1 files changed, 342 insertions, 120 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index c34a35ec0f03..a93ed7d2a160 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -15,6 +15,8 @@
  * Software Developer Manual June 2016, volume 3, section 17.17.
  */
 
+#define pr_fmt(fmt)	"resctrl: " fmt
+
 #include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/sizes.h>
@@ -24,6 +26,7 @@
 #include <asm/resctrl.h>
 
 #include "internal.h"
+#include "trace.h"
 
 /**
  * struct rmid_entry - dirty tracking for all RMID.
@@ -96,6 +99,8 @@ unsigned int resctrl_rmid_realloc_limit;
 
 #define CF(cf)	((unsigned long)(1048576 * (cf) + 0.5))
 
+static int snc_nodes_per_l3_cache = 1;
+
 /*
  * The correction factor table is documented in Documentation/arch/x86/resctrl.rst.
  * If rmid > rmid threshold, MBM total and local values should be multiplied
@@ -184,7 +189,43 @@ static inline struct rmid_entry *__rmid_entry(u32 idx)
 	return entry;
 }
 
-static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
+/*
+ * When Sub-NUMA Cluster (SNC) mode is not enabled (as indicated by
+ * "snc_nodes_per_l3_cache == 1") no translation of the RMID value is
+ * needed. The physical RMID is the same as the logical RMID.
+ *
+ * On a platform with SNC mode enabled, Linux enables RMID sharing mode
+ * via MSR 0xCA0 (see the "RMID Sharing Mode" section in the "Intel
+ * Resource Director Technology Architecture Specification" for a full
+ * description of RMID sharing mode).
+ *
+ * In RMID sharing mode there are fewer "logical RMID" values available
+ * to accumulate data ("physical RMIDs" are divided evenly between SNC
+ * nodes that share an L3 cache). Linux creates an rdt_mon_domain for
+ * each SNC node.
+ *
+ * The value loaded into IA32_PQR_ASSOC is the "logical RMID".
+ *
+ * Data is collected independently on each SNC node and can be retrieved
+ * using the "physical RMID" value computed by this function and loaded
+ * into IA32_QM_EVTSEL. @cpu can be any CPU in the SNC node.
+ *
+ * The scope of the IA32_QM_EVTSEL and IA32_QM_CTR MSRs is at the L3
+ * cache.  So a "physical RMID" may be read from any CPU that shares
+ * the L3 cache with the desired SNC node, not just from a CPU in
+ * the specific SNC node.
+ */
+static int logical_rmid_to_physical_rmid(int cpu, int lrmid)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+
+	if (snc_nodes_per_l3_cache == 1)
+		return lrmid;
+
+	return lrmid + (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid;
+}
+
+static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val)
 {
 	u64 msr_val;
 
@@ -196,7 +237,7 @@ 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, prmid);
 	rdmsrl(MSR_IA32_QM_CTR, msr_val);
 
 	if (msr_val & RMID_VAL_ERROR)
@@ -208,7 +249,7 @@ 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)
 {
@@ -227,19 +268,22 @@ 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 unused, 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);
+	int cpu = cpumask_any(&d->hdr.cpu_mask);
 	struct arch_mbm_state *am;
+	u32 prmid;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
 	if (am) {
 		memset(am, 0, sizeof(*am));
 
+		prmid = logical_rmid_to_physical_rmid(cpu, rmid);
 		/* Record any initial, non-zero count value. */
-		__rmid_read(rmid, eventid, &am->prev_msr);
+		__rmid_read_phys(prmid, eventid, &am->prev_msr);
 	}
 }
 
@@ -247,15 +291,15 @@ 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())
+	if (resctrl_arch_is_mbm_total_enabled())
 		memset(hw_dom->arch_mbm_total, 0,
 		       sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
 
-	if (is_mbm_local_enabled())
+	if (resctrl_arch_is_mbm_local_enabled())
 		memset(hw_dom->arch_mbm_local, 0,
 		       sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
 }
@@ -268,22 +312,22 @@ 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 unused, u32 rmid, enum resctrl_event_id eventid,
 			   u64 *val, void *ignored)
 {
+	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);
+	int cpu = cpumask_any(&d->hdr.cpu_mask);
 	struct arch_mbm_state *am;
 	u64 msr_val, chunks;
+	u32 prmid;
 	int ret;
 
 	resctrl_arch_rmid_read_context_check();
 
-	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
-		return -EINVAL;
-
-	ret = __rmid_read(rmid, eventid, &msr_val);
+	prmid = logical_rmid_to_physical_rmid(cpu, rmid);
+	ret = __rmid_read_phys(prmid, eventid, &msr_val);
 	if (ret)
 		return ret;
 
@@ -319,9 +363,9 @@ static void limbo_release_entry(struct rmid_entry *entry)
  * 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 rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	struct rmid_entry *entry;
 	u32 idx, cur_idx = 1;
@@ -354,6 +398,16 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 			rmid_dirty = true;
 		} else {
 			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
+
+			/*
+			 * x86's CLOSID and RMID are independent numbers, so the entry's
+			 * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the
+			 * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't
+			 * used to select the configuration. It is thus necessary to track both
+			 * CLOSID and RMID because there may be dependencies between them
+			 * on some architectures.
+			 */
+			trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->hdr.id, val);
 		}
 
 		if (force_free || !rmid_dirty) {
@@ -367,7 +421,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 	resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
 }
 
-bool has_busy_rmid(struct rdt_domain *d)
+bool has_busy_rmid(struct rdt_mon_domain *d)
 {
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 
@@ -467,8 +521,8 @@ int alloc_rmid(u32 closid)
 
 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_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	struct rdt_mon_domain *d;
 	u32 idx;
 
 	lockdep_assert_held(&rdtgroup_mutex);
@@ -479,7 +533,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
 
 	entry->busy = 0;
-	list_for_each_entry(d, &r->domains, list) {
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
 		/*
 		 * For the first limbo RMID in the domain,
 		 * setup up the limbo worker.
@@ -508,19 +562,20 @@ void free_rmid(u32 closid, u32 rmid)
 	 * allows architectures that ignore the closid parameter to avoid an
 	 * unnecessary check.
 	 */
-	if (idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
+	if (!resctrl_arch_mon_capable() ||
+	    idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
 						RESCTRL_RESERVED_RMID))
 		return;
 
 	entry = __rmid_entry(idx);
 
-	if (is_llc_occupancy_enabled())
+	if (resctrl_arch_is_llc_occupancy_enabled())
 		add_rmid_to_limbo(entry);
 	else
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid,
+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);
@@ -537,7 +592,10 @@ static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid,
 
 static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
+	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
 	struct mbm_state *m;
+	int err, ret;
 	u64 tval = 0;
 
 	if (rr->first) {
@@ -548,14 +606,47 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 		return 0;
 	}
 
-	rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid,
-					 &tval, rr->arch_mon_ctx);
-	if (rr->err)
-		return rr->err;
+	if (rr->d) {
+		/* Reading a single domain, must be on a CPU in that domain. */
+		if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask))
+			return -EINVAL;
+		rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
+						 rr->evtid, &tval, rr->arch_mon_ctx);
+		if (rr->err)
+			return rr->err;
 
-	rr->val += tval;
+		rr->val += tval;
 
-	return 0;
+		return 0;
+	}
+
+	/* Summing domains that share a cache, must be on a CPU for that cache. */
+	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
+		return -EINVAL;
+
+	/*
+	 * Legacy files must report the sum of an event across all
+	 * domains that share the same L3 cache instance.
+	 * Report success if a read from any domain succeeds, -EINVAL
+	 * (translated to "Unavailable" for user space) if reading from
+	 * all domains fail for any reason.
+	 */
+	ret = -EINVAL;
+	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
+		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);
+		if (!err) {
+			rr->val += tval;
+			ret = 0;
+		}
+	}
+
+	if (ret)
+		rr->err = ret;
+
+	return ret;
 }
 
 /*
@@ -572,9 +663,12 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
  */
 static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
-	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-	struct mbm_state *m = &rr->d->mbm_local[idx];
 	u64 cur_bw, bytes, cur_bytes;
+	struct mbm_state *m;
+
+	m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
+	if (WARN_ON_ONCE(!m))
+		return;
 
 	cur_bytes = rr->val;
 	bytes = cur_bytes - m->prev_bw_bytes;
@@ -624,6 +718,22 @@ void mon_event_count(void *info)
 		rr->err = 0;
 }
 
+static struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu,
+							struct rdt_resource *r)
+{
+	struct rdt_ctrl_domain *d;
+
+	lockdep_assert_cpus_held();
+
+	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;
+	}
+
+	return NULL;
+}
+
 /*
  * Feedback loop for MBA software controller (mba_sc)
  *
@@ -656,27 +766,27 @@ 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;
+	enum resctrl_event_id evt_id;
 	struct rdt_resource *r_mba;
-	struct rdt_domain *dom_mba;
-	u32 cur_bw, user_bw, idx;
 	struct list_head *head;
 	struct rdtgroup *entry;
+	u32 cur_bw, user_bw;
 
-	if (!is_mbm_local_enabled())
-		return;
-
-	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+	r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
+	evt_id = rgrp->mba_mbps_event;
 
 	closid = rgrp->closid;
 	rmid = rgrp->mon.rmid;
-	idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-	pmbm_data = &dom_mbm->mbm_local[idx];
+	pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id);
+	if (WARN_ON_ONCE(!pmbm_data))
+		return;
 
-	dom_mba = get_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;
@@ -693,7 +803,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	 */
 	head = &rgrp->mon.crdtgrp_list;
 	list_for_each_entry(entry, head, mon.crdtgrp_list) {
-		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+		cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id);
+		if (WARN_ON_ONCE(!cmbm_data))
+			return;
 		cur_bw += cmbm_data->prev_bw;
 	}
 
@@ -722,55 +834,45 @@ 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,
-		       u32 closid, u32 rmid)
+static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
+				 u32 closid, u32 rmid, enum resctrl_event_id evtid)
 {
-	struct rmid_read rr;
+	struct rmid_read rr = {0};
 
-	rr.first = false;
 	rr.r = r;
 	rr.d = d;
+	rr.evtid = evtid;
+	rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+	if (IS_ERR(rr.arch_mon_ctx)) {
+		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+				    PTR_ERR(rr.arch_mon_ctx));
+		return;
+	}
+
+	__mon_event_count(closid, rmid, &rr);
 
 	/*
-	 * This is protected from concurrent reads from user
-	 * as both the user and we hold the global mutex.
+	 * If the software controller is enabled, compute the
+	 * bandwidth for this event id.
 	 */
-	if (is_mbm_total_enabled()) {
-		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
-		rr.val = 0;
-		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-		if (IS_ERR(rr.arch_mon_ctx)) {
-			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-					    PTR_ERR(rr.arch_mon_ctx));
-			return;
-		}
-
-		__mon_event_count(closid, rmid, &rr);
+	if (is_mba_sc(NULL))
+		mbm_bw_count(closid, rmid, &rr);
 
-		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-	}
-	if (is_mbm_local_enabled()) {
-		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
-		rr.val = 0;
-		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-		if (IS_ERR(rr.arch_mon_ctx)) {
-			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-					    PTR_ERR(rr.arch_mon_ctx));
-			return;
-		}
-
-		__mon_event_count(closid, rmid, &rr);
+	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
+}
 
-		/*
-		 * Call the MBA software controller only for the
-		 * control groups and when user has enabled
-		 * the software controller explicitly.
-		 */
-		if (is_mba_sc(NULL))
-			mbm_bw_count(closid, rmid, &rr);
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
+		       u32 closid, u32 rmid)
+{
+	/*
+	 * This is protected from concurrent reads from user as both
+	 * the user and overflow handler hold the global mutex.
+	 */
+	if (resctrl_arch_is_mbm_total_enabled())
+		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
 
-		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-	}
+	if (resctrl_arch_is_mbm_local_enabled())
+		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
 /*
@@ -780,17 +882,17 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
 void cqm_handle_limbo(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
-	struct rdt_domain *d;
+	struct rdt_mon_domain *d;
 
 	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
-	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);
 
 	if (has_busy_rmid(d)) {
-		d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+		d->cqm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
 							   RESCTRL_PICK_ANY_CPU);
 		schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
 					 delay);
@@ -808,13 +910,13 @@ void cqm_handle_limbo(struct work_struct *work)
  * @exclude_cpu:   Which CPU the handler should not run on,
  *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
  */
-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,
 			     int exclude_cpu)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
+	cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
 	dom->cqm_work_cpu = cpu;
 
 	if (cpu < nr_cpu_ids)
@@ -825,9 +927,9 @@ void mbm_handle_overflow(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
 	struct rdtgroup *prgrp, *crgrp;
+	struct rdt_mon_domain *d;
 	struct list_head *head;
 	struct rdt_resource *r;
-	struct rdt_domain *d;
 
 	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
@@ -839,8 +941,8 @@ void mbm_handle_overflow(struct work_struct *work)
 	if (!resctrl_mounted || !resctrl_arch_mon_capable())
 		goto out_unlock;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_domain, mbm_over.work);
+	r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	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->closid, prgrp->mon.rmid);
@@ -857,7 +959,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	 * Re-check for housekeeping CPUs. This allows the overflow handler to
 	 * move off a nohz_full CPU quickly.
 	 */
-	d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+	d->mbm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
 						   RESCTRL_PICK_ANY_CPU);
 	schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
 
@@ -874,7 +976,7 @@ out_unlock:
  * @exclude_cpu:   Which CPU the handler should not run on,
  *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
  */
-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,
 				int exclude_cpu)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
@@ -886,7 +988,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms,
 	 */
 	if (!resctrl_mounted || !resctrl_arch_mon_capable())
 		return;
-	cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
+	cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
 	dom->mbm_work_cpu = cpu;
 
 	if (cpu < nr_cpu_ids)
@@ -941,7 +1043,7 @@ static int dom_data_init(struct rdt_resource *r)
 	/*
 	 * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and
 	 * are always allocated. These are used for the rdtgroup_default
-	 * control group, which will be setup later in rdtgroup_init().
+	 * control group, which will be setup later in resctrl_init().
 	 */
 	idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
 					   RESCTRL_RESERVED_RMID);
@@ -954,10 +1056,13 @@ out_unlock:
 	return err;
 }
 
-static void __exit dom_data_exit(void)
+static void dom_data_exit(struct rdt_resource *r)
 {
 	mutex_lock(&rdtgroup_mutex);
 
+	if (!r->mon_capable)
+		goto out_unlock;
+
 	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
 		kfree(closid_num_dirty_rmid);
 		closid_num_dirty_rmid = NULL;
@@ -966,6 +1071,7 @@ static void __exit dom_data_exit(void)
 	kfree(rmid_ptrs);
 	rmid_ptrs = NULL;
 
+out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
 }
 
@@ -995,24 +1101,153 @@ static void l3_mon_evt_init(struct rdt_resource *r)
 {
 	INIT_LIST_HEAD(&r->evt_list);
 
-	if (is_llc_occupancy_enabled())
+	if (resctrl_arch_is_llc_occupancy_enabled())
 		list_add_tail(&llc_occupancy_event.list, &r->evt_list);
-	if (is_mbm_total_enabled())
+	if (resctrl_arch_is_mbm_total_enabled())
 		list_add_tail(&mbm_total_event.list, &r->evt_list);
-	if (is_mbm_local_enabled())
+	if (resctrl_arch_is_mbm_local_enabled())
 		list_add_tail(&mbm_local_event.list, &r->evt_list);
 }
 
+/*
+ * 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 RMID sharing 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
+ * counting operations from tasks. Code to read the counters
+ * must adjust RMID counter numbers based on SNC node. See
+ * logical_rmid_to_physical_rmid() for code that does this.
+ */
+void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+	if (snc_nodes_per_l3_cache > 1)
+		msr_clear_bit(MSR_RMID_SNC_CONFIG, 0);
+}
+
+/* CPU models that support MSR_RMID_SNC_CONFIG */
+static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
+	X86_MATCH_VFM(INTEL_ICELAKE_X, 0),
+	X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, 0),
+	X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, 0),
+	X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, 0),
+	X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_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
+ * number of CPUs sharing the L3 cache with CPU0 to the number of CPUs in
+ * the same NUMA node as CPU0.
+ * 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)
+{
+	struct cacheinfo *ci = get_cpu_cacheinfo_level(0, RESCTRL_L3_CACHE);
+	const cpumask_t *node0_cpumask;
+	int cpus_per_node, cpus_per_l3;
+	int ret;
+
+	if (!x86_match_cpu(snc_cpu_ids) || !ci)
+		return 1;
+
+	cpus_read_lock();
+	if (num_online_cpus() != num_present_cpus())
+		pr_warn("Some CPUs offline, SNC detection may be incorrect\n");
+	cpus_read_unlock();
+
+	node0_cpumask = cpumask_of_node(cpu_to_node(0));
+
+	cpus_per_node = cpumask_weight(node0_cpumask);
+	cpus_per_l3 = cpumask_weight(&ci->shared_cpu_map);
+
+	if (!cpus_per_node || !cpus_per_l3)
+		return 1;
+
+	ret = cpus_per_l3 / cpus_per_node;
+
+	/* sanity check: Only valid results are 1, 2, 3, 4, 6 */
+	switch (ret) {
+	case 1:
+		break;
+	case 2 ... 4:
+	case 6:
+		pr_info("Sub-NUMA Cluster mode detected with %d nodes per L3 cache\n", ret);
+		rdt_resources_all[RDT_RESOURCE_L3].r_resctrl.mon_scope = RESCTRL_L3_NODE;
+		break;
+	default:
+		pr_warn("Ignore improbable SNC node count %d\n", ret);
+		ret = 1;
+		break;
+	}
+
+	return ret;
+}
+
+/**
+ * resctrl_mon_resource_init() - Initialise global monitoring structures.
+ *
+ * Allocate and initialise global monitor resources that do not belong to a
+ * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists.
+ * Called once during boot after the struct rdt_resource's have been configured
+ * but before the filesystem is mounted.
+ * Resctrl's cpuhp callbacks may be called before this point to bring a domain
+ * online.
+ *
+ * Returns 0 for success, or -ENOMEM.
+ */
+int __init resctrl_mon_resource_init(void)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	int ret;
+
+	if (!r->mon_capable)
+		return 0;
+
+	ret = dom_data_init(r);
+	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;
+		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;
+		resctrl_file_fflags_init("mbm_local_bytes_config",
+					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
+	}
+
+	if (resctrl_arch_is_mbm_local_enabled())
+		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+	else if (resctrl_arch_is_mbm_total_enabled())
+		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
+
+	return 0;
+}
+
 int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 {
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	unsigned int threshold;
-	int ret;
+
+	snc_nodes_per_l3_cache = snc_get_config();
 
 	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)
@@ -1036,37 +1271,24 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	 */
 	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold);
 
-	ret = dom_data_init(r);
-	if (ret)
-		return ret;
-
 	if (rdt_cpu_has(X86_FEATURE_BMEC)) {
 		u32 eax, ebx, ecx, edx;
 
 		/* Detect list of bandwidth sources that can be tracked */
 		cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx);
-		hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
-
-		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
-			mbm_total_event.configurable = true;
-			mbm_config_rftype_init("mbm_total_bytes_config");
-		}
-		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
-			mbm_local_event.configurable = true;
-			mbm_config_rftype_init("mbm_local_bytes_config");
-		}
+		r->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
 	}
 
-	l3_mon_evt_init(r);
-
 	r->mon_capable = true;
 
 	return 0;
 }
 
-void __exit rdt_put_mon_l3_config(void)
+void resctrl_mon_resource_exit(void)
 {
-	dom_data_exit();
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+
+	dom_data_exit(r);
 }
 
 void __init intel_rdt_mbm_apply_quirk(void)