[PATCH 0/5] Latest version of initial patches in AET series

[PATCH 0/5] Latest version of initial patches in AET series

[Tony Luck]

Babu,

Here's my latest version of those four patches (build on top of Qinyun's
patch that I believe should go upstream via tip/urgent).

I believe I addressed all the comments[1] in these four patches

[1] https://lore.kernel.org/lkml/20250521225049.132551-1-tony.luck@intel.com/

-Tony

Qinyun Tan (1):
  x86,fs/resctrl: Remove unappropriate references to cacheinfo in the
    resctrl subsystem.

Tony Luck (4):
  x86,fs/resctrl: Consolidate monitor event descriptions
  x86,fs/resctrl: Replace architecture event enabled checks
  x86/resctrl: Remove 'rdt_mon_features' global variable
  x86,fs/resctrl: Prepare for more monitor events

 include/linux/resctrl.h                | 28 +++++---
 include/linux/resctrl_types.h          | 15 ++--
 arch/x86/include/asm/resctrl.h         | 16 -----
 arch/x86/kernel/cpu/resctrl/internal.h |  9 +--
 fs/resctrl/internal.h                  | 17 +++--
 arch/x86/kernel/cpu/resctrl/core.c     | 65 +++++++++--------
 arch/x86/kernel/cpu/resctrl/monitor.c  | 41 +++++------
 fs/resctrl/ctrlmondata.c               | 17 +++--
 fs/resctrl/monitor.c                   | 96 ++++++++++++++------------
 fs/resctrl/rdtgroup.c                  | 79 +++++++++++----------
 10 files changed, 204 insertions(+), 179 deletions(-)

-- 
2.49.0

[PATCH 1/5] x86,fs/resctrl: Remove unappropriate references to cacheinfo in the resctrl subsystem.

[Tony Luck]

From: Qinyun Tan <qinyuntan@linux.alibaba.com>

In the resctrl subsystem's Sub-NUMA Cluster (SNC) mode, the rdt_mon_domain
structure representing a NUMA node relies on the cacheinfo interface
(rdt_mon_domain::ci) to store L3 cache information (e.g., shared_cpu_map)
for monitoring. The L3 cache information of a SNC NUMA node determines
which domains are summed for the "top level" L3-scoped events.

rdt_mon_domain::ci is initialized using the first online CPU of a NUMA
node. When this CPU goes offline, its shared_cpu_map is cleared to contain
only the offline CPU itself. Subsequently, attempting to read counters
via smp_call_on_cpu(offline_cpu) fails (and error ignored), returning
zero values for "top-level events" without any error indication.

Replace the cacheinfo references in struct rdt_mon_domain and struct
rmid_read with the cacheinfo ID (a unique identifier for the L3 cache).

rdt_domain_hdr::cpu_mask contains the online CPUs associated with that
domain. When reading "top-level events", select a CPU from
rdt_domain_hdr::cpu_mask and utilize its L3 shared_cpu_map to determine
valid CPUs for reading RMID counter via the MSR interface.

Considering all CPUs associated with the L3 cache improves the chances
of picking a housekeeping CPU on which the counter reading work can be
queued, avoiding an unnecessary IPI.

Fixes: 328ea68874642 ("x86/resctrl: Prepare for new Sub-NUMA Cluster (SNC) monitor files")
Signed-off-by: Qinyun Tan <qinyuntan@linux.alibaba.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
---
 include/linux/resctrl.h            |  4 ++--
 fs/resctrl/internal.h              |  4 ++--
 arch/x86/kernel/cpu/resctrl/core.c |  6 ++++--
 fs/resctrl/ctrlmondata.c           | 13 +++++++++----
 fs/resctrl/monitor.c               |  6 ++++--
 fs/resctrl/rdtgroup.c              |  6 +++---
 6 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 9ba771f2ddea..6fb4894b8cfd 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -159,7 +159,7 @@ struct rdt_ctrl_domain {
 /**
  * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
  * @hdr:		common header for different domain types
- * @ci:			cache info for this domain
+ * @ci_id:		cache info id for this domain
  * @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
@@ -170,7 +170,7 @@ struct rdt_ctrl_domain {
  */
 struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
-	struct cacheinfo		*ci;
+	unsigned int			ci_id;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 9a8cf6f11151..0a1eedba2b03 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -98,7 +98,7 @@ struct mon_data {
  *	   domains in @r sharing L3 @ci.id
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
- * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
  *	   @val includes the sum of event counts from its child resource groups.
@@ -112,7 +112,7 @@ struct rmid_read {
 	struct rdt_mon_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
-	struct cacheinfo	*ci;
+	unsigned int		ci_id;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 7109cbfcad4f..187d527ef73b 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -498,6 +498,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	struct rdt_hw_mon_domain *hw_dom;
 	struct rdt_domain_hdr *hdr;
 	struct rdt_mon_domain *d;
+	struct cacheinfo *ci;
 	int err;
 
 	lockdep_assert_held(&domain_list_lock);
@@ -525,12 +526,13 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	d = &hw_dom->d_resctrl;
 	d->hdr.id = id;
 	d->hdr.type = RESCTRL_MON_DOMAIN;
-	d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
-	if (!d->ci) {
+	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!ci) {
 		pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
 		mon_domain_free(hw_dom);
 		return;
 	}
+	d->ci_id = ci->id;
 	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	arch_mon_domain_online(r, d);
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 6ed2dfd4dbbd..d98e0d2de09f 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -594,9 +594,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	struct rmid_read rr = {0};
 	struct rdt_mon_domain *d;
 	struct rdtgroup *rdtgrp;
+	int domid, cpu, ret = 0;
 	struct rdt_resource *r;
+	struct cacheinfo *ci;
 	struct mon_data *md;
-	int domid, ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
@@ -623,10 +624,14 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 * one that matches this cache id.
 		 */
 		list_for_each_entry(d, &r->mon_domains, hdr.list) {
-			if (d->ci->id == domid) {
-				rr.ci = d->ci;
+			if (d->ci_id == domid) {
+				rr.ci_id = d->ci_id;
+				cpu = cpumask_any(&d->hdr.cpu_mask);
+				ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+				if (!ci)
+					continue;
 				mon_event_read(&rr, r, NULL, rdtgrp,
-					       &d->ci->shared_cpu_map, evtid, false);
+					       &ci->shared_cpu_map, evtid, false);
 				goto checkresult;
 			}
 		}
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index bde2801289d3..f5637855c3ac 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -361,6 +361,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
 	struct rdt_mon_domain *d;
+	struct cacheinfo *ci;
 	struct mbm_state *m;
 	int err, ret;
 	u64 tval = 0;
@@ -388,7 +389,8 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	}
 
 	/* Summing domains that share a cache, must be on a CPU for that cache. */
-	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
+	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!ci || ci->id != rr->ci_id)
 		return -EINVAL;
 
 	/*
@@ -400,7 +402,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	 */
 	ret = -EINVAL;
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
-		if (d->ci->id != rr->ci->id)
+		if (d->ci_id != rr->ci_id)
 			continue;
 		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
 					     rr->evtid, &tval, rr->arch_mon_ctx);
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 1beb124e25f6..77d08229d855 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -3036,7 +3036,7 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 	char name[32];
 
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
 	if (snc_mode)
 		sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
 
@@ -3061,7 +3061,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 		return -EPERM;
 
 	list_for_each_entry(mevt, &r->evt_list, list) {
-		domid = do_sum ? d->ci->id : d->hdr.id;
+		domid = do_sum ? d->ci_id : d->hdr.id;
 		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
 		if (WARN_ON_ONCE(!priv))
 			return -EINVAL;
@@ -3089,7 +3089,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
 	kn = kernfs_find_and_get(parent_kn, name);
 	if (kn) {
 		/*
-- 
2.49.0

[PATCH 2/5] x86,fs/resctrl: Consolidate monitor event descriptions

[Tony Luck]

There are currently only three monitor events, all associated with
the RDT_RESOURCE_L3 resource. Growing support for additional events
will be easier with some restructuring to have a single point in
file system code where all attributes of all events are defined.

Place all event descriptions into an array mon_event_all[]. Doing
this has the beneficial side effect of removing the need for
rdt_resource::evt_list.

Add resctrl_event_id::QOS_FIRST_EVENT for a lower bound on range
checks for event ids and as the starting index to scan mon_event_all[].

Drop the code that builds evt_list and change the two places where
the list is scanned to scan mon_event_all[] instead using a new
helper macro for_each_mon_event().

Architecture code now informs file system code which events are
available with resctrl_enable_mon_event().

Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 include/linux/resctrl.h            |  4 +-
 include/linux/resctrl_types.h      | 12 ++++--
 fs/resctrl/internal.h              | 13 ++++--
 arch/x86/kernel/cpu/resctrl/core.c | 12 ++++--
 fs/resctrl/monitor.c               | 63 +++++++++++++++---------------
 fs/resctrl/rdtgroup.c              | 11 +++---
 6 files changed, 66 insertions(+), 49 deletions(-)

diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 6fb4894b8cfd..2944042bd84c 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -269,7 +269,6 @@ enum resctrl_schema_fmt {
  * @mon_domains:	RCU list of all monitor domains for this resource
  * @name:		Name to use in "schemata" file.
  * @schema_fmt:		Which format string and parser is used for this schema.
- * @evt_list:		List of monitoring events
  * @mbm_cfg_mask:	Bandwidth sources that can be tracked when bandwidth
  *			monitoring events can be configured.
  * @cdp_capable:	Is the CDP feature available on this resource
@@ -287,7 +286,6 @@ struct rdt_resource {
 	struct list_head	mon_domains;
 	char			*name;
 	enum resctrl_schema_fmt	schema_fmt;
-	struct list_head	evt_list;
 	unsigned int		mbm_cfg_mask;
 	bool			cdp_capable;
 };
@@ -372,6 +370,8 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
 u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
+void resctrl_enable_mon_event(enum resctrl_event_id eventid);
+
 bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt);
 
 /**
diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h
index a25fb9c4070d..2dadbc54e4b3 100644
--- a/include/linux/resctrl_types.h
+++ b/include/linux/resctrl_types.h
@@ -34,11 +34,15 @@
 /* Max event bits supported */
 #define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
 
-/*
- * Event IDs, the values match those used to program IA32_QM_EVTSEL before
- * reading IA32_QM_CTR on RDT systems.
- */
+/* Event IDs */
 enum resctrl_event_id {
+	/* Must match value of first event below */
+	QOS_FIRST_EVENT			= 0x01,
+
+	/*
+	 * These values match those used to program IA32_QM_EVTSEL before
+	 * reading IA32_QM_CTR on RDT systems.
+	 */
 	QOS_L3_OCCUP_EVENT_ID		= 0x01,
 	QOS_L3_MBM_TOTAL_EVENT_ID	= 0x02,
 	QOS_L3_MBM_LOCAL_EVENT_ID	= 0x03,
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 0a1eedba2b03..20e2c45cea64 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -52,19 +52,26 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
 }
 
 /**
- * struct mon_evt - Entry in the event list of a resource
+ * struct mon_evt - Description of a monitor event
  * @evtid:		event id
+ * @rid:		index of the resource for this event
  * @name:		name of the event
  * @configurable:	true if the event is configurable
- * @list:		entry in &rdt_resource->evt_list
+ * @enabled:		true if the event is enabled
  */
 struct mon_evt {
 	enum resctrl_event_id	evtid;
+	enum resctrl_res_level	rid;
 	char			*name;
 	bool			configurable;
-	struct list_head	list;
+	bool			enabled;
 };
 
+extern struct mon_evt mon_event_all[QOS_NUM_EVENTS];
+
+#define for_each_mon_event(mevt) for (mevt = &mon_event_all[QOS_FIRST_EVENT];	\
+				      mevt < &mon_event_all[QOS_NUM_EVENTS]; mevt++)
+
 /**
  * struct mon_data - Monitoring details for each event file.
  * @list:            Member of the global @mon_data_kn_priv_list list.
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 187d527ef73b..7fcae25874fe 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -864,12 +864,18 @@ static __init bool get_rdt_mon_resources(void)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 
-	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC))
+	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) {
+		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID);
 		rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
-	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL))
+	}
+	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
+		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID);
 		rdt_mon_features |= (1 << QOS_L3_MBM_TOTAL_EVENT_ID);
-	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL))
+	}
+	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
+		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID);
 		rdt_mon_features |= (1 << QOS_L3_MBM_LOCAL_EVENT_ID);
+	}
 
 	if (!rdt_mon_features)
 		return false;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index f5637855c3ac..2313e48de55f 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -844,38 +844,39 @@ static void dom_data_exit(struct rdt_resource *r)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-static struct mon_evt llc_occupancy_event = {
-	.name		= "llc_occupancy",
-	.evtid		= QOS_L3_OCCUP_EVENT_ID,
-};
-
-static struct mon_evt mbm_total_event = {
-	.name		= "mbm_total_bytes",
-	.evtid		= QOS_L3_MBM_TOTAL_EVENT_ID,
-};
-
-static struct mon_evt mbm_local_event = {
-	.name		= "mbm_local_bytes",
-	.evtid		= QOS_L3_MBM_LOCAL_EVENT_ID,
-};
-
 /*
- * 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.
+ * All available events. Architecture code marks the ones that
+ * are supported by a system using resctrl_enable_mon_event()
+ * to set .enabled.
  */
-static void l3_mon_evt_init(struct rdt_resource *r)
+struct mon_evt mon_event_all[QOS_NUM_EVENTS] = {
+	[QOS_L3_OCCUP_EVENT_ID] = {
+		.name	= "llc_occupancy",
+		.evtid	= QOS_L3_OCCUP_EVENT_ID,
+		.rid	= RDT_RESOURCE_L3,
+	},
+	[QOS_L3_MBM_TOTAL_EVENT_ID] = {
+		.name	= "mbm_total_bytes",
+		.evtid	= QOS_L3_MBM_TOTAL_EVENT_ID,
+		.rid	= RDT_RESOURCE_L3,
+	},
+	[QOS_L3_MBM_LOCAL_EVENT_ID] = {
+		.name	= "mbm_local_bytes",
+		.evtid	= QOS_L3_MBM_LOCAL_EVENT_ID,
+		.rid	= RDT_RESOURCE_L3,
+	},
+};
+
+void resctrl_enable_mon_event(enum resctrl_event_id eventid)
 {
-	INIT_LIST_HEAD(&r->evt_list);
+	if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS))
+		return;
+	if (mon_event_all[eventid].enabled) {
+		pr_warn("Duplicate enable for event %d\n", eventid);
+		return;
+	}
 
-	if (resctrl_arch_is_llc_occupancy_enabled())
-		list_add_tail(&llc_occupancy_event.list, &r->evt_list);
-	if (resctrl_arch_is_mbm_total_enabled())
-		list_add_tail(&mbm_total_event.list, &r->evt_list);
-	if (resctrl_arch_is_mbm_local_enabled())
-		list_add_tail(&mbm_local_event.list, &r->evt_list);
+	mon_event_all[eventid].enabled = true;
 }
 
 /**
@@ -902,15 +903,13 @@ int resctrl_mon_resource_init(void)
 	if (ret)
 		return ret;
 
-	l3_mon_evt_init(r);
-
 	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) {
-		mbm_total_event.configurable = true;
+		mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].configurable = true;
 		resctrl_file_fflags_init("mbm_total_bytes_config",
 					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 	}
 	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID)) {
-		mbm_local_event.configurable = true;
+		mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].configurable = true;
 		resctrl_file_fflags_init("mbm_local_bytes_config",
 					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 	}
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 77d08229d855..b95501d4b5de 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -1152,7 +1152,9 @@ static int rdt_mon_features_show(struct kernfs_open_file *of,
 	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 	struct mon_evt *mevt;
 
-	list_for_each_entry(mevt, &r->evt_list, list) {
+	for_each_mon_event(mevt) {
+		if (mevt->rid != r->rid || !mevt->enabled)
+			continue;
 		seq_printf(seq, "%s\n", mevt->name);
 		if (mevt->configurable)
 			seq_printf(seq, "%s_config\n", mevt->name);
@@ -3057,10 +3059,9 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 	struct mon_evt *mevt;
 	int ret, domid;
 
-	if (WARN_ON(list_empty(&r->evt_list)))
-		return -EPERM;
-
-	list_for_each_entry(mevt, &r->evt_list, list) {
+	for_each_mon_event(mevt) {
+		if (mevt->rid != r->rid || !mevt->enabled)
+			continue;
 		domid = do_sum ? d->ci_id : d->hdr.id;
 		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
 		if (WARN_ON_ONCE(!priv))
-- 
2.49.0

[PATCH 3/5] x86,fs/resctrl: Replace architecture event enabled checks

[Tony Luck]

The resctrl file system now has complete knowledge of the status
of every event. So there is no need for per-event function calls
to check.

Replace each of the resctrl_arch_is_{event}enabled() calls with
resctrl_is_mon_event_enabled(QOS_{EVENT}).

No functional change.

Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 include/linux/resctrl.h               |  2 ++
 arch/x86/include/asm/resctrl.h        | 15 ---------------
 arch/x86/kernel/cpu/resctrl/core.c    |  4 ++--
 arch/x86/kernel/cpu/resctrl/monitor.c |  4 ++--
 fs/resctrl/ctrlmondata.c              |  4 ++--
 fs/resctrl/monitor.c                  | 16 +++++++++++-----
 fs/resctrl/rdtgroup.c                 | 18 +++++++++---------
 7 files changed, 28 insertions(+), 35 deletions(-)

diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 2944042bd84c..40aba6b5d4f0 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -372,6 +372,8 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
 void resctrl_enable_mon_event(enum resctrl_event_id eventid);
 
+bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid);
+
 bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt);
 
 /**
diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index feb93b50e990..b1dd5d6b87db 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -84,21 +84,6 @@ static inline void resctrl_arch_disable_mon(void)
 	static_branch_dec_cpuslocked(&rdt_enable_key);
 }
 
-static inline bool resctrl_arch_is_llc_occupancy_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID));
-}
-
-static inline bool resctrl_arch_is_mbm_total_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID));
-}
-
-static inline bool resctrl_arch_is_mbm_local_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID));
-}
-
 /*
  * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR
  *
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 7fcae25874fe..1a319ce9328c 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -402,13 +402,13 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom)
 {
 	size_t tsize;
 
-	if (resctrl_arch_is_mbm_total_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) {
 		tsize = sizeof(*hw_dom->arch_mbm_total);
 		hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL);
 		if (!hw_dom->arch_mbm_total)
 			return -ENOMEM;
 	}
-	if (resctrl_arch_is_mbm_local_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) {
 		tsize = sizeof(*hw_dom->arch_mbm_local);
 		hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL);
 		if (!hw_dom->arch_mbm_local) {
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index c261558276cd..61d38517e2bf 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -207,11 +207,11 @@ void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *
 {
 	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 
-	if (resctrl_arch_is_mbm_total_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
 		memset(hw_dom->arch_mbm_total, 0,
 		       sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
 
-	if (resctrl_arch_is_mbm_local_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
 		memset(hw_dom->arch_mbm_local, 0,
 		       sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
 }
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index d98e0d2de09f..ad7ffc6acf13 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -473,12 +473,12 @@ ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
 	rdt_last_cmd_clear();
 
 	if (!strcmp(buf, "mbm_local_bytes")) {
-		if (resctrl_arch_is_mbm_local_enabled())
+		if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
 			rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
 		else
 			ret = -EINVAL;
 	} else if (!strcmp(buf, "mbm_total_bytes")) {
-		if (resctrl_arch_is_mbm_total_enabled())
+		if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
 			rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID;
 		else
 			ret = -EINVAL;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 2313e48de55f..9e988b2c1a22 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -336,7 +336,7 @@ void free_rmid(u32 closid, u32 rmid)
 
 	entry = __rmid_entry(idx);
 
-	if (resctrl_arch_is_llc_occupancy_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID))
 		add_rmid_to_limbo(entry);
 	else
 		list_add_tail(&entry->list, &rmid_free_lru);
@@ -637,10 +637,10 @@ static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
 	 * This is protected from concurrent reads from user as both
 	 * the user and overflow handler hold the global mutex.
 	 */
-	if (resctrl_arch_is_mbm_total_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
 		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
 
-	if (resctrl_arch_is_mbm_local_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
 		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
@@ -879,6 +879,12 @@ void resctrl_enable_mon_event(enum resctrl_event_id eventid)
 	mon_event_all[eventid].enabled = true;
 }
 
+bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid)
+{
+	return eventid >= QOS_FIRST_EVENT && eventid < QOS_NUM_EVENTS &&
+	       mon_event_all[eventid].enabled;
+}
+
 /**
  * resctrl_mon_resource_init() - Initialise global monitoring structures.
  *
@@ -914,9 +920,9 @@ int resctrl_mon_resource_init(void)
 					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 	}
 
-	if (resctrl_arch_is_mbm_local_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
 		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
-	else if (resctrl_arch_is_mbm_total_enabled())
+	else if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
 		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
 
 	return 0;
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index b95501d4b5de..a7eeb33501da 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -123,8 +123,8 @@ void rdt_staged_configs_clear(void)
 
 static bool resctrl_is_mbm_enabled(void)
 {
-	return (resctrl_arch_is_mbm_total_enabled() ||
-		resctrl_arch_is_mbm_local_enabled());
+	return (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID) ||
+		resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID));
 }
 
 static bool resctrl_is_mbm_event(int e)
@@ -196,7 +196,7 @@ static int closid_alloc(void)
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) &&
-	    resctrl_arch_is_llc_occupancy_enabled()) {
+	    resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) {
 		cleanest_closid = resctrl_find_cleanest_closid();
 		if (cleanest_closid < 0)
 			return cleanest_closid;
@@ -4051,7 +4051,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d
 
 	if (resctrl_is_mbm_enabled())
 		cancel_delayed_work(&d->mbm_over);
-	if (resctrl_arch_is_llc_occupancy_enabled() && has_busy_rmid(d)) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && has_busy_rmid(d)) {
 		/*
 		 * When a package is going down, forcefully
 		 * decrement rmid->ebusy. There is no way to know
@@ -4087,12 +4087,12 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	size_t tsize;
 
-	if (resctrl_arch_is_llc_occupancy_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) {
 		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
 		if (!d->rmid_busy_llc)
 			return -ENOMEM;
 	}
-	if (resctrl_arch_is_mbm_total_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) {
 		tsize = sizeof(*d->mbm_total);
 		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
 		if (!d->mbm_total) {
@@ -4100,7 +4100,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain
 			return -ENOMEM;
 		}
 	}
-	if (resctrl_arch_is_mbm_local_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) {
 		tsize = sizeof(*d->mbm_local);
 		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
 		if (!d->mbm_local) {
@@ -4145,7 +4145,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
 					   RESCTRL_PICK_ANY_CPU);
 	}
 
-	if (resctrl_arch_is_llc_occupancy_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID))
 		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
 
 	/*
@@ -4220,7 +4220,7 @@ void resctrl_offline_cpu(unsigned int cpu)
 			cancel_delayed_work(&d->mbm_over);
 			mbm_setup_overflow_handler(d, 0, cpu);
 		}
-		if (resctrl_arch_is_llc_occupancy_enabled() &&
+		if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) &&
 		    cpu == d->cqm_work_cpu && has_busy_rmid(d)) {
 			cancel_delayed_work(&d->cqm_limbo);
 			cqm_setup_limbo_handler(d, 0, cpu);
-- 
2.49.0

[PATCH 4/5] x86/resctrl: Remove 'rdt_mon_features' global variable

[Tony Luck]

rdt_mon_features is used as a bitmask of enabled monitor events. A monitor
event's status is now maintained in mon_evt::enabled with all monitor
events' mon_evt structures found in the filesystem's mon_event_all[] array.

Remove the remaining uses of rdt_mon_features.

Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 arch/x86/include/asm/resctrl.h        | 1 -
 arch/x86/kernel/cpu/resctrl/core.c    | 9 +++++----
 arch/x86/kernel/cpu/resctrl/monitor.c | 5 -----
 3 files changed, 5 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index b1dd5d6b87db..575f8408a9e7 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -44,7 +44,6 @@ DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
 extern bool rdt_alloc_capable;
 extern bool rdt_mon_capable;
-extern unsigned int rdt_mon_features;
 
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 1a319ce9328c..5d14f9a14eda 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -863,21 +863,22 @@ 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;
+	bool ret = false;
 
 	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) {
 		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID);
-		rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
+		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
 		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID);
-		rdt_mon_features |= (1 << QOS_L3_MBM_TOTAL_EVENT_ID);
+		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
 		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID);
-		rdt_mon_features |= (1 << QOS_L3_MBM_LOCAL_EVENT_ID);
+		ret = true;
 	}
 
-	if (!rdt_mon_features)
+	if (!ret)
 		return false;
 
 	return !rdt_get_mon_l3_config(r);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 61d38517e2bf..07f8ab097cbe 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -31,11 +31,6 @@
  */
 bool rdt_mon_capable;
 
-/*
- * Global to indicate which monitoring events are enabled.
- */
-unsigned int rdt_mon_features;
-
 #define CF(cf)	((unsigned long)(1048576 * (cf) + 0.5))
 
 static int snc_nodes_per_l3_cache = 1;
-- 
2.49.0

[PATCH 5/5] x86,fs/resctrl: Prepare for more monitor events

[Tony Luck]

There's a rule in computer programming that objects appear zero,
once, or many times. So code accordingly.

There are two MBM events and resctrl is coded with a lot of

        if (local)
                do one thing
        if (total)
                do a different thing

Change the rdt_mon_domain and rdt_hw_mon_domain structures to hold arrays
of pointers to per event data instead of explicit fields for total and
local bandwidth.

Simplify by coding for many events using loops on which are enabled.

Move resctrl_is_mbm_event() to <linux/resctrl.h> so it can be used more
widely. Also provide a for_each_mbm_event_id() helper macro.

Cleanup variable names in functions touched to consistently use
"eventid" for those with type enum resctrl_event_id.

Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 include/linux/resctrl.h                | 18 +++++++---
 include/linux/resctrl_types.h          |  3 ++
 arch/x86/kernel/cpu/resctrl/internal.h |  9 ++---
 arch/x86/kernel/cpu/resctrl/core.c     | 38 ++++++++++----------
 arch/x86/kernel/cpu/resctrl/monitor.c  | 36 +++++++++----------
 fs/resctrl/monitor.c                   | 13 ++++---
 fs/resctrl/rdtgroup.c                  | 48 ++++++++++++--------------
 7 files changed, 88 insertions(+), 77 deletions(-)

diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 40aba6b5d4f0..bbe57eff962b 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -161,8 +161,9 @@ struct rdt_ctrl_domain {
  * @hdr:		common header for different domain types
  * @ci_id:		cache info id for this domain
  * @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
+ * @mbm_states:		Per-event pointer to the MBM event's saved state.
+ *			An MBM event's state is an array of struct mbm_state
+ *			indexed by RMID on x86 or combined CLOSID, RMID on Arm.
  * @mbm_over:		worker to periodically read MBM h/w counters
  * @cqm_limbo:		worker to periodically read CQM h/w counters
  * @mbm_work_cpu:	worker CPU for MBM h/w counters
@@ -172,8 +173,7 @@ struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
 	unsigned int			ci_id;
 	unsigned long			*rmid_busy_llc;
-	struct mbm_state		*mbm_total;
-	struct mbm_state		*mbm_local;
+	struct mbm_state		*mbm_states[QOS_NUM_L3_MBM_EVENTS];
 	struct delayed_work		mbm_over;
 	struct delayed_work		cqm_limbo;
 	int				mbm_work_cpu;
@@ -376,6 +376,16 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid);
 
 bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt);
 
+static inline bool resctrl_is_mbm_event(enum resctrl_event_id eventid)
+{
+	return (eventid >= QOS_L3_MBM_TOTAL_EVENT_ID &&
+		eventid <= QOS_L3_MBM_LOCAL_EVENT_ID);
+}
+
+#define for_each_mbm_event_id(eventid)				\
+	for (eventid = QOS_L3_MBM_TOTAL_EVENT_ID;		\
+	     eventid <= QOS_L3_MBM_LOCAL_EVENT_ID; eventid++)
+
 /**
  * resctrl_arch_mon_event_config_write() - Write the config for an event.
  * @config_info: struct resctrl_mon_config_info describing the resource, domain
diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h
index 2dadbc54e4b3..d98351663c2c 100644
--- a/include/linux/resctrl_types.h
+++ b/include/linux/resctrl_types.h
@@ -51,4 +51,7 @@ enum resctrl_event_id {
 	QOS_NUM_EVENTS,
 };
 
+#define QOS_NUM_L3_MBM_EVENTS	(QOS_L3_MBM_LOCAL_EVENT_ID - QOS_L3_MBM_TOTAL_EVENT_ID + 1)
+#define MBM_STATE_IDX(evt)	((evt) - QOS_L3_MBM_TOTAL_EVENT_ID)
+
 #endif /* __LINUX_RESCTRL_TYPES_H */
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 5e3c41b36437..44ef0d94131e 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -54,15 +54,16 @@ struct rdt_hw_ctrl_domain {
  * 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
+ * @arch_mbm_states:	arch private state for each MBM event
+ * @arch_mbm_states:	Per-event pointer to the MBM event's saved state.
+ *			An MBM event's state is an array of struct arch_mbm_state
+ *			indexed by RMID on x86 or combined CLOSID, RMID on Arm.
  *
  * Members of this structure are accessed via helpers that provide abstraction.
  */
 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;
+	struct arch_mbm_state		*arch_mbm_states[QOS_NUM_L3_MBM_EVENTS];
 };
 
 static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctrl_domain *r)
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 5d14f9a14eda..6bf2103aac27 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -365,8 +365,8 @@ static void ctrl_domain_free(struct rdt_hw_ctrl_domain *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);
+	for (int i = 0; i < QOS_NUM_L3_MBM_EVENTS; i++)
+		kfree(hw_dom->arch_mbm_states[i]);
 	kfree(hw_dom);
 }
 
@@ -400,25 +400,27 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain *
  */
 static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom)
 {
-	size_t tsize;
-
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) {
-		tsize = sizeof(*hw_dom->arch_mbm_total);
-		hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL);
-		if (!hw_dom->arch_mbm_total)
-			return -ENOMEM;
-	}
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) {
-		tsize = sizeof(*hw_dom->arch_mbm_local);
-		hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL);
-		if (!hw_dom->arch_mbm_local) {
-			kfree(hw_dom->arch_mbm_total);
-			hw_dom->arch_mbm_total = NULL;
-			return -ENOMEM;
-		}
+	size_t tsize = sizeof(*hw_dom->arch_mbm_states[0]);
+	enum resctrl_event_id eventid;
+	int idx;
+
+	for_each_mbm_event_id(eventid) {
+		if (!resctrl_is_mon_event_enabled(eventid))
+			continue;
+		idx = MBM_STATE_IDX(eventid);
+		hw_dom->arch_mbm_states[idx] = kcalloc(num_rmid, tsize, GFP_KERNEL);
+		if (!hw_dom->arch_mbm_states[idx])
+			goto cleanup;
 	}
 
 	return 0;
+cleanup:
+	while (--idx >= 0) {
+		kfree(hw_dom->arch_mbm_states[idx]);
+		hw_dom->arch_mbm_states[idx] = NULL;
+	}
+
+	return -ENOMEM;
 }
 
 static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 07f8ab097cbe..0add57b29a4d 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -161,18 +161,14 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_do
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
 {
-	switch (eventid) {
-	case QOS_L3_OCCUP_EVENT_ID:
-		return NULL;
-	case QOS_L3_MBM_TOTAL_EVENT_ID:
-		return &hw_dom->arch_mbm_total[rmid];
-	case QOS_L3_MBM_LOCAL_EVENT_ID:
-		return &hw_dom->arch_mbm_local[rmid];
-	default:
-		/* Never expect to get here */
-		WARN_ON_ONCE(1);
+	struct arch_mbm_state *state;
+
+	if (!resctrl_is_mbm_event(eventid))
 		return NULL;
-	}
+
+	state = hw_dom->arch_mbm_states[MBM_STATE_IDX(eventid)];
+
+	return state ? &state[rmid] : NULL;
 }
 
 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
@@ -201,14 +197,16 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
-
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
-		memset(hw_dom->arch_mbm_total, 0,
-		       sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
-
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
-		memset(hw_dom->arch_mbm_local, 0,
-		       sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
+	enum resctrl_event_id eventid;
+	int idx;
+
+	for_each_mbm_event_id(eventid) {
+		if (!resctrl_is_mon_event_enabled(eventid))
+			continue;
+		idx = MBM_STATE_IDX(eventid);
+		memset(hw_dom->arch_mbm_states[idx], 0,
+		       sizeof(struct arch_mbm_state) * r->num_rmid);
+	}
 }
 
 static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 9e988b2c1a22..dcc6c00eb362 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -346,15 +346,14 @@ static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
 				       u32 rmid, enum resctrl_event_id evtid)
 {
 	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
+	struct mbm_state *state;
 
-	switch (evtid) {
-	case QOS_L3_MBM_TOTAL_EVENT_ID:
-		return &d->mbm_total[idx];
-	case QOS_L3_MBM_LOCAL_EVENT_ID:
-		return &d->mbm_local[idx];
-	default:
+	if (!resctrl_is_mbm_event(evtid))
 		return NULL;
-	}
+
+	state = d->mbm_states[MBM_STATE_IDX(evtid)];
+
+	return state ? &state[idx] : NULL;
 }
 
 static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index a7eeb33501da..bd6718f0ffd6 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -127,12 +127,6 @@ static bool resctrl_is_mbm_enabled(void)
 		resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID));
 }
 
-static bool resctrl_is_mbm_event(int e)
-{
-	return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
-		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
-}
-
 /*
  * Trivial allocator for CLOSIDs. Use BITMAP APIs to manipulate a bitmap
  * of free CLOSIDs.
@@ -4024,8 +4018,10 @@ static void rdtgroup_setup_default(void)
 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);
+	for (int i = 0; i < QOS_NUM_L3_MBM_EVENTS; i++) {
+		kfree(d->mbm_states[i]);
+		d->mbm_states[i] = NULL;
+	}
 }
 
 void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
@@ -4085,32 +4081,34 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d
 static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-	size_t tsize;
+	size_t tsize = sizeof(*d->mbm_states[0]);
+	enum resctrl_event_id eventid;
+	int idx;
 
 	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) {
 		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
 		if (!d->rmid_busy_llc)
 			return -ENOMEM;
 	}
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) {
-		tsize = sizeof(*d->mbm_total);
-		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
-		if (!d->mbm_total) {
-			bitmap_free(d->rmid_busy_llc);
-			return -ENOMEM;
-		}
-	}
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) {
-		tsize = sizeof(*d->mbm_local);
-		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
-		if (!d->mbm_local) {
-			bitmap_free(d->rmid_busy_llc);
-			kfree(d->mbm_total);
-			return -ENOMEM;
-		}
+
+	for_each_mbm_event_id(eventid) {
+		if (!resctrl_is_mon_event_enabled(eventid))
+			continue;
+		idx = MBM_STATE_IDX(eventid);
+		d->mbm_states[idx] = kcalloc(idx_limit, tsize, GFP_KERNEL);
+		if (!d->mbm_states[idx])
+			goto cleanup;
 	}
 
 	return 0;
+cleanup:
+	bitmap_free(d->rmid_busy_llc);
+	while (--idx >= 0) {
+		kfree(d->mbm_states[idx]);
+		d->mbm_states[idx] = NULL;
+	}
+
+	return -ENOMEM;
 }
 
 int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
-- 
2.49.0

Re: [PATCH 0/5] Latest version of initial patches in AET series

[Moger, Babu]

Hi Tony,

On 6/9/25 11:21, Tony Luck wrote:
> Babu,
> 
> Here's my latest version of those four patches (build on top of Qinyun's
> patch that I believe should go upstream via tip/urgent).

Wonderful. Thank you. Will rebase my patches.

> 
> I believe I addressed all the comments[1] in these four patches
> 
> [1] https://lore.kernel.org/lkml/20250521225049.132551-1-tony.luck@intel.com/
> 
> -Tony
> 
> Qinyun Tan (1):
>   x86,fs/resctrl: Remove unappropriate references to cacheinfo in the
>     resctrl subsystem.
> 
> Tony Luck (4):
>   x86,fs/resctrl: Consolidate monitor event descriptions
>   x86,fs/resctrl: Replace architecture event enabled checks
>   x86/resctrl: Remove 'rdt_mon_features' global variable
>   x86,fs/resctrl: Prepare for more monitor events
> 
>  include/linux/resctrl.h                | 28 +++++---
>  include/linux/resctrl_types.h          | 15 ++--
>  arch/x86/include/asm/resctrl.h         | 16 -----
>  arch/x86/kernel/cpu/resctrl/internal.h |  9 +--
>  fs/resctrl/internal.h                  | 17 +++--
>  arch/x86/kernel/cpu/resctrl/core.c     | 65 +++++++++--------
>  arch/x86/kernel/cpu/resctrl/monitor.c  | 41 +++++------
>  fs/resctrl/ctrlmondata.c               | 17 +++--
>  fs/resctrl/monitor.c                   | 96 ++++++++++++++------------
>  fs/resctrl/rdtgroup.c                  | 79 +++++++++++----------
>  10 files changed, 204 insertions(+), 179 deletions(-)
> 

-- 
Thanks
Babu Moger