to take appropriate action when SNC mode is enabled:
1) The number of logical RMIDs per L3 cache available for use is the number of physical RMIDs divided by the number of SNC nodes.
2) Likewise the "mon_scale" value must be divided by the number of SNC nodes.
3) The RMID renumbering operates when using the value from the IA32_PQR_ASSOC MSR to count accesses by a task. When reading an RMID counter, adjust from the logical RMID to the physical RMID value for the SNC node that it wishes to read and load the adjusted value into the IA32_QM_EVTSEL MSR.
4) Divide the L3 cache between the SNC nodes. Divide the value reported in the resctrl "size" file by the number of SNC nodes because the effective amount of cache that can be allocated is reduced by that factor.
5) Disable the "-o mba_MBps" mount option in SNC mode because the monitoring is being done per SNC node, while the bandwidth allocation is still done at the L3 cache scope. Trying to use this feedback loop might result in contradictory changes to the throttling level coming from each of the SNC node bandwidth measurements.

---
 arch/x86/kernel/cpu/resctrl/internal.h |  2 ++
 arch/x86/kernel/cpu/resctrl/core.c     |  6 ++++++
 arch/x86/kernel/cpu/resctrl/monitor.c  | 16 +++++++++++++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  5 +++--
 4 files changed, 24 insertions(+), 5 deletions(-)
arch/x86/kernel/cpu/resctrl/internal.h +2 -0
index 3bfd1cf25b49..a1fb73e0681d 100644
@@ -444,6 +444,8 @@ DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
 extern struct dentry *debugfs_resctrl;
 
+extern unsigned int snc_nodes_per_l3_cache;
+
 enum resctrl_res_level {
 	RDT_RESOURCE_L3,
 	RDT_RESOURCE_L2,
arch/x86/kernel/cpu/resctrl/core.c +6 -0
index 27523841f9fd..fcfc0b117ff7 100644
@@ -48,6 +48,12 @@ int max_name_width, max_data_width;
  */
 bool rdt_alloc_capable;
 
+/*
+ * Number of SNC nodes that share each L3 cache.  Default is 1 for
+ * systems that do not support SNC, or have SNC disabled.
+ */
+unsigned int snc_nodes_per_l3_cache = 1;
+
 static void
 mba_wrmsr_intel(struct rdt_ctrl_domain *d, struct msr_param *m,
 		struct rdt_resource *r);
arch/x86/kernel/cpu/resctrl/monitor.c +13 -3
index e51bafc1945b..d93f50f1e1b4 100644
@@ -148,8 +148,18 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
 
 static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 {
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	int cpu = smp_processor_id();
+	int rmid_offset = 0;
 	u64 msr_val;
 
+	/*
+	 * When SNC mode is on, need to compute the offset to read the
+	 * physical RMID counter for the node to which this CPU belongs.
+	 */
+	if (snc_nodes_per_l3_cache > 1)
+		rmid_offset = (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid;
+
 	/*
 	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
 	 * with a valid event code for supported resource type and the bits
@@ -158,7 +168,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
 	 * are error bits.
 	 */
-	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid + rmid_offset);
 	rdmsrl(MSR_IA32_QM_CTR, msr_val);
 
 	if (msr_val & RMID_VAL_ERROR)
@@ -761,8 +771,8 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	int ret;
 
 	resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
-	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
-	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_nodes_per_l3_cache;
+	r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache;
 	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
 
 	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
arch/x86/kernel/cpu/resctrl/rdtgroup.c +3 -2
index 441d2f744ccc..52f8e0971ff1 100644
@@ -1425,7 +1425,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 		}
 	}
 
-	return size;
+	return size / snc_nodes_per_l3_cache;
 }
 
 /*
@@ -2293,7 +2293,8 @@ static bool supports_mba_mbps(void)
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 
 	return (is_mbm_local_enabled() &&
-		r->alloc_capable && is_mba_linear());
+		r->alloc_capable && is_mba_linear() &&
+		snc_nodes_per_l3_cache == 1);
 }
 
 /*
Signature · 1 line
2.43.0
author maintainer
#284 lore raw

PATCH v14 7/8 x86/resctrl: Sub NUMA Cluster detection and enable

In reply to Tony Luck

There isn't a simple hardware bit that indicates whether a CPU is running in Sub NUMA Cluster (SNC) mode. Infer the state by comparing the ratio of NUMA nodes to L3 cache instances.

When SNC mode is detected, reconfigure the RMID counters by updating the MSR_RMID_SNC_CONFIG MSR on each socket as CPUs are seen.

Clearing bit zero of the MSR divides the RMIDs and renumbers the ones on the second SNC node to start from zero.

---
 arch/x86/include/asm/msr-index.h   |   1 +
 arch/x86/kernel/cpu/resctrl/core.c | 118 +++++++++++++++++++++++++++++
 2 files changed, 119 insertions(+)
arch/x86/include/asm/msr-index.h +1 -0
index f1bd7b91b3c6..f6ba7d0397b8 100644
@@ -1119,6 +1119,7 @@
 #define MSR_IA32_QM_CTR			0xc8e
 #define MSR_IA32_PQR_ASSOC		0xc8f
 #define MSR_IA32_L3_CBM_BASE		0xc90
+#define MSR_RMID_SNC_CONFIG		0xca0
 #define MSR_IA32_L2_CBM_BASE		0xd10
 #define MSR_IA32_MBA_THRTL_BASE		0xd50
 
arch/x86/kernel/cpu/resctrl/core.c +118 -0

151 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#285 lore raw

PATCH v14 8/8 x86/resctrl: Update documentation with Sub-NUMA cluster changes

In reply to Tony Luck

With Sub-NUMA Cluster mode enabled the scope of monitoring resources is per-NODE instead of per-L3 cache. Suffixes of directories with "L3" in their name refer to Sub-NUMA nodes instead of L3 cache ids.

Users should be aware that SNC mode also affects the amount of L3 cache available for allocation within each SNC node.

---
 Documentation/arch/x86/resctrl.rst | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)
Documentation/arch/x86/resctrl.rst +21 -4
index a6279df64a9d..15f1cff6ee76 100644
@@ -366,10 +366,10 @@ When control is enabled all CTRL_MON groups will also contain:
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
-	This contains a set of files organized by L3 domain and by
-	RDT event. E.g. on a system with two L3 domains there will
-	be subdirectories "mon_L3_00" and "mon_L3_01".	Each of these
-	directories have one file per event (e.g. "llc_occupancy",
+	This contains a set of files organized by L3 domain or by NUMA
+	node (depending on whether Sub-NUMA Cluster (SNC) mode is disabled
+	or enabled respectively) and by RDT event.  Each of these
+	directories has one file per event (e.g. "llc_occupancy",
 	"mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
 	files provide a read out of the current value of the event for
 	all tasks in the group. In CTRL_MON groups these files provide
@@ -478,6 +478,23 @@ if non-contiguous 1s value is supported. On a system with a 20-bit mask
 each bit represents 5% of the capacity of the cache. You could partition
 the cache into four equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
 
+Notes on Sub-NUMA Cluster mode
+==============================
+When SNC mode is enabled, Linux may load balance tasks between Sub-NUMA
+nodes much more readily than between regular NUMA nodes since the CPUs
+on Sub-NUMA nodes share the same L3 cache and the system may report
+the NUMA distance between Sub-NUMA nodes with a lower value than used
+for regular NUMA nodes.  Users who do not bind tasks to the CPUs of a
+specific Sub-NUMA node must read the "llc_occupancy", "mbm_total_bytes",
+and "mbm_local_bytes" for all Sub-NUMA nodes where the tasks may execute
+to get the full view of traffic for which the tasks were the source.
+
+The cache allocation feature still provides the same number of
+bits in a mask to control allocation into the L3 cache, but each
+of those ways has its capacity reduced because the cache is divided
+between the SNC nodes. The values reported in the resctrl
+"size" files are adjusted accordingly.
+
 Memory bandwidth Allocation and monitoring
 ==========================================
 
Signature · 1 line
2.43.0
author maintainer
#286 lore raw

Re: [PATCH v14 0/8] Add support for Sub-NUMA cluster (SNC) systems

In reply to Tony Luck

I've been wondering whether the SNC patches were creating way too much infrastructure that isn't generally useful. Specifically the capability for a reactrl resource to have different scope for monitoring and control functions.

That seems like a very strange thing.

History here is that Intel CMT, MBM and L3 CAT features arrived in quick succession, closely followed by MBA and then L2 CAT. At the time it made sense for the "L3" resource to cover all of CMT, MBM and L3 CAT.

That became slightly odd when MBA (another L3 scoped resource) was added. It was given its own "struct rdt_resource". AMD later added SMBA as yet another L3-scoped resource with its own "struct resource".

I wondered how the SNC series would look if I went back to an approach from one of the earlier versions. In that one I created a new resource for SNC monitoring that was NODE scoped. And then made all the CMT and MBM code switch over to using that one when SNC was enabled. That was a bit hacky, and I moved from there to the dual domain lists per resource.

I just tried out an approach the split the RDT_RESOURCE_L3 resource into separate resources, one for control, one for monitoring.

It makes the code much simpler:

 8 files changed, 235 insertions(+), 30 deletions(-) [1]

vs.

 9 files changed, 629 insertions(+), 282 deletions(-)

Tradeoffs:

The complex series (posted as v14) cleanly split the "rdt_domain" structure into two. So it no longer carried all the fields needed for both control and monitor, even though only one set was ever used. But the cost was a lot of code churn that may never be useful for anything other than SNC.

On non-SNC systems the new series produces separate linked lists of domains for L3 control & monitor, even though the lists are the same, and the domain structures still carry all fields for both control and monitor functions.

Question: Does anyone think that single domain with different scope for control and monitor is inherently more useful than two separate domains?

While I get this sorted out, maybe Boris should take James next set of MPAM patches as they are, instead of on top of the complex SNC series.

-Tony

[1] I'll post this set just as soon as I can get time on and SNC machine to make sure they actually work.

author maintainer
#287 lore raw

cover Add support for Sub-NUMA cluster (SNC) systems

In reply to Tony Luck

This is the re-worked version of this series that I promised to post yesterday. Check that e-mail for the arguments for this alternate approach.

https://lore.kernel.org/all/ZbhLRDvZrxBZDv2j@agluck-desk3/

Apologies to Drew Fustini who I'd somehow dropped from later versions of this series. Drew: you had made a comment at one point that having different scopes within a single resource may be useful on RISC-V. Version 14 included that, but it's gone here. Maybe multiple resctrl "struct resource" for a single h/w entity like L3 as I'm doing in this version could work for you too?

Patches 1-5 are almost completely rewritten based around the new idea to give CMT and MBM their own "resource" instead of sharing one with L3 CAT. This removes the need for separate domain lists, and thus most of the churn of the previous version of this series.

Patches 6-8 are largely unchanged. But I removed all the Reviewed and Tested tags since they are now built on a completely different base.

Patches are against tip x86/cache:

fc747eebef73 ("x86/resctrl: Remove redundant variable in mbm_config_write_domain()")

Re-work doesn't affect the v14 cover letter, so pasting it here:

The Sub-NUMA cluster feature on some Intel processors partitions the CPUs that share an L3 cache into two or more sets. This plays havoc with the Resource Director Technology (RDT) monitoring features. Prior to this patch Intel has advised that SNC and RDT are incompatible.

Some of these CPU support an MSR that can partition the RMID counters in the same way. This allows monitoring features to be used. With the caveat that users must be aware that Linux may migrate tasks more frequently between SNC nodes than between "regular" NUMA nodes, so reading counters from all SNC nodes may be needed to get a complete picture of activity for tasks.

Cache and memory bandwidth allocation features continue to operate at the scope of the L3 cache.

Tony Luck (8):
x86/resctrl: Split the RDT_RESOURCE_L3 resource x86/resctrl: Move all monitoring functions to RDT_RESOURCE_L3_MON x86/resctrl: Prepare for non-cache-scoped resources x86/resctrl: Add helper function to look up domain_id from scope x86/resctrl: Add "NODE" as an option for resource scope x86/resctrl: Introduce snc_nodes_per_l3_cache x86/resctrl: Sub NUMA Cluster detection and enable x86/resctrl: Update documentation with Sub-NUMA cluster changes

 Documentation/arch/x86/resctrl.rst        |  25 ++-
 include/linux/resctrl.h                   |  10 +-
 arch/x86/include/asm/msr-index.h          |   1 +
 arch/x86/kernel/cpu/resctrl/internal.h    |   3 +
 arch/x86/kernel/cpu/resctrl/core.c        | 181 +++++++++++++++++++++-
 arch/x86/kernel/cpu/resctrl/monitor.c     |  28 ++--
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |   6 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  12 +-
 8 files changed, 236 insertions(+), 30 deletions(-)

base-commit: fc747eebef734563cf68a512f57937c8f231834a

Signature · 1 line
2.43.0
author maintainer
#288 lore raw

PATCH v3 1/8 x86/resctrl: Split the RDT_RESOURCE_L3 resource

The RDT_RESOURCE_L3 is unique in that it is used for both monitoring an control functions. This made sense while both uses had the same scope. But systems with Sub-NUMA clustering enabled do not follow this pattern.

Create a new resource: RDT_RESOURCE_L3_MON ready to take over the monitoring functions.

---
 arch/x86/kernel/cpu/resctrl/internal.h |  1 +
 arch/x86/kernel/cpu/resctrl/core.c     | 10 ++++++++++
 2 files changed, 11 insertions(+)
arch/x86/kernel/cpu/resctrl/internal.h +1 -0
index 52e7e7deee10..c6051bc70e96 100644
@@ -429,6 +429,7 @@ DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 extern struct dentry *debugfs_resctrl;
 
 enum resctrl_res_level {
+	RDT_RESOURCE_L3_MON,
 	RDT_RESOURCE_L3,
 	RDT_RESOURCE_L2,
 	RDT_RESOURCE_MBA,
arch/x86/kernel/cpu/resctrl/core.c +10 -0
index aa9810a64258..c50f55d7790e 100644
@@ -60,6 +60,16 @@ mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
 
 struct rdt_hw_resource rdt_resources_all[] = {
+	[RDT_RESOURCE_L3_MON] =
+	{
+		.r_resctrl = {
+			.rid			= RDT_RESOURCE_L3_MON,
+			.name			= "L3",
+			.cache_level		= 3,
+			.domains		= domain_init(RDT_RESOURCE_L3_MON),
+			.fflags			= RFTYPE_RES_CACHE,
+		},
+	},
 	[RDT_RESOURCE_L3] =
 	{
 		.r_resctrl = {
Signature · 1 line
2.43.0
reviewer
#289 lore raw

Re: [PATCH v15-RFC 1/8] x86/resctrl: Split the RDT_RESOURCE_L3 resource

Hi Tony,

Quoted 2 lines · Tony Luck

The RDT_RESOURCE_L3 is unique in that it is used for both monitoring an control functions. This made sense while both uses had the same

an/and

Quoted 17 lines

scope. But systems with Sub-NUMA clustering enabled do not follow this pattern.

Create a new resource: RDT_RESOURCE_L3_MON ready to take over the monitoring functions.

---
 arch/x86/kernel/cpu/resctrl/internal.h |  1 +
 arch/x86/kernel/cpu/resctrl/core.c     | 10 ++++++++++
 2 files changed, 11 insertions(+)
arch/x86/kernel/cpu/resctrl/internal.h +0 -0
index 52e7e7deee10..c6051bc70e96 100644

arch/x86/kernel/cpu/resctrl/internal.h DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); · line 433

Quoted 5 lines
arch/x86/kernel/cpu/resctrl/internal.h +1 -0
@@ -429,6 +429,7 @@ DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 extern struct dentry *debugfs_resctrl;
 
 enum resctrl_res_level {
+	RDT_RESOURCE_L3_MON,
 	RDT_RESOURCE_L3,

How about?
RDT_RESOURCE_L3,
RDT_RESOURCE_L3_MON,

Quoted 7 lines
arch/x86/kernel/cpu/resctrl/internal.h +0 -0
 	RDT_RESOURCE_L2,
 	RDT_RESOURCE_MBA,
arch/x86/kernel/cpu/resctrl/core.c +0 -0
index aa9810a64258..c50f55d7790e 100644

arch/x86/kernel/cpu/resctrl/core.c mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, · line 67

Quoted 8 lines
arch/x86/kernel/cpu/resctrl/core.c +5 -0
@@ -60,6 +60,16 @@ mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
 
 struct rdt_hw_resource rdt_resources_all[] = {
+	[RDT_RESOURCE_L3_MON] =
+	{
+		.r_resctrl = {
+			.rid			= RDT_RESOURCE_L3_MON,
+			.name			= "L3",

L3_MON ?

Quoted 8 lines
arch/x86/kernel/cpu/resctrl/core.c +5 -0
+			.cache_level		= 3,
+			.domains		= domain_init(RDT_RESOURCE_L3_MON),
+			.fflags			= RFTYPE_RES_CACHE,
+		},
+	},
 	[RDT_RESOURCE_L3] =
 	{
 		.r_resctrl = {
Signature · 2 lines
Thanks
Babu Moger
author maintainer
#290 lore raw

Re: [PATCH v15-RFC 1/8] x86/resctrl: Split the RDT_RESOURCE_L3 resource

Quoted 7 lines · Babu

arch/x86/kernel/cpu/resctrl/internal.h DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); · line 433

Quoted 3 lines

enum resctrl_res_level {

arch/x86/kernel/cpu/resctrl/internal.h +1 -0
+	RDT_RESOURCE_L3_MON,
 	RDT_RESOURCE_L3,

How about?
RDT_RESOURCE_L3,
RDT_RESOURCE_L3_MON,

Does the order matter? I put the L3_MON one first because historically cache occupancy was the first resctrl tool. But if you have a better argument for the order, then I can change it.

Quoted 9 lines
Quoted 9 lines
arch/x86/kernel/cpu/resctrl/internal.h +0 -0
 	RDT_RESOURCE_L2,
 	RDT_RESOURCE_MBA,
arch/x86/kernel/cpu/resctrl/core.c +0 -0
index aa9810a64258..c50f55d7790e 100644
@@ -60,6 +60,16 @@ mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
 
Quoted 8 lines

arch/x86/kernel/cpu/resctrl/core.c mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, · line 67

Quoted 6 lines
arch/x86/kernel/cpu/resctrl/core.c +5 -0
 struct rdt_hw_resource rdt_resources_all[] = {
+	[RDT_RESOURCE_L3_MON] =
+	{
+		.r_resctrl = {
+			.rid			= RDT_RESOURCE_L3_MON,
+			.name			= "L3",

L3_MON ?

That was my first choice too. But I found:

$ ls /sys/fs/resctrl/info
L3  L3_MON_MON  last_cmd_status  MB

This would be easy to fix ... just change this code to not append an extra "_MON" to the directory name:

        for_each_mon_capable_rdt_resource(r) {
                fflags = r->fflags | RFTYPE_MON_INFO;
                sprintf(name, "%s_MON", r->name);
                ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
                if (ret)
                        goto out_destroy;
        }

But I also saw this:

$ ls /sys/fs/resctrl/mon_data/
mon_L3_MON_00  mon_L3_MON_01

which didn't seem to have an easy fix. So I took the easy route and left the ".name" field as "L3_MON".

-Tony

reviewer
#291 lore raw

Re: [PATCH v15-RFC 1/8] x86/resctrl: Split the RDT_RESOURCE_L3 resource

Quoted 9 lines · Tony Luck
Quoted 7 lines · Babu

arch/x86/kernel/cpu/resctrl/internal.h DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); · line 433

Quoted 3 lines

enum resctrl_res_level {

arch/x86/kernel/cpu/resctrl/internal.h +1 -0
+	RDT_RESOURCE_L3_MON,
 	RDT_RESOURCE_L3,

How about?
RDT_RESOURCE_L3,
RDT_RESOURCE_L3_MON,

Quoted 3 lines

Does the order matter? I put the L3_MON one first because historically cache occupancy was the first resctrl tool. But if you have a better argument for the order, then I can change it.

That is fine. No need to change.

Quoted 35 lines
Quoted 10 lines
Quoted 10 lines
arch/x86/kernel/cpu/resctrl/internal.h +0 -0
 	RDT_RESOURCE_L2,
 	RDT_RESOURCE_MBA,
arch/x86/kernel/cpu/resctrl/core.c +0 -0
index aa9810a64258..c50f55d7790e 100644
@@ -60,6 +60,16 @@ mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
 
Quoted 8 lines

arch/x86/kernel/cpu/resctrl/core.c mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, · line 67

Quoted 6 lines
arch/x86/kernel/cpu/resctrl/core.c +5 -0
 struct rdt_hw_resource rdt_resources_all[] = {
+	[RDT_RESOURCE_L3_MON] =
+	{
+		.r_resctrl = {
+			.rid			= RDT_RESOURCE_L3_MON,
+			.name			= "L3",

L3_MON ?

That was my first choice too. But I found:

$ ls /sys/fs/resctrl/info
L3  L3_MON_MON  last_cmd_status  MB

This would be easy to fix ... just change this code to not append an extra "_MON" to the directory name:

        for_each_mon_capable_rdt_resource(r) {
                fflags = r->fflags | RFTYPE_MON_INFO;
                sprintf(name, "%s_MON", r->name);
                ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
                if (ret)
                        goto out_destroy;
        }
Quoted 7 lines

But I also saw this:

$ ls /sys/fs/resctrl/mon_data/
mon_L3_MON_00  mon_L3_MON_01

which didn't seem to have an easy fix. So I took the easy route and left the ".name" field as "L3_MON".

Ok. Sounds good.

Signature · 2 lines
Thanks
Babu Moger
author maintainer
#292 lore raw

PATCH v3 2/8 x86/resctrl: Move all monitoring functions to RDT_RESOURCE_L3_MON

In reply to Tony Luck

Switch over all places that setup and use monitoring funtions to use the new resource structure.

---
 arch/x86/kernel/cpu/resctrl/core.c     |  6 ++++--
 arch/x86/kernel/cpu/resctrl/monitor.c  | 12 ++++--------
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  2 +-
 3 files changed, 9 insertions(+), 11 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +4 -2
index c50f55d7790e..0828575c3e13 100644
@@ -591,11 +591,13 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl) {
 		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
 			cancel_delayed_work(&d->mbm_over);
 			mbm_setup_overflow_handler(d, 0);
 		}
+	}
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
 		if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
 		    has_busy_rmid(r, d)) {
 			cancel_delayed_work(&d->cqm_limbo);
@@ -826,7 +828,7 @@ static __init bool get_rdt_alloc_resources(void)
 
 static __init bool get_rdt_mon_resources(void)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 
 	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC))
 		rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
arch/x86/kernel/cpu/resctrl/monitor.c +4 -8
index 3a6c069614eb..080cad0d7288 100644
@@ -268,7 +268,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  */
 void __check_limbo(struct rdt_domain *d, bool force_free)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 	struct rmid_entry *entry;
 	u32 crmid = 1, nrmid;
 	bool rmid_dirty;
@@ -333,7 +333,7 @@ int alloc_rmid(void)
 
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 	struct rdt_domain *d;
 	int cpu, err;
 	u64 val = 0;
@@ -623,7 +623,7 @@ void cqm_handle_limbo(struct work_struct *work)
 
 	mutex_lock(&rdtgroup_mutex);
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 	d = container_of(work, struct rdt_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
@@ -659,7 +659,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		goto out_unlock;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 	d = container_of(work, struct rdt_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
@@ -736,10 +736,6 @@ static struct mon_evt mbm_local_event = {
 
 /*
  * Initialize the event list for the resource.
- *
- * Note that MBM events are also part of RDT_RESOURCE_L3 resource
- * because as per the SDM the total and local memory bandwidth
- * are enumerated as part of L3 monitoring.
  */
 static void l3_mon_evt_init(struct rdt_resource *r)
 {
arch/x86/kernel/cpu/resctrl/rdtgroup.c +1 -1
index aa24343f1d23..9ee3a9906781 100644
@@ -2644,7 +2644,7 @@ static int rdt_get_tree(struct fs_context *fc)
 		static_branch_enable_cpuslocked(&rdt_enable_key);
 
 	if (is_mbm_enabled()) {
-		r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+		r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 		list_for_each_entry(dom, &r->domains, list)
 			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
 	}
Signature · 1 line
2.43.0
reviewer
#293 lore raw

Re: [PATCH v15-RFC 2/8] x86/resctrl: Move all monitoring functions to RDT_RESOURCE_L3_MON

Tony,

Quoted 1 line · Tony Luck

Switch over all places that setup and use monitoring funtions to

functions?

Quoted 15 lines

use the new resource structure.

---
 arch/x86/kernel/cpu/resctrl/core.c     |  6 ++++--
 arch/x86/kernel/cpu/resctrl/monitor.c  | 12 ++++--------
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  2 +-
 3 files changed, 9 insertions(+), 11 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +0 -0
index c50f55d7790e..0828575c3e13 100644
@@ -591,11 +591,13 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 		return;

arch/x86/kernel/cpu/resctrl/core.c static void domain_remove_cpu(int cpu, struct rdt_resource *r) · line 600

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +3 -1
 	}
 
-	if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl) {
 		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
 			cancel_delayed_work(&d->mbm_over);
 			mbm_setup_overflow_handler(d, 0);
 		}
+	}
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {

RDT_RESOURCE_L3_MON?

Quoted 76 lines
arch/x86/kernel/cpu/resctrl/core.c +1 -1
 		if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
 		    has_busy_rmid(r, d)) {
 			cancel_delayed_work(&d->cqm_limbo);
@@ -826,7 +828,7 @@ static __init bool get_rdt_alloc_resources(void)
 
 static __init bool get_rdt_mon_resources(void)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 
 	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC))
 		rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
arch/x86/kernel/cpu/resctrl/monitor.c +4 -8
index 3a6c069614eb..080cad0d7288 100644
@@ -268,7 +268,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
  */
 void __check_limbo(struct rdt_domain *d, bool force_free)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 	struct rmid_entry *entry;
 	u32 crmid = 1, nrmid;
 	bool rmid_dirty;
@@ -333,7 +333,7 @@ int alloc_rmid(void)
 
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 	struct rdt_domain *d;
 	int cpu, err;
 	u64 val = 0;
@@ -623,7 +623,7 @@ void cqm_handle_limbo(struct work_struct *work)
 
 	mutex_lock(&rdtgroup_mutex);
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 	d = container_of(work, struct rdt_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
@@ -659,7 +659,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		goto out_unlock;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 	d = container_of(work, struct rdt_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
@@ -736,10 +736,6 @@ static struct mon_evt mbm_local_event = {
 
 /*
  * Initialize the event list for the resource.
- *
- * Note that MBM events are also part of RDT_RESOURCE_L3 resource
- * because as per the SDM the total and local memory bandwidth
- * are enumerated as part of L3 monitoring.
  */
 static void l3_mon_evt_init(struct rdt_resource *r)
 {
arch/x86/kernel/cpu/resctrl/rdtgroup.c +1 -1
index aa24343f1d23..9ee3a9906781 100644
@@ -2644,7 +2644,7 @@ static int rdt_get_tree(struct fs_context *fc)
 		static_branch_enable_cpuslocked(&rdt_enable_key);
 
 	if (is_mbm_enabled()) {
-		r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+		r = &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl;
 		list_for_each_entry(dom, &r->domains, list)
 			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
 	}
Signature · 2 lines
Thanks
Babu Moger
author maintainer
#294 lore raw

Re: [PATCH v15-RFC 2/8] x86/resctrl: Move all monitoring functions to RDT_RESOURCE_L3_MON

Quoted 6 lines · Babu

Tony,

Quoted 1 line · Tony Luck

Switch over all places that setup and use monitoring funtions to

functions?

Yes. Will fix.

Quoted 17 lines
Quoted 17 lines

use the new resource structure.

---
 arch/x86/kernel/cpu/resctrl/core.c     |  6 ++++--
 arch/x86/kernel/cpu/resctrl/monitor.c  | 12 ++++--------
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  2 +-
 3 files changed, 9 insertions(+), 11 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +0 -0
index c50f55d7790e..0828575c3e13 100644
@@ -591,11 +591,13 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 		return;
 	}
 
Quoted 10 lines

arch/x86/kernel/cpu/resctrl/core.c static void domain_remove_cpu(int cpu, struct rdt_resource *r) · line 600

Quoted 8 lines
arch/x86/kernel/cpu/resctrl/core.c +3 -1
-	if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3_MON].r_resctrl) {
 		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
 			cancel_delayed_work(&d->mbm_over);
 			mbm_setup_overflow_handler(d, 0);
 		}
+	}
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {

RDT_RESOURCE_L3_MON?

Good catch.

-Tony

author maintainer
#295 lore raw

PATCH v3 3/8 x86/resctrl: Prepare for non-cache-scoped resources

In reply to Tony Luck

Not all resources are scoped in line with some level of hardware cache.

Prepare by renaming the "cache_level" field to "scope" and change the type to an enum to ease adding new scopes.

---
 include/linux/resctrl.h                   |  9 +++++++--
 arch/x86/kernel/cpu/resctrl/core.c        | 14 +++++++-------
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  2 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  2 +-
 4 files changed, 16 insertions(+), 11 deletions(-)
include/linux/resctrl.h +7 -2
index 66942d7fba7f..2155dc15e636 100644
@@ -144,13 +144,18 @@ struct resctrl_membw {
 struct rdt_parse_data;
 struct resctrl_schema;
 
+enum resctrl_scope {
+	RESCTRL_L2_CACHE = 2,
+	RESCTRL_L3_CACHE = 3,
+};
+
 /**
  * struct rdt_resource - attributes of a resctrl resource
  * @rid:		The index of the resource
  * @alloc_capable:	Is allocation available on this machine
  * @mon_capable:	Is monitor feature available on this machine
  * @num_rmid:		Number of RMIDs available
- * @cache_level:	Which cache level defines scope of this resource
+ * @scope:		Hardware scope for this resource
  * @cache:		Cache allocation related data
  * @membw:		If the component has bandwidth controls, their properties.
  * @domains:		All domains for this resource
@@ -168,7 +173,7 @@ struct rdt_resource {
 	bool			alloc_capable;
 	bool			mon_capable;
 	int			num_rmid;
-	int			cache_level;
+	enum resctrl_scope	scope;
 	struct resctrl_cache	cache;
 	struct resctrl_membw	membw;
 	struct list_head	domains;
arch/x86/kernel/cpu/resctrl/core.c +7 -7
index 0828575c3e13..d89dce63397b 100644
@@ -65,7 +65,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_L3_MON,
 			.name			= "L3",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_L3_MON),
 			.fflags			= RFTYPE_RES_CACHE,
 		},
@@ -75,7 +75,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_L3,
 			.name			= "L3",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_L3),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -89,7 +89,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_L2,
 			.name			= "L2",
-			.cache_level		= 2,
+			.scope			= RESCTRL_L2_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_L2),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -103,7 +103,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_MBA,
 			.name			= "MB",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_MBA),
 			.parse_ctrlval		= parse_bw,
 			.format_str		= "%d=%*u",
@@ -115,7 +115,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_SMBA,
 			.name			= "SMBA",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_SMBA),
 			.parse_ctrlval		= parse_bw,
 			.format_str		= "%d=%*u",
@@ -514,7 +514,7 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+	int id = get_cpu_cacheinfo_id(cpu, r->scope);
 	struct list_head *add_pos = NULL;
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
@@ -564,7 +564,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+	int id = get_cpu_cacheinfo_id(cpu, r->scope);
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +1 -1
index 8f559eeae08e..6a72fb627aa5 100644
@@ -311,7 +311,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
 
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == plr->s->res->cache_level) {
+		if (ci->info_list[i].level == plr->s->res->scope) {
 			plr->line_size = ci->info_list[i].coherency_line_size;
 			return 0;
 		}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +1 -1
index 9ee3a9906781..eff9d87547c9 100644
@@ -1416,7 +1416,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
 	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == r->cache_level) {
+		if (ci->info_list[i].level == r->scope) {
 			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
 			break;
 		}
Signature · 1 line
2.43.0
reviewer
#296 lore raw

Re: [PATCH v15-RFC 3/8] x86/resctrl: Prepare for non-cache-scoped resources

Hi Tony,

Quoted 1 line · Tony Luck

Not all resources are scoped in line with some level of hardware cache.

same level?

Thanks
Babu

Quoted 138 lines

Prepare by renaming the "cache_level" field to "scope" and change the type to an enum to ease adding new scopes.

---
 include/linux/resctrl.h                   |  9 +++++++--
 arch/x86/kernel/cpu/resctrl/core.c        | 14 +++++++-------
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  2 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  2 +-
 4 files changed, 16 insertions(+), 11 deletions(-)
include/linux/resctrl.h +7 -2
index 66942d7fba7f..2155dc15e636 100644
@@ -144,13 +144,18 @@ struct resctrl_membw {
 struct rdt_parse_data;
 struct resctrl_schema;
 
+enum resctrl_scope {
+	RESCTRL_L2_CACHE = 2,
+	RESCTRL_L3_CACHE = 3,
+};
+
 /**
  * struct rdt_resource - attributes of a resctrl resource
  * @rid:		The index of the resource
  * @alloc_capable:	Is allocation available on this machine
  * @mon_capable:	Is monitor feature available on this machine
  * @num_rmid:		Number of RMIDs available
- * @cache_level:	Which cache level defines scope of this resource
+ * @scope:		Hardware scope for this resource
  * @cache:		Cache allocation related data
  * @membw:		If the component has bandwidth controls, their properties.
  * @domains:		All domains for this resource
@@ -168,7 +173,7 @@ struct rdt_resource {
 	bool			alloc_capable;
 	bool			mon_capable;
 	int			num_rmid;
-	int			cache_level;
+	enum resctrl_scope	scope;
 	struct resctrl_cache	cache;
 	struct resctrl_membw	membw;
 	struct list_head	domains;
arch/x86/kernel/cpu/resctrl/core.c +7 -7
index 0828575c3e13..d89dce63397b 100644
@@ -65,7 +65,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_L3_MON,
 			.name			= "L3",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_L3_MON),
 			.fflags			= RFTYPE_RES_CACHE,
 		},
@@ -75,7 +75,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_L3,
 			.name			= "L3",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_L3),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -89,7 +89,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_L2,
 			.name			= "L2",
-			.cache_level		= 2,
+			.scope			= RESCTRL_L2_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_L2),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -103,7 +103,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_MBA,
 			.name			= "MB",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_MBA),
 			.parse_ctrlval		= parse_bw,
 			.format_str		= "%d=%*u",
@@ -115,7 +115,7 @@ struct rdt_hw_resource rdt_resources_all[] = {
 		.r_resctrl = {
 			.rid			= RDT_RESOURCE_SMBA,
 			.name			= "SMBA",
-			.cache_level		= 3,
+			.scope			= RESCTRL_L3_CACHE,
 			.domains		= domain_init(RDT_RESOURCE_SMBA),
 			.parse_ctrlval		= parse_bw,
 			.format_str		= "%d=%*u",
@@ -514,7 +514,7 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+	int id = get_cpu_cacheinfo_id(cpu, r->scope);
 	struct list_head *add_pos = NULL;
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
@@ -564,7 +564,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+	int id = get_cpu_cacheinfo_id(cpu, r->scope);
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +1 -1
index 8f559eeae08e..6a72fb627aa5 100644
@@ -311,7 +311,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
 
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == plr->s->res->cache_level) {
+		if (ci->info_list[i].level == plr->s->res->scope) {
 			plr->line_size = ci->info_list[i].coherency_line_size;
 			return 0;
 		}
arch/x86/kernel/cpu/resctrl/rdtgroup.c +1 -1
index 9ee3a9906781..eff9d87547c9 100644
@@ -1416,7 +1416,7 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
 	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
 	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == r->cache_level) {
+		if (ci->info_list[i].level == r->scope) {
 			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
 			break;
 		}
Signature · 2 lines
Thanks
Babu Moger
author maintainer
#297 lore raw

Re: [PATCH v15-RFC 3/8] x86/resctrl: Prepare for non-cache-scoped resources

Quoted 6 lines · Babu

Hi Tony,

Quoted 1 line · Tony Luck

Not all resources are scoped in line with some level of hardware cache.

same level?

No. "same" isn't what I meant here. If I shuffle this around:

Not all resources are scoped to match the scope of a hardware cache level.

Is that more clear?

-Tony

reviewer
#298 lore raw

Re: [PATCH v15-RFC 3/8] x86/resctrl: Prepare for non-cache-scoped resources

Quoted 6 lines · Tony Luck
Quoted 5 lines · Babu

Hi Tony,

Quoted 1 line · Tony Luck

Not all resources are scoped in line with some level of hardware cache.

Quoted 8 lines
Quoted 1 line

same level?

No. "same" isn't what I meant here. If I shuffle this around:

Not all resources are scoped to match the scope of a hardware cache level.

Is that more clear?

Sure. Looks good.

Signature · 2 lines
Thanks
Babu Moger
author maintainer
#299 lore raw

PATCH v3 4/8 x86/resctrl: Add helper function to look up domain_id from scope

In reply to Tony Luck

Prepare for more options for scope of resources. Add some diagnostic messages if lookup fails.

---
 arch/x86/kernel/cpu/resctrl/core.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +27 -2
index d89dce63397b..59e6aa7abef5 100644
@@ -499,6 +499,19 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
 	return 0;
 }
 
+static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
+{
+	switch (scope) {
+	case RESCTRL_L2_CACHE:
+	case RESCTRL_L3_CACHE:
+		return get_cpu_cacheinfo_id(cpu, scope);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
 /*
  * domain_add_cpu - Add a cpu to a resource's domain list.
  *
@@ -514,12 +527,18 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cpu_cacheinfo_id(cpu, r->scope);
+	int id = get_domain_id_from_scope(cpu, r->scope);
 	struct list_head *add_pos = NULL;
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 	int err;
 
+	if (id < 0) {
+		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->scope, r->name);
+		return;
+	}
+
 	d = rdt_find_domain(r, id, &add_pos);
 	if (IS_ERR(d)) {
 		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
@@ -564,10 +583,16 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cpu_cacheinfo_id(cpu, r->scope);
+	int id = get_domain_id_from_scope(cpu, r->scope);
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 
+	if (id < 0) {
+		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->scope, r->name);
+		return;
+	}
+
 	d = rdt_find_domain(r, id, NULL);
 	if (IS_ERR_OR_NULL(d)) {
 		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
Signature · 1 line
2.43.0
reviewer
#300 lore raw

Re: [PATCH v15-RFC 4/8] x86/resctrl: Add helper function to look up domain_id from scope

Hi Tony,

Quoted 36 lines · Tony Luck

Prepare for more options for scope of resources. Add some diagnostic messages if lookup fails.

---
 arch/x86/kernel/cpu/resctrl/core.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +13 -0
index d89dce63397b..59e6aa7abef5 100644
@@ -499,6 +499,19 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
 	return 0;
 }
 
+static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
+{
+	switch (scope) {
+	case RESCTRL_L2_CACHE:
+	case RESCTRL_L3_CACHE:
+		return get_cpu_cacheinfo_id(cpu, scope);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
 /*
  * domain_add_cpu - Add a cpu to a resource's domain list.
  *
@@ -514,12 +527,18 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {

arch/x86/kernel/cpu/resctrl/core.c static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom) · line 538

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +4 -1
-	int id = get_cpu_cacheinfo_id(cpu, r->scope);
+	int id = get_domain_id_from_scope(cpu, r->scope);
 	struct list_head *add_pos = NULL;
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 	int err;
 
+	if (id < 0) {
+		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->scope, r->name);

Will it be good to move pr_warn_once inside get_domain_id_from_scope instead of repeating during every call?

Quoted 8 lines
arch/x86/kernel/cpu/resctrl/core.c +3 -0
+		return;
+	}
+
 	d = rdt_find_domain(r, id, &add_pos);
 	if (IS_ERR(d)) {
 		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
@@ -564,10 +583,16 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 

arch/x86/kernel/cpu/resctrl/core.c static void domain_add_cpu(int cpu, struct rdt_resource *r) · line 592

Quoted 10 lines
arch/x86/kernel/cpu/resctrl/core.c +4 -1
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cpu_cacheinfo_id(cpu, r->scope);
+	int id = get_domain_id_from_scope(cpu, r->scope);
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 
+	if (id < 0) {
+		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->scope, r->name);

Same comment as above. Will it be good to move pr_warn_once inside get_domain_id_from_scope ?

Quoted 6 lines
arch/x86/kernel/cpu/resctrl/core.c +3 -0
+		return;
+	}
+
 	d = rdt_find_domain(r, id, NULL);
 	if (IS_ERR_OR_NULL(d)) {
 		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
Signature · 2 lines
Thanks
Babu Moger
author maintainer
#301 lore raw

Re: [PATCH v15-RFC 4/8] x86/resctrl: Add helper function to look up domain_id from scope

Quoted 6 lines · Babu

arch/x86/kernel/cpu/resctrl/core.c static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom) · line 538

Quoted 3 lines
arch/x86/kernel/cpu/resctrl/core.c +3 -0
+	if (id < 0) {
+		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->scope, r->name);

Will it be good to move pr_warn_once inside get_domain_id_from_scope instead of repeating during every call?

Yes. Will move from here to get_domain_id_from_scope().

Quoted 6 lines

arch/x86/kernel/cpu/resctrl/core.c static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom) · line 538

Quoted 3 lines
arch/x86/kernel/cpu/resctrl/core.c +3 -0
+	if (id < 0) {
+		pr_warn_once("Can't find domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->scope, r->name);

Same comment as above. Will it be good to move pr_warn_once inside get_domain_id_from_scope ?

Moved this one too.

Thanks

-Tony

author maintainer
#302 lore raw

PATCH v3 5/8 x86/resctrl: Add "NODE" as an option for resource scope

In reply to Tony Luck

Add RESCTRL_NODE to the enum, and to the helper function that looks up a domain id from a scope.

There are a couple of places where the scope must be a cache scope. Add some defensive WARN_ON checks to those.

---
 include/linux/resctrl.h                   | 1 +
 arch/x86/kernel/cpu/resctrl/core.c        | 3 +++
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 4 ++++
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 3 +++
 4 files changed, 11 insertions(+)
include/linux/resctrl.h +1 -0
index 2155dc15e636..e3cddf3f07f8 100644
@@ -147,6 +147,7 @@ struct resctrl_schema;
 enum resctrl_scope {
 	RESCTRL_L2_CACHE = 2,
 	RESCTRL_L3_CACHE = 3,
+	RESCTRL_NODE,
 };
 
 /**
arch/x86/kernel/cpu/resctrl/core.c +3 -0
index 59e6aa7abef5..b741cbf61843 100644
@@ -505,6 +505,9 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
 	case RESCTRL_L2_CACHE:
 	case RESCTRL_L3_CACHE:
 		return get_cpu_cacheinfo_id(cpu, scope);
+	case RESCTRL_NODE:
+		return cpu_to_node(cpu);
+
 	default:
 		break;
 	}
arch/x86/kernel/cpu/resctrl/pseudo_lock.c +4 -0
index 6a72fb627aa5..2bafc73b51e2 100644
@@ -292,10 +292,14 @@ 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;
 	struct cpu_cacheinfo *ci;
 	int ret;
 	int i;
 
+	if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
+		return -ENODEV;
+
 	/* Pick the first cpu we find that is associated with the cache. */
 	plr->cpu = cpumask_first(&plr->d->cpu_mask);
 
arch/x86/kernel/cpu/resctrl/rdtgroup.c +3 -0
index eff9d87547c9..770f2bf98462 100644
@@ -1413,6 +1413,9 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 	unsigned int size = 0;
 	int num_b, i;
 
+	if (WARN_ON_ONCE(r->scope != RESCTRL_L2_CACHE && r->scope != RESCTRL_L3_CACHE))
+		return size;
+
 	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
 	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
 	for (i = 0; i < ci->num_leaves; i++) {
Signature · 1 line
2.43.0