x86,fs/resctrl: Remove inappropriate references to cacheinfo in the resctrl subsystem

commit 594902c986e269660302f09df9ec4bf1cf017b77 upstream.

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.

Intel-SIG: commit 594902c986e
x86,fs/resctrl: Remove inappropriate references to cacheinfo in the resctrl subsystem
backport to RDT driver for CWF

Fixes: 328ea68 ("x86/resctrl: Prepare for new Sub-NUMA Cluster (SNC) monitor files")
Signed-off-by: Qinyun Tan <qinyuntan@linux.alibaba.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250530182053.37502-2-qinyuntan@linux.alibaba.com
Signed-off-by: Kui Wen <kui.wen@intel.com>

Author: beckwen

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

@@ -588,6 +588,7 @@ 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);
@@ -615,12 +616,13 @@ 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);

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

@@ -558,11 +558,12 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	struct rdt_domain_hdr *hdr;
 	struct rmid_read rr = {0};
 	struct rdt_mon_domain *d;
-	u32 resid, evtid, domid;
+	u32 resid, evtid;
 	struct rdtgroup *rdtgrp;
+	int domid, cpu, ret = 0;
 	struct rdt_resource *r;
+	struct cacheinfo *ci;
 	union mon_data_bits md;
-	int ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
@@ -584,10 +585,14 @@ 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;
 			}
 		}

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

@@ -160,7 +160,7 @@ union mon_data_bits {
  *	   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.
@@ -174,7 +174,7 @@ 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;

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

@@ -594,6 +594,7 @@ 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;
@@ -621,7 +622,8 @@ 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;
 
 	/*
@@ -633,7 +635,7 @@ 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);

arch/x86/kernel/cpu/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;
 
 	priv.u.rid = r->rid;
-	priv.u.domid = do_sum ? d->ci->id : d->hdr.id;
+	priv.u.domid = do_sum ? d->ci_id : d->hdr.id;
 	priv.u.sum = do_sum;
 	list_for_each_entry(mevt, &r->evt_list, list) {
 		priv.u.evtid = mevt->evtid;
@@ -3088,7 +3088,7 @@ 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) {
 		/*

include/linux/resctrl.h

@@ -97,7 +97,7 @@ 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
@@ -108,7 +108,7 @@ struct rdt_ctrl_domain {
  */
 struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
-	struct cacheinfo		*ci;
+	unsigned long			ci_id;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;