Merge tag 'x86_cache_for_v6.9_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull resource control updates from Borislav Petkov:

 - Rework different aspects of the resctrl code like adding
   arch-specific accessors and splitting the locking, in order to
   accomodate ARM's MPAM implementation of hw resource control and be
   able to use the same filesystem control interface like on x86. Work
   by James Morse

 - Improve the memory bandwidth throttling heuristic to handle workloads
   with not too regular load levels which end up penalized unnecessarily

 - Use CPUID to detect the memory bandwidth enforcement limit on AMD

 - The usual set of fixes

* tag 'x86_cache_for_v6.9_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  x86/resctrl: Remove lockdep annotation that triggers false positive
  x86/resctrl: Separate arch and fs resctrl locks
  x86/resctrl: Move domain helper migration into resctrl_offline_cpu()
  x86/resctrl: Add CPU offline callback for resctrl work
  x86/resctrl: Allow overflow/limbo handlers to be scheduled on any-but CPU
  x86/resctrl: Add CPU online callback for resctrl work
  x86/resctrl: Add helpers for system wide mon/alloc capable
  x86/resctrl: Make rdt_enable_key the arch's decision to switch
  x86/resctrl: Move alloc/mon static keys into helpers
  x86/resctrl: Make resctrl_mounted checks explicit
  x86/resctrl: Allow arch to allocate memory needed in resctrl_arch_rmid_read()
  x86/resctrl: Allow resctrl_arch_rmid_read() to sleep
  x86/resctrl: Queue mon_event_read() instead of sending an IPI
  x86/resctrl: Add cpumask_any_housekeeping() for limbo/overflow
  x86/resctrl: Move CLOSID/RMID matching and setting to use helpers
  x86/resctrl: Allocate the cleanest CLOSID by searching closid_num_dirty_rmid
  x86/resctrl: Use __set_bit()/__clear_bit() instead of open coding
  x86/resctrl: Track the number of dirty RMID a CLOSID has
  x86/resctrl: Allow RMID allocation to be scoped by CLOSID
  x86/resctrl: Access per-rmid structures by index
  ...

9 files changed, 946 insertions, 339 deletions

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 255a78d9d90672..12dbd2588ca7cc 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -7,6 +7,13 @@
 #include <linux/sched.h>
 #include <linux/jump_label.h>
 
+/*
+ * This value can never be a valid CLOSID, and is used when mapping a
+ * (closid, rmid) pair to an index and back. On x86 only the RMID is
+ * needed. The index is a software defined value.
+ */
+#define X86_RESCTRL_EMPTY_CLOSID         ((u32)~0)
+
 /**
  * struct resctrl_pqr_state - State cache for the PQR MSR
  * @cur_rmid:		The cached Resource Monitoring ID
@@ -31,10 +38,47 @@ struct resctrl_pqr_state {
 
 DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
+extern bool rdt_alloc_capable;
+extern bool rdt_mon_capable;
+
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
 
+static inline bool resctrl_arch_alloc_capable(void)
+{
+	return rdt_alloc_capable;
+}
+
+static inline void resctrl_arch_enable_alloc(void)
+{
+	static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
+	static_branch_inc_cpuslocked(&rdt_enable_key);
+}
+
+static inline void resctrl_arch_disable_alloc(void)
+{
+	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
+	static_branch_dec_cpuslocked(&rdt_enable_key);
+}
+
+static inline bool resctrl_arch_mon_capable(void)
+{
+	return rdt_mon_capable;
+}
+
+static inline void resctrl_arch_enable_mon(void)
+{
+	static_branch_enable_cpuslocked(&rdt_mon_enable_key);
+	static_branch_inc_cpuslocked(&rdt_enable_key);
+}
+
+static inline void resctrl_arch_disable_mon(void)
+{
+	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
+	static_branch_dec_cpuslocked(&rdt_enable_key);
+}
+
 /*
  * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR
  *
@@ -88,12 +132,58 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
 	return val * scale;
 }
 
+static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk,
+						u32 closid, u32 rmid)
+{
+	WRITE_ONCE(tsk->closid, closid);
+	WRITE_ONCE(tsk->rmid, rmid);
+}
+
+static inline bool resctrl_arch_match_closid(struct task_struct *tsk, u32 closid)
+{
+	return READ_ONCE(tsk->closid) == closid;
+}
+
+static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored,
+					   u32 rmid)
+{
+	return READ_ONCE(tsk->rmid) == rmid;
+}
+
 static inline void resctrl_sched_in(struct task_struct *tsk)
 {
 	if (static_branch_likely(&rdt_enable_key))
 		__resctrl_sched_in(tsk);
 }
 
+static inline u32 resctrl_arch_system_num_rmid_idx(void)
+{
+	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
+	return boot_cpu_data.x86_cache_max_rmid + 1;
+}
+
+static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid)
+{
+	*rmid = idx;
+	*closid = X86_RESCTRL_EMPTY_CLOSID;
+}
+
+static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid)
+{
+	return rmid;
+}
+
+/* x86 can always read an rmid, nothing needs allocating */
+struct rdt_resource;
+static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid)
+{
+	might_sleep();
+	return NULL;
+};
+
+static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
+					     void *ctx) { };
+
 void resctrl_cpu_detect(struct cpuinfo_x86 *c);
 
 #else
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 19e0681f04356d..83e40341583e6f 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -16,6 +16,7 @@
 
 #define pr_fmt(fmt)	"resctrl: " fmt
 
+#include <linux/cpu.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/cacheinfo.h>
@@ -25,8 +26,15 @@
 #include <asm/resctrl.h>
 #include "internal.h"
 
-/* Mutex to protect rdtgroup access. */
-DEFINE_MUTEX(rdtgroup_mutex);
+/*
+ * rdt_domain structures are kfree()d when their last CPU goes offline,
+ * and allocated when the first CPU in a new domain comes online.
+ * The rdt_resource's domain list is updated when this happens. Readers of
+ * the domain list must either take cpus_read_lock(), or rely on an RCU
+ * read-side critical section, to avoid observing concurrent modification.
+ * All writers take this mutex:
+ */
+static DEFINE_MUTEX(domain_list_lock);
 
 /*
  * The cached resctrl_pqr_state is strictly per CPU and can never be
@@ -136,15 +144,15 @@ static inline void cache_alloc_hsw_probe(void)
 {
 	struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_L3];
 	struct rdt_resource *r  = &hw_res->r_resctrl;
-	u32 l, h, max_cbm = BIT_MASK(20) - 1;
+	u64 max_cbm = BIT_ULL_MASK(20) - 1, l3_cbm_0;
 
-	if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0))
+	if (wrmsrl_safe(MSR_IA32_L3_CBM_BASE, max_cbm))
 		return;
 
-	rdmsr(MSR_IA32_L3_CBM_BASE, l, h);
+	rdmsrl(MSR_IA32_L3_CBM_BASE, l3_cbm_0);
 
 	/* If all the bits were set in MSR, return success */
-	if (l != max_cbm)
+	if (l3_cbm_0 != max_cbm)
 		return;
 
 	hw_res->num_closid = 4;
@@ -231,9 +239,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
 static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	union cpuid_0x10_3_eax eax;
-	union cpuid_0x10_x_edx edx;
-	u32 ebx, ecx, subleaf;
+	u32 eax, ebx, ecx, edx, subleaf;
 
 	/*
 	 * Query CPUID_Fn80000020_EDX_x01 for MBA and
@@ -241,9 +247,9 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 	 */
 	subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 :  1;
 
-	cpuid_count(0x80000020, subleaf, &eax.full, &ebx, &ecx, &edx.full);
-	hw_res->num_closid = edx.split.cos_max + 1;
-	r->default_ctrl = MAX_MBA_BW_AMD;
+	cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx);
+	hw_res->num_closid = edx + 1;
+	r->default_ctrl = 1 << eax;
 
 	/* AMD does not use delay */
 	r->membw.delay_linear = false;
@@ -512,6 +518,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	struct rdt_domain *d;
 	int err;
 
+	lockdep_assert_held(&domain_list_lock);
+
 	d = rdt_find_domain(r, id, &add_pos);
 	if (IS_ERR(d)) {
 		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
@@ -545,11 +553,12 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	list_add_tail(&d->list, add_pos);
+	list_add_tail_rcu(&d->list, add_pos);
 
 	err = resctrl_online_domain(r, d);
 	if (err) {
-		list_del(&d->list);
+		list_del_rcu(&d->list);
+		synchronize_rcu();
 		domain_free(hw_dom);
 	}
 }
@@ -560,6 +569,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 
+	lockdep_assert_held(&domain_list_lock);
+
 	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);
@@ -570,7 +581,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 	cpumask_clear_cpu(cpu, &d->cpu_mask);
 	if (cpumask_empty(&d->cpu_mask)) {
 		resctrl_offline_domain(r, d);
-		list_del(&d->list);
+		list_del_rcu(&d->list);
+		synchronize_rcu();
 
 		/*
 		 * rdt_domain "d" is going to be freed below, so clear
@@ -582,73 +594,47 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 
 		return;
 	}
-
-	if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
-		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
-			cancel_delayed_work(&d->mbm_over);
-			mbm_setup_overflow_handler(d, 0);
-		}
-		if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
-		    has_busy_rmid(r, d)) {
-			cancel_delayed_work(&d->cqm_limbo);
-			cqm_setup_limbo_handler(d, 0);
-		}
-	}
 }
 
 static void clear_closid_rmid(int cpu)
 {
 	struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state);
 
-	state->default_closid = 0;
-	state->default_rmid = 0;
-	state->cur_closid = 0;
-	state->cur_rmid = 0;
-	wrmsr(MSR_IA32_PQR_ASSOC, 0, 0);
+	state->default_closid = RESCTRL_RESERVED_CLOSID;
+	state->default_rmid = RESCTRL_RESERVED_RMID;
+	state->cur_closid = RESCTRL_RESERVED_CLOSID;
+	state->cur_rmid = RESCTRL_RESERVED_RMID;
+	wrmsr(MSR_IA32_PQR_ASSOC, RESCTRL_RESERVED_RMID,
+	      RESCTRL_RESERVED_CLOSID);
 }
 
-static int resctrl_online_cpu(unsigned int cpu)
+static int resctrl_arch_online_cpu(unsigned int cpu)
 {
 	struct rdt_resource *r;
 
-	mutex_lock(&rdtgroup_mutex);
+	mutex_lock(&domain_list_lock);
 	for_each_capable_rdt_resource(r)
 		domain_add_cpu(cpu, r);
-	/* The cpu is set in default rdtgroup after online. */
-	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
+	mutex_unlock(&domain_list_lock);
+
 	clear_closid_rmid(cpu);
-	mutex_unlock(&rdtgroup_mutex);
+	resctrl_online_cpu(cpu);
 
 	return 0;
 }
 
-static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
-{
-	struct rdtgroup *cr;
-
-	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
-		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) {
-			break;
-		}
-	}
-}
-
-static int resctrl_offline_cpu(unsigned int cpu)
+static int resctrl_arch_offline_cpu(unsigned int cpu)
 {
-	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
 
-	mutex_lock(&rdtgroup_mutex);
+	resctrl_offline_cpu(cpu);
+
+	mutex_lock(&domain_list_lock);
 	for_each_capable_rdt_resource(r)
 		domain_remove_cpu(cpu, r);
-	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
-		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
-			clear_childcpus(rdtgrp, cpu);
-			break;
-		}
-	}
+	mutex_unlock(&domain_list_lock);
+
 	clear_closid_rmid(cpu);
-	mutex_unlock(&rdtgroup_mutex);
 
 	return 0;
 }
@@ -968,7 +954,8 @@ static int __init resctrl_late_init(void)
 
 	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 				  "x86/resctrl/cat:online:",
-				  resctrl_online_cpu, resctrl_offline_cpu);
+				  resctrl_arch_online_cpu,
+				  resctrl_arch_offline_cpu);
 	if (state < 0)
 		return state;
 
@@ -992,8 +979,14 @@ late_initcall(resctrl_late_init);
 
 static void __exit resctrl_exit(void)
 {
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+
 	cpuhp_remove_state(rdt_online);
+
 	rdtgroup_exit();
+
+	if (r->mon_capable)
+		rdt_put_mon_l3_config();
 }
 
 __exitcall(resctrl_exit);
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index beccb0e87ba741..7997b47743a210 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -19,6 +19,8 @@
 #include <linux/kernfs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/tick.h>
+
 #include "internal.h"
 
 /*
@@ -210,6 +212,9 @@ static int parse_line(char *line, struct resctrl_schema *s,
 	struct rdt_domain *d;
 	unsigned long dom_id;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
 	    (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
 		rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
@@ -314,6 +319,9 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 	struct rdt_domain *d;
 	u32 idx;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
 
@@ -379,11 +387,9 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 		return -EINVAL;
 	buf[nbytes - 1] = '\0';
 
-	cpus_read_lock();
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
 		rdtgroup_kn_unlock(of->kn);
-		cpus_read_unlock();
 		return -ENOENT;
 	}
 	rdt_last_cmd_clear();
@@ -445,7 +451,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 out:
 	rdt_staged_configs_clear();
 	rdtgroup_kn_unlock(of->kn);
-	cpus_read_unlock();
 	return ret ?: nbytes;
 }
 
@@ -465,6 +470,9 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	bool sep = false;
 	u32 ctrl_val;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	seq_printf(s, "%*s:", max_name_width, schema->name);
 	list_for_each_entry(dom, &r->domains, list) {
 		if (sep)
@@ -522,12 +530,24 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 	return ret;
 }
 
+static int smp_mon_event_count(void *arg)
+{
+	mon_event_count(arg);
+
+	return 0;
+}
+
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
 		    int evtid, int first)
 {
+	int cpu;
+
+	/* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	/*
-	 * setup the parameters to send to the IPI to read the data.
+	 * Setup the parameters to pass to mon_event_count() to read the data.
 	 */
 	rr->rgrp = rdtgrp;
 	rr->evtid = evtid;
@@ -535,8 +555,26 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	rr->d = d;
 	rr->val = 0;
 	rr->first = first;
+	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
+	if (IS_ERR(rr->arch_mon_ctx)) {
+		rr->err = -EINVAL;
+		return;
+	}
+
+	cpu = cpumask_any_housekeeping(&d->cpu_mask, RESCTRL_PICK_ANY_CPU);
+
+	/*
+	 * cpumask_any_housekeeping() prefers housekeeping CPUs, but
+	 * are all the CPUs nohz_full? If yes, pick a CPU to IPI.
+	 * MPAM's resctrl_arch_rmid_read() is unable to read the
+	 * counters on some platforms if its called in IRQ context.
+	 */
+	if (tick_nohz_full_cpu(cpu))
+		smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	else
+		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
 
-	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index a4f1aa15f0a2a8..c99f26ebe7a653 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -7,6 +7,9 @@
 #include <linux/kernfs.h>
 #include <linux/fs_context.h>
 #include <linux/jump_label.h>
+#include <linux/tick.h>
+
+#include <asm/resctrl.h>
 
 #define L3_QOS_CDP_ENABLE		0x01ULL
 
@@ -18,7 +21,6 @@
 #define MBM_OVERFLOW_INTERVAL		1000
 #define MAX_MBA_BW			100u
 #define MBA_IS_LINEAR			0x4
-#define MAX_MBA_BW_AMD			0x800
 #define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
@@ -54,6 +56,46 @@
 /* Max event bits supported */
 #define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
 
+/**
+ * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
+ *			        aren't marked nohz_full
+ * @mask:	The mask to pick a CPU from.
+ * @exclude_cpu:The CPU to avoid picking.
+ *
+ * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping
+ * CPUs that don't use nohz_full, these are preferred. Pass
+ * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs.
+ *
+ * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available.
+ */
+static inline unsigned int
+cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
+{
+	unsigned int cpu, hk_cpu;
+
+	if (exclude_cpu == RESCTRL_PICK_ANY_CPU)
+		cpu = cpumask_any(mask);
+	else
+		cpu = cpumask_any_but(mask, exclude_cpu);
+
+	if (!IS_ENABLED(CONFIG_NO_HZ_FULL))
+		return cpu;
+
+	/* If the CPU picked isn't marked nohz_full nothing more needs doing. */
+	if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu))
+		return cpu;
+
+	/* Try to find a CPU that isn't nohz_full to use in preference */
+	hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
+	if (hk_cpu == exclude_cpu)
+		hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask);
+
+	if (hk_cpu < nr_cpu_ids)
+		cpu = hk_cpu;
+
+	return cpu;
+}
+
 struct rdt_fs_context {
 	struct kernfs_fs_context	kfc;
 	bool				enable_cdpl2;
@@ -69,9 +111,6 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
 	return container_of(kfc, struct rdt_fs_context, kfc);
 }
 
-DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
-DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
-
 /**
  * struct mon_evt - Entry in the event list of a resource
  * @evtid:		event id
@@ -112,12 +151,12 @@ struct rmid_read {
 	bool			first;
 	int			err;
 	u64			val;
+	void			*arch_mon_ctx;
 };
 
-extern bool rdt_alloc_capable;
-extern bool rdt_mon_capable;
 extern unsigned int rdt_mon_features;
 extern struct list_head resctrl_schema_all;
+extern bool resctrl_mounted;
 
 enum rdt_group_type {
 	RDTCTRL_GROUP = 0,
@@ -296,14 +335,10 @@ struct rftype {
  * struct mbm_state - status for each MBM counter in each domain
  * @prev_bw_bytes: Previous bytes value read for bandwidth calculation
  * @prev_bw:	The most recent bandwidth in MBps
- * @delta_bw:	Difference between the current and previous bandwidth
- * @delta_comp:	Indicates whether to compute the delta_bw
  */
 struct mbm_state {
 	u64	prev_bw_bytes;
 	u32	prev_bw;
-	u32	delta_bw;
-	bool	delta_comp;
 };
 
 /**
@@ -395,6 +430,8 @@ struct rdt_parse_data {
  * @msr_update:		Function pointer to update QOS MSRs
  * @mon_scale:		cqm counter * mon_scale = occupancy in bytes
  * @mbm_width:		Monitor width, to detect and correct for overflow.
+ * @mbm_cfg_mask:	Bandwidth sources that can be tracked when Bandwidth
+ *			Monitoring Event Configuration (BMEC) is supported.
  * @cdp_enabled:	CDP state of this resource
  *
  * Members of this structure are either private to the architecture
@@ -409,6 +446,7 @@ struct rdt_hw_resource {
 				 struct rdt_resource *r);
 	unsigned int		mon_scale;
 	unsigned int		mbm_width;
+	unsigned int		mbm_cfg_mask;
 	bool			cdp_enabled;
 };
 
@@ -426,8 +464,6 @@ extern struct mutex rdtgroup_mutex;
 
 extern struct rdt_hw_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
-DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
-
 extern struct dentry *debugfs_resctrl;
 
 enum resctrl_res_level {
@@ -543,9 +579,10 @@ void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int closids_supported(void);
 void closid_free(int closid);
-int alloc_rmid(void);
-void free_rmid(u32 rmid);
+int alloc_rmid(u32 closid);
+void free_rmid(u32 closid, u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
+void __exit rdt_put_mon_l3_config(void);
 bool __init rdt_cpu_has(int flag);
 void mon_event_count(void *info);
 int rdtgroup_mondata_show(struct seq_file *m, void *arg);
@@ -553,17 +590,21 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
 		    int evtid, int first);
 void mbm_setup_overflow_handler(struct rdt_domain *dom,
-				unsigned long delay_ms);
+				unsigned long delay_ms,
+				int exclude_cpu);
 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_domain *dom, unsigned long delay_ms,
+			     int exclude_cpu);
 void cqm_handle_limbo(struct work_struct *work);
-bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
+bool has_busy_rmid(struct rdt_domain *d);
 void __check_limbo(struct rdt_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);
 void rdt_staged_configs_clear(void);
+bool closid_allocated(unsigned int closid);
+int resctrl_find_cleanest_closid(void);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f136ac046851c8..c34a35ec0f031a 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -15,6 +15,7 @@
  * Software Developer Manual June 2016, volume 3, section 17.17.
  */
 
+#include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
@@ -24,7 +25,20 @@
 
 #include "internal.h"
 
+/**
+ * struct rmid_entry - dirty tracking for all RMID.
+ * @closid:	The CLOSID for this entry.
+ * @rmid:	The RMID for this entry.
+ * @busy:	The number of domains with cached data using this RMID.
+ * @list:	Member of the rmid_free_lru list when busy == 0.
+ *
+ * Depending on the architecture the correct monitor is accessed using
+ * both @closid and @rmid, or @rmid only.
+ *
+ * Take the rdtgroup_mutex when accessing.
+ */
 struct rmid_entry {
+	u32				closid;
 	u32				rmid;
 	int				busy;
 	struct list_head		list;
@@ -38,6 +52,13 @@ struct rmid_entry {
 static LIST_HEAD(rmid_free_lru);
 
 /*
+ * @closid_num_dirty_rmid    The number of dirty RMID each CLOSID has.
+ *     Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined.
+ *     Indexed by CLOSID. Protected by rdtgroup_mutex.
+ */
+static u32 *closid_num_dirty_rmid;
+
+/*
  * @rmid_limbo_count - count of currently unused but (potentially)
  *     dirty RMIDs.
  *     This counts RMIDs that no one is currently using but that
@@ -136,12 +157,29 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
 	return val;
 }
 
-static inline struct rmid_entry *__rmid_entry(u32 rmid)
+/*
+ * x86 and arm64 differ in their handling of monitoring.
+ * x86's RMID are independent numbers, there is only one source of traffic
+ * with an RMID value of '1'.
+ * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of
+ * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID
+ * value is no longer unique.
+ * To account for this, resctrl uses an index. On x86 this is just the RMID,
+ * on arm64 it encodes the CLOSID and RMID. This gives a unique number.
+ *
+ * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code
+ * must accept an attempt to read every index.
+ */
+static inline struct rmid_entry *__rmid_entry(u32 idx)
 {
 	struct rmid_entry *entry;
+	u32 closid, rmid;
+
+	entry = &rmid_ptrs[idx];
+	resctrl_arch_rmid_idx_decode(idx, &closid, &rmid);
 
-	entry = &rmid_ptrs[rmid];
-	WARN_ON(entry->rmid != rmid);
+	WARN_ON_ONCE(entry->closid != closid);
+	WARN_ON_ONCE(entry->rmid != rmid);
 
 	return entry;
 }
@@ -190,7 +228,8 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 }
 
 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
-			     u32 rmid, enum resctrl_event_id eventid)
+			     u32 unused, u32 rmid,
+			     enum resctrl_event_id eventid)
 {
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
@@ -230,7 +269,8 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 }
 
 int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
-			   u32 rmid, enum resctrl_event_id eventid, u64 *val)
+			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
+			   u64 *val, void *ignored)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
@@ -238,6 +278,8 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	u64 msr_val, chunks;
 	int ret;
 
+	resctrl_arch_rmid_read_context_check();
+
 	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
 		return -EINVAL;
 
@@ -260,6 +302,17 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	return 0;
 }
 
+static void limbo_release_entry(struct rmid_entry *entry)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	rmid_limbo_count--;
+	list_add_tail(&entry->list, &rmid_free_lru);
+
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+		closid_num_dirty_rmid[entry->closid]--;
+}
+
 /*
  * Check the RMIDs that are marked as busy for this domain. If the
  * reported LLC occupancy is below the threshold clear the busy bit and
@@ -269,11 +322,20 @@ 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;
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	struct rmid_entry *entry;
-	u32 crmid = 1, nrmid;
+	u32 idx, cur_idx = 1;
+	void *arch_mon_ctx;
 	bool rmid_dirty;
 	u64 val = 0;
 
+	arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID);
+	if (IS_ERR(arch_mon_ctx)) {
+		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+				    PTR_ERR(arch_mon_ctx));
+		return;
+	}
+
 	/*
 	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
 	 * are marked as busy for occupancy < threshold. If the occupancy
@@ -281,53 +343,125 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 	 * RMID and move it to the free list when the counter reaches 0.
 	 */
 	for (;;) {
-		nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid);
-		if (nrmid >= r->num_rmid)
+		idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx);
+		if (idx >= idx_limit)
 			break;
 
-		entry = __rmid_entry(nrmid);
-
-		if (resctrl_arch_rmid_read(r, d, entry->rmid,
-					   QOS_L3_OCCUP_EVENT_ID, &val)) {
+		entry = __rmid_entry(idx);
+		if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
+					   QOS_L3_OCCUP_EVENT_ID, &val,
+					   arch_mon_ctx)) {
 			rmid_dirty = true;
 		} else {
 			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
 		}
 
 		if (force_free || !rmid_dirty) {
-			clear_bit(entry->rmid, d->rmid_busy_llc);
-			if (!--entry->busy) {
-				rmid_limbo_count--;
-				list_add_tail(&entry->list, &rmid_free_lru);
-			}
+			clear_bit(idx, d->rmid_busy_llc);
+			if (!--entry->busy)
+				limbo_release_entry(entry);
 		}
-		crmid = nrmid + 1;
+		cur_idx = idx + 1;
 	}
+
+	resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
 }
 
-bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d)
+bool has_busy_rmid(struct rdt_domain *d)
 {
-	return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid;
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+
+	return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit;
+}
+
+static struct rmid_entry *resctrl_find_free_rmid(u32 closid)
+{
+	struct rmid_entry *itr;
+	u32 itr_idx, cmp_idx;
+
+	if (list_empty(&rmid_free_lru))
+		return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC);
+
+	list_for_each_entry(itr, &rmid_free_lru, list) {
+		/*
+		 * Get the index of this free RMID, and the index it would need
+		 * to be if it were used with this CLOSID.
+		 * If the CLOSID is irrelevant on this architecture, the two
+		 * index values are always the same on every entry and thus the
+		 * very first entry will be returned.
+		 */
+		itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid);
+		cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid);
+
+		if (itr_idx == cmp_idx)
+			return itr;
+	}
+
+	return ERR_PTR(-ENOSPC);
+}
+
+/**
+ * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated
+ *                                  RMID are clean, or the CLOSID that has
+ *                                  the most clean RMID.
+ *
+ * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID
+ * may not be able to allocate clean RMID. To avoid this the allocator will
+ * choose the CLOSID with the most clean RMID.
+ *
+ * When the CLOSID and RMID are independent numbers, the first free CLOSID will
+ * be returned.
+ */
+int resctrl_find_cleanest_closid(void)
+{
+	u32 cleanest_closid = ~0;
+	int i = 0;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+		return -EIO;
+
+	for (i = 0; i < closids_supported(); i++) {
+		int num_dirty;
+
+		if (closid_allocated(i))
+			continue;
+
+		num_dirty = closid_num_dirty_rmid[i];
+		if (num_dirty == 0)
+			return i;
+
+		if (cleanest_closid == ~0)
+			cleanest_closid = i;
+
+		if (num_dirty < closid_num_dirty_rmid[cleanest_closid])
+			cleanest_closid = i;
+	}
+
+	if (cleanest_closid == ~0)
+		return -ENOSPC;
+
+	return cleanest_closid;
 }
 
 /*
- * As of now the RMIDs allocation is global.
- * However we keep track of which packages the RMIDs
- * are used to optimize the limbo list management.
+ * For MPAM the RMID value is not unique, and has to be considered with
+ * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which
+ * allows all domains to be managed by a single free list.
+ * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler.
  */
-int alloc_rmid(void)
+int alloc_rmid(u32 closid)
 {
 	struct rmid_entry *entry;
 
 	lockdep_assert_held(&rdtgroup_mutex);
 
-	if (list_empty(&rmid_free_lru))
-		return rmid_limbo_count ? -EBUSY : -ENOSPC;
+	entry = resctrl_find_free_rmid(closid);
+	if (IS_ERR(entry))
+		return PTR_ERR(entry);
 
-	entry = list_first_entry(&rmid_free_lru,
-				 struct rmid_entry, list);
 	list_del(&entry->list);
-
 	return entry->rmid;
 }
 
@@ -335,47 +469,50 @@ 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;
-	int cpu, err;
-	u64 val = 0;
+	u32 idx;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
 
 	entry->busy = 0;
-	cpu = get_cpu();
 	list_for_each_entry(d, &r->domains, list) {
-		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
-			err = resctrl_arch_rmid_read(r, d, entry->rmid,
-						     QOS_L3_OCCUP_EVENT_ID,
-						     &val);
-			if (err || val <= resctrl_rmid_realloc_threshold)
-				continue;
-		}
-
 		/*
 		 * For the first limbo RMID in the domain,
 		 * setup up the limbo worker.
 		 */
-		if (!has_busy_rmid(r, d))
-			cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL);
-		set_bit(entry->rmid, d->rmid_busy_llc);
+		if (!has_busy_rmid(d))
+			cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL,
+						RESCTRL_PICK_ANY_CPU);
+		set_bit(idx, d->rmid_busy_llc);
 		entry->busy++;
 	}
-	put_cpu();
 
-	if (entry->busy)
-		rmid_limbo_count++;
-	else
-		list_add_tail(&entry->list, &rmid_free_lru);
+	rmid_limbo_count++;
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+		closid_num_dirty_rmid[entry->closid]++;
 }
 
-void free_rmid(u32 rmid)
+void free_rmid(u32 closid, u32 rmid)
 {
+	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
 	struct rmid_entry *entry;
 
-	if (!rmid)
-		return;
-
 	lockdep_assert_held(&rdtgroup_mutex);
 
-	entry = __rmid_entry(rmid);
+	/*
+	 * Do not allow the default rmid to be free'd. Comparing by index
+	 * allows architectures that ignore the closid parameter to avoid an
+	 * unnecessary check.
+	 */
+	if (idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
+						RESCTRL_RESERVED_RMID))
+		return;
+
+	entry = __rmid_entry(idx);
 
 	if (is_llc_occupancy_enabled())
 		add_rmid_to_limbo(entry);
@@ -383,33 +520,36 @@ 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,
-				       enum resctrl_event_id evtid)
+static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid,
+				       u32 rmid, enum resctrl_event_id evtid)
 {
+	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
+
 	switch (evtid) {
 	case QOS_L3_MBM_TOTAL_EVENT_ID:
-		return &d->mbm_total[rmid];
+		return &d->mbm_total[idx];
 	case QOS_L3_MBM_LOCAL_EVENT_ID:
-		return &d->mbm_local[rmid];
+		return &d->mbm_local[idx];
 	default:
 		return NULL;
 	}
 }
 
-static int __mon_event_count(u32 rmid, struct rmid_read *rr)
+static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	struct mbm_state *m;
 	u64 tval = 0;
 
 	if (rr->first) {
-		resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid);
-		m = get_mbm_state(rr->d, rmid, rr->evtid);
+		resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
+		m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
 		if (m)
 			memset(m, 0, sizeof(struct mbm_state));
 		return 0;
 	}
 
-	rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval);
+	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;
 
@@ -421,6 +561,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 /*
  * mbm_bw_count() - Update bw count from values previously read by
  *		    __mon_event_count().
+ * @closid:	The closid used to identify the cached mbm_state.
  * @rmid:	The rmid used to identify the cached mbm_state.
  * @rr:		The struct rmid_read populated by __mon_event_count().
  *
@@ -429,9 +570,10 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
  * __mon_event_count() is compared with the chunks value from the previous
  * invocation. This must be called once per second to maintain values in MBps.
  */
-static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
+static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
-	struct mbm_state *m = &rr->d->mbm_local[rmid];
+	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
+	struct mbm_state *m = &rr->d->mbm_local[idx];
 	u64 cur_bw, bytes, cur_bytes;
 
 	cur_bytes = rr->val;
@@ -440,14 +582,11 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 
 	cur_bw = bytes / SZ_1M;
 
-	if (m->delta_comp)
-		m->delta_bw = abs(cur_bw - m->prev_bw);
-	m->delta_comp = false;
 	m->prev_bw = cur_bw;
 }
 
 /*
- * This is called via IPI to read the CQM/MBM counters
+ * This is scheduled by mon_event_read() to read the CQM/MBM counters
  * on a domain.
  */
 void mon_event_count(void *info)
@@ -459,7 +598,7 @@ void mon_event_count(void *info)
 
 	rdtgrp = rr->rgrp;
 
-	ret = __mon_event_count(rdtgrp->mon.rmid, rr);
+	ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr);
 
 	/*
 	 * For Ctrl groups read data from child monitor groups and
@@ -470,7 +609,8 @@ void mon_event_count(void *info)
 
 	if (rdtgrp->type == RDTCTRL_GROUP) {
 		list_for_each_entry(entry, head, mon.crdtgrp_list) {
-			if (__mon_event_count(entry->mon.rmid, rr) == 0)
+			if (__mon_event_count(entry->closid, entry->mon.rmid,
+					      rr) == 0)
 				ret = 0;
 		}
 	}
@@ -520,9 +660,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 {
 	u32 closid, rmid, cur_msr_val, new_msr_val;
 	struct mbm_state *pmbm_data, *cmbm_data;
-	u32 cur_bw, delta_bw, user_bw;
 	struct rdt_resource *r_mba;
 	struct rdt_domain *dom_mba;
+	u32 cur_bw, user_bw, idx;
 	struct list_head *head;
 	struct rdtgroup *entry;
 
@@ -533,7 +673,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 
 	closid = rgrp->closid;
 	rmid = rgrp->mon.rmid;
-	pmbm_data = &dom_mbm->mbm_local[rmid];
+	idx = resctrl_arch_rmid_idx_encode(closid, rmid);
+	pmbm_data = &dom_mbm->mbm_local[idx];
 
 	dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba);
 	if (!dom_mba) {
@@ -543,7 +684,6 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 
 	cur_bw = pmbm_data->prev_bw;
 	user_bw = dom_mba->mbps_val[closid];
-	delta_bw = pmbm_data->delta_bw;
 
 	/* MBA resource doesn't support CDP */
 	cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
@@ -555,52 +695,35 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	list_for_each_entry(entry, head, mon.crdtgrp_list) {
 		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
 		cur_bw += cmbm_data->prev_bw;
-		delta_bw += cmbm_data->delta_bw;
 	}
 
 	/*
 	 * Scale up/down the bandwidth linearly for the ctrl group.  The
 	 * bandwidth step is the bandwidth granularity specified by the
 	 * hardware.
-	 *
-	 * The delta_bw is used when increasing the bandwidth so that we
-	 * dont alternately increase and decrease the control values
-	 * continuously.
-	 *
-	 * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if
-	 * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep
-	 * switching between 90 and 110 continuously if we only check
-	 * cur_bw < user_bw.
+	 * Always increase throttling if current bandwidth is above the
+	 * target set by user.
+	 * But avoid thrashing up and down on every poll by checking
+	 * whether a decrease in throttling is likely to push the group
+	 * back over target. E.g. if currently throttling to 30% of bandwidth
+	 * on a system with 10% granularity steps, check whether moving to
+	 * 40% would go past the limit by multiplying current bandwidth by
+	 * "(30 + 10) / 30".
 	 */
 	if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) {
 		new_msr_val = cur_msr_val - r_mba->membw.bw_gran;
 	} else if (cur_msr_val < MAX_MBA_BW &&
-		   (user_bw > (cur_bw + delta_bw))) {
+		   (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) {
 		new_msr_val = cur_msr_val + r_mba->membw.bw_gran;
 	} else {
 		return;
 	}
 
 	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
-
-	/*
-	 * Delta values are updated dynamically package wise for each
-	 * rdtgrp every time the throttle MSR changes value.
-	 *
-	 * This is because (1)the increase in bandwidth is not perfectly
-	 * linear and only "approximately" linear even when the hardware
-	 * says it is linear.(2)Also since MBA is a core specific
-	 * mechanism, the delta values vary based on number of cores used
-	 * by the rdtgrp.
-	 */
-	pmbm_data->delta_comp = true;
-	list_for_each_entry(entry, head, mon.crdtgrp_list) {
-		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
-		cmbm_data->delta_comp = true;
-	}
 }
 
-static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
+		       u32 closid, u32 rmid)
 {
 	struct rmid_read rr;
 
@@ -615,12 +738,28 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 	if (is_mbm_total_enabled()) {
 		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
 		rr.val = 0;
-		__mon_event_count(rmid, &rr);
+		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);
 	}
 	if (is_mbm_local_enabled()) {
 		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
 		rr.val = 0;
-		__mon_event_count(rmid, &rr);
+		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);
 
 		/*
 		 * Call the MBA software controller only for the
@@ -628,7 +767,9 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 		 * the software controller explicitly.
 		 */
 		if (is_mba_sc(NULL))
-			mbm_bw_count(rmid, &rr);
+			mbm_bw_count(closid, rmid, &rr);
+
+		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
 	}
 }
 
@@ -639,106 +780,193 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 void cqm_handle_limbo(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
-	int cpu = smp_processor_id();
-	struct rdt_resource *r;
 	struct rdt_domain *d;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	d = container_of(work, struct rdt_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
 
-	if (has_busy_rmid(r, d))
-		schedule_delayed_work_on(cpu, &d->cqm_limbo, delay);
+	if (has_busy_rmid(d)) {
+		d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+							   RESCTRL_PICK_ANY_CPU);
+		schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
+					 delay);
+	}
 
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 }
 
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+/**
+ * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this
+ *                             domain.
+ * @dom:           The domain the limbo handler should run for.
+ * @delay_ms:      How far in the future the handler should run.
+ * @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,
+			     int exclude_cpu)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
 	dom->cqm_work_cpu = cpu;
 
-	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
+	if (cpu < nr_cpu_ids)
+		schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
 }
 
 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 list_head *head;
 	struct rdt_resource *r;
 	struct rdt_domain *d;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
-	if (!static_branch_likely(&rdt_mon_enable_key))
+	/*
+	 * If the filesystem has been unmounted this work no longer needs to
+	 * run.
+	 */
+	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);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mbm_update(r, d, prgrp->mon.rmid);
+		mbm_update(r, d, prgrp->closid, prgrp->mon.rmid);
 
 		head = &prgrp->mon.crdtgrp_list;
 		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
-			mbm_update(r, d, crgrp->mon.rmid);
+			mbm_update(r, d, crgrp->closid, crgrp->mon.rmid);
 
 		if (is_mba_sc(NULL))
 			update_mba_bw(prgrp, d);
 	}
 
-	schedule_delayed_work_on(cpu, &d->mbm_over, delay);
+	/*
+	 * 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,
+						   RESCTRL_PICK_ANY_CPU);
+	schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
 
 out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 }
 
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+/**
+ * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this
+ *                                domain.
+ * @dom:           The domain the overflow handler should run for.
+ * @delay_ms:      How far in the future the handler should run.
+ * @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,
+				int exclude_cpu)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	if (!static_branch_likely(&rdt_mon_enable_key))
+	/*
+	 * When a domain comes online there is no guarantee the filesystem is
+	 * mounted. If not, there is no need to catch counter overflow.
+	 */
+	if (!resctrl_mounted || !resctrl_arch_mon_capable())
 		return;
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
 	dom->mbm_work_cpu = cpu;
-	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
+
+	if (cpu < nr_cpu_ids)
+		schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
 }
 
 static int dom_data_init(struct rdt_resource *r)
 {
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+	u32 num_closid = resctrl_arch_get_num_closid(r);
 	struct rmid_entry *entry = NULL;
-	int i, nr_rmids;
+	int err = 0, i;
+	u32 idx;
+
+	mutex_lock(&rdtgroup_mutex);
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		u32 *tmp;
+
+		/*
+		 * If the architecture hasn't provided a sanitised value here,
+		 * this may result in larger arrays than necessary. Resctrl will
+		 * use a smaller system wide value based on the resources in
+		 * use.
+		 */
+		tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL);
+		if (!tmp) {
+			err = -ENOMEM;
+			goto out_unlock;
+		}
 
-	nr_rmids = r->num_rmid;
-	rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL);
-	if (!rmid_ptrs)
-		return -ENOMEM;
+		closid_num_dirty_rmid = tmp;
+	}
+
+	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
+	if (!rmid_ptrs) {
+		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+			kfree(closid_num_dirty_rmid);
+			closid_num_dirty_rmid = NULL;
+		}
+		err = -ENOMEM;
+		goto out_unlock;
+	}
 
-	for (i = 0; i < nr_rmids; i++) {
+	for (i = 0; i < idx_limit; i++) {
 		entry = &rmid_ptrs[i];
 		INIT_LIST_HEAD(&entry->list);
 
-		entry->rmid = i;
+		resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid);
 		list_add_tail(&entry->list, &rmid_free_lru);
 	}
 
 	/*
-	 * RMID 0 is special and is always allocated. It's used for all
-	 * tasks that are not monitored.
+	 * 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().
 	 */
-	entry = __rmid_entry(0);
+	idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
+					   RESCTRL_RESERVED_RMID);
+	entry = __rmid_entry(idx);
 	list_del(&entry->list);
 
-	return 0;
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return err;
+}
+
+static void __exit dom_data_exit(void)
+{
+	mutex_lock(&rdtgroup_mutex);
+
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		kfree(closid_num_dirty_rmid);
+		closid_num_dirty_rmid = NULL;
+	}
+
+	kfree(rmid_ptrs);
+	rmid_ptrs = NULL;
+
+	mutex_unlock(&rdtgroup_mutex);
 }
 
 static struct mon_evt llc_occupancy_event = {
@@ -813,6 +1041,12 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 		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");
@@ -830,6 +1064,11 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	return 0;
 }
 
+void __exit rdt_put_mon_l3_config(void)
+{
+	dom_data_exit();
+}
+
 void __init intel_rdt_mbm_apply_quirk(void)
 {
 	int cf_index;
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 8f559eeae08ed5..884b88e2514130 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -581,7 +581,7 @@ static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
 	if (ret)
 		goto err_cpus;
 
-	if (rdt_mon_capable) {
+	if (resctrl_arch_mon_capable()) {
 		ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
 		if (ret)
 			goto err_cpus_list;
@@ -628,7 +628,7 @@ static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
 	if (ret)
 		goto err_cpus;
 
-	if (rdt_mon_capable) {
+	if (resctrl_arch_mon_capable()) {
 		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
 		if (ret)
 			goto err_cpus_list;
@@ -752,7 +752,7 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	 * anymore when this group would be used for pseudo-locking. This
 	 * is safe to call on platforms not capable of monitoring.
 	 */
-	free_rmid(rdtgrp->mon.rmid);
+	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 
 	ret = 0;
 	goto out;
@@ -776,8 +776,8 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
 {
 	int ret;
 
-	if (rdt_mon_capable) {
-		ret = alloc_rmid();
+	if (resctrl_arch_mon_capable()) {
+		ret = alloc_rmid(rdtgrp->closid);
 		if (ret < 0) {
 			rdt_last_cmd_puts("Out of RMIDs\n");
 			return ret;
@@ -787,7 +787,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
 
 	ret = rdtgroup_locksetup_user_restore(rdtgrp);
 	if (ret) {
-		free_rmid(rdtgrp->mon.rmid);
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 		return ret;
 	}
 
@@ -844,6 +844,9 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	struct rdt_domain *d_i;
 	bool ret = false;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
 		return true;
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 69a1de92384ab2..011e17efb1a66e 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -35,6 +35,10 @@
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
 DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
 DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
+
+/* Mutex to protect rdtgroup access. */
+DEFINE_MUTEX(rdtgroup_mutex);
+
 static struct kernfs_root *rdt_root;
 struct rdtgroup rdtgroup_default;
 LIST_HEAD(rdt_all_groups);
@@ -42,6 +46,9 @@ LIST_HEAD(rdt_all_groups);
 /* list of entries for the schemata file */
 LIST_HEAD(resctrl_schema_all);
 
+/* The filesystem can only be mounted once. */
+bool resctrl_mounted;
+
 /* Kernel fs node for "info" directory under root */
 static struct kernfs_node *kn_info;
 
@@ -102,7 +109,7 @@ void rdt_staged_configs_clear(void)
  *
  * Using a global CLOSID across all resources has some advantages and
  * some drawbacks:
- * + We can simply set "current->closid" to assign a task to a resource
+ * + We can simply set current's closid to assign a task to a resource
  *   group.
  * + Context switch code can avoid extra memory references deciding which
  *   CLOSID to load into the PQR_ASSOC MSR
@@ -111,7 +118,7 @@ void rdt_staged_configs_clear(void)
  * - Our choices on how to configure each resource become progressively more
  *   limited as the number of resources grows.
  */
-static int closid_free_map;
+static unsigned long closid_free_map;
 static int closid_free_map_len;
 
 int closids_supported(void)
@@ -130,26 +137,39 @@ static void closid_init(void)
 
 	closid_free_map = BIT_MASK(rdt_min_closid) - 1;
 
-	/* CLOSID 0 is always reserved for the default group */
-	closid_free_map &= ~1;
+	/* RESCTRL_RESERVED_CLOSID is always reserved for the default group */
+	__clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map);
 	closid_free_map_len = rdt_min_closid;
 }
 
 static int closid_alloc(void)
 {
-	u32 closid = ffs(closid_free_map);
+	int cleanest_closid;
+	u32 closid;
 
-	if (closid == 0)
-		return -ENOSPC;
-	closid--;
-	closid_free_map &= ~(1 << closid);
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		cleanest_closid = resctrl_find_cleanest_closid();
+		if (cleanest_closid < 0)
+			return cleanest_closid;
+		closid = cleanest_closid;
+	} else {
+		closid = ffs(closid_free_map);
+		if (closid == 0)
+			return -ENOSPC;
+		closid--;
+	}
+	__clear_bit(closid, &closid_free_map);
 
 	return closid;
 }
 
 void closid_free(int closid)
 {
-	closid_free_map |= 1 << closid;
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	__set_bit(closid, &closid_free_map);
 }
 
 /**
@@ -159,9 +179,11 @@ void closid_free(int closid)
  * Return: true if @closid is currently associated with a resource group,
  * false if @closid is free
  */
-static bool closid_allocated(unsigned int closid)
+bool closid_allocated(unsigned int closid)
 {
-	return (closid_free_map & (1 << closid)) == 0;
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	return !test_bit(closid, &closid_free_map);
 }
 
 /**
@@ -559,14 +581,26 @@ static void update_task_closid_rmid(struct task_struct *t)
 		_update_task_closid_rmid(t);
 }
 
+static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp)
+{
+	u32 closid, rmid = rdtgrp->mon.rmid;
+
+	if (rdtgrp->type == RDTCTRL_GROUP)
+		closid = rdtgrp->closid;
+	else if (rdtgrp->type == RDTMON_GROUP)
+		closid = rdtgrp->mon.parent->closid;
+	else
+		return false;
+
+	return resctrl_arch_match_closid(tsk, closid) &&
+	       resctrl_arch_match_rmid(tsk, closid, rmid);
+}
+
 static int __rdtgroup_move_task(struct task_struct *tsk,
 				struct rdtgroup *rdtgrp)
 {
 	/* If the task is already in rdtgrp, no need to move the task. */
-	if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid &&
-	     tsk->rmid == rdtgrp->mon.rmid) ||
-	    (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid &&
-	     tsk->closid == rdtgrp->mon.parent->closid))
+	if (task_in_rdtgroup(tsk, rdtgrp))
 		return 0;
 
 	/*
@@ -577,19 +611,19 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	 * For monitor groups, can move the tasks only from
 	 * their parent CTRL group.
 	 */
-
-	if (rdtgrp->type == RDTCTRL_GROUP) {
-		WRITE_ONCE(tsk->closid, rdtgrp->closid);
-		WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid);
-	} else if (rdtgrp->type == RDTMON_GROUP) {
-		if (rdtgrp->mon.parent->closid == tsk->closid) {
-			WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid);
-		} else {
-			rdt_last_cmd_puts("Can't move task to different control group\n");
-			return -EINVAL;
-		}
+	if (rdtgrp->type == RDTMON_GROUP &&
+	    !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) {
+		rdt_last_cmd_puts("Can't move task to different control group\n");
+		return -EINVAL;
 	}
 
+	if (rdtgrp->type == RDTMON_GROUP)
+		resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid,
+					     rdtgrp->mon.rmid);
+	else
+		resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid,
+					     rdtgrp->mon.rmid);
+
 	/*
 	 * Ensure the task's closid and rmid are written before determining if
 	 * the task is current that will decide if it will be interrupted.
@@ -611,14 +645,15 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 
 static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
 {
-	return (rdt_alloc_capable &&
-	       (r->type == RDTCTRL_GROUP) && (t->closid == r->closid));
+	return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) &&
+		resctrl_arch_match_closid(t, r->closid));
 }
 
 static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
 {
-	return (rdt_mon_capable &&
-	       (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid));
+	return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) &&
+		resctrl_arch_match_rmid(t, r->mon.parent->closid,
+					r->mon.rmid));
 }
 
 /**
@@ -853,7 +888,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
 	mutex_lock(&rdtgroup_mutex);
 
 	/* Return empty if resctrl has not been mounted. */
-	if (!static_branch_unlikely(&rdt_enable_key)) {
+	if (!resctrl_mounted) {
 		seq_puts(s, "res:\nmon:\n");
 		goto unlock;
 	}
@@ -869,7 +904,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
 		    rdtg->mode != RDT_MODE_EXCLUSIVE)
 			continue;
 
-		if (rdtg->closid != tsk->closid)
+		if (!resctrl_arch_match_closid(tsk, rdtg->closid))
 			continue;
 
 		seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
@@ -877,7 +912,8 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
 		seq_puts(s, "mon:");
 		list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
 				    mon.crdtgrp_list) {
-			if (tsk->rmid != crg->mon.rmid)
+			if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
+						     crg->mon.rmid))
 				continue;
 			seq_printf(s, "%s", crg->kn->name);
 			break;
@@ -982,6 +1018,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 	bool sep = false;
 	u32 ctrl_val;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 	hw_shareable = r->cache.shareable_bits;
 	list_for_each_entry(dom, &r->domains, list) {
@@ -1042,6 +1079,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 	}
 	seq_putc(seq, '\n');
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 	return 0;
 }
 
@@ -1297,6 +1335,9 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
 	struct rdt_domain *d;
 	u32 ctrl;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
 		if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
@@ -1561,6 +1602,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 	struct rdt_domain *dom;
 	bool sep = false;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
 	list_for_each_entry(dom, &r->domains, list) {
@@ -1577,6 +1619,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 	seq_puts(s, "\n");
 
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 
 	return 0;
 }
@@ -1614,17 +1657,10 @@ static void mon_event_config_write(void *info)
 	wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0);
 }
 
-static int mbm_config_write_domain(struct rdt_resource *r,
-				   struct rdt_domain *d, u32 evtid, u32 val)
+static void mbm_config_write_domain(struct rdt_resource *r,
+				    struct rdt_domain *d, u32 evtid, u32 val)
 {
 	struct mon_config_info mon_info = {0};
-	int ret = 0;
-
-	/* mon_config cannot be more than the supported set of events */
-	if (val > MAX_EVT_CONFIG_BITS) {
-		rdt_last_cmd_puts("Invalid event configuration\n");
-		return -EINVAL;
-	}
 
 	/*
 	 * Read the current config value first. If both are the same then
@@ -1633,7 +1669,7 @@ static int mbm_config_write_domain(struct rdt_resource *r,
 	mon_info.evtid = evtid;
 	mondata_config_read(d, &mon_info);
 	if (mon_info.mon_config == val)
-		goto out;
+		return;
 
 	mon_info.mon_config = val;
 
@@ -1656,17 +1692,17 @@ static int mbm_config_write_domain(struct rdt_resource *r,
 	 * mbm_local and mbm_total counts for all the RMIDs.
 	 */
 	resctrl_arch_reset_rmid_all(r, d);
-
-out:
-	return ret;
 }
 
 static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
 {
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	char *dom_str = NULL, *id_str;
 	unsigned long dom_id, val;
 	struct rdt_domain *d;
-	int ret = 0;
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
 
 next:
 	if (!tok || tok[0] == '\0')
@@ -1686,11 +1722,16 @@ next:
 		return -EINVAL;
 	}
 
+	/* Value from user cannot be more than the supported set of events */
+	if ((val & hw_res->mbm_cfg_mask) != val) {
+		rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
+				    hw_res->mbm_cfg_mask);
+		return -EINVAL;
+	}
+
 	list_for_each_entry(d, &r->domains, list) {
 		if (d->id == dom_id) {
-			ret = mbm_config_write_domain(r, d, evtid, val);
-			if (ret)
-				return -EINVAL;
+			mbm_config_write_domain(r, d, evtid, val);
 			goto next;
 		}
 	}
@@ -1709,6 +1750,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
 	if (nbytes == 0 || buf[nbytes - 1] != '\n')
 		return -EINVAL;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
 	rdt_last_cmd_clear();
@@ -1718,6 +1760,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
 	ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID);
 
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 
 	return ret ?: nbytes;
 }
@@ -1733,6 +1776,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
 	if (nbytes == 0 || buf[nbytes - 1] != '\n')
 		return -EINVAL;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
 	rdt_last_cmd_clear();
@@ -1742,6 +1786,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
 	ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID);
 
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 
 	return ret ?: nbytes;
 }
@@ -2218,6 +2263,9 @@ static int set_cache_qos_cfg(int level, bool enable)
 	struct rdt_domain *d;
 	int cpu;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (level == RDT_RESOURCE_L3)
 		update = l3_qos_cfg_update;
 	else if (level == RDT_RESOURCE_L2)
@@ -2417,6 +2465,7 @@ struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
 
 	rdtgroup_kn_get(rdtgrp, kn);
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
 	/* Was this group deleted while we waited? */
@@ -2434,6 +2483,8 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 		return;
 
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
 	rdtgroup_kn_put(rdtgrp, kn);
 }
 
@@ -2584,7 +2635,7 @@ static int rdt_get_tree(struct fs_context *fc)
 	/*
 	 * resctrl file system can only be mounted once.
 	 */
-	if (static_branch_unlikely(&rdt_enable_key)) {
+	if (resctrl_mounted) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -2605,7 +2656,7 @@ static int rdt_get_tree(struct fs_context *fc)
 
 	closid_init();
 
-	if (rdt_mon_capable)
+	if (resctrl_arch_mon_capable())
 		flags |= RFTYPE_MON;
 
 	ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
@@ -2618,7 +2669,7 @@ static int rdt_get_tree(struct fs_context *fc)
 	if (ret < 0)
 		goto out_schemata_free;
 
-	if (rdt_mon_capable) {
+	if (resctrl_arch_mon_capable()) {
 		ret = mongroup_create_dir(rdtgroup_default.kn,
 					  &rdtgroup_default, "mon_groups",
 					  &kn_mongrp);
@@ -2640,18 +2691,19 @@ static int rdt_get_tree(struct fs_context *fc)
 	if (ret < 0)
 		goto out_psl;
 
-	if (rdt_alloc_capable)
-		static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
-	if (rdt_mon_capable)
-		static_branch_enable_cpuslocked(&rdt_mon_enable_key);
+	if (resctrl_arch_alloc_capable())
+		resctrl_arch_enable_alloc();
+	if (resctrl_arch_mon_capable())
+		resctrl_arch_enable_mon();
 
-	if (rdt_alloc_capable || rdt_mon_capable)
-		static_branch_enable_cpuslocked(&rdt_enable_key);
+	if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable())
+		resctrl_mounted = true;
 
 	if (is_mbm_enabled()) {
 		r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 		list_for_each_entry(dom, &r->domains, list)
-			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
+			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
+						   RESCTRL_PICK_ANY_CPU);
 	}
 
 	goto out;
@@ -2659,10 +2711,10 @@ static int rdt_get_tree(struct fs_context *fc)
 out_psl:
 	rdt_pseudo_lock_release();
 out_mondata:
-	if (rdt_mon_capable)
+	if (resctrl_arch_mon_capable())
 		kernfs_remove(kn_mondata);
 out_mongrp:
-	if (rdt_mon_capable)
+	if (resctrl_arch_mon_capable())
 		kernfs_remove(kn_mongrp);
 out_info:
 	kernfs_remove(kn_info);
@@ -2765,6 +2817,9 @@ static int reset_all_ctrls(struct rdt_resource *r)
 	struct rdt_domain *d;
 	int i;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
 
@@ -2810,8 +2865,8 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
 	for_each_process_thread(p, t) {
 		if (!from || is_closid_match(t, from) ||
 		    is_rmid_match(t, from)) {
-			WRITE_ONCE(t->closid, to->closid);
-			WRITE_ONCE(t->rmid, to->mon.rmid);
+			resctrl_arch_set_closid_rmid(t, to->closid,
+						     to->mon.rmid);
 
 			/*
 			 * Order the closid/rmid stores above before the loads
@@ -2842,7 +2897,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
 
 	head = &rdtgrp->mon.crdtgrp_list;
 	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
-		free_rmid(sentry->mon.rmid);
+		free_rmid(sentry->closid, sentry->mon.rmid);
 		list_del(&sentry->mon.crdtgrp_list);
 
 		if (atomic_read(&sentry->waitcount) != 0)
@@ -2882,7 +2937,7 @@ static void rmdir_all_sub(void)
 		cpumask_or(&rdtgroup_default.cpu_mask,
 			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
 
-		free_rmid(rdtgrp->mon.rmid);
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 
 		kernfs_remove(rdtgrp->kn);
 		list_del(&rdtgrp->rdtgroup_list);
@@ -2917,9 +2972,11 @@ static void rdt_kill_sb(struct super_block *sb)
 	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
 	schemata_list_destroy();
 	rdtgroup_destroy_root();
-	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
-	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
-	static_branch_disable_cpuslocked(&rdt_enable_key);
+	if (resctrl_arch_alloc_capable())
+		resctrl_arch_disable_alloc();
+	if (resctrl_arch_mon_capable())
+		resctrl_arch_disable_mon();
+	resctrl_mounted = false;
 	kernfs_kill_sb(sb);
 	mutex_unlock(&rdtgroup_mutex);
 	cpus_read_unlock();
@@ -3047,6 +3104,9 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
 	struct rdt_domain *dom;
 	int ret;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	list_for_each_entry(dom, &r->domains, list) {
 		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
 		if (ret)
@@ -3293,6 +3353,36 @@ out:
 	return ret;
 }
 
+static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	if (!resctrl_arch_mon_capable())
+		return 0;
+
+	ret = alloc_rmid(rdtgrp->closid);
+	if (ret < 0) {
+		rdt_last_cmd_puts("Out of RMIDs\n");
+		return ret;
+	}
+	rdtgrp->mon.rmid = ret;
+
+	ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
+	if (ret) {
+		rdt_last_cmd_puts("kernfs subdir error\n");
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
+{
+	if (resctrl_arch_mon_capable())
+		free_rmid(rgrp->closid, rgrp->mon.rmid);
+}
+
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 			     const char *name, umode_t mode,
 			     enum rdt_group_type rtype, struct rdtgroup **r)
@@ -3353,7 +3443,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 
 	if (rtype == RDTCTRL_GROUP) {
 		files = RFTYPE_BASE | RFTYPE_CTRL;
-		if (rdt_mon_capable)
+		if (resctrl_arch_mon_capable())
 			files |= RFTYPE_MON;
 	} else {
 		files = RFTYPE_BASE | RFTYPE_MON;
@@ -3365,29 +3455,11 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 		goto out_destroy;
 	}
 
-	if (rdt_mon_capable) {
-		ret = alloc_rmid();
-		if (ret < 0) {
-			rdt_last_cmd_puts("Out of RMIDs\n");
-			goto out_destroy;
-		}
-		rdtgrp->mon.rmid = ret;
-
-		ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
-		if (ret) {
-			rdt_last_cmd_puts("kernfs subdir error\n");
-			goto out_idfree;
-		}
-	}
-	kernfs_activate(kn);
-
 	/*
 	 * The caller unlocks the parent_kn upon success.
 	 */
 	return 0;
 
-out_idfree:
-	free_rmid(rdtgrp->mon.rmid);
 out_destroy:
 	kernfs_put(rdtgrp->kn);
 	kernfs_remove(rdtgrp->kn);
@@ -3401,7 +3473,6 @@ out_unlock:
 static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
 {
 	kernfs_remove(rgrp->kn);
-	free_rmid(rgrp->mon.rmid);
 	rdtgroup_remove(rgrp);
 }
 
@@ -3423,12 +3494,21 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
 	prgrp = rdtgrp->mon.parent;
 	rdtgrp->closid = prgrp->closid;
 
+	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
+	if (ret) {
+		mkdir_rdt_prepare_clean(rdtgrp);
+		goto out_unlock;
+	}
+
+	kernfs_activate(rdtgrp->kn);
+
 	/*
 	 * Add the rdtgrp to the list of rdtgrps the parent
 	 * ctrl_mon group has to track.
 	 */
 	list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list);
 
+out_unlock:
 	rdtgroup_kn_unlock(parent_kn);
 	return ret;
 }
@@ -3459,13 +3539,20 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 	ret = 0;
 
 	rdtgrp->closid = closid;
+
+	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
+	if (ret)
+		goto out_closid_free;
+
+	kernfs_activate(rdtgrp->kn);
+
 	ret = rdtgroup_init_alloc(rdtgrp);
 	if (ret < 0)
-		goto out_id_free;
+		goto out_rmid_free;
 
 	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
 
-	if (rdt_mon_capable) {
+	if (resctrl_arch_mon_capable()) {
 		/*
 		 * Create an empty mon_groups directory to hold the subset
 		 * of tasks and cpus to monitor.
@@ -3481,7 +3568,9 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 
 out_del_list:
 	list_del(&rdtgrp->rdtgroup_list);
-out_id_free:
+out_rmid_free:
+	mkdir_rdt_prepare_rmid_free(rdtgrp);
+out_closid_free:
 	closid_free(closid);
 out_common_fail:
 	mkdir_rdt_prepare_clean(rdtgrp);
@@ -3518,14 +3607,14 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	 * allocation is supported, add a control and monitoring
 	 * subdirectory
 	 */
-	if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn)
+	if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn)
 		return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);
 
 	/*
 	 * If RDT monitoring is supported and the parent directory is a valid
 	 * "mon_groups" directory, add a monitoring subdirectory.
 	 */
-	if (rdt_mon_capable && is_mon_groups(parent_kn, name))
+	if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name))
 		return rdtgroup_mkdir_mon(parent_kn, name, mode);
 
 	return -EPERM;
@@ -3550,7 +3639,7 @@ static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 	update_closid_rmid(tmpmask, NULL);
 
 	rdtgrp->flags = RDT_DELETED;
-	free_rmid(rdtgrp->mon.rmid);
+	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 
 	/*
 	 * Remove the rdtgrp from the parent ctrl_mon group's list
@@ -3596,8 +3685,8 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
 	update_closid_rmid(tmpmask, NULL);
 
+	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 	closid_free(rdtgrp->closid);
-	free_rmid(rdtgrp->mon.rmid);
 
 	rdtgroup_ctrl_remove(rdtgrp);
 
@@ -3829,8 +3918,8 @@ static void __init rdtgroup_setup_default(void)
 {
 	mutex_lock(&rdtgroup_mutex);
 
-	rdtgroup_default.closid = 0;
-	rdtgroup_default.mon.rmid = 0;
+	rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID;
+	rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID;
 	rdtgroup_default.type = RDTCTRL_GROUP;
 	INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list);
 
@@ -3848,24 +3937,24 @@ static void domain_destroy_mon_state(struct rdt_domain *d)
 
 void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
 {
-	lockdep_assert_held(&rdtgroup_mutex);
+	mutex_lock(&rdtgroup_mutex);
 
 	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
 		mba_sc_domain_destroy(r, d);
 
 	if (!r->mon_capable)
-		return;
+		goto out_unlock;
 
 	/*
 	 * If resctrl is mounted, remove all the
 	 * per domain monitor data directories.
 	 */
-	if (static_branch_unlikely(&rdt_mon_enable_key))
+	if (resctrl_mounted && resctrl_arch_mon_capable())
 		rmdir_mondata_subdir_allrdtgrp(r, d->id);
 
 	if (is_mbm_enabled())
 		cancel_delayed_work(&d->mbm_over);
-	if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) {
+	if (is_llc_occupancy_enabled() && has_busy_rmid(d)) {
 		/*
 		 * When a package is going down, forcefully
 		 * decrement rmid->ebusy. There is no way to know
@@ -3879,20 +3968,24 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
 	}
 
 	domain_destroy_mon_state(d);
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
 }
 
 static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 {
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	size_t tsize;
 
 	if (is_llc_occupancy_enabled()) {
-		d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL);
+		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
 		if (!d->rmid_busy_llc)
 			return -ENOMEM;
 	}
 	if (is_mbm_total_enabled()) {
 		tsize = sizeof(*d->mbm_total);
-		d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
 		if (!d->mbm_total) {
 			bitmap_free(d->rmid_busy_llc);
 			return -ENOMEM;
@@ -3900,7 +3993,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 	}
 	if (is_mbm_local_enabled()) {
 		tsize = sizeof(*d->mbm_local);
-		d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
 		if (!d->mbm_local) {
 			bitmap_free(d->rmid_busy_llc);
 			kfree(d->mbm_total);
@@ -3913,34 +4006,97 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 
 int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
 {
-	int err;
+	int err = 0;
 
-	lockdep_assert_held(&rdtgroup_mutex);
+	mutex_lock(&rdtgroup_mutex);
 
-	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
+	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) {
 		/* RDT_RESOURCE_MBA is never mon_capable */
-		return mba_sc_domain_allocate(r, d);
+		err = mba_sc_domain_allocate(r, d);
+		goto out_unlock;
+	}
 
 	if (!r->mon_capable)
-		return 0;
+		goto out_unlock;
 
 	err = domain_setup_mon_state(r, d);
 	if (err)
-		return err;
+		goto out_unlock;
 
 	if (is_mbm_enabled()) {
 		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
-		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
+		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
+					   RESCTRL_PICK_ANY_CPU);
 	}
 
 	if (is_llc_occupancy_enabled())
 		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
 
-	/* If resctrl is mounted, add per domain monitor data directories. */
-	if (static_branch_unlikely(&rdt_mon_enable_key))
+	/*
+	 * If the filesystem is not mounted then only the default resource group
+	 * exists. Creation of its directories is deferred until mount time
+	 * by rdt_get_tree() calling mkdir_mondata_all().
+	 * If resctrl is mounted, add per domain monitor data directories.
+	 */
+	if (resctrl_mounted && resctrl_arch_mon_capable())
 		mkdir_mondata_subdir_allrdtgrp(r, d);
 
-	return 0;
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return err;
+}
+
+void resctrl_online_cpu(unsigned int cpu)
+{
+	mutex_lock(&rdtgroup_mutex);
+	/* The CPU is set in default rdtgroup after online. */
+	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
+{
+	struct rdtgroup *cr;
+
+	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask))
+			break;
+	}
+}
+
+void resctrl_offline_cpu(unsigned int cpu)
+{
+	struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdtgroup *rdtgrp;
+	struct rdt_domain *d;
+
+	mutex_lock(&rdtgroup_mutex);
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
+			clear_childcpus(rdtgrp, cpu);
+			break;
+		}
+	}
+
+	if (!l3->mon_capable)
+		goto out_unlock;
+
+	d = get_domain_from_cpu(cpu, l3);
+	if (d) {
+		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
+			cancel_delayed_work(&d->mbm_over);
+			mbm_setup_overflow_handler(d, 0, cpu);
+		}
+		if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
+		    has_busy_rmid(d)) {
+			cancel_delayed_work(&d->cqm_limbo);
+			cqm_setup_limbo_handler(d, 0, cpu);
+		}
+	}
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
 }
 
 /*
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 66942d7fba7fc6..a365f67131ecef 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -6,6 +6,12 @@
 #include <linux/list.h>
 #include <linux/pid.h>
 
+/* CLOSID, RMID value used by the default control group */
+#define RESCTRL_RESERVED_CLOSID		0
+#define RESCTRL_RESERVED_RMID		0
+
+#define RESCTRL_PICK_ANY_CPU		-1
+
 #ifdef CONFIG_PROC_CPU_RESCTRL
 
 int proc_resctrl_show(struct seq_file *m,
@@ -153,7 +159,7 @@ struct resctrl_schema;
  * @cache_level:	Which cache level defines scope of this resource
  * @cache:		Cache allocation related data
  * @membw:		If the component has bandwidth controls, their properties.
- * @domains:		All domains for this resource
+ * @domains:		RCU list of all 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.
@@ -219,36 +225,70 @@ 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);
+void resctrl_online_cpu(unsigned int cpu);
+void resctrl_offline_cpu(unsigned int cpu);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
  *			      for this resource and domain.
  * @r:			resource that the counter should be read from.
  * @d:			domain that the counter should be read from.
+ * @closid:		closid that matches the rmid. Depending on the architecture, the
+ *			counter may match traffic of both @closid and @rmid, or @rmid
+ *			only.
  * @rmid:		rmid of the counter to read.
  * @eventid:		eventid to read, e.g. L3 occupancy.
  * @val:		result of the counter read in bytes.
+ * @arch_mon_ctx:	An architecture specific value from
+ *			resctrl_arch_mon_ctx_alloc(), for MPAM this identifies
+ *			the hardware monitor allocated for this read request.
  *
- * Call from process context on a CPU that belongs to domain @d.
+ * Some architectures need to sleep when first programming some of the counters.
+ * (specifically: arm64's MPAM cache occupancy counters can return 'not ready'
+ *  for a short period of time). Call from a non-migrateable process context on
+ * a CPU that belongs to domain @d. e.g. use smp_call_on_cpu() or
+ * schedule_work_on(). This function can be called with interrupts masked,
+ * e.g. using smp_call_function_any(), but may consistently return an error.
  *
  * Return:
  * 0 on success, or -EIO, -EINVAL etc on error.
  */
 int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
-			   u32 rmid, enum resctrl_event_id eventid, u64 *val);
+			   u32 closid, u32 rmid, enum resctrl_event_id eventid,
+			   u64 *val, void *arch_mon_ctx);
+
+/**
+ * resctrl_arch_rmid_read_context_check()  - warn about invalid contexts
+ *
+ * When built with CONFIG_DEBUG_ATOMIC_SLEEP generate a warning when
+ * resctrl_arch_rmid_read() is called with preemption disabled.
+ *
+ * The contract with resctrl_arch_rmid_read() is that if interrupts
+ * are unmasked, it can sleep. This allows NOHZ_FULL systems to use an
+ * IPI, (and fail if the call needed to sleep), while most of the time
+ * the work is scheduled, allowing the call to sleep.
+ */
+static inline void resctrl_arch_rmid_read_context_check(void)
+{
+	if (!irqs_disabled())
+		might_sleep();
+}
 
 /**
  * resctrl_arch_reset_rmid() - Reset any private state associated with rmid
  *			       and eventid.
  * @r:		The domain's resource.
  * @d:		The rmid's domain.
+ * @closid:	closid that matches the rmid. Depending on the architecture, the
+ *		counter may match traffic of both @closid and @rmid, or @rmid only.
  * @rmid:	The rmid whose counter values should be reset.
  * @eventid:	The eventid whose counter values should be reset.
  *
  * This can be called from any CPU.
  */
 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
-			     u32 rmid, enum resctrl_event_id eventid);
+			     u32 closid, u32 rmid,
+			     enum resctrl_event_id eventid);
 
 /**
  * resctrl_arch_reset_rmid_all() - Reset all private state associated with
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 44fddfa93e18c8..70dc884054f659 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -164,9 +164,16 @@ static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 #endif /* !CONFIG_NO_HZ_COMMON */
 
+/*
+ * Mask of CPUs that are nohz_full.
+ *
+ * Users should be guarded by CONFIG_NO_HZ_FULL or a tick_nohz_full_cpu()
+ * check.
+ */
+extern cpumask_var_t tick_nohz_full_mask;
+
 #ifdef CONFIG_NO_HZ_FULL
 extern bool tick_nohz_full_running;
-extern cpumask_var_t tick_nohz_full_mask;
 
 static inline bool tick_nohz_full_enabled(void)
 {